{"current_steps": 1, "total_steps": 6710, "loss": 2.4544, "lr": 2.4999998629955372e-06, "epoch": 0.0007451564828614009, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "6:13:26", "throughput": 1226.42, "total_tokens": 4096} {"current_steps": 2, "total_steps": 6710, "loss": 2.1705, "lr": 2.4999994519821783e-06, "epoch": 0.0014903129657228018, "percentage": 0.03, "elapsed_time": "0:00:04", "remaining_time": "4:22:59", "throughput": 1741.2, "total_tokens": 8192} {"current_steps": 3, "total_steps": 6710, "loss": 2.1284, "lr": 2.499998766960014e-06, "epoch": 0.0022354694485842027, "percentage": 0.04, "elapsed_time": "0:00:05", "remaining_time": "3:26:03", "throughput": 2222.05, "total_tokens": 12288} {"current_steps": 4, "total_steps": 6710, "loss": 2.0113, "lr": 2.4999978079291947e-06, "epoch": 0.0029806259314456036, "percentage": 0.06, "elapsed_time": "0:00:06", "remaining_time": "2:57:37", "throughput": 2577.25, "total_tokens": 16384} {"current_steps": 5, "total_steps": 6710, "loss": 1.8607, "lr": 2.4999965748899295e-06, "epoch": 0.0037257824143070045, "percentage": 0.07, "elapsed_time": "0:00:07", "remaining_time": "2:40:09", "throughput": 2857.86, "total_tokens": 20480} {"current_steps": 6, "total_steps": 6710, "loss": 1.7343, "lr": 2.4999950678424892e-06, "epoch": 0.004470938897168405, "percentage": 0.09, "elapsed_time": "0:00:07", "remaining_time": "2:28:44", "throughput": 3076.97, "total_tokens": 24576} {"current_steps": 7, "total_steps": 6710, "loss": 2.1515, "lr": 2.4999932867872047e-06, "epoch": 0.005216095380029807, "percentage": 0.1, "elapsed_time": "0:00:08", "remaining_time": "2:20:27", "throughput": 3257.98, "total_tokens": 28672} {"current_steps": 8, "total_steps": 6710, "loss": 2.0501, "lr": 2.499991231724466e-06, "epoch": 0.005961251862891207, "percentage": 0.12, "elapsed_time": "0:00:09", "remaining_time": "2:14:20", "throughput": 3405.74, "total_tokens": 32768} {"current_steps": 9, "total_steps": 6710, "loss": 1.7586, "lr": 2.499988902654723e-06, "epoch": 0.0067064083457526085, "percentage": 0.13, "elapsed_time": "0:00:10", "remaining_time": "2:09:37", "throughput": 3528.89, "total_tokens": 36864} {"current_steps": 10, "total_steps": 6710, "loss": 2.0887, "lr": 2.499986299578487e-06, "epoch": 0.007451564828614009, "percentage": 0.15, "elapsed_time": "0:00:11", "remaining_time": "2:05:32", "throughput": 3643.45, "total_tokens": 40960} {"current_steps": 11, "total_steps": 6710, "loss": 1.7723, "lr": 2.4999834224963287e-06, "epoch": 0.00819672131147541, "percentage": 0.16, "elapsed_time": "0:00:12", "remaining_time": "2:02:08", "throughput": 3744.34, "total_tokens": 45056} {"current_steps": 12, "total_steps": 6710, "loss": 1.96, "lr": 2.4999802714088784e-06, "epoch": 0.00894187779433681, "percentage": 0.18, "elapsed_time": "0:00:12", "remaining_time": "1:59:27", "throughput": 3827.69, "total_tokens": 49152} {"current_steps": 13, "total_steps": 6710, "loss": 1.9163, "lr": 2.4999768463168266e-06, "epoch": 0.009687034277198211, "percentage": 0.19, "elapsed_time": "0:00:13", "remaining_time": "1:57:30", "throughput": 3890.37, "total_tokens": 53248} {"current_steps": 14, "total_steps": 6710, "loss": 1.8526, "lr": 2.4999731472209247e-06, "epoch": 0.010432190760059613, "percentage": 0.21, "elapsed_time": "0:00:14", "remaining_time": "1:55:48", "throughput": 3946.98, "total_tokens": 57344} {"current_steps": 15, "total_steps": 6710, "loss": 1.9305, "lr": 2.4999691741219837e-06, "epoch": 0.011177347242921014, "percentage": 0.22, "elapsed_time": "0:00:15", "remaining_time": "1:53:58", "throughput": 4009.79, "total_tokens": 61440} {"current_steps": 16, "total_steps": 6710, "loss": 1.9454, "lr": 2.4999649270208736e-06, "epoch": 0.011922503725782414, "percentage": 0.24, "elapsed_time": "0:00:16", "remaining_time": "1:52:27", "throughput": 4063.58, "total_tokens": 65536} {"current_steps": 17, "total_steps": 6710, "loss": 2.0263, "lr": 2.4999604059185264e-06, "epoch": 0.012667660208643815, "percentage": 0.25, "elapsed_time": "0:00:16", "remaining_time": "1:51:08", "throughput": 4110.92, "total_tokens": 69632} {"current_steps": 18, "total_steps": 6710, "loss": 2.1609, "lr": 2.4999556108159328e-06, "epoch": 0.013412816691505217, "percentage": 0.27, "elapsed_time": "0:00:17", "remaining_time": "1:49:58", "throughput": 4154.25, "total_tokens": 73728} {"current_steps": 19, "total_steps": 6710, "loss": 2.074, "lr": 2.4999505417141435e-06, "epoch": 0.014157973174366617, "percentage": 0.28, "elapsed_time": "0:00:18", "remaining_time": "1:49:00", "throughput": 4190.22, "total_tokens": 77824} {"current_steps": 20, "total_steps": 6710, "loss": 1.9962, "lr": 2.49994519861427e-06, "epoch": 0.014903129657228018, "percentage": 0.3, "elapsed_time": "0:00:19", "remaining_time": "1:48:15", "throughput": 4218.63, "total_tokens": 81920} {"current_steps": 21, "total_steps": 6710, "loss": 1.4408, "lr": 2.4999395815174837e-06, "epoch": 0.01564828614008942, "percentage": 0.31, "elapsed_time": "0:00:20", "remaining_time": "1:47:28", "throughput": 4248.56, "total_tokens": 86016} {"current_steps": 22, "total_steps": 6710, "loss": 1.4921, "lr": 2.4999336904250153e-06, "epoch": 0.01639344262295082, "percentage": 0.33, "elapsed_time": "0:00:21", "remaining_time": "1:47:47", "throughput": 4235.56, "total_tokens": 90112} {"current_steps": 23, "total_steps": 6710, "loss": 2.2125, "lr": 2.4999275253381574e-06, "epoch": 0.01713859910581222, "percentage": 0.34, "elapsed_time": "0:00:22", "remaining_time": "1:46:59", "throughput": 4266.57, "total_tokens": 94208} {"current_steps": 24, "total_steps": 6710, "loss": 1.5723, "lr": 2.49992108625826e-06, "epoch": 0.01788375558867362, "percentage": 0.36, "elapsed_time": "0:00:22", "remaining_time": "1:46:18", "throughput": 4293.2, "total_tokens": 98304} {"current_steps": 25, "total_steps": 6710, "loss": 1.6901, "lr": 2.4999143731867355e-06, "epoch": 0.018628912071535022, "percentage": 0.37, "elapsed_time": "0:00:23", "remaining_time": "1:45:35", "throughput": 4322.1, "total_tokens": 102400} {"current_steps": 26, "total_steps": 6710, "loss": 1.7441, "lr": 2.4999073861250554e-06, "epoch": 0.019374068554396422, "percentage": 0.39, "elapsed_time": "0:00:24", "remaining_time": "1:45:04", "throughput": 4342.76, "total_tokens": 106496} {"current_steps": 27, "total_steps": 6710, "loss": 2.096, "lr": 2.499900125074751e-06, "epoch": 0.020119225037257823, "percentage": 0.4, "elapsed_time": "0:00:25", "remaining_time": "1:44:30", "throughput": 4365.21, "total_tokens": 110592} {"current_steps": 28, "total_steps": 6710, "loss": 1.8458, "lr": 2.4998925900374143e-06, "epoch": 0.020864381520119227, "percentage": 0.42, "elapsed_time": "0:00:26", "remaining_time": "1:44:06", "throughput": 4381.24, "total_tokens": 114688} {"current_steps": 29, "total_steps": 6710, "loss": 1.7789, "lr": 2.4998847810146966e-06, "epoch": 0.021609538002980627, "percentage": 0.43, "elapsed_time": "0:00:27", "remaining_time": "1:43:40", "throughput": 4399.04, "total_tokens": 118784} {"current_steps": 30, "total_steps": 6710, "loss": 1.6771, "lr": 2.4998766980083098e-06, "epoch": 0.022354694485842028, "percentage": 0.45, "elapsed_time": "0:00:27", "remaining_time": "1:43:14", "throughput": 4417.05, "total_tokens": 122880} {"current_steps": 31, "total_steps": 6710, "loss": 1.9485, "lr": 2.4998683410200258e-06, "epoch": 0.023099850968703428, "percentage": 0.46, "elapsed_time": "0:00:28", "remaining_time": "1:42:45", "throughput": 4436.94, "total_tokens": 126976} {"current_steps": 32, "total_steps": 6710, "loss": 1.661, "lr": 2.499859710051677e-06, "epoch": 0.02384500745156483, "percentage": 0.48, "elapsed_time": "0:00:29", "remaining_time": "1:42:20", "throughput": 4454.85, "total_tokens": 131072} {"current_steps": 33, "total_steps": 6710, "loss": 1.5875, "lr": 2.4998508051051546e-06, "epoch": 0.02459016393442623, "percentage": 0.49, "elapsed_time": "0:00:30", "remaining_time": "1:42:01", "throughput": 4467.61, "total_tokens": 135168} {"current_steps": 34, "total_steps": 6710, "loss": 1.5721, "lr": 2.4998416261824113e-06, "epoch": 0.02533532041728763, "percentage": 0.51, "elapsed_time": "0:00:31", "remaining_time": "1:41:37", "throughput": 4484.38, "total_tokens": 139264} {"current_steps": 35, "total_steps": 6710, "loss": 2.3301, "lr": 2.4998321732854585e-06, "epoch": 0.02608047690014903, "percentage": 0.52, "elapsed_time": "0:00:31", "remaining_time": "1:41:18", "throughput": 4497.77, "total_tokens": 143360} {"current_steps": 36, "total_steps": 6710, "loss": 2.0368, "lr": 2.4998224464163693e-06, "epoch": 0.026825633383010434, "percentage": 0.54, "elapsed_time": "0:00:32", "remaining_time": "1:40:56", "throughput": 4513.34, "total_tokens": 147456} {"current_steps": 37, "total_steps": 6710, "loss": 1.5724, "lr": 2.499812445577275e-06, "epoch": 0.027570789865871834, "percentage": 0.55, "elapsed_time": "0:00:33", "remaining_time": "1:40:37", "throughput": 4527.33, "total_tokens": 151552} {"current_steps": 38, "total_steps": 6710, "loss": 1.2955, "lr": 2.499802170770368e-06, "epoch": 0.028315946348733235, "percentage": 0.57, "elapsed_time": "0:00:34", "remaining_time": "1:40:19", "throughput": 4539.74, "total_tokens": 155648} {"current_steps": 39, "total_steps": 6710, "loss": 1.9262, "lr": 2.4997916219979007e-06, "epoch": 0.029061102831594635, "percentage": 0.58, "elapsed_time": "0:00:35", "remaining_time": "1:40:01", "throughput": 4553.1, "total_tokens": 159744} {"current_steps": 40, "total_steps": 6710, "loss": 1.5556, "lr": 2.499780799262186e-06, "epoch": 0.029806259314456036, "percentage": 0.6, "elapsed_time": "0:00:35", "remaining_time": "1:39:44", "throughput": 4564.85, "total_tokens": 163840} {"current_steps": 41, "total_steps": 6710, "loss": 1.6539, "lr": 2.499769702565596e-06, "epoch": 0.030551415797317436, "percentage": 0.61, "elapsed_time": "0:00:36", "remaining_time": "1:39:27", "throughput": 4577.29, "total_tokens": 167936} {"current_steps": 42, "total_steps": 6710, "loss": 1.3057, "lr": 2.4997583319105624e-06, "epoch": 0.03129657228017884, "percentage": 0.63, "elapsed_time": "0:00:37", "remaining_time": "1:39:13", "throughput": 4587.26, "total_tokens": 172032} {"current_steps": 43, "total_steps": 6710, "loss": 1.7122, "lr": 2.4997466872995786e-06, "epoch": 0.03204172876304024, "percentage": 0.64, "elapsed_time": "0:00:38", "remaining_time": "1:38:57", "throughput": 4599.16, "total_tokens": 176128} {"current_steps": 44, "total_steps": 6710, "loss": 1.7401, "lr": 2.499734768735197e-06, "epoch": 0.03278688524590164, "percentage": 0.66, "elapsed_time": "0:00:39", "remaining_time": "1:38:42", "throughput": 4610.41, "total_tokens": 180224} {"current_steps": 45, "total_steps": 6710, "loss": 1.7047, "lr": 2.49972257622003e-06, "epoch": 0.03353204172876304, "percentage": 0.67, "elapsed_time": "0:00:39", "remaining_time": "1:38:26", "throughput": 4622.04, "total_tokens": 184320} {"current_steps": 46, "total_steps": 6710, "loss": 1.567, "lr": 2.4997101097567508e-06, "epoch": 0.03427719821162444, "percentage": 0.69, "elapsed_time": "0:00:40", "remaining_time": "1:38:15", "throughput": 4629.62, "total_tokens": 188416} {"current_steps": 47, "total_steps": 6710, "loss": 1.6003, "lr": 2.499697369348092e-06, "epoch": 0.03502235469448584, "percentage": 0.7, "elapsed_time": "0:00:41", "remaining_time": "1:38:03", "throughput": 4638.73, "total_tokens": 192512} {"current_steps": 48, "total_steps": 6710, "loss": 1.4636, "lr": 2.4996843549968457e-06, "epoch": 0.03576751117734724, "percentage": 0.72, "elapsed_time": "0:00:42", "remaining_time": "1:37:50", "throughput": 4648.54, "total_tokens": 196608} {"current_steps": 49, "total_steps": 6710, "loss": 2.0578, "lr": 2.4996710667058654e-06, "epoch": 0.03651266766020864, "percentage": 0.73, "elapsed_time": "0:00:43", "remaining_time": "1:38:09", "throughput": 4632.71, "total_tokens": 200704} {"current_steps": 50, "total_steps": 6710, "loss": 1.3995, "lr": 2.4996575044780637e-06, "epoch": 0.037257824143070044, "percentage": 0.75, "elapsed_time": "0:00:44", "remaining_time": "1:37:58", "throughput": 4640.78, "total_tokens": 204800} {"current_steps": 51, "total_steps": 6710, "loss": 1.7972, "lr": 2.499643668316414e-06, "epoch": 0.038002980625931444, "percentage": 0.76, "elapsed_time": "0:00:45", "remaining_time": "1:38:17", "throughput": 4625.14, "total_tokens": 208896} {"current_steps": 52, "total_steps": 6710, "loss": 1.3429, "lr": 2.4996295582239488e-06, "epoch": 0.038748137108792845, "percentage": 0.77, "elapsed_time": "0:00:45", "remaining_time": "1:38:03", "throughput": 4634.91, "total_tokens": 212992} {"current_steps": 53, "total_steps": 6710, "loss": 1.9008, "lr": 2.499615174203761e-06, "epoch": 0.039493293591654245, "percentage": 0.79, "elapsed_time": "0:00:46", "remaining_time": "1:37:53", "throughput": 4642.25, "total_tokens": 217088} {"current_steps": 54, "total_steps": 6710, "loss": 1.8574, "lr": 2.4996005162590044e-06, "epoch": 0.040238450074515646, "percentage": 0.8, "elapsed_time": "0:00:47", "remaining_time": "1:37:43", "throughput": 4649.79, "total_tokens": 221184} {"current_steps": 55, "total_steps": 6710, "loss": 1.6347, "lr": 2.4995855843928915e-06, "epoch": 0.040983606557377046, "percentage": 0.82, "elapsed_time": "0:00:48", "remaining_time": "1:37:31", "throughput": 4658.55, "total_tokens": 225280} {"current_steps": 56, "total_steps": 6710, "loss": 1.8412, "lr": 2.4995703786086957e-06, "epoch": 0.041728763040238454, "percentage": 0.83, "elapsed_time": "0:00:49", "remaining_time": "1:37:21", "throughput": 4666.09, "total_tokens": 229376} {"current_steps": 57, "total_steps": 6710, "loss": 1.9378, "lr": 2.49955489890975e-06, "epoch": 0.042473919523099854, "percentage": 0.85, "elapsed_time": "0:00:49", "remaining_time": "1:37:11", "throughput": 4673.0, "total_tokens": 233472} {"current_steps": 58, "total_steps": 6710, "loss": 1.6359, "lr": 2.499539145299448e-06, "epoch": 0.043219076005961254, "percentage": 0.86, "elapsed_time": "0:00:50", "remaining_time": "1:37:00", "throughput": 4680.92, "total_tokens": 237568} {"current_steps": 59, "total_steps": 6710, "loss": 1.2167, "lr": 2.499523117781243e-06, "epoch": 0.043964232488822655, "percentage": 0.88, "elapsed_time": "0:00:51", "remaining_time": "1:36:51", "throughput": 4687.8, "total_tokens": 241664} {"current_steps": 60, "total_steps": 6710, "loss": 1.6408, "lr": 2.4995068163586483e-06, "epoch": 0.044709388971684055, "percentage": 0.89, "elapsed_time": "0:00:52", "remaining_time": "1:36:41", "throughput": 4695.17, "total_tokens": 245760} {"current_steps": 61, "total_steps": 6710, "loss": 1.7217, "lr": 2.4994902410352366e-06, "epoch": 0.045454545454545456, "percentage": 0.91, "elapsed_time": "0:00:53", "remaining_time": "1:36:31", "throughput": 4702.62, "total_tokens": 249856} {"current_steps": 62, "total_steps": 6710, "loss": 1.8552, "lr": 2.4994733918146425e-06, "epoch": 0.046199701937406856, "percentage": 0.92, "elapsed_time": "0:00:53", "remaining_time": "1:36:21", "throughput": 4709.88, "total_tokens": 253952} {"current_steps": 63, "total_steps": 6710, "loss": 1.3624, "lr": 2.4994562687005586e-06, "epoch": 0.04694485842026826, "percentage": 0.94, "elapsed_time": "0:00:54", "remaining_time": "1:36:13", "throughput": 4715.4, "total_tokens": 258048} {"current_steps": 64, "total_steps": 6710, "loss": 2.0331, "lr": 2.4994388716967386e-06, "epoch": 0.04769001490312966, "percentage": 0.95, "elapsed_time": "0:00:55", "remaining_time": "1:36:05", "throughput": 4721.35, "total_tokens": 262144} {"current_steps": 65, "total_steps": 6710, "loss": 1.2969, "lr": 2.4994212008069962e-06, "epoch": 0.04843517138599106, "percentage": 0.97, "elapsed_time": "0:00:56", "remaining_time": "1:35:57", "throughput": 4727.78, "total_tokens": 266240} {"current_steps": 66, "total_steps": 6710, "loss": 1.5188, "lr": 2.499403256035205e-06, "epoch": 0.04918032786885246, "percentage": 0.98, "elapsed_time": "0:00:57", "remaining_time": "1:35:49", "throughput": 4733.26, "total_tokens": 270336} {"current_steps": 67, "total_steps": 6710, "loss": 1.8453, "lr": 2.4993850373852983e-06, "epoch": 0.04992548435171386, "percentage": 1.0, "elapsed_time": "0:00:57", "remaining_time": "1:35:41", "throughput": 4739.06, "total_tokens": 274432} {"current_steps": 68, "total_steps": 6710, "loss": 1.6573, "lr": 2.4993665448612702e-06, "epoch": 0.05067064083457526, "percentage": 1.01, "elapsed_time": "0:00:58", "remaining_time": "1:35:35", "throughput": 4743.58, "total_tokens": 278528} {"current_steps": 69, "total_steps": 6710, "loss": 1.7681, "lr": 2.4993477784671745e-06, "epoch": 0.05141579731743666, "percentage": 1.03, "elapsed_time": "0:00:59", "remaining_time": "1:35:29", "throughput": 4748.03, "total_tokens": 282624} {"current_steps": 70, "total_steps": 6710, "loss": 1.4704, "lr": 2.499328738207124e-06, "epoch": 0.05216095380029806, "percentage": 1.04, "elapsed_time": "0:01:00", "remaining_time": "1:35:21", "throughput": 4753.23, "total_tokens": 286720} {"current_steps": 71, "total_steps": 6710, "loss": 1.9907, "lr": 2.4993094240852935e-06, "epoch": 0.05290611028315946, "percentage": 1.06, "elapsed_time": "0:01:01", "remaining_time": "1:35:14", "throughput": 4758.83, "total_tokens": 290816} {"current_steps": 72, "total_steps": 6710, "loss": 1.7665, "lr": 2.4992898361059163e-06, "epoch": 0.05365126676602087, "percentage": 1.07, "elapsed_time": "0:01:01", "remaining_time": "1:35:07", "throughput": 4763.82, "total_tokens": 294912} {"current_steps": 73, "total_steps": 6710, "loss": 1.6887, "lr": 2.4992699742732864e-06, "epoch": 0.05439642324888227, "percentage": 1.09, "elapsed_time": "0:01:02", "remaining_time": "1:35:02", "throughput": 4767.6, "total_tokens": 299008} {"current_steps": 74, "total_steps": 6710, "loss": 1.5901, "lr": 2.499249838591757e-06, "epoch": 0.05514157973174367, "percentage": 1.1, "elapsed_time": "0:01:03", "remaining_time": "1:34:55", "throughput": 4772.7, "total_tokens": 303104} {"current_steps": 75, "total_steps": 6710, "loss": 1.6904, "lr": 2.4992294290657434e-06, "epoch": 0.05588673621460507, "percentage": 1.12, "elapsed_time": "0:01:04", "remaining_time": "1:34:48", "throughput": 4777.88, "total_tokens": 307200} {"current_steps": 76, "total_steps": 6710, "loss": 1.6694, "lr": 2.499208745699718e-06, "epoch": 0.05663189269746647, "percentage": 1.13, "elapsed_time": "0:01:05", "remaining_time": "1:34:42", "throughput": 4781.84, "total_tokens": 311296} {"current_steps": 77, "total_steps": 6710, "loss": 1.7089, "lr": 2.4991877884982154e-06, "epoch": 0.05737704918032787, "percentage": 1.15, "elapsed_time": "0:01:05", "remaining_time": "1:34:37", "throughput": 4785.48, "total_tokens": 315392} {"current_steps": 78, "total_steps": 6710, "loss": 1.5323, "lr": 2.49916655746583e-06, "epoch": 0.05812220566318927, "percentage": 1.16, "elapsed_time": "0:01:06", "remaining_time": "1:34:31", "throughput": 4789.64, "total_tokens": 319488} {"current_steps": 79, "total_steps": 6710, "loss": 1.6363, "lr": 2.499145052607215e-06, "epoch": 0.05886736214605067, "percentage": 1.18, "elapsed_time": "0:01:07", "remaining_time": "1:34:24", "throughput": 4794.54, "total_tokens": 323584} {"current_steps": 80, "total_steps": 6710, "loss": 1.8472, "lr": 2.4991232739270847e-06, "epoch": 0.05961251862891207, "percentage": 1.19, "elapsed_time": "0:01:08", "remaining_time": "1:34:19", "throughput": 4798.51, "total_tokens": 327680} {"current_steps": 81, "total_steps": 6710, "loss": 1.675, "lr": 2.4991012214302136e-06, "epoch": 0.06035767511177347, "percentage": 1.21, "elapsed_time": "0:01:09", "remaining_time": "1:34:13", "throughput": 4803.15, "total_tokens": 331776} {"current_steps": 82, "total_steps": 6710, "loss": 1.6056, "lr": 2.499078895121435e-06, "epoch": 0.06110283159463487, "percentage": 1.22, "elapsed_time": "0:01:09", "remaining_time": "1:34:08", "throughput": 4806.46, "total_tokens": 335872} {"current_steps": 83, "total_steps": 6710, "loss": 1.7192, "lr": 2.4990562950056437e-06, "epoch": 0.06184798807749627, "percentage": 1.24, "elapsed_time": "0:01:10", "remaining_time": "1:34:03", "throughput": 4809.89, "total_tokens": 339968} {"current_steps": 84, "total_steps": 6710, "loss": 1.8451, "lr": 2.499033421087793e-06, "epoch": 0.06259314456035768, "percentage": 1.25, "elapsed_time": "0:01:11", "remaining_time": "1:33:57", "throughput": 4814.07, "total_tokens": 344064} {"current_steps": 85, "total_steps": 6710, "loss": 1.4133, "lr": 2.4990102733728982e-06, "epoch": 0.06333830104321908, "percentage": 1.27, "elapsed_time": "0:01:12", "remaining_time": "1:33:52", "throughput": 4817.42, "total_tokens": 348160} {"current_steps": 86, "total_steps": 6710, "loss": 1.8014, "lr": 2.4989868518660323e-06, "epoch": 0.06408345752608048, "percentage": 1.28, "elapsed_time": "0:01:13", "remaining_time": "1:33:48", "throughput": 4820.18, "total_tokens": 352256} {"current_steps": 87, "total_steps": 6710, "loss": 1.4308, "lr": 2.49896315657233e-06, "epoch": 0.06482861400894188, "percentage": 1.3, "elapsed_time": "0:01:13", "remaining_time": "1:33:43", "throughput": 4823.68, "total_tokens": 356352} {"current_steps": 88, "total_steps": 6710, "loss": 1.4928, "lr": 2.4989391874969854e-06, "epoch": 0.06557377049180328, "percentage": 1.31, "elapsed_time": "0:01:14", "remaining_time": "1:33:38", "throughput": 4827.96, "total_tokens": 360448} {"current_steps": 89, "total_steps": 6710, "loss": 1.5195, "lr": 2.4989149446452527e-06, "epoch": 0.06631892697466468, "percentage": 1.33, "elapsed_time": "0:01:15", "remaining_time": "1:33:33", "throughput": 4831.55, "total_tokens": 364544} {"current_steps": 90, "total_steps": 6710, "loss": 1.9749, "lr": 2.498890428022446e-06, "epoch": 0.06706408345752608, "percentage": 1.34, "elapsed_time": "0:01:16", "remaining_time": "1:33:28", "throughput": 4835.11, "total_tokens": 368640} {"current_steps": 91, "total_steps": 6710, "loss": 1.5448, "lr": 2.4988656376339395e-06, "epoch": 0.06780923994038748, "percentage": 1.36, "elapsed_time": "0:01:17", "remaining_time": "1:33:22", "throughput": 4838.8, "total_tokens": 372736} {"current_steps": 92, "total_steps": 6710, "loss": 2.0974, "lr": 2.498840573485168e-06, "epoch": 0.06855439642324888, "percentage": 1.37, "elapsed_time": "0:01:17", "remaining_time": "1:33:17", "throughput": 4842.54, "total_tokens": 376832} {"current_steps": 93, "total_steps": 6710, "loss": 1.1699, "lr": 2.498815235581625e-06, "epoch": 0.06929955290611028, "percentage": 1.39, "elapsed_time": "0:01:18", "remaining_time": "1:33:13", "throughput": 4845.76, "total_tokens": 380928} {"current_steps": 94, "total_steps": 6710, "loss": 1.8106, "lr": 2.4987896239288646e-06, "epoch": 0.07004470938897168, "percentage": 1.4, "elapsed_time": "0:01:19", "remaining_time": "1:33:08", "throughput": 4849.29, "total_tokens": 385024} {"current_steps": 95, "total_steps": 6710, "loss": 1.8658, "lr": 2.498763738532502e-06, "epoch": 0.07078986587183309, "percentage": 1.42, "elapsed_time": "0:01:20", "remaining_time": "1:33:06", "throughput": 4850.03, "total_tokens": 389120} {"current_steps": 96, "total_steps": 6710, "loss": 1.6157, "lr": 2.498737579398211e-06, "epoch": 0.07153502235469449, "percentage": 1.43, "elapsed_time": "0:01:21", "remaining_time": "1:33:01", "throughput": 4853.36, "total_tokens": 393216} {"current_steps": 97, "total_steps": 6710, "loss": 1.4651, "lr": 2.4987111465317252e-06, "epoch": 0.07228017883755589, "percentage": 1.45, "elapsed_time": "0:01:21", "remaining_time": "1:32:57", "throughput": 4856.31, "total_tokens": 397312} {"current_steps": 98, "total_steps": 6710, "loss": 1.7253, "lr": 2.4986844399388398e-06, "epoch": 0.07302533532041729, "percentage": 1.46, "elapsed_time": "0:01:22", "remaining_time": "1:32:54", "throughput": 4858.16, "total_tokens": 401408} {"current_steps": 99, "total_steps": 6710, "loss": 1.8181, "lr": 2.498657459625409e-06, "epoch": 0.07377049180327869, "percentage": 1.48, "elapsed_time": "0:01:23", "remaining_time": "1:32:50", "throughput": 4861.34, "total_tokens": 405504} {"current_steps": 100, "total_steps": 6710, "loss": 1.7382, "lr": 2.4986302055973466e-06, "epoch": 0.07451564828614009, "percentage": 1.49, "elapsed_time": "0:01:24", "remaining_time": "1:32:46", "throughput": 4864.2, "total_tokens": 409600} {"current_steps": 101, "total_steps": 6710, "loss": 1.6686, "lr": 2.498602677860628e-06, "epoch": 0.07526080476900149, "percentage": 1.51, "elapsed_time": "0:01:24", "remaining_time": "1:32:41", "throughput": 4867.2, "total_tokens": 413696} {"current_steps": 102, "total_steps": 6710, "loss": 1.6356, "lr": 2.4985748764212854e-06, "epoch": 0.07600596125186289, "percentage": 1.52, "elapsed_time": "0:01:25", "remaining_time": "1:32:37", "throughput": 4870.29, "total_tokens": 417792} {"current_steps": 103, "total_steps": 6710, "loss": 1.4051, "lr": 2.4985468012854142e-06, "epoch": 0.07675111773472429, "percentage": 1.54, "elapsed_time": "0:01:26", "remaining_time": "1:32:33", "throughput": 4873.09, "total_tokens": 421888} {"current_steps": 104, "total_steps": 6710, "loss": 1.9119, "lr": 2.4985184524591693e-06, "epoch": 0.07749627421758569, "percentage": 1.55, "elapsed_time": "0:01:27", "remaining_time": "1:32:29", "throughput": 4875.81, "total_tokens": 425984} {"current_steps": 105, "total_steps": 6710, "loss": 1.6375, "lr": 2.4984898299487643e-06, "epoch": 0.07824143070044709, "percentage": 1.56, "elapsed_time": "0:01:28", "remaining_time": "1:32:26", "throughput": 4877.76, "total_tokens": 430080} {"current_steps": 106, "total_steps": 6710, "loss": 1.8567, "lr": 2.4984609337604737e-06, "epoch": 0.07898658718330849, "percentage": 1.58, "elapsed_time": "0:01:28", "remaining_time": "1:32:23", "throughput": 4879.99, "total_tokens": 434176} {"current_steps": 107, "total_steps": 6710, "loss": 1.5457, "lr": 2.4984317639006317e-06, "epoch": 0.07973174366616989, "percentage": 1.59, "elapsed_time": "0:01:29", "remaining_time": "1:32:18", "throughput": 4882.83, "total_tokens": 438272} {"current_steps": 108, "total_steps": 6710, "loss": 1.6477, "lr": 2.498402320375632e-06, "epoch": 0.08047690014903129, "percentage": 1.61, "elapsed_time": "0:01:30", "remaining_time": "1:32:15", "throughput": 4885.1, "total_tokens": 442368} {"current_steps": 109, "total_steps": 6710, "loss": 1.4253, "lr": 2.49837260319193e-06, "epoch": 0.08122205663189269, "percentage": 1.62, "elapsed_time": "0:01:31", "remaining_time": "1:32:12", "throughput": 4886.85, "total_tokens": 446464} {"current_steps": 110, "total_steps": 6710, "loss": 1.4538, "lr": 2.4983426123560383e-06, "epoch": 0.08196721311475409, "percentage": 1.64, "elapsed_time": "0:01:32", "remaining_time": "1:32:10", "throughput": 4888.42, "total_tokens": 450560} {"current_steps": 111, "total_steps": 6710, "loss": 1.1376, "lr": 2.4983123478745326e-06, "epoch": 0.08271236959761549, "percentage": 1.65, "elapsed_time": "0:01:32", "remaining_time": "1:32:06", "throughput": 4890.84, "total_tokens": 454656} {"current_steps": 112, "total_steps": 6710, "loss": 1.8518, "lr": 2.4982818097540464e-06, "epoch": 0.08345752608047691, "percentage": 1.67, "elapsed_time": "0:01:33", "remaining_time": "1:32:02", "throughput": 4893.46, "total_tokens": 458752} {"current_steps": 113, "total_steps": 6710, "loss": 1.5002, "lr": 2.4982509980012737e-06, "epoch": 0.08420268256333831, "percentage": 1.68, "elapsed_time": "0:01:34", "remaining_time": "1:31:59", "throughput": 4895.6, "total_tokens": 462848} {"current_steps": 114, "total_steps": 6710, "loss": 1.8247, "lr": 2.4982199126229693e-06, "epoch": 0.08494783904619971, "percentage": 1.7, "elapsed_time": "0:01:35", "remaining_time": "1:31:56", "throughput": 4897.32, "total_tokens": 466944} {"current_steps": 115, "total_steps": 6710, "loss": 1.6219, "lr": 2.4981885536259463e-06, "epoch": 0.08569299552906111, "percentage": 1.71, "elapsed_time": "0:01:36", "remaining_time": "1:31:53", "throughput": 4899.88, "total_tokens": 471040} {"current_steps": 116, "total_steps": 6710, "loss": 1.8122, "lr": 2.4981569210170804e-06, "epoch": 0.08643815201192251, "percentage": 1.73, "elapsed_time": "0:01:36", "remaining_time": "1:31:49", "throughput": 4902.47, "total_tokens": 475136} {"current_steps": 117, "total_steps": 6710, "loss": 1.6108, "lr": 2.498125014803304e-06, "epoch": 0.08718330849478391, "percentage": 1.74, "elapsed_time": "0:01:37", "remaining_time": "1:31:45", "throughput": 4905.09, "total_tokens": 479232} {"current_steps": 118, "total_steps": 6710, "loss": 1.3979, "lr": 2.498092834991613e-06, "epoch": 0.08792846497764531, "percentage": 1.76, "elapsed_time": "0:01:38", "remaining_time": "1:31:42", "throughput": 4907.17, "total_tokens": 483328} {"current_steps": 119, "total_steps": 6710, "loss": 1.4653, "lr": 2.4980603815890593e-06, "epoch": 0.08867362146050671, "percentage": 1.77, "elapsed_time": "0:01:39", "remaining_time": "1:31:39", "throughput": 4908.83, "total_tokens": 487424} {"current_steps": 120, "total_steps": 6710, "loss": 1.7755, "lr": 2.4980276546027586e-06, "epoch": 0.08941877794336811, "percentage": 1.79, "elapsed_time": "0:01:40", "remaining_time": "1:31:36", "throughput": 4910.83, "total_tokens": 491520} {"current_steps": 121, "total_steps": 6710, "loss": 1.6424, "lr": 2.4979946540398837e-06, "epoch": 0.09016393442622951, "percentage": 1.8, "elapsed_time": "0:01:40", "remaining_time": "1:31:34", "throughput": 4912.3, "total_tokens": 495616} {"current_steps": 122, "total_steps": 6710, "loss": 1.6357, "lr": 2.4979613799076697e-06, "epoch": 0.09090909090909091, "percentage": 1.82, "elapsed_time": "0:01:41", "remaining_time": "1:31:32", "throughput": 4913.41, "total_tokens": 499712} {"current_steps": 123, "total_steps": 6710, "loss": 1.8447, "lr": 2.49792783221341e-06, "epoch": 0.09165424739195231, "percentage": 1.83, "elapsed_time": "0:01:42", "remaining_time": "1:31:28", "throughput": 4915.47, "total_tokens": 503808} {"current_steps": 124, "total_steps": 6710, "loss": 1.9269, "lr": 2.4978940109644583e-06, "epoch": 0.09239940387481371, "percentage": 1.85, "elapsed_time": "0:01:43", "remaining_time": "1:31:25", "throughput": 4917.89, "total_tokens": 507904} {"current_steps": 125, "total_steps": 6710, "loss": 1.7432, "lr": 2.497859916168229e-06, "epoch": 0.09314456035767511, "percentage": 1.86, "elapsed_time": "0:01:44", "remaining_time": "1:31:22", "throughput": 4920.03, "total_tokens": 512000} {"current_steps": 126, "total_steps": 6710, "loss": 1.7555, "lr": 2.497825547832195e-06, "epoch": 0.09388971684053651, "percentage": 1.88, "elapsed_time": "0:01:44", "remaining_time": "1:31:20", "throughput": 4921.04, "total_tokens": 516096} {"current_steps": 127, "total_steps": 6710, "loss": 1.9104, "lr": 2.497790905963891e-06, "epoch": 0.09463487332339791, "percentage": 1.89, "elapsed_time": "0:01:45", "remaining_time": "1:31:17", "throughput": 4922.82, "total_tokens": 520192} {"current_steps": 128, "total_steps": 6710, "loss": 1.2189, "lr": 2.49775599057091e-06, "epoch": 0.09538002980625931, "percentage": 1.91, "elapsed_time": "0:01:46", "remaining_time": "1:31:14", "throughput": 4925.07, "total_tokens": 524288} {"current_steps": 129, "total_steps": 6710, "loss": 1.4676, "lr": 2.497720801660906e-06, "epoch": 0.09612518628912071, "percentage": 1.92, "elapsed_time": "0:01:47", "remaining_time": "1:31:10", "throughput": 4927.24, "total_tokens": 528384} {"current_steps": 130, "total_steps": 6710, "loss": 1.4556, "lr": 2.4976853392415934e-06, "epoch": 0.09687034277198212, "percentage": 1.94, "elapsed_time": "0:01:48", "remaining_time": "1:31:07", "throughput": 4929.06, "total_tokens": 532480} {"current_steps": 131, "total_steps": 6710, "loss": 1.4825, "lr": 2.4976496033207448e-06, "epoch": 0.09761549925484352, "percentage": 1.95, "elapsed_time": "0:01:48", "remaining_time": "1:31:05", "throughput": 4930.77, "total_tokens": 536576} {"current_steps": 132, "total_steps": 6710, "loss": 1.5276, "lr": 2.4976135939061945e-06, "epoch": 0.09836065573770492, "percentage": 1.97, "elapsed_time": "0:01:49", "remaining_time": "1:31:01", "throughput": 4932.96, "total_tokens": 540672} {"current_steps": 133, "total_steps": 6710, "loss": 1.5871, "lr": 2.497577311005835e-06, "epoch": 0.09910581222056632, "percentage": 1.98, "elapsed_time": "0:01:50", "remaining_time": "1:30:58", "throughput": 4934.9, "total_tokens": 544768} {"current_steps": 134, "total_steps": 6710, "loss": 2.0733, "lr": 2.497540754627621e-06, "epoch": 0.09985096870342772, "percentage": 2.0, "elapsed_time": "0:01:51", "remaining_time": "1:30:55", "throughput": 4937.0, "total_tokens": 548864} {"current_steps": 135, "total_steps": 6710, "loss": 1.5911, "lr": 2.497503924779565e-06, "epoch": 0.10059612518628912, "percentage": 2.01, "elapsed_time": "0:01:51", "remaining_time": "1:30:52", "throughput": 4938.98, "total_tokens": 552960} {"current_steps": 136, "total_steps": 6710, "loss": 1.3958, "lr": 2.4974668214697412e-06, "epoch": 0.10134128166915052, "percentage": 2.03, "elapsed_time": "0:01:52", "remaining_time": "1:30:49", "throughput": 4940.92, "total_tokens": 557056} {"current_steps": 137, "total_steps": 6710, "loss": 1.6137, "lr": 2.497429444706282e-06, "epoch": 0.10208643815201192, "percentage": 2.04, "elapsed_time": "0:01:53", "remaining_time": "1:30:47", "throughput": 4942.32, "total_tokens": 561152} {"current_steps": 138, "total_steps": 6710, "loss": 1.5397, "lr": 2.4973917944973812e-06, "epoch": 0.10283159463487332, "percentage": 2.06, "elapsed_time": "0:01:54", "remaining_time": "1:30:44", "throughput": 4944.07, "total_tokens": 565248} {"current_steps": 139, "total_steps": 6710, "loss": 1.7236, "lr": 2.4973538708512916e-06, "epoch": 0.10357675111773472, "percentage": 2.07, "elapsed_time": "0:01:55", "remaining_time": "1:30:41", "throughput": 4945.88, "total_tokens": 569344} {"current_steps": 140, "total_steps": 6710, "loss": 1.5369, "lr": 2.497315673776327e-06, "epoch": 0.10432190760059612, "percentage": 2.09, "elapsed_time": "0:01:55", "remaining_time": "1:30:38", "throughput": 4947.8, "total_tokens": 573440} {"current_steps": 141, "total_steps": 6710, "loss": 1.8095, "lr": 2.49727720328086e-06, "epoch": 0.10506706408345752, "percentage": 2.1, "elapsed_time": "0:01:56", "remaining_time": "1:30:38", "throughput": 4947.82, "total_tokens": 577536} {"current_steps": 142, "total_steps": 6710, "loss": 1.6887, "lr": 2.4972384593733233e-06, "epoch": 0.10581222056631892, "percentage": 2.12, "elapsed_time": "0:01:57", "remaining_time": "1:30:35", "throughput": 4949.74, "total_tokens": 581632} {"current_steps": 143, "total_steps": 6710, "loss": 1.6321, "lr": 2.497199442062211e-06, "epoch": 0.10655737704918032, "percentage": 2.13, "elapsed_time": "0:01:58", "remaining_time": "1:30:32", "throughput": 4951.35, "total_tokens": 585728} {"current_steps": 144, "total_steps": 6710, "loss": 1.6307, "lr": 2.4971601513560744e-06, "epoch": 0.10730253353204174, "percentage": 2.15, "elapsed_time": "0:01:59", "remaining_time": "1:30:30", "throughput": 4952.07, "total_tokens": 589824} {"current_steps": 145, "total_steps": 6710, "loss": 1.5312, "lr": 2.4971205872635272e-06, "epoch": 0.10804769001490314, "percentage": 2.16, "elapsed_time": "0:01:59", "remaining_time": "1:30:28", "throughput": 4953.65, "total_tokens": 593920} {"current_steps": 146, "total_steps": 6710, "loss": 1.7228, "lr": 2.4970807497932427e-06, "epoch": 0.10879284649776454, "percentage": 2.18, "elapsed_time": "0:02:00", "remaining_time": "1:30:26", "throughput": 4954.62, "total_tokens": 598016} {"current_steps": 147, "total_steps": 6710, "loss": 1.8044, "lr": 2.4970406389539524e-06, "epoch": 0.10953800298062594, "percentage": 2.19, "elapsed_time": "0:02:01", "remaining_time": "1:30:23", "throughput": 4956.5, "total_tokens": 602112} {"current_steps": 148, "total_steps": 6710, "loss": 1.6499, "lr": 2.497000254754449e-06, "epoch": 0.11028315946348734, "percentage": 2.21, "elapsed_time": "0:02:02", "remaining_time": "1:30:20", "throughput": 4958.36, "total_tokens": 606208} {"current_steps": 149, "total_steps": 6710, "loss": 2.1141, "lr": 2.4969595972035863e-06, "epoch": 0.11102831594634874, "percentage": 2.22, "elapsed_time": "0:02:03", "remaining_time": "1:30:18", "throughput": 4959.68, "total_tokens": 610304} {"current_steps": 150, "total_steps": 6710, "loss": 1.7277, "lr": 2.4969186663102753e-06, "epoch": 0.11177347242921014, "percentage": 2.24, "elapsed_time": "0:02:03", "remaining_time": "1:30:16", "throughput": 4960.59, "total_tokens": 614400} {"current_steps": 151, "total_steps": 6710, "loss": 1.4498, "lr": 2.4968774620834886e-06, "epoch": 0.11251862891207154, "percentage": 2.25, "elapsed_time": "0:02:04", "remaining_time": "1:30:13", "throughput": 4962.34, "total_tokens": 618496} {"current_steps": 152, "total_steps": 6710, "loss": 1.1958, "lr": 2.4968359845322595e-06, "epoch": 0.11326378539493294, "percentage": 2.27, "elapsed_time": "0:02:05", "remaining_time": "1:30:11", "throughput": 4963.7, "total_tokens": 622592} {"current_steps": 153, "total_steps": 6710, "loss": 1.5152, "lr": 2.4967942336656786e-06, "epoch": 0.11400894187779434, "percentage": 2.28, "elapsed_time": "0:02:06", "remaining_time": "1:30:09", "throughput": 4964.89, "total_tokens": 626688} {"current_steps": 154, "total_steps": 6710, "loss": 1.706, "lr": 2.4967522094928988e-06, "epoch": 0.11475409836065574, "percentage": 2.3, "elapsed_time": "0:02:07", "remaining_time": "1:30:06", "throughput": 4966.64, "total_tokens": 630784} {"current_steps": 155, "total_steps": 6710, "loss": 1.2176, "lr": 2.4967099120231326e-06, "epoch": 0.11549925484351714, "percentage": 2.31, "elapsed_time": "0:02:07", "remaining_time": "1:30:04", "throughput": 4968.26, "total_tokens": 634880} {"current_steps": 156, "total_steps": 6710, "loss": 1.8425, "lr": 2.4966673412656513e-06, "epoch": 0.11624441132637854, "percentage": 2.32, "elapsed_time": "0:02:08", "remaining_time": "1:30:01", "throughput": 4969.86, "total_tokens": 638976} {"current_steps": 157, "total_steps": 6710, "loss": 1.6235, "lr": 2.4966244972297867e-06, "epoch": 0.11698956780923994, "percentage": 2.34, "elapsed_time": "0:02:09", "remaining_time": "1:29:59", "throughput": 4971.2, "total_tokens": 643072} {"current_steps": 158, "total_steps": 6710, "loss": 1.4302, "lr": 2.49658137992493e-06, "epoch": 0.11773472429210134, "percentage": 2.35, "elapsed_time": "0:02:10", "remaining_time": "1:29:56", "throughput": 4972.58, "total_tokens": 647168} {"current_steps": 159, "total_steps": 6710, "loss": 1.4197, "lr": 2.496537989360534e-06, "epoch": 0.11847988077496274, "percentage": 2.37, "elapsed_time": "0:02:10", "remaining_time": "1:29:55", "throughput": 4973.39, "total_tokens": 651264} {"current_steps": 160, "total_steps": 6710, "loss": 1.6116, "lr": 2.4964943255461095e-06, "epoch": 0.11922503725782414, "percentage": 2.38, "elapsed_time": "0:02:11", "remaining_time": "1:29:53", "throughput": 4974.57, "total_tokens": 655360} {"current_steps": 161, "total_steps": 6710, "loss": 1.5379, "lr": 2.4964503884912285e-06, "epoch": 0.11997019374068554, "percentage": 2.4, "elapsed_time": "0:02:12", "remaining_time": "1:29:51", "throughput": 4975.77, "total_tokens": 659456} {"current_steps": 162, "total_steps": 6710, "loss": 1.8032, "lr": 2.4964061782055216e-06, "epoch": 0.12071535022354694, "percentage": 2.41, "elapsed_time": "0:02:13", "remaining_time": "1:29:48", "throughput": 4977.04, "total_tokens": 663552} {"current_steps": 163, "total_steps": 6710, "loss": 1.1715, "lr": 2.4963616946986803e-06, "epoch": 0.12146050670640834, "percentage": 2.43, "elapsed_time": "0:02:14", "remaining_time": "1:29:47", "throughput": 4977.26, "total_tokens": 667648} {"current_steps": 164, "total_steps": 6710, "loss": 1.7125, "lr": 2.496316937980455e-06, "epoch": 0.12220566318926974, "percentage": 2.44, "elapsed_time": "0:02:14", "remaining_time": "1:29:45", "throughput": 4978.92, "total_tokens": 671744} {"current_steps": 165, "total_steps": 6710, "loss": 1.3531, "lr": 2.4962719080606584e-06, "epoch": 0.12295081967213115, "percentage": 2.46, "elapsed_time": "0:02:15", "remaining_time": "1:29:43", "throughput": 4979.42, "total_tokens": 675840} {"current_steps": 166, "total_steps": 6710, "loss": 1.5327, "lr": 2.49622660494916e-06, "epoch": 0.12369597615499255, "percentage": 2.47, "elapsed_time": "0:02:16", "remaining_time": "1:29:41", "throughput": 4980.56, "total_tokens": 679936} {"current_steps": 167, "total_steps": 6710, "loss": 1.5877, "lr": 2.496181028655891e-06, "epoch": 0.12444113263785395, "percentage": 2.49, "elapsed_time": "0:02:17", "remaining_time": "1:29:39", "throughput": 4981.95, "total_tokens": 684032} {"current_steps": 168, "total_steps": 6710, "loss": 1.3713, "lr": 2.4961351791908424e-06, "epoch": 0.12518628912071536, "percentage": 2.5, "elapsed_time": "0:02:18", "remaining_time": "1:29:37", "throughput": 4982.76, "total_tokens": 688128} {"current_steps": 169, "total_steps": 6710, "loss": 1.7287, "lr": 2.496089056564064e-06, "epoch": 0.12593144560357675, "percentage": 2.52, "elapsed_time": "0:02:18", "remaining_time": "1:29:35", "throughput": 4984.1, "total_tokens": 692224} {"current_steps": 170, "total_steps": 6710, "loss": 1.4257, "lr": 2.496042660785666e-06, "epoch": 0.12667660208643816, "percentage": 2.53, "elapsed_time": "0:02:19", "remaining_time": "1:29:33", "throughput": 4985.24, "total_tokens": 696320} {"current_steps": 171, "total_steps": 6710, "loss": 1.7821, "lr": 2.4959959918658196e-06, "epoch": 0.12742175856929955, "percentage": 2.55, "elapsed_time": "0:02:20", "remaining_time": "1:29:31", "throughput": 4985.87, "total_tokens": 700416} {"current_steps": 172, "total_steps": 6710, "loss": 1.6067, "lr": 2.4959490498147547e-06, "epoch": 0.12816691505216096, "percentage": 2.56, "elapsed_time": "0:02:21", "remaining_time": "1:29:29", "throughput": 4987.38, "total_tokens": 704512} {"current_steps": 173, "total_steps": 6710, "loss": 1.6112, "lr": 2.495901834642761e-06, "epoch": 0.12891207153502235, "percentage": 2.58, "elapsed_time": "0:02:22", "remaining_time": "1:29:27", "throughput": 4988.86, "total_tokens": 708608} {"current_steps": 174, "total_steps": 6710, "loss": 1.7217, "lr": 2.4958543463601888e-06, "epoch": 0.12965722801788376, "percentage": 2.59, "elapsed_time": "0:02:22", "remaining_time": "1:29:24", "throughput": 4990.07, "total_tokens": 712704} {"current_steps": 175, "total_steps": 6710, "loss": 1.6066, "lr": 2.4958065849774477e-06, "epoch": 0.13040238450074515, "percentage": 2.61, "elapsed_time": "0:02:23", "remaining_time": "1:29:30", "throughput": 4984.0, "total_tokens": 716800} {"current_steps": 176, "total_steps": 6710, "loss": 1.7766, "lr": 2.4957585505050075e-06, "epoch": 0.13114754098360656, "percentage": 2.62, "elapsed_time": "0:02:24", "remaining_time": "1:29:28", "throughput": 4985.18, "total_tokens": 720896} {"current_steps": 177, "total_steps": 6710, "loss": 1.7861, "lr": 2.4957102429533968e-06, "epoch": 0.13189269746646795, "percentage": 2.64, "elapsed_time": "0:02:25", "remaining_time": "1:29:26", "throughput": 4986.43, "total_tokens": 724992} {"current_steps": 178, "total_steps": 6710, "loss": 1.7738, "lr": 2.4956616623332064e-06, "epoch": 0.13263785394932937, "percentage": 2.65, "elapsed_time": "0:02:26", "remaining_time": "1:29:25", "throughput": 4986.49, "total_tokens": 729088} {"current_steps": 179, "total_steps": 6710, "loss": 1.6766, "lr": 2.4956128086550844e-06, "epoch": 0.13338301043219075, "percentage": 2.67, "elapsed_time": "0:02:27", "remaining_time": "1:29:23", "throughput": 4987.14, "total_tokens": 733184} {"current_steps": 180, "total_steps": 6710, "loss": 1.3119, "lr": 2.495563681929741e-06, "epoch": 0.13412816691505217, "percentage": 2.68, "elapsed_time": "0:02:27", "remaining_time": "1:29:22", "throughput": 4987.51, "total_tokens": 737280} {"current_steps": 181, "total_steps": 6710, "loss": 1.4729, "lr": 2.4955142821679433e-06, "epoch": 0.13487332339791355, "percentage": 2.7, "elapsed_time": "0:02:28", "remaining_time": "1:29:20", "throughput": 4988.61, "total_tokens": 741376} {"current_steps": 182, "total_steps": 6710, "loss": 1.3914, "lr": 2.495464609380522e-06, "epoch": 0.13561847988077497, "percentage": 2.71, "elapsed_time": "0:02:29", "remaining_time": "1:29:18", "throughput": 4989.81, "total_tokens": 745472} {"current_steps": 183, "total_steps": 6710, "loss": 1.6569, "lr": 2.4954146635783645e-06, "epoch": 0.13636363636363635, "percentage": 2.73, "elapsed_time": "0:02:30", "remaining_time": "1:29:17", "throughput": 4989.91, "total_tokens": 749568} {"current_steps": 184, "total_steps": 6710, "loss": 1.5013, "lr": 2.4953644447724196e-06, "epoch": 0.13710879284649777, "percentage": 2.74, "elapsed_time": "0:02:31", "remaining_time": "1:29:17", "throughput": 4989.15, "total_tokens": 753664} {"current_steps": 185, "total_steps": 6710, "loss": 1.5253, "lr": 2.495313952973696e-06, "epoch": 0.13785394932935915, "percentage": 2.76, "elapsed_time": "0:02:31", "remaining_time": "1:29:17", "throughput": 4988.65, "total_tokens": 757760} {"current_steps": 186, "total_steps": 6710, "loss": 1.2854, "lr": 2.4952631881932615e-06, "epoch": 0.13859910581222057, "percentage": 2.77, "elapsed_time": "0:02:32", "remaining_time": "1:29:15", "throughput": 4989.42, "total_tokens": 761856} {"current_steps": 187, "total_steps": 6710, "loss": 1.2934, "lr": 2.495212150442244e-06, "epoch": 0.13934426229508196, "percentage": 2.79, "elapsed_time": "0:02:33", "remaining_time": "1:29:14", "throughput": 4990.14, "total_tokens": 765952} {"current_steps": 188, "total_steps": 6710, "loss": 1.4835, "lr": 2.4951608397318316e-06, "epoch": 0.14008941877794337, "percentage": 2.8, "elapsed_time": "0:02:34", "remaining_time": "1:29:12", "throughput": 4990.72, "total_tokens": 770048} {"current_steps": 189, "total_steps": 6710, "loss": 1.5125, "lr": 2.495109256073272e-06, "epoch": 0.14083457526080476, "percentage": 2.82, "elapsed_time": "0:02:35", "remaining_time": "1:29:11", "throughput": 4991.37, "total_tokens": 774144} {"current_steps": 190, "total_steps": 6710, "loss": 1.332, "lr": 2.4950573994778725e-06, "epoch": 0.14157973174366617, "percentage": 2.83, "elapsed_time": "0:02:35", "remaining_time": "1:29:09", "throughput": 4992.66, "total_tokens": 778240} {"current_steps": 191, "total_steps": 6710, "loss": 1.505, "lr": 2.495005269957001e-06, "epoch": 0.14232488822652756, "percentage": 2.85, "elapsed_time": "0:02:36", "remaining_time": "1:29:07", "throughput": 4993.63, "total_tokens": 782336} {"current_steps": 192, "total_steps": 6710, "loss": 1.4962, "lr": 2.4949528675220836e-06, "epoch": 0.14307004470938897, "percentage": 2.86, "elapsed_time": "0:02:37", "remaining_time": "1:29:05", "throughput": 4994.64, "total_tokens": 786432} {"current_steps": 193, "total_steps": 6710, "loss": 1.4783, "lr": 2.494900192184608e-06, "epoch": 0.14381520119225039, "percentage": 2.88, "elapsed_time": "0:02:38", "remaining_time": "1:29:03", "throughput": 4995.88, "total_tokens": 790528} {"current_steps": 194, "total_steps": 6710, "loss": 1.578, "lr": 2.4948472439561212e-06, "epoch": 0.14456035767511177, "percentage": 2.89, "elapsed_time": "0:02:39", "remaining_time": "1:29:01", "throughput": 4996.67, "total_tokens": 794624} {"current_steps": 195, "total_steps": 6710, "loss": 1.6124, "lr": 2.4947940228482293e-06, "epoch": 0.1453055141579732, "percentage": 2.91, "elapsed_time": "0:02:39", "remaining_time": "1:28:59", "throughput": 4997.68, "total_tokens": 798720} {"current_steps": 196, "total_steps": 6710, "loss": 1.7206, "lr": 2.4947405288725986e-06, "epoch": 0.14605067064083457, "percentage": 2.92, "elapsed_time": "0:02:40", "remaining_time": "1:28:57", "throughput": 4998.66, "total_tokens": 802816} {"current_steps": 197, "total_steps": 6710, "loss": 1.8828, "lr": 2.4946867620409562e-06, "epoch": 0.146795827123696, "percentage": 2.94, "elapsed_time": "0:02:41", "remaining_time": "1:28:55", "throughput": 4999.85, "total_tokens": 806912} {"current_steps": 198, "total_steps": 6710, "loss": 1.6511, "lr": 2.494632722365088e-06, "epoch": 0.14754098360655737, "percentage": 2.95, "elapsed_time": "0:02:42", "remaining_time": "1:28:53", "throughput": 5001.04, "total_tokens": 811008} {"current_steps": 199, "total_steps": 6710, "loss": 1.5511, "lr": 2.4945784098568388e-06, "epoch": 0.1482861400894188, "percentage": 2.97, "elapsed_time": "0:02:42", "remaining_time": "1:28:51", "throughput": 5002.02, "total_tokens": 815104} {"current_steps": 200, "total_steps": 6710, "loss": 1.5366, "lr": 2.4945238245281153e-06, "epoch": 0.14903129657228018, "percentage": 2.98, "elapsed_time": "0:02:43", "remaining_time": "1:28:49", "throughput": 5003.14, "total_tokens": 819200} {"current_steps": 201, "total_steps": 6710, "loss": 1.5477, "lr": 2.494468966390883e-06, "epoch": 0.1497764530551416, "percentage": 3.0, "elapsed_time": "0:02:44", "remaining_time": "1:28:47", "throughput": 5004.28, "total_tokens": 823296} {"current_steps": 202, "total_steps": 6710, "loss": 1.7468, "lr": 2.4944138354571667e-06, "epoch": 0.15052160953800298, "percentage": 3.01, "elapsed_time": "0:02:45", "remaining_time": "1:28:45", "throughput": 5005.03, "total_tokens": 827392} {"current_steps": 203, "total_steps": 6710, "loss": 1.3275, "lr": 2.494358431739052e-06, "epoch": 0.1512667660208644, "percentage": 3.03, "elapsed_time": "0:02:46", "remaining_time": "1:28:44", "throughput": 5006.07, "total_tokens": 831488} {"current_steps": 204, "total_steps": 6710, "loss": 1.2918, "lr": 2.4943027552486837e-06, "epoch": 0.15201192250372578, "percentage": 3.04, "elapsed_time": "0:02:46", "remaining_time": "1:28:42", "throughput": 5007.1, "total_tokens": 835584} {"current_steps": 205, "total_steps": 6710, "loss": 1.544, "lr": 2.494246805998266e-06, "epoch": 0.1527570789865872, "percentage": 3.06, "elapsed_time": "0:02:47", "remaining_time": "1:28:40", "throughput": 5008.14, "total_tokens": 839680} {"current_steps": 206, "total_steps": 6710, "loss": 1.6492, "lr": 2.494190584000064e-06, "epoch": 0.15350223546944858, "percentage": 3.07, "elapsed_time": "0:02:48", "remaining_time": "1:28:38", "throughput": 5009.18, "total_tokens": 843776} {"current_steps": 207, "total_steps": 6710, "loss": 1.5733, "lr": 2.494134089266401e-06, "epoch": 0.15424739195231, "percentage": 3.08, "elapsed_time": "0:02:49", "remaining_time": "1:28:36", "throughput": 5010.23, "total_tokens": 847872} {"current_steps": 208, "total_steps": 6710, "loss": 1.5674, "lr": 2.4940773218096625e-06, "epoch": 0.15499254843517138, "percentage": 3.1, "elapsed_time": "0:02:50", "remaining_time": "1:28:34", "throughput": 5011.35, "total_tokens": 851968} {"current_steps": 209, "total_steps": 6710, "loss": 1.7445, "lr": 2.494020281642291e-06, "epoch": 0.1557377049180328, "percentage": 3.11, "elapsed_time": "0:02:50", "remaining_time": "1:28:32", "throughput": 5012.26, "total_tokens": 856064} {"current_steps": 210, "total_steps": 6710, "loss": 1.5282, "lr": 2.493962968776791e-06, "epoch": 0.15648286140089418, "percentage": 3.13, "elapsed_time": "0:02:51", "remaining_time": "1:28:30", "throughput": 5013.19, "total_tokens": 860160} {"current_steps": 211, "total_steps": 6710, "loss": 1.5178, "lr": 2.4939053832257255e-06, "epoch": 0.1572280178837556, "percentage": 3.14, "elapsed_time": "0:02:52", "remaining_time": "1:28:28", "throughput": 5014.27, "total_tokens": 864256} {"current_steps": 212, "total_steps": 6710, "loss": 1.5608, "lr": 2.493847525001718e-06, "epoch": 0.15797317436661698, "percentage": 3.16, "elapsed_time": "0:02:53", "remaining_time": "1:28:26", "throughput": 5015.23, "total_tokens": 868352} {"current_steps": 213, "total_steps": 6710, "loss": 1.6601, "lr": 2.493789394117451e-06, "epoch": 0.1587183308494784, "percentage": 3.17, "elapsed_time": "0:02:53", "remaining_time": "1:28:25", "throughput": 5016.26, "total_tokens": 872448} {"current_steps": 214, "total_steps": 6710, "loss": 1.3614, "lr": 2.4937309905856673e-06, "epoch": 0.15946348733233978, "percentage": 3.19, "elapsed_time": "0:02:54", "remaining_time": "1:28:23", "throughput": 5017.32, "total_tokens": 876544} {"current_steps": 215, "total_steps": 6710, "loss": 1.5145, "lr": 2.493672314419169e-06, "epoch": 0.1602086438152012, "percentage": 3.2, "elapsed_time": "0:02:55", "remaining_time": "1:28:21", "throughput": 5018.31, "total_tokens": 880640} {"current_steps": 216, "total_steps": 6710, "loss": 1.5232, "lr": 2.493613365630819e-06, "epoch": 0.16095380029806258, "percentage": 3.22, "elapsed_time": "0:02:56", "remaining_time": "1:28:19", "throughput": 5019.36, "total_tokens": 884736} {"current_steps": 217, "total_steps": 6710, "loss": 1.5342, "lr": 2.493554144233539e-06, "epoch": 0.161698956780924, "percentage": 3.23, "elapsed_time": "0:02:57", "remaining_time": "1:28:17", "throughput": 5019.95, "total_tokens": 888832} {"current_steps": 218, "total_steps": 6710, "loss": 1.4846, "lr": 2.493494650240311e-06, "epoch": 0.16244411326378538, "percentage": 3.25, "elapsed_time": "0:02:57", "remaining_time": "1:28:16", "throughput": 5020.98, "total_tokens": 892928} {"current_steps": 219, "total_steps": 6710, "loss": 1.5216, "lr": 2.4934348836641765e-06, "epoch": 0.1631892697466468, "percentage": 3.26, "elapsed_time": "0:02:58", "remaining_time": "1:28:14", "throughput": 5022.01, "total_tokens": 897024} {"current_steps": 220, "total_steps": 6710, "loss": 1.6706, "lr": 2.4933748445182367e-06, "epoch": 0.16393442622950818, "percentage": 3.28, "elapsed_time": "0:02:59", "remaining_time": "1:28:12", "throughput": 5022.75, "total_tokens": 901120} {"current_steps": 221, "total_steps": 6710, "loss": 1.7307, "lr": 2.493314532815652e-06, "epoch": 0.1646795827123696, "percentage": 3.29, "elapsed_time": "0:03:00", "remaining_time": "1:28:11", "throughput": 5022.7, "total_tokens": 905216} {"current_steps": 222, "total_steps": 6710, "loss": 1.606, "lr": 2.4932539485696438e-06, "epoch": 0.16542473919523099, "percentage": 3.31, "elapsed_time": "0:03:01", "remaining_time": "1:28:10", "throughput": 5023.48, "total_tokens": 909312} {"current_steps": 223, "total_steps": 6710, "loss": 1.6733, "lr": 2.4931930917934926e-06, "epoch": 0.1661698956780924, "percentage": 3.32, "elapsed_time": "0:03:01", "remaining_time": "1:28:08", "throughput": 5024.32, "total_tokens": 913408} {"current_steps": 224, "total_steps": 6710, "loss": 1.5496, "lr": 2.4931319625005385e-06, "epoch": 0.16691505216095381, "percentage": 3.34, "elapsed_time": "0:03:02", "remaining_time": "1:28:07", "throughput": 5024.57, "total_tokens": 917504} {"current_steps": 225, "total_steps": 6710, "loss": 1.6427, "lr": 2.493070560704181e-06, "epoch": 0.1676602086438152, "percentage": 3.35, "elapsed_time": "0:03:03", "remaining_time": "1:28:05", "throughput": 5025.26, "total_tokens": 921600} {"current_steps": 226, "total_steps": 6710, "loss": 1.4676, "lr": 2.4930088864178807e-06, "epoch": 0.16840536512667661, "percentage": 3.37, "elapsed_time": "0:03:04", "remaining_time": "1:28:04", "throughput": 5025.8, "total_tokens": 925696} {"current_steps": 227, "total_steps": 6710, "loss": 1.7631, "lr": 2.4929469396551563e-06, "epoch": 0.169150521609538, "percentage": 3.38, "elapsed_time": "0:03:04", "remaining_time": "1:28:02", "throughput": 5026.66, "total_tokens": 929792} {"current_steps": 228, "total_steps": 6710, "loss": 1.3236, "lr": 2.492884720429588e-06, "epoch": 0.16989567809239942, "percentage": 3.4, "elapsed_time": "0:03:05", "remaining_time": "1:28:00", "throughput": 5027.54, "total_tokens": 933888} {"current_steps": 229, "total_steps": 6710, "loss": 1.3123, "lr": 2.4928222287548133e-06, "epoch": 0.1706408345752608, "percentage": 3.41, "elapsed_time": "0:03:06", "remaining_time": "1:27:59", "throughput": 5028.1, "total_tokens": 937984} {"current_steps": 230, "total_steps": 6710, "loss": 1.702, "lr": 2.492759464644532e-06, "epoch": 0.17138599105812222, "percentage": 3.43, "elapsed_time": "0:03:07", "remaining_time": "1:27:57", "throughput": 5028.91, "total_tokens": 942080} {"current_steps": 231, "total_steps": 6710, "loss": 1.5967, "lr": 2.4926964281125017e-06, "epoch": 0.1721311475409836, "percentage": 3.44, "elapsed_time": "0:03:08", "remaining_time": "1:27:56", "throughput": 5029.74, "total_tokens": 946176} {"current_steps": 232, "total_steps": 6710, "loss": 1.3976, "lr": 2.4926331191725406e-06, "epoch": 0.17287630402384502, "percentage": 3.46, "elapsed_time": "0:03:08", "remaining_time": "1:27:54", "throughput": 5030.6, "total_tokens": 950272} {"current_steps": 233, "total_steps": 6710, "loss": 1.0019, "lr": 2.4925695378385266e-06, "epoch": 0.1736214605067064, "percentage": 3.47, "elapsed_time": "0:03:09", "remaining_time": "1:27:52", "throughput": 5031.39, "total_tokens": 954368} {"current_steps": 234, "total_steps": 6710, "loss": 1.2974, "lr": 2.492505684124397e-06, "epoch": 0.17436661698956782, "percentage": 3.49, "elapsed_time": "0:03:10", "remaining_time": "1:27:51", "throughput": 5032.28, "total_tokens": 958464} {"current_steps": 235, "total_steps": 6710, "loss": 1.2614, "lr": 2.4924415580441497e-06, "epoch": 0.1751117734724292, "percentage": 3.5, "elapsed_time": "0:03:11", "remaining_time": "1:27:49", "throughput": 5032.65, "total_tokens": 962560} {"current_steps": 236, "total_steps": 6710, "loss": 1.4689, "lr": 2.4923771596118406e-06, "epoch": 0.17585692995529062, "percentage": 3.52, "elapsed_time": "0:03:12", "remaining_time": "1:27:48", "throughput": 5033.4, "total_tokens": 966656} {"current_steps": 237, "total_steps": 6710, "loss": 1.6646, "lr": 2.492312488841587e-06, "epoch": 0.176602086438152, "percentage": 3.53, "elapsed_time": "0:03:12", "remaining_time": "1:27:46", "throughput": 5034.12, "total_tokens": 970752} {"current_steps": 238, "total_steps": 6710, "loss": 1.4991, "lr": 2.4922475457475646e-06, "epoch": 0.17734724292101342, "percentage": 3.55, "elapsed_time": "0:03:13", "remaining_time": "1:27:45", "throughput": 5034.97, "total_tokens": 974848} {"current_steps": 239, "total_steps": 6710, "loss": 1.5118, "lr": 2.4921823303440103e-06, "epoch": 0.1780923994038748, "percentage": 3.56, "elapsed_time": "0:03:14", "remaining_time": "1:27:43", "throughput": 5035.68, "total_tokens": 978944} {"current_steps": 240, "total_steps": 6710, "loss": 1.6395, "lr": 2.4921168426452186e-06, "epoch": 0.17883755588673622, "percentage": 3.58, "elapsed_time": "0:03:15", "remaining_time": "1:27:41", "throughput": 5036.34, "total_tokens": 983040} {"current_steps": 241, "total_steps": 6710, "loss": 1.6805, "lr": 2.492051082665546e-06, "epoch": 0.1795827123695976, "percentage": 3.59, "elapsed_time": "0:03:15", "remaining_time": "1:27:40", "throughput": 5036.88, "total_tokens": 987136} {"current_steps": 242, "total_steps": 6710, "loss": 1.4206, "lr": 2.491985050419407e-06, "epoch": 0.18032786885245902, "percentage": 3.61, "elapsed_time": "0:03:16", "remaining_time": "1:27:38", "throughput": 5037.7, "total_tokens": 991232} {"current_steps": 243, "total_steps": 6710, "loss": 1.2479, "lr": 2.491918745921276e-06, "epoch": 0.1810730253353204, "percentage": 3.62, "elapsed_time": "0:03:17", "remaining_time": "1:27:37", "throughput": 5038.49, "total_tokens": 995328} {"current_steps": 244, "total_steps": 6710, "loss": 1.3356, "lr": 2.4918521691856877e-06, "epoch": 0.18181818181818182, "percentage": 3.64, "elapsed_time": "0:03:18", "remaining_time": "1:27:35", "throughput": 5039.28, "total_tokens": 999424} {"current_steps": 245, "total_steps": 6710, "loss": 1.6335, "lr": 2.491785320227237e-06, "epoch": 0.1825633383010432, "percentage": 3.65, "elapsed_time": "0:03:19", "remaining_time": "1:27:34", "throughput": 5040.01, "total_tokens": 1003520} {"current_steps": 246, "total_steps": 6710, "loss": 1.738, "lr": 2.4917181990605767e-06, "epoch": 0.18330849478390462, "percentage": 3.67, "elapsed_time": "0:03:19", "remaining_time": "1:27:32", "throughput": 5040.69, "total_tokens": 1007616} {"current_steps": 247, "total_steps": 6710, "loss": 1.5037, "lr": 2.49165080570042e-06, "epoch": 0.184053651266766, "percentage": 3.68, "elapsed_time": "0:03:20", "remaining_time": "1:27:30", "throughput": 5041.46, "total_tokens": 1011712} {"current_steps": 248, "total_steps": 6710, "loss": 1.7546, "lr": 2.491583140161541e-06, "epoch": 0.18479880774962743, "percentage": 3.7, "elapsed_time": "0:03:21", "remaining_time": "1:27:29", "throughput": 5042.3, "total_tokens": 1015808} {"current_steps": 249, "total_steps": 6710, "loss": 1.438, "lr": 2.4915152024587718e-06, "epoch": 0.1855439642324888, "percentage": 3.71, "elapsed_time": "0:03:22", "remaining_time": "1:27:27", "throughput": 5043.14, "total_tokens": 1019904} {"current_steps": 250, "total_steps": 6710, "loss": 1.2943, "lr": 2.491446992607005e-06, "epoch": 0.18628912071535023, "percentage": 3.73, "elapsed_time": "0:03:23", "remaining_time": "1:27:25", "throughput": 5043.93, "total_tokens": 1024000} {"current_steps": 251, "total_steps": 6710, "loss": 1.557, "lr": 2.491378510621193e-06, "epoch": 0.1870342771982116, "percentage": 3.74, "elapsed_time": "0:03:23", "remaining_time": "1:27:24", "throughput": 5044.58, "total_tokens": 1028096} {"current_steps": 252, "total_steps": 6710, "loss": 1.3775, "lr": 2.491309756516347e-06, "epoch": 0.18777943368107303, "percentage": 3.76, "elapsed_time": "0:03:24", "remaining_time": "1:27:22", "throughput": 5045.32, "total_tokens": 1032192} {"current_steps": 253, "total_steps": 6710, "loss": 1.4781, "lr": 2.4912407303075387e-06, "epoch": 0.1885245901639344, "percentage": 3.77, "elapsed_time": "0:03:25", "remaining_time": "1:27:21", "throughput": 5046.07, "total_tokens": 1036288} {"current_steps": 254, "total_steps": 6710, "loss": 1.4287, "lr": 2.491171432009899e-06, "epoch": 0.18926974664679583, "percentage": 3.79, "elapsed_time": "0:03:26", "remaining_time": "1:27:19", "throughput": 5046.73, "total_tokens": 1040384} {"current_steps": 255, "total_steps": 6710, "loss": 1.6187, "lr": 2.4911018616386184e-06, "epoch": 0.19001490312965721, "percentage": 3.8, "elapsed_time": "0:03:26", "remaining_time": "1:27:18", "throughput": 5047.53, "total_tokens": 1044480} {"current_steps": 256, "total_steps": 6710, "loss": 1.1897, "lr": 2.4910320192089475e-06, "epoch": 0.19076005961251863, "percentage": 3.82, "elapsed_time": "0:03:27", "remaining_time": "1:27:16", "throughput": 5048.28, "total_tokens": 1048576} {"current_steps": 257, "total_steps": 6710, "loss": 1.5343, "lr": 2.490961904736197e-06, "epoch": 0.19150521609538004, "percentage": 3.83, "elapsed_time": "0:03:28", "remaining_time": "1:27:15", "throughput": 5048.79, "total_tokens": 1052672} {"current_steps": 258, "total_steps": 6710, "loss": 1.2896, "lr": 2.4908915182357353e-06, "epoch": 0.19225037257824143, "percentage": 3.85, "elapsed_time": "0:03:29", "remaining_time": "1:27:13", "throughput": 5049.41, "total_tokens": 1056768} {"current_steps": 259, "total_steps": 6710, "loss": 1.548, "lr": 2.4908208597229916e-06, "epoch": 0.19299552906110284, "percentage": 3.86, "elapsed_time": "0:03:30", "remaining_time": "1:27:12", "throughput": 5050.11, "total_tokens": 1060864} {"current_steps": 260, "total_steps": 6710, "loss": 1.5618, "lr": 2.4907499292134556e-06, "epoch": 0.19374068554396423, "percentage": 3.87, "elapsed_time": "0:03:30", "remaining_time": "1:27:10", "throughput": 5050.8, "total_tokens": 1064960} {"current_steps": 261, "total_steps": 6710, "loss": 1.2519, "lr": 2.4906787267226752e-06, "epoch": 0.19448584202682564, "percentage": 3.89, "elapsed_time": "0:03:31", "remaining_time": "1:27:09", "throughput": 5051.52, "total_tokens": 1069056} {"current_steps": 262, "total_steps": 6710, "loss": 1.5084, "lr": 2.490607252266259e-06, "epoch": 0.19523099850968703, "percentage": 3.9, "elapsed_time": "0:03:32", "remaining_time": "1:27:08", "throughput": 5051.83, "total_tokens": 1073152} {"current_steps": 263, "total_steps": 6710, "loss": 1.7471, "lr": 2.490535505859874e-06, "epoch": 0.19597615499254845, "percentage": 3.92, "elapsed_time": "0:03:33", "remaining_time": "1:27:06", "throughput": 5052.26, "total_tokens": 1077248} {"current_steps": 264, "total_steps": 6710, "loss": 1.4647, "lr": 2.490463487519248e-06, "epoch": 0.19672131147540983, "percentage": 3.93, "elapsed_time": "0:03:34", "remaining_time": "1:27:05", "throughput": 5052.72, "total_tokens": 1081344} {"current_steps": 265, "total_steps": 6710, "loss": 0.9944, "lr": 2.490391197260168e-06, "epoch": 0.19746646795827125, "percentage": 3.95, "elapsed_time": "0:03:34", "remaining_time": "1:27:04", "throughput": 5053.21, "total_tokens": 1085440} {"current_steps": 266, "total_steps": 6710, "loss": 1.4426, "lr": 2.49031863509848e-06, "epoch": 0.19821162444113263, "percentage": 3.96, "elapsed_time": "0:03:35", "remaining_time": "1:27:03", "throughput": 5053.31, "total_tokens": 1089536} {"current_steps": 267, "total_steps": 6710, "loss": 1.4764, "lr": 2.490245801050091e-06, "epoch": 0.19895678092399405, "percentage": 3.98, "elapsed_time": "0:03:36", "remaining_time": "1:27:02", "throughput": 5053.31, "total_tokens": 1093632} {"current_steps": 268, "total_steps": 6710, "loss": 1.3711, "lr": 2.4901726951309657e-06, "epoch": 0.19970193740685543, "percentage": 3.99, "elapsed_time": "0:03:37", "remaining_time": "1:27:01", "throughput": 5053.62, "total_tokens": 1097728} {"current_steps": 269, "total_steps": 6710, "loss": 1.6872, "lr": 2.4900993173571303e-06, "epoch": 0.20044709388971685, "percentage": 4.01, "elapsed_time": "0:03:38", "remaining_time": "1:27:00", "throughput": 5053.99, "total_tokens": 1101824} {"current_steps": 270, "total_steps": 6710, "loss": 1.8193, "lr": 2.4900256677446698e-06, "epoch": 0.20119225037257824, "percentage": 4.02, "elapsed_time": "0:03:38", "remaining_time": "1:26:58", "throughput": 5054.48, "total_tokens": 1105920} {"current_steps": 271, "total_steps": 6710, "loss": 1.3367, "lr": 2.4899517463097277e-06, "epoch": 0.20193740685543965, "percentage": 4.04, "elapsed_time": "0:03:39", "remaining_time": "1:26:57", "throughput": 5054.84, "total_tokens": 1110016} {"current_steps": 272, "total_steps": 6710, "loss": 1.7942, "lr": 2.489877553068509e-06, "epoch": 0.20268256333830104, "percentage": 4.05, "elapsed_time": "0:03:40", "remaining_time": "1:26:56", "throughput": 5055.3, "total_tokens": 1114112} {"current_steps": 273, "total_steps": 6710, "loss": 1.1166, "lr": 2.4898030880372775e-06, "epoch": 0.20342771982116245, "percentage": 4.07, "elapsed_time": "0:03:41", "remaining_time": "1:26:55", "throughput": 5055.68, "total_tokens": 1118208} {"current_steps": 274, "total_steps": 6710, "loss": 1.1182, "lr": 2.4897283512323556e-06, "epoch": 0.20417287630402384, "percentage": 4.08, "elapsed_time": "0:03:41", "remaining_time": "1:26:53", "throughput": 5056.19, "total_tokens": 1122304} {"current_steps": 275, "total_steps": 6710, "loss": 1.6443, "lr": 2.4896533426701267e-06, "epoch": 0.20491803278688525, "percentage": 4.1, "elapsed_time": "0:03:42", "remaining_time": "1:26:52", "throughput": 5056.75, "total_tokens": 1126400} {"current_steps": 276, "total_steps": 6710, "loss": 1.503, "lr": 2.489578062367034e-06, "epoch": 0.20566318926974664, "percentage": 4.11, "elapsed_time": "0:03:43", "remaining_time": "1:26:51", "throughput": 5057.25, "total_tokens": 1130496} {"current_steps": 277, "total_steps": 6710, "loss": 1.7784, "lr": 2.4895025103395777e-06, "epoch": 0.20640834575260805, "percentage": 4.13, "elapsed_time": "0:03:44", "remaining_time": "1:26:49", "throughput": 5057.73, "total_tokens": 1134592} {"current_steps": 278, "total_steps": 6710, "loss": 1.2738, "lr": 2.4894266866043206e-06, "epoch": 0.20715350223546944, "percentage": 4.14, "elapsed_time": "0:03:45", "remaining_time": "1:26:48", "throughput": 5058.26, "total_tokens": 1138688} {"current_steps": 279, "total_steps": 6710, "loss": 1.5221, "lr": 2.4893505911778835e-06, "epoch": 0.20789865871833085, "percentage": 4.16, "elapsed_time": "0:03:45", "remaining_time": "1:26:47", "throughput": 5058.72, "total_tokens": 1142784} {"current_steps": 280, "total_steps": 6710, "loss": 1.6493, "lr": 2.4892742240769476e-06, "epoch": 0.20864381520119224, "percentage": 4.17, "elapsed_time": "0:03:46", "remaining_time": "1:26:45", "throughput": 5059.22, "total_tokens": 1146880} {"current_steps": 281, "total_steps": 6710, "loss": 1.2188, "lr": 2.4891975853182513e-06, "epoch": 0.20938897168405365, "percentage": 4.19, "elapsed_time": "0:03:47", "remaining_time": "1:26:44", "throughput": 5059.74, "total_tokens": 1150976} {"current_steps": 282, "total_steps": 6710, "loss": 1.3961, "lr": 2.489120674918597e-06, "epoch": 0.21013412816691504, "percentage": 4.2, "elapsed_time": "0:03:48", "remaining_time": "1:26:43", "throughput": 5060.24, "total_tokens": 1155072} {"current_steps": 283, "total_steps": 6710, "loss": 1.4742, "lr": 2.4890434928948416e-06, "epoch": 0.21087928464977646, "percentage": 4.22, "elapsed_time": "0:03:49", "remaining_time": "1:26:41", "throughput": 5060.75, "total_tokens": 1159168} {"current_steps": 284, "total_steps": 6710, "loss": 1.3562, "lr": 2.4889660392639058e-06, "epoch": 0.21162444113263784, "percentage": 4.23, "elapsed_time": "0:03:49", "remaining_time": "1:26:40", "throughput": 5061.28, "total_tokens": 1163264} {"current_steps": 285, "total_steps": 6710, "loss": 1.3346, "lr": 2.4888883140427664e-06, "epoch": 0.21236959761549926, "percentage": 4.25, "elapsed_time": "0:03:50", "remaining_time": "1:26:39", "throughput": 5061.61, "total_tokens": 1167360} {"current_steps": 286, "total_steps": 6710, "loss": 1.3977, "lr": 2.488810317248463e-06, "epoch": 0.21311475409836064, "percentage": 4.26, "elapsed_time": "0:03:51", "remaining_time": "1:26:38", "throughput": 5061.92, "total_tokens": 1171456} {"current_steps": 287, "total_steps": 6710, "loss": 1.5056, "lr": 2.4887320488980914e-06, "epoch": 0.21385991058122206, "percentage": 4.28, "elapsed_time": "0:03:52", "remaining_time": "1:26:37", "throughput": 5062.25, "total_tokens": 1175552} {"current_steps": 288, "total_steps": 6710, "loss": 1.5831, "lr": 2.48865350900881e-06, "epoch": 0.21460506706408347, "percentage": 4.29, "elapsed_time": "0:03:53", "remaining_time": "1:26:35", "throughput": 5062.77, "total_tokens": 1179648} {"current_steps": 289, "total_steps": 6710, "loss": 1.5339, "lr": 2.4885746975978344e-06, "epoch": 0.21535022354694486, "percentage": 4.31, "elapsed_time": "0:03:53", "remaining_time": "1:26:34", "throughput": 5063.27, "total_tokens": 1183744} {"current_steps": 290, "total_steps": 6710, "loss": 1.125, "lr": 2.48849561468244e-06, "epoch": 0.21609538002980627, "percentage": 4.32, "elapsed_time": "0:03:54", "remaining_time": "1:26:33", "throughput": 5063.78, "total_tokens": 1187840} {"current_steps": 291, "total_steps": 6710, "loss": 1.573, "lr": 2.4884162602799646e-06, "epoch": 0.21684053651266766, "percentage": 4.34, "elapsed_time": "0:03:55", "remaining_time": "1:26:31", "throughput": 5064.27, "total_tokens": 1191936} {"current_steps": 292, "total_steps": 6710, "loss": 1.0401, "lr": 2.4883366344078007e-06, "epoch": 0.21758569299552907, "percentage": 4.35, "elapsed_time": "0:03:56", "remaining_time": "1:26:30", "throughput": 5064.75, "total_tokens": 1196032} {"current_steps": 293, "total_steps": 6710, "loss": 1.2717, "lr": 2.488256737083405e-06, "epoch": 0.21833084947839046, "percentage": 4.37, "elapsed_time": "0:03:56", "remaining_time": "1:26:29", "throughput": 5065.29, "total_tokens": 1200128} {"current_steps": 294, "total_steps": 6710, "loss": 1.334, "lr": 2.48817656832429e-06, "epoch": 0.21907600596125187, "percentage": 4.38, "elapsed_time": "0:03:57", "remaining_time": "1:26:27", "throughput": 5065.8, "total_tokens": 1204224} {"current_steps": 295, "total_steps": 6710, "loss": 1.1574, "lr": 2.48809612814803e-06, "epoch": 0.21982116244411326, "percentage": 4.4, "elapsed_time": "0:03:58", "remaining_time": "1:26:26", "throughput": 5066.19, "total_tokens": 1208320} {"current_steps": 296, "total_steps": 6710, "loss": 1.4306, "lr": 2.488015416572258e-06, "epoch": 0.22056631892697467, "percentage": 4.41, "elapsed_time": "0:03:59", "remaining_time": "1:26:25", "throughput": 5066.4, "total_tokens": 1212416} {"current_steps": 297, "total_steps": 6710, "loss": 1.5369, "lr": 2.487934433614666e-06, "epoch": 0.22131147540983606, "percentage": 4.43, "elapsed_time": "0:04:00", "remaining_time": "1:26:24", "throughput": 5066.6, "total_tokens": 1216512} {"current_steps": 298, "total_steps": 6710, "loss": 1.3197, "lr": 2.4878531792930074e-06, "epoch": 0.22205663189269748, "percentage": 4.44, "elapsed_time": "0:04:00", "remaining_time": "1:26:23", "throughput": 5067.03, "total_tokens": 1220608} {"current_steps": 299, "total_steps": 6710, "loss": 1.2565, "lr": 2.4877716536250922e-06, "epoch": 0.22280178837555886, "percentage": 4.46, "elapsed_time": "0:04:01", "remaining_time": "1:26:21", "throughput": 5067.54, "total_tokens": 1224704} {"current_steps": 300, "total_steps": 6710, "loss": 1.5078, "lr": 2.4876898566287923e-06, "epoch": 0.22354694485842028, "percentage": 4.47, "elapsed_time": "0:04:02", "remaining_time": "1:26:21", "throughput": 5067.55, "total_tokens": 1228800} {"current_steps": 301, "total_steps": 6710, "loss": 1.5352, "lr": 2.4876077883220377e-06, "epoch": 0.22429210134128166, "percentage": 4.49, "elapsed_time": "0:04:03", "remaining_time": "1:26:19", "throughput": 5068.06, "total_tokens": 1232896} {"current_steps": 302, "total_steps": 6710, "loss": 1.7399, "lr": 2.4875254487228184e-06, "epoch": 0.22503725782414308, "percentage": 4.5, "elapsed_time": "0:04:04", "remaining_time": "1:26:18", "throughput": 5068.54, "total_tokens": 1236992} {"current_steps": 303, "total_steps": 6710, "loss": 1.4718, "lr": 2.4874428378491844e-06, "epoch": 0.22578241430700446, "percentage": 4.52, "elapsed_time": "0:04:04", "remaining_time": "1:26:17", "throughput": 5069.0, "total_tokens": 1241088} {"current_steps": 304, "total_steps": 6710, "loss": 1.6293, "lr": 2.487359955719244e-06, "epoch": 0.22652757078986588, "percentage": 4.53, "elapsed_time": "0:04:05", "remaining_time": "1:26:15", "throughput": 5069.51, "total_tokens": 1245184} {"current_steps": 305, "total_steps": 6710, "loss": 1.0553, "lr": 2.487276802351166e-06, "epoch": 0.22727272727272727, "percentage": 4.55, "elapsed_time": "0:04:06", "remaining_time": "1:26:14", "throughput": 5070.0, "total_tokens": 1249280} {"current_steps": 306, "total_steps": 6710, "loss": 1.5699, "lr": 2.487193377763178e-06, "epoch": 0.22801788375558868, "percentage": 4.56, "elapsed_time": "0:04:07", "remaining_time": "1:26:13", "throughput": 5070.47, "total_tokens": 1253376} {"current_steps": 307, "total_steps": 6710, "loss": 1.4865, "lr": 2.487109681973567e-06, "epoch": 0.22876304023845007, "percentage": 4.58, "elapsed_time": "0:04:07", "remaining_time": "1:26:11", "throughput": 5070.91, "total_tokens": 1257472} {"current_steps": 308, "total_steps": 6710, "loss": 1.6482, "lr": 2.48702571500068e-06, "epoch": 0.22950819672131148, "percentage": 4.59, "elapsed_time": "0:04:08", "remaining_time": "1:26:10", "throughput": 5071.37, "total_tokens": 1261568} {"current_steps": 309, "total_steps": 6710, "loss": 1.1673, "lr": 2.4869414768629237e-06, "epoch": 0.23025335320417287, "percentage": 4.61, "elapsed_time": "0:04:09", "remaining_time": "1:26:09", "throughput": 5071.8, "total_tokens": 1265664} {"current_steps": 310, "total_steps": 6710, "loss": 1.6454, "lr": 2.4868569675787625e-06, "epoch": 0.23099850968703428, "percentage": 4.62, "elapsed_time": "0:04:10", "remaining_time": "1:26:08", "throughput": 5072.27, "total_tokens": 1269760} {"current_steps": 311, "total_steps": 6710, "loss": 1.3966, "lr": 2.486772187166722e-06, "epoch": 0.23174366616989567, "percentage": 4.63, "elapsed_time": "0:04:11", "remaining_time": "1:26:06", "throughput": 5072.67, "total_tokens": 1273856} {"current_steps": 312, "total_steps": 6710, "loss": 1.4258, "lr": 2.486687135645387e-06, "epoch": 0.23248882265275708, "percentage": 4.65, "elapsed_time": "0:04:11", "remaining_time": "1:26:05", "throughput": 5073.09, "total_tokens": 1277952} {"current_steps": 313, "total_steps": 6710, "loss": 1.3126, "lr": 2.486601813033401e-06, "epoch": 0.23323397913561847, "percentage": 4.66, "elapsed_time": "0:04:12", "remaining_time": "1:26:04", "throughput": 5073.5, "total_tokens": 1282048} {"current_steps": 314, "total_steps": 6710, "loss": 0.9145, "lr": 2.4865162193494675e-06, "epoch": 0.23397913561847988, "percentage": 4.68, "elapsed_time": "0:04:13", "remaining_time": "1:26:03", "throughput": 5073.96, "total_tokens": 1286144} {"current_steps": 315, "total_steps": 6710, "loss": 1.514, "lr": 2.486430354612349e-06, "epoch": 0.23472429210134127, "percentage": 4.69, "elapsed_time": "0:04:14", "remaining_time": "1:26:01", "throughput": 5074.45, "total_tokens": 1290240} {"current_steps": 316, "total_steps": 6710, "loss": 1.1735, "lr": 2.486344218840868e-06, "epoch": 0.23546944858420268, "percentage": 4.71, "elapsed_time": "0:04:15", "remaining_time": "1:26:00", "throughput": 5074.98, "total_tokens": 1294336} {"current_steps": 317, "total_steps": 6710, "loss": 1.5333, "lr": 2.486257812053906e-06, "epoch": 0.23621460506706407, "percentage": 4.72, "elapsed_time": "0:04:15", "remaining_time": "1:25:59", "throughput": 5075.43, "total_tokens": 1298432} {"current_steps": 318, "total_steps": 6710, "loss": 1.4778, "lr": 2.4861711342704044e-06, "epoch": 0.23695976154992549, "percentage": 4.74, "elapsed_time": "0:04:16", "remaining_time": "1:25:58", "throughput": 5075.9, "total_tokens": 1302528} {"current_steps": 319, "total_steps": 6710, "loss": 1.7696, "lr": 2.4860841855093628e-06, "epoch": 0.23770491803278687, "percentage": 4.75, "elapsed_time": "0:04:17", "remaining_time": "1:25:56", "throughput": 5076.29, "total_tokens": 1306624} {"current_steps": 320, "total_steps": 6710, "loss": 1.6006, "lr": 2.4859969657898408e-06, "epoch": 0.23845007451564829, "percentage": 4.77, "elapsed_time": "0:04:18", "remaining_time": "1:25:55", "throughput": 5076.75, "total_tokens": 1310720} {"current_steps": 321, "total_steps": 6710, "loss": 1.5358, "lr": 2.4859094751309584e-06, "epoch": 0.2391952309985097, "percentage": 4.78, "elapsed_time": "0:04:18", "remaining_time": "1:25:54", "throughput": 5077.22, "total_tokens": 1314816} {"current_steps": 322, "total_steps": 6710, "loss": 1.687, "lr": 2.485821713551894e-06, "epoch": 0.2399403874813711, "percentage": 4.8, "elapsed_time": "0:04:19", "remaining_time": "1:25:52", "throughput": 5077.71, "total_tokens": 1318912} {"current_steps": 323, "total_steps": 6710, "loss": 1.6788, "lr": 2.485733681071885e-06, "epoch": 0.2406855439642325, "percentage": 4.81, "elapsed_time": "0:04:20", "remaining_time": "1:25:51", "throughput": 5078.15, "total_tokens": 1323008} {"current_steps": 324, "total_steps": 6710, "loss": 1.483, "lr": 2.4856453777102296e-06, "epoch": 0.2414307004470939, "percentage": 4.83, "elapsed_time": "0:04:21", "remaining_time": "1:25:50", "throughput": 5078.63, "total_tokens": 1327104} {"current_steps": 325, "total_steps": 6710, "loss": 1.2704, "lr": 2.4855568034862842e-06, "epoch": 0.2421758569299553, "percentage": 4.84, "elapsed_time": "0:04:22", "remaining_time": "1:25:49", "throughput": 5078.99, "total_tokens": 1331200} {"current_steps": 326, "total_steps": 6710, "loss": 1.8306, "lr": 2.4854679584194645e-06, "epoch": 0.2429210134128167, "percentage": 4.86, "elapsed_time": "0:04:22", "remaining_time": "1:25:48", "throughput": 5079.29, "total_tokens": 1335296} {"current_steps": 327, "total_steps": 6710, "loss": 1.1652, "lr": 2.485378842529247e-06, "epoch": 0.2436661698956781, "percentage": 4.87, "elapsed_time": "0:04:23", "remaining_time": "1:25:46", "throughput": 5079.62, "total_tokens": 1339392} {"current_steps": 328, "total_steps": 6710, "loss": 1.482, "lr": 2.485289455835165e-06, "epoch": 0.2444113263785395, "percentage": 4.89, "elapsed_time": "0:04:24", "remaining_time": "1:25:46", "throughput": 5079.09, "total_tokens": 1343488} {"current_steps": 329, "total_steps": 6710, "loss": 1.57, "lr": 2.4851997983568137e-06, "epoch": 0.2451564828614009, "percentage": 4.9, "elapsed_time": "0:04:25", "remaining_time": "1:25:45", "throughput": 5079.42, "total_tokens": 1347584} {"current_steps": 330, "total_steps": 6710, "loss": 1.5237, "lr": 2.4851098701138465e-06, "epoch": 0.2459016393442623, "percentage": 4.92, "elapsed_time": "0:04:26", "remaining_time": "1:25:44", "throughput": 5079.81, "total_tokens": 1351680} {"current_steps": 331, "total_steps": 6710, "loss": 1.3897, "lr": 2.4850196711259765e-06, "epoch": 0.2466467958271237, "percentage": 4.93, "elapsed_time": "0:04:26", "remaining_time": "1:25:43", "throughput": 5079.97, "total_tokens": 1355776} {"current_steps": 332, "total_steps": 6710, "loss": 1.5734, "lr": 2.4849292014129756e-06, "epoch": 0.2473919523099851, "percentage": 4.95, "elapsed_time": "0:04:27", "remaining_time": "1:25:42", "throughput": 5080.2, "total_tokens": 1359872} {"current_steps": 333, "total_steps": 6710, "loss": 1.1313, "lr": 2.4848384609946755e-06, "epoch": 0.2481371087928465, "percentage": 4.96, "elapsed_time": "0:04:28", "remaining_time": "1:25:41", "throughput": 5080.51, "total_tokens": 1363968} {"current_steps": 334, "total_steps": 6710, "loss": 1.1235, "lr": 2.4847474498909675e-06, "epoch": 0.2488822652757079, "percentage": 4.98, "elapsed_time": "0:04:29", "remaining_time": "1:25:40", "throughput": 5080.77, "total_tokens": 1368064} {"current_steps": 335, "total_steps": 6710, "loss": 1.1531, "lr": 2.4846561681218016e-06, "epoch": 0.2496274217585693, "percentage": 4.99, "elapsed_time": "0:04:30", "remaining_time": "1:25:39", "throughput": 5081.14, "total_tokens": 1372160} {"current_steps": 336, "total_steps": 6710, "loss": 1.7077, "lr": 2.484564615707187e-06, "epoch": 0.2503725782414307, "percentage": 5.01, "elapsed_time": "0:04:30", "remaining_time": "1:25:37", "throughput": 5081.44, "total_tokens": 1376256} {"current_steps": 337, "total_steps": 6710, "loss": 1.5824, "lr": 2.4844727926671935e-06, "epoch": 0.2511177347242921, "percentage": 5.02, "elapsed_time": "0:04:31", "remaining_time": "1:25:36", "throughput": 5081.78, "total_tokens": 1380352} {"current_steps": 338, "total_steps": 6710, "loss": 1.2452, "lr": 2.4843806990219486e-06, "epoch": 0.2518628912071535, "percentage": 5.04, "elapsed_time": "0:04:32", "remaining_time": "1:25:35", "throughput": 5082.11, "total_tokens": 1384448} {"current_steps": 339, "total_steps": 6710, "loss": 1.223, "lr": 2.4842883347916403e-06, "epoch": 0.2526080476900149, "percentage": 5.05, "elapsed_time": "0:04:33", "remaining_time": "1:25:34", "throughput": 5082.39, "total_tokens": 1388544} {"current_steps": 340, "total_steps": 6710, "loss": 1.4545, "lr": 2.4841956999965157e-06, "epoch": 0.2533532041728763, "percentage": 5.07, "elapsed_time": "0:04:33", "remaining_time": "1:25:33", "throughput": 5082.79, "total_tokens": 1392640} {"current_steps": 341, "total_steps": 6710, "loss": 1.8993, "lr": 2.4841027946568802e-06, "epoch": 0.2540983606557377, "percentage": 5.08, "elapsed_time": "0:04:34", "remaining_time": "1:25:32", "throughput": 5083.15, "total_tokens": 1396736} {"current_steps": 342, "total_steps": 6710, "loss": 1.5224, "lr": 2.4840096187931e-06, "epoch": 0.2548435171385991, "percentage": 5.1, "elapsed_time": "0:04:35", "remaining_time": "1:25:31", "throughput": 5083.47, "total_tokens": 1400832} {"current_steps": 343, "total_steps": 6710, "loss": 1.5111, "lr": 2.4839161724256e-06, "epoch": 0.2555886736214605, "percentage": 5.11, "elapsed_time": "0:04:36", "remaining_time": "1:25:29", "throughput": 5083.79, "total_tokens": 1404928} {"current_steps": 344, "total_steps": 6710, "loss": 1.0978, "lr": 2.483822455574864e-06, "epoch": 0.2563338301043219, "percentage": 5.13, "elapsed_time": "0:04:37", "remaining_time": "1:25:28", "throughput": 5084.15, "total_tokens": 1409024} {"current_steps": 345, "total_steps": 6710, "loss": 1.5529, "lr": 2.483728468261435e-06, "epoch": 0.2570789865871833, "percentage": 5.14, "elapsed_time": "0:04:37", "remaining_time": "1:25:27", "throughput": 5084.46, "total_tokens": 1413120} {"current_steps": 346, "total_steps": 6710, "loss": 1.3758, "lr": 2.4836342105059167e-06, "epoch": 0.2578241430700447, "percentage": 5.16, "elapsed_time": "0:04:38", "remaining_time": "1:25:26", "throughput": 5084.8, "total_tokens": 1417216} {"current_steps": 347, "total_steps": 6710, "loss": 1.6892, "lr": 2.4835396823289704e-06, "epoch": 0.2585692995529061, "percentage": 5.17, "elapsed_time": "0:04:39", "remaining_time": "1:25:25", "throughput": 5085.08, "total_tokens": 1421312} {"current_steps": 348, "total_steps": 6710, "loss": 1.6127, "lr": 2.4834448837513175e-06, "epoch": 0.2593144560357675, "percentage": 5.19, "elapsed_time": "0:04:40", "remaining_time": "1:25:24", "throughput": 5085.38, "total_tokens": 1425408} {"current_steps": 349, "total_steps": 6710, "loss": 1.3349, "lr": 2.483349814793738e-06, "epoch": 0.2600596125186289, "percentage": 5.2, "elapsed_time": "0:04:41", "remaining_time": "1:25:23", "throughput": 5085.6, "total_tokens": 1429504} {"current_steps": 350, "total_steps": 6710, "loss": 1.3887, "lr": 2.483254475477073e-06, "epoch": 0.2608047690014903, "percentage": 5.22, "elapsed_time": "0:04:41", "remaining_time": "1:25:22", "throughput": 5085.97, "total_tokens": 1433600} {"current_steps": 351, "total_steps": 6710, "loss": 1.0432, "lr": 2.48315886582222e-06, "epoch": 0.2615499254843517, "percentage": 5.23, "elapsed_time": "0:04:42", "remaining_time": "1:25:20", "throughput": 5086.29, "total_tokens": 1437696} {"current_steps": 352, "total_steps": 6710, "loss": 1.5336, "lr": 2.4830629858501385e-06, "epoch": 0.26229508196721313, "percentage": 5.25, "elapsed_time": "0:04:43", "remaining_time": "1:25:19", "throughput": 5086.6, "total_tokens": 1441792} {"current_steps": 353, "total_steps": 6710, "loss": 1.1921, "lr": 2.4829668355818454e-06, "epoch": 0.2630402384500745, "percentage": 5.26, "elapsed_time": "0:04:44", "remaining_time": "1:25:18", "throughput": 5086.95, "total_tokens": 1445888} {"current_steps": 354, "total_steps": 6710, "loss": 1.4285, "lr": 2.482870415038418e-06, "epoch": 0.2637853949329359, "percentage": 5.28, "elapsed_time": "0:04:45", "remaining_time": "1:25:17", "throughput": 5087.29, "total_tokens": 1449984} {"current_steps": 355, "total_steps": 6710, "loss": 1.4776, "lr": 2.482773724240992e-06, "epoch": 0.26453055141579734, "percentage": 5.29, "elapsed_time": "0:04:45", "remaining_time": "1:25:16", "throughput": 5087.67, "total_tokens": 1454080} {"current_steps": 356, "total_steps": 6710, "loss": 1.6028, "lr": 2.482676763210763e-06, "epoch": 0.26527570789865873, "percentage": 5.31, "elapsed_time": "0:04:46", "remaining_time": "1:25:15", "throughput": 5088.0, "total_tokens": 1458176} {"current_steps": 357, "total_steps": 6710, "loss": 1.5723, "lr": 2.482579531968985e-06, "epoch": 0.2660208643815201, "percentage": 5.32, "elapsed_time": "0:04:47", "remaining_time": "1:25:13", "throughput": 5088.37, "total_tokens": 1462272} {"current_steps": 358, "total_steps": 6710, "loss": 1.3897, "lr": 2.482482030536973e-06, "epoch": 0.2667660208643815, "percentage": 5.34, "elapsed_time": "0:04:48", "remaining_time": "1:25:12", "throughput": 5088.65, "total_tokens": 1466368} {"current_steps": 359, "total_steps": 6710, "loss": 1.6181, "lr": 2.4823842589360985e-06, "epoch": 0.26751117734724295, "percentage": 5.35, "elapsed_time": "0:04:48", "remaining_time": "1:25:11", "throughput": 5088.98, "total_tokens": 1470464} {"current_steps": 360, "total_steps": 6710, "loss": 1.6111, "lr": 2.4822862171877946e-06, "epoch": 0.26825633383010433, "percentage": 5.37, "elapsed_time": "0:04:49", "remaining_time": "1:25:10", "throughput": 5089.33, "total_tokens": 1474560} {"current_steps": 361, "total_steps": 6710, "loss": 1.7431, "lr": 2.4821879053135527e-06, "epoch": 0.2690014903129657, "percentage": 5.38, "elapsed_time": "0:04:50", "remaining_time": "1:25:09", "throughput": 5089.52, "total_tokens": 1478656} {"current_steps": 362, "total_steps": 6710, "loss": 1.347, "lr": 2.482089323334923e-06, "epoch": 0.2697466467958271, "percentage": 5.39, "elapsed_time": "0:04:51", "remaining_time": "1:25:08", "throughput": 5089.85, "total_tokens": 1482752} {"current_steps": 363, "total_steps": 6710, "loss": 1.3662, "lr": 2.4819904712735162e-06, "epoch": 0.27049180327868855, "percentage": 5.41, "elapsed_time": "0:04:52", "remaining_time": "1:25:07", "throughput": 5090.18, "total_tokens": 1486848} {"current_steps": 364, "total_steps": 6710, "loss": 1.6084, "lr": 2.4818913491510003e-06, "epoch": 0.27123695976154993, "percentage": 5.42, "elapsed_time": "0:04:52", "remaining_time": "1:25:06", "throughput": 5090.42, "total_tokens": 1490944} {"current_steps": 365, "total_steps": 6710, "loss": 1.4882, "lr": 2.481791956989105e-06, "epoch": 0.2719821162444113, "percentage": 5.44, "elapsed_time": "0:04:53", "remaining_time": "1:25:05", "throughput": 5090.7, "total_tokens": 1495040} {"current_steps": 366, "total_steps": 6710, "loss": 1.2649, "lr": 2.4816922948096166e-06, "epoch": 0.2727272727272727, "percentage": 5.45, "elapsed_time": "0:04:54", "remaining_time": "1:25:04", "throughput": 5090.97, "total_tokens": 1499136} {"current_steps": 367, "total_steps": 6710, "loss": 1.4349, "lr": 2.481592362634382e-06, "epoch": 0.27347242921013415, "percentage": 5.47, "elapsed_time": "0:04:55", "remaining_time": "1:25:03", "throughput": 5091.15, "total_tokens": 1503232} {"current_steps": 368, "total_steps": 6710, "loss": 1.5792, "lr": 2.481492160485307e-06, "epoch": 0.27421758569299554, "percentage": 5.48, "elapsed_time": "0:04:56", "remaining_time": "1:25:02", "throughput": 5091.37, "total_tokens": 1507328} {"current_steps": 369, "total_steps": 6710, "loss": 1.5104, "lr": 2.481391688384357e-06, "epoch": 0.2749627421758569, "percentage": 5.5, "elapsed_time": "0:04:56", "remaining_time": "1:25:01", "throughput": 5091.39, "total_tokens": 1511424} {"current_steps": 370, "total_steps": 6710, "loss": 1.3875, "lr": 2.481290946353556e-06, "epoch": 0.2757078986587183, "percentage": 5.51, "elapsed_time": "0:04:57", "remaining_time": "1:25:00", "throughput": 5091.45, "total_tokens": 1515520} {"current_steps": 371, "total_steps": 6710, "loss": 1.5366, "lr": 2.4811899344149875e-06, "epoch": 0.27645305514157975, "percentage": 5.53, "elapsed_time": "0:04:58", "remaining_time": "1:24:59", "throughput": 5091.55, "total_tokens": 1519616} {"current_steps": 372, "total_steps": 6710, "loss": 1.4399, "lr": 2.4810886525907934e-06, "epoch": 0.27719821162444114, "percentage": 5.54, "elapsed_time": "0:04:59", "remaining_time": "1:24:58", "throughput": 5091.39, "total_tokens": 1523712} {"current_steps": 373, "total_steps": 6710, "loss": 1.3209, "lr": 2.4809871009031762e-06, "epoch": 0.2779433681073025, "percentage": 5.56, "elapsed_time": "0:05:00", "remaining_time": "1:24:57", "throughput": 5091.54, "total_tokens": 1527808} {"current_steps": 374, "total_steps": 6710, "loss": 1.5141, "lr": 2.4808852793743965e-06, "epoch": 0.2786885245901639, "percentage": 5.57, "elapsed_time": "0:05:00", "remaining_time": "1:24:57", "throughput": 5091.62, "total_tokens": 1531904} {"current_steps": 375, "total_steps": 6710, "loss": 1.4588, "lr": 2.480783188026774e-06, "epoch": 0.27943368107302535, "percentage": 5.59, "elapsed_time": "0:05:01", "remaining_time": "1:24:56", "throughput": 5091.68, "total_tokens": 1536000} {"current_steps": 376, "total_steps": 6710, "loss": 1.2374, "lr": 2.4806808268826883e-06, "epoch": 0.28017883755588674, "percentage": 5.6, "elapsed_time": "0:05:02", "remaining_time": "1:24:55", "throughput": 5091.77, "total_tokens": 1540096} {"current_steps": 377, "total_steps": 6710, "loss": 1.3717, "lr": 2.4805781959645776e-06, "epoch": 0.2809239940387481, "percentage": 5.62, "elapsed_time": "0:05:03", "remaining_time": "1:24:54", "throughput": 5091.97, "total_tokens": 1544192} {"current_steps": 378, "total_steps": 6710, "loss": 1.3189, "lr": 2.480475295294939e-06, "epoch": 0.2816691505216095, "percentage": 5.63, "elapsed_time": "0:05:04", "remaining_time": "1:24:53", "throughput": 5091.6, "total_tokens": 1548288} {"current_steps": 379, "total_steps": 6710, "loss": 1.1976, "lr": 2.4803721248963295e-06, "epoch": 0.28241430700447095, "percentage": 5.65, "elapsed_time": "0:05:04", "remaining_time": "1:24:52", "throughput": 5091.77, "total_tokens": 1552384} {"current_steps": 380, "total_steps": 6710, "loss": 1.4341, "lr": 2.4802686847913644e-06, "epoch": 0.28315946348733234, "percentage": 5.66, "elapsed_time": "0:05:05", "remaining_time": "1:24:51", "throughput": 5091.86, "total_tokens": 1556480} {"current_steps": 381, "total_steps": 6710, "loss": 1.523, "lr": 2.480164975002719e-06, "epoch": 0.28390461997019373, "percentage": 5.68, "elapsed_time": "0:05:06", "remaining_time": "1:24:50", "throughput": 5092.1, "total_tokens": 1560576} {"current_steps": 382, "total_steps": 6710, "loss": 1.3181, "lr": 2.4800609955531268e-06, "epoch": 0.2846497764530551, "percentage": 5.69, "elapsed_time": "0:05:07", "remaining_time": "1:24:50", "throughput": 5092.22, "total_tokens": 1564672} {"current_steps": 383, "total_steps": 6710, "loss": 1.2529, "lr": 2.4799567464653806e-06, "epoch": 0.28539493293591656, "percentage": 5.71, "elapsed_time": "0:05:08", "remaining_time": "1:24:48", "throughput": 5092.5, "total_tokens": 1568768} {"current_steps": 384, "total_steps": 6710, "loss": 1.6835, "lr": 2.4798522277623332e-06, "epoch": 0.28614008941877794, "percentage": 5.72, "elapsed_time": "0:05:08", "remaining_time": "1:24:47", "throughput": 5092.7, "total_tokens": 1572864} {"current_steps": 385, "total_steps": 6710, "loss": 1.337, "lr": 2.479747439466896e-06, "epoch": 0.28688524590163933, "percentage": 5.74, "elapsed_time": "0:05:09", "remaining_time": "1:24:47", "throughput": 5092.69, "total_tokens": 1576960} {"current_steps": 386, "total_steps": 6710, "loss": 1.6153, "lr": 2.4796423816020382e-06, "epoch": 0.28763040238450077, "percentage": 5.75, "elapsed_time": "0:05:10", "remaining_time": "1:24:46", "throughput": 5092.91, "total_tokens": 1581056} {"current_steps": 387, "total_steps": 6710, "loss": 1.5914, "lr": 2.47953705419079e-06, "epoch": 0.28837555886736216, "percentage": 5.77, "elapsed_time": "0:05:11", "remaining_time": "1:24:45", "throughput": 5093.11, "total_tokens": 1585152} {"current_steps": 388, "total_steps": 6710, "loss": 1.2155, "lr": 2.47943145725624e-06, "epoch": 0.28912071535022354, "percentage": 5.78, "elapsed_time": "0:05:12", "remaining_time": "1:24:44", "throughput": 5093.35, "total_tokens": 1589248} {"current_steps": 389, "total_steps": 6710, "loss": 1.16, "lr": 2.4793255908215356e-06, "epoch": 0.28986587183308493, "percentage": 5.8, "elapsed_time": "0:05:12", "remaining_time": "1:24:43", "throughput": 5093.52, "total_tokens": 1593344} {"current_steps": 390, "total_steps": 6710, "loss": 1.0841, "lr": 2.4792194549098836e-06, "epoch": 0.2906110283159464, "percentage": 5.81, "elapsed_time": "0:05:13", "remaining_time": "1:24:41", "throughput": 5093.84, "total_tokens": 1597440} {"current_steps": 391, "total_steps": 6710, "loss": 1.5789, "lr": 2.4791130495445493e-06, "epoch": 0.29135618479880776, "percentage": 5.83, "elapsed_time": "0:05:14", "remaining_time": "1:24:40", "throughput": 5094.15, "total_tokens": 1601536} {"current_steps": 392, "total_steps": 6710, "loss": 1.3685, "lr": 2.4790063747488584e-06, "epoch": 0.29210134128166915, "percentage": 5.84, "elapsed_time": "0:05:15", "remaining_time": "1:24:39", "throughput": 5094.37, "total_tokens": 1605632} {"current_steps": 393, "total_steps": 6710, "loss": 1.0257, "lr": 2.478899430546194e-06, "epoch": 0.29284649776453053, "percentage": 5.86, "elapsed_time": "0:05:15", "remaining_time": "1:24:38", "throughput": 5094.73, "total_tokens": 1609728} {"current_steps": 394, "total_steps": 6710, "loss": 1.4347, "lr": 2.4787922169599992e-06, "epoch": 0.293591654247392, "percentage": 5.87, "elapsed_time": "0:05:16", "remaining_time": "1:24:37", "throughput": 5095.04, "total_tokens": 1613824} {"current_steps": 395, "total_steps": 6710, "loss": 1.4672, "lr": 2.4786847340137765e-06, "epoch": 0.29433681073025336, "percentage": 5.89, "elapsed_time": "0:05:17", "remaining_time": "1:24:36", "throughput": 5095.39, "total_tokens": 1617920} {"current_steps": 396, "total_steps": 6710, "loss": 1.4601, "lr": 2.478576981731086e-06, "epoch": 0.29508196721311475, "percentage": 5.9, "elapsed_time": "0:05:18", "remaining_time": "1:24:35", "throughput": 5095.76, "total_tokens": 1622016} {"current_steps": 397, "total_steps": 6710, "loss": 1.5117, "lr": 2.4784689601355487e-06, "epoch": 0.29582712369597614, "percentage": 5.92, "elapsed_time": "0:05:19", "remaining_time": "1:24:34", "throughput": 5096.09, "total_tokens": 1626112} {"current_steps": 398, "total_steps": 6710, "loss": 1.9308, "lr": 2.478360669250843e-06, "epoch": 0.2965722801788376, "percentage": 5.93, "elapsed_time": "0:05:19", "remaining_time": "1:24:32", "throughput": 5096.42, "total_tokens": 1630208} {"current_steps": 399, "total_steps": 6710, "loss": 1.2112, "lr": 2.4782521091007074e-06, "epoch": 0.29731743666169896, "percentage": 5.95, "elapsed_time": "0:05:20", "remaining_time": "1:24:31", "throughput": 5096.73, "total_tokens": 1634304} {"current_steps": 400, "total_steps": 6710, "loss": 1.2532, "lr": 2.478143279708939e-06, "epoch": 0.29806259314456035, "percentage": 5.96, "elapsed_time": "0:05:21", "remaining_time": "1:24:30", "throughput": 5097.03, "total_tokens": 1638400} {"current_steps": 401, "total_steps": 6710, "loss": 1.4957, "lr": 2.4780341810993943e-06, "epoch": 0.29880774962742174, "percentage": 5.98, "elapsed_time": "0:05:22", "remaining_time": "1:24:29", "throughput": 5097.28, "total_tokens": 1642496} {"current_steps": 402, "total_steps": 6710, "loss": 1.1833, "lr": 2.4779248132959878e-06, "epoch": 0.2995529061102832, "percentage": 5.99, "elapsed_time": "0:05:23", "remaining_time": "1:24:28", "throughput": 5097.59, "total_tokens": 1646592} {"current_steps": 403, "total_steps": 6710, "loss": 1.6559, "lr": 2.477815176322694e-06, "epoch": 0.30029806259314457, "percentage": 6.01, "elapsed_time": "0:05:23", "remaining_time": "1:24:27", "throughput": 5097.86, "total_tokens": 1650688} {"current_steps": 404, "total_steps": 6710, "loss": 1.4503, "lr": 2.477705270203546e-06, "epoch": 0.30104321907600595, "percentage": 6.02, "elapsed_time": "0:05:24", "remaining_time": "1:24:26", "throughput": 5097.91, "total_tokens": 1654784} {"current_steps": 405, "total_steps": 6710, "loss": 1.5521, "lr": 2.4775950949626364e-06, "epoch": 0.30178837555886734, "percentage": 6.04, "elapsed_time": "0:05:25", "remaining_time": "1:24:25", "throughput": 5098.03, "total_tokens": 1658880} {"current_steps": 406, "total_steps": 6710, "loss": 1.0846, "lr": 2.4774846506241163e-06, "epoch": 0.3025335320417288, "percentage": 6.05, "elapsed_time": "0:05:26", "remaining_time": "1:24:24", "throughput": 5098.19, "total_tokens": 1662976} {"current_steps": 407, "total_steps": 6710, "loss": 1.5374, "lr": 2.4773739372121957e-06, "epoch": 0.30327868852459017, "percentage": 6.07, "elapsed_time": "0:05:26", "remaining_time": "1:24:23", "throughput": 5098.39, "total_tokens": 1667072} {"current_steps": 408, "total_steps": 6710, "loss": 1.4517, "lr": 2.477262954751144e-06, "epoch": 0.30402384500745155, "percentage": 6.08, "elapsed_time": "0:05:27", "remaining_time": "1:24:22", "throughput": 5098.6, "total_tokens": 1671168} {"current_steps": 409, "total_steps": 6710, "loss": 1.3962, "lr": 2.4771517032652886e-06, "epoch": 0.30476900149031294, "percentage": 6.1, "elapsed_time": "0:05:28", "remaining_time": "1:24:21", "throughput": 5098.8, "total_tokens": 1675264} {"current_steps": 410, "total_steps": 6710, "loss": 1.3347, "lr": 2.477040182779018e-06, "epoch": 0.3055141579731744, "percentage": 6.11, "elapsed_time": "0:05:29", "remaining_time": "1:24:21", "throughput": 5098.29, "total_tokens": 1679360} {"current_steps": 411, "total_steps": 6710, "loss": 1.7301, "lr": 2.476928393316777e-06, "epoch": 0.30625931445603577, "percentage": 6.13, "elapsed_time": "0:05:30", "remaining_time": "1:24:20", "throughput": 5098.33, "total_tokens": 1683456} {"current_steps": 412, "total_steps": 6710, "loss": 1.2193, "lr": 2.476816334903071e-06, "epoch": 0.30700447093889716, "percentage": 6.14, "elapsed_time": "0:05:30", "remaining_time": "1:24:19", "throughput": 5098.54, "total_tokens": 1687552} {"current_steps": 413, "total_steps": 6710, "loss": 1.2628, "lr": 2.4767040075624644e-06, "epoch": 0.30774962742175854, "percentage": 6.15, "elapsed_time": "0:05:31", "remaining_time": "1:24:18", "throughput": 5098.7, "total_tokens": 1691648} {"current_steps": 414, "total_steps": 6710, "loss": 1.5691, "lr": 2.47659141131958e-06, "epoch": 0.30849478390462, "percentage": 6.17, "elapsed_time": "0:05:32", "remaining_time": "1:24:17", "throughput": 5098.95, "total_tokens": 1695744} {"current_steps": 415, "total_steps": 6710, "loss": 1.4451, "lr": 2.476478546199099e-06, "epoch": 0.30923994038748137, "percentage": 6.18, "elapsed_time": "0:05:33", "remaining_time": "1:24:16", "throughput": 5099.21, "total_tokens": 1699840} {"current_steps": 416, "total_steps": 6710, "loss": 1.5741, "lr": 2.4763654122257635e-06, "epoch": 0.30998509687034276, "percentage": 6.2, "elapsed_time": "0:05:34", "remaining_time": "1:24:15", "throughput": 5099.24, "total_tokens": 1703936} {"current_steps": 417, "total_steps": 6710, "loss": 1.3575, "lr": 2.476252009424372e-06, "epoch": 0.3107302533532042, "percentage": 6.21, "elapsed_time": "0:05:34", "remaining_time": "1:24:14", "throughput": 5099.43, "total_tokens": 1708032} {"current_steps": 418, "total_steps": 6710, "loss": 1.9621, "lr": 2.4761383378197847e-06, "epoch": 0.3114754098360656, "percentage": 6.23, "elapsed_time": "0:05:35", "remaining_time": "1:24:13", "throughput": 5099.72, "total_tokens": 1712128} {"current_steps": 419, "total_steps": 6710, "loss": 1.5874, "lr": 2.4760243974369174e-06, "epoch": 0.312220566318927, "percentage": 6.24, "elapsed_time": "0:05:36", "remaining_time": "1:24:12", "throughput": 5100.05, "total_tokens": 1716224} {"current_steps": 420, "total_steps": 6710, "loss": 1.794, "lr": 2.475910188300748e-06, "epoch": 0.31296572280178836, "percentage": 6.26, "elapsed_time": "0:05:37", "remaining_time": "1:24:11", "throughput": 5100.34, "total_tokens": 1720320} {"current_steps": 421, "total_steps": 6710, "loss": 1.3028, "lr": 2.4757957104363117e-06, "epoch": 0.3137108792846498, "percentage": 6.27, "elapsed_time": "0:05:38", "remaining_time": "1:24:10", "throughput": 5100.64, "total_tokens": 1724416} {"current_steps": 422, "total_steps": 6710, "loss": 1.587, "lr": 2.4756809638687025e-06, "epoch": 0.3144560357675112, "percentage": 6.29, "elapsed_time": "0:05:38", "remaining_time": "1:24:09", "throughput": 5100.97, "total_tokens": 1728512} {"current_steps": 423, "total_steps": 6710, "loss": 1.3168, "lr": 2.475565948623074e-06, "epoch": 0.3152011922503726, "percentage": 6.3, "elapsed_time": "0:05:39", "remaining_time": "1:24:08", "throughput": 5101.3, "total_tokens": 1732608} {"current_steps": 424, "total_steps": 6710, "loss": 1.021, "lr": 2.475450664724638e-06, "epoch": 0.31594634873323396, "percentage": 6.32, "elapsed_time": "0:05:40", "remaining_time": "1:24:06", "throughput": 5101.58, "total_tokens": 1736704} {"current_steps": 425, "total_steps": 6710, "loss": 1.5652, "lr": 2.4753351121986662e-06, "epoch": 0.3166915052160954, "percentage": 6.33, "elapsed_time": "0:05:41", "remaining_time": "1:24:05", "throughput": 5101.88, "total_tokens": 1740800} {"current_steps": 426, "total_steps": 6710, "loss": 0.9005, "lr": 2.4752192910704874e-06, "epoch": 0.3174366616989568, "percentage": 6.35, "elapsed_time": "0:05:41", "remaining_time": "1:24:04", "throughput": 5102.12, "total_tokens": 1744896} {"current_steps": 427, "total_steps": 6710, "loss": 1.1475, "lr": 2.475103201365492e-06, "epoch": 0.3181818181818182, "percentage": 6.36, "elapsed_time": "0:05:42", "remaining_time": "1:24:03", "throughput": 5102.38, "total_tokens": 1748992} {"current_steps": 428, "total_steps": 6710, "loss": 1.3521, "lr": 2.4749868431091265e-06, "epoch": 0.31892697466467956, "percentage": 6.38, "elapsed_time": "0:05:43", "remaining_time": "1:24:02", "throughput": 5102.71, "total_tokens": 1753088} {"current_steps": 429, "total_steps": 6710, "loss": 1.123, "lr": 2.4748702163268977e-06, "epoch": 0.319672131147541, "percentage": 6.39, "elapsed_time": "0:05:44", "remaining_time": "1:24:01", "throughput": 5103.02, "total_tokens": 1757184} {"current_steps": 430, "total_steps": 6710, "loss": 1.3884, "lr": 2.4747533210443714e-06, "epoch": 0.3204172876304024, "percentage": 6.41, "elapsed_time": "0:05:45", "remaining_time": "1:24:00", "throughput": 5103.28, "total_tokens": 1761280} {"current_steps": 431, "total_steps": 6710, "loss": 1.3675, "lr": 2.4746361572871715e-06, "epoch": 0.3211624441132638, "percentage": 6.42, "elapsed_time": "0:05:45", "remaining_time": "1:23:59", "throughput": 5103.56, "total_tokens": 1765376} {"current_steps": 432, "total_steps": 6710, "loss": 1.1608, "lr": 2.474518725080981e-06, "epoch": 0.32190760059612517, "percentage": 6.44, "elapsed_time": "0:05:46", "remaining_time": "1:23:58", "throughput": 5103.81, "total_tokens": 1769472} {"current_steps": 433, "total_steps": 6710, "loss": 1.3447, "lr": 2.474401024451542e-06, "epoch": 0.3226527570789866, "percentage": 6.45, "elapsed_time": "0:05:47", "remaining_time": "1:23:57", "throughput": 5104.05, "total_tokens": 1773568} {"current_steps": 434, "total_steps": 6710, "loss": 1.323, "lr": 2.474283055424656e-06, "epoch": 0.323397913561848, "percentage": 6.47, "elapsed_time": "0:05:48", "remaining_time": "1:23:56", "throughput": 5104.33, "total_tokens": 1777664} {"current_steps": 435, "total_steps": 6710, "loss": 1.698, "lr": 2.474164818026182e-06, "epoch": 0.3241430700447094, "percentage": 6.48, "elapsed_time": "0:05:49", "remaining_time": "1:23:55", "throughput": 5104.63, "total_tokens": 1781760} {"current_steps": 436, "total_steps": 6710, "loss": 1.8131, "lr": 2.474046312282038e-06, "epoch": 0.32488822652757077, "percentage": 6.5, "elapsed_time": "0:05:49", "remaining_time": "1:23:53", "throughput": 5104.95, "total_tokens": 1785856} {"current_steps": 437, "total_steps": 6710, "loss": 1.4422, "lr": 2.473927538218202e-06, "epoch": 0.3256333830104322, "percentage": 6.51, "elapsed_time": "0:05:50", "remaining_time": "1:23:52", "throughput": 5105.19, "total_tokens": 1789952} {"current_steps": 438, "total_steps": 6710, "loss": 1.6463, "lr": 2.4738084958607108e-06, "epoch": 0.3263785394932936, "percentage": 6.53, "elapsed_time": "0:05:51", "remaining_time": "1:23:51", "throughput": 5105.41, "total_tokens": 1794048} {"current_steps": 439, "total_steps": 6710, "loss": 1.3007, "lr": 2.4736891852356575e-06, "epoch": 0.327123695976155, "percentage": 6.54, "elapsed_time": "0:05:52", "remaining_time": "1:23:50", "throughput": 5105.65, "total_tokens": 1798144} {"current_steps": 440, "total_steps": 6710, "loss": 1.5711, "lr": 2.4735696063691975e-06, "epoch": 0.32786885245901637, "percentage": 6.56, "elapsed_time": "0:05:52", "remaining_time": "1:23:49", "throughput": 5105.92, "total_tokens": 1802240} {"current_steps": 441, "total_steps": 6710, "loss": 1.6552, "lr": 2.4734497592875424e-06, "epoch": 0.3286140089418778, "percentage": 6.57, "elapsed_time": "0:05:53", "remaining_time": "1:23:48", "throughput": 5106.22, "total_tokens": 1806336} {"current_steps": 442, "total_steps": 6710, "loss": 1.4643, "lr": 2.473329644016964e-06, "epoch": 0.3293591654247392, "percentage": 6.59, "elapsed_time": "0:05:54", "remaining_time": "1:23:47", "throughput": 5106.52, "total_tokens": 1810432} {"current_steps": 443, "total_steps": 6710, "loss": 1.4656, "lr": 2.4732092605837925e-06, "epoch": 0.3301043219076006, "percentage": 6.6, "elapsed_time": "0:05:55", "remaining_time": "1:23:46", "throughput": 5106.83, "total_tokens": 1814528} {"current_steps": 444, "total_steps": 6710, "loss": 1.247, "lr": 2.4730886090144162e-06, "epoch": 0.33084947839046197, "percentage": 6.62, "elapsed_time": "0:05:56", "remaining_time": "1:23:45", "throughput": 5107.07, "total_tokens": 1818624} {"current_steps": 445, "total_steps": 6710, "loss": 1.6404, "lr": 2.4729676893352835e-06, "epoch": 0.3315946348733234, "percentage": 6.63, "elapsed_time": "0:05:56", "remaining_time": "1:23:44", "throughput": 5107.37, "total_tokens": 1822720} {"current_steps": 446, "total_steps": 6710, "loss": 1.5393, "lr": 2.4728465015729003e-06, "epoch": 0.3323397913561848, "percentage": 6.65, "elapsed_time": "0:05:57", "remaining_time": "1:23:43", "throughput": 5107.68, "total_tokens": 1826816} {"current_steps": 447, "total_steps": 6710, "loss": 1.3715, "lr": 2.472725045753832e-06, "epoch": 0.3330849478390462, "percentage": 6.66, "elapsed_time": "0:05:58", "remaining_time": "1:23:42", "throughput": 5107.98, "total_tokens": 1830912} {"current_steps": 448, "total_steps": 6710, "loss": 1.5113, "lr": 2.472603321904703e-06, "epoch": 0.33383010432190763, "percentage": 6.68, "elapsed_time": "0:05:59", "remaining_time": "1:23:41", "throughput": 5108.15, "total_tokens": 1835008} {"current_steps": 449, "total_steps": 6710, "loss": 1.5703, "lr": 2.4724813300521953e-06, "epoch": 0.334575260804769, "percentage": 6.69, "elapsed_time": "0:06:00", "remaining_time": "1:23:40", "throughput": 5108.42, "total_tokens": 1839104} {"current_steps": 450, "total_steps": 6710, "loss": 1.3687, "lr": 2.472359070223051e-06, "epoch": 0.3353204172876304, "percentage": 6.71, "elapsed_time": "0:06:00", "remaining_time": "1:23:39", "throughput": 5108.71, "total_tokens": 1843200} {"current_steps": 451, "total_steps": 6710, "loss": 1.4196, "lr": 2.47223654244407e-06, "epoch": 0.3360655737704918, "percentage": 6.72, "elapsed_time": "0:06:01", "remaining_time": "1:23:38", "throughput": 5108.93, "total_tokens": 1847296} {"current_steps": 452, "total_steps": 6710, "loss": 1.4345, "lr": 2.4721137467421115e-06, "epoch": 0.33681073025335323, "percentage": 6.74, "elapsed_time": "0:06:02", "remaining_time": "1:23:36", "throughput": 5109.21, "total_tokens": 1851392} {"current_steps": 453, "total_steps": 6710, "loss": 1.2513, "lr": 2.4719906831440926e-06, "epoch": 0.3375558867362146, "percentage": 6.75, "elapsed_time": "0:06:03", "remaining_time": "1:23:35", "throughput": 5109.5, "total_tokens": 1855488} {"current_steps": 454, "total_steps": 6710, "loss": 1.1784, "lr": 2.4718673516769905e-06, "epoch": 0.338301043219076, "percentage": 6.77, "elapsed_time": "0:06:03", "remaining_time": "1:23:34", "throughput": 5109.78, "total_tokens": 1859584} {"current_steps": 455, "total_steps": 6710, "loss": 0.9471, "lr": 2.47174375236784e-06, "epoch": 0.3390461997019374, "percentage": 6.78, "elapsed_time": "0:06:04", "remaining_time": "1:23:33", "throughput": 5110.05, "total_tokens": 1863680} {"current_steps": 456, "total_steps": 6710, "loss": 1.5449, "lr": 2.471619885243735e-06, "epoch": 0.33979135618479883, "percentage": 6.8, "elapsed_time": "0:06:05", "remaining_time": "1:23:32", "throughput": 5110.3, "total_tokens": 1867776} {"current_steps": 457, "total_steps": 6710, "loss": 1.3811, "lr": 2.4714957503318277e-06, "epoch": 0.3405365126676602, "percentage": 6.81, "elapsed_time": "0:06:06", "remaining_time": "1:23:31", "throughput": 5110.56, "total_tokens": 1871872} {"current_steps": 458, "total_steps": 6710, "loss": 1.5398, "lr": 2.4713713476593297e-06, "epoch": 0.3412816691505216, "percentage": 6.83, "elapsed_time": "0:06:07", "remaining_time": "1:23:30", "throughput": 5110.87, "total_tokens": 1875968} {"current_steps": 459, "total_steps": 6710, "loss": 1.3297, "lr": 2.4712466772535114e-06, "epoch": 0.342026825633383, "percentage": 6.84, "elapsed_time": "0:06:07", "remaining_time": "1:23:29", "throughput": 5111.17, "total_tokens": 1880064} {"current_steps": 460, "total_steps": 6710, "loss": 2.1771, "lr": 2.4711217391417003e-06, "epoch": 0.34277198211624443, "percentage": 6.86, "elapsed_time": "0:06:08", "remaining_time": "1:23:28", "throughput": 5111.43, "total_tokens": 1884160} {"current_steps": 461, "total_steps": 6710, "loss": 1.4106, "lr": 2.4709965333512846e-06, "epoch": 0.3435171385991058, "percentage": 6.87, "elapsed_time": "0:06:09", "remaining_time": "1:23:27", "throughput": 5111.69, "total_tokens": 1888256} {"current_steps": 462, "total_steps": 6710, "loss": 1.2218, "lr": 2.4708710599097105e-06, "epoch": 0.3442622950819672, "percentage": 6.89, "elapsed_time": "0:06:10", "remaining_time": "1:23:26", "throughput": 5111.9, "total_tokens": 1892352} {"current_steps": 463, "total_steps": 6710, "loss": 1.2774, "lr": 2.470745318844482e-06, "epoch": 0.3450074515648286, "percentage": 6.9, "elapsed_time": "0:06:10", "remaining_time": "1:23:25", "throughput": 5112.09, "total_tokens": 1896448} {"current_steps": 464, "total_steps": 6710, "loss": 1.4884, "lr": 2.470619310183163e-06, "epoch": 0.34575260804769004, "percentage": 6.92, "elapsed_time": "0:06:11", "remaining_time": "1:23:24", "throughput": 5112.33, "total_tokens": 1900544} {"current_steps": 465, "total_steps": 6710, "loss": 1.2903, "lr": 2.4704930339533745e-06, "epoch": 0.3464977645305514, "percentage": 6.93, "elapsed_time": "0:06:12", "remaining_time": "1:23:23", "throughput": 5112.58, "total_tokens": 1904640} {"current_steps": 466, "total_steps": 6710, "loss": 1.3325, "lr": 2.4703664901827985e-06, "epoch": 0.3472429210134128, "percentage": 6.94, "elapsed_time": "0:06:13", "remaining_time": "1:23:22", "throughput": 5112.85, "total_tokens": 1908736} {"current_steps": 467, "total_steps": 6710, "loss": 1.401, "lr": 2.4702396788991736e-06, "epoch": 0.3479880774962742, "percentage": 6.96, "elapsed_time": "0:06:14", "remaining_time": "1:23:21", "throughput": 5113.1, "total_tokens": 1912832} {"current_steps": 468, "total_steps": 6710, "loss": 1.421, "lr": 2.4701126001302972e-06, "epoch": 0.34873323397913564, "percentage": 6.97, "elapsed_time": "0:06:14", "remaining_time": "1:23:20", "throughput": 5113.28, "total_tokens": 1916928} {"current_steps": 469, "total_steps": 6710, "loss": 1.3461, "lr": 2.469985253904027e-06, "epoch": 0.349478390461997, "percentage": 6.99, "elapsed_time": "0:06:15", "remaining_time": "1:23:19", "throughput": 5113.55, "total_tokens": 1921024} {"current_steps": 470, "total_steps": 6710, "loss": 1.3228, "lr": 2.4698576402482776e-06, "epoch": 0.3502235469448584, "percentage": 7.0, "elapsed_time": "0:06:16", "remaining_time": "1:23:18", "throughput": 5113.81, "total_tokens": 1925120} {"current_steps": 471, "total_steps": 6710, "loss": 1.4832, "lr": 2.469729759191023e-06, "epoch": 0.3509687034277198, "percentage": 7.02, "elapsed_time": "0:06:17", "remaining_time": "1:23:16", "throughput": 5114.08, "total_tokens": 1929216} {"current_steps": 472, "total_steps": 6710, "loss": 1.5615, "lr": 2.4696016107602957e-06, "epoch": 0.35171385991058124, "percentage": 7.03, "elapsed_time": "0:06:18", "remaining_time": "1:23:15", "throughput": 5114.31, "total_tokens": 1933312} {"current_steps": 473, "total_steps": 6710, "loss": 1.2009, "lr": 2.469473194984186e-06, "epoch": 0.3524590163934426, "percentage": 7.05, "elapsed_time": "0:06:18", "remaining_time": "1:23:14", "throughput": 5114.58, "total_tokens": 1937408} {"current_steps": 474, "total_steps": 6710, "loss": 1.4042, "lr": 2.4693445118908445e-06, "epoch": 0.353204172876304, "percentage": 7.06, "elapsed_time": "0:06:19", "remaining_time": "1:23:13", "throughput": 5114.74, "total_tokens": 1941504} {"current_steps": 475, "total_steps": 6710, "loss": 1.4482, "lr": 2.469215561508479e-06, "epoch": 0.3539493293591654, "percentage": 7.08, "elapsed_time": "0:06:20", "remaining_time": "1:23:13", "throughput": 5114.83, "total_tokens": 1945600} {"current_steps": 476, "total_steps": 6710, "loss": 1.3643, "lr": 2.4690863438653563e-06, "epoch": 0.35469448584202684, "percentage": 7.09, "elapsed_time": "0:06:21", "remaining_time": "1:23:12", "throughput": 5114.95, "total_tokens": 1949696} {"current_steps": 477, "total_steps": 6710, "loss": 1.6095, "lr": 2.468956858989802e-06, "epoch": 0.3554396423248882, "percentage": 7.11, "elapsed_time": "0:06:21", "remaining_time": "1:23:11", "throughput": 5115.14, "total_tokens": 1953792} {"current_steps": 478, "total_steps": 6710, "loss": 1.5309, "lr": 2.4688271069102003e-06, "epoch": 0.3561847988077496, "percentage": 7.12, "elapsed_time": "0:06:22", "remaining_time": "1:23:10", "throughput": 5115.35, "total_tokens": 1957888} {"current_steps": 479, "total_steps": 6710, "loss": 1.4163, "lr": 2.4686970876549935e-06, "epoch": 0.356929955290611, "percentage": 7.14, "elapsed_time": "0:06:23", "remaining_time": "1:23:09", "throughput": 5115.44, "total_tokens": 1961984} {"current_steps": 480, "total_steps": 6710, "loss": 1.6612, "lr": 2.4685668012526828e-06, "epoch": 0.35767511177347244, "percentage": 7.15, "elapsed_time": "0:06:24", "remaining_time": "1:23:08", "throughput": 5115.36, "total_tokens": 1966080} {"current_steps": 481, "total_steps": 6710, "loss": 1.225, "lr": 2.468436247731828e-06, "epoch": 0.35842026825633383, "percentage": 7.17, "elapsed_time": "0:06:25", "remaining_time": "1:23:07", "throughput": 5115.6, "total_tokens": 1970176} {"current_steps": 482, "total_steps": 6710, "loss": 1.4525, "lr": 2.468305427121047e-06, "epoch": 0.3591654247391952, "percentage": 7.18, "elapsed_time": "0:06:25", "remaining_time": "1:23:06", "throughput": 5115.82, "total_tokens": 1974272} {"current_steps": 483, "total_steps": 6710, "loss": 1.4807, "lr": 2.468174339449017e-06, "epoch": 0.35991058122205666, "percentage": 7.2, "elapsed_time": "0:06:26", "remaining_time": "1:23:05", "throughput": 5116.08, "total_tokens": 1978368} {"current_steps": 484, "total_steps": 6710, "loss": 1.3893, "lr": 2.4680429847444738e-06, "epoch": 0.36065573770491804, "percentage": 7.21, "elapsed_time": "0:06:27", "remaining_time": "1:23:04", "throughput": 5116.33, "total_tokens": 1982464} {"current_steps": 485, "total_steps": 6710, "loss": 1.6122, "lr": 2.46791136303621e-06, "epoch": 0.36140089418777943, "percentage": 7.23, "elapsed_time": "0:06:28", "remaining_time": "1:23:03", "throughput": 5116.59, "total_tokens": 1986560} {"current_steps": 486, "total_steps": 6710, "loss": 1.6938, "lr": 2.467779474353079e-06, "epoch": 0.3621460506706408, "percentage": 7.24, "elapsed_time": "0:06:29", "remaining_time": "1:23:02", "throughput": 5116.78, "total_tokens": 1990656} {"current_steps": 487, "total_steps": 6710, "loss": 1.249, "lr": 2.4676473187239915e-06, "epoch": 0.36289120715350226, "percentage": 7.26, "elapsed_time": "0:06:29", "remaining_time": "1:23:01", "throughput": 5117.03, "total_tokens": 1994752} {"current_steps": 488, "total_steps": 6710, "loss": 1.3806, "lr": 2.467514896177917e-06, "epoch": 0.36363636363636365, "percentage": 7.27, "elapsed_time": "0:06:30", "remaining_time": "1:23:00", "throughput": 5117.2, "total_tokens": 1998848} {"current_steps": 489, "total_steps": 6710, "loss": 1.5156, "lr": 2.4673822067438833e-06, "epoch": 0.36438152011922503, "percentage": 7.29, "elapsed_time": "0:06:31", "remaining_time": "1:22:59", "throughput": 5117.46, "total_tokens": 2002944} {"current_steps": 490, "total_steps": 6710, "loss": 1.3477, "lr": 2.4672492504509773e-06, "epoch": 0.3651266766020864, "percentage": 7.3, "elapsed_time": "0:06:32", "remaining_time": "1:22:58", "throughput": 5117.68, "total_tokens": 2007040} {"current_steps": 491, "total_steps": 6710, "loss": 1.6865, "lr": 2.4671160273283433e-06, "epoch": 0.36587183308494786, "percentage": 7.32, "elapsed_time": "0:06:32", "remaining_time": "1:22:57", "throughput": 5117.92, "total_tokens": 2011136} {"current_steps": 492, "total_steps": 6710, "loss": 1.2314, "lr": 2.4669825374051853e-06, "epoch": 0.36661698956780925, "percentage": 7.33, "elapsed_time": "0:06:33", "remaining_time": "1:22:56", "throughput": 5118.11, "total_tokens": 2015232} {"current_steps": 493, "total_steps": 6710, "loss": 1.4593, "lr": 2.4668487807107654e-06, "epoch": 0.36736214605067063, "percentage": 7.35, "elapsed_time": "0:06:34", "remaining_time": "1:22:55", "throughput": 5118.35, "total_tokens": 2019328} {"current_steps": 494, "total_steps": 6710, "loss": 1.4163, "lr": 2.466714757274403e-06, "epoch": 0.368107302533532, "percentage": 7.36, "elapsed_time": "0:06:35", "remaining_time": "1:22:54", "throughput": 5118.54, "total_tokens": 2023424} {"current_steps": 495, "total_steps": 6710, "loss": 1.3205, "lr": 2.4665804671254784e-06, "epoch": 0.36885245901639346, "percentage": 7.38, "elapsed_time": "0:06:36", "remaining_time": "1:22:53", "throughput": 5118.75, "total_tokens": 2027520} {"current_steps": 496, "total_steps": 6710, "loss": 1.4007, "lr": 2.466445910293428e-06, "epoch": 0.36959761549925485, "percentage": 7.39, "elapsed_time": "0:06:36", "remaining_time": "1:22:52", "throughput": 5119.0, "total_tokens": 2031616} {"current_steps": 497, "total_steps": 6710, "loss": 1.523, "lr": 2.4663110868077478e-06, "epoch": 0.37034277198211624, "percentage": 7.41, "elapsed_time": "0:06:37", "remaining_time": "1:22:51", "throughput": 5119.23, "total_tokens": 2035712} {"current_steps": 498, "total_steps": 6710, "loss": 1.4062, "lr": 2.466175996697992e-06, "epoch": 0.3710879284649776, "percentage": 7.42, "elapsed_time": "0:06:38", "remaining_time": "1:22:50", "throughput": 5119.46, "total_tokens": 2039808} {"current_steps": 499, "total_steps": 6710, "loss": 1.1439, "lr": 2.4660406399937737e-06, "epoch": 0.37183308494783907, "percentage": 7.44, "elapsed_time": "0:06:39", "remaining_time": "1:22:49", "throughput": 5119.71, "total_tokens": 2043904} {"current_steps": 500, "total_steps": 6710, "loss": 1.1165, "lr": 2.4659050167247633e-06, "epoch": 0.37257824143070045, "percentage": 7.45, "elapsed_time": "0:06:40", "remaining_time": "1:22:48", "throughput": 5119.97, "total_tokens": 2048000} {"current_steps": 501, "total_steps": 6710, "loss": 1.2341, "lr": 2.465769126920691e-06, "epoch": 0.37332339791356184, "percentage": 7.47, "elapsed_time": "0:06:40", "remaining_time": "1:22:46", "throughput": 5120.21, "total_tokens": 2052096} {"current_steps": 502, "total_steps": 6710, "loss": 1.3726, "lr": 2.4656329706113453e-06, "epoch": 0.3740685543964232, "percentage": 7.48, "elapsed_time": "0:06:41", "remaining_time": "1:22:45", "throughput": 5120.46, "total_tokens": 2056192} {"current_steps": 503, "total_steps": 6710, "loss": 1.3128, "lr": 2.465496547826572e-06, "epoch": 0.37481371087928467, "percentage": 7.5, "elapsed_time": "0:06:42", "remaining_time": "1:22:44", "throughput": 5120.69, "total_tokens": 2060288} {"current_steps": 504, "total_steps": 6710, "loss": 1.4912, "lr": 2.465359858596275e-06, "epoch": 0.37555886736214605, "percentage": 7.51, "elapsed_time": "0:06:43", "remaining_time": "1:22:43", "throughput": 5120.92, "total_tokens": 2064384} {"current_steps": 505, "total_steps": 6710, "loss": 1.2561, "lr": 2.46522290295042e-06, "epoch": 0.37630402384500744, "percentage": 7.53, "elapsed_time": "0:06:43", "remaining_time": "1:22:42", "throughput": 5121.16, "total_tokens": 2068480} {"current_steps": 506, "total_steps": 6710, "loss": 1.5411, "lr": 2.465085680919026e-06, "epoch": 0.3770491803278688, "percentage": 7.54, "elapsed_time": "0:06:44", "remaining_time": "1:22:41", "throughput": 5121.37, "total_tokens": 2072576} {"current_steps": 507, "total_steps": 6710, "loss": 1.2335, "lr": 2.464948192532175e-06, "epoch": 0.37779433681073027, "percentage": 7.56, "elapsed_time": "0:06:45", "remaining_time": "1:22:40", "throughput": 5121.6, "total_tokens": 2076672} {"current_steps": 508, "total_steps": 6710, "loss": 1.375, "lr": 2.4648104378200043e-06, "epoch": 0.37853949329359166, "percentage": 7.57, "elapsed_time": "0:06:46", "remaining_time": "1:22:39", "throughput": 5121.83, "total_tokens": 2080768} {"current_steps": 509, "total_steps": 6710, "loss": 1.2086, "lr": 2.4646724168127114e-06, "epoch": 0.37928464977645304, "percentage": 7.59, "elapsed_time": "0:06:47", "remaining_time": "1:22:38", "throughput": 5122.01, "total_tokens": 2084864} {"current_steps": 510, "total_steps": 6710, "loss": 1.3022, "lr": 2.464534129540551e-06, "epoch": 0.38002980625931443, "percentage": 7.6, "elapsed_time": "0:06:47", "remaining_time": "1:22:37", "throughput": 5122.18, "total_tokens": 2088960} {"current_steps": 511, "total_steps": 6710, "loss": 1.3279, "lr": 2.4643955760338365e-06, "epoch": 0.38077496274217587, "percentage": 7.62, "elapsed_time": "0:06:48", "remaining_time": "1:22:36", "throughput": 5122.37, "total_tokens": 2093056} {"current_steps": 512, "total_steps": 6710, "loss": 1.3924, "lr": 2.4642567563229407e-06, "epoch": 0.38152011922503726, "percentage": 7.63, "elapsed_time": "0:06:49", "remaining_time": "1:22:35", "throughput": 5122.59, "total_tokens": 2097152} {"current_steps": 513, "total_steps": 6710, "loss": 1.5393, "lr": 2.464117670438293e-06, "epoch": 0.38226527570789864, "percentage": 7.65, "elapsed_time": "0:06:50", "remaining_time": "1:22:34", "throughput": 5122.79, "total_tokens": 2101248} {"current_steps": 514, "total_steps": 6710, "loss": 1.3122, "lr": 2.4639783184103828e-06, "epoch": 0.3830104321907601, "percentage": 7.66, "elapsed_time": "0:06:50", "remaining_time": "1:22:33", "throughput": 5123.02, "total_tokens": 2105344} {"current_steps": 515, "total_steps": 6710, "loss": 1.7126, "lr": 2.4638387002697565e-06, "epoch": 0.3837555886736215, "percentage": 7.68, "elapsed_time": "0:06:51", "remaining_time": "1:22:32", "throughput": 5123.26, "total_tokens": 2109440} {"current_steps": 516, "total_steps": 6710, "loss": 1.3359, "lr": 2.4636988160470194e-06, "epoch": 0.38450074515648286, "percentage": 7.69, "elapsed_time": "0:06:52", "remaining_time": "1:22:31", "throughput": 5123.49, "total_tokens": 2113536} {"current_steps": 517, "total_steps": 6710, "loss": 1.5919, "lr": 2.463558665772835e-06, "epoch": 0.38524590163934425, "percentage": 7.7, "elapsed_time": "0:06:53", "remaining_time": "1:22:30", "throughput": 5123.68, "total_tokens": 2117632} {"current_steps": 518, "total_steps": 6710, "loss": 1.4738, "lr": 2.4634182494779257e-06, "epoch": 0.3859910581222057, "percentage": 7.72, "elapsed_time": "0:06:54", "remaining_time": "1:22:29", "throughput": 5123.84, "total_tokens": 2121728} {"current_steps": 519, "total_steps": 6710, "loss": 1.5325, "lr": 2.4632775671930717e-06, "epoch": 0.3867362146050671, "percentage": 7.73, "elapsed_time": "0:06:54", "remaining_time": "1:22:28", "throughput": 5124.04, "total_tokens": 2125824} {"current_steps": 520, "total_steps": 6710, "loss": 1.511, "lr": 2.4631366189491112e-06, "epoch": 0.38748137108792846, "percentage": 7.75, "elapsed_time": "0:06:55", "remaining_time": "1:22:27", "throughput": 5124.21, "total_tokens": 2129920} {"current_steps": 521, "total_steps": 6710, "loss": 1.3882, "lr": 2.462995404776941e-06, "epoch": 0.38822652757078985, "percentage": 7.76, "elapsed_time": "0:06:56", "remaining_time": "1:22:26", "throughput": 5124.4, "total_tokens": 2134016} {"current_steps": 522, "total_steps": 6710, "loss": 1.4353, "lr": 2.462853924707517e-06, "epoch": 0.3889716840536513, "percentage": 7.78, "elapsed_time": "0:06:57", "remaining_time": "1:22:25", "throughput": 5124.56, "total_tokens": 2138112} {"current_steps": 523, "total_steps": 6710, "loss": 1.6179, "lr": 2.462712178771852e-06, "epoch": 0.3897168405365127, "percentage": 7.79, "elapsed_time": "0:06:58", "remaining_time": "1:22:25", "throughput": 5124.74, "total_tokens": 2142208} {"current_steps": 524, "total_steps": 6710, "loss": 1.3083, "lr": 2.462570167001018e-06, "epoch": 0.39046199701937406, "percentage": 7.81, "elapsed_time": "0:06:58", "remaining_time": "1:22:24", "throughput": 5124.93, "total_tokens": 2146304} {"current_steps": 525, "total_steps": 6710, "loss": 1.2218, "lr": 2.4624278894261446e-06, "epoch": 0.39120715350223545, "percentage": 7.82, "elapsed_time": "0:06:59", "remaining_time": "1:22:23", "throughput": 5124.99, "total_tokens": 2150400} {"current_steps": 526, "total_steps": 6710, "loss": 1.2524, "lr": 2.4622853460784205e-06, "epoch": 0.3919523099850969, "percentage": 7.84, "elapsed_time": "0:07:00", "remaining_time": "1:22:22", "throughput": 5125.16, "total_tokens": 2154496} {"current_steps": 527, "total_steps": 6710, "loss": 1.3151, "lr": 2.462142536989092e-06, "epoch": 0.3926974664679583, "percentage": 7.85, "elapsed_time": "0:07:01", "remaining_time": "1:22:21", "throughput": 5125.38, "total_tokens": 2158592} {"current_steps": 528, "total_steps": 6710, "loss": 1.3512, "lr": 2.4619994621894638e-06, "epoch": 0.39344262295081966, "percentage": 7.87, "elapsed_time": "0:07:01", "remaining_time": "1:22:20", "throughput": 5125.59, "total_tokens": 2162688} {"current_steps": 529, "total_steps": 6710, "loss": 1.3919, "lr": 2.4618561217108996e-06, "epoch": 0.39418777943368105, "percentage": 7.88, "elapsed_time": "0:07:02", "remaining_time": "1:22:19", "throughput": 5125.8, "total_tokens": 2166784} {"current_steps": 530, "total_steps": 6710, "loss": 1.2302, "lr": 2.4617125155848193e-06, "epoch": 0.3949329359165425, "percentage": 7.9, "elapsed_time": "0:07:03", "remaining_time": "1:22:18", "throughput": 5126.03, "total_tokens": 2170880} {"current_steps": 531, "total_steps": 6710, "loss": 1.3854, "lr": 2.4615686438427035e-06, "epoch": 0.3956780923994039, "percentage": 7.91, "elapsed_time": "0:07:04", "remaining_time": "1:22:17", "throughput": 5126.26, "total_tokens": 2174976} {"current_steps": 532, "total_steps": 6710, "loss": 1.4646, "lr": 2.4614245065160896e-06, "epoch": 0.39642324888226527, "percentage": 7.93, "elapsed_time": "0:07:05", "remaining_time": "1:22:16", "throughput": 5126.45, "total_tokens": 2179072} {"current_steps": 533, "total_steps": 6710, "loss": 1.5803, "lr": 2.4612801036365736e-06, "epoch": 0.39716840536512665, "percentage": 7.94, "elapsed_time": "0:07:05", "remaining_time": "1:22:15", "throughput": 5126.63, "total_tokens": 2183168} {"current_steps": 534, "total_steps": 6710, "loss": 1.3156, "lr": 2.4611354352358097e-06, "epoch": 0.3979135618479881, "percentage": 7.96, "elapsed_time": "0:07:06", "remaining_time": "1:22:14", "throughput": 5126.85, "total_tokens": 2187264} {"current_steps": 535, "total_steps": 6710, "loss": 1.5557, "lr": 2.46099050134551e-06, "epoch": 0.3986587183308495, "percentage": 7.97, "elapsed_time": "0:07:07", "remaining_time": "1:22:13", "throughput": 5127.03, "total_tokens": 2191360} {"current_steps": 536, "total_steps": 6710, "loss": 1.7731, "lr": 2.460845301997445e-06, "epoch": 0.39940387481371087, "percentage": 7.99, "elapsed_time": "0:07:08", "remaining_time": "1:22:12", "throughput": 5127.21, "total_tokens": 2195456} {"current_steps": 537, "total_steps": 6710, "loss": 1.0355, "lr": 2.4606998372234436e-06, "epoch": 0.40014903129657226, "percentage": 8.0, "elapsed_time": "0:07:08", "remaining_time": "1:22:11", "throughput": 5127.4, "total_tokens": 2199552} {"current_steps": 538, "total_steps": 6710, "loss": 1.1422, "lr": 2.460554107055393e-06, "epoch": 0.4008941877794337, "percentage": 8.02, "elapsed_time": "0:07:09", "remaining_time": "1:22:10", "throughput": 5127.6, "total_tokens": 2203648} {"current_steps": 539, "total_steps": 6710, "loss": 1.2464, "lr": 2.4604081115252376e-06, "epoch": 0.4016393442622951, "percentage": 8.03, "elapsed_time": "0:07:10", "remaining_time": "1:22:09", "throughput": 5127.78, "total_tokens": 2207744} {"current_steps": 540, "total_steps": 6710, "loss": 1.3075, "lr": 2.4602618506649813e-06, "epoch": 0.40238450074515647, "percentage": 8.05, "elapsed_time": "0:07:11", "remaining_time": "1:22:08", "throughput": 5127.89, "total_tokens": 2211840} {"current_steps": 541, "total_steps": 6710, "loss": 1.1862, "lr": 2.4601153245066854e-06, "epoch": 0.40312965722801786, "percentage": 8.06, "elapsed_time": "0:07:12", "remaining_time": "1:22:07", "throughput": 5128.05, "total_tokens": 2215936} {"current_steps": 542, "total_steps": 6710, "loss": 1.1412, "lr": 2.459968533082469e-06, "epoch": 0.4038748137108793, "percentage": 8.08, "elapsed_time": "0:07:12", "remaining_time": "1:22:06", "throughput": 5128.19, "total_tokens": 2220032} {"current_steps": 543, "total_steps": 6710, "loss": 1.1007, "lr": 2.4598214764245106e-06, "epoch": 0.4046199701937407, "percentage": 8.09, "elapsed_time": "0:07:13", "remaining_time": "1:22:05", "throughput": 5128.39, "total_tokens": 2224128} {"current_steps": 544, "total_steps": 6710, "loss": 1.5582, "lr": 2.4596741545650455e-06, "epoch": 0.40536512667660207, "percentage": 8.11, "elapsed_time": "0:07:14", "remaining_time": "1:22:04", "throughput": 5128.58, "total_tokens": 2228224} {"current_steps": 545, "total_steps": 6710, "loss": 1.4454, "lr": 2.4595265675363678e-06, "epoch": 0.4061102831594635, "percentage": 8.12, "elapsed_time": "0:07:15", "remaining_time": "1:22:03", "throughput": 5128.78, "total_tokens": 2232320} {"current_steps": 546, "total_steps": 6710, "loss": 0.9828, "lr": 2.45937871537083e-06, "epoch": 0.4068554396423249, "percentage": 8.14, "elapsed_time": "0:07:16", "remaining_time": "1:22:02", "throughput": 5128.97, "total_tokens": 2236416} {"current_steps": 547, "total_steps": 6710, "loss": 1.3441, "lr": 2.4592305981008417e-06, "epoch": 0.4076005961251863, "percentage": 8.15, "elapsed_time": "0:07:16", "remaining_time": "1:22:01", "throughput": 5129.18, "total_tokens": 2240512} {"current_steps": 548, "total_steps": 6710, "loss": 1.4857, "lr": 2.459082215758872e-06, "epoch": 0.4083457526080477, "percentage": 8.17, "elapsed_time": "0:07:17", "remaining_time": "1:22:00", "throughput": 5129.41, "total_tokens": 2244608} {"current_steps": 549, "total_steps": 6710, "loss": 1.5338, "lr": 2.458933568377447e-06, "epoch": 0.4090909090909091, "percentage": 8.18, "elapsed_time": "0:07:18", "remaining_time": "1:21:59", "throughput": 5129.59, "total_tokens": 2248704} {"current_steps": 550, "total_steps": 6710, "loss": 1.4245, "lr": 2.4587846559891507e-06, "epoch": 0.4098360655737705, "percentage": 8.2, "elapsed_time": "0:07:19", "remaining_time": "1:21:58", "throughput": 5129.77, "total_tokens": 2252800} {"current_steps": 551, "total_steps": 6710, "loss": 1.1714, "lr": 2.4586354786266263e-06, "epoch": 0.4105812220566319, "percentage": 8.21, "elapsed_time": "0:07:19", "remaining_time": "1:21:57", "throughput": 5129.93, "total_tokens": 2256896} {"current_steps": 552, "total_steps": 6710, "loss": 1.1984, "lr": 2.458486036322575e-06, "epoch": 0.4113263785394933, "percentage": 8.23, "elapsed_time": "0:07:20", "remaining_time": "1:21:56", "throughput": 5130.13, "total_tokens": 2260992} {"current_steps": 553, "total_steps": 6710, "loss": 1.3793, "lr": 2.458336329109755e-06, "epoch": 0.4120715350223547, "percentage": 8.24, "elapsed_time": "0:07:21", "remaining_time": "1:21:55", "throughput": 5130.27, "total_tokens": 2265088} {"current_steps": 554, "total_steps": 6710, "loss": 1.236, "lr": 2.4581863570209835e-06, "epoch": 0.4128166915052161, "percentage": 8.26, "elapsed_time": "0:07:22", "remaining_time": "1:21:54", "throughput": 5130.47, "total_tokens": 2269184} {"current_steps": 555, "total_steps": 6710, "loss": 1.4198, "lr": 2.458036120089135e-06, "epoch": 0.4135618479880775, "percentage": 8.27, "elapsed_time": "0:07:23", "remaining_time": "1:21:53", "throughput": 5130.66, "total_tokens": 2273280} {"current_steps": 556, "total_steps": 6710, "loss": 1.5225, "lr": 2.4578856183471433e-06, "epoch": 0.4143070044709389, "percentage": 8.29, "elapsed_time": "0:07:23", "remaining_time": "1:21:52", "throughput": 5130.82, "total_tokens": 2277376} {"current_steps": 557, "total_steps": 6710, "loss": 1.125, "lr": 2.457734851827999e-06, "epoch": 0.4150521609538003, "percentage": 8.3, "elapsed_time": "0:07:24", "remaining_time": "1:21:51", "throughput": 5131.02, "total_tokens": 2281472} {"current_steps": 558, "total_steps": 6710, "loss": 1.1746, "lr": 2.4575838205647505e-06, "epoch": 0.4157973174366617, "percentage": 8.32, "elapsed_time": "0:07:25", "remaining_time": "1:21:50", "throughput": 5131.2, "total_tokens": 2285568} {"current_steps": 559, "total_steps": 6710, "loss": 1.4708, "lr": 2.4574325245905063e-06, "epoch": 0.4165424739195231, "percentage": 8.33, "elapsed_time": "0:07:26", "remaining_time": "1:21:49", "throughput": 5131.4, "total_tokens": 2289664} {"current_steps": 560, "total_steps": 6710, "loss": 1.4515, "lr": 2.4572809639384306e-06, "epoch": 0.4172876304023845, "percentage": 8.35, "elapsed_time": "0:07:26", "remaining_time": "1:21:48", "throughput": 5131.53, "total_tokens": 2293760} {"current_steps": 561, "total_steps": 6710, "loss": 2.2347, "lr": 2.457129138641747e-06, "epoch": 0.4180327868852459, "percentage": 8.36, "elapsed_time": "0:07:27", "remaining_time": "1:21:47", "throughput": 5131.75, "total_tokens": 2297856} {"current_steps": 562, "total_steps": 6710, "loss": 1.5675, "lr": 2.4569770487337365e-06, "epoch": 0.4187779433681073, "percentage": 8.38, "elapsed_time": "0:07:28", "remaining_time": "1:21:46", "throughput": 5131.92, "total_tokens": 2301952} {"current_steps": 563, "total_steps": 6710, "loss": 1.5482, "lr": 2.456824694247738e-06, "epoch": 0.4195230998509687, "percentage": 8.39, "elapsed_time": "0:07:29", "remaining_time": "1:21:46", "throughput": 5132.08, "total_tokens": 2306048} {"current_steps": 564, "total_steps": 6710, "loss": 1.3036, "lr": 2.4566720752171493e-06, "epoch": 0.4202682563338301, "percentage": 8.41, "elapsed_time": "0:07:30", "remaining_time": "1:21:45", "throughput": 5132.24, "total_tokens": 2310144} {"current_steps": 565, "total_steps": 6710, "loss": 1.3679, "lr": 2.4565191916754257e-06, "epoch": 0.4210134128166915, "percentage": 8.42, "elapsed_time": "0:07:30", "remaining_time": "1:21:44", "throughput": 5132.41, "total_tokens": 2314240} {"current_steps": 566, "total_steps": 6710, "loss": 1.3813, "lr": 2.456366043656079e-06, "epoch": 0.4217585692995529, "percentage": 8.44, "elapsed_time": "0:07:31", "remaining_time": "1:21:43", "throughput": 5132.56, "total_tokens": 2318336} {"current_steps": 567, "total_steps": 6710, "loss": 1.2034, "lr": 2.456212631192682e-06, "epoch": 0.4225037257824143, "percentage": 8.45, "elapsed_time": "0:07:32", "remaining_time": "1:21:42", "throughput": 5132.7, "total_tokens": 2322432} {"current_steps": 568, "total_steps": 6710, "loss": 1.5088, "lr": 2.456058954318863e-06, "epoch": 0.4232488822652757, "percentage": 8.46, "elapsed_time": "0:07:33", "remaining_time": "1:21:41", "throughput": 5132.76, "total_tokens": 2326528} {"current_steps": 569, "total_steps": 6710, "loss": 1.2647, "lr": 2.4559050130683093e-06, "epoch": 0.4239940387481371, "percentage": 8.48, "elapsed_time": "0:07:34", "remaining_time": "1:21:40", "throughput": 5132.93, "total_tokens": 2330624} {"current_steps": 570, "total_steps": 6710, "loss": 1.3038, "lr": 2.4557508074747656e-06, "epoch": 0.4247391952309985, "percentage": 8.49, "elapsed_time": "0:07:34", "remaining_time": "1:21:39", "throughput": 5133.08, "total_tokens": 2334720} {"current_steps": 571, "total_steps": 6710, "loss": 1.3381, "lr": 2.455596337572035e-06, "epoch": 0.4254843517138599, "percentage": 8.51, "elapsed_time": "0:07:35", "remaining_time": "1:21:38", "throughput": 5133.25, "total_tokens": 2338816} {"current_steps": 572, "total_steps": 6710, "loss": 1.5287, "lr": 2.455441603393979e-06, "epoch": 0.4262295081967213, "percentage": 8.52, "elapsed_time": "0:07:36", "remaining_time": "1:21:37", "throughput": 5133.38, "total_tokens": 2342912} {"current_steps": 573, "total_steps": 6710, "loss": 1.5204, "lr": 2.455286604974515e-06, "epoch": 0.4269746646795827, "percentage": 8.54, "elapsed_time": "0:07:37", "remaining_time": "1:21:36", "throughput": 5133.5, "total_tokens": 2347008} {"current_steps": 574, "total_steps": 6710, "loss": 1.797, "lr": 2.4551313423476215e-06, "epoch": 0.4277198211624441, "percentage": 8.55, "elapsed_time": "0:07:37", "remaining_time": "1:21:35", "throughput": 5133.63, "total_tokens": 2351104} {"current_steps": 575, "total_steps": 6710, "loss": 1.4357, "lr": 2.4549758155473318e-06, "epoch": 0.4284649776453055, "percentage": 8.57, "elapsed_time": "0:07:38", "remaining_time": "1:21:34", "throughput": 5133.78, "total_tokens": 2355200} {"current_steps": 576, "total_steps": 6710, "loss": 1.1528, "lr": 2.4548200246077394e-06, "epoch": 0.42921013412816694, "percentage": 8.58, "elapsed_time": "0:07:39", "remaining_time": "1:21:33", "throughput": 5133.89, "total_tokens": 2359296} {"current_steps": 577, "total_steps": 6710, "loss": 1.4596, "lr": 2.454663969562994e-06, "epoch": 0.42995529061102833, "percentage": 8.6, "elapsed_time": "0:07:40", "remaining_time": "1:21:33", "throughput": 5134.0, "total_tokens": 2363392} {"current_steps": 578, "total_steps": 6710, "loss": 1.3362, "lr": 2.454507650447305e-06, "epoch": 0.4307004470938897, "percentage": 8.61, "elapsed_time": "0:07:41", "remaining_time": "1:21:32", "throughput": 5134.13, "total_tokens": 2367488} {"current_steps": 579, "total_steps": 6710, "loss": 1.4502, "lr": 2.454351067294938e-06, "epoch": 0.4314456035767511, "percentage": 8.63, "elapsed_time": "0:07:41", "remaining_time": "1:21:31", "throughput": 5134.29, "total_tokens": 2371584} {"current_steps": 580, "total_steps": 6710, "loss": 1.5816, "lr": 2.4541942201402165e-06, "epoch": 0.43219076005961254, "percentage": 8.64, "elapsed_time": "0:07:42", "remaining_time": "1:21:30", "throughput": 5134.46, "total_tokens": 2375680} {"current_steps": 581, "total_steps": 6710, "loss": 1.3506, "lr": 2.454037109017524e-06, "epoch": 0.43293591654247393, "percentage": 8.66, "elapsed_time": "0:07:43", "remaining_time": "1:21:29", "throughput": 5134.63, "total_tokens": 2379776} {"current_steps": 582, "total_steps": 6710, "loss": 1.5274, "lr": 2.453879733961299e-06, "epoch": 0.4336810730253353, "percentage": 8.67, "elapsed_time": "0:07:44", "remaining_time": "1:21:28", "throughput": 5134.8, "total_tokens": 2383872} {"current_steps": 583, "total_steps": 6710, "loss": 1.3867, "lr": 2.4537220950060403e-06, "epoch": 0.4344262295081967, "percentage": 8.69, "elapsed_time": "0:07:45", "remaining_time": "1:21:27", "throughput": 5134.96, "total_tokens": 2387968} {"current_steps": 584, "total_steps": 6710, "loss": 1.5162, "lr": 2.453564192186303e-06, "epoch": 0.43517138599105815, "percentage": 8.7, "elapsed_time": "0:07:45", "remaining_time": "1:21:26", "throughput": 5135.11, "total_tokens": 2392064} {"current_steps": 585, "total_steps": 6710, "loss": 1.2941, "lr": 2.4534060255367002e-06, "epoch": 0.43591654247391953, "percentage": 8.72, "elapsed_time": "0:07:46", "remaining_time": "1:21:25", "throughput": 5135.22, "total_tokens": 2396160} {"current_steps": 586, "total_steps": 6710, "loss": 1.4745, "lr": 2.453247595091904e-06, "epoch": 0.4366616989567809, "percentage": 8.73, "elapsed_time": "0:07:47", "remaining_time": "1:21:24", "throughput": 5135.35, "total_tokens": 2400256} {"current_steps": 587, "total_steps": 6710, "loss": 1.2825, "lr": 2.4530889008866426e-06, "epoch": 0.4374068554396423, "percentage": 8.75, "elapsed_time": "0:07:48", "remaining_time": "1:21:23", "throughput": 5135.49, "total_tokens": 2404352} {"current_steps": 588, "total_steps": 6710, "loss": 1.2442, "lr": 2.4529299429557037e-06, "epoch": 0.43815201192250375, "percentage": 8.76, "elapsed_time": "0:07:48", "remaining_time": "1:21:22", "throughput": 5135.63, "total_tokens": 2408448} {"current_steps": 589, "total_steps": 6710, "loss": 1.1523, "lr": 2.4527707213339313e-06, "epoch": 0.43889716840536513, "percentage": 8.78, "elapsed_time": "0:07:49", "remaining_time": "1:21:21", "throughput": 5135.76, "total_tokens": 2412544} {"current_steps": 590, "total_steps": 6710, "loss": 1.427, "lr": 2.4526112360562283e-06, "epoch": 0.4396423248882265, "percentage": 8.79, "elapsed_time": "0:07:50", "remaining_time": "1:21:20", "throughput": 5135.88, "total_tokens": 2416640} {"current_steps": 591, "total_steps": 6710, "loss": 1.2343, "lr": 2.452451487157555e-06, "epoch": 0.4403874813710879, "percentage": 8.81, "elapsed_time": "0:07:51", "remaining_time": "1:21:19", "throughput": 5136.06, "total_tokens": 2420736} {"current_steps": 592, "total_steps": 6710, "loss": 0.9506, "lr": 2.452291474672929e-06, "epoch": 0.44113263785394935, "percentage": 8.82, "elapsed_time": "0:07:52", "remaining_time": "1:21:19", "throughput": 5136.11, "total_tokens": 2424832} {"current_steps": 593, "total_steps": 6710, "loss": 1.2496, "lr": 2.4521311986374275e-06, "epoch": 0.44187779433681074, "percentage": 8.84, "elapsed_time": "0:07:52", "remaining_time": "1:21:18", "throughput": 5136.28, "total_tokens": 2428928} {"current_steps": 594, "total_steps": 6710, "loss": 1.344, "lr": 2.4519706590861826e-06, "epoch": 0.4426229508196721, "percentage": 8.85, "elapsed_time": "0:07:53", "remaining_time": "1:21:17", "throughput": 5136.46, "total_tokens": 2433024} {"current_steps": 595, "total_steps": 6710, "loss": 1.6058, "lr": 2.451809856054387e-06, "epoch": 0.4433681073025335, "percentage": 8.87, "elapsed_time": "0:07:54", "remaining_time": "1:21:16", "throughput": 5136.64, "total_tokens": 2437120} {"current_steps": 596, "total_steps": 6710, "loss": 1.3307, "lr": 2.4516487895772888e-06, "epoch": 0.44411326378539495, "percentage": 8.88, "elapsed_time": "0:07:55", "remaining_time": "1:21:15", "throughput": 5136.84, "total_tokens": 2441216} {"current_steps": 597, "total_steps": 6710, "loss": 1.3125, "lr": 2.451487459690195e-06, "epoch": 0.44485842026825634, "percentage": 8.9, "elapsed_time": "0:07:56", "remaining_time": "1:21:14", "throughput": 5137.01, "total_tokens": 2445312} {"current_steps": 598, "total_steps": 6710, "loss": 1.1923, "lr": 2.451325866428471e-06, "epoch": 0.4456035767511177, "percentage": 8.91, "elapsed_time": "0:07:56", "remaining_time": "1:21:13", "throughput": 5137.22, "total_tokens": 2449408} {"current_steps": 599, "total_steps": 6710, "loss": 1.435, "lr": 2.451164009827539e-06, "epoch": 0.4463487332339791, "percentage": 8.93, "elapsed_time": "0:07:57", "remaining_time": "1:21:12", "throughput": 5137.4, "total_tokens": 2453504} {"current_steps": 600, "total_steps": 6710, "loss": 1.0631, "lr": 2.4510018899228795e-06, "epoch": 0.44709388971684055, "percentage": 8.94, "elapsed_time": "0:07:58", "remaining_time": "1:21:11", "throughput": 5137.54, "total_tokens": 2457600} {"current_steps": 601, "total_steps": 6710, "loss": 1.192, "lr": 2.450839506750029e-06, "epoch": 0.44783904619970194, "percentage": 8.96, "elapsed_time": "0:07:59", "remaining_time": "1:21:10", "throughput": 5137.67, "total_tokens": 2461696} {"current_steps": 602, "total_steps": 6710, "loss": 1.2563, "lr": 2.450676860344584e-06, "epoch": 0.4485842026825633, "percentage": 8.97, "elapsed_time": "0:07:59", "remaining_time": "1:21:09", "throughput": 5137.83, "total_tokens": 2465792} {"current_steps": 603, "total_steps": 6710, "loss": 1.0509, "lr": 2.450513950742198e-06, "epoch": 0.4493293591654247, "percentage": 8.99, "elapsed_time": "0:08:00", "remaining_time": "1:21:08", "throughput": 5137.97, "total_tokens": 2469888} {"current_steps": 604, "total_steps": 6710, "loss": 1.4135, "lr": 2.450350777978581e-06, "epoch": 0.45007451564828616, "percentage": 9.0, "elapsed_time": "0:08:01", "remaining_time": "1:21:07", "throughput": 5138.14, "total_tokens": 2473984} {"current_steps": 605, "total_steps": 6710, "loss": 1.3968, "lr": 2.4501873420895025e-06, "epoch": 0.45081967213114754, "percentage": 9.02, "elapsed_time": "0:08:02", "remaining_time": "1:21:06", "throughput": 5138.34, "total_tokens": 2478080} {"current_steps": 606, "total_steps": 6710, "loss": 1.3819, "lr": 2.4500236431107883e-06, "epoch": 0.45156482861400893, "percentage": 9.03, "elapsed_time": "0:08:03", "remaining_time": "1:21:05", "throughput": 5138.52, "total_tokens": 2482176} {"current_steps": 607, "total_steps": 6710, "loss": 1.1977, "lr": 2.449859681078323e-06, "epoch": 0.4523099850968703, "percentage": 9.05, "elapsed_time": "0:08:03", "remaining_time": "1:21:04", "throughput": 5138.7, "total_tokens": 2486272} {"current_steps": 608, "total_steps": 6710, "loss": 1.1876, "lr": 2.4496954560280474e-06, "epoch": 0.45305514157973176, "percentage": 9.06, "elapsed_time": "0:08:04", "remaining_time": "1:21:03", "throughput": 5138.85, "total_tokens": 2490368} {"current_steps": 609, "total_steps": 6710, "loss": 1.4114, "lr": 2.449530967995962e-06, "epoch": 0.45380029806259314, "percentage": 9.08, "elapsed_time": "0:08:05", "remaining_time": "1:21:02", "throughput": 5138.99, "total_tokens": 2494464} {"current_steps": 610, "total_steps": 6710, "loss": 1.4661, "lr": 2.4493662170181222e-06, "epoch": 0.45454545454545453, "percentage": 9.09, "elapsed_time": "0:08:06", "remaining_time": "1:21:01", "throughput": 5139.16, "total_tokens": 2498560} {"current_steps": 611, "total_steps": 6710, "loss": 1.2853, "lr": 2.4492012031306434e-06, "epoch": 0.455290611028316, "percentage": 9.11, "elapsed_time": "0:08:06", "remaining_time": "1:21:00", "throughput": 5139.33, "total_tokens": 2502656} {"current_steps": 612, "total_steps": 6710, "loss": 1.1033, "lr": 2.449035926369698e-06, "epoch": 0.45603576751117736, "percentage": 9.12, "elapsed_time": "0:08:07", "remaining_time": "1:20:59", "throughput": 5139.48, "total_tokens": 2506752} {"current_steps": 613, "total_steps": 6710, "loss": 1.259, "lr": 2.4488703867715156e-06, "epoch": 0.45678092399403875, "percentage": 9.14, "elapsed_time": "0:08:08", "remaining_time": "1:20:58", "throughput": 5139.68, "total_tokens": 2510848} {"current_steps": 614, "total_steps": 6710, "loss": 1.1026, "lr": 2.4487045843723837e-06, "epoch": 0.45752608047690013, "percentage": 9.15, "elapsed_time": "0:08:09", "remaining_time": "1:20:57", "throughput": 5139.84, "total_tokens": 2514944} {"current_steps": 615, "total_steps": 6710, "loss": 1.3927, "lr": 2.448538519208648e-06, "epoch": 0.4582712369597616, "percentage": 9.17, "elapsed_time": "0:08:10", "remaining_time": "1:20:57", "throughput": 5140.01, "total_tokens": 2519040} {"current_steps": 616, "total_steps": 6710, "loss": 1.5729, "lr": 2.4483721913167096e-06, "epoch": 0.45901639344262296, "percentage": 9.18, "elapsed_time": "0:08:10", "remaining_time": "1:20:56", "throughput": 5140.12, "total_tokens": 2523136} {"current_steps": 617, "total_steps": 6710, "loss": 1.5655, "lr": 2.4482056007330305e-06, "epoch": 0.45976154992548435, "percentage": 9.2, "elapsed_time": "0:08:11", "remaining_time": "1:20:55", "throughput": 5140.23, "total_tokens": 2527232} {"current_steps": 618, "total_steps": 6710, "loss": 1.4684, "lr": 2.4480387474941274e-06, "epoch": 0.46050670640834573, "percentage": 9.21, "elapsed_time": "0:08:12", "remaining_time": "1:20:54", "throughput": 5140.39, "total_tokens": 2531328} {"current_steps": 619, "total_steps": 6710, "loss": 1.3556, "lr": 2.447871631636576e-06, "epoch": 0.4612518628912072, "percentage": 9.23, "elapsed_time": "0:08:13", "remaining_time": "1:20:53", "throughput": 5140.56, "total_tokens": 2535424} {"current_steps": 620, "total_steps": 6710, "loss": 1.2794, "lr": 2.4477042531970096e-06, "epoch": 0.46199701937406856, "percentage": 9.24, "elapsed_time": "0:08:13", "remaining_time": "1:20:52", "throughput": 5140.75, "total_tokens": 2539520} {"current_steps": 621, "total_steps": 6710, "loss": 1.1589, "lr": 2.4475366122121188e-06, "epoch": 0.46274217585692995, "percentage": 9.25, "elapsed_time": "0:08:14", "remaining_time": "1:20:51", "throughput": 5140.92, "total_tokens": 2543616} {"current_steps": 622, "total_steps": 6710, "loss": 1.411, "lr": 2.4473687087186508e-06, "epoch": 0.46348733233979134, "percentage": 9.27, "elapsed_time": "0:08:15", "remaining_time": "1:20:50", "throughput": 5141.09, "total_tokens": 2547712} {"current_steps": 623, "total_steps": 6710, "loss": 1.3693, "lr": 2.447200542753412e-06, "epoch": 0.4642324888226528, "percentage": 9.28, "elapsed_time": "0:08:16", "remaining_time": "1:20:49", "throughput": 5141.26, "total_tokens": 2551808} {"current_steps": 624, "total_steps": 6710, "loss": 1.1206, "lr": 2.447032114353266e-06, "epoch": 0.46497764530551416, "percentage": 9.3, "elapsed_time": "0:08:17", "remaining_time": "1:20:48", "throughput": 5141.45, "total_tokens": 2555904} {"current_steps": 625, "total_steps": 6710, "loss": 1.2339, "lr": 2.4468634235551325e-06, "epoch": 0.46572280178837555, "percentage": 9.31, "elapsed_time": "0:08:17", "remaining_time": "1:20:47", "throughput": 5141.6, "total_tokens": 2560000} {"current_steps": 626, "total_steps": 6710, "loss": 1.5603, "lr": 2.4466944703959903e-06, "epoch": 0.46646795827123694, "percentage": 9.33, "elapsed_time": "0:08:18", "remaining_time": "1:20:46", "throughput": 5141.77, "total_tokens": 2564096} {"current_steps": 627, "total_steps": 6710, "loss": 1.213, "lr": 2.4465252549128746e-06, "epoch": 0.4672131147540984, "percentage": 9.34, "elapsed_time": "0:08:19", "remaining_time": "1:20:45", "throughput": 5141.95, "total_tokens": 2568192} {"current_steps": 628, "total_steps": 6710, "loss": 1.1963, "lr": 2.4463557771428796e-06, "epoch": 0.46795827123695977, "percentage": 9.36, "elapsed_time": "0:08:20", "remaining_time": "1:20:44", "throughput": 5142.11, "total_tokens": 2572288} {"current_steps": 629, "total_steps": 6710, "loss": 1.3465, "lr": 2.4461860371231557e-06, "epoch": 0.46870342771982115, "percentage": 9.37, "elapsed_time": "0:08:21", "remaining_time": "1:20:43", "throughput": 5142.3, "total_tokens": 2576384} {"current_steps": 630, "total_steps": 6710, "loss": 1.2459, "lr": 2.4460160348909104e-06, "epoch": 0.46944858420268254, "percentage": 9.39, "elapsed_time": "0:08:21", "remaining_time": "1:20:42", "throughput": 5142.46, "total_tokens": 2580480} {"current_steps": 631, "total_steps": 6710, "loss": 1.3675, "lr": 2.4458457704834103e-06, "epoch": 0.470193740685544, "percentage": 9.4, "elapsed_time": "0:08:22", "remaining_time": "1:20:41", "throughput": 5142.64, "total_tokens": 2584576} {"current_steps": 632, "total_steps": 6710, "loss": 1.1732, "lr": 2.445675243937978e-06, "epoch": 0.47093889716840537, "percentage": 9.42, "elapsed_time": "0:08:23", "remaining_time": "1:20:40", "throughput": 5142.8, "total_tokens": 2588672} {"current_steps": 633, "total_steps": 6710, "loss": 1.2998, "lr": 2.445504455291994e-06, "epoch": 0.47168405365126675, "percentage": 9.43, "elapsed_time": "0:08:24", "remaining_time": "1:20:39", "throughput": 5142.93, "total_tokens": 2592768} {"current_steps": 634, "total_steps": 6710, "loss": 0.9837, "lr": 2.4453334045828973e-06, "epoch": 0.47242921013412814, "percentage": 9.45, "elapsed_time": "0:08:24", "remaining_time": "1:20:38", "throughput": 5143.07, "total_tokens": 2596864} {"current_steps": 635, "total_steps": 6710, "loss": 1.3605, "lr": 2.445162091848183e-06, "epoch": 0.4731743666169896, "percentage": 9.46, "elapsed_time": "0:08:25", "remaining_time": "1:20:38", "throughput": 5143.23, "total_tokens": 2600960} {"current_steps": 636, "total_steps": 6710, "loss": 1.3417, "lr": 2.4449905171254033e-06, "epoch": 0.47391952309985097, "percentage": 9.48, "elapsed_time": "0:08:26", "remaining_time": "1:20:37", "throughput": 5143.4, "total_tokens": 2605056} {"current_steps": 637, "total_steps": 6710, "loss": 1.1621, "lr": 2.4448186804521698e-06, "epoch": 0.47466467958271236, "percentage": 9.49, "elapsed_time": "0:08:27", "remaining_time": "1:20:36", "throughput": 5143.53, "total_tokens": 2609152} {"current_steps": 638, "total_steps": 6710, "loss": 1.1752, "lr": 2.44464658186615e-06, "epoch": 0.47540983606557374, "percentage": 9.51, "elapsed_time": "0:08:28", "remaining_time": "1:20:35", "throughput": 5143.71, "total_tokens": 2613248} {"current_steps": 639, "total_steps": 6710, "loss": 1.0429, "lr": 2.444474221405068e-06, "epoch": 0.4761549925484352, "percentage": 9.52, "elapsed_time": "0:08:28", "remaining_time": "1:20:34", "throughput": 5143.84, "total_tokens": 2617344} {"current_steps": 640, "total_steps": 6710, "loss": 1.1841, "lr": 2.444301599106708e-06, "epoch": 0.47690014903129657, "percentage": 9.54, "elapsed_time": "0:08:29", "remaining_time": "1:20:33", "throughput": 5144.02, "total_tokens": 2621440} {"current_steps": 641, "total_steps": 6710, "loss": 1.2, "lr": 2.444128715008909e-06, "epoch": 0.47764530551415796, "percentage": 9.55, "elapsed_time": "0:08:30", "remaining_time": "1:20:32", "throughput": 5144.17, "total_tokens": 2625536} {"current_steps": 642, "total_steps": 6710, "loss": 1.533, "lr": 2.4439555691495694e-06, "epoch": 0.4783904619970194, "percentage": 9.57, "elapsed_time": "0:08:31", "remaining_time": "1:20:31", "throughput": 5144.33, "total_tokens": 2629632} {"current_steps": 643, "total_steps": 6710, "loss": 1.0186, "lr": 2.443782161566643e-06, "epoch": 0.4791356184798808, "percentage": 9.58, "elapsed_time": "0:08:31", "remaining_time": "1:20:30", "throughput": 5144.5, "total_tokens": 2633728} {"current_steps": 644, "total_steps": 6710, "loss": 1.3541, "lr": 2.443608492298142e-06, "epoch": 0.4798807749627422, "percentage": 9.6, "elapsed_time": "0:08:32", "remaining_time": "1:20:29", "throughput": 5144.65, "total_tokens": 2637824} {"current_steps": 645, "total_steps": 6710, "loss": 1.0941, "lr": 2.4434345613821373e-06, "epoch": 0.48062593144560356, "percentage": 9.61, "elapsed_time": "0:08:33", "remaining_time": "1:20:28", "throughput": 5144.79, "total_tokens": 2641920} {"current_steps": 646, "total_steps": 6710, "loss": 1.1553, "lr": 2.4432603688567545e-06, "epoch": 0.481371087928465, "percentage": 9.63, "elapsed_time": "0:08:34", "remaining_time": "1:20:27", "throughput": 5144.94, "total_tokens": 2646016} {"current_steps": 647, "total_steps": 6710, "loss": 1.183, "lr": 2.443085914760178e-06, "epoch": 0.4821162444113264, "percentage": 9.64, "elapsed_time": "0:08:35", "remaining_time": "1:20:26", "throughput": 5145.08, "total_tokens": 2650112} {"current_steps": 648, "total_steps": 6710, "loss": 1.3903, "lr": 2.4429111991306498e-06, "epoch": 0.4828614008941878, "percentage": 9.66, "elapsed_time": "0:08:35", "remaining_time": "1:20:25", "throughput": 5145.19, "total_tokens": 2654208} {"current_steps": 649, "total_steps": 6710, "loss": 1.2329, "lr": 2.4427362220064686e-06, "epoch": 0.48360655737704916, "percentage": 9.67, "elapsed_time": "0:08:36", "remaining_time": "1:20:24", "throughput": 5145.32, "total_tokens": 2658304} {"current_steps": 650, "total_steps": 6710, "loss": 1.3614, "lr": 2.4425609834259904e-06, "epoch": 0.4843517138599106, "percentage": 9.69, "elapsed_time": "0:08:37", "remaining_time": "1:20:24", "throughput": 5145.45, "total_tokens": 2662400} {"current_steps": 651, "total_steps": 6710, "loss": 1.1476, "lr": 2.4423854834276293e-06, "epoch": 0.485096870342772, "percentage": 9.7, "elapsed_time": "0:08:38", "remaining_time": "1:20:23", "throughput": 5145.48, "total_tokens": 2666496} {"current_steps": 652, "total_steps": 6710, "loss": 1.2758, "lr": 2.442209722049856e-06, "epoch": 0.4858420268256334, "percentage": 9.72, "elapsed_time": "0:08:39", "remaining_time": "1:20:22", "throughput": 5145.47, "total_tokens": 2670592} {"current_steps": 653, "total_steps": 6710, "loss": 1.3325, "lr": 2.442033699331198e-06, "epoch": 0.48658718330849476, "percentage": 9.73, "elapsed_time": "0:08:39", "remaining_time": "1:20:21", "throughput": 5145.53, "total_tokens": 2674688} {"current_steps": 654, "total_steps": 6710, "loss": 0.9667, "lr": 2.4418574153102416e-06, "epoch": 0.4873323397913562, "percentage": 9.75, "elapsed_time": "0:08:40", "remaining_time": "1:20:20", "throughput": 5145.62, "total_tokens": 2678784} {"current_steps": 655, "total_steps": 6710, "loss": 1.1164, "lr": 2.441680870025629e-06, "epoch": 0.4880774962742176, "percentage": 9.76, "elapsed_time": "0:08:41", "remaining_time": "1:20:19", "throughput": 5145.78, "total_tokens": 2682880} {"current_steps": 656, "total_steps": 6710, "loss": 1.5123, "lr": 2.44150406351606e-06, "epoch": 0.488822652757079, "percentage": 9.78, "elapsed_time": "0:08:42", "remaining_time": "1:20:18", "throughput": 5145.86, "total_tokens": 2686976} {"current_steps": 657, "total_steps": 6710, "loss": 1.2855, "lr": 2.4413269958202926e-06, "epoch": 0.48956780923994037, "percentage": 9.79, "elapsed_time": "0:08:42", "remaining_time": "1:20:17", "throughput": 5146.02, "total_tokens": 2691072} {"current_steps": 658, "total_steps": 6710, "loss": 1.2835, "lr": 2.4411496669771408e-06, "epoch": 0.4903129657228018, "percentage": 9.81, "elapsed_time": "0:08:43", "remaining_time": "1:20:17", "throughput": 5146.14, "total_tokens": 2695168} {"current_steps": 659, "total_steps": 6710, "loss": 1.3573, "lr": 2.4409720770254765e-06, "epoch": 0.4910581222056632, "percentage": 9.82, "elapsed_time": "0:08:44", "remaining_time": "1:20:16", "throughput": 5146.29, "total_tokens": 2699264} {"current_steps": 660, "total_steps": 6710, "loss": 1.2715, "lr": 2.4407942260042284e-06, "epoch": 0.4918032786885246, "percentage": 9.84, "elapsed_time": "0:08:45", "remaining_time": "1:20:15", "throughput": 5146.42, "total_tokens": 2703360} {"current_steps": 661, "total_steps": 6710, "loss": 1.0092, "lr": 2.4406161139523834e-06, "epoch": 0.49254843517138597, "percentage": 9.85, "elapsed_time": "0:08:46", "remaining_time": "1:20:14", "throughput": 5146.55, "total_tokens": 2707456} {"current_steps": 662, "total_steps": 6710, "loss": 1.1991, "lr": 2.4404377409089837e-06, "epoch": 0.4932935916542474, "percentage": 9.87, "elapsed_time": "0:08:46", "remaining_time": "1:20:13", "throughput": 5146.68, "total_tokens": 2711552} {"current_steps": 663, "total_steps": 6710, "loss": 1.4246, "lr": 2.440259106913131e-06, "epoch": 0.4940387481371088, "percentage": 9.88, "elapsed_time": "0:08:47", "remaining_time": "1:20:12", "throughput": 5146.82, "total_tokens": 2715648} {"current_steps": 664, "total_steps": 6710, "loss": 1.3441, "lr": 2.440080212003983e-06, "epoch": 0.4947839046199702, "percentage": 9.9, "elapsed_time": "0:08:48", "remaining_time": "1:20:11", "throughput": 5147.0, "total_tokens": 2719744} {"current_steps": 665, "total_steps": 6710, "loss": 1.16, "lr": 2.4399010562207547e-06, "epoch": 0.49552906110283157, "percentage": 9.91, "elapsed_time": "0:08:49", "remaining_time": "1:20:10", "throughput": 5147.16, "total_tokens": 2723840} {"current_steps": 666, "total_steps": 6710, "loss": 1.4045, "lr": 2.439721639602718e-06, "epoch": 0.496274217585693, "percentage": 9.93, "elapsed_time": "0:08:49", "remaining_time": "1:20:09", "throughput": 5147.28, "total_tokens": 2727936} {"current_steps": 667, "total_steps": 6710, "loss": 1.3165, "lr": 2.4395419621892027e-06, "epoch": 0.4970193740685544, "percentage": 9.94, "elapsed_time": "0:08:50", "remaining_time": "1:20:08", "throughput": 5147.27, "total_tokens": 2732032} {"current_steps": 668, "total_steps": 6710, "loss": 1.6292, "lr": 2.439362024019595e-06, "epoch": 0.4977645305514158, "percentage": 9.96, "elapsed_time": "0:08:51", "remaining_time": "1:20:07", "throughput": 5147.34, "total_tokens": 2736128} {"current_steps": 669, "total_steps": 6710, "loss": 1.1544, "lr": 2.439181825133339e-06, "epoch": 0.49850968703427717, "percentage": 9.97, "elapsed_time": "0:08:52", "remaining_time": "1:20:07", "throughput": 5147.39, "total_tokens": 2740224} {"current_steps": 670, "total_steps": 6710, "loss": 1.3072, "lr": 2.4390013655699355e-06, "epoch": 0.4992548435171386, "percentage": 9.99, "elapsed_time": "0:08:53", "remaining_time": "1:20:06", "throughput": 5147.51, "total_tokens": 2744320} {"current_steps": 671, "total_steps": 6710, "loss": 1.3539, "lr": 2.4388206453689422e-06, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:08:53", "remaining_time": "1:20:05", "throughput": 5147.64, "total_tokens": 2748416} {"current_steps": 672, "total_steps": 6710, "loss": 1.606, "lr": 2.4386396645699745e-06, "epoch": 0.5007451564828614, "percentage": 10.01, "elapsed_time": "0:08:54", "remaining_time": "1:20:04", "throughput": 5147.79, "total_tokens": 2752512} {"current_steps": 673, "total_steps": 6710, "loss": 1.2512, "lr": 2.438458423212705e-06, "epoch": 0.5014903129657228, "percentage": 10.03, "elapsed_time": "0:08:55", "remaining_time": "1:20:03", "throughput": 5147.87, "total_tokens": 2756608} {"current_steps": 674, "total_steps": 6710, "loss": 1.1623, "lr": 2.4382769213368625e-06, "epoch": 0.5022354694485842, "percentage": 10.04, "elapsed_time": "0:08:56", "remaining_time": "1:20:02", "throughput": 5147.89, "total_tokens": 2760704} {"current_steps": 675, "total_steps": 6710, "loss": 1.1248, "lr": 2.438095158982234e-06, "epoch": 0.5029806259314457, "percentage": 10.06, "elapsed_time": "0:08:57", "remaining_time": "1:20:01", "throughput": 5147.92, "total_tokens": 2764800} {"current_steps": 676, "total_steps": 6710, "loss": 1.5054, "lr": 2.437913136188663e-06, "epoch": 0.503725782414307, "percentage": 10.07, "elapsed_time": "0:08:57", "remaining_time": "1:20:00", "throughput": 5148.01, "total_tokens": 2768896} {"current_steps": 677, "total_steps": 6710, "loss": 1.2641, "lr": 2.437730852996049e-06, "epoch": 0.5044709388971684, "percentage": 10.09, "elapsed_time": "0:08:58", "remaining_time": "1:20:00", "throughput": 5148.11, "total_tokens": 2772992} {"current_steps": 678, "total_steps": 6710, "loss": 1.2964, "lr": 2.437548309444352e-06, "epoch": 0.5052160953800298, "percentage": 10.1, "elapsed_time": "0:08:59", "remaining_time": "1:19:59", "throughput": 5148.05, "total_tokens": 2777088} {"current_steps": 679, "total_steps": 6710, "loss": 1.3964, "lr": 2.437365505573585e-06, "epoch": 0.5059612518628912, "percentage": 10.12, "elapsed_time": "0:09:00", "remaining_time": "1:19:58", "throughput": 5148.09, "total_tokens": 2781184} {"current_steps": 680, "total_steps": 6710, "loss": 1.2854, "lr": 2.4371824414238217e-06, "epoch": 0.5067064083457526, "percentage": 10.13, "elapsed_time": "0:09:01", "remaining_time": "1:19:57", "throughput": 5148.21, "total_tokens": 2785280} {"current_steps": 681, "total_steps": 6710, "loss": 1.2426, "lr": 2.4369991170351893e-06, "epoch": 0.507451564828614, "percentage": 10.15, "elapsed_time": "0:09:01", "remaining_time": "1:19:56", "throughput": 5148.34, "total_tokens": 2789376} {"current_steps": 682, "total_steps": 6710, "loss": 1.1428, "lr": 2.4368155324478743e-06, "epoch": 0.5081967213114754, "percentage": 10.16, "elapsed_time": "0:09:02", "remaining_time": "1:19:55", "throughput": 5148.41, "total_tokens": 2793472} {"current_steps": 683, "total_steps": 6710, "loss": 1.1919, "lr": 2.43663168770212e-06, "epoch": 0.5089418777943369, "percentage": 10.18, "elapsed_time": "0:09:03", "remaining_time": "1:19:54", "throughput": 5148.54, "total_tokens": 2797568} {"current_steps": 684, "total_steps": 6710, "loss": 1.0981, "lr": 2.436447582838227e-06, "epoch": 0.5096870342771982, "percentage": 10.19, "elapsed_time": "0:09:04", "remaining_time": "1:19:53", "throughput": 5148.68, "total_tokens": 2801664} {"current_steps": 685, "total_steps": 6710, "loss": 1.3656, "lr": 2.4362632178965515e-06, "epoch": 0.5104321907600596, "percentage": 10.21, "elapsed_time": "0:09:04", "remaining_time": "1:19:53", "throughput": 5148.83, "total_tokens": 2805760} {"current_steps": 686, "total_steps": 6710, "loss": 1.5296, "lr": 2.436078592917508e-06, "epoch": 0.511177347242921, "percentage": 10.22, "elapsed_time": "0:09:05", "remaining_time": "1:19:52", "throughput": 5148.97, "total_tokens": 2809856} {"current_steps": 687, "total_steps": 6710, "loss": 1.2666, "lr": 2.4358937079415673e-06, "epoch": 0.5119225037257824, "percentage": 10.24, "elapsed_time": "0:09:06", "remaining_time": "1:19:51", "throughput": 5149.1, "total_tokens": 2813952} {"current_steps": 688, "total_steps": 6710, "loss": 1.4138, "lr": 2.435708563009258e-06, "epoch": 0.5126676602086438, "percentage": 10.25, "elapsed_time": "0:09:07", "remaining_time": "1:19:50", "throughput": 5149.26, "total_tokens": 2818048} {"current_steps": 689, "total_steps": 6710, "loss": 1.3956, "lr": 2.435523158161165e-06, "epoch": 0.5134128166915052, "percentage": 10.27, "elapsed_time": "0:09:08", "remaining_time": "1:19:49", "throughput": 5149.38, "total_tokens": 2822144} {"current_steps": 690, "total_steps": 6710, "loss": 1.2367, "lr": 2.4353374934379306e-06, "epoch": 0.5141579731743666, "percentage": 10.28, "elapsed_time": "0:09:08", "remaining_time": "1:19:48", "throughput": 5149.53, "total_tokens": 2826240} {"current_steps": 691, "total_steps": 6710, "loss": 1.2604, "lr": 2.4351515688802532e-06, "epoch": 0.5149031296572281, "percentage": 10.3, "elapsed_time": "0:09:09", "remaining_time": "1:19:47", "throughput": 5149.67, "total_tokens": 2830336} {"current_steps": 692, "total_steps": 6710, "loss": 1.5445, "lr": 2.4349653845288897e-06, "epoch": 0.5156482861400894, "percentage": 10.31, "elapsed_time": "0:09:10", "remaining_time": "1:19:46", "throughput": 5149.77, "total_tokens": 2834432} {"current_steps": 693, "total_steps": 6710, "loss": 1.2387, "lr": 2.4347789404246517e-06, "epoch": 0.5163934426229508, "percentage": 10.33, "elapsed_time": "0:09:11", "remaining_time": "1:19:45", "throughput": 5149.84, "total_tokens": 2838528} {"current_steps": 694, "total_steps": 6710, "loss": 1.2528, "lr": 2.43459223660841e-06, "epoch": 0.5171385991058122, "percentage": 10.34, "elapsed_time": "0:09:11", "remaining_time": "1:19:44", "throughput": 5149.91, "total_tokens": 2842624} {"current_steps": 695, "total_steps": 6710, "loss": 1.2713, "lr": 2.434405273121092e-06, "epoch": 0.5178837555886736, "percentage": 10.36, "elapsed_time": "0:09:12", "remaining_time": "1:19:43", "throughput": 5150.0, "total_tokens": 2846720} {"current_steps": 696, "total_steps": 6710, "loss": 1.2254, "lr": 2.4342180500036803e-06, "epoch": 0.518628912071535, "percentage": 10.37, "elapsed_time": "0:09:13", "remaining_time": "1:19:43", "throughput": 5150.13, "total_tokens": 2850816} {"current_steps": 697, "total_steps": 6710, "loss": 1.3186, "lr": 2.4340305672972157e-06, "epoch": 0.5193740685543964, "percentage": 10.39, "elapsed_time": "0:09:14", "remaining_time": "1:19:42", "throughput": 5150.29, "total_tokens": 2854912} {"current_steps": 698, "total_steps": 6710, "loss": 1.5027, "lr": 2.4338428250427965e-06, "epoch": 0.5201192250372578, "percentage": 10.4, "elapsed_time": "0:09:15", "remaining_time": "1:19:41", "throughput": 5150.42, "total_tokens": 2859008} {"current_steps": 699, "total_steps": 6710, "loss": 1.461, "lr": 2.4336548232815764e-06, "epoch": 0.5208643815201193, "percentage": 10.42, "elapsed_time": "0:09:15", "remaining_time": "1:19:40", "throughput": 5150.58, "total_tokens": 2863104} {"current_steps": 700, "total_steps": 6710, "loss": 1.4051, "lr": 2.433466562054767e-06, "epoch": 0.5216095380029806, "percentage": 10.43, "elapsed_time": "0:09:16", "remaining_time": "1:19:39", "throughput": 5150.7, "total_tokens": 2867200} {"current_steps": 701, "total_steps": 6710, "loss": 1.4564, "lr": 2.4332780414036365e-06, "epoch": 0.522354694485842, "percentage": 10.45, "elapsed_time": "0:09:17", "remaining_time": "1:19:38", "throughput": 5150.86, "total_tokens": 2871296} {"current_steps": 702, "total_steps": 6710, "loss": 1.3472, "lr": 2.43308926136951e-06, "epoch": 0.5230998509687034, "percentage": 10.46, "elapsed_time": "0:09:18", "remaining_time": "1:19:37", "throughput": 5151.01, "total_tokens": 2875392} {"current_steps": 703, "total_steps": 6710, "loss": 1.1996, "lr": 2.432900221993769e-06, "epoch": 0.5238450074515648, "percentage": 10.48, "elapsed_time": "0:09:19", "remaining_time": "1:19:36", "throughput": 5151.13, "total_tokens": 2879488} {"current_steps": 704, "total_steps": 6710, "loss": 1.3172, "lr": 2.4327109233178533e-06, "epoch": 0.5245901639344263, "percentage": 10.49, "elapsed_time": "0:09:19", "remaining_time": "1:19:35", "throughput": 5151.26, "total_tokens": 2883584} {"current_steps": 705, "total_steps": 6710, "loss": 1.4348, "lr": 2.4325213653832573e-06, "epoch": 0.5253353204172876, "percentage": 10.51, "elapsed_time": "0:09:20", "remaining_time": "1:19:34", "throughput": 5151.39, "total_tokens": 2887680} {"current_steps": 706, "total_steps": 6710, "loss": 1.249, "lr": 2.4323315482315344e-06, "epoch": 0.526080476900149, "percentage": 10.52, "elapsed_time": "0:09:21", "remaining_time": "1:19:33", "throughput": 5151.52, "total_tokens": 2891776} {"current_steps": 707, "total_steps": 6710, "loss": 0.8963, "lr": 2.432141471904294e-06, "epoch": 0.5268256333830105, "percentage": 10.54, "elapsed_time": "0:09:22", "remaining_time": "1:19:32", "throughput": 5151.65, "total_tokens": 2895872} {"current_steps": 708, "total_steps": 6710, "loss": 1.4897, "lr": 2.431951136443201e-06, "epoch": 0.5275707898658718, "percentage": 10.55, "elapsed_time": "0:09:22", "remaining_time": "1:19:31", "throughput": 5151.79, "total_tokens": 2899968} {"current_steps": 709, "total_steps": 6710, "loss": 1.1677, "lr": 2.4317605418899793e-06, "epoch": 0.5283159463487332, "percentage": 10.57, "elapsed_time": "0:09:23", "remaining_time": "1:19:31", "throughput": 5151.92, "total_tokens": 2904064} {"current_steps": 710, "total_steps": 6710, "loss": 1.4971, "lr": 2.431569688286408e-06, "epoch": 0.5290611028315947, "percentage": 10.58, "elapsed_time": "0:09:24", "remaining_time": "1:19:30", "throughput": 5152.01, "total_tokens": 2908160} {"current_steps": 711, "total_steps": 6710, "loss": 0.9813, "lr": 2.4313785756743242e-06, "epoch": 0.529806259314456, "percentage": 10.6, "elapsed_time": "0:09:25", "remaining_time": "1:19:29", "throughput": 5152.14, "total_tokens": 2912256} {"current_steps": 712, "total_steps": 6710, "loss": 1.0746, "lr": 2.431187204095621e-06, "epoch": 0.5305514157973175, "percentage": 10.61, "elapsed_time": "0:09:26", "remaining_time": "1:19:28", "throughput": 5152.27, "total_tokens": 2916352} {"current_steps": 713, "total_steps": 6710, "loss": 1.3755, "lr": 2.4309955735922476e-06, "epoch": 0.5312965722801788, "percentage": 10.63, "elapsed_time": "0:09:26", "remaining_time": "1:19:27", "throughput": 5152.4, "total_tokens": 2920448} {"current_steps": 714, "total_steps": 6710, "loss": 1.2146, "lr": 2.4308036842062118e-06, "epoch": 0.5320417287630402, "percentage": 10.64, "elapsed_time": "0:09:27", "remaining_time": "1:19:26", "throughput": 5152.55, "total_tokens": 2924544} {"current_steps": 715, "total_steps": 6710, "loss": 1.1652, "lr": 2.4306115359795768e-06, "epoch": 0.5327868852459017, "percentage": 10.66, "elapsed_time": "0:09:28", "remaining_time": "1:19:25", "throughput": 5152.64, "total_tokens": 2928640} {"current_steps": 716, "total_steps": 6710, "loss": 1.2002, "lr": 2.4304191289544625e-06, "epoch": 0.533532041728763, "percentage": 10.67, "elapsed_time": "0:09:29", "remaining_time": "1:19:24", "throughput": 5152.73, "total_tokens": 2932736} {"current_steps": 717, "total_steps": 6710, "loss": 1.1663, "lr": 2.4302264631730467e-06, "epoch": 0.5342771982116244, "percentage": 10.69, "elapsed_time": "0:09:29", "remaining_time": "1:19:23", "throughput": 5152.87, "total_tokens": 2936832} {"current_steps": 718, "total_steps": 6710, "loss": 1.4108, "lr": 2.430033538677562e-06, "epoch": 0.5350223546944859, "percentage": 10.7, "elapsed_time": "0:09:30", "remaining_time": "1:19:22", "throughput": 5152.98, "total_tokens": 2940928} {"current_steps": 719, "total_steps": 6710, "loss": 1.3065, "lr": 2.4298403555102996e-06, "epoch": 0.5357675111773472, "percentage": 10.72, "elapsed_time": "0:09:31", "remaining_time": "1:19:22", "throughput": 5153.11, "total_tokens": 2945024} {"current_steps": 720, "total_steps": 6710, "loss": 1.2607, "lr": 2.429646913713607e-06, "epoch": 0.5365126676602087, "percentage": 10.73, "elapsed_time": "0:09:32", "remaining_time": "1:19:21", "throughput": 5153.23, "total_tokens": 2949120} {"current_steps": 721, "total_steps": 6710, "loss": 1.2119, "lr": 2.429453213329887e-06, "epoch": 0.53725782414307, "percentage": 10.75, "elapsed_time": "0:09:33", "remaining_time": "1:19:20", "throughput": 5153.36, "total_tokens": 2953216} {"current_steps": 722, "total_steps": 6710, "loss": 1.149, "lr": 2.4292592544016003e-06, "epoch": 0.5380029806259314, "percentage": 10.76, "elapsed_time": "0:09:33", "remaining_time": "1:19:19", "throughput": 5153.4, "total_tokens": 2957312} {"current_steps": 723, "total_steps": 6710, "loss": 1.1457, "lr": 2.4290650369712647e-06, "epoch": 0.5387481371087929, "percentage": 10.77, "elapsed_time": "0:09:34", "remaining_time": "1:19:18", "throughput": 5153.5, "total_tokens": 2961408} {"current_steps": 724, "total_steps": 6710, "loss": 1.3743, "lr": 2.428870561081454e-06, "epoch": 0.5394932935916542, "percentage": 10.79, "elapsed_time": "0:09:35", "remaining_time": "1:19:17", "throughput": 5153.59, "total_tokens": 2965504} {"current_steps": 725, "total_steps": 6710, "loss": 1.4058, "lr": 2.428675826774798e-06, "epoch": 0.5402384500745157, "percentage": 10.8, "elapsed_time": "0:09:36", "remaining_time": "1:19:16", "throughput": 5153.71, "total_tokens": 2969600} {"current_steps": 726, "total_steps": 6710, "loss": 1.5599, "lr": 2.428480834093984e-06, "epoch": 0.5409836065573771, "percentage": 10.82, "elapsed_time": "0:09:36", "remaining_time": "1:19:15", "throughput": 5153.81, "total_tokens": 2973696} {"current_steps": 727, "total_steps": 6710, "loss": 1.2899, "lr": 2.428285583081757e-06, "epoch": 0.5417287630402384, "percentage": 10.83, "elapsed_time": "0:09:37", "remaining_time": "1:19:14", "throughput": 5153.95, "total_tokens": 2977792} {"current_steps": 728, "total_steps": 6710, "loss": 1.2234, "lr": 2.4280900737809157e-06, "epoch": 0.5424739195230999, "percentage": 10.85, "elapsed_time": "0:09:38", "remaining_time": "1:19:13", "throughput": 5154.09, "total_tokens": 2981888} {"current_steps": 729, "total_steps": 6710, "loss": 1.3479, "lr": 2.427894306234318e-06, "epoch": 0.5432190760059612, "percentage": 10.86, "elapsed_time": "0:09:39", "remaining_time": "1:19:13", "throughput": 5154.22, "total_tokens": 2985984} {"current_steps": 730, "total_steps": 6710, "loss": 1.2431, "lr": 2.427698280484878e-06, "epoch": 0.5439642324888226, "percentage": 10.88, "elapsed_time": "0:09:40", "remaining_time": "1:19:12", "throughput": 5154.36, "total_tokens": 2990080} {"current_steps": 731, "total_steps": 6710, "loss": 1.3404, "lr": 2.427501996575565e-06, "epoch": 0.5447093889716841, "percentage": 10.89, "elapsed_time": "0:09:40", "remaining_time": "1:19:11", "throughput": 5154.47, "total_tokens": 2994176} {"current_steps": 732, "total_steps": 6710, "loss": 0.95, "lr": 2.4273054545494064e-06, "epoch": 0.5454545454545454, "percentage": 10.91, "elapsed_time": "0:09:41", "remaining_time": "1:19:10", "throughput": 5154.6, "total_tokens": 2998272} {"current_steps": 733, "total_steps": 6710, "loss": 1.5866, "lr": 2.4271086544494847e-06, "epoch": 0.5461997019374069, "percentage": 10.92, "elapsed_time": "0:09:42", "remaining_time": "1:19:09", "throughput": 5154.72, "total_tokens": 3002368} {"current_steps": 734, "total_steps": 6710, "loss": 1.2454, "lr": 2.4269115963189415e-06, "epoch": 0.5469448584202683, "percentage": 10.94, "elapsed_time": "0:09:43", "remaining_time": "1:19:08", "throughput": 5154.85, "total_tokens": 3006464} {"current_steps": 735, "total_steps": 6710, "loss": 1.2163, "lr": 2.4267142802009722e-06, "epoch": 0.5476900149031296, "percentage": 10.95, "elapsed_time": "0:09:44", "remaining_time": "1:19:07", "throughput": 5154.91, "total_tokens": 3010560} {"current_steps": 736, "total_steps": 6710, "loss": 1.0999, "lr": 2.42651670613883e-06, "epoch": 0.5484351713859911, "percentage": 10.97, "elapsed_time": "0:09:44", "remaining_time": "1:19:06", "throughput": 5154.94, "total_tokens": 3014656} {"current_steps": 737, "total_steps": 6710, "loss": 1.294, "lr": 2.4263188741758254e-06, "epoch": 0.5491803278688525, "percentage": 10.98, "elapsed_time": "0:09:45", "remaining_time": "1:19:06", "throughput": 5154.84, "total_tokens": 3018752} {"current_steps": 738, "total_steps": 6710, "loss": 1.5013, "lr": 2.4261207843553235e-06, "epoch": 0.5499254843517138, "percentage": 11.0, "elapsed_time": "0:09:46", "remaining_time": "1:19:05", "throughput": 5154.86, "total_tokens": 3022848} {"current_steps": 739, "total_steps": 6710, "loss": 1.3703, "lr": 2.4259224367207475e-06, "epoch": 0.5506706408345753, "percentage": 11.01, "elapsed_time": "0:09:47", "remaining_time": "1:19:04", "throughput": 5154.94, "total_tokens": 3026944} {"current_steps": 740, "total_steps": 6710, "loss": 1.4053, "lr": 2.425723831315576e-06, "epoch": 0.5514157973174366, "percentage": 11.03, "elapsed_time": "0:09:47", "remaining_time": "1:19:03", "throughput": 5155.0, "total_tokens": 3031040} {"current_steps": 741, "total_steps": 6710, "loss": 1.3927, "lr": 2.425524968183346e-06, "epoch": 0.5521609538002981, "percentage": 11.04, "elapsed_time": "0:09:48", "remaining_time": "1:19:02", "throughput": 5155.06, "total_tokens": 3035136} {"current_steps": 742, "total_steps": 6710, "loss": 0.9611, "lr": 2.4253258473676485e-06, "epoch": 0.5529061102831595, "percentage": 11.06, "elapsed_time": "0:09:49", "remaining_time": "1:19:01", "throughput": 5155.14, "total_tokens": 3039232} {"current_steps": 743, "total_steps": 6710, "loss": 1.2406, "lr": 2.4251264689121327e-06, "epoch": 0.5536512667660208, "percentage": 11.07, "elapsed_time": "0:09:50", "remaining_time": "1:19:00", "throughput": 5155.21, "total_tokens": 3043328} {"current_steps": 744, "total_steps": 6710, "loss": 1.1565, "lr": 2.424926832860504e-06, "epoch": 0.5543964232488823, "percentage": 11.09, "elapsed_time": "0:09:51", "remaining_time": "1:19:00", "throughput": 5155.3, "total_tokens": 3047424} {"current_steps": 745, "total_steps": 6710, "loss": 1.2893, "lr": 2.4247269392565238e-06, "epoch": 0.5551415797317437, "percentage": 11.1, "elapsed_time": "0:09:51", "remaining_time": "1:18:59", "throughput": 5155.34, "total_tokens": 3051520} {"current_steps": 746, "total_steps": 6710, "loss": 1.3199, "lr": 2.42452678814401e-06, "epoch": 0.555886736214605, "percentage": 11.12, "elapsed_time": "0:09:52", "remaining_time": "1:18:58", "throughput": 5155.4, "total_tokens": 3055616} {"current_steps": 747, "total_steps": 6710, "loss": 1.5452, "lr": 2.4243263795668377e-06, "epoch": 0.5566318926974665, "percentage": 11.13, "elapsed_time": "0:09:53", "remaining_time": "1:18:57", "throughput": 5155.48, "total_tokens": 3059712} {"current_steps": 748, "total_steps": 6710, "loss": 1.1645, "lr": 2.4241257135689374e-06, "epoch": 0.5573770491803278, "percentage": 11.15, "elapsed_time": "0:09:54", "remaining_time": "1:18:56", "throughput": 5155.54, "total_tokens": 3063808} {"current_steps": 749, "total_steps": 6710, "loss": 1.5502, "lr": 2.4239247901942964e-06, "epoch": 0.5581222056631893, "percentage": 11.16, "elapsed_time": "0:09:55", "remaining_time": "1:18:55", "throughput": 5155.62, "total_tokens": 3067904} {"current_steps": 750, "total_steps": 6710, "loss": 1.2269, "lr": 2.423723609486959e-06, "epoch": 0.5588673621460507, "percentage": 11.18, "elapsed_time": "0:09:55", "remaining_time": "1:18:54", "throughput": 5155.7, "total_tokens": 3072000} {"current_steps": 751, "total_steps": 6710, "loss": 1.3736, "lr": 2.4235221714910252e-06, "epoch": 0.559612518628912, "percentage": 11.19, "elapsed_time": "0:09:56", "remaining_time": "1:18:54", "throughput": 5155.75, "total_tokens": 3076096} {"current_steps": 752, "total_steps": 6710, "loss": 1.1629, "lr": 2.4233204762506518e-06, "epoch": 0.5603576751117735, "percentage": 11.21, "elapsed_time": "0:09:57", "remaining_time": "1:18:53", "throughput": 5155.82, "total_tokens": 3080192} {"current_steps": 753, "total_steps": 6710, "loss": 1.2592, "lr": 2.423118523810052e-06, "epoch": 0.5611028315946349, "percentage": 11.22, "elapsed_time": "0:09:58", "remaining_time": "1:18:52", "throughput": 5155.9, "total_tokens": 3084288} {"current_steps": 754, "total_steps": 6710, "loss": 1.0912, "lr": 2.4229163142134945e-06, "epoch": 0.5618479880774963, "percentage": 11.24, "elapsed_time": "0:09:59", "remaining_time": "1:18:51", "throughput": 5155.88, "total_tokens": 3088384} {"current_steps": 755, "total_steps": 6710, "loss": 1.1611, "lr": 2.4227138475053056e-06, "epoch": 0.5625931445603577, "percentage": 11.25, "elapsed_time": "0:09:59", "remaining_time": "1:18:50", "throughput": 5155.94, "total_tokens": 3092480} {"current_steps": 756, "total_steps": 6710, "loss": 0.9464, "lr": 2.422511123729868e-06, "epoch": 0.563338301043219, "percentage": 11.27, "elapsed_time": "0:10:00", "remaining_time": "1:18:50", "throughput": 5155.86, "total_tokens": 3096576} {"current_steps": 757, "total_steps": 6710, "loss": 1.2653, "lr": 2.422308142931619e-06, "epoch": 0.5640834575260805, "percentage": 11.28, "elapsed_time": "0:10:01", "remaining_time": "1:18:49", "throughput": 5155.95, "total_tokens": 3100672} {"current_steps": 758, "total_steps": 6710, "loss": 1.3637, "lr": 2.4221049051550544e-06, "epoch": 0.5648286140089419, "percentage": 11.3, "elapsed_time": "0:10:02", "remaining_time": "1:18:48", "throughput": 5156.02, "total_tokens": 3104768} {"current_steps": 759, "total_steps": 6710, "loss": 1.0185, "lr": 2.4219014104447248e-06, "epoch": 0.5655737704918032, "percentage": 11.31, "elapsed_time": "0:10:02", "remaining_time": "1:18:47", "throughput": 5156.09, "total_tokens": 3108864} {"current_steps": 760, "total_steps": 6710, "loss": 1.5107, "lr": 2.421697658845238e-06, "epoch": 0.5663189269746647, "percentage": 11.33, "elapsed_time": "0:10:03", "remaining_time": "1:18:46", "throughput": 5156.15, "total_tokens": 3112960} {"current_steps": 761, "total_steps": 6710, "loss": 1.3374, "lr": 2.421493650401258e-06, "epoch": 0.5670640834575261, "percentage": 11.34, "elapsed_time": "0:10:04", "remaining_time": "1:18:45", "throughput": 5156.2, "total_tokens": 3117056} {"current_steps": 762, "total_steps": 6710, "loss": 1.661, "lr": 2.4212893851575036e-06, "epoch": 0.5678092399403875, "percentage": 11.36, "elapsed_time": "0:10:05", "remaining_time": "1:18:44", "throughput": 5156.26, "total_tokens": 3121152} {"current_steps": 763, "total_steps": 6710, "loss": 1.0845, "lr": 2.421084863158753e-06, "epoch": 0.5685543964232489, "percentage": 11.37, "elapsed_time": "0:10:06", "remaining_time": "1:18:44", "throughput": 5156.3, "total_tokens": 3125248} {"current_steps": 764, "total_steps": 6710, "loss": 1.21, "lr": 2.420880084449838e-06, "epoch": 0.5692995529061102, "percentage": 11.39, "elapsed_time": "0:10:06", "remaining_time": "1:18:43", "throughput": 5156.32, "total_tokens": 3129344} {"current_steps": 765, "total_steps": 6710, "loss": 1.2289, "lr": 2.4206750490756476e-06, "epoch": 0.5700447093889717, "percentage": 11.4, "elapsed_time": "0:10:07", "remaining_time": "1:18:42", "throughput": 5156.4, "total_tokens": 3133440} {"current_steps": 766, "total_steps": 6710, "loss": 1.0426, "lr": 2.4204697570811274e-06, "epoch": 0.5707898658718331, "percentage": 11.42, "elapsed_time": "0:10:08", "remaining_time": "1:18:41", "throughput": 5156.48, "total_tokens": 3137536} {"current_steps": 767, "total_steps": 6710, "loss": 1.3052, "lr": 2.420264208511278e-06, "epoch": 0.5715350223546944, "percentage": 11.43, "elapsed_time": "0:10:09", "remaining_time": "1:18:40", "throughput": 5156.55, "total_tokens": 3141632} {"current_steps": 768, "total_steps": 6710, "loss": 1.3107, "lr": 2.420058403411158e-06, "epoch": 0.5722801788375559, "percentage": 11.45, "elapsed_time": "0:10:10", "remaining_time": "1:18:39", "throughput": 5156.62, "total_tokens": 3145728} {"current_steps": 769, "total_steps": 6710, "loss": 1.0538, "lr": 2.4198523418258814e-06, "epoch": 0.5730253353204173, "percentage": 11.46, "elapsed_time": "0:10:10", "remaining_time": "1:18:38", "throughput": 5156.73, "total_tokens": 3149824} {"current_steps": 770, "total_steps": 6710, "loss": 1.2781, "lr": 2.419646023800617e-06, "epoch": 0.5737704918032787, "percentage": 11.48, "elapsed_time": "0:10:11", "remaining_time": "1:18:38", "throughput": 5156.82, "total_tokens": 3153920} {"current_steps": 771, "total_steps": 6710, "loss": 1.3699, "lr": 2.419439449380593e-06, "epoch": 0.5745156482861401, "percentage": 11.49, "elapsed_time": "0:10:12", "remaining_time": "1:18:37", "throughput": 5156.91, "total_tokens": 3158016} {"current_steps": 772, "total_steps": 6710, "loss": 1.429, "lr": 2.419232618611091e-06, "epoch": 0.5752608047690015, "percentage": 11.51, "elapsed_time": "0:10:13", "remaining_time": "1:18:36", "throughput": 5157.01, "total_tokens": 3162112} {"current_steps": 773, "total_steps": 6710, "loss": 1.1685, "lr": 2.4190255315374496e-06, "epoch": 0.5760059612518629, "percentage": 11.52, "elapsed_time": "0:10:13", "remaining_time": "1:18:35", "throughput": 5157.11, "total_tokens": 3166208} {"current_steps": 774, "total_steps": 6710, "loss": 1.1626, "lr": 2.4188181882050645e-06, "epoch": 0.5767511177347243, "percentage": 11.54, "elapsed_time": "0:10:14", "remaining_time": "1:18:34", "throughput": 5157.2, "total_tokens": 3170304} {"current_steps": 775, "total_steps": 6710, "loss": 1.2217, "lr": 2.4186105886593862e-06, "epoch": 0.5774962742175856, "percentage": 11.55, "elapsed_time": "0:10:15", "remaining_time": "1:18:33", "throughput": 5157.25, "total_tokens": 3174400} {"current_steps": 776, "total_steps": 6710, "loss": 1.2758, "lr": 2.418402732945922e-06, "epoch": 0.5782414307004471, "percentage": 11.56, "elapsed_time": "0:10:16", "remaining_time": "1:18:32", "throughput": 5157.33, "total_tokens": 3178496} {"current_steps": 777, "total_steps": 6710, "loss": 1.3064, "lr": 2.4181946211102357e-06, "epoch": 0.5789865871833085, "percentage": 11.58, "elapsed_time": "0:10:17", "remaining_time": "1:18:31", "throughput": 5157.4, "total_tokens": 3182592} {"current_steps": 778, "total_steps": 6710, "loss": 1.2424, "lr": 2.417986253197947e-06, "epoch": 0.5797317436661699, "percentage": 11.59, "elapsed_time": "0:10:17", "remaining_time": "1:18:31", "throughput": 5157.48, "total_tokens": 3186688} {"current_steps": 779, "total_steps": 6710, "loss": 1.428, "lr": 2.4177776292547316e-06, "epoch": 0.5804769001490313, "percentage": 11.61, "elapsed_time": "0:10:18", "remaining_time": "1:18:30", "throughput": 5157.55, "total_tokens": 3190784} {"current_steps": 780, "total_steps": 6710, "loss": 1.3414, "lr": 2.417568749326321e-06, "epoch": 0.5812220566318927, "percentage": 11.62, "elapsed_time": "0:10:19", "remaining_time": "1:18:29", "throughput": 5157.62, "total_tokens": 3194880} {"current_steps": 781, "total_steps": 6710, "loss": 1.0248, "lr": 2.4173596134585034e-06, "epoch": 0.5819672131147541, "percentage": 11.64, "elapsed_time": "0:10:20", "remaining_time": "1:18:28", "throughput": 5157.7, "total_tokens": 3198976} {"current_steps": 782, "total_steps": 6710, "loss": 0.9261, "lr": 2.4171502216971226e-06, "epoch": 0.5827123695976155, "percentage": 11.65, "elapsed_time": "0:10:21", "remaining_time": "1:18:27", "throughput": 5157.78, "total_tokens": 3203072} {"current_steps": 783, "total_steps": 6710, "loss": 1.3307, "lr": 2.4169405740880793e-06, "epoch": 0.5834575260804769, "percentage": 11.67, "elapsed_time": "0:10:21", "remaining_time": "1:18:26", "throughput": 5157.87, "total_tokens": 3207168} {"current_steps": 784, "total_steps": 6710, "loss": 1.2326, "lr": 2.4167306706773292e-06, "epoch": 0.5842026825633383, "percentage": 11.68, "elapsed_time": "0:10:22", "remaining_time": "1:18:25", "throughput": 5157.93, "total_tokens": 3211264} {"current_steps": 785, "total_steps": 6710, "loss": 0.9757, "lr": 2.4165205115108854e-06, "epoch": 0.5849478390461997, "percentage": 11.7, "elapsed_time": "0:10:23", "remaining_time": "1:18:25", "throughput": 5158.03, "total_tokens": 3215360} {"current_steps": 786, "total_steps": 6710, "loss": 1.2443, "lr": 2.416310096634815e-06, "epoch": 0.5856929955290611, "percentage": 11.71, "elapsed_time": "0:10:24", "remaining_time": "1:18:24", "throughput": 5158.11, "total_tokens": 3219456} {"current_steps": 787, "total_steps": 6710, "loss": 1.1751, "lr": 2.4160994260952436e-06, "epoch": 0.5864381520119225, "percentage": 11.73, "elapsed_time": "0:10:24", "remaining_time": "1:18:23", "throughput": 5158.19, "total_tokens": 3223552} {"current_steps": 788, "total_steps": 6710, "loss": 1.3353, "lr": 2.4158884999383515e-06, "epoch": 0.587183308494784, "percentage": 11.74, "elapsed_time": "0:10:25", "remaining_time": "1:18:22", "throughput": 5158.29, "total_tokens": 3227648} {"current_steps": 789, "total_steps": 6710, "loss": 0.9832, "lr": 2.4156773182103747e-06, "epoch": 0.5879284649776453, "percentage": 11.76, "elapsed_time": "0:10:26", "remaining_time": "1:18:21", "throughput": 5158.38, "total_tokens": 3231744} {"current_steps": 790, "total_steps": 6710, "loss": 1.2529, "lr": 2.4154658809576066e-06, "epoch": 0.5886736214605067, "percentage": 11.77, "elapsed_time": "0:10:27", "remaining_time": "1:18:20", "throughput": 5158.47, "total_tokens": 3235840} {"current_steps": 791, "total_steps": 6710, "loss": 1.7215, "lr": 2.4152541882263948e-06, "epoch": 0.589418777943368, "percentage": 11.79, "elapsed_time": "0:10:28", "remaining_time": "1:18:19", "throughput": 5158.55, "total_tokens": 3239936} {"current_steps": 792, "total_steps": 6710, "loss": 1.2363, "lr": 2.415042240063144e-06, "epoch": 0.5901639344262295, "percentage": 11.8, "elapsed_time": "0:10:28", "remaining_time": "1:18:18", "throughput": 5158.62, "total_tokens": 3244032} {"current_steps": 793, "total_steps": 6710, "loss": 1.3795, "lr": 2.4148300365143157e-06, "epoch": 0.5909090909090909, "percentage": 11.82, "elapsed_time": "0:10:29", "remaining_time": "1:18:18", "throughput": 5158.69, "total_tokens": 3248128} {"current_steps": 794, "total_steps": 6710, "loss": 1.5385, "lr": 2.414617577626425e-06, "epoch": 0.5916542473919523, "percentage": 11.83, "elapsed_time": "0:10:30", "remaining_time": "1:18:17", "throughput": 5158.77, "total_tokens": 3252224} {"current_steps": 795, "total_steps": 6710, "loss": 1.3681, "lr": 2.414404863446046e-06, "epoch": 0.5923994038748137, "percentage": 11.85, "elapsed_time": "0:10:31", "remaining_time": "1:18:16", "throughput": 5158.83, "total_tokens": 3256320} {"current_steps": 796, "total_steps": 6710, "loss": 1.4527, "lr": 2.414191894019806e-06, "epoch": 0.5931445603576752, "percentage": 11.86, "elapsed_time": "0:10:31", "remaining_time": "1:18:15", "throughput": 5158.92, "total_tokens": 3260416} {"current_steps": 797, "total_steps": 6710, "loss": 1.3565, "lr": 2.4139786693943897e-06, "epoch": 0.5938897168405365, "percentage": 11.88, "elapsed_time": "0:10:32", "remaining_time": "1:18:14", "throughput": 5158.94, "total_tokens": 3264512} {"current_steps": 798, "total_steps": 6710, "loss": 1.046, "lr": 2.4137651896165374e-06, "epoch": 0.5946348733233979, "percentage": 11.89, "elapsed_time": "0:10:33", "remaining_time": "1:18:13", "throughput": 5159.02, "total_tokens": 3268608} {"current_steps": 799, "total_steps": 6710, "loss": 1.4138, "lr": 2.4135514547330455e-06, "epoch": 0.5953800298062594, "percentage": 11.91, "elapsed_time": "0:10:34", "remaining_time": "1:18:12", "throughput": 5159.08, "total_tokens": 3272704} {"current_steps": 800, "total_steps": 6710, "loss": 1.4083, "lr": 2.4133374647907664e-06, "epoch": 0.5961251862891207, "percentage": 11.92, "elapsed_time": "0:10:35", "remaining_time": "1:18:12", "throughput": 5159.16, "total_tokens": 3276800} {"current_steps": 801, "total_steps": 6710, "loss": 1.0277, "lr": 2.413123219836608e-06, "epoch": 0.5968703427719821, "percentage": 11.94, "elapsed_time": "0:10:35", "remaining_time": "1:18:11", "throughput": 5159.22, "total_tokens": 3280896} {"current_steps": 802, "total_steps": 6710, "loss": 1.3456, "lr": 2.4129087199175342e-06, "epoch": 0.5976154992548435, "percentage": 11.95, "elapsed_time": "0:10:36", "remaining_time": "1:18:10", "throughput": 5159.29, "total_tokens": 3284992} {"current_steps": 803, "total_steps": 6710, "loss": 1.3122, "lr": 2.4126939650805658e-06, "epoch": 0.5983606557377049, "percentage": 11.97, "elapsed_time": "0:10:37", "remaining_time": "1:18:09", "throughput": 5159.37, "total_tokens": 3289088} {"current_steps": 804, "total_steps": 6710, "loss": 1.0205, "lr": 2.412478955372777e-06, "epoch": 0.5991058122205664, "percentage": 11.98, "elapsed_time": "0:10:38", "remaining_time": "1:18:08", "throughput": 5159.43, "total_tokens": 3293184} {"current_steps": 805, "total_steps": 6710, "loss": 1.0479, "lr": 2.4122636908413006e-06, "epoch": 0.5998509687034277, "percentage": 12.0, "elapsed_time": "0:10:39", "remaining_time": "1:18:07", "throughput": 5159.51, "total_tokens": 3297280} {"current_steps": 806, "total_steps": 6710, "loss": 1.0664, "lr": 2.412048171533324e-06, "epoch": 0.6005961251862891, "percentage": 12.01, "elapsed_time": "0:10:39", "remaining_time": "1:18:06", "throughput": 5159.59, "total_tokens": 3301376} {"current_steps": 807, "total_steps": 6710, "loss": 1.2646, "lr": 2.4118323974960907e-06, "epoch": 0.6013412816691506, "percentage": 12.03, "elapsed_time": "0:10:40", "remaining_time": "1:18:06", "throughput": 5159.67, "total_tokens": 3305472} {"current_steps": 808, "total_steps": 6710, "loss": 0.8616, "lr": 2.411616368776899e-06, "epoch": 0.6020864381520119, "percentage": 12.04, "elapsed_time": "0:10:41", "remaining_time": "1:18:05", "throughput": 5159.76, "total_tokens": 3309568} {"current_steps": 809, "total_steps": 6710, "loss": 1.0925, "lr": 2.411400085423105e-06, "epoch": 0.6028315946348733, "percentage": 12.06, "elapsed_time": "0:10:42", "remaining_time": "1:18:04", "throughput": 5159.85, "total_tokens": 3313664} {"current_steps": 810, "total_steps": 6710, "loss": 1.0549, "lr": 2.411183547482119e-06, "epoch": 0.6035767511177347, "percentage": 12.07, "elapsed_time": "0:10:42", "remaining_time": "1:18:03", "throughput": 5159.94, "total_tokens": 3317760} {"current_steps": 811, "total_steps": 6710, "loss": 1.3051, "lr": 2.410966755001408e-06, "epoch": 0.6043219076005961, "percentage": 12.09, "elapsed_time": "0:10:43", "remaining_time": "1:18:02", "throughput": 5160.01, "total_tokens": 3321856} {"current_steps": 812, "total_steps": 6710, "loss": 1.3321, "lr": 2.4107497080284937e-06, "epoch": 0.6050670640834576, "percentage": 12.1, "elapsed_time": "0:10:44", "remaining_time": "1:18:01", "throughput": 5160.07, "total_tokens": 3325952} {"current_steps": 813, "total_steps": 6710, "loss": 1.0523, "lr": 2.4105324066109556e-06, "epoch": 0.6058122205663189, "percentage": 12.12, "elapsed_time": "0:10:45", "remaining_time": "1:18:00", "throughput": 5160.14, "total_tokens": 3330048} {"current_steps": 814, "total_steps": 6710, "loss": 1.1885, "lr": 2.4103148507964264e-06, "epoch": 0.6065573770491803, "percentage": 12.13, "elapsed_time": "0:10:46", "remaining_time": "1:18:00", "throughput": 5160.23, "total_tokens": 3334144} {"current_steps": 815, "total_steps": 6710, "loss": 1.5439, "lr": 2.410097040632597e-06, "epoch": 0.6073025335320418, "percentage": 12.15, "elapsed_time": "0:10:46", "remaining_time": "1:17:59", "throughput": 5160.28, "total_tokens": 3338240} {"current_steps": 816, "total_steps": 6710, "loss": 1.3573, "lr": 2.4098789761672127e-06, "epoch": 0.6080476900149031, "percentage": 12.16, "elapsed_time": "0:10:47", "remaining_time": "1:17:58", "throughput": 5160.36, "total_tokens": 3342336} {"current_steps": 817, "total_steps": 6710, "loss": 1.3817, "lr": 2.409660657448074e-06, "epoch": 0.6087928464977646, "percentage": 12.18, "elapsed_time": "0:10:48", "remaining_time": "1:17:57", "throughput": 5160.45, "total_tokens": 3346432} {"current_steps": 818, "total_steps": 6710, "loss": 1.0828, "lr": 2.4094420845230386e-06, "epoch": 0.6095380029806259, "percentage": 12.19, "elapsed_time": "0:10:49", "remaining_time": "1:17:56", "throughput": 5160.53, "total_tokens": 3350528} {"current_steps": 819, "total_steps": 6710, "loss": 1.2243, "lr": 2.409223257440019e-06, "epoch": 0.6102831594634873, "percentage": 12.21, "elapsed_time": "0:10:50", "remaining_time": "1:17:55", "throughput": 5160.56, "total_tokens": 3354624} {"current_steps": 820, "total_steps": 6710, "loss": 1.3524, "lr": 2.409004176246984e-06, "epoch": 0.6110283159463488, "percentage": 12.22, "elapsed_time": "0:10:50", "remaining_time": "1:17:54", "throughput": 5160.61, "total_tokens": 3358720} {"current_steps": 821, "total_steps": 6710, "loss": 1.1358, "lr": 2.4087848409919575e-06, "epoch": 0.6117734724292101, "percentage": 12.24, "elapsed_time": "0:10:51", "remaining_time": "1:17:54", "throughput": 5160.67, "total_tokens": 3362816} {"current_steps": 822, "total_steps": 6710, "loss": 1.3048, "lr": 2.4085652517230192e-06, "epoch": 0.6125186289120715, "percentage": 12.25, "elapsed_time": "0:10:52", "remaining_time": "1:17:53", "throughput": 5160.75, "total_tokens": 3366912} {"current_steps": 823, "total_steps": 6710, "loss": 1.4542, "lr": 2.408345408488305e-06, "epoch": 0.613263785394933, "percentage": 12.27, "elapsed_time": "0:10:53", "remaining_time": "1:17:52", "throughput": 5160.82, "total_tokens": 3371008} {"current_steps": 824, "total_steps": 6710, "loss": 1.0713, "lr": 2.408125311336006e-06, "epoch": 0.6140089418777943, "percentage": 12.28, "elapsed_time": "0:10:53", "remaining_time": "1:17:51", "throughput": 5160.87, "total_tokens": 3375104} {"current_steps": 825, "total_steps": 6710, "loss": 1.5038, "lr": 2.407904960314369e-06, "epoch": 0.6147540983606558, "percentage": 12.3, "elapsed_time": "0:10:54", "remaining_time": "1:17:50", "throughput": 5160.97, "total_tokens": 3379200} {"current_steps": 826, "total_steps": 6710, "loss": 1.1769, "lr": 2.4076843554716965e-06, "epoch": 0.6154992548435171, "percentage": 12.31, "elapsed_time": "0:10:55", "remaining_time": "1:17:49", "throughput": 5161.06, "total_tokens": 3383296} {"current_steps": 827, "total_steps": 6710, "loss": 1.0399, "lr": 2.4074634968563465e-06, "epoch": 0.6162444113263785, "percentage": 12.32, "elapsed_time": "0:10:56", "remaining_time": "1:17:48", "throughput": 5161.14, "total_tokens": 3387392} {"current_steps": 828, "total_steps": 6710, "loss": 1.3285, "lr": 2.407242384516733e-06, "epoch": 0.61698956780924, "percentage": 12.34, "elapsed_time": "0:10:57", "remaining_time": "1:17:48", "throughput": 5161.23, "total_tokens": 3391488} {"current_steps": 829, "total_steps": 6710, "loss": 1.397, "lr": 2.4070210185013256e-06, "epoch": 0.6177347242921013, "percentage": 12.35, "elapsed_time": "0:10:57", "remaining_time": "1:17:47", "throughput": 5161.3, "total_tokens": 3395584} {"current_steps": 830, "total_steps": 6710, "loss": 1.2062, "lr": 2.406799398858649e-06, "epoch": 0.6184798807749627, "percentage": 12.37, "elapsed_time": "0:10:58", "remaining_time": "1:17:46", "throughput": 5161.37, "total_tokens": 3399680} {"current_steps": 831, "total_steps": 6710, "loss": 1.4808, "lr": 2.4065775256372835e-06, "epoch": 0.6192250372578242, "percentage": 12.38, "elapsed_time": "0:10:59", "remaining_time": "1:17:45", "throughput": 5161.38, "total_tokens": 3403776} {"current_steps": 832, "total_steps": 6710, "loss": 1.2355, "lr": 2.406355398885866e-06, "epoch": 0.6199701937406855, "percentage": 12.4, "elapsed_time": "0:11:00", "remaining_time": "1:17:44", "throughput": 5161.44, "total_tokens": 3407872} {"current_steps": 833, "total_steps": 6710, "loss": 1.3289, "lr": 2.406133018653088e-06, "epoch": 0.620715350223547, "percentage": 12.41, "elapsed_time": "0:11:01", "remaining_time": "1:17:43", "throughput": 5161.53, "total_tokens": 3411968} {"current_steps": 834, "total_steps": 6710, "loss": 1.247, "lr": 2.405910384987697e-06, "epoch": 0.6214605067064084, "percentage": 12.43, "elapsed_time": "0:11:01", "remaining_time": "1:17:42", "throughput": 5161.61, "total_tokens": 3416064} {"current_steps": 835, "total_steps": 6710, "loss": 1.3754, "lr": 2.405687497938495e-06, "epoch": 0.6222056631892697, "percentage": 12.44, "elapsed_time": "0:11:02", "remaining_time": "1:17:42", "throughput": 5161.68, "total_tokens": 3420160} {"current_steps": 836, "total_steps": 6710, "loss": 0.8989, "lr": 2.4054643575543414e-06, "epoch": 0.6229508196721312, "percentage": 12.46, "elapsed_time": "0:11:03", "remaining_time": "1:17:41", "throughput": 5161.79, "total_tokens": 3424256} {"current_steps": 837, "total_steps": 6710, "loss": 1.2362, "lr": 2.4052409638841503e-06, "epoch": 0.6236959761549925, "percentage": 12.47, "elapsed_time": "0:11:04", "remaining_time": "1:17:40", "throughput": 5161.88, "total_tokens": 3428352} {"current_steps": 838, "total_steps": 6710, "loss": 1.2858, "lr": 2.4050173169768903e-06, "epoch": 0.624441132637854, "percentage": 12.49, "elapsed_time": "0:11:04", "remaining_time": "1:17:39", "throughput": 5161.94, "total_tokens": 3432448} {"current_steps": 839, "total_steps": 6710, "loss": 1.3605, "lr": 2.404793416881587e-06, "epoch": 0.6251862891207154, "percentage": 12.5, "elapsed_time": "0:11:05", "remaining_time": "1:17:38", "throughput": 5161.98, "total_tokens": 3436544} {"current_steps": 840, "total_steps": 6710, "loss": 0.9805, "lr": 2.4045692636473206e-06, "epoch": 0.6259314456035767, "percentage": 12.52, "elapsed_time": "0:11:06", "remaining_time": "1:17:37", "throughput": 5162.07, "total_tokens": 3440640} {"current_steps": 841, "total_steps": 6710, "loss": 1.2875, "lr": 2.4043448573232273e-06, "epoch": 0.6266766020864382, "percentage": 12.53, "elapsed_time": "0:11:07", "remaining_time": "1:17:36", "throughput": 5162.16, "total_tokens": 3444736} {"current_steps": 842, "total_steps": 6710, "loss": 1.18, "lr": 2.404120197958499e-06, "epoch": 0.6274217585692996, "percentage": 12.55, "elapsed_time": "0:11:08", "remaining_time": "1:17:35", "throughput": 5162.24, "total_tokens": 3448832} {"current_steps": 843, "total_steps": 6710, "loss": 1.0681, "lr": 2.4038952856023816e-06, "epoch": 0.6281669150521609, "percentage": 12.56, "elapsed_time": "0:11:08", "remaining_time": "1:17:35", "throughput": 5162.33, "total_tokens": 3452928} {"current_steps": 844, "total_steps": 6710, "loss": 1.157, "lr": 2.403670120304178e-06, "epoch": 0.6289120715350224, "percentage": 12.58, "elapsed_time": "0:11:09", "remaining_time": "1:17:34", "throughput": 5162.42, "total_tokens": 3457024} {"current_steps": 845, "total_steps": 6710, "loss": 1.3828, "lr": 2.403444702113246e-06, "epoch": 0.6296572280178837, "percentage": 12.59, "elapsed_time": "0:11:10", "remaining_time": "1:17:33", "throughput": 5162.5, "total_tokens": 3461120} {"current_steps": 846, "total_steps": 6710, "loss": 1.6265, "lr": 2.4032190310789996e-06, "epoch": 0.6304023845007451, "percentage": 12.61, "elapsed_time": "0:11:11", "remaining_time": "1:17:32", "throughput": 5162.51, "total_tokens": 3465216} {"current_steps": 847, "total_steps": 6710, "loss": 0.9738, "lr": 2.4029931072509066e-06, "epoch": 0.6311475409836066, "percentage": 12.62, "elapsed_time": "0:11:12", "remaining_time": "1:17:31", "throughput": 5162.58, "total_tokens": 3469312} {"current_steps": 848, "total_steps": 6710, "loss": 1.4362, "lr": 2.4027669306784914e-06, "epoch": 0.6318926974664679, "percentage": 12.64, "elapsed_time": "0:11:12", "remaining_time": "1:17:30", "throughput": 5162.65, "total_tokens": 3473408} {"current_steps": 849, "total_steps": 6710, "loss": 1.9489, "lr": 2.4025405014113333e-06, "epoch": 0.6326378539493294, "percentage": 12.65, "elapsed_time": "0:11:13", "remaining_time": "1:17:29", "throughput": 5162.75, "total_tokens": 3477504} {"current_steps": 850, "total_steps": 6710, "loss": 1.211, "lr": 2.4023138194990677e-06, "epoch": 0.6333830104321908, "percentage": 12.67, "elapsed_time": "0:11:14", "remaining_time": "1:17:29", "throughput": 5162.84, "total_tokens": 3481600} {"current_steps": 851, "total_steps": 6710, "loss": 1.6616, "lr": 2.402086884991384e-06, "epoch": 0.6341281669150521, "percentage": 12.68, "elapsed_time": "0:11:15", "remaining_time": "1:17:28", "throughput": 5162.93, "total_tokens": 3485696} {"current_steps": 852, "total_steps": 6710, "loss": 1.2117, "lr": 2.401859697938029e-06, "epoch": 0.6348733233979136, "percentage": 12.7, "elapsed_time": "0:11:15", "remaining_time": "1:17:27", "throughput": 5162.97, "total_tokens": 3489792} {"current_steps": 853, "total_steps": 6710, "loss": 1.2683, "lr": 2.401632258388803e-06, "epoch": 0.6356184798807749, "percentage": 12.71, "elapsed_time": "0:11:16", "remaining_time": "1:17:26", "throughput": 5163.04, "total_tokens": 3493888} {"current_steps": 854, "total_steps": 6710, "loss": 1.4729, "lr": 2.4014045663935627e-06, "epoch": 0.6363636363636364, "percentage": 12.73, "elapsed_time": "0:11:17", "remaining_time": "1:17:25", "throughput": 5163.09, "total_tokens": 3497984} {"current_steps": 855, "total_steps": 6710, "loss": 1.0317, "lr": 2.4011766220022197e-06, "epoch": 0.6371087928464978, "percentage": 12.74, "elapsed_time": "0:11:18", "remaining_time": "1:17:24", "throughput": 5163.16, "total_tokens": 3502080} {"current_steps": 856, "total_steps": 6710, "loss": 1.3454, "lr": 2.400948425264741e-06, "epoch": 0.6378539493293591, "percentage": 12.76, "elapsed_time": "0:11:19", "remaining_time": "1:17:24", "throughput": 5163.2, "total_tokens": 3506176} {"current_steps": 857, "total_steps": 6710, "loss": 1.4704, "lr": 2.400719976231149e-06, "epoch": 0.6385991058122206, "percentage": 12.77, "elapsed_time": "0:11:19", "remaining_time": "1:17:23", "throughput": 5163.27, "total_tokens": 3510272} {"current_steps": 858, "total_steps": 6710, "loss": 1.4298, "lr": 2.4004912749515213e-06, "epoch": 0.639344262295082, "percentage": 12.79, "elapsed_time": "0:11:20", "remaining_time": "1:17:22", "throughput": 5163.33, "total_tokens": 3514368} {"current_steps": 859, "total_steps": 6710, "loss": 1.129, "lr": 2.400262321475991e-06, "epoch": 0.6400894187779433, "percentage": 12.8, "elapsed_time": "0:11:21", "remaining_time": "1:17:21", "throughput": 5163.38, "total_tokens": 3518464} {"current_steps": 860, "total_steps": 6710, "loss": 1.337, "lr": 2.400033115854746e-06, "epoch": 0.6408345752608048, "percentage": 12.82, "elapsed_time": "0:11:22", "remaining_time": "1:17:20", "throughput": 5163.47, "total_tokens": 3522560} {"current_steps": 861, "total_steps": 6710, "loss": 1.027, "lr": 2.39980365813803e-06, "epoch": 0.6415797317436661, "percentage": 12.83, "elapsed_time": "0:11:22", "remaining_time": "1:17:19", "throughput": 5163.51, "total_tokens": 3526656} {"current_steps": 862, "total_steps": 6710, "loss": 1.116, "lr": 2.399573948376142e-06, "epoch": 0.6423248882265276, "percentage": 12.85, "elapsed_time": "0:11:23", "remaining_time": "1:17:18", "throughput": 5163.58, "total_tokens": 3530752} {"current_steps": 863, "total_steps": 6710, "loss": 1.1201, "lr": 2.3993439866194358e-06, "epoch": 0.643070044709389, "percentage": 12.86, "elapsed_time": "0:11:24", "remaining_time": "1:17:18", "throughput": 5163.64, "total_tokens": 3534848} {"current_steps": 864, "total_steps": 6710, "loss": 1.3722, "lr": 2.3991137729183205e-06, "epoch": 0.6438152011922503, "percentage": 12.88, "elapsed_time": "0:11:25", "remaining_time": "1:17:17", "throughput": 5163.7, "total_tokens": 3538944} {"current_steps": 865, "total_steps": 6710, "loss": 1.1371, "lr": 2.3988833073232614e-06, "epoch": 0.6445603576751118, "percentage": 12.89, "elapsed_time": "0:11:26", "remaining_time": "1:17:16", "throughput": 5163.75, "total_tokens": 3543040} {"current_steps": 866, "total_steps": 6710, "loss": 1.1571, "lr": 2.3986525898847766e-06, "epoch": 0.6453055141579732, "percentage": 12.91, "elapsed_time": "0:11:26", "remaining_time": "1:17:15", "throughput": 5163.81, "total_tokens": 3547136} {"current_steps": 867, "total_steps": 6710, "loss": 1.5149, "lr": 2.3984216206534426e-06, "epoch": 0.6460506706408345, "percentage": 12.92, "elapsed_time": "0:11:27", "remaining_time": "1:17:14", "throughput": 5163.9, "total_tokens": 3551232} {"current_steps": 868, "total_steps": 6710, "loss": 1.1092, "lr": 2.398190399679889e-06, "epoch": 0.646795827123696, "percentage": 12.94, "elapsed_time": "0:11:28", "remaining_time": "1:17:13", "throughput": 5163.99, "total_tokens": 3555328} {"current_steps": 869, "total_steps": 6710, "loss": 0.9001, "lr": 2.3979589270148006e-06, "epoch": 0.6475409836065574, "percentage": 12.95, "elapsed_time": "0:11:29", "remaining_time": "1:17:12", "throughput": 5164.06, "total_tokens": 3559424} {"current_steps": 870, "total_steps": 6710, "loss": 1.3023, "lr": 2.3977272027089184e-06, "epoch": 0.6482861400894188, "percentage": 12.97, "elapsed_time": "0:11:30", "remaining_time": "1:17:12", "throughput": 5164.12, "total_tokens": 3563520} {"current_steps": 871, "total_steps": 6710, "loss": 1.3731, "lr": 2.397495226813038e-06, "epoch": 0.6490312965722802, "percentage": 12.98, "elapsed_time": "0:11:30", "remaining_time": "1:17:11", "throughput": 5164.2, "total_tokens": 3567616} {"current_steps": 872, "total_steps": 6710, "loss": 1.08, "lr": 2.39726299937801e-06, "epoch": 0.6497764530551415, "percentage": 13.0, "elapsed_time": "0:11:31", "remaining_time": "1:17:10", "throughput": 5164.3, "total_tokens": 3571712} {"current_steps": 873, "total_steps": 6710, "loss": 1.35, "lr": 2.39703052045474e-06, "epoch": 0.650521609538003, "percentage": 13.01, "elapsed_time": "0:11:32", "remaining_time": "1:17:09", "throughput": 5164.38, "total_tokens": 3575808} {"current_steps": 874, "total_steps": 6710, "loss": 1.6071, "lr": 2.3967977900941895e-06, "epoch": 0.6512667660208644, "percentage": 13.03, "elapsed_time": "0:11:33", "remaining_time": "1:17:08", "throughput": 5164.46, "total_tokens": 3579904} {"current_steps": 875, "total_steps": 6710, "loss": 1.6211, "lr": 2.396564808347375e-06, "epoch": 0.6520119225037257, "percentage": 13.04, "elapsed_time": "0:11:33", "remaining_time": "1:17:07", "throughput": 5164.55, "total_tokens": 3584000} {"current_steps": 876, "total_steps": 6710, "loss": 1.3252, "lr": 2.3963315752653666e-06, "epoch": 0.6527570789865872, "percentage": 13.06, "elapsed_time": "0:11:34", "remaining_time": "1:17:06", "throughput": 5164.63, "total_tokens": 3588096} {"current_steps": 877, "total_steps": 6710, "loss": 1.256, "lr": 2.396098090899292e-06, "epoch": 0.6535022354694486, "percentage": 13.07, "elapsed_time": "0:11:35", "remaining_time": "1:17:06", "throughput": 5164.71, "total_tokens": 3592192} {"current_steps": 878, "total_steps": 6710, "loss": 1.4644, "lr": 2.395864355300332e-06, "epoch": 0.65424739195231, "percentage": 13.08, "elapsed_time": "0:11:36", "remaining_time": "1:17:05", "throughput": 5164.8, "total_tokens": 3596288} {"current_steps": 879, "total_steps": 6710, "loss": 1.3268, "lr": 2.3956303685197225e-06, "epoch": 0.6549925484351714, "percentage": 13.1, "elapsed_time": "0:11:37", "remaining_time": "1:17:04", "throughput": 5164.87, "total_tokens": 3600384} {"current_steps": 880, "total_steps": 6710, "loss": 1.3351, "lr": 2.3953961306087563e-06, "epoch": 0.6557377049180327, "percentage": 13.11, "elapsed_time": "0:11:37", "remaining_time": "1:17:03", "throughput": 5164.81, "total_tokens": 3604480} {"current_steps": 881, "total_steps": 6710, "loss": 1.4455, "lr": 2.3951616416187788e-06, "epoch": 0.6564828614008942, "percentage": 13.13, "elapsed_time": "0:11:38", "remaining_time": "1:17:02", "throughput": 5164.89, "total_tokens": 3608576} {"current_steps": 882, "total_steps": 6710, "loss": 1.5285, "lr": 2.394926901601193e-06, "epoch": 0.6572280178837556, "percentage": 13.14, "elapsed_time": "0:11:39", "remaining_time": "1:17:01", "throughput": 5164.92, "total_tokens": 3612672} {"current_steps": 883, "total_steps": 6710, "loss": 0.969, "lr": 2.394691910607454e-06, "epoch": 0.657973174366617, "percentage": 13.16, "elapsed_time": "0:11:40", "remaining_time": "1:17:00", "throughput": 5165.01, "total_tokens": 3616768} {"current_steps": 884, "total_steps": 6710, "loss": 1.3137, "lr": 2.3944566686890753e-06, "epoch": 0.6587183308494784, "percentage": 13.17, "elapsed_time": "0:11:41", "remaining_time": "1:17:00", "throughput": 5165.1, "total_tokens": 3620864} {"current_steps": 885, "total_steps": 6710, "loss": 1.1338, "lr": 2.394221175897622e-06, "epoch": 0.6594634873323398, "percentage": 13.19, "elapsed_time": "0:11:41", "remaining_time": "1:16:59", "throughput": 5165.19, "total_tokens": 3624960} {"current_steps": 886, "total_steps": 6710, "loss": 1.3286, "lr": 2.3939854322847165e-06, "epoch": 0.6602086438152012, "percentage": 13.2, "elapsed_time": "0:11:42", "remaining_time": "1:16:58", "throughput": 5165.27, "total_tokens": 3629056} {"current_steps": 887, "total_steps": 6710, "loss": 1.4376, "lr": 2.393749437902036e-06, "epoch": 0.6609538002980626, "percentage": 13.22, "elapsed_time": "0:11:43", "remaining_time": "1:16:57", "throughput": 5165.36, "total_tokens": 3633152} {"current_steps": 888, "total_steps": 6710, "loss": 1.4718, "lr": 2.393513192801311e-06, "epoch": 0.6616989567809239, "percentage": 13.23, "elapsed_time": "0:11:44", "remaining_time": "1:16:56", "throughput": 5165.44, "total_tokens": 3637248} {"current_steps": 889, "total_steps": 6710, "loss": 1.4197, "lr": 2.393276697034329e-06, "epoch": 0.6624441132637854, "percentage": 13.25, "elapsed_time": "0:11:44", "remaining_time": "1:16:55", "throughput": 5165.53, "total_tokens": 3641344} {"current_steps": 890, "total_steps": 6710, "loss": 1.4711, "lr": 2.3930399506529316e-06, "epoch": 0.6631892697466468, "percentage": 13.26, "elapsed_time": "0:11:45", "remaining_time": "1:16:54", "throughput": 5165.61, "total_tokens": 3645440} {"current_steps": 891, "total_steps": 6710, "loss": 1.0811, "lr": 2.3928029537090146e-06, "epoch": 0.6639344262295082, "percentage": 13.28, "elapsed_time": "0:11:46", "remaining_time": "1:16:54", "throughput": 5165.69, "total_tokens": 3649536} {"current_steps": 892, "total_steps": 6710, "loss": 1.3585, "lr": 2.39256570625453e-06, "epoch": 0.6646795827123696, "percentage": 13.29, "elapsed_time": "0:11:47", "remaining_time": "1:16:53", "throughput": 5165.75, "total_tokens": 3653632} {"current_steps": 893, "total_steps": 6710, "loss": 1.08, "lr": 2.3923282083414837e-06, "epoch": 0.665424739195231, "percentage": 13.31, "elapsed_time": "0:11:48", "remaining_time": "1:16:52", "throughput": 5165.83, "total_tokens": 3657728} {"current_steps": 894, "total_steps": 6710, "loss": 1.5732, "lr": 2.3920904600219374e-06, "epoch": 0.6661698956780924, "percentage": 13.32, "elapsed_time": "0:11:48", "remaining_time": "1:16:51", "throughput": 5165.92, "total_tokens": 3661824} {"current_steps": 895, "total_steps": 6710, "loss": 1.4815, "lr": 2.3918524613480066e-06, "epoch": 0.6669150521609538, "percentage": 13.34, "elapsed_time": "0:11:49", "remaining_time": "1:16:50", "throughput": 5166.0, "total_tokens": 3665920} {"current_steps": 896, "total_steps": 6710, "loss": 1.4483, "lr": 2.391614212371863e-06, "epoch": 0.6676602086438153, "percentage": 13.35, "elapsed_time": "0:11:50", "remaining_time": "1:16:49", "throughput": 5166.09, "total_tokens": 3670016} {"current_steps": 897, "total_steps": 6710, "loss": 1.2528, "lr": 2.391375713145732e-06, "epoch": 0.6684053651266766, "percentage": 13.37, "elapsed_time": "0:11:51", "remaining_time": "1:16:48", "throughput": 5166.18, "total_tokens": 3674112} {"current_steps": 898, "total_steps": 6710, "loss": 1.3198, "lr": 2.391136963721895e-06, "epoch": 0.669150521609538, "percentage": 13.38, "elapsed_time": "0:11:51", "remaining_time": "1:16:47", "throughput": 5166.25, "total_tokens": 3678208} {"current_steps": 899, "total_steps": 6710, "loss": 1.0639, "lr": 2.390897964152687e-06, "epoch": 0.6698956780923994, "percentage": 13.4, "elapsed_time": "0:11:52", "remaining_time": "1:16:47", "throughput": 5166.34, "total_tokens": 3682304} {"current_steps": 900, "total_steps": 6710, "loss": 1.1768, "lr": 2.390658714490498e-06, "epoch": 0.6706408345752608, "percentage": 13.41, "elapsed_time": "0:11:53", "remaining_time": "1:16:46", "throughput": 5166.42, "total_tokens": 3686400} {"current_steps": 901, "total_steps": 6710, "loss": 1.5266, "lr": 2.390419214787774e-06, "epoch": 0.6713859910581222, "percentage": 13.43, "elapsed_time": "0:11:54", "remaining_time": "1:16:45", "throughput": 5166.52, "total_tokens": 3690496} {"current_steps": 902, "total_steps": 6710, "loss": 1.4232, "lr": 2.3901794650970153e-06, "epoch": 0.6721311475409836, "percentage": 13.44, "elapsed_time": "0:11:55", "remaining_time": "1:16:44", "throughput": 5166.62, "total_tokens": 3694592} {"current_steps": 903, "total_steps": 6710, "loss": 1.4031, "lr": 2.389939465470776e-06, "epoch": 0.672876304023845, "percentage": 13.46, "elapsed_time": "0:11:55", "remaining_time": "1:16:43", "throughput": 5166.7, "total_tokens": 3698688} {"current_steps": 904, "total_steps": 6710, "loss": 1.1351, "lr": 2.3896992159616657e-06, "epoch": 0.6736214605067065, "percentage": 13.47, "elapsed_time": "0:11:56", "remaining_time": "1:16:42", "throughput": 5166.8, "total_tokens": 3702784} {"current_steps": 905, "total_steps": 6710, "loss": 1.0706, "lr": 2.3894587166223493e-06, "epoch": 0.6743666169895678, "percentage": 13.49, "elapsed_time": "0:11:57", "remaining_time": "1:16:41", "throughput": 5166.89, "total_tokens": 3706880} {"current_steps": 906, "total_steps": 6710, "loss": 1.3011, "lr": 2.3892179675055457e-06, "epoch": 0.6751117734724292, "percentage": 13.5, "elapsed_time": "0:11:58", "remaining_time": "1:16:40", "throughput": 5166.97, "total_tokens": 3710976} {"current_steps": 907, "total_steps": 6710, "loss": 1.1733, "lr": 2.3889769686640283e-06, "epoch": 0.6758569299552906, "percentage": 13.52, "elapsed_time": "0:11:58", "remaining_time": "1:16:40", "throughput": 5167.01, "total_tokens": 3715072} {"current_steps": 908, "total_steps": 6710, "loss": 1.1269, "lr": 2.388735720150627e-06, "epoch": 0.676602086438152, "percentage": 13.53, "elapsed_time": "0:11:59", "remaining_time": "1:16:39", "throughput": 5167.06, "total_tokens": 3719168} {"current_steps": 909, "total_steps": 6710, "loss": 1.3924, "lr": 2.3884942220182244e-06, "epoch": 0.6773472429210134, "percentage": 13.55, "elapsed_time": "0:12:00", "remaining_time": "1:16:38", "throughput": 5167.11, "total_tokens": 3723264} {"current_steps": 910, "total_steps": 6710, "loss": 1.4298, "lr": 2.388252474319759e-06, "epoch": 0.6780923994038748, "percentage": 13.56, "elapsed_time": "0:12:01", "remaining_time": "1:16:37", "throughput": 5167.2, "total_tokens": 3727360} {"current_steps": 911, "total_steps": 6710, "loss": 1.0164, "lr": 2.388010477108223e-06, "epoch": 0.6788375558867362, "percentage": 13.58, "elapsed_time": "0:12:02", "remaining_time": "1:16:36", "throughput": 5167.29, "total_tokens": 3731456} {"current_steps": 912, "total_steps": 6710, "loss": 1.2606, "lr": 2.3877682304366645e-06, "epoch": 0.6795827123695977, "percentage": 13.59, "elapsed_time": "0:12:02", "remaining_time": "1:16:35", "throughput": 5167.4, "total_tokens": 3735552} {"current_steps": 913, "total_steps": 6710, "loss": 1.3982, "lr": 2.3875257343581856e-06, "epoch": 0.680327868852459, "percentage": 13.61, "elapsed_time": "0:12:03", "remaining_time": "1:16:34", "throughput": 5167.49, "total_tokens": 3739648} {"current_steps": 914, "total_steps": 6710, "loss": 1.2133, "lr": 2.387282988925943e-06, "epoch": 0.6810730253353204, "percentage": 13.62, "elapsed_time": "0:12:04", "remaining_time": "1:16:34", "throughput": 5167.58, "total_tokens": 3743744} {"current_steps": 915, "total_steps": 6710, "loss": 1.6279, "lr": 2.3870399941931483e-06, "epoch": 0.6818181818181818, "percentage": 13.64, "elapsed_time": "0:12:05", "remaining_time": "1:16:33", "throughput": 5167.66, "total_tokens": 3747840} {"current_steps": 916, "total_steps": 6710, "loss": 1.4502, "lr": 2.3867967502130674e-06, "epoch": 0.6825633383010432, "percentage": 13.65, "elapsed_time": "0:12:06", "remaining_time": "1:16:32", "throughput": 5167.76, "total_tokens": 3751936} {"current_steps": 917, "total_steps": 6710, "loss": 1.2153, "lr": 2.3865532570390214e-06, "epoch": 0.6833084947839047, "percentage": 13.67, "elapsed_time": "0:12:06", "remaining_time": "1:16:31", "throughput": 5167.85, "total_tokens": 3756032} {"current_steps": 918, "total_steps": 6710, "loss": 1.2165, "lr": 2.3863095147243863e-06, "epoch": 0.684053651266766, "percentage": 13.68, "elapsed_time": "0:12:07", "remaining_time": "1:16:30", "throughput": 5167.95, "total_tokens": 3760128} {"current_steps": 919, "total_steps": 6710, "loss": 1.13, "lr": 2.386065523322591e-06, "epoch": 0.6847988077496274, "percentage": 13.7, "elapsed_time": "0:12:08", "remaining_time": "1:16:29", "throughput": 5168.04, "total_tokens": 3764224} {"current_steps": 920, "total_steps": 6710, "loss": 1.3527, "lr": 2.3858212828871213e-06, "epoch": 0.6855439642324889, "percentage": 13.71, "elapsed_time": "0:12:09", "remaining_time": "1:16:28", "throughput": 5168.12, "total_tokens": 3768320} {"current_steps": 921, "total_steps": 6710, "loss": 1.3477, "lr": 2.3855767934715154e-06, "epoch": 0.6862891207153502, "percentage": 13.73, "elapsed_time": "0:12:09", "remaining_time": "1:16:28", "throughput": 5168.08, "total_tokens": 3772416} {"current_steps": 922, "total_steps": 6710, "loss": 1.2423, "lr": 2.385332055129368e-06, "epoch": 0.6870342771982116, "percentage": 13.74, "elapsed_time": "0:12:10", "remaining_time": "1:16:27", "throughput": 5168.18, "total_tokens": 3776512} {"current_steps": 923, "total_steps": 6710, "loss": 1.1732, "lr": 2.3850870679143268e-06, "epoch": 0.687779433681073, "percentage": 13.76, "elapsed_time": "0:12:11", "remaining_time": "1:16:26", "throughput": 5168.22, "total_tokens": 3780608} {"current_steps": 924, "total_steps": 6710, "loss": 1.2838, "lr": 2.3848418318800954e-06, "epoch": 0.6885245901639344, "percentage": 13.77, "elapsed_time": "0:12:12", "remaining_time": "1:16:25", "throughput": 5168.31, "total_tokens": 3784704} {"current_steps": 925, "total_steps": 6710, "loss": 1.463, "lr": 2.384596347080431e-06, "epoch": 0.6892697466467959, "percentage": 13.79, "elapsed_time": "0:12:13", "remaining_time": "1:16:24", "throughput": 5168.4, "total_tokens": 3788800} {"current_steps": 926, "total_steps": 6710, "loss": 1.1807, "lr": 2.384350613569145e-06, "epoch": 0.6900149031296572, "percentage": 13.8, "elapsed_time": "0:12:13", "remaining_time": "1:16:23", "throughput": 5168.51, "total_tokens": 3792896} {"current_steps": 927, "total_steps": 6710, "loss": 1.1445, "lr": 2.384104631400105e-06, "epoch": 0.6907600596125186, "percentage": 13.82, "elapsed_time": "0:12:14", "remaining_time": "1:16:22", "throughput": 5168.53, "total_tokens": 3796992} {"current_steps": 928, "total_steps": 6710, "loss": 0.9957, "lr": 2.3838584006272313e-06, "epoch": 0.6915052160953801, "percentage": 13.83, "elapsed_time": "0:12:15", "remaining_time": "1:16:22", "throughput": 5168.62, "total_tokens": 3801088} {"current_steps": 929, "total_steps": 6710, "loss": 1.0374, "lr": 2.3836119213045e-06, "epoch": 0.6922503725782414, "percentage": 13.85, "elapsed_time": "0:12:16", "remaining_time": "1:16:21", "throughput": 5168.7, "total_tokens": 3805184} {"current_steps": 930, "total_steps": 6710, "loss": 0.9511, "lr": 2.383365193485941e-06, "epoch": 0.6929955290611028, "percentage": 13.86, "elapsed_time": "0:12:16", "remaining_time": "1:16:20", "throughput": 5168.79, "total_tokens": 3809280} {"current_steps": 931, "total_steps": 6710, "loss": 1.1104, "lr": 2.3831182172256377e-06, "epoch": 0.6937406855439643, "percentage": 13.87, "elapsed_time": "0:12:17", "remaining_time": "1:16:19", "throughput": 5168.87, "total_tokens": 3813376} {"current_steps": 932, "total_steps": 6710, "loss": 1.3981, "lr": 2.382870992577731e-06, "epoch": 0.6944858420268256, "percentage": 13.89, "elapsed_time": "0:12:18", "remaining_time": "1:16:18", "throughput": 5168.97, "total_tokens": 3817472} {"current_steps": 933, "total_steps": 6710, "loss": 1.299, "lr": 2.382623519596413e-06, "epoch": 0.6952309985096871, "percentage": 13.9, "elapsed_time": "0:12:19", "remaining_time": "1:16:17", "throughput": 5169.04, "total_tokens": 3821568} {"current_steps": 934, "total_steps": 6710, "loss": 1.4596, "lr": 2.3823757983359315e-06, "epoch": 0.6959761549925484, "percentage": 13.92, "elapsed_time": "0:12:20", "remaining_time": "1:16:16", "throughput": 5169.13, "total_tokens": 3825664} {"current_steps": 935, "total_steps": 6710, "loss": 1.4286, "lr": 2.3821278288505894e-06, "epoch": 0.6967213114754098, "percentage": 13.93, "elapsed_time": "0:12:20", "remaining_time": "1:16:16", "throughput": 5169.16, "total_tokens": 3829760} {"current_steps": 936, "total_steps": 6710, "loss": 1.2375, "lr": 2.3818796111947433e-06, "epoch": 0.6974664679582713, "percentage": 13.95, "elapsed_time": "0:12:21", "remaining_time": "1:16:15", "throughput": 5169.22, "total_tokens": 3833856} {"current_steps": 937, "total_steps": 6710, "loss": 1.1216, "lr": 2.3816311454228037e-06, "epoch": 0.6982116244411326, "percentage": 13.96, "elapsed_time": "0:12:22", "remaining_time": "1:16:14", "throughput": 5169.31, "total_tokens": 3837952} {"current_steps": 938, "total_steps": 6710, "loss": 1.353, "lr": 2.381382431589237e-06, "epoch": 0.698956780923994, "percentage": 13.98, "elapsed_time": "0:12:23", "remaining_time": "1:16:13", "throughput": 5169.38, "total_tokens": 3842048} {"current_steps": 939, "total_steps": 6710, "loss": 1.3062, "lr": 2.381133469748562e-06, "epoch": 0.6997019374068555, "percentage": 13.99, "elapsed_time": "0:12:24", "remaining_time": "1:16:12", "throughput": 5169.47, "total_tokens": 3846144} {"current_steps": 940, "total_steps": 6710, "loss": 1.4833, "lr": 2.3808842599553533e-06, "epoch": 0.7004470938897168, "percentage": 14.01, "elapsed_time": "0:12:24", "remaining_time": "1:16:11", "throughput": 5169.52, "total_tokens": 3850240} {"current_steps": 941, "total_steps": 6710, "loss": 1.0806, "lr": 2.38063480226424e-06, "epoch": 0.7011922503725783, "percentage": 14.02, "elapsed_time": "0:12:25", "remaining_time": "1:16:10", "throughput": 5169.6, "total_tokens": 3854336} {"current_steps": 942, "total_steps": 6710, "loss": 1.516, "lr": 2.3803850967299046e-06, "epoch": 0.7019374068554396, "percentage": 14.04, "elapsed_time": "0:12:26", "remaining_time": "1:16:10", "throughput": 5169.69, "total_tokens": 3858432} {"current_steps": 943, "total_steps": 6710, "loss": 1.4738, "lr": 2.380135143407084e-06, "epoch": 0.702682563338301, "percentage": 14.05, "elapsed_time": "0:12:27", "remaining_time": "1:16:09", "throughput": 5169.78, "total_tokens": 3862528} {"current_steps": 944, "total_steps": 6710, "loss": 1.2424, "lr": 2.3798849423505705e-06, "epoch": 0.7034277198211625, "percentage": 14.07, "elapsed_time": "0:12:27", "remaining_time": "1:16:08", "throughput": 5169.86, "total_tokens": 3866624} {"current_steps": 945, "total_steps": 6710, "loss": 1.5676, "lr": 2.379634493615209e-06, "epoch": 0.7041728763040238, "percentage": 14.08, "elapsed_time": "0:12:28", "remaining_time": "1:16:07", "throughput": 5169.92, "total_tokens": 3870720} {"current_steps": 946, "total_steps": 6710, "loss": 1.1493, "lr": 2.3793837972559005e-06, "epoch": 0.7049180327868853, "percentage": 14.1, "elapsed_time": "0:12:29", "remaining_time": "1:16:06", "throughput": 5170.0, "total_tokens": 3874816} {"current_steps": 947, "total_steps": 6710, "loss": 1.2209, "lr": 2.379132853327599e-06, "epoch": 0.7056631892697467, "percentage": 14.11, "elapsed_time": "0:12:30", "remaining_time": "1:16:05", "throughput": 5170.07, "total_tokens": 3878912} {"current_steps": 948, "total_steps": 6710, "loss": 1.2003, "lr": 2.3788816618853134e-06, "epoch": 0.706408345752608, "percentage": 14.13, "elapsed_time": "0:12:31", "remaining_time": "1:16:04", "throughput": 5170.16, "total_tokens": 3883008} {"current_steps": 949, "total_steps": 6710, "loss": 1.3086, "lr": 2.3786302229841067e-06, "epoch": 0.7071535022354695, "percentage": 14.14, "elapsed_time": "0:12:31", "remaining_time": "1:16:04", "throughput": 5170.24, "total_tokens": 3887104} {"current_steps": 950, "total_steps": 6710, "loss": 1.3345, "lr": 2.378378536679096e-06, "epoch": 0.7078986587183308, "percentage": 14.16, "elapsed_time": "0:12:32", "remaining_time": "1:16:03", "throughput": 5170.33, "total_tokens": 3891200} {"current_steps": 951, "total_steps": 6710, "loss": 1.4225, "lr": 2.3781266030254523e-06, "epoch": 0.7086438152011922, "percentage": 14.17, "elapsed_time": "0:12:33", "remaining_time": "1:16:02", "throughput": 5170.39, "total_tokens": 3895296} {"current_steps": 952, "total_steps": 6710, "loss": 1.0829, "lr": 2.377874422078402e-06, "epoch": 0.7093889716840537, "percentage": 14.19, "elapsed_time": "0:12:34", "remaining_time": "1:16:01", "throughput": 5170.42, "total_tokens": 3899392} {"current_steps": 953, "total_steps": 6710, "loss": 1.3673, "lr": 2.377621993893225e-06, "epoch": 0.710134128166915, "percentage": 14.2, "elapsed_time": "0:12:34", "remaining_time": "1:16:00", "throughput": 5170.48, "total_tokens": 3903488} {"current_steps": 954, "total_steps": 6710, "loss": 1.4038, "lr": 2.3773693185252546e-06, "epoch": 0.7108792846497765, "percentage": 14.22, "elapsed_time": "0:12:35", "remaining_time": "1:15:59", "throughput": 5170.56, "total_tokens": 3907584} {"current_steps": 955, "total_steps": 6710, "loss": 1.353, "lr": 2.3771163960298793e-06, "epoch": 0.7116244411326379, "percentage": 14.23, "elapsed_time": "0:12:36", "remaining_time": "1:15:58", "throughput": 5170.65, "total_tokens": 3911680} {"current_steps": 956, "total_steps": 6710, "loss": 1.3524, "lr": 2.3768632264625417e-06, "epoch": 0.7123695976154992, "percentage": 14.25, "elapsed_time": "0:12:37", "remaining_time": "1:15:58", "throughput": 5170.68, "total_tokens": 3915776} {"current_steps": 957, "total_steps": 6710, "loss": 1.2701, "lr": 2.3766098098787384e-06, "epoch": 0.7131147540983607, "percentage": 14.26, "elapsed_time": "0:12:38", "remaining_time": "1:15:57", "throughput": 5170.76, "total_tokens": 3919872} {"current_steps": 958, "total_steps": 6710, "loss": 1.3607, "lr": 2.37635614633402e-06, "epoch": 0.713859910581222, "percentage": 14.28, "elapsed_time": "0:12:38", "remaining_time": "1:15:56", "throughput": 5170.85, "total_tokens": 3923968} {"current_steps": 959, "total_steps": 6710, "loss": 1.3686, "lr": 2.3761022358839917e-06, "epoch": 0.7146050670640834, "percentage": 14.29, "elapsed_time": "0:12:39", "remaining_time": "1:15:55", "throughput": 5170.94, "total_tokens": 3928064} {"current_steps": 960, "total_steps": 6710, "loss": 1.498, "lr": 2.375848078584312e-06, "epoch": 0.7153502235469449, "percentage": 14.31, "elapsed_time": "0:12:40", "remaining_time": "1:15:54", "throughput": 5171.02, "total_tokens": 3932160} {"current_steps": 961, "total_steps": 6710, "loss": 1.3957, "lr": 2.3755936744906945e-06, "epoch": 0.7160953800298062, "percentage": 14.32, "elapsed_time": "0:12:41", "remaining_time": "1:15:53", "throughput": 5171.1, "total_tokens": 3936256} {"current_steps": 962, "total_steps": 6710, "loss": 1.4242, "lr": 2.3753390236589054e-06, "epoch": 0.7168405365126677, "percentage": 14.34, "elapsed_time": "0:12:41", "remaining_time": "1:15:52", "throughput": 5171.13, "total_tokens": 3940352} {"current_steps": 963, "total_steps": 6710, "loss": 1.0752, "lr": 2.375084126144767e-06, "epoch": 0.7175856929955291, "percentage": 14.35, "elapsed_time": "0:12:42", "remaining_time": "1:15:52", "throughput": 5171.23, "total_tokens": 3944448} {"current_steps": 964, "total_steps": 6710, "loss": 1.2123, "lr": 2.3748289820041547e-06, "epoch": 0.7183308494783904, "percentage": 14.37, "elapsed_time": "0:12:43", "remaining_time": "1:15:51", "throughput": 5171.27, "total_tokens": 3948544} {"current_steps": 965, "total_steps": 6710, "loss": 1.3737, "lr": 2.3745735912929973e-06, "epoch": 0.7190760059612519, "percentage": 14.38, "elapsed_time": "0:12:44", "remaining_time": "1:15:50", "throughput": 5171.35, "total_tokens": 3952640} {"current_steps": 966, "total_steps": 6710, "loss": 0.8661, "lr": 2.3743179540672785e-06, "epoch": 0.7198211624441133, "percentage": 14.4, "elapsed_time": "0:12:45", "remaining_time": "1:15:49", "throughput": 5171.39, "total_tokens": 3956736} {"current_steps": 967, "total_steps": 6710, "loss": 1.4366, "lr": 2.3740620703830356e-06, "epoch": 0.7205663189269746, "percentage": 14.41, "elapsed_time": "0:12:45", "remaining_time": "1:15:48", "throughput": 5171.47, "total_tokens": 3960832} {"current_steps": 968, "total_steps": 6710, "loss": 1.4412, "lr": 2.3738059402963607e-06, "epoch": 0.7213114754098361, "percentage": 14.43, "elapsed_time": "0:12:46", "remaining_time": "1:15:47", "throughput": 5171.55, "total_tokens": 3964928} {"current_steps": 969, "total_steps": 6710, "loss": 1.5885, "lr": 2.3735495638633986e-06, "epoch": 0.7220566318926974, "percentage": 14.44, "elapsed_time": "0:12:47", "remaining_time": "1:15:46", "throughput": 5171.63, "total_tokens": 3969024} {"current_steps": 970, "total_steps": 6710, "loss": 1.2252, "lr": 2.37329294114035e-06, "epoch": 0.7228017883755589, "percentage": 14.46, "elapsed_time": "0:12:48", "remaining_time": "1:15:46", "throughput": 5171.7, "total_tokens": 3973120} {"current_steps": 971, "total_steps": 6710, "loss": 1.0892, "lr": 2.373036072183467e-06, "epoch": 0.7235469448584203, "percentage": 14.47, "elapsed_time": "0:12:49", "remaining_time": "1:15:45", "throughput": 5171.79, "total_tokens": 3977216} {"current_steps": 972, "total_steps": 6710, "loss": 1.1057, "lr": 2.372778957049058e-06, "epoch": 0.7242921013412816, "percentage": 14.49, "elapsed_time": "0:12:49", "remaining_time": "1:15:44", "throughput": 5171.87, "total_tokens": 3981312} {"current_steps": 973, "total_steps": 6710, "loss": 1.3325, "lr": 2.372521595793484e-06, "epoch": 0.7250372578241431, "percentage": 14.5, "elapsed_time": "0:12:50", "remaining_time": "1:15:43", "throughput": 5171.93, "total_tokens": 3985408} {"current_steps": 974, "total_steps": 6710, "loss": 1.25, "lr": 2.372263988473161e-06, "epoch": 0.7257824143070045, "percentage": 14.52, "elapsed_time": "0:12:51", "remaining_time": "1:15:42", "throughput": 5172.0, "total_tokens": 3989504} {"current_steps": 975, "total_steps": 6710, "loss": 1.2783, "lr": 2.372006135144558e-06, "epoch": 0.7265275707898659, "percentage": 14.53, "elapsed_time": "0:12:52", "remaining_time": "1:15:41", "throughput": 5172.08, "total_tokens": 3993600} {"current_steps": 976, "total_steps": 6710, "loss": 1.2621, "lr": 2.371748035864198e-06, "epoch": 0.7272727272727273, "percentage": 14.55, "elapsed_time": "0:12:52", "remaining_time": "1:15:40", "throughput": 5172.14, "total_tokens": 3997696} {"current_steps": 977, "total_steps": 6710, "loss": 1.2575, "lr": 2.371489690688659e-06, "epoch": 0.7280178837555886, "percentage": 14.56, "elapsed_time": "0:12:53", "remaining_time": "1:15:40", "throughput": 5172.18, "total_tokens": 4001792} {"current_steps": 978, "total_steps": 6710, "loss": 0.9802, "lr": 2.3712310996745712e-06, "epoch": 0.7287630402384501, "percentage": 14.58, "elapsed_time": "0:12:54", "remaining_time": "1:15:39", "throughput": 5172.26, "total_tokens": 4005888} {"current_steps": 979, "total_steps": 6710, "loss": 1.227, "lr": 2.3709722628786207e-06, "epoch": 0.7295081967213115, "percentage": 14.59, "elapsed_time": "0:12:55", "remaining_time": "1:15:38", "throughput": 5172.33, "total_tokens": 4009984} {"current_steps": 980, "total_steps": 6710, "loss": 1.0719, "lr": 2.370713180357545e-06, "epoch": 0.7302533532041728, "percentage": 14.61, "elapsed_time": "0:12:56", "remaining_time": "1:15:37", "throughput": 5172.4, "total_tokens": 4014080} {"current_steps": 981, "total_steps": 6710, "loss": 1.1913, "lr": 2.370453852168138e-06, "epoch": 0.7309985096870343, "percentage": 14.62, "elapsed_time": "0:12:56", "remaining_time": "1:15:36", "throughput": 5172.46, "total_tokens": 4018176} {"current_steps": 982, "total_steps": 6710, "loss": 1.1926, "lr": 2.370194278367246e-06, "epoch": 0.7317436661698957, "percentage": 14.63, "elapsed_time": "0:12:57", "remaining_time": "1:15:35", "throughput": 5172.54, "total_tokens": 4022272} {"current_steps": 983, "total_steps": 6710, "loss": 1.3796, "lr": 2.369934459011769e-06, "epoch": 0.732488822652757, "percentage": 14.65, "elapsed_time": "0:12:58", "remaining_time": "1:15:34", "throughput": 5172.62, "total_tokens": 4026368} {"current_steps": 984, "total_steps": 6710, "loss": 1.3733, "lr": 2.3696743941586616e-06, "epoch": 0.7332339791356185, "percentage": 14.66, "elapsed_time": "0:12:59", "remaining_time": "1:15:34", "throughput": 5172.62, "total_tokens": 4030464} {"current_steps": 985, "total_steps": 6710, "loss": 1.0258, "lr": 2.3694140838649317e-06, "epoch": 0.7339791356184798, "percentage": 14.68, "elapsed_time": "0:12:59", "remaining_time": "1:15:33", "throughput": 5172.67, "total_tokens": 4034560} {"current_steps": 986, "total_steps": 6710, "loss": 1.0486, "lr": 2.369153528187641e-06, "epoch": 0.7347242921013413, "percentage": 14.69, "elapsed_time": "0:13:00", "remaining_time": "1:15:32", "throughput": 5172.73, "total_tokens": 4038656} {"current_steps": 987, "total_steps": 6710, "loss": 1.1026, "lr": 2.3688927271839064e-06, "epoch": 0.7354694485842027, "percentage": 14.71, "elapsed_time": "0:13:01", "remaining_time": "1:15:31", "throughput": 5172.8, "total_tokens": 4042752} {"current_steps": 988, "total_steps": 6710, "loss": 0.9371, "lr": 2.3686316809108956e-06, "epoch": 0.736214605067064, "percentage": 14.72, "elapsed_time": "0:13:02", "remaining_time": "1:15:30", "throughput": 5172.86, "total_tokens": 4046848} {"current_steps": 989, "total_steps": 6710, "loss": 1.5479, "lr": 2.368370389425833e-06, "epoch": 0.7369597615499255, "percentage": 14.74, "elapsed_time": "0:13:03", "remaining_time": "1:15:29", "throughput": 5172.94, "total_tokens": 4050944} {"current_steps": 990, "total_steps": 6710, "loss": 1.3941, "lr": 2.3681088527859947e-06, "epoch": 0.7377049180327869, "percentage": 14.75, "elapsed_time": "0:13:03", "remaining_time": "1:15:29", "throughput": 5173.02, "total_tokens": 4055040} {"current_steps": 991, "total_steps": 6710, "loss": 1.3487, "lr": 2.367847071048712e-06, "epoch": 0.7384500745156483, "percentage": 14.77, "elapsed_time": "0:13:04", "remaining_time": "1:15:28", "throughput": 5173.09, "total_tokens": 4059136} {"current_steps": 992, "total_steps": 6710, "loss": 0.97, "lr": 2.3675850442713694e-06, "epoch": 0.7391952309985097, "percentage": 14.78, "elapsed_time": "0:13:05", "remaining_time": "1:15:27", "throughput": 5173.17, "total_tokens": 4063232} {"current_steps": 993, "total_steps": 6710, "loss": 1.2549, "lr": 2.367322772511405e-06, "epoch": 0.7399403874813711, "percentage": 14.8, "elapsed_time": "0:13:06", "remaining_time": "1:15:26", "throughput": 5173.24, "total_tokens": 4067328} {"current_steps": 994, "total_steps": 6710, "loss": 1.1393, "lr": 2.36706025582631e-06, "epoch": 0.7406855439642325, "percentage": 14.81, "elapsed_time": "0:13:07", "remaining_time": "1:15:25", "throughput": 5173.32, "total_tokens": 4071424} {"current_steps": 995, "total_steps": 6710, "loss": 1.3605, "lr": 2.3667974942736306e-06, "epoch": 0.7414307004470939, "percentage": 14.83, "elapsed_time": "0:13:07", "remaining_time": "1:15:24", "throughput": 5173.41, "total_tokens": 4075520} {"current_steps": 996, "total_steps": 6710, "loss": 1.265, "lr": 2.3665344879109657e-06, "epoch": 0.7421758569299552, "percentage": 14.84, "elapsed_time": "0:13:08", "remaining_time": "1:15:23", "throughput": 5173.47, "total_tokens": 4079616} {"current_steps": 997, "total_steps": 6710, "loss": 0.9492, "lr": 2.3662712367959683e-06, "epoch": 0.7429210134128167, "percentage": 14.86, "elapsed_time": "0:13:09", "remaining_time": "1:15:23", "throughput": 5173.54, "total_tokens": 4083712} {"current_steps": 998, "total_steps": 6710, "loss": 1.0021, "lr": 2.3660077409863453e-06, "epoch": 0.7436661698956781, "percentage": 14.87, "elapsed_time": "0:13:10", "remaining_time": "1:15:22", "throughput": 5173.62, "total_tokens": 4087808} {"current_steps": 999, "total_steps": 6710, "loss": 1.1417, "lr": 2.365744000539856e-06, "epoch": 0.7444113263785395, "percentage": 14.89, "elapsed_time": "0:13:10", "remaining_time": "1:15:21", "throughput": 5173.68, "total_tokens": 4091904} {"current_steps": 1000, "total_steps": 6710, "loss": 1.305, "lr": 2.3654800155143147e-06, "epoch": 0.7451564828614009, "percentage": 14.9, "elapsed_time": "0:13:11", "remaining_time": "1:15:20", "throughput": 5173.7, "total_tokens": 4096000} {"current_steps": 1001, "total_steps": 6710, "loss": 1.2033, "lr": 2.365215785967589e-06, "epoch": 0.7459016393442623, "percentage": 14.92, "elapsed_time": "0:13:12", "remaining_time": "1:15:19", "throughput": 5173.76, "total_tokens": 4100096} {"current_steps": 1002, "total_steps": 6710, "loss": 1.2773, "lr": 2.3649513119575994e-06, "epoch": 0.7466467958271237, "percentage": 14.93, "elapsed_time": "0:13:13", "remaining_time": "1:15:18", "throughput": 5173.84, "total_tokens": 4104192} {"current_steps": 1003, "total_steps": 6710, "loss": 0.9841, "lr": 2.364686593542321e-06, "epoch": 0.7473919523099851, "percentage": 14.95, "elapsed_time": "0:13:14", "remaining_time": "1:15:18", "throughput": 5173.9, "total_tokens": 4108288} {"current_steps": 1004, "total_steps": 6710, "loss": 1.2493, "lr": 2.364421630779782e-06, "epoch": 0.7481371087928465, "percentage": 14.96, "elapsed_time": "0:13:14", "remaining_time": "1:15:17", "throughput": 5173.91, "total_tokens": 4112384} {"current_steps": 1005, "total_steps": 6710, "loss": 1.1815, "lr": 2.364156423728063e-06, "epoch": 0.7488822652757079, "percentage": 14.98, "elapsed_time": "0:13:15", "remaining_time": "1:15:16", "throughput": 5173.97, "total_tokens": 4116480} {"current_steps": 1006, "total_steps": 6710, "loss": 1.012, "lr": 2.3638909724453007e-06, "epoch": 0.7496274217585693, "percentage": 14.99, "elapsed_time": "0:13:16", "remaining_time": "1:15:15", "throughput": 5174.04, "total_tokens": 4120576} {"current_steps": 1007, "total_steps": 6710, "loss": 1.6547, "lr": 2.3636252769896834e-06, "epoch": 0.7503725782414307, "percentage": 15.01, "elapsed_time": "0:13:17", "remaining_time": "1:15:14", "throughput": 5174.11, "total_tokens": 4124672} {"current_steps": 1008, "total_steps": 6710, "loss": 0.9154, "lr": 2.363359337419453e-06, "epoch": 0.7511177347242921, "percentage": 15.02, "elapsed_time": "0:13:17", "remaining_time": "1:15:13", "throughput": 5174.18, "total_tokens": 4128768} {"current_steps": 1009, "total_steps": 6710, "loss": 1.181, "lr": 2.363093153792906e-06, "epoch": 0.7518628912071535, "percentage": 15.04, "elapsed_time": "0:13:18", "remaining_time": "1:15:12", "throughput": 5174.23, "total_tokens": 4132864} {"current_steps": 1010, "total_steps": 6710, "loss": 0.8272, "lr": 2.3628267261683917e-06, "epoch": 0.7526080476900149, "percentage": 15.05, "elapsed_time": "0:13:19", "remaining_time": "1:15:12", "throughput": 5174.27, "total_tokens": 4136960} {"current_steps": 1011, "total_steps": 6710, "loss": 0.9569, "lr": 2.3625600546043125e-06, "epoch": 0.7533532041728763, "percentage": 15.07, "elapsed_time": "0:13:20", "remaining_time": "1:15:11", "throughput": 5174.31, "total_tokens": 4141056} {"current_steps": 1012, "total_steps": 6710, "loss": 1.218, "lr": 2.362293139159125e-06, "epoch": 0.7540983606557377, "percentage": 15.08, "elapsed_time": "0:13:21", "remaining_time": "1:15:10", "throughput": 5174.38, "total_tokens": 4145152} {"current_steps": 1013, "total_steps": 6710, "loss": 1.1766, "lr": 2.3620259798913386e-06, "epoch": 0.7548435171385991, "percentage": 15.1, "elapsed_time": "0:13:21", "remaining_time": "1:15:09", "throughput": 5174.44, "total_tokens": 4149248} {"current_steps": 1014, "total_steps": 6710, "loss": 1.3807, "lr": 2.361758576859517e-06, "epoch": 0.7555886736214605, "percentage": 15.11, "elapsed_time": "0:13:22", "remaining_time": "1:15:08", "throughput": 5174.51, "total_tokens": 4153344} {"current_steps": 1015, "total_steps": 6710, "loss": 1.0177, "lr": 2.3614909301222773e-06, "epoch": 0.7563338301043219, "percentage": 15.13, "elapsed_time": "0:13:23", "remaining_time": "1:15:07", "throughput": 5174.56, "total_tokens": 4157440} {"current_steps": 1016, "total_steps": 6710, "loss": 1.4113, "lr": 2.361223039738288e-06, "epoch": 0.7570789865871833, "percentage": 15.14, "elapsed_time": "0:13:24", "remaining_time": "1:15:07", "throughput": 5174.6, "total_tokens": 4161536} {"current_steps": 1017, "total_steps": 6710, "loss": 1.3528, "lr": 2.3609549057662744e-06, "epoch": 0.7578241430700448, "percentage": 15.16, "elapsed_time": "0:13:25", "remaining_time": "1:15:06", "throughput": 5174.63, "total_tokens": 4165632} {"current_steps": 1018, "total_steps": 6710, "loss": 1.2692, "lr": 2.360686528265012e-06, "epoch": 0.7585692995529061, "percentage": 15.17, "elapsed_time": "0:13:25", "remaining_time": "1:15:05", "throughput": 5174.67, "total_tokens": 4169728} {"current_steps": 1019, "total_steps": 6710, "loss": 1.1127, "lr": 2.360417907293332e-06, "epoch": 0.7593144560357675, "percentage": 15.19, "elapsed_time": "0:13:26", "remaining_time": "1:15:04", "throughput": 5174.71, "total_tokens": 4173824} {"current_steps": 1020, "total_steps": 6710, "loss": 0.9913, "lr": 2.360149042910117e-06, "epoch": 0.7600596125186289, "percentage": 15.2, "elapsed_time": "0:13:27", "remaining_time": "1:15:03", "throughput": 5174.79, "total_tokens": 4177920} {"current_steps": 1021, "total_steps": 6710, "loss": 1.1392, "lr": 2.359879935174305e-06, "epoch": 0.7608047690014903, "percentage": 15.22, "elapsed_time": "0:13:28", "remaining_time": "1:15:02", "throughput": 5174.86, "total_tokens": 4182016} {"current_steps": 1022, "total_steps": 6710, "loss": 1.1858, "lr": 2.359610584144886e-06, "epoch": 0.7615499254843517, "percentage": 15.23, "elapsed_time": "0:13:28", "remaining_time": "1:15:02", "throughput": 5174.92, "total_tokens": 4186112} {"current_steps": 1023, "total_steps": 6710, "loss": 0.9929, "lr": 2.359340989880903e-06, "epoch": 0.7622950819672131, "percentage": 15.25, "elapsed_time": "0:13:29", "remaining_time": "1:15:01", "throughput": 5174.96, "total_tokens": 4190208} {"current_steps": 1024, "total_steps": 6710, "loss": 1.2821, "lr": 2.3590711524414545e-06, "epoch": 0.7630402384500745, "percentage": 15.26, "elapsed_time": "0:13:30", "remaining_time": "1:15:00", "throughput": 5175.0, "total_tokens": 4194304} {"current_steps": 1025, "total_steps": 6710, "loss": 0.9257, "lr": 2.3588010718856898e-06, "epoch": 0.763785394932936, "percentage": 15.28, "elapsed_time": "0:13:31", "remaining_time": "1:14:59", "throughput": 5175.04, "total_tokens": 4198400} {"current_steps": 1026, "total_steps": 6710, "loss": 1.2367, "lr": 2.3585307482728125e-06, "epoch": 0.7645305514157973, "percentage": 15.29, "elapsed_time": "0:13:32", "remaining_time": "1:14:58", "throughput": 5175.09, "total_tokens": 4202496} {"current_steps": 1027, "total_steps": 6710, "loss": 1.2578, "lr": 2.3582601816620793e-06, "epoch": 0.7652757078986587, "percentage": 15.31, "elapsed_time": "0:13:32", "remaining_time": "1:14:57", "throughput": 5175.15, "total_tokens": 4206592} {"current_steps": 1028, "total_steps": 6710, "loss": 1.3088, "lr": 2.3579893721128003e-06, "epoch": 0.7660208643815202, "percentage": 15.32, "elapsed_time": "0:13:33", "remaining_time": "1:14:57", "throughput": 5175.13, "total_tokens": 4210688} {"current_steps": 1029, "total_steps": 6710, "loss": 1.2169, "lr": 2.35771831968434e-06, "epoch": 0.7667660208643815, "percentage": 15.34, "elapsed_time": "0:13:34", "remaining_time": "1:14:56", "throughput": 5175.19, "total_tokens": 4214784} {"current_steps": 1030, "total_steps": 6710, "loss": 1.2802, "lr": 2.3574470244361135e-06, "epoch": 0.767511177347243, "percentage": 15.35, "elapsed_time": "0:13:35", "remaining_time": "1:14:55", "throughput": 5175.25, "total_tokens": 4218880} {"current_steps": 1031, "total_steps": 6710, "loss": 1.2986, "lr": 2.357175486427592e-06, "epoch": 0.7682563338301043, "percentage": 15.37, "elapsed_time": "0:13:35", "remaining_time": "1:14:54", "throughput": 5175.31, "total_tokens": 4222976} {"current_steps": 1032, "total_steps": 6710, "loss": 1.3282, "lr": 2.3569037057182975e-06, "epoch": 0.7690014903129657, "percentage": 15.38, "elapsed_time": "0:13:36", "remaining_time": "1:14:53", "throughput": 5175.38, "total_tokens": 4227072} {"current_steps": 1033, "total_steps": 6710, "loss": 1.3905, "lr": 2.356631682367807e-06, "epoch": 0.7697466467958272, "percentage": 15.39, "elapsed_time": "0:13:37", "remaining_time": "1:14:52", "throughput": 5175.43, "total_tokens": 4231168} {"current_steps": 1034, "total_steps": 6710, "loss": 1.3325, "lr": 2.3563594164357495e-06, "epoch": 0.7704918032786885, "percentage": 15.41, "elapsed_time": "0:13:38", "remaining_time": "1:14:52", "throughput": 5175.49, "total_tokens": 4235264} {"current_steps": 1035, "total_steps": 6710, "loss": 1.492, "lr": 2.3560869079818076e-06, "epoch": 0.7712369597615499, "percentage": 15.42, "elapsed_time": "0:13:39", "remaining_time": "1:14:51", "throughput": 5175.56, "total_tokens": 4239360} {"current_steps": 1036, "total_steps": 6710, "loss": 1.1564, "lr": 2.355814157065718e-06, "epoch": 0.7719821162444114, "percentage": 15.44, "elapsed_time": "0:13:39", "remaining_time": "1:14:50", "throughput": 5175.61, "total_tokens": 4243456} {"current_steps": 1037, "total_steps": 6710, "loss": 1.143, "lr": 2.355541163747268e-06, "epoch": 0.7727272727272727, "percentage": 15.45, "elapsed_time": "0:13:40", "remaining_time": "1:14:49", "throughput": 5175.67, "total_tokens": 4247552} {"current_steps": 1038, "total_steps": 6710, "loss": 1.2915, "lr": 2.355267928086301e-06, "epoch": 0.7734724292101341, "percentage": 15.47, "elapsed_time": "0:13:41", "remaining_time": "1:14:48", "throughput": 5175.73, "total_tokens": 4251648} {"current_steps": 1039, "total_steps": 6710, "loss": 1.5708, "lr": 2.3549944501427122e-06, "epoch": 0.7742175856929955, "percentage": 15.48, "elapsed_time": "0:13:42", "remaining_time": "1:14:47", "throughput": 5175.77, "total_tokens": 4255744} {"current_steps": 1040, "total_steps": 6710, "loss": 1.1881, "lr": 2.354720729976449e-06, "epoch": 0.7749627421758569, "percentage": 15.5, "elapsed_time": "0:13:43", "remaining_time": "1:14:47", "throughput": 5175.76, "total_tokens": 4259840} {"current_steps": 1041, "total_steps": 6710, "loss": 1.3994, "lr": 2.354446767647514e-06, "epoch": 0.7757078986587184, "percentage": 15.51, "elapsed_time": "0:13:43", "remaining_time": "1:14:46", "throughput": 5175.82, "total_tokens": 4263936} {"current_steps": 1042, "total_steps": 6710, "loss": 1.101, "lr": 2.3541725632159607e-06, "epoch": 0.7764530551415797, "percentage": 15.53, "elapsed_time": "0:13:44", "remaining_time": "1:14:45", "throughput": 5175.87, "total_tokens": 4268032} {"current_steps": 1043, "total_steps": 6710, "loss": 1.3357, "lr": 2.353898116741897e-06, "epoch": 0.7771982116244411, "percentage": 15.54, "elapsed_time": "0:13:45", "remaining_time": "1:14:44", "throughput": 5175.93, "total_tokens": 4272128} {"current_steps": 1044, "total_steps": 6710, "loss": 1.278, "lr": 2.353623428285484e-06, "epoch": 0.7779433681073026, "percentage": 15.56, "elapsed_time": "0:13:46", "remaining_time": "1:14:43", "throughput": 5175.97, "total_tokens": 4276224} {"current_steps": 1045, "total_steps": 6710, "loss": 1.322, "lr": 2.3533484979069343e-06, "epoch": 0.7786885245901639, "percentage": 15.57, "elapsed_time": "0:13:46", "remaining_time": "1:14:42", "throughput": 5175.98, "total_tokens": 4280320} {"current_steps": 1046, "total_steps": 6710, "loss": 1.2637, "lr": 2.3530733256665155e-06, "epoch": 0.7794336810730254, "percentage": 15.59, "elapsed_time": "0:13:47", "remaining_time": "1:14:42", "throughput": 5176.04, "total_tokens": 4284416} {"current_steps": 1047, "total_steps": 6710, "loss": 1.0619, "lr": 2.3527979116245473e-06, "epoch": 0.7801788375558867, "percentage": 15.6, "elapsed_time": "0:13:48", "remaining_time": "1:14:41", "throughput": 5176.1, "total_tokens": 4288512} {"current_steps": 1048, "total_steps": 6710, "loss": 1.1219, "lr": 2.352522255841402e-06, "epoch": 0.7809239940387481, "percentage": 15.62, "elapsed_time": "0:13:49", "remaining_time": "1:14:40", "throughput": 5176.16, "total_tokens": 4292608} {"current_steps": 1049, "total_steps": 6710, "loss": 1.0783, "lr": 2.3522463583775056e-06, "epoch": 0.7816691505216096, "percentage": 15.63, "elapsed_time": "0:13:50", "remaining_time": "1:14:39", "throughput": 5176.22, "total_tokens": 4296704} {"current_steps": 1050, "total_steps": 6710, "loss": 1.0869, "lr": 2.351970219293337e-06, "epoch": 0.7824143070044709, "percentage": 15.65, "elapsed_time": "0:13:50", "remaining_time": "1:14:38", "throughput": 5176.28, "total_tokens": 4300800} {"current_steps": 1051, "total_steps": 6710, "loss": 1.0302, "lr": 2.351693838649427e-06, "epoch": 0.7831594634873323, "percentage": 15.66, "elapsed_time": "0:13:51", "remaining_time": "1:14:37", "throughput": 5176.34, "total_tokens": 4304896} {"current_steps": 1052, "total_steps": 6710, "loss": 1.155, "lr": 2.3514172165063608e-06, "epoch": 0.7839046199701938, "percentage": 15.68, "elapsed_time": "0:13:52", "remaining_time": "1:14:37", "throughput": 5176.39, "total_tokens": 4308992} {"current_steps": 1053, "total_steps": 6710, "loss": 1.43, "lr": 2.3511403529247763e-06, "epoch": 0.7846497764530551, "percentage": 15.69, "elapsed_time": "0:13:53", "remaining_time": "1:14:36", "throughput": 5176.43, "total_tokens": 4313088} {"current_steps": 1054, "total_steps": 6710, "loss": 1.2485, "lr": 2.350863247965363e-06, "epoch": 0.7853949329359166, "percentage": 15.71, "elapsed_time": "0:13:53", "remaining_time": "1:14:35", "throughput": 5176.5, "total_tokens": 4317184} {"current_steps": 1055, "total_steps": 6710, "loss": 1.2869, "lr": 2.3505859016888656e-06, "epoch": 0.786140089418778, "percentage": 15.72, "elapsed_time": "0:13:54", "remaining_time": "1:14:34", "throughput": 5176.56, "total_tokens": 4321280} {"current_steps": 1056, "total_steps": 6710, "loss": 1.3825, "lr": 2.3503083141560794e-06, "epoch": 0.7868852459016393, "percentage": 15.74, "elapsed_time": "0:13:55", "remaining_time": "1:14:33", "throughput": 5176.62, "total_tokens": 4325376} {"current_steps": 1057, "total_steps": 6710, "loss": 1.1774, "lr": 2.350030485427854e-06, "epoch": 0.7876304023845008, "percentage": 15.75, "elapsed_time": "0:13:56", "remaining_time": "1:14:32", "throughput": 5176.66, "total_tokens": 4329472} {"current_steps": 1058, "total_steps": 6710, "loss": 1.2702, "lr": 2.3497524155650906e-06, "epoch": 0.7883755588673621, "percentage": 15.77, "elapsed_time": "0:13:57", "remaining_time": "1:14:32", "throughput": 5176.7, "total_tokens": 4333568} {"current_steps": 1059, "total_steps": 6710, "loss": 1.2545, "lr": 2.349474104628745e-06, "epoch": 0.7891207153502235, "percentage": 15.78, "elapsed_time": "0:13:57", "remaining_time": "1:14:31", "throughput": 5176.77, "total_tokens": 4337664} {"current_steps": 1060, "total_steps": 6710, "loss": 1.1897, "lr": 2.3491955526798255e-06, "epoch": 0.789865871833085, "percentage": 15.8, "elapsed_time": "0:13:58", "remaining_time": "1:14:30", "throughput": 5176.83, "total_tokens": 4341760} {"current_steps": 1061, "total_steps": 6710, "loss": 1.1419, "lr": 2.348916759779391e-06, "epoch": 0.7906110283159463, "percentage": 15.81, "elapsed_time": "0:13:59", "remaining_time": "1:14:29", "throughput": 5176.86, "total_tokens": 4345856} {"current_steps": 1062, "total_steps": 6710, "loss": 1.1993, "lr": 2.3486377259885563e-06, "epoch": 0.7913561847988078, "percentage": 15.83, "elapsed_time": "0:14:00", "remaining_time": "1:14:28", "throughput": 5176.82, "total_tokens": 4349952} {"current_steps": 1063, "total_steps": 6710, "loss": 1.3785, "lr": 2.348358451368487e-06, "epoch": 0.7921013412816692, "percentage": 15.84, "elapsed_time": "0:14:01", "remaining_time": "1:14:27", "throughput": 5176.86, "total_tokens": 4354048} {"current_steps": 1064, "total_steps": 6710, "loss": 1.0656, "lr": 2.3480789359804016e-06, "epoch": 0.7928464977645305, "percentage": 15.86, "elapsed_time": "0:14:01", "remaining_time": "1:14:27", "throughput": 5176.92, "total_tokens": 4358144} {"current_steps": 1065, "total_steps": 6710, "loss": 1.0763, "lr": 2.3477991798855732e-06, "epoch": 0.793591654247392, "percentage": 15.87, "elapsed_time": "0:14:02", "remaining_time": "1:14:26", "throughput": 5176.98, "total_tokens": 4362240} {"current_steps": 1066, "total_steps": 6710, "loss": 1.1535, "lr": 2.3475191831453252e-06, "epoch": 0.7943368107302533, "percentage": 15.89, "elapsed_time": "0:14:03", "remaining_time": "1:14:25", "throughput": 5177.0, "total_tokens": 4366336} {"current_steps": 1067, "total_steps": 6710, "loss": 1.2282, "lr": 2.3472389458210353e-06, "epoch": 0.7950819672131147, "percentage": 15.9, "elapsed_time": "0:14:04", "remaining_time": "1:14:24", "throughput": 5177.06, "total_tokens": 4370432} {"current_steps": 1068, "total_steps": 6710, "loss": 1.077, "lr": 2.3469584679741336e-06, "epoch": 0.7958271236959762, "percentage": 15.92, "elapsed_time": "0:14:04", "remaining_time": "1:14:23", "throughput": 5177.06, "total_tokens": 4374528} {"current_steps": 1069, "total_steps": 6710, "loss": 1.299, "lr": 2.346677749666103e-06, "epoch": 0.7965722801788375, "percentage": 15.93, "elapsed_time": "0:14:05", "remaining_time": "1:14:23", "throughput": 5177.13, "total_tokens": 4378624} {"current_steps": 1070, "total_steps": 6710, "loss": 1.243, "lr": 2.3463967909584784e-06, "epoch": 0.797317436661699, "percentage": 15.95, "elapsed_time": "0:14:06", "remaining_time": "1:14:22", "throughput": 5177.19, "total_tokens": 4382720} {"current_steps": 1071, "total_steps": 6710, "loss": 1.4846, "lr": 2.346115591912848e-06, "epoch": 0.7980625931445604, "percentage": 15.96, "elapsed_time": "0:14:07", "remaining_time": "1:14:21", "throughput": 5177.25, "total_tokens": 4386816} {"current_steps": 1072, "total_steps": 6710, "loss": 1.0485, "lr": 2.3458341525908536e-06, "epoch": 0.7988077496274217, "percentage": 15.98, "elapsed_time": "0:14:08", "remaining_time": "1:14:20", "throughput": 5177.3, "total_tokens": 4390912} {"current_steps": 1073, "total_steps": 6710, "loss": 1.5474, "lr": 2.345552473054187e-06, "epoch": 0.7995529061102832, "percentage": 15.99, "elapsed_time": "0:14:08", "remaining_time": "1:14:19", "throughput": 5177.36, "total_tokens": 4395008} {"current_steps": 1074, "total_steps": 6710, "loss": 1.2135, "lr": 2.345270553364596e-06, "epoch": 0.8002980625931445, "percentage": 16.01, "elapsed_time": "0:14:09", "remaining_time": "1:14:18", "throughput": 5177.42, "total_tokens": 4399104} {"current_steps": 1075, "total_steps": 6710, "loss": 1.2684, "lr": 2.344988393583879e-06, "epoch": 0.801043219076006, "percentage": 16.02, "elapsed_time": "0:14:10", "remaining_time": "1:14:17", "throughput": 5177.47, "total_tokens": 4403200} {"current_steps": 1076, "total_steps": 6710, "loss": 1.3523, "lr": 2.3447059937738868e-06, "epoch": 0.8017883755588674, "percentage": 16.04, "elapsed_time": "0:14:11", "remaining_time": "1:14:17", "throughput": 5177.47, "total_tokens": 4407296} {"current_steps": 1077, "total_steps": 6710, "loss": 0.9602, "lr": 2.344423353996524e-06, "epoch": 0.8025335320417287, "percentage": 16.05, "elapsed_time": "0:14:12", "remaining_time": "1:14:16", "throughput": 5177.45, "total_tokens": 4411392} {"current_steps": 1078, "total_steps": 6710, "loss": 0.9933, "lr": 2.3441404743137467e-06, "epoch": 0.8032786885245902, "percentage": 16.07, "elapsed_time": "0:14:12", "remaining_time": "1:14:15", "throughput": 5177.52, "total_tokens": 4415488} {"current_steps": 1079, "total_steps": 6710, "loss": 1.2585, "lr": 2.3438573547875655e-06, "epoch": 0.8040238450074516, "percentage": 16.08, "elapsed_time": "0:14:13", "remaining_time": "1:14:14", "throughput": 5177.47, "total_tokens": 4419584} {"current_steps": 1080, "total_steps": 6710, "loss": 1.0014, "lr": 2.3435739954800404e-06, "epoch": 0.8047690014903129, "percentage": 16.1, "elapsed_time": "0:14:14", "remaining_time": "1:14:13", "throughput": 5177.5, "total_tokens": 4423680} {"current_steps": 1081, "total_steps": 6710, "loss": 1.3195, "lr": 2.343290396453287e-06, "epoch": 0.8055141579731744, "percentage": 16.11, "elapsed_time": "0:14:15", "remaining_time": "1:14:13", "throughput": 5177.54, "total_tokens": 4427776} {"current_steps": 1082, "total_steps": 6710, "loss": 0.9785, "lr": 2.343006557769472e-06, "epoch": 0.8062593144560357, "percentage": 16.13, "elapsed_time": "0:14:15", "remaining_time": "1:14:12", "throughput": 5177.58, "total_tokens": 4431872} {"current_steps": 1083, "total_steps": 6710, "loss": 1.3129, "lr": 2.342722479490815e-06, "epoch": 0.8070044709388972, "percentage": 16.14, "elapsed_time": "0:14:16", "remaining_time": "1:14:11", "throughput": 5177.63, "total_tokens": 4435968} {"current_steps": 1084, "total_steps": 6710, "loss": 1.1725, "lr": 2.3424381616795873e-06, "epoch": 0.8077496274217586, "percentage": 16.15, "elapsed_time": "0:14:17", "remaining_time": "1:14:10", "throughput": 5177.69, "total_tokens": 4440064} {"current_steps": 1085, "total_steps": 6710, "loss": 1.1465, "lr": 2.342153604398114e-06, "epoch": 0.8084947839046199, "percentage": 16.17, "elapsed_time": "0:14:18", "remaining_time": "1:14:09", "throughput": 5177.75, "total_tokens": 4444160} {"current_steps": 1086, "total_steps": 6710, "loss": 1.0685, "lr": 2.341868807708772e-06, "epoch": 0.8092399403874814, "percentage": 16.18, "elapsed_time": "0:14:19", "remaining_time": "1:14:08", "throughput": 5177.82, "total_tokens": 4448256} {"current_steps": 1087, "total_steps": 6710, "loss": 1.4202, "lr": 2.3415837716739903e-06, "epoch": 0.8099850968703428, "percentage": 16.2, "elapsed_time": "0:14:19", "remaining_time": "1:14:08", "throughput": 5177.88, "total_tokens": 4452352} {"current_steps": 1088, "total_steps": 6710, "loss": 1.1176, "lr": 2.341298496356252e-06, "epoch": 0.8107302533532041, "percentage": 16.21, "elapsed_time": "0:14:20", "remaining_time": "1:14:07", "throughput": 5177.91, "total_tokens": 4456448} {"current_steps": 1089, "total_steps": 6710, "loss": 1.3241, "lr": 2.34101298181809e-06, "epoch": 0.8114754098360656, "percentage": 16.23, "elapsed_time": "0:14:21", "remaining_time": "1:14:06", "throughput": 5177.98, "total_tokens": 4460544} {"current_steps": 1090, "total_steps": 6710, "loss": 1.1413, "lr": 2.340727228122092e-06, "epoch": 0.812220566318927, "percentage": 16.24, "elapsed_time": "0:14:22", "remaining_time": "1:14:05", "throughput": 5178.04, "total_tokens": 4464640} {"current_steps": 1091, "total_steps": 6710, "loss": 1.06, "lr": 2.3404412353308975e-06, "epoch": 0.8129657228017884, "percentage": 16.26, "elapsed_time": "0:14:23", "remaining_time": "1:14:04", "throughput": 5178.1, "total_tokens": 4468736} {"current_steps": 1092, "total_steps": 6710, "loss": 1.0281, "lr": 2.340155003507198e-06, "epoch": 0.8137108792846498, "percentage": 16.27, "elapsed_time": "0:14:23", "remaining_time": "1:14:03", "throughput": 5178.15, "total_tokens": 4472832} {"current_steps": 1093, "total_steps": 6710, "loss": 1.2282, "lr": 2.3398685327137367e-06, "epoch": 0.8144560357675111, "percentage": 16.29, "elapsed_time": "0:14:24", "remaining_time": "1:14:03", "throughput": 5178.19, "total_tokens": 4476928} {"current_steps": 1094, "total_steps": 6710, "loss": 1.298, "lr": 2.339581823013311e-06, "epoch": 0.8152011922503726, "percentage": 16.3, "elapsed_time": "0:14:25", "remaining_time": "1:14:02", "throughput": 5178.25, "total_tokens": 4481024} {"current_steps": 1095, "total_steps": 6710, "loss": 0.9998, "lr": 2.3392948744687692e-06, "epoch": 0.815946348733234, "percentage": 16.32, "elapsed_time": "0:14:26", "remaining_time": "1:14:01", "throughput": 5178.32, "total_tokens": 4485120} {"current_steps": 1096, "total_steps": 6710, "loss": 1.1488, "lr": 2.3390076871430126e-06, "epoch": 0.8166915052160953, "percentage": 16.33, "elapsed_time": "0:14:26", "remaining_time": "1:14:00", "throughput": 5178.38, "total_tokens": 4489216} {"current_steps": 1097, "total_steps": 6710, "loss": 0.888, "lr": 2.3387202610989947e-06, "epoch": 0.8174366616989568, "percentage": 16.35, "elapsed_time": "0:14:27", "remaining_time": "1:13:59", "throughput": 5178.44, "total_tokens": 4493312} {"current_steps": 1098, "total_steps": 6710, "loss": 1.3033, "lr": 2.3384325963997216e-06, "epoch": 0.8181818181818182, "percentage": 16.36, "elapsed_time": "0:14:28", "remaining_time": "1:13:58", "throughput": 5178.5, "total_tokens": 4497408} {"current_steps": 1099, "total_steps": 6710, "loss": 1.4606, "lr": 2.338144693108251e-06, "epoch": 0.8189269746646796, "percentage": 16.38, "elapsed_time": "0:14:29", "remaining_time": "1:13:58", "throughput": 5178.53, "total_tokens": 4501504} {"current_steps": 1100, "total_steps": 6710, "loss": 1.332, "lr": 2.3378565512876945e-06, "epoch": 0.819672131147541, "percentage": 16.39, "elapsed_time": "0:14:30", "remaining_time": "1:13:57", "throughput": 5178.58, "total_tokens": 4505600} {"current_steps": 1101, "total_steps": 6710, "loss": 1.0153, "lr": 2.337568171001213e-06, "epoch": 0.8204172876304023, "percentage": 16.41, "elapsed_time": "0:14:30", "remaining_time": "1:13:56", "throughput": 5178.64, "total_tokens": 4509696} {"current_steps": 1102, "total_steps": 6710, "loss": 1.2477, "lr": 2.337279552312023e-06, "epoch": 0.8211624441132638, "percentage": 16.42, "elapsed_time": "0:14:31", "remaining_time": "1:13:55", "throughput": 5178.69, "total_tokens": 4513792} {"current_steps": 1103, "total_steps": 6710, "loss": 0.8414, "lr": 2.336990695283391e-06, "epoch": 0.8219076005961252, "percentage": 16.44, "elapsed_time": "0:14:32", "remaining_time": "1:13:54", "throughput": 5178.76, "total_tokens": 4517888} {"current_steps": 1104, "total_steps": 6710, "loss": 1.0334, "lr": 2.336701599978637e-06, "epoch": 0.8226527570789866, "percentage": 16.45, "elapsed_time": "0:14:33", "remaining_time": "1:13:53", "throughput": 5178.82, "total_tokens": 4521984} {"current_steps": 1105, "total_steps": 6710, "loss": 1.1444, "lr": 2.3364122664611324e-06, "epoch": 0.823397913561848, "percentage": 16.47, "elapsed_time": "0:14:33", "remaining_time": "1:13:53", "throughput": 5178.89, "total_tokens": 4526080} {"current_steps": 1106, "total_steps": 6710, "loss": 1.1888, "lr": 2.3361226947943012e-06, "epoch": 0.8241430700447094, "percentage": 16.48, "elapsed_time": "0:14:34", "remaining_time": "1:13:52", "throughput": 5178.96, "total_tokens": 4530176} {"current_steps": 1107, "total_steps": 6710, "loss": 1.3883, "lr": 2.33583288504162e-06, "epoch": 0.8248882265275708, "percentage": 16.5, "elapsed_time": "0:14:35", "remaining_time": "1:13:51", "throughput": 5179.03, "total_tokens": 4534272} {"current_steps": 1108, "total_steps": 6710, "loss": 1.5025, "lr": 2.3355428372666165e-06, "epoch": 0.8256333830104322, "percentage": 16.51, "elapsed_time": "0:14:36", "remaining_time": "1:13:50", "throughput": 5179.09, "total_tokens": 4538368} {"current_steps": 1109, "total_steps": 6710, "loss": 1.3131, "lr": 2.335252551532872e-06, "epoch": 0.8263785394932935, "percentage": 16.53, "elapsed_time": "0:14:37", "remaining_time": "1:13:49", "throughput": 5179.13, "total_tokens": 4542464} {"current_steps": 1110, "total_steps": 6710, "loss": 1.1515, "lr": 2.3349620279040185e-06, "epoch": 0.827123695976155, "percentage": 16.54, "elapsed_time": "0:14:37", "remaining_time": "1:13:48", "throughput": 5179.19, "total_tokens": 4546560} {"current_steps": 1111, "total_steps": 6710, "loss": 1.4146, "lr": 2.334671266443741e-06, "epoch": 0.8278688524590164, "percentage": 16.56, "elapsed_time": "0:14:38", "remaining_time": "1:13:47", "throughput": 5179.24, "total_tokens": 4550656} {"current_steps": 1112, "total_steps": 6710, "loss": 1.2018, "lr": 2.334380267215777e-06, "epoch": 0.8286140089418778, "percentage": 16.57, "elapsed_time": "0:14:39", "remaining_time": "1:13:47", "throughput": 5179.28, "total_tokens": 4554752} {"current_steps": 1113, "total_steps": 6710, "loss": 1.5003, "lr": 2.3340890302839153e-06, "epoch": 0.8293591654247392, "percentage": 16.59, "elapsed_time": "0:14:40", "remaining_time": "1:13:46", "throughput": 5179.33, "total_tokens": 4558848} {"current_steps": 1114, "total_steps": 6710, "loss": 1.095, "lr": 2.333797555711997e-06, "epoch": 0.8301043219076006, "percentage": 16.6, "elapsed_time": "0:14:40", "remaining_time": "1:13:45", "throughput": 5179.4, "total_tokens": 4562944} {"current_steps": 1115, "total_steps": 6710, "loss": 1.1946, "lr": 2.3335058435639155e-06, "epoch": 0.830849478390462, "percentage": 16.62, "elapsed_time": "0:14:41", "remaining_time": "1:13:44", "throughput": 5179.45, "total_tokens": 4567040} {"current_steps": 1116, "total_steps": 6710, "loss": 1.2968, "lr": 2.333213893903616e-06, "epoch": 0.8315946348733234, "percentage": 16.63, "elapsed_time": "0:14:42", "remaining_time": "1:13:43", "throughput": 5179.51, "total_tokens": 4571136} {"current_steps": 1117, "total_steps": 6710, "loss": 0.8539, "lr": 2.332921706795096e-06, "epoch": 0.8323397913561847, "percentage": 16.65, "elapsed_time": "0:14:43", "remaining_time": "1:13:42", "throughput": 5179.58, "total_tokens": 4575232} {"current_steps": 1118, "total_steps": 6710, "loss": 0.9755, "lr": 2.3326292823024056e-06, "epoch": 0.8330849478390462, "percentage": 16.66, "elapsed_time": "0:14:44", "remaining_time": "1:13:42", "throughput": 5179.64, "total_tokens": 4579328} {"current_steps": 1119, "total_steps": 6710, "loss": 1.1895, "lr": 2.3323366204896456e-06, "epoch": 0.8338301043219076, "percentage": 16.68, "elapsed_time": "0:14:44", "remaining_time": "1:13:41", "throughput": 5179.7, "total_tokens": 4583424} {"current_steps": 1120, "total_steps": 6710, "loss": 1.441, "lr": 2.3320437214209694e-06, "epoch": 0.834575260804769, "percentage": 16.69, "elapsed_time": "0:14:45", "remaining_time": "1:13:40", "throughput": 5179.76, "total_tokens": 4587520} {"current_steps": 1121, "total_steps": 6710, "loss": 1.1101, "lr": 2.3317505851605835e-06, "epoch": 0.8353204172876304, "percentage": 16.71, "elapsed_time": "0:14:46", "remaining_time": "1:13:39", "throughput": 5179.81, "total_tokens": 4591616} {"current_steps": 1122, "total_steps": 6710, "loss": 0.8749, "lr": 2.331457211772745e-06, "epoch": 0.8360655737704918, "percentage": 16.72, "elapsed_time": "0:14:47", "remaining_time": "1:13:38", "throughput": 5179.87, "total_tokens": 4595712} {"current_steps": 1123, "total_steps": 6710, "loss": 1.4112, "lr": 2.3311636013217635e-06, "epoch": 0.8368107302533532, "percentage": 16.74, "elapsed_time": "0:14:48", "remaining_time": "1:13:37", "throughput": 5179.92, "total_tokens": 4599808} {"current_steps": 1124, "total_steps": 6710, "loss": 1.1541, "lr": 2.330869753872e-06, "epoch": 0.8375558867362146, "percentage": 16.75, "elapsed_time": "0:14:48", "remaining_time": "1:13:37", "throughput": 5179.98, "total_tokens": 4603904} {"current_steps": 1125, "total_steps": 6710, "loss": 1.1595, "lr": 2.3305756694878684e-06, "epoch": 0.8383010432190761, "percentage": 16.77, "elapsed_time": "0:14:49", "remaining_time": "1:13:36", "throughput": 5180.05, "total_tokens": 4608000} {"current_steps": 1126, "total_steps": 6710, "loss": 1.161, "lr": 2.330281348233834e-06, "epoch": 0.8390461997019374, "percentage": 16.78, "elapsed_time": "0:14:50", "remaining_time": "1:13:35", "throughput": 5180.07, "total_tokens": 4612096} {"current_steps": 1127, "total_steps": 6710, "loss": 1.3913, "lr": 2.3299867901744145e-06, "epoch": 0.8397913561847988, "percentage": 16.8, "elapsed_time": "0:14:51", "remaining_time": "1:13:34", "throughput": 5180.13, "total_tokens": 4616192} {"current_steps": 1128, "total_steps": 6710, "loss": 1.0658, "lr": 2.3296919953741787e-06, "epoch": 0.8405365126676602, "percentage": 16.81, "elapsed_time": "0:14:51", "remaining_time": "1:13:33", "throughput": 5180.19, "total_tokens": 4620288} {"current_steps": 1129, "total_steps": 6710, "loss": 1.2459, "lr": 2.3293969638977475e-06, "epoch": 0.8412816691505216, "percentage": 16.83, "elapsed_time": "0:14:52", "remaining_time": "1:13:32", "throughput": 5180.25, "total_tokens": 4624384} {"current_steps": 1130, "total_steps": 6710, "loss": 1.2693, "lr": 2.3291016958097946e-06, "epoch": 0.842026825633383, "percentage": 16.84, "elapsed_time": "0:14:53", "remaining_time": "1:13:32", "throughput": 5180.3, "total_tokens": 4628480} {"current_steps": 1131, "total_steps": 6710, "loss": 1.2205, "lr": 2.328806191175044e-06, "epoch": 0.8427719821162444, "percentage": 16.86, "elapsed_time": "0:14:54", "remaining_time": "1:13:31", "throughput": 5180.36, "total_tokens": 4632576} {"current_steps": 1132, "total_steps": 6710, "loss": 0.9117, "lr": 2.3285104500582736e-06, "epoch": 0.8435171385991058, "percentage": 16.87, "elapsed_time": "0:14:55", "remaining_time": "1:13:30", "throughput": 5180.41, "total_tokens": 4636672} {"current_steps": 1133, "total_steps": 6710, "loss": 1.1843, "lr": 2.328214472524311e-06, "epoch": 0.8442622950819673, "percentage": 16.89, "elapsed_time": "0:14:55", "remaining_time": "1:13:29", "throughput": 5180.46, "total_tokens": 4640768} {"current_steps": 1134, "total_steps": 6710, "loss": 1.2124, "lr": 2.3279182586380366e-06, "epoch": 0.8450074515648286, "percentage": 16.9, "elapsed_time": "0:14:56", "remaining_time": "1:13:28", "throughput": 5180.52, "total_tokens": 4644864} {"current_steps": 1135, "total_steps": 6710, "loss": 1.1707, "lr": 2.327621808464383e-06, "epoch": 0.84575260804769, "percentage": 16.92, "elapsed_time": "0:14:57", "remaining_time": "1:13:27", "throughput": 5180.58, "total_tokens": 4648960} {"current_steps": 1136, "total_steps": 6710, "loss": 1.1088, "lr": 2.3273251220683344e-06, "epoch": 0.8464977645305514, "percentage": 16.93, "elapsed_time": "0:14:58", "remaining_time": "1:13:27", "throughput": 5180.63, "total_tokens": 4653056} {"current_steps": 1137, "total_steps": 6710, "loss": 1.3592, "lr": 2.327028199514926e-06, "epoch": 0.8472429210134128, "percentage": 16.94, "elapsed_time": "0:14:58", "remaining_time": "1:13:26", "throughput": 5180.67, "total_tokens": 4657152} {"current_steps": 1138, "total_steps": 6710, "loss": 1.237, "lr": 2.3267310408692456e-06, "epoch": 0.8479880774962743, "percentage": 16.96, "elapsed_time": "0:14:59", "remaining_time": "1:13:25", "throughput": 5180.68, "total_tokens": 4661248} {"current_steps": 1139, "total_steps": 6710, "loss": 1.4257, "lr": 2.3264336461964326e-06, "epoch": 0.8487332339791356, "percentage": 16.97, "elapsed_time": "0:15:00", "remaining_time": "1:13:24", "throughput": 5180.74, "total_tokens": 4665344} {"current_steps": 1140, "total_steps": 6710, "loss": 1.3648, "lr": 2.326136015561678e-06, "epoch": 0.849478390461997, "percentage": 16.99, "elapsed_time": "0:15:01", "remaining_time": "1:13:23", "throughput": 5180.81, "total_tokens": 4669440} {"current_steps": 1141, "total_steps": 6710, "loss": 1.3011, "lr": 2.3258381490302247e-06, "epoch": 0.8502235469448585, "percentage": 17.0, "elapsed_time": "0:15:02", "remaining_time": "1:13:22", "throughput": 5180.88, "total_tokens": 4673536} {"current_steps": 1142, "total_steps": 6710, "loss": 1.2322, "lr": 2.325540046667366e-06, "epoch": 0.8509687034277198, "percentage": 17.02, "elapsed_time": "0:15:02", "remaining_time": "1:13:22", "throughput": 5180.92, "total_tokens": 4677632} {"current_steps": 1143, "total_steps": 6710, "loss": 1.0347, "lr": 2.32524170853845e-06, "epoch": 0.8517138599105812, "percentage": 17.03, "elapsed_time": "0:15:03", "remaining_time": "1:13:21", "throughput": 5180.99, "total_tokens": 4681728} {"current_steps": 1144, "total_steps": 6710, "loss": 1.1598, "lr": 2.324943134708873e-06, "epoch": 0.8524590163934426, "percentage": 17.05, "elapsed_time": "0:15:04", "remaining_time": "1:13:20", "throughput": 5181.05, "total_tokens": 4685824} {"current_steps": 1145, "total_steps": 6710, "loss": 1.323, "lr": 2.324644325244085e-06, "epoch": 0.853204172876304, "percentage": 17.06, "elapsed_time": "0:15:05", "remaining_time": "1:13:19", "throughput": 5181.1, "total_tokens": 4689920} {"current_steps": 1146, "total_steps": 6710, "loss": 0.9736, "lr": 2.324345280209588e-06, "epoch": 0.8539493293591655, "percentage": 17.08, "elapsed_time": "0:15:05", "remaining_time": "1:13:18", "throughput": 5181.15, "total_tokens": 4694016} {"current_steps": 1147, "total_steps": 6710, "loss": 1.3485, "lr": 2.3240459996709337e-06, "epoch": 0.8546944858420268, "percentage": 17.09, "elapsed_time": "0:15:06", "remaining_time": "1:13:17", "throughput": 5181.21, "total_tokens": 4698112} {"current_steps": 1148, "total_steps": 6710, "loss": 1.3009, "lr": 2.323746483693727e-06, "epoch": 0.8554396423248882, "percentage": 17.11, "elapsed_time": "0:15:07", "remaining_time": "1:13:16", "throughput": 5181.26, "total_tokens": 4702208} {"current_steps": 1149, "total_steps": 6710, "loss": 1.2576, "lr": 2.3234467323436237e-06, "epoch": 0.8561847988077497, "percentage": 17.12, "elapsed_time": "0:15:08", "remaining_time": "1:13:16", "throughput": 5181.32, "total_tokens": 4706304} {"current_steps": 1150, "total_steps": 6710, "loss": 1.0699, "lr": 2.3231467456863316e-06, "epoch": 0.856929955290611, "percentage": 17.14, "elapsed_time": "0:15:09", "remaining_time": "1:13:15", "throughput": 5181.38, "total_tokens": 4710400} {"current_steps": 1151, "total_steps": 6710, "loss": 1.0016, "lr": 2.3228465237876097e-06, "epoch": 0.8576751117734724, "percentage": 17.15, "elapsed_time": "0:15:09", "remaining_time": "1:13:14", "throughput": 5181.41, "total_tokens": 4714496} {"current_steps": 1152, "total_steps": 6710, "loss": 1.0671, "lr": 2.3225460667132693e-06, "epoch": 0.8584202682563339, "percentage": 17.17, "elapsed_time": "0:15:10", "remaining_time": "1:13:13", "throughput": 5181.44, "total_tokens": 4718592} {"current_steps": 1153, "total_steps": 6710, "loss": 0.8633, "lr": 2.322245374529172e-06, "epoch": 0.8591654247391952, "percentage": 17.18, "elapsed_time": "0:15:11", "remaining_time": "1:13:12", "throughput": 5181.44, "total_tokens": 4722688} {"current_steps": 1154, "total_steps": 6710, "loss": 1.2143, "lr": 2.3219444473012326e-06, "epoch": 0.8599105812220567, "percentage": 17.2, "elapsed_time": "0:15:12", "remaining_time": "1:13:12", "throughput": 5181.48, "total_tokens": 4726784} {"current_steps": 1155, "total_steps": 6710, "loss": 1.4448, "lr": 2.321643285095416e-06, "epoch": 0.860655737704918, "percentage": 17.21, "elapsed_time": "0:15:13", "remaining_time": "1:13:11", "throughput": 5181.53, "total_tokens": 4730880} {"current_steps": 1156, "total_steps": 6710, "loss": 0.8918, "lr": 2.3213418879777383e-06, "epoch": 0.8614008941877794, "percentage": 17.23, "elapsed_time": "0:15:13", "remaining_time": "1:13:10", "throughput": 5181.59, "total_tokens": 4734976} {"current_steps": 1157, "total_steps": 6710, "loss": 1.0215, "lr": 2.3210402560142693e-06, "epoch": 0.8621460506706409, "percentage": 17.24, "elapsed_time": "0:15:14", "remaining_time": "1:13:09", "throughput": 5181.64, "total_tokens": 4739072} {"current_steps": 1158, "total_steps": 6710, "loss": 1.1583, "lr": 2.3207383892711284e-06, "epoch": 0.8628912071535022, "percentage": 17.26, "elapsed_time": "0:15:15", "remaining_time": "1:13:08", "throughput": 5181.7, "total_tokens": 4743168} {"current_steps": 1159, "total_steps": 6710, "loss": 1.2182, "lr": 2.3204362878144864e-06, "epoch": 0.8636363636363636, "percentage": 17.27, "elapsed_time": "0:15:16", "remaining_time": "1:13:07", "throughput": 5181.75, "total_tokens": 4747264} {"current_steps": 1160, "total_steps": 6710, "loss": 1.4664, "lr": 2.3201339517105667e-06, "epoch": 0.8643815201192251, "percentage": 17.29, "elapsed_time": "0:15:16", "remaining_time": "1:13:07", "throughput": 5181.8, "total_tokens": 4751360} {"current_steps": 1161, "total_steps": 6710, "loss": 0.8433, "lr": 2.3198313810256435e-06, "epoch": 0.8651266766020864, "percentage": 17.3, "elapsed_time": "0:15:17", "remaining_time": "1:13:06", "throughput": 5181.84, "total_tokens": 4755456} {"current_steps": 1162, "total_steps": 6710, "loss": 0.8912, "lr": 2.319528575826042e-06, "epoch": 0.8658718330849479, "percentage": 17.32, "elapsed_time": "0:15:18", "remaining_time": "1:13:05", "throughput": 5181.89, "total_tokens": 4759552} {"current_steps": 1163, "total_steps": 6710, "loss": 1.453, "lr": 2.3192255361781396e-06, "epoch": 0.8666169895678092, "percentage": 17.33, "elapsed_time": "0:15:19", "remaining_time": "1:13:04", "throughput": 5181.95, "total_tokens": 4763648} {"current_steps": 1164, "total_steps": 6710, "loss": 1.3584, "lr": 2.318922262148365e-06, "epoch": 0.8673621460506706, "percentage": 17.35, "elapsed_time": "0:15:20", "remaining_time": "1:13:03", "throughput": 5182.01, "total_tokens": 4767744} {"current_steps": 1165, "total_steps": 6710, "loss": 1.3873, "lr": 2.3186187538031976e-06, "epoch": 0.8681073025335321, "percentage": 17.36, "elapsed_time": "0:15:20", "remaining_time": "1:13:02", "throughput": 5182.06, "total_tokens": 4771840} {"current_steps": 1166, "total_steps": 6710, "loss": 1.0278, "lr": 2.3183150112091687e-06, "epoch": 0.8688524590163934, "percentage": 17.38, "elapsed_time": "0:15:21", "remaining_time": "1:13:02", "throughput": 5182.12, "total_tokens": 4775936} {"current_steps": 1167, "total_steps": 6710, "loss": 1.238, "lr": 2.318011034432861e-06, "epoch": 0.8695976154992549, "percentage": 17.39, "elapsed_time": "0:15:22", "remaining_time": "1:13:01", "throughput": 5182.18, "total_tokens": 4780032} {"current_steps": 1168, "total_steps": 6710, "loss": 1.3372, "lr": 2.317706823540908e-06, "epoch": 0.8703427719821163, "percentage": 17.41, "elapsed_time": "0:15:23", "remaining_time": "1:13:00", "throughput": 5182.23, "total_tokens": 4784128} {"current_steps": 1169, "total_steps": 6710, "loss": 1.4581, "lr": 2.3174023785999953e-06, "epoch": 0.8710879284649776, "percentage": 17.42, "elapsed_time": "0:15:23", "remaining_time": "1:12:59", "throughput": 5182.28, "total_tokens": 4788224} {"current_steps": 1170, "total_steps": 6710, "loss": 1.0156, "lr": 2.3170976996768594e-06, "epoch": 0.8718330849478391, "percentage": 17.44, "elapsed_time": "0:15:24", "remaining_time": "1:12:58", "throughput": 5182.29, "total_tokens": 4792320} {"current_steps": 1171, "total_steps": 6710, "loss": 1.07, "lr": 2.316792786838288e-06, "epoch": 0.8725782414307004, "percentage": 17.45, "elapsed_time": "0:15:25", "remaining_time": "1:12:57", "throughput": 5182.34, "total_tokens": 4796416} {"current_steps": 1172, "total_steps": 6710, "loss": 1.2689, "lr": 2.31648764015112e-06, "epoch": 0.8733233979135618, "percentage": 17.47, "elapsed_time": "0:15:26", "remaining_time": "1:12:57", "throughput": 5182.41, "total_tokens": 4800512} {"current_steps": 1173, "total_steps": 6710, "loss": 1.2357, "lr": 2.316182259682246e-06, "epoch": 0.8740685543964233, "percentage": 17.48, "elapsed_time": "0:15:27", "remaining_time": "1:12:56", "throughput": 5182.46, "total_tokens": 4804608} {"current_steps": 1174, "total_steps": 6710, "loss": 1.2576, "lr": 2.3158766454986077e-06, "epoch": 0.8748137108792846, "percentage": 17.5, "elapsed_time": "0:15:27", "remaining_time": "1:12:55", "throughput": 5182.52, "total_tokens": 4808704} {"current_steps": 1175, "total_steps": 6710, "loss": 1.5547, "lr": 2.315570797667197e-06, "epoch": 0.875558867362146, "percentage": 17.51, "elapsed_time": "0:15:28", "remaining_time": "1:12:54", "throughput": 5182.57, "total_tokens": 4812800} {"current_steps": 1176, "total_steps": 6710, "loss": 1.2329, "lr": 2.315264716255059e-06, "epoch": 0.8763040238450075, "percentage": 17.53, "elapsed_time": "0:15:29", "remaining_time": "1:12:53", "throughput": 5182.6, "total_tokens": 4816896} {"current_steps": 1177, "total_steps": 6710, "loss": 1.1299, "lr": 2.3149584013292888e-06, "epoch": 0.8770491803278688, "percentage": 17.54, "elapsed_time": "0:15:30", "remaining_time": "1:12:52", "throughput": 5182.66, "total_tokens": 4820992} {"current_steps": 1178, "total_steps": 6710, "loss": 1.1472, "lr": 2.3146518529570323e-06, "epoch": 0.8777943368107303, "percentage": 17.56, "elapsed_time": "0:15:30", "remaining_time": "1:12:52", "throughput": 5182.72, "total_tokens": 4825088} {"current_steps": 1179, "total_steps": 6710, "loss": 1.2971, "lr": 2.314345071205487e-06, "epoch": 0.8785394932935916, "percentage": 17.57, "elapsed_time": "0:15:31", "remaining_time": "1:12:51", "throughput": 5182.76, "total_tokens": 4829184} {"current_steps": 1180, "total_steps": 6710, "loss": 0.9226, "lr": 2.3140380561419023e-06, "epoch": 0.879284649776453, "percentage": 17.59, "elapsed_time": "0:15:32", "remaining_time": "1:12:50", "throughput": 5182.81, "total_tokens": 4833280} {"current_steps": 1181, "total_steps": 6710, "loss": 0.8857, "lr": 2.313730807833578e-06, "epoch": 0.8800298062593145, "percentage": 17.6, "elapsed_time": "0:15:33", "remaining_time": "1:12:49", "throughput": 5182.85, "total_tokens": 4837376} {"current_steps": 1182, "total_steps": 6710, "loss": 1.1453, "lr": 2.3134233263478644e-06, "epoch": 0.8807749627421758, "percentage": 17.62, "elapsed_time": "0:15:34", "remaining_time": "1:12:48", "throughput": 5182.91, "total_tokens": 4841472} {"current_steps": 1183, "total_steps": 6710, "loss": 1.2844, "lr": 2.3131156117521643e-06, "epoch": 0.8815201192250373, "percentage": 17.63, "elapsed_time": "0:15:34", "remaining_time": "1:12:47", "throughput": 5182.96, "total_tokens": 4845568} {"current_steps": 1184, "total_steps": 6710, "loss": 1.0443, "lr": 2.3128076641139306e-06, "epoch": 0.8822652757078987, "percentage": 17.65, "elapsed_time": "0:15:35", "remaining_time": "1:12:47", "throughput": 5183.01, "total_tokens": 4849664} {"current_steps": 1185, "total_steps": 6710, "loss": 1.1532, "lr": 2.3124994835006683e-06, "epoch": 0.88301043219076, "percentage": 17.66, "elapsed_time": "0:15:36", "remaining_time": "1:12:46", "throughput": 5183.05, "total_tokens": 4853760} {"current_steps": 1186, "total_steps": 6710, "loss": 1.0056, "lr": 2.312191069979932e-06, "epoch": 0.8837555886736215, "percentage": 17.68, "elapsed_time": "0:15:37", "remaining_time": "1:12:45", "throughput": 5183.11, "total_tokens": 4857856} {"current_steps": 1187, "total_steps": 6710, "loss": 1.1566, "lr": 2.3118824236193286e-06, "epoch": 0.8845007451564829, "percentage": 17.69, "elapsed_time": "0:15:38", "remaining_time": "1:12:44", "throughput": 5183.17, "total_tokens": 4861952} {"current_steps": 1188, "total_steps": 6710, "loss": 1.2417, "lr": 2.3115735444865156e-06, "epoch": 0.8852459016393442, "percentage": 17.7, "elapsed_time": "0:15:38", "remaining_time": "1:12:43", "throughput": 5183.21, "total_tokens": 4866048} {"current_steps": 1189, "total_steps": 6710, "loss": 1.2299, "lr": 2.3112644326492007e-06, "epoch": 0.8859910581222057, "percentage": 17.72, "elapsed_time": "0:15:39", "remaining_time": "1:12:42", "throughput": 5183.27, "total_tokens": 4870144} {"current_steps": 1190, "total_steps": 6710, "loss": 1.2333, "lr": 2.3109550881751445e-06, "epoch": 0.886736214605067, "percentage": 17.73, "elapsed_time": "0:15:40", "remaining_time": "1:12:42", "throughput": 5183.32, "total_tokens": 4874240} {"current_steps": 1191, "total_steps": 6710, "loss": 0.9251, "lr": 2.310645511132157e-06, "epoch": 0.8874813710879285, "percentage": 17.75, "elapsed_time": "0:15:41", "remaining_time": "1:12:41", "throughput": 5183.36, "total_tokens": 4878336} {"current_steps": 1192, "total_steps": 6710, "loss": 1.1659, "lr": 2.3103357015881e-06, "epoch": 0.8882265275707899, "percentage": 17.76, "elapsed_time": "0:15:41", "remaining_time": "1:12:40", "throughput": 5183.42, "total_tokens": 4882432} {"current_steps": 1193, "total_steps": 6710, "loss": 0.9696, "lr": 2.3100256596108856e-06, "epoch": 0.8889716840536512, "percentage": 17.78, "elapsed_time": "0:15:42", "remaining_time": "1:12:39", "throughput": 5183.45, "total_tokens": 4886528} {"current_steps": 1194, "total_steps": 6710, "loss": 0.9451, "lr": 2.309715385268477e-06, "epoch": 0.8897168405365127, "percentage": 17.79, "elapsed_time": "0:15:43", "remaining_time": "1:12:38", "throughput": 5183.49, "total_tokens": 4890624} {"current_steps": 1195, "total_steps": 6710, "loss": 1.1588, "lr": 2.3094048786288893e-06, "epoch": 0.8904619970193741, "percentage": 17.81, "elapsed_time": "0:15:44", "remaining_time": "1:12:37", "throughput": 5183.54, "total_tokens": 4894720} {"current_steps": 1196, "total_steps": 6710, "loss": 1.258, "lr": 2.3090941397601876e-06, "epoch": 0.8912071535022354, "percentage": 17.82, "elapsed_time": "0:15:45", "remaining_time": "1:12:37", "throughput": 5183.6, "total_tokens": 4898816} {"current_steps": 1197, "total_steps": 6710, "loss": 1.3441, "lr": 2.308783168730487e-06, "epoch": 0.8919523099850969, "percentage": 17.84, "elapsed_time": "0:15:45", "remaining_time": "1:12:36", "throughput": 5183.65, "total_tokens": 4902912} {"current_steps": 1198, "total_steps": 6710, "loss": 1.2108, "lr": 2.308471965607956e-06, "epoch": 0.8926974664679582, "percentage": 17.85, "elapsed_time": "0:15:46", "remaining_time": "1:12:35", "throughput": 5183.71, "total_tokens": 4907008} {"current_steps": 1199, "total_steps": 6710, "loss": 1.3057, "lr": 2.3081605304608117e-06, "epoch": 0.8934426229508197, "percentage": 17.87, "elapsed_time": "0:15:47", "remaining_time": "1:12:34", "throughput": 5183.77, "total_tokens": 4911104} {"current_steps": 1200, "total_steps": 6710, "loss": 1.2104, "lr": 2.307848863357324e-06, "epoch": 0.8941877794336811, "percentage": 17.88, "elapsed_time": "0:15:48", "remaining_time": "1:12:33", "throughput": 5183.83, "total_tokens": 4915200} {"current_steps": 1201, "total_steps": 6710, "loss": 1.1334, "lr": 2.307536964365811e-06, "epoch": 0.8949329359165424, "percentage": 17.9, "elapsed_time": "0:15:48", "remaining_time": "1:12:32", "throughput": 5183.88, "total_tokens": 4919296} {"current_steps": 1202, "total_steps": 6710, "loss": 1.0975, "lr": 2.307224833554644e-06, "epoch": 0.8956780923994039, "percentage": 17.91, "elapsed_time": "0:15:49", "remaining_time": "1:12:32", "throughput": 5183.93, "total_tokens": 4923392} {"current_steps": 1203, "total_steps": 6710, "loss": 1.2066, "lr": 2.306912470992244e-06, "epoch": 0.8964232488822653, "percentage": 17.93, "elapsed_time": "0:15:50", "remaining_time": "1:12:31", "throughput": 5183.98, "total_tokens": 4927488} {"current_steps": 1204, "total_steps": 6710, "loss": 1.324, "lr": 2.306599876747084e-06, "epoch": 0.8971684053651267, "percentage": 17.94, "elapsed_time": "0:15:51", "remaining_time": "1:12:30", "throughput": 5184.03, "total_tokens": 4931584} {"current_steps": 1205, "total_steps": 6710, "loss": 1.3097, "lr": 2.3062870508876855e-06, "epoch": 0.8979135618479881, "percentage": 17.96, "elapsed_time": "0:15:52", "remaining_time": "1:12:29", "throughput": 5184.08, "total_tokens": 4935680} {"current_steps": 1206, "total_steps": 6710, "loss": 1.1886, "lr": 2.305973993482623e-06, "epoch": 0.8986587183308494, "percentage": 17.97, "elapsed_time": "0:15:52", "remaining_time": "1:12:28", "throughput": 5184.14, "total_tokens": 4939776} {"current_steps": 1207, "total_steps": 6710, "loss": 0.9159, "lr": 2.3056607046005213e-06, "epoch": 0.8994038748137109, "percentage": 17.99, "elapsed_time": "0:15:53", "remaining_time": "1:12:27", "throughput": 5184.2, "total_tokens": 4943872} {"current_steps": 1208, "total_steps": 6710, "loss": 1.0504, "lr": 2.3053471843100545e-06, "epoch": 0.9001490312965723, "percentage": 18.0, "elapsed_time": "0:15:54", "remaining_time": "1:12:27", "throughput": 5184.24, "total_tokens": 4947968} {"current_steps": 1209, "total_steps": 6710, "loss": 1.0112, "lr": 2.3050334326799494e-06, "epoch": 0.9008941877794336, "percentage": 18.02, "elapsed_time": "0:15:55", "remaining_time": "1:12:26", "throughput": 5184.28, "total_tokens": 4952064} {"current_steps": 1210, "total_steps": 6710, "loss": 1.4603, "lr": 2.304719449778982e-06, "epoch": 0.9016393442622951, "percentage": 18.03, "elapsed_time": "0:15:55", "remaining_time": "1:12:25", "throughput": 5184.32, "total_tokens": 4956160} {"current_steps": 1211, "total_steps": 6710, "loss": 1.3825, "lr": 2.30440523567598e-06, "epoch": 0.9023845007451565, "percentage": 18.05, "elapsed_time": "0:15:56", "remaining_time": "1:12:24", "throughput": 5184.33, "total_tokens": 4960256} {"current_steps": 1212, "total_steps": 6710, "loss": 1.5298, "lr": 2.3040907904398214e-06, "epoch": 0.9031296572280179, "percentage": 18.06, "elapsed_time": "0:15:57", "remaining_time": "1:12:23", "throughput": 5184.37, "total_tokens": 4964352} {"current_steps": 1213, "total_steps": 6710, "loss": 1.1537, "lr": 2.303776114139434e-06, "epoch": 0.9038748137108793, "percentage": 18.08, "elapsed_time": "0:15:58", "remaining_time": "1:12:22", "throughput": 5184.43, "total_tokens": 4968448} {"current_steps": 1214, "total_steps": 6710, "loss": 1.1767, "lr": 2.303461206843799e-06, "epoch": 0.9046199701937406, "percentage": 18.09, "elapsed_time": "0:15:59", "remaining_time": "1:12:22", "throughput": 5184.44, "total_tokens": 4972544} {"current_steps": 1215, "total_steps": 6710, "loss": 1.0499, "lr": 2.3031460686219444e-06, "epoch": 0.9053651266766021, "percentage": 18.11, "elapsed_time": "0:15:59", "remaining_time": "1:12:21", "throughput": 5184.48, "total_tokens": 4976640} {"current_steps": 1216, "total_steps": 6710, "loss": 1.2986, "lr": 2.302830699542951e-06, "epoch": 0.9061102831594635, "percentage": 18.12, "elapsed_time": "0:16:00", "remaining_time": "1:12:20", "throughput": 5184.5, "total_tokens": 4980736} {"current_steps": 1217, "total_steps": 6710, "loss": 1.063, "lr": 2.3025150996759503e-06, "epoch": 0.9068554396423248, "percentage": 18.14, "elapsed_time": "0:16:01", "remaining_time": "1:12:19", "throughput": 5184.56, "total_tokens": 4984832} {"current_steps": 1218, "total_steps": 6710, "loss": 1.4517, "lr": 2.3021992690901247e-06, "epoch": 0.9076005961251863, "percentage": 18.15, "elapsed_time": "0:16:02", "remaining_time": "1:12:18", "throughput": 5184.61, "total_tokens": 4988928} {"current_steps": 1219, "total_steps": 6710, "loss": 1.099, "lr": 2.301883207854706e-06, "epoch": 0.9083457526080477, "percentage": 18.17, "elapsed_time": "0:16:03", "remaining_time": "1:12:18", "throughput": 5184.66, "total_tokens": 4993024} {"current_steps": 1220, "total_steps": 6710, "loss": 1.2502, "lr": 2.3015669160389766e-06, "epoch": 0.9090909090909091, "percentage": 18.18, "elapsed_time": "0:16:03", "remaining_time": "1:12:17", "throughput": 5184.7, "total_tokens": 4997120} {"current_steps": 1221, "total_steps": 6710, "loss": 1.3209, "lr": 2.3012503937122703e-06, "epoch": 0.9098360655737705, "percentage": 18.2, "elapsed_time": "0:16:04", "remaining_time": "1:12:16", "throughput": 5184.75, "total_tokens": 5001216} {"current_steps": 1222, "total_steps": 6710, "loss": 1.1675, "lr": 2.3009336409439715e-06, "epoch": 0.910581222056632, "percentage": 18.21, "elapsed_time": "0:16:05", "remaining_time": "1:12:15", "throughput": 5184.73, "total_tokens": 5005312} {"current_steps": 1223, "total_steps": 6710, "loss": 1.0914, "lr": 2.3006166578035143e-06, "epoch": 0.9113263785394933, "percentage": 18.23, "elapsed_time": "0:16:06", "remaining_time": "1:12:14", "throughput": 5184.78, "total_tokens": 5009408} {"current_steps": 1224, "total_steps": 6710, "loss": 1.3941, "lr": 2.300299444360383e-06, "epoch": 0.9120715350223547, "percentage": 18.24, "elapsed_time": "0:16:06", "remaining_time": "1:12:13", "throughput": 5184.82, "total_tokens": 5013504} {"current_steps": 1225, "total_steps": 6710, "loss": 1.428, "lr": 2.2999820006841146e-06, "epoch": 0.912816691505216, "percentage": 18.26, "elapsed_time": "0:16:07", "remaining_time": "1:12:13", "throughput": 5184.84, "total_tokens": 5017600} {"current_steps": 1226, "total_steps": 6710, "loss": 0.9285, "lr": 2.2996643268442934e-06, "epoch": 0.9135618479880775, "percentage": 18.27, "elapsed_time": "0:16:08", "remaining_time": "1:12:12", "throughput": 5184.89, "total_tokens": 5021696} {"current_steps": 1227, "total_steps": 6710, "loss": 1.1296, "lr": 2.299346422910557e-06, "epoch": 0.9143070044709389, "percentage": 18.29, "elapsed_time": "0:16:09", "remaining_time": "1:12:11", "throughput": 5184.92, "total_tokens": 5025792} {"current_steps": 1228, "total_steps": 6710, "loss": 1.1678, "lr": 2.299028288952591e-06, "epoch": 0.9150521609538003, "percentage": 18.3, "elapsed_time": "0:16:10", "remaining_time": "1:12:10", "throughput": 5184.96, "total_tokens": 5029888} {"current_steps": 1229, "total_steps": 6710, "loss": 0.8149, "lr": 2.298709925040134e-06, "epoch": 0.9157973174366617, "percentage": 18.32, "elapsed_time": "0:16:10", "remaining_time": "1:12:09", "throughput": 5184.99, "total_tokens": 5033984} {"current_steps": 1230, "total_steps": 6710, "loss": 1.2315, "lr": 2.2983913312429726e-06, "epoch": 0.9165424739195231, "percentage": 18.33, "elapsed_time": "0:16:11", "remaining_time": "1:12:09", "throughput": 5185.01, "total_tokens": 5038080} {"current_steps": 1231, "total_steps": 6710, "loss": 1.164, "lr": 2.298072507630945e-06, "epoch": 0.9172876304023845, "percentage": 18.35, "elapsed_time": "0:16:12", "remaining_time": "1:12:08", "throughput": 5185.04, "total_tokens": 5042176} {"current_steps": 1232, "total_steps": 6710, "loss": 1.1128, "lr": 2.2977534542739404e-06, "epoch": 0.9180327868852459, "percentage": 18.36, "elapsed_time": "0:16:13", "remaining_time": "1:12:07", "throughput": 5185.08, "total_tokens": 5046272} {"current_steps": 1233, "total_steps": 6710, "loss": 1.1526, "lr": 2.2974341712418967e-06, "epoch": 0.9187779433681073, "percentage": 18.38, "elapsed_time": "0:16:14", "remaining_time": "1:12:06", "throughput": 5185.13, "total_tokens": 5050368} {"current_steps": 1234, "total_steps": 6710, "loss": 1.2583, "lr": 2.297114658604803e-06, "epoch": 0.9195230998509687, "percentage": 18.39, "elapsed_time": "0:16:14", "remaining_time": "1:12:05", "throughput": 5185.17, "total_tokens": 5054464} {"current_steps": 1235, "total_steps": 6710, "loss": 0.9214, "lr": 2.2967949164326995e-06, "epoch": 0.9202682563338301, "percentage": 18.41, "elapsed_time": "0:16:15", "remaining_time": "1:12:04", "throughput": 5185.21, "total_tokens": 5058560} {"current_steps": 1236, "total_steps": 6710, "loss": 1.1788, "lr": 2.2964749447956758e-06, "epoch": 0.9210134128166915, "percentage": 18.42, "elapsed_time": "0:16:16", "remaining_time": "1:12:04", "throughput": 5185.27, "total_tokens": 5062656} {"current_steps": 1237, "total_steps": 6710, "loss": 1.4192, "lr": 2.2961547437638712e-06, "epoch": 0.9217585692995529, "percentage": 18.44, "elapsed_time": "0:16:17", "remaining_time": "1:12:03", "throughput": 5185.31, "total_tokens": 5066752} {"current_steps": 1238, "total_steps": 6710, "loss": 1.1698, "lr": 2.2958343134074766e-06, "epoch": 0.9225037257824144, "percentage": 18.45, "elapsed_time": "0:16:17", "remaining_time": "1:12:02", "throughput": 5185.36, "total_tokens": 5070848} {"current_steps": 1239, "total_steps": 6710, "loss": 1.1774, "lr": 2.2955136537967325e-06, "epoch": 0.9232488822652757, "percentage": 18.46, "elapsed_time": "0:16:18", "remaining_time": "1:12:01", "throughput": 5185.41, "total_tokens": 5074944} {"current_steps": 1240, "total_steps": 6710, "loss": 1.2984, "lr": 2.2951927650019304e-06, "epoch": 0.9239940387481371, "percentage": 18.48, "elapsed_time": "0:16:19", "remaining_time": "1:12:00", "throughput": 5185.45, "total_tokens": 5079040} {"current_steps": 1241, "total_steps": 6710, "loss": 0.8935, "lr": 2.2948716470934104e-06, "epoch": 0.9247391952309985, "percentage": 18.49, "elapsed_time": "0:16:20", "remaining_time": "1:11:59", "throughput": 5185.48, "total_tokens": 5083136} {"current_steps": 1242, "total_steps": 6710, "loss": 0.9927, "lr": 2.2945503001415643e-06, "epoch": 0.9254843517138599, "percentage": 18.51, "elapsed_time": "0:16:21", "remaining_time": "1:11:59", "throughput": 5185.52, "total_tokens": 5087232} {"current_steps": 1243, "total_steps": 6710, "loss": 1.4336, "lr": 2.2942287242168337e-06, "epoch": 0.9262295081967213, "percentage": 18.52, "elapsed_time": "0:16:21", "remaining_time": "1:11:58", "throughput": 5185.56, "total_tokens": 5091328} {"current_steps": 1244, "total_steps": 6710, "loss": 1.1284, "lr": 2.2939069193897105e-06, "epoch": 0.9269746646795827, "percentage": 18.54, "elapsed_time": "0:16:22", "remaining_time": "1:11:57", "throughput": 5185.6, "total_tokens": 5095424} {"current_steps": 1245, "total_steps": 6710, "loss": 1.4079, "lr": 2.2935848857307362e-06, "epoch": 0.9277198211624441, "percentage": 18.55, "elapsed_time": "0:16:23", "remaining_time": "1:11:56", "throughput": 5185.65, "total_tokens": 5099520} {"current_steps": 1246, "total_steps": 6710, "loss": 1.2626, "lr": 2.2932626233105034e-06, "epoch": 0.9284649776453056, "percentage": 18.57, "elapsed_time": "0:16:24", "remaining_time": "1:11:55", "throughput": 5185.69, "total_tokens": 5103616} {"current_steps": 1247, "total_steps": 6710, "loss": 1.0845, "lr": 2.2929401321996537e-06, "epoch": 0.9292101341281669, "percentage": 18.58, "elapsed_time": "0:16:24", "remaining_time": "1:11:55", "throughput": 5185.73, "total_tokens": 5107712} {"current_steps": 1248, "total_steps": 6710, "loss": 1.0761, "lr": 2.2926174124688797e-06, "epoch": 0.9299552906110283, "percentage": 18.6, "elapsed_time": "0:16:25", "remaining_time": "1:11:54", "throughput": 5185.76, "total_tokens": 5111808} {"current_steps": 1249, "total_steps": 6710, "loss": 1.1594, "lr": 2.292294464188924e-06, "epoch": 0.9307004470938898, "percentage": 18.61, "elapsed_time": "0:16:26", "remaining_time": "1:11:53", "throughput": 5185.81, "total_tokens": 5115904} {"current_steps": 1250, "total_steps": 6710, "loss": 1.2593, "lr": 2.2919712874305794e-06, "epoch": 0.9314456035767511, "percentage": 18.63, "elapsed_time": "0:16:27", "remaining_time": "1:11:52", "throughput": 5185.86, "total_tokens": 5120000} {"current_steps": 1251, "total_steps": 6710, "loss": 1.1582, "lr": 2.2916478822646877e-06, "epoch": 0.9321907600596125, "percentage": 18.64, "elapsed_time": "0:16:28", "remaining_time": "1:11:51", "throughput": 5185.89, "total_tokens": 5124096} {"current_steps": 1252, "total_steps": 6710, "loss": 1.3744, "lr": 2.2913242487621427e-06, "epoch": 0.9329359165424739, "percentage": 18.66, "elapsed_time": "0:16:28", "remaining_time": "1:11:50", "throughput": 5185.86, "total_tokens": 5128192} {"current_steps": 1253, "total_steps": 6710, "loss": 1.2049, "lr": 2.291000386993886e-06, "epoch": 0.9336810730253353, "percentage": 18.67, "elapsed_time": "0:16:29", "remaining_time": "1:11:50", "throughput": 5185.9, "total_tokens": 5132288} {"current_steps": 1254, "total_steps": 6710, "loss": 1.1112, "lr": 2.290676297030912e-06, "epoch": 0.9344262295081968, "percentage": 18.69, "elapsed_time": "0:16:30", "remaining_time": "1:11:49", "throughput": 5185.93, "total_tokens": 5136384} {"current_steps": 1255, "total_steps": 6710, "loss": 1.2231, "lr": 2.290351978944262e-06, "epoch": 0.9351713859910581, "percentage": 18.7, "elapsed_time": "0:16:31", "remaining_time": "1:11:48", "throughput": 5185.97, "total_tokens": 5140480} {"current_steps": 1256, "total_steps": 6710, "loss": 1.0871, "lr": 2.2900274328050295e-06, "epoch": 0.9359165424739195, "percentage": 18.72, "elapsed_time": "0:16:32", "remaining_time": "1:11:47", "throughput": 5186.03, "total_tokens": 5144576} {"current_steps": 1257, "total_steps": 6710, "loss": 1.4123, "lr": 2.2897026586843573e-06, "epoch": 0.936661698956781, "percentage": 18.73, "elapsed_time": "0:16:32", "remaining_time": "1:11:46", "throughput": 5186.07, "total_tokens": 5148672} {"current_steps": 1258, "total_steps": 6710, "loss": 1.0333, "lr": 2.289377656653438e-06, "epoch": 0.9374068554396423, "percentage": 18.75, "elapsed_time": "0:16:33", "remaining_time": "1:11:46", "throughput": 5186.1, "total_tokens": 5152768} {"current_steps": 1259, "total_steps": 6710, "loss": 1.2072, "lr": 2.289052426783515e-06, "epoch": 0.9381520119225037, "percentage": 18.76, "elapsed_time": "0:16:34", "remaining_time": "1:11:45", "throughput": 5186.14, "total_tokens": 5156864} {"current_steps": 1260, "total_steps": 6710, "loss": 1.249, "lr": 2.2887269691458804e-06, "epoch": 0.9388971684053651, "percentage": 18.78, "elapsed_time": "0:16:35", "remaining_time": "1:11:44", "throughput": 5186.18, "total_tokens": 5160960} {"current_steps": 1261, "total_steps": 6710, "loss": 0.9638, "lr": 2.2884012838118765e-06, "epoch": 0.9396423248882265, "percentage": 18.79, "elapsed_time": "0:16:35", "remaining_time": "1:11:43", "throughput": 5186.23, "total_tokens": 5165056} {"current_steps": 1262, "total_steps": 6710, "loss": 0.9925, "lr": 2.288075370852897e-06, "epoch": 0.940387481371088, "percentage": 18.81, "elapsed_time": "0:16:36", "remaining_time": "1:11:42", "throughput": 5186.27, "total_tokens": 5169152} {"current_steps": 1263, "total_steps": 6710, "loss": 1.0942, "lr": 2.287749230340383e-06, "epoch": 0.9411326378539493, "percentage": 18.82, "elapsed_time": "0:16:37", "remaining_time": "1:11:41", "throughput": 5186.31, "total_tokens": 5173248} {"current_steps": 1264, "total_steps": 6710, "loss": 1.2773, "lr": 2.2874228623458283e-06, "epoch": 0.9418777943368107, "percentage": 18.84, "elapsed_time": "0:16:38", "remaining_time": "1:11:41", "throughput": 5186.35, "total_tokens": 5177344} {"current_steps": 1265, "total_steps": 6710, "loss": 1.4217, "lr": 2.2870962669407735e-06, "epoch": 0.9426229508196722, "percentage": 18.85, "elapsed_time": "0:16:39", "remaining_time": "1:11:40", "throughput": 5186.38, "total_tokens": 5181440} {"current_steps": 1266, "total_steps": 6710, "loss": 1.2464, "lr": 2.2867694441968123e-06, "epoch": 0.9433681073025335, "percentage": 18.87, "elapsed_time": "0:16:39", "remaining_time": "1:11:39", "throughput": 5186.42, "total_tokens": 5185536} {"current_steps": 1267, "total_steps": 6710, "loss": 1.3176, "lr": 2.286442394185585e-06, "epoch": 0.944113263785395, "percentage": 18.88, "elapsed_time": "0:16:40", "remaining_time": "1:11:38", "throughput": 5186.45, "total_tokens": 5189632} {"current_steps": 1268, "total_steps": 6710, "loss": 1.2914, "lr": 2.2861151169787845e-06, "epoch": 0.9448584202682563, "percentage": 18.9, "elapsed_time": "0:16:41", "remaining_time": "1:11:37", "throughput": 5186.47, "total_tokens": 5193728} {"current_steps": 1269, "total_steps": 6710, "loss": 1.2796, "lr": 2.285787612648152e-06, "epoch": 0.9456035767511177, "percentage": 18.91, "elapsed_time": "0:16:42", "remaining_time": "1:11:37", "throughput": 5186.48, "total_tokens": 5197824} {"current_steps": 1270, "total_steps": 6710, "loss": 1.1236, "lr": 2.2854598812654784e-06, "epoch": 0.9463487332339792, "percentage": 18.93, "elapsed_time": "0:16:42", "remaining_time": "1:11:36", "throughput": 5186.51, "total_tokens": 5201920} {"current_steps": 1271, "total_steps": 6710, "loss": 1.0794, "lr": 2.2851319229026046e-06, "epoch": 0.9470938897168405, "percentage": 18.94, "elapsed_time": "0:16:43", "remaining_time": "1:11:35", "throughput": 5186.55, "total_tokens": 5206016} {"current_steps": 1272, "total_steps": 6710, "loss": 1.0616, "lr": 2.284803737631422e-06, "epoch": 0.9478390461997019, "percentage": 18.96, "elapsed_time": "0:16:44", "remaining_time": "1:11:34", "throughput": 5186.56, "total_tokens": 5210112} {"current_steps": 1273, "total_steps": 6710, "loss": 1.0694, "lr": 2.284475325523871e-06, "epoch": 0.9485842026825634, "percentage": 18.97, "elapsed_time": "0:16:45", "remaining_time": "1:11:33", "throughput": 5186.59, "total_tokens": 5214208} {"current_steps": 1274, "total_steps": 6710, "loss": 0.8849, "lr": 2.284146686651942e-06, "epoch": 0.9493293591654247, "percentage": 18.99, "elapsed_time": "0:16:46", "remaining_time": "1:11:32", "throughput": 5186.61, "total_tokens": 5218304} {"current_steps": 1275, "total_steps": 6710, "loss": 1.1473, "lr": 2.283817821087675e-06, "epoch": 0.9500745156482862, "percentage": 19.0, "elapsed_time": "0:16:46", "remaining_time": "1:11:32", "throughput": 5186.65, "total_tokens": 5222400} {"current_steps": 1276, "total_steps": 6710, "loss": 1.2546, "lr": 2.2834887289031586e-06, "epoch": 0.9508196721311475, "percentage": 19.02, "elapsed_time": "0:16:47", "remaining_time": "1:11:31", "throughput": 5186.68, "total_tokens": 5226496} {"current_steps": 1277, "total_steps": 6710, "loss": 1.4144, "lr": 2.283159410170534e-06, "epoch": 0.9515648286140089, "percentage": 19.03, "elapsed_time": "0:16:48", "remaining_time": "1:11:30", "throughput": 5186.72, "total_tokens": 5230592} {"current_steps": 1278, "total_steps": 6710, "loss": 1.2992, "lr": 2.282829864961989e-06, "epoch": 0.9523099850968704, "percentage": 19.05, "elapsed_time": "0:16:49", "remaining_time": "1:11:29", "throughput": 5186.77, "total_tokens": 5234688} {"current_steps": 1279, "total_steps": 6710, "loss": 0.8906, "lr": 2.2825000933497623e-06, "epoch": 0.9530551415797317, "percentage": 19.06, "elapsed_time": "0:16:50", "remaining_time": "1:11:28", "throughput": 5186.81, "total_tokens": 5238784} {"current_steps": 1280, "total_steps": 6710, "loss": 1.2396, "lr": 2.2821700954061425e-06, "epoch": 0.9538002980625931, "percentage": 19.08, "elapsed_time": "0:16:50", "remaining_time": "1:11:28", "throughput": 5186.86, "total_tokens": 5242880} {"current_steps": 1281, "total_steps": 6710, "loss": 1.206, "lr": 2.2818398712034677e-06, "epoch": 0.9545454545454546, "percentage": 19.09, "elapsed_time": "0:16:51", "remaining_time": "1:11:27", "throughput": 5186.9, "total_tokens": 5246976} {"current_steps": 1282, "total_steps": 6710, "loss": 1.2336, "lr": 2.281509420814125e-06, "epoch": 0.9552906110283159, "percentage": 19.11, "elapsed_time": "0:16:52", "remaining_time": "1:11:26", "throughput": 5186.96, "total_tokens": 5251072} {"current_steps": 1283, "total_steps": 6710, "loss": 1.2145, "lr": 2.2811787443105513e-06, "epoch": 0.9560357675111774, "percentage": 19.12, "elapsed_time": "0:16:53", "remaining_time": "1:11:25", "throughput": 5186.99, "total_tokens": 5255168} {"current_steps": 1284, "total_steps": 6710, "loss": 1.2463, "lr": 2.280847841765234e-06, "epoch": 0.9567809239940388, "percentage": 19.14, "elapsed_time": "0:16:53", "remaining_time": "1:11:24", "throughput": 5187.03, "total_tokens": 5259264} {"current_steps": 1285, "total_steps": 6710, "loss": 0.9038, "lr": 2.280516713250709e-06, "epoch": 0.9575260804769001, "percentage": 19.15, "elapsed_time": "0:16:54", "remaining_time": "1:11:23", "throughput": 5187.07, "total_tokens": 5263360} {"current_steps": 1286, "total_steps": 6710, "loss": 1.3812, "lr": 2.2801853588395615e-06, "epoch": 0.9582712369597616, "percentage": 19.17, "elapsed_time": "0:16:55", "remaining_time": "1:11:23", "throughput": 5187.1, "total_tokens": 5267456} {"current_steps": 1287, "total_steps": 6710, "loss": 1.5859, "lr": 2.2798537786044273e-06, "epoch": 0.9590163934426229, "percentage": 19.18, "elapsed_time": "0:16:56", "remaining_time": "1:11:22", "throughput": 5187.14, "total_tokens": 5271552} {"current_steps": 1288, "total_steps": 6710, "loss": 1.2467, "lr": 2.279521972617991e-06, "epoch": 0.9597615499254843, "percentage": 19.2, "elapsed_time": "0:16:57", "remaining_time": "1:11:21", "throughput": 5187.19, "total_tokens": 5275648} {"current_steps": 1289, "total_steps": 6710, "loss": 1.1051, "lr": 2.279189940952987e-06, "epoch": 0.9605067064083458, "percentage": 19.21, "elapsed_time": "0:16:57", "remaining_time": "1:11:20", "throughput": 5187.24, "total_tokens": 5279744} {"current_steps": 1290, "total_steps": 6710, "loss": 1.0335, "lr": 2.2788576836821985e-06, "epoch": 0.9612518628912071, "percentage": 19.23, "elapsed_time": "0:16:58", "remaining_time": "1:11:19", "throughput": 5187.28, "total_tokens": 5283840} {"current_steps": 1291, "total_steps": 6710, "loss": 1.3206, "lr": 2.2785252008784594e-06, "epoch": 0.9619970193740686, "percentage": 19.24, "elapsed_time": "0:16:59", "remaining_time": "1:11:18", "throughput": 5187.25, "total_tokens": 5287936} {"current_steps": 1292, "total_steps": 6710, "loss": 1.1775, "lr": 2.278192492614652e-06, "epoch": 0.96274217585693, "percentage": 19.25, "elapsed_time": "0:17:00", "remaining_time": "1:11:18", "throughput": 5187.28, "total_tokens": 5292032} {"current_steps": 1293, "total_steps": 6710, "loss": 1.2737, "lr": 2.277859558963708e-06, "epoch": 0.9634873323397913, "percentage": 19.27, "elapsed_time": "0:17:00", "remaining_time": "1:11:17", "throughput": 5187.3, "total_tokens": 5296128} {"current_steps": 1294, "total_steps": 6710, "loss": 1.2061, "lr": 2.277526399998609e-06, "epoch": 0.9642324888226528, "percentage": 19.28, "elapsed_time": "0:17:01", "remaining_time": "1:11:16", "throughput": 5187.35, "total_tokens": 5300224} {"current_steps": 1295, "total_steps": 6710, "loss": 1.1353, "lr": 2.277193015792386e-06, "epoch": 0.9649776453055141, "percentage": 19.3, "elapsed_time": "0:17:02", "remaining_time": "1:11:15", "throughput": 5187.38, "total_tokens": 5304320} {"current_steps": 1296, "total_steps": 6710, "loss": 1.3654, "lr": 2.2768594064181193e-06, "epoch": 0.9657228017883756, "percentage": 19.31, "elapsed_time": "0:17:03", "remaining_time": "1:11:14", "throughput": 5187.43, "total_tokens": 5308416} {"current_steps": 1297, "total_steps": 6710, "loss": 1.1877, "lr": 2.276525571948938e-06, "epoch": 0.966467958271237, "percentage": 19.33, "elapsed_time": "0:17:04", "remaining_time": "1:11:14", "throughput": 5187.47, "total_tokens": 5312512} {"current_steps": 1298, "total_steps": 6710, "loss": 1.3979, "lr": 2.276191512458022e-06, "epoch": 0.9672131147540983, "percentage": 19.34, "elapsed_time": "0:17:04", "remaining_time": "1:11:13", "throughput": 5187.49, "total_tokens": 5316608} {"current_steps": 1299, "total_steps": 6710, "loss": 1.0945, "lr": 2.2758572280185983e-06, "epoch": 0.9679582712369598, "percentage": 19.36, "elapsed_time": "0:17:05", "remaining_time": "1:11:12", "throughput": 5187.52, "total_tokens": 5320704} {"current_steps": 1300, "total_steps": 6710, "loss": 1.0659, "lr": 2.2755227187039446e-06, "epoch": 0.9687034277198212, "percentage": 19.37, "elapsed_time": "0:17:06", "remaining_time": "1:11:11", "throughput": 5187.56, "total_tokens": 5324800} {"current_steps": 1301, "total_steps": 6710, "loss": 1.0792, "lr": 2.275187984587389e-06, "epoch": 0.9694485842026825, "percentage": 19.39, "elapsed_time": "0:17:07", "remaining_time": "1:11:10", "throughput": 5187.61, "total_tokens": 5328896} {"current_steps": 1302, "total_steps": 6710, "loss": 1.065, "lr": 2.2748530257423056e-06, "epoch": 0.970193740685544, "percentage": 19.4, "elapsed_time": "0:17:08", "remaining_time": "1:11:09", "throughput": 5187.65, "total_tokens": 5332992} {"current_steps": 1303, "total_steps": 6710, "loss": 0.9912, "lr": 2.2745178422421215e-06, "epoch": 0.9709388971684053, "percentage": 19.42, "elapsed_time": "0:17:08", "remaining_time": "1:11:09", "throughput": 5187.7, "total_tokens": 5337088} {"current_steps": 1304, "total_steps": 6710, "loss": 1.0781, "lr": 2.2741824341603105e-06, "epoch": 0.9716840536512668, "percentage": 19.43, "elapsed_time": "0:17:09", "remaining_time": "1:11:08", "throughput": 5187.75, "total_tokens": 5341184} {"current_steps": 1305, "total_steps": 6710, "loss": 1.2993, "lr": 2.2738468015703966e-06, "epoch": 0.9724292101341282, "percentage": 19.45, "elapsed_time": "0:17:10", "remaining_time": "1:11:07", "throughput": 5187.78, "total_tokens": 5345280} {"current_steps": 1306, "total_steps": 6710, "loss": 1.3574, "lr": 2.273510944545953e-06, "epoch": 0.9731743666169895, "percentage": 19.46, "elapsed_time": "0:17:11", "remaining_time": "1:11:06", "throughput": 5187.82, "total_tokens": 5349376} {"current_steps": 1307, "total_steps": 6710, "loss": 1.1263, "lr": 2.2731748631606018e-06, "epoch": 0.973919523099851, "percentage": 19.48, "elapsed_time": "0:17:11", "remaining_time": "1:11:05", "throughput": 5187.82, "total_tokens": 5353472} {"current_steps": 1308, "total_steps": 6710, "loss": 1.4476, "lr": 2.2728385574880147e-06, "epoch": 0.9746646795827124, "percentage": 19.49, "elapsed_time": "0:17:12", "remaining_time": "1:11:05", "throughput": 5187.83, "total_tokens": 5357568} {"current_steps": 1309, "total_steps": 6710, "loss": 0.9841, "lr": 2.2725020276019115e-06, "epoch": 0.9754098360655737, "percentage": 19.51, "elapsed_time": "0:17:13", "remaining_time": "1:11:04", "throughput": 5187.88, "total_tokens": 5361664} {"current_steps": 1310, "total_steps": 6710, "loss": 1.2425, "lr": 2.272165273576063e-06, "epoch": 0.9761549925484352, "percentage": 19.52, "elapsed_time": "0:17:14", "remaining_time": "1:11:03", "throughput": 5187.92, "total_tokens": 5365760} {"current_steps": 1311, "total_steps": 6710, "loss": 1.2612, "lr": 2.2718282954842875e-06, "epoch": 0.9769001490312966, "percentage": 19.54, "elapsed_time": "0:17:15", "remaining_time": "1:11:02", "throughput": 5187.97, "total_tokens": 5369856} {"current_steps": 1312, "total_steps": 6710, "loss": 0.957, "lr": 2.271491093400453e-06, "epoch": 0.977645305514158, "percentage": 19.55, "elapsed_time": "0:17:15", "remaining_time": "1:11:01", "throughput": 5188.02, "total_tokens": 5373952} {"current_steps": 1313, "total_steps": 6710, "loss": 1.0855, "lr": 2.271153667398477e-06, "epoch": 0.9783904619970194, "percentage": 19.57, "elapsed_time": "0:17:16", "remaining_time": "1:11:00", "throughput": 5188.07, "total_tokens": 5378048} {"current_steps": 1314, "total_steps": 6710, "loss": 1.1942, "lr": 2.270816017552325e-06, "epoch": 0.9791356184798807, "percentage": 19.58, "elapsed_time": "0:17:17", "remaining_time": "1:11:00", "throughput": 5188.11, "total_tokens": 5382144} {"current_steps": 1315, "total_steps": 6710, "loss": 1.1862, "lr": 2.270478143936013e-06, "epoch": 0.9798807749627422, "percentage": 19.6, "elapsed_time": "0:17:18", "remaining_time": "1:10:59", "throughput": 5188.15, "total_tokens": 5386240} {"current_steps": 1316, "total_steps": 6710, "loss": 0.97, "lr": 2.270140046623605e-06, "epoch": 0.9806259314456036, "percentage": 19.61, "elapsed_time": "0:17:18", "remaining_time": "1:10:58", "throughput": 5188.18, "total_tokens": 5390336} {"current_steps": 1317, "total_steps": 6710, "loss": 0.8966, "lr": 2.2698017256892143e-06, "epoch": 0.981371087928465, "percentage": 19.63, "elapsed_time": "0:17:19", "remaining_time": "1:10:57", "throughput": 5188.23, "total_tokens": 5394432} {"current_steps": 1318, "total_steps": 6710, "loss": 1.0896, "lr": 2.2694631812070028e-06, "epoch": 0.9821162444113264, "percentage": 19.64, "elapsed_time": "0:17:20", "remaining_time": "1:10:56", "throughput": 5188.28, "total_tokens": 5398528} {"current_steps": 1319, "total_steps": 6710, "loss": 1.4936, "lr": 2.269124413251183e-06, "epoch": 0.9828614008941878, "percentage": 19.66, "elapsed_time": "0:17:21", "remaining_time": "1:10:56", "throughput": 5188.28, "total_tokens": 5402624} {"current_steps": 1320, "total_steps": 6710, "loss": 1.0596, "lr": 2.268785421896014e-06, "epoch": 0.9836065573770492, "percentage": 19.67, "elapsed_time": "0:17:22", "remaining_time": "1:10:55", "throughput": 5188.32, "total_tokens": 5406720} {"current_steps": 1321, "total_steps": 6710, "loss": 1.0785, "lr": 2.2684462072158064e-06, "epoch": 0.9843517138599106, "percentage": 19.69, "elapsed_time": "0:17:22", "remaining_time": "1:10:54", "throughput": 5188.36, "total_tokens": 5410816} {"current_steps": 1322, "total_steps": 6710, "loss": 1.2295, "lr": 2.2681067692849176e-06, "epoch": 0.9850968703427719, "percentage": 19.7, "elapsed_time": "0:17:23", "remaining_time": "1:10:53", "throughput": 5188.41, "total_tokens": 5414912} {"current_steps": 1323, "total_steps": 6710, "loss": 1.0792, "lr": 2.267767108177755e-06, "epoch": 0.9858420268256334, "percentage": 19.72, "elapsed_time": "0:17:24", "remaining_time": "1:10:52", "throughput": 5188.43, "total_tokens": 5419008} {"current_steps": 1324, "total_steps": 6710, "loss": 1.2822, "lr": 2.267427223968775e-06, "epoch": 0.9865871833084948, "percentage": 19.73, "elapsed_time": "0:17:25", "remaining_time": "1:10:51", "throughput": 5188.48, "total_tokens": 5423104} {"current_steps": 1325, "total_steps": 6710, "loss": 1.0748, "lr": 2.267087116732482e-06, "epoch": 0.9873323397913562, "percentage": 19.75, "elapsed_time": "0:17:25", "remaining_time": "1:10:51", "throughput": 5188.53, "total_tokens": 5427200} {"current_steps": 1326, "total_steps": 6710, "loss": 1.2333, "lr": 2.2667467865434304e-06, "epoch": 0.9880774962742176, "percentage": 19.76, "elapsed_time": "0:17:26", "remaining_time": "1:10:50", "throughput": 5188.57, "total_tokens": 5431296} {"current_steps": 1327, "total_steps": 6710, "loss": 1.2005, "lr": 2.266406233476223e-06, "epoch": 0.988822652757079, "percentage": 19.78, "elapsed_time": "0:17:27", "remaining_time": "1:10:49", "throughput": 5188.57, "total_tokens": 5435392} {"current_steps": 1328, "total_steps": 6710, "loss": 1.0831, "lr": 2.266065457605512e-06, "epoch": 0.9895678092399404, "percentage": 19.79, "elapsed_time": "0:17:28", "remaining_time": "1:10:48", "throughput": 5188.62, "total_tokens": 5439488} {"current_steps": 1329, "total_steps": 6710, "loss": 1.3163, "lr": 2.2657244590059966e-06, "epoch": 0.9903129657228018, "percentage": 19.81, "elapsed_time": "0:17:29", "remaining_time": "1:10:47", "throughput": 5188.67, "total_tokens": 5443584} {"current_steps": 1330, "total_steps": 6710, "loss": 0.8155, "lr": 2.2653832377524274e-06, "epoch": 0.9910581222056631, "percentage": 19.82, "elapsed_time": "0:17:29", "remaining_time": "1:10:47", "throughput": 5188.7, "total_tokens": 5447680} {"current_steps": 1331, "total_steps": 6710, "loss": 1.129, "lr": 2.265041793919602e-06, "epoch": 0.9918032786885246, "percentage": 19.84, "elapsed_time": "0:17:30", "remaining_time": "1:10:46", "throughput": 5188.73, "total_tokens": 5451776} {"current_steps": 1332, "total_steps": 6710, "loss": 1.2989, "lr": 2.264700127582367e-06, "epoch": 0.992548435171386, "percentage": 19.85, "elapsed_time": "0:17:31", "remaining_time": "1:10:45", "throughput": 5188.78, "total_tokens": 5455872} {"current_steps": 1333, "total_steps": 6710, "loss": 1.1894, "lr": 2.264358238815619e-06, "epoch": 0.9932935916542474, "percentage": 19.87, "elapsed_time": "0:17:32", "remaining_time": "1:10:44", "throughput": 5188.83, "total_tokens": 5459968} {"current_steps": 1334, "total_steps": 6710, "loss": 1.4266, "lr": 2.264016127694301e-06, "epoch": 0.9940387481371088, "percentage": 19.88, "elapsed_time": "0:17:33", "remaining_time": "1:10:43", "throughput": 5188.88, "total_tokens": 5464064} {"current_steps": 1335, "total_steps": 6710, "loss": 0.9122, "lr": 2.263673794293407e-06, "epoch": 0.9947839046199702, "percentage": 19.9, "elapsed_time": "0:17:33", "remaining_time": "1:10:42", "throughput": 5188.91, "total_tokens": 5468160} {"current_steps": 1336, "total_steps": 6710, "loss": 1.1205, "lr": 2.26333123868798e-06, "epoch": 0.9955290611028316, "percentage": 19.91, "elapsed_time": "0:17:34", "remaining_time": "1:10:42", "throughput": 5188.95, "total_tokens": 5472256} {"current_steps": 1337, "total_steps": 6710, "loss": 0.876, "lr": 2.2629884609531093e-06, "epoch": 0.996274217585693, "percentage": 19.93, "elapsed_time": "0:17:35", "remaining_time": "1:10:41", "throughput": 5189.0, "total_tokens": 5476352} {"current_steps": 1338, "total_steps": 6710, "loss": 1.0428, "lr": 2.262645461163934e-06, "epoch": 0.9970193740685543, "percentage": 19.94, "elapsed_time": "0:17:36", "remaining_time": "1:10:40", "throughput": 5189.03, "total_tokens": 5480448} {"current_steps": 1339, "total_steps": 6710, "loss": 1.2635, "lr": 2.2623022393956433e-06, "epoch": 0.9977645305514158, "percentage": 19.96, "elapsed_time": "0:17:36", "remaining_time": "1:10:39", "throughput": 5189.05, "total_tokens": 5484544} {"current_steps": 1340, "total_steps": 6710, "loss": 0.8619, "lr": 2.261958795723473e-06, "epoch": 0.9985096870342772, "percentage": 19.97, "elapsed_time": "0:17:37", "remaining_time": "1:10:38", "throughput": 5189.09, "total_tokens": 5488640} {"current_steps": 1341, "total_steps": 6710, "loss": 1.376, "lr": 2.261615130222709e-06, "epoch": 0.9992548435171386, "percentage": 19.99, "elapsed_time": "0:17:38", "remaining_time": "1:10:37", "throughput": 5189.13, "total_tokens": 5492736} {"current_steps": 1342, "total_steps": 6710, "loss": 1.0728, "lr": 2.2612712429686846e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:17:39", "remaining_time": "1:10:37", "throughput": 5189.15, "total_tokens": 5496832} {"current_steps": 1343, "total_steps": 6710, "loss": 0.7283, "lr": 2.2609271340367826e-06, "epoch": 1.0007451564828613, "percentage": 20.01, "elapsed_time": "0:17:40", "remaining_time": "1:10:36", "throughput": 5189.14, "total_tokens": 5500928} {"current_steps": 1344, "total_steps": 6710, "loss": 1.0523, "lr": 2.260582803502434e-06, "epoch": 1.0014903129657229, "percentage": 20.03, "elapsed_time": "0:17:40", "remaining_time": "1:10:35", "throughput": 5189.18, "total_tokens": 5505024} {"current_steps": 1345, "total_steps": 6710, "loss": 0.9486, "lr": 2.2602382514411186e-06, "epoch": 1.0022354694485842, "percentage": 20.04, "elapsed_time": "0:17:41", "remaining_time": "1:10:34", "throughput": 5189.21, "total_tokens": 5509120} {"current_steps": 1346, "total_steps": 6710, "loss": 0.927, "lr": 2.2598934779283656e-06, "epoch": 1.0029806259314455, "percentage": 20.06, "elapsed_time": "0:17:42", "remaining_time": "1:10:33", "throughput": 5189.25, "total_tokens": 5513216} {"current_steps": 1347, "total_steps": 6710, "loss": 0.7872, "lr": 2.2595484830397503e-06, "epoch": 1.003725782414307, "percentage": 20.07, "elapsed_time": "0:17:43", "remaining_time": "1:10:33", "throughput": 5189.29, "total_tokens": 5517312} {"current_steps": 1348, "total_steps": 6710, "loss": 0.9156, "lr": 2.2592032668508985e-06, "epoch": 1.0044709388971684, "percentage": 20.09, "elapsed_time": "0:17:43", "remaining_time": "1:10:32", "throughput": 5189.3, "total_tokens": 5521408} {"current_steps": 1349, "total_steps": 6710, "loss": 0.9037, "lr": 2.258857829437484e-06, "epoch": 1.0052160953800298, "percentage": 20.1, "elapsed_time": "0:17:44", "remaining_time": "1:10:31", "throughput": 5189.32, "total_tokens": 5525504} {"current_steps": 1350, "total_steps": 6710, "loss": 0.5464, "lr": 2.25851217087523e-06, "epoch": 1.0059612518628913, "percentage": 20.12, "elapsed_time": "0:17:45", "remaining_time": "1:10:30", "throughput": 5189.34, "total_tokens": 5529600} {"current_steps": 1351, "total_steps": 6710, "loss": 0.9373, "lr": 2.258166291239907e-06, "epoch": 1.0067064083457526, "percentage": 20.13, "elapsed_time": "0:17:46", "remaining_time": "1:10:29", "throughput": 5189.37, "total_tokens": 5533696} {"current_steps": 1352, "total_steps": 6710, "loss": 0.6238, "lr": 2.257820190607333e-06, "epoch": 1.007451564828614, "percentage": 20.15, "elapsed_time": "0:17:47", "remaining_time": "1:10:29", "throughput": 5189.42, "total_tokens": 5537792} {"current_steps": 1353, "total_steps": 6710, "loss": 0.934, "lr": 2.2574738690533774e-06, "epoch": 1.0081967213114753, "percentage": 20.16, "elapsed_time": "0:17:47", "remaining_time": "1:10:28", "throughput": 5189.44, "total_tokens": 5541888} {"current_steps": 1354, "total_steps": 6710, "loss": 0.7284, "lr": 2.257127326653956e-06, "epoch": 1.0089418777943369, "percentage": 20.18, "elapsed_time": "0:17:48", "remaining_time": "1:10:27", "throughput": 5189.48, "total_tokens": 5545984} {"current_steps": 1355, "total_steps": 6710, "loss": 1.0416, "lr": 2.2567805634850327e-06, "epoch": 1.0096870342771982, "percentage": 20.19, "elapsed_time": "0:17:49", "remaining_time": "1:10:26", "throughput": 5189.51, "total_tokens": 5550080} {"current_steps": 1356, "total_steps": 6710, "loss": 0.6216, "lr": 2.256433579622621e-06, "epoch": 1.0104321907600595, "percentage": 20.21, "elapsed_time": "0:17:50", "remaining_time": "1:10:25", "throughput": 5189.53, "total_tokens": 5554176} {"current_steps": 1357, "total_steps": 6710, "loss": 0.6755, "lr": 2.256086375142782e-06, "epoch": 1.011177347242921, "percentage": 20.22, "elapsed_time": "0:17:51", "remaining_time": "1:10:24", "throughput": 5189.58, "total_tokens": 5558272} {"current_steps": 1358, "total_steps": 6710, "loss": 0.4222, "lr": 2.255738950121625e-06, "epoch": 1.0119225037257824, "percentage": 20.24, "elapsed_time": "0:17:51", "remaining_time": "1:10:24", "throughput": 5189.62, "total_tokens": 5562368} {"current_steps": 1359, "total_steps": 6710, "loss": 1.0672, "lr": 2.255391304635309e-06, "epoch": 1.0126676602086437, "percentage": 20.25, "elapsed_time": "0:17:52", "remaining_time": "1:10:23", "throughput": 5189.65, "total_tokens": 5566464} {"current_steps": 1360, "total_steps": 6710, "loss": 0.6409, "lr": 2.25504343876004e-06, "epoch": 1.0134128166915053, "percentage": 20.27, "elapsed_time": "0:17:53", "remaining_time": "1:10:22", "throughput": 5189.68, "total_tokens": 5570560} {"current_steps": 1361, "total_steps": 6710, "loss": 0.7976, "lr": 2.2546953525720724e-06, "epoch": 1.0141579731743666, "percentage": 20.28, "elapsed_time": "0:17:54", "remaining_time": "1:10:21", "throughput": 5189.68, "total_tokens": 5574656} {"current_steps": 1362, "total_steps": 6710, "loss": 0.996, "lr": 2.254347046147709e-06, "epoch": 1.014903129657228, "percentage": 20.3, "elapsed_time": "0:17:54", "remaining_time": "1:10:20", "throughput": 5189.71, "total_tokens": 5578752} {"current_steps": 1363, "total_steps": 6710, "loss": 0.4849, "lr": 2.2539985195633016e-06, "epoch": 1.0156482861400895, "percentage": 20.31, "elapsed_time": "0:17:55", "remaining_time": "1:10:20", "throughput": 5189.74, "total_tokens": 5582848} {"current_steps": 1364, "total_steps": 6710, "loss": 1.0111, "lr": 2.25364977289525e-06, "epoch": 1.0163934426229508, "percentage": 20.33, "elapsed_time": "0:17:56", "remaining_time": "1:10:19", "throughput": 5189.77, "total_tokens": 5586944} {"current_steps": 1365, "total_steps": 6710, "loss": 0.6742, "lr": 2.2533008062200006e-06, "epoch": 1.0171385991058122, "percentage": 20.34, "elapsed_time": "0:17:57", "remaining_time": "1:10:18", "throughput": 5189.8, "total_tokens": 5591040} {"current_steps": 1366, "total_steps": 6710, "loss": 1.1177, "lr": 2.2529516196140513e-06, "epoch": 1.0178837555886737, "percentage": 20.36, "elapsed_time": "0:17:58", "remaining_time": "1:10:17", "throughput": 5189.84, "total_tokens": 5595136} {"current_steps": 1367, "total_steps": 6710, "loss": 0.395, "lr": 2.252602213153944e-06, "epoch": 1.018628912071535, "percentage": 20.37, "elapsed_time": "0:17:58", "remaining_time": "1:10:16", "throughput": 5189.86, "total_tokens": 5599232} {"current_steps": 1368, "total_steps": 6710, "loss": 0.7613, "lr": 2.252252586916274e-06, "epoch": 1.0193740685543964, "percentage": 20.39, "elapsed_time": "0:17:59", "remaining_time": "1:10:16", "throughput": 5189.87, "total_tokens": 5603328} {"current_steps": 1369, "total_steps": 6710, "loss": 0.8923, "lr": 2.251902740977679e-06, "epoch": 1.0201192250372577, "percentage": 20.4, "elapsed_time": "0:18:00", "remaining_time": "1:10:15", "throughput": 5189.87, "total_tokens": 5607424} {"current_steps": 1370, "total_steps": 6710, "loss": 0.5857, "lr": 2.2515526754148493e-06, "epoch": 1.0208643815201193, "percentage": 20.42, "elapsed_time": "0:18:01", "remaining_time": "1:10:14", "throughput": 5189.91, "total_tokens": 5611520} {"current_steps": 1371, "total_steps": 6710, "loss": 0.7844, "lr": 2.251202390304521e-06, "epoch": 1.0216095380029806, "percentage": 20.43, "elapsed_time": "0:18:02", "remaining_time": "1:10:13", "throughput": 5189.94, "total_tokens": 5615616} {"current_steps": 1372, "total_steps": 6710, "loss": 0.6654, "lr": 2.2508518857234802e-06, "epoch": 1.022354694485842, "percentage": 20.45, "elapsed_time": "0:18:02", "remaining_time": "1:10:12", "throughput": 5189.96, "total_tokens": 5619712} {"current_steps": 1373, "total_steps": 6710, "loss": 0.8404, "lr": 2.2505011617485588e-06, "epoch": 1.0230998509687035, "percentage": 20.46, "elapsed_time": "0:18:03", "remaining_time": "1:10:12", "throughput": 5189.99, "total_tokens": 5623808} {"current_steps": 1374, "total_steps": 6710, "loss": 0.452, "lr": 2.2501502184566394e-06, "epoch": 1.0238450074515648, "percentage": 20.48, "elapsed_time": "0:18:04", "remaining_time": "1:10:11", "throughput": 5190.02, "total_tokens": 5627904} {"current_steps": 1375, "total_steps": 6710, "loss": 0.6388, "lr": 2.2497990559246496e-06, "epoch": 1.0245901639344261, "percentage": 20.49, "elapsed_time": "0:18:05", "remaining_time": "1:10:10", "throughput": 5190.04, "total_tokens": 5632000} {"current_steps": 1376, "total_steps": 6710, "loss": 0.9449, "lr": 2.2494476742295675e-06, "epoch": 1.0253353204172877, "percentage": 20.51, "elapsed_time": "0:18:05", "remaining_time": "1:10:09", "throughput": 5190.01, "total_tokens": 5636096} {"current_steps": 1377, "total_steps": 6710, "loss": 0.7754, "lr": 2.2490960734484186e-06, "epoch": 1.026080476900149, "percentage": 20.52, "elapsed_time": "0:18:06", "remaining_time": "1:10:08", "throughput": 5190.05, "total_tokens": 5640192} {"current_steps": 1378, "total_steps": 6710, "loss": 0.8899, "lr": 2.2487442536582764e-06, "epoch": 1.0268256333830104, "percentage": 20.54, "elapsed_time": "0:18:07", "remaining_time": "1:10:07", "throughput": 5190.08, "total_tokens": 5644288} {"current_steps": 1379, "total_steps": 6710, "loss": 0.5382, "lr": 2.2483922149362622e-06, "epoch": 1.027570789865872, "percentage": 20.55, "elapsed_time": "0:18:08", "remaining_time": "1:10:07", "throughput": 5190.1, "total_tokens": 5648384} {"current_steps": 1380, "total_steps": 6710, "loss": 0.7545, "lr": 2.248039957359545e-06, "epoch": 1.0283159463487332, "percentage": 20.57, "elapsed_time": "0:18:09", "remaining_time": "1:10:06", "throughput": 5190.13, "total_tokens": 5652480} {"current_steps": 1381, "total_steps": 6710, "loss": 0.7258, "lr": 2.247687481005343e-06, "epoch": 1.0290611028315946, "percentage": 20.58, "elapsed_time": "0:18:09", "remaining_time": "1:10:05", "throughput": 5190.15, "total_tokens": 5656576} {"current_steps": 1382, "total_steps": 6710, "loss": 0.4328, "lr": 2.2473347859509206e-06, "epoch": 1.0298062593144561, "percentage": 20.6, "elapsed_time": "0:18:10", "remaining_time": "1:10:04", "throughput": 5190.17, "total_tokens": 5660672} {"current_steps": 1383, "total_steps": 6710, "loss": 0.9117, "lr": 2.2469818722735918e-06, "epoch": 1.0305514157973175, "percentage": 20.61, "elapsed_time": "0:18:11", "remaining_time": "1:10:03", "throughput": 5190.16, "total_tokens": 5664768} {"current_steps": 1384, "total_steps": 6710, "loss": 1.1401, "lr": 2.2466287400507177e-06, "epoch": 1.0312965722801788, "percentage": 20.63, "elapsed_time": "0:18:12", "remaining_time": "1:10:03", "throughput": 5190.18, "total_tokens": 5668864} {"current_steps": 1385, "total_steps": 6710, "loss": 0.6311, "lr": 2.2462753893597065e-06, "epoch": 1.0320417287630403, "percentage": 20.64, "elapsed_time": "0:18:13", "remaining_time": "1:10:02", "throughput": 5190.21, "total_tokens": 5672960} {"current_steps": 1386, "total_steps": 6710, "loss": 0.9778, "lr": 2.2459218202780165e-06, "epoch": 1.0327868852459017, "percentage": 20.66, "elapsed_time": "0:18:13", "remaining_time": "1:10:01", "throughput": 5190.24, "total_tokens": 5677056} {"current_steps": 1387, "total_steps": 6710, "loss": 1.0053, "lr": 2.2455680328831515e-06, "epoch": 1.033532041728763, "percentage": 20.67, "elapsed_time": "0:18:14", "remaining_time": "1:10:00", "throughput": 5190.28, "total_tokens": 5681152} {"current_steps": 1388, "total_steps": 6710, "loss": 0.8007, "lr": 2.245214027252665e-06, "epoch": 1.0342771982116243, "percentage": 20.69, "elapsed_time": "0:18:15", "remaining_time": "1:09:59", "throughput": 5190.31, "total_tokens": 5685248} {"current_steps": 1389, "total_steps": 6710, "loss": 0.6788, "lr": 2.2448598034641574e-06, "epoch": 1.035022354694486, "percentage": 20.7, "elapsed_time": "0:18:16", "remaining_time": "1:09:59", "throughput": 5190.35, "total_tokens": 5689344} {"current_steps": 1390, "total_steps": 6710, "loss": 1.0024, "lr": 2.2445053615952767e-06, "epoch": 1.0357675111773472, "percentage": 20.72, "elapsed_time": "0:18:16", "remaining_time": "1:09:58", "throughput": 5190.38, "total_tokens": 5693440} {"current_steps": 1391, "total_steps": 6710, "loss": 0.466, "lr": 2.2441507017237196e-06, "epoch": 1.0365126676602086, "percentage": 20.73, "elapsed_time": "0:18:17", "remaining_time": "1:09:57", "throughput": 5190.42, "total_tokens": 5697536} {"current_steps": 1392, "total_steps": 6710, "loss": 1.0094, "lr": 2.2437958239272294e-06, "epoch": 1.03725782414307, "percentage": 20.75, "elapsed_time": "0:18:18", "remaining_time": "1:09:56", "throughput": 5190.42, "total_tokens": 5701632} {"current_steps": 1393, "total_steps": 6710, "loss": 0.9878, "lr": 2.2434407282835984e-06, "epoch": 1.0380029806259314, "percentage": 20.76, "elapsed_time": "0:18:19", "remaining_time": "1:09:55", "throughput": 5190.46, "total_tokens": 5705728} {"current_steps": 1394, "total_steps": 6710, "loss": 0.5129, "lr": 2.2430854148706664e-06, "epoch": 1.0387481371087928, "percentage": 20.77, "elapsed_time": "0:18:20", "remaining_time": "1:09:55", "throughput": 5190.5, "total_tokens": 5709824} {"current_steps": 1395, "total_steps": 6710, "loss": 0.5691, "lr": 2.24272988376632e-06, "epoch": 1.0394932935916543, "percentage": 20.79, "elapsed_time": "0:18:20", "remaining_time": "1:09:54", "throughput": 5190.53, "total_tokens": 5713920} {"current_steps": 1396, "total_steps": 6710, "loss": 0.8821, "lr": 2.242374135048494e-06, "epoch": 1.0402384500745157, "percentage": 20.8, "elapsed_time": "0:18:21", "remaining_time": "1:09:53", "throughput": 5190.56, "total_tokens": 5718016} {"current_steps": 1397, "total_steps": 6710, "loss": 0.9621, "lr": 2.2420181687951714e-06, "epoch": 1.040983606557377, "percentage": 20.82, "elapsed_time": "0:18:22", "remaining_time": "1:09:52", "throughput": 5190.6, "total_tokens": 5722112} {"current_steps": 1398, "total_steps": 6710, "loss": 0.813, "lr": 2.241661985084383e-06, "epoch": 1.0417287630402385, "percentage": 20.83, "elapsed_time": "0:18:23", "remaining_time": "1:09:51", "throughput": 5190.63, "total_tokens": 5726208} {"current_steps": 1399, "total_steps": 6710, "loss": 0.7249, "lr": 2.2413055839942063e-06, "epoch": 1.0424739195230999, "percentage": 20.85, "elapsed_time": "0:18:23", "remaining_time": "1:09:50", "throughput": 5190.66, "total_tokens": 5730304} {"current_steps": 1400, "total_steps": 6710, "loss": 0.8146, "lr": 2.2409489656027665e-06, "epoch": 1.0432190760059612, "percentage": 20.86, "elapsed_time": "0:18:24", "remaining_time": "1:09:50", "throughput": 5190.67, "total_tokens": 5734400} {"current_steps": 1401, "total_steps": 6710, "loss": 0.9992, "lr": 2.240592129988238e-06, "epoch": 1.0439642324888228, "percentage": 20.88, "elapsed_time": "0:18:25", "remaining_time": "1:09:49", "throughput": 5190.71, "total_tokens": 5738496} {"current_steps": 1402, "total_steps": 6710, "loss": 0.9069, "lr": 2.240235077228841e-06, "epoch": 1.044709388971684, "percentage": 20.89, "elapsed_time": "0:18:26", "remaining_time": "1:09:48", "throughput": 5190.75, "total_tokens": 5742592} {"current_steps": 1403, "total_steps": 6710, "loss": 1.1653, "lr": 2.2398778074028442e-06, "epoch": 1.0454545454545454, "percentage": 20.91, "elapsed_time": "0:18:27", "remaining_time": "1:09:47", "throughput": 5190.79, "total_tokens": 5746688} {"current_steps": 1404, "total_steps": 6710, "loss": 1.0047, "lr": 2.2395203205885633e-06, "epoch": 1.046199701937407, "percentage": 20.92, "elapsed_time": "0:18:27", "remaining_time": "1:09:46", "throughput": 5190.84, "total_tokens": 5750784} {"current_steps": 1405, "total_steps": 6710, "loss": 0.8445, "lr": 2.239162616864363e-06, "epoch": 1.0469448584202683, "percentage": 20.94, "elapsed_time": "0:18:28", "remaining_time": "1:09:46", "throughput": 5190.87, "total_tokens": 5754880} {"current_steps": 1406, "total_steps": 6710, "loss": 1.149, "lr": 2.238804696308653e-06, "epoch": 1.0476900149031296, "percentage": 20.95, "elapsed_time": "0:18:29", "remaining_time": "1:09:45", "throughput": 5190.91, "total_tokens": 5758976} {"current_steps": 1407, "total_steps": 6710, "loss": 0.8877, "lr": 2.2384465589998937e-06, "epoch": 1.048435171385991, "percentage": 20.97, "elapsed_time": "0:18:30", "remaining_time": "1:09:44", "throughput": 5190.94, "total_tokens": 5763072} {"current_steps": 1408, "total_steps": 6710, "loss": 0.7374, "lr": 2.2380882050165897e-06, "epoch": 1.0491803278688525, "percentage": 20.98, "elapsed_time": "0:18:30", "remaining_time": "1:09:43", "throughput": 5190.98, "total_tokens": 5767168} {"current_steps": 1409, "total_steps": 6710, "loss": 0.8589, "lr": 2.2377296344372963e-06, "epoch": 1.0499254843517138, "percentage": 21.0, "elapsed_time": "0:18:31", "remaining_time": "1:09:42", "throughput": 5191.02, "total_tokens": 5771264} {"current_steps": 1410, "total_steps": 6710, "loss": 0.8586, "lr": 2.2373708473406137e-06, "epoch": 1.0506706408345752, "percentage": 21.01, "elapsed_time": "0:18:32", "remaining_time": "1:09:41", "throughput": 5191.05, "total_tokens": 5775360} {"current_steps": 1411, "total_steps": 6710, "loss": 1.0529, "lr": 2.2370118438051906e-06, "epoch": 1.0514157973174367, "percentage": 21.03, "elapsed_time": "0:18:33", "remaining_time": "1:09:41", "throughput": 5191.09, "total_tokens": 5779456} {"current_steps": 1412, "total_steps": 6710, "loss": 1.0071, "lr": 2.2366526239097243e-06, "epoch": 1.052160953800298, "percentage": 21.04, "elapsed_time": "0:18:34", "remaining_time": "1:09:40", "throughput": 5191.14, "total_tokens": 5783552} {"current_steps": 1413, "total_steps": 6710, "loss": 0.6733, "lr": 2.2362931877329567e-06, "epoch": 1.0529061102831594, "percentage": 21.06, "elapsed_time": "0:18:34", "remaining_time": "1:09:39", "throughput": 5191.17, "total_tokens": 5787648} {"current_steps": 1414, "total_steps": 6710, "loss": 0.6588, "lr": 2.2359335353536797e-06, "epoch": 1.053651266766021, "percentage": 21.07, "elapsed_time": "0:18:35", "remaining_time": "1:09:38", "throughput": 5191.2, "total_tokens": 5791744} {"current_steps": 1415, "total_steps": 6710, "loss": 1.0424, "lr": 2.235573666850732e-06, "epoch": 1.0543964232488823, "percentage": 21.09, "elapsed_time": "0:18:36", "remaining_time": "1:09:37", "throughput": 5191.23, "total_tokens": 5795840} {"current_steps": 1416, "total_steps": 6710, "loss": 0.6086, "lr": 2.2352135823029987e-06, "epoch": 1.0551415797317436, "percentage": 21.1, "elapsed_time": "0:18:37", "remaining_time": "1:09:37", "throughput": 5191.27, "total_tokens": 5799936} {"current_steps": 1417, "total_steps": 6710, "loss": 0.726, "lr": 2.234853281789413e-06, "epoch": 1.0558867362146052, "percentage": 21.12, "elapsed_time": "0:18:38", "remaining_time": "1:09:36", "throughput": 5191.27, "total_tokens": 5804032} {"current_steps": 1418, "total_steps": 6710, "loss": 0.4419, "lr": 2.2344927653889553e-06, "epoch": 1.0566318926974665, "percentage": 21.13, "elapsed_time": "0:18:38", "remaining_time": "1:09:35", "throughput": 5191.32, "total_tokens": 5808128} {"current_steps": 1419, "total_steps": 6710, "loss": 0.8642, "lr": 2.234132033180654e-06, "epoch": 1.0573770491803278, "percentage": 21.15, "elapsed_time": "0:18:39", "remaining_time": "1:09:34", "throughput": 5191.35, "total_tokens": 5812224} {"current_steps": 1420, "total_steps": 6710, "loss": 0.7513, "lr": 2.2337710852435835e-06, "epoch": 1.0581222056631894, "percentage": 21.16, "elapsed_time": "0:18:40", "remaining_time": "1:09:33", "throughput": 5191.38, "total_tokens": 5816320} {"current_steps": 1421, "total_steps": 6710, "loss": 0.6049, "lr": 2.233409921656866e-06, "epoch": 1.0588673621460507, "percentage": 21.18, "elapsed_time": "0:18:41", "remaining_time": "1:09:32", "throughput": 5191.41, "total_tokens": 5820416} {"current_steps": 1422, "total_steps": 6710, "loss": 0.7998, "lr": 2.2330485424996717e-06, "epoch": 1.059612518628912, "percentage": 21.19, "elapsed_time": "0:18:41", "remaining_time": "1:09:32", "throughput": 5191.46, "total_tokens": 5824512} {"current_steps": 1423, "total_steps": 6710, "loss": 0.4963, "lr": 2.2326869478512177e-06, "epoch": 1.0603576751117734, "percentage": 21.21, "elapsed_time": "0:18:42", "remaining_time": "1:09:31", "throughput": 5191.5, "total_tokens": 5828608} {"current_steps": 1424, "total_steps": 6710, "loss": 0.91, "lr": 2.232325137790767e-06, "epoch": 1.061102831594635, "percentage": 21.22, "elapsed_time": "0:18:43", "remaining_time": "1:09:30", "throughput": 5191.54, "total_tokens": 5832704} {"current_steps": 1425, "total_steps": 6710, "loss": 0.7668, "lr": 2.231963112397632e-06, "epoch": 1.0618479880774963, "percentage": 21.24, "elapsed_time": "0:18:44", "remaining_time": "1:09:29", "throughput": 5191.58, "total_tokens": 5836800} {"current_steps": 1426, "total_steps": 6710, "loss": 1.0563, "lr": 2.231600871751171e-06, "epoch": 1.0625931445603576, "percentage": 21.25, "elapsed_time": "0:18:45", "remaining_time": "1:09:28", "throughput": 5191.62, "total_tokens": 5840896} {"current_steps": 1427, "total_steps": 6710, "loss": 1.0332, "lr": 2.2312384159307897e-06, "epoch": 1.0633383010432191, "percentage": 21.27, "elapsed_time": "0:18:45", "remaining_time": "1:09:28", "throughput": 5191.65, "total_tokens": 5844992} {"current_steps": 1428, "total_steps": 6710, "loss": 0.7653, "lr": 2.230875745015941e-06, "epoch": 1.0640834575260805, "percentage": 21.28, "elapsed_time": "0:18:46", "remaining_time": "1:09:27", "throughput": 5191.68, "total_tokens": 5849088} {"current_steps": 1429, "total_steps": 6710, "loss": 0.7781, "lr": 2.230512859086125e-06, "epoch": 1.0648286140089418, "percentage": 21.3, "elapsed_time": "0:18:47", "remaining_time": "1:09:26", "throughput": 5191.72, "total_tokens": 5853184} {"current_steps": 1430, "total_steps": 6710, "loss": 0.68, "lr": 2.2301497582208883e-06, "epoch": 1.0655737704918034, "percentage": 21.31, "elapsed_time": "0:18:48", "remaining_time": "1:09:25", "throughput": 5191.75, "total_tokens": 5857280} {"current_steps": 1431, "total_steps": 6710, "loss": 0.647, "lr": 2.229786442499826e-06, "epoch": 1.0663189269746647, "percentage": 21.33, "elapsed_time": "0:18:48", "remaining_time": "1:09:24", "throughput": 5191.78, "total_tokens": 5861376} {"current_steps": 1432, "total_steps": 6710, "loss": 0.862, "lr": 2.229422912002579e-06, "epoch": 1.067064083457526, "percentage": 21.34, "elapsed_time": "0:18:49", "remaining_time": "1:09:23", "throughput": 5191.82, "total_tokens": 5865472} {"current_steps": 1433, "total_steps": 6710, "loss": 0.6868, "lr": 2.2290591668088363e-06, "epoch": 1.0678092399403876, "percentage": 21.36, "elapsed_time": "0:18:50", "remaining_time": "1:09:23", "throughput": 5191.82, "total_tokens": 5869568} {"current_steps": 1434, "total_steps": 6710, "loss": 0.5191, "lr": 2.228695206998333e-06, "epoch": 1.068554396423249, "percentage": 21.37, "elapsed_time": "0:18:51", "remaining_time": "1:09:22", "throughput": 5191.82, "total_tokens": 5873664} {"current_steps": 1435, "total_steps": 6710, "loss": 0.5623, "lr": 2.228331032650852e-06, "epoch": 1.0692995529061102, "percentage": 21.39, "elapsed_time": "0:18:52", "remaining_time": "1:09:21", "throughput": 5191.86, "total_tokens": 5877760} {"current_steps": 1436, "total_steps": 6710, "loss": 0.6721, "lr": 2.2279666438462222e-06, "epoch": 1.0700447093889718, "percentage": 21.4, "elapsed_time": "0:18:52", "remaining_time": "1:09:20", "throughput": 5191.91, "total_tokens": 5881856} {"current_steps": 1437, "total_steps": 6710, "loss": 0.5542, "lr": 2.227602040664321e-06, "epoch": 1.0707898658718331, "percentage": 21.42, "elapsed_time": "0:18:53", "remaining_time": "1:09:19", "throughput": 5191.94, "total_tokens": 5885952} {"current_steps": 1438, "total_steps": 6710, "loss": 0.6836, "lr": 2.227237223185072e-06, "epoch": 1.0715350223546944, "percentage": 21.43, "elapsed_time": "0:18:54", "remaining_time": "1:09:19", "throughput": 5191.97, "total_tokens": 5890048} {"current_steps": 1439, "total_steps": 6710, "loss": 0.7088, "lr": 2.2268721914884456e-06, "epoch": 1.072280178837556, "percentage": 21.45, "elapsed_time": "0:18:55", "remaining_time": "1:09:18", "throughput": 5191.97, "total_tokens": 5894144} {"current_steps": 1440, "total_steps": 6710, "loss": 0.5817, "lr": 2.226506945654459e-06, "epoch": 1.0730253353204173, "percentage": 21.46, "elapsed_time": "0:18:56", "remaining_time": "1:09:17", "throughput": 5192.01, "total_tokens": 5898240} {"current_steps": 1441, "total_steps": 6710, "loss": 1.1852, "lr": 2.2261414857631773e-06, "epoch": 1.0737704918032787, "percentage": 21.48, "elapsed_time": "0:18:56", "remaining_time": "1:09:16", "throughput": 5192.04, "total_tokens": 5902336} {"current_steps": 1442, "total_steps": 6710, "loss": 0.7594, "lr": 2.225775811894712e-06, "epoch": 1.07451564828614, "percentage": 21.49, "elapsed_time": "0:18:57", "remaining_time": "1:09:15", "throughput": 5192.08, "total_tokens": 5906432} {"current_steps": 1443, "total_steps": 6710, "loss": 0.6414, "lr": 2.2254099241292203e-06, "epoch": 1.0752608047690015, "percentage": 21.51, "elapsed_time": "0:18:58", "remaining_time": "1:09:15", "throughput": 5192.12, "total_tokens": 5910528} {"current_steps": 1444, "total_steps": 6710, "loss": 0.5979, "lr": 2.225043822546909e-06, "epoch": 1.0760059612518629, "percentage": 21.52, "elapsed_time": "0:18:59", "remaining_time": "1:09:14", "throughput": 5192.14, "total_tokens": 5914624} {"current_steps": 1445, "total_steps": 6710, "loss": 0.8946, "lr": 2.2246775072280284e-06, "epoch": 1.0767511177347242, "percentage": 21.54, "elapsed_time": "0:18:59", "remaining_time": "1:09:13", "throughput": 5192.16, "total_tokens": 5918720} {"current_steps": 1446, "total_steps": 6710, "loss": 0.975, "lr": 2.2243109782528794e-06, "epoch": 1.0774962742175858, "percentage": 21.55, "elapsed_time": "0:19:00", "remaining_time": "1:09:12", "throughput": 5192.18, "total_tokens": 5922816} {"current_steps": 1447, "total_steps": 6710, "loss": 0.9852, "lr": 2.223944235701806e-06, "epoch": 1.078241430700447, "percentage": 21.56, "elapsed_time": "0:19:01", "remaining_time": "1:09:11", "throughput": 5192.21, "total_tokens": 5926912} {"current_steps": 1448, "total_steps": 6710, "loss": 0.8953, "lr": 2.223577279655202e-06, "epoch": 1.0789865871833084, "percentage": 21.58, "elapsed_time": "0:19:02", "remaining_time": "1:09:11", "throughput": 5192.24, "total_tokens": 5931008} {"current_steps": 1449, "total_steps": 6710, "loss": 1.0809, "lr": 2.223210110193506e-06, "epoch": 1.07973174366617, "percentage": 21.59, "elapsed_time": "0:19:03", "remaining_time": "1:09:10", "throughput": 5192.26, "total_tokens": 5935104} {"current_steps": 1450, "total_steps": 6710, "loss": 0.8595, "lr": 2.222842727397205e-06, "epoch": 1.0804769001490313, "percentage": 21.61, "elapsed_time": "0:19:03", "remaining_time": "1:09:09", "throughput": 5192.3, "total_tokens": 5939200} {"current_steps": 1451, "total_steps": 6710, "loss": 0.9901, "lr": 2.2224751313468308e-06, "epoch": 1.0812220566318926, "percentage": 21.62, "elapsed_time": "0:19:04", "remaining_time": "1:09:08", "throughput": 5192.34, "total_tokens": 5943296} {"current_steps": 1452, "total_steps": 6710, "loss": 0.8226, "lr": 2.222107322122964e-06, "epoch": 1.0819672131147542, "percentage": 21.64, "elapsed_time": "0:19:05", "remaining_time": "1:09:07", "throughput": 5192.38, "total_tokens": 5947392} {"current_steps": 1453, "total_steps": 6710, "loss": 0.5297, "lr": 2.2217392998062307e-06, "epoch": 1.0827123695976155, "percentage": 21.65, "elapsed_time": "0:19:06", "remaining_time": "1:09:06", "throughput": 5192.42, "total_tokens": 5951488} {"current_steps": 1454, "total_steps": 6710, "loss": 0.7703, "lr": 2.2213710644773044e-06, "epoch": 1.0834575260804769, "percentage": 21.67, "elapsed_time": "0:19:06", "remaining_time": "1:09:06", "throughput": 5192.45, "total_tokens": 5955584} {"current_steps": 1455, "total_steps": 6710, "loss": 0.9134, "lr": 2.221002616216904e-06, "epoch": 1.0842026825633384, "percentage": 21.68, "elapsed_time": "0:19:07", "remaining_time": "1:09:05", "throughput": 5192.49, "total_tokens": 5959680} {"current_steps": 1456, "total_steps": 6710, "loss": 0.646, "lr": 2.220633955105797e-06, "epoch": 1.0849478390461997, "percentage": 21.7, "elapsed_time": "0:19:08", "remaining_time": "1:09:04", "throughput": 5192.53, "total_tokens": 5963776} {"current_steps": 1457, "total_steps": 6710, "loss": 0.5858, "lr": 2.2202650812247958e-06, "epoch": 1.085692995529061, "percentage": 21.71, "elapsed_time": "0:19:09", "remaining_time": "1:09:03", "throughput": 5192.51, "total_tokens": 5967872} {"current_steps": 1458, "total_steps": 6710, "loss": 0.842, "lr": 2.2198959946547605e-06, "epoch": 1.0864381520119224, "percentage": 21.73, "elapsed_time": "0:19:10", "remaining_time": "1:09:02", "throughput": 5192.51, "total_tokens": 5971968} {"current_steps": 1459, "total_steps": 6710, "loss": 0.7724, "lr": 2.2195266954765975e-06, "epoch": 1.087183308494784, "percentage": 21.74, "elapsed_time": "0:19:10", "remaining_time": "1:09:02", "throughput": 5192.53, "total_tokens": 5976064} {"current_steps": 1460, "total_steps": 6710, "loss": 0.7467, "lr": 2.21915718377126e-06, "epoch": 1.0879284649776453, "percentage": 21.76, "elapsed_time": "0:19:11", "remaining_time": "1:09:01", "throughput": 5192.54, "total_tokens": 5980160} {"current_steps": 1461, "total_steps": 6710, "loss": 0.7992, "lr": 2.218787459619747e-06, "epoch": 1.0886736214605066, "percentage": 21.77, "elapsed_time": "0:19:12", "remaining_time": "1:09:00", "throughput": 5192.56, "total_tokens": 5984256} {"current_steps": 1462, "total_steps": 6710, "loss": 0.6548, "lr": 2.218417523103106e-06, "epoch": 1.0894187779433682, "percentage": 21.79, "elapsed_time": "0:19:13", "remaining_time": "1:08:59", "throughput": 5192.59, "total_tokens": 5988352} {"current_steps": 1463, "total_steps": 6710, "loss": 0.8524, "lr": 2.218047374302428e-06, "epoch": 1.0901639344262295, "percentage": 21.8, "elapsed_time": "0:19:14", "remaining_time": "1:08:58", "throughput": 5192.62, "total_tokens": 5992448} {"current_steps": 1464, "total_steps": 6710, "loss": 0.7067, "lr": 2.2176770132988535e-06, "epoch": 1.0909090909090908, "percentage": 21.82, "elapsed_time": "0:19:14", "remaining_time": "1:08:58", "throughput": 5192.65, "total_tokens": 5996544} {"current_steps": 1465, "total_steps": 6710, "loss": 0.8302, "lr": 2.2173064401735672e-06, "epoch": 1.0916542473919524, "percentage": 21.83, "elapsed_time": "0:19:15", "remaining_time": "1:08:57", "throughput": 5192.68, "total_tokens": 6000640} {"current_steps": 1466, "total_steps": 6710, "loss": 0.7855, "lr": 2.2169356550078026e-06, "epoch": 1.0923994038748137, "percentage": 21.85, "elapsed_time": "0:19:16", "remaining_time": "1:08:56", "throughput": 5192.71, "total_tokens": 6004736} {"current_steps": 1467, "total_steps": 6710, "loss": 0.8276, "lr": 2.216564657882838e-06, "epoch": 1.093144560357675, "percentage": 21.86, "elapsed_time": "0:19:17", "remaining_time": "1:08:55", "throughput": 5192.69, "total_tokens": 6008832} {"current_steps": 1468, "total_steps": 6710, "loss": 0.8417, "lr": 2.2161934488799978e-06, "epoch": 1.0938897168405366, "percentage": 21.88, "elapsed_time": "0:19:17", "remaining_time": "1:08:54", "throughput": 5192.73, "total_tokens": 6012928} {"current_steps": 1469, "total_steps": 6710, "loss": 0.6189, "lr": 2.215822028080655e-06, "epoch": 1.094634873323398, "percentage": 21.89, "elapsed_time": "0:19:18", "remaining_time": "1:08:54", "throughput": 5192.76, "total_tokens": 6017024} {"current_steps": 1470, "total_steps": 6710, "loss": 0.8005, "lr": 2.215450395566227e-06, "epoch": 1.0953800298062593, "percentage": 21.91, "elapsed_time": "0:19:19", "remaining_time": "1:08:53", "throughput": 5192.8, "total_tokens": 6021120} {"current_steps": 1471, "total_steps": 6710, "loss": 1.0426, "lr": 2.2150785514181785e-06, "epoch": 1.0961251862891208, "percentage": 21.92, "elapsed_time": "0:19:20", "remaining_time": "1:08:52", "throughput": 5192.83, "total_tokens": 6025216} {"current_steps": 1472, "total_steps": 6710, "loss": 0.7231, "lr": 2.2147064957180198e-06, "epoch": 1.0968703427719821, "percentage": 21.94, "elapsed_time": "0:19:21", "remaining_time": "1:08:51", "throughput": 5192.86, "total_tokens": 6029312} {"current_steps": 1473, "total_steps": 6710, "loss": 0.7686, "lr": 2.2143342285473084e-06, "epoch": 1.0976154992548435, "percentage": 21.95, "elapsed_time": "0:19:21", "remaining_time": "1:08:50", "throughput": 5192.88, "total_tokens": 6033408} {"current_steps": 1474, "total_steps": 6710, "loss": 1.1421, "lr": 2.213961749987649e-06, "epoch": 1.098360655737705, "percentage": 21.97, "elapsed_time": "0:19:22", "remaining_time": "1:08:49", "throughput": 5192.91, "total_tokens": 6037504} {"current_steps": 1475, "total_steps": 6710, "loss": 0.7509, "lr": 2.2135890601206903e-06, "epoch": 1.0991058122205664, "percentage": 21.98, "elapsed_time": "0:19:23", "remaining_time": "1:08:49", "throughput": 5192.94, "total_tokens": 6041600} {"current_steps": 1476, "total_steps": 6710, "loss": 0.7996, "lr": 2.213216159028129e-06, "epoch": 1.0998509687034277, "percentage": 22.0, "elapsed_time": "0:19:24", "remaining_time": "1:08:48", "throughput": 5192.88, "total_tokens": 6045696} {"current_steps": 1477, "total_steps": 6710, "loss": 0.7698, "lr": 2.212843046791707e-06, "epoch": 1.100596125186289, "percentage": 22.01, "elapsed_time": "0:19:25", "remaining_time": "1:08:47", "throughput": 5192.91, "total_tokens": 6049792} {"current_steps": 1478, "total_steps": 6710, "loss": 0.8504, "lr": 2.2124697234932145e-06, "epoch": 1.1013412816691506, "percentage": 22.03, "elapsed_time": "0:19:25", "remaining_time": "1:08:46", "throughput": 5192.95, "total_tokens": 6053888} {"current_steps": 1479, "total_steps": 6710, "loss": 1.182, "lr": 2.212096189214486e-06, "epoch": 1.102086438152012, "percentage": 22.04, "elapsed_time": "0:19:26", "remaining_time": "1:08:45", "throughput": 5192.98, "total_tokens": 6057984} {"current_steps": 1480, "total_steps": 6710, "loss": 0.9932, "lr": 2.211722444037403e-06, "epoch": 1.1028315946348732, "percentage": 22.06, "elapsed_time": "0:19:27", "remaining_time": "1:08:45", "throughput": 5193.0, "total_tokens": 6062080} {"current_steps": 1481, "total_steps": 6710, "loss": 0.8632, "lr": 2.2113484880438924e-06, "epoch": 1.1035767511177348, "percentage": 22.07, "elapsed_time": "0:19:28", "remaining_time": "1:08:44", "throughput": 5193.04, "total_tokens": 6066176} {"current_steps": 1482, "total_steps": 6710, "loss": 0.9739, "lr": 2.210974321315929e-06, "epoch": 1.1043219076005961, "percentage": 22.09, "elapsed_time": "0:19:28", "remaining_time": "1:08:43", "throughput": 5193.06, "total_tokens": 6070272} {"current_steps": 1483, "total_steps": 6710, "loss": 0.8261, "lr": 2.2105999439355326e-06, "epoch": 1.1050670640834575, "percentage": 22.1, "elapsed_time": "0:19:29", "remaining_time": "1:08:42", "throughput": 5193.09, "total_tokens": 6074368} {"current_steps": 1484, "total_steps": 6710, "loss": 0.7689, "lr": 2.2102253559847688e-06, "epoch": 1.105812220566319, "percentage": 22.12, "elapsed_time": "0:19:30", "remaining_time": "1:08:41", "throughput": 5193.1, "total_tokens": 6078464} {"current_steps": 1485, "total_steps": 6710, "loss": 0.8814, "lr": 2.20985055754575e-06, "epoch": 1.1065573770491803, "percentage": 22.13, "elapsed_time": "0:19:31", "remaining_time": "1:08:41", "throughput": 5193.11, "total_tokens": 6082560} {"current_steps": 1486, "total_steps": 6710, "loss": 0.6127, "lr": 2.209475548700636e-06, "epoch": 1.1073025335320417, "percentage": 22.15, "elapsed_time": "0:19:32", "remaining_time": "1:08:40", "throughput": 5193.13, "total_tokens": 6086656} {"current_steps": 1487, "total_steps": 6710, "loss": 0.9052, "lr": 2.209100329531629e-06, "epoch": 1.1080476900149032, "percentage": 22.16, "elapsed_time": "0:19:32", "remaining_time": "1:08:39", "throughput": 5193.15, "total_tokens": 6090752} {"current_steps": 1488, "total_steps": 6710, "loss": 1.0809, "lr": 2.208724900120983e-06, "epoch": 1.1087928464977646, "percentage": 22.18, "elapsed_time": "0:19:33", "remaining_time": "1:08:38", "throughput": 5193.17, "total_tokens": 6094848} {"current_steps": 1489, "total_steps": 6710, "loss": 0.9315, "lr": 2.2083492605509916e-06, "epoch": 1.1095380029806259, "percentage": 22.19, "elapsed_time": "0:19:34", "remaining_time": "1:08:37", "throughput": 5193.2, "total_tokens": 6098944} {"current_steps": 1490, "total_steps": 6710, "loss": 0.6088, "lr": 2.2079734109039995e-06, "epoch": 1.1102831594634874, "percentage": 22.21, "elapsed_time": "0:19:35", "remaining_time": "1:08:37", "throughput": 5193.24, "total_tokens": 6103040} {"current_steps": 1491, "total_steps": 6710, "loss": 0.8192, "lr": 2.2075973512623956e-06, "epoch": 1.1110283159463488, "percentage": 22.22, "elapsed_time": "0:19:35", "remaining_time": "1:08:36", "throughput": 5193.27, "total_tokens": 6107136} {"current_steps": 1492, "total_steps": 6710, "loss": 1.1068, "lr": 2.2072210817086137e-06, "epoch": 1.11177347242921, "percentage": 22.24, "elapsed_time": "0:19:36", "remaining_time": "1:08:35", "throughput": 5193.31, "total_tokens": 6111232} {"current_steps": 1493, "total_steps": 6710, "loss": 0.8353, "lr": 2.206844602325136e-06, "epoch": 1.1125186289120714, "percentage": 22.25, "elapsed_time": "0:19:37", "remaining_time": "1:08:34", "throughput": 5193.34, "total_tokens": 6115328} {"current_steps": 1494, "total_steps": 6710, "loss": 0.8322, "lr": 2.206467913194489e-06, "epoch": 1.113263785394933, "percentage": 22.27, "elapsed_time": "0:19:38", "remaining_time": "1:08:33", "throughput": 5193.37, "total_tokens": 6119424} {"current_steps": 1495, "total_steps": 6710, "loss": 0.9355, "lr": 2.2060910143992453e-06, "epoch": 1.1140089418777943, "percentage": 22.28, "elapsed_time": "0:19:39", "remaining_time": "1:08:33", "throughput": 5193.39, "total_tokens": 6123520} {"current_steps": 1496, "total_steps": 6710, "loss": 0.8158, "lr": 2.2057139060220247e-06, "epoch": 1.1147540983606556, "percentage": 22.3, "elapsed_time": "0:19:39", "remaining_time": "1:08:32", "throughput": 5193.42, "total_tokens": 6127616} {"current_steps": 1497, "total_steps": 6710, "loss": 0.7862, "lr": 2.2053365881454907e-06, "epoch": 1.1154992548435172, "percentage": 22.31, "elapsed_time": "0:19:40", "remaining_time": "1:08:31", "throughput": 5193.44, "total_tokens": 6131712} {"current_steps": 1498, "total_steps": 6710, "loss": 0.6756, "lr": 2.204959060852356e-06, "epoch": 1.1162444113263785, "percentage": 22.32, "elapsed_time": "0:19:41", "remaining_time": "1:08:30", "throughput": 5193.45, "total_tokens": 6135808} {"current_steps": 1499, "total_steps": 6710, "loss": 0.7433, "lr": 2.2045813242253748e-06, "epoch": 1.1169895678092399, "percentage": 22.34, "elapsed_time": "0:19:42", "remaining_time": "1:08:29", "throughput": 5193.47, "total_tokens": 6139904} {"current_steps": 1500, "total_steps": 6710, "loss": 0.6119, "lr": 2.2042033783473523e-06, "epoch": 1.1177347242921014, "percentage": 22.35, "elapsed_time": "0:19:43", "remaining_time": "1:08:29", "throughput": 5193.47, "total_tokens": 6144000} {"current_steps": 1501, "total_steps": 6710, "loss": 1.0115, "lr": 2.2038252233011347e-06, "epoch": 1.1184798807749627, "percentage": 22.37, "elapsed_time": "0:19:43", "remaining_time": "1:08:28", "throughput": 5193.5, "total_tokens": 6148096} {"current_steps": 1502, "total_steps": 6710, "loss": 0.6371, "lr": 2.2034468591696177e-06, "epoch": 1.119225037257824, "percentage": 22.38, "elapsed_time": "0:19:44", "remaining_time": "1:08:27", "throughput": 5193.53, "total_tokens": 6152192} {"current_steps": 1503, "total_steps": 6710, "loss": 0.7969, "lr": 2.2030682860357406e-06, "epoch": 1.1199701937406856, "percentage": 22.4, "elapsed_time": "0:19:45", "remaining_time": "1:08:26", "throughput": 5193.56, "total_tokens": 6156288} {"current_steps": 1504, "total_steps": 6710, "loss": 0.6474, "lr": 2.20268950398249e-06, "epoch": 1.120715350223547, "percentage": 22.41, "elapsed_time": "0:19:46", "remaining_time": "1:08:25", "throughput": 5193.6, "total_tokens": 6160384} {"current_steps": 1505, "total_steps": 6710, "loss": 0.8641, "lr": 2.202310513092897e-06, "epoch": 1.1214605067064083, "percentage": 22.43, "elapsed_time": "0:19:46", "remaining_time": "1:08:24", "throughput": 5193.64, "total_tokens": 6164480} {"current_steps": 1506, "total_steps": 6710, "loss": 0.7603, "lr": 2.2019313134500396e-06, "epoch": 1.1222056631892698, "percentage": 22.44, "elapsed_time": "0:19:47", "remaining_time": "1:08:24", "throughput": 5193.68, "total_tokens": 6168576} {"current_steps": 1507, "total_steps": 6710, "loss": 0.7949, "lr": 2.201551905137041e-06, "epoch": 1.1229508196721312, "percentage": 22.46, "elapsed_time": "0:19:48", "remaining_time": "1:08:23", "throughput": 5193.71, "total_tokens": 6172672} {"current_steps": 1508, "total_steps": 6710, "loss": 0.8071, "lr": 2.20117228823707e-06, "epoch": 1.1236959761549925, "percentage": 22.47, "elapsed_time": "0:19:49", "remaining_time": "1:08:22", "throughput": 5193.74, "total_tokens": 6176768} {"current_steps": 1509, "total_steps": 6710, "loss": 1.0614, "lr": 2.2007924628333417e-06, "epoch": 1.124441132637854, "percentage": 22.49, "elapsed_time": "0:19:50", "remaining_time": "1:08:21", "throughput": 5193.78, "total_tokens": 6180864} {"current_steps": 1510, "total_steps": 6710, "loss": 0.653, "lr": 2.200412429009116e-06, "epoch": 1.1251862891207154, "percentage": 22.5, "elapsed_time": "0:19:50", "remaining_time": "1:08:20", "throughput": 5193.82, "total_tokens": 6184960} {"current_steps": 1511, "total_steps": 6710, "loss": 0.8789, "lr": 2.2000321868476993e-06, "epoch": 1.1259314456035767, "percentage": 22.52, "elapsed_time": "0:19:51", "remaining_time": "1:08:20", "throughput": 5193.86, "total_tokens": 6189056} {"current_steps": 1512, "total_steps": 6710, "loss": 0.7755, "lr": 2.1996517364324435e-06, "epoch": 1.1266766020864383, "percentage": 22.53, "elapsed_time": "0:19:52", "remaining_time": "1:08:19", "throughput": 5193.9, "total_tokens": 6193152} {"current_steps": 1513, "total_steps": 6710, "loss": 0.7414, "lr": 2.1992710778467457e-06, "epoch": 1.1274217585692996, "percentage": 22.55, "elapsed_time": "0:19:53", "remaining_time": "1:08:18", "throughput": 5193.94, "total_tokens": 6197248} {"current_steps": 1514, "total_steps": 6710, "loss": 1.0021, "lr": 2.1988902111740496e-06, "epoch": 1.128166915052161, "percentage": 22.56, "elapsed_time": "0:19:53", "remaining_time": "1:08:17", "throughput": 5193.97, "total_tokens": 6201344} {"current_steps": 1515, "total_steps": 6710, "loss": 0.8841, "lr": 2.1985091364978435e-06, "epoch": 1.1289120715350223, "percentage": 22.58, "elapsed_time": "0:19:54", "remaining_time": "1:08:16", "throughput": 5194.02, "total_tokens": 6205440} {"current_steps": 1516, "total_steps": 6710, "loss": 0.5987, "lr": 2.1981278539016614e-06, "epoch": 1.1296572280178838, "percentage": 22.59, "elapsed_time": "0:19:55", "remaining_time": "1:08:15", "throughput": 5194.05, "total_tokens": 6209536} {"current_steps": 1517, "total_steps": 6710, "loss": 0.7728, "lr": 2.1977463634690838e-06, "epoch": 1.1304023845007451, "percentage": 22.61, "elapsed_time": "0:19:56", "remaining_time": "1:08:15", "throughput": 5194.09, "total_tokens": 6213632} {"current_steps": 1518, "total_steps": 6710, "loss": 0.6559, "lr": 2.1973646652837357e-06, "epoch": 1.1311475409836065, "percentage": 22.62, "elapsed_time": "0:19:57", "remaining_time": "1:08:14", "throughput": 5194.13, "total_tokens": 6217728} {"current_steps": 1519, "total_steps": 6710, "loss": 0.8777, "lr": 2.196982759429288e-06, "epoch": 1.131892697466468, "percentage": 22.64, "elapsed_time": "0:19:57", "remaining_time": "1:08:13", "throughput": 5194.17, "total_tokens": 6221824} {"current_steps": 1520, "total_steps": 6710, "loss": 0.8797, "lr": 2.1966006459894577e-06, "epoch": 1.1326378539493294, "percentage": 22.65, "elapsed_time": "0:19:58", "remaining_time": "1:08:12", "throughput": 5194.21, "total_tokens": 6225920} {"current_steps": 1521, "total_steps": 6710, "loss": 0.9191, "lr": 2.196218325048006e-06, "epoch": 1.1333830104321907, "percentage": 22.67, "elapsed_time": "0:19:59", "remaining_time": "1:08:11", "throughput": 5194.21, "total_tokens": 6230016} {"current_steps": 1522, "total_steps": 6710, "loss": 0.6395, "lr": 2.1958357966887416e-06, "epoch": 1.1341281669150522, "percentage": 22.68, "elapsed_time": "0:20:00", "remaining_time": "1:08:11", "throughput": 5194.24, "total_tokens": 6234112} {"current_steps": 1523, "total_steps": 6710, "loss": 0.8271, "lr": 2.195453060995516e-06, "epoch": 1.1348733233979136, "percentage": 22.7, "elapsed_time": "0:20:00", "remaining_time": "1:08:10", "throughput": 5194.28, "total_tokens": 6238208} {"current_steps": 1524, "total_steps": 6710, "loss": 0.8018, "lr": 2.1950701180522287e-06, "epoch": 1.135618479880775, "percentage": 22.71, "elapsed_time": "0:20:01", "remaining_time": "1:08:09", "throughput": 5194.31, "total_tokens": 6242304} {"current_steps": 1525, "total_steps": 6710, "loss": 0.5855, "lr": 2.1946869679428232e-06, "epoch": 1.1363636363636362, "percentage": 22.73, "elapsed_time": "0:20:02", "remaining_time": "1:08:08", "throughput": 5194.34, "total_tokens": 6246400} {"current_steps": 1526, "total_steps": 6710, "loss": 0.6912, "lr": 2.1943036107512882e-06, "epoch": 1.1371087928464978, "percentage": 22.74, "elapsed_time": "0:20:03", "remaining_time": "1:08:07", "throughput": 5194.38, "total_tokens": 6250496} {"current_steps": 1527, "total_steps": 6710, "loss": 0.6584, "lr": 2.193920046561659e-06, "epoch": 1.1378539493293591, "percentage": 22.76, "elapsed_time": "0:20:04", "remaining_time": "1:08:06", "throughput": 5194.43, "total_tokens": 6254592} {"current_steps": 1528, "total_steps": 6710, "loss": 0.8829, "lr": 2.1935362754580155e-06, "epoch": 1.1385991058122205, "percentage": 22.77, "elapsed_time": "0:20:04", "remaining_time": "1:08:06", "throughput": 5194.47, "total_tokens": 6258688} {"current_steps": 1529, "total_steps": 6710, "loss": 0.6881, "lr": 2.193152297524483e-06, "epoch": 1.139344262295082, "percentage": 22.79, "elapsed_time": "0:20:05", "remaining_time": "1:08:05", "throughput": 5194.51, "total_tokens": 6262784} {"current_steps": 1530, "total_steps": 6710, "loss": 0.8213, "lr": 2.192768112845232e-06, "epoch": 1.1400894187779433, "percentage": 22.8, "elapsed_time": "0:20:06", "remaining_time": "1:08:04", "throughput": 5194.53, "total_tokens": 6266880} {"current_steps": 1531, "total_steps": 6710, "loss": 0.8868, "lr": 2.192383721504479e-06, "epoch": 1.1408345752608047, "percentage": 22.82, "elapsed_time": "0:20:07", "remaining_time": "1:08:03", "throughput": 5194.58, "total_tokens": 6270976} {"current_steps": 1532, "total_steps": 6710, "loss": 1.097, "lr": 2.1919991235864846e-06, "epoch": 1.1415797317436662, "percentage": 22.83, "elapsed_time": "0:20:07", "remaining_time": "1:08:02", "throughput": 5194.62, "total_tokens": 6275072} {"current_steps": 1533, "total_steps": 6710, "loss": 0.9098, "lr": 2.1916143191755563e-06, "epoch": 1.1423248882265276, "percentage": 22.85, "elapsed_time": "0:20:08", "remaining_time": "1:08:02", "throughput": 5194.66, "total_tokens": 6279168} {"current_steps": 1534, "total_steps": 6710, "loss": 0.6419, "lr": 2.1912293083560447e-06, "epoch": 1.1430700447093889, "percentage": 22.86, "elapsed_time": "0:20:09", "remaining_time": "1:08:01", "throughput": 5194.7, "total_tokens": 6283264} {"current_steps": 1535, "total_steps": 6710, "loss": 0.548, "lr": 2.1908440912123484e-06, "epoch": 1.1438152011922504, "percentage": 22.88, "elapsed_time": "0:20:10", "remaining_time": "1:08:00", "throughput": 5194.74, "total_tokens": 6287360} {"current_steps": 1536, "total_steps": 6710, "loss": 0.7824, "lr": 2.190458667828909e-06, "epoch": 1.1445603576751118, "percentage": 22.89, "elapsed_time": "0:20:11", "remaining_time": "1:07:59", "throughput": 5194.78, "total_tokens": 6291456} {"current_steps": 1537, "total_steps": 6710, "loss": 0.6707, "lr": 2.190073038290214e-06, "epoch": 1.145305514157973, "percentage": 22.91, "elapsed_time": "0:20:11", "remaining_time": "1:07:58", "throughput": 5194.78, "total_tokens": 6295552} {"current_steps": 1538, "total_steps": 6710, "loss": 0.6804, "lr": 2.1896872026807967e-06, "epoch": 1.1460506706408347, "percentage": 22.92, "elapsed_time": "0:20:12", "remaining_time": "1:07:58", "throughput": 5194.81, "total_tokens": 6299648} {"current_steps": 1539, "total_steps": 6710, "loss": 0.6622, "lr": 2.189301161085234e-06, "epoch": 1.146795827123696, "percentage": 22.94, "elapsed_time": "0:20:13", "remaining_time": "1:07:57", "throughput": 5194.84, "total_tokens": 6303744} {"current_steps": 1540, "total_steps": 6710, "loss": 0.4927, "lr": 2.1889149135881497e-06, "epoch": 1.1475409836065573, "percentage": 22.95, "elapsed_time": "0:20:14", "remaining_time": "1:07:56", "throughput": 5194.83, "total_tokens": 6307840} {"current_steps": 1541, "total_steps": 6710, "loss": 0.8156, "lr": 2.1885284602742123e-06, "epoch": 1.1482861400894189, "percentage": 22.97, "elapsed_time": "0:20:15", "remaining_time": "1:07:55", "throughput": 5194.82, "total_tokens": 6311936} {"current_steps": 1542, "total_steps": 6710, "loss": 1.002, "lr": 2.1881418012281345e-06, "epoch": 1.1490312965722802, "percentage": 22.98, "elapsed_time": "0:20:15", "remaining_time": "1:07:54", "throughput": 5194.85, "total_tokens": 6316032} {"current_steps": 1543, "total_steps": 6710, "loss": 1.1582, "lr": 2.187754936534675e-06, "epoch": 1.1497764530551415, "percentage": 23.0, "elapsed_time": "0:20:16", "remaining_time": "1:07:54", "throughput": 5194.89, "total_tokens": 6320128} {"current_steps": 1544, "total_steps": 6710, "loss": 0.8551, "lr": 2.187367866278637e-06, "epoch": 1.150521609538003, "percentage": 23.01, "elapsed_time": "0:20:17", "remaining_time": "1:07:53", "throughput": 5194.93, "total_tokens": 6324224} {"current_steps": 1545, "total_steps": 6710, "loss": 0.6966, "lr": 2.1869805905448697e-06, "epoch": 1.1512667660208644, "percentage": 23.03, "elapsed_time": "0:20:18", "remaining_time": "1:07:52", "throughput": 5194.97, "total_tokens": 6328320} {"current_steps": 1546, "total_steps": 6710, "loss": 0.7812, "lr": 2.186593109418266e-06, "epoch": 1.1520119225037257, "percentage": 23.04, "elapsed_time": "0:20:18", "remaining_time": "1:07:51", "throughput": 5195.0, "total_tokens": 6332416} {"current_steps": 1547, "total_steps": 6710, "loss": 0.7356, "lr": 2.1862054229837647e-06, "epoch": 1.1527570789865873, "percentage": 23.06, "elapsed_time": "0:20:19", "remaining_time": "1:07:50", "throughput": 5195.03, "total_tokens": 6336512} {"current_steps": 1548, "total_steps": 6710, "loss": 0.9918, "lr": 2.1858175313263504e-06, "epoch": 1.1535022354694486, "percentage": 23.07, "elapsed_time": "0:20:20", "remaining_time": "1:07:49", "throughput": 5195.02, "total_tokens": 6340608} {"current_steps": 1549, "total_steps": 6710, "loss": 0.8448, "lr": 2.18542943453105e-06, "epoch": 1.15424739195231, "percentage": 23.08, "elapsed_time": "0:20:21", "remaining_time": "1:07:49", "throughput": 5195.04, "total_tokens": 6344704} {"current_steps": 1550, "total_steps": 6710, "loss": 0.8573, "lr": 2.185041132682938e-06, "epoch": 1.1549925484351713, "percentage": 23.1, "elapsed_time": "0:20:22", "remaining_time": "1:07:48", "throughput": 5195.04, "total_tokens": 6348800} {"current_steps": 1551, "total_steps": 6710, "loss": 0.8355, "lr": 2.1846526258671335e-06, "epoch": 1.1557377049180328, "percentage": 23.11, "elapsed_time": "0:20:22", "remaining_time": "1:07:47", "throughput": 5195.07, "total_tokens": 6352896} {"current_steps": 1552, "total_steps": 6710, "loss": 0.9341, "lr": 2.1842639141687986e-06, "epoch": 1.1564828614008942, "percentage": 23.13, "elapsed_time": "0:20:23", "remaining_time": "1:07:46", "throughput": 5195.1, "total_tokens": 6356992} {"current_steps": 1553, "total_steps": 6710, "loss": 0.6795, "lr": 2.1838749976731432e-06, "epoch": 1.1572280178837555, "percentage": 23.14, "elapsed_time": "0:20:24", "remaining_time": "1:07:45", "throughput": 5195.12, "total_tokens": 6361088} {"current_steps": 1554, "total_steps": 6710, "loss": 0.9029, "lr": 2.18348587646542e-06, "epoch": 1.157973174366617, "percentage": 23.16, "elapsed_time": "0:20:25", "remaining_time": "1:07:45", "throughput": 5195.12, "total_tokens": 6365184} {"current_steps": 1555, "total_steps": 6710, "loss": 0.7619, "lr": 2.1830965506309263e-06, "epoch": 1.1587183308494784, "percentage": 23.17, "elapsed_time": "0:20:26", "remaining_time": "1:07:44", "throughput": 5195.15, "total_tokens": 6369280} {"current_steps": 1556, "total_steps": 6710, "loss": 1.0137, "lr": 2.182707020255006e-06, "epoch": 1.1594634873323397, "percentage": 23.19, "elapsed_time": "0:20:26", "remaining_time": "1:07:43", "throughput": 5195.18, "total_tokens": 6373376} {"current_steps": 1557, "total_steps": 6710, "loss": 0.9585, "lr": 2.182317285423047e-06, "epoch": 1.1602086438152013, "percentage": 23.2, "elapsed_time": "0:20:27", "remaining_time": "1:07:42", "throughput": 5195.21, "total_tokens": 6377472} {"current_steps": 1558, "total_steps": 6710, "loss": 0.8468, "lr": 2.1819273462204815e-06, "epoch": 1.1609538002980626, "percentage": 23.22, "elapsed_time": "0:20:28", "remaining_time": "1:07:41", "throughput": 5195.24, "total_tokens": 6381568} {"current_steps": 1559, "total_steps": 6710, "loss": 0.6678, "lr": 2.1815372027327875e-06, "epoch": 1.161698956780924, "percentage": 23.23, "elapsed_time": "0:20:29", "remaining_time": "1:07:41", "throughput": 5195.26, "total_tokens": 6385664} {"current_steps": 1560, "total_steps": 6710, "loss": 1.0819, "lr": 2.181146855045486e-06, "epoch": 1.1624441132637853, "percentage": 23.25, "elapsed_time": "0:20:29", "remaining_time": "1:07:40", "throughput": 5195.3, "total_tokens": 6389760} {"current_steps": 1561, "total_steps": 6710, "loss": 0.5922, "lr": 2.1807563032441457e-06, "epoch": 1.1631892697466468, "percentage": 23.26, "elapsed_time": "0:20:30", "remaining_time": "1:07:39", "throughput": 5195.33, "total_tokens": 6393856} {"current_steps": 1562, "total_steps": 6710, "loss": 0.8629, "lr": 2.1803655474143774e-06, "epoch": 1.1639344262295082, "percentage": 23.28, "elapsed_time": "0:20:31", "remaining_time": "1:07:38", "throughput": 5195.36, "total_tokens": 6397952} {"current_steps": 1563, "total_steps": 6710, "loss": 1.0499, "lr": 2.1799745876418376e-06, "epoch": 1.1646795827123695, "percentage": 23.29, "elapsed_time": "0:20:32", "remaining_time": "1:07:37", "throughput": 5195.4, "total_tokens": 6402048} {"current_steps": 1564, "total_steps": 6710, "loss": 0.4961, "lr": 2.1795834240122276e-06, "epoch": 1.165424739195231, "percentage": 23.31, "elapsed_time": "0:20:33", "remaining_time": "1:07:37", "throughput": 5195.44, "total_tokens": 6406144} {"current_steps": 1565, "total_steps": 6710, "loss": 0.9088, "lr": 2.1791920566112933e-06, "epoch": 1.1661698956780924, "percentage": 23.32, "elapsed_time": "0:20:33", "remaining_time": "1:07:36", "throughput": 5195.46, "total_tokens": 6410240} {"current_steps": 1566, "total_steps": 6710, "loss": 0.5755, "lr": 2.178800485524825e-06, "epoch": 1.1669150521609537, "percentage": 23.34, "elapsed_time": "0:20:34", "remaining_time": "1:07:35", "throughput": 5195.5, "total_tokens": 6414336} {"current_steps": 1567, "total_steps": 6710, "loss": 0.3341, "lr": 2.178408710838658e-06, "epoch": 1.1676602086438153, "percentage": 23.35, "elapsed_time": "0:20:35", "remaining_time": "1:07:34", "throughput": 5195.53, "total_tokens": 6418432} {"current_steps": 1568, "total_steps": 6710, "loss": 0.8375, "lr": 2.1780167326386724e-06, "epoch": 1.1684053651266766, "percentage": 23.37, "elapsed_time": "0:20:36", "remaining_time": "1:07:33", "throughput": 5195.56, "total_tokens": 6422528} {"current_steps": 1569, "total_steps": 6710, "loss": 0.8837, "lr": 2.1776245510107924e-06, "epoch": 1.169150521609538, "percentage": 23.38, "elapsed_time": "0:20:36", "remaining_time": "1:07:32", "throughput": 5195.59, "total_tokens": 6426624} {"current_steps": 1570, "total_steps": 6710, "loss": 0.9372, "lr": 2.1772321660409868e-06, "epoch": 1.1698956780923995, "percentage": 23.4, "elapsed_time": "0:20:37", "remaining_time": "1:07:32", "throughput": 5195.63, "total_tokens": 6430720} {"current_steps": 1571, "total_steps": 6710, "loss": 0.5798, "lr": 2.1768395778152696e-06, "epoch": 1.1706408345752608, "percentage": 23.41, "elapsed_time": "0:20:38", "remaining_time": "1:07:31", "throughput": 5195.66, "total_tokens": 6434816} {"current_steps": 1572, "total_steps": 6710, "loss": 0.8164, "lr": 2.1764467864196986e-06, "epoch": 1.1713859910581221, "percentage": 23.43, "elapsed_time": "0:20:39", "remaining_time": "1:07:30", "throughput": 5195.68, "total_tokens": 6438912} {"current_steps": 1573, "total_steps": 6710, "loss": 0.7502, "lr": 2.1760537919403764e-06, "epoch": 1.1721311475409837, "percentage": 23.44, "elapsed_time": "0:20:40", "remaining_time": "1:07:29", "throughput": 5195.71, "total_tokens": 6443008} {"current_steps": 1574, "total_steps": 6710, "loss": 0.6984, "lr": 2.175660594463451e-06, "epoch": 1.172876304023845, "percentage": 23.46, "elapsed_time": "0:20:40", "remaining_time": "1:07:28", "throughput": 5195.74, "total_tokens": 6447104} {"current_steps": 1575, "total_steps": 6710, "loss": 0.7538, "lr": 2.1752671940751123e-06, "epoch": 1.1736214605067063, "percentage": 23.47, "elapsed_time": "0:20:41", "remaining_time": "1:07:28", "throughput": 5195.78, "total_tokens": 6451200} {"current_steps": 1576, "total_steps": 6710, "loss": 0.6063, "lr": 2.1748735908615988e-06, "epoch": 1.174366616989568, "percentage": 23.49, "elapsed_time": "0:20:42", "remaining_time": "1:07:27", "throughput": 5195.82, "total_tokens": 6455296} {"current_steps": 1577, "total_steps": 6710, "loss": 0.8235, "lr": 2.1744797849091895e-06, "epoch": 1.1751117734724292, "percentage": 23.5, "elapsed_time": "0:20:43", "remaining_time": "1:07:26", "throughput": 5195.86, "total_tokens": 6459392} {"current_steps": 1578, "total_steps": 6710, "loss": 1.1454, "lr": 2.17408577630421e-06, "epoch": 1.1758569299552906, "percentage": 23.52, "elapsed_time": "0:20:43", "remaining_time": "1:07:25", "throughput": 5195.89, "total_tokens": 6463488} {"current_steps": 1579, "total_steps": 6710, "loss": 0.7536, "lr": 2.1736915651330297e-06, "epoch": 1.1766020864381521, "percentage": 23.53, "elapsed_time": "0:20:44", "remaining_time": "1:07:24", "throughput": 5195.93, "total_tokens": 6467584} {"current_steps": 1580, "total_steps": 6710, "loss": 0.6921, "lr": 2.173297151482063e-06, "epoch": 1.1773472429210134, "percentage": 23.55, "elapsed_time": "0:20:45", "remaining_time": "1:07:24", "throughput": 5195.96, "total_tokens": 6471680} {"current_steps": 1581, "total_steps": 6710, "loss": 0.6272, "lr": 2.1729025354377673e-06, "epoch": 1.1780923994038748, "percentage": 23.56, "elapsed_time": "0:20:46", "remaining_time": "1:07:23", "throughput": 5195.99, "total_tokens": 6475776} {"current_steps": 1582, "total_steps": 6710, "loss": 0.9309, "lr": 2.172507717086646e-06, "epoch": 1.1788375558867363, "percentage": 23.58, "elapsed_time": "0:20:47", "remaining_time": "1:07:22", "throughput": 5196.0, "total_tokens": 6479872} {"current_steps": 1583, "total_steps": 6710, "loss": 1.0797, "lr": 2.1721126965152457e-06, "epoch": 1.1795827123695977, "percentage": 23.59, "elapsed_time": "0:20:47", "remaining_time": "1:07:21", "throughput": 5196.01, "total_tokens": 6483968} {"current_steps": 1584, "total_steps": 6710, "loss": 0.4872, "lr": 2.171717473810158e-06, "epoch": 1.180327868852459, "percentage": 23.61, "elapsed_time": "0:20:48", "remaining_time": "1:07:20", "throughput": 5196.03, "total_tokens": 6488064} {"current_steps": 1585, "total_steps": 6710, "loss": 0.8957, "lr": 2.171322049058018e-06, "epoch": 1.1810730253353203, "percentage": 23.62, "elapsed_time": "0:20:49", "remaining_time": "1:07:19", "throughput": 5196.06, "total_tokens": 6492160} {"current_steps": 1586, "total_steps": 6710, "loss": 0.9181, "lr": 2.170926422345506e-06, "epoch": 1.1818181818181819, "percentage": 23.64, "elapsed_time": "0:20:50", "remaining_time": "1:07:19", "throughput": 5196.09, "total_tokens": 6496256} {"current_steps": 1587, "total_steps": 6710, "loss": 0.509, "lr": 2.170530593759347e-06, "epoch": 1.1825633383010432, "percentage": 23.65, "elapsed_time": "0:20:51", "remaining_time": "1:07:18", "throughput": 5196.11, "total_tokens": 6500352} {"current_steps": 1588, "total_steps": 6710, "loss": 0.7087, "lr": 2.170134563386308e-06, "epoch": 1.1833084947839045, "percentage": 23.67, "elapsed_time": "0:20:51", "remaining_time": "1:07:17", "throughput": 5196.14, "total_tokens": 6504448} {"current_steps": 1589, "total_steps": 6710, "loss": 0.6914, "lr": 2.1697383313132027e-06, "epoch": 1.184053651266766, "percentage": 23.68, "elapsed_time": "0:20:52", "remaining_time": "1:07:16", "throughput": 5196.17, "total_tokens": 6508544} {"current_steps": 1590, "total_steps": 6710, "loss": 0.9289, "lr": 2.1693418976268874e-06, "epoch": 1.1847988077496274, "percentage": 23.7, "elapsed_time": "0:20:53", "remaining_time": "1:07:15", "throughput": 5196.2, "total_tokens": 6512640} {"current_steps": 1591, "total_steps": 6710, "loss": 0.7461, "lr": 2.1689452624142632e-06, "epoch": 1.1855439642324888, "percentage": 23.71, "elapsed_time": "0:20:54", "remaining_time": "1:07:15", "throughput": 5196.23, "total_tokens": 6516736} {"current_steps": 1592, "total_steps": 6710, "loss": 0.5903, "lr": 2.168548425762276e-06, "epoch": 1.1862891207153503, "percentage": 23.73, "elapsed_time": "0:20:54", "remaining_time": "1:07:14", "throughput": 5196.26, "total_tokens": 6520832} {"current_steps": 1593, "total_steps": 6710, "loss": 0.9188, "lr": 2.168151387757915e-06, "epoch": 1.1870342771982116, "percentage": 23.74, "elapsed_time": "0:20:55", "remaining_time": "1:07:13", "throughput": 5196.3, "total_tokens": 6524928} {"current_steps": 1594, "total_steps": 6710, "loss": 0.842, "lr": 2.167754148488213e-06, "epoch": 1.187779433681073, "percentage": 23.76, "elapsed_time": "0:20:56", "remaining_time": "1:07:12", "throughput": 5196.33, "total_tokens": 6529024} {"current_steps": 1595, "total_steps": 6710, "loss": 0.9741, "lr": 2.167356708040249e-06, "epoch": 1.1885245901639343, "percentage": 23.77, "elapsed_time": "0:20:57", "remaining_time": "1:07:11", "throughput": 5196.36, "total_tokens": 6533120} {"current_steps": 1596, "total_steps": 6710, "loss": 0.9358, "lr": 2.1669590665011438e-06, "epoch": 1.1892697466467959, "percentage": 23.79, "elapsed_time": "0:20:58", "remaining_time": "1:07:11", "throughput": 5196.38, "total_tokens": 6537216} {"current_steps": 1597, "total_steps": 6710, "loss": 0.7475, "lr": 2.1665612239580635e-06, "epoch": 1.1900149031296572, "percentage": 23.8, "elapsed_time": "0:20:58", "remaining_time": "1:07:10", "throughput": 5196.4, "total_tokens": 6541312} {"current_steps": 1598, "total_steps": 6710, "loss": 0.719, "lr": 2.1661631804982184e-06, "epoch": 1.1907600596125185, "percentage": 23.82, "elapsed_time": "0:20:59", "remaining_time": "1:07:09", "throughput": 5196.41, "total_tokens": 6545408} {"current_steps": 1599, "total_steps": 6710, "loss": 0.7886, "lr": 2.1657649362088618e-06, "epoch": 1.19150521609538, "percentage": 23.83, "elapsed_time": "0:21:00", "remaining_time": "1:07:08", "throughput": 5196.42, "total_tokens": 6549504} {"current_steps": 1600, "total_steps": 6710, "loss": 0.6116, "lr": 2.165366491177292e-06, "epoch": 1.1922503725782414, "percentage": 23.85, "elapsed_time": "0:21:01", "remaining_time": "1:07:07", "throughput": 5196.44, "total_tokens": 6553600} {"current_steps": 1601, "total_steps": 6710, "loss": 0.9469, "lr": 2.164967845490851e-06, "epoch": 1.1929955290611027, "percentage": 23.86, "elapsed_time": "0:21:01", "remaining_time": "1:07:07", "throughput": 5196.48, "total_tokens": 6557696} {"current_steps": 1602, "total_steps": 6710, "loss": 0.6396, "lr": 2.164568999236925e-06, "epoch": 1.1937406855439643, "percentage": 23.87, "elapsed_time": "0:21:02", "remaining_time": "1:07:06", "throughput": 5196.49, "total_tokens": 6561792} {"current_steps": 1603, "total_steps": 6710, "loss": 0.9009, "lr": 2.1641699525029443e-06, "epoch": 1.1944858420268256, "percentage": 23.89, "elapsed_time": "0:21:03", "remaining_time": "1:07:05", "throughput": 5196.52, "total_tokens": 6565888} {"current_steps": 1604, "total_steps": 6710, "loss": 0.6602, "lr": 2.163770705376381e-06, "epoch": 1.195230998509687, "percentage": 23.9, "elapsed_time": "0:21:04", "remaining_time": "1:07:04", "throughput": 5196.54, "total_tokens": 6569984} {"current_steps": 1605, "total_steps": 6710, "loss": 0.5451, "lr": 2.1633712579447553e-06, "epoch": 1.1959761549925485, "percentage": 23.92, "elapsed_time": "0:21:05", "remaining_time": "1:07:03", "throughput": 5196.58, "total_tokens": 6574080} {"current_steps": 1606, "total_steps": 6710, "loss": 0.9573, "lr": 2.1629716102956272e-06, "epoch": 1.1967213114754098, "percentage": 23.93, "elapsed_time": "0:21:05", "remaining_time": "1:07:03", "throughput": 5196.61, "total_tokens": 6578176} {"current_steps": 1607, "total_steps": 6710, "loss": 0.8637, "lr": 2.162571762516603e-06, "epoch": 1.1974664679582712, "percentage": 23.95, "elapsed_time": "0:21:06", "remaining_time": "1:07:02", "throughput": 5196.62, "total_tokens": 6582272} {"current_steps": 1608, "total_steps": 6710, "loss": 0.7868, "lr": 2.1621717146953322e-06, "epoch": 1.1982116244411327, "percentage": 23.96, "elapsed_time": "0:21:07", "remaining_time": "1:07:01", "throughput": 5196.63, "total_tokens": 6586368} {"current_steps": 1609, "total_steps": 6710, "loss": 0.5366, "lr": 2.1617714669195083e-06, "epoch": 1.198956780923994, "percentage": 23.98, "elapsed_time": "0:21:08", "remaining_time": "1:07:00", "throughput": 5196.67, "total_tokens": 6590464} {"current_steps": 1610, "total_steps": 6710, "loss": 0.6688, "lr": 2.1613710192768677e-06, "epoch": 1.1997019374068554, "percentage": 23.99, "elapsed_time": "0:21:08", "remaining_time": "1:06:59", "throughput": 5196.7, "total_tokens": 6594560} {"current_steps": 1611, "total_steps": 6710, "loss": 0.6758, "lr": 2.1609703718551923e-06, "epoch": 1.200447093889717, "percentage": 24.01, "elapsed_time": "0:21:09", "remaining_time": "1:06:58", "throughput": 5196.73, "total_tokens": 6598656} {"current_steps": 1612, "total_steps": 6710, "loss": 0.8504, "lr": 2.1605695247423063e-06, "epoch": 1.2011922503725783, "percentage": 24.02, "elapsed_time": "0:21:10", "remaining_time": "1:06:58", "throughput": 5196.74, "total_tokens": 6602752} {"current_steps": 1613, "total_steps": 6710, "loss": 0.9736, "lr": 2.1601684780260783e-06, "epoch": 1.2019374068554396, "percentage": 24.04, "elapsed_time": "0:21:11", "remaining_time": "1:06:57", "throughput": 5196.77, "total_tokens": 6606848} {"current_steps": 1614, "total_steps": 6710, "loss": 0.8768, "lr": 2.159767231794421e-06, "epoch": 1.2026825633383011, "percentage": 24.05, "elapsed_time": "0:21:12", "remaining_time": "1:06:56", "throughput": 5196.78, "total_tokens": 6610944} {"current_steps": 1615, "total_steps": 6710, "loss": 0.6426, "lr": 2.15936578613529e-06, "epoch": 1.2034277198211625, "percentage": 24.07, "elapsed_time": "0:21:12", "remaining_time": "1:06:55", "throughput": 5196.78, "total_tokens": 6615040} {"current_steps": 1616, "total_steps": 6710, "loss": 0.5461, "lr": 2.1589641411366855e-06, "epoch": 1.2041728763040238, "percentage": 24.08, "elapsed_time": "0:21:13", "remaining_time": "1:06:54", "throughput": 5196.81, "total_tokens": 6619136} {"current_steps": 1617, "total_steps": 6710, "loss": 0.9702, "lr": 2.1585622968866504e-06, "epoch": 1.2049180327868854, "percentage": 24.1, "elapsed_time": "0:21:14", "remaining_time": "1:06:54", "throughput": 5196.84, "total_tokens": 6623232} {"current_steps": 1618, "total_steps": 6710, "loss": 1.0523, "lr": 2.158160253473272e-06, "epoch": 1.2056631892697467, "percentage": 24.11, "elapsed_time": "0:21:15", "remaining_time": "1:06:53", "throughput": 5196.87, "total_tokens": 6627328} {"current_steps": 1619, "total_steps": 6710, "loss": 0.8628, "lr": 2.157758010984682e-06, "epoch": 1.206408345752608, "percentage": 24.13, "elapsed_time": "0:21:16", "remaining_time": "1:06:52", "throughput": 5196.9, "total_tokens": 6631424} {"current_steps": 1620, "total_steps": 6710, "loss": 0.9243, "lr": 2.157355569509053e-06, "epoch": 1.2071535022354694, "percentage": 24.14, "elapsed_time": "0:21:16", "remaining_time": "1:06:51", "throughput": 5196.91, "total_tokens": 6635520} {"current_steps": 1621, "total_steps": 6710, "loss": 0.8747, "lr": 2.1569529291346046e-06, "epoch": 1.207898658718331, "percentage": 24.16, "elapsed_time": "0:21:17", "remaining_time": "1:06:50", "throughput": 5196.94, "total_tokens": 6639616} {"current_steps": 1622, "total_steps": 6710, "loss": 0.9788, "lr": 2.156550089949598e-06, "epoch": 1.2086438152011922, "percentage": 24.17, "elapsed_time": "0:21:18", "remaining_time": "1:06:50", "throughput": 5196.97, "total_tokens": 6643712} {"current_steps": 1623, "total_steps": 6710, "loss": 1.0361, "lr": 2.1561470520423377e-06, "epoch": 1.2093889716840536, "percentage": 24.19, "elapsed_time": "0:21:19", "remaining_time": "1:06:49", "throughput": 5196.97, "total_tokens": 6647808} {"current_steps": 1624, "total_steps": 6710, "loss": 0.7785, "lr": 2.1557438155011735e-06, "epoch": 1.2101341281669151, "percentage": 24.2, "elapsed_time": "0:21:19", "remaining_time": "1:06:48", "throughput": 5197.0, "total_tokens": 6651904} {"current_steps": 1625, "total_steps": 6710, "loss": 0.8129, "lr": 2.1553403804144976e-06, "epoch": 1.2108792846497765, "percentage": 24.22, "elapsed_time": "0:21:20", "remaining_time": "1:06:47", "throughput": 5197.03, "total_tokens": 6656000} {"current_steps": 1626, "total_steps": 6710, "loss": 0.9142, "lr": 2.1549367468707456e-06, "epoch": 1.2116244411326378, "percentage": 24.23, "elapsed_time": "0:21:21", "remaining_time": "1:06:46", "throughput": 5197.06, "total_tokens": 6660096} {"current_steps": 1627, "total_steps": 6710, "loss": 0.6924, "lr": 2.1545329149583966e-06, "epoch": 1.2123695976154993, "percentage": 24.25, "elapsed_time": "0:21:22", "remaining_time": "1:06:46", "throughput": 5197.1, "total_tokens": 6664192} {"current_steps": 1628, "total_steps": 6710, "loss": 0.8504, "lr": 2.1541288847659736e-06, "epoch": 1.2131147540983607, "percentage": 24.26, "elapsed_time": "0:21:23", "remaining_time": "1:06:45", "throughput": 5197.14, "total_tokens": 6668288} {"current_steps": 1629, "total_steps": 6710, "loss": 0.7109, "lr": 2.153724656382043e-06, "epoch": 1.213859910581222, "percentage": 24.28, "elapsed_time": "0:21:23", "remaining_time": "1:06:44", "throughput": 5197.18, "total_tokens": 6672384} {"current_steps": 1630, "total_steps": 6710, "loss": 0.6959, "lr": 2.153320229895215e-06, "epoch": 1.2146050670640836, "percentage": 24.29, "elapsed_time": "0:21:24", "remaining_time": "1:06:43", "throughput": 5197.21, "total_tokens": 6676480} {"current_steps": 1631, "total_steps": 6710, "loss": 0.7278, "lr": 2.1529156053941417e-06, "epoch": 1.2153502235469449, "percentage": 24.31, "elapsed_time": "0:21:25", "remaining_time": "1:06:42", "throughput": 5197.23, "total_tokens": 6680576} {"current_steps": 1632, "total_steps": 6710, "loss": 0.7945, "lr": 2.152510782967521e-06, "epoch": 1.2160953800298062, "percentage": 24.32, "elapsed_time": "0:21:26", "remaining_time": "1:06:42", "throughput": 5197.25, "total_tokens": 6684672} {"current_steps": 1633, "total_steps": 6710, "loss": 0.8687, "lr": 2.152105762704092e-06, "epoch": 1.2168405365126675, "percentage": 24.34, "elapsed_time": "0:21:26", "remaining_time": "1:06:41", "throughput": 5197.29, "total_tokens": 6688768} {"current_steps": 1634, "total_steps": 6710, "loss": 0.6837, "lr": 2.151700544692638e-06, "epoch": 1.217585692995529, "percentage": 24.35, "elapsed_time": "0:21:27", "remaining_time": "1:06:40", "throughput": 5197.3, "total_tokens": 6692864} {"current_steps": 1635, "total_steps": 6710, "loss": 0.6959, "lr": 2.1512951290219857e-06, "epoch": 1.2183308494783904, "percentage": 24.37, "elapsed_time": "0:21:28", "remaining_time": "1:06:39", "throughput": 5197.33, "total_tokens": 6696960} {"current_steps": 1636, "total_steps": 6710, "loss": 0.7076, "lr": 2.1508895157810057e-06, "epoch": 1.2190760059612518, "percentage": 24.38, "elapsed_time": "0:21:29", "remaining_time": "1:06:38", "throughput": 5197.36, "total_tokens": 6701056} {"current_steps": 1637, "total_steps": 6710, "loss": 0.8535, "lr": 2.1504837050586105e-06, "epoch": 1.2198211624441133, "percentage": 24.4, "elapsed_time": "0:21:30", "remaining_time": "1:06:38", "throughput": 5197.35, "total_tokens": 6705152} {"current_steps": 1638, "total_steps": 6710, "loss": 0.7408, "lr": 2.1500776969437577e-06, "epoch": 1.2205663189269746, "percentage": 24.41, "elapsed_time": "0:21:30", "remaining_time": "1:06:37", "throughput": 5197.38, "total_tokens": 6709248} {"current_steps": 1639, "total_steps": 6710, "loss": 0.5969, "lr": 2.149671491525446e-06, "epoch": 1.221311475409836, "percentage": 24.43, "elapsed_time": "0:21:31", "remaining_time": "1:06:36", "throughput": 5197.42, "total_tokens": 6713344} {"current_steps": 1640, "total_steps": 6710, "loss": 0.7405, "lr": 2.1492650888927193e-06, "epoch": 1.2220566318926975, "percentage": 24.44, "elapsed_time": "0:21:32", "remaining_time": "1:06:35", "throughput": 5197.45, "total_tokens": 6717440} {"current_steps": 1641, "total_steps": 6710, "loss": 0.9589, "lr": 2.148858489134664e-06, "epoch": 1.2228017883755589, "percentage": 24.46, "elapsed_time": "0:21:33", "remaining_time": "1:06:34", "throughput": 5197.48, "total_tokens": 6721536} {"current_steps": 1642, "total_steps": 6710, "loss": 0.9518, "lr": 2.1484516923404094e-06, "epoch": 1.2235469448584202, "percentage": 24.47, "elapsed_time": "0:21:34", "remaining_time": "1:06:33", "throughput": 5197.51, "total_tokens": 6725632} {"current_steps": 1643, "total_steps": 6710, "loss": 1.0332, "lr": 2.148044698599128e-06, "epoch": 1.2242921013412817, "percentage": 24.49, "elapsed_time": "0:21:34", "remaining_time": "1:06:33", "throughput": 5197.53, "total_tokens": 6729728} {"current_steps": 1644, "total_steps": 6710, "loss": 0.8794, "lr": 2.1476375080000365e-06, "epoch": 1.225037257824143, "percentage": 24.5, "elapsed_time": "0:21:35", "remaining_time": "1:06:32", "throughput": 5197.56, "total_tokens": 6733824} {"current_steps": 1645, "total_steps": 6710, "loss": 0.7255, "lr": 2.147230120632393e-06, "epoch": 1.2257824143070044, "percentage": 24.52, "elapsed_time": "0:21:36", "remaining_time": "1:06:31", "throughput": 5197.58, "total_tokens": 6737920} {"current_steps": 1646, "total_steps": 6710, "loss": 0.7532, "lr": 2.146822536585501e-06, "epoch": 1.226527570789866, "percentage": 24.53, "elapsed_time": "0:21:37", "remaining_time": "1:06:30", "throughput": 5197.61, "total_tokens": 6742016} {"current_steps": 1647, "total_steps": 6710, "loss": 0.5866, "lr": 2.1464147559487046e-06, "epoch": 1.2272727272727273, "percentage": 24.55, "elapsed_time": "0:21:37", "remaining_time": "1:06:29", "throughput": 5197.63, "total_tokens": 6746112} {"current_steps": 1648, "total_steps": 6710, "loss": 0.6818, "lr": 2.146006778811393e-06, "epoch": 1.2280178837555886, "percentage": 24.56, "elapsed_time": "0:21:38", "remaining_time": "1:06:29", "throughput": 5197.66, "total_tokens": 6750208} {"current_steps": 1649, "total_steps": 6710, "loss": 0.6344, "lr": 2.145598605262997e-06, "epoch": 1.2287630402384502, "percentage": 24.58, "elapsed_time": "0:21:39", "remaining_time": "1:06:28", "throughput": 5197.69, "total_tokens": 6754304} {"current_steps": 1650, "total_steps": 6710, "loss": 0.8675, "lr": 2.145190235392992e-06, "epoch": 1.2295081967213115, "percentage": 24.59, "elapsed_time": "0:21:40", "remaining_time": "1:06:27", "throughput": 5197.71, "total_tokens": 6758400} {"current_steps": 1651, "total_steps": 6710, "loss": 0.7736, "lr": 2.144781669290895e-06, "epoch": 1.2302533532041728, "percentage": 24.61, "elapsed_time": "0:21:41", "remaining_time": "1:06:26", "throughput": 5197.72, "total_tokens": 6762496} {"current_steps": 1652, "total_steps": 6710, "loss": 0.8095, "lr": 2.1443729070462665e-06, "epoch": 1.2309985096870344, "percentage": 24.62, "elapsed_time": "0:21:41", "remaining_time": "1:06:25", "throughput": 5197.74, "total_tokens": 6766592} {"current_steps": 1653, "total_steps": 6710, "loss": 0.905, "lr": 2.143963948748711e-06, "epoch": 1.2317436661698957, "percentage": 24.63, "elapsed_time": "0:21:42", "remaining_time": "1:06:25", "throughput": 5197.77, "total_tokens": 6770688} {"current_steps": 1654, "total_steps": 6710, "loss": 0.8251, "lr": 2.143554794487874e-06, "epoch": 1.232488822652757, "percentage": 24.65, "elapsed_time": "0:21:43", "remaining_time": "1:06:24", "throughput": 5197.8, "total_tokens": 6774784} {"current_steps": 1655, "total_steps": 6710, "loss": 1.0111, "lr": 2.1431454443534456e-06, "epoch": 1.2332339791356184, "percentage": 24.66, "elapsed_time": "0:21:44", "remaining_time": "1:06:23", "throughput": 5197.81, "total_tokens": 6778880} {"current_steps": 1656, "total_steps": 6710, "loss": 0.8582, "lr": 2.1427358984351583e-06, "epoch": 1.23397913561848, "percentage": 24.68, "elapsed_time": "0:21:44", "remaining_time": "1:06:22", "throughput": 5197.83, "total_tokens": 6782976} {"current_steps": 1657, "total_steps": 6710, "loss": 0.7202, "lr": 2.1423261568227873e-06, "epoch": 1.2347242921013413, "percentage": 24.69, "elapsed_time": "0:21:45", "remaining_time": "1:06:21", "throughput": 5197.85, "total_tokens": 6787072} {"current_steps": 1658, "total_steps": 6710, "loss": 0.7817, "lr": 2.1419162196061506e-06, "epoch": 1.2354694485842026, "percentage": 24.71, "elapsed_time": "0:21:46", "remaining_time": "1:06:21", "throughput": 5197.87, "total_tokens": 6791168} {"current_steps": 1659, "total_steps": 6710, "loss": 0.9006, "lr": 2.1415060868751104e-06, "epoch": 1.2362146050670642, "percentage": 24.72, "elapsed_time": "0:21:47", "remaining_time": "1:06:20", "throughput": 5197.9, "total_tokens": 6795264} {"current_steps": 1660, "total_steps": 6710, "loss": 0.6204, "lr": 2.1410957587195695e-06, "epoch": 1.2369597615499255, "percentage": 24.74, "elapsed_time": "0:21:48", "remaining_time": "1:06:19", "throughput": 5197.92, "total_tokens": 6799360} {"current_steps": 1661, "total_steps": 6710, "loss": 1.1719, "lr": 2.1406852352294752e-06, "epoch": 1.2377049180327868, "percentage": 24.75, "elapsed_time": "0:21:48", "remaining_time": "1:06:18", "throughput": 5197.95, "total_tokens": 6803456} {"current_steps": 1662, "total_steps": 6710, "loss": 0.755, "lr": 2.1402745164948175e-06, "epoch": 1.2384500745156484, "percentage": 24.77, "elapsed_time": "0:21:49", "remaining_time": "1:06:17", "throughput": 5197.97, "total_tokens": 6807552} {"current_steps": 1663, "total_steps": 6710, "loss": 0.7038, "lr": 2.139863602605629e-06, "epoch": 1.2391952309985097, "percentage": 24.78, "elapsed_time": "0:21:50", "remaining_time": "1:06:17", "throughput": 5198.0, "total_tokens": 6811648} {"current_steps": 1664, "total_steps": 6710, "loss": 0.8825, "lr": 2.139452493651984e-06, "epoch": 1.239940387481371, "percentage": 24.8, "elapsed_time": "0:21:51", "remaining_time": "1:06:16", "throughput": 5198.01, "total_tokens": 6815744} {"current_steps": 1665, "total_steps": 6710, "loss": 0.8254, "lr": 2.1390411897240014e-06, "epoch": 1.2406855439642326, "percentage": 24.81, "elapsed_time": "0:21:52", "remaining_time": "1:06:15", "throughput": 5198.03, "total_tokens": 6819840} {"current_steps": 1666, "total_steps": 6710, "loss": 0.5245, "lr": 2.1386296909118416e-06, "epoch": 1.241430700447094, "percentage": 24.83, "elapsed_time": "0:21:52", "remaining_time": "1:06:14", "throughput": 5198.05, "total_tokens": 6823936} {"current_steps": 1667, "total_steps": 6710, "loss": 0.7573, "lr": 2.1382179973057087e-06, "epoch": 1.2421758569299552, "percentage": 24.84, "elapsed_time": "0:21:53", "remaining_time": "1:06:13", "throughput": 5198.07, "total_tokens": 6828032} {"current_steps": 1668, "total_steps": 6710, "loss": 1.1089, "lr": 2.1378061089958476e-06, "epoch": 1.2429210134128166, "percentage": 24.86, "elapsed_time": "0:21:54", "remaining_time": "1:06:12", "throughput": 5198.1, "total_tokens": 6832128} {"current_steps": 1669, "total_steps": 6710, "loss": 1.2109, "lr": 2.1373940260725486e-06, "epoch": 1.2436661698956781, "percentage": 24.87, "elapsed_time": "0:21:55", "remaining_time": "1:06:12", "throughput": 5198.12, "total_tokens": 6836224} {"current_steps": 1670, "total_steps": 6710, "loss": 0.9001, "lr": 2.136981748626142e-06, "epoch": 1.2444113263785395, "percentage": 24.89, "elapsed_time": "0:21:55", "remaining_time": "1:06:11", "throughput": 5198.14, "total_tokens": 6840320} {"current_steps": 1671, "total_steps": 6710, "loss": 0.7827, "lr": 2.1365692767470025e-06, "epoch": 1.2451564828614008, "percentage": 24.9, "elapsed_time": "0:21:56", "remaining_time": "1:06:10", "throughput": 5198.17, "total_tokens": 6844416} {"current_steps": 1672, "total_steps": 6710, "loss": 0.5272, "lr": 2.136156610525547e-06, "epoch": 1.2459016393442623, "percentage": 24.92, "elapsed_time": "0:21:57", "remaining_time": "1:06:09", "throughput": 5198.19, "total_tokens": 6848512} {"current_steps": 1673, "total_steps": 6710, "loss": 0.7636, "lr": 2.135743750052235e-06, "epoch": 1.2466467958271237, "percentage": 24.93, "elapsed_time": "0:21:58", "remaining_time": "1:06:08", "throughput": 5198.22, "total_tokens": 6852608} {"current_steps": 1674, "total_steps": 6710, "loss": 0.8569, "lr": 2.135330695417568e-06, "epoch": 1.247391952309985, "percentage": 24.95, "elapsed_time": "0:21:59", "remaining_time": "1:06:08", "throughput": 5198.21, "total_tokens": 6856704} {"current_steps": 1675, "total_steps": 6710, "loss": 0.775, "lr": 2.1349174467120905e-06, "epoch": 1.2481371087928466, "percentage": 24.96, "elapsed_time": "0:21:59", "remaining_time": "1:06:07", "throughput": 5198.23, "total_tokens": 6860800} {"current_steps": 1676, "total_steps": 6710, "loss": 0.9679, "lr": 2.13450400402639e-06, "epoch": 1.248882265275708, "percentage": 24.98, "elapsed_time": "0:22:00", "remaining_time": "1:06:06", "throughput": 5198.24, "total_tokens": 6864896} {"current_steps": 1677, "total_steps": 6710, "loss": 0.9434, "lr": 2.134090367451096e-06, "epoch": 1.2496274217585692, "percentage": 24.99, "elapsed_time": "0:22:01", "remaining_time": "1:06:05", "throughput": 5198.27, "total_tokens": 6868992} {"current_steps": 1678, "total_steps": 6710, "loss": 0.74, "lr": 2.1336765370768804e-06, "epoch": 1.2503725782414308, "percentage": 25.01, "elapsed_time": "0:22:02", "remaining_time": "1:06:04", "throughput": 5198.29, "total_tokens": 6873088} {"current_steps": 1679, "total_steps": 6710, "loss": 0.8013, "lr": 2.1332625129944577e-06, "epoch": 1.251117734724292, "percentage": 25.02, "elapsed_time": "0:22:02", "remaining_time": "1:06:04", "throughput": 5198.3, "total_tokens": 6877184} {"current_steps": 1680, "total_steps": 6710, "loss": 0.8076, "lr": 2.1328482952945855e-06, "epoch": 1.2518628912071534, "percentage": 25.04, "elapsed_time": "0:22:03", "remaining_time": "1:06:03", "throughput": 5198.32, "total_tokens": 6881280} {"current_steps": 1681, "total_steps": 6710, "loss": 0.7281, "lr": 2.1324338840680627e-06, "epoch": 1.252608047690015, "percentage": 25.05, "elapsed_time": "0:22:04", "remaining_time": "1:06:02", "throughput": 5198.34, "total_tokens": 6885376} {"current_steps": 1682, "total_steps": 6710, "loss": 0.6707, "lr": 2.132019279405731e-06, "epoch": 1.2533532041728763, "percentage": 25.07, "elapsed_time": "0:22:05", "remaining_time": "1:06:01", "throughput": 5198.36, "total_tokens": 6889472} {"current_steps": 1683, "total_steps": 6710, "loss": 0.7168, "lr": 2.1316044813984753e-06, "epoch": 1.2540983606557377, "percentage": 25.08, "elapsed_time": "0:22:06", "remaining_time": "1:06:00", "throughput": 5198.38, "total_tokens": 6893568} {"current_steps": 1684, "total_steps": 6710, "loss": 0.7621, "lr": 2.131189490137222e-06, "epoch": 1.2548435171385992, "percentage": 25.1, "elapsed_time": "0:22:06", "remaining_time": "1:06:00", "throughput": 5198.4, "total_tokens": 6897664} {"current_steps": 1685, "total_steps": 6710, "loss": 0.889, "lr": 2.1307743057129403e-06, "epoch": 1.2555886736214605, "percentage": 25.11, "elapsed_time": "0:22:07", "remaining_time": "1:05:59", "throughput": 5198.42, "total_tokens": 6901760} {"current_steps": 1686, "total_steps": 6710, "loss": 0.7806, "lr": 2.130358928216642e-06, "epoch": 1.2563338301043219, "percentage": 25.13, "elapsed_time": "0:22:08", "remaining_time": "1:05:58", "throughput": 5198.44, "total_tokens": 6905856} {"current_steps": 1687, "total_steps": 6710, "loss": 0.8145, "lr": 2.1299433577393795e-06, "epoch": 1.2570789865871834, "percentage": 25.14, "elapsed_time": "0:22:09", "remaining_time": "1:05:57", "throughput": 5198.45, "total_tokens": 6909952} {"current_steps": 1688, "total_steps": 6710, "loss": 1.0746, "lr": 2.1295275943722503e-06, "epoch": 1.2578241430700448, "percentage": 25.16, "elapsed_time": "0:22:10", "remaining_time": "1:05:56", "throughput": 5198.47, "total_tokens": 6914048} {"current_steps": 1689, "total_steps": 6710, "loss": 0.9881, "lr": 2.1291116382063916e-06, "epoch": 1.258569299552906, "percentage": 25.17, "elapsed_time": "0:22:10", "remaining_time": "1:05:56", "throughput": 5198.47, "total_tokens": 6918144} {"current_steps": 1690, "total_steps": 6710, "loss": 0.6757, "lr": 2.128695489332984e-06, "epoch": 1.2593144560357676, "percentage": 25.19, "elapsed_time": "0:22:11", "remaining_time": "1:05:55", "throughput": 5198.5, "total_tokens": 6922240} {"current_steps": 1691, "total_steps": 6710, "loss": 0.8283, "lr": 2.1282791478432517e-06, "epoch": 1.260059612518629, "percentage": 25.2, "elapsed_time": "0:22:12", "remaining_time": "1:05:54", "throughput": 5198.52, "total_tokens": 6926336} {"current_steps": 1692, "total_steps": 6710, "loss": 0.7841, "lr": 2.127862613828458e-06, "epoch": 1.2608047690014903, "percentage": 25.22, "elapsed_time": "0:22:13", "remaining_time": "1:05:53", "throughput": 5198.55, "total_tokens": 6930432} {"current_steps": 1693, "total_steps": 6710, "loss": 0.9732, "lr": 2.127445887379911e-06, "epoch": 1.2615499254843516, "percentage": 25.23, "elapsed_time": "0:22:13", "remaining_time": "1:05:52", "throughput": 5198.58, "total_tokens": 6934528} {"current_steps": 1694, "total_steps": 6710, "loss": 0.7823, "lr": 2.12702896858896e-06, "epoch": 1.2622950819672132, "percentage": 25.25, "elapsed_time": "0:22:14", "remaining_time": "1:05:52", "throughput": 5198.6, "total_tokens": 6938624} {"current_steps": 1695, "total_steps": 6710, "loss": 1.0662, "lr": 2.1266118575469967e-06, "epoch": 1.2630402384500745, "percentage": 25.26, "elapsed_time": "0:22:15", "remaining_time": "1:05:51", "throughput": 5198.62, "total_tokens": 6942720} {"current_steps": 1696, "total_steps": 6710, "loss": 0.8921, "lr": 2.1261945543454544e-06, "epoch": 1.2637853949329358, "percentage": 25.28, "elapsed_time": "0:22:16", "remaining_time": "1:05:50", "throughput": 5198.65, "total_tokens": 6946816} {"current_steps": 1697, "total_steps": 6710, "loss": 0.9767, "lr": 2.1257770590758094e-06, "epoch": 1.2645305514157974, "percentage": 25.29, "elapsed_time": "0:22:17", "remaining_time": "1:05:49", "throughput": 5198.67, "total_tokens": 6950912} {"current_steps": 1698, "total_steps": 6710, "loss": 0.8518, "lr": 2.125359371829579e-06, "epoch": 1.2652757078986587, "percentage": 25.31, "elapsed_time": "0:22:17", "remaining_time": "1:05:48", "throughput": 5198.65, "total_tokens": 6955008} {"current_steps": 1699, "total_steps": 6710, "loss": 0.9527, "lr": 2.1249414926983244e-06, "epoch": 1.26602086438152, "percentage": 25.32, "elapsed_time": "0:22:18", "remaining_time": "1:05:48", "throughput": 5198.67, "total_tokens": 6959104} {"current_steps": 1700, "total_steps": 6710, "loss": 0.9239, "lr": 2.1245234217736463e-06, "epoch": 1.2667660208643814, "percentage": 25.34, "elapsed_time": "0:22:19", "remaining_time": "1:05:47", "throughput": 5198.69, "total_tokens": 6963200} {"current_steps": 1701, "total_steps": 6710, "loss": 0.6991, "lr": 2.1241051591471897e-06, "epoch": 1.267511177347243, "percentage": 25.35, "elapsed_time": "0:22:20", "remaining_time": "1:05:46", "throughput": 5198.71, "total_tokens": 6967296} {"current_steps": 1702, "total_steps": 6710, "loss": 0.8355, "lr": 2.1236867049106406e-06, "epoch": 1.2682563338301043, "percentage": 25.37, "elapsed_time": "0:22:20", "remaining_time": "1:05:45", "throughput": 5198.72, "total_tokens": 6971392} {"current_steps": 1703, "total_steps": 6710, "loss": 0.8313, "lr": 2.1232680591557274e-06, "epoch": 1.2690014903129656, "percentage": 25.38, "elapsed_time": "0:22:21", "remaining_time": "1:05:44", "throughput": 5198.74, "total_tokens": 6975488} {"current_steps": 1704, "total_steps": 6710, "loss": 0.9172, "lr": 2.1228492219742196e-06, "epoch": 1.2697466467958272, "percentage": 25.39, "elapsed_time": "0:22:22", "remaining_time": "1:05:44", "throughput": 5198.76, "total_tokens": 6979584} {"current_steps": 1705, "total_steps": 6710, "loss": 0.77, "lr": 2.1224301934579292e-06, "epoch": 1.2704918032786885, "percentage": 25.41, "elapsed_time": "0:22:23", "remaining_time": "1:05:43", "throughput": 5198.78, "total_tokens": 6983680} {"current_steps": 1706, "total_steps": 6710, "loss": 0.7985, "lr": 2.1220109736987116e-06, "epoch": 1.2712369597615498, "percentage": 25.42, "elapsed_time": "0:22:24", "remaining_time": "1:05:42", "throughput": 5198.78, "total_tokens": 6987776} {"current_steps": 1707, "total_steps": 6710, "loss": 0.9528, "lr": 2.1215915627884613e-06, "epoch": 1.2719821162444114, "percentage": 25.44, "elapsed_time": "0:22:24", "remaining_time": "1:05:41", "throughput": 5198.81, "total_tokens": 6991872} {"current_steps": 1708, "total_steps": 6710, "loss": 0.7585, "lr": 2.1211719608191173e-06, "epoch": 1.2727272727272727, "percentage": 25.45, "elapsed_time": "0:22:25", "remaining_time": "1:05:40", "throughput": 5198.82, "total_tokens": 6995968} {"current_steps": 1709, "total_steps": 6710, "loss": 0.7919, "lr": 2.120752167882658e-06, "epoch": 1.273472429210134, "percentage": 25.47, "elapsed_time": "0:22:26", "remaining_time": "1:05:40", "throughput": 5198.85, "total_tokens": 7000064} {"current_steps": 1710, "total_steps": 6710, "loss": 0.6678, "lr": 2.120332184071106e-06, "epoch": 1.2742175856929956, "percentage": 25.48, "elapsed_time": "0:22:27", "remaining_time": "1:05:39", "throughput": 5198.87, "total_tokens": 7004160} {"current_steps": 1711, "total_steps": 6710, "loss": 0.8287, "lr": 2.1199120094765247e-06, "epoch": 1.274962742175857, "percentage": 25.5, "elapsed_time": "0:22:28", "remaining_time": "1:05:38", "throughput": 5198.89, "total_tokens": 7008256} {"current_steps": 1712, "total_steps": 6710, "loss": 0.6469, "lr": 2.119491644191019e-06, "epoch": 1.2757078986587183, "percentage": 25.51, "elapsed_time": "0:22:28", "remaining_time": "1:05:37", "throughput": 5198.88, "total_tokens": 7012352} {"current_steps": 1713, "total_steps": 6710, "loss": 0.6906, "lr": 2.1190710883067364e-06, "epoch": 1.2764530551415798, "percentage": 25.53, "elapsed_time": "0:22:29", "remaining_time": "1:05:36", "throughput": 5198.91, "total_tokens": 7016448} {"current_steps": 1714, "total_steps": 6710, "loss": 0.7775, "lr": 2.1186503419158657e-06, "epoch": 1.2771982116244411, "percentage": 25.54, "elapsed_time": "0:22:30", "remaining_time": "1:05:36", "throughput": 5198.9, "total_tokens": 7020544} {"current_steps": 1715, "total_steps": 6710, "loss": 0.6812, "lr": 2.1182294051106366e-06, "epoch": 1.2779433681073025, "percentage": 25.56, "elapsed_time": "0:22:31", "remaining_time": "1:05:35", "throughput": 5198.9, "total_tokens": 7024640} {"current_steps": 1716, "total_steps": 6710, "loss": 0.7998, "lr": 2.117808277983323e-06, "epoch": 1.278688524590164, "percentage": 25.57, "elapsed_time": "0:22:31", "remaining_time": "1:05:34", "throughput": 5198.93, "total_tokens": 7028736} {"current_steps": 1717, "total_steps": 6710, "loss": 0.6957, "lr": 2.1173869606262377e-06, "epoch": 1.2794336810730254, "percentage": 25.59, "elapsed_time": "0:22:32", "remaining_time": "1:05:33", "throughput": 5198.96, "total_tokens": 7032832} {"current_steps": 1718, "total_steps": 6710, "loss": 0.5105, "lr": 2.1169654531317367e-06, "epoch": 1.2801788375558867, "percentage": 25.6, "elapsed_time": "0:22:33", "remaining_time": "1:05:32", "throughput": 5198.98, "total_tokens": 7036928} {"current_steps": 1719, "total_steps": 6710, "loss": 0.8779, "lr": 2.116543755592218e-06, "epoch": 1.2809239940387482, "percentage": 25.62, "elapsed_time": "0:22:34", "remaining_time": "1:05:32", "throughput": 5199.02, "total_tokens": 7041024} {"current_steps": 1720, "total_steps": 6710, "loss": 0.9793, "lr": 2.1161218681001206e-06, "epoch": 1.2816691505216096, "percentage": 25.63, "elapsed_time": "0:22:35", "remaining_time": "1:05:31", "throughput": 5199.04, "total_tokens": 7045120} {"current_steps": 1721, "total_steps": 6710, "loss": 0.6913, "lr": 2.115699790747925e-06, "epoch": 1.282414307004471, "percentage": 25.65, "elapsed_time": "0:22:35", "remaining_time": "1:05:30", "throughput": 5199.07, "total_tokens": 7049216} {"current_steps": 1722, "total_steps": 6710, "loss": 0.6254, "lr": 2.1152775236281535e-06, "epoch": 1.2831594634873325, "percentage": 25.66, "elapsed_time": "0:22:36", "remaining_time": "1:05:29", "throughput": 5199.1, "total_tokens": 7053312} {"current_steps": 1723, "total_steps": 6710, "loss": 0.7801, "lr": 2.11485506683337e-06, "epoch": 1.2839046199701938, "percentage": 25.68, "elapsed_time": "0:22:37", "remaining_time": "1:05:28", "throughput": 5199.13, "total_tokens": 7057408} {"current_steps": 1724, "total_steps": 6710, "loss": 0.6497, "lr": 2.1144324204561805e-06, "epoch": 1.2846497764530551, "percentage": 25.69, "elapsed_time": "0:22:38", "remaining_time": "1:05:28", "throughput": 5199.15, "total_tokens": 7061504} {"current_steps": 1725, "total_steps": 6710, "loss": 0.7983, "lr": 2.1140095845892317e-06, "epoch": 1.2853949329359167, "percentage": 25.71, "elapsed_time": "0:22:38", "remaining_time": "1:05:27", "throughput": 5199.18, "total_tokens": 7065600} {"current_steps": 1726, "total_steps": 6710, "loss": 0.9725, "lr": 2.1135865593252124e-06, "epoch": 1.286140089418778, "percentage": 25.72, "elapsed_time": "0:22:39", "remaining_time": "1:05:26", "throughput": 5199.21, "total_tokens": 7069696} {"current_steps": 1727, "total_steps": 6710, "loss": 0.4756, "lr": 2.1131633447568527e-06, "epoch": 1.2868852459016393, "percentage": 25.74, "elapsed_time": "0:22:40", "remaining_time": "1:05:25", "throughput": 5199.23, "total_tokens": 7073792} {"current_steps": 1728, "total_steps": 6710, "loss": 0.7014, "lr": 2.1127399409769243e-06, "epoch": 1.2876304023845009, "percentage": 25.75, "elapsed_time": "0:22:41", "remaining_time": "1:05:24", "throughput": 5199.26, "total_tokens": 7077888} {"current_steps": 1729, "total_steps": 6710, "loss": 0.7319, "lr": 2.1123163480782405e-06, "epoch": 1.2883755588673622, "percentage": 25.77, "elapsed_time": "0:22:42", "remaining_time": "1:05:24", "throughput": 5199.29, "total_tokens": 7081984} {"current_steps": 1730, "total_steps": 6710, "loss": 0.79, "lr": 2.1118925661536556e-06, "epoch": 1.2891207153502235, "percentage": 25.78, "elapsed_time": "0:22:42", "remaining_time": "1:05:23", "throughput": 5199.31, "total_tokens": 7086080} {"current_steps": 1731, "total_steps": 6710, "loss": 0.7949, "lr": 2.1114685952960657e-06, "epoch": 1.2898658718330849, "percentage": 25.8, "elapsed_time": "0:22:43", "remaining_time": "1:05:22", "throughput": 5199.34, "total_tokens": 7090176} {"current_steps": 1732, "total_steps": 6710, "loss": 0.7241, "lr": 2.111044435598408e-06, "epoch": 1.2906110283159464, "percentage": 25.81, "elapsed_time": "0:22:44", "remaining_time": "1:05:21", "throughput": 5199.37, "total_tokens": 7094272} {"current_steps": 1733, "total_steps": 6710, "loss": 0.6321, "lr": 2.110620087153662e-06, "epoch": 1.2913561847988078, "percentage": 25.83, "elapsed_time": "0:22:45", "remaining_time": "1:05:20", "throughput": 5199.4, "total_tokens": 7098368} {"current_steps": 1734, "total_steps": 6710, "loss": 0.6636, "lr": 2.110195550054848e-06, "epoch": 1.292101341281669, "percentage": 25.84, "elapsed_time": "0:22:46", "remaining_time": "1:05:19", "throughput": 5199.42, "total_tokens": 7102464} {"current_steps": 1735, "total_steps": 6710, "loss": 0.7383, "lr": 2.109770824395026e-06, "epoch": 1.2928464977645304, "percentage": 25.86, "elapsed_time": "0:22:46", "remaining_time": "1:05:19", "throughput": 5199.45, "total_tokens": 7106560} {"current_steps": 1736, "total_steps": 6710, "loss": 0.8434, "lr": 2.1093459102673005e-06, "epoch": 1.293591654247392, "percentage": 25.87, "elapsed_time": "0:22:47", "remaining_time": "1:05:18", "throughput": 5199.48, "total_tokens": 7110656} {"current_steps": 1737, "total_steps": 6710, "loss": 0.5901, "lr": 2.1089208077648153e-06, "epoch": 1.2943368107302533, "percentage": 25.89, "elapsed_time": "0:22:48", "remaining_time": "1:05:17", "throughput": 5199.51, "total_tokens": 7114752} {"current_steps": 1738, "total_steps": 6710, "loss": 0.9642, "lr": 2.1084955169807554e-06, "epoch": 1.2950819672131146, "percentage": 25.9, "elapsed_time": "0:22:49", "remaining_time": "1:05:16", "throughput": 5199.54, "total_tokens": 7118848} {"current_steps": 1739, "total_steps": 6710, "loss": 0.9967, "lr": 2.1080700380083485e-06, "epoch": 1.2958271236959762, "percentage": 25.92, "elapsed_time": "0:22:49", "remaining_time": "1:05:15", "throughput": 5199.56, "total_tokens": 7122944} {"current_steps": 1740, "total_steps": 6710, "loss": 0.9752, "lr": 2.107644370940862e-06, "epoch": 1.2965722801788375, "percentage": 25.93, "elapsed_time": "0:22:50", "remaining_time": "1:05:15", "throughput": 5199.58, "total_tokens": 7127040} {"current_steps": 1741, "total_steps": 6710, "loss": 0.9458, "lr": 2.107218515871605e-06, "epoch": 1.2973174366616989, "percentage": 25.95, "elapsed_time": "0:22:51", "remaining_time": "1:05:14", "throughput": 5199.61, "total_tokens": 7131136} {"current_steps": 1742, "total_steps": 6710, "loss": 0.8479, "lr": 2.106792472893928e-06, "epoch": 1.2980625931445604, "percentage": 25.96, "elapsed_time": "0:22:52", "remaining_time": "1:05:13", "throughput": 5199.64, "total_tokens": 7135232} {"current_steps": 1743, "total_steps": 6710, "loss": 0.6524, "lr": 2.1063662421012234e-06, "epoch": 1.2988077496274217, "percentage": 25.98, "elapsed_time": "0:22:53", "remaining_time": "1:05:12", "throughput": 5199.67, "total_tokens": 7139328} {"current_steps": 1744, "total_steps": 6710, "loss": 0.8687, "lr": 2.1059398235869233e-06, "epoch": 1.299552906110283, "percentage": 25.99, "elapsed_time": "0:22:53", "remaining_time": "1:05:11", "throughput": 5199.7, "total_tokens": 7143424} {"current_steps": 1745, "total_steps": 6710, "loss": 1.0127, "lr": 2.105513217444502e-06, "epoch": 1.3002980625931446, "percentage": 26.01, "elapsed_time": "0:22:54", "remaining_time": "1:05:11", "throughput": 5199.73, "total_tokens": 7147520} {"current_steps": 1746, "total_steps": 6710, "loss": 0.7312, "lr": 2.1050864237674745e-06, "epoch": 1.301043219076006, "percentage": 26.02, "elapsed_time": "0:22:55", "remaining_time": "1:05:10", "throughput": 5199.77, "total_tokens": 7151616} {"current_steps": 1747, "total_steps": 6710, "loss": 0.6583, "lr": 2.1046594426493973e-06, "epoch": 1.3017883755588673, "percentage": 26.04, "elapsed_time": "0:22:56", "remaining_time": "1:05:09", "throughput": 5199.77, "total_tokens": 7155712} {"current_steps": 1748, "total_steps": 6710, "loss": 0.5958, "lr": 2.104232274183867e-06, "epoch": 1.3025335320417288, "percentage": 26.05, "elapsed_time": "0:22:56", "remaining_time": "1:05:08", "throughput": 5199.78, "total_tokens": 7159808} {"current_steps": 1749, "total_steps": 6710, "loss": 0.7951, "lr": 2.1038049184645225e-06, "epoch": 1.3032786885245902, "percentage": 26.07, "elapsed_time": "0:22:57", "remaining_time": "1:05:07", "throughput": 5199.79, "total_tokens": 7163904} {"current_steps": 1750, "total_steps": 6710, "loss": 0.8481, "lr": 2.1033773755850434e-06, "epoch": 1.3040238450074515, "percentage": 26.08, "elapsed_time": "0:22:58", "remaining_time": "1:05:07", "throughput": 5199.78, "total_tokens": 7168000} {"current_steps": 1751, "total_steps": 6710, "loss": 0.9515, "lr": 2.1029496456391497e-06, "epoch": 1.304769001490313, "percentage": 26.1, "elapsed_time": "0:22:59", "remaining_time": "1:05:06", "throughput": 5199.73, "total_tokens": 7172096} {"current_steps": 1752, "total_steps": 6710, "loss": 0.6205, "lr": 2.1025217287206034e-06, "epoch": 1.3055141579731744, "percentage": 26.11, "elapsed_time": "0:23:00", "remaining_time": "1:05:05", "throughput": 5199.72, "total_tokens": 7176192} {"current_steps": 1753, "total_steps": 6710, "loss": 0.8949, "lr": 2.102093624923206e-06, "epoch": 1.3062593144560357, "percentage": 26.13, "elapsed_time": "0:23:00", "remaining_time": "1:05:04", "throughput": 5199.71, "total_tokens": 7180288} {"current_steps": 1754, "total_steps": 6710, "loss": 0.8827, "lr": 2.1016653343408024e-06, "epoch": 1.3070044709388973, "percentage": 26.14, "elapsed_time": "0:23:01", "remaining_time": "1:05:04", "throughput": 5199.7, "total_tokens": 7184384} {"current_steps": 1755, "total_steps": 6710, "loss": 0.7502, "lr": 2.1012368570672757e-06, "epoch": 1.3077496274217586, "percentage": 26.15, "elapsed_time": "0:23:02", "remaining_time": "1:05:03", "throughput": 5199.68, "total_tokens": 7188480} {"current_steps": 1756, "total_steps": 6710, "loss": 0.896, "lr": 2.1008081931965513e-06, "epoch": 1.30849478390462, "percentage": 26.17, "elapsed_time": "0:23:03", "remaining_time": "1:05:02", "throughput": 5199.67, "total_tokens": 7192576} {"current_steps": 1757, "total_steps": 6710, "loss": 0.816, "lr": 2.1003793428225957e-06, "epoch": 1.3092399403874815, "percentage": 26.18, "elapsed_time": "0:23:04", "remaining_time": "1:05:01", "throughput": 5199.66, "total_tokens": 7196672} {"current_steps": 1758, "total_steps": 6710, "loss": 0.8379, "lr": 2.099950306039416e-06, "epoch": 1.3099850968703428, "percentage": 26.2, "elapsed_time": "0:23:04", "remaining_time": "1:05:00", "throughput": 5199.65, "total_tokens": 7200768} {"current_steps": 1759, "total_steps": 6710, "loss": 0.6935, "lr": 2.09952108294106e-06, "epoch": 1.3107302533532041, "percentage": 26.21, "elapsed_time": "0:23:05", "remaining_time": "1:05:00", "throughput": 5199.64, "total_tokens": 7204864} {"current_steps": 1760, "total_steps": 6710, "loss": 0.7534, "lr": 2.0990916736216164e-06, "epoch": 1.3114754098360657, "percentage": 26.23, "elapsed_time": "0:23:06", "remaining_time": "1:04:59", "throughput": 5199.62, "total_tokens": 7208960} {"current_steps": 1761, "total_steps": 6710, "loss": 0.9513, "lr": 2.098662078175215e-06, "epoch": 1.312220566318927, "percentage": 26.24, "elapsed_time": "0:23:07", "remaining_time": "1:04:58", "throughput": 5199.61, "total_tokens": 7213056} {"current_steps": 1762, "total_steps": 6710, "loss": 0.556, "lr": 2.0982322966960264e-06, "epoch": 1.3129657228017884, "percentage": 26.26, "elapsed_time": "0:23:08", "remaining_time": "1:04:57", "throughput": 5199.59, "total_tokens": 7217152} {"current_steps": 1763, "total_steps": 6710, "loss": 0.6825, "lr": 2.0978023292782613e-06, "epoch": 1.31371087928465, "percentage": 26.27, "elapsed_time": "0:23:08", "remaining_time": "1:04:57", "throughput": 5199.57, "total_tokens": 7221248} {"current_steps": 1764, "total_steps": 6710, "loss": 0.5707, "lr": 2.0973721760161714e-06, "epoch": 1.3144560357675112, "percentage": 26.29, "elapsed_time": "0:23:09", "remaining_time": "1:04:56", "throughput": 5199.55, "total_tokens": 7225344} {"current_steps": 1765, "total_steps": 6710, "loss": 0.6204, "lr": 2.09694183700405e-06, "epoch": 1.3152011922503726, "percentage": 26.3, "elapsed_time": "0:23:10", "remaining_time": "1:04:55", "throughput": 5199.52, "total_tokens": 7229440} {"current_steps": 1766, "total_steps": 6710, "loss": 0.6249, "lr": 2.0965113123362303e-06, "epoch": 1.315946348733234, "percentage": 26.32, "elapsed_time": "0:23:11", "remaining_time": "1:04:54", "throughput": 5199.51, "total_tokens": 7233536} {"current_steps": 1767, "total_steps": 6710, "loss": 0.5253, "lr": 2.096080602107086e-06, "epoch": 1.3166915052160955, "percentage": 26.33, "elapsed_time": "0:23:12", "remaining_time": "1:04:53", "throughput": 5199.44, "total_tokens": 7237632} {"current_steps": 1768, "total_steps": 6710, "loss": 0.5797, "lr": 2.095649706411032e-06, "epoch": 1.3174366616989568, "percentage": 26.35, "elapsed_time": "0:23:12", "remaining_time": "1:04:53", "throughput": 5199.41, "total_tokens": 7241728} {"current_steps": 1769, "total_steps": 6710, "loss": 1.0169, "lr": 2.0952186253425244e-06, "epoch": 1.3181818181818181, "percentage": 26.36, "elapsed_time": "0:23:13", "remaining_time": "1:04:52", "throughput": 5199.39, "total_tokens": 7245824} {"current_steps": 1770, "total_steps": 6710, "loss": 0.8783, "lr": 2.0947873589960586e-06, "epoch": 1.3189269746646795, "percentage": 26.38, "elapsed_time": "0:23:14", "remaining_time": "1:04:51", "throughput": 5199.38, "total_tokens": 7249920} {"current_steps": 1771, "total_steps": 6710, "loss": 0.8094, "lr": 2.0943559074661714e-06, "epoch": 1.319672131147541, "percentage": 26.39, "elapsed_time": "0:23:15", "remaining_time": "1:04:50", "throughput": 5199.34, "total_tokens": 7254016} {"current_steps": 1772, "total_steps": 6710, "loss": 1.0997, "lr": 2.09392427084744e-06, "epoch": 1.3204172876304023, "percentage": 26.41, "elapsed_time": "0:23:15", "remaining_time": "1:04:50", "throughput": 5199.33, "total_tokens": 7258112} {"current_steps": 1773, "total_steps": 6710, "loss": 0.7451, "lr": 2.093492449234482e-06, "epoch": 1.3211624441132637, "percentage": 26.42, "elapsed_time": "0:23:16", "remaining_time": "1:04:49", "throughput": 5199.33, "total_tokens": 7262208} {"current_steps": 1774, "total_steps": 6710, "loss": 1.1393, "lr": 2.0930604427219565e-06, "epoch": 1.3219076005961252, "percentage": 26.44, "elapsed_time": "0:23:17", "remaining_time": "1:04:48", "throughput": 5199.31, "total_tokens": 7266304} {"current_steps": 1775, "total_steps": 6710, "loss": 0.8294, "lr": 2.0926282514045618e-06, "epoch": 1.3226527570789866, "percentage": 26.45, "elapsed_time": "0:23:18", "remaining_time": "1:04:47", "throughput": 5199.3, "total_tokens": 7270400} {"current_steps": 1776, "total_steps": 6710, "loss": 0.584, "lr": 2.0921958753770373e-06, "epoch": 1.3233979135618479, "percentage": 26.47, "elapsed_time": "0:23:19", "remaining_time": "1:04:46", "throughput": 5199.31, "total_tokens": 7274496} {"current_steps": 1777, "total_steps": 6710, "loss": 0.7814, "lr": 2.0917633147341634e-06, "epoch": 1.3241430700447094, "percentage": 26.48, "elapsed_time": "0:23:19", "remaining_time": "1:04:46", "throughput": 5199.3, "total_tokens": 7278592} {"current_steps": 1778, "total_steps": 6710, "loss": 0.9582, "lr": 2.09133056957076e-06, "epoch": 1.3248882265275708, "percentage": 26.5, "elapsed_time": "0:23:20", "remaining_time": "1:04:45", "throughput": 5199.28, "total_tokens": 7282688} {"current_steps": 1779, "total_steps": 6710, "loss": 0.7912, "lr": 2.090897639981688e-06, "epoch": 1.325633383010432, "percentage": 26.51, "elapsed_time": "0:23:21", "remaining_time": "1:04:44", "throughput": 5199.26, "total_tokens": 7286784} {"current_steps": 1780, "total_steps": 6710, "loss": 0.873, "lr": 2.090464526061849e-06, "epoch": 1.3263785394932937, "percentage": 26.53, "elapsed_time": "0:23:22", "remaining_time": "1:04:43", "throughput": 5199.22, "total_tokens": 7290880} {"current_steps": 1781, "total_steps": 6710, "loss": 0.6401, "lr": 2.0900312279061844e-06, "epoch": 1.327123695976155, "percentage": 26.54, "elapsed_time": "0:23:23", "remaining_time": "1:04:43", "throughput": 5199.21, "total_tokens": 7294976} {"current_steps": 1782, "total_steps": 6710, "loss": 0.7722, "lr": 2.0895977456096766e-06, "epoch": 1.3278688524590163, "percentage": 26.56, "elapsed_time": "0:23:23", "remaining_time": "1:04:42", "throughput": 5199.18, "total_tokens": 7299072} {"current_steps": 1783, "total_steps": 6710, "loss": 0.7975, "lr": 2.089164079267347e-06, "epoch": 1.3286140089418779, "percentage": 26.57, "elapsed_time": "0:23:24", "remaining_time": "1:04:41", "throughput": 5199.15, "total_tokens": 7303168} {"current_steps": 1784, "total_steps": 6710, "loss": 0.8267, "lr": 2.0887302289742594e-06, "epoch": 1.3293591654247392, "percentage": 26.59, "elapsed_time": "0:23:25", "remaining_time": "1:04:40", "throughput": 5199.12, "total_tokens": 7307264} {"current_steps": 1785, "total_steps": 6710, "loss": 0.8456, "lr": 2.0882961948255166e-06, "epoch": 1.3301043219076005, "percentage": 26.6, "elapsed_time": "0:23:26", "remaining_time": "1:04:40", "throughput": 5199.1, "total_tokens": 7311360} {"current_steps": 1786, "total_steps": 6710, "loss": 0.9644, "lr": 2.087861976916262e-06, "epoch": 1.330849478390462, "percentage": 26.62, "elapsed_time": "0:23:27", "remaining_time": "1:04:39", "throughput": 5199.09, "total_tokens": 7315456} {"current_steps": 1787, "total_steps": 6710, "loss": 0.7009, "lr": 2.087427575341679e-06, "epoch": 1.3315946348733234, "percentage": 26.63, "elapsed_time": "0:23:27", "remaining_time": "1:04:38", "throughput": 5199.07, "total_tokens": 7319552} {"current_steps": 1788, "total_steps": 6710, "loss": 0.6899, "lr": 2.0869929901969914e-06, "epoch": 1.3323397913561847, "percentage": 26.65, "elapsed_time": "0:23:28", "remaining_time": "1:04:37", "throughput": 5199.05, "total_tokens": 7323648} {"current_steps": 1789, "total_steps": 6710, "loss": 0.8562, "lr": 2.0865582215774643e-06, "epoch": 1.3330849478390463, "percentage": 26.66, "elapsed_time": "0:23:29", "remaining_time": "1:04:36", "throughput": 5199.02, "total_tokens": 7327744} {"current_steps": 1790, "total_steps": 6710, "loss": 0.8324, "lr": 2.0861232695784014e-06, "epoch": 1.3338301043219076, "percentage": 26.68, "elapsed_time": "0:23:30", "remaining_time": "1:04:36", "throughput": 5198.99, "total_tokens": 7331840} {"current_steps": 1791, "total_steps": 6710, "loss": 0.8884, "lr": 2.0856881342951467e-06, "epoch": 1.334575260804769, "percentage": 26.69, "elapsed_time": "0:23:31", "remaining_time": "1:04:35", "throughput": 5198.96, "total_tokens": 7335936} {"current_steps": 1792, "total_steps": 6710, "loss": 0.7484, "lr": 2.0852528158230863e-06, "epoch": 1.3353204172876305, "percentage": 26.71, "elapsed_time": "0:23:31", "remaining_time": "1:04:34", "throughput": 5198.94, "total_tokens": 7340032} {"current_steps": 1793, "total_steps": 6710, "loss": 0.7244, "lr": 2.084817314257644e-06, "epoch": 1.3360655737704918, "percentage": 26.72, "elapsed_time": "0:23:32", "remaining_time": "1:04:33", "throughput": 5198.91, "total_tokens": 7344128} {"current_steps": 1794, "total_steps": 6710, "loss": 0.7846, "lr": 2.084381629694286e-06, "epoch": 1.3368107302533532, "percentage": 26.74, "elapsed_time": "0:23:33", "remaining_time": "1:04:33", "throughput": 5198.9, "total_tokens": 7348224} {"current_steps": 1795, "total_steps": 6710, "loss": 1.0558, "lr": 2.0839457622285158e-06, "epoch": 1.3375558867362147, "percentage": 26.75, "elapsed_time": "0:23:34", "remaining_time": "1:04:32", "throughput": 5198.88, "total_tokens": 7352320} {"current_steps": 1796, "total_steps": 6710, "loss": 0.8539, "lr": 2.0835097119558807e-06, "epoch": 1.338301043219076, "percentage": 26.77, "elapsed_time": "0:23:35", "remaining_time": "1:04:31", "throughput": 5198.87, "total_tokens": 7356416} {"current_steps": 1797, "total_steps": 6710, "loss": 0.6881, "lr": 2.083073478971964e-06, "epoch": 1.3390461997019374, "percentage": 26.78, "elapsed_time": "0:23:35", "remaining_time": "1:04:30", "throughput": 5198.86, "total_tokens": 7360512} {"current_steps": 1798, "total_steps": 6710, "loss": 1.0265, "lr": 2.0826370633723926e-06, "epoch": 1.339791356184799, "percentage": 26.8, "elapsed_time": "0:23:36", "remaining_time": "1:04:29", "throughput": 5198.85, "total_tokens": 7364608} {"current_steps": 1799, "total_steps": 6710, "loss": 0.8868, "lr": 2.082200465252831e-06, "epoch": 1.3405365126676603, "percentage": 26.81, "elapsed_time": "0:23:37", "remaining_time": "1:04:29", "throughput": 5198.85, "total_tokens": 7368704} {"current_steps": 1800, "total_steps": 6710, "loss": 0.7198, "lr": 2.081763684708985e-06, "epoch": 1.3412816691505216, "percentage": 26.83, "elapsed_time": "0:23:38", "remaining_time": "1:04:28", "throughput": 5198.84, "total_tokens": 7372800} {"current_steps": 1801, "total_steps": 6710, "loss": 0.6231, "lr": 2.0813267218366e-06, "epoch": 1.342026825633383, "percentage": 26.84, "elapsed_time": "0:23:38", "remaining_time": "1:04:27", "throughput": 5198.83, "total_tokens": 7376896} {"current_steps": 1802, "total_steps": 6710, "loss": 0.8079, "lr": 2.0808895767314614e-06, "epoch": 1.3427719821162445, "percentage": 26.86, "elapsed_time": "0:23:39", "remaining_time": "1:04:26", "throughput": 5198.83, "total_tokens": 7380992} {"current_steps": 1803, "total_steps": 6710, "loss": 0.7523, "lr": 2.0804522494893946e-06, "epoch": 1.3435171385991058, "percentage": 26.87, "elapsed_time": "0:23:40", "remaining_time": "1:04:26", "throughput": 5198.81, "total_tokens": 7385088} {"current_steps": 1804, "total_steps": 6710, "loss": 0.6134, "lr": 2.080014740206265e-06, "epoch": 1.3442622950819672, "percentage": 26.89, "elapsed_time": "0:23:41", "remaining_time": "1:04:25", "throughput": 5198.8, "total_tokens": 7389184} {"current_steps": 1805, "total_steps": 6710, "loss": 0.7481, "lr": 2.079577048977977e-06, "epoch": 1.3450074515648285, "percentage": 26.9, "elapsed_time": "0:23:42", "remaining_time": "1:04:24", "throughput": 5198.78, "total_tokens": 7393280} {"current_steps": 1806, "total_steps": 6710, "loss": 0.6915, "lr": 2.0791391759004765e-06, "epoch": 1.34575260804769, "percentage": 26.92, "elapsed_time": "0:23:42", "remaining_time": "1:04:23", "throughput": 5198.76, "total_tokens": 7397376} {"current_steps": 1807, "total_steps": 6710, "loss": 0.7923, "lr": 2.078701121069748e-06, "epoch": 1.3464977645305514, "percentage": 26.93, "elapsed_time": "0:23:43", "remaining_time": "1:04:22", "throughput": 5198.75, "total_tokens": 7401472} {"current_steps": 1808, "total_steps": 6710, "loss": 0.9189, "lr": 2.078262884581816e-06, "epoch": 1.3472429210134127, "percentage": 26.94, "elapsed_time": "0:23:44", "remaining_time": "1:04:22", "throughput": 5198.75, "total_tokens": 7405568} {"current_steps": 1809, "total_steps": 6710, "loss": 0.8063, "lr": 2.077824466532746e-06, "epoch": 1.3479880774962743, "percentage": 26.96, "elapsed_time": "0:23:45", "remaining_time": "1:04:21", "throughput": 5198.74, "total_tokens": 7409664} {"current_steps": 1810, "total_steps": 6710, "loss": 0.7168, "lr": 2.077385867018641e-06, "epoch": 1.3487332339791356, "percentage": 26.97, "elapsed_time": "0:23:46", "remaining_time": "1:04:20", "throughput": 5198.73, "total_tokens": 7413760} {"current_steps": 1811, "total_steps": 6710, "loss": 0.9537, "lr": 2.0769470861356463e-06, "epoch": 1.349478390461997, "percentage": 26.99, "elapsed_time": "0:23:46", "remaining_time": "1:04:19", "throughput": 5198.72, "total_tokens": 7417856} {"current_steps": 1812, "total_steps": 6710, "loss": 0.7761, "lr": 2.076508123979945e-06, "epoch": 1.3502235469448585, "percentage": 27.0, "elapsed_time": "0:23:47", "remaining_time": "1:04:19", "throughput": 5198.71, "total_tokens": 7421952} {"current_steps": 1813, "total_steps": 6710, "loss": 0.9399, "lr": 2.0760689806477617e-06, "epoch": 1.3509687034277198, "percentage": 27.02, "elapsed_time": "0:23:48", "remaining_time": "1:04:18", "throughput": 5198.7, "total_tokens": 7426048} {"current_steps": 1814, "total_steps": 6710, "loss": 0.7927, "lr": 2.0756296562353588e-06, "epoch": 1.3517138599105811, "percentage": 27.03, "elapsed_time": "0:23:49", "remaining_time": "1:04:17", "throughput": 5198.7, "total_tokens": 7430144} {"current_steps": 1815, "total_steps": 6710, "loss": 0.6576, "lr": 2.07519015083904e-06, "epoch": 1.3524590163934427, "percentage": 27.05, "elapsed_time": "0:23:50", "remaining_time": "1:04:16", "throughput": 5198.7, "total_tokens": 7434240} {"current_steps": 1816, "total_steps": 6710, "loss": 0.674, "lr": 2.0747504645551474e-06, "epoch": 1.353204172876304, "percentage": 27.06, "elapsed_time": "0:23:50", "remaining_time": "1:04:15", "throughput": 5198.7, "total_tokens": 7438336} {"current_steps": 1817, "total_steps": 6710, "loss": 0.8149, "lr": 2.0743105974800644e-06, "epoch": 1.3539493293591653, "percentage": 27.08, "elapsed_time": "0:23:51", "remaining_time": "1:04:15", "throughput": 5198.68, "total_tokens": 7442432} {"current_steps": 1818, "total_steps": 6710, "loss": 0.5288, "lr": 2.0738705497102117e-06, "epoch": 1.354694485842027, "percentage": 27.09, "elapsed_time": "0:23:52", "remaining_time": "1:04:14", "throughput": 5198.68, "total_tokens": 7446528} {"current_steps": 1819, "total_steps": 6710, "loss": 0.8162, "lr": 2.0734303213420515e-06, "epoch": 1.3554396423248882, "percentage": 27.11, "elapsed_time": "0:23:53", "remaining_time": "1:04:13", "throughput": 5198.67, "total_tokens": 7450624} {"current_steps": 1820, "total_steps": 6710, "loss": 0.8337, "lr": 2.0729899124720855e-06, "epoch": 1.3561847988077496, "percentage": 27.12, "elapsed_time": "0:23:53", "remaining_time": "1:04:12", "throughput": 5198.66, "total_tokens": 7454720} {"current_steps": 1821, "total_steps": 6710, "loss": 1.0083, "lr": 2.0725493231968534e-06, "epoch": 1.3569299552906111, "percentage": 27.14, "elapsed_time": "0:23:54", "remaining_time": "1:04:12", "throughput": 5198.66, "total_tokens": 7458816} {"current_steps": 1822, "total_steps": 6710, "loss": 0.8933, "lr": 2.0721085536129364e-06, "epoch": 1.3576751117734724, "percentage": 27.15, "elapsed_time": "0:23:55", "remaining_time": "1:04:11", "throughput": 5198.64, "total_tokens": 7462912} {"current_steps": 1823, "total_steps": 6710, "loss": 0.7055, "lr": 2.0716676038169543e-06, "epoch": 1.3584202682563338, "percentage": 27.17, "elapsed_time": "0:23:56", "remaining_time": "1:04:10", "throughput": 5198.63, "total_tokens": 7467008} {"current_steps": 1824, "total_steps": 6710, "loss": 0.8861, "lr": 2.0712264739055663e-06, "epoch": 1.3591654247391953, "percentage": 27.18, "elapsed_time": "0:23:57", "remaining_time": "1:04:09", "throughput": 5198.63, "total_tokens": 7471104} {"current_steps": 1825, "total_steps": 6710, "loss": 0.7286, "lr": 2.070785163975471e-06, "epoch": 1.3599105812220567, "percentage": 27.2, "elapsed_time": "0:23:57", "remaining_time": "1:04:08", "throughput": 5198.62, "total_tokens": 7475200} {"current_steps": 1826, "total_steps": 6710, "loss": 0.9796, "lr": 2.070343674123407e-06, "epoch": 1.360655737704918, "percentage": 27.21, "elapsed_time": "0:23:58", "remaining_time": "1:04:08", "throughput": 5198.61, "total_tokens": 7479296} {"current_steps": 1827, "total_steps": 6710, "loss": 0.9288, "lr": 2.069902004446151e-06, "epoch": 1.3614008941877795, "percentage": 27.23, "elapsed_time": "0:23:59", "remaining_time": "1:04:07", "throughput": 5198.58, "total_tokens": 7483392} {"current_steps": 1828, "total_steps": 6710, "loss": 1.0561, "lr": 2.069460155040522e-06, "epoch": 1.3621460506706409, "percentage": 27.24, "elapsed_time": "0:24:00", "remaining_time": "1:04:06", "throughput": 5198.54, "total_tokens": 7487488} {"current_steps": 1829, "total_steps": 6710, "loss": 0.7046, "lr": 2.069018126003375e-06, "epoch": 1.3628912071535022, "percentage": 27.26, "elapsed_time": "0:24:01", "remaining_time": "1:04:05", "throughput": 5198.52, "total_tokens": 7491584} {"current_steps": 1830, "total_steps": 6710, "loss": 0.952, "lr": 2.0685759174316067e-06, "epoch": 1.3636363636363638, "percentage": 27.27, "elapsed_time": "0:24:01", "remaining_time": "1:04:05", "throughput": 5198.5, "total_tokens": 7495680} {"current_steps": 1831, "total_steps": 6710, "loss": 0.6904, "lr": 2.068133529422152e-06, "epoch": 1.364381520119225, "percentage": 27.29, "elapsed_time": "0:24:02", "remaining_time": "1:04:04", "throughput": 5198.47, "total_tokens": 7499776} {"current_steps": 1832, "total_steps": 6710, "loss": 0.9648, "lr": 2.0676909620719857e-06, "epoch": 1.3651266766020864, "percentage": 27.3, "elapsed_time": "0:24:03", "remaining_time": "1:04:03", "throughput": 5198.44, "total_tokens": 7503872} {"current_steps": 1833, "total_steps": 6710, "loss": 0.9323, "lr": 2.0672482154781217e-06, "epoch": 1.365871833084948, "percentage": 27.32, "elapsed_time": "0:24:04", "remaining_time": "1:04:02", "throughput": 5198.42, "total_tokens": 7507968} {"current_steps": 1834, "total_steps": 6710, "loss": 0.7238, "lr": 2.0668052897376127e-06, "epoch": 1.3666169895678093, "percentage": 27.33, "elapsed_time": "0:24:05", "remaining_time": "1:04:01", "throughput": 5198.41, "total_tokens": 7512064} {"current_steps": 1835, "total_steps": 6710, "loss": 0.8859, "lr": 2.0663621849475523e-06, "epoch": 1.3673621460506706, "percentage": 27.35, "elapsed_time": "0:24:05", "remaining_time": "1:04:01", "throughput": 5198.37, "total_tokens": 7516160} {"current_steps": 1836, "total_steps": 6710, "loss": 0.6447, "lr": 2.0659189012050716e-06, "epoch": 1.368107302533532, "percentage": 27.36, "elapsed_time": "0:24:06", "remaining_time": "1:04:00", "throughput": 5198.36, "total_tokens": 7520256} {"current_steps": 1837, "total_steps": 6710, "loss": 0.7783, "lr": 2.0654754386073417e-06, "epoch": 1.3688524590163935, "percentage": 27.38, "elapsed_time": "0:24:07", "remaining_time": "1:03:59", "throughput": 5198.35, "total_tokens": 7524352} {"current_steps": 1838, "total_steps": 6710, "loss": 0.7708, "lr": 2.0650317972515723e-06, "epoch": 1.3695976154992549, "percentage": 27.39, "elapsed_time": "0:24:08", "remaining_time": "1:03:58", "throughput": 5198.33, "total_tokens": 7528448} {"current_steps": 1839, "total_steps": 6710, "loss": 0.9122, "lr": 2.064587977235013e-06, "epoch": 1.3703427719821162, "percentage": 27.41, "elapsed_time": "0:24:09", "remaining_time": "1:03:58", "throughput": 5198.32, "total_tokens": 7532544} {"current_steps": 1840, "total_steps": 6710, "loss": 0.961, "lr": 2.064143978654953e-06, "epoch": 1.3710879284649775, "percentage": 27.42, "elapsed_time": "0:24:09", "remaining_time": "1:03:57", "throughput": 5198.28, "total_tokens": 7536640} {"current_steps": 1841, "total_steps": 6710, "loss": 0.8772, "lr": 2.063699801608719e-06, "epoch": 1.371833084947839, "percentage": 27.44, "elapsed_time": "0:24:10", "remaining_time": "1:03:56", "throughput": 5198.28, "total_tokens": 7540736} {"current_steps": 1842, "total_steps": 6710, "loss": 0.9022, "lr": 2.0632554461936776e-06, "epoch": 1.3725782414307004, "percentage": 27.45, "elapsed_time": "0:24:11", "remaining_time": "1:03:55", "throughput": 5198.27, "total_tokens": 7544832} {"current_steps": 1843, "total_steps": 6710, "loss": 0.7817, "lr": 2.062810912507236e-06, "epoch": 1.3733233979135617, "percentage": 27.47, "elapsed_time": "0:24:12", "remaining_time": "1:03:54", "throughput": 5198.25, "total_tokens": 7548928} {"current_steps": 1844, "total_steps": 6710, "loss": 0.8723, "lr": 2.062366200646838e-06, "epoch": 1.3740685543964233, "percentage": 27.48, "elapsed_time": "0:24:12", "remaining_time": "1:03:54", "throughput": 5198.24, "total_tokens": 7553024} {"current_steps": 1845, "total_steps": 6710, "loss": 0.6757, "lr": 2.0619213107099683e-06, "epoch": 1.3748137108792846, "percentage": 27.5, "elapsed_time": "0:24:13", "remaining_time": "1:03:53", "throughput": 5198.24, "total_tokens": 7557120} {"current_steps": 1846, "total_steps": 6710, "loss": 0.9755, "lr": 2.0614762427941494e-06, "epoch": 1.375558867362146, "percentage": 27.51, "elapsed_time": "0:24:14", "remaining_time": "1:03:52", "throughput": 5198.24, "total_tokens": 7561216} {"current_steps": 1847, "total_steps": 6710, "loss": 0.7674, "lr": 2.061030996996944e-06, "epoch": 1.3763040238450075, "percentage": 27.53, "elapsed_time": "0:24:15", "remaining_time": "1:03:51", "throughput": 5198.25, "total_tokens": 7565312} {"current_steps": 1848, "total_steps": 6710, "loss": 0.7393, "lr": 2.0605855734159523e-06, "epoch": 1.3770491803278688, "percentage": 27.54, "elapsed_time": "0:24:16", "remaining_time": "1:03:51", "throughput": 5198.24, "total_tokens": 7569408} {"current_steps": 1849, "total_steps": 6710, "loss": 0.7606, "lr": 2.0601399721488154e-06, "epoch": 1.3777943368107302, "percentage": 27.56, "elapsed_time": "0:24:16", "remaining_time": "1:03:50", "throughput": 5198.25, "total_tokens": 7573504} {"current_steps": 1850, "total_steps": 6710, "loss": 0.825, "lr": 2.0596941932932114e-06, "epoch": 1.3785394932935917, "percentage": 27.57, "elapsed_time": "0:24:17", "remaining_time": "1:03:49", "throughput": 5198.25, "total_tokens": 7577600} {"current_steps": 1851, "total_steps": 6710, "loss": 0.8372, "lr": 2.059248236946858e-06, "epoch": 1.379284649776453, "percentage": 27.59, "elapsed_time": "0:24:18", "remaining_time": "1:03:48", "throughput": 5198.25, "total_tokens": 7581696} {"current_steps": 1852, "total_steps": 6710, "loss": 0.6764, "lr": 2.0588021032075127e-06, "epoch": 1.3800298062593144, "percentage": 27.6, "elapsed_time": "0:24:19", "remaining_time": "1:03:47", "throughput": 5198.25, "total_tokens": 7585792} {"current_steps": 1853, "total_steps": 6710, "loss": 0.8432, "lr": 2.058355792172971e-06, "epoch": 1.380774962742176, "percentage": 27.62, "elapsed_time": "0:24:20", "remaining_time": "1:03:47", "throughput": 5198.26, "total_tokens": 7589888} {"current_steps": 1854, "total_steps": 6710, "loss": 0.6539, "lr": 2.057909303941068e-06, "epoch": 1.3815201192250373, "percentage": 27.63, "elapsed_time": "0:24:20", "remaining_time": "1:03:46", "throughput": 5198.26, "total_tokens": 7593984} {"current_steps": 1855, "total_steps": 6710, "loss": 0.5617, "lr": 2.0574626386096765e-06, "epoch": 1.3822652757078986, "percentage": 27.65, "elapsed_time": "0:24:21", "remaining_time": "1:03:45", "throughput": 5198.27, "total_tokens": 7598080} {"current_steps": 1856, "total_steps": 6710, "loss": 0.7351, "lr": 2.0570157962767084e-06, "epoch": 1.3830104321907601, "percentage": 27.66, "elapsed_time": "0:24:22", "remaining_time": "1:03:44", "throughput": 5198.27, "total_tokens": 7602176} {"current_steps": 1857, "total_steps": 6710, "loss": 1.0504, "lr": 2.0565687770401155e-06, "epoch": 1.3837555886736215, "percentage": 27.68, "elapsed_time": "0:24:23", "remaining_time": "1:03:43", "throughput": 5198.29, "total_tokens": 7606272} {"current_steps": 1858, "total_steps": 6710, "loss": 0.64, "lr": 2.0561215809978874e-06, "epoch": 1.3845007451564828, "percentage": 27.69, "elapsed_time": "0:24:24", "remaining_time": "1:03:43", "throughput": 5198.3, "total_tokens": 7610368} {"current_steps": 1859, "total_steps": 6710, "loss": 1.0681, "lr": 2.055674208248052e-06, "epoch": 1.3852459016393444, "percentage": 27.7, "elapsed_time": "0:24:24", "remaining_time": "1:03:42", "throughput": 5198.31, "total_tokens": 7614464} {"current_steps": 1860, "total_steps": 6710, "loss": 0.7455, "lr": 2.0552266588886775e-06, "epoch": 1.3859910581222057, "percentage": 27.72, "elapsed_time": "0:24:25", "remaining_time": "1:03:41", "throughput": 5198.34, "total_tokens": 7618560} {"current_steps": 1861, "total_steps": 6710, "loss": 0.7302, "lr": 2.054778933017869e-06, "epoch": 1.386736214605067, "percentage": 27.73, "elapsed_time": "0:24:26", "remaining_time": "1:03:40", "throughput": 5198.35, "total_tokens": 7622656} {"current_steps": 1862, "total_steps": 6710, "loss": 0.9751, "lr": 2.0543310307337724e-06, "epoch": 1.3874813710879286, "percentage": 27.75, "elapsed_time": "0:24:27", "remaining_time": "1:03:39", "throughput": 5198.38, "total_tokens": 7626752} {"current_steps": 1863, "total_steps": 6710, "loss": 0.9034, "lr": 2.0538829521345706e-06, "epoch": 1.38822652757079, "percentage": 27.76, "elapsed_time": "0:24:27", "remaining_time": "1:03:39", "throughput": 5198.4, "total_tokens": 7630848} {"current_steps": 1864, "total_steps": 6710, "loss": 0.6213, "lr": 2.053434697318485e-06, "epoch": 1.3889716840536512, "percentage": 27.78, "elapsed_time": "0:24:28", "remaining_time": "1:03:38", "throughput": 5198.43, "total_tokens": 7634944} {"current_steps": 1865, "total_steps": 6710, "loss": 0.9241, "lr": 2.0529862663837767e-06, "epoch": 1.3897168405365128, "percentage": 27.79, "elapsed_time": "0:24:29", "remaining_time": "1:03:37", "throughput": 5198.44, "total_tokens": 7639040} {"current_steps": 1866, "total_steps": 6710, "loss": 0.779, "lr": 2.052537659428745e-06, "epoch": 1.3904619970193741, "percentage": 27.81, "elapsed_time": "0:24:30", "remaining_time": "1:03:36", "throughput": 5198.46, "total_tokens": 7643136} {"current_steps": 1867, "total_steps": 6710, "loss": 0.8896, "lr": 2.0520888765517277e-06, "epoch": 1.3912071535022354, "percentage": 27.82, "elapsed_time": "0:24:31", "remaining_time": "1:03:35", "throughput": 5198.48, "total_tokens": 7647232} {"current_steps": 1868, "total_steps": 6710, "loss": 0.7807, "lr": 2.051639917851101e-06, "epoch": 1.391952309985097, "percentage": 27.84, "elapsed_time": "0:24:31", "remaining_time": "1:03:35", "throughput": 5198.51, "total_tokens": 7651328} {"current_steps": 1869, "total_steps": 6710, "loss": 0.5771, "lr": 2.0511907834252805e-06, "epoch": 1.3926974664679583, "percentage": 27.85, "elapsed_time": "0:24:32", "remaining_time": "1:03:34", "throughput": 5198.46, "total_tokens": 7655424} {"current_steps": 1870, "total_steps": 6710, "loss": 0.8021, "lr": 2.050741473372719e-06, "epoch": 1.3934426229508197, "percentage": 27.87, "elapsed_time": "0:24:33", "remaining_time": "1:03:33", "throughput": 5198.48, "total_tokens": 7659520} {"current_steps": 1871, "total_steps": 6710, "loss": 0.9464, "lr": 2.0502919877919092e-06, "epoch": 1.394187779433681, "percentage": 27.88, "elapsed_time": "0:24:34", "remaining_time": "1:03:32", "throughput": 5198.5, "total_tokens": 7663616} {"current_steps": 1872, "total_steps": 6710, "loss": 0.642, "lr": 2.0498423267813805e-06, "epoch": 1.3949329359165425, "percentage": 27.9, "elapsed_time": "0:24:34", "remaining_time": "1:03:31", "throughput": 5198.52, "total_tokens": 7667712} {"current_steps": 1873, "total_steps": 6710, "loss": 0.8505, "lr": 2.0493924904397027e-06, "epoch": 1.3956780923994039, "percentage": 27.91, "elapsed_time": "0:24:35", "remaining_time": "1:03:31", "throughput": 5198.54, "total_tokens": 7671808} {"current_steps": 1874, "total_steps": 6710, "loss": 0.8541, "lr": 2.0489424788654827e-06, "epoch": 1.3964232488822652, "percentage": 27.93, "elapsed_time": "0:24:36", "remaining_time": "1:03:30", "throughput": 5198.57, "total_tokens": 7675904} {"current_steps": 1875, "total_steps": 6710, "loss": 0.9523, "lr": 2.0484922921573664e-06, "epoch": 1.3971684053651265, "percentage": 27.94, "elapsed_time": "0:24:37", "remaining_time": "1:03:29", "throughput": 5198.59, "total_tokens": 7680000} {"current_steps": 1876, "total_steps": 6710, "loss": 0.9877, "lr": 2.048041930414038e-06, "epoch": 1.397913561847988, "percentage": 27.96, "elapsed_time": "0:24:38", "remaining_time": "1:03:28", "throughput": 5198.62, "total_tokens": 7684096} {"current_steps": 1877, "total_steps": 6710, "loss": 0.7729, "lr": 2.0475913937342197e-06, "epoch": 1.3986587183308494, "percentage": 27.97, "elapsed_time": "0:24:38", "remaining_time": "1:03:27", "throughput": 5198.65, "total_tokens": 7688192} {"current_steps": 1878, "total_steps": 6710, "loss": 0.64, "lr": 2.047140682216673e-06, "epoch": 1.3994038748137108, "percentage": 27.99, "elapsed_time": "0:24:39", "remaining_time": "1:03:27", "throughput": 5198.68, "total_tokens": 7692288} {"current_steps": 1879, "total_steps": 6710, "loss": 0.6047, "lr": 2.0466897959601963e-06, "epoch": 1.4001490312965723, "percentage": 28.0, "elapsed_time": "0:24:40", "remaining_time": "1:03:26", "throughput": 5198.71, "total_tokens": 7696384} {"current_steps": 1880, "total_steps": 6710, "loss": 0.7812, "lr": 2.0462387350636274e-06, "epoch": 1.4008941877794336, "percentage": 28.02, "elapsed_time": "0:24:41", "remaining_time": "1:03:25", "throughput": 5198.73, "total_tokens": 7700480} {"current_steps": 1881, "total_steps": 6710, "loss": 0.6199, "lr": 2.0457874996258426e-06, "epoch": 1.401639344262295, "percentage": 28.03, "elapsed_time": "0:24:42", "remaining_time": "1:03:24", "throughput": 5198.76, "total_tokens": 7704576} {"current_steps": 1882, "total_steps": 6710, "loss": 0.6233, "lr": 2.045336089745755e-06, "epoch": 1.4023845007451565, "percentage": 28.05, "elapsed_time": "0:24:42", "remaining_time": "1:03:23", "throughput": 5198.79, "total_tokens": 7708672} {"current_steps": 1883, "total_steps": 6710, "loss": 0.7564, "lr": 2.0448845055223175e-06, "epoch": 1.4031296572280179, "percentage": 28.06, "elapsed_time": "0:24:43", "remaining_time": "1:03:23", "throughput": 5198.82, "total_tokens": 7712768} {"current_steps": 1884, "total_steps": 6710, "loss": 0.622, "lr": 2.0444327470545207e-06, "epoch": 1.4038748137108792, "percentage": 28.08, "elapsed_time": "0:24:44", "remaining_time": "1:03:22", "throughput": 5198.85, "total_tokens": 7716864} {"current_steps": 1885, "total_steps": 6710, "loss": 0.7925, "lr": 2.043980814441392e-06, "epoch": 1.4046199701937407, "percentage": 28.09, "elapsed_time": "0:24:45", "remaining_time": "1:03:21", "throughput": 5198.88, "total_tokens": 7720960} {"current_steps": 1886, "total_steps": 6710, "loss": 0.7553, "lr": 2.043528707782e-06, "epoch": 1.405365126676602, "percentage": 28.11, "elapsed_time": "0:24:45", "remaining_time": "1:03:20", "throughput": 5198.91, "total_tokens": 7725056} {"current_steps": 1887, "total_steps": 6710, "loss": 0.6119, "lr": 2.043076427175449e-06, "epoch": 1.4061102831594634, "percentage": 28.12, "elapsed_time": "0:24:46", "remaining_time": "1:03:19", "throughput": 5198.93, "total_tokens": 7729152} {"current_steps": 1888, "total_steps": 6710, "loss": 0.8733, "lr": 2.042623972720882e-06, "epoch": 1.406855439642325, "percentage": 28.14, "elapsed_time": "0:24:47", "remaining_time": "1:03:19", "throughput": 5198.96, "total_tokens": 7733248} {"current_steps": 1889, "total_steps": 6710, "loss": 0.6438, "lr": 2.0421713445174803e-06, "epoch": 1.4076005961251863, "percentage": 28.15, "elapsed_time": "0:24:48", "remaining_time": "1:03:18", "throughput": 5198.99, "total_tokens": 7737344} {"current_steps": 1890, "total_steps": 6710, "loss": 0.7542, "lr": 2.041718542664463e-06, "epoch": 1.4083457526080476, "percentage": 28.17, "elapsed_time": "0:24:49", "remaining_time": "1:03:17", "throughput": 5199.02, "total_tokens": 7741440} {"current_steps": 1891, "total_steps": 6710, "loss": 0.825, "lr": 2.041265567261088e-06, "epoch": 1.4090909090909092, "percentage": 28.18, "elapsed_time": "0:24:49", "remaining_time": "1:03:16", "throughput": 5199.05, "total_tokens": 7745536} {"current_steps": 1892, "total_steps": 6710, "loss": 0.699, "lr": 2.0408124184066507e-06, "epoch": 1.4098360655737705, "percentage": 28.2, "elapsed_time": "0:24:50", "remaining_time": "1:03:15", "throughput": 5199.08, "total_tokens": 7749632} {"current_steps": 1893, "total_steps": 6710, "loss": 0.9673, "lr": 2.0403590962004845e-06, "epoch": 1.4105812220566318, "percentage": 28.21, "elapsed_time": "0:24:51", "remaining_time": "1:03:14", "throughput": 5199.1, "total_tokens": 7753728} {"current_steps": 1894, "total_steps": 6710, "loss": 0.9729, "lr": 2.0399056007419603e-06, "epoch": 1.4113263785394934, "percentage": 28.23, "elapsed_time": "0:24:52", "remaining_time": "1:03:14", "throughput": 5199.13, "total_tokens": 7757824} {"current_steps": 1895, "total_steps": 6710, "loss": 0.6775, "lr": 2.039451932130488e-06, "epoch": 1.4120715350223547, "percentage": 28.24, "elapsed_time": "0:24:52", "remaining_time": "1:03:13", "throughput": 5199.15, "total_tokens": 7761920} {"current_steps": 1896, "total_steps": 6710, "loss": 0.7267, "lr": 2.0389980904655153e-06, "epoch": 1.412816691505216, "percentage": 28.26, "elapsed_time": "0:24:53", "remaining_time": "1:03:12", "throughput": 5199.18, "total_tokens": 7766016} {"current_steps": 1897, "total_steps": 6710, "loss": 0.5634, "lr": 2.038544075846527e-06, "epoch": 1.4135618479880776, "percentage": 28.27, "elapsed_time": "0:24:54", "remaining_time": "1:03:11", "throughput": 5199.21, "total_tokens": 7770112} {"current_steps": 1898, "total_steps": 6710, "loss": 0.836, "lr": 2.0380898883730466e-06, "epoch": 1.414307004470939, "percentage": 28.29, "elapsed_time": "0:24:55", "remaining_time": "1:03:10", "throughput": 5199.24, "total_tokens": 7774208} {"current_steps": 1899, "total_steps": 6710, "loss": 0.6671, "lr": 2.0376355281446354e-06, "epoch": 1.4150521609538003, "percentage": 28.3, "elapsed_time": "0:24:56", "remaining_time": "1:03:10", "throughput": 5199.27, "total_tokens": 7778304} {"current_steps": 1900, "total_steps": 6710, "loss": 0.4541, "lr": 2.0371809952608916e-06, "epoch": 1.4157973174366618, "percentage": 28.32, "elapsed_time": "0:24:56", "remaining_time": "1:03:09", "throughput": 5199.3, "total_tokens": 7782400} {"current_steps": 1901, "total_steps": 6710, "loss": 0.7147, "lr": 2.0367262898214533e-06, "epoch": 1.4165424739195231, "percentage": 28.33, "elapsed_time": "0:24:57", "remaining_time": "1:03:08", "throughput": 5199.32, "total_tokens": 7786496} {"current_steps": 1902, "total_steps": 6710, "loss": 0.7761, "lr": 2.0362714119259943e-06, "epoch": 1.4172876304023845, "percentage": 28.35, "elapsed_time": "0:24:58", "remaining_time": "1:03:07", "throughput": 5199.34, "total_tokens": 7790592} {"current_steps": 1903, "total_steps": 6710, "loss": 0.8911, "lr": 2.0358163616742272e-06, "epoch": 1.418032786885246, "percentage": 28.36, "elapsed_time": "0:24:59", "remaining_time": "1:03:07", "throughput": 5199.21, "total_tokens": 7794688} {"current_steps": 1904, "total_steps": 6710, "loss": 0.7347, "lr": 2.035361139165903e-06, "epoch": 1.4187779433681074, "percentage": 28.38, "elapsed_time": "0:24:59", "remaining_time": "1:03:06", "throughput": 5199.23, "total_tokens": 7798784} {"current_steps": 1905, "total_steps": 6710, "loss": 0.7215, "lr": 2.0349057445008085e-06, "epoch": 1.4195230998509687, "percentage": 28.39, "elapsed_time": "0:25:00", "remaining_time": "1:03:05", "throughput": 5199.25, "total_tokens": 7802880} {"current_steps": 1906, "total_steps": 6710, "loss": 0.6971, "lr": 2.0344501777787703e-06, "epoch": 1.42026825633383, "percentage": 28.41, "elapsed_time": "0:25:01", "remaining_time": "1:03:04", "throughput": 5199.28, "total_tokens": 7806976} {"current_steps": 1907, "total_steps": 6710, "loss": 0.8762, "lr": 2.0339944390996515e-06, "epoch": 1.4210134128166916, "percentage": 28.42, "elapsed_time": "0:25:02", "remaining_time": "1:03:03", "throughput": 5199.28, "total_tokens": 7811072} {"current_steps": 1908, "total_steps": 6710, "loss": 0.5777, "lr": 2.0335385285633537e-06, "epoch": 1.421758569299553, "percentage": 28.44, "elapsed_time": "0:25:03", "remaining_time": "1:03:03", "throughput": 5199.29, "total_tokens": 7815168} {"current_steps": 1909, "total_steps": 6710, "loss": 0.7393, "lr": 2.0330824462698153e-06, "epoch": 1.4225037257824142, "percentage": 28.45, "elapsed_time": "0:25:03", "remaining_time": "1:03:02", "throughput": 5199.32, "total_tokens": 7819264} {"current_steps": 1910, "total_steps": 6710, "loss": 1.0289, "lr": 2.0326261923190133e-06, "epoch": 1.4232488822652756, "percentage": 28.46, "elapsed_time": "0:25:04", "remaining_time": "1:03:01", "throughput": 5199.34, "total_tokens": 7823360} {"current_steps": 1911, "total_steps": 6710, "loss": 0.8112, "lr": 2.032169766810961e-06, "epoch": 1.4239940387481371, "percentage": 28.48, "elapsed_time": "0:25:05", "remaining_time": "1:03:00", "throughput": 5199.36, "total_tokens": 7827456} {"current_steps": 1912, "total_steps": 6710, "loss": 0.8357, "lr": 2.0317131698457105e-06, "epoch": 1.4247391952309985, "percentage": 28.49, "elapsed_time": "0:25:06", "remaining_time": "1:02:59", "throughput": 5199.36, "total_tokens": 7831552} {"current_steps": 1913, "total_steps": 6710, "loss": 0.8064, "lr": 2.0312564015233517e-06, "epoch": 1.4254843517138598, "percentage": 28.51, "elapsed_time": "0:25:07", "remaining_time": "1:02:59", "throughput": 5199.38, "total_tokens": 7835648} {"current_steps": 1914, "total_steps": 6710, "loss": 0.7143, "lr": 2.0307994619440108e-06, "epoch": 1.4262295081967213, "percentage": 28.52, "elapsed_time": "0:25:07", "remaining_time": "1:02:58", "throughput": 5199.4, "total_tokens": 7839744} {"current_steps": 1915, "total_steps": 6710, "loss": 0.6194, "lr": 2.0303423512078524e-06, "epoch": 1.4269746646795827, "percentage": 28.54, "elapsed_time": "0:25:08", "remaining_time": "1:02:57", "throughput": 5199.42, "total_tokens": 7843840} {"current_steps": 1916, "total_steps": 6710, "loss": 0.7912, "lr": 2.0298850694150785e-06, "epoch": 1.427719821162444, "percentage": 28.55, "elapsed_time": "0:25:09", "remaining_time": "1:02:56", "throughput": 5199.44, "total_tokens": 7847936} {"current_steps": 1917, "total_steps": 6710, "loss": 0.7058, "lr": 2.0294276166659286e-06, "epoch": 1.4284649776453056, "percentage": 28.57, "elapsed_time": "0:25:10", "remaining_time": "1:02:55", "throughput": 5199.45, "total_tokens": 7852032} {"current_steps": 1918, "total_steps": 6710, "loss": 0.8517, "lr": 2.0289699930606796e-06, "epoch": 1.4292101341281669, "percentage": 28.58, "elapsed_time": "0:25:10", "remaining_time": "1:02:55", "throughput": 5199.46, "total_tokens": 7856128} {"current_steps": 1919, "total_steps": 6710, "loss": 0.7135, "lr": 2.028512198699646e-06, "epoch": 1.4299552906110282, "percentage": 28.6, "elapsed_time": "0:25:11", "remaining_time": "1:02:54", "throughput": 5199.48, "total_tokens": 7860224} {"current_steps": 1920, "total_steps": 6710, "loss": 0.6601, "lr": 2.0280542336831787e-06, "epoch": 1.4307004470938898, "percentage": 28.61, "elapsed_time": "0:25:12", "remaining_time": "1:02:53", "throughput": 5199.5, "total_tokens": 7864320} {"current_steps": 1921, "total_steps": 6710, "loss": 0.5379, "lr": 2.027596098111668e-06, "epoch": 1.431445603576751, "percentage": 28.63, "elapsed_time": "0:25:13", "remaining_time": "1:02:52", "throughput": 5199.53, "total_tokens": 7868416} {"current_steps": 1922, "total_steps": 6710, "loss": 0.9298, "lr": 2.02713779208554e-06, "epoch": 1.4321907600596124, "percentage": 28.64, "elapsed_time": "0:25:14", "remaining_time": "1:02:51", "throughput": 5199.55, "total_tokens": 7872512} {"current_steps": 1923, "total_steps": 6710, "loss": 0.5326, "lr": 2.0266793157052587e-06, "epoch": 1.432935916542474, "percentage": 28.66, "elapsed_time": "0:25:14", "remaining_time": "1:02:51", "throughput": 5199.56, "total_tokens": 7876608} {"current_steps": 1924, "total_steps": 6710, "loss": 0.8675, "lr": 2.0262206690713253e-06, "epoch": 1.4336810730253353, "percentage": 28.67, "elapsed_time": "0:25:15", "remaining_time": "1:02:50", "throughput": 5199.58, "total_tokens": 7880704} {"current_steps": 1925, "total_steps": 6710, "loss": 0.988, "lr": 2.0257618522842785e-06, "epoch": 1.4344262295081966, "percentage": 28.69, "elapsed_time": "0:25:16", "remaining_time": "1:02:49", "throughput": 5199.6, "total_tokens": 7884800} {"current_steps": 1926, "total_steps": 6710, "loss": 0.867, "lr": 2.0253028654446944e-06, "epoch": 1.4351713859910582, "percentage": 28.7, "elapsed_time": "0:25:17", "remaining_time": "1:02:48", "throughput": 5199.62, "total_tokens": 7888896} {"current_steps": 1927, "total_steps": 6710, "loss": 0.6626, "lr": 2.0248437086531863e-06, "epoch": 1.4359165424739195, "percentage": 28.72, "elapsed_time": "0:25:17", "remaining_time": "1:02:47", "throughput": 5199.65, "total_tokens": 7892992} {"current_steps": 1928, "total_steps": 6710, "loss": 0.68, "lr": 2.024384382010404e-06, "epoch": 1.4366616989567809, "percentage": 28.73, "elapsed_time": "0:25:18", "remaining_time": "1:02:46", "throughput": 5199.67, "total_tokens": 7897088} {"current_steps": 1929, "total_steps": 6710, "loss": 1.0023, "lr": 2.0239248856170357e-06, "epoch": 1.4374068554396424, "percentage": 28.75, "elapsed_time": "0:25:19", "remaining_time": "1:02:46", "throughput": 5199.7, "total_tokens": 7901184} {"current_steps": 1930, "total_steps": 6710, "loss": 0.5118, "lr": 2.023465219573806e-06, "epoch": 1.4381520119225037, "percentage": 28.76, "elapsed_time": "0:25:20", "remaining_time": "1:02:45", "throughput": 5199.73, "total_tokens": 7905280} {"current_steps": 1931, "total_steps": 6710, "loss": 0.6836, "lr": 2.023005383981477e-06, "epoch": 1.438897168405365, "percentage": 28.78, "elapsed_time": "0:25:21", "remaining_time": "1:02:44", "throughput": 5199.74, "total_tokens": 7909376} {"current_steps": 1932, "total_steps": 6710, "loss": 0.5789, "lr": 2.022545378940849e-06, "epoch": 1.4396423248882266, "percentage": 28.79, "elapsed_time": "0:25:21", "remaining_time": "1:02:43", "throughput": 5199.77, "total_tokens": 7913472} {"current_steps": 1933, "total_steps": 6710, "loss": 0.7936, "lr": 2.0220852045527565e-06, "epoch": 1.440387481371088, "percentage": 28.81, "elapsed_time": "0:25:22", "remaining_time": "1:02:42", "throughput": 5199.78, "total_tokens": 7917568} {"current_steps": 1934, "total_steps": 6710, "loss": 0.7127, "lr": 2.0216248609180743e-06, "epoch": 1.4411326378539493, "percentage": 28.82, "elapsed_time": "0:25:23", "remaining_time": "1:02:42", "throughput": 5199.81, "total_tokens": 7921664} {"current_steps": 1935, "total_steps": 6710, "loss": 0.8341, "lr": 2.0211643481377124e-06, "epoch": 1.4418777943368108, "percentage": 28.84, "elapsed_time": "0:25:24", "remaining_time": "1:02:41", "throughput": 5199.8, "total_tokens": 7925760} {"current_steps": 1936, "total_steps": 6710, "loss": 0.6438, "lr": 2.020703666312619e-06, "epoch": 1.4426229508196722, "percentage": 28.85, "elapsed_time": "0:25:25", "remaining_time": "1:02:40", "throughput": 5199.82, "total_tokens": 7929856} {"current_steps": 1937, "total_steps": 6710, "loss": 0.8816, "lr": 2.020242815543779e-06, "epoch": 1.4433681073025335, "percentage": 28.87, "elapsed_time": "0:25:25", "remaining_time": "1:02:39", "throughput": 5199.85, "total_tokens": 7933952} {"current_steps": 1938, "total_steps": 6710, "loss": 0.8635, "lr": 2.0197817959322134e-06, "epoch": 1.444113263785395, "percentage": 28.88, "elapsed_time": "0:25:26", "remaining_time": "1:02:38", "throughput": 5199.87, "total_tokens": 7938048} {"current_steps": 1939, "total_steps": 6710, "loss": 1.0744, "lr": 2.019320607578982e-06, "epoch": 1.4448584202682564, "percentage": 28.9, "elapsed_time": "0:25:27", "remaining_time": "1:02:38", "throughput": 5199.9, "total_tokens": 7942144} {"current_steps": 1940, "total_steps": 6710, "loss": 0.9076, "lr": 2.018859250585179e-06, "epoch": 1.4456035767511177, "percentage": 28.91, "elapsed_time": "0:25:28", "remaining_time": "1:02:37", "throughput": 5199.91, "total_tokens": 7946240} {"current_steps": 1941, "total_steps": 6710, "loss": 0.7192, "lr": 2.018397725051939e-06, "epoch": 1.446348733233979, "percentage": 28.93, "elapsed_time": "0:25:28", "remaining_time": "1:02:36", "throughput": 5199.93, "total_tokens": 7950336} {"current_steps": 1942, "total_steps": 6710, "loss": 0.6166, "lr": 2.01793603108043e-06, "epoch": 1.4470938897168406, "percentage": 28.94, "elapsed_time": "0:25:29", "remaining_time": "1:02:35", "throughput": 5199.94, "total_tokens": 7954432} {"current_steps": 1943, "total_steps": 6710, "loss": 0.9141, "lr": 2.0174741687718597e-06, "epoch": 1.447839046199702, "percentage": 28.96, "elapsed_time": "0:25:30", "remaining_time": "1:02:34", "throughput": 5199.97, "total_tokens": 7958528} {"current_steps": 1944, "total_steps": 6710, "loss": 0.9312, "lr": 2.0170121382274717e-06, "epoch": 1.4485842026825633, "percentage": 28.97, "elapsed_time": "0:25:31", "remaining_time": "1:02:34", "throughput": 5199.98, "total_tokens": 7962624} {"current_steps": 1945, "total_steps": 6710, "loss": 0.7388, "lr": 2.016549939548546e-06, "epoch": 1.4493293591654246, "percentage": 28.99, "elapsed_time": "0:25:32", "remaining_time": "1:02:33", "throughput": 5200.0, "total_tokens": 7966720} {"current_steps": 1946, "total_steps": 6710, "loss": 0.716, "lr": 2.0160875728363996e-06, "epoch": 1.4500745156482862, "percentage": 29.0, "elapsed_time": "0:25:32", "remaining_time": "1:02:32", "throughput": 5200.01, "total_tokens": 7970816} {"current_steps": 1947, "total_steps": 6710, "loss": 0.6628, "lr": 2.015625038192387e-06, "epoch": 1.4508196721311475, "percentage": 29.02, "elapsed_time": "0:25:33", "remaining_time": "1:02:31", "throughput": 5200.03, "total_tokens": 7974912} {"current_steps": 1948, "total_steps": 6710, "loss": 0.7116, "lr": 2.015162335717899e-06, "epoch": 1.4515648286140088, "percentage": 29.03, "elapsed_time": "0:25:34", "remaining_time": "1:02:30", "throughput": 5200.05, "total_tokens": 7979008} {"current_steps": 1949, "total_steps": 6710, "loss": 0.6629, "lr": 2.0146994655143633e-06, "epoch": 1.4523099850968704, "percentage": 29.05, "elapsed_time": "0:25:35", "remaining_time": "1:02:30", "throughput": 5200.08, "total_tokens": 7983104} {"current_steps": 1950, "total_steps": 6710, "loss": 0.6824, "lr": 2.0142364276832445e-06, "epoch": 1.4530551415797317, "percentage": 29.06, "elapsed_time": "0:25:35", "remaining_time": "1:02:29", "throughput": 5200.1, "total_tokens": 7987200} {"current_steps": 1951, "total_steps": 6710, "loss": 0.5549, "lr": 2.013773222326043e-06, "epoch": 1.453800298062593, "percentage": 29.08, "elapsed_time": "0:25:36", "remaining_time": "1:02:28", "throughput": 5200.12, "total_tokens": 7991296} {"current_steps": 1952, "total_steps": 6710, "loss": 0.938, "lr": 2.0133098495442978e-06, "epoch": 1.4545454545454546, "percentage": 29.09, "elapsed_time": "0:25:37", "remaining_time": "1:02:27", "throughput": 5200.13, "total_tokens": 7995392} {"current_steps": 1953, "total_steps": 6710, "loss": 0.8168, "lr": 2.012846309439583e-06, "epoch": 1.455290611028316, "percentage": 29.11, "elapsed_time": "0:25:38", "remaining_time": "1:02:26", "throughput": 5200.16, "total_tokens": 7999488} {"current_steps": 1954, "total_steps": 6710, "loss": 0.6229, "lr": 2.0123826021135102e-06, "epoch": 1.4560357675111772, "percentage": 29.12, "elapsed_time": "0:25:39", "remaining_time": "1:02:26", "throughput": 5200.18, "total_tokens": 8003584} {"current_steps": 1955, "total_steps": 6710, "loss": 0.9812, "lr": 2.0119187276677267e-06, "epoch": 1.4567809239940388, "percentage": 29.14, "elapsed_time": "0:25:39", "remaining_time": "1:02:25", "throughput": 5200.2, "total_tokens": 8007680} {"current_steps": 1956, "total_steps": 6710, "loss": 0.7793, "lr": 2.0114546862039176e-06, "epoch": 1.4575260804769001, "percentage": 29.15, "elapsed_time": "0:25:40", "remaining_time": "1:02:24", "throughput": 5200.21, "total_tokens": 8011776} {"current_steps": 1957, "total_steps": 6710, "loss": 0.9691, "lr": 2.010990477823804e-06, "epoch": 1.4582712369597615, "percentage": 29.17, "elapsed_time": "0:25:41", "remaining_time": "1:02:23", "throughput": 5200.23, "total_tokens": 8015872} {"current_steps": 1958, "total_steps": 6710, "loss": 0.961, "lr": 2.010526102629144e-06, "epoch": 1.459016393442623, "percentage": 29.18, "elapsed_time": "0:25:42", "remaining_time": "1:02:22", "throughput": 5200.26, "total_tokens": 8019968} {"current_steps": 1959, "total_steps": 6710, "loss": 1.0833, "lr": 2.0100615607217313e-06, "epoch": 1.4597615499254843, "percentage": 29.2, "elapsed_time": "0:25:43", "remaining_time": "1:02:22", "throughput": 5200.29, "total_tokens": 8024064} {"current_steps": 1960, "total_steps": 6710, "loss": 0.6639, "lr": 2.009596852203398e-06, "epoch": 1.4605067064083457, "percentage": 29.21, "elapsed_time": "0:25:43", "remaining_time": "1:02:21", "throughput": 5200.31, "total_tokens": 8028160} {"current_steps": 1961, "total_steps": 6710, "loss": 0.6732, "lr": 2.0091319771760094e-06, "epoch": 1.4612518628912072, "percentage": 29.23, "elapsed_time": "0:25:44", "remaining_time": "1:02:20", "throughput": 5200.34, "total_tokens": 8032256} {"current_steps": 1962, "total_steps": 6710, "loss": 1.0387, "lr": 2.0086669357414714e-06, "epoch": 1.4619970193740686, "percentage": 29.24, "elapsed_time": "0:25:45", "remaining_time": "1:02:19", "throughput": 5200.37, "total_tokens": 8036352} {"current_steps": 1963, "total_steps": 6710, "loss": 0.8233, "lr": 2.0082017280017237e-06, "epoch": 1.46274217585693, "percentage": 29.25, "elapsed_time": "0:25:46", "remaining_time": "1:02:18", "throughput": 5200.4, "total_tokens": 8040448} {"current_steps": 1964, "total_steps": 6710, "loss": 0.7006, "lr": 2.007736354058743e-06, "epoch": 1.4634873323397914, "percentage": 29.27, "elapsed_time": "0:25:46", "remaining_time": "1:02:18", "throughput": 5200.42, "total_tokens": 8044544} {"current_steps": 1965, "total_steps": 6710, "loss": 0.7369, "lr": 2.007270814014543e-06, "epoch": 1.4642324888226528, "percentage": 29.28, "elapsed_time": "0:25:47", "remaining_time": "1:02:17", "throughput": 5200.45, "total_tokens": 8048640} {"current_steps": 1966, "total_steps": 6710, "loss": 0.7927, "lr": 2.0068051079711732e-06, "epoch": 1.464977645305514, "percentage": 29.3, "elapsed_time": "0:25:48", "remaining_time": "1:02:16", "throughput": 5200.49, "total_tokens": 8052736} {"current_steps": 1967, "total_steps": 6710, "loss": 0.8511, "lr": 2.0063392360307195e-06, "epoch": 1.4657228017883757, "percentage": 29.31, "elapsed_time": "0:25:49", "remaining_time": "1:02:15", "throughput": 5200.52, "total_tokens": 8056832} {"current_steps": 1968, "total_steps": 6710, "loss": 0.7079, "lr": 2.0058731982953046e-06, "epoch": 1.466467958271237, "percentage": 29.33, "elapsed_time": "0:25:50", "remaining_time": "1:02:14", "throughput": 5200.54, "total_tokens": 8060928} {"current_steps": 1969, "total_steps": 6710, "loss": 0.6043, "lr": 2.005406994867087e-06, "epoch": 1.4672131147540983, "percentage": 29.34, "elapsed_time": "0:25:50", "remaining_time": "1:02:14", "throughput": 5200.57, "total_tokens": 8065024} {"current_steps": 1970, "total_steps": 6710, "loss": 0.83, "lr": 2.0049406258482624e-06, "epoch": 1.4679582712369599, "percentage": 29.36, "elapsed_time": "0:25:51", "remaining_time": "1:02:13", "throughput": 5200.6, "total_tokens": 8069120} {"current_steps": 1971, "total_steps": 6710, "loss": 0.7314, "lr": 2.0044740913410614e-06, "epoch": 1.4687034277198212, "percentage": 29.37, "elapsed_time": "0:25:52", "remaining_time": "1:02:12", "throughput": 5200.62, "total_tokens": 8073216} {"current_steps": 1972, "total_steps": 6710, "loss": 0.6839, "lr": 2.0040073914477526e-06, "epoch": 1.4694485842026825, "percentage": 29.39, "elapsed_time": "0:25:53", "remaining_time": "1:02:11", "throughput": 5200.64, "total_tokens": 8077312} {"current_steps": 1973, "total_steps": 6710, "loss": 0.7545, "lr": 2.003540526270639e-06, "epoch": 1.470193740685544, "percentage": 29.4, "elapsed_time": "0:25:53", "remaining_time": "1:02:10", "throughput": 5200.68, "total_tokens": 8081408} {"current_steps": 1974, "total_steps": 6710, "loss": 1.0183, "lr": 2.003073495912062e-06, "epoch": 1.4709388971684054, "percentage": 29.42, "elapsed_time": "0:25:54", "remaining_time": "1:02:10", "throughput": 5200.71, "total_tokens": 8085504} {"current_steps": 1975, "total_steps": 6710, "loss": 0.6806, "lr": 2.0026063004743966e-06, "epoch": 1.4716840536512668, "percentage": 29.43, "elapsed_time": "0:25:55", "remaining_time": "1:02:09", "throughput": 5200.73, "total_tokens": 8089600} {"current_steps": 1976, "total_steps": 6710, "loss": 1.0329, "lr": 2.0021389400600564e-06, "epoch": 1.472429210134128, "percentage": 29.45, "elapsed_time": "0:25:56", "remaining_time": "1:02:08", "throughput": 5200.75, "total_tokens": 8093696} {"current_steps": 1977, "total_steps": 6710, "loss": 0.968, "lr": 2.0016714147714896e-06, "epoch": 1.4731743666169896, "percentage": 29.46, "elapsed_time": "0:25:57", "remaining_time": "1:02:07", "throughput": 5200.78, "total_tokens": 8097792} {"current_steps": 1978, "total_steps": 6710, "loss": 0.8327, "lr": 2.0012037247111815e-06, "epoch": 1.473919523099851, "percentage": 29.48, "elapsed_time": "0:25:57", "remaining_time": "1:02:06", "throughput": 5200.81, "total_tokens": 8101888} {"current_steps": 1979, "total_steps": 6710, "loss": 0.6685, "lr": 2.0007358699816525e-06, "epoch": 1.4746646795827123, "percentage": 29.49, "elapsed_time": "0:25:58", "remaining_time": "1:02:05", "throughput": 5200.83, "total_tokens": 8105984} {"current_steps": 1980, "total_steps": 6710, "loss": 0.8311, "lr": 2.0002678506854608e-06, "epoch": 1.4754098360655736, "percentage": 29.51, "elapsed_time": "0:25:59", "remaining_time": "1:02:05", "throughput": 5200.84, "total_tokens": 8110080} {"current_steps": 1981, "total_steps": 6710, "loss": 0.9739, "lr": 1.9997996669251977e-06, "epoch": 1.4761549925484352, "percentage": 29.52, "elapsed_time": "0:26:00", "remaining_time": "1:02:04", "throughput": 5200.83, "total_tokens": 8114176} {"current_steps": 1982, "total_steps": 6710, "loss": 0.6609, "lr": 1.9993313188034946e-06, "epoch": 1.4769001490312965, "percentage": 29.54, "elapsed_time": "0:26:00", "remaining_time": "1:02:03", "throughput": 5200.85, "total_tokens": 8118272} {"current_steps": 1983, "total_steps": 6710, "loss": 0.7391, "lr": 1.9988628064230155e-06, "epoch": 1.4776453055141578, "percentage": 29.55, "elapsed_time": "0:26:01", "remaining_time": "1:02:02", "throughput": 5200.87, "total_tokens": 8122368} {"current_steps": 1984, "total_steps": 6710, "loss": 0.6768, "lr": 1.998394129886461e-06, "epoch": 1.4783904619970194, "percentage": 29.57, "elapsed_time": "0:26:02", "remaining_time": "1:02:01", "throughput": 5200.9, "total_tokens": 8126464} {"current_steps": 1985, "total_steps": 6710, "loss": 0.9577, "lr": 1.9979252892965705e-06, "epoch": 1.4791356184798807, "percentage": 29.58, "elapsed_time": "0:26:03", "remaining_time": "1:02:01", "throughput": 5200.89, "total_tokens": 8130560} {"current_steps": 1986, "total_steps": 6710, "loss": 0.6312, "lr": 1.997456284756115e-06, "epoch": 1.479880774962742, "percentage": 29.6, "elapsed_time": "0:26:04", "remaining_time": "1:02:00", "throughput": 5200.85, "total_tokens": 8134656} {"current_steps": 1987, "total_steps": 6710, "loss": 0.682, "lr": 1.996987116367905e-06, "epoch": 1.4806259314456036, "percentage": 29.61, "elapsed_time": "0:26:04", "remaining_time": "1:01:59", "throughput": 5200.88, "total_tokens": 8138752} {"current_steps": 1988, "total_steps": 6710, "loss": 0.7615, "lr": 1.996517784234785e-06, "epoch": 1.481371087928465, "percentage": 29.63, "elapsed_time": "0:26:05", "remaining_time": "1:01:58", "throughput": 5200.89, "total_tokens": 8142848} {"current_steps": 1989, "total_steps": 6710, "loss": 0.8965, "lr": 1.996048288459636e-06, "epoch": 1.4821162444113263, "percentage": 29.64, "elapsed_time": "0:26:06", "remaining_time": "1:01:58", "throughput": 5200.92, "total_tokens": 8146944} {"current_steps": 1990, "total_steps": 6710, "loss": 0.8896, "lr": 1.9955786291453753e-06, "epoch": 1.4828614008941878, "percentage": 29.66, "elapsed_time": "0:26:07", "remaining_time": "1:01:57", "throughput": 5200.94, "total_tokens": 8151040} {"current_steps": 1991, "total_steps": 6710, "loss": 0.941, "lr": 1.9951088063949547e-06, "epoch": 1.4836065573770492, "percentage": 29.67, "elapsed_time": "0:26:08", "remaining_time": "1:01:56", "throughput": 5200.96, "total_tokens": 8155136} {"current_steps": 1992, "total_steps": 6710, "loss": 0.9704, "lr": 1.9946388203113635e-06, "epoch": 1.4843517138599105, "percentage": 29.69, "elapsed_time": "0:26:08", "remaining_time": "1:01:55", "throughput": 5200.99, "total_tokens": 8159232} {"current_steps": 1993, "total_steps": 6710, "loss": 0.8226, "lr": 1.9941686709976256e-06, "epoch": 1.485096870342772, "percentage": 29.7, "elapsed_time": "0:26:09", "remaining_time": "1:01:54", "throughput": 5201.01, "total_tokens": 8163328} {"current_steps": 1994, "total_steps": 6710, "loss": 0.5011, "lr": 1.9936983585568008e-06, "epoch": 1.4858420268256334, "percentage": 29.72, "elapsed_time": "0:26:10", "remaining_time": "1:01:54", "throughput": 5201.0, "total_tokens": 8167424} {"current_steps": 1995, "total_steps": 6710, "loss": 0.5904, "lr": 1.993227883091986e-06, "epoch": 1.4865871833084947, "percentage": 29.73, "elapsed_time": "0:26:11", "remaining_time": "1:01:53", "throughput": 5201.0, "total_tokens": 8171520} {"current_steps": 1996, "total_steps": 6710, "loss": 1.0457, "lr": 1.9927572447063117e-06, "epoch": 1.4873323397913563, "percentage": 29.75, "elapsed_time": "0:26:11", "remaining_time": "1:01:52", "throughput": 5200.96, "total_tokens": 8175616} {"current_steps": 1997, "total_steps": 6710, "loss": 1.004, "lr": 1.9922864435029457e-06, "epoch": 1.4880774962742176, "percentage": 29.76, "elapsed_time": "0:26:12", "remaining_time": "1:01:51", "throughput": 5200.86, "total_tokens": 8179712} {"current_steps": 1998, "total_steps": 6710, "loss": 0.6677, "lr": 1.991815479585091e-06, "epoch": 1.488822652757079, "percentage": 29.78, "elapsed_time": "0:26:13", "remaining_time": "1:01:50", "throughput": 5200.87, "total_tokens": 8183808} {"current_steps": 1999, "total_steps": 6710, "loss": 0.5498, "lr": 1.991344353055986e-06, "epoch": 1.4895678092399405, "percentage": 29.79, "elapsed_time": "0:26:14", "remaining_time": "1:01:50", "throughput": 5200.85, "total_tokens": 8187904} {"current_steps": 2000, "total_steps": 6710, "loss": 0.5411, "lr": 1.9908730640189053e-06, "epoch": 1.4903129657228018, "percentage": 29.81, "elapsed_time": "0:26:15", "remaining_time": "1:01:49", "throughput": 5200.86, "total_tokens": 8192000} {"current_steps": 2001, "total_steps": 6710, "loss": 0.8725, "lr": 1.9904016125771585e-06, "epoch": 1.4910581222056631, "percentage": 29.82, "elapsed_time": "0:26:15", "remaining_time": "1:01:48", "throughput": 5200.89, "total_tokens": 8196096} {"current_steps": 2002, "total_steps": 6710, "loss": 0.6239, "lr": 1.989929998834091e-06, "epoch": 1.4918032786885247, "percentage": 29.84, "elapsed_time": "0:26:16", "remaining_time": "1:01:47", "throughput": 5200.91, "total_tokens": 8200192} {"current_steps": 2003, "total_steps": 6710, "loss": 0.8744, "lr": 1.9894582228930845e-06, "epoch": 1.492548435171386, "percentage": 29.85, "elapsed_time": "0:26:17", "remaining_time": "1:01:47", "throughput": 5200.93, "total_tokens": 8204288} {"current_steps": 2004, "total_steps": 6710, "loss": 0.7452, "lr": 1.9889862848575554e-06, "epoch": 1.4932935916542474, "percentage": 29.87, "elapsed_time": "0:26:18", "remaining_time": "1:01:46", "throughput": 5200.96, "total_tokens": 8208384} {"current_steps": 2005, "total_steps": 6710, "loss": 0.6563, "lr": 1.9885141848309557e-06, "epoch": 1.494038748137109, "percentage": 29.88, "elapsed_time": "0:26:19", "remaining_time": "1:01:45", "throughput": 5200.98, "total_tokens": 8212480} {"current_steps": 2006, "total_steps": 6710, "loss": 0.6544, "lr": 1.9880419229167735e-06, "epoch": 1.4947839046199702, "percentage": 29.9, "elapsed_time": "0:26:19", "remaining_time": "1:01:44", "throughput": 5201.0, "total_tokens": 8216576} {"current_steps": 2007, "total_steps": 6710, "loss": 0.6499, "lr": 1.9875694992185314e-06, "epoch": 1.4955290611028316, "percentage": 29.91, "elapsed_time": "0:26:20", "remaining_time": "1:01:43", "throughput": 5201.0, "total_tokens": 8220672} {"current_steps": 2008, "total_steps": 6710, "loss": 0.8445, "lr": 1.9870969138397884e-06, "epoch": 1.4962742175856931, "percentage": 29.93, "elapsed_time": "0:26:21", "remaining_time": "1:01:43", "throughput": 5200.66, "total_tokens": 8224768} {"current_steps": 2009, "total_steps": 6710, "loss": 0.4635, "lr": 1.9866241668841385e-06, "epoch": 1.4970193740685545, "percentage": 29.94, "elapsed_time": "0:26:22", "remaining_time": "1:01:42", "throughput": 5200.2, "total_tokens": 8228864} {"current_steps": 2010, "total_steps": 6710, "loss": 0.9121, "lr": 1.9861512584552113e-06, "epoch": 1.4977645305514158, "percentage": 29.96, "elapsed_time": "0:26:23", "remaining_time": "1:01:42", "throughput": 5199.78, "total_tokens": 8232960} {"current_steps": 2011, "total_steps": 6710, "loss": 0.7387, "lr": 1.9856781886566716e-06, "epoch": 1.4985096870342771, "percentage": 29.97, "elapsed_time": "0:26:24", "remaining_time": "1:01:41", "throughput": 5199.68, "total_tokens": 8237056} {"current_steps": 2012, "total_steps": 6710, "loss": 0.4775, "lr": 1.98520495759222e-06, "epoch": 1.4992548435171387, "percentage": 29.99, "elapsed_time": "0:26:24", "remaining_time": "1:01:40", "throughput": 5199.62, "total_tokens": 8241152} {"current_steps": 2013, "total_steps": 6710, "loss": 0.8879, "lr": 1.9847315653655916e-06, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "0:26:25", "remaining_time": "1:01:40", "throughput": 5199.41, "total_tokens": 8245248} {"current_steps": 2014, "total_steps": 6710, "loss": 0.872, "lr": 1.984258012080558e-06, "epoch": 1.5007451564828616, "percentage": 30.01, "elapsed_time": "0:26:26", "remaining_time": "1:01:39", "throughput": 5199.31, "total_tokens": 8249344} {"current_steps": 2015, "total_steps": 6710, "loss": 0.9248, "lr": 1.9837842978409242e-06, "epoch": 1.5014903129657227, "percentage": 30.03, "elapsed_time": "0:26:27", "remaining_time": "1:01:38", "throughput": 5199.22, "total_tokens": 8253440} {"current_steps": 2016, "total_steps": 6710, "loss": 0.6801, "lr": 1.9833104227505335e-06, "epoch": 1.5022354694485842, "percentage": 30.04, "elapsed_time": "0:26:28", "remaining_time": "1:01:38", "throughput": 5199.17, "total_tokens": 8257536} {"current_steps": 2017, "total_steps": 6710, "loss": 1.0082, "lr": 1.9828363869132616e-06, "epoch": 1.5029806259314458, "percentage": 30.06, "elapsed_time": "0:26:29", "remaining_time": "1:01:37", "throughput": 5199.11, "total_tokens": 8261632} {"current_steps": 2018, "total_steps": 6710, "loss": 0.813, "lr": 1.9823621904330207e-06, "epoch": 1.5037257824143069, "percentage": 30.07, "elapsed_time": "0:26:29", "remaining_time": "1:01:36", "throughput": 5198.97, "total_tokens": 8265728} {"current_steps": 2019, "total_steps": 6710, "loss": 0.7706, "lr": 1.981887833413758e-06, "epoch": 1.5044709388971684, "percentage": 30.09, "elapsed_time": "0:26:30", "remaining_time": "1:01:35", "throughput": 5198.76, "total_tokens": 8269824} {"current_steps": 2020, "total_steps": 6710, "loss": 0.4791, "lr": 1.981413315959456e-06, "epoch": 1.5052160953800298, "percentage": 30.1, "elapsed_time": "0:26:31", "remaining_time": "1:01:35", "throughput": 5198.6, "total_tokens": 8273920} {"current_steps": 2021, "total_steps": 6710, "loss": 0.8152, "lr": 1.980938638174133e-06, "epoch": 1.505961251862891, "percentage": 30.12, "elapsed_time": "0:26:32", "remaining_time": "1:01:34", "throughput": 5198.58, "total_tokens": 8278016} {"current_steps": 2022, "total_steps": 6710, "loss": 0.7121, "lr": 1.9804638001618404e-06, "epoch": 1.5067064083457526, "percentage": 30.13, "elapsed_time": "0:26:33", "remaining_time": "1:01:33", "throughput": 5198.53, "total_tokens": 8282112} {"current_steps": 2023, "total_steps": 6710, "loss": 0.7817, "lr": 1.979988802026667e-06, "epoch": 1.507451564828614, "percentage": 30.15, "elapsed_time": "0:26:33", "remaining_time": "1:01:33", "throughput": 5198.4, "total_tokens": 8286208} {"current_steps": 2024, "total_steps": 6710, "loss": 0.9041, "lr": 1.9795136438727356e-06, "epoch": 1.5081967213114753, "percentage": 30.16, "elapsed_time": "0:26:34", "remaining_time": "1:01:32", "throughput": 5198.33, "total_tokens": 8290304} {"current_steps": 2025, "total_steps": 6710, "loss": 0.9788, "lr": 1.979038325804205e-06, "epoch": 1.5089418777943369, "percentage": 30.18, "elapsed_time": "0:26:35", "remaining_time": "1:01:31", "throughput": 5198.25, "total_tokens": 8294400} {"current_steps": 2026, "total_steps": 6710, "loss": 0.9794, "lr": 1.978562847925267e-06, "epoch": 1.5096870342771982, "percentage": 30.19, "elapsed_time": "0:26:36", "remaining_time": "1:01:30", "throughput": 5198.19, "total_tokens": 8298496} {"current_steps": 2027, "total_steps": 6710, "loss": 0.6799, "lr": 1.9780872103401504e-06, "epoch": 1.5104321907600595, "percentage": 30.21, "elapsed_time": "0:26:37", "remaining_time": "1:01:30", "throughput": 5198.03, "total_tokens": 8302592} {"current_steps": 2028, "total_steps": 6710, "loss": 0.5488, "lr": 1.9776114131531183e-06, "epoch": 1.511177347242921, "percentage": 30.22, "elapsed_time": "0:26:38", "remaining_time": "1:01:29", "throughput": 5197.96, "total_tokens": 8306688} {"current_steps": 2029, "total_steps": 6710, "loss": 1.0917, "lr": 1.9771354564684685e-06, "epoch": 1.5119225037257824, "percentage": 30.24, "elapsed_time": "0:26:38", "remaining_time": "1:01:28", "throughput": 5197.88, "total_tokens": 8310784} {"current_steps": 2030, "total_steps": 6710, "loss": 0.5443, "lr": 1.9766593403905347e-06, "epoch": 1.5126676602086437, "percentage": 30.25, "elapsed_time": "0:26:39", "remaining_time": "1:01:28", "throughput": 5197.73, "total_tokens": 8314880} {"current_steps": 2031, "total_steps": 6710, "loss": 0.7051, "lr": 1.9761830650236844e-06, "epoch": 1.5134128166915053, "percentage": 30.27, "elapsed_time": "0:26:40", "remaining_time": "1:01:27", "throughput": 5197.69, "total_tokens": 8318976} {"current_steps": 2032, "total_steps": 6710, "loss": 0.7641, "lr": 1.9757066304723218e-06, "epoch": 1.5141579731743666, "percentage": 30.28, "elapsed_time": "0:26:41", "remaining_time": "1:01:26", "throughput": 5197.65, "total_tokens": 8323072} {"current_steps": 2033, "total_steps": 6710, "loss": 0.5923, "lr": 1.975230036840883e-06, "epoch": 1.514903129657228, "percentage": 30.3, "elapsed_time": "0:26:42", "remaining_time": "1:01:25", "throughput": 5197.47, "total_tokens": 8327168} {"current_steps": 2034, "total_steps": 6710, "loss": 0.8794, "lr": 1.9747532842338413e-06, "epoch": 1.5156482861400895, "percentage": 30.31, "elapsed_time": "0:26:42", "remaining_time": "1:01:25", "throughput": 5197.42, "total_tokens": 8331264} {"current_steps": 2035, "total_steps": 6710, "loss": 0.8095, "lr": 1.9742763727557047e-06, "epoch": 1.5163934426229508, "percentage": 30.33, "elapsed_time": "0:26:43", "remaining_time": "1:01:24", "throughput": 5197.34, "total_tokens": 8335360} {"current_steps": 2036, "total_steps": 6710, "loss": 0.8827, "lr": 1.9737993025110157e-06, "epoch": 1.5171385991058122, "percentage": 30.34, "elapsed_time": "0:26:44", "remaining_time": "1:01:23", "throughput": 5197.32, "total_tokens": 8339456} {"current_steps": 2037, "total_steps": 6710, "loss": 0.7378, "lr": 1.9733220736043505e-06, "epoch": 1.5178837555886737, "percentage": 30.36, "elapsed_time": "0:26:45", "remaining_time": "1:01:22", "throughput": 5197.2, "total_tokens": 8343552} {"current_steps": 2038, "total_steps": 6710, "loss": 0.573, "lr": 1.972844686140323e-06, "epoch": 1.518628912071535, "percentage": 30.37, "elapsed_time": "0:26:46", "remaining_time": "1:01:22", "throughput": 5197.1, "total_tokens": 8347648} {"current_steps": 2039, "total_steps": 6710, "loss": 0.8084, "lr": 1.972367140223578e-06, "epoch": 1.5193740685543964, "percentage": 30.39, "elapsed_time": "0:26:47", "remaining_time": "1:01:21", "throughput": 5197.05, "total_tokens": 8351744} {"current_steps": 2040, "total_steps": 6710, "loss": 0.7734, "lr": 1.9718894359587977e-06, "epoch": 1.520119225037258, "percentage": 30.4, "elapsed_time": "0:26:47", "remaining_time": "1:01:20", "throughput": 5197.03, "total_tokens": 8355840} {"current_steps": 2041, "total_steps": 6710, "loss": 0.6374, "lr": 1.971411573450698e-06, "epoch": 1.5208643815201193, "percentage": 30.42, "elapsed_time": "0:26:48", "remaining_time": "1:01:19", "throughput": 5196.88, "total_tokens": 8359936} {"current_steps": 2042, "total_steps": 6710, "loss": 0.683, "lr": 1.9709335528040306e-06, "epoch": 1.5216095380029806, "percentage": 30.43, "elapsed_time": "0:26:49", "remaining_time": "1:01:19", "throughput": 5196.84, "total_tokens": 8364032} {"current_steps": 2043, "total_steps": 6710, "loss": 0.7245, "lr": 1.9704553741235797e-06, "epoch": 1.5223546944858422, "percentage": 30.45, "elapsed_time": "0:26:50", "remaining_time": "1:01:18", "throughput": 5196.8, "total_tokens": 8368128} {"current_steps": 2044, "total_steps": 6710, "loss": 0.8661, "lr": 1.969977037514167e-06, "epoch": 1.5230998509687033, "percentage": 30.46, "elapsed_time": "0:26:51", "remaining_time": "1:01:17", "throughput": 5196.71, "total_tokens": 8372224} {"current_steps": 2045, "total_steps": 6710, "loss": 0.8827, "lr": 1.9694985430806467e-06, "epoch": 1.5238450074515648, "percentage": 30.48, "elapsed_time": "0:26:51", "remaining_time": "1:01:16", "throughput": 5196.69, "total_tokens": 8376320} {"current_steps": 2046, "total_steps": 6710, "loss": 0.7172, "lr": 1.9690198909279077e-06, "epoch": 1.5245901639344264, "percentage": 30.49, "elapsed_time": "0:26:52", "remaining_time": "1:01:16", "throughput": 5196.65, "total_tokens": 8380416} {"current_steps": 2047, "total_steps": 6710, "loss": 0.8031, "lr": 1.9685410811608746e-06, "epoch": 1.5253353204172875, "percentage": 30.51, "elapsed_time": "0:26:53", "remaining_time": "1:01:15", "throughput": 5196.51, "total_tokens": 8384512} {"current_steps": 2048, "total_steps": 6710, "loss": 0.6411, "lr": 1.9680621138845056e-06, "epoch": 1.526080476900149, "percentage": 30.52, "elapsed_time": "0:26:54", "remaining_time": "1:01:14", "throughput": 5196.44, "total_tokens": 8388608} {"current_steps": 2049, "total_steps": 6710, "loss": 0.7383, "lr": 1.9675829892037936e-06, "epoch": 1.5268256333830106, "percentage": 30.54, "elapsed_time": "0:26:55", "remaining_time": "1:01:13", "throughput": 5196.44, "total_tokens": 8392704} {"current_steps": 2050, "total_steps": 6710, "loss": 0.766, "lr": 1.9671037072237664e-06, "epoch": 1.5275707898658717, "percentage": 30.55, "elapsed_time": "0:26:55", "remaining_time": "1:01:13", "throughput": 5196.43, "total_tokens": 8396800} {"current_steps": 2051, "total_steps": 6710, "loss": 0.9248, "lr": 1.966624268049486e-06, "epoch": 1.5283159463487332, "percentage": 30.57, "elapsed_time": "0:26:56", "remaining_time": "1:01:12", "throughput": 5196.24, "total_tokens": 8400896} {"current_steps": 2052, "total_steps": 6710, "loss": 0.5944, "lr": 1.9661446717860496e-06, "epoch": 1.5290611028315948, "percentage": 30.58, "elapsed_time": "0:26:57", "remaining_time": "1:01:11", "throughput": 5196.2, "total_tokens": 8404992} {"current_steps": 2053, "total_steps": 6710, "loss": 0.7988, "lr": 1.9656649185385864e-06, "epoch": 1.529806259314456, "percentage": 30.6, "elapsed_time": "0:26:58", "remaining_time": "1:01:10", "throughput": 5196.19, "total_tokens": 8409088} {"current_steps": 2054, "total_steps": 6710, "loss": 0.5616, "lr": 1.9651850084122633e-06, "epoch": 1.5305514157973175, "percentage": 30.61, "elapsed_time": "0:26:59", "remaining_time": "1:01:10", "throughput": 5196.15, "total_tokens": 8413184} {"current_steps": 2055, "total_steps": 6710, "loss": 0.9779, "lr": 1.9647049415122792e-06, "epoch": 1.5312965722801788, "percentage": 30.63, "elapsed_time": "0:26:59", "remaining_time": "1:01:09", "throughput": 5196.0, "total_tokens": 8417280} {"current_steps": 2056, "total_steps": 6710, "loss": 0.7533, "lr": 1.9642247179438682e-06, "epoch": 1.5320417287630401, "percentage": 30.64, "elapsed_time": "0:27:00", "remaining_time": "1:01:08", "throughput": 5195.96, "total_tokens": 8421376} {"current_steps": 2057, "total_steps": 6710, "loss": 0.6336, "lr": 1.9637443378122997e-06, "epoch": 1.5327868852459017, "percentage": 30.66, "elapsed_time": "0:27:01", "remaining_time": "1:01:07", "throughput": 5195.95, "total_tokens": 8425472} {"current_steps": 2058, "total_steps": 6710, "loss": 0.6061, "lr": 1.9632638012228753e-06, "epoch": 1.533532041728763, "percentage": 30.67, "elapsed_time": "0:27:02", "remaining_time": "1:01:07", "throughput": 5195.95, "total_tokens": 8429568} {"current_steps": 2059, "total_steps": 6710, "loss": 0.9124, "lr": 1.962783108280933e-06, "epoch": 1.5342771982116243, "percentage": 30.69, "elapsed_time": "0:27:03", "remaining_time": "1:01:06", "throughput": 5195.86, "total_tokens": 8433664} {"current_steps": 2060, "total_steps": 6710, "loss": 0.5938, "lr": 1.9623022590918434e-06, "epoch": 1.535022354694486, "percentage": 30.7, "elapsed_time": "0:27:03", "remaining_time": "1:01:05", "throughput": 5195.86, "total_tokens": 8437760} {"current_steps": 2061, "total_steps": 6710, "loss": 0.7769, "lr": 1.961821253761012e-06, "epoch": 1.5357675111773472, "percentage": 30.72, "elapsed_time": "0:27:04", "remaining_time": "1:01:04", "throughput": 5195.75, "total_tokens": 8441856} {"current_steps": 2062, "total_steps": 6710, "loss": 0.8616, "lr": 1.961340092393879e-06, "epoch": 1.5365126676602086, "percentage": 30.73, "elapsed_time": "0:27:05", "remaining_time": "1:01:04", "throughput": 5195.56, "total_tokens": 8445952} {"current_steps": 2063, "total_steps": 6710, "loss": 0.7325, "lr": 1.9608587750959186e-06, "epoch": 1.53725782414307, "percentage": 30.75, "elapsed_time": "0:27:06", "remaining_time": "1:01:03", "throughput": 5195.51, "total_tokens": 8450048} {"current_steps": 2064, "total_steps": 6710, "loss": 0.9506, "lr": 1.9603773019726387e-06, "epoch": 1.5380029806259314, "percentage": 30.76, "elapsed_time": "0:27:07", "remaining_time": "1:01:02", "throughput": 5195.46, "total_tokens": 8454144} {"current_steps": 2065, "total_steps": 6710, "loss": 0.5519, "lr": 1.9598956731295816e-06, "epoch": 1.5387481371087928, "percentage": 30.77, "elapsed_time": "0:27:08", "remaining_time": "1:01:02", "throughput": 5195.46, "total_tokens": 8458240} {"current_steps": 2066, "total_steps": 6710, "loss": 0.7527, "lr": 1.959413888672324e-06, "epoch": 1.5394932935916543, "percentage": 30.79, "elapsed_time": "0:27:08", "remaining_time": "1:01:01", "throughput": 5195.36, "total_tokens": 8462336} {"current_steps": 2067, "total_steps": 6710, "loss": 1.015, "lr": 1.9589319487064757e-06, "epoch": 1.5402384500745157, "percentage": 30.8, "elapsed_time": "0:27:09", "remaining_time": "1:01:00", "throughput": 5195.36, "total_tokens": 8466432} {"current_steps": 2068, "total_steps": 6710, "loss": 0.7763, "lr": 1.958449853337683e-06, "epoch": 1.540983606557377, "percentage": 30.82, "elapsed_time": "0:27:10", "remaining_time": "1:00:59", "throughput": 5195.35, "total_tokens": 8470528} {"current_steps": 2069, "total_steps": 6710, "loss": 0.8995, "lr": 1.9579676026716227e-06, "epoch": 1.5417287630402385, "percentage": 30.83, "elapsed_time": "0:27:11", "remaining_time": "1:00:58", "throughput": 5195.33, "total_tokens": 8474624} {"current_steps": 2070, "total_steps": 6710, "loss": 0.8029, "lr": 1.9574851968140092e-06, "epoch": 1.5424739195230999, "percentage": 30.85, "elapsed_time": "0:27:12", "remaining_time": "1:00:58", "throughput": 5195.21, "total_tokens": 8478720} {"current_steps": 2071, "total_steps": 6710, "loss": 0.7278, "lr": 1.957002635870588e-06, "epoch": 1.5432190760059612, "percentage": 30.86, "elapsed_time": "0:27:12", "remaining_time": "1:00:57", "throughput": 5195.16, "total_tokens": 8482816} {"current_steps": 2072, "total_steps": 6710, "loss": 0.3949, "lr": 1.9565199199471414e-06, "epoch": 1.5439642324888228, "percentage": 30.88, "elapsed_time": "0:27:13", "remaining_time": "1:00:56", "throughput": 5195.15, "total_tokens": 8486912} {"current_steps": 2073, "total_steps": 6710, "loss": 0.8169, "lr": 1.9560370491494827e-06, "epoch": 1.544709388971684, "percentage": 30.89, "elapsed_time": "0:27:14", "remaining_time": "1:00:55", "throughput": 5195.08, "total_tokens": 8491008} {"current_steps": 2074, "total_steps": 6710, "loss": 0.6117, "lr": 1.955554023583462e-06, "epoch": 1.5454545454545454, "percentage": 30.91, "elapsed_time": "0:27:15", "remaining_time": "1:00:55", "throughput": 5195.08, "total_tokens": 8495104} {"current_steps": 2075, "total_steps": 6710, "loss": 1.1341, "lr": 1.9550708433549605e-06, "epoch": 1.546199701937407, "percentage": 30.92, "elapsed_time": "0:27:16", "remaining_time": "1:00:54", "throughput": 5195.0, "total_tokens": 8499200} {"current_steps": 2076, "total_steps": 6710, "loss": 0.5256, "lr": 1.9545875085698955e-06, "epoch": 1.5469448584202683, "percentage": 30.94, "elapsed_time": "0:27:16", "remaining_time": "1:00:53", "throughput": 5194.86, "total_tokens": 8503296} {"current_steps": 2077, "total_steps": 6710, "loss": 0.6214, "lr": 1.954104019334218e-06, "epoch": 1.5476900149031296, "percentage": 30.95, "elapsed_time": "0:27:17", "remaining_time": "1:00:52", "throughput": 5194.85, "total_tokens": 8507392} {"current_steps": 2078, "total_steps": 6710, "loss": 0.8861, "lr": 1.953620375753911e-06, "epoch": 1.5484351713859912, "percentage": 30.97, "elapsed_time": "0:27:18", "remaining_time": "1:00:52", "throughput": 5194.85, "total_tokens": 8511488} {"current_steps": 2079, "total_steps": 6710, "loss": 0.7485, "lr": 1.953136577934994e-06, "epoch": 1.5491803278688525, "percentage": 30.98, "elapsed_time": "0:27:19", "remaining_time": "1:00:51", "throughput": 5194.8, "total_tokens": 8515584} {"current_steps": 2080, "total_steps": 6710, "loss": 0.7887, "lr": 1.952652625983518e-06, "epoch": 1.5499254843517138, "percentage": 31.0, "elapsed_time": "0:27:20", "remaining_time": "1:00:50", "throughput": 5194.69, "total_tokens": 8519680} {"current_steps": 2081, "total_steps": 6710, "loss": 0.8405, "lr": 1.9521685200055687e-06, "epoch": 1.5506706408345754, "percentage": 31.01, "elapsed_time": "0:27:20", "remaining_time": "1:00:50", "throughput": 5194.61, "total_tokens": 8523776} {"current_steps": 2082, "total_steps": 6710, "loss": 0.7363, "lr": 1.951684260107266e-06, "epoch": 1.5514157973174365, "percentage": 31.03, "elapsed_time": "0:27:21", "remaining_time": "1:00:49", "throughput": 5194.54, "total_tokens": 8527872} {"current_steps": 2083, "total_steps": 6710, "loss": 0.8393, "lr": 1.9511998463947636e-06, "epoch": 1.552160953800298, "percentage": 31.04, "elapsed_time": "0:27:22", "remaining_time": "1:00:48", "throughput": 5194.5, "total_tokens": 8531968} {"current_steps": 2084, "total_steps": 6710, "loss": 0.5989, "lr": 1.950715278974247e-06, "epoch": 1.5529061102831596, "percentage": 31.06, "elapsed_time": "0:27:23", "remaining_time": "1:00:47", "throughput": 5194.4, "total_tokens": 8536064} {"current_steps": 2085, "total_steps": 6710, "loss": 0.9128, "lr": 1.950230557951938e-06, "epoch": 1.5536512667660207, "percentage": 31.07, "elapsed_time": "0:27:24", "remaining_time": "1:00:47", "throughput": 5194.36, "total_tokens": 8540160} {"current_steps": 2086, "total_steps": 6710, "loss": 0.4605, "lr": 1.9497456834340912e-06, "epoch": 1.5543964232488823, "percentage": 31.09, "elapsed_time": "0:27:24", "remaining_time": "1:00:46", "throughput": 5194.31, "total_tokens": 8544256} {"current_steps": 2087, "total_steps": 6710, "loss": 1.0317, "lr": 1.9492606555269932e-06, "epoch": 1.5551415797317438, "percentage": 31.1, "elapsed_time": "0:27:25", "remaining_time": "1:00:45", "throughput": 5194.17, "total_tokens": 8548352} {"current_steps": 2088, "total_steps": 6710, "loss": 0.6327, "lr": 1.9487754743369667e-06, "epoch": 1.555886736214605, "percentage": 31.12, "elapsed_time": "0:27:26", "remaining_time": "1:00:44", "throughput": 5194.1, "total_tokens": 8552448} {"current_steps": 2089, "total_steps": 6710, "loss": 0.4872, "lr": 1.9482901399703664e-06, "epoch": 1.5566318926974665, "percentage": 31.13, "elapsed_time": "0:27:27", "remaining_time": "1:00:44", "throughput": 5194.03, "total_tokens": 8556544} {"current_steps": 2090, "total_steps": 6710, "loss": 0.602, "lr": 1.947804652533581e-06, "epoch": 1.5573770491803278, "percentage": 31.15, "elapsed_time": "0:27:28", "remaining_time": "1:00:43", "throughput": 5193.96, "total_tokens": 8560640} {"current_steps": 2091, "total_steps": 6710, "loss": 0.6024, "lr": 1.947319012133033e-06, "epoch": 1.5581222056631892, "percentage": 31.16, "elapsed_time": "0:27:29", "remaining_time": "1:00:42", "throughput": 5193.84, "total_tokens": 8564736} {"current_steps": 2092, "total_steps": 6710, "loss": 0.7804, "lr": 1.9468332188751787e-06, "epoch": 1.5588673621460507, "percentage": 31.18, "elapsed_time": "0:27:29", "remaining_time": "1:00:41", "throughput": 5193.8, "total_tokens": 8568832} {"current_steps": 2093, "total_steps": 6710, "loss": 0.7384, "lr": 1.9463472728665065e-06, "epoch": 1.559612518628912, "percentage": 31.19, "elapsed_time": "0:27:30", "remaining_time": "1:00:41", "throughput": 5193.81, "total_tokens": 8572928} {"current_steps": 2094, "total_steps": 6710, "loss": 0.5744, "lr": 1.9458611742135402e-06, "epoch": 1.5603576751117734, "percentage": 31.21, "elapsed_time": "0:27:31", "remaining_time": "1:00:40", "throughput": 5193.64, "total_tokens": 8577024} {"current_steps": 2095, "total_steps": 6710, "loss": 0.6146, "lr": 1.9453749230228354e-06, "epoch": 1.561102831594635, "percentage": 31.22, "elapsed_time": "0:27:32", "remaining_time": "1:00:39", "throughput": 5193.62, "total_tokens": 8581120} {"current_steps": 2096, "total_steps": 6710, "loss": 1.0057, "lr": 1.944888519400982e-06, "epoch": 1.5618479880774963, "percentage": 31.24, "elapsed_time": "0:27:33", "remaining_time": "1:00:38", "throughput": 5193.54, "total_tokens": 8585216} {"current_steps": 2097, "total_steps": 6710, "loss": 0.6682, "lr": 1.9444019634546034e-06, "epoch": 1.5625931445603576, "percentage": 31.25, "elapsed_time": "0:27:33", "remaining_time": "1:00:38", "throughput": 5193.49, "total_tokens": 8589312} {"current_steps": 2098, "total_steps": 6710, "loss": 0.4519, "lr": 1.943915255290356e-06, "epoch": 1.5633383010432191, "percentage": 31.27, "elapsed_time": "0:27:34", "remaining_time": "1:00:37", "throughput": 5193.42, "total_tokens": 8593408} {"current_steps": 2099, "total_steps": 6710, "loss": 0.8564, "lr": 1.943428395014929e-06, "epoch": 1.5640834575260805, "percentage": 31.28, "elapsed_time": "0:27:35", "remaining_time": "1:00:36", "throughput": 5193.4, "total_tokens": 8597504} {"current_steps": 2100, "total_steps": 6710, "loss": 0.6908, "lr": 1.9429413827350468e-06, "epoch": 1.5648286140089418, "percentage": 31.3, "elapsed_time": "0:27:36", "remaining_time": "1:00:35", "throughput": 5193.34, "total_tokens": 8601600} {"current_steps": 2101, "total_steps": 6710, "loss": 0.827, "lr": 1.9424542185574656e-06, "epoch": 1.5655737704918034, "percentage": 31.31, "elapsed_time": "0:27:37", "remaining_time": "1:00:35", "throughput": 5193.27, "total_tokens": 8605696} {"current_steps": 2102, "total_steps": 6710, "loss": 0.4904, "lr": 1.941966902588975e-06, "epoch": 1.5663189269746647, "percentage": 31.33, "elapsed_time": "0:27:37", "remaining_time": "1:00:34", "throughput": 5193.15, "total_tokens": 8609792} {"current_steps": 2103, "total_steps": 6710, "loss": 0.7761, "lr": 1.9414794349363976e-06, "epoch": 1.567064083457526, "percentage": 31.34, "elapsed_time": "0:27:38", "remaining_time": "1:00:33", "throughput": 5193.07, "total_tokens": 8613888} {"current_steps": 2104, "total_steps": 6710, "loss": 0.9227, "lr": 1.940991815706591e-06, "epoch": 1.5678092399403876, "percentage": 31.36, "elapsed_time": "0:27:39", "remaining_time": "1:00:33", "throughput": 5192.94, "total_tokens": 8617984} {"current_steps": 2105, "total_steps": 6710, "loss": 0.7205, "lr": 1.9405040450064443e-06, "epoch": 1.568554396423249, "percentage": 31.37, "elapsed_time": "0:27:40", "remaining_time": "1:00:32", "throughput": 5192.78, "total_tokens": 8622080} {"current_steps": 2106, "total_steps": 6710, "loss": 0.7615, "lr": 1.9400161229428805e-06, "epoch": 1.5692995529061102, "percentage": 31.39, "elapsed_time": "0:27:41", "remaining_time": "1:00:31", "throughput": 5192.69, "total_tokens": 8626176} {"current_steps": 2107, "total_steps": 6710, "loss": 0.8497, "lr": 1.9395280496228553e-06, "epoch": 1.5700447093889718, "percentage": 31.4, "elapsed_time": "0:27:42", "remaining_time": "1:00:30", "throughput": 5192.56, "total_tokens": 8630272} {"current_steps": 2108, "total_steps": 6710, "loss": 0.768, "lr": 1.9390398251533578e-06, "epoch": 1.5707898658718331, "percentage": 31.42, "elapsed_time": "0:27:42", "remaining_time": "1:00:30", "throughput": 5192.42, "total_tokens": 8634368} {"current_steps": 2109, "total_steps": 6710, "loss": 0.7872, "lr": 1.9385514496414105e-06, "epoch": 1.5715350223546944, "percentage": 31.43, "elapsed_time": "0:27:43", "remaining_time": "1:00:29", "throughput": 5192.4, "total_tokens": 8638464} {"current_steps": 2110, "total_steps": 6710, "loss": 0.654, "lr": 1.9380629231940684e-06, "epoch": 1.572280178837556, "percentage": 31.45, "elapsed_time": "0:27:44", "remaining_time": "1:00:28", "throughput": 5192.4, "total_tokens": 8642560} {"current_steps": 2111, "total_steps": 6710, "loss": 0.8486, "lr": 1.937574245918421e-06, "epoch": 1.5730253353204173, "percentage": 31.46, "elapsed_time": "0:27:45", "remaining_time": "1:00:27", "throughput": 5192.28, "total_tokens": 8646656} {"current_steps": 2112, "total_steps": 6710, "loss": 0.8393, "lr": 1.9370854179215888e-06, "epoch": 1.5737704918032787, "percentage": 31.48, "elapsed_time": "0:27:46", "remaining_time": "1:00:27", "throughput": 5192.25, "total_tokens": 8650752} {"current_steps": 2113, "total_steps": 6710, "loss": 0.9178, "lr": 1.9365964393107265e-06, "epoch": 1.5745156482861402, "percentage": 31.49, "elapsed_time": "0:27:46", "remaining_time": "1:00:26", "throughput": 5192.19, "total_tokens": 8654848} {"current_steps": 2114, "total_steps": 6710, "loss": 0.8375, "lr": 1.9361073101930223e-06, "epoch": 1.5752608047690015, "percentage": 31.51, "elapsed_time": "0:27:47", "remaining_time": "1:00:25", "throughput": 5192.12, "total_tokens": 8658944} {"current_steps": 2115, "total_steps": 6710, "loss": 0.9243, "lr": 1.9356180306756965e-06, "epoch": 1.5760059612518629, "percentage": 31.52, "elapsed_time": "0:27:48", "remaining_time": "1:00:24", "throughput": 5192.09, "total_tokens": 8663040} {"current_steps": 2116, "total_steps": 6710, "loss": 0.764, "lr": 1.9351286008660026e-06, "epoch": 1.5767511177347244, "percentage": 31.54, "elapsed_time": "0:27:49", "remaining_time": "1:00:24", "throughput": 5192.07, "total_tokens": 8667136} {"current_steps": 2117, "total_steps": 6710, "loss": 0.9405, "lr": 1.934639020871227e-06, "epoch": 1.5774962742175855, "percentage": 31.55, "elapsed_time": "0:27:50", "remaining_time": "1:00:23", "throughput": 5192.0, "total_tokens": 8671232} {"current_steps": 2118, "total_steps": 6710, "loss": 0.5942, "lr": 1.934149290798689e-06, "epoch": 1.578241430700447, "percentage": 31.56, "elapsed_time": "0:27:50", "remaining_time": "1:00:22", "throughput": 5191.95, "total_tokens": 8675328} {"current_steps": 2119, "total_steps": 6710, "loss": 1.039, "lr": 1.933659410755742e-06, "epoch": 1.5789865871833086, "percentage": 31.58, "elapsed_time": "0:27:51", "remaining_time": "1:00:21", "throughput": 5191.94, "total_tokens": 8679424} {"current_steps": 2120, "total_steps": 6710, "loss": 0.5888, "lr": 1.93316938084977e-06, "epoch": 1.5797317436661698, "percentage": 31.59, "elapsed_time": "0:27:52", "remaining_time": "1:00:21", "throughput": 5191.93, "total_tokens": 8683520} {"current_steps": 2121, "total_steps": 6710, "loss": 0.7347, "lr": 1.9326792011881912e-06, "epoch": 1.5804769001490313, "percentage": 31.61, "elapsed_time": "0:27:53", "remaining_time": "1:00:20", "throughput": 5191.91, "total_tokens": 8687616} {"current_steps": 2122, "total_steps": 6710, "loss": 0.7622, "lr": 1.932188871878457e-06, "epoch": 1.5812220566318929, "percentage": 31.62, "elapsed_time": "0:27:54", "remaining_time": "1:00:19", "throughput": 5191.82, "total_tokens": 8691712} {"current_steps": 2123, "total_steps": 6710, "loss": 0.6037, "lr": 1.931698393028051e-06, "epoch": 1.581967213114754, "percentage": 31.64, "elapsed_time": "0:27:54", "remaining_time": "1:00:18", "throughput": 5191.83, "total_tokens": 8695808} {"current_steps": 2124, "total_steps": 6710, "loss": 0.8124, "lr": 1.9312077647444886e-06, "epoch": 1.5827123695976155, "percentage": 31.65, "elapsed_time": "0:27:55", "remaining_time": "1:00:18", "throughput": 5191.8, "total_tokens": 8699904} {"current_steps": 2125, "total_steps": 6710, "loss": 0.898, "lr": 1.9307169871353206e-06, "epoch": 1.5834575260804769, "percentage": 31.67, "elapsed_time": "0:27:56", "remaining_time": "1:00:17", "throughput": 5191.71, "total_tokens": 8704000} {"current_steps": 2126, "total_steps": 6710, "loss": 0.9343, "lr": 1.9302260603081284e-06, "epoch": 1.5842026825633382, "percentage": 31.68, "elapsed_time": "0:27:57", "remaining_time": "1:00:16", "throughput": 5191.73, "total_tokens": 8708096} {"current_steps": 2127, "total_steps": 6710, "loss": 0.8778, "lr": 1.9297349843705267e-06, "epoch": 1.5849478390461997, "percentage": 31.7, "elapsed_time": "0:27:58", "remaining_time": "1:00:15", "throughput": 5191.72, "total_tokens": 8712192} {"current_steps": 2128, "total_steps": 6710, "loss": 0.8074, "lr": 1.929243759430162e-06, "epoch": 1.585692995529061, "percentage": 31.71, "elapsed_time": "0:27:58", "remaining_time": "1:00:15", "throughput": 5191.62, "total_tokens": 8716288} {"current_steps": 2129, "total_steps": 6710, "loss": 0.6313, "lr": 1.9287523855947154e-06, "epoch": 1.5864381520119224, "percentage": 31.73, "elapsed_time": "0:27:59", "remaining_time": "1:00:14", "throughput": 5191.57, "total_tokens": 8720384} {"current_steps": 2130, "total_steps": 6710, "loss": 0.8059, "lr": 1.928260862971899e-06, "epoch": 1.587183308494784, "percentage": 31.74, "elapsed_time": "0:28:00", "remaining_time": "1:00:13", "throughput": 5191.56, "total_tokens": 8724480} {"current_steps": 2131, "total_steps": 6710, "loss": 0.8395, "lr": 1.927769191669458e-06, "epoch": 1.5879284649776453, "percentage": 31.76, "elapsed_time": "0:28:01", "remaining_time": "1:00:12", "throughput": 5191.52, "total_tokens": 8728576} {"current_steps": 2132, "total_steps": 6710, "loss": 0.6044, "lr": 1.9272773717951707e-06, "epoch": 1.5886736214605066, "percentage": 31.77, "elapsed_time": "0:28:02", "remaining_time": "1:00:12", "throughput": 5191.39, "total_tokens": 8732672} {"current_steps": 2133, "total_steps": 6710, "loss": 0.753, "lr": 1.9267854034568477e-06, "epoch": 1.5894187779433682, "percentage": 31.79, "elapsed_time": "0:28:02", "remaining_time": "1:00:11", "throughput": 5191.29, "total_tokens": 8736768} {"current_steps": 2134, "total_steps": 6710, "loss": 0.9087, "lr": 1.9262932867623314e-06, "epoch": 1.5901639344262295, "percentage": 31.8, "elapsed_time": "0:28:03", "remaining_time": "1:00:10", "throughput": 5191.23, "total_tokens": 8740864} {"current_steps": 2135, "total_steps": 6710, "loss": 0.822, "lr": 1.9258010218194972e-06, "epoch": 1.5909090909090908, "percentage": 31.82, "elapsed_time": "0:28:04", "remaining_time": "1:00:09", "throughput": 5191.2, "total_tokens": 8744960} {"current_steps": 2136, "total_steps": 6710, "loss": 0.5674, "lr": 1.9253086087362536e-06, "epoch": 1.5916542473919524, "percentage": 31.83, "elapsed_time": "0:28:05", "remaining_time": "1:00:09", "throughput": 5191.19, "total_tokens": 8749056} {"current_steps": 2137, "total_steps": 6710, "loss": 0.9132, "lr": 1.9248160476205406e-06, "epoch": 1.5923994038748137, "percentage": 31.85, "elapsed_time": "0:28:06", "remaining_time": "1:00:08", "throughput": 5191.19, "total_tokens": 8753152} {"current_steps": 2138, "total_steps": 6710, "loss": 0.7409, "lr": 1.9243233385803316e-06, "epoch": 1.593144560357675, "percentage": 31.86, "elapsed_time": "0:28:06", "remaining_time": "1:00:07", "throughput": 5191.18, "total_tokens": 8757248} {"current_steps": 2139, "total_steps": 6710, "loss": 0.8176, "lr": 1.9238304817236313e-06, "epoch": 1.5938897168405366, "percentage": 31.88, "elapsed_time": "0:28:07", "remaining_time": "1:00:06", "throughput": 5191.16, "total_tokens": 8761344} {"current_steps": 2140, "total_steps": 6710, "loss": 0.721, "lr": 1.9233374771584784e-06, "epoch": 1.594634873323398, "percentage": 31.89, "elapsed_time": "0:28:08", "remaining_time": "1:00:05", "throughput": 5191.06, "total_tokens": 8765440} {"current_steps": 2141, "total_steps": 6710, "loss": 0.9456, "lr": 1.922844324992942e-06, "epoch": 1.5953800298062593, "percentage": 31.91, "elapsed_time": "0:28:09", "remaining_time": "1:00:05", "throughput": 5191.02, "total_tokens": 8769536} {"current_steps": 2142, "total_steps": 6710, "loss": 0.8984, "lr": 1.9223510253351253e-06, "epoch": 1.5961251862891208, "percentage": 31.92, "elapsed_time": "0:28:10", "remaining_time": "1:00:04", "throughput": 5190.99, "total_tokens": 8773632} {"current_steps": 2143, "total_steps": 6710, "loss": 0.993, "lr": 1.9218575782931626e-06, "epoch": 1.5968703427719821, "percentage": 31.94, "elapsed_time": "0:28:10", "remaining_time": "1:00:03", "throughput": 5190.91, "total_tokens": 8777728} {"current_steps": 2144, "total_steps": 6710, "loss": 0.8204, "lr": 1.9213639839752215e-06, "epoch": 1.5976154992548435, "percentage": 31.95, "elapsed_time": "0:28:11", "remaining_time": "1:00:03", "throughput": 5190.75, "total_tokens": 8781824} {"current_steps": 2145, "total_steps": 6710, "loss": 0.8726, "lr": 1.920870242489501e-06, "epoch": 1.598360655737705, "percentage": 31.97, "elapsed_time": "0:28:12", "remaining_time": "1:00:02", "throughput": 5190.67, "total_tokens": 8785920} {"current_steps": 2146, "total_steps": 6710, "loss": 0.7083, "lr": 1.920376353944233e-06, "epoch": 1.5991058122205664, "percentage": 31.98, "elapsed_time": "0:28:13", "remaining_time": "1:00:01", "throughput": 5190.56, "total_tokens": 8790016} {"current_steps": 2147, "total_steps": 6710, "loss": 0.937, "lr": 1.919882318447681e-06, "epoch": 1.5998509687034277, "percentage": 32.0, "elapsed_time": "0:28:14", "remaining_time": "1:00:00", "throughput": 5190.44, "total_tokens": 8794112} {"current_steps": 2148, "total_steps": 6710, "loss": 0.8217, "lr": 1.9193881361081415e-06, "epoch": 1.6005961251862892, "percentage": 32.01, "elapsed_time": "0:28:15", "remaining_time": "1:00:00", "throughput": 5190.33, "total_tokens": 8798208} {"current_steps": 2149, "total_steps": 6710, "loss": 0.7174, "lr": 1.9188938070339428e-06, "epoch": 1.6013412816691506, "percentage": 32.03, "elapsed_time": "0:28:15", "remaining_time": "0:59:59", "throughput": 5190.34, "total_tokens": 8802304} {"current_steps": 2150, "total_steps": 6710, "loss": 0.9726, "lr": 1.9183993313334455e-06, "epoch": 1.602086438152012, "percentage": 32.04, "elapsed_time": "0:28:16", "remaining_time": "0:59:58", "throughput": 5190.18, "total_tokens": 8806400} {"current_steps": 2151, "total_steps": 6710, "loss": 0.9086, "lr": 1.9179047091150414e-06, "epoch": 1.6028315946348735, "percentage": 32.06, "elapsed_time": "0:28:17", "remaining_time": "0:59:57", "throughput": 5190.13, "total_tokens": 8810496} {"current_steps": 2152, "total_steps": 6710, "loss": 0.9792, "lr": 1.917409940487156e-06, "epoch": 1.6035767511177346, "percentage": 32.07, "elapsed_time": "0:28:18", "remaining_time": "0:59:57", "throughput": 5190.08, "total_tokens": 8814592} {"current_steps": 2153, "total_steps": 6710, "loss": 0.5756, "lr": 1.9169150255582464e-06, "epoch": 1.6043219076005961, "percentage": 32.09, "elapsed_time": "0:28:19", "remaining_time": "0:59:56", "throughput": 5189.93, "total_tokens": 8818688} {"current_steps": 2154, "total_steps": 6710, "loss": 0.8135, "lr": 1.916419964436801e-06, "epoch": 1.6050670640834577, "percentage": 32.1, "elapsed_time": "0:28:19", "remaining_time": "0:59:55", "throughput": 5189.87, "total_tokens": 8822784} {"current_steps": 2155, "total_steps": 6710, "loss": 0.7177, "lr": 1.91592475723134e-06, "epoch": 1.6058122205663188, "percentage": 32.12, "elapsed_time": "0:28:20", "remaining_time": "0:59:54", "throughput": 5189.83, "total_tokens": 8826880} {"current_steps": 2156, "total_steps": 6710, "loss": 0.8452, "lr": 1.9154294040504174e-06, "epoch": 1.6065573770491803, "percentage": 32.13, "elapsed_time": "0:28:21", "remaining_time": "0:59:54", "throughput": 5189.75, "total_tokens": 8830976} {"current_steps": 2157, "total_steps": 6710, "loss": 0.8262, "lr": 1.914933905002618e-06, "epoch": 1.6073025335320419, "percentage": 32.15, "elapsed_time": "0:28:22", "remaining_time": "0:59:53", "throughput": 5189.62, "total_tokens": 8835072} {"current_steps": 2158, "total_steps": 6710, "loss": 0.7745, "lr": 1.9144382601965584e-06, "epoch": 1.608047690014903, "percentage": 32.16, "elapsed_time": "0:28:23", "remaining_time": "0:59:52", "throughput": 5189.52, "total_tokens": 8839168} {"current_steps": 2159, "total_steps": 6710, "loss": 0.8278, "lr": 1.9139424697408877e-06, "epoch": 1.6087928464977646, "percentage": 32.18, "elapsed_time": "0:28:24", "remaining_time": "0:59:52", "throughput": 5189.39, "total_tokens": 8843264} {"current_steps": 2160, "total_steps": 6710, "loss": 0.9915, "lr": 1.913446533744287e-06, "epoch": 1.6095380029806259, "percentage": 32.19, "elapsed_time": "0:28:24", "remaining_time": "0:59:51", "throughput": 5189.17, "total_tokens": 8847360} {"current_steps": 2161, "total_steps": 6710, "loss": 0.7092, "lr": 1.912950452315468e-06, "epoch": 1.6102831594634872, "percentage": 32.21, "elapsed_time": "0:28:25", "remaining_time": "0:59:50", "throughput": 5189.0, "total_tokens": 8851456} {"current_steps": 2162, "total_steps": 6710, "loss": 0.9986, "lr": 1.9124542255631763e-06, "epoch": 1.6110283159463488, "percentage": 32.22, "elapsed_time": "0:28:26", "remaining_time": "0:59:50", "throughput": 5188.92, "total_tokens": 8855552} {"current_steps": 2163, "total_steps": 6710, "loss": 0.6872, "lr": 1.9119578535961888e-06, "epoch": 1.61177347242921, "percentage": 32.24, "elapsed_time": "0:28:27", "remaining_time": "0:59:49", "throughput": 5188.8, "total_tokens": 8859648} {"current_steps": 2164, "total_steps": 6710, "loss": 0.9358, "lr": 1.9114613365233115e-06, "epoch": 1.6125186289120714, "percentage": 32.25, "elapsed_time": "0:28:28", "remaining_time": "0:59:48", "throughput": 5188.78, "total_tokens": 8863744} {"current_steps": 2165, "total_steps": 6710, "loss": 0.7972, "lr": 1.910964674453387e-06, "epoch": 1.613263785394933, "percentage": 32.27, "elapsed_time": "0:28:29", "remaining_time": "0:59:47", "throughput": 5188.76, "total_tokens": 8867840} {"current_steps": 2166, "total_steps": 6710, "loss": 0.9061, "lr": 1.9104678674952858e-06, "epoch": 1.6140089418777943, "percentage": 32.28, "elapsed_time": "0:28:29", "remaining_time": "0:59:47", "throughput": 5188.75, "total_tokens": 8871936} {"current_steps": 2167, "total_steps": 6710, "loss": 0.9333, "lr": 1.9099709157579124e-06, "epoch": 1.6147540983606556, "percentage": 32.3, "elapsed_time": "0:28:30", "remaining_time": "0:59:46", "throughput": 5188.65, "total_tokens": 8876032} {"current_steps": 2168, "total_steps": 6710, "loss": 0.7366, "lr": 1.909473819350201e-06, "epoch": 1.6154992548435172, "percentage": 32.31, "elapsed_time": "0:28:31", "remaining_time": "0:59:45", "throughput": 5188.65, "total_tokens": 8880128} {"current_steps": 2169, "total_steps": 6710, "loss": 0.7859, "lr": 1.9089765783811193e-06, "epoch": 1.6162444113263785, "percentage": 32.32, "elapsed_time": "0:28:32", "remaining_time": "0:59:44", "throughput": 5188.6, "total_tokens": 8884224} {"current_steps": 2170, "total_steps": 6710, "loss": 0.8399, "lr": 1.9084791929596662e-06, "epoch": 1.6169895678092399, "percentage": 32.34, "elapsed_time": "0:28:33", "remaining_time": "0:59:44", "throughput": 5188.49, "total_tokens": 8888320} {"current_steps": 2171, "total_steps": 6710, "loss": 0.8492, "lr": 1.907981663194872e-06, "epoch": 1.6177347242921014, "percentage": 32.35, "elapsed_time": "0:28:33", "remaining_time": "0:59:43", "throughput": 5188.42, "total_tokens": 8892416} {"current_steps": 2172, "total_steps": 6710, "loss": 0.7083, "lr": 1.9074839891957995e-06, "epoch": 1.6184798807749627, "percentage": 32.37, "elapsed_time": "0:28:34", "remaining_time": "0:59:42", "throughput": 5188.37, "total_tokens": 8896512} {"current_steps": 2173, "total_steps": 6710, "loss": 0.8047, "lr": 1.9069861710715413e-06, "epoch": 1.619225037257824, "percentage": 32.38, "elapsed_time": "0:28:35", "remaining_time": "0:59:41", "throughput": 5188.31, "total_tokens": 8900608} {"current_steps": 2174, "total_steps": 6710, "loss": 0.9092, "lr": 1.906488208931223e-06, "epoch": 1.6199701937406856, "percentage": 32.4, "elapsed_time": "0:28:36", "remaining_time": "0:59:41", "throughput": 5188.15, "total_tokens": 8904704} {"current_steps": 2175, "total_steps": 6710, "loss": 0.7106, "lr": 1.9059901028840014e-06, "epoch": 1.620715350223547, "percentage": 32.41, "elapsed_time": "0:28:37", "remaining_time": "0:59:40", "throughput": 5188.1, "total_tokens": 8908800} {"current_steps": 2176, "total_steps": 6710, "loss": 0.6825, "lr": 1.9054918530390654e-06, "epoch": 1.6214605067064083, "percentage": 32.43, "elapsed_time": "0:28:37", "remaining_time": "0:59:39", "throughput": 5188.04, "total_tokens": 8912896} {"current_steps": 2177, "total_steps": 6710, "loss": 0.6509, "lr": 1.904993459505634e-06, "epoch": 1.6222056631892698, "percentage": 32.44, "elapsed_time": "0:28:38", "remaining_time": "0:59:38", "throughput": 5188.04, "total_tokens": 8916992} {"current_steps": 2178, "total_steps": 6710, "loss": 0.8192, "lr": 1.90449492239296e-06, "epoch": 1.6229508196721312, "percentage": 32.46, "elapsed_time": "0:28:39", "remaining_time": "0:59:38", "throughput": 5187.96, "total_tokens": 8921088} {"current_steps": 2179, "total_steps": 6710, "loss": 1.0025, "lr": 1.9039962418103248e-06, "epoch": 1.6236959761549925, "percentage": 32.47, "elapsed_time": "0:28:40", "remaining_time": "0:59:37", "throughput": 5187.91, "total_tokens": 8925184} {"current_steps": 2180, "total_steps": 6710, "loss": 0.7238, "lr": 1.903497417867044e-06, "epoch": 1.624441132637854, "percentage": 32.49, "elapsed_time": "0:28:41", "remaining_time": "0:59:36", "throughput": 5187.89, "total_tokens": 8929280} {"current_steps": 2181, "total_steps": 6710, "loss": 0.7912, "lr": 1.9029984506724628e-06, "epoch": 1.6251862891207154, "percentage": 32.5, "elapsed_time": "0:28:41", "remaining_time": "0:59:35", "throughput": 5187.82, "total_tokens": 8933376} {"current_steps": 2182, "total_steps": 6710, "loss": 0.6922, "lr": 1.9024993403359582e-06, "epoch": 1.6259314456035767, "percentage": 32.52, "elapsed_time": "0:28:42", "remaining_time": "0:59:35", "throughput": 5187.83, "total_tokens": 8937472} {"current_steps": 2183, "total_steps": 6710, "loss": 0.8642, "lr": 1.9020000869669386e-06, "epoch": 1.6266766020864383, "percentage": 32.53, "elapsed_time": "0:28:43", "remaining_time": "0:59:34", "throughput": 5187.8, "total_tokens": 8941568} {"current_steps": 2184, "total_steps": 6710, "loss": 0.5313, "lr": 1.9015006906748446e-06, "epoch": 1.6274217585692996, "percentage": 32.55, "elapsed_time": "0:28:44", "remaining_time": "0:59:33", "throughput": 5187.77, "total_tokens": 8945664} {"current_steps": 2185, "total_steps": 6710, "loss": 0.6639, "lr": 1.9010011515691468e-06, "epoch": 1.628166915052161, "percentage": 32.56, "elapsed_time": "0:28:45", "remaining_time": "0:59:32", "throughput": 5187.75, "total_tokens": 8949760} {"current_steps": 2186, "total_steps": 6710, "loss": 1.0073, "lr": 1.9005014697593483e-06, "epoch": 1.6289120715350225, "percentage": 32.58, "elapsed_time": "0:28:45", "remaining_time": "0:59:31", "throughput": 5187.72, "total_tokens": 8953856} {"current_steps": 2187, "total_steps": 6710, "loss": 0.8097, "lr": 1.9000016453549828e-06, "epoch": 1.6296572280178836, "percentage": 32.59, "elapsed_time": "0:28:46", "remaining_time": "0:59:31", "throughput": 5187.69, "total_tokens": 8957952} {"current_steps": 2188, "total_steps": 6710, "loss": 0.887, "lr": 1.899501678465615e-06, "epoch": 1.6304023845007451, "percentage": 32.61, "elapsed_time": "0:28:47", "remaining_time": "0:59:30", "throughput": 5187.57, "total_tokens": 8962048} {"current_steps": 2189, "total_steps": 6710, "loss": 0.9171, "lr": 1.8990015692008413e-06, "epoch": 1.6311475409836067, "percentage": 32.62, "elapsed_time": "0:28:48", "remaining_time": "0:59:29", "throughput": 5187.55, "total_tokens": 8966144} {"current_steps": 2190, "total_steps": 6710, "loss": 0.5415, "lr": 1.8985013176702893e-06, "epoch": 1.6318926974664678, "percentage": 32.64, "elapsed_time": "0:28:49", "remaining_time": "0:59:28", "throughput": 5187.54, "total_tokens": 8970240} {"current_steps": 2191, "total_steps": 6710, "loss": 0.6207, "lr": 1.898000923983618e-06, "epoch": 1.6326378539493294, "percentage": 32.65, "elapsed_time": "0:28:49", "remaining_time": "0:59:28", "throughput": 5187.52, "total_tokens": 8974336} {"current_steps": 2192, "total_steps": 6710, "loss": 1.0076, "lr": 1.897500388250517e-06, "epoch": 1.633383010432191, "percentage": 32.67, "elapsed_time": "0:28:50", "remaining_time": "0:59:27", "throughput": 5187.42, "total_tokens": 8978432} {"current_steps": 2193, "total_steps": 6710, "loss": 0.9423, "lr": 1.8969997105807076e-06, "epoch": 1.634128166915052, "percentage": 32.68, "elapsed_time": "0:28:51", "remaining_time": "0:59:26", "throughput": 5187.41, "total_tokens": 8982528} {"current_steps": 2194, "total_steps": 6710, "loss": 0.7315, "lr": 1.896498891083941e-06, "epoch": 1.6348733233979136, "percentage": 32.7, "elapsed_time": "0:28:52", "remaining_time": "0:59:25", "throughput": 5187.4, "total_tokens": 8986624} {"current_steps": 2195, "total_steps": 6710, "loss": 0.9464, "lr": 1.8959979298700012e-06, "epoch": 1.635618479880775, "percentage": 32.71, "elapsed_time": "0:28:53", "remaining_time": "0:59:25", "throughput": 5187.29, "total_tokens": 8990720} {"current_steps": 2196, "total_steps": 6710, "loss": 0.63, "lr": 1.8954968270487026e-06, "epoch": 1.6363636363636362, "percentage": 32.73, "elapsed_time": "0:28:54", "remaining_time": "0:59:24", "throughput": 5187.28, "total_tokens": 8994816} {"current_steps": 2197, "total_steps": 6710, "loss": 0.707, "lr": 1.89499558272989e-06, "epoch": 1.6371087928464978, "percentage": 32.74, "elapsed_time": "0:28:54", "remaining_time": "0:59:23", "throughput": 5187.21, "total_tokens": 8998912} {"current_steps": 2198, "total_steps": 6710, "loss": 0.7296, "lr": 1.8944941970234402e-06, "epoch": 1.6378539493293591, "percentage": 32.76, "elapsed_time": "0:28:55", "remaining_time": "0:59:22", "throughput": 5187.12, "total_tokens": 9003008} {"current_steps": 2199, "total_steps": 6710, "loss": 0.7671, "lr": 1.8939926700392603e-06, "epoch": 1.6385991058122205, "percentage": 32.77, "elapsed_time": "0:28:56", "remaining_time": "0:59:22", "throughput": 5187.08, "total_tokens": 9007104} {"current_steps": 2200, "total_steps": 6710, "loss": 0.9156, "lr": 1.8934910018872886e-06, "epoch": 1.639344262295082, "percentage": 32.79, "elapsed_time": "0:28:57", "remaining_time": "0:59:21", "throughput": 5186.98, "total_tokens": 9011200} {"current_steps": 2201, "total_steps": 6710, "loss": 0.8891, "lr": 1.8929891926774945e-06, "epoch": 1.6400894187779433, "percentage": 32.8, "elapsed_time": "0:28:58", "remaining_time": "0:59:20", "throughput": 5186.9, "total_tokens": 9015296} {"current_steps": 2202, "total_steps": 6710, "loss": 0.8984, "lr": 1.8924872425198777e-06, "epoch": 1.6408345752608047, "percentage": 32.82, "elapsed_time": "0:28:58", "remaining_time": "0:59:19", "throughput": 5186.86, "total_tokens": 9019392} {"current_steps": 2203, "total_steps": 6710, "loss": 0.5693, "lr": 1.8919851515244698e-06, "epoch": 1.6415797317436662, "percentage": 32.83, "elapsed_time": "0:28:59", "remaining_time": "0:59:19", "throughput": 5186.84, "total_tokens": 9023488} {"current_steps": 2204, "total_steps": 6710, "loss": 0.6143, "lr": 1.8914829198013323e-06, "epoch": 1.6423248882265276, "percentage": 32.85, "elapsed_time": "0:29:00", "remaining_time": "0:59:18", "throughput": 5186.79, "total_tokens": 9027584} {"current_steps": 2205, "total_steps": 6710, "loss": 0.7863, "lr": 1.8909805474605581e-06, "epoch": 1.6430700447093889, "percentage": 32.86, "elapsed_time": "0:29:01", "remaining_time": "0:59:17", "throughput": 5186.65, "total_tokens": 9031680} {"current_steps": 2206, "total_steps": 6710, "loss": 0.7408, "lr": 1.8904780346122709e-06, "epoch": 1.6438152011922504, "percentage": 32.88, "elapsed_time": "0:29:02", "remaining_time": "0:59:16", "throughput": 5186.56, "total_tokens": 9035776} {"current_steps": 2207, "total_steps": 6710, "loss": 0.9875, "lr": 1.8899753813666256e-06, "epoch": 1.6445603576751118, "percentage": 32.89, "elapsed_time": "0:29:02", "remaining_time": "0:59:16", "throughput": 5186.45, "total_tokens": 9039872} {"current_steps": 2208, "total_steps": 6710, "loss": 0.7876, "lr": 1.8894725878338064e-06, "epoch": 1.645305514157973, "percentage": 32.91, "elapsed_time": "0:29:03", "remaining_time": "0:59:15", "throughput": 5186.43, "total_tokens": 9043968} {"current_steps": 2209, "total_steps": 6710, "loss": 0.9592, "lr": 1.8889696541240298e-06, "epoch": 1.6460506706408347, "percentage": 32.92, "elapsed_time": "0:29:04", "remaining_time": "0:59:14", "throughput": 5186.32, "total_tokens": 9048064} {"current_steps": 2210, "total_steps": 6710, "loss": 0.9166, "lr": 1.8884665803475428e-06, "epoch": 1.646795827123696, "percentage": 32.94, "elapsed_time": "0:29:05", "remaining_time": "0:59:14", "throughput": 5186.24, "total_tokens": 9052160} {"current_steps": 2211, "total_steps": 6710, "loss": 0.8387, "lr": 1.8879633666146216e-06, "epoch": 1.6475409836065573, "percentage": 32.95, "elapsed_time": "0:29:06", "remaining_time": "0:59:13", "throughput": 5186.18, "total_tokens": 9056256} {"current_steps": 2212, "total_steps": 6710, "loss": 0.6236, "lr": 1.8874600130355752e-06, "epoch": 1.6482861400894189, "percentage": 32.97, "elapsed_time": "0:29:07", "remaining_time": "0:59:12", "throughput": 5186.12, "total_tokens": 9060352} {"current_steps": 2213, "total_steps": 6710, "loss": 0.8283, "lr": 1.8869565197207423e-06, "epoch": 1.6490312965722802, "percentage": 32.98, "elapsed_time": "0:29:07", "remaining_time": "0:59:11", "throughput": 5186.13, "total_tokens": 9064448} {"current_steps": 2214, "total_steps": 6710, "loss": 0.8317, "lr": 1.8864528867804922e-06, "epoch": 1.6497764530551415, "percentage": 33.0, "elapsed_time": "0:29:08", "remaining_time": "0:59:10", "throughput": 5186.11, "total_tokens": 9068544} {"current_steps": 2215, "total_steps": 6710, "loss": 0.8288, "lr": 1.885949114325224e-06, "epoch": 1.650521609538003, "percentage": 33.01, "elapsed_time": "0:29:09", "remaining_time": "0:59:10", "throughput": 5186.09, "total_tokens": 9072640} {"current_steps": 2216, "total_steps": 6710, "loss": 0.8772, "lr": 1.885445202465369e-06, "epoch": 1.6512667660208644, "percentage": 33.03, "elapsed_time": "0:29:10", "remaining_time": "0:59:09", "throughput": 5185.95, "total_tokens": 9076736} {"current_steps": 2217, "total_steps": 6710, "loss": 0.7784, "lr": 1.8849411513113886e-06, "epoch": 1.6520119225037257, "percentage": 33.04, "elapsed_time": "0:29:11", "remaining_time": "0:59:08", "throughput": 5185.87, "total_tokens": 9080832} {"current_steps": 2218, "total_steps": 6710, "loss": 0.6874, "lr": 1.8844369609737734e-06, "epoch": 1.6527570789865873, "percentage": 33.06, "elapsed_time": "0:29:11", "remaining_time": "0:59:07", "throughput": 5185.82, "total_tokens": 9084928} {"current_steps": 2219, "total_steps": 6710, "loss": 0.831, "lr": 1.8839326315630463e-06, "epoch": 1.6535022354694486, "percentage": 33.07, "elapsed_time": "0:29:12", "remaining_time": "0:59:07", "throughput": 5185.77, "total_tokens": 9089024} {"current_steps": 2220, "total_steps": 6710, "loss": 0.6357, "lr": 1.88342816318976e-06, "epoch": 1.65424739195231, "percentage": 33.08, "elapsed_time": "0:29:13", "remaining_time": "0:59:06", "throughput": 5185.63, "total_tokens": 9093120} {"current_steps": 2221, "total_steps": 6710, "loss": 0.5853, "lr": 1.8829235559644967e-06, "epoch": 1.6549925484351715, "percentage": 33.1, "elapsed_time": "0:29:14", "remaining_time": "0:59:05", "throughput": 5185.58, "total_tokens": 9097216} {"current_steps": 2222, "total_steps": 6710, "loss": 0.9527, "lr": 1.8824188099978708e-06, "epoch": 1.6557377049180326, "percentage": 33.11, "elapsed_time": "0:29:15", "remaining_time": "0:59:05", "throughput": 5185.57, "total_tokens": 9101312} {"current_steps": 2223, "total_steps": 6710, "loss": 0.6133, "lr": 1.8819139254005258e-06, "epoch": 1.6564828614008942, "percentage": 33.13, "elapsed_time": "0:29:15", "remaining_time": "0:59:04", "throughput": 5185.39, "total_tokens": 9105408} {"current_steps": 2224, "total_steps": 6710, "loss": 0.6729, "lr": 1.8814089022831358e-06, "epoch": 1.6572280178837557, "percentage": 33.14, "elapsed_time": "0:29:16", "remaining_time": "0:59:03", "throughput": 5185.37, "total_tokens": 9109504} {"current_steps": 2225, "total_steps": 6710, "loss": 0.7084, "lr": 1.8809037407564062e-06, "epoch": 1.6579731743666168, "percentage": 33.16, "elapsed_time": "0:29:17", "remaining_time": "0:59:02", "throughput": 5185.33, "total_tokens": 9113600} {"current_steps": 2226, "total_steps": 6710, "loss": 0.6407, "lr": 1.8803984409310716e-06, "epoch": 1.6587183308494784, "percentage": 33.17, "elapsed_time": "0:29:18", "remaining_time": "0:59:02", "throughput": 5185.28, "total_tokens": 9117696} {"current_steps": 2227, "total_steps": 6710, "loss": 0.8668, "lr": 1.8798930029178968e-06, "epoch": 1.65946348733234, "percentage": 33.19, "elapsed_time": "0:29:19", "remaining_time": "0:59:01", "throughput": 5185.19, "total_tokens": 9121792} {"current_steps": 2228, "total_steps": 6710, "loss": 0.6095, "lr": 1.8793874268276785e-06, "epoch": 1.660208643815201, "percentage": 33.2, "elapsed_time": "0:29:20", "remaining_time": "0:59:00", "throughput": 5185.16, "total_tokens": 9125888} {"current_steps": 2229, "total_steps": 6710, "loss": 0.9043, "lr": 1.8788817127712416e-06, "epoch": 1.6609538002980626, "percentage": 33.22, "elapsed_time": "0:29:20", "remaining_time": "0:58:59", "throughput": 5185.11, "total_tokens": 9129984} {"current_steps": 2230, "total_steps": 6710, "loss": 0.9768, "lr": 1.8783758608594426e-06, "epoch": 1.661698956780924, "percentage": 33.23, "elapsed_time": "0:29:21", "remaining_time": "0:58:59", "throughput": 5184.9, "total_tokens": 9134080} {"current_steps": 2231, "total_steps": 6710, "loss": 0.5945, "lr": 1.877869871203168e-06, "epoch": 1.6624441132637853, "percentage": 33.25, "elapsed_time": "0:29:22", "remaining_time": "0:58:58", "throughput": 5184.86, "total_tokens": 9138176} {"current_steps": 2232, "total_steps": 6710, "loss": 0.4582, "lr": 1.8773637439133343e-06, "epoch": 1.6631892697466468, "percentage": 33.26, "elapsed_time": "0:29:23", "remaining_time": "0:58:57", "throughput": 5184.84, "total_tokens": 9142272} {"current_steps": 2233, "total_steps": 6710, "loss": 0.9218, "lr": 1.8768574791008882e-06, "epoch": 1.6639344262295082, "percentage": 33.28, "elapsed_time": "0:29:24", "remaining_time": "0:58:56", "throughput": 5184.78, "total_tokens": 9146368} {"current_steps": 2234, "total_steps": 6710, "loss": 1.0306, "lr": 1.8763510768768067e-06, "epoch": 1.6646795827123695, "percentage": 33.29, "elapsed_time": "0:29:24", "remaining_time": "0:58:56", "throughput": 5184.71, "total_tokens": 9150464} {"current_steps": 2235, "total_steps": 6710, "loss": 0.8921, "lr": 1.8758445373520961e-06, "epoch": 1.665424739195231, "percentage": 33.31, "elapsed_time": "0:29:25", "remaining_time": "0:58:55", "throughput": 5184.66, "total_tokens": 9154560} {"current_steps": 2236, "total_steps": 6710, "loss": 0.7571, "lr": 1.8753378606377944e-06, "epoch": 1.6661698956780924, "percentage": 33.32, "elapsed_time": "0:29:26", "remaining_time": "0:58:54", "throughput": 5184.64, "total_tokens": 9158656} {"current_steps": 2237, "total_steps": 6710, "loss": 0.6254, "lr": 1.874831046844968e-06, "epoch": 1.6669150521609537, "percentage": 33.34, "elapsed_time": "0:29:27", "remaining_time": "0:58:53", "throughput": 5184.51, "total_tokens": 9162752} {"current_steps": 2238, "total_steps": 6710, "loss": 0.5998, "lr": 1.8743240960847147e-06, "epoch": 1.6676602086438153, "percentage": 33.35, "elapsed_time": "0:29:28", "remaining_time": "0:58:53", "throughput": 5184.47, "total_tokens": 9166848} {"current_steps": 2239, "total_steps": 6710, "loss": 0.7507, "lr": 1.8738170084681615e-06, "epoch": 1.6684053651266766, "percentage": 33.37, "elapsed_time": "0:29:28", "remaining_time": "0:58:52", "throughput": 5184.45, "total_tokens": 9170944} {"current_steps": 2240, "total_steps": 6710, "loss": 0.9042, "lr": 1.8733097841064653e-06, "epoch": 1.669150521609538, "percentage": 33.38, "elapsed_time": "0:29:29", "remaining_time": "0:58:51", "throughput": 5184.42, "total_tokens": 9175040} {"current_steps": 2241, "total_steps": 6710, "loss": 0.7864, "lr": 1.872802423110814e-06, "epoch": 1.6698956780923995, "percentage": 33.4, "elapsed_time": "0:29:30", "remaining_time": "0:58:50", "throughput": 5184.33, "total_tokens": 9179136} {"current_steps": 2242, "total_steps": 6710, "loss": 0.5395, "lr": 1.8722949255924241e-06, "epoch": 1.6706408345752608, "percentage": 33.41, "elapsed_time": "0:29:31", "remaining_time": "0:58:50", "throughput": 5184.27, "total_tokens": 9183232} {"current_steps": 2243, "total_steps": 6710, "loss": 0.6697, "lr": 1.871787291662543e-06, "epoch": 1.6713859910581221, "percentage": 33.43, "elapsed_time": "0:29:32", "remaining_time": "0:58:49", "throughput": 5184.19, "total_tokens": 9187328} {"current_steps": 2244, "total_steps": 6710, "loss": 0.6458, "lr": 1.8712795214324475e-06, "epoch": 1.6721311475409837, "percentage": 33.44, "elapsed_time": "0:29:33", "remaining_time": "0:58:48", "throughput": 5184.04, "total_tokens": 9191424} {"current_steps": 2245, "total_steps": 6710, "loss": 0.6309, "lr": 1.8707716150134447e-06, "epoch": 1.672876304023845, "percentage": 33.46, "elapsed_time": "0:29:33", "remaining_time": "0:58:47", "throughput": 5184.03, "total_tokens": 9195520} {"current_steps": 2246, "total_steps": 6710, "loss": 0.6988, "lr": 1.870263572516871e-06, "epoch": 1.6736214605067063, "percentage": 33.47, "elapsed_time": "0:29:34", "remaining_time": "0:58:47", "throughput": 5183.97, "total_tokens": 9199616} {"current_steps": 2247, "total_steps": 6710, "loss": 0.7052, "lr": 1.8697553940540935e-06, "epoch": 1.674366616989568, "percentage": 33.49, "elapsed_time": "0:29:35", "remaining_time": "0:58:46", "throughput": 5183.94, "total_tokens": 9203712} {"current_steps": 2248, "total_steps": 6710, "loss": 0.5135, "lr": 1.869247079736508e-06, "epoch": 1.6751117734724292, "percentage": 33.5, "elapsed_time": "0:29:36", "remaining_time": "0:58:45", "throughput": 5183.83, "total_tokens": 9207808} {"current_steps": 2249, "total_steps": 6710, "loss": 0.7878, "lr": 1.8687386296755406e-06, "epoch": 1.6758569299552906, "percentage": 33.52, "elapsed_time": "0:29:37", "remaining_time": "0:58:44", "throughput": 5183.84, "total_tokens": 9211904} {"current_steps": 2250, "total_steps": 6710, "loss": 0.8366, "lr": 1.8682300439826476e-06, "epoch": 1.6766020864381521, "percentage": 33.53, "elapsed_time": "0:29:37", "remaining_time": "0:58:44", "throughput": 5183.85, "total_tokens": 9216000} {"current_steps": 2251, "total_steps": 6710, "loss": 0.9015, "lr": 1.8677213227693143e-06, "epoch": 1.6773472429210134, "percentage": 33.55, "elapsed_time": "0:29:38", "remaining_time": "0:58:43", "throughput": 5183.67, "total_tokens": 9220096} {"current_steps": 2252, "total_steps": 6710, "loss": 0.9677, "lr": 1.867212466147056e-06, "epoch": 1.6780923994038748, "percentage": 33.56, "elapsed_time": "0:29:39", "remaining_time": "0:58:42", "throughput": 5183.65, "total_tokens": 9224192} {"current_steps": 2253, "total_steps": 6710, "loss": 0.8318, "lr": 1.8667034742274181e-06, "epoch": 1.6788375558867363, "percentage": 33.58, "elapsed_time": "0:29:40", "remaining_time": "0:58:41", "throughput": 5183.62, "total_tokens": 9228288} {"current_steps": 2254, "total_steps": 6710, "loss": 0.9643, "lr": 1.8661943471219748e-06, "epoch": 1.6795827123695977, "percentage": 33.59, "elapsed_time": "0:29:41", "remaining_time": "0:58:41", "throughput": 5183.62, "total_tokens": 9232384} {"current_steps": 2255, "total_steps": 6710, "loss": 0.8523, "lr": 1.8656850849423308e-06, "epoch": 1.680327868852459, "percentage": 33.61, "elapsed_time": "0:29:41", "remaining_time": "0:58:40", "throughput": 5183.54, "total_tokens": 9236480} {"current_steps": 2256, "total_steps": 6710, "loss": 0.6501, "lr": 1.8651756878001198e-06, "epoch": 1.6810730253353205, "percentage": 33.62, "elapsed_time": "0:29:42", "remaining_time": "0:58:39", "throughput": 5183.48, "total_tokens": 9240576} {"current_steps": 2257, "total_steps": 6710, "loss": 0.9621, "lr": 1.864666155807005e-06, "epoch": 1.6818181818181817, "percentage": 33.64, "elapsed_time": "0:29:43", "remaining_time": "0:58:38", "throughput": 5183.42, "total_tokens": 9244672} {"current_steps": 2258, "total_steps": 6710, "loss": 0.7479, "lr": 1.8641564890746796e-06, "epoch": 1.6825633383010432, "percentage": 33.65, "elapsed_time": "0:29:44", "remaining_time": "0:58:38", "throughput": 5183.27, "total_tokens": 9248768} {"current_steps": 2259, "total_steps": 6710, "loss": 0.5757, "lr": 1.8636466877148669e-06, "epoch": 1.6833084947839048, "percentage": 33.67, "elapsed_time": "0:29:45", "remaining_time": "0:58:37", "throughput": 5183.21, "total_tokens": 9252864} {"current_steps": 2260, "total_steps": 6710, "loss": 0.7505, "lr": 1.8631367518393178e-06, "epoch": 1.6840536512667659, "percentage": 33.68, "elapsed_time": "0:29:45", "remaining_time": "0:58:36", "throughput": 5183.21, "total_tokens": 9256960} {"current_steps": 2261, "total_steps": 6710, "loss": 0.747, "lr": 1.8626266815598152e-06, "epoch": 1.6847988077496274, "percentage": 33.7, "elapsed_time": "0:29:46", "remaining_time": "0:58:35", "throughput": 5183.17, "total_tokens": 9261056} {"current_steps": 2262, "total_steps": 6710, "loss": 0.7668, "lr": 1.862116476988169e-06, "epoch": 1.685543964232489, "percentage": 33.71, "elapsed_time": "0:29:47", "remaining_time": "0:58:35", "throughput": 5183.04, "total_tokens": 9265152} {"current_steps": 2263, "total_steps": 6710, "loss": 0.6812, "lr": 1.8616061382362205e-06, "epoch": 1.68628912071535, "percentage": 33.73, "elapsed_time": "0:29:48", "remaining_time": "0:58:34", "throughput": 5183.02, "total_tokens": 9269248} {"current_steps": 2264, "total_steps": 6710, "loss": 0.8488, "lr": 1.8610956654158389e-06, "epoch": 1.6870342771982116, "percentage": 33.74, "elapsed_time": "0:29:49", "remaining_time": "0:58:33", "throughput": 5182.96, "total_tokens": 9273344} {"current_steps": 2265, "total_steps": 6710, "loss": 0.7937, "lr": 1.8605850586389238e-06, "epoch": 1.687779433681073, "percentage": 33.76, "elapsed_time": "0:29:50", "remaining_time": "0:58:32", "throughput": 5182.85, "total_tokens": 9277440} {"current_steps": 2266, "total_steps": 6710, "loss": 0.7379, "lr": 1.8600743180174038e-06, "epoch": 1.6885245901639343, "percentage": 33.77, "elapsed_time": "0:29:50", "remaining_time": "0:58:32", "throughput": 5182.8, "total_tokens": 9281536} {"current_steps": 2267, "total_steps": 6710, "loss": 0.7815, "lr": 1.8595634436632374e-06, "epoch": 1.6892697466467959, "percentage": 33.79, "elapsed_time": "0:29:51", "remaining_time": "0:58:31", "throughput": 5182.7, "total_tokens": 9285632} {"current_steps": 2268, "total_steps": 6710, "loss": 0.5522, "lr": 1.859052435688411e-06, "epoch": 1.6900149031296572, "percentage": 33.8, "elapsed_time": "0:29:52", "remaining_time": "0:58:30", "throughput": 5182.59, "total_tokens": 9289728} {"current_steps": 2269, "total_steps": 6710, "loss": 0.6393, "lr": 1.858541294204942e-06, "epoch": 1.6907600596125185, "percentage": 33.82, "elapsed_time": "0:29:53", "remaining_time": "0:58:29", "throughput": 5182.51, "total_tokens": 9293824} {"current_steps": 2270, "total_steps": 6710, "loss": 0.9517, "lr": 1.8580300193248757e-06, "epoch": 1.69150521609538, "percentage": 33.83, "elapsed_time": "0:29:54", "remaining_time": "0:58:29", "throughput": 5182.39, "total_tokens": 9297920} {"current_steps": 2271, "total_steps": 6710, "loss": 0.6983, "lr": 1.8575186111602877e-06, "epoch": 1.6922503725782414, "percentage": 33.85, "elapsed_time": "0:29:54", "remaining_time": "0:58:28", "throughput": 5182.34, "total_tokens": 9302016} {"current_steps": 2272, "total_steps": 6710, "loss": 0.8444, "lr": 1.857007069823282e-06, "epoch": 1.6929955290611027, "percentage": 33.86, "elapsed_time": "0:29:55", "remaining_time": "0:58:27", "throughput": 5182.31, "total_tokens": 9306112} {"current_steps": 2273, "total_steps": 6710, "loss": 0.7624, "lr": 1.856495395425992e-06, "epoch": 1.6937406855439643, "percentage": 33.87, "elapsed_time": "0:29:56", "remaining_time": "0:58:26", "throughput": 5182.24, "total_tokens": 9310208} {"current_steps": 2274, "total_steps": 6710, "loss": 0.9802, "lr": 1.855983588080581e-06, "epoch": 1.6944858420268256, "percentage": 33.89, "elapsed_time": "0:29:57", "remaining_time": "0:58:26", "throughput": 5182.26, "total_tokens": 9314304} {"current_steps": 2275, "total_steps": 6710, "loss": 0.6955, "lr": 1.8554716478992398e-06, "epoch": 1.695230998509687, "percentage": 33.9, "elapsed_time": "0:29:58", "remaining_time": "0:58:25", "throughput": 5182.15, "total_tokens": 9318400} {"current_steps": 2276, "total_steps": 6710, "loss": 0.862, "lr": 1.8549595749941904e-06, "epoch": 1.6959761549925485, "percentage": 33.92, "elapsed_time": "0:29:58", "remaining_time": "0:58:24", "throughput": 5182.11, "total_tokens": 9322496} {"current_steps": 2277, "total_steps": 6710, "loss": 0.7899, "lr": 1.854447369477682e-06, "epoch": 1.6967213114754098, "percentage": 33.93, "elapsed_time": "0:29:59", "remaining_time": "0:58:23", "throughput": 5182.06, "total_tokens": 9326592} {"current_steps": 2278, "total_steps": 6710, "loss": 0.9078, "lr": 1.853935031461994e-06, "epoch": 1.6974664679582712, "percentage": 33.95, "elapsed_time": "0:30:00", "remaining_time": "0:58:23", "throughput": 5182.01, "total_tokens": 9330688} {"current_steps": 2279, "total_steps": 6710, "loss": 0.6915, "lr": 1.853422561059435e-06, "epoch": 1.6982116244411327, "percentage": 33.96, "elapsed_time": "0:30:01", "remaining_time": "0:58:22", "throughput": 5181.9, "total_tokens": 9334784} {"current_steps": 2280, "total_steps": 6710, "loss": 0.5629, "lr": 1.8529099583823416e-06, "epoch": 1.698956780923994, "percentage": 33.98, "elapsed_time": "0:30:02", "remaining_time": "0:58:21", "throughput": 5181.9, "total_tokens": 9338880} {"current_steps": 2281, "total_steps": 6710, "loss": 0.5394, "lr": 1.8523972235430803e-06, "epoch": 1.6997019374068554, "percentage": 33.99, "elapsed_time": "0:30:03", "remaining_time": "0:58:20", "throughput": 5181.86, "total_tokens": 9342976} {"current_steps": 2282, "total_steps": 6710, "loss": 0.5814, "lr": 1.8518843566540462e-06, "epoch": 1.700447093889717, "percentage": 34.01, "elapsed_time": "0:30:03", "remaining_time": "0:58:20", "throughput": 5181.84, "total_tokens": 9347072} {"current_steps": 2283, "total_steps": 6710, "loss": 0.9215, "lr": 1.8513713578276631e-06, "epoch": 1.7011922503725783, "percentage": 34.02, "elapsed_time": "0:30:04", "remaining_time": "0:58:19", "throughput": 5181.81, "total_tokens": 9351168} {"current_steps": 2284, "total_steps": 6710, "loss": 0.4942, "lr": 1.8508582271763841e-06, "epoch": 1.7019374068554396, "percentage": 34.04, "elapsed_time": "0:30:05", "remaining_time": "0:58:18", "throughput": 5181.78, "total_tokens": 9355264} {"current_steps": 2285, "total_steps": 6710, "loss": 0.765, "lr": 1.8503449648126912e-06, "epoch": 1.7026825633383011, "percentage": 34.05, "elapsed_time": "0:30:06", "remaining_time": "0:58:17", "throughput": 5181.73, "total_tokens": 9359360} {"current_steps": 2286, "total_steps": 6710, "loss": 0.6078, "lr": 1.8498315708490953e-06, "epoch": 1.7034277198211625, "percentage": 34.07, "elapsed_time": "0:30:07", "remaining_time": "0:58:17", "throughput": 5181.69, "total_tokens": 9363456} {"current_steps": 2287, "total_steps": 6710, "loss": 0.8763, "lr": 1.8493180453981357e-06, "epoch": 1.7041728763040238, "percentage": 34.08, "elapsed_time": "0:30:07", "remaining_time": "0:58:16", "throughput": 5181.66, "total_tokens": 9367552} {"current_steps": 2288, "total_steps": 6710, "loss": 0.7654, "lr": 1.848804388572381e-06, "epoch": 1.7049180327868854, "percentage": 34.1, "elapsed_time": "0:30:08", "remaining_time": "0:58:15", "throughput": 5181.63, "total_tokens": 9371648} {"current_steps": 2289, "total_steps": 6710, "loss": 0.8881, "lr": 1.8482906004844289e-06, "epoch": 1.7056631892697467, "percentage": 34.11, "elapsed_time": "0:30:09", "remaining_time": "0:58:14", "throughput": 5181.56, "total_tokens": 9375744} {"current_steps": 2290, "total_steps": 6710, "loss": 0.8071, "lr": 1.8477766812469045e-06, "epoch": 1.706408345752608, "percentage": 34.13, "elapsed_time": "0:30:10", "remaining_time": "0:58:14", "throughput": 5181.51, "total_tokens": 9379840} {"current_steps": 2291, "total_steps": 6710, "loss": 0.6771, "lr": 1.8472626309724638e-06, "epoch": 1.7071535022354696, "percentage": 34.14, "elapsed_time": "0:30:11", "remaining_time": "0:58:13", "throughput": 5181.48, "total_tokens": 9383936} {"current_steps": 2292, "total_steps": 6710, "loss": 0.7961, "lr": 1.8467484497737887e-06, "epoch": 1.7078986587183307, "percentage": 34.16, "elapsed_time": "0:30:11", "remaining_time": "0:58:12", "throughput": 5181.43, "total_tokens": 9388032} {"current_steps": 2293, "total_steps": 6710, "loss": 0.6324, "lr": 1.8462341377635926e-06, "epoch": 1.7086438152011922, "percentage": 34.17, "elapsed_time": "0:30:12", "remaining_time": "0:58:11", "throughput": 5181.33, "total_tokens": 9392128} {"current_steps": 2294, "total_steps": 6710, "loss": 0.8893, "lr": 1.8457196950546164e-06, "epoch": 1.7093889716840538, "percentage": 34.19, "elapsed_time": "0:30:13", "remaining_time": "0:58:11", "throughput": 5181.29, "total_tokens": 9396224} {"current_steps": 2295, "total_steps": 6710, "loss": 0.742, "lr": 1.8452051217596287e-06, "epoch": 1.710134128166915, "percentage": 34.2, "elapsed_time": "0:30:14", "remaining_time": "0:58:10", "throughput": 5181.26, "total_tokens": 9400320} {"current_steps": 2296, "total_steps": 6710, "loss": 0.7978, "lr": 1.8446904179914283e-06, "epoch": 1.7108792846497765, "percentage": 34.22, "elapsed_time": "0:30:15", "remaining_time": "0:58:10", "throughput": 5180.04, "total_tokens": 9404416} {"current_steps": 2297, "total_steps": 6710, "loss": 0.4678, "lr": 1.8441755838628417e-06, "epoch": 1.711624441132638, "percentage": 34.23, "elapsed_time": "0:30:16", "remaining_time": "0:58:09", "throughput": 5179.98, "total_tokens": 9408512} {"current_steps": 2298, "total_steps": 6710, "loss": 0.2787, "lr": 1.8436606194867244e-06, "epoch": 1.7123695976154991, "percentage": 34.25, "elapsed_time": "0:30:17", "remaining_time": "0:58:08", "throughput": 5179.94, "total_tokens": 9412608} {"current_steps": 2299, "total_steps": 6710, "loss": 0.8856, "lr": 1.8431455249759602e-06, "epoch": 1.7131147540983607, "percentage": 34.26, "elapsed_time": "0:30:17", "remaining_time": "0:58:08", "throughput": 5179.83, "total_tokens": 9416704} {"current_steps": 2300, "total_steps": 6710, "loss": 0.7759, "lr": 1.8426303004434615e-06, "epoch": 1.713859910581222, "percentage": 34.28, "elapsed_time": "0:30:18", "remaining_time": "0:58:07", "throughput": 5179.72, "total_tokens": 9420800} {"current_steps": 2301, "total_steps": 6710, "loss": 0.6387, "lr": 1.8421149460021696e-06, "epoch": 1.7146050670640833, "percentage": 34.29, "elapsed_time": "0:30:19", "remaining_time": "0:58:06", "throughput": 5179.62, "total_tokens": 9424896} {"current_steps": 2302, "total_steps": 6710, "loss": 1.1064, "lr": 1.8415994617650528e-06, "epoch": 1.7153502235469449, "percentage": 34.31, "elapsed_time": "0:30:20", "remaining_time": "0:58:05", "throughput": 5179.49, "total_tokens": 9428992} {"current_steps": 2303, "total_steps": 6710, "loss": 0.6034, "lr": 1.8410838478451098e-06, "epoch": 1.7160953800298062, "percentage": 34.32, "elapsed_time": "0:30:21", "remaining_time": "0:58:05", "throughput": 5179.43, "total_tokens": 9433088} {"current_steps": 2304, "total_steps": 6710, "loss": 0.5015, "lr": 1.8405681043553667e-06, "epoch": 1.7168405365126675, "percentage": 34.34, "elapsed_time": "0:30:22", "remaining_time": "0:58:04", "throughput": 5179.42, "total_tokens": 9437184} {"current_steps": 2305, "total_steps": 6710, "loss": 0.8543, "lr": 1.8400522314088778e-06, "epoch": 1.717585692995529, "percentage": 34.35, "elapsed_time": "0:30:22", "remaining_time": "0:58:03", "throughput": 5179.42, "total_tokens": 9441280} {"current_steps": 2306, "total_steps": 6710, "loss": 0.8591, "lr": 1.8395362291187269e-06, "epoch": 1.7183308494783904, "percentage": 34.37, "elapsed_time": "0:30:23", "remaining_time": "0:58:02", "throughput": 5179.33, "total_tokens": 9445376} {"current_steps": 2307, "total_steps": 6710, "loss": 0.5112, "lr": 1.8390200975980244e-06, "epoch": 1.7190760059612518, "percentage": 34.38, "elapsed_time": "0:30:24", "remaining_time": "0:58:02", "throughput": 5179.34, "total_tokens": 9449472} {"current_steps": 2308, "total_steps": 6710, "loss": 0.7991, "lr": 1.838503836959911e-06, "epoch": 1.7198211624441133, "percentage": 34.4, "elapsed_time": "0:30:25", "remaining_time": "0:58:01", "throughput": 5179.31, "total_tokens": 9453568} {"current_steps": 2309, "total_steps": 6710, "loss": 0.5431, "lr": 1.8379874473175543e-06, "epoch": 1.7205663189269746, "percentage": 34.41, "elapsed_time": "0:30:26", "remaining_time": "0:58:00", "throughput": 5179.27, "total_tokens": 9457664} {"current_steps": 2310, "total_steps": 6710, "loss": 0.843, "lr": 1.8374709287841503e-06, "epoch": 1.721311475409836, "percentage": 34.43, "elapsed_time": "0:30:26", "remaining_time": "0:57:59", "throughput": 5179.26, "total_tokens": 9461760} {"current_steps": 2311, "total_steps": 6710, "loss": 0.8532, "lr": 1.836954281472924e-06, "epoch": 1.7220566318926975, "percentage": 34.44, "elapsed_time": "0:30:27", "remaining_time": "0:57:58", "throughput": 5179.21, "total_tokens": 9465856} {"current_steps": 2312, "total_steps": 6710, "loss": 0.8601, "lr": 1.8364375054971276e-06, "epoch": 1.7228017883755589, "percentage": 34.46, "elapsed_time": "0:30:28", "remaining_time": "0:57:58", "throughput": 5179.18, "total_tokens": 9469952} {"current_steps": 2313, "total_steps": 6710, "loss": 0.7313, "lr": 1.8359206009700425e-06, "epoch": 1.7235469448584202, "percentage": 34.47, "elapsed_time": "0:30:29", "remaining_time": "0:57:57", "throughput": 5179.02, "total_tokens": 9474048} {"current_steps": 2314, "total_steps": 6710, "loss": 0.759, "lr": 1.835403568004978e-06, "epoch": 1.7242921013412817, "percentage": 34.49, "elapsed_time": "0:30:30", "remaining_time": "0:57:56", "throughput": 5178.95, "total_tokens": 9478144} {"current_steps": 2315, "total_steps": 6710, "loss": 0.6122, "lr": 1.8348864067152713e-06, "epoch": 1.725037257824143, "percentage": 34.5, "elapsed_time": "0:30:30", "remaining_time": "0:57:56", "throughput": 5178.91, "total_tokens": 9482240} {"current_steps": 2316, "total_steps": 6710, "loss": 0.8862, "lr": 1.8343691172142877e-06, "epoch": 1.7257824143070044, "percentage": 34.52, "elapsed_time": "0:30:31", "remaining_time": "0:57:55", "throughput": 5178.79, "total_tokens": 9486336} {"current_steps": 2317, "total_steps": 6710, "loss": 0.8742, "lr": 1.8338516996154206e-06, "epoch": 1.726527570789866, "percentage": 34.53, "elapsed_time": "0:30:32", "remaining_time": "0:57:54", "throughput": 5178.73, "total_tokens": 9490432} {"current_steps": 2318, "total_steps": 6710, "loss": 0.8891, "lr": 1.8333341540320923e-06, "epoch": 1.7272727272727273, "percentage": 34.55, "elapsed_time": "0:30:33", "remaining_time": "0:57:53", "throughput": 5178.69, "total_tokens": 9494528} {"current_steps": 2319, "total_steps": 6710, "loss": 0.8102, "lr": 1.832816480577752e-06, "epoch": 1.7280178837555886, "percentage": 34.56, "elapsed_time": "0:30:34", "remaining_time": "0:57:53", "throughput": 5178.61, "total_tokens": 9498624} {"current_steps": 2320, "total_steps": 6710, "loss": 0.8622, "lr": 1.832298679365877e-06, "epoch": 1.7287630402384502, "percentage": 34.58, "elapsed_time": "0:30:35", "remaining_time": "0:57:52", "throughput": 5178.5, "total_tokens": 9502720} {"current_steps": 2321, "total_steps": 6710, "loss": 0.6037, "lr": 1.8317807505099742e-06, "epoch": 1.7295081967213115, "percentage": 34.59, "elapsed_time": "0:30:35", "remaining_time": "0:57:51", "throughput": 5178.45, "total_tokens": 9506816} {"current_steps": 2322, "total_steps": 6710, "loss": 0.9767, "lr": 1.831262694123576e-06, "epoch": 1.7302533532041728, "percentage": 34.61, "elapsed_time": "0:30:36", "remaining_time": "0:57:50", "throughput": 5178.41, "total_tokens": 9510912} {"current_steps": 2323, "total_steps": 6710, "loss": 0.5912, "lr": 1.8307445103202452e-06, "epoch": 1.7309985096870344, "percentage": 34.62, "elapsed_time": "0:30:37", "remaining_time": "0:57:50", "throughput": 5178.4, "total_tokens": 9515008} {"current_steps": 2324, "total_steps": 6710, "loss": 0.8564, "lr": 1.8302261992135704e-06, "epoch": 1.7317436661698957, "percentage": 34.63, "elapsed_time": "0:30:38", "remaining_time": "0:57:49", "throughput": 5178.38, "total_tokens": 9519104} {"current_steps": 2325, "total_steps": 6710, "loss": 0.9171, "lr": 1.8297077609171696e-06, "epoch": 1.732488822652757, "percentage": 34.65, "elapsed_time": "0:30:39", "remaining_time": "0:57:48", "throughput": 5178.35, "total_tokens": 9523200} {"current_steps": 2326, "total_steps": 6710, "loss": 0.6807, "lr": 1.829189195544688e-06, "epoch": 1.7332339791356186, "percentage": 34.66, "elapsed_time": "0:30:39", "remaining_time": "0:57:47", "throughput": 5178.3, "total_tokens": 9527296} {"current_steps": 2327, "total_steps": 6710, "loss": 0.6739, "lr": 1.8286705032097995e-06, "epoch": 1.7339791356184797, "percentage": 34.68, "elapsed_time": "0:30:40", "remaining_time": "0:57:46", "throughput": 5178.24, "total_tokens": 9531392} {"current_steps": 2328, "total_steps": 6710, "loss": 0.7216, "lr": 1.8281516840262044e-06, "epoch": 1.7347242921013413, "percentage": 34.69, "elapsed_time": "0:30:41", "remaining_time": "0:57:46", "throughput": 5178.12, "total_tokens": 9535488} {"current_steps": 2329, "total_steps": 6710, "loss": 0.8508, "lr": 1.8276327381076317e-06, "epoch": 1.7354694485842028, "percentage": 34.71, "elapsed_time": "0:30:42", "remaining_time": "0:57:45", "throughput": 5178.1, "total_tokens": 9539584} {"current_steps": 2330, "total_steps": 6710, "loss": 0.5607, "lr": 1.827113665567838e-06, "epoch": 1.736214605067064, "percentage": 34.72, "elapsed_time": "0:30:43", "remaining_time": "0:57:44", "throughput": 5178.04, "total_tokens": 9543680} {"current_steps": 2331, "total_steps": 6710, "loss": 0.7823, "lr": 1.8265944665206079e-06, "epoch": 1.7369597615499255, "percentage": 34.74, "elapsed_time": "0:30:43", "remaining_time": "0:57:43", "throughput": 5178.01, "total_tokens": 9547776} {"current_steps": 2332, "total_steps": 6710, "loss": 0.383, "lr": 1.8260751410797533e-06, "epoch": 1.737704918032787, "percentage": 34.75, "elapsed_time": "0:30:44", "remaining_time": "0:57:43", "throughput": 5177.94, "total_tokens": 9551872} {"current_steps": 2333, "total_steps": 6710, "loss": 0.8413, "lr": 1.8255556893591147e-06, "epoch": 1.7384500745156481, "percentage": 34.77, "elapsed_time": "0:30:45", "remaining_time": "0:57:42", "throughput": 5177.86, "total_tokens": 9555968} {"current_steps": 2334, "total_steps": 6710, "loss": 0.8302, "lr": 1.825036111472559e-06, "epoch": 1.7391952309985097, "percentage": 34.78, "elapsed_time": "0:30:46", "remaining_time": "0:57:41", "throughput": 5177.8, "total_tokens": 9560064} {"current_steps": 2335, "total_steps": 6710, "loss": 0.7792, "lr": 1.8245164075339816e-06, "epoch": 1.7399403874813713, "percentage": 34.8, "elapsed_time": "0:30:47", "remaining_time": "0:57:40", "throughput": 5177.74, "total_tokens": 9564160} {"current_steps": 2336, "total_steps": 6710, "loss": 0.8532, "lr": 1.8239965776573048e-06, "epoch": 1.7406855439642324, "percentage": 34.81, "elapsed_time": "0:30:47", "remaining_time": "0:57:40", "throughput": 5177.71, "total_tokens": 9568256} {"current_steps": 2337, "total_steps": 6710, "loss": 0.8345, "lr": 1.8234766219564804e-06, "epoch": 1.741430700447094, "percentage": 34.83, "elapsed_time": "0:30:48", "remaining_time": "0:57:39", "throughput": 5177.65, "total_tokens": 9572352} {"current_steps": 2338, "total_steps": 6710, "loss": 0.6299, "lr": 1.8229565405454846e-06, "epoch": 1.7421758569299552, "percentage": 34.84, "elapsed_time": "0:30:49", "remaining_time": "0:57:38", "throughput": 5177.58, "total_tokens": 9576448} {"current_steps": 2339, "total_steps": 6710, "loss": 0.7637, "lr": 1.822436333538324e-06, "epoch": 1.7429210134128166, "percentage": 34.86, "elapsed_time": "0:30:50", "remaining_time": "0:57:38", "throughput": 5177.45, "total_tokens": 9580544} {"current_steps": 2340, "total_steps": 6710, "loss": 0.7656, "lr": 1.8219160010490316e-06, "epoch": 1.7436661698956781, "percentage": 34.87, "elapsed_time": "0:30:51", "remaining_time": "0:57:37", "throughput": 5177.3, "total_tokens": 9584640} {"current_steps": 2341, "total_steps": 6710, "loss": 0.7814, "lr": 1.821395543191668e-06, "epoch": 1.7444113263785395, "percentage": 34.89, "elapsed_time": "0:30:52", "remaining_time": "0:57:36", "throughput": 5177.26, "total_tokens": 9588736} {"current_steps": 2342, "total_steps": 6710, "loss": 0.5757, "lr": 1.8208749600803214e-06, "epoch": 1.7451564828614008, "percentage": 34.9, "elapsed_time": "0:30:52", "remaining_time": "0:57:35", "throughput": 5177.19, "total_tokens": 9592832} {"current_steps": 2343, "total_steps": 6710, "loss": 0.7427, "lr": 1.8203542518291067e-06, "epoch": 1.7459016393442623, "percentage": 34.92, "elapsed_time": "0:30:53", "remaining_time": "0:57:35", "throughput": 5177.13, "total_tokens": 9596928} {"current_steps": 2344, "total_steps": 6710, "loss": 1.0191, "lr": 1.8198334185521677e-06, "epoch": 1.7466467958271237, "percentage": 34.93, "elapsed_time": "0:30:54", "remaining_time": "0:57:34", "throughput": 5177.07, "total_tokens": 9601024} {"current_steps": 2345, "total_steps": 6710, "loss": 0.7398, "lr": 1.8193124603636744e-06, "epoch": 1.747391952309985, "percentage": 34.95, "elapsed_time": "0:30:55", "remaining_time": "0:57:33", "throughput": 5176.98, "total_tokens": 9605120} {"current_steps": 2346, "total_steps": 6710, "loss": 0.7138, "lr": 1.8187913773778244e-06, "epoch": 1.7481371087928466, "percentage": 34.96, "elapsed_time": "0:30:56", "remaining_time": "0:57:32", "throughput": 5176.92, "total_tokens": 9609216} {"current_steps": 2347, "total_steps": 6710, "loss": 0.806, "lr": 1.8182701697088428e-06, "epoch": 1.748882265275708, "percentage": 34.98, "elapsed_time": "0:30:56", "remaining_time": "0:57:32", "throughput": 5176.87, "total_tokens": 9613312} {"current_steps": 2348, "total_steps": 6710, "loss": 0.5165, "lr": 1.8177488374709823e-06, "epoch": 1.7496274217585692, "percentage": 34.99, "elapsed_time": "0:30:57", "remaining_time": "0:57:31", "throughput": 5176.75, "total_tokens": 9617408} {"current_steps": 2349, "total_steps": 6710, "loss": 0.9544, "lr": 1.8172273807785225e-06, "epoch": 1.7503725782414308, "percentage": 35.01, "elapsed_time": "0:30:58", "remaining_time": "0:57:30", "throughput": 5176.67, "total_tokens": 9621504} {"current_steps": 2350, "total_steps": 6710, "loss": 0.9882, "lr": 1.8167057997457705e-06, "epoch": 1.751117734724292, "percentage": 35.02, "elapsed_time": "0:30:59", "remaining_time": "0:57:29", "throughput": 5176.63, "total_tokens": 9625600} {"current_steps": 2351, "total_steps": 6710, "loss": 0.4561, "lr": 1.8161840944870604e-06, "epoch": 1.7518628912071534, "percentage": 35.04, "elapsed_time": "0:31:00", "remaining_time": "0:57:29", "throughput": 5176.52, "total_tokens": 9629696} {"current_steps": 2352, "total_steps": 6710, "loss": 0.6001, "lr": 1.815662265116754e-06, "epoch": 1.752608047690015, "percentage": 35.05, "elapsed_time": "0:31:01", "remaining_time": "0:57:28", "throughput": 5176.45, "total_tokens": 9633792} {"current_steps": 2353, "total_steps": 6710, "loss": 1.0491, "lr": 1.81514031174924e-06, "epoch": 1.7533532041728763, "percentage": 35.07, "elapsed_time": "0:31:01", "remaining_time": "0:57:27", "throughput": 5176.39, "total_tokens": 9637888} {"current_steps": 2354, "total_steps": 6710, "loss": 0.766, "lr": 1.814618234498934e-06, "epoch": 1.7540983606557377, "percentage": 35.08, "elapsed_time": "0:31:02", "remaining_time": "0:57:26", "throughput": 5176.28, "total_tokens": 9641984} {"current_steps": 2355, "total_steps": 6710, "loss": 0.8135, "lr": 1.8140960334802798e-06, "epoch": 1.7548435171385992, "percentage": 35.1, "elapsed_time": "0:31:03", "remaining_time": "0:57:26", "throughput": 5176.22, "total_tokens": 9646080} {"current_steps": 2356, "total_steps": 6710, "loss": 0.5521, "lr": 1.8135737088077465e-06, "epoch": 1.7555886736214605, "percentage": 35.11, "elapsed_time": "0:31:04", "remaining_time": "0:57:25", "throughput": 5176.12, "total_tokens": 9650176} {"current_steps": 2357, "total_steps": 6710, "loss": 0.8375, "lr": 1.813051260595832e-06, "epoch": 1.7563338301043219, "percentage": 35.13, "elapsed_time": "0:31:05", "remaining_time": "0:57:24", "throughput": 5176.12, "total_tokens": 9654272} {"current_steps": 2358, "total_steps": 6710, "loss": 0.7759, "lr": 1.8125286889590608e-06, "epoch": 1.7570789865871834, "percentage": 35.14, "elapsed_time": "0:31:05", "remaining_time": "0:57:23", "throughput": 5176.02, "total_tokens": 9658368} {"current_steps": 2359, "total_steps": 6710, "loss": 0.6984, "lr": 1.812005994011984e-06, "epoch": 1.7578241430700448, "percentage": 35.16, "elapsed_time": "0:31:06", "remaining_time": "0:57:23", "throughput": 5176.0, "total_tokens": 9662464} {"current_steps": 2360, "total_steps": 6710, "loss": 0.7767, "lr": 1.8114831758691803e-06, "epoch": 1.758569299552906, "percentage": 35.17, "elapsed_time": "0:31:07", "remaining_time": "0:57:22", "throughput": 5175.99, "total_tokens": 9666560} {"current_steps": 2361, "total_steps": 6710, "loss": 0.5785, "lr": 1.8109602346452547e-06, "epoch": 1.7593144560357676, "percentage": 35.19, "elapsed_time": "0:31:08", "remaining_time": "0:57:21", "throughput": 5175.87, "total_tokens": 9670656} {"current_steps": 2362, "total_steps": 6710, "loss": 0.5541, "lr": 1.810437170454841e-06, "epoch": 1.7600596125186287, "percentage": 35.2, "elapsed_time": "0:31:09", "remaining_time": "0:57:20", "throughput": 5175.83, "total_tokens": 9674752} {"current_steps": 2363, "total_steps": 6710, "loss": 0.7538, "lr": 1.809913983412597e-06, "epoch": 1.7608047690014903, "percentage": 35.22, "elapsed_time": "0:31:10", "remaining_time": "0:57:20", "throughput": 5175.74, "total_tokens": 9678848} {"current_steps": 2364, "total_steps": 6710, "loss": 0.9452, "lr": 1.80939067363321e-06, "epoch": 1.7615499254843519, "percentage": 35.23, "elapsed_time": "0:31:10", "remaining_time": "0:57:19", "throughput": 5175.7, "total_tokens": 9682944} {"current_steps": 2365, "total_steps": 6710, "loss": 0.893, "lr": 1.8088672412313927e-06, "epoch": 1.762295081967213, "percentage": 35.25, "elapsed_time": "0:31:11", "remaining_time": "0:57:18", "throughput": 5175.62, "total_tokens": 9687040} {"current_steps": 2366, "total_steps": 6710, "loss": 0.6094, "lr": 1.8083436863218854e-06, "epoch": 1.7630402384500745, "percentage": 35.26, "elapsed_time": "0:31:12", "remaining_time": "0:57:17", "throughput": 5175.54, "total_tokens": 9691136} {"current_steps": 2367, "total_steps": 6710, "loss": 0.6885, "lr": 1.8078200090194552e-06, "epoch": 1.763785394932936, "percentage": 35.28, "elapsed_time": "0:31:13", "remaining_time": "0:57:17", "throughput": 5175.48, "total_tokens": 9695232} {"current_steps": 2368, "total_steps": 6710, "loss": 0.7585, "lr": 1.8072962094388958e-06, "epoch": 1.7645305514157972, "percentage": 35.29, "elapsed_time": "0:31:14", "remaining_time": "0:57:16", "throughput": 5175.38, "total_tokens": 9699328} {"current_steps": 2369, "total_steps": 6710, "loss": 0.7558, "lr": 1.806772287695028e-06, "epoch": 1.7652757078986587, "percentage": 35.31, "elapsed_time": "0:31:14", "remaining_time": "0:57:15", "throughput": 5175.33, "total_tokens": 9703424} {"current_steps": 2370, "total_steps": 6710, "loss": 0.6304, "lr": 1.806248243902699e-06, "epoch": 1.7660208643815203, "percentage": 35.32, "elapsed_time": "0:31:15", "remaining_time": "0:57:14", "throughput": 5175.26, "total_tokens": 9707520} {"current_steps": 2371, "total_steps": 6710, "loss": 0.5273, "lr": 1.8057240781767826e-06, "epoch": 1.7667660208643814, "percentage": 35.34, "elapsed_time": "0:31:16", "remaining_time": "0:57:14", "throughput": 5175.19, "total_tokens": 9711616} {"current_steps": 2372, "total_steps": 6710, "loss": 0.7844, "lr": 1.8051997906321805e-06, "epoch": 1.767511177347243, "percentage": 35.35, "elapsed_time": "0:31:17", "remaining_time": "0:57:13", "throughput": 5175.02, "total_tokens": 9715712} {"current_steps": 2373, "total_steps": 6710, "loss": 0.5586, "lr": 1.8046753813838197e-06, "epoch": 1.7682563338301043, "percentage": 35.37, "elapsed_time": "0:31:18", "remaining_time": "0:57:12", "throughput": 5174.99, "total_tokens": 9719808} {"current_steps": 2374, "total_steps": 6710, "loss": 0.9281, "lr": 1.8041508505466546e-06, "epoch": 1.7690014903129656, "percentage": 35.38, "elapsed_time": "0:31:19", "remaining_time": "0:57:11", "throughput": 5175.0, "total_tokens": 9723904} {"current_steps": 2375, "total_steps": 6710, "loss": 0.7286, "lr": 1.8036261982356663e-06, "epoch": 1.7697466467958272, "percentage": 35.39, "elapsed_time": "0:31:19", "remaining_time": "0:57:11", "throughput": 5174.95, "total_tokens": 9728000} {"current_steps": 2376, "total_steps": 6710, "loss": 0.7782, "lr": 1.8031014245658614e-06, "epoch": 1.7704918032786885, "percentage": 35.41, "elapsed_time": "0:31:20", "remaining_time": "0:57:10", "throughput": 5174.87, "total_tokens": 9732096} {"current_steps": 2377, "total_steps": 6710, "loss": 0.8235, "lr": 1.802576529652275e-06, "epoch": 1.7712369597615498, "percentage": 35.42, "elapsed_time": "0:31:21", "remaining_time": "0:57:09", "throughput": 5174.89, "total_tokens": 9736192} {"current_steps": 2378, "total_steps": 6710, "loss": 0.9386, "lr": 1.8020515136099678e-06, "epoch": 1.7719821162444114, "percentage": 35.44, "elapsed_time": "0:31:22", "remaining_time": "0:57:08", "throughput": 5174.87, "total_tokens": 9740288} {"current_steps": 2379, "total_steps": 6710, "loss": 0.5928, "lr": 1.8015263765540267e-06, "epoch": 1.7727272727272727, "percentage": 35.45, "elapsed_time": "0:31:23", "remaining_time": "0:57:08", "throughput": 5174.85, "total_tokens": 9744384} {"current_steps": 2380, "total_steps": 6710, "loss": 0.7419, "lr": 1.8010011185995657e-06, "epoch": 1.773472429210134, "percentage": 35.47, "elapsed_time": "0:31:23", "remaining_time": "0:57:07", "throughput": 5174.76, "total_tokens": 9748480} {"current_steps": 2381, "total_steps": 6710, "loss": 0.8327, "lr": 1.800475739861725e-06, "epoch": 1.7742175856929956, "percentage": 35.48, "elapsed_time": "0:31:24", "remaining_time": "0:57:06", "throughput": 5174.66, "total_tokens": 9752576} {"current_steps": 2382, "total_steps": 6710, "loss": 0.7862, "lr": 1.7999502404556712e-06, "epoch": 1.774962742175857, "percentage": 35.5, "elapsed_time": "0:31:25", "remaining_time": "0:57:05", "throughput": 5174.41, "total_tokens": 9756672} {"current_steps": 2383, "total_steps": 6710, "loss": 0.805, "lr": 1.7994246204965979e-06, "epoch": 1.7757078986587183, "percentage": 35.51, "elapsed_time": "0:31:26", "remaining_time": "0:57:05", "throughput": 5174.29, "total_tokens": 9760768} {"current_steps": 2384, "total_steps": 6710, "loss": 0.8415, "lr": 1.7988988800997246e-06, "epoch": 1.7764530551415798, "percentage": 35.53, "elapsed_time": "0:31:27", "remaining_time": "0:57:04", "throughput": 5174.27, "total_tokens": 9764864} {"current_steps": 2385, "total_steps": 6710, "loss": 0.7795, "lr": 1.7983730193802967e-06, "epoch": 1.7771982116244411, "percentage": 35.54, "elapsed_time": "0:31:28", "remaining_time": "0:57:03", "throughput": 5174.2, "total_tokens": 9768960} {"current_steps": 2386, "total_steps": 6710, "loss": 0.7664, "lr": 1.797847038453588e-06, "epoch": 1.7779433681073025, "percentage": 35.56, "elapsed_time": "0:31:28", "remaining_time": "0:57:03", "throughput": 5174.04, "total_tokens": 9773056} {"current_steps": 2387, "total_steps": 6710, "loss": 0.5822, "lr": 1.797320937434896e-06, "epoch": 1.778688524590164, "percentage": 35.57, "elapsed_time": "0:31:29", "remaining_time": "0:57:02", "throughput": 5173.93, "total_tokens": 9777152} {"current_steps": 2388, "total_steps": 6710, "loss": 0.896, "lr": 1.7967947164395461e-06, "epoch": 1.7794336810730254, "percentage": 35.59, "elapsed_time": "0:31:30", "remaining_time": "0:57:01", "throughput": 5173.87, "total_tokens": 9781248} {"current_steps": 2389, "total_steps": 6710, "loss": 0.6895, "lr": 1.7962683755828906e-06, "epoch": 1.7801788375558867, "percentage": 35.6, "elapsed_time": "0:31:31", "remaining_time": "0:57:00", "throughput": 5173.88, "total_tokens": 9785344} {"current_steps": 2390, "total_steps": 6710, "loss": 0.8229, "lr": 1.795741914980306e-06, "epoch": 1.7809239940387482, "percentage": 35.62, "elapsed_time": "0:31:32", "remaining_time": "0:57:00", "throughput": 5173.8, "total_tokens": 9789440} {"current_steps": 2391, "total_steps": 6710, "loss": 0.8198, "lr": 1.7952153347471967e-06, "epoch": 1.7816691505216096, "percentage": 35.63, "elapsed_time": "0:31:32", "remaining_time": "0:56:59", "throughput": 5173.77, "total_tokens": 9793536} {"current_steps": 2392, "total_steps": 6710, "loss": 0.8972, "lr": 1.794688634998993e-06, "epoch": 1.782414307004471, "percentage": 35.65, "elapsed_time": "0:31:33", "remaining_time": "0:56:58", "throughput": 5173.69, "total_tokens": 9797632} {"current_steps": 2393, "total_steps": 6710, "loss": 0.9238, "lr": 1.794161815851151e-06, "epoch": 1.7831594634873325, "percentage": 35.66, "elapsed_time": "0:31:34", "remaining_time": "0:56:57", "throughput": 5173.57, "total_tokens": 9801728} {"current_steps": 2394, "total_steps": 6710, "loss": 0.6836, "lr": 1.793634877419153e-06, "epoch": 1.7839046199701938, "percentage": 35.68, "elapsed_time": "0:31:35", "remaining_time": "0:56:57", "throughput": 5173.48, "total_tokens": 9805824} {"current_steps": 2395, "total_steps": 6710, "loss": 0.6351, "lr": 1.7931078198185086e-06, "epoch": 1.7846497764530551, "percentage": 35.69, "elapsed_time": "0:31:36", "remaining_time": "0:56:56", "throughput": 5173.4, "total_tokens": 9809920} {"current_steps": 2396, "total_steps": 6710, "loss": 1.0468, "lr": 1.7925806431647517e-06, "epoch": 1.7853949329359167, "percentage": 35.71, "elapsed_time": "0:31:37", "remaining_time": "0:56:55", "throughput": 5173.3, "total_tokens": 9814016} {"current_steps": 2397, "total_steps": 6710, "loss": 0.807, "lr": 1.7920533475734435e-06, "epoch": 1.786140089418778, "percentage": 35.72, "elapsed_time": "0:31:37", "remaining_time": "0:56:54", "throughput": 5173.26, "total_tokens": 9818112} {"current_steps": 2398, "total_steps": 6710, "loss": 0.7353, "lr": 1.7915259331601706e-06, "epoch": 1.7868852459016393, "percentage": 35.74, "elapsed_time": "0:31:38", "remaining_time": "0:56:54", "throughput": 5173.24, "total_tokens": 9822208} {"current_steps": 2399, "total_steps": 6710, "loss": 0.8917, "lr": 1.7909984000405464e-06, "epoch": 1.7876304023845009, "percentage": 35.75, "elapsed_time": "0:31:39", "remaining_time": "0:56:53", "throughput": 5173.25, "total_tokens": 9826304} {"current_steps": 2400, "total_steps": 6710, "loss": 0.6224, "lr": 1.7904707483302101e-06, "epoch": 1.788375558867362, "percentage": 35.77, "elapsed_time": "0:31:40", "remaining_time": "0:56:52", "throughput": 5173.15, "total_tokens": 9830400} {"current_steps": 2401, "total_steps": 6710, "loss": 0.5491, "lr": 1.7899429781448264e-06, "epoch": 1.7891207153502235, "percentage": 35.78, "elapsed_time": "0:31:41", "remaining_time": "0:56:51", "throughput": 5173.11, "total_tokens": 9834496} {"current_steps": 2402, "total_steps": 6710, "loss": 0.7425, "lr": 1.7894150896000862e-06, "epoch": 1.789865871833085, "percentage": 35.8, "elapsed_time": "0:31:41", "remaining_time": "0:56:51", "throughput": 5173.09, "total_tokens": 9838592} {"current_steps": 2403, "total_steps": 6710, "loss": 0.9035, "lr": 1.7888870828117067e-06, "epoch": 1.7906110283159462, "percentage": 35.81, "elapsed_time": "0:31:42", "remaining_time": "0:56:50", "throughput": 5173.08, "total_tokens": 9842688} {"current_steps": 2404, "total_steps": 6710, "loss": 0.815, "lr": 1.7883589578954305e-06, "epoch": 1.7913561847988078, "percentage": 35.83, "elapsed_time": "0:31:43", "remaining_time": "0:56:49", "throughput": 5173.07, "total_tokens": 9846784} {"current_steps": 2405, "total_steps": 6710, "loss": 0.8222, "lr": 1.7878307149670265e-06, "epoch": 1.7921013412816693, "percentage": 35.84, "elapsed_time": "0:31:44", "remaining_time": "0:56:48", "throughput": 5173.07, "total_tokens": 9850880} {"current_steps": 2406, "total_steps": 6710, "loss": 0.629, "lr": 1.7873023541422893e-06, "epoch": 1.7928464977645304, "percentage": 35.86, "elapsed_time": "0:31:45", "remaining_time": "0:56:47", "throughput": 5173.03, "total_tokens": 9854976} {"current_steps": 2407, "total_steps": 6710, "loss": 0.6531, "lr": 1.7867738755370396e-06, "epoch": 1.793591654247392, "percentage": 35.87, "elapsed_time": "0:31:45", "remaining_time": "0:56:47", "throughput": 5172.95, "total_tokens": 9859072} {"current_steps": 2408, "total_steps": 6710, "loss": 0.8068, "lr": 1.7862452792671235e-06, "epoch": 1.7943368107302533, "percentage": 35.89, "elapsed_time": "0:31:46", "remaining_time": "0:56:46", "throughput": 5172.89, "total_tokens": 9863168} {"current_steps": 2409, "total_steps": 6710, "loss": 0.678, "lr": 1.7857165654484128e-06, "epoch": 1.7950819672131146, "percentage": 35.9, "elapsed_time": "0:31:47", "remaining_time": "0:56:45", "throughput": 5172.89, "total_tokens": 9867264} {"current_steps": 2410, "total_steps": 6710, "loss": 0.7056, "lr": 1.785187734196806e-06, "epoch": 1.7958271236959762, "percentage": 35.92, "elapsed_time": "0:31:48", "remaining_time": "0:56:44", "throughput": 5172.77, "total_tokens": 9871360} {"current_steps": 2411, "total_steps": 6710, "loss": 0.8072, "lr": 1.784658785628226e-06, "epoch": 1.7965722801788375, "percentage": 35.93, "elapsed_time": "0:31:49", "remaining_time": "0:56:44", "throughput": 5172.74, "total_tokens": 9875456} {"current_steps": 2412, "total_steps": 6710, "loss": 0.5477, "lr": 1.7841297198586222e-06, "epoch": 1.7973174366616989, "percentage": 35.95, "elapsed_time": "0:31:49", "remaining_time": "0:56:43", "throughput": 5172.67, "total_tokens": 9879552} {"current_steps": 2413, "total_steps": 6710, "loss": 0.8398, "lr": 1.78360053700397e-06, "epoch": 1.7980625931445604, "percentage": 35.96, "elapsed_time": "0:31:50", "remaining_time": "0:56:42", "throughput": 5172.64, "total_tokens": 9883648} {"current_steps": 2414, "total_steps": 6710, "loss": 1.0525, "lr": 1.7830712371802697e-06, "epoch": 1.7988077496274217, "percentage": 35.98, "elapsed_time": "0:31:51", "remaining_time": "0:56:41", "throughput": 5172.59, "total_tokens": 9887744} {"current_steps": 2415, "total_steps": 6710, "loss": 1.0611, "lr": 1.7825418205035477e-06, "epoch": 1.799552906110283, "percentage": 35.99, "elapsed_time": "0:31:52", "remaining_time": "0:56:41", "throughput": 5172.55, "total_tokens": 9891840} {"current_steps": 2416, "total_steps": 6710, "loss": 0.7547, "lr": 1.7820122870898565e-06, "epoch": 1.8002980625931446, "percentage": 36.01, "elapsed_time": "0:31:53", "remaining_time": "0:56:40", "throughput": 5172.54, "total_tokens": 9895936} {"current_steps": 2417, "total_steps": 6710, "loss": 0.6974, "lr": 1.7814826370552727e-06, "epoch": 1.801043219076006, "percentage": 36.02, "elapsed_time": "0:31:53", "remaining_time": "0:56:39", "throughput": 5172.48, "total_tokens": 9900032} {"current_steps": 2418, "total_steps": 6710, "loss": 0.758, "lr": 1.7809528705158995e-06, "epoch": 1.8017883755588673, "percentage": 36.04, "elapsed_time": "0:31:54", "remaining_time": "0:56:38", "throughput": 5172.46, "total_tokens": 9904128} {"current_steps": 2419, "total_steps": 6710, "loss": 0.796, "lr": 1.7804229875878663e-06, "epoch": 1.8025335320417288, "percentage": 36.05, "elapsed_time": "0:31:55", "remaining_time": "0:56:38", "throughput": 5172.41, "total_tokens": 9908224} {"current_steps": 2420, "total_steps": 6710, "loss": 0.9959, "lr": 1.7798929883873262e-06, "epoch": 1.8032786885245902, "percentage": 36.07, "elapsed_time": "0:31:56", "remaining_time": "0:56:37", "throughput": 5172.33, "total_tokens": 9912320} {"current_steps": 2421, "total_steps": 6710, "loss": 0.663, "lr": 1.779362873030459e-06, "epoch": 1.8040238450074515, "percentage": 36.08, "elapsed_time": "0:31:57", "remaining_time": "0:56:36", "throughput": 5172.21, "total_tokens": 9916416} {"current_steps": 2422, "total_steps": 6710, "loss": 0.9598, "lr": 1.778832641633471e-06, "epoch": 1.804769001490313, "percentage": 36.1, "elapsed_time": "0:31:58", "remaining_time": "0:56:35", "throughput": 5172.2, "total_tokens": 9920512} {"current_steps": 2423, "total_steps": 6710, "loss": 0.9081, "lr": 1.778302294312591e-06, "epoch": 1.8055141579731744, "percentage": 36.11, "elapsed_time": "0:31:58", "remaining_time": "0:56:35", "throughput": 5172.16, "total_tokens": 9924608} {"current_steps": 2424, "total_steps": 6710, "loss": 0.5507, "lr": 1.7777718311840759e-06, "epoch": 1.8062593144560357, "percentage": 36.13, "elapsed_time": "0:31:59", "remaining_time": "0:56:34", "throughput": 5172.02, "total_tokens": 9928704} {"current_steps": 2425, "total_steps": 6710, "loss": 0.7036, "lr": 1.7772412523642066e-06, "epoch": 1.8070044709388973, "percentage": 36.14, "elapsed_time": "0:32:00", "remaining_time": "0:56:33", "throughput": 5171.94, "total_tokens": 9932800} {"current_steps": 2426, "total_steps": 6710, "loss": 0.8037, "lr": 1.77671055796929e-06, "epoch": 1.8077496274217586, "percentage": 36.15, "elapsed_time": "0:32:01", "remaining_time": "0:56:32", "throughput": 5171.92, "total_tokens": 9936896} {"current_steps": 2427, "total_steps": 6710, "loss": 0.5273, "lr": 1.7761797481156582e-06, "epoch": 1.80849478390462, "percentage": 36.17, "elapsed_time": "0:32:02", "remaining_time": "0:56:32", "throughput": 5171.91, "total_tokens": 9940992} {"current_steps": 2428, "total_steps": 6710, "loss": 0.8206, "lr": 1.7756488229196684e-06, "epoch": 1.8092399403874815, "percentage": 36.18, "elapsed_time": "0:32:02", "remaining_time": "0:56:31", "throughput": 5171.8, "total_tokens": 9945088} {"current_steps": 2429, "total_steps": 6710, "loss": 0.6955, "lr": 1.7751177824977029e-06, "epoch": 1.8099850968703428, "percentage": 36.2, "elapsed_time": "0:32:03", "remaining_time": "0:56:30", "throughput": 5171.71, "total_tokens": 9949184} {"current_steps": 2430, "total_steps": 6710, "loss": 1.0713, "lr": 1.77458662696617e-06, "epoch": 1.8107302533532041, "percentage": 36.21, "elapsed_time": "0:32:04", "remaining_time": "0:56:29", "throughput": 5171.67, "total_tokens": 9953280} {"current_steps": 2431, "total_steps": 6710, "loss": 0.656, "lr": 1.7740553564415025e-06, "epoch": 1.8114754098360657, "percentage": 36.23, "elapsed_time": "0:32:05", "remaining_time": "0:56:29", "throughput": 5171.63, "total_tokens": 9957376} {"current_steps": 2432, "total_steps": 6710, "loss": 0.5698, "lr": 1.7735239710401585e-06, "epoch": 1.812220566318927, "percentage": 36.24, "elapsed_time": "0:32:06", "remaining_time": "0:56:28", "throughput": 5171.62, "total_tokens": 9961472} {"current_steps": 2433, "total_steps": 6710, "loss": 0.8074, "lr": 1.7729924708786222e-06, "epoch": 1.8129657228017884, "percentage": 36.26, "elapsed_time": "0:32:06", "remaining_time": "0:56:27", "throughput": 5171.57, "total_tokens": 9965568} {"current_steps": 2434, "total_steps": 6710, "loss": 0.5885, "lr": 1.7724608560734014e-06, "epoch": 1.81371087928465, "percentage": 36.27, "elapsed_time": "0:32:07", "remaining_time": "0:56:26", "throughput": 5171.53, "total_tokens": 9969664} {"current_steps": 2435, "total_steps": 6710, "loss": 0.7707, "lr": 1.7719291267410305e-06, "epoch": 1.814456035767511, "percentage": 36.29, "elapsed_time": "0:32:08", "remaining_time": "0:56:25", "throughput": 5171.48, "total_tokens": 9973760} {"current_steps": 2436, "total_steps": 6710, "loss": 0.975, "lr": 1.7713972829980682e-06, "epoch": 1.8152011922503726, "percentage": 36.3, "elapsed_time": "0:32:09", "remaining_time": "0:56:25", "throughput": 5171.46, "total_tokens": 9977856} {"current_steps": 2437, "total_steps": 6710, "loss": 0.5786, "lr": 1.7708653249610985e-06, "epoch": 1.8159463487332341, "percentage": 36.32, "elapsed_time": "0:32:10", "remaining_time": "0:56:24", "throughput": 5171.43, "total_tokens": 9981952} {"current_steps": 2438, "total_steps": 6710, "loss": 0.8454, "lr": 1.7703332527467298e-06, "epoch": 1.8166915052160952, "percentage": 36.33, "elapsed_time": "0:32:11", "remaining_time": "0:56:23", "throughput": 5171.32, "total_tokens": 9986048} {"current_steps": 2439, "total_steps": 6710, "loss": 0.7454, "lr": 1.7698010664715966e-06, "epoch": 1.8174366616989568, "percentage": 36.35, "elapsed_time": "0:32:11", "remaining_time": "0:56:23", "throughput": 5171.15, "total_tokens": 9990144} {"current_steps": 2440, "total_steps": 6710, "loss": 0.8091, "lr": 1.7692687662523584e-06, "epoch": 1.8181818181818183, "percentage": 36.36, "elapsed_time": "0:32:12", "remaining_time": "0:56:22", "throughput": 5170.98, "total_tokens": 9994240} {"current_steps": 2441, "total_steps": 6710, "loss": 1.0315, "lr": 1.7687363522056982e-06, "epoch": 1.8189269746646795, "percentage": 36.38, "elapsed_time": "0:32:13", "remaining_time": "0:56:21", "throughput": 5170.91, "total_tokens": 9998336} {"current_steps": 2442, "total_steps": 6710, "loss": 0.7675, "lr": 1.7682038244483258e-06, "epoch": 1.819672131147541, "percentage": 36.39, "elapsed_time": "0:32:14", "remaining_time": "0:56:20", "throughput": 5170.77, "total_tokens": 10002432} {"current_steps": 2443, "total_steps": 6710, "loss": 0.5989, "lr": 1.7676711830969747e-06, "epoch": 1.8204172876304023, "percentage": 36.41, "elapsed_time": "0:32:15", "remaining_time": "0:56:20", "throughput": 5170.72, "total_tokens": 10006528} {"current_steps": 2444, "total_steps": 6710, "loss": 0.756, "lr": 1.7671384282684036e-06, "epoch": 1.8211624441132637, "percentage": 36.42, "elapsed_time": "0:32:16", "remaining_time": "0:56:19", "throughput": 5170.67, "total_tokens": 10010624} {"current_steps": 2445, "total_steps": 6710, "loss": 0.7149, "lr": 1.7666055600793964e-06, "epoch": 1.8219076005961252, "percentage": 36.44, "elapsed_time": "0:32:16", "remaining_time": "0:56:18", "throughput": 5170.56, "total_tokens": 10014720} {"current_steps": 2446, "total_steps": 6710, "loss": 0.6809, "lr": 1.766072578646762e-06, "epoch": 1.8226527570789866, "percentage": 36.45, "elapsed_time": "0:32:17", "remaining_time": "0:56:17", "throughput": 5170.55, "total_tokens": 10018816} {"current_steps": 2447, "total_steps": 6710, "loss": 0.9233, "lr": 1.7655394840873326e-06, "epoch": 1.8233979135618479, "percentage": 36.47, "elapsed_time": "0:32:18", "remaining_time": "0:56:17", "throughput": 5170.52, "total_tokens": 10022912} {"current_steps": 2448, "total_steps": 6710, "loss": 1.144, "lr": 1.7650062765179674e-06, "epoch": 1.8241430700447094, "percentage": 36.48, "elapsed_time": "0:32:19", "remaining_time": "0:56:16", "throughput": 5170.51, "total_tokens": 10027008} {"current_steps": 2449, "total_steps": 6710, "loss": 0.6004, "lr": 1.764472956055549e-06, "epoch": 1.8248882265275708, "percentage": 36.5, "elapsed_time": "0:32:20", "remaining_time": "0:56:15", "throughput": 5170.43, "total_tokens": 10031104} {"current_steps": 2450, "total_steps": 6710, "loss": 0.7301, "lr": 1.7639395228169848e-06, "epoch": 1.825633383010432, "percentage": 36.51, "elapsed_time": "0:32:20", "remaining_time": "0:56:14", "throughput": 5170.42, "total_tokens": 10035200} {"current_steps": 2451, "total_steps": 6710, "loss": 0.7768, "lr": 1.7634059769192071e-06, "epoch": 1.8263785394932937, "percentage": 36.53, "elapsed_time": "0:32:21", "remaining_time": "0:56:13", "throughput": 5170.39, "total_tokens": 10039296} {"current_steps": 2452, "total_steps": 6710, "loss": 0.7108, "lr": 1.7628723184791736e-06, "epoch": 1.827123695976155, "percentage": 36.54, "elapsed_time": "0:32:22", "remaining_time": "0:56:13", "throughput": 5170.37, "total_tokens": 10043392} {"current_steps": 2453, "total_steps": 6710, "loss": 0.8036, "lr": 1.7623385476138651e-06, "epoch": 1.8278688524590163, "percentage": 36.56, "elapsed_time": "0:32:23", "remaining_time": "0:56:12", "throughput": 5170.22, "total_tokens": 10047488} {"current_steps": 2454, "total_steps": 6710, "loss": 0.9896, "lr": 1.761804664440289e-06, "epoch": 1.8286140089418779, "percentage": 36.57, "elapsed_time": "0:32:24", "remaining_time": "0:56:11", "throughput": 5170.16, "total_tokens": 10051584} {"current_steps": 2455, "total_steps": 6710, "loss": 0.7696, "lr": 1.7612706690754757e-06, "epoch": 1.8293591654247392, "percentage": 36.59, "elapsed_time": "0:32:24", "remaining_time": "0:56:11", "throughput": 5170.09, "total_tokens": 10055680} {"current_steps": 2456, "total_steps": 6710, "loss": 0.5282, "lr": 1.7607365616364814e-06, "epoch": 1.8301043219076005, "percentage": 36.6, "elapsed_time": "0:32:25", "remaining_time": "0:56:10", "throughput": 5169.99, "total_tokens": 10059776} {"current_steps": 2457, "total_steps": 6710, "loss": 0.8774, "lr": 1.7602023422403851e-06, "epoch": 1.830849478390462, "percentage": 36.62, "elapsed_time": "0:32:26", "remaining_time": "0:56:09", "throughput": 5169.95, "total_tokens": 10063872} {"current_steps": 2458, "total_steps": 6710, "loss": 0.9739, "lr": 1.7596680110042927e-06, "epoch": 1.8315946348733234, "percentage": 36.63, "elapsed_time": "0:32:27", "remaining_time": "0:56:08", "throughput": 5169.96, "total_tokens": 10067968} {"current_steps": 2459, "total_steps": 6710, "loss": 0.7715, "lr": 1.7591335680453326e-06, "epoch": 1.8323397913561847, "percentage": 36.65, "elapsed_time": "0:32:28", "remaining_time": "0:56:07", "throughput": 5169.96, "total_tokens": 10072064} {"current_steps": 2460, "total_steps": 6710, "loss": 0.9166, "lr": 1.7585990134806591e-06, "epoch": 1.8330849478390463, "percentage": 36.66, "elapsed_time": "0:32:29", "remaining_time": "0:56:07", "throughput": 5169.85, "total_tokens": 10076160} {"current_steps": 2461, "total_steps": 6710, "loss": 0.6351, "lr": 1.7580643474274498e-06, "epoch": 1.8338301043219076, "percentage": 36.68, "elapsed_time": "0:32:29", "remaining_time": "0:56:06", "throughput": 5169.82, "total_tokens": 10080256} {"current_steps": 2462, "total_steps": 6710, "loss": 0.7865, "lr": 1.7575295700029077e-06, "epoch": 1.834575260804769, "percentage": 36.69, "elapsed_time": "0:32:30", "remaining_time": "0:56:05", "throughput": 5169.75, "total_tokens": 10084352} {"current_steps": 2463, "total_steps": 6710, "loss": 0.9527, "lr": 1.7569946813242603e-06, "epoch": 1.8353204172876305, "percentage": 36.71, "elapsed_time": "0:32:31", "remaining_time": "0:56:04", "throughput": 5169.67, "total_tokens": 10088448} {"current_steps": 2464, "total_steps": 6710, "loss": 0.71, "lr": 1.756459681508758e-06, "epoch": 1.8360655737704918, "percentage": 36.72, "elapsed_time": "0:32:32", "remaining_time": "0:56:04", "throughput": 5169.64, "total_tokens": 10092544} {"current_steps": 2465, "total_steps": 6710, "loss": 0.6768, "lr": 1.7559245706736775e-06, "epoch": 1.8368107302533532, "percentage": 36.74, "elapsed_time": "0:32:33", "remaining_time": "0:56:03", "throughput": 5169.59, "total_tokens": 10096640} {"current_steps": 2466, "total_steps": 6710, "loss": 0.5816, "lr": 1.755389348936318e-06, "epoch": 1.8375558867362147, "percentage": 36.75, "elapsed_time": "0:32:33", "remaining_time": "0:56:02", "throughput": 5169.49, "total_tokens": 10100736} {"current_steps": 2467, "total_steps": 6710, "loss": 0.5604, "lr": 1.7548540164140047e-06, "epoch": 1.838301043219076, "percentage": 36.77, "elapsed_time": "0:32:34", "remaining_time": "0:56:01", "throughput": 5169.42, "total_tokens": 10104832} {"current_steps": 2468, "total_steps": 6710, "loss": 1.0002, "lr": 1.7543185732240858e-06, "epoch": 1.8390461997019374, "percentage": 36.78, "elapsed_time": "0:32:35", "remaining_time": "0:56:01", "throughput": 5169.34, "total_tokens": 10108928} {"current_steps": 2469, "total_steps": 6710, "loss": 0.6521, "lr": 1.7537830194839345e-06, "epoch": 1.839791356184799, "percentage": 36.8, "elapsed_time": "0:32:36", "remaining_time": "0:56:00", "throughput": 5169.29, "total_tokens": 10113024} {"current_steps": 2470, "total_steps": 6710, "loss": 0.6385, "lr": 1.753247355310948e-06, "epoch": 1.84053651266766, "percentage": 36.81, "elapsed_time": "0:32:37", "remaining_time": "0:55:59", "throughput": 5169.17, "total_tokens": 10117120} {"current_steps": 2471, "total_steps": 6710, "loss": 0.8598, "lr": 1.7527115808225478e-06, "epoch": 1.8412816691505216, "percentage": 36.83, "elapsed_time": "0:32:38", "remaining_time": "0:55:58", "throughput": 5169.13, "total_tokens": 10121216} {"current_steps": 2472, "total_steps": 6710, "loss": 0.5823, "lr": 1.7521756961361795e-06, "epoch": 1.8420268256333832, "percentage": 36.84, "elapsed_time": "0:32:38", "remaining_time": "0:55:58", "throughput": 5169.02, "total_tokens": 10125312} {"current_steps": 2473, "total_steps": 6710, "loss": 0.7765, "lr": 1.751639701369313e-06, "epoch": 1.8427719821162443, "percentage": 36.86, "elapsed_time": "0:32:39", "remaining_time": "0:55:57", "throughput": 5168.89, "total_tokens": 10129408} {"current_steps": 2474, "total_steps": 6710, "loss": 0.4741, "lr": 1.7511035966394412e-06, "epoch": 1.8435171385991058, "percentage": 36.87, "elapsed_time": "0:32:40", "remaining_time": "0:55:56", "throughput": 5168.8, "total_tokens": 10133504} {"current_steps": 2475, "total_steps": 6710, "loss": 0.7034, "lr": 1.7505673820640834e-06, "epoch": 1.8442622950819674, "percentage": 36.89, "elapsed_time": "0:32:41", "remaining_time": "0:55:56", "throughput": 5168.77, "total_tokens": 10137600} {"current_steps": 2476, "total_steps": 6710, "loss": 0.6634, "lr": 1.750031057760781e-06, "epoch": 1.8450074515648285, "percentage": 36.9, "elapsed_time": "0:32:42", "remaining_time": "0:55:55", "throughput": 5168.73, "total_tokens": 10141696} {"current_steps": 2477, "total_steps": 6710, "loss": 0.5948, "lr": 1.7494946238471e-06, "epoch": 1.84575260804769, "percentage": 36.92, "elapsed_time": "0:32:42", "remaining_time": "0:55:54", "throughput": 5168.65, "total_tokens": 10145792} {"current_steps": 2478, "total_steps": 6710, "loss": 0.8269, "lr": 1.7489580804406309e-06, "epoch": 1.8464977645305514, "percentage": 36.93, "elapsed_time": "0:32:43", "remaining_time": "0:55:53", "throughput": 5168.56, "total_tokens": 10149888} {"current_steps": 2479, "total_steps": 6710, "loss": 0.9313, "lr": 1.7484214276589872e-06, "epoch": 1.8472429210134127, "percentage": 36.94, "elapsed_time": "0:32:44", "remaining_time": "0:55:53", "throughput": 5168.48, "total_tokens": 10153984} {"current_steps": 2480, "total_steps": 6710, "loss": 0.7831, "lr": 1.747884665619808e-06, "epoch": 1.8479880774962743, "percentage": 36.96, "elapsed_time": "0:32:45", "remaining_time": "0:55:52", "throughput": 5168.36, "total_tokens": 10158080} {"current_steps": 2481, "total_steps": 6710, "loss": 0.6754, "lr": 1.7473477944407546e-06, "epoch": 1.8487332339791356, "percentage": 36.97, "elapsed_time": "0:32:46", "remaining_time": "0:55:51", "throughput": 5168.28, "total_tokens": 10162176} {"current_steps": 2482, "total_steps": 6710, "loss": 0.8317, "lr": 1.746810814239514e-06, "epoch": 1.849478390461997, "percentage": 36.99, "elapsed_time": "0:32:47", "remaining_time": "0:55:50", "throughput": 5168.19, "total_tokens": 10166272} {"current_steps": 2483, "total_steps": 6710, "loss": 0.8968, "lr": 1.746273725133795e-06, "epoch": 1.8502235469448585, "percentage": 37.0, "elapsed_time": "0:32:47", "remaining_time": "0:55:50", "throughput": 5168.17, "total_tokens": 10170368} {"current_steps": 2484, "total_steps": 6710, "loss": 0.7683, "lr": 1.7457365272413315e-06, "epoch": 1.8509687034277198, "percentage": 37.02, "elapsed_time": "0:32:48", "remaining_time": "0:55:49", "throughput": 5168.1, "total_tokens": 10174464} {"current_steps": 2485, "total_steps": 6710, "loss": 0.8262, "lr": 1.7451992206798813e-06, "epoch": 1.8517138599105811, "percentage": 37.03, "elapsed_time": "0:32:49", "remaining_time": "0:55:48", "throughput": 5168.06, "total_tokens": 10178560} {"current_steps": 2486, "total_steps": 6710, "loss": 0.6326, "lr": 1.744661805567226e-06, "epoch": 1.8524590163934427, "percentage": 37.05, "elapsed_time": "0:32:50", "remaining_time": "0:55:47", "throughput": 5168.0, "total_tokens": 10182656} {"current_steps": 2487, "total_steps": 6710, "loss": 0.7167, "lr": 1.7441242820211707e-06, "epoch": 1.853204172876304, "percentage": 37.06, "elapsed_time": "0:32:51", "remaining_time": "0:55:47", "throughput": 5167.89, "total_tokens": 10186752} {"current_steps": 2488, "total_steps": 6710, "loss": 0.8554, "lr": 1.7435866501595444e-06, "epoch": 1.8539493293591653, "percentage": 37.08, "elapsed_time": "0:32:51", "remaining_time": "0:55:46", "throughput": 5167.88, "total_tokens": 10190848} {"current_steps": 2489, "total_steps": 6710, "loss": 0.7951, "lr": 1.7430489101001998e-06, "epoch": 1.854694485842027, "percentage": 37.09, "elapsed_time": "0:32:52", "remaining_time": "0:55:45", "throughput": 5167.87, "total_tokens": 10194944} {"current_steps": 2490, "total_steps": 6710, "loss": 0.6484, "lr": 1.742511061961014e-06, "epoch": 1.8554396423248882, "percentage": 37.11, "elapsed_time": "0:32:53", "remaining_time": "0:55:44", "throughput": 5167.89, "total_tokens": 10199040} {"current_steps": 2491, "total_steps": 6710, "loss": 0.8186, "lr": 1.741973105859886e-06, "epoch": 1.8561847988077496, "percentage": 37.12, "elapsed_time": "0:32:54", "remaining_time": "0:55:43", "throughput": 5167.8, "total_tokens": 10203136} {"current_steps": 2492, "total_steps": 6710, "loss": 0.6619, "lr": 1.7414350419147404e-06, "epoch": 1.8569299552906111, "percentage": 37.14, "elapsed_time": "0:32:55", "remaining_time": "0:55:43", "throughput": 5167.78, "total_tokens": 10207232} {"current_steps": 2493, "total_steps": 6710, "loss": 0.8044, "lr": 1.7408968702435245e-06, "epoch": 1.8576751117734724, "percentage": 37.15, "elapsed_time": "0:32:55", "remaining_time": "0:55:42", "throughput": 5167.74, "total_tokens": 10211328} {"current_steps": 2494, "total_steps": 6710, "loss": 0.7771, "lr": 1.740358590964209e-06, "epoch": 1.8584202682563338, "percentage": 37.17, "elapsed_time": "0:32:56", "remaining_time": "0:55:41", "throughput": 5167.73, "total_tokens": 10215424} {"current_steps": 2495, "total_steps": 6710, "loss": 1.0977, "lr": 1.739820204194789e-06, "epoch": 1.8591654247391953, "percentage": 37.18, "elapsed_time": "0:32:57", "remaining_time": "0:55:40", "throughput": 5167.73, "total_tokens": 10219520} {"current_steps": 2496, "total_steps": 6710, "loss": 0.7698, "lr": 1.7392817100532828e-06, "epoch": 1.8599105812220567, "percentage": 37.2, "elapsed_time": "0:32:58", "remaining_time": "0:55:40", "throughput": 5167.73, "total_tokens": 10223616} {"current_steps": 2497, "total_steps": 6710, "loss": 0.8416, "lr": 1.738743108657732e-06, "epoch": 1.860655737704918, "percentage": 37.21, "elapsed_time": "0:32:59", "remaining_time": "0:55:39", "throughput": 5167.64, "total_tokens": 10227712} {"current_steps": 2498, "total_steps": 6710, "loss": 1.0281, "lr": 1.7382044001262016e-06, "epoch": 1.8614008941877795, "percentage": 37.23, "elapsed_time": "0:32:59", "remaining_time": "0:55:38", "throughput": 5167.59, "total_tokens": 10231808} {"current_steps": 2499, "total_steps": 6710, "loss": 0.4612, "lr": 1.7376655845767807e-06, "epoch": 1.8621460506706409, "percentage": 37.24, "elapsed_time": "0:33:00", "remaining_time": "0:55:37", "throughput": 5167.59, "total_tokens": 10235904} {"current_steps": 2500, "total_steps": 6710, "loss": 0.5586, "lr": 1.7371266621275814e-06, "epoch": 1.8628912071535022, "percentage": 37.26, "elapsed_time": "0:33:01", "remaining_time": "0:55:36", "throughput": 5167.59, "total_tokens": 10240000} {"current_steps": 2501, "total_steps": 6710, "loss": 0.7373, "lr": 1.7365876328967396e-06, "epoch": 1.8636363636363638, "percentage": 37.27, "elapsed_time": "0:33:02", "remaining_time": "0:55:36", "throughput": 5167.48, "total_tokens": 10244096} {"current_steps": 2502, "total_steps": 6710, "loss": 0.8375, "lr": 1.7360484970024139e-06, "epoch": 1.864381520119225, "percentage": 37.29, "elapsed_time": "0:33:03", "remaining_time": "0:55:35", "throughput": 5167.48, "total_tokens": 10248192} {"current_steps": 2503, "total_steps": 6710, "loss": 0.5943, "lr": 1.7355092545627872e-06, "epoch": 1.8651266766020864, "percentage": 37.3, "elapsed_time": "0:33:04", "remaining_time": "0:55:34", "throughput": 5167.46, "total_tokens": 10252288} {"current_steps": 2504, "total_steps": 6710, "loss": 0.849, "lr": 1.7349699056960647e-06, "epoch": 1.865871833084948, "percentage": 37.32, "elapsed_time": "0:33:04", "remaining_time": "0:55:33", "throughput": 5167.39, "total_tokens": 10256384} {"current_steps": 2505, "total_steps": 6710, "loss": 0.6991, "lr": 1.734430450520476e-06, "epoch": 1.866616989567809, "percentage": 37.33, "elapsed_time": "0:33:05", "remaining_time": "0:55:33", "throughput": 5167.34, "total_tokens": 10260480} {"current_steps": 2506, "total_steps": 6710, "loss": 0.8384, "lr": 1.7338908891542732e-06, "epoch": 1.8673621460506706, "percentage": 37.35, "elapsed_time": "0:33:06", "remaining_time": "0:55:32", "throughput": 5167.32, "total_tokens": 10264576} {"current_steps": 2507, "total_steps": 6710, "loss": 0.7302, "lr": 1.7333512217157324e-06, "epoch": 1.8681073025335322, "percentage": 37.36, "elapsed_time": "0:33:07", "remaining_time": "0:55:31", "throughput": 5167.22, "total_tokens": 10268672} {"current_steps": 2508, "total_steps": 6710, "loss": 0.7857, "lr": 1.7328114483231526e-06, "epoch": 1.8688524590163933, "percentage": 37.38, "elapsed_time": "0:33:08", "remaining_time": "0:55:30", "throughput": 5167.24, "total_tokens": 10272768} {"current_steps": 2509, "total_steps": 6710, "loss": 0.5283, "lr": 1.7322715690948554e-06, "epoch": 1.8695976154992549, "percentage": 37.39, "elapsed_time": "0:33:08", "remaining_time": "0:55:30", "throughput": 5167.22, "total_tokens": 10276864} {"current_steps": 2510, "total_steps": 6710, "loss": 0.6622, "lr": 1.731731584149187e-06, "epoch": 1.8703427719821164, "percentage": 37.41, "elapsed_time": "0:33:09", "remaining_time": "0:55:29", "throughput": 5167.22, "total_tokens": 10280960} {"current_steps": 2511, "total_steps": 6710, "loss": 0.9909, "lr": 1.7311914936045151e-06, "epoch": 1.8710879284649775, "percentage": 37.42, "elapsed_time": "0:33:10", "remaining_time": "0:55:28", "throughput": 5167.15, "total_tokens": 10285056} {"current_steps": 2512, "total_steps": 6710, "loss": 0.8214, "lr": 1.7306512975792319e-06, "epoch": 1.871833084947839, "percentage": 37.44, "elapsed_time": "0:33:11", "remaining_time": "0:55:27", "throughput": 5167.14, "total_tokens": 10289152} {"current_steps": 2513, "total_steps": 6710, "loss": 0.9594, "lr": 1.730110996191752e-06, "epoch": 1.8725782414307004, "percentage": 37.45, "elapsed_time": "0:33:12", "remaining_time": "0:55:26", "throughput": 5167.12, "total_tokens": 10293248} {"current_steps": 2514, "total_steps": 6710, "loss": 0.6738, "lr": 1.7295705895605133e-06, "epoch": 1.8733233979135617, "percentage": 37.47, "elapsed_time": "0:33:12", "remaining_time": "0:55:26", "throughput": 5167.11, "total_tokens": 10297344} {"current_steps": 2515, "total_steps": 6710, "loss": 0.7987, "lr": 1.729030077803977e-06, "epoch": 1.8740685543964233, "percentage": 37.48, "elapsed_time": "0:33:13", "remaining_time": "0:55:25", "throughput": 5166.99, "total_tokens": 10301440} {"current_steps": 2516, "total_steps": 6710, "loss": 0.7214, "lr": 1.7284894610406271e-06, "epoch": 1.8748137108792846, "percentage": 37.5, "elapsed_time": "0:33:14", "remaining_time": "0:55:24", "throughput": 5166.89, "total_tokens": 10305536} {"current_steps": 2517, "total_steps": 6710, "loss": 0.6798, "lr": 1.727948739388971e-06, "epoch": 1.875558867362146, "percentage": 37.51, "elapsed_time": "0:33:15", "remaining_time": "0:55:23", "throughput": 5166.83, "total_tokens": 10309632} {"current_steps": 2518, "total_steps": 6710, "loss": 0.953, "lr": 1.727407912967538e-06, "epoch": 1.8763040238450075, "percentage": 37.53, "elapsed_time": "0:33:16", "remaining_time": "0:55:23", "throughput": 5166.77, "total_tokens": 10313728} {"current_steps": 2519, "total_steps": 6710, "loss": 0.6018, "lr": 1.726866981894882e-06, "epoch": 1.8770491803278688, "percentage": 37.54, "elapsed_time": "0:33:17", "remaining_time": "0:55:22", "throughput": 5166.65, "total_tokens": 10317824} {"current_steps": 2520, "total_steps": 6710, "loss": 0.7063, "lr": 1.7263259462895777e-06, "epoch": 1.8777943368107302, "percentage": 37.56, "elapsed_time": "0:33:17", "remaining_time": "0:55:21", "throughput": 5166.56, "total_tokens": 10321920} {"current_steps": 2521, "total_steps": 6710, "loss": 0.6741, "lr": 1.725784806270225e-06, "epoch": 1.8785394932935917, "percentage": 37.57, "elapsed_time": "0:33:18", "remaining_time": "0:55:21", "throughput": 5166.43, "total_tokens": 10326016} {"current_steps": 2522, "total_steps": 6710, "loss": 0.7672, "lr": 1.7252435619554453e-06, "epoch": 1.879284649776453, "percentage": 37.59, "elapsed_time": "0:33:19", "remaining_time": "0:55:20", "throughput": 5166.43, "total_tokens": 10330112} {"current_steps": 2523, "total_steps": 6710, "loss": 0.6816, "lr": 1.7247022134638836e-06, "epoch": 1.8800298062593144, "percentage": 37.6, "elapsed_time": "0:33:20", "remaining_time": "0:55:19", "throughput": 5166.41, "total_tokens": 10334208} {"current_steps": 2524, "total_steps": 6710, "loss": 0.6718, "lr": 1.7241607609142066e-06, "epoch": 1.880774962742176, "percentage": 37.62, "elapsed_time": "0:33:21", "remaining_time": "0:55:18", "throughput": 5166.38, "total_tokens": 10338304} {"current_steps": 2525, "total_steps": 6710, "loss": 0.8233, "lr": 1.7236192044251052e-06, "epoch": 1.8815201192250373, "percentage": 37.63, "elapsed_time": "0:33:21", "remaining_time": "0:55:17", "throughput": 5166.35, "total_tokens": 10342400} {"current_steps": 2526, "total_steps": 6710, "loss": 0.7441, "lr": 1.723077544115292e-06, "epoch": 1.8822652757078986, "percentage": 37.65, "elapsed_time": "0:33:22", "remaining_time": "0:55:17", "throughput": 5166.33, "total_tokens": 10346496} {"current_steps": 2527, "total_steps": 6710, "loss": 0.8961, "lr": 1.722535780103503e-06, "epoch": 1.8830104321907601, "percentage": 37.66, "elapsed_time": "0:33:23", "remaining_time": "0:55:16", "throughput": 5166.27, "total_tokens": 10350592} {"current_steps": 2528, "total_steps": 6710, "loss": 0.7049, "lr": 1.7219939125084975e-06, "epoch": 1.8837555886736215, "percentage": 37.68, "elapsed_time": "0:33:24", "remaining_time": "0:55:15", "throughput": 5166.16, "total_tokens": 10354688} {"current_steps": 2529, "total_steps": 6710, "loss": 0.7811, "lr": 1.7214519414490556e-06, "epoch": 1.8845007451564828, "percentage": 37.69, "elapsed_time": "0:33:25", "remaining_time": "0:55:14", "throughput": 5166.15, "total_tokens": 10358784} {"current_steps": 2530, "total_steps": 6710, "loss": 0.595, "lr": 1.7209098670439816e-06, "epoch": 1.8852459016393444, "percentage": 37.7, "elapsed_time": "0:33:25", "remaining_time": "0:55:14", "throughput": 5166.1, "total_tokens": 10362880} {"current_steps": 2531, "total_steps": 6710, "loss": 0.6474, "lr": 1.7203676894121024e-06, "epoch": 1.8859910581222057, "percentage": 37.72, "elapsed_time": "0:33:26", "remaining_time": "0:55:13", "throughput": 5165.99, "total_tokens": 10366976} {"current_steps": 2532, "total_steps": 6710, "loss": 0.7649, "lr": 1.7198254086722666e-06, "epoch": 1.886736214605067, "percentage": 37.73, "elapsed_time": "0:33:27", "remaining_time": "0:55:12", "throughput": 5165.99, "total_tokens": 10371072} {"current_steps": 2533, "total_steps": 6710, "loss": 0.9173, "lr": 1.7192830249433466e-06, "epoch": 1.8874813710879286, "percentage": 37.75, "elapsed_time": "0:33:28", "remaining_time": "0:55:11", "throughput": 5165.97, "total_tokens": 10375168} {"current_steps": 2534, "total_steps": 6710, "loss": 0.8516, "lr": 1.7187405383442364e-06, "epoch": 1.88822652757079, "percentage": 37.76, "elapsed_time": "0:33:29", "remaining_time": "0:55:11", "throughput": 5165.93, "total_tokens": 10379264} {"current_steps": 2535, "total_steps": 6710, "loss": 0.7537, "lr": 1.718197948993853e-06, "epoch": 1.8889716840536512, "percentage": 37.78, "elapsed_time": "0:33:29", "remaining_time": "0:55:10", "throughput": 5165.88, "total_tokens": 10383360} {"current_steps": 2536, "total_steps": 6710, "loss": 0.7049, "lr": 1.7176552570111362e-06, "epoch": 1.8897168405365128, "percentage": 37.79, "elapsed_time": "0:33:30", "remaining_time": "0:55:09", "throughput": 5165.82, "total_tokens": 10387456} {"current_steps": 2537, "total_steps": 6710, "loss": 0.8191, "lr": 1.7171124625150476e-06, "epoch": 1.8904619970193741, "percentage": 37.81, "elapsed_time": "0:33:31", "remaining_time": "0:55:08", "throughput": 5165.77, "total_tokens": 10391552} {"current_steps": 2538, "total_steps": 6710, "loss": 0.6971, "lr": 1.716569565624572e-06, "epoch": 1.8912071535022354, "percentage": 37.82, "elapsed_time": "0:33:32", "remaining_time": "0:55:08", "throughput": 5165.67, "total_tokens": 10395648} {"current_steps": 2539, "total_steps": 6710, "loss": 0.8354, "lr": 1.7160265664587155e-06, "epoch": 1.891952309985097, "percentage": 37.84, "elapsed_time": "0:33:33", "remaining_time": "0:55:07", "throughput": 5165.64, "total_tokens": 10399744} {"current_steps": 2540, "total_steps": 6710, "loss": 0.7834, "lr": 1.7154834651365082e-06, "epoch": 1.8926974664679581, "percentage": 37.85, "elapsed_time": "0:33:34", "remaining_time": "0:55:06", "throughput": 5165.55, "total_tokens": 10403840} {"current_steps": 2541, "total_steps": 6710, "loss": 0.7051, "lr": 1.7149402617770017e-06, "epoch": 1.8934426229508197, "percentage": 37.87, "elapsed_time": "0:33:34", "remaining_time": "0:55:05", "throughput": 5165.43, "total_tokens": 10407936} {"current_steps": 2542, "total_steps": 6710, "loss": 0.8822, "lr": 1.7143969564992694e-06, "epoch": 1.8941877794336812, "percentage": 37.88, "elapsed_time": "0:33:35", "remaining_time": "0:55:05", "throughput": 5165.4, "total_tokens": 10412032} {"current_steps": 2543, "total_steps": 6710, "loss": 0.9149, "lr": 1.713853549422408e-06, "epoch": 1.8949329359165423, "percentage": 37.9, "elapsed_time": "0:33:36", "remaining_time": "0:55:04", "throughput": 5165.38, "total_tokens": 10416128} {"current_steps": 2544, "total_steps": 6710, "loss": 0.8371, "lr": 1.7133100406655373e-06, "epoch": 1.8956780923994039, "percentage": 37.91, "elapsed_time": "0:33:37", "remaining_time": "0:55:03", "throughput": 5165.35, "total_tokens": 10420224} {"current_steps": 2545, "total_steps": 6710, "loss": 0.7452, "lr": 1.7127664303477965e-06, "epoch": 1.8964232488822654, "percentage": 37.93, "elapsed_time": "0:33:38", "remaining_time": "0:55:02", "throughput": 5165.26, "total_tokens": 10424320} {"current_steps": 2546, "total_steps": 6710, "loss": 0.5569, "lr": 1.71222271858835e-06, "epoch": 1.8971684053651265, "percentage": 37.94, "elapsed_time": "0:33:38", "remaining_time": "0:55:02", "throughput": 5165.21, "total_tokens": 10428416} {"current_steps": 2547, "total_steps": 6710, "loss": 0.8786, "lr": 1.711678905506383e-06, "epoch": 1.897913561847988, "percentage": 37.96, "elapsed_time": "0:33:39", "remaining_time": "0:55:01", "throughput": 5165.19, "total_tokens": 10432512} {"current_steps": 2548, "total_steps": 6710, "loss": 0.839, "lr": 1.7111349912211033e-06, "epoch": 1.8986587183308494, "percentage": 37.97, "elapsed_time": "0:33:40", "remaining_time": "0:55:00", "throughput": 5165.01, "total_tokens": 10436608} {"current_steps": 2549, "total_steps": 6710, "loss": 0.8588, "lr": 1.710590975851741e-06, "epoch": 1.8994038748137108, "percentage": 37.99, "elapsed_time": "0:33:41", "remaining_time": "0:54:59", "throughput": 5164.99, "total_tokens": 10440704} {"current_steps": 2550, "total_steps": 6710, "loss": 0.4206, "lr": 1.7100468595175473e-06, "epoch": 1.9001490312965723, "percentage": 38.0, "elapsed_time": "0:33:42", "remaining_time": "0:54:59", "throughput": 5164.94, "total_tokens": 10444800} {"current_steps": 2551, "total_steps": 6710, "loss": 0.6992, "lr": 1.7095026423377973e-06, "epoch": 1.9008941877794336, "percentage": 38.02, "elapsed_time": "0:33:43", "remaining_time": "0:54:58", "throughput": 5164.83, "total_tokens": 10448896} {"current_steps": 2552, "total_steps": 6710, "loss": 0.9966, "lr": 1.708958324431787e-06, "epoch": 1.901639344262295, "percentage": 38.03, "elapsed_time": "0:33:43", "remaining_time": "0:54:57", "throughput": 5164.76, "total_tokens": 10452992} {"current_steps": 2553, "total_steps": 6710, "loss": 0.6082, "lr": 1.7084139059188342e-06, "epoch": 1.9023845007451565, "percentage": 38.05, "elapsed_time": "0:33:44", "remaining_time": "0:54:56", "throughput": 5164.72, "total_tokens": 10457088} {"current_steps": 2554, "total_steps": 6710, "loss": 0.9604, "lr": 1.7078693869182806e-06, "epoch": 1.9031296572280179, "percentage": 38.06, "elapsed_time": "0:33:45", "remaining_time": "0:54:56", "throughput": 5164.66, "total_tokens": 10461184} {"current_steps": 2555, "total_steps": 6710, "loss": 0.862, "lr": 1.7073247675494875e-06, "epoch": 1.9038748137108792, "percentage": 38.08, "elapsed_time": "0:33:46", "remaining_time": "0:54:55", "throughput": 5164.57, "total_tokens": 10465280} {"current_steps": 2556, "total_steps": 6710, "loss": 0.7241, "lr": 1.7067800479318396e-06, "epoch": 1.9046199701937407, "percentage": 38.09, "elapsed_time": "0:33:47", "remaining_time": "0:54:54", "throughput": 5164.56, "total_tokens": 10469376} {"current_steps": 2557, "total_steps": 6710, "loss": 0.731, "lr": 1.7062352281847442e-06, "epoch": 1.905365126676602, "percentage": 38.11, "elapsed_time": "0:33:47", "remaining_time": "0:54:53", "throughput": 5164.52, "total_tokens": 10473472} {"current_steps": 2558, "total_steps": 6710, "loss": 0.8691, "lr": 1.7056903084276282e-06, "epoch": 1.9061102831594634, "percentage": 38.12, "elapsed_time": "0:33:48", "remaining_time": "0:54:53", "throughput": 5164.42, "total_tokens": 10477568} {"current_steps": 2559, "total_steps": 6710, "loss": 0.9733, "lr": 1.705145288779943e-06, "epoch": 1.906855439642325, "percentage": 38.14, "elapsed_time": "0:33:49", "remaining_time": "0:54:52", "throughput": 5164.33, "total_tokens": 10481664} {"current_steps": 2560, "total_steps": 6710, "loss": 0.4061, "lr": 1.7046001693611605e-06, "epoch": 1.9076005961251863, "percentage": 38.15, "elapsed_time": "0:33:50", "remaining_time": "0:54:51", "throughput": 5164.29, "total_tokens": 10485760} {"current_steps": 2561, "total_steps": 6710, "loss": 0.6979, "lr": 1.7040549502907743e-06, "epoch": 1.9083457526080476, "percentage": 38.17, "elapsed_time": "0:33:51", "remaining_time": "0:54:50", "throughput": 5164.19, "total_tokens": 10489856} {"current_steps": 2562, "total_steps": 6710, "loss": 0.8704, "lr": 1.7035096316883013e-06, "epoch": 1.9090909090909092, "percentage": 38.18, "elapsed_time": "0:33:52", "remaining_time": "0:54:50", "throughput": 5164.13, "total_tokens": 10493952} {"current_steps": 2563, "total_steps": 6710, "loss": 0.8867, "lr": 1.7029642136732785e-06, "epoch": 1.9098360655737705, "percentage": 38.2, "elapsed_time": "0:33:52", "remaining_time": "0:54:49", "throughput": 5164.07, "total_tokens": 10498048} {"current_steps": 2564, "total_steps": 6710, "loss": 0.6748, "lr": 1.7024186963652659e-06, "epoch": 1.9105812220566318, "percentage": 38.21, "elapsed_time": "0:33:53", "remaining_time": "0:54:48", "throughput": 5164.03, "total_tokens": 10502144} {"current_steps": 2565, "total_steps": 6710, "loss": 0.6985, "lr": 1.7018730798838442e-06, "epoch": 1.9113263785394934, "percentage": 38.23, "elapsed_time": "0:33:54", "remaining_time": "0:54:47", "throughput": 5163.96, "total_tokens": 10506240} {"current_steps": 2566, "total_steps": 6710, "loss": 0.6425, "lr": 1.7013273643486166e-06, "epoch": 1.9120715350223547, "percentage": 38.24, "elapsed_time": "0:33:55", "remaining_time": "0:54:46", "throughput": 5163.96, "total_tokens": 10510336} {"current_steps": 2567, "total_steps": 6710, "loss": 1.0475, "lr": 1.7007815498792083e-06, "epoch": 1.912816691505216, "percentage": 38.26, "elapsed_time": "0:33:56", "remaining_time": "0:54:46", "throughput": 5163.96, "total_tokens": 10514432} {"current_steps": 2568, "total_steps": 6710, "loss": 0.8989, "lr": 1.7002356365952652e-06, "epoch": 1.9135618479880776, "percentage": 38.27, "elapsed_time": "0:33:56", "remaining_time": "0:54:45", "throughput": 5163.89, "total_tokens": 10518528} {"current_steps": 2569, "total_steps": 6710, "loss": 0.7157, "lr": 1.6996896246164554e-06, "epoch": 1.914307004470939, "percentage": 38.29, "elapsed_time": "0:33:57", "remaining_time": "0:54:44", "throughput": 5163.91, "total_tokens": 10522624} {"current_steps": 2570, "total_steps": 6710, "loss": 0.887, "lr": 1.699143514062469e-06, "epoch": 1.9150521609538003, "percentage": 38.3, "elapsed_time": "0:33:58", "remaining_time": "0:54:43", "throughput": 5163.9, "total_tokens": 10526720} {"current_steps": 2571, "total_steps": 6710, "loss": 0.8139, "lr": 1.6985973050530175e-06, "epoch": 1.9157973174366618, "percentage": 38.32, "elapsed_time": "0:33:59", "remaining_time": "0:54:43", "throughput": 5163.9, "total_tokens": 10530816} {"current_steps": 2572, "total_steps": 6710, "loss": 0.6019, "lr": 1.698050997707833e-06, "epoch": 1.9165424739195231, "percentage": 38.33, "elapsed_time": "0:34:00", "remaining_time": "0:54:42", "throughput": 5163.85, "total_tokens": 10534912} {"current_steps": 2573, "total_steps": 6710, "loss": 0.697, "lr": 1.6975045921466703e-06, "epoch": 1.9172876304023845, "percentage": 38.35, "elapsed_time": "0:34:00", "remaining_time": "0:54:41", "throughput": 5163.86, "total_tokens": 10539008} {"current_steps": 2574, "total_steps": 6710, "loss": 0.8472, "lr": 1.6969580884893062e-06, "epoch": 1.918032786885246, "percentage": 38.36, "elapsed_time": "0:34:01", "remaining_time": "0:54:40", "throughput": 5163.86, "total_tokens": 10543104} {"current_steps": 2575, "total_steps": 6710, "loss": 0.7733, "lr": 1.696411486855537e-06, "epoch": 1.9187779433681071, "percentage": 38.38, "elapsed_time": "0:34:02", "remaining_time": "0:54:39", "throughput": 5163.76, "total_tokens": 10547200} {"current_steps": 2576, "total_steps": 6710, "loss": 0.9701, "lr": 1.6958647873651824e-06, "epoch": 1.9195230998509687, "percentage": 38.39, "elapsed_time": "0:34:03", "remaining_time": "0:54:39", "throughput": 5163.74, "total_tokens": 10551296} {"current_steps": 2577, "total_steps": 6710, "loss": 0.5165, "lr": 1.6953179901380828e-06, "epoch": 1.9202682563338302, "percentage": 38.41, "elapsed_time": "0:34:04", "remaining_time": "0:54:38", "throughput": 5163.67, "total_tokens": 10555392} {"current_steps": 2578, "total_steps": 6710, "loss": 0.7931, "lr": 1.6947710952940997e-06, "epoch": 1.9210134128166914, "percentage": 38.42, "elapsed_time": "0:34:04", "remaining_time": "0:54:37", "throughput": 5163.57, "total_tokens": 10559488} {"current_steps": 2579, "total_steps": 6710, "loss": 0.7213, "lr": 1.6942241029531164e-06, "epoch": 1.921758569299553, "percentage": 38.44, "elapsed_time": "0:34:05", "remaining_time": "0:54:36", "throughput": 5163.53, "total_tokens": 10563584} {"current_steps": 2580, "total_steps": 6710, "loss": 0.5577, "lr": 1.6936770132350378e-06, "epoch": 1.9225037257824145, "percentage": 38.45, "elapsed_time": "0:34:06", "remaining_time": "0:54:36", "throughput": 5163.52, "total_tokens": 10567680} {"current_steps": 2581, "total_steps": 6710, "loss": 1.039, "lr": 1.6931298262597898e-06, "epoch": 1.9232488822652756, "percentage": 38.46, "elapsed_time": "0:34:07", "remaining_time": "0:54:35", "throughput": 5163.5, "total_tokens": 10571776} {"current_steps": 2582, "total_steps": 6710, "loss": 0.7151, "lr": 1.6925825421473197e-06, "epoch": 1.9239940387481371, "percentage": 38.48, "elapsed_time": "0:34:08", "remaining_time": "0:54:34", "throughput": 5163.44, "total_tokens": 10575872} {"current_steps": 2583, "total_steps": 6710, "loss": 0.6451, "lr": 1.692035161017596e-06, "epoch": 1.9247391952309985, "percentage": 38.49, "elapsed_time": "0:34:09", "remaining_time": "0:54:33", "throughput": 5163.46, "total_tokens": 10579968} {"current_steps": 2584, "total_steps": 6710, "loss": 0.9173, "lr": 1.6914876829906089e-06, "epoch": 1.9254843517138598, "percentage": 38.51, "elapsed_time": "0:34:09", "remaining_time": "0:54:33", "throughput": 5163.4, "total_tokens": 10584064} {"current_steps": 2585, "total_steps": 6710, "loss": 1.0676, "lr": 1.6909401081863688e-06, "epoch": 1.9262295081967213, "percentage": 38.52, "elapsed_time": "0:34:10", "remaining_time": "0:54:32", "throughput": 5163.35, "total_tokens": 10588160} {"current_steps": 2586, "total_steps": 6710, "loss": 0.6482, "lr": 1.6903924367249084e-06, "epoch": 1.9269746646795827, "percentage": 38.54, "elapsed_time": "0:34:11", "remaining_time": "0:54:31", "throughput": 5163.34, "total_tokens": 10592256} {"current_steps": 2587, "total_steps": 6710, "loss": 0.6732, "lr": 1.6898446687262811e-06, "epoch": 1.927719821162444, "percentage": 38.55, "elapsed_time": "0:34:12", "remaining_time": "0:54:30", "throughput": 5163.31, "total_tokens": 10596352} {"current_steps": 2588, "total_steps": 6710, "loss": 0.8144, "lr": 1.6892968043105618e-06, "epoch": 1.9284649776453056, "percentage": 38.57, "elapsed_time": "0:34:13", "remaining_time": "0:54:29", "throughput": 5163.22, "total_tokens": 10600448} {"current_steps": 2589, "total_steps": 6710, "loss": 0.7649, "lr": 1.688748843597846e-06, "epoch": 1.9292101341281669, "percentage": 38.58, "elapsed_time": "0:34:13", "remaining_time": "0:54:29", "throughput": 5163.18, "total_tokens": 10604544} {"current_steps": 2590, "total_steps": 6710, "loss": 0.5524, "lr": 1.6882007867082511e-06, "epoch": 1.9299552906110282, "percentage": 38.6, "elapsed_time": "0:34:14", "remaining_time": "0:54:28", "throughput": 5163.15, "total_tokens": 10608640} {"current_steps": 2591, "total_steps": 6710, "loss": 0.8416, "lr": 1.6876526337619146e-06, "epoch": 1.9307004470938898, "percentage": 38.61, "elapsed_time": "0:34:15", "remaining_time": "0:54:27", "throughput": 5163.12, "total_tokens": 10612736} {"current_steps": 2592, "total_steps": 6710, "loss": 0.5957, "lr": 1.6871043848789957e-06, "epoch": 1.931445603576751, "percentage": 38.63, "elapsed_time": "0:34:16", "remaining_time": "0:54:26", "throughput": 5163.06, "total_tokens": 10616832} {"current_steps": 2593, "total_steps": 6710, "loss": 0.8509, "lr": 1.6865560401796744e-06, "epoch": 1.9321907600596124, "percentage": 38.64, "elapsed_time": "0:34:17", "remaining_time": "0:54:26", "throughput": 5163.03, "total_tokens": 10620928} {"current_steps": 2594, "total_steps": 6710, "loss": 0.5539, "lr": 1.6860075997841515e-06, "epoch": 1.932935916542474, "percentage": 38.66, "elapsed_time": "0:34:17", "remaining_time": "0:54:25", "throughput": 5163.0, "total_tokens": 10625024} {"current_steps": 2595, "total_steps": 6710, "loss": 0.8815, "lr": 1.6854590638126494e-06, "epoch": 1.9336810730253353, "percentage": 38.67, "elapsed_time": "0:34:18", "remaining_time": "0:54:24", "throughput": 5162.95, "total_tokens": 10629120} {"current_steps": 2596, "total_steps": 6710, "loss": 0.9296, "lr": 1.6849104323854113e-06, "epoch": 1.9344262295081966, "percentage": 38.69, "elapsed_time": "0:34:19", "remaining_time": "0:54:23", "throughput": 5162.96, "total_tokens": 10633216} {"current_steps": 2597, "total_steps": 6710, "loss": 0.9187, "lr": 1.6843617056227007e-06, "epoch": 1.9351713859910582, "percentage": 38.7, "elapsed_time": "0:34:20", "remaining_time": "0:54:23", "throughput": 5162.93, "total_tokens": 10637312} {"current_steps": 2598, "total_steps": 6710, "loss": 0.7589, "lr": 1.6838128836448031e-06, "epoch": 1.9359165424739195, "percentage": 38.72, "elapsed_time": "0:34:21", "remaining_time": "0:54:22", "throughput": 5162.91, "total_tokens": 10641408} {"current_steps": 2599, "total_steps": 6710, "loss": 0.8522, "lr": 1.683263966572023e-06, "epoch": 1.9366616989567809, "percentage": 38.73, "elapsed_time": "0:34:21", "remaining_time": "0:54:21", "throughput": 5162.88, "total_tokens": 10645504} {"current_steps": 2600, "total_steps": 6710, "loss": 0.9223, "lr": 1.6827149545246878e-06, "epoch": 1.9374068554396424, "percentage": 38.75, "elapsed_time": "0:34:22", "remaining_time": "0:54:20", "throughput": 5162.86, "total_tokens": 10649600} {"current_steps": 2601, "total_steps": 6710, "loss": 0.8379, "lr": 1.6821658476231453e-06, "epoch": 1.9381520119225037, "percentage": 38.76, "elapsed_time": "0:34:23", "remaining_time": "0:54:19", "throughput": 5162.82, "total_tokens": 10653696} {"current_steps": 2602, "total_steps": 6710, "loss": 0.6177, "lr": 1.6816166459877624e-06, "epoch": 1.938897168405365, "percentage": 38.78, "elapsed_time": "0:34:24", "remaining_time": "0:54:19", "throughput": 5162.66, "total_tokens": 10657792} {"current_steps": 2603, "total_steps": 6710, "loss": 0.7283, "lr": 1.681067349738929e-06, "epoch": 1.9396423248882266, "percentage": 38.79, "elapsed_time": "0:34:25", "remaining_time": "0:54:18", "throughput": 5162.68, "total_tokens": 10661888} {"current_steps": 2604, "total_steps": 6710, "loss": 0.6375, "lr": 1.6805179589970543e-06, "epoch": 1.940387481371088, "percentage": 38.81, "elapsed_time": "0:34:25", "remaining_time": "0:54:17", "throughput": 5162.67, "total_tokens": 10665984} {"current_steps": 2605, "total_steps": 6710, "loss": 0.6783, "lr": 1.6799684738825688e-06, "epoch": 1.9411326378539493, "percentage": 38.82, "elapsed_time": "0:34:26", "remaining_time": "0:54:16", "throughput": 5162.66, "total_tokens": 10670080} {"current_steps": 2606, "total_steps": 6710, "loss": 0.7247, "lr": 1.6794188945159236e-06, "epoch": 1.9418777943368108, "percentage": 38.84, "elapsed_time": "0:34:27", "remaining_time": "0:54:16", "throughput": 5162.62, "total_tokens": 10674176} {"current_steps": 2607, "total_steps": 6710, "loss": 0.7035, "lr": 1.6788692210175905e-06, "epoch": 1.9426229508196722, "percentage": 38.85, "elapsed_time": "0:34:28", "remaining_time": "0:54:15", "throughput": 5162.6, "total_tokens": 10678272} {"current_steps": 2608, "total_steps": 6710, "loss": 0.8991, "lr": 1.6783194535080616e-06, "epoch": 1.9433681073025335, "percentage": 38.87, "elapsed_time": "0:34:29", "remaining_time": "0:54:14", "throughput": 5162.59, "total_tokens": 10682368} {"current_steps": 2609, "total_steps": 6710, "loss": 0.656, "lr": 1.6777695921078502e-06, "epoch": 1.944113263785395, "percentage": 38.88, "elapsed_time": "0:34:30", "remaining_time": "0:54:13", "throughput": 5162.48, "total_tokens": 10686464} {"current_steps": 2610, "total_steps": 6710, "loss": 0.7294, "lr": 1.6772196369374896e-06, "epoch": 1.9448584202682562, "percentage": 38.9, "elapsed_time": "0:34:30", "remaining_time": "0:54:13", "throughput": 5162.47, "total_tokens": 10690560} {"current_steps": 2611, "total_steps": 6710, "loss": 0.8296, "lr": 1.6766695881175343e-06, "epoch": 1.9456035767511177, "percentage": 38.91, "elapsed_time": "0:34:31", "remaining_time": "0:54:12", "throughput": 5162.43, "total_tokens": 10694656} {"current_steps": 2612, "total_steps": 6710, "loss": 0.5654, "lr": 1.6761194457685582e-06, "epoch": 1.9463487332339793, "percentage": 38.93, "elapsed_time": "0:34:32", "remaining_time": "0:54:11", "throughput": 5162.34, "total_tokens": 10698752} {"current_steps": 2613, "total_steps": 6710, "loss": 0.8306, "lr": 1.6755692100111567e-06, "epoch": 1.9470938897168404, "percentage": 38.94, "elapsed_time": "0:34:33", "remaining_time": "0:54:10", "throughput": 5162.34, "total_tokens": 10702848} {"current_steps": 2614, "total_steps": 6710, "loss": 0.7825, "lr": 1.6750188809659457e-06, "epoch": 1.947839046199702, "percentage": 38.96, "elapsed_time": "0:34:34", "remaining_time": "0:54:09", "throughput": 5162.34, "total_tokens": 10706944} {"current_steps": 2615, "total_steps": 6710, "loss": 1.044, "lr": 1.674468458753561e-06, "epoch": 1.9485842026825635, "percentage": 38.97, "elapsed_time": "0:34:34", "remaining_time": "0:54:09", "throughput": 5162.32, "total_tokens": 10711040} {"current_steps": 2616, "total_steps": 6710, "loss": 0.8419, "lr": 1.673917943494659e-06, "epoch": 1.9493293591654246, "percentage": 38.99, "elapsed_time": "0:34:35", "remaining_time": "0:54:08", "throughput": 5162.29, "total_tokens": 10715136} {"current_steps": 2617, "total_steps": 6710, "loss": 0.746, "lr": 1.673367335309917e-06, "epoch": 1.9500745156482862, "percentage": 39.0, "elapsed_time": "0:34:36", "remaining_time": "0:54:07", "throughput": 5162.25, "total_tokens": 10719232} {"current_steps": 2618, "total_steps": 6710, "loss": 0.7629, "lr": 1.672816634320032e-06, "epoch": 1.9508196721311475, "percentage": 39.02, "elapsed_time": "0:34:37", "remaining_time": "0:54:06", "throughput": 5162.22, "total_tokens": 10723328} {"current_steps": 2619, "total_steps": 6710, "loss": 0.6461, "lr": 1.6722658406457214e-06, "epoch": 1.9515648286140088, "percentage": 39.03, "elapsed_time": "0:34:38", "remaining_time": "0:54:06", "throughput": 5162.12, "total_tokens": 10727424} {"current_steps": 2620, "total_steps": 6710, "loss": 0.4727, "lr": 1.6717149544077238e-06, "epoch": 1.9523099850968704, "percentage": 39.05, "elapsed_time": "0:34:38", "remaining_time": "0:54:05", "throughput": 5162.13, "total_tokens": 10731520} {"current_steps": 2621, "total_steps": 6710, "loss": 0.8153, "lr": 1.6711639757267965e-06, "epoch": 1.9530551415797317, "percentage": 39.06, "elapsed_time": "0:34:39", "remaining_time": "0:54:04", "throughput": 5162.12, "total_tokens": 10735616} {"current_steps": 2622, "total_steps": 6710, "loss": 0.8163, "lr": 1.6706129047237182e-06, "epoch": 1.953800298062593, "percentage": 39.08, "elapsed_time": "0:34:40", "remaining_time": "0:54:03", "throughput": 5162.11, "total_tokens": 10739712} {"current_steps": 2623, "total_steps": 6710, "loss": 0.4761, "lr": 1.6700617415192877e-06, "epoch": 1.9545454545454546, "percentage": 39.09, "elapsed_time": "0:34:41", "remaining_time": "0:54:02", "throughput": 5162.03, "total_tokens": 10743808} {"current_steps": 2624, "total_steps": 6710, "loss": 0.6517, "lr": 1.6695104862343242e-06, "epoch": 1.955290611028316, "percentage": 39.11, "elapsed_time": "0:34:42", "remaining_time": "0:54:02", "throughput": 5162.03, "total_tokens": 10747904} {"current_steps": 2625, "total_steps": 6710, "loss": 0.4896, "lr": 1.6689591389896663e-06, "epoch": 1.9560357675111772, "percentage": 39.12, "elapsed_time": "0:34:42", "remaining_time": "0:54:01", "throughput": 5162.02, "total_tokens": 10752000} {"current_steps": 2626, "total_steps": 6710, "loss": 0.8779, "lr": 1.6684076999061737e-06, "epoch": 1.9567809239940388, "percentage": 39.14, "elapsed_time": "0:34:43", "remaining_time": "0:54:00", "throughput": 5161.98, "total_tokens": 10756096} {"current_steps": 2627, "total_steps": 6710, "loss": 0.8013, "lr": 1.6678561691047258e-06, "epoch": 1.9575260804769001, "percentage": 39.15, "elapsed_time": "0:34:44", "remaining_time": "0:53:59", "throughput": 5161.94, "total_tokens": 10760192} {"current_steps": 2628, "total_steps": 6710, "loss": 0.4834, "lr": 1.6673045467062216e-06, "epoch": 1.9582712369597615, "percentage": 39.17, "elapsed_time": "0:34:45", "remaining_time": "0:53:59", "throughput": 5161.9, "total_tokens": 10764288} {"current_steps": 2629, "total_steps": 6710, "loss": 0.8306, "lr": 1.666752832831581e-06, "epoch": 1.959016393442623, "percentage": 39.18, "elapsed_time": "0:34:46", "remaining_time": "0:53:58", "throughput": 5161.79, "total_tokens": 10768384} {"current_steps": 2630, "total_steps": 6710, "loss": 0.6936, "lr": 1.6662010276017435e-06, "epoch": 1.9597615499254843, "percentage": 39.2, "elapsed_time": "0:34:46", "remaining_time": "0:53:57", "throughput": 5161.77, "total_tokens": 10772480} {"current_steps": 2631, "total_steps": 6710, "loss": 0.6988, "lr": 1.6656491311376691e-06, "epoch": 1.9605067064083457, "percentage": 39.21, "elapsed_time": "0:34:47", "remaining_time": "0:53:56", "throughput": 5161.72, "total_tokens": 10776576} {"current_steps": 2632, "total_steps": 6710, "loss": 0.8685, "lr": 1.665097143560337e-06, "epoch": 1.9612518628912072, "percentage": 39.23, "elapsed_time": "0:34:48", "remaining_time": "0:53:56", "throughput": 5161.69, "total_tokens": 10780672} {"current_steps": 2633, "total_steps": 6710, "loss": 0.6517, "lr": 1.6645450649907466e-06, "epoch": 1.9619970193740686, "percentage": 39.24, "elapsed_time": "0:34:49", "remaining_time": "0:53:55", "throughput": 5161.59, "total_tokens": 10784768} {"current_steps": 2634, "total_steps": 6710, "loss": 0.684, "lr": 1.663992895549918e-06, "epoch": 1.96274217585693, "percentage": 39.25, "elapsed_time": "0:34:50", "remaining_time": "0:53:54", "throughput": 5161.54, "total_tokens": 10788864} {"current_steps": 2635, "total_steps": 6710, "loss": 1.0455, "lr": 1.6634406353588906e-06, "epoch": 1.9634873323397914, "percentage": 39.27, "elapsed_time": "0:34:51", "remaining_time": "0:53:53", "throughput": 5161.46, "total_tokens": 10792960} {"current_steps": 2636, "total_steps": 6710, "loss": 0.9604, "lr": 1.6628882845387236e-06, "epoch": 1.9642324888226528, "percentage": 39.28, "elapsed_time": "0:34:51", "remaining_time": "0:53:53", "throughput": 5161.35, "total_tokens": 10797056} {"current_steps": 2637, "total_steps": 6710, "loss": 0.6552, "lr": 1.6623358432104966e-06, "epoch": 1.964977645305514, "percentage": 39.3, "elapsed_time": "0:34:52", "remaining_time": "0:53:52", "throughput": 5161.34, "total_tokens": 10801152} {"current_steps": 2638, "total_steps": 6710, "loss": 0.6323, "lr": 1.6617833114953083e-06, "epoch": 1.9657228017883757, "percentage": 39.31, "elapsed_time": "0:34:53", "remaining_time": "0:53:51", "throughput": 5161.31, "total_tokens": 10805248} {"current_steps": 2639, "total_steps": 6710, "loss": 0.7723, "lr": 1.6612306895142779e-06, "epoch": 1.966467958271237, "percentage": 39.33, "elapsed_time": "0:34:54", "remaining_time": "0:53:50", "throughput": 5161.29, "total_tokens": 10809344} {"current_steps": 2640, "total_steps": 6710, "loss": 0.7332, "lr": 1.6606779773885436e-06, "epoch": 1.9672131147540983, "percentage": 39.34, "elapsed_time": "0:34:55", "remaining_time": "0:53:49", "throughput": 5161.28, "total_tokens": 10813440} {"current_steps": 2641, "total_steps": 6710, "loss": 0.6956, "lr": 1.6601251752392645e-06, "epoch": 1.9679582712369599, "percentage": 39.36, "elapsed_time": "0:34:55", "remaining_time": "0:53:49", "throughput": 5161.24, "total_tokens": 10817536} {"current_steps": 2642, "total_steps": 6710, "loss": 1.0454, "lr": 1.659572283187618e-06, "epoch": 1.9687034277198212, "percentage": 39.37, "elapsed_time": "0:34:56", "remaining_time": "0:53:48", "throughput": 5161.16, "total_tokens": 10821632} {"current_steps": 2643, "total_steps": 6710, "loss": 0.6749, "lr": 1.6590193013548026e-06, "epoch": 1.9694485842026825, "percentage": 39.39, "elapsed_time": "0:34:57", "remaining_time": "0:53:47", "throughput": 5161.13, "total_tokens": 10825728} {"current_steps": 2644, "total_steps": 6710, "loss": 0.7033, "lr": 1.6584662298620357e-06, "epoch": 1.970193740685544, "percentage": 39.4, "elapsed_time": "0:34:58", "remaining_time": "0:53:46", "throughput": 5161.1, "total_tokens": 10829824} {"current_steps": 2645, "total_steps": 6710, "loss": 0.6798, "lr": 1.6579130688305546e-06, "epoch": 1.9709388971684052, "percentage": 39.42, "elapsed_time": "0:34:59", "remaining_time": "0:53:46", "throughput": 5161.05, "total_tokens": 10833920} {"current_steps": 2646, "total_steps": 6710, "loss": 0.6724, "lr": 1.6573598183816158e-06, "epoch": 1.9716840536512668, "percentage": 39.43, "elapsed_time": "0:34:59", "remaining_time": "0:53:45", "throughput": 5160.96, "total_tokens": 10838016} {"current_steps": 2647, "total_steps": 6710, "loss": 0.7161, "lr": 1.6568064786364965e-06, "epoch": 1.9724292101341283, "percentage": 39.45, "elapsed_time": "0:35:00", "remaining_time": "0:53:44", "throughput": 5160.89, "total_tokens": 10842112} {"current_steps": 2648, "total_steps": 6710, "loss": 1.0085, "lr": 1.656253049716492e-06, "epoch": 1.9731743666169894, "percentage": 39.46, "elapsed_time": "0:35:01", "remaining_time": "0:53:44", "throughput": 5160.07, "total_tokens": 10846208} {"current_steps": 2649, "total_steps": 6710, "loss": 0.4326, "lr": 1.6556995317429178e-06, "epoch": 1.973919523099851, "percentage": 39.48, "elapsed_time": "0:35:02", "remaining_time": "0:53:43", "throughput": 5159.93, "total_tokens": 10850304} {"current_steps": 2650, "total_steps": 6710, "loss": 0.6909, "lr": 1.6551459248371093e-06, "epoch": 1.9746646795827125, "percentage": 39.49, "elapsed_time": "0:35:03", "remaining_time": "0:53:42", "throughput": 5159.82, "total_tokens": 10854400} {"current_steps": 2651, "total_steps": 6710, "loss": 0.8459, "lr": 1.6545922291204215e-06, "epoch": 1.9754098360655736, "percentage": 39.51, "elapsed_time": "0:35:04", "remaining_time": "0:53:42", "throughput": 5159.77, "total_tokens": 10858496} {"current_steps": 2652, "total_steps": 6710, "loss": 0.7103, "lr": 1.6540384447142278e-06, "epoch": 1.9761549925484352, "percentage": 39.52, "elapsed_time": "0:35:05", "remaining_time": "0:53:41", "throughput": 5159.71, "total_tokens": 10862592} {"current_steps": 2653, "total_steps": 6710, "loss": 0.9879, "lr": 1.6534845717399218e-06, "epoch": 1.9769001490312967, "percentage": 39.54, "elapsed_time": "0:35:06", "remaining_time": "0:53:40", "throughput": 5159.63, "total_tokens": 10866688} {"current_steps": 2654, "total_steps": 6710, "loss": 0.6545, "lr": 1.6529306103189165e-06, "epoch": 1.9776453055141578, "percentage": 39.55, "elapsed_time": "0:35:06", "remaining_time": "0:53:39", "throughput": 5159.61, "total_tokens": 10870784} {"current_steps": 2655, "total_steps": 6710, "loss": 0.9201, "lr": 1.6523765605726444e-06, "epoch": 1.9783904619970194, "percentage": 39.57, "elapsed_time": "0:35:07", "remaining_time": "0:53:39", "throughput": 5159.59, "total_tokens": 10874880} {"current_steps": 2656, "total_steps": 6710, "loss": 0.7125, "lr": 1.6518224226225572e-06, "epoch": 1.9791356184798807, "percentage": 39.58, "elapsed_time": "0:35:08", "remaining_time": "0:53:38", "throughput": 5159.45, "total_tokens": 10878976} {"current_steps": 2657, "total_steps": 6710, "loss": 0.5274, "lr": 1.6512681965901255e-06, "epoch": 1.979880774962742, "percentage": 39.6, "elapsed_time": "0:35:09", "remaining_time": "0:53:38", "throughput": 5158.65, "total_tokens": 10883072} {"current_steps": 2658, "total_steps": 6710, "loss": 0.6972, "lr": 1.65071388259684e-06, "epoch": 1.9806259314456036, "percentage": 39.61, "elapsed_time": "0:35:10", "remaining_time": "0:53:37", "throughput": 5158.59, "total_tokens": 10887168} {"current_steps": 2659, "total_steps": 6710, "loss": 0.6862, "lr": 1.6501594807642097e-06, "epoch": 1.981371087928465, "percentage": 39.63, "elapsed_time": "0:35:11", "remaining_time": "0:53:36", "throughput": 5158.5, "total_tokens": 10891264} {"current_steps": 2660, "total_steps": 6710, "loss": 0.7729, "lr": 1.649604991213764e-06, "epoch": 1.9821162444113263, "percentage": 39.64, "elapsed_time": "0:35:12", "remaining_time": "0:53:35", "throughput": 5158.49, "total_tokens": 10895360} {"current_steps": 2661, "total_steps": 6710, "loss": 0.673, "lr": 1.6490504140670508e-06, "epoch": 1.9828614008941878, "percentage": 39.66, "elapsed_time": "0:35:12", "remaining_time": "0:53:35", "throughput": 5158.46, "total_tokens": 10899456} {"current_steps": 2662, "total_steps": 6710, "loss": 0.9319, "lr": 1.6484957494456373e-06, "epoch": 1.9836065573770492, "percentage": 39.67, "elapsed_time": "0:35:13", "remaining_time": "0:53:34", "throughput": 5158.44, "total_tokens": 10903552} {"current_steps": 2663, "total_steps": 6710, "loss": 0.5617, "lr": 1.6479409974711097e-06, "epoch": 1.9843517138599105, "percentage": 39.69, "elapsed_time": "0:35:14", "remaining_time": "0:53:33", "throughput": 5158.42, "total_tokens": 10907648} {"current_steps": 2664, "total_steps": 6710, "loss": 0.7447, "lr": 1.6473861582650746e-06, "epoch": 1.985096870342772, "percentage": 39.7, "elapsed_time": "0:35:15", "remaining_time": "0:53:32", "throughput": 5158.35, "total_tokens": 10911744} {"current_steps": 2665, "total_steps": 6710, "loss": 0.9365, "lr": 1.6468312319491556e-06, "epoch": 1.9858420268256334, "percentage": 39.72, "elapsed_time": "0:35:16", "remaining_time": "0:53:31", "throughput": 5158.32, "total_tokens": 10915840} {"current_steps": 2666, "total_steps": 6710, "loss": 0.6593, "lr": 1.646276218644997e-06, "epoch": 1.9865871833084947, "percentage": 39.73, "elapsed_time": "0:35:16", "remaining_time": "0:53:31", "throughput": 5158.29, "total_tokens": 10919936} {"current_steps": 2667, "total_steps": 6710, "loss": 0.6863, "lr": 1.6457211184742617e-06, "epoch": 1.9873323397913563, "percentage": 39.75, "elapsed_time": "0:35:17", "remaining_time": "0:53:30", "throughput": 5158.28, "total_tokens": 10924032} {"current_steps": 2668, "total_steps": 6710, "loss": 0.777, "lr": 1.6451659315586313e-06, "epoch": 1.9880774962742176, "percentage": 39.76, "elapsed_time": "0:35:18", "remaining_time": "0:53:29", "throughput": 5158.26, "total_tokens": 10928128} {"current_steps": 2669, "total_steps": 6710, "loss": 0.6995, "lr": 1.644610658019807e-06, "epoch": 1.988822652757079, "percentage": 39.78, "elapsed_time": "0:35:19", "remaining_time": "0:53:28", "throughput": 5158.14, "total_tokens": 10932224} {"current_steps": 2670, "total_steps": 6710, "loss": 0.8632, "lr": 1.644055297979509e-06, "epoch": 1.9895678092399405, "percentage": 39.79, "elapsed_time": "0:35:20", "remaining_time": "0:53:28", "throughput": 5158.15, "total_tokens": 10936320} {"current_steps": 2671, "total_steps": 6710, "loss": 0.5669, "lr": 1.6434998515594752e-06, "epoch": 1.9903129657228018, "percentage": 39.81, "elapsed_time": "0:35:21", "remaining_time": "0:53:27", "throughput": 5158.13, "total_tokens": 10940416} {"current_steps": 2672, "total_steps": 6710, "loss": 0.5922, "lr": 1.6429443188814648e-06, "epoch": 1.9910581222056631, "percentage": 39.82, "elapsed_time": "0:35:21", "remaining_time": "0:53:26", "throughput": 5158.03, "total_tokens": 10944512} {"current_steps": 2673, "total_steps": 6710, "loss": 0.6794, "lr": 1.6423887000672536e-06, "epoch": 1.9918032786885247, "percentage": 39.84, "elapsed_time": "0:35:22", "remaining_time": "0:53:25", "throughput": 5157.99, "total_tokens": 10948608} {"current_steps": 2674, "total_steps": 6710, "loss": 0.681, "lr": 1.6418329952386374e-06, "epoch": 1.992548435171386, "percentage": 39.85, "elapsed_time": "0:35:23", "remaining_time": "0:53:25", "throughput": 5157.99, "total_tokens": 10952704} {"current_steps": 2675, "total_steps": 6710, "loss": 0.6777, "lr": 1.6412772045174308e-06, "epoch": 1.9932935916542474, "percentage": 39.87, "elapsed_time": "0:35:24", "remaining_time": "0:53:24", "throughput": 5157.96, "total_tokens": 10956800} {"current_steps": 2676, "total_steps": 6710, "loss": 0.6353, "lr": 1.640721328025467e-06, "epoch": 1.994038748137109, "percentage": 39.88, "elapsed_time": "0:35:25", "remaining_time": "0:53:23", "throughput": 5157.84, "total_tokens": 10960896} {"current_steps": 2677, "total_steps": 6710, "loss": 0.9433, "lr": 1.6401653658845978e-06, "epoch": 1.9947839046199702, "percentage": 39.9, "elapsed_time": "0:35:25", "remaining_time": "0:53:22", "throughput": 5157.72, "total_tokens": 10964992} {"current_steps": 2678, "total_steps": 6710, "loss": 0.7561, "lr": 1.639609318216695e-06, "epoch": 1.9955290611028316, "percentage": 39.91, "elapsed_time": "0:35:26", "remaining_time": "0:53:22", "throughput": 5157.7, "total_tokens": 10969088} {"current_steps": 2679, "total_steps": 6710, "loss": 0.6235, "lr": 1.639053185143647e-06, "epoch": 1.9962742175856931, "percentage": 39.93, "elapsed_time": "0:35:27", "remaining_time": "0:53:21", "throughput": 5157.66, "total_tokens": 10973184} {"current_steps": 2680, "total_steps": 6710, "loss": 0.7934, "lr": 1.638496966787363e-06, "epoch": 1.9970193740685542, "percentage": 39.94, "elapsed_time": "0:35:28", "remaining_time": "0:53:20", "throughput": 5157.67, "total_tokens": 10977280} {"current_steps": 2681, "total_steps": 6710, "loss": 0.7215, "lr": 1.6379406632697694e-06, "epoch": 1.9977645305514158, "percentage": 39.96, "elapsed_time": "0:35:29", "remaining_time": "0:53:19", "throughput": 5157.67, "total_tokens": 10981376} {"current_steps": 2682, "total_steps": 6710, "loss": 0.6235, "lr": 1.6373842747128126e-06, "epoch": 1.9985096870342773, "percentage": 39.97, "elapsed_time": "0:35:29", "remaining_time": "0:53:18", "throughput": 5157.57, "total_tokens": 10985472} {"current_steps": 2683, "total_steps": 6710, "loss": 0.9071, "lr": 1.636827801238457e-06, "epoch": 1.9992548435171384, "percentage": 39.99, "elapsed_time": "0:35:30", "remaining_time": "0:53:18", "throughput": 5157.52, "total_tokens": 10989568} {"current_steps": 2684, "total_steps": 6710, "loss": 0.6732, "lr": 1.6362712429686844e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:35:31", "remaining_time": "0:53:17", "throughput": 5157.48, "total_tokens": 10993664} {"current_steps": 2685, "total_steps": 6710, "loss": 0.3061, "lr": 1.635714600025498e-06, "epoch": 2.0007451564828616, "percentage": 40.01, "elapsed_time": "0:35:32", "remaining_time": "0:53:16", "throughput": 5157.41, "total_tokens": 10997760} {"current_steps": 2686, "total_steps": 6710, "loss": 0.3507, "lr": 1.6351578725309161e-06, "epoch": 2.0014903129657227, "percentage": 40.03, "elapsed_time": "0:35:33", "remaining_time": "0:53:15", "throughput": 5157.29, "total_tokens": 11001856} {"current_steps": 2687, "total_steps": 6710, "loss": 0.5314, "lr": 1.6346010606069787e-06, "epoch": 2.002235469448584, "percentage": 40.04, "elapsed_time": "0:35:34", "remaining_time": "0:53:15", "throughput": 5157.28, "total_tokens": 11005952} {"current_steps": 2688, "total_steps": 6710, "loss": 0.3147, "lr": 1.6340441643757424e-06, "epoch": 2.0029806259314458, "percentage": 40.06, "elapsed_time": "0:35:34", "remaining_time": "0:53:14", "throughput": 5157.26, "total_tokens": 11010048} {"current_steps": 2689, "total_steps": 6710, "loss": 0.4407, "lr": 1.6334871839592827e-06, "epoch": 2.003725782414307, "percentage": 40.07, "elapsed_time": "0:35:35", "remaining_time": "0:53:13", "throughput": 5157.22, "total_tokens": 11014144} {"current_steps": 2690, "total_steps": 6710, "loss": 0.4112, "lr": 1.6329301194796942e-06, "epoch": 2.0044709388971684, "percentage": 40.09, "elapsed_time": "0:35:36", "remaining_time": "0:53:12", "throughput": 5157.18, "total_tokens": 11018240} {"current_steps": 2691, "total_steps": 6710, "loss": 0.5016, "lr": 1.6323729710590892e-06, "epoch": 2.00521609538003, "percentage": 40.1, "elapsed_time": "0:35:37", "remaining_time": "0:53:12", "throughput": 5157.07, "total_tokens": 11022336} {"current_steps": 2692, "total_steps": 6710, "loss": 0.4642, "lr": 1.6318157388195987e-06, "epoch": 2.005961251862891, "percentage": 40.12, "elapsed_time": "0:35:38", "remaining_time": "0:53:11", "throughput": 5157.01, "total_tokens": 11026432} {"current_steps": 2693, "total_steps": 6710, "loss": 0.5168, "lr": 1.631258422883372e-06, "epoch": 2.0067064083457526, "percentage": 40.13, "elapsed_time": "0:35:38", "remaining_time": "0:53:10", "throughput": 5157.0, "total_tokens": 11030528} {"current_steps": 2694, "total_steps": 6710, "loss": 0.4503, "lr": 1.6307010233725762e-06, "epoch": 2.007451564828614, "percentage": 40.15, "elapsed_time": "0:35:39", "remaining_time": "0:53:09", "throughput": 5157.0, "total_tokens": 11034624} {"current_steps": 2695, "total_steps": 6710, "loss": 0.4077, "lr": 1.6301435404093977e-06, "epoch": 2.0081967213114753, "percentage": 40.16, "elapsed_time": "0:35:40", "remaining_time": "0:53:08", "throughput": 5156.96, "total_tokens": 11038720} {"current_steps": 2696, "total_steps": 6710, "loss": 0.416, "lr": 1.6295859741160405e-06, "epoch": 2.008941877794337, "percentage": 40.18, "elapsed_time": "0:35:41", "remaining_time": "0:53:08", "throughput": 5156.85, "total_tokens": 11042816} {"current_steps": 2697, "total_steps": 6710, "loss": 0.2201, "lr": 1.6290283246147274e-06, "epoch": 2.0096870342771984, "percentage": 40.19, "elapsed_time": "0:35:42", "remaining_time": "0:53:07", "throughput": 5156.8, "total_tokens": 11046912} {"current_steps": 2698, "total_steps": 6710, "loss": 0.5057, "lr": 1.6284705920276988e-06, "epoch": 2.0104321907600595, "percentage": 40.21, "elapsed_time": "0:35:42", "remaining_time": "0:53:06", "throughput": 5156.8, "total_tokens": 11051008} {"current_steps": 2699, "total_steps": 6710, "loss": 0.4316, "lr": 1.6279127764772146e-06, "epoch": 2.011177347242921, "percentage": 40.22, "elapsed_time": "0:35:43", "remaining_time": "0:53:05", "throughput": 5156.67, "total_tokens": 11055104} {"current_steps": 2700, "total_steps": 6710, "loss": 0.4176, "lr": 1.6273548780855508e-06, "epoch": 2.0119225037257826, "percentage": 40.24, "elapsed_time": "0:35:44", "remaining_time": "0:53:05", "throughput": 5156.66, "total_tokens": 11059200} {"current_steps": 2701, "total_steps": 6710, "loss": 0.2473, "lr": 1.6267968969750031e-06, "epoch": 2.0126676602086437, "percentage": 40.25, "elapsed_time": "0:35:45", "remaining_time": "0:53:04", "throughput": 5156.63, "total_tokens": 11063296} {"current_steps": 2702, "total_steps": 6710, "loss": 0.3498, "lr": 1.6262388332678855e-06, "epoch": 2.0134128166915053, "percentage": 40.27, "elapsed_time": "0:35:46", "remaining_time": "0:53:03", "throughput": 5156.58, "total_tokens": 11067392} {"current_steps": 2703, "total_steps": 6710, "loss": 0.486, "lr": 1.6256806870865285e-06, "epoch": 2.0141579731743664, "percentage": 40.28, "elapsed_time": "0:35:47", "remaining_time": "0:53:02", "throughput": 5156.5, "total_tokens": 11071488} {"current_steps": 2704, "total_steps": 6710, "loss": 0.6937, "lr": 1.6251224585532824e-06, "epoch": 2.014903129657228, "percentage": 40.3, "elapsed_time": "0:35:47", "remaining_time": "0:53:02", "throughput": 5156.47, "total_tokens": 11075584} {"current_steps": 2705, "total_steps": 6710, "loss": 0.4116, "lr": 1.6245641477905152e-06, "epoch": 2.0156482861400895, "percentage": 40.31, "elapsed_time": "0:35:49", "remaining_time": "0:53:01", "throughput": 5155.65, "total_tokens": 11079680} {"current_steps": 2706, "total_steps": 6710, "loss": 0.3832, "lr": 1.6240057549206117e-06, "epoch": 2.0163934426229506, "percentage": 40.33, "elapsed_time": "0:35:49", "remaining_time": "0:53:01", "throughput": 5155.57, "total_tokens": 11083776} {"current_steps": 2707, "total_steps": 6710, "loss": 0.2631, "lr": 1.6234472800659762e-06, "epoch": 2.017138599105812, "percentage": 40.34, "elapsed_time": "0:35:50", "remaining_time": "0:53:00", "throughput": 5155.53, "total_tokens": 11087872} {"current_steps": 2708, "total_steps": 6710, "loss": 0.2366, "lr": 1.6228887233490303e-06, "epoch": 2.0178837555886737, "percentage": 40.36, "elapsed_time": "0:35:51", "remaining_time": "0:52:59", "throughput": 5155.49, "total_tokens": 11091968} {"current_steps": 2709, "total_steps": 6710, "loss": 0.426, "lr": 1.6223300848922135e-06, "epoch": 2.018628912071535, "percentage": 40.37, "elapsed_time": "0:35:52", "remaining_time": "0:52:58", "throughput": 5155.38, "total_tokens": 11096064} {"current_steps": 2710, "total_steps": 6710, "loss": 0.3948, "lr": 1.6217713648179833e-06, "epoch": 2.0193740685543964, "percentage": 40.39, "elapsed_time": "0:35:53", "remaining_time": "0:52:58", "throughput": 5155.35, "total_tokens": 11100160} {"current_steps": 2711, "total_steps": 6710, "loss": 0.329, "lr": 1.6212125632488157e-06, "epoch": 2.020119225037258, "percentage": 40.4, "elapsed_time": "0:35:53", "remaining_time": "0:52:57", "throughput": 5155.33, "total_tokens": 11104256} {"current_steps": 2712, "total_steps": 6710, "loss": 0.389, "lr": 1.6206536803072035e-06, "epoch": 2.020864381520119, "percentage": 40.42, "elapsed_time": "0:35:54", "remaining_time": "0:52:56", "throughput": 5155.24, "total_tokens": 11108352} {"current_steps": 2713, "total_steps": 6710, "loss": 0.2559, "lr": 1.6200947161156575e-06, "epoch": 2.0216095380029806, "percentage": 40.43, "elapsed_time": "0:35:55", "remaining_time": "0:52:55", "throughput": 5155.17, "total_tokens": 11112448} {"current_steps": 2714, "total_steps": 6710, "loss": 0.6652, "lr": 1.6195356707967068e-06, "epoch": 2.022354694485842, "percentage": 40.45, "elapsed_time": "0:35:56", "remaining_time": "0:52:55", "throughput": 5155.11, "total_tokens": 11116544} {"current_steps": 2715, "total_steps": 6710, "loss": 0.2475, "lr": 1.6189765444728988e-06, "epoch": 2.0230998509687033, "percentage": 40.46, "elapsed_time": "0:35:57", "remaining_time": "0:52:54", "throughput": 5155.04, "total_tokens": 11120640} {"current_steps": 2716, "total_steps": 6710, "loss": 0.4209, "lr": 1.6184173372667975e-06, "epoch": 2.023845007451565, "percentage": 40.48, "elapsed_time": "0:35:58", "remaining_time": "0:52:53", "throughput": 5154.93, "total_tokens": 11124736} {"current_steps": 2717, "total_steps": 6710, "loss": 0.2503, "lr": 1.6178580493009849e-06, "epoch": 2.0245901639344264, "percentage": 40.49, "elapsed_time": "0:35:58", "remaining_time": "0:52:52", "throughput": 5154.9, "total_tokens": 11128832} {"current_steps": 2718, "total_steps": 6710, "loss": 0.4661, "lr": 1.6172986806980613e-06, "epoch": 2.0253353204172875, "percentage": 40.51, "elapsed_time": "0:35:59", "remaining_time": "0:52:52", "throughput": 5154.85, "total_tokens": 11132928} {"current_steps": 2719, "total_steps": 6710, "loss": 0.4247, "lr": 1.6167392315806443e-06, "epoch": 2.026080476900149, "percentage": 40.52, "elapsed_time": "0:36:00", "remaining_time": "0:52:51", "throughput": 5154.79, "total_tokens": 11137024} {"current_steps": 2720, "total_steps": 6710, "loss": 0.3609, "lr": 1.6161797020713688e-06, "epoch": 2.0268256333830106, "percentage": 40.54, "elapsed_time": "0:36:01", "remaining_time": "0:52:50", "throughput": 5154.78, "total_tokens": 11141120} {"current_steps": 2721, "total_steps": 6710, "loss": 0.3843, "lr": 1.615620092292888e-06, "epoch": 2.0275707898658717, "percentage": 40.55, "elapsed_time": "0:36:02", "remaining_time": "0:52:49", "throughput": 5154.77, "total_tokens": 11145216} {"current_steps": 2722, "total_steps": 6710, "loss": 0.2619, "lr": 1.615060402367872e-06, "epoch": 2.0283159463487332, "percentage": 40.57, "elapsed_time": "0:36:02", "remaining_time": "0:52:48", "throughput": 5154.74, "total_tokens": 11149312} {"current_steps": 2723, "total_steps": 6710, "loss": 0.284, "lr": 1.6145006324190093e-06, "epoch": 2.029061102831595, "percentage": 40.58, "elapsed_time": "0:36:03", "remaining_time": "0:52:48", "throughput": 5154.71, "total_tokens": 11153408} {"current_steps": 2724, "total_steps": 6710, "loss": 0.4266, "lr": 1.6139407825690048e-06, "epoch": 2.029806259314456, "percentage": 40.6, "elapsed_time": "0:36:04", "remaining_time": "0:52:47", "throughput": 5154.65, "total_tokens": 11157504} {"current_steps": 2725, "total_steps": 6710, "loss": 0.4134, "lr": 1.6133808529405823e-06, "epoch": 2.0305514157973175, "percentage": 40.61, "elapsed_time": "0:36:05", "remaining_time": "0:52:46", "throughput": 5154.61, "total_tokens": 11161600} {"current_steps": 2726, "total_steps": 6710, "loss": 0.4224, "lr": 1.612820843656482e-06, "epoch": 2.031296572280179, "percentage": 40.63, "elapsed_time": "0:36:06", "remaining_time": "0:52:45", "throughput": 5154.49, "total_tokens": 11165696} {"current_steps": 2727, "total_steps": 6710, "loss": 0.3673, "lr": 1.612260754839462e-06, "epoch": 2.03204172876304, "percentage": 40.64, "elapsed_time": "0:36:07", "remaining_time": "0:52:45", "throughput": 5154.43, "total_tokens": 11169792} {"current_steps": 2728, "total_steps": 6710, "loss": 0.334, "lr": 1.6117005866122976e-06, "epoch": 2.0327868852459017, "percentage": 40.66, "elapsed_time": "0:36:07", "remaining_time": "0:52:44", "throughput": 5154.39, "total_tokens": 11173888} {"current_steps": 2729, "total_steps": 6710, "loss": 0.3824, "lr": 1.6111403390977824e-06, "epoch": 2.0335320417287632, "percentage": 40.67, "elapsed_time": "0:36:08", "remaining_time": "0:52:43", "throughput": 5154.37, "total_tokens": 11177984} {"current_steps": 2730, "total_steps": 6710, "loss": 0.1766, "lr": 1.6105800124187254e-06, "epoch": 2.0342771982116243, "percentage": 40.69, "elapsed_time": "0:36:09", "remaining_time": "0:52:42", "throughput": 5154.29, "total_tokens": 11182080} {"current_steps": 2731, "total_steps": 6710, "loss": 0.4043, "lr": 1.6100196066979554e-06, "epoch": 2.035022354694486, "percentage": 40.7, "elapsed_time": "0:36:10", "remaining_time": "0:52:42", "throughput": 5154.31, "total_tokens": 11186176} {"current_steps": 2732, "total_steps": 6710, "loss": 0.5028, "lr": 1.6094591220583167e-06, "epoch": 2.0357675111773474, "percentage": 40.72, "elapsed_time": "0:36:11", "remaining_time": "0:52:41", "throughput": 5154.26, "total_tokens": 11190272} {"current_steps": 2733, "total_steps": 6710, "loss": 0.4971, "lr": 1.6088985586226715e-06, "epoch": 2.0365126676602086, "percentage": 40.73, "elapsed_time": "0:36:11", "remaining_time": "0:52:40", "throughput": 5154.21, "total_tokens": 11194368} {"current_steps": 2734, "total_steps": 6710, "loss": 0.3338, "lr": 1.6083379165138996e-06, "epoch": 2.03725782414307, "percentage": 40.75, "elapsed_time": "0:36:12", "remaining_time": "0:52:39", "throughput": 5154.14, "total_tokens": 11198464} {"current_steps": 2735, "total_steps": 6710, "loss": 0.3952, "lr": 1.6077771958548977e-06, "epoch": 2.0380029806259317, "percentage": 40.76, "elapsed_time": "0:36:13", "remaining_time": "0:52:38", "throughput": 5154.08, "total_tokens": 11202560} {"current_steps": 2736, "total_steps": 6710, "loss": 0.3486, "lr": 1.6072163967685795e-06, "epoch": 2.0387481371087928, "percentage": 40.77, "elapsed_time": "0:36:14", "remaining_time": "0:52:38", "throughput": 5154.05, "total_tokens": 11206656} {"current_steps": 2737, "total_steps": 6710, "loss": 0.304, "lr": 1.6066555193778766e-06, "epoch": 2.0394932935916543, "percentage": 40.79, "elapsed_time": "0:36:15", "remaining_time": "0:52:37", "throughput": 5153.98, "total_tokens": 11210752} {"current_steps": 2738, "total_steps": 6710, "loss": 0.4441, "lr": 1.6060945638057372e-06, "epoch": 2.0402384500745154, "percentage": 40.8, "elapsed_time": "0:36:15", "remaining_time": "0:52:36", "throughput": 5153.93, "total_tokens": 11214848} {"current_steps": 2739, "total_steps": 6710, "loss": 0.3805, "lr": 1.6055335301751266e-06, "epoch": 2.040983606557377, "percentage": 40.82, "elapsed_time": "0:36:16", "remaining_time": "0:52:35", "throughput": 5153.88, "total_tokens": 11218944} {"current_steps": 2740, "total_steps": 6710, "loss": 0.5175, "lr": 1.6049724186090273e-06, "epoch": 2.0417287630402385, "percentage": 40.83, "elapsed_time": "0:36:17", "remaining_time": "0:52:35", "throughput": 5153.76, "total_tokens": 11223040} {"current_steps": 2741, "total_steps": 6710, "loss": 0.766, "lr": 1.6044112292304391e-06, "epoch": 2.0424739195230996, "percentage": 40.85, "elapsed_time": "0:36:18", "remaining_time": "0:52:34", "throughput": 5153.78, "total_tokens": 11227136} {"current_steps": 2742, "total_steps": 6710, "loss": 0.2235, "lr": 1.6038499621623787e-06, "epoch": 2.043219076005961, "percentage": 40.86, "elapsed_time": "0:36:19", "remaining_time": "0:52:33", "throughput": 5153.74, "total_tokens": 11231232} {"current_steps": 2743, "total_steps": 6710, "loss": 0.2392, "lr": 1.6032886175278801e-06, "epoch": 2.0439642324888228, "percentage": 40.88, "elapsed_time": "0:36:20", "remaining_time": "0:52:32", "throughput": 5153.69, "total_tokens": 11235328} {"current_steps": 2744, "total_steps": 6710, "loss": 0.5272, "lr": 1.6027271954499934e-06, "epoch": 2.044709388971684, "percentage": 40.89, "elapsed_time": "0:36:20", "remaining_time": "0:52:32", "throughput": 5153.64, "total_tokens": 11239424} {"current_steps": 2745, "total_steps": 6710, "loss": 0.2898, "lr": 1.6021656960517873e-06, "epoch": 2.0454545454545454, "percentage": 40.91, "elapsed_time": "0:36:21", "remaining_time": "0:52:31", "throughput": 5153.65, "total_tokens": 11243520} {"current_steps": 2746, "total_steps": 6710, "loss": 0.4285, "lr": 1.6016041194563458e-06, "epoch": 2.046199701937407, "percentage": 40.92, "elapsed_time": "0:36:22", "remaining_time": "0:52:30", "throughput": 5153.65, "total_tokens": 11247616} {"current_steps": 2747, "total_steps": 6710, "loss": 0.4264, "lr": 1.6010424657867704e-06, "epoch": 2.046944858420268, "percentage": 40.94, "elapsed_time": "0:36:23", "remaining_time": "0:52:29", "throughput": 5153.62, "total_tokens": 11251712} {"current_steps": 2748, "total_steps": 6710, "loss": 0.5424, "lr": 1.6004807351661803e-06, "epoch": 2.0476900149031296, "percentage": 40.95, "elapsed_time": "0:36:24", "remaining_time": "0:52:28", "throughput": 5153.53, "total_tokens": 11255808} {"current_steps": 2749, "total_steps": 6710, "loss": 0.3185, "lr": 1.59991892771771e-06, "epoch": 2.048435171385991, "percentage": 40.97, "elapsed_time": "0:36:24", "remaining_time": "0:52:28", "throughput": 5153.52, "total_tokens": 11259904} {"current_steps": 2750, "total_steps": 6710, "loss": 0.4703, "lr": 1.599357043564512e-06, "epoch": 2.0491803278688523, "percentage": 40.98, "elapsed_time": "0:36:25", "remaining_time": "0:52:27", "throughput": 5153.4, "total_tokens": 11264000} {"current_steps": 2751, "total_steps": 6710, "loss": 0.4219, "lr": 1.5987950828297556e-06, "epoch": 2.049925484351714, "percentage": 41.0, "elapsed_time": "0:36:26", "remaining_time": "0:52:26", "throughput": 5153.33, "total_tokens": 11268096} {"current_steps": 2752, "total_steps": 6710, "loss": 0.2799, "lr": 1.5982330456366263e-06, "epoch": 2.0506706408345754, "percentage": 41.01, "elapsed_time": "0:36:27", "remaining_time": "0:52:25", "throughput": 5153.29, "total_tokens": 11272192} {"current_steps": 2753, "total_steps": 6710, "loss": 0.3161, "lr": 1.5976709321083272e-06, "epoch": 2.0514157973174365, "percentage": 41.03, "elapsed_time": "0:36:28", "remaining_time": "0:52:25", "throughput": 5153.28, "total_tokens": 11276288} {"current_steps": 2754, "total_steps": 6710, "loss": 0.6422, "lr": 1.5971087423680768e-06, "epoch": 2.052160953800298, "percentage": 41.04, "elapsed_time": "0:36:29", "remaining_time": "0:52:24", "throughput": 5153.17, "total_tokens": 11280384} {"current_steps": 2755, "total_steps": 6710, "loss": 0.335, "lr": 1.5965464765391114e-06, "epoch": 2.0529061102831596, "percentage": 41.06, "elapsed_time": "0:36:29", "remaining_time": "0:52:23", "throughput": 5153.12, "total_tokens": 11284480} {"current_steps": 2756, "total_steps": 6710, "loss": 0.4738, "lr": 1.595984134744684e-06, "epoch": 2.0536512667660207, "percentage": 41.07, "elapsed_time": "0:36:30", "remaining_time": "0:52:22", "throughput": 5153.08, "total_tokens": 11288576} {"current_steps": 2757, "total_steps": 6710, "loss": 0.4752, "lr": 1.5954217171080637e-06, "epoch": 2.0543964232488823, "percentage": 41.09, "elapsed_time": "0:36:31", "remaining_time": "0:52:22", "throughput": 5152.95, "total_tokens": 11292672} {"current_steps": 2758, "total_steps": 6710, "loss": 0.5173, "lr": 1.5948592237525364e-06, "epoch": 2.055141579731744, "percentage": 41.1, "elapsed_time": "0:36:32", "remaining_time": "0:52:21", "throughput": 5152.93, "total_tokens": 11296768} {"current_steps": 2759, "total_steps": 6710, "loss": 0.5173, "lr": 1.5942966548014053e-06, "epoch": 2.055886736214605, "percentage": 41.12, "elapsed_time": "0:36:33", "remaining_time": "0:52:20", "throughput": 5152.89, "total_tokens": 11300864} {"current_steps": 2760, "total_steps": 6710, "loss": 0.5662, "lr": 1.5937340103779882e-06, "epoch": 2.0566318926974665, "percentage": 41.13, "elapsed_time": "0:36:33", "remaining_time": "0:52:19", "throughput": 5152.77, "total_tokens": 11304960} {"current_steps": 2761, "total_steps": 6710, "loss": 0.5471, "lr": 1.5931712906056219e-06, "epoch": 2.057377049180328, "percentage": 41.15, "elapsed_time": "0:36:34", "remaining_time": "0:52:19", "throughput": 5152.78, "total_tokens": 11309056} {"current_steps": 2762, "total_steps": 6710, "loss": 0.3139, "lr": 1.5926084956076583e-06, "epoch": 2.058122205663189, "percentage": 41.16, "elapsed_time": "0:36:35", "remaining_time": "0:52:18", "throughput": 5152.79, "total_tokens": 11313152} {"current_steps": 2763, "total_steps": 6710, "loss": 0.3528, "lr": 1.5920456255074657e-06, "epoch": 2.0588673621460507, "percentage": 41.18, "elapsed_time": "0:36:36", "remaining_time": "0:52:17", "throughput": 5152.79, "total_tokens": 11317248} {"current_steps": 2764, "total_steps": 6710, "loss": 0.3929, "lr": 1.5914826804284295e-06, "epoch": 2.0596125186289123, "percentage": 41.19, "elapsed_time": "0:36:37", "remaining_time": "0:52:16", "throughput": 5152.76, "total_tokens": 11321344} {"current_steps": 2765, "total_steps": 6710, "loss": 0.1518, "lr": 1.590919660493952e-06, "epoch": 2.0603576751117734, "percentage": 41.21, "elapsed_time": "0:36:37", "remaining_time": "0:52:15", "throughput": 5152.77, "total_tokens": 11325440} {"current_steps": 2766, "total_steps": 6710, "loss": 0.3578, "lr": 1.5903565658274501e-06, "epoch": 2.061102831594635, "percentage": 41.22, "elapsed_time": "0:36:38", "remaining_time": "0:52:15", "throughput": 5152.78, "total_tokens": 11329536} {"current_steps": 2767, "total_steps": 6710, "loss": 0.3016, "lr": 1.5897933965523584e-06, "epoch": 2.0618479880774965, "percentage": 41.24, "elapsed_time": "0:36:39", "remaining_time": "0:52:14", "throughput": 5152.64, "total_tokens": 11333632} {"current_steps": 2768, "total_steps": 6710, "loss": 0.5065, "lr": 1.5892301527921283e-06, "epoch": 2.0625931445603576, "percentage": 41.25, "elapsed_time": "0:36:40", "remaining_time": "0:52:13", "throughput": 5152.57, "total_tokens": 11337728} {"current_steps": 2769, "total_steps": 6710, "loss": 0.2405, "lr": 1.5886668346702261e-06, "epoch": 2.063338301043219, "percentage": 41.27, "elapsed_time": "0:36:41", "remaining_time": "0:52:12", "throughput": 5152.47, "total_tokens": 11341824} {"current_steps": 2770, "total_steps": 6710, "loss": 0.5252, "lr": 1.5881034423101355e-06, "epoch": 2.0640834575260807, "percentage": 41.28, "elapsed_time": "0:36:42", "remaining_time": "0:52:12", "throughput": 5152.42, "total_tokens": 11345920} {"current_steps": 2771, "total_steps": 6710, "loss": 0.3742, "lr": 1.5875399758353556e-06, "epoch": 2.064828614008942, "percentage": 41.3, "elapsed_time": "0:36:42", "remaining_time": "0:52:11", "throughput": 5152.38, "total_tokens": 11350016} {"current_steps": 2772, "total_steps": 6710, "loss": 0.5077, "lr": 1.5869764353694033e-06, "epoch": 2.0655737704918034, "percentage": 41.31, "elapsed_time": "0:36:43", "remaining_time": "0:52:10", "throughput": 5152.38, "total_tokens": 11354112} {"current_steps": 2773, "total_steps": 6710, "loss": 0.5829, "lr": 1.5864128210358104e-06, "epoch": 2.066318926974665, "percentage": 41.33, "elapsed_time": "0:36:44", "remaining_time": "0:52:09", "throughput": 5152.39, "total_tokens": 11358208} {"current_steps": 2774, "total_steps": 6710, "loss": 0.2311, "lr": 1.5858491329581243e-06, "epoch": 2.067064083457526, "percentage": 41.34, "elapsed_time": "0:36:45", "remaining_time": "0:52:09", "throughput": 5152.35, "total_tokens": 11362304} {"current_steps": 2775, "total_steps": 6710, "loss": 0.4408, "lr": 1.5852853712599107e-06, "epoch": 2.0678092399403876, "percentage": 41.36, "elapsed_time": "0:36:46", "remaining_time": "0:52:08", "throughput": 5152.36, "total_tokens": 11366400} {"current_steps": 2776, "total_steps": 6710, "loss": 0.555, "lr": 1.5847215360647491e-06, "epoch": 2.0685543964232487, "percentage": 41.37, "elapsed_time": "0:36:46", "remaining_time": "0:52:07", "throughput": 5152.35, "total_tokens": 11370496} {"current_steps": 2777, "total_steps": 6710, "loss": 0.3865, "lr": 1.5841576274962367e-06, "epoch": 2.0692995529061102, "percentage": 41.39, "elapsed_time": "0:36:47", "remaining_time": "0:52:06", "throughput": 5152.28, "total_tokens": 11374592} {"current_steps": 2778, "total_steps": 6710, "loss": 0.509, "lr": 1.5835936456779862e-06, "epoch": 2.070044709388972, "percentage": 41.4, "elapsed_time": "0:36:48", "remaining_time": "0:52:05", "throughput": 5152.25, "total_tokens": 11378688} {"current_steps": 2779, "total_steps": 6710, "loss": 0.4251, "lr": 1.5830295907336272e-06, "epoch": 2.070789865871833, "percentage": 41.42, "elapsed_time": "0:36:49", "remaining_time": "0:52:05", "throughput": 5152.26, "total_tokens": 11382784} {"current_steps": 2780, "total_steps": 6710, "loss": 0.3993, "lr": 1.582465462786803e-06, "epoch": 2.0715350223546944, "percentage": 41.43, "elapsed_time": "0:36:50", "remaining_time": "0:52:04", "throughput": 5152.28, "total_tokens": 11386880} {"current_steps": 2781, "total_steps": 6710, "loss": 0.176, "lr": 1.5819012619611756e-06, "epoch": 2.072280178837556, "percentage": 41.45, "elapsed_time": "0:36:50", "remaining_time": "0:52:03", "throughput": 5152.14, "total_tokens": 11390976} {"current_steps": 2782, "total_steps": 6710, "loss": 0.3882, "lr": 1.5813369883804217e-06, "epoch": 2.073025335320417, "percentage": 41.46, "elapsed_time": "0:36:51", "remaining_time": "0:52:02", "throughput": 5152.14, "total_tokens": 11395072} {"current_steps": 2783, "total_steps": 6710, "loss": 0.5884, "lr": 1.5807726421682337e-06, "epoch": 2.0737704918032787, "percentage": 41.48, "elapsed_time": "0:36:52", "remaining_time": "0:52:02", "throughput": 5152.11, "total_tokens": 11399168} {"current_steps": 2784, "total_steps": 6710, "loss": 0.3777, "lr": 1.5802082234483212e-06, "epoch": 2.07451564828614, "percentage": 41.49, "elapsed_time": "0:36:53", "remaining_time": "0:52:01", "throughput": 5152.12, "total_tokens": 11403264} {"current_steps": 2785, "total_steps": 6710, "loss": 0.4458, "lr": 1.5796437323444077e-06, "epoch": 2.0752608047690013, "percentage": 41.51, "elapsed_time": "0:36:54", "remaining_time": "0:52:00", "throughput": 5152.06, "total_tokens": 11407360} {"current_steps": 2786, "total_steps": 6710, "loss": 0.212, "lr": 1.5790791689802345e-06, "epoch": 2.076005961251863, "percentage": 41.52, "elapsed_time": "0:36:54", "remaining_time": "0:51:59", "throughput": 5152.05, "total_tokens": 11411456} {"current_steps": 2787, "total_steps": 6710, "loss": 0.4058, "lr": 1.5785145334795575e-06, "epoch": 2.0767511177347244, "percentage": 41.54, "elapsed_time": "0:36:55", "remaining_time": "0:51:58", "throughput": 5152.02, "total_tokens": 11415552} {"current_steps": 2788, "total_steps": 6710, "loss": 0.4544, "lr": 1.577949825966149e-06, "epoch": 2.0774962742175855, "percentage": 41.55, "elapsed_time": "0:36:56", "remaining_time": "0:51:58", "throughput": 5151.93, "total_tokens": 11419648} {"current_steps": 2789, "total_steps": 6710, "loss": 0.4831, "lr": 1.5773850465637969e-06, "epoch": 2.078241430700447, "percentage": 41.56, "elapsed_time": "0:36:57", "remaining_time": "0:51:57", "throughput": 5151.92, "total_tokens": 11423744} {"current_steps": 2790, "total_steps": 6710, "loss": 0.3531, "lr": 1.5768201953963047e-06, "epoch": 2.0789865871833086, "percentage": 41.58, "elapsed_time": "0:36:58", "remaining_time": "0:51:56", "throughput": 5151.93, "total_tokens": 11427840} {"current_steps": 2791, "total_steps": 6710, "loss": 0.3724, "lr": 1.576255272587492e-06, "epoch": 2.0797317436661698, "percentage": 41.59, "elapsed_time": "0:36:59", "remaining_time": "0:51:55", "throughput": 5151.8, "total_tokens": 11431936} {"current_steps": 2792, "total_steps": 6710, "loss": 0.2955, "lr": 1.5756902782611937e-06, "epoch": 2.0804769001490313, "percentage": 41.61, "elapsed_time": "0:36:59", "remaining_time": "0:51:55", "throughput": 5151.82, "total_tokens": 11436032} {"current_steps": 2793, "total_steps": 6710, "loss": 0.2901, "lr": 1.5751252125412612e-06, "epoch": 2.081222056631893, "percentage": 41.62, "elapsed_time": "0:37:00", "remaining_time": "0:51:54", "throughput": 5151.81, "total_tokens": 11440128} {"current_steps": 2794, "total_steps": 6710, "loss": 0.4373, "lr": 1.5745600755515606e-06, "epoch": 2.081967213114754, "percentage": 41.64, "elapsed_time": "0:37:01", "remaining_time": "0:51:53", "throughput": 5151.79, "total_tokens": 11444224} {"current_steps": 2795, "total_steps": 6710, "loss": 0.6305, "lr": 1.5739948674159732e-06, "epoch": 2.0827123695976155, "percentage": 41.65, "elapsed_time": "0:37:02", "remaining_time": "0:51:52", "throughput": 5151.65, "total_tokens": 11448320} {"current_steps": 2796, "total_steps": 6710, "loss": 0.1947, "lr": 1.5734295882583978e-06, "epoch": 2.083457526080477, "percentage": 41.67, "elapsed_time": "0:37:03", "remaining_time": "0:51:51", "throughput": 5151.64, "total_tokens": 11452416} {"current_steps": 2797, "total_steps": 6710, "loss": 0.4697, "lr": 1.572864238202747e-06, "epoch": 2.084202682563338, "percentage": 41.68, "elapsed_time": "0:37:03", "remaining_time": "0:51:51", "throughput": 5151.64, "total_tokens": 11456512} {"current_steps": 2798, "total_steps": 6710, "loss": 0.644, "lr": 1.5722988173729497e-06, "epoch": 2.0849478390461997, "percentage": 41.7, "elapsed_time": "0:37:04", "remaining_time": "0:51:50", "throughput": 5151.51, "total_tokens": 11460608} {"current_steps": 2799, "total_steps": 6710, "loss": 0.5074, "lr": 1.5717333258929504e-06, "epoch": 2.0856929955290613, "percentage": 41.71, "elapsed_time": "0:37:05", "remaining_time": "0:51:49", "throughput": 5151.51, "total_tokens": 11464704} {"current_steps": 2800, "total_steps": 6710, "loss": 0.216, "lr": 1.5711677638867088e-06, "epoch": 2.0864381520119224, "percentage": 41.73, "elapsed_time": "0:37:06", "remaining_time": "0:51:48", "throughput": 5151.47, "total_tokens": 11468800} {"current_steps": 2801, "total_steps": 6710, "loss": 0.3164, "lr": 1.5706021314781997e-06, "epoch": 2.087183308494784, "percentage": 41.74, "elapsed_time": "0:37:07", "remaining_time": "0:51:48", "throughput": 5151.45, "total_tokens": 11472896} {"current_steps": 2802, "total_steps": 6710, "loss": 0.4065, "lr": 1.570036428791414e-06, "epoch": 2.0879284649776455, "percentage": 41.76, "elapsed_time": "0:37:07", "remaining_time": "0:51:47", "throughput": 5151.46, "total_tokens": 11476992} {"current_steps": 2803, "total_steps": 6710, "loss": 0.4132, "lr": 1.5694706559503584e-06, "epoch": 2.0886736214605066, "percentage": 41.77, "elapsed_time": "0:37:08", "remaining_time": "0:51:46", "throughput": 5151.44, "total_tokens": 11481088} {"current_steps": 2804, "total_steps": 6710, "loss": 0.5662, "lr": 1.5689048130790533e-06, "epoch": 2.089418777943368, "percentage": 41.79, "elapsed_time": "0:37:09", "remaining_time": "0:51:45", "throughput": 5151.42, "total_tokens": 11485184} {"current_steps": 2805, "total_steps": 6710, "loss": 0.4178, "lr": 1.5683389003015358e-06, "epoch": 2.0901639344262297, "percentage": 41.8, "elapsed_time": "0:37:10", "remaining_time": "0:51:44", "throughput": 5151.33, "total_tokens": 11489280} {"current_steps": 2806, "total_steps": 6710, "loss": 0.2604, "lr": 1.5677729177418592e-06, "epoch": 2.090909090909091, "percentage": 41.82, "elapsed_time": "0:37:11", "remaining_time": "0:51:44", "throughput": 5151.35, "total_tokens": 11493376} {"current_steps": 2807, "total_steps": 6710, "loss": 0.506, "lr": 1.5672068655240892e-06, "epoch": 2.0916542473919524, "percentage": 41.83, "elapsed_time": "0:37:11", "remaining_time": "0:51:43", "throughput": 5151.35, "total_tokens": 11497472} {"current_steps": 2808, "total_steps": 6710, "loss": 0.5232, "lr": 1.566640743772309e-06, "epoch": 2.092399403874814, "percentage": 41.85, "elapsed_time": "0:37:12", "remaining_time": "0:51:42", "throughput": 5151.24, "total_tokens": 11501568} {"current_steps": 2809, "total_steps": 6710, "loss": 0.3914, "lr": 1.5660745526106169e-06, "epoch": 2.093144560357675, "percentage": 41.86, "elapsed_time": "0:37:13", "remaining_time": "0:51:41", "throughput": 5151.18, "total_tokens": 11505664} {"current_steps": 2810, "total_steps": 6710, "loss": 0.2953, "lr": 1.565508292163126e-06, "epoch": 2.0938897168405366, "percentage": 41.88, "elapsed_time": "0:37:14", "remaining_time": "0:51:41", "throughput": 5151.16, "total_tokens": 11509760} {"current_steps": 2811, "total_steps": 6710, "loss": 0.4823, "lr": 1.5649419625539646e-06, "epoch": 2.0946348733233977, "percentage": 41.89, "elapsed_time": "0:37:15", "remaining_time": "0:51:40", "throughput": 5151.15, "total_tokens": 11513856} {"current_steps": 2812, "total_steps": 6710, "loss": 0.5895, "lr": 1.564375563907276e-06, "epoch": 2.0953800298062593, "percentage": 41.91, "elapsed_time": "0:37:16", "remaining_time": "0:51:39", "throughput": 5151.06, "total_tokens": 11517952} {"current_steps": 2813, "total_steps": 6710, "loss": 0.4524, "lr": 1.5638090963472195e-06, "epoch": 2.096125186289121, "percentage": 41.92, "elapsed_time": "0:37:16", "remaining_time": "0:51:38", "throughput": 5151.05, "total_tokens": 11522048} {"current_steps": 2814, "total_steps": 6710, "loss": 0.4906, "lr": 1.5632425599979675e-06, "epoch": 2.096870342771982, "percentage": 41.94, "elapsed_time": "0:37:17", "remaining_time": "0:51:38", "throughput": 5151.02, "total_tokens": 11526144} {"current_steps": 2815, "total_steps": 6710, "loss": 0.3687, "lr": 1.56267595498371e-06, "epoch": 2.0976154992548435, "percentage": 41.95, "elapsed_time": "0:37:18", "remaining_time": "0:51:37", "throughput": 5150.89, "total_tokens": 11530240} {"current_steps": 2816, "total_steps": 6710, "loss": 0.3802, "lr": 1.56210928142865e-06, "epoch": 2.098360655737705, "percentage": 41.97, "elapsed_time": "0:37:19", "remaining_time": "0:51:36", "throughput": 5150.87, "total_tokens": 11534336} {"current_steps": 2817, "total_steps": 6710, "loss": 0.3171, "lr": 1.5615425394570074e-06, "epoch": 2.099105812220566, "percentage": 41.98, "elapsed_time": "0:37:20", "remaining_time": "0:51:35", "throughput": 5150.82, "total_tokens": 11538432} {"current_steps": 2818, "total_steps": 6710, "loss": 0.4325, "lr": 1.5609757291930152e-06, "epoch": 2.0998509687034277, "percentage": 42.0, "elapsed_time": "0:37:20", "remaining_time": "0:51:35", "throughput": 5150.67, "total_tokens": 11542528} {"current_steps": 2819, "total_steps": 6710, "loss": 0.3426, "lr": 1.5604088507609228e-06, "epoch": 2.1005961251862892, "percentage": 42.01, "elapsed_time": "0:37:21", "remaining_time": "0:51:34", "throughput": 5150.52, "total_tokens": 11546624} {"current_steps": 2820, "total_steps": 6710, "loss": 0.2365, "lr": 1.5598419042849938e-06, "epoch": 2.1013412816691504, "percentage": 42.03, "elapsed_time": "0:37:22", "remaining_time": "0:51:33", "throughput": 5150.5, "total_tokens": 11550720} {"current_steps": 2821, "total_steps": 6710, "loss": 0.4685, "lr": 1.5592748898895071e-06, "epoch": 2.102086438152012, "percentage": 42.04, "elapsed_time": "0:37:23", "remaining_time": "0:51:32", "throughput": 5150.48, "total_tokens": 11554816} {"current_steps": 2822, "total_steps": 6710, "loss": 0.2973, "lr": 1.5587078076987559e-06, "epoch": 2.1028315946348735, "percentage": 42.06, "elapsed_time": "0:37:24", "remaining_time": "0:51:32", "throughput": 5150.34, "total_tokens": 11558912} {"current_steps": 2823, "total_steps": 6710, "loss": 0.5264, "lr": 1.5581406578370487e-06, "epoch": 2.1035767511177346, "percentage": 42.07, "elapsed_time": "0:37:25", "remaining_time": "0:51:31", "throughput": 5150.31, "total_tokens": 11563008} {"current_steps": 2824, "total_steps": 6710, "loss": 0.3356, "lr": 1.5575734404287091e-06, "epoch": 2.104321907600596, "percentage": 42.09, "elapsed_time": "0:37:25", "remaining_time": "0:51:30", "throughput": 5150.26, "total_tokens": 11567104} {"current_steps": 2825, "total_steps": 6710, "loss": 0.5804, "lr": 1.557006155598075e-06, "epoch": 2.1050670640834577, "percentage": 42.1, "elapsed_time": "0:37:26", "remaining_time": "0:51:29", "throughput": 5150.15, "total_tokens": 11571200} {"current_steps": 2826, "total_steps": 6710, "loss": 0.4639, "lr": 1.5564388034694994e-06, "epoch": 2.105812220566319, "percentage": 42.12, "elapsed_time": "0:37:27", "remaining_time": "0:51:29", "throughput": 5150.13, "total_tokens": 11575296} {"current_steps": 2827, "total_steps": 6710, "loss": 0.3367, "lr": 1.5558713841673502e-06, "epoch": 2.1065573770491803, "percentage": 42.13, "elapsed_time": "0:37:28", "remaining_time": "0:51:28", "throughput": 5150.09, "total_tokens": 11579392} {"current_steps": 2828, "total_steps": 6710, "loss": 0.5619, "lr": 1.5553038978160093e-06, "epoch": 2.107302533532042, "percentage": 42.15, "elapsed_time": "0:37:29", "remaining_time": "0:51:27", "throughput": 5150.07, "total_tokens": 11583488} {"current_steps": 2829, "total_steps": 6710, "loss": 0.3859, "lr": 1.5547363445398738e-06, "epoch": 2.108047690014903, "percentage": 42.16, "elapsed_time": "0:37:30", "remaining_time": "0:51:26", "throughput": 5149.99, "total_tokens": 11587584} {"current_steps": 2830, "total_steps": 6710, "loss": 0.3712, "lr": 1.5541687244633557e-06, "epoch": 2.1087928464977646, "percentage": 42.18, "elapsed_time": "0:37:30", "remaining_time": "0:51:25", "throughput": 5149.96, "total_tokens": 11591680} {"current_steps": 2831, "total_steps": 6710, "loss": 0.6298, "lr": 1.5536010377108812e-06, "epoch": 2.109538002980626, "percentage": 42.19, "elapsed_time": "0:37:31", "remaining_time": "0:51:25", "throughput": 5149.91, "total_tokens": 11595776} {"current_steps": 2832, "total_steps": 6710, "loss": 0.4157, "lr": 1.5530332844068914e-06, "epoch": 2.110283159463487, "percentage": 42.21, "elapsed_time": "0:37:32", "remaining_time": "0:51:24", "throughput": 5149.8, "total_tokens": 11599872} {"current_steps": 2833, "total_steps": 6710, "loss": 0.3885, "lr": 1.552465464675842e-06, "epoch": 2.1110283159463488, "percentage": 42.22, "elapsed_time": "0:37:33", "remaining_time": "0:51:23", "throughput": 5149.71, "total_tokens": 11603968} {"current_steps": 2834, "total_steps": 6710, "loss": 0.3571, "lr": 1.5518975786422024e-06, "epoch": 2.1117734724292103, "percentage": 42.24, "elapsed_time": "0:37:34", "remaining_time": "0:51:22", "throughput": 5149.67, "total_tokens": 11608064} {"current_steps": 2835, "total_steps": 6710, "loss": 0.4153, "lr": 1.551329626430458e-06, "epoch": 2.1125186289120714, "percentage": 42.25, "elapsed_time": "0:37:34", "remaining_time": "0:51:22", "throughput": 5149.66, "total_tokens": 11612160} {"current_steps": 2836, "total_steps": 6710, "loss": 0.3135, "lr": 1.550761608165108e-06, "epoch": 2.113263785394933, "percentage": 42.27, "elapsed_time": "0:37:35", "remaining_time": "0:51:21", "throughput": 5149.51, "total_tokens": 11616256} {"current_steps": 2837, "total_steps": 6710, "loss": 0.4389, "lr": 1.5501935239706656e-06, "epoch": 2.1140089418777945, "percentage": 42.28, "elapsed_time": "0:37:36", "remaining_time": "0:51:20", "throughput": 5149.53, "total_tokens": 11620352} {"current_steps": 2838, "total_steps": 6710, "loss": 0.415, "lr": 1.5496253739716596e-06, "epoch": 2.1147540983606556, "percentage": 42.3, "elapsed_time": "0:37:37", "remaining_time": "0:51:19", "throughput": 5149.55, "total_tokens": 11624448} {"current_steps": 2839, "total_steps": 6710, "loss": 0.4284, "lr": 1.5490571582926316e-06, "epoch": 2.115499254843517, "percentage": 42.31, "elapsed_time": "0:37:38", "remaining_time": "0:51:19", "throughput": 5149.41, "total_tokens": 11628544} {"current_steps": 2840, "total_steps": 6710, "loss": 0.2738, "lr": 1.5484888770581396e-06, "epoch": 2.1162444113263787, "percentage": 42.32, "elapsed_time": "0:37:39", "remaining_time": "0:51:18", "throughput": 5149.4, "total_tokens": 11632640} {"current_steps": 2841, "total_steps": 6710, "loss": 0.4983, "lr": 1.5479205303927541e-06, "epoch": 2.11698956780924, "percentage": 42.34, "elapsed_time": "0:37:39", "remaining_time": "0:51:17", "throughput": 5149.33, "total_tokens": 11636736} {"current_steps": 2842, "total_steps": 6710, "loss": 0.1542, "lr": 1.547352118421061e-06, "epoch": 2.1177347242921014, "percentage": 42.35, "elapsed_time": "0:37:40", "remaining_time": "0:51:16", "throughput": 5149.27, "total_tokens": 11640832} {"current_steps": 2843, "total_steps": 6710, "loss": 0.2851, "lr": 1.54678364126766e-06, "epoch": 2.118479880774963, "percentage": 42.37, "elapsed_time": "0:37:41", "remaining_time": "0:51:16", "throughput": 5149.24, "total_tokens": 11644928} {"current_steps": 2844, "total_steps": 6710, "loss": 0.3389, "lr": 1.546215099057166e-06, "epoch": 2.119225037257824, "percentage": 42.38, "elapsed_time": "0:37:42", "remaining_time": "0:51:15", "throughput": 5149.23, "total_tokens": 11649024} {"current_steps": 2845, "total_steps": 6710, "loss": 0.3968, "lr": 1.5456464919142067e-06, "epoch": 2.1199701937406856, "percentage": 42.4, "elapsed_time": "0:37:43", "remaining_time": "0:51:14", "throughput": 5149.15, "total_tokens": 11653120} {"current_steps": 2846, "total_steps": 6710, "loss": 0.3809, "lr": 1.5450778199634254e-06, "epoch": 2.1207153502235467, "percentage": 42.41, "elapsed_time": "0:37:43", "remaining_time": "0:51:13", "throughput": 5149.07, "total_tokens": 11657216} {"current_steps": 2847, "total_steps": 6710, "loss": 0.5735, "lr": 1.5445090833294793e-06, "epoch": 2.1214605067064083, "percentage": 42.43, "elapsed_time": "0:37:44", "remaining_time": "0:51:12", "throughput": 5149.07, "total_tokens": 11661312} {"current_steps": 2848, "total_steps": 6710, "loss": 0.4265, "lr": 1.5439402821370387e-06, "epoch": 2.12220566318927, "percentage": 42.44, "elapsed_time": "0:37:45", "remaining_time": "0:51:12", "throughput": 5149.05, "total_tokens": 11665408} {"current_steps": 2849, "total_steps": 6710, "loss": 0.3274, "lr": 1.5433714165107897e-06, "epoch": 2.122950819672131, "percentage": 42.46, "elapsed_time": "0:37:46", "remaining_time": "0:51:11", "throughput": 5148.95, "total_tokens": 11669504} {"current_steps": 2850, "total_steps": 6710, "loss": 0.3373, "lr": 1.542802486575431e-06, "epoch": 2.1236959761549925, "percentage": 42.47, "elapsed_time": "0:37:47", "remaining_time": "0:51:10", "throughput": 5148.9, "total_tokens": 11673600} {"current_steps": 2851, "total_steps": 6710, "loss": 0.3044, "lr": 1.5422334924556768e-06, "epoch": 2.124441132637854, "percentage": 42.49, "elapsed_time": "0:37:48", "remaining_time": "0:51:09", "throughput": 5148.84, "total_tokens": 11677696} {"current_steps": 2852, "total_steps": 6710, "loss": 0.5766, "lr": 1.5416644342762538e-06, "epoch": 2.125186289120715, "percentage": 42.5, "elapsed_time": "0:37:48", "remaining_time": "0:51:09", "throughput": 5148.79, "total_tokens": 11681792} {"current_steps": 2853, "total_steps": 6710, "loss": 0.2952, "lr": 1.5410953121619043e-06, "epoch": 2.1259314456035767, "percentage": 42.52, "elapsed_time": "0:37:49", "remaining_time": "0:51:08", "throughput": 5148.71, "total_tokens": 11685888} {"current_steps": 2854, "total_steps": 6710, "loss": 0.2679, "lr": 1.5405261262373844e-06, "epoch": 2.1266766020864383, "percentage": 42.53, "elapsed_time": "0:37:50", "remaining_time": "0:51:07", "throughput": 5148.64, "total_tokens": 11689984} {"current_steps": 2855, "total_steps": 6710, "loss": 0.5521, "lr": 1.5399568766274624e-06, "epoch": 2.1274217585692994, "percentage": 42.55, "elapsed_time": "0:37:51", "remaining_time": "0:51:06", "throughput": 5148.6, "total_tokens": 11694080} {"current_steps": 2856, "total_steps": 6710, "loss": 0.297, "lr": 1.5393875634569227e-06, "epoch": 2.128166915052161, "percentage": 42.56, "elapsed_time": "0:37:52", "remaining_time": "0:51:06", "throughput": 5148.51, "total_tokens": 11698176} {"current_steps": 2857, "total_steps": 6710, "loss": 0.5034, "lr": 1.538818186850563e-06, "epoch": 2.1289120715350225, "percentage": 42.58, "elapsed_time": "0:37:52", "remaining_time": "0:51:05", "throughput": 5148.46, "total_tokens": 11702272} {"current_steps": 2858, "total_steps": 6710, "loss": 0.447, "lr": 1.5382487469331941e-06, "epoch": 2.1296572280178836, "percentage": 42.59, "elapsed_time": "0:37:53", "remaining_time": "0:51:04", "throughput": 5148.45, "total_tokens": 11706368} {"current_steps": 2859, "total_steps": 6710, "loss": 0.3753, "lr": 1.5376792438296416e-06, "epoch": 2.130402384500745, "percentage": 42.61, "elapsed_time": "0:37:54", "remaining_time": "0:51:03", "throughput": 5148.3, "total_tokens": 11710464} {"current_steps": 2860, "total_steps": 6710, "loss": 0.577, "lr": 1.5371096776647448e-06, "epoch": 2.1311475409836067, "percentage": 42.62, "elapsed_time": "0:37:55", "remaining_time": "0:51:03", "throughput": 5148.25, "total_tokens": 11714560} {"current_steps": 2861, "total_steps": 6710, "loss": 0.3646, "lr": 1.5365400485633564e-06, "epoch": 2.131892697466468, "percentage": 42.64, "elapsed_time": "0:37:56", "remaining_time": "0:51:02", "throughput": 5148.25, "total_tokens": 11718656} {"current_steps": 2862, "total_steps": 6710, "loss": 0.5789, "lr": 1.535970356650343e-06, "epoch": 2.1326378539493294, "percentage": 42.65, "elapsed_time": "0:37:57", "remaining_time": "0:51:01", "throughput": 5148.14, "total_tokens": 11722752} {"current_steps": 2863, "total_steps": 6710, "loss": 0.6561, "lr": 1.5354006020505857e-06, "epoch": 2.133383010432191, "percentage": 42.67, "elapsed_time": "0:37:57", "remaining_time": "0:51:00", "throughput": 5148.08, "total_tokens": 11726848} {"current_steps": 2864, "total_steps": 6710, "loss": 0.553, "lr": 1.5348307848889784e-06, "epoch": 2.134128166915052, "percentage": 42.68, "elapsed_time": "0:37:58", "remaining_time": "0:51:00", "throughput": 5148.08, "total_tokens": 11730944} {"current_steps": 2865, "total_steps": 6710, "loss": 0.4025, "lr": 1.5342609052904292e-06, "epoch": 2.1348733233979136, "percentage": 42.7, "elapsed_time": "0:37:59", "remaining_time": "0:50:59", "throughput": 5148.08, "total_tokens": 11735040} {"current_steps": 2866, "total_steps": 6710, "loss": 0.3439, "lr": 1.53369096337986e-06, "epoch": 2.135618479880775, "percentage": 42.71, "elapsed_time": "0:38:00", "remaining_time": "0:50:58", "throughput": 5147.98, "total_tokens": 11739136} {"current_steps": 2867, "total_steps": 6710, "loss": 0.3059, "lr": 1.5331209592822059e-06, "epoch": 2.1363636363636362, "percentage": 42.73, "elapsed_time": "0:38:01", "remaining_time": "0:50:57", "throughput": 5147.99, "total_tokens": 11743232} {"current_steps": 2868, "total_steps": 6710, "loss": 0.2961, "lr": 1.5325508931224155e-06, "epoch": 2.137108792846498, "percentage": 42.74, "elapsed_time": "0:38:01", "remaining_time": "0:50:56", "throughput": 5147.93, "total_tokens": 11747328} {"current_steps": 2869, "total_steps": 6710, "loss": 0.3533, "lr": 1.531980765025452e-06, "epoch": 2.1378539493293593, "percentage": 42.76, "elapsed_time": "0:38:02", "remaining_time": "0:50:56", "throughput": 5147.82, "total_tokens": 11751424} {"current_steps": 2870, "total_steps": 6710, "loss": 0.4546, "lr": 1.531410575116291e-06, "epoch": 2.1385991058122205, "percentage": 42.77, "elapsed_time": "0:38:03", "remaining_time": "0:50:55", "throughput": 5147.8, "total_tokens": 11755520} {"current_steps": 2871, "total_steps": 6710, "loss": 0.2776, "lr": 1.5308403235199227e-06, "epoch": 2.139344262295082, "percentage": 42.79, "elapsed_time": "0:38:04", "remaining_time": "0:50:54", "throughput": 5147.74, "total_tokens": 11759616} {"current_steps": 2872, "total_steps": 6710, "loss": 0.3002, "lr": 1.53027001036135e-06, "epoch": 2.1400894187779436, "percentage": 42.8, "elapsed_time": "0:38:05", "remaining_time": "0:50:53", "throughput": 5147.61, "total_tokens": 11763712} {"current_steps": 2873, "total_steps": 6710, "loss": 0.2503, "lr": 1.5296996357655897e-06, "epoch": 2.1408345752608047, "percentage": 42.82, "elapsed_time": "0:38:06", "remaining_time": "0:50:53", "throughput": 5147.52, "total_tokens": 11767808} {"current_steps": 2874, "total_steps": 6710, "loss": 0.3578, "lr": 1.5291291998576721e-06, "epoch": 2.1415797317436662, "percentage": 42.83, "elapsed_time": "0:38:06", "remaining_time": "0:50:52", "throughput": 5147.48, "total_tokens": 11771904} {"current_steps": 2875, "total_steps": 6710, "loss": 0.2244, "lr": 1.528558702762641e-06, "epoch": 2.1423248882265273, "percentage": 42.85, "elapsed_time": "0:38:07", "remaining_time": "0:50:51", "throughput": 5147.46, "total_tokens": 11776000} {"current_steps": 2876, "total_steps": 6710, "loss": 0.3864, "lr": 1.5279881446055528e-06, "epoch": 2.143070044709389, "percentage": 42.86, "elapsed_time": "0:38:08", "remaining_time": "0:50:50", "throughput": 5147.3, "total_tokens": 11780096} {"current_steps": 2877, "total_steps": 6710, "loss": 0.4362, "lr": 1.5274175255114784e-06, "epoch": 2.1438152011922504, "percentage": 42.88, "elapsed_time": "0:38:09", "remaining_time": "0:50:50", "throughput": 5147.31, "total_tokens": 11784192} {"current_steps": 2878, "total_steps": 6710, "loss": 0.372, "lr": 1.5268468456055014e-06, "epoch": 2.144560357675112, "percentage": 42.89, "elapsed_time": "0:38:10", "remaining_time": "0:50:49", "throughput": 5147.27, "total_tokens": 11788288} {"current_steps": 2879, "total_steps": 6710, "loss": 0.577, "lr": 1.526276105012719e-06, "epoch": 2.145305514157973, "percentage": 42.91, "elapsed_time": "0:38:11", "remaining_time": "0:50:48", "throughput": 5147.16, "total_tokens": 11792384} {"current_steps": 2880, "total_steps": 6710, "loss": 0.4113, "lr": 1.5257053038582414e-06, "epoch": 2.1460506706408347, "percentage": 42.92, "elapsed_time": "0:38:11", "remaining_time": "0:50:47", "throughput": 5147.16, "total_tokens": 11796480} {"current_steps": 2881, "total_steps": 6710, "loss": 0.3681, "lr": 1.525134442267193e-06, "epoch": 2.1467958271236958, "percentage": 42.94, "elapsed_time": "0:38:12", "remaining_time": "0:50:47", "throughput": 5147.1, "total_tokens": 11800576} {"current_steps": 2882, "total_steps": 6710, "loss": 0.2374, "lr": 1.5245635203647097e-06, "epoch": 2.1475409836065573, "percentage": 42.95, "elapsed_time": "0:38:13", "remaining_time": "0:50:46", "throughput": 5147.05, "total_tokens": 11804672} {"current_steps": 2883, "total_steps": 6710, "loss": 0.3389, "lr": 1.5239925382759423e-06, "epoch": 2.148286140089419, "percentage": 42.97, "elapsed_time": "0:38:14", "remaining_time": "0:50:45", "throughput": 5147.05, "total_tokens": 11808768} {"current_steps": 2884, "total_steps": 6710, "loss": 0.2766, "lr": 1.5234214961260541e-06, "epoch": 2.14903129657228, "percentage": 42.98, "elapsed_time": "0:38:15", "remaining_time": "0:50:44", "throughput": 5146.99, "total_tokens": 11812864} {"current_steps": 2885, "total_steps": 6710, "loss": 0.3455, "lr": 1.5228503940402217e-06, "epoch": 2.1497764530551415, "percentage": 43.0, "elapsed_time": "0:38:15", "remaining_time": "0:50:43", "throughput": 5146.98, "total_tokens": 11816960} {"current_steps": 2886, "total_steps": 6710, "loss": 0.1862, "lr": 1.5222792321436344e-06, "epoch": 2.150521609538003, "percentage": 43.01, "elapsed_time": "0:38:16", "remaining_time": "0:50:43", "throughput": 5146.89, "total_tokens": 11821056} {"current_steps": 2887, "total_steps": 6710, "loss": 0.2918, "lr": 1.5217080105614956e-06, "epoch": 2.151266766020864, "percentage": 43.03, "elapsed_time": "0:38:17", "remaining_time": "0:50:42", "throughput": 5146.88, "total_tokens": 11825152} {"current_steps": 2888, "total_steps": 6710, "loss": 0.3844, "lr": 1.5211367294190203e-06, "epoch": 2.1520119225037257, "percentage": 43.04, "elapsed_time": "0:38:18", "remaining_time": "0:50:41", "throughput": 5146.9, "total_tokens": 11829248} {"current_steps": 2889, "total_steps": 6710, "loss": 0.4214, "lr": 1.520565388841438e-06, "epoch": 2.1527570789865873, "percentage": 43.06, "elapsed_time": "0:38:19", "remaining_time": "0:50:40", "throughput": 5146.79, "total_tokens": 11833344} {"current_steps": 2890, "total_steps": 6710, "loss": 0.5161, "lr": 1.51999398895399e-06, "epoch": 2.1535022354694484, "percentage": 43.07, "elapsed_time": "0:38:20", "remaining_time": "0:50:40", "throughput": 5146.7, "total_tokens": 11837440} {"current_steps": 2891, "total_steps": 6710, "loss": 0.5021, "lr": 1.519422529881932e-06, "epoch": 2.15424739195231, "percentage": 43.08, "elapsed_time": "0:38:20", "remaining_time": "0:50:39", "throughput": 5146.68, "total_tokens": 11841536} {"current_steps": 2892, "total_steps": 6710, "loss": 0.4678, "lr": 1.5188510117505314e-06, "epoch": 2.1549925484351715, "percentage": 43.1, "elapsed_time": "0:38:21", "remaining_time": "0:50:38", "throughput": 5146.68, "total_tokens": 11845632} {"current_steps": 2893, "total_steps": 6710, "loss": 0.4419, "lr": 1.51827943468507e-06, "epoch": 2.1557377049180326, "percentage": 43.11, "elapsed_time": "0:38:22", "remaining_time": "0:50:37", "throughput": 5146.6, "total_tokens": 11849728} {"current_steps": 2894, "total_steps": 6710, "loss": 0.3976, "lr": 1.51770779881084e-06, "epoch": 2.156482861400894, "percentage": 43.13, "elapsed_time": "0:38:23", "remaining_time": "0:50:37", "throughput": 5146.59, "total_tokens": 11853824} {"current_steps": 2895, "total_steps": 6710, "loss": 0.2924, "lr": 1.5171361042531497e-06, "epoch": 2.1572280178837557, "percentage": 43.14, "elapsed_time": "0:38:24", "remaining_time": "0:50:36", "throughput": 5146.59, "total_tokens": 11857920} {"current_steps": 2896, "total_steps": 6710, "loss": 0.4336, "lr": 1.5165643511373171e-06, "epoch": 2.157973174366617, "percentage": 43.16, "elapsed_time": "0:38:24", "remaining_time": "0:50:35", "throughput": 5146.54, "total_tokens": 11862016} {"current_steps": 2897, "total_steps": 6710, "loss": 0.385, "lr": 1.5159925395886755e-06, "epoch": 2.1587183308494784, "percentage": 43.17, "elapsed_time": "0:38:25", "remaining_time": "0:50:34", "throughput": 5146.55, "total_tokens": 11866112} {"current_steps": 2898, "total_steps": 6710, "loss": 0.3809, "lr": 1.5154206697325696e-06, "epoch": 2.15946348733234, "percentage": 43.19, "elapsed_time": "0:38:26", "remaining_time": "0:50:33", "throughput": 5146.55, "total_tokens": 11870208} {"current_steps": 2899, "total_steps": 6710, "loss": 0.3857, "lr": 1.514848741694358e-06, "epoch": 2.160208643815201, "percentage": 43.2, "elapsed_time": "0:38:27", "remaining_time": "0:50:33", "throughput": 5146.47, "total_tokens": 11874304} {"current_steps": 2900, "total_steps": 6710, "loss": 0.65, "lr": 1.5142767555994108e-06, "epoch": 2.1609538002980626, "percentage": 43.22, "elapsed_time": "0:38:28", "remaining_time": "0:50:32", "throughput": 5146.44, "total_tokens": 11878400} {"current_steps": 2901, "total_steps": 6710, "loss": 0.3255, "lr": 1.513704711573112e-06, "epoch": 2.161698956780924, "percentage": 43.23, "elapsed_time": "0:38:28", "remaining_time": "0:50:31", "throughput": 5146.43, "total_tokens": 11882496} {"current_steps": 2902, "total_steps": 6710, "loss": 0.3606, "lr": 1.5131326097408571e-06, "epoch": 2.1624441132637853, "percentage": 43.25, "elapsed_time": "0:38:29", "remaining_time": "0:50:30", "throughput": 5146.45, "total_tokens": 11886592} {"current_steps": 2903, "total_steps": 6710, "loss": 0.528, "lr": 1.5125604502280556e-06, "epoch": 2.163189269746647, "percentage": 43.26, "elapsed_time": "0:38:30", "remaining_time": "0:50:29", "throughput": 5146.4, "total_tokens": 11890688} {"current_steps": 2904, "total_steps": 6710, "loss": 0.2675, "lr": 1.5119882331601283e-06, "epoch": 2.1639344262295084, "percentage": 43.28, "elapsed_time": "0:38:31", "remaining_time": "0:50:29", "throughput": 5146.41, "total_tokens": 11894784} {"current_steps": 2905, "total_steps": 6710, "loss": 0.5281, "lr": 1.5114159586625093e-06, "epoch": 2.1646795827123695, "percentage": 43.29, "elapsed_time": "0:38:32", "remaining_time": "0:50:28", "throughput": 5146.41, "total_tokens": 11898880} {"current_steps": 2906, "total_steps": 6710, "loss": 0.3231, "lr": 1.5108436268606457e-06, "epoch": 2.165424739195231, "percentage": 43.31, "elapsed_time": "0:38:32", "remaining_time": "0:50:27", "throughput": 5146.37, "total_tokens": 11902976} {"current_steps": 2907, "total_steps": 6710, "loss": 0.2027, "lr": 1.5102712378799966e-06, "epoch": 2.1661698956780926, "percentage": 43.32, "elapsed_time": "0:38:33", "remaining_time": "0:50:26", "throughput": 5146.37, "total_tokens": 11907072} {"current_steps": 2908, "total_steps": 6710, "loss": 0.3883, "lr": 1.5096987918460337e-06, "epoch": 2.1669150521609537, "percentage": 43.34, "elapsed_time": "0:38:34", "remaining_time": "0:50:26", "throughput": 5146.37, "total_tokens": 11911168} {"current_steps": 2909, "total_steps": 6710, "loss": 0.5236, "lr": 1.509126288884241e-06, "epoch": 2.1676602086438153, "percentage": 43.35, "elapsed_time": "0:38:35", "remaining_time": "0:50:25", "throughput": 5146.32, "total_tokens": 11915264} {"current_steps": 2910, "total_steps": 6710, "loss": 0.4717, "lr": 1.5085537291201154e-06, "epoch": 2.168405365126677, "percentage": 43.37, "elapsed_time": "0:38:36", "remaining_time": "0:50:24", "throughput": 5146.27, "total_tokens": 11919360} {"current_steps": 2911, "total_steps": 6710, "loss": 0.3493, "lr": 1.5079811126791664e-06, "epoch": 2.169150521609538, "percentage": 43.38, "elapsed_time": "0:38:36", "remaining_time": "0:50:23", "throughput": 5146.29, "total_tokens": 11923456} {"current_steps": 2912, "total_steps": 6710, "loss": 0.2228, "lr": 1.507408439686915e-06, "epoch": 2.1698956780923995, "percentage": 43.4, "elapsed_time": "0:38:37", "remaining_time": "0:50:22", "throughput": 5146.31, "total_tokens": 11927552} {"current_steps": 2913, "total_steps": 6710, "loss": 0.4876, "lr": 1.506835710268896e-06, "epoch": 2.170640834575261, "percentage": 43.41, "elapsed_time": "0:38:38", "remaining_time": "0:50:22", "throughput": 5146.19, "total_tokens": 11931648} {"current_steps": 2914, "total_steps": 6710, "loss": 0.2116, "lr": 1.5062629245506551e-06, "epoch": 2.171385991058122, "percentage": 43.43, "elapsed_time": "0:38:39", "remaining_time": "0:50:21", "throughput": 5146.2, "total_tokens": 11935744} {"current_steps": 2915, "total_steps": 6710, "loss": 0.2326, "lr": 1.5056900826577514e-06, "epoch": 2.1721311475409837, "percentage": 43.44, "elapsed_time": "0:38:40", "remaining_time": "0:50:20", "throughput": 5146.18, "total_tokens": 11939840} {"current_steps": 2916, "total_steps": 6710, "loss": 0.4084, "lr": 1.5051171847157556e-06, "epoch": 2.172876304023845, "percentage": 43.46, "elapsed_time": "0:38:40", "remaining_time": "0:50:19", "throughput": 5146.1, "total_tokens": 11943936} {"current_steps": 2917, "total_steps": 6710, "loss": 0.4902, "lr": 1.5045442308502511e-06, "epoch": 2.1736214605067063, "percentage": 43.47, "elapsed_time": "0:38:41", "remaining_time": "0:50:19", "throughput": 5146.05, "total_tokens": 11948032} {"current_steps": 2918, "total_steps": 6710, "loss": 0.3805, "lr": 1.5039712211868337e-06, "epoch": 2.174366616989568, "percentage": 43.49, "elapsed_time": "0:38:42", "remaining_time": "0:50:18", "throughput": 5146.01, "total_tokens": 11952128} {"current_steps": 2919, "total_steps": 6710, "loss": 0.3713, "lr": 1.503398155851111e-06, "epoch": 2.175111773472429, "percentage": 43.5, "elapsed_time": "0:38:43", "remaining_time": "0:50:17", "throughput": 5145.95, "total_tokens": 11956224} {"current_steps": 2920, "total_steps": 6710, "loss": 0.3683, "lr": 1.5028250349687035e-06, "epoch": 2.1758569299552906, "percentage": 43.52, "elapsed_time": "0:38:44", "remaining_time": "0:50:16", "throughput": 5145.88, "total_tokens": 11960320} {"current_steps": 2921, "total_steps": 6710, "loss": 0.3923, "lr": 1.502251858665243e-06, "epoch": 2.176602086438152, "percentage": 43.53, "elapsed_time": "0:38:45", "remaining_time": "0:50:15", "throughput": 5145.85, "total_tokens": 11964416} {"current_steps": 2922, "total_steps": 6710, "loss": 0.4093, "lr": 1.5016786270663735e-06, "epoch": 2.1773472429210132, "percentage": 43.55, "elapsed_time": "0:38:45", "remaining_time": "0:50:15", "throughput": 5145.83, "total_tokens": 11968512} {"current_steps": 2923, "total_steps": 6710, "loss": 0.4167, "lr": 1.5011053402977518e-06, "epoch": 2.178092399403875, "percentage": 43.56, "elapsed_time": "0:38:46", "remaining_time": "0:50:14", "throughput": 5145.76, "total_tokens": 11972608} {"current_steps": 2924, "total_steps": 6710, "loss": 0.3657, "lr": 1.5005319984850467e-06, "epoch": 2.1788375558867363, "percentage": 43.58, "elapsed_time": "0:38:47", "remaining_time": "0:50:13", "throughput": 5145.75, "total_tokens": 11976704} {"current_steps": 2925, "total_steps": 6710, "loss": 0.399, "lr": 1.4999586017539384e-06, "epoch": 2.1795827123695974, "percentage": 43.59, "elapsed_time": "0:38:48", "remaining_time": "0:50:12", "throughput": 5145.75, "total_tokens": 11980800} {"current_steps": 2926, "total_steps": 6710, "loss": 0.3606, "lr": 1.4993851502301197e-06, "epoch": 2.180327868852459, "percentage": 43.61, "elapsed_time": "0:38:49", "remaining_time": "0:50:12", "throughput": 5145.69, "total_tokens": 11984896} {"current_steps": 2927, "total_steps": 6710, "loss": 0.4108, "lr": 1.4988116440392952e-06, "epoch": 2.1810730253353205, "percentage": 43.62, "elapsed_time": "0:38:49", "remaining_time": "0:50:11", "throughput": 5145.64, "total_tokens": 11988992} {"current_steps": 2928, "total_steps": 6710, "loss": 0.522, "lr": 1.4982380833071819e-06, "epoch": 2.1818181818181817, "percentage": 43.64, "elapsed_time": "0:38:50", "remaining_time": "0:50:10", "throughput": 5145.66, "total_tokens": 11993088} {"current_steps": 2929, "total_steps": 6710, "loss": 0.3299, "lr": 1.497664468159508e-06, "epoch": 2.182563338301043, "percentage": 43.65, "elapsed_time": "0:38:51", "remaining_time": "0:50:09", "throughput": 5145.68, "total_tokens": 11997184} {"current_steps": 2930, "total_steps": 6710, "loss": 0.2721, "lr": 1.4970907987220144e-06, "epoch": 2.1833084947839048, "percentage": 43.67, "elapsed_time": "0:38:52", "remaining_time": "0:50:08", "throughput": 5145.59, "total_tokens": 12001280} {"current_steps": 2931, "total_steps": 6710, "loss": 0.7498, "lr": 1.4965170751204534e-06, "epoch": 2.184053651266766, "percentage": 43.68, "elapsed_time": "0:38:53", "remaining_time": "0:50:08", "throughput": 5145.56, "total_tokens": 12005376} {"current_steps": 2932, "total_steps": 6710, "loss": 0.3671, "lr": 1.4959432974805891e-06, "epoch": 2.1847988077496274, "percentage": 43.7, "elapsed_time": "0:38:53", "remaining_time": "0:50:07", "throughput": 5145.59, "total_tokens": 12009472} {"current_steps": 2933, "total_steps": 6710, "loss": 0.3561, "lr": 1.4953694659281975e-06, "epoch": 2.185543964232489, "percentage": 43.71, "elapsed_time": "0:38:54", "remaining_time": "0:50:06", "throughput": 5145.6, "total_tokens": 12013568} {"current_steps": 2934, "total_steps": 6710, "loss": 0.3969, "lr": 1.4947955805890673e-06, "epoch": 2.18628912071535, "percentage": 43.73, "elapsed_time": "0:38:55", "remaining_time": "0:50:05", "throughput": 5145.52, "total_tokens": 12017664} {"current_steps": 2935, "total_steps": 6710, "loss": 0.3874, "lr": 1.4942216415889976e-06, "epoch": 2.1870342771982116, "percentage": 43.74, "elapsed_time": "0:38:56", "remaining_time": "0:50:05", "throughput": 5145.5, "total_tokens": 12021760} {"current_steps": 2936, "total_steps": 6710, "loss": 0.4428, "lr": 1.4936476490538005e-06, "epoch": 2.187779433681073, "percentage": 43.76, "elapsed_time": "0:38:57", "remaining_time": "0:50:04", "throughput": 5145.52, "total_tokens": 12025856} {"current_steps": 2937, "total_steps": 6710, "loss": 0.4871, "lr": 1.4930736031092986e-06, "epoch": 2.1885245901639343, "percentage": 43.77, "elapsed_time": "0:38:57", "remaining_time": "0:50:03", "throughput": 5145.53, "total_tokens": 12029952} {"current_steps": 2938, "total_steps": 6710, "loss": 0.2403, "lr": 1.4924995038813269e-06, "epoch": 2.189269746646796, "percentage": 43.79, "elapsed_time": "0:38:58", "remaining_time": "0:50:02", "throughput": 5145.53, "total_tokens": 12034048} {"current_steps": 2939, "total_steps": 6710, "loss": 0.2015, "lr": 1.491925351495733e-06, "epoch": 2.1900149031296574, "percentage": 43.8, "elapsed_time": "0:38:59", "remaining_time": "0:50:01", "throughput": 5145.46, "total_tokens": 12038144} {"current_steps": 2940, "total_steps": 6710, "loss": 0.3163, "lr": 1.491351146078374e-06, "epoch": 2.1907600596125185, "percentage": 43.82, "elapsed_time": "0:39:00", "remaining_time": "0:50:01", "throughput": 5145.44, "total_tokens": 12042240} {"current_steps": 2941, "total_steps": 6710, "loss": 0.5122, "lr": 1.4907768877551209e-06, "epoch": 2.19150521609538, "percentage": 43.83, "elapsed_time": "0:39:01", "remaining_time": "0:50:00", "throughput": 5145.42, "total_tokens": 12046336} {"current_steps": 2942, "total_steps": 6710, "loss": 0.4209, "lr": 1.4902025766518547e-06, "epoch": 2.1922503725782416, "percentage": 43.85, "elapsed_time": "0:39:01", "remaining_time": "0:49:59", "throughput": 5145.39, "total_tokens": 12050432} {"current_steps": 2943, "total_steps": 6710, "loss": 0.5446, "lr": 1.489628212894468e-06, "epoch": 2.1929955290611027, "percentage": 43.86, "elapsed_time": "0:39:02", "remaining_time": "0:49:58", "throughput": 5145.32, "total_tokens": 12054528} {"current_steps": 2944, "total_steps": 6710, "loss": 0.464, "lr": 1.489053796608866e-06, "epoch": 2.1937406855439643, "percentage": 43.87, "elapsed_time": "0:39:03", "remaining_time": "0:49:58", "throughput": 5145.24, "total_tokens": 12058624} {"current_steps": 2945, "total_steps": 6710, "loss": 0.5114, "lr": 1.488479327920965e-06, "epoch": 2.194485842026826, "percentage": 43.89, "elapsed_time": "0:39:04", "remaining_time": "0:49:57", "throughput": 5145.25, "total_tokens": 12062720} {"current_steps": 2946, "total_steps": 6710, "loss": 0.4866, "lr": 1.4879048069566924e-06, "epoch": 2.195230998509687, "percentage": 43.9, "elapsed_time": "0:39:05", "remaining_time": "0:49:56", "throughput": 5145.21, "total_tokens": 12066816} {"current_steps": 2947, "total_steps": 6710, "loss": 0.3957, "lr": 1.4873302338419874e-06, "epoch": 2.1959761549925485, "percentage": 43.92, "elapsed_time": "0:39:06", "remaining_time": "0:49:55", "throughput": 5145.1, "total_tokens": 12070912} {"current_steps": 2948, "total_steps": 6710, "loss": 0.3186, "lr": 1.4867556087028004e-06, "epoch": 2.19672131147541, "percentage": 43.93, "elapsed_time": "0:39:06", "remaining_time": "0:49:54", "throughput": 5145.12, "total_tokens": 12075008} {"current_steps": 2949, "total_steps": 6710, "loss": 0.5842, "lr": 1.4861809316650935e-06, "epoch": 2.197466467958271, "percentage": 43.95, "elapsed_time": "0:39:07", "remaining_time": "0:49:54", "throughput": 5145.11, "total_tokens": 12079104} {"current_steps": 2950, "total_steps": 6710, "loss": 0.2813, "lr": 1.4856062028548395e-06, "epoch": 2.1982116244411327, "percentage": 43.96, "elapsed_time": "0:39:08", "remaining_time": "0:49:53", "throughput": 5145.02, "total_tokens": 12083200} {"current_steps": 2951, "total_steps": 6710, "loss": 0.1757, "lr": 1.485031422398024e-06, "epoch": 2.198956780923994, "percentage": 43.98, "elapsed_time": "0:39:09", "remaining_time": "0:49:52", "throughput": 5145.0, "total_tokens": 12087296} {"current_steps": 2952, "total_steps": 6710, "loss": 0.5214, "lr": 1.484456590420642e-06, "epoch": 2.1997019374068554, "percentage": 43.99, "elapsed_time": "0:39:10", "remaining_time": "0:49:51", "throughput": 5144.95, "total_tokens": 12091392} {"current_steps": 2953, "total_steps": 6710, "loss": 0.5578, "lr": 1.4838817070487013e-06, "epoch": 2.200447093889717, "percentage": 44.01, "elapsed_time": "0:39:10", "remaining_time": "0:49:51", "throughput": 5144.83, "total_tokens": 12095488} {"current_steps": 2954, "total_steps": 6710, "loss": 0.3284, "lr": 1.4833067724082204e-06, "epoch": 2.201192250372578, "percentage": 44.02, "elapsed_time": "0:39:11", "remaining_time": "0:49:50", "throughput": 5144.8, "total_tokens": 12099584} {"current_steps": 2955, "total_steps": 6710, "loss": 0.6187, "lr": 1.4827317866252292e-06, "epoch": 2.2019374068554396, "percentage": 44.04, "elapsed_time": "0:39:12", "remaining_time": "0:49:49", "throughput": 5144.74, "total_tokens": 12103680} {"current_steps": 2956, "total_steps": 6710, "loss": 0.656, "lr": 1.4821567498257683e-06, "epoch": 2.202682563338301, "percentage": 44.05, "elapsed_time": "0:39:13", "remaining_time": "0:49:48", "throughput": 5144.72, "total_tokens": 12107776} {"current_steps": 2957, "total_steps": 6710, "loss": 0.3065, "lr": 1.48158166213589e-06, "epoch": 2.2034277198211623, "percentage": 44.07, "elapsed_time": "0:39:14", "remaining_time": "0:49:48", "throughput": 5144.56, "total_tokens": 12111872} {"current_steps": 2958, "total_steps": 6710, "loss": 0.191, "lr": 1.481006523681658e-06, "epoch": 2.204172876304024, "percentage": 44.08, "elapsed_time": "0:39:15", "remaining_time": "0:49:47", "throughput": 5144.55, "total_tokens": 12115968} {"current_steps": 2959, "total_steps": 6710, "loss": 0.3173, "lr": 1.4804313345891464e-06, "epoch": 2.2049180327868854, "percentage": 44.1, "elapsed_time": "0:39:15", "remaining_time": "0:49:46", "throughput": 5144.55, "total_tokens": 12120064} {"current_steps": 2960, "total_steps": 6710, "loss": 0.41, "lr": 1.4798560949844407e-06, "epoch": 2.2056631892697465, "percentage": 44.11, "elapsed_time": "0:39:16", "remaining_time": "0:49:45", "throughput": 5144.49, "total_tokens": 12124160} {"current_steps": 2961, "total_steps": 6710, "loss": 0.2662, "lr": 1.4792808049936378e-06, "epoch": 2.206408345752608, "percentage": 44.13, "elapsed_time": "0:39:17", "remaining_time": "0:49:44", "throughput": 5144.49, "total_tokens": 12128256} {"current_steps": 2962, "total_steps": 6710, "loss": 0.402, "lr": 1.478705464742845e-06, "epoch": 2.2071535022354696, "percentage": 44.14, "elapsed_time": "0:39:18", "remaining_time": "0:49:44", "throughput": 5144.44, "total_tokens": 12132352} {"current_steps": 2963, "total_steps": 6710, "loss": 0.2727, "lr": 1.4781300743581813e-06, "epoch": 2.2078986587183307, "percentage": 44.16, "elapsed_time": "0:39:19", "remaining_time": "0:49:43", "throughput": 5144.45, "total_tokens": 12136448} {"current_steps": 2964, "total_steps": 6710, "loss": 0.2287, "lr": 1.4775546339657765e-06, "epoch": 2.2086438152011922, "percentage": 44.17, "elapsed_time": "0:39:19", "remaining_time": "0:49:42", "throughput": 5144.41, "total_tokens": 12140544} {"current_steps": 2965, "total_steps": 6710, "loss": 0.6115, "lr": 1.4769791436917708e-06, "epoch": 2.209388971684054, "percentage": 44.19, "elapsed_time": "0:39:20", "remaining_time": "0:49:41", "throughput": 5144.38, "total_tokens": 12144640} {"current_steps": 2966, "total_steps": 6710, "loss": 0.3564, "lr": 1.4764036036623165e-06, "epoch": 2.210134128166915, "percentage": 44.2, "elapsed_time": "0:39:21", "remaining_time": "0:49:41", "throughput": 5144.31, "total_tokens": 12148736} {"current_steps": 2967, "total_steps": 6710, "loss": 0.232, "lr": 1.4758280140035752e-06, "epoch": 2.2108792846497765, "percentage": 44.22, "elapsed_time": "0:39:22", "remaining_time": "0:49:40", "throughput": 5144.23, "total_tokens": 12152832} {"current_steps": 2968, "total_steps": 6710, "loss": 0.3098, "lr": 1.4752523748417207e-06, "epoch": 2.211624441132638, "percentage": 44.23, "elapsed_time": "0:39:23", "remaining_time": "0:49:39", "throughput": 5144.25, "total_tokens": 12156928} {"current_steps": 2969, "total_steps": 6710, "loss": 0.3678, "lr": 1.4746766863029375e-06, "epoch": 2.212369597615499, "percentage": 44.25, "elapsed_time": "0:39:24", "remaining_time": "0:49:38", "throughput": 5144.23, "total_tokens": 12161024} {"current_steps": 2970, "total_steps": 6710, "loss": 0.4757, "lr": 1.4741009485134198e-06, "epoch": 2.2131147540983607, "percentage": 44.26, "elapsed_time": "0:39:24", "remaining_time": "0:49:37", "throughput": 5144.24, "total_tokens": 12165120} {"current_steps": 2971, "total_steps": 6710, "loss": 0.521, "lr": 1.4735251615993743e-06, "epoch": 2.2138599105812222, "percentage": 44.28, "elapsed_time": "0:39:25", "remaining_time": "0:49:37", "throughput": 5144.15, "total_tokens": 12169216} {"current_steps": 2972, "total_steps": 6710, "loss": 0.5305, "lr": 1.472949325687017e-06, "epoch": 2.2146050670640833, "percentage": 44.29, "elapsed_time": "0:39:26", "remaining_time": "0:49:36", "throughput": 5144.1, "total_tokens": 12173312} {"current_steps": 2973, "total_steps": 6710, "loss": 0.215, "lr": 1.4723734409025755e-06, "epoch": 2.215350223546945, "percentage": 44.31, "elapsed_time": "0:39:27", "remaining_time": "0:49:35", "throughput": 5144.11, "total_tokens": 12177408} {"current_steps": 2974, "total_steps": 6710, "loss": 0.3233, "lr": 1.4717975073722881e-06, "epoch": 2.2160953800298064, "percentage": 44.32, "elapsed_time": "0:39:28", "remaining_time": "0:49:34", "throughput": 5144.01, "total_tokens": 12181504} {"current_steps": 2975, "total_steps": 6710, "loss": 0.3932, "lr": 1.4712215252224036e-06, "epoch": 2.2168405365126675, "percentage": 44.34, "elapsed_time": "0:39:28", "remaining_time": "0:49:34", "throughput": 5144.02, "total_tokens": 12185600} {"current_steps": 2976, "total_steps": 6710, "loss": 0.348, "lr": 1.4706454945791806e-06, "epoch": 2.217585692995529, "percentage": 44.35, "elapsed_time": "0:39:29", "remaining_time": "0:49:33", "throughput": 5143.99, "total_tokens": 12189696} {"current_steps": 2977, "total_steps": 6710, "loss": 0.1446, "lr": 1.4700694155688902e-06, "epoch": 2.2183308494783907, "percentage": 44.37, "elapsed_time": "0:39:30", "remaining_time": "0:49:32", "throughput": 5143.97, "total_tokens": 12193792} {"current_steps": 2978, "total_steps": 6710, "loss": 0.4464, "lr": 1.469493288317812e-06, "epoch": 2.2190760059612518, "percentage": 44.38, "elapsed_time": "0:39:31", "remaining_time": "0:49:31", "throughput": 5143.95, "total_tokens": 12197888} {"current_steps": 2979, "total_steps": 6710, "loss": 0.6049, "lr": 1.4689171129522375e-06, "epoch": 2.2198211624441133, "percentage": 44.4, "elapsed_time": "0:39:32", "remaining_time": "0:49:30", "throughput": 5143.94, "total_tokens": 12201984} {"current_steps": 2980, "total_steps": 6710, "loss": 0.4506, "lr": 1.4683408895984692e-06, "epoch": 2.220566318926975, "percentage": 44.41, "elapsed_time": "0:39:32", "remaining_time": "0:49:30", "throughput": 5143.94, "total_tokens": 12206080} {"current_steps": 2981, "total_steps": 6710, "loss": 0.4816, "lr": 1.4677646183828182e-06, "epoch": 2.221311475409836, "percentage": 44.43, "elapsed_time": "0:39:33", "remaining_time": "0:49:29", "throughput": 5143.9, "total_tokens": 12210176} {"current_steps": 2982, "total_steps": 6710, "loss": 0.4619, "lr": 1.4671882994316083e-06, "epoch": 2.2220566318926975, "percentage": 44.44, "elapsed_time": "0:39:34", "remaining_time": "0:49:28", "throughput": 5143.89, "total_tokens": 12214272} {"current_steps": 2983, "total_steps": 6710, "loss": 0.3135, "lr": 1.4666119328711723e-06, "epoch": 2.222801788375559, "percentage": 44.46, "elapsed_time": "0:39:35", "remaining_time": "0:49:27", "throughput": 5143.9, "total_tokens": 12218368} {"current_steps": 2984, "total_steps": 6710, "loss": 0.5205, "lr": 1.4660355188278535e-06, "epoch": 2.22354694485842, "percentage": 44.47, "elapsed_time": "0:39:36", "remaining_time": "0:49:26", "throughput": 5143.82, "total_tokens": 12222464} {"current_steps": 2985, "total_steps": 6710, "loss": 0.4373, "lr": 1.465459057428007e-06, "epoch": 2.2242921013412817, "percentage": 44.49, "elapsed_time": "0:39:36", "remaining_time": "0:49:26", "throughput": 5143.77, "total_tokens": 12226560} {"current_steps": 2986, "total_steps": 6710, "loss": 0.3545, "lr": 1.4648825487979963e-06, "epoch": 2.225037257824143, "percentage": 44.5, "elapsed_time": "0:39:37", "remaining_time": "0:49:25", "throughput": 5143.74, "total_tokens": 12230656} {"current_steps": 2987, "total_steps": 6710, "loss": 0.405, "lr": 1.4643059930641961e-06, "epoch": 2.2257824143070044, "percentage": 44.52, "elapsed_time": "0:39:38", "remaining_time": "0:49:24", "throughput": 5143.71, "total_tokens": 12234752} {"current_steps": 2988, "total_steps": 6710, "loss": 0.6535, "lr": 1.4637293903529925e-06, "epoch": 2.226527570789866, "percentage": 44.53, "elapsed_time": "0:39:39", "remaining_time": "0:49:23", "throughput": 5143.66, "total_tokens": 12238848} {"current_steps": 2989, "total_steps": 6710, "loss": 0.2777, "lr": 1.46315274079078e-06, "epoch": 2.227272727272727, "percentage": 44.55, "elapsed_time": "0:39:40", "remaining_time": "0:49:23", "throughput": 5143.63, "total_tokens": 12242944} {"current_steps": 2990, "total_steps": 6710, "loss": 0.4808, "lr": 1.4625760445039646e-06, "epoch": 2.2280178837555886, "percentage": 44.56, "elapsed_time": "0:39:41", "remaining_time": "0:49:22", "throughput": 5143.63, "total_tokens": 12247040} {"current_steps": 2991, "total_steps": 6710, "loss": 0.2245, "lr": 1.4619993016189626e-06, "epoch": 2.22876304023845, "percentage": 44.58, "elapsed_time": "0:39:41", "remaining_time": "0:49:21", "throughput": 5143.58, "total_tokens": 12251136} {"current_steps": 2992, "total_steps": 6710, "loss": 0.3872, "lr": 1.4614225122621997e-06, "epoch": 2.2295081967213113, "percentage": 44.59, "elapsed_time": "0:39:42", "remaining_time": "0:49:20", "throughput": 5143.55, "total_tokens": 12255232} {"current_steps": 2993, "total_steps": 6710, "loss": 0.4147, "lr": 1.4608456765601123e-06, "epoch": 2.230253353204173, "percentage": 44.61, "elapsed_time": "0:39:43", "remaining_time": "0:49:19", "throughput": 5143.54, "total_tokens": 12259328} {"current_steps": 2994, "total_steps": 6710, "loss": 0.1431, "lr": 1.4602687946391475e-06, "epoch": 2.2309985096870344, "percentage": 44.62, "elapsed_time": "0:39:44", "remaining_time": "0:49:19", "throughput": 5143.47, "total_tokens": 12263424} {"current_steps": 2995, "total_steps": 6710, "loss": 0.4753, "lr": 1.4596918666257614e-06, "epoch": 2.2317436661698955, "percentage": 44.63, "elapsed_time": "0:39:45", "remaining_time": "0:49:18", "throughput": 5143.49, "total_tokens": 12267520} {"current_steps": 2996, "total_steps": 6710, "loss": 0.3872, "lr": 1.4591148926464206e-06, "epoch": 2.232488822652757, "percentage": 44.65, "elapsed_time": "0:39:45", "remaining_time": "0:49:17", "throughput": 5143.46, "total_tokens": 12271616} {"current_steps": 2997, "total_steps": 6710, "loss": 0.428, "lr": 1.458537872827602e-06, "epoch": 2.2332339791356186, "percentage": 44.66, "elapsed_time": "0:39:46", "remaining_time": "0:49:16", "throughput": 5143.43, "total_tokens": 12275712} {"current_steps": 2998, "total_steps": 6710, "loss": 0.2906, "lr": 1.4579608072957927e-06, "epoch": 2.2339791356184797, "percentage": 44.68, "elapsed_time": "0:39:47", "remaining_time": "0:49:16", "throughput": 5143.33, "total_tokens": 12279808} {"current_steps": 2999, "total_steps": 6710, "loss": 0.2576, "lr": 1.4573836961774894e-06, "epoch": 2.2347242921013413, "percentage": 44.69, "elapsed_time": "0:39:48", "remaining_time": "0:49:15", "throughput": 5143.28, "total_tokens": 12283904} {"current_steps": 3000, "total_steps": 6710, "loss": 0.4738, "lr": 1.456806539599199e-06, "epoch": 2.235469448584203, "percentage": 44.71, "elapsed_time": "0:39:49", "remaining_time": "0:49:14", "throughput": 5143.3, "total_tokens": 12288000} {"current_steps": 3001, "total_steps": 6710, "loss": 0.4262, "lr": 1.4562293376874383e-06, "epoch": 2.236214605067064, "percentage": 44.72, "elapsed_time": "0:39:49", "remaining_time": "0:49:13", "throughput": 5143.21, "total_tokens": 12292096} {"current_steps": 3002, "total_steps": 6710, "loss": 0.6103, "lr": 1.4556520905687347e-06, "epoch": 2.2369597615499255, "percentage": 44.74, "elapsed_time": "0:39:50", "remaining_time": "0:49:13", "throughput": 5143.22, "total_tokens": 12296192} {"current_steps": 3003, "total_steps": 6710, "loss": 0.2693, "lr": 1.455074798369624e-06, "epoch": 2.237704918032787, "percentage": 44.75, "elapsed_time": "0:39:51", "remaining_time": "0:49:12", "throughput": 5143.18, "total_tokens": 12300288} {"current_steps": 3004, "total_steps": 6710, "loss": 0.2797, "lr": 1.4544974612166532e-06, "epoch": 2.238450074515648, "percentage": 44.77, "elapsed_time": "0:39:52", "remaining_time": "0:49:11", "throughput": 5143.15, "total_tokens": 12304384} {"current_steps": 3005, "total_steps": 6710, "loss": 0.3159, "lr": 1.4539200792363786e-06, "epoch": 2.2391952309985097, "percentage": 44.78, "elapsed_time": "0:39:53", "remaining_time": "0:49:10", "throughput": 5143.16, "total_tokens": 12308480} {"current_steps": 3006, "total_steps": 6710, "loss": 0.5437, "lr": 1.4533426525553663e-06, "epoch": 2.2399403874813713, "percentage": 44.8, "elapsed_time": "0:39:53", "remaining_time": "0:49:09", "throughput": 5143.16, "total_tokens": 12312576} {"current_steps": 3007, "total_steps": 6710, "loss": 0.1908, "lr": 1.4527651813001928e-06, "epoch": 2.2406855439642324, "percentage": 44.81, "elapsed_time": "0:39:54", "remaining_time": "0:49:09", "throughput": 5143.17, "total_tokens": 12316672} {"current_steps": 3008, "total_steps": 6710, "loss": 0.394, "lr": 1.4521876655974438e-06, "epoch": 2.241430700447094, "percentage": 44.83, "elapsed_time": "0:39:55", "remaining_time": "0:49:08", "throughput": 5143.05, "total_tokens": 12320768} {"current_steps": 3009, "total_steps": 6710, "loss": 0.5488, "lr": 1.4516101055737148e-06, "epoch": 2.2421758569299555, "percentage": 44.84, "elapsed_time": "0:39:56", "remaining_time": "0:49:07", "throughput": 5143.05, "total_tokens": 12324864} {"current_steps": 3010, "total_steps": 6710, "loss": 0.2477, "lr": 1.4510325013556107e-06, "epoch": 2.2429210134128166, "percentage": 44.86, "elapsed_time": "0:39:57", "remaining_time": "0:49:06", "throughput": 5143.07, "total_tokens": 12328960} {"current_steps": 3011, "total_steps": 6710, "loss": 0.5269, "lr": 1.4504548530697468e-06, "epoch": 2.243666169895678, "percentage": 44.87, "elapsed_time": "0:39:58", "remaining_time": "0:49:05", "throughput": 5143.01, "total_tokens": 12333056} {"current_steps": 3012, "total_steps": 6710, "loss": 0.3195, "lr": 1.4498771608427478e-06, "epoch": 2.2444113263785397, "percentage": 44.89, "elapsed_time": "0:39:58", "remaining_time": "0:49:05", "throughput": 5142.97, "total_tokens": 12337152} {"current_steps": 3013, "total_steps": 6710, "loss": 0.2579, "lr": 1.4492994248012481e-06, "epoch": 2.245156482861401, "percentage": 44.9, "elapsed_time": "0:39:59", "remaining_time": "0:49:04", "throughput": 5142.98, "total_tokens": 12341248} {"current_steps": 3014, "total_steps": 6710, "loss": 0.3826, "lr": 1.4487216450718913e-06, "epoch": 2.2459016393442623, "percentage": 44.92, "elapsed_time": "0:40:00", "remaining_time": "0:49:03", "throughput": 5142.98, "total_tokens": 12345344} {"current_steps": 3015, "total_steps": 6710, "loss": 0.1891, "lr": 1.448143821781331e-06, "epoch": 2.246646795827124, "percentage": 44.93, "elapsed_time": "0:40:01", "remaining_time": "0:49:02", "throughput": 5142.86, "total_tokens": 12349440} {"current_steps": 3016, "total_steps": 6710, "loss": 0.2339, "lr": 1.4475659550562298e-06, "epoch": 2.247391952309985, "percentage": 44.95, "elapsed_time": "0:40:02", "remaining_time": "0:49:02", "throughput": 5142.88, "total_tokens": 12353536} {"current_steps": 3017, "total_steps": 6710, "loss": 0.4826, "lr": 1.4469880450232606e-06, "epoch": 2.2481371087928466, "percentage": 44.96, "elapsed_time": "0:40:02", "remaining_time": "0:49:01", "throughput": 5142.82, "total_tokens": 12357632} {"current_steps": 3018, "total_steps": 6710, "loss": 0.3406, "lr": 1.4464100918091053e-06, "epoch": 2.248882265275708, "percentage": 44.98, "elapsed_time": "0:40:03", "remaining_time": "0:49:00", "throughput": 5142.75, "total_tokens": 12361728} {"current_steps": 3019, "total_steps": 6710, "loss": 0.3919, "lr": 1.4458320955404554e-06, "epoch": 2.2496274217585692, "percentage": 44.99, "elapsed_time": "0:40:04", "remaining_time": "0:48:59", "throughput": 5142.75, "total_tokens": 12365824} {"current_steps": 3020, "total_steps": 6710, "loss": 0.397, "lr": 1.4452540563440118e-06, "epoch": 2.2503725782414308, "percentage": 45.01, "elapsed_time": "0:40:05", "remaining_time": "0:48:58", "throughput": 5142.75, "total_tokens": 12369920} {"current_steps": 3021, "total_steps": 6710, "loss": 0.431, "lr": 1.444675974346485e-06, "epoch": 2.251117734724292, "percentage": 45.02, "elapsed_time": "0:40:06", "remaining_time": "0:48:58", "throughput": 5142.74, "total_tokens": 12374016} {"current_steps": 3022, "total_steps": 6710, "loss": 0.3393, "lr": 1.4440978496745944e-06, "epoch": 2.2518628912071534, "percentage": 45.04, "elapsed_time": "0:40:06", "remaining_time": "0:48:57", "throughput": 5142.67, "total_tokens": 12378112} {"current_steps": 3023, "total_steps": 6710, "loss": 0.523, "lr": 1.4435196824550694e-06, "epoch": 2.252608047690015, "percentage": 45.05, "elapsed_time": "0:40:07", "remaining_time": "0:48:56", "throughput": 5142.66, "total_tokens": 12382208} {"current_steps": 3024, "total_steps": 6710, "loss": 0.196, "lr": 1.4429414728146476e-06, "epoch": 2.2533532041728765, "percentage": 45.07, "elapsed_time": "0:40:08", "remaining_time": "0:48:55", "throughput": 5142.61, "total_tokens": 12386304} {"current_steps": 3025, "total_steps": 6710, "loss": 0.5833, "lr": 1.4423632208800775e-06, "epoch": 2.2540983606557377, "percentage": 45.08, "elapsed_time": "0:40:09", "remaining_time": "0:48:55", "throughput": 5142.49, "total_tokens": 12390400} {"current_steps": 3026, "total_steps": 6710, "loss": 0.3832, "lr": 1.4417849267781157e-06, "epoch": 2.254843517138599, "percentage": 45.1, "elapsed_time": "0:40:10", "remaining_time": "0:48:54", "throughput": 5142.48, "total_tokens": 12394496} {"current_steps": 3027, "total_steps": 6710, "loss": 0.2309, "lr": 1.4412065906355284e-06, "epoch": 2.2555886736214603, "percentage": 45.11, "elapsed_time": "0:40:11", "remaining_time": "0:48:53", "throughput": 5142.48, "total_tokens": 12398592} {"current_steps": 3028, "total_steps": 6710, "loss": 0.4436, "lr": 1.4406282125790913e-06, "epoch": 2.256333830104322, "percentage": 45.13, "elapsed_time": "0:40:11", "remaining_time": "0:48:52", "throughput": 5142.47, "total_tokens": 12402688} {"current_steps": 3029, "total_steps": 6710, "loss": 0.5134, "lr": 1.4400497927355888e-06, "epoch": 2.2570789865871834, "percentage": 45.14, "elapsed_time": "0:40:12", "remaining_time": "0:48:51", "throughput": 5142.44, "total_tokens": 12406784} {"current_steps": 3030, "total_steps": 6710, "loss": 0.5512, "lr": 1.4394713312318147e-06, "epoch": 2.2578241430700445, "percentage": 45.16, "elapsed_time": "0:40:13", "remaining_time": "0:48:51", "throughput": 5142.39, "total_tokens": 12410880} {"current_steps": 3031, "total_steps": 6710, "loss": 0.4545, "lr": 1.4388928281945719e-06, "epoch": 2.258569299552906, "percentage": 45.17, "elapsed_time": "0:40:14", "remaining_time": "0:48:50", "throughput": 5142.35, "total_tokens": 12414976} {"current_steps": 3032, "total_steps": 6710, "loss": 0.4957, "lr": 1.4383142837506722e-06, "epoch": 2.2593144560357676, "percentage": 45.19, "elapsed_time": "0:40:15", "remaining_time": "0:48:49", "throughput": 5142.25, "total_tokens": 12419072} {"current_steps": 3033, "total_steps": 6710, "loss": 0.4584, "lr": 1.4377356980269368e-06, "epoch": 2.2600596125186287, "percentage": 45.2, "elapsed_time": "0:40:15", "remaining_time": "0:48:48", "throughput": 5142.22, "total_tokens": 12423168} {"current_steps": 3034, "total_steps": 6710, "loss": 0.6032, "lr": 1.4371570711501959e-06, "epoch": 2.2608047690014903, "percentage": 45.22, "elapsed_time": "0:40:16", "remaining_time": "0:48:48", "throughput": 5142.17, "total_tokens": 12427264} {"current_steps": 3035, "total_steps": 6710, "loss": 0.4283, "lr": 1.4365784032472886e-06, "epoch": 2.261549925484352, "percentage": 45.23, "elapsed_time": "0:40:17", "remaining_time": "0:48:47", "throughput": 5142.09, "total_tokens": 12431360} {"current_steps": 3036, "total_steps": 6710, "loss": 0.3765, "lr": 1.435999694445063e-06, "epoch": 2.262295081967213, "percentage": 45.25, "elapsed_time": "0:40:18", "remaining_time": "0:48:46", "throughput": 5142.1, "total_tokens": 12435456} {"current_steps": 3037, "total_steps": 6710, "loss": 0.3062, "lr": 1.435420944870376e-06, "epoch": 2.2630402384500745, "percentage": 45.26, "elapsed_time": "0:40:19", "remaining_time": "0:48:45", "throughput": 5142.09, "total_tokens": 12439552} {"current_steps": 3038, "total_steps": 6710, "loss": 0.3711, "lr": 1.434842154650094e-06, "epoch": 2.263785394932936, "percentage": 45.28, "elapsed_time": "0:40:19", "remaining_time": "0:48:44", "throughput": 5142.08, "total_tokens": 12443648} {"current_steps": 3039, "total_steps": 6710, "loss": 0.3327, "lr": 1.4342633239110917e-06, "epoch": 2.264530551415797, "percentage": 45.29, "elapsed_time": "0:40:20", "remaining_time": "0:48:44", "throughput": 5141.96, "total_tokens": 12447744} {"current_steps": 3040, "total_steps": 6710, "loss": 0.5049, "lr": 1.4336844527802536e-06, "epoch": 2.2652757078986587, "percentage": 45.31, "elapsed_time": "0:40:21", "remaining_time": "0:48:43", "throughput": 5141.92, "total_tokens": 12451840} {"current_steps": 3041, "total_steps": 6710, "loss": 0.517, "lr": 1.4331055413844714e-06, "epoch": 2.2660208643815203, "percentage": 45.32, "elapsed_time": "0:40:22", "remaining_time": "0:48:42", "throughput": 5141.9, "total_tokens": 12455936} {"current_steps": 3042, "total_steps": 6710, "loss": 0.5063, "lr": 1.432526589850647e-06, "epoch": 2.2667660208643814, "percentage": 45.34, "elapsed_time": "0:40:23", "remaining_time": "0:48:41", "throughput": 5141.82, "total_tokens": 12460032} {"current_steps": 3043, "total_steps": 6710, "loss": 0.533, "lr": 1.431947598305691e-06, "epoch": 2.267511177347243, "percentage": 45.35, "elapsed_time": "0:40:24", "remaining_time": "0:48:41", "throughput": 5141.83, "total_tokens": 12464128} {"current_steps": 3044, "total_steps": 6710, "loss": 0.4727, "lr": 1.431368566876522e-06, "epoch": 2.2682563338301045, "percentage": 45.37, "elapsed_time": "0:40:24", "remaining_time": "0:48:40", "throughput": 5141.8, "total_tokens": 12468224} {"current_steps": 3045, "total_steps": 6710, "loss": 0.4546, "lr": 1.430789495690068e-06, "epoch": 2.2690014903129656, "percentage": 45.38, "elapsed_time": "0:40:25", "remaining_time": "0:48:39", "throughput": 5141.79, "total_tokens": 12472320} {"current_steps": 3046, "total_steps": 6710, "loss": 0.6237, "lr": 1.4302103848732656e-06, "epoch": 2.269746646795827, "percentage": 45.39, "elapsed_time": "0:40:26", "remaining_time": "0:48:38", "throughput": 5141.81, "total_tokens": 12476416} {"current_steps": 3047, "total_steps": 6710, "loss": 0.2744, "lr": 1.42963123455306e-06, "epoch": 2.2704918032786887, "percentage": 45.41, "elapsed_time": "0:40:27", "remaining_time": "0:48:37", "throughput": 5141.82, "total_tokens": 12480512} {"current_steps": 3048, "total_steps": 6710, "loss": 0.4956, "lr": 1.4290520448564055e-06, "epoch": 2.27123695976155, "percentage": 45.42, "elapsed_time": "0:40:28", "remaining_time": "0:48:37", "throughput": 5141.84, "total_tokens": 12484608} {"current_steps": 3049, "total_steps": 6710, "loss": 0.398, "lr": 1.4284728159102637e-06, "epoch": 2.2719821162444114, "percentage": 45.44, "elapsed_time": "0:40:28", "remaining_time": "0:48:36", "throughput": 5141.7, "total_tokens": 12488704} {"current_steps": 3050, "total_steps": 6710, "loss": 0.4017, "lr": 1.4278935478416068e-06, "epoch": 2.2727272727272725, "percentage": 45.45, "elapsed_time": "0:40:29", "remaining_time": "0:48:35", "throughput": 5141.67, "total_tokens": 12492800} {"current_steps": 3051, "total_steps": 6710, "loss": 0.5062, "lr": 1.4273142407774135e-06, "epoch": 2.273472429210134, "percentage": 45.47, "elapsed_time": "0:40:30", "remaining_time": "0:48:34", "throughput": 5141.65, "total_tokens": 12496896} {"current_steps": 3052, "total_steps": 6710, "loss": 0.2203, "lr": 1.4267348948446725e-06, "epoch": 2.2742175856929956, "percentage": 45.48, "elapsed_time": "0:40:31", "remaining_time": "0:48:34", "throughput": 5141.64, "total_tokens": 12500992} {"current_steps": 3053, "total_steps": 6710, "loss": 0.4127, "lr": 1.4261555101703806e-06, "epoch": 2.274962742175857, "percentage": 45.5, "elapsed_time": "0:40:32", "remaining_time": "0:48:33", "throughput": 5141.56, "total_tokens": 12505088} {"current_steps": 3054, "total_steps": 6710, "loss": 0.5122, "lr": 1.425576086881543e-06, "epoch": 2.2757078986587183, "percentage": 45.51, "elapsed_time": "0:40:32", "remaining_time": "0:48:32", "throughput": 5141.54, "total_tokens": 12509184} {"current_steps": 3055, "total_steps": 6710, "loss": 0.5266, "lr": 1.4249966251051734e-06, "epoch": 2.27645305514158, "percentage": 45.53, "elapsed_time": "0:40:33", "remaining_time": "0:48:31", "throughput": 5141.46, "total_tokens": 12513280} {"current_steps": 3056, "total_steps": 6710, "loss": 0.4766, "lr": 1.4244171249682945e-06, "epoch": 2.277198211624441, "percentage": 45.54, "elapsed_time": "0:40:34", "remaining_time": "0:48:31", "throughput": 5141.38, "total_tokens": 12517376} {"current_steps": 3057, "total_steps": 6710, "loss": 0.4141, "lr": 1.4238375865979356e-06, "epoch": 2.2779433681073025, "percentage": 45.56, "elapsed_time": "0:40:35", "remaining_time": "0:48:30", "throughput": 5141.38, "total_tokens": 12521472} {"current_steps": 3058, "total_steps": 6710, "loss": 0.423, "lr": 1.4232580101211369e-06, "epoch": 2.278688524590164, "percentage": 45.57, "elapsed_time": "0:40:36", "remaining_time": "0:48:29", "throughput": 5141.33, "total_tokens": 12525568} {"current_steps": 3059, "total_steps": 6710, "loss": 0.3788, "lr": 1.422678395664945e-06, "epoch": 2.2794336810730256, "percentage": 45.59, "elapsed_time": "0:40:37", "remaining_time": "0:48:28", "throughput": 5141.2, "total_tokens": 12529664} {"current_steps": 3060, "total_steps": 6710, "loss": 0.2648, "lr": 1.422098743356416e-06, "epoch": 2.2801788375558867, "percentage": 45.6, "elapsed_time": "0:40:37", "remaining_time": "0:48:27", "throughput": 5141.19, "total_tokens": 12533760} {"current_steps": 3061, "total_steps": 6710, "loss": 0.4008, "lr": 1.421519053322613e-06, "epoch": 2.2809239940387482, "percentage": 45.62, "elapsed_time": "0:40:38", "remaining_time": "0:48:27", "throughput": 5141.12, "total_tokens": 12537856} {"current_steps": 3062, "total_steps": 6710, "loss": 0.5209, "lr": 1.4209393256906095e-06, "epoch": 2.2816691505216093, "percentage": 45.63, "elapsed_time": "0:40:39", "remaining_time": "0:48:26", "throughput": 5141.04, "total_tokens": 12541952} {"current_steps": 3063, "total_steps": 6710, "loss": 0.4565, "lr": 1.4203595605874847e-06, "epoch": 2.282414307004471, "percentage": 45.65, "elapsed_time": "0:40:40", "remaining_time": "0:48:25", "throughput": 5141.03, "total_tokens": 12546048} {"current_steps": 3064, "total_steps": 6710, "loss": 0.4115, "lr": 1.4197797581403277e-06, "epoch": 2.2831594634873325, "percentage": 45.66, "elapsed_time": "0:40:41", "remaining_time": "0:48:24", "throughput": 5141.02, "total_tokens": 12550144} {"current_steps": 3065, "total_steps": 6710, "loss": 0.4202, "lr": 1.4191999184762356e-06, "epoch": 2.2839046199701936, "percentage": 45.68, "elapsed_time": "0:40:42", "remaining_time": "0:48:24", "throughput": 5140.96, "total_tokens": 12554240} {"current_steps": 3066, "total_steps": 6710, "loss": 0.459, "lr": 1.418620041722313e-06, "epoch": 2.284649776453055, "percentage": 45.69, "elapsed_time": "0:40:42", "remaining_time": "0:48:23", "throughput": 5140.91, "total_tokens": 12558336} {"current_steps": 3067, "total_steps": 6710, "loss": 0.3759, "lr": 1.4180401280056735e-06, "epoch": 2.2853949329359167, "percentage": 45.71, "elapsed_time": "0:40:43", "remaining_time": "0:48:22", "throughput": 5140.87, "total_tokens": 12562432} {"current_steps": 3068, "total_steps": 6710, "loss": 0.4738, "lr": 1.4174601774534377e-06, "epoch": 2.2861400894187778, "percentage": 45.72, "elapsed_time": "0:40:44", "remaining_time": "0:48:21", "throughput": 5140.82, "total_tokens": 12566528} {"current_steps": 3069, "total_steps": 6710, "loss": 0.7308, "lr": 1.4168801901927356e-06, "epoch": 2.2868852459016393, "percentage": 45.74, "elapsed_time": "0:40:45", "remaining_time": "0:48:21", "throughput": 5140.74, "total_tokens": 12570624} {"current_steps": 3070, "total_steps": 6710, "loss": 0.4127, "lr": 1.416300166350704e-06, "epoch": 2.287630402384501, "percentage": 45.75, "elapsed_time": "0:40:46", "remaining_time": "0:48:20", "throughput": 5140.71, "total_tokens": 12574720} {"current_steps": 3071, "total_steps": 6710, "loss": 0.2445, "lr": 1.415720106054488e-06, "epoch": 2.288375558867362, "percentage": 45.77, "elapsed_time": "0:40:46", "remaining_time": "0:48:19", "throughput": 5140.68, "total_tokens": 12578816} {"current_steps": 3072, "total_steps": 6710, "loss": 0.4603, "lr": 1.415140009431242e-06, "epoch": 2.2891207153502235, "percentage": 45.78, "elapsed_time": "0:40:47", "remaining_time": "0:48:18", "throughput": 5140.59, "total_tokens": 12582912} {"current_steps": 3073, "total_steps": 6710, "loss": 0.2091, "lr": 1.4145598766081264e-06, "epoch": 2.289865871833085, "percentage": 45.8, "elapsed_time": "0:40:48", "remaining_time": "0:48:17", "throughput": 5140.59, "total_tokens": 12587008} {"current_steps": 3074, "total_steps": 6710, "loss": 0.1509, "lr": 1.4139797077123108e-06, "epoch": 2.290611028315946, "percentage": 45.81, "elapsed_time": "0:40:49", "remaining_time": "0:48:17", "throughput": 5140.61, "total_tokens": 12591104} {"current_steps": 3075, "total_steps": 6710, "loss": 0.314, "lr": 1.4133995028709724e-06, "epoch": 2.2913561847988078, "percentage": 45.83, "elapsed_time": "0:40:50", "remaining_time": "0:48:16", "throughput": 5140.61, "total_tokens": 12595200} {"current_steps": 3076, "total_steps": 6710, "loss": 0.3463, "lr": 1.4128192622112962e-06, "epoch": 2.2921013412816693, "percentage": 45.84, "elapsed_time": "0:40:50", "remaining_time": "0:48:15", "throughput": 5140.5, "total_tokens": 12599296} {"current_steps": 3077, "total_steps": 6710, "loss": 0.4648, "lr": 1.4122389858604756e-06, "epoch": 2.2928464977645304, "percentage": 45.86, "elapsed_time": "0:40:51", "remaining_time": "0:48:14", "throughput": 5140.52, "total_tokens": 12603392} {"current_steps": 3078, "total_steps": 6710, "loss": 0.2547, "lr": 1.4116586739457103e-06, "epoch": 2.293591654247392, "percentage": 45.87, "elapsed_time": "0:40:52", "remaining_time": "0:48:14", "throughput": 5140.51, "total_tokens": 12607488} {"current_steps": 3079, "total_steps": 6710, "loss": 0.1662, "lr": 1.4110783265942094e-06, "epoch": 2.2943368107302535, "percentage": 45.89, "elapsed_time": "0:40:53", "remaining_time": "0:48:13", "throughput": 5140.44, "total_tokens": 12611584} {"current_steps": 3080, "total_steps": 6710, "loss": 0.3104, "lr": 1.410497943933189e-06, "epoch": 2.2950819672131146, "percentage": 45.9, "elapsed_time": "0:40:54", "remaining_time": "0:48:12", "throughput": 5140.39, "total_tokens": 12615680} {"current_steps": 3081, "total_steps": 6710, "loss": 0.4838, "lr": 1.409917526089873e-06, "epoch": 2.295827123695976, "percentage": 45.92, "elapsed_time": "0:40:55", "remaining_time": "0:48:11", "throughput": 5140.39, "total_tokens": 12619776} {"current_steps": 3082, "total_steps": 6710, "loss": 0.3412, "lr": 1.4093370731914937e-06, "epoch": 2.2965722801788377, "percentage": 45.93, "elapsed_time": "0:40:55", "remaining_time": "0:48:10", "throughput": 5140.34, "total_tokens": 12623872} {"current_steps": 3083, "total_steps": 6710, "loss": 0.5774, "lr": 1.4087565853652905e-06, "epoch": 2.297317436661699, "percentage": 45.95, "elapsed_time": "0:40:56", "remaining_time": "0:48:10", "throughput": 5140.27, "total_tokens": 12627968} {"current_steps": 3084, "total_steps": 6710, "loss": 0.3416, "lr": 1.4081760627385097e-06, "epoch": 2.2980625931445604, "percentage": 45.96, "elapsed_time": "0:40:57", "remaining_time": "0:48:09", "throughput": 5140.23, "total_tokens": 12632064} {"current_steps": 3085, "total_steps": 6710, "loss": 0.3756, "lr": 1.4075955054384064e-06, "epoch": 2.2988077496274215, "percentage": 45.98, "elapsed_time": "0:40:58", "remaining_time": "0:48:08", "throughput": 5140.22, "total_tokens": 12636160} {"current_steps": 3086, "total_steps": 6710, "loss": 0.308, "lr": 1.4070149135922434e-06, "epoch": 2.299552906110283, "percentage": 45.99, "elapsed_time": "0:40:59", "remaining_time": "0:48:07", "throughput": 5140.13, "total_tokens": 12640256} {"current_steps": 3087, "total_steps": 6710, "loss": 0.4044, "lr": 1.4064342873272899e-06, "epoch": 2.3002980625931446, "percentage": 46.01, "elapsed_time": "0:40:59", "remaining_time": "0:48:07", "throughput": 5140.09, "total_tokens": 12644352} {"current_steps": 3088, "total_steps": 6710, "loss": 0.5874, "lr": 1.4058536267708236e-06, "epoch": 2.301043219076006, "percentage": 46.02, "elapsed_time": "0:41:00", "remaining_time": "0:48:06", "throughput": 5140.06, "total_tokens": 12648448} {"current_steps": 3089, "total_steps": 6710, "loss": 0.2474, "lr": 1.4052729320501295e-06, "epoch": 2.3017883755588673, "percentage": 46.04, "elapsed_time": "0:41:01", "remaining_time": "0:48:05", "throughput": 5140.0, "total_tokens": 12652544} {"current_steps": 3090, "total_steps": 6710, "loss": 0.3157, "lr": 1.4046922032924998e-06, "epoch": 2.302533532041729, "percentage": 46.05, "elapsed_time": "0:41:02", "remaining_time": "0:48:04", "throughput": 5139.95, "total_tokens": 12656640} {"current_steps": 3091, "total_steps": 6710, "loss": 0.4241, "lr": 1.4041114406252346e-06, "epoch": 2.30327868852459, "percentage": 46.07, "elapsed_time": "0:41:03", "remaining_time": "0:48:03", "throughput": 5139.89, "total_tokens": 12660736} {"current_steps": 3092, "total_steps": 6710, "loss": 0.5309, "lr": 1.4035306441756412e-06, "epoch": 2.3040238450074515, "percentage": 46.08, "elapsed_time": "0:41:04", "remaining_time": "0:48:03", "throughput": 5139.88, "total_tokens": 12664832} {"current_steps": 3093, "total_steps": 6710, "loss": 0.4897, "lr": 1.402949814071034e-06, "epoch": 2.304769001490313, "percentage": 46.1, "elapsed_time": "0:41:04", "remaining_time": "0:48:02", "throughput": 5139.77, "total_tokens": 12668928} {"current_steps": 3094, "total_steps": 6710, "loss": 0.3127, "lr": 1.4023689504387359e-06, "epoch": 2.3055141579731746, "percentage": 46.11, "elapsed_time": "0:41:05", "remaining_time": "0:48:01", "throughput": 5139.76, "total_tokens": 12673024} {"current_steps": 3095, "total_steps": 6710, "loss": 0.3728, "lr": 1.4017880534060757e-06, "epoch": 2.3062593144560357, "percentage": 46.13, "elapsed_time": "0:41:06", "remaining_time": "0:48:00", "throughput": 5139.75, "total_tokens": 12677120} {"current_steps": 3096, "total_steps": 6710, "loss": 0.2115, "lr": 1.4012071231003905e-06, "epoch": 2.3070044709388973, "percentage": 46.14, "elapsed_time": "0:41:07", "remaining_time": "0:48:00", "throughput": 5139.68, "total_tokens": 12681216} {"current_steps": 3097, "total_steps": 6710, "loss": 0.3914, "lr": 1.4006261596490236e-06, "epoch": 2.3077496274217584, "percentage": 46.15, "elapsed_time": "0:41:08", "remaining_time": "0:47:59", "throughput": 5139.69, "total_tokens": 12685312} {"current_steps": 3098, "total_steps": 6710, "loss": 0.1664, "lr": 1.4000451631793274e-06, "epoch": 2.30849478390462, "percentage": 46.17, "elapsed_time": "0:41:08", "remaining_time": "0:47:58", "throughput": 5139.68, "total_tokens": 12689408} {"current_steps": 3099, "total_steps": 6710, "loss": 0.2612, "lr": 1.3994641338186598e-06, "epoch": 2.3092399403874815, "percentage": 46.18, "elapsed_time": "0:41:09", "remaining_time": "0:47:57", "throughput": 5139.67, "total_tokens": 12693504} {"current_steps": 3100, "total_steps": 6710, "loss": 0.5036, "lr": 1.3988830716943868e-06, "epoch": 2.3099850968703426, "percentage": 46.2, "elapsed_time": "0:41:10", "remaining_time": "0:47:56", "throughput": 5139.59, "total_tokens": 12697600} {"current_steps": 3101, "total_steps": 6710, "loss": 0.3834, "lr": 1.3983019769338813e-06, "epoch": 2.310730253353204, "percentage": 46.21, "elapsed_time": "0:41:11", "remaining_time": "0:47:56", "throughput": 5139.56, "total_tokens": 12701696} {"current_steps": 3102, "total_steps": 6710, "loss": 0.3692, "lr": 1.3977208496645237e-06, "epoch": 2.3114754098360657, "percentage": 46.23, "elapsed_time": "0:41:12", "remaining_time": "0:47:55", "throughput": 5139.53, "total_tokens": 12705792} {"current_steps": 3103, "total_steps": 6710, "loss": 0.4381, "lr": 1.397139690013701e-06, "epoch": 2.312220566318927, "percentage": 46.24, "elapsed_time": "0:41:12", "remaining_time": "0:47:54", "throughput": 5139.48, "total_tokens": 12709888} {"current_steps": 3104, "total_steps": 6710, "loss": 0.2705, "lr": 1.3965584981088076e-06, "epoch": 2.3129657228017884, "percentage": 46.26, "elapsed_time": "0:41:13", "remaining_time": "0:47:53", "throughput": 5139.46, "total_tokens": 12713984} {"current_steps": 3105, "total_steps": 6710, "loss": 0.2593, "lr": 1.3959772740772452e-06, "epoch": 2.31371087928465, "percentage": 46.27, "elapsed_time": "0:41:14", "remaining_time": "0:47:53", "throughput": 5139.46, "total_tokens": 12718080} {"current_steps": 3106, "total_steps": 6710, "loss": 0.6583, "lr": 1.3953960180464212e-06, "epoch": 2.314456035767511, "percentage": 46.29, "elapsed_time": "0:41:15", "remaining_time": "0:47:52", "throughput": 5139.43, "total_tokens": 12722176} {"current_steps": 3107, "total_steps": 6710, "loss": 0.4185, "lr": 1.3948147301437523e-06, "epoch": 2.3152011922503726, "percentage": 46.3, "elapsed_time": "0:41:16", "remaining_time": "0:47:51", "throughput": 5139.42, "total_tokens": 12726272} {"current_steps": 3108, "total_steps": 6710, "loss": 0.3559, "lr": 1.3942334104966603e-06, "epoch": 2.315946348733234, "percentage": 46.32, "elapsed_time": "0:41:17", "remaining_time": "0:47:50", "throughput": 5139.41, "total_tokens": 12730368} {"current_steps": 3109, "total_steps": 6710, "loss": 0.6587, "lr": 1.3936520592325746e-06, "epoch": 2.3166915052160952, "percentage": 46.33, "elapsed_time": "0:41:17", "remaining_time": "0:47:49", "throughput": 5139.39, "total_tokens": 12734464} {"current_steps": 3110, "total_steps": 6710, "loss": 0.4883, "lr": 1.3930706764789325e-06, "epoch": 2.317436661698957, "percentage": 46.35, "elapsed_time": "0:41:18", "remaining_time": "0:47:49", "throughput": 5139.37, "total_tokens": 12738560} {"current_steps": 3111, "total_steps": 6710, "loss": 0.4098, "lr": 1.3924892623631758e-06, "epoch": 2.3181818181818183, "percentage": 46.36, "elapsed_time": "0:41:19", "remaining_time": "0:47:48", "throughput": 5139.39, "total_tokens": 12742656} {"current_steps": 3112, "total_steps": 6710, "loss": 0.3641, "lr": 1.3919078170127555e-06, "epoch": 2.3189269746646795, "percentage": 46.38, "elapsed_time": "0:41:20", "remaining_time": "0:47:47", "throughput": 5139.4, "total_tokens": 12746752} {"current_steps": 3113, "total_steps": 6710, "loss": 0.3532, "lr": 1.3913263405551288e-06, "epoch": 2.319672131147541, "percentage": 46.39, "elapsed_time": "0:41:20", "remaining_time": "0:47:46", "throughput": 5139.42, "total_tokens": 12750848} {"current_steps": 3114, "total_steps": 6710, "loss": 0.3681, "lr": 1.3907448331177587e-06, "epoch": 2.3204172876304026, "percentage": 46.41, "elapsed_time": "0:41:21", "remaining_time": "0:47:45", "throughput": 5139.45, "total_tokens": 12754944} {"current_steps": 3115, "total_steps": 6710, "loss": 0.4868, "lr": 1.3901632948281163e-06, "epoch": 2.3211624441132637, "percentage": 46.42, "elapsed_time": "0:41:22", "remaining_time": "0:47:45", "throughput": 5139.47, "total_tokens": 12759040} {"current_steps": 3116, "total_steps": 6710, "loss": 0.5319, "lr": 1.3895817258136788e-06, "epoch": 2.321907600596125, "percentage": 46.44, "elapsed_time": "0:41:23", "remaining_time": "0:47:44", "throughput": 5139.47, "total_tokens": 12763136} {"current_steps": 3117, "total_steps": 6710, "loss": 0.5422, "lr": 1.3890001262019303e-06, "epoch": 2.3226527570789868, "percentage": 46.45, "elapsed_time": "0:41:24", "remaining_time": "0:47:43", "throughput": 5139.48, "total_tokens": 12767232} {"current_steps": 3118, "total_steps": 6710, "loss": 0.7065, "lr": 1.3884184961203614e-06, "epoch": 2.323397913561848, "percentage": 46.47, "elapsed_time": "0:41:24", "remaining_time": "0:47:42", "throughput": 5139.49, "total_tokens": 12771328} {"current_steps": 3119, "total_steps": 6710, "loss": 0.3173, "lr": 1.3878368356964696e-06, "epoch": 2.3241430700447094, "percentage": 46.48, "elapsed_time": "0:41:25", "remaining_time": "0:47:41", "throughput": 5139.52, "total_tokens": 12775424} {"current_steps": 3120, "total_steps": 6710, "loss": 0.4693, "lr": 1.3872551450577595e-06, "epoch": 2.3248882265275705, "percentage": 46.5, "elapsed_time": "0:41:26", "remaining_time": "0:47:41", "throughput": 5139.55, "total_tokens": 12779520} {"current_steps": 3121, "total_steps": 6710, "loss": 0.4157, "lr": 1.3866734243317415e-06, "epoch": 2.325633383010432, "percentage": 46.51, "elapsed_time": "0:41:27", "remaining_time": "0:47:40", "throughput": 5139.57, "total_tokens": 12783616} {"current_steps": 3122, "total_steps": 6710, "loss": 0.2775, "lr": 1.3860916736459333e-06, "epoch": 2.3263785394932937, "percentage": 46.53, "elapsed_time": "0:41:28", "remaining_time": "0:47:39", "throughput": 5139.59, "total_tokens": 12787712} {"current_steps": 3123, "total_steps": 6710, "loss": 0.1326, "lr": 1.3855098931278583e-06, "epoch": 2.327123695976155, "percentage": 46.54, "elapsed_time": "0:41:28", "remaining_time": "0:47:38", "throughput": 5139.61, "total_tokens": 12791808} {"current_steps": 3124, "total_steps": 6710, "loss": 0.4771, "lr": 1.3849280829050465e-06, "epoch": 2.3278688524590163, "percentage": 46.56, "elapsed_time": "0:41:29", "remaining_time": "0:47:37", "throughput": 5139.64, "total_tokens": 12795904} {"current_steps": 3125, "total_steps": 6710, "loss": 0.4869, "lr": 1.3843462431050359e-06, "epoch": 2.328614008941878, "percentage": 46.57, "elapsed_time": "0:41:30", "remaining_time": "0:47:37", "throughput": 5139.65, "total_tokens": 12800000} {"current_steps": 3126, "total_steps": 6710, "loss": 0.2273, "lr": 1.3837643738553695e-06, "epoch": 2.329359165424739, "percentage": 46.59, "elapsed_time": "0:41:31", "remaining_time": "0:47:36", "throughput": 5139.68, "total_tokens": 12804096} {"current_steps": 3127, "total_steps": 6710, "loss": 0.5341, "lr": 1.383182475283597e-06, "epoch": 2.3301043219076005, "percentage": 46.6, "elapsed_time": "0:41:32", "remaining_time": "0:47:35", "throughput": 5139.72, "total_tokens": 12808192} {"current_steps": 3128, "total_steps": 6710, "loss": 0.247, "lr": 1.3826005475172748e-06, "epoch": 2.330849478390462, "percentage": 46.62, "elapsed_time": "0:41:32", "remaining_time": "0:47:34", "throughput": 5139.75, "total_tokens": 12812288} {"current_steps": 3129, "total_steps": 6710, "loss": 0.3658, "lr": 1.382018590683966e-06, "epoch": 2.3315946348733236, "percentage": 46.63, "elapsed_time": "0:41:33", "remaining_time": "0:47:33", "throughput": 5139.76, "total_tokens": 12816384} {"current_steps": 3130, "total_steps": 6710, "loss": 0.4468, "lr": 1.3814366049112396e-06, "epoch": 2.3323397913561847, "percentage": 46.65, "elapsed_time": "0:41:34", "remaining_time": "0:47:32", "throughput": 5139.78, "total_tokens": 12820480} {"current_steps": 3131, "total_steps": 6710, "loss": 0.2607, "lr": 1.3808545903266708e-06, "epoch": 2.3330849478390463, "percentage": 46.66, "elapsed_time": "0:41:35", "remaining_time": "0:47:32", "throughput": 5139.8, "total_tokens": 12824576} {"current_steps": 3132, "total_steps": 6710, "loss": 0.4223, "lr": 1.3802725470578413e-06, "epoch": 2.3338301043219074, "percentage": 46.68, "elapsed_time": "0:41:35", "remaining_time": "0:47:31", "throughput": 5139.82, "total_tokens": 12828672} {"current_steps": 3133, "total_steps": 6710, "loss": 0.2823, "lr": 1.3796904752323392e-06, "epoch": 2.334575260804769, "percentage": 46.69, "elapsed_time": "0:41:36", "remaining_time": "0:47:30", "throughput": 5139.85, "total_tokens": 12832768} {"current_steps": 3134, "total_steps": 6710, "loss": 0.5312, "lr": 1.3791083749777587e-06, "epoch": 2.3353204172876305, "percentage": 46.71, "elapsed_time": "0:41:37", "remaining_time": "0:47:29", "throughput": 5139.87, "total_tokens": 12836864} {"current_steps": 3135, "total_steps": 6710, "loss": 0.4057, "lr": 1.3785262464217006e-06, "epoch": 2.3360655737704916, "percentage": 46.72, "elapsed_time": "0:41:38", "remaining_time": "0:47:28", "throughput": 5139.87, "total_tokens": 12840960} {"current_steps": 3136, "total_steps": 6710, "loss": 0.4281, "lr": 1.3779440896917715e-06, "epoch": 2.336810730253353, "percentage": 46.74, "elapsed_time": "0:41:39", "remaining_time": "0:47:28", "throughput": 5139.87, "total_tokens": 12845056} {"current_steps": 3137, "total_steps": 6710, "loss": 0.3196, "lr": 1.3773619049155846e-06, "epoch": 2.3375558867362147, "percentage": 46.75, "elapsed_time": "0:41:39", "remaining_time": "0:47:27", "throughput": 5139.86, "total_tokens": 12849152} {"current_steps": 3138, "total_steps": 6710, "loss": 0.3497, "lr": 1.3767796922207585e-06, "epoch": 2.338301043219076, "percentage": 46.77, "elapsed_time": "0:41:40", "remaining_time": "0:47:26", "throughput": 5139.88, "total_tokens": 12853248} {"current_steps": 3139, "total_steps": 6710, "loss": 0.7392, "lr": 1.3761974517349186e-06, "epoch": 2.3390461997019374, "percentage": 46.78, "elapsed_time": "0:41:41", "remaining_time": "0:47:25", "throughput": 5139.91, "total_tokens": 12857344} {"current_steps": 3140, "total_steps": 6710, "loss": 0.425, "lr": 1.3756151835856959e-06, "epoch": 2.339791356184799, "percentage": 46.8, "elapsed_time": "0:41:42", "remaining_time": "0:47:24", "throughput": 5139.93, "total_tokens": 12861440} {"current_steps": 3141, "total_steps": 6710, "loss": 0.531, "lr": 1.3750328879007286e-06, "epoch": 2.34053651266766, "percentage": 46.81, "elapsed_time": "0:41:43", "remaining_time": "0:47:24", "throughput": 5139.94, "total_tokens": 12865536} {"current_steps": 3142, "total_steps": 6710, "loss": 0.4377, "lr": 1.374450564807659e-06, "epoch": 2.3412816691505216, "percentage": 46.83, "elapsed_time": "0:41:43", "remaining_time": "0:47:23", "throughput": 5139.95, "total_tokens": 12869632} {"current_steps": 3143, "total_steps": 6710, "loss": 0.3386, "lr": 1.3738682144341372e-06, "epoch": 2.342026825633383, "percentage": 46.84, "elapsed_time": "0:41:44", "remaining_time": "0:47:22", "throughput": 5139.96, "total_tokens": 12873728} {"current_steps": 3144, "total_steps": 6710, "loss": 0.3569, "lr": 1.373285836907818e-06, "epoch": 2.3427719821162443, "percentage": 46.86, "elapsed_time": "0:41:45", "remaining_time": "0:47:21", "throughput": 5139.98, "total_tokens": 12877824} {"current_steps": 3145, "total_steps": 6710, "loss": 0.2613, "lr": 1.3727034323563632e-06, "epoch": 2.343517138599106, "percentage": 46.87, "elapsed_time": "0:41:46", "remaining_time": "0:47:20", "throughput": 5140.01, "total_tokens": 12881920} {"current_steps": 3146, "total_steps": 6710, "loss": 0.4936, "lr": 1.3721210009074399e-06, "epoch": 2.3442622950819674, "percentage": 46.89, "elapsed_time": "0:41:46", "remaining_time": "0:47:20", "throughput": 5140.03, "total_tokens": 12886016} {"current_steps": 3147, "total_steps": 6710, "loss": 0.4816, "lr": 1.3715385426887208e-06, "epoch": 2.3450074515648285, "percentage": 46.9, "elapsed_time": "0:41:47", "remaining_time": "0:47:19", "throughput": 5140.05, "total_tokens": 12890112} {"current_steps": 3148, "total_steps": 6710, "loss": 0.5208, "lr": 1.3709560578278856e-06, "epoch": 2.34575260804769, "percentage": 46.92, "elapsed_time": "0:41:48", "remaining_time": "0:47:18", "throughput": 5140.08, "total_tokens": 12894208} {"current_steps": 3149, "total_steps": 6710, "loss": 0.2994, "lr": 1.3703735464526188e-06, "epoch": 2.3464977645305516, "percentage": 46.93, "elapsed_time": "0:41:49", "remaining_time": "0:47:17", "throughput": 5140.11, "total_tokens": 12898304} {"current_steps": 3150, "total_steps": 6710, "loss": 0.3681, "lr": 1.3697910086906112e-06, "epoch": 2.3472429210134127, "percentage": 46.94, "elapsed_time": "0:41:50", "remaining_time": "0:47:16", "throughput": 5140.13, "total_tokens": 12902400} {"current_steps": 3151, "total_steps": 6710, "loss": 0.2217, "lr": 1.3692084446695589e-06, "epoch": 2.3479880774962743, "percentage": 46.96, "elapsed_time": "0:41:50", "remaining_time": "0:47:16", "throughput": 5140.15, "total_tokens": 12906496} {"current_steps": 3152, "total_steps": 6710, "loss": 0.4265, "lr": 1.3686258545171643e-06, "epoch": 2.348733233979136, "percentage": 46.97, "elapsed_time": "0:41:51", "remaining_time": "0:47:15", "throughput": 5140.19, "total_tokens": 12910592} {"current_steps": 3153, "total_steps": 6710, "loss": 0.3955, "lr": 1.3680432383611353e-06, "epoch": 2.349478390461997, "percentage": 46.99, "elapsed_time": "0:41:52", "remaining_time": "0:47:14", "throughput": 5140.22, "total_tokens": 12914688} {"current_steps": 3154, "total_steps": 6710, "loss": 0.49, "lr": 1.3674605963291856e-06, "epoch": 2.3502235469448585, "percentage": 47.0, "elapsed_time": "0:41:53", "remaining_time": "0:47:13", "throughput": 5140.25, "total_tokens": 12918784} {"current_steps": 3155, "total_steps": 6710, "loss": 0.3849, "lr": 1.3668779285490344e-06, "epoch": 2.3509687034277196, "percentage": 47.02, "elapsed_time": "0:41:54", "remaining_time": "0:47:12", "throughput": 5140.28, "total_tokens": 12922880} {"current_steps": 3156, "total_steps": 6710, "loss": 0.2853, "lr": 1.3662952351484069e-06, "epoch": 2.351713859910581, "percentage": 47.03, "elapsed_time": "0:41:54", "remaining_time": "0:47:11", "throughput": 5140.32, "total_tokens": 12926976} {"current_steps": 3157, "total_steps": 6710, "loss": 0.5103, "lr": 1.3657125162550333e-06, "epoch": 2.3524590163934427, "percentage": 47.05, "elapsed_time": "0:41:55", "remaining_time": "0:47:11", "throughput": 5140.35, "total_tokens": 12931072} {"current_steps": 3158, "total_steps": 6710, "loss": 0.4166, "lr": 1.3651297719966496e-06, "epoch": 2.3532041728763042, "percentage": 47.06, "elapsed_time": "0:41:56", "remaining_time": "0:47:10", "throughput": 5140.39, "total_tokens": 12935168} {"current_steps": 3159, "total_steps": 6710, "loss": 0.2278, "lr": 1.3645470025009984e-06, "epoch": 2.3539493293591653, "percentage": 47.08, "elapsed_time": "0:41:57", "remaining_time": "0:47:09", "throughput": 5140.42, "total_tokens": 12939264} {"current_steps": 3160, "total_steps": 6710, "loss": 0.4586, "lr": 1.363964207895826e-06, "epoch": 2.354694485842027, "percentage": 47.09, "elapsed_time": "0:41:57", "remaining_time": "0:47:08", "throughput": 5140.45, "total_tokens": 12943360} {"current_steps": 3161, "total_steps": 6710, "loss": 0.2853, "lr": 1.3633813883088854e-06, "epoch": 2.355439642324888, "percentage": 47.11, "elapsed_time": "0:41:58", "remaining_time": "0:47:07", "throughput": 5140.47, "total_tokens": 12947456} {"current_steps": 3162, "total_steps": 6710, "loss": 0.492, "lr": 1.3627985438679348e-06, "epoch": 2.3561847988077496, "percentage": 47.12, "elapsed_time": "0:41:59", "remaining_time": "0:47:07", "throughput": 5140.48, "total_tokens": 12951552} {"current_steps": 3163, "total_steps": 6710, "loss": 0.5406, "lr": 1.362215674700738e-06, "epoch": 2.356929955290611, "percentage": 47.14, "elapsed_time": "0:42:00", "remaining_time": "0:47:06", "throughput": 5140.49, "total_tokens": 12955648} {"current_steps": 3164, "total_steps": 6710, "loss": 0.4802, "lr": 1.3616327809350642e-06, "epoch": 2.3576751117734727, "percentage": 47.15, "elapsed_time": "0:42:01", "remaining_time": "0:47:05", "throughput": 5140.51, "total_tokens": 12959744} {"current_steps": 3165, "total_steps": 6710, "loss": 0.2746, "lr": 1.3610498626986874e-06, "epoch": 2.3584202682563338, "percentage": 47.17, "elapsed_time": "0:42:01", "remaining_time": "0:47:04", "throughput": 5140.54, "total_tokens": 12963840} {"current_steps": 3166, "total_steps": 6710, "loss": 0.3594, "lr": 1.3604669201193876e-06, "epoch": 2.3591654247391953, "percentage": 47.18, "elapsed_time": "0:42:02", "remaining_time": "0:47:03", "throughput": 5140.56, "total_tokens": 12967936} {"current_steps": 3167, "total_steps": 6710, "loss": 0.4439, "lr": 1.3598839533249502e-06, "epoch": 2.3599105812220564, "percentage": 47.2, "elapsed_time": "0:42:03", "remaining_time": "0:47:03", "throughput": 5140.57, "total_tokens": 12972032} {"current_steps": 3168, "total_steps": 6710, "loss": 0.3499, "lr": 1.359300962443166e-06, "epoch": 2.360655737704918, "percentage": 47.21, "elapsed_time": "0:42:04", "remaining_time": "0:47:02", "throughput": 5140.58, "total_tokens": 12976128} {"current_steps": 3169, "total_steps": 6710, "loss": 0.325, "lr": 1.35871794760183e-06, "epoch": 2.3614008941877795, "percentage": 47.23, "elapsed_time": "0:42:05", "remaining_time": "0:47:01", "throughput": 5140.6, "total_tokens": 12980224} {"current_steps": 3170, "total_steps": 6710, "loss": 0.3942, "lr": 1.3581349089287438e-06, "epoch": 2.3621460506706407, "percentage": 47.24, "elapsed_time": "0:42:05", "remaining_time": "0:47:00", "throughput": 5140.62, "total_tokens": 12984320} {"current_steps": 3171, "total_steps": 6710, "loss": 0.2676, "lr": 1.3575518465517132e-06, "epoch": 2.362891207153502, "percentage": 47.26, "elapsed_time": "0:42:06", "remaining_time": "0:46:59", "throughput": 5140.64, "total_tokens": 12988416} {"current_steps": 3172, "total_steps": 6710, "loss": 0.5905, "lr": 1.35696876059855e-06, "epoch": 2.3636363636363638, "percentage": 47.27, "elapsed_time": "0:42:07", "remaining_time": "0:46:59", "throughput": 5140.64, "total_tokens": 12992512} {"current_steps": 3173, "total_steps": 6710, "loss": 0.3601, "lr": 1.3563856511970705e-06, "epoch": 2.364381520119225, "percentage": 47.29, "elapsed_time": "0:42:08", "remaining_time": "0:46:58", "throughput": 5140.66, "total_tokens": 12996608} {"current_steps": 3174, "total_steps": 6710, "loss": 0.5748, "lr": 1.3558025184750964e-06, "epoch": 2.3651266766020864, "percentage": 47.3, "elapsed_time": "0:42:08", "remaining_time": "0:46:57", "throughput": 5140.67, "total_tokens": 13000704} {"current_steps": 3175, "total_steps": 6710, "loss": 0.5193, "lr": 1.3552193625604551e-06, "epoch": 2.365871833084948, "percentage": 47.32, "elapsed_time": "0:42:09", "remaining_time": "0:46:56", "throughput": 5140.68, "total_tokens": 13004800} {"current_steps": 3176, "total_steps": 6710, "loss": 0.3043, "lr": 1.3546361835809782e-06, "epoch": 2.366616989567809, "percentage": 47.33, "elapsed_time": "0:42:10", "remaining_time": "0:46:55", "throughput": 5140.69, "total_tokens": 13008896} {"current_steps": 3177, "total_steps": 6710, "loss": 0.4603, "lr": 1.3540529816645025e-06, "epoch": 2.3673621460506706, "percentage": 47.35, "elapsed_time": "0:42:11", "remaining_time": "0:46:55", "throughput": 5140.71, "total_tokens": 13012992} {"current_steps": 3178, "total_steps": 6710, "loss": 0.5477, "lr": 1.3534697569388704e-06, "epoch": 2.368107302533532, "percentage": 47.36, "elapsed_time": "0:42:12", "remaining_time": "0:46:54", "throughput": 5140.73, "total_tokens": 13017088} {"current_steps": 3179, "total_steps": 6710, "loss": 0.263, "lr": 1.3528865095319287e-06, "epoch": 2.3688524590163933, "percentage": 47.38, "elapsed_time": "0:42:12", "remaining_time": "0:46:53", "throughput": 5140.73, "total_tokens": 13021184} {"current_steps": 3180, "total_steps": 6710, "loss": 0.3961, "lr": 1.3523032395715293e-06, "epoch": 2.369597615499255, "percentage": 47.39, "elapsed_time": "0:42:13", "remaining_time": "0:46:52", "throughput": 5140.74, "total_tokens": 13025280} {"current_steps": 3181, "total_steps": 6710, "loss": 0.4476, "lr": 1.3517199471855294e-06, "epoch": 2.3703427719821164, "percentage": 47.41, "elapsed_time": "0:42:14", "remaining_time": "0:46:51", "throughput": 5140.76, "total_tokens": 13029376} {"current_steps": 3182, "total_steps": 6710, "loss": 0.6291, "lr": 1.3511366325017905e-06, "epoch": 2.3710879284649775, "percentage": 47.42, "elapsed_time": "0:42:15", "remaining_time": "0:46:50", "throughput": 5140.78, "total_tokens": 13033472} {"current_steps": 3183, "total_steps": 6710, "loss": 0.3292, "lr": 1.3505532956481798e-06, "epoch": 2.371833084947839, "percentage": 47.44, "elapsed_time": "0:42:16", "remaining_time": "0:46:50", "throughput": 5140.8, "total_tokens": 13037568} {"current_steps": 3184, "total_steps": 6710, "loss": 0.2436, "lr": 1.3499699367525686e-06, "epoch": 2.3725782414307006, "percentage": 47.45, "elapsed_time": "0:42:16", "remaining_time": "0:46:49", "throughput": 5140.84, "total_tokens": 13041664} {"current_steps": 3185, "total_steps": 6710, "loss": 0.593, "lr": 1.3493865559428338e-06, "epoch": 2.3733233979135617, "percentage": 47.47, "elapsed_time": "0:42:17", "remaining_time": "0:46:48", "throughput": 5140.86, "total_tokens": 13045760} {"current_steps": 3186, "total_steps": 6710, "loss": 0.2313, "lr": 1.3488031533468558e-06, "epoch": 2.3740685543964233, "percentage": 47.48, "elapsed_time": "0:42:18", "remaining_time": "0:46:47", "throughput": 5140.9, "total_tokens": 13049856} {"current_steps": 3187, "total_steps": 6710, "loss": 0.5581, "lr": 1.3482197290925212e-06, "epoch": 2.374813710879285, "percentage": 47.5, "elapsed_time": "0:42:19", "remaining_time": "0:46:46", "throughput": 5140.93, "total_tokens": 13053952} {"current_steps": 3188, "total_steps": 6710, "loss": 0.4513, "lr": 1.3476362833077205e-06, "epoch": 2.375558867362146, "percentage": 47.51, "elapsed_time": "0:42:20", "remaining_time": "0:46:46", "throughput": 5140.96, "total_tokens": 13058048} {"current_steps": 3189, "total_steps": 6710, "loss": 0.4965, "lr": 1.3470528161203493e-06, "epoch": 2.3763040238450075, "percentage": 47.53, "elapsed_time": "0:42:20", "remaining_time": "0:46:45", "throughput": 5140.99, "total_tokens": 13062144} {"current_steps": 3190, "total_steps": 6710, "loss": 0.5795, "lr": 1.3464693276583082e-06, "epoch": 2.3770491803278686, "percentage": 47.54, "elapsed_time": "0:42:21", "remaining_time": "0:46:44", "throughput": 5141.02, "total_tokens": 13066240} {"current_steps": 3191, "total_steps": 6710, "loss": 0.2668, "lr": 1.3458858180495014e-06, "epoch": 2.37779433681073, "percentage": 47.56, "elapsed_time": "0:42:22", "remaining_time": "0:46:43", "throughput": 5141.06, "total_tokens": 13070336} {"current_steps": 3192, "total_steps": 6710, "loss": 0.264, "lr": 1.3453022874218385e-06, "epoch": 2.3785394932935917, "percentage": 47.57, "elapsed_time": "0:42:23", "remaining_time": "0:46:42", "throughput": 5141.09, "total_tokens": 13074432} {"current_steps": 3193, "total_steps": 6710, "loss": 0.4246, "lr": 1.3447187359032335e-06, "epoch": 2.3792846497764533, "percentage": 47.59, "elapsed_time": "0:42:23", "remaining_time": "0:46:42", "throughput": 5141.07, "total_tokens": 13078528} {"current_steps": 3194, "total_steps": 6710, "loss": 0.2187, "lr": 1.3441351636216054e-06, "epoch": 2.3800298062593144, "percentage": 47.6, "elapsed_time": "0:42:24", "remaining_time": "0:46:41", "throughput": 5141.06, "total_tokens": 13082624} {"current_steps": 3195, "total_steps": 6710, "loss": 0.4262, "lr": 1.3435515707048773e-06, "epoch": 2.380774962742176, "percentage": 47.62, "elapsed_time": "0:42:25", "remaining_time": "0:46:40", "throughput": 5141.02, "total_tokens": 13086720} {"current_steps": 3196, "total_steps": 6710, "loss": 0.3607, "lr": 1.342967957280977e-06, "epoch": 2.381520119225037, "percentage": 47.63, "elapsed_time": "0:42:26", "remaining_time": "0:46:39", "throughput": 5140.97, "total_tokens": 13090816} {"current_steps": 3197, "total_steps": 6710, "loss": 0.2279, "lr": 1.3423843234778367e-06, "epoch": 2.3822652757078986, "percentage": 47.65, "elapsed_time": "0:42:27", "remaining_time": "0:46:38", "throughput": 5140.95, "total_tokens": 13094912} {"current_steps": 3198, "total_steps": 6710, "loss": 0.3399, "lr": 1.3418006694233928e-06, "epoch": 2.38301043219076, "percentage": 47.66, "elapsed_time": "0:42:27", "remaining_time": "0:46:38", "throughput": 5140.96, "total_tokens": 13099008} {"current_steps": 3199, "total_steps": 6710, "loss": 0.7625, "lr": 1.3412169952455867e-06, "epoch": 2.3837555886736217, "percentage": 47.68, "elapsed_time": "0:42:28", "remaining_time": "0:46:37", "throughput": 5140.96, "total_tokens": 13103104} {"current_steps": 3200, "total_steps": 6710, "loss": 0.3541, "lr": 1.3406333010723638e-06, "epoch": 2.384500745156483, "percentage": 47.69, "elapsed_time": "0:42:29", "remaining_time": "0:46:36", "throughput": 5140.96, "total_tokens": 13107200} {"current_steps": 3201, "total_steps": 6710, "loss": 0.4626, "lr": 1.340049587031674e-06, "epoch": 2.3852459016393444, "percentage": 47.7, "elapsed_time": "0:42:30", "remaining_time": "0:46:35", "throughput": 5140.95, "total_tokens": 13111296} {"current_steps": 3202, "total_steps": 6710, "loss": 0.3186, "lr": 1.3394658532514718e-06, "epoch": 2.3859910581222055, "percentage": 47.72, "elapsed_time": "0:42:31", "remaining_time": "0:46:34", "throughput": 5140.96, "total_tokens": 13115392} {"current_steps": 3203, "total_steps": 6710, "loss": 0.2772, "lr": 1.3388820998597158e-06, "epoch": 2.386736214605067, "percentage": 47.73, "elapsed_time": "0:42:31", "remaining_time": "0:46:34", "throughput": 5140.96, "total_tokens": 13119488} {"current_steps": 3204, "total_steps": 6710, "loss": 0.2838, "lr": 1.3382983269843692e-06, "epoch": 2.3874813710879286, "percentage": 47.75, "elapsed_time": "0:42:32", "remaining_time": "0:46:33", "throughput": 5140.95, "total_tokens": 13123584} {"current_steps": 3205, "total_steps": 6710, "loss": 0.328, "lr": 1.3377145347533984e-06, "epoch": 2.3882265275707897, "percentage": 47.76, "elapsed_time": "0:42:33", "remaining_time": "0:46:32", "throughput": 5140.95, "total_tokens": 13127680} {"current_steps": 3206, "total_steps": 6710, "loss": 0.2418, "lr": 1.3371307232947753e-06, "epoch": 2.3889716840536512, "percentage": 47.78, "elapsed_time": "0:42:34", "remaining_time": "0:46:31", "throughput": 5140.93, "total_tokens": 13131776} {"current_steps": 3207, "total_steps": 6710, "loss": 0.2957, "lr": 1.3365468927364755e-06, "epoch": 2.389716840536513, "percentage": 47.79, "elapsed_time": "0:42:35", "remaining_time": "0:46:30", "throughput": 5140.92, "total_tokens": 13135872} {"current_steps": 3208, "total_steps": 6710, "loss": 0.466, "lr": 1.3359630432064788e-06, "epoch": 2.390461997019374, "percentage": 47.81, "elapsed_time": "0:42:35", "remaining_time": "0:46:30", "throughput": 5140.9, "total_tokens": 13139968} {"current_steps": 3209, "total_steps": 6710, "loss": 0.3179, "lr": 1.3353791748327691e-06, "epoch": 2.3912071535022354, "percentage": 47.82, "elapsed_time": "0:42:36", "remaining_time": "0:46:29", "throughput": 5140.89, "total_tokens": 13144064} {"current_steps": 3210, "total_steps": 6710, "loss": 0.3614, "lr": 1.3347952877433346e-06, "epoch": 2.391952309985097, "percentage": 47.84, "elapsed_time": "0:42:37", "remaining_time": "0:46:28", "throughput": 5140.87, "total_tokens": 13148160} {"current_steps": 3211, "total_steps": 6710, "loss": 0.4377, "lr": 1.3342113820661677e-06, "epoch": 2.392697466467958, "percentage": 47.85, "elapsed_time": "0:42:38", "remaining_time": "0:46:27", "throughput": 5140.87, "total_tokens": 13152256} {"current_steps": 3212, "total_steps": 6710, "loss": 0.2243, "lr": 1.3336274579292646e-06, "epoch": 2.3934426229508197, "percentage": 47.87, "elapsed_time": "0:42:39", "remaining_time": "0:46:27", "throughput": 5140.88, "total_tokens": 13156352} {"current_steps": 3213, "total_steps": 6710, "loss": 0.6157, "lr": 1.3330435154606252e-06, "epoch": 2.394187779433681, "percentage": 47.88, "elapsed_time": "0:42:39", "remaining_time": "0:46:26", "throughput": 5140.91, "total_tokens": 13160448} {"current_steps": 3214, "total_steps": 6710, "loss": 0.4609, "lr": 1.332459554788255e-06, "epoch": 2.3949329359165423, "percentage": 47.9, "elapsed_time": "0:42:40", "remaining_time": "0:46:25", "throughput": 5140.92, "total_tokens": 13164544} {"current_steps": 3215, "total_steps": 6710, "loss": 0.3736, "lr": 1.3318755760401608e-06, "epoch": 2.395678092399404, "percentage": 47.91, "elapsed_time": "0:42:41", "remaining_time": "0:46:24", "throughput": 5140.95, "total_tokens": 13168640} {"current_steps": 3216, "total_steps": 6710, "loss": 0.6219, "lr": 1.3312915793443559e-06, "epoch": 2.3964232488822654, "percentage": 47.93, "elapsed_time": "0:42:42", "remaining_time": "0:46:23", "throughput": 5140.98, "total_tokens": 13172736} {"current_steps": 3217, "total_steps": 6710, "loss": 0.4362, "lr": 1.3307075648288564e-06, "epoch": 2.3971684053651265, "percentage": 47.94, "elapsed_time": "0:42:43", "remaining_time": "0:46:22", "throughput": 5141.0, "total_tokens": 13176832} {"current_steps": 3218, "total_steps": 6710, "loss": 0.3646, "lr": 1.3301235326216824e-06, "epoch": 2.397913561847988, "percentage": 47.96, "elapsed_time": "0:42:43", "remaining_time": "0:46:22", "throughput": 5141.03, "total_tokens": 13180928} {"current_steps": 3219, "total_steps": 6710, "loss": 0.5394, "lr": 1.329539482850858e-06, "epoch": 2.3986587183308496, "percentage": 47.97, "elapsed_time": "0:42:44", "remaining_time": "0:46:21", "throughput": 5141.06, "total_tokens": 13185024} {"current_steps": 3220, "total_steps": 6710, "loss": 0.2907, "lr": 1.3289554156444106e-06, "epoch": 2.3994038748137108, "percentage": 47.99, "elapsed_time": "0:42:45", "remaining_time": "0:46:20", "throughput": 5141.1, "total_tokens": 13189120} {"current_steps": 3221, "total_steps": 6710, "loss": 0.3105, "lr": 1.3283713311303725e-06, "epoch": 2.4001490312965723, "percentage": 48.0, "elapsed_time": "0:42:46", "remaining_time": "0:46:19", "throughput": 5141.13, "total_tokens": 13193216} {"current_steps": 3222, "total_steps": 6710, "loss": 0.605, "lr": 1.3277872294367795e-06, "epoch": 2.400894187779434, "percentage": 48.02, "elapsed_time": "0:42:46", "remaining_time": "0:46:18", "throughput": 5141.16, "total_tokens": 13197312} {"current_steps": 3223, "total_steps": 6710, "loss": 0.3406, "lr": 1.3272031106916698e-06, "epoch": 2.401639344262295, "percentage": 48.03, "elapsed_time": "0:42:47", "remaining_time": "0:46:18", "throughput": 5141.19, "total_tokens": 13201408} {"current_steps": 3224, "total_steps": 6710, "loss": 0.3305, "lr": 1.326618975023087e-06, "epoch": 2.4023845007451565, "percentage": 48.05, "elapsed_time": "0:42:48", "remaining_time": "0:46:17", "throughput": 5141.23, "total_tokens": 13205504} {"current_steps": 3225, "total_steps": 6710, "loss": 0.3749, "lr": 1.326034822559078e-06, "epoch": 2.4031296572280176, "percentage": 48.06, "elapsed_time": "0:42:49", "remaining_time": "0:46:16", "throughput": 5141.26, "total_tokens": 13209600} {"current_steps": 3226, "total_steps": 6710, "loss": 0.4594, "lr": 1.3254506534276927e-06, "epoch": 2.403874813710879, "percentage": 48.08, "elapsed_time": "0:42:50", "remaining_time": "0:46:15", "throughput": 5141.29, "total_tokens": 13213696} {"current_steps": 3227, "total_steps": 6710, "loss": 0.0833, "lr": 1.3248664677569853e-06, "epoch": 2.4046199701937407, "percentage": 48.09, "elapsed_time": "0:42:50", "remaining_time": "0:46:14", "throughput": 5141.32, "total_tokens": 13217792} {"current_steps": 3228, "total_steps": 6710, "loss": 0.2093, "lr": 1.3242822656750138e-06, "epoch": 2.4053651266766023, "percentage": 48.11, "elapsed_time": "0:42:51", "remaining_time": "0:46:14", "throughput": 5141.34, "total_tokens": 13221888} {"current_steps": 3229, "total_steps": 6710, "loss": 0.6045, "lr": 1.3236980473098393e-06, "epoch": 2.4061102831594634, "percentage": 48.12, "elapsed_time": "0:42:52", "remaining_time": "0:46:13", "throughput": 5141.35, "total_tokens": 13225984} {"current_steps": 3230, "total_steps": 6710, "loss": 0.2727, "lr": 1.3231138127895262e-06, "epoch": 2.406855439642325, "percentage": 48.14, "elapsed_time": "0:42:53", "remaining_time": "0:46:12", "throughput": 5141.37, "total_tokens": 13230080} {"current_steps": 3231, "total_steps": 6710, "loss": 0.2966, "lr": 1.3225295622421438e-06, "epoch": 2.407600596125186, "percentage": 48.15, "elapsed_time": "0:42:54", "remaining_time": "0:46:11", "throughput": 5141.39, "total_tokens": 13234176} {"current_steps": 3232, "total_steps": 6710, "loss": 0.4964, "lr": 1.3219452957957632e-06, "epoch": 2.4083457526080476, "percentage": 48.17, "elapsed_time": "0:42:54", "remaining_time": "0:46:10", "throughput": 5141.4, "total_tokens": 13238272} {"current_steps": 3233, "total_steps": 6710, "loss": 0.348, "lr": 1.3213610135784603e-06, "epoch": 2.409090909090909, "percentage": 48.18, "elapsed_time": "0:42:55", "remaining_time": "0:46:10", "throughput": 5141.42, "total_tokens": 13242368} {"current_steps": 3234, "total_steps": 6710, "loss": 0.4552, "lr": 1.3207767157183132e-06, "epoch": 2.4098360655737707, "percentage": 48.2, "elapsed_time": "0:42:56", "remaining_time": "0:46:09", "throughput": 5141.44, "total_tokens": 13246464} {"current_steps": 3235, "total_steps": 6710, "loss": 0.3017, "lr": 1.3201924023434048e-06, "epoch": 2.410581222056632, "percentage": 48.21, "elapsed_time": "0:42:57", "remaining_time": "0:46:08", "throughput": 5141.46, "total_tokens": 13250560} {"current_steps": 3236, "total_steps": 6710, "loss": 0.4062, "lr": 1.3196080735818206e-06, "epoch": 2.4113263785394934, "percentage": 48.23, "elapsed_time": "0:42:57", "remaining_time": "0:46:07", "throughput": 5141.47, "total_tokens": 13254656} {"current_steps": 3237, "total_steps": 6710, "loss": 0.3222, "lr": 1.3190237295616495e-06, "epoch": 2.4120715350223545, "percentage": 48.24, "elapsed_time": "0:42:58", "remaining_time": "0:46:06", "throughput": 5141.46, "total_tokens": 13258752} {"current_steps": 3238, "total_steps": 6710, "loss": 0.1969, "lr": 1.3184393704109844e-06, "epoch": 2.412816691505216, "percentage": 48.26, "elapsed_time": "0:42:59", "remaining_time": "0:46:06", "throughput": 5141.44, "total_tokens": 13262848} {"current_steps": 3239, "total_steps": 6710, "loss": 0.5332, "lr": 1.3178549962579204e-06, "epoch": 2.4135618479880776, "percentage": 48.27, "elapsed_time": "0:43:00", "remaining_time": "0:46:05", "throughput": 5141.42, "total_tokens": 13266944} {"current_steps": 3240, "total_steps": 6710, "loss": 0.2303, "lr": 1.3172706072305563e-06, "epoch": 2.4143070044709387, "percentage": 48.29, "elapsed_time": "0:43:01", "remaining_time": "0:46:04", "throughput": 5141.44, "total_tokens": 13271040} {"current_steps": 3241, "total_steps": 6710, "loss": 0.3537, "lr": 1.3166862034569955e-06, "epoch": 2.4150521609538003, "percentage": 48.3, "elapsed_time": "0:43:01", "remaining_time": "0:46:03", "throughput": 5141.43, "total_tokens": 13275136} {"current_steps": 3242, "total_steps": 6710, "loss": 0.1919, "lr": 1.316101785065342e-06, "epoch": 2.415797317436662, "percentage": 48.32, "elapsed_time": "0:43:02", "remaining_time": "0:46:02", "throughput": 5141.43, "total_tokens": 13279232} {"current_steps": 3243, "total_steps": 6710, "loss": 0.4534, "lr": 1.3155173521837056e-06, "epoch": 2.416542473919523, "percentage": 48.33, "elapsed_time": "0:43:03", "remaining_time": "0:46:02", "throughput": 5141.4, "total_tokens": 13283328} {"current_steps": 3244, "total_steps": 6710, "loss": 0.3452, "lr": 1.314932904940198e-06, "epoch": 2.4172876304023845, "percentage": 48.35, "elapsed_time": "0:43:04", "remaining_time": "0:46:01", "throughput": 5141.4, "total_tokens": 13287424} {"current_steps": 3245, "total_steps": 6710, "loss": 0.3315, "lr": 1.3143484434629333e-06, "epoch": 2.418032786885246, "percentage": 48.36, "elapsed_time": "0:43:05", "remaining_time": "0:46:00", "throughput": 5141.39, "total_tokens": 13291520} {"current_steps": 3246, "total_steps": 6710, "loss": 0.4886, "lr": 1.3137639678800307e-06, "epoch": 2.418777943368107, "percentage": 48.38, "elapsed_time": "0:43:06", "remaining_time": "0:45:59", "throughput": 5141.38, "total_tokens": 13295616} {"current_steps": 3247, "total_steps": 6710, "loss": 0.2585, "lr": 1.3131794783196108e-06, "epoch": 2.4195230998509687, "percentage": 48.39, "elapsed_time": "0:43:06", "remaining_time": "0:45:58", "throughput": 5141.4, "total_tokens": 13299712} {"current_steps": 3248, "total_steps": 6710, "loss": 0.5271, "lr": 1.3125949749097982e-06, "epoch": 2.4202682563338302, "percentage": 48.41, "elapsed_time": "0:43:07", "remaining_time": "0:45:58", "throughput": 5141.43, "total_tokens": 13303808} {"current_steps": 3249, "total_steps": 6710, "loss": 0.2492, "lr": 1.3120104577787202e-06, "epoch": 2.4210134128166914, "percentage": 48.42, "elapsed_time": "0:43:08", "remaining_time": "0:45:57", "throughput": 5141.46, "total_tokens": 13307904} {"current_steps": 3250, "total_steps": 6710, "loss": 0.3467, "lr": 1.3114259270545074e-06, "epoch": 2.421758569299553, "percentage": 48.44, "elapsed_time": "0:43:09", "remaining_time": "0:45:56", "throughput": 5141.48, "total_tokens": 13312000} {"current_steps": 3251, "total_steps": 6710, "loss": 0.4668, "lr": 1.3108413828652926e-06, "epoch": 2.4225037257824145, "percentage": 48.45, "elapsed_time": "0:43:09", "remaining_time": "0:45:55", "throughput": 5141.5, "total_tokens": 13316096} {"current_steps": 3252, "total_steps": 6710, "loss": 0.2925, "lr": 1.310256825339212e-06, "epoch": 2.4232488822652756, "percentage": 48.46, "elapsed_time": "0:43:10", "remaining_time": "0:45:54", "throughput": 5141.52, "total_tokens": 13320192} {"current_steps": 3253, "total_steps": 6710, "loss": 0.1664, "lr": 1.3096722546044049e-06, "epoch": 2.423994038748137, "percentage": 48.48, "elapsed_time": "0:43:11", "remaining_time": "0:45:54", "throughput": 5141.55, "total_tokens": 13324288} {"current_steps": 3254, "total_steps": 6710, "loss": 0.4095, "lr": 1.3090876707890138e-06, "epoch": 2.4247391952309987, "percentage": 48.49, "elapsed_time": "0:43:12", "remaining_time": "0:45:53", "throughput": 5141.58, "total_tokens": 13328384} {"current_steps": 3255, "total_steps": 6710, "loss": 0.345, "lr": 1.3085030740211832e-06, "epoch": 2.42548435171386, "percentage": 48.51, "elapsed_time": "0:43:13", "remaining_time": "0:45:52", "throughput": 5141.59, "total_tokens": 13332480} {"current_steps": 3256, "total_steps": 6710, "loss": 0.7363, "lr": 1.307918464429061e-06, "epoch": 2.4262295081967213, "percentage": 48.52, "elapsed_time": "0:43:13", "remaining_time": "0:45:51", "throughput": 5141.59, "total_tokens": 13336576} {"current_steps": 3257, "total_steps": 6710, "loss": 0.2426, "lr": 1.3073338421407977e-06, "epoch": 2.426974664679583, "percentage": 48.54, "elapsed_time": "0:43:14", "remaining_time": "0:45:50", "throughput": 5141.62, "total_tokens": 13340672} {"current_steps": 3258, "total_steps": 6710, "loss": 0.3555, "lr": 1.3067492072845472e-06, "epoch": 2.427719821162444, "percentage": 48.55, "elapsed_time": "0:43:15", "remaining_time": "0:45:49", "throughput": 5141.66, "total_tokens": 13344768} {"current_steps": 3259, "total_steps": 6710, "loss": 0.3606, "lr": 1.3061645599884648e-06, "epoch": 2.4284649776453056, "percentage": 48.57, "elapsed_time": "0:43:16", "remaining_time": "0:45:49", "throughput": 5141.69, "total_tokens": 13348864} {"current_steps": 3260, "total_steps": 6710, "loss": 0.3475, "lr": 1.3055799003807104e-06, "epoch": 2.429210134128167, "percentage": 48.58, "elapsed_time": "0:43:16", "remaining_time": "0:45:48", "throughput": 5141.7, "total_tokens": 13352960} {"current_steps": 3261, "total_steps": 6710, "loss": 0.3438, "lr": 1.3049952285894444e-06, "epoch": 2.429955290611028, "percentage": 48.6, "elapsed_time": "0:43:17", "remaining_time": "0:45:47", "throughput": 5141.73, "total_tokens": 13357056} {"current_steps": 3262, "total_steps": 6710, "loss": 0.2783, "lr": 1.3044105447428319e-06, "epoch": 2.4307004470938898, "percentage": 48.61, "elapsed_time": "0:43:18", "remaining_time": "0:45:46", "throughput": 5141.76, "total_tokens": 13361152} {"current_steps": 3263, "total_steps": 6710, "loss": 0.3821, "lr": 1.303825848969039e-06, "epoch": 2.4314456035767513, "percentage": 48.63, "elapsed_time": "0:43:19", "remaining_time": "0:45:45", "throughput": 5141.79, "total_tokens": 13365248} {"current_steps": 3264, "total_steps": 6710, "loss": 0.1717, "lr": 1.303241141396236e-06, "epoch": 2.4321907600596124, "percentage": 48.64, "elapsed_time": "0:43:20", "remaining_time": "0:45:45", "throughput": 5141.81, "total_tokens": 13369344} {"current_steps": 3265, "total_steps": 6710, "loss": 0.416, "lr": 1.3026564221525948e-06, "epoch": 2.432935916542474, "percentage": 48.66, "elapsed_time": "0:43:20", "remaining_time": "0:45:44", "throughput": 5141.84, "total_tokens": 13373440} {"current_steps": 3266, "total_steps": 6710, "loss": 0.4053, "lr": 1.3020716913662896e-06, "epoch": 2.433681073025335, "percentage": 48.67, "elapsed_time": "0:43:21", "remaining_time": "0:45:43", "throughput": 5141.87, "total_tokens": 13377536} {"current_steps": 3267, "total_steps": 6710, "loss": 0.664, "lr": 1.3014869491654977e-06, "epoch": 2.4344262295081966, "percentage": 48.69, "elapsed_time": "0:43:22", "remaining_time": "0:45:42", "throughput": 5141.9, "total_tokens": 13381632} {"current_steps": 3268, "total_steps": 6710, "loss": 0.3354, "lr": 1.3009021956783994e-06, "epoch": 2.435171385991058, "percentage": 48.7, "elapsed_time": "0:43:23", "remaining_time": "0:45:41", "throughput": 5141.93, "total_tokens": 13385728} {"current_steps": 3269, "total_steps": 6710, "loss": 0.3743, "lr": 1.3003174310331758e-06, "epoch": 2.4359165424739198, "percentage": 48.72, "elapsed_time": "0:43:24", "remaining_time": "0:45:41", "throughput": 5141.95, "total_tokens": 13389824} {"current_steps": 3270, "total_steps": 6710, "loss": 0.4002, "lr": 1.2997326553580122e-06, "epoch": 2.436661698956781, "percentage": 48.73, "elapsed_time": "0:43:24", "remaining_time": "0:45:40", "throughput": 5141.95, "total_tokens": 13393920} {"current_steps": 3271, "total_steps": 6710, "loss": 0.395, "lr": 1.2991478687810956e-06, "epoch": 2.4374068554396424, "percentage": 48.75, "elapsed_time": "0:43:25", "remaining_time": "0:45:39", "throughput": 5141.97, "total_tokens": 13398016} {"current_steps": 3272, "total_steps": 6710, "loss": 0.3988, "lr": 1.2985630714306152e-06, "epoch": 2.4381520119225035, "percentage": 48.76, "elapsed_time": "0:43:26", "remaining_time": "0:45:38", "throughput": 5141.99, "total_tokens": 13402112} {"current_steps": 3273, "total_steps": 6710, "loss": 0.3688, "lr": 1.2979782634347627e-06, "epoch": 2.438897168405365, "percentage": 48.78, "elapsed_time": "0:43:27", "remaining_time": "0:45:37", "throughput": 5142.01, "total_tokens": 13406208} {"current_steps": 3274, "total_steps": 6710, "loss": 0.4492, "lr": 1.2973934449217321e-06, "epoch": 2.4396423248882266, "percentage": 48.79, "elapsed_time": "0:43:27", "remaining_time": "0:45:37", "throughput": 5142.04, "total_tokens": 13410304} {"current_steps": 3275, "total_steps": 6710, "loss": 0.5288, "lr": 1.29680861601972e-06, "epoch": 2.4403874813710877, "percentage": 48.81, "elapsed_time": "0:43:28", "remaining_time": "0:45:36", "throughput": 5142.07, "total_tokens": 13414400} {"current_steps": 3276, "total_steps": 6710, "loss": 0.3587, "lr": 1.296223776856925e-06, "epoch": 2.4411326378539493, "percentage": 48.82, "elapsed_time": "0:43:29", "remaining_time": "0:45:35", "throughput": 5142.1, "total_tokens": 13418496} {"current_steps": 3277, "total_steps": 6710, "loss": 0.2278, "lr": 1.2956389275615483e-06, "epoch": 2.441877794336811, "percentage": 48.84, "elapsed_time": "0:43:30", "remaining_time": "0:45:34", "throughput": 5142.11, "total_tokens": 13422592} {"current_steps": 3278, "total_steps": 6710, "loss": 0.53, "lr": 1.2950540682617926e-06, "epoch": 2.442622950819672, "percentage": 48.85, "elapsed_time": "0:43:31", "remaining_time": "0:45:33", "throughput": 5142.13, "total_tokens": 13426688} {"current_steps": 3279, "total_steps": 6710, "loss": 0.4296, "lr": 1.2944691990858638e-06, "epoch": 2.4433681073025335, "percentage": 48.87, "elapsed_time": "0:43:31", "remaining_time": "0:45:32", "throughput": 5142.11, "total_tokens": 13430784} {"current_steps": 3280, "total_steps": 6710, "loss": 0.6245, "lr": 1.2938843201619687e-06, "epoch": 2.444113263785395, "percentage": 48.88, "elapsed_time": "0:43:32", "remaining_time": "0:45:32", "throughput": 5142.1, "total_tokens": 13434880} {"current_steps": 3281, "total_steps": 6710, "loss": 0.4452, "lr": 1.293299431618317e-06, "epoch": 2.444858420268256, "percentage": 48.9, "elapsed_time": "0:43:33", "remaining_time": "0:45:31", "throughput": 5142.12, "total_tokens": 13438976} {"current_steps": 3282, "total_steps": 6710, "loss": 0.6708, "lr": 1.292714533583121e-06, "epoch": 2.4456035767511177, "percentage": 48.91, "elapsed_time": "0:43:34", "remaining_time": "0:45:30", "throughput": 5142.14, "total_tokens": 13443072} {"current_steps": 3283, "total_steps": 6710, "loss": 0.2072, "lr": 1.2921296261845939e-06, "epoch": 2.4463487332339793, "percentage": 48.93, "elapsed_time": "0:43:35", "remaining_time": "0:45:29", "throughput": 5142.16, "total_tokens": 13447168} {"current_steps": 3284, "total_steps": 6710, "loss": 0.2924, "lr": 1.291544709550952e-06, "epoch": 2.4470938897168404, "percentage": 48.94, "elapsed_time": "0:43:35", "remaining_time": "0:45:28", "throughput": 5142.19, "total_tokens": 13451264} {"current_steps": 3285, "total_steps": 6710, "loss": 0.4232, "lr": 1.2909597838104135e-06, "epoch": 2.447839046199702, "percentage": 48.96, "elapsed_time": "0:43:36", "remaining_time": "0:45:28", "throughput": 5142.23, "total_tokens": 13455360} {"current_steps": 3286, "total_steps": 6710, "loss": 0.2544, "lr": 1.2903748490911976e-06, "epoch": 2.4485842026825635, "percentage": 48.97, "elapsed_time": "0:43:37", "remaining_time": "0:45:27", "throughput": 5142.26, "total_tokens": 13459456} {"current_steps": 3287, "total_steps": 6710, "loss": 0.3442, "lr": 1.289789905521527e-06, "epoch": 2.4493293591654246, "percentage": 48.99, "elapsed_time": "0:43:38", "remaining_time": "0:45:26", "throughput": 5142.29, "total_tokens": 13463552} {"current_steps": 3288, "total_steps": 6710, "loss": 0.3876, "lr": 1.2892049532296244e-06, "epoch": 2.450074515648286, "percentage": 49.0, "elapsed_time": "0:43:38", "remaining_time": "0:45:25", "throughput": 5142.33, "total_tokens": 13467648} {"current_steps": 3289, "total_steps": 6710, "loss": 0.4853, "lr": 1.2886199923437162e-06, "epoch": 2.4508196721311477, "percentage": 49.02, "elapsed_time": "0:43:39", "remaining_time": "0:45:24", "throughput": 5142.36, "total_tokens": 13471744} {"current_steps": 3290, "total_steps": 6710, "loss": 0.285, "lr": 1.28803502299203e-06, "epoch": 2.451564828614009, "percentage": 49.03, "elapsed_time": "0:43:40", "remaining_time": "0:45:24", "throughput": 5142.39, "total_tokens": 13475840} {"current_steps": 3291, "total_steps": 6710, "loss": 0.3445, "lr": 1.2874500453027951e-06, "epoch": 2.4523099850968704, "percentage": 49.05, "elapsed_time": "0:43:41", "remaining_time": "0:45:23", "throughput": 5142.42, "total_tokens": 13479936} {"current_steps": 3292, "total_steps": 6710, "loss": 0.3988, "lr": 1.2868650594042428e-06, "epoch": 2.453055141579732, "percentage": 49.06, "elapsed_time": "0:43:42", "remaining_time": "0:45:22", "throughput": 5142.45, "total_tokens": 13484032} {"current_steps": 3293, "total_steps": 6710, "loss": 0.4382, "lr": 1.2862800654246063e-06, "epoch": 2.453800298062593, "percentage": 49.08, "elapsed_time": "0:43:42", "remaining_time": "0:45:21", "throughput": 5142.47, "total_tokens": 13488128} {"current_steps": 3294, "total_steps": 6710, "loss": 0.2164, "lr": 1.2856950634921202e-06, "epoch": 2.4545454545454546, "percentage": 49.09, "elapsed_time": "0:43:43", "remaining_time": "0:45:20", "throughput": 5142.48, "total_tokens": 13492224} {"current_steps": 3295, "total_steps": 6710, "loss": 0.3825, "lr": 1.2851100537350217e-06, "epoch": 2.455290611028316, "percentage": 49.11, "elapsed_time": "0:43:44", "remaining_time": "0:45:20", "throughput": 5142.48, "total_tokens": 13496320} {"current_steps": 3296, "total_steps": 6710, "loss": 0.2407, "lr": 1.2845250362815486e-06, "epoch": 2.4560357675111772, "percentage": 49.12, "elapsed_time": "0:43:45", "remaining_time": "0:45:19", "throughput": 5142.47, "total_tokens": 13500416} {"current_steps": 3297, "total_steps": 6710, "loss": 0.5335, "lr": 1.283940011259941e-06, "epoch": 2.456780923994039, "percentage": 49.14, "elapsed_time": "0:43:46", "remaining_time": "0:45:18", "throughput": 5142.46, "total_tokens": 13504512} {"current_steps": 3298, "total_steps": 6710, "loss": 0.571, "lr": 1.2833549787984406e-06, "epoch": 2.4575260804769004, "percentage": 49.15, "elapsed_time": "0:43:46", "remaining_time": "0:45:17", "throughput": 5142.43, "total_tokens": 13508608} {"current_steps": 3299, "total_steps": 6710, "loss": 0.0913, "lr": 1.2827699390252906e-06, "epoch": 2.4582712369597615, "percentage": 49.17, "elapsed_time": "0:43:47", "remaining_time": "0:45:16", "throughput": 5142.43, "total_tokens": 13512704} {"current_steps": 3300, "total_steps": 6710, "loss": 0.5557, "lr": 1.2821848920687361e-06, "epoch": 2.459016393442623, "percentage": 49.18, "elapsed_time": "0:43:48", "remaining_time": "0:45:16", "throughput": 5142.45, "total_tokens": 13516800} {"current_steps": 3301, "total_steps": 6710, "loss": 0.4178, "lr": 1.281599838057023e-06, "epoch": 2.459761549925484, "percentage": 49.2, "elapsed_time": "0:43:49", "remaining_time": "0:45:15", "throughput": 5142.47, "total_tokens": 13520896} {"current_steps": 3302, "total_steps": 6710, "loss": 0.4041, "lr": 1.2810147771184e-06, "epoch": 2.4605067064083457, "percentage": 49.21, "elapsed_time": "0:43:50", "remaining_time": "0:45:14", "throughput": 5142.48, "total_tokens": 13524992} {"current_steps": 3303, "total_steps": 6710, "loss": 0.218, "lr": 1.2804297093811163e-06, "epoch": 2.4612518628912072, "percentage": 49.23, "elapsed_time": "0:43:50", "remaining_time": "0:45:13", "throughput": 5142.5, "total_tokens": 13529088} {"current_steps": 3304, "total_steps": 6710, "loss": 0.4688, "lr": 1.2798446349734233e-06, "epoch": 2.461997019374069, "percentage": 49.24, "elapsed_time": "0:43:51", "remaining_time": "0:45:12", "throughput": 5142.5, "total_tokens": 13533184} {"current_steps": 3305, "total_steps": 6710, "loss": 0.3762, "lr": 1.2792595540235731e-06, "epoch": 2.46274217585693, "percentage": 49.25, "elapsed_time": "0:43:52", "remaining_time": "0:45:12", "throughput": 5142.5, "total_tokens": 13537280} {"current_steps": 3306, "total_steps": 6710, "loss": 0.5364, "lr": 1.2786744666598199e-06, "epoch": 2.4634873323397914, "percentage": 49.27, "elapsed_time": "0:43:53", "remaining_time": "0:45:11", "throughput": 5142.5, "total_tokens": 13541376} {"current_steps": 3307, "total_steps": 6710, "loss": 0.43, "lr": 1.2780893730104185e-06, "epoch": 2.4642324888226526, "percentage": 49.28, "elapsed_time": "0:43:54", "remaining_time": "0:45:10", "throughput": 5142.5, "total_tokens": 13545472} {"current_steps": 3308, "total_steps": 6710, "loss": 0.5577, "lr": 1.277504273203626e-06, "epoch": 2.464977645305514, "percentage": 49.3, "elapsed_time": "0:43:54", "remaining_time": "0:45:09", "throughput": 5142.51, "total_tokens": 13549568} {"current_steps": 3309, "total_steps": 6710, "loss": 0.488, "lr": 1.2769191673677006e-06, "epoch": 2.4657228017883757, "percentage": 49.31, "elapsed_time": "0:43:55", "remaining_time": "0:45:08", "throughput": 5142.5, "total_tokens": 13553664} {"current_steps": 3310, "total_steps": 6710, "loss": 0.3031, "lr": 1.2763340556309014e-06, "epoch": 2.4664679582712368, "percentage": 49.33, "elapsed_time": "0:43:56", "remaining_time": "0:45:08", "throughput": 5142.5, "total_tokens": 13557760} {"current_steps": 3311, "total_steps": 6710, "loss": 0.4377, "lr": 1.275748938121489e-06, "epoch": 2.4672131147540983, "percentage": 49.34, "elapsed_time": "0:43:57", "remaining_time": "0:45:07", "throughput": 5142.52, "total_tokens": 13561856} {"current_steps": 3312, "total_steps": 6710, "loss": 0.5657, "lr": 1.275163814967726e-06, "epoch": 2.46795827123696, "percentage": 49.36, "elapsed_time": "0:43:57", "remaining_time": "0:45:06", "throughput": 5142.54, "total_tokens": 13565952} {"current_steps": 3313, "total_steps": 6710, "loss": 0.3958, "lr": 1.2745786862978746e-06, "epoch": 2.468703427719821, "percentage": 49.37, "elapsed_time": "0:43:58", "remaining_time": "0:45:05", "throughput": 5142.56, "total_tokens": 13570048} {"current_steps": 3314, "total_steps": 6710, "loss": 0.3296, "lr": 1.2739935522401998e-06, "epoch": 2.4694485842026825, "percentage": 49.39, "elapsed_time": "0:43:59", "remaining_time": "0:45:04", "throughput": 5142.55, "total_tokens": 13574144} {"current_steps": 3315, "total_steps": 6710, "loss": 0.3841, "lr": 1.2734084129229673e-06, "epoch": 2.470193740685544, "percentage": 49.4, "elapsed_time": "0:44:00", "remaining_time": "0:45:04", "throughput": 5142.53, "total_tokens": 13578240} {"current_steps": 3316, "total_steps": 6710, "loss": 0.5648, "lr": 1.2728232684744433e-06, "epoch": 2.470938897168405, "percentage": 49.42, "elapsed_time": "0:44:01", "remaining_time": "0:45:03", "throughput": 5142.54, "total_tokens": 13582336} {"current_steps": 3317, "total_steps": 6710, "loss": 0.658, "lr": 1.2722381190228955e-06, "epoch": 2.4716840536512668, "percentage": 49.43, "elapsed_time": "0:44:01", "remaining_time": "0:45:02", "throughput": 5142.57, "total_tokens": 13586432} {"current_steps": 3318, "total_steps": 6710, "loss": 0.3127, "lr": 1.2716529646965938e-06, "epoch": 2.4724292101341283, "percentage": 49.45, "elapsed_time": "0:44:02", "remaining_time": "0:45:01", "throughput": 5142.6, "total_tokens": 13590528} {"current_steps": 3319, "total_steps": 6710, "loss": 0.2885, "lr": 1.2710678056238074e-06, "epoch": 2.4731743666169894, "percentage": 49.46, "elapsed_time": "0:44:03", "remaining_time": "0:45:00", "throughput": 5142.63, "total_tokens": 13594624} {"current_steps": 3320, "total_steps": 6710, "loss": 0.487, "lr": 1.2704826419328075e-06, "epoch": 2.473919523099851, "percentage": 49.48, "elapsed_time": "0:44:04", "remaining_time": "0:45:00", "throughput": 5142.66, "total_tokens": 13598720} {"current_steps": 3321, "total_steps": 6710, "loss": 0.7054, "lr": 1.2698974737518662e-06, "epoch": 2.4746646795827125, "percentage": 49.49, "elapsed_time": "0:44:05", "remaining_time": "0:44:59", "throughput": 5142.69, "total_tokens": 13602816} {"current_steps": 3322, "total_steps": 6710, "loss": 0.3633, "lr": 1.2693123012092564e-06, "epoch": 2.4754098360655736, "percentage": 49.51, "elapsed_time": "0:44:05", "remaining_time": "0:44:58", "throughput": 5142.72, "total_tokens": 13606912} {"current_steps": 3323, "total_steps": 6710, "loss": 0.6508, "lr": 1.2687271244332526e-06, "epoch": 2.476154992548435, "percentage": 49.52, "elapsed_time": "0:44:06", "remaining_time": "0:44:57", "throughput": 5142.75, "total_tokens": 13611008} {"current_steps": 3324, "total_steps": 6710, "loss": 0.4514, "lr": 1.2681419435521295e-06, "epoch": 2.4769001490312967, "percentage": 49.54, "elapsed_time": "0:44:07", "remaining_time": "0:44:56", "throughput": 5142.77, "total_tokens": 13615104} {"current_steps": 3325, "total_steps": 6710, "loss": 0.5054, "lr": 1.2675567586941628e-06, "epoch": 2.477645305514158, "percentage": 49.55, "elapsed_time": "0:44:08", "remaining_time": "0:44:56", "throughput": 5142.73, "total_tokens": 13619200} {"current_steps": 3326, "total_steps": 6710, "loss": 0.5148, "lr": 1.2669715699876292e-06, "epoch": 2.4783904619970194, "percentage": 49.57, "elapsed_time": "0:44:09", "remaining_time": "0:44:55", "throughput": 5142.71, "total_tokens": 13623296} {"current_steps": 3327, "total_steps": 6710, "loss": 0.271, "lr": 1.266386377560806e-06, "epoch": 2.479135618479881, "percentage": 49.58, "elapsed_time": "0:44:09", "remaining_time": "0:44:54", "throughput": 5142.71, "total_tokens": 13627392} {"current_steps": 3328, "total_steps": 6710, "loss": 0.3666, "lr": 1.2658011815419719e-06, "epoch": 2.479880774962742, "percentage": 49.6, "elapsed_time": "0:44:10", "remaining_time": "0:44:53", "throughput": 5142.72, "total_tokens": 13631488} {"current_steps": 3329, "total_steps": 6710, "loss": 0.4862, "lr": 1.265215982059406e-06, "epoch": 2.4806259314456036, "percentage": 49.61, "elapsed_time": "0:44:11", "remaining_time": "0:44:52", "throughput": 5142.73, "total_tokens": 13635584} {"current_steps": 3330, "total_steps": 6710, "loss": 0.3073, "lr": 1.2646307792413882e-06, "epoch": 2.481371087928465, "percentage": 49.63, "elapsed_time": "0:44:12", "remaining_time": "0:44:52", "throughput": 5142.74, "total_tokens": 13639680} {"current_steps": 3331, "total_steps": 6710, "loss": 0.5788, "lr": 1.2640455732161992e-06, "epoch": 2.4821162444113263, "percentage": 49.64, "elapsed_time": "0:44:13", "remaining_time": "0:44:51", "throughput": 5142.74, "total_tokens": 13643776} {"current_steps": 3332, "total_steps": 6710, "loss": 0.3611, "lr": 1.2634603641121201e-06, "epoch": 2.482861400894188, "percentage": 49.66, "elapsed_time": "0:44:13", "remaining_time": "0:44:50", "throughput": 5142.75, "total_tokens": 13647872} {"current_steps": 3333, "total_steps": 6710, "loss": 0.3443, "lr": 1.2628751520574336e-06, "epoch": 2.4836065573770494, "percentage": 49.67, "elapsed_time": "0:44:14", "remaining_time": "0:44:49", "throughput": 5142.76, "total_tokens": 13651968} {"current_steps": 3334, "total_steps": 6710, "loss": 0.6179, "lr": 1.2622899371804212e-06, "epoch": 2.4843517138599105, "percentage": 49.69, "elapsed_time": "0:44:15", "remaining_time": "0:44:48", "throughput": 5142.74, "total_tokens": 13656064} {"current_steps": 3335, "total_steps": 6710, "loss": 0.7325, "lr": 1.2617047196093671e-06, "epoch": 2.485096870342772, "percentage": 49.7, "elapsed_time": "0:44:16", "remaining_time": "0:44:48", "throughput": 5142.72, "total_tokens": 13660160} {"current_steps": 3336, "total_steps": 6710, "loss": 0.3844, "lr": 1.2611194994725548e-06, "epoch": 2.485842026825633, "percentage": 49.72, "elapsed_time": "0:44:17", "remaining_time": "0:44:47", "throughput": 5142.72, "total_tokens": 13664256} {"current_steps": 3337, "total_steps": 6710, "loss": 0.2519, "lr": 1.2605342768982688e-06, "epoch": 2.4865871833084947, "percentage": 49.73, "elapsed_time": "0:44:17", "remaining_time": "0:44:46", "throughput": 5142.73, "total_tokens": 13668352} {"current_steps": 3338, "total_steps": 6710, "loss": 0.4418, "lr": 1.259949052014794e-06, "epoch": 2.4873323397913563, "percentage": 49.75, "elapsed_time": "0:44:18", "remaining_time": "0:44:45", "throughput": 5142.72, "total_tokens": 13672448} {"current_steps": 3339, "total_steps": 6710, "loss": 0.3993, "lr": 1.259363824950416e-06, "epoch": 2.488077496274218, "percentage": 49.76, "elapsed_time": "0:44:19", "remaining_time": "0:44:44", "throughput": 5142.7, "total_tokens": 13676544} {"current_steps": 3340, "total_steps": 6710, "loss": 0.3014, "lr": 1.2587785958334208e-06, "epoch": 2.488822652757079, "percentage": 49.78, "elapsed_time": "0:44:20", "remaining_time": "0:44:44", "throughput": 5142.7, "total_tokens": 13680640} {"current_steps": 3341, "total_steps": 6710, "loss": 0.4106, "lr": 1.2581933647920945e-06, "epoch": 2.4895678092399405, "percentage": 49.79, "elapsed_time": "0:44:20", "remaining_time": "0:44:43", "throughput": 5142.72, "total_tokens": 13684736} {"current_steps": 3342, "total_steps": 6710, "loss": 0.3953, "lr": 1.2576081319547247e-06, "epoch": 2.4903129657228016, "percentage": 49.81, "elapsed_time": "0:44:21", "remaining_time": "0:44:42", "throughput": 5142.75, "total_tokens": 13688832} {"current_steps": 3343, "total_steps": 6710, "loss": 0.2827, "lr": 1.2570228974495976e-06, "epoch": 2.491058122205663, "percentage": 49.82, "elapsed_time": "0:44:22", "remaining_time": "0:44:41", "throughput": 5142.76, "total_tokens": 13692928} {"current_steps": 3344, "total_steps": 6710, "loss": 0.6276, "lr": 1.256437661405001e-06, "epoch": 2.4918032786885247, "percentage": 49.84, "elapsed_time": "0:44:23", "remaining_time": "0:44:40", "throughput": 5142.75, "total_tokens": 13697024} {"current_steps": 3345, "total_steps": 6710, "loss": 0.4185, "lr": 1.2558524239492237e-06, "epoch": 2.492548435171386, "percentage": 49.85, "elapsed_time": "0:44:24", "remaining_time": "0:44:40", "throughput": 5142.74, "total_tokens": 13701120} {"current_steps": 3346, "total_steps": 6710, "loss": 0.3374, "lr": 1.255267185210553e-06, "epoch": 2.4932935916542474, "percentage": 49.87, "elapsed_time": "0:44:24", "remaining_time": "0:44:39", "throughput": 5142.72, "total_tokens": 13705216} {"current_steps": 3347, "total_steps": 6710, "loss": 0.4391, "lr": 1.2546819453172772e-06, "epoch": 2.494038748137109, "percentage": 49.88, "elapsed_time": "0:44:25", "remaining_time": "0:44:38", "throughput": 5142.74, "total_tokens": 13709312} {"current_steps": 3348, "total_steps": 6710, "loss": 0.6904, "lr": 1.2540967043976863e-06, "epoch": 2.49478390461997, "percentage": 49.9, "elapsed_time": "0:44:26", "remaining_time": "0:44:37", "throughput": 5142.76, "total_tokens": 13713408} {"current_steps": 3349, "total_steps": 6710, "loss": 0.2237, "lr": 1.2535114625800679e-06, "epoch": 2.4955290611028316, "percentage": 49.91, "elapsed_time": "0:44:27", "remaining_time": "0:44:36", "throughput": 5142.79, "total_tokens": 13717504} {"current_steps": 3350, "total_steps": 6710, "loss": 0.2834, "lr": 1.2529262199927125e-06, "epoch": 2.496274217585693, "percentage": 49.93, "elapsed_time": "0:44:28", "remaining_time": "0:44:36", "throughput": 5142.81, "total_tokens": 13721600} {"current_steps": 3351, "total_steps": 6710, "loss": 0.2134, "lr": 1.2523409767639084e-06, "epoch": 2.4970193740685542, "percentage": 49.94, "elapsed_time": "0:44:28", "remaining_time": "0:44:35", "throughput": 5142.82, "total_tokens": 13725696} {"current_steps": 3352, "total_steps": 6710, "loss": 0.4353, "lr": 1.2517557330219456e-06, "epoch": 2.497764530551416, "percentage": 49.96, "elapsed_time": "0:44:29", "remaining_time": "0:44:34", "throughput": 5142.84, "total_tokens": 13729792} {"current_steps": 3353, "total_steps": 6710, "loss": 0.2914, "lr": 1.2511704888951134e-06, "epoch": 2.4985096870342773, "percentage": 49.97, "elapsed_time": "0:44:30", "remaining_time": "0:44:33", "throughput": 5142.85, "total_tokens": 13733888} {"current_steps": 3354, "total_steps": 6710, "loss": 0.316, "lr": 1.2505852445117017e-06, "epoch": 2.4992548435171384, "percentage": 49.99, "elapsed_time": "0:44:31", "remaining_time": "0:44:32", "throughput": 5142.87, "total_tokens": 13737984} {"current_steps": 3355, "total_steps": 6710, "loss": 0.3543, "lr": 1.25e-06, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "0:44:32", "remaining_time": "0:44:32", "throughput": 5142.89, "total_tokens": 13742080} {"current_steps": 3356, "total_steps": 6710, "loss": 0.2797, "lr": 1.2494147554882987e-06, "epoch": 2.5007451564828616, "percentage": 50.01, "elapsed_time": "0:44:32", "remaining_time": "0:44:31", "throughput": 5142.91, "total_tokens": 13746176} {"current_steps": 3357, "total_steps": 6710, "loss": 0.544, "lr": 1.248829511104887e-06, "epoch": 2.5014903129657227, "percentage": 50.03, "elapsed_time": "0:44:33", "remaining_time": "0:44:30", "throughput": 5142.92, "total_tokens": 13750272} {"current_steps": 3358, "total_steps": 6710, "loss": 0.4357, "lr": 1.2482442669780548e-06, "epoch": 2.502235469448584, "percentage": 50.04, "elapsed_time": "0:44:34", "remaining_time": "0:44:29", "throughput": 5142.9, "total_tokens": 13754368} {"current_steps": 3359, "total_steps": 6710, "loss": 0.3914, "lr": 1.247659023236092e-06, "epoch": 2.5029806259314458, "percentage": 50.06, "elapsed_time": "0:44:35", "remaining_time": "0:44:28", "throughput": 5142.87, "total_tokens": 13758464} {"current_steps": 3360, "total_steps": 6710, "loss": 0.5298, "lr": 1.247073780007288e-06, "epoch": 2.503725782414307, "percentage": 50.07, "elapsed_time": "0:44:36", "remaining_time": "0:44:28", "throughput": 5142.85, "total_tokens": 13762560} {"current_steps": 3361, "total_steps": 6710, "loss": 0.191, "lr": 1.2464885374199321e-06, "epoch": 2.5044709388971684, "percentage": 50.09, "elapsed_time": "0:44:36", "remaining_time": "0:44:27", "throughput": 5142.87, "total_tokens": 13766656} {"current_steps": 3362, "total_steps": 6710, "loss": 0.5687, "lr": 1.2459032956023145e-06, "epoch": 2.50521609538003, "percentage": 50.1, "elapsed_time": "0:44:37", "remaining_time": "0:44:26", "throughput": 5142.89, "total_tokens": 13770752} {"current_steps": 3363, "total_steps": 6710, "loss": 0.5974, "lr": 1.2453180546827232e-06, "epoch": 2.505961251862891, "percentage": 50.12, "elapsed_time": "0:44:38", "remaining_time": "0:44:25", "throughput": 5142.88, "total_tokens": 13774848} {"current_steps": 3364, "total_steps": 6710, "loss": 0.306, "lr": 1.2447328147894478e-06, "epoch": 2.5067064083457526, "percentage": 50.13, "elapsed_time": "0:44:39", "remaining_time": "0:44:24", "throughput": 5142.89, "total_tokens": 13778944} {"current_steps": 3365, "total_steps": 6710, "loss": 0.5289, "lr": 1.244147576050777e-06, "epoch": 2.5074515648286138, "percentage": 50.15, "elapsed_time": "0:44:40", "remaining_time": "0:44:24", "throughput": 5142.88, "total_tokens": 13783040} {"current_steps": 3366, "total_steps": 6710, "loss": 0.2106, "lr": 1.2435623385949992e-06, "epoch": 2.5081967213114753, "percentage": 50.16, "elapsed_time": "0:44:40", "remaining_time": "0:44:23", "throughput": 5142.88, "total_tokens": 13787136} {"current_steps": 3367, "total_steps": 6710, "loss": 0.3404, "lr": 1.2429771025504028e-06, "epoch": 2.508941877794337, "percentage": 50.18, "elapsed_time": "0:44:41", "remaining_time": "0:44:22", "throughput": 5142.85, "total_tokens": 13791232} {"current_steps": 3368, "total_steps": 6710, "loss": 0.4793, "lr": 1.2423918680452757e-06, "epoch": 2.5096870342771984, "percentage": 50.19, "elapsed_time": "0:44:42", "remaining_time": "0:44:21", "throughput": 5142.86, "total_tokens": 13795328} {"current_steps": 3369, "total_steps": 6710, "loss": 0.313, "lr": 1.2418066352079057e-06, "epoch": 2.5104321907600595, "percentage": 50.21, "elapsed_time": "0:44:43", "remaining_time": "0:44:20", "throughput": 5142.88, "total_tokens": 13799424} {"current_steps": 3370, "total_steps": 6710, "loss": 0.2538, "lr": 1.2412214041665794e-06, "epoch": 2.511177347242921, "percentage": 50.22, "elapsed_time": "0:44:44", "remaining_time": "0:44:20", "throughput": 5142.89, "total_tokens": 13803520} {"current_steps": 3371, "total_steps": 6710, "loss": 0.334, "lr": 1.2406361750495841e-06, "epoch": 2.511922503725782, "percentage": 50.24, "elapsed_time": "0:44:44", "remaining_time": "0:44:19", "throughput": 5142.9, "total_tokens": 13807616} {"current_steps": 3372, "total_steps": 6710, "loss": 0.2669, "lr": 1.240050947985206e-06, "epoch": 2.5126676602086437, "percentage": 50.25, "elapsed_time": "0:44:45", "remaining_time": "0:44:18", "throughput": 5142.9, "total_tokens": 13811712} {"current_steps": 3373, "total_steps": 6710, "loss": 0.5589, "lr": 1.2394657231017314e-06, "epoch": 2.5134128166915053, "percentage": 50.27, "elapsed_time": "0:44:46", "remaining_time": "0:44:17", "throughput": 5142.88, "total_tokens": 13815808} {"current_steps": 3374, "total_steps": 6710, "loss": 0.4447, "lr": 1.2388805005274454e-06, "epoch": 2.514157973174367, "percentage": 50.28, "elapsed_time": "0:44:47", "remaining_time": "0:44:16", "throughput": 5142.88, "total_tokens": 13819904} {"current_steps": 3375, "total_steps": 6710, "loss": 0.41, "lr": 1.238295280390633e-06, "epoch": 2.514903129657228, "percentage": 50.3, "elapsed_time": "0:44:47", "remaining_time": "0:44:16", "throughput": 5142.9, "total_tokens": 13824000} {"current_steps": 3376, "total_steps": 6710, "loss": 0.2345, "lr": 1.2377100628195792e-06, "epoch": 2.5156482861400895, "percentage": 50.31, "elapsed_time": "0:44:48", "remaining_time": "0:44:15", "throughput": 5142.93, "total_tokens": 13828096} {"current_steps": 3377, "total_steps": 6710, "loss": 0.235, "lr": 1.237124847942567e-06, "epoch": 2.5163934426229506, "percentage": 50.33, "elapsed_time": "0:44:49", "remaining_time": "0:44:14", "throughput": 5142.95, "total_tokens": 13832192} {"current_steps": 3378, "total_steps": 6710, "loss": 0.412, "lr": 1.23653963588788e-06, "epoch": 2.517138599105812, "percentage": 50.34, "elapsed_time": "0:44:50", "remaining_time": "0:44:13", "throughput": 5142.94, "total_tokens": 13836288} {"current_steps": 3379, "total_steps": 6710, "loss": 0.4421, "lr": 1.2359544267838013e-06, "epoch": 2.5178837555886737, "percentage": 50.36, "elapsed_time": "0:44:51", "remaining_time": "0:44:12", "throughput": 5142.93, "total_tokens": 13840384} {"current_steps": 3380, "total_steps": 6710, "loss": 0.5525, "lr": 1.2353692207586122e-06, "epoch": 2.5186289120715353, "percentage": 50.37, "elapsed_time": "0:44:51", "remaining_time": "0:44:12", "throughput": 5142.91, "total_tokens": 13844480} {"current_steps": 3381, "total_steps": 6710, "loss": 0.168, "lr": 1.2347840179405945e-06, "epoch": 2.5193740685543964, "percentage": 50.39, "elapsed_time": "0:44:52", "remaining_time": "0:44:11", "throughput": 5142.91, "total_tokens": 13848576} {"current_steps": 3382, "total_steps": 6710, "loss": 0.4576, "lr": 1.2341988184580285e-06, "epoch": 2.520119225037258, "percentage": 50.4, "elapsed_time": "0:44:53", "remaining_time": "0:44:10", "throughput": 5142.94, "total_tokens": 13852672} {"current_steps": 3383, "total_steps": 6710, "loss": 0.2815, "lr": 1.2336136224391944e-06, "epoch": 2.520864381520119, "percentage": 50.42, "elapsed_time": "0:44:54", "remaining_time": "0:44:09", "throughput": 5142.97, "total_tokens": 13856768} {"current_steps": 3384, "total_steps": 6710, "loss": 0.2526, "lr": 1.2330284300123712e-06, "epoch": 2.5216095380029806, "percentage": 50.43, "elapsed_time": "0:44:55", "remaining_time": "0:44:08", "throughput": 5143.0, "total_tokens": 13860864} {"current_steps": 3385, "total_steps": 6710, "loss": 0.4147, "lr": 1.2324432413058374e-06, "epoch": 2.522354694485842, "percentage": 50.45, "elapsed_time": "0:44:55", "remaining_time": "0:44:08", "throughput": 5143.03, "total_tokens": 13864960} {"current_steps": 3386, "total_steps": 6710, "loss": 0.4174, "lr": 1.2318580564478707e-06, "epoch": 2.5230998509687033, "percentage": 50.46, "elapsed_time": "0:44:56", "remaining_time": "0:44:07", "throughput": 5143.06, "total_tokens": 13869056} {"current_steps": 3387, "total_steps": 6710, "loss": 0.4381, "lr": 1.2312728755667476e-06, "epoch": 2.523845007451565, "percentage": 50.48, "elapsed_time": "0:44:57", "remaining_time": "0:44:06", "throughput": 5143.09, "total_tokens": 13873152} {"current_steps": 3388, "total_steps": 6710, "loss": 0.2613, "lr": 1.2306876987907436e-06, "epoch": 2.5245901639344264, "percentage": 50.49, "elapsed_time": "0:44:58", "remaining_time": "0:44:05", "throughput": 5143.11, "total_tokens": 13877248} {"current_steps": 3389, "total_steps": 6710, "loss": 0.3783, "lr": 1.2301025262481344e-06, "epoch": 2.5253353204172875, "percentage": 50.51, "elapsed_time": "0:44:59", "remaining_time": "0:44:04", "throughput": 5143.14, "total_tokens": 13881344} {"current_steps": 3390, "total_steps": 6710, "loss": 0.2685, "lr": 1.2295173580671931e-06, "epoch": 2.526080476900149, "percentage": 50.52, "elapsed_time": "0:44:59", "remaining_time": "0:44:04", "throughput": 5143.15, "total_tokens": 13885440} {"current_steps": 3391, "total_steps": 6710, "loss": 0.325, "lr": 1.2289321943761933e-06, "epoch": 2.5268256333830106, "percentage": 50.54, "elapsed_time": "0:45:00", "remaining_time": "0:44:03", "throughput": 5143.18, "total_tokens": 13889536} {"current_steps": 3392, "total_steps": 6710, "loss": 0.2603, "lr": 1.2283470353034068e-06, "epoch": 2.5275707898658717, "percentage": 50.55, "elapsed_time": "0:45:01", "remaining_time": "0:44:02", "throughput": 5143.2, "total_tokens": 13893632} {"current_steps": 3393, "total_steps": 6710, "loss": 0.4098, "lr": 1.2277618809771047e-06, "epoch": 2.5283159463487332, "percentage": 50.57, "elapsed_time": "0:45:02", "remaining_time": "0:44:01", "throughput": 5143.19, "total_tokens": 13897728} {"current_steps": 3394, "total_steps": 6710, "loss": 0.4225, "lr": 1.2271767315255573e-06, "epoch": 2.529061102831595, "percentage": 50.58, "elapsed_time": "0:45:02", "remaining_time": "0:44:00", "throughput": 5143.18, "total_tokens": 13901824} {"current_steps": 3395, "total_steps": 6710, "loss": 0.4468, "lr": 1.2265915870770331e-06, "epoch": 2.529806259314456, "percentage": 50.6, "elapsed_time": "0:45:03", "remaining_time": "0:44:00", "throughput": 5143.17, "total_tokens": 13905920} {"current_steps": 3396, "total_steps": 6710, "loss": 0.5304, "lr": 1.2260064477598004e-06, "epoch": 2.5305514157973175, "percentage": 50.61, "elapsed_time": "0:45:04", "remaining_time": "0:43:59", "throughput": 5143.14, "total_tokens": 13910016} {"current_steps": 3397, "total_steps": 6710, "loss": 0.4223, "lr": 1.2254213137021256e-06, "epoch": 2.531296572280179, "percentage": 50.63, "elapsed_time": "0:45:05", "remaining_time": "0:43:58", "throughput": 5143.16, "total_tokens": 13914112} {"current_steps": 3398, "total_steps": 6710, "loss": 0.4959, "lr": 1.2248361850322743e-06, "epoch": 2.53204172876304, "percentage": 50.64, "elapsed_time": "0:45:06", "remaining_time": "0:43:57", "throughput": 5143.16, "total_tokens": 13918208} {"current_steps": 3399, "total_steps": 6710, "loss": 0.4156, "lr": 1.224251061878511e-06, "epoch": 2.5327868852459017, "percentage": 50.66, "elapsed_time": "0:45:06", "remaining_time": "0:43:56", "throughput": 5143.17, "total_tokens": 13922304} {"current_steps": 3400, "total_steps": 6710, "loss": 0.1398, "lr": 1.2236659443690988e-06, "epoch": 2.533532041728763, "percentage": 50.67, "elapsed_time": "0:45:07", "remaining_time": "0:43:56", "throughput": 5143.17, "total_tokens": 13926400} {"current_steps": 3401, "total_steps": 6710, "loss": 0.2606, "lr": 1.2230808326322994e-06, "epoch": 2.5342771982116243, "percentage": 50.69, "elapsed_time": "0:45:08", "remaining_time": "0:43:55", "throughput": 5143.17, "total_tokens": 13930496} {"current_steps": 3402, "total_steps": 6710, "loss": 0.4289, "lr": 1.222495726796374e-06, "epoch": 2.535022354694486, "percentage": 50.7, "elapsed_time": "0:45:09", "remaining_time": "0:43:54", "throughput": 5143.19, "total_tokens": 13934592} {"current_steps": 3403, "total_steps": 6710, "loss": 0.6357, "lr": 1.221910626989582e-06, "epoch": 2.5357675111773474, "percentage": 50.72, "elapsed_time": "0:45:10", "remaining_time": "0:43:53", "throughput": 5143.17, "total_tokens": 13938688} {"current_steps": 3404, "total_steps": 6710, "loss": 0.4609, "lr": 1.2213255333401805e-06, "epoch": 2.5365126676602086, "percentage": 50.73, "elapsed_time": "0:45:10", "remaining_time": "0:43:52", "throughput": 5143.19, "total_tokens": 13942784} {"current_steps": 3405, "total_steps": 6710, "loss": 0.332, "lr": 1.220740445976427e-06, "epoch": 2.53725782414307, "percentage": 50.75, "elapsed_time": "0:45:11", "remaining_time": "0:43:52", "throughput": 5143.21, "total_tokens": 13946880} {"current_steps": 3406, "total_steps": 6710, "loss": 0.2976, "lr": 1.2201553650265769e-06, "epoch": 2.538002980625931, "percentage": 50.76, "elapsed_time": "0:45:12", "remaining_time": "0:43:51", "throughput": 5143.24, "total_tokens": 13950976} {"current_steps": 3407, "total_steps": 6710, "loss": 0.4376, "lr": 1.219570290618884e-06, "epoch": 2.5387481371087928, "percentage": 50.77, "elapsed_time": "0:45:13", "remaining_time": "0:43:50", "throughput": 5143.26, "total_tokens": 13955072} {"current_steps": 3408, "total_steps": 6710, "loss": 0.4329, "lr": 1.2189852228816002e-06, "epoch": 2.5394932935916543, "percentage": 50.79, "elapsed_time": "0:45:14", "remaining_time": "0:43:49", "throughput": 5143.24, "total_tokens": 13959168} {"current_steps": 3409, "total_steps": 6710, "loss": 0.3158, "lr": 1.2184001619429773e-06, "epoch": 2.540238450074516, "percentage": 50.8, "elapsed_time": "0:45:14", "remaining_time": "0:43:48", "throughput": 5143.25, "total_tokens": 13963264} {"current_steps": 3410, "total_steps": 6710, "loss": 0.2281, "lr": 1.2178151079312645e-06, "epoch": 2.540983606557377, "percentage": 50.82, "elapsed_time": "0:45:15", "remaining_time": "0:43:48", "throughput": 5143.27, "total_tokens": 13967360} {"current_steps": 3411, "total_steps": 6710, "loss": 0.1622, "lr": 1.2172300609747096e-06, "epoch": 2.5417287630402385, "percentage": 50.83, "elapsed_time": "0:45:16", "remaining_time": "0:43:47", "throughput": 5143.26, "total_tokens": 13971456} {"current_steps": 3412, "total_steps": 6710, "loss": 0.3686, "lr": 1.2166450212015596e-06, "epoch": 2.5424739195230996, "percentage": 50.85, "elapsed_time": "0:45:17", "remaining_time": "0:43:46", "throughput": 5143.26, "total_tokens": 13975552} {"current_steps": 3413, "total_steps": 6710, "loss": 0.3913, "lr": 1.216059988740059e-06, "epoch": 2.543219076005961, "percentage": 50.86, "elapsed_time": "0:45:18", "remaining_time": "0:43:45", "throughput": 5143.26, "total_tokens": 13979648} {"current_steps": 3414, "total_steps": 6710, "loss": 0.5461, "lr": 1.2154749637184516e-06, "epoch": 2.5439642324888228, "percentage": 50.88, "elapsed_time": "0:45:18", "remaining_time": "0:43:44", "throughput": 5143.28, "total_tokens": 13983744} {"current_steps": 3415, "total_steps": 6710, "loss": 0.3236, "lr": 1.2148899462649783e-06, "epoch": 2.5447093889716843, "percentage": 50.89, "elapsed_time": "0:45:19", "remaining_time": "0:43:44", "throughput": 5143.27, "total_tokens": 13987840} {"current_steps": 3416, "total_steps": 6710, "loss": 0.3437, "lr": 1.21430493650788e-06, "epoch": 2.5454545454545454, "percentage": 50.91, "elapsed_time": "0:45:20", "remaining_time": "0:43:43", "throughput": 5143.25, "total_tokens": 13991936} {"current_steps": 3417, "total_steps": 6710, "loss": 0.5926, "lr": 1.2137199345753944e-06, "epoch": 2.546199701937407, "percentage": 50.92, "elapsed_time": "0:45:21", "remaining_time": "0:43:42", "throughput": 5143.17, "total_tokens": 13996032} {"current_steps": 3418, "total_steps": 6710, "loss": 0.2362, "lr": 1.2131349405957576e-06, "epoch": 2.546944858420268, "percentage": 50.94, "elapsed_time": "0:45:22", "remaining_time": "0:43:41", "throughput": 5143.17, "total_tokens": 14000128} {"current_steps": 3419, "total_steps": 6710, "loss": 0.4551, "lr": 1.2125499546972055e-06, "epoch": 2.5476900149031296, "percentage": 50.95, "elapsed_time": "0:45:22", "remaining_time": "0:43:40", "throughput": 5143.19, "total_tokens": 14004224} {"current_steps": 3420, "total_steps": 6710, "loss": 0.3987, "lr": 1.2119649770079705e-06, "epoch": 2.548435171385991, "percentage": 50.97, "elapsed_time": "0:45:23", "remaining_time": "0:43:40", "throughput": 5143.21, "total_tokens": 14008320} {"current_steps": 3421, "total_steps": 6710, "loss": 0.4355, "lr": 1.211380007656284e-06, "epoch": 2.5491803278688527, "percentage": 50.98, "elapsed_time": "0:45:24", "remaining_time": "0:43:39", "throughput": 5143.24, "total_tokens": 14012416} {"current_steps": 3422, "total_steps": 6710, "loss": 0.4036, "lr": 1.210795046770376e-06, "epoch": 2.549925484351714, "percentage": 51.0, "elapsed_time": "0:45:25", "remaining_time": "0:43:38", "throughput": 5143.27, "total_tokens": 14016512} {"current_steps": 3423, "total_steps": 6710, "loss": 0.2797, "lr": 1.2102100944784735e-06, "epoch": 2.5506706408345754, "percentage": 51.01, "elapsed_time": "0:45:25", "remaining_time": "0:43:37", "throughput": 5143.3, "total_tokens": 14020608} {"current_steps": 3424, "total_steps": 6710, "loss": 0.3075, "lr": 1.2096251509088026e-06, "epoch": 2.5514157973174365, "percentage": 51.03, "elapsed_time": "0:45:26", "remaining_time": "0:43:36", "throughput": 5143.32, "total_tokens": 14024704} {"current_steps": 3425, "total_steps": 6710, "loss": 0.3832, "lr": 1.2090402161895867e-06, "epoch": 2.552160953800298, "percentage": 51.04, "elapsed_time": "0:45:27", "remaining_time": "0:43:36", "throughput": 5143.35, "total_tokens": 14028800} {"current_steps": 3426, "total_steps": 6710, "loss": 0.2296, "lr": 1.208455290449048e-06, "epoch": 2.5529061102831596, "percentage": 51.06, "elapsed_time": "0:45:28", "remaining_time": "0:43:35", "throughput": 5143.37, "total_tokens": 14032896} {"current_steps": 3427, "total_steps": 6710, "loss": 0.5366, "lr": 1.2078703738154061e-06, "epoch": 2.5536512667660207, "percentage": 51.07, "elapsed_time": "0:45:29", "remaining_time": "0:43:34", "throughput": 5143.4, "total_tokens": 14036992} {"current_steps": 3428, "total_steps": 6710, "loss": 0.4134, "lr": 1.2072854664168792e-06, "epoch": 2.5543964232488823, "percentage": 51.09, "elapsed_time": "0:45:29", "remaining_time": "0:43:33", "throughput": 5143.38, "total_tokens": 14041088} {"current_steps": 3429, "total_steps": 6710, "loss": 0.3741, "lr": 1.2067005683816832e-06, "epoch": 2.555141579731744, "percentage": 51.1, "elapsed_time": "0:45:30", "remaining_time": "0:43:32", "throughput": 5143.37, "total_tokens": 14045184} {"current_steps": 3430, "total_steps": 6710, "loss": 0.2155, "lr": 1.2061156798380322e-06, "epoch": 2.555886736214605, "percentage": 51.12, "elapsed_time": "0:45:31", "remaining_time": "0:43:32", "throughput": 5143.31, "total_tokens": 14049280} {"current_steps": 3431, "total_steps": 6710, "loss": 0.3548, "lr": 1.205530800914137e-06, "epoch": 2.5566318926974665, "percentage": 51.13, "elapsed_time": "0:45:32", "remaining_time": "0:43:31", "throughput": 5143.28, "total_tokens": 14053376} {"current_steps": 3432, "total_steps": 6710, "loss": 0.4427, "lr": 1.2049459317382078e-06, "epoch": 2.557377049180328, "percentage": 51.15, "elapsed_time": "0:45:33", "remaining_time": "0:43:30", "throughput": 5143.26, "total_tokens": 14057472} {"current_steps": 3433, "total_steps": 6710, "loss": 0.3189, "lr": 1.204361072438452e-06, "epoch": 2.558122205663189, "percentage": 51.16, "elapsed_time": "0:45:33", "remaining_time": "0:43:29", "throughput": 5143.27, "total_tokens": 14061568} {"current_steps": 3434, "total_steps": 6710, "loss": 0.4334, "lr": 1.2037762231430754e-06, "epoch": 2.5588673621460507, "percentage": 51.18, "elapsed_time": "0:45:34", "remaining_time": "0:43:28", "throughput": 5143.29, "total_tokens": 14065664} {"current_steps": 3435, "total_steps": 6710, "loss": 0.4868, "lr": 1.2031913839802805e-06, "epoch": 2.559612518628912, "percentage": 51.19, "elapsed_time": "0:45:35", "remaining_time": "0:43:28", "throughput": 5143.31, "total_tokens": 14069760} {"current_steps": 3436, "total_steps": 6710, "loss": 0.5275, "lr": 1.2026065550782683e-06, "epoch": 2.5603576751117734, "percentage": 51.21, "elapsed_time": "0:45:36", "remaining_time": "0:43:27", "throughput": 5143.31, "total_tokens": 14073856} {"current_steps": 3437, "total_steps": 6710, "loss": 0.2561, "lr": 1.2020217365652377e-06, "epoch": 2.561102831594635, "percentage": 51.22, "elapsed_time": "0:45:37", "remaining_time": "0:43:26", "throughput": 5143.31, "total_tokens": 14077952} {"current_steps": 3438, "total_steps": 6710, "loss": 0.2281, "lr": 1.201436928569385e-06, "epoch": 2.5618479880774965, "percentage": 51.24, "elapsed_time": "0:45:37", "remaining_time": "0:43:25", "throughput": 5143.32, "total_tokens": 14082048} {"current_steps": 3439, "total_steps": 6710, "loss": 0.3498, "lr": 1.2008521312189046e-06, "epoch": 2.5625931445603576, "percentage": 51.25, "elapsed_time": "0:45:38", "remaining_time": "0:43:24", "throughput": 5143.34, "total_tokens": 14086144} {"current_steps": 3440, "total_steps": 6710, "loss": 0.4865, "lr": 1.2002673446419878e-06, "epoch": 2.563338301043219, "percentage": 51.27, "elapsed_time": "0:45:39", "remaining_time": "0:43:24", "throughput": 5143.35, "total_tokens": 14090240} {"current_steps": 3441, "total_steps": 6710, "loss": 0.4352, "lr": 1.1996825689668244e-06, "epoch": 2.5640834575260802, "percentage": 51.28, "elapsed_time": "0:45:40", "remaining_time": "0:43:23", "throughput": 5143.32, "total_tokens": 14094336} {"current_steps": 3442, "total_steps": 6710, "loss": 0.3421, "lr": 1.1990978043216008e-06, "epoch": 2.564828614008942, "percentage": 51.3, "elapsed_time": "0:45:41", "remaining_time": "0:43:22", "throughput": 5143.34, "total_tokens": 14098432} {"current_steps": 3443, "total_steps": 6710, "loss": 0.3333, "lr": 1.1985130508345025e-06, "epoch": 2.5655737704918034, "percentage": 51.31, "elapsed_time": "0:45:41", "remaining_time": "0:43:21", "throughput": 5143.33, "total_tokens": 14102528} {"current_steps": 3444, "total_steps": 6710, "loss": 0.3008, "lr": 1.197928308633711e-06, "epoch": 2.566318926974665, "percentage": 51.33, "elapsed_time": "0:45:42", "remaining_time": "0:43:20", "throughput": 5143.31, "total_tokens": 14106624} {"current_steps": 3445, "total_steps": 6710, "loss": 0.4145, "lr": 1.1973435778474058e-06, "epoch": 2.567064083457526, "percentage": 51.34, "elapsed_time": "0:45:43", "remaining_time": "0:43:20", "throughput": 5143.31, "total_tokens": 14110720} {"current_steps": 3446, "total_steps": 6710, "loss": 0.1899, "lr": 1.1967588586037644e-06, "epoch": 2.5678092399403876, "percentage": 51.36, "elapsed_time": "0:45:44", "remaining_time": "0:43:19", "throughput": 5143.33, "total_tokens": 14114816} {"current_steps": 3447, "total_steps": 6710, "loss": 0.2911, "lr": 1.1961741510309612e-06, "epoch": 2.5685543964232487, "percentage": 51.37, "elapsed_time": "0:45:45", "remaining_time": "0:43:18", "throughput": 5143.35, "total_tokens": 14118912} {"current_steps": 3448, "total_steps": 6710, "loss": 0.3056, "lr": 1.1955894552571687e-06, "epoch": 2.5692995529061102, "percentage": 51.39, "elapsed_time": "0:45:45", "remaining_time": "0:43:17", "throughput": 5143.38, "total_tokens": 14123008} {"current_steps": 3449, "total_steps": 6710, "loss": 0.4178, "lr": 1.195004771410556e-06, "epoch": 2.570044709388972, "percentage": 51.4, "elapsed_time": "0:45:46", "remaining_time": "0:43:16", "throughput": 5143.39, "total_tokens": 14127104} {"current_steps": 3450, "total_steps": 6710, "loss": 0.3342, "lr": 1.19442009961929e-06, "epoch": 2.5707898658718333, "percentage": 51.42, "elapsed_time": "0:45:47", "remaining_time": "0:43:16", "throughput": 5143.42, "total_tokens": 14131200} {"current_steps": 3451, "total_steps": 6710, "loss": 0.445, "lr": 1.1938354400115355e-06, "epoch": 2.5715350223546944, "percentage": 51.43, "elapsed_time": "0:45:48", "remaining_time": "0:43:15", "throughput": 5143.45, "total_tokens": 14135296} {"current_steps": 3452, "total_steps": 6710, "loss": 0.2197, "lr": 1.1932507927154532e-06, "epoch": 2.572280178837556, "percentage": 51.45, "elapsed_time": "0:45:48", "remaining_time": "0:43:14", "throughput": 5143.48, "total_tokens": 14139392} {"current_steps": 3453, "total_steps": 6710, "loss": 0.4243, "lr": 1.1926661578592025e-06, "epoch": 2.573025335320417, "percentage": 51.46, "elapsed_time": "0:45:49", "remaining_time": "0:43:13", "throughput": 5143.51, "total_tokens": 14143488} {"current_steps": 3454, "total_steps": 6710, "loss": 0.3532, "lr": 1.1920815355709392e-06, "epoch": 2.5737704918032787, "percentage": 51.48, "elapsed_time": "0:45:50", "remaining_time": "0:43:12", "throughput": 5143.52, "total_tokens": 14147584} {"current_steps": 3455, "total_steps": 6710, "loss": 0.3987, "lr": 1.191496925978817e-06, "epoch": 2.57451564828614, "percentage": 51.49, "elapsed_time": "0:45:51", "remaining_time": "0:43:12", "throughput": 5143.55, "total_tokens": 14151680} {"current_steps": 3456, "total_steps": 6710, "loss": 0.2947, "lr": 1.1909123292109862e-06, "epoch": 2.5752608047690018, "percentage": 51.51, "elapsed_time": "0:45:52", "remaining_time": "0:43:11", "throughput": 5143.58, "total_tokens": 14155776} {"current_steps": 3457, "total_steps": 6710, "loss": 0.2443, "lr": 1.1903277453955955e-06, "epoch": 2.576005961251863, "percentage": 51.52, "elapsed_time": "0:45:52", "remaining_time": "0:43:10", "throughput": 5143.61, "total_tokens": 14159872} {"current_steps": 3458, "total_steps": 6710, "loss": 0.5147, "lr": 1.1897431746607885e-06, "epoch": 2.5767511177347244, "percentage": 51.54, "elapsed_time": "0:45:53", "remaining_time": "0:43:09", "throughput": 5143.63, "total_tokens": 14163968} {"current_steps": 3459, "total_steps": 6710, "loss": 0.4321, "lr": 1.189158617134708e-06, "epoch": 2.5774962742175855, "percentage": 51.55, "elapsed_time": "0:45:54", "remaining_time": "0:43:08", "throughput": 5143.66, "total_tokens": 14168064} {"current_steps": 3460, "total_steps": 6710, "loss": 0.2632, "lr": 1.188574072945493e-06, "epoch": 2.578241430700447, "percentage": 51.56, "elapsed_time": "0:45:55", "remaining_time": "0:43:08", "throughput": 5143.68, "total_tokens": 14172160} {"current_steps": 3461, "total_steps": 6710, "loss": 0.3273, "lr": 1.18798954222128e-06, "epoch": 2.5789865871833086, "percentage": 51.58, "elapsed_time": "0:45:56", "remaining_time": "0:43:07", "throughput": 5143.7, "total_tokens": 14176256} {"current_steps": 3462, "total_steps": 6710, "loss": 0.3446, "lr": 1.187405025090202e-06, "epoch": 2.5797317436661698, "percentage": 51.59, "elapsed_time": "0:45:56", "remaining_time": "0:43:06", "throughput": 5143.73, "total_tokens": 14180352} {"current_steps": 3463, "total_steps": 6710, "loss": 0.4213, "lr": 1.1868205216803894e-06, "epoch": 2.5804769001490313, "percentage": 51.61, "elapsed_time": "0:45:57", "remaining_time": "0:43:05", "throughput": 5143.75, "total_tokens": 14184448} {"current_steps": 3464, "total_steps": 6710, "loss": 0.2405, "lr": 1.1862360321199697e-06, "epoch": 2.581222056631893, "percentage": 51.62, "elapsed_time": "0:45:58", "remaining_time": "0:43:04", "throughput": 5143.77, "total_tokens": 14188544} {"current_steps": 3465, "total_steps": 6710, "loss": 0.6244, "lr": 1.185651556537067e-06, "epoch": 2.581967213114754, "percentage": 51.64, "elapsed_time": "0:45:59", "remaining_time": "0:43:03", "throughput": 5143.78, "total_tokens": 14192640} {"current_steps": 3466, "total_steps": 6710, "loss": 0.5554, "lr": 1.1850670950598025e-06, "epoch": 2.5827123695976155, "percentage": 51.65, "elapsed_time": "0:45:59", "remaining_time": "0:43:03", "throughput": 5143.79, "total_tokens": 14196736} {"current_steps": 3467, "total_steps": 6710, "loss": 0.2827, "lr": 1.1844826478162944e-06, "epoch": 2.583457526080477, "percentage": 51.67, "elapsed_time": "0:46:00", "remaining_time": "0:43:02", "throughput": 5143.77, "total_tokens": 14200832} {"current_steps": 3468, "total_steps": 6710, "loss": 0.7028, "lr": 1.1838982149346582e-06, "epoch": 2.584202682563338, "percentage": 51.68, "elapsed_time": "0:46:01", "remaining_time": "0:43:01", "throughput": 5143.76, "total_tokens": 14204928} {"current_steps": 3469, "total_steps": 6710, "loss": 0.2263, "lr": 1.183313796543005e-06, "epoch": 2.5849478390461997, "percentage": 51.7, "elapsed_time": "0:46:02", "remaining_time": "0:43:00", "throughput": 5143.77, "total_tokens": 14209024} {"current_steps": 3470, "total_steps": 6710, "loss": 0.4647, "lr": 1.182729392769444e-06, "epoch": 2.585692995529061, "percentage": 51.71, "elapsed_time": "0:46:03", "remaining_time": "0:43:00", "throughput": 5143.77, "total_tokens": 14213120} {"current_steps": 3471, "total_steps": 6710, "loss": 0.3584, "lr": 1.1821450037420804e-06, "epoch": 2.5864381520119224, "percentage": 51.73, "elapsed_time": "0:46:03", "remaining_time": "0:42:59", "throughput": 5143.78, "total_tokens": 14217216} {"current_steps": 3472, "total_steps": 6710, "loss": 0.4094, "lr": 1.1815606295890162e-06, "epoch": 2.587183308494784, "percentage": 51.74, "elapsed_time": "0:46:04", "remaining_time": "0:42:58", "throughput": 5143.78, "total_tokens": 14221312} {"current_steps": 3473, "total_steps": 6710, "loss": 0.7428, "lr": 1.1809762704383509e-06, "epoch": 2.5879284649776455, "percentage": 51.76, "elapsed_time": "0:46:05", "remaining_time": "0:42:57", "throughput": 5143.78, "total_tokens": 14225408} {"current_steps": 3474, "total_steps": 6710, "loss": 0.2473, "lr": 1.1803919264181796e-06, "epoch": 2.5886736214605066, "percentage": 51.77, "elapsed_time": "0:46:06", "remaining_time": "0:42:56", "throughput": 5143.8, "total_tokens": 14229504} {"current_steps": 3475, "total_steps": 6710, "loss": 0.628, "lr": 1.1798075976565954e-06, "epoch": 2.589418777943368, "percentage": 51.79, "elapsed_time": "0:46:07", "remaining_time": "0:42:56", "throughput": 5143.81, "total_tokens": 14233600} {"current_steps": 3476, "total_steps": 6710, "loss": 0.6466, "lr": 1.179223284281687e-06, "epoch": 2.5901639344262293, "percentage": 51.8, "elapsed_time": "0:46:07", "remaining_time": "0:42:55", "throughput": 5143.82, "total_tokens": 14237696} {"current_steps": 3477, "total_steps": 6710, "loss": 0.4867, "lr": 1.17863898642154e-06, "epoch": 2.590909090909091, "percentage": 51.82, "elapsed_time": "0:46:08", "remaining_time": "0:42:54", "throughput": 5143.85, "total_tokens": 14241792} {"current_steps": 3478, "total_steps": 6710, "loss": 0.2797, "lr": 1.1780547042042372e-06, "epoch": 2.5916542473919524, "percentage": 51.83, "elapsed_time": "0:46:09", "remaining_time": "0:42:53", "throughput": 5143.87, "total_tokens": 14245888} {"current_steps": 3479, "total_steps": 6710, "loss": 0.3814, "lr": 1.1774704377578564e-06, "epoch": 2.592399403874814, "percentage": 51.85, "elapsed_time": "0:46:10", "remaining_time": "0:42:52", "throughput": 5143.9, "total_tokens": 14249984} {"current_steps": 3480, "total_steps": 6710, "loss": 0.4292, "lr": 1.1768861872104738e-06, "epoch": 2.593144560357675, "percentage": 51.86, "elapsed_time": "0:46:11", "remaining_time": "0:42:51", "throughput": 5143.89, "total_tokens": 14254080} {"current_steps": 3481, "total_steps": 6710, "loss": 0.3057, "lr": 1.176301952690161e-06, "epoch": 2.5938897168405366, "percentage": 51.88, "elapsed_time": "0:46:11", "remaining_time": "0:42:51", "throughput": 5143.89, "total_tokens": 14258176} {"current_steps": 3482, "total_steps": 6710, "loss": 0.306, "lr": 1.1757177343249862e-06, "epoch": 2.5946348733233977, "percentage": 51.89, "elapsed_time": "0:46:12", "remaining_time": "0:42:50", "throughput": 5143.86, "total_tokens": 14262272} {"current_steps": 3483, "total_steps": 6710, "loss": 0.3711, "lr": 1.1751335322430147e-06, "epoch": 2.5953800298062593, "percentage": 51.91, "elapsed_time": "0:46:13", "remaining_time": "0:42:49", "throughput": 5143.87, "total_tokens": 14266368} {"current_steps": 3484, "total_steps": 6710, "loss": 0.6082, "lr": 1.174549346572308e-06, "epoch": 2.596125186289121, "percentage": 51.92, "elapsed_time": "0:46:14", "remaining_time": "0:42:48", "throughput": 5143.89, "total_tokens": 14270464} {"current_steps": 3485, "total_steps": 6710, "loss": 0.4426, "lr": 1.1739651774409227e-06, "epoch": 2.5968703427719824, "percentage": 51.94, "elapsed_time": "0:46:15", "remaining_time": "0:42:48", "throughput": 5143.9, "total_tokens": 14274560} {"current_steps": 3486, "total_steps": 6710, "loss": 0.3139, "lr": 1.1733810249769134e-06, "epoch": 2.5976154992548435, "percentage": 51.95, "elapsed_time": "0:46:15", "remaining_time": "0:42:47", "throughput": 5143.93, "total_tokens": 14278656} {"current_steps": 3487, "total_steps": 6710, "loss": 0.4105, "lr": 1.1727968893083306e-06, "epoch": 2.598360655737705, "percentage": 51.97, "elapsed_time": "0:46:16", "remaining_time": "0:42:46", "throughput": 5143.95, "total_tokens": 14282752} {"current_steps": 3488, "total_steps": 6710, "loss": 0.4766, "lr": 1.1722127705632211e-06, "epoch": 2.599105812220566, "percentage": 51.98, "elapsed_time": "0:46:17", "remaining_time": "0:42:45", "throughput": 5143.97, "total_tokens": 14286848} {"current_steps": 3489, "total_steps": 6710, "loss": 0.4836, "lr": 1.1716286688696277e-06, "epoch": 2.5998509687034277, "percentage": 52.0, "elapsed_time": "0:46:18", "remaining_time": "0:42:44", "throughput": 5143.99, "total_tokens": 14290944} {"current_steps": 3490, "total_steps": 6710, "loss": 0.4369, "lr": 1.1710445843555898e-06, "epoch": 2.6005961251862892, "percentage": 52.01, "elapsed_time": "0:46:18", "remaining_time": "0:42:43", "throughput": 5144.02, "total_tokens": 14295040} {"current_steps": 3491, "total_steps": 6710, "loss": 0.5515, "lr": 1.1704605171491425e-06, "epoch": 2.601341281669151, "percentage": 52.03, "elapsed_time": "0:46:19", "remaining_time": "0:42:43", "throughput": 5144.0, "total_tokens": 14299136} {"current_steps": 3492, "total_steps": 6710, "loss": 0.3006, "lr": 1.1698764673783178e-06, "epoch": 2.602086438152012, "percentage": 52.04, "elapsed_time": "0:46:20", "remaining_time": "0:42:42", "throughput": 5143.98, "total_tokens": 14303232} {"current_steps": 3493, "total_steps": 6710, "loss": 0.4438, "lr": 1.1692924351711438e-06, "epoch": 2.6028315946348735, "percentage": 52.06, "elapsed_time": "0:46:21", "remaining_time": "0:42:41", "throughput": 5143.99, "total_tokens": 14307328} {"current_steps": 3494, "total_steps": 6710, "loss": 0.2042, "lr": 1.1687084206556443e-06, "epoch": 2.6035767511177346, "percentage": 52.07, "elapsed_time": "0:46:22", "remaining_time": "0:42:40", "throughput": 5143.98, "total_tokens": 14311424} {"current_steps": 3495, "total_steps": 6710, "loss": 0.2168, "lr": 1.1681244239598392e-06, "epoch": 2.604321907600596, "percentage": 52.09, "elapsed_time": "0:46:22", "remaining_time": "0:42:39", "throughput": 5144.01, "total_tokens": 14315520} {"current_steps": 3496, "total_steps": 6710, "loss": 0.3757, "lr": 1.1675404452117456e-06, "epoch": 2.6050670640834577, "percentage": 52.1, "elapsed_time": "0:46:23", "remaining_time": "0:42:39", "throughput": 5143.98, "total_tokens": 14319616} {"current_steps": 3497, "total_steps": 6710, "loss": 0.2571, "lr": 1.166956484539375e-06, "epoch": 2.605812220566319, "percentage": 52.12, "elapsed_time": "0:46:24", "remaining_time": "0:42:38", "throughput": 5143.98, "total_tokens": 14323712} {"current_steps": 3498, "total_steps": 6710, "loss": 0.444, "lr": 1.1663725420707358e-06, "epoch": 2.6065573770491803, "percentage": 52.13, "elapsed_time": "0:46:25", "remaining_time": "0:42:37", "throughput": 5143.99, "total_tokens": 14327808} {"current_steps": 3499, "total_steps": 6710, "loss": 0.4145, "lr": 1.1657886179338327e-06, "epoch": 2.607302533532042, "percentage": 52.15, "elapsed_time": "0:46:26", "remaining_time": "0:42:36", "throughput": 5144.0, "total_tokens": 14331904} {"current_steps": 3500, "total_steps": 6710, "loss": 0.4051, "lr": 1.1652047122566658e-06, "epoch": 2.608047690014903, "percentage": 52.16, "elapsed_time": "0:46:26", "remaining_time": "0:42:36", "throughput": 5143.98, "total_tokens": 14336000} {"current_steps": 3501, "total_steps": 6710, "loss": 0.4226, "lr": 1.1646208251672315e-06, "epoch": 2.6087928464977646, "percentage": 52.18, "elapsed_time": "0:46:27", "remaining_time": "0:42:35", "throughput": 5143.93, "total_tokens": 14340096} {"current_steps": 3502, "total_steps": 6710, "loss": 0.5332, "lr": 1.1640369567935216e-06, "epoch": 2.609538002980626, "percentage": 52.19, "elapsed_time": "0:46:28", "remaining_time": "0:42:34", "throughput": 5143.91, "total_tokens": 14344192} {"current_steps": 3503, "total_steps": 6710, "loss": 0.5139, "lr": 1.1634531072635249e-06, "epoch": 2.610283159463487, "percentage": 52.21, "elapsed_time": "0:46:29", "remaining_time": "0:42:33", "throughput": 5143.89, "total_tokens": 14348288} {"current_steps": 3504, "total_steps": 6710, "loss": 0.4021, "lr": 1.162869276705225e-06, "epoch": 2.6110283159463488, "percentage": 52.22, "elapsed_time": "0:46:30", "remaining_time": "0:42:32", "throughput": 5143.86, "total_tokens": 14352384} {"current_steps": 3505, "total_steps": 6710, "loss": 0.6017, "lr": 1.162285465246602e-06, "epoch": 2.61177347242921, "percentage": 52.24, "elapsed_time": "0:46:31", "remaining_time": "0:42:32", "throughput": 5143.83, "total_tokens": 14356480} {"current_steps": 3506, "total_steps": 6710, "loss": 0.2348, "lr": 1.1617016730156314e-06, "epoch": 2.6125186289120714, "percentage": 52.25, "elapsed_time": "0:46:31", "remaining_time": "0:42:31", "throughput": 5143.8, "total_tokens": 14360576} {"current_steps": 3507, "total_steps": 6710, "loss": 0.6743, "lr": 1.1611179001402842e-06, "epoch": 2.613263785394933, "percentage": 52.27, "elapsed_time": "0:46:32", "remaining_time": "0:42:30", "throughput": 5143.8, "total_tokens": 14364672} {"current_steps": 3508, "total_steps": 6710, "loss": 0.1933, "lr": 1.1605341467485282e-06, "epoch": 2.6140089418777945, "percentage": 52.28, "elapsed_time": "0:46:33", "remaining_time": "0:42:29", "throughput": 5143.81, "total_tokens": 14368768} {"current_steps": 3509, "total_steps": 6710, "loss": 0.4021, "lr": 1.1599504129683262e-06, "epoch": 2.6147540983606556, "percentage": 52.3, "elapsed_time": "0:46:34", "remaining_time": "0:42:28", "throughput": 5143.81, "total_tokens": 14372864} {"current_steps": 3510, "total_steps": 6710, "loss": 0.3059, "lr": 1.159366698927637e-06, "epoch": 2.615499254843517, "percentage": 52.31, "elapsed_time": "0:46:35", "remaining_time": "0:42:28", "throughput": 5143.8, "total_tokens": 14376960} {"current_steps": 3511, "total_steps": 6710, "loss": 0.3, "lr": 1.1587830047544141e-06, "epoch": 2.6162444113263783, "percentage": 52.32, "elapsed_time": "0:46:35", "remaining_time": "0:42:27", "throughput": 5143.79, "total_tokens": 14381056} {"current_steps": 3512, "total_steps": 6710, "loss": 0.4086, "lr": 1.1581993305766078e-06, "epoch": 2.61698956780924, "percentage": 52.34, "elapsed_time": "0:46:36", "remaining_time": "0:42:26", "throughput": 5143.79, "total_tokens": 14385152} {"current_steps": 3513, "total_steps": 6710, "loss": 0.5888, "lr": 1.1576156765221639e-06, "epoch": 2.6177347242921014, "percentage": 52.35, "elapsed_time": "0:46:37", "remaining_time": "0:42:25", "throughput": 5143.78, "total_tokens": 14389248} {"current_steps": 3514, "total_steps": 6710, "loss": 0.2163, "lr": 1.1570320427190233e-06, "epoch": 2.618479880774963, "percentage": 52.37, "elapsed_time": "0:46:38", "remaining_time": "0:42:24", "throughput": 5143.79, "total_tokens": 14393344} {"current_steps": 3515, "total_steps": 6710, "loss": 0.4061, "lr": 1.1564484292951229e-06, "epoch": 2.619225037257824, "percentage": 52.38, "elapsed_time": "0:46:38", "remaining_time": "0:42:24", "throughput": 5143.81, "total_tokens": 14397440} {"current_steps": 3516, "total_steps": 6710, "loss": 0.4301, "lr": 1.155864836378395e-06, "epoch": 2.6199701937406856, "percentage": 52.4, "elapsed_time": "0:46:39", "remaining_time": "0:42:23", "throughput": 5143.82, "total_tokens": 14401536} {"current_steps": 3517, "total_steps": 6710, "loss": 0.4474, "lr": 1.155281264096767e-06, "epoch": 2.6207153502235467, "percentage": 52.41, "elapsed_time": "0:46:40", "remaining_time": "0:42:22", "throughput": 5143.85, "total_tokens": 14405632} {"current_steps": 3518, "total_steps": 6710, "loss": 0.3086, "lr": 1.154697712578162e-06, "epoch": 2.6214605067064083, "percentage": 52.43, "elapsed_time": "0:46:41", "remaining_time": "0:42:21", "throughput": 5143.87, "total_tokens": 14409728} {"current_steps": 3519, "total_steps": 6710, "loss": 0.267, "lr": 1.154114181950499e-06, "epoch": 2.62220566318927, "percentage": 52.44, "elapsed_time": "0:46:42", "remaining_time": "0:42:20", "throughput": 5143.88, "total_tokens": 14413824} {"current_steps": 3520, "total_steps": 6710, "loss": 0.3475, "lr": 1.1535306723416922e-06, "epoch": 2.6229508196721314, "percentage": 52.46, "elapsed_time": "0:46:42", "remaining_time": "0:42:20", "throughput": 5143.91, "total_tokens": 14417920} {"current_steps": 3521, "total_steps": 6710, "loss": 0.3978, "lr": 1.1529471838796507e-06, "epoch": 2.6236959761549925, "percentage": 52.47, "elapsed_time": "0:46:43", "remaining_time": "0:42:19", "throughput": 5143.92, "total_tokens": 14422016} {"current_steps": 3522, "total_steps": 6710, "loss": 0.4115, "lr": 1.1523637166922795e-06, "epoch": 2.624441132637854, "percentage": 52.49, "elapsed_time": "0:46:44", "remaining_time": "0:42:18", "throughput": 5143.94, "total_tokens": 14426112} {"current_steps": 3523, "total_steps": 6710, "loss": 0.1262, "lr": 1.151780270907479e-06, "epoch": 2.625186289120715, "percentage": 52.5, "elapsed_time": "0:46:45", "remaining_time": "0:42:17", "throughput": 5143.93, "total_tokens": 14430208} {"current_steps": 3524, "total_steps": 6710, "loss": 0.4811, "lr": 1.1511968466531446e-06, "epoch": 2.6259314456035767, "percentage": 52.52, "elapsed_time": "0:46:46", "remaining_time": "0:42:16", "throughput": 5143.91, "total_tokens": 14434304} {"current_steps": 3525, "total_steps": 6710, "loss": 0.4714, "lr": 1.1506134440571668e-06, "epoch": 2.6266766020864383, "percentage": 52.53, "elapsed_time": "0:46:46", "remaining_time": "0:42:16", "throughput": 5143.87, "total_tokens": 14438400} {"current_steps": 3526, "total_steps": 6710, "loss": 0.5017, "lr": 1.1500300632474318e-06, "epoch": 2.6274217585693, "percentage": 52.55, "elapsed_time": "0:46:47", "remaining_time": "0:42:15", "throughput": 5143.86, "total_tokens": 14442496} {"current_steps": 3527, "total_steps": 6710, "loss": 0.2242, "lr": 1.1494467043518206e-06, "epoch": 2.628166915052161, "percentage": 52.56, "elapsed_time": "0:46:48", "remaining_time": "0:42:14", "throughput": 5143.85, "total_tokens": 14446592} {"current_steps": 3528, "total_steps": 6710, "loss": 0.3743, "lr": 1.1488633674982097e-06, "epoch": 2.6289120715350225, "percentage": 52.58, "elapsed_time": "0:46:49", "remaining_time": "0:42:13", "throughput": 5143.85, "total_tokens": 14450688} {"current_steps": 3529, "total_steps": 6710, "loss": 0.3964, "lr": 1.148280052814471e-06, "epoch": 2.6296572280178836, "percentage": 52.59, "elapsed_time": "0:46:50", "remaining_time": "0:42:13", "throughput": 5143.84, "total_tokens": 14454784} {"current_steps": 3530, "total_steps": 6710, "loss": 0.334, "lr": 1.147696760428471e-06, "epoch": 2.630402384500745, "percentage": 52.61, "elapsed_time": "0:46:50", "remaining_time": "0:42:12", "throughput": 5143.83, "total_tokens": 14458880} {"current_steps": 3531, "total_steps": 6710, "loss": 0.3026, "lr": 1.1471134904680715e-06, "epoch": 2.6311475409836067, "percentage": 52.62, "elapsed_time": "0:46:51", "remaining_time": "0:42:11", "throughput": 5143.8, "total_tokens": 14462976} {"current_steps": 3532, "total_steps": 6710, "loss": 0.4094, "lr": 1.1465302430611298e-06, "epoch": 2.631892697466468, "percentage": 52.64, "elapsed_time": "0:46:52", "remaining_time": "0:42:10", "throughput": 5143.77, "total_tokens": 14467072} {"current_steps": 3533, "total_steps": 6710, "loss": 0.464, "lr": 1.1459470183354977e-06, "epoch": 2.6326378539493294, "percentage": 52.65, "elapsed_time": "0:46:53", "remaining_time": "0:42:09", "throughput": 5143.72, "total_tokens": 14471168} {"current_steps": 3534, "total_steps": 6710, "loss": 0.3522, "lr": 1.1453638164190222e-06, "epoch": 2.633383010432191, "percentage": 52.67, "elapsed_time": "0:46:54", "remaining_time": "0:42:09", "throughput": 5143.69, "total_tokens": 14475264} {"current_steps": 3535, "total_steps": 6710, "loss": 0.2746, "lr": 1.144780637439545e-06, "epoch": 2.634128166915052, "percentage": 52.68, "elapsed_time": "0:46:54", "remaining_time": "0:42:08", "throughput": 5143.68, "total_tokens": 14479360} {"current_steps": 3536, "total_steps": 6710, "loss": 0.3148, "lr": 1.1441974815249036e-06, "epoch": 2.6348733233979136, "percentage": 52.7, "elapsed_time": "0:46:55", "remaining_time": "0:42:07", "throughput": 5143.68, "total_tokens": 14483456} {"current_steps": 3537, "total_steps": 6710, "loss": 0.2396, "lr": 1.1436143488029302e-06, "epoch": 2.635618479880775, "percentage": 52.71, "elapsed_time": "0:46:56", "remaining_time": "0:42:06", "throughput": 5143.67, "total_tokens": 14487552} {"current_steps": 3538, "total_steps": 6710, "loss": 0.393, "lr": 1.1430312394014507e-06, "epoch": 2.6363636363636362, "percentage": 52.73, "elapsed_time": "0:46:57", "remaining_time": "0:42:05", "throughput": 5143.68, "total_tokens": 14491648} {"current_steps": 3539, "total_steps": 6710, "loss": 0.3525, "lr": 1.1424481534482873e-06, "epoch": 2.637108792846498, "percentage": 52.74, "elapsed_time": "0:46:58", "remaining_time": "0:42:05", "throughput": 5143.69, "total_tokens": 14495744} {"current_steps": 3540, "total_steps": 6710, "loss": 0.3514, "lr": 1.1418650910712568e-06, "epoch": 2.637853949329359, "percentage": 52.76, "elapsed_time": "0:46:58", "remaining_time": "0:42:04", "throughput": 5143.69, "total_tokens": 14499840} {"current_steps": 3541, "total_steps": 6710, "loss": 0.2351, "lr": 1.1412820523981704e-06, "epoch": 2.6385991058122205, "percentage": 52.77, "elapsed_time": "0:46:59", "remaining_time": "0:42:03", "throughput": 5143.7, "total_tokens": 14503936} {"current_steps": 3542, "total_steps": 6710, "loss": 0.5326, "lr": 1.1406990375568343e-06, "epoch": 2.639344262295082, "percentage": 52.79, "elapsed_time": "0:47:00", "remaining_time": "0:42:02", "throughput": 5143.72, "total_tokens": 14508032} {"current_steps": 3543, "total_steps": 6710, "loss": 0.3324, "lr": 1.14011604667505e-06, "epoch": 2.6400894187779436, "percentage": 52.8, "elapsed_time": "0:47:01", "remaining_time": "0:42:01", "throughput": 5143.73, "total_tokens": 14512128} {"current_steps": 3544, "total_steps": 6710, "loss": 0.2965, "lr": 1.1395330798806128e-06, "epoch": 2.6408345752608047, "percentage": 52.82, "elapsed_time": "0:47:02", "remaining_time": "0:42:01", "throughput": 5143.71, "total_tokens": 14516224} {"current_steps": 3545, "total_steps": 6710, "loss": 0.6146, "lr": 1.1389501373013132e-06, "epoch": 2.6415797317436662, "percentage": 52.83, "elapsed_time": "0:47:02", "remaining_time": "0:42:00", "throughput": 5143.7, "total_tokens": 14520320} {"current_steps": 3546, "total_steps": 6710, "loss": 0.5798, "lr": 1.1383672190649365e-06, "epoch": 2.6423248882265273, "percentage": 52.85, "elapsed_time": "0:47:03", "remaining_time": "0:41:59", "throughput": 5143.69, "total_tokens": 14524416} {"current_steps": 3547, "total_steps": 6710, "loss": 0.5623, "lr": 1.1377843252992624e-06, "epoch": 2.643070044709389, "percentage": 52.86, "elapsed_time": "0:47:04", "remaining_time": "0:41:58", "throughput": 5143.71, "total_tokens": 14528512} {"current_steps": 3548, "total_steps": 6710, "loss": 0.551, "lr": 1.1372014561320654e-06, "epoch": 2.6438152011922504, "percentage": 52.88, "elapsed_time": "0:47:05", "remaining_time": "0:41:57", "throughput": 5143.73, "total_tokens": 14532608} {"current_steps": 3549, "total_steps": 6710, "loss": 0.3512, "lr": 1.1366186116911148e-06, "epoch": 2.644560357675112, "percentage": 52.89, "elapsed_time": "0:47:06", "remaining_time": "0:41:57", "throughput": 5143.76, "total_tokens": 14536704} {"current_steps": 3550, "total_steps": 6710, "loss": 0.1728, "lr": 1.1360357921041743e-06, "epoch": 2.645305514157973, "percentage": 52.91, "elapsed_time": "0:47:06", "remaining_time": "0:41:56", "throughput": 5143.79, "total_tokens": 14540800} {"current_steps": 3551, "total_steps": 6710, "loss": 0.6809, "lr": 1.1354529974990022e-06, "epoch": 2.6460506706408347, "percentage": 52.92, "elapsed_time": "0:47:07", "remaining_time": "0:41:55", "throughput": 5143.82, "total_tokens": 14544896} {"current_steps": 3552, "total_steps": 6710, "loss": 0.2593, "lr": 1.1348702280033506e-06, "epoch": 2.6467958271236958, "percentage": 52.94, "elapsed_time": "0:47:08", "remaining_time": "0:41:54", "throughput": 5143.85, "total_tokens": 14548992} {"current_steps": 3553, "total_steps": 6710, "loss": 0.6094, "lr": 1.1342874837449673e-06, "epoch": 2.6475409836065573, "percentage": 52.95, "elapsed_time": "0:47:09", "remaining_time": "0:41:53", "throughput": 5143.88, "total_tokens": 14553088} {"current_steps": 3554, "total_steps": 6710, "loss": 0.3515, "lr": 1.1337047648515935e-06, "epoch": 2.648286140089419, "percentage": 52.97, "elapsed_time": "0:47:09", "remaining_time": "0:41:53", "throughput": 5143.9, "total_tokens": 14557184} {"current_steps": 3555, "total_steps": 6710, "loss": 0.4677, "lr": 1.133122071450966e-06, "epoch": 2.6490312965722804, "percentage": 52.98, "elapsed_time": "0:47:10", "remaining_time": "0:41:52", "throughput": 5143.93, "total_tokens": 14561280} {"current_steps": 3556, "total_steps": 6710, "loss": 0.4201, "lr": 1.1325394036708148e-06, "epoch": 2.6497764530551415, "percentage": 53.0, "elapsed_time": "0:47:11", "remaining_time": "0:41:51", "throughput": 5143.96, "total_tokens": 14565376} {"current_steps": 3557, "total_steps": 6710, "loss": 0.3379, "lr": 1.131956761638865e-06, "epoch": 2.650521609538003, "percentage": 53.01, "elapsed_time": "0:47:12", "remaining_time": "0:41:50", "throughput": 5143.98, "total_tokens": 14569472} {"current_steps": 3558, "total_steps": 6710, "loss": 0.3547, "lr": 1.131374145482836e-06, "epoch": 2.651266766020864, "percentage": 53.03, "elapsed_time": "0:47:13", "remaining_time": "0:41:49", "throughput": 5143.97, "total_tokens": 14573568} {"current_steps": 3559, "total_steps": 6710, "loss": 0.4682, "lr": 1.1307915553304413e-06, "epoch": 2.6520119225037257, "percentage": 53.04, "elapsed_time": "0:47:13", "remaining_time": "0:41:49", "throughput": 5143.95, "total_tokens": 14577664} {"current_steps": 3560, "total_steps": 6710, "loss": 0.4024, "lr": 1.1302089913093893e-06, "epoch": 2.6527570789865873, "percentage": 53.06, "elapsed_time": "0:47:14", "remaining_time": "0:41:48", "throughput": 5143.95, "total_tokens": 14581760} {"current_steps": 3561, "total_steps": 6710, "loss": 0.4452, "lr": 1.1296264535473816e-06, "epoch": 2.653502235469449, "percentage": 53.07, "elapsed_time": "0:47:15", "remaining_time": "0:41:47", "throughput": 5143.95, "total_tokens": 14585856} {"current_steps": 3562, "total_steps": 6710, "loss": 0.3435, "lr": 1.1290439421721146e-06, "epoch": 2.65424739195231, "percentage": 53.08, "elapsed_time": "0:47:16", "remaining_time": "0:41:46", "throughput": 5143.96, "total_tokens": 14589952} {"current_steps": 3563, "total_steps": 6710, "loss": 0.5881, "lr": 1.1284614573112792e-06, "epoch": 2.6549925484351715, "percentage": 53.1, "elapsed_time": "0:47:17", "remaining_time": "0:41:45", "throughput": 5143.95, "total_tokens": 14594048} {"current_steps": 3564, "total_steps": 6710, "loss": 0.4911, "lr": 1.127878999092561e-06, "epoch": 2.6557377049180326, "percentage": 53.11, "elapsed_time": "0:47:17", "remaining_time": "0:41:45", "throughput": 5143.94, "total_tokens": 14598144} {"current_steps": 3565, "total_steps": 6710, "loss": 0.3728, "lr": 1.1272965676436374e-06, "epoch": 2.656482861400894, "percentage": 53.13, "elapsed_time": "0:47:18", "remaining_time": "0:41:44", "throughput": 5143.94, "total_tokens": 14602240} {"current_steps": 3566, "total_steps": 6710, "loss": 0.5463, "lr": 1.1267141630921826e-06, "epoch": 2.6572280178837557, "percentage": 53.14, "elapsed_time": "0:47:19", "remaining_time": "0:41:43", "throughput": 5143.96, "total_tokens": 14606336} {"current_steps": 3567, "total_steps": 6710, "loss": 0.298, "lr": 1.1261317855658634e-06, "epoch": 2.657973174366617, "percentage": 53.16, "elapsed_time": "0:47:20", "remaining_time": "0:41:42", "throughput": 5143.96, "total_tokens": 14610432} {"current_steps": 3568, "total_steps": 6710, "loss": 0.5725, "lr": 1.1255494351923412e-06, "epoch": 2.6587183308494784, "percentage": 53.17, "elapsed_time": "0:47:21", "remaining_time": "0:41:41", "throughput": 5143.95, "total_tokens": 14614528} {"current_steps": 3569, "total_steps": 6710, "loss": 0.4199, "lr": 1.1249671120992718e-06, "epoch": 2.65946348733234, "percentage": 53.19, "elapsed_time": "0:47:21", "remaining_time": "0:41:41", "throughput": 5143.97, "total_tokens": 14618624} {"current_steps": 3570, "total_steps": 6710, "loss": 0.3499, "lr": 1.1243848164143043e-06, "epoch": 2.660208643815201, "percentage": 53.2, "elapsed_time": "0:47:22", "remaining_time": "0:41:40", "throughput": 5143.99, "total_tokens": 14622720} {"current_steps": 3571, "total_steps": 6710, "loss": 0.5526, "lr": 1.1238025482650818e-06, "epoch": 2.6609538002980626, "percentage": 53.22, "elapsed_time": "0:47:23", "remaining_time": "0:41:39", "throughput": 5144.01, "total_tokens": 14626816} {"current_steps": 3572, "total_steps": 6710, "loss": 0.4634, "lr": 1.123220307779242e-06, "epoch": 2.661698956780924, "percentage": 53.23, "elapsed_time": "0:47:24", "remaining_time": "0:41:38", "throughput": 5144.02, "total_tokens": 14630912} {"current_steps": 3573, "total_steps": 6710, "loss": 0.4727, "lr": 1.1226380950844156e-06, "epoch": 2.6624441132637853, "percentage": 53.25, "elapsed_time": "0:47:25", "remaining_time": "0:41:37", "throughput": 5144.04, "total_tokens": 14635008} {"current_steps": 3574, "total_steps": 6710, "loss": 0.4721, "lr": 1.1220559103082287e-06, "epoch": 2.663189269746647, "percentage": 53.26, "elapsed_time": "0:47:25", "remaining_time": "0:41:37", "throughput": 5144.06, "total_tokens": 14639104} {"current_steps": 3575, "total_steps": 6710, "loss": 0.5573, "lr": 1.1214737535782994e-06, "epoch": 2.663934426229508, "percentage": 53.28, "elapsed_time": "0:47:26", "remaining_time": "0:41:36", "throughput": 5144.08, "total_tokens": 14643200} {"current_steps": 3576, "total_steps": 6710, "loss": 0.5803, "lr": 1.1208916250222413e-06, "epoch": 2.6646795827123695, "percentage": 53.29, "elapsed_time": "0:47:27", "remaining_time": "0:41:35", "throughput": 5144.1, "total_tokens": 14647296} {"current_steps": 3577, "total_steps": 6710, "loss": 0.5272, "lr": 1.120309524767661e-06, "epoch": 2.665424739195231, "percentage": 53.31, "elapsed_time": "0:47:28", "remaining_time": "0:41:34", "throughput": 5144.11, "total_tokens": 14651392} {"current_steps": 3578, "total_steps": 6710, "loss": 0.4701, "lr": 1.1197274529421593e-06, "epoch": 2.6661698956780926, "percentage": 53.32, "elapsed_time": "0:47:28", "remaining_time": "0:41:33", "throughput": 5144.11, "total_tokens": 14655488} {"current_steps": 3579, "total_steps": 6710, "loss": 0.3019, "lr": 1.1191454096733299e-06, "epoch": 2.6669150521609537, "percentage": 53.34, "elapsed_time": "0:47:29", "remaining_time": "0:41:33", "throughput": 5144.12, "total_tokens": 14659584} {"current_steps": 3580, "total_steps": 6710, "loss": 0.5384, "lr": 1.1185633950887606e-06, "epoch": 2.6676602086438153, "percentage": 53.35, "elapsed_time": "0:47:30", "remaining_time": "0:41:32", "throughput": 5144.12, "total_tokens": 14663680} {"current_steps": 3581, "total_steps": 6710, "loss": 0.4015, "lr": 1.1179814093160343e-06, "epoch": 2.6684053651266764, "percentage": 53.37, "elapsed_time": "0:47:31", "remaining_time": "0:41:31", "throughput": 5144.13, "total_tokens": 14667776} {"current_steps": 3582, "total_steps": 6710, "loss": 0.6746, "lr": 1.1173994524827254e-06, "epoch": 2.669150521609538, "percentage": 53.38, "elapsed_time": "0:47:32", "remaining_time": "0:41:30", "throughput": 5144.16, "total_tokens": 14671872} {"current_steps": 3583, "total_steps": 6710, "loss": 0.3615, "lr": 1.1168175247164034e-06, "epoch": 2.6698956780923995, "percentage": 53.4, "elapsed_time": "0:47:32", "remaining_time": "0:41:29", "throughput": 5144.16, "total_tokens": 14675968} {"current_steps": 3584, "total_steps": 6710, "loss": 0.4114, "lr": 1.116235626144631e-06, "epoch": 2.670640834575261, "percentage": 53.41, "elapsed_time": "0:47:33", "remaining_time": "0:41:29", "throughput": 5144.19, "total_tokens": 14680064} {"current_steps": 3585, "total_steps": 6710, "loss": 0.2063, "lr": 1.1156537568949644e-06, "epoch": 2.671385991058122, "percentage": 53.43, "elapsed_time": "0:47:34", "remaining_time": "0:41:28", "throughput": 5144.21, "total_tokens": 14684160} {"current_steps": 3586, "total_steps": 6710, "loss": 0.353, "lr": 1.1150719170949537e-06, "epoch": 2.6721311475409837, "percentage": 53.44, "elapsed_time": "0:47:35", "remaining_time": "0:41:27", "throughput": 5144.23, "total_tokens": 14688256} {"current_steps": 3587, "total_steps": 6710, "loss": 0.2947, "lr": 1.1144901068721422e-06, "epoch": 2.672876304023845, "percentage": 53.46, "elapsed_time": "0:47:36", "remaining_time": "0:41:26", "throughput": 5144.26, "total_tokens": 14692352} {"current_steps": 3588, "total_steps": 6710, "loss": 0.4089, "lr": 1.1139083263540671e-06, "epoch": 2.6736214605067063, "percentage": 53.47, "elapsed_time": "0:47:36", "remaining_time": "0:41:25", "throughput": 5144.28, "total_tokens": 14696448} {"current_steps": 3589, "total_steps": 6710, "loss": 0.1855, "lr": 1.1133265756682585e-06, "epoch": 2.674366616989568, "percentage": 53.49, "elapsed_time": "0:47:37", "remaining_time": "0:41:25", "throughput": 5144.31, "total_tokens": 14700544} {"current_steps": 3590, "total_steps": 6710, "loss": 0.4792, "lr": 1.1127448549422405e-06, "epoch": 2.6751117734724295, "percentage": 53.5, "elapsed_time": "0:47:38", "remaining_time": "0:41:24", "throughput": 5144.33, "total_tokens": 14704640} {"current_steps": 3591, "total_steps": 6710, "loss": 0.3907, "lr": 1.1121631643035308e-06, "epoch": 2.6758569299552906, "percentage": 53.52, "elapsed_time": "0:47:39", "remaining_time": "0:41:23", "throughput": 5144.32, "total_tokens": 14708736} {"current_steps": 3592, "total_steps": 6710, "loss": 0.4785, "lr": 1.1115815038796393e-06, "epoch": 2.676602086438152, "percentage": 53.53, "elapsed_time": "0:47:40", "remaining_time": "0:41:22", "throughput": 5144.32, "total_tokens": 14712832} {"current_steps": 3593, "total_steps": 6710, "loss": 0.5395, "lr": 1.1109998737980703e-06, "epoch": 2.6773472429210132, "percentage": 53.55, "elapsed_time": "0:47:40", "remaining_time": "0:41:21", "throughput": 5144.33, "total_tokens": 14716928} {"current_steps": 3594, "total_steps": 6710, "loss": 0.3811, "lr": 1.1104182741863218e-06, "epoch": 2.678092399403875, "percentage": 53.56, "elapsed_time": "0:47:41", "remaining_time": "0:41:21", "throughput": 5144.35, "total_tokens": 14721024} {"current_steps": 3595, "total_steps": 6710, "loss": 0.6048, "lr": 1.1098367051718842e-06, "epoch": 2.6788375558867363, "percentage": 53.58, "elapsed_time": "0:47:42", "remaining_time": "0:41:20", "throughput": 5144.35, "total_tokens": 14725120} {"current_steps": 3596, "total_steps": 6710, "loss": 0.4313, "lr": 1.1092551668822417e-06, "epoch": 2.679582712369598, "percentage": 53.59, "elapsed_time": "0:47:43", "remaining_time": "0:41:19", "throughput": 5144.34, "total_tokens": 14729216} {"current_steps": 3597, "total_steps": 6710, "loss": 0.3067, "lr": 1.1086736594448716e-06, "epoch": 2.680327868852459, "percentage": 53.61, "elapsed_time": "0:47:43", "remaining_time": "0:41:18", "throughput": 5144.33, "total_tokens": 14733312} {"current_steps": 3598, "total_steps": 6710, "loss": 0.5244, "lr": 1.1080921829872447e-06, "epoch": 2.6810730253353205, "percentage": 53.62, "elapsed_time": "0:47:44", "remaining_time": "0:41:17", "throughput": 5144.33, "total_tokens": 14737408} {"current_steps": 3599, "total_steps": 6710, "loss": 0.4404, "lr": 1.1075107376368244e-06, "epoch": 2.6818181818181817, "percentage": 53.64, "elapsed_time": "0:47:45", "remaining_time": "0:41:17", "throughput": 5144.35, "total_tokens": 14741504} {"current_steps": 3600, "total_steps": 6710, "loss": 0.2816, "lr": 1.1069293235210679e-06, "epoch": 2.682563338301043, "percentage": 53.65, "elapsed_time": "0:47:46", "remaining_time": "0:41:16", "throughput": 5144.36, "total_tokens": 14745600} {"current_steps": 3601, "total_steps": 6710, "loss": 0.417, "lr": 1.1063479407674253e-06, "epoch": 2.6833084947839048, "percentage": 53.67, "elapsed_time": "0:47:47", "remaining_time": "0:41:15", "throughput": 5144.37, "total_tokens": 14749696} {"current_steps": 3602, "total_steps": 6710, "loss": 0.4393, "lr": 1.10576658950334e-06, "epoch": 2.684053651266766, "percentage": 53.68, "elapsed_time": "0:47:47", "remaining_time": "0:41:14", "throughput": 5144.38, "total_tokens": 14753792} {"current_steps": 3603, "total_steps": 6710, "loss": 0.3313, "lr": 1.1051852698562479e-06, "epoch": 2.6847988077496274, "percentage": 53.7, "elapsed_time": "0:47:48", "remaining_time": "0:41:13", "throughput": 5144.4, "total_tokens": 14757888} {"current_steps": 3604, "total_steps": 6710, "loss": 0.2667, "lr": 1.1046039819535788e-06, "epoch": 2.685543964232489, "percentage": 53.71, "elapsed_time": "0:47:49", "remaining_time": "0:41:13", "throughput": 5144.39, "total_tokens": 14761984} {"current_steps": 3605, "total_steps": 6710, "loss": 0.2549, "lr": 1.1040227259227557e-06, "epoch": 2.68628912071535, "percentage": 53.73, "elapsed_time": "0:47:50", "remaining_time": "0:41:12", "throughput": 5144.37, "total_tokens": 14766080} {"current_steps": 3606, "total_steps": 6710, "loss": 0.348, "lr": 1.1034415018911928e-06, "epoch": 2.6870342771982116, "percentage": 53.74, "elapsed_time": "0:47:51", "remaining_time": "0:41:11", "throughput": 5144.38, "total_tokens": 14770176} {"current_steps": 3607, "total_steps": 6710, "loss": 0.534, "lr": 1.1028603099862993e-06, "epoch": 2.687779433681073, "percentage": 53.76, "elapsed_time": "0:47:51", "remaining_time": "0:41:10", "throughput": 5144.38, "total_tokens": 14774272} {"current_steps": 3608, "total_steps": 6710, "loss": 0.3289, "lr": 1.102279150335477e-06, "epoch": 2.6885245901639343, "percentage": 53.77, "elapsed_time": "0:47:52", "remaining_time": "0:41:09", "throughput": 5144.38, "total_tokens": 14778368} {"current_steps": 3609, "total_steps": 6710, "loss": 0.4078, "lr": 1.101698023066119e-06, "epoch": 2.689269746646796, "percentage": 53.79, "elapsed_time": "0:47:53", "remaining_time": "0:41:09", "throughput": 5144.38, "total_tokens": 14782464} {"current_steps": 3610, "total_steps": 6710, "loss": 0.4499, "lr": 1.1011169283056136e-06, "epoch": 2.690014903129657, "percentage": 53.8, "elapsed_time": "0:47:54", "remaining_time": "0:41:08", "throughput": 5144.38, "total_tokens": 14786560} {"current_steps": 3611, "total_steps": 6710, "loss": 0.2369, "lr": 1.1005358661813406e-06, "epoch": 2.6907600596125185, "percentage": 53.82, "elapsed_time": "0:47:55", "remaining_time": "0:41:07", "throughput": 5144.38, "total_tokens": 14790656} {"current_steps": 3612, "total_steps": 6710, "loss": 0.4457, "lr": 1.099954836820673e-06, "epoch": 2.69150521609538, "percentage": 53.83, "elapsed_time": "0:47:55", "remaining_time": "0:41:06", "throughput": 5144.37, "total_tokens": 14794752} {"current_steps": 3613, "total_steps": 6710, "loss": 0.4135, "lr": 1.0993738403509768e-06, "epoch": 2.6922503725782416, "percentage": 53.85, "elapsed_time": "0:47:56", "remaining_time": "0:41:05", "throughput": 5144.38, "total_tokens": 14798848} {"current_steps": 3614, "total_steps": 6710, "loss": 0.2774, "lr": 1.0987928768996101e-06, "epoch": 2.6929955290611027, "percentage": 53.86, "elapsed_time": "0:47:57", "remaining_time": "0:41:05", "throughput": 5144.4, "total_tokens": 14802944} {"current_steps": 3615, "total_steps": 6710, "loss": 0.5572, "lr": 1.0982119465939247e-06, "epoch": 2.6937406855439643, "percentage": 53.87, "elapsed_time": "0:47:58", "remaining_time": "0:41:04", "throughput": 5144.42, "total_tokens": 14807040} {"current_steps": 3616, "total_steps": 6710, "loss": 0.3271, "lr": 1.0976310495612643e-06, "epoch": 2.6944858420268254, "percentage": 53.89, "elapsed_time": "0:47:59", "remaining_time": "0:41:03", "throughput": 5144.43, "total_tokens": 14811136} {"current_steps": 3617, "total_steps": 6710, "loss": 0.4542, "lr": 1.097050185928966e-06, "epoch": 2.695230998509687, "percentage": 53.9, "elapsed_time": "0:47:59", "remaining_time": "0:41:02", "throughput": 5144.45, "total_tokens": 14815232} {"current_steps": 3618, "total_steps": 6710, "loss": 0.1502, "lr": 1.0964693558243595e-06, "epoch": 2.6959761549925485, "percentage": 53.92, "elapsed_time": "0:48:00", "remaining_time": "0:41:01", "throughput": 5144.48, "total_tokens": 14819328} {"current_steps": 3619, "total_steps": 6710, "loss": 0.5128, "lr": 1.095888559374766e-06, "epoch": 2.69672131147541, "percentage": 53.93, "elapsed_time": "0:48:01", "remaining_time": "0:41:01", "throughput": 5144.5, "total_tokens": 14823424} {"current_steps": 3620, "total_steps": 6710, "loss": 0.2421, "lr": 1.0953077967075006e-06, "epoch": 2.697466467958271, "percentage": 53.95, "elapsed_time": "0:48:02", "remaining_time": "0:41:00", "throughput": 5144.53, "total_tokens": 14827520} {"current_steps": 3621, "total_steps": 6710, "loss": 0.4019, "lr": 1.0947270679498711e-06, "epoch": 2.6982116244411327, "percentage": 53.96, "elapsed_time": "0:48:02", "remaining_time": "0:40:59", "throughput": 5144.55, "total_tokens": 14831616} {"current_steps": 3622, "total_steps": 6710, "loss": 0.2458, "lr": 1.0941463732291768e-06, "epoch": 2.698956780923994, "percentage": 53.98, "elapsed_time": "0:48:03", "remaining_time": "0:40:58", "throughput": 5144.58, "total_tokens": 14835712} {"current_steps": 3623, "total_steps": 6710, "loss": 0.2759, "lr": 1.0935657126727105e-06, "epoch": 2.6997019374068554, "percentage": 53.99, "elapsed_time": "0:48:04", "remaining_time": "0:40:57", "throughput": 5144.61, "total_tokens": 14839808} {"current_steps": 3624, "total_steps": 6710, "loss": 0.5087, "lr": 1.0929850864077569e-06, "epoch": 2.700447093889717, "percentage": 54.01, "elapsed_time": "0:48:05", "remaining_time": "0:40:56", "throughput": 5144.62, "total_tokens": 14843904} {"current_steps": 3625, "total_steps": 6710, "loss": 0.4488, "lr": 1.0924044945615938e-06, "epoch": 2.7011922503725785, "percentage": 54.02, "elapsed_time": "0:48:06", "remaining_time": "0:40:56", "throughput": 5144.63, "total_tokens": 14848000} {"current_steps": 3626, "total_steps": 6710, "loss": 0.1715, "lr": 1.0918239372614907e-06, "epoch": 2.7019374068554396, "percentage": 54.04, "elapsed_time": "0:48:06", "remaining_time": "0:40:55", "throughput": 5144.64, "total_tokens": 14852096} {"current_steps": 3627, "total_steps": 6710, "loss": 0.6072, "lr": 1.0912434146347101e-06, "epoch": 2.702682563338301, "percentage": 54.05, "elapsed_time": "0:48:07", "remaining_time": "0:40:54", "throughput": 5144.64, "total_tokens": 14856192} {"current_steps": 3628, "total_steps": 6710, "loss": 0.4129, "lr": 1.0906629268085065e-06, "epoch": 2.7034277198211623, "percentage": 54.07, "elapsed_time": "0:48:08", "remaining_time": "0:40:53", "throughput": 5144.64, "total_tokens": 14860288} {"current_steps": 3629, "total_steps": 6710, "loss": 0.3469, "lr": 1.0900824739101272e-06, "epoch": 2.704172876304024, "percentage": 54.08, "elapsed_time": "0:48:09", "remaining_time": "0:40:52", "throughput": 5144.65, "total_tokens": 14864384} {"current_steps": 3630, "total_steps": 6710, "loss": 0.5107, "lr": 1.0895020560668112e-06, "epoch": 2.7049180327868854, "percentage": 54.1, "elapsed_time": "0:48:10", "remaining_time": "0:40:52", "throughput": 5144.66, "total_tokens": 14868480} {"current_steps": 3631, "total_steps": 6710, "loss": 0.4332, "lr": 1.0889216734057908e-06, "epoch": 2.705663189269747, "percentage": 54.11, "elapsed_time": "0:48:10", "remaining_time": "0:40:51", "throughput": 5144.67, "total_tokens": 14872576} {"current_steps": 3632, "total_steps": 6710, "loss": 0.3315, "lr": 1.0883413260542904e-06, "epoch": 2.706408345752608, "percentage": 54.13, "elapsed_time": "0:48:11", "remaining_time": "0:40:50", "throughput": 5144.67, "total_tokens": 14876672} {"current_steps": 3633, "total_steps": 6710, "loss": 0.3177, "lr": 1.087761014139525e-06, "epoch": 2.7071535022354696, "percentage": 54.14, "elapsed_time": "0:48:12", "remaining_time": "0:40:49", "throughput": 5144.69, "total_tokens": 14880768} {"current_steps": 3634, "total_steps": 6710, "loss": 0.4397, "lr": 1.087180737788704e-06, "epoch": 2.7078986587183307, "percentage": 54.16, "elapsed_time": "0:48:13", "remaining_time": "0:40:48", "throughput": 5144.7, "total_tokens": 14884864} {"current_steps": 3635, "total_steps": 6710, "loss": 0.31, "lr": 1.086600497129028e-06, "epoch": 2.7086438152011922, "percentage": 54.17, "elapsed_time": "0:48:14", "remaining_time": "0:40:48", "throughput": 5144.71, "total_tokens": 14888960} {"current_steps": 3636, "total_steps": 6710, "loss": 0.359, "lr": 1.0860202922876896e-06, "epoch": 2.709388971684054, "percentage": 54.19, "elapsed_time": "0:48:14", "remaining_time": "0:40:47", "throughput": 5144.72, "total_tokens": 14893056} {"current_steps": 3637, "total_steps": 6710, "loss": 0.4167, "lr": 1.085440123391874e-06, "epoch": 2.710134128166915, "percentage": 54.2, "elapsed_time": "0:48:15", "remaining_time": "0:40:46", "throughput": 5144.73, "total_tokens": 14897152} {"current_steps": 3638, "total_steps": 6710, "loss": 0.1896, "lr": 1.0848599905687584e-06, "epoch": 2.7108792846497765, "percentage": 54.22, "elapsed_time": "0:48:16", "remaining_time": "0:40:45", "throughput": 5144.74, "total_tokens": 14901248} {"current_steps": 3639, "total_steps": 6710, "loss": 0.369, "lr": 1.0842798939455121e-06, "epoch": 2.711624441132638, "percentage": 54.23, "elapsed_time": "0:48:17", "remaining_time": "0:40:44", "throughput": 5144.76, "total_tokens": 14905344} {"current_steps": 3640, "total_steps": 6710, "loss": 0.7195, "lr": 1.0836998336492965e-06, "epoch": 2.712369597615499, "percentage": 54.25, "elapsed_time": "0:48:17", "remaining_time": "0:40:44", "throughput": 5144.78, "total_tokens": 14909440} {"current_steps": 3641, "total_steps": 6710, "loss": 0.5649, "lr": 1.0831198098072648e-06, "epoch": 2.7131147540983607, "percentage": 54.26, "elapsed_time": "0:48:18", "remaining_time": "0:40:43", "throughput": 5144.8, "total_tokens": 14913536} {"current_steps": 3642, "total_steps": 6710, "loss": 0.3876, "lr": 1.0825398225465627e-06, "epoch": 2.7138599105812222, "percentage": 54.28, "elapsed_time": "0:48:19", "remaining_time": "0:40:42", "throughput": 5144.82, "total_tokens": 14917632} {"current_steps": 3643, "total_steps": 6710, "loss": 0.3816, "lr": 1.0819598719943269e-06, "epoch": 2.7146050670640833, "percentage": 54.29, "elapsed_time": "0:48:20", "remaining_time": "0:40:41", "throughput": 5144.82, "total_tokens": 14921728} {"current_steps": 3644, "total_steps": 6710, "loss": 0.1772, "lr": 1.0813799582776871e-06, "epoch": 2.715350223546945, "percentage": 54.31, "elapsed_time": "0:48:21", "remaining_time": "0:40:40", "throughput": 5144.82, "total_tokens": 14925824} {"current_steps": 3645, "total_steps": 6710, "loss": 0.5746, "lr": 1.0808000815237652e-06, "epoch": 2.716095380029806, "percentage": 54.32, "elapsed_time": "0:48:21", "remaining_time": "0:40:40", "throughput": 5144.81, "total_tokens": 14929920} {"current_steps": 3646, "total_steps": 6710, "loss": 0.3335, "lr": 1.080220241859673e-06, "epoch": 2.7168405365126675, "percentage": 54.34, "elapsed_time": "0:48:22", "remaining_time": "0:40:39", "throughput": 5144.8, "total_tokens": 14934016} {"current_steps": 3647, "total_steps": 6710, "loss": 0.3026, "lr": 1.079640439412516e-06, "epoch": 2.717585692995529, "percentage": 54.35, "elapsed_time": "0:48:23", "remaining_time": "0:40:38", "throughput": 5144.81, "total_tokens": 14938112} {"current_steps": 3648, "total_steps": 6710, "loss": 0.5475, "lr": 1.079060674309391e-06, "epoch": 2.7183308494783907, "percentage": 54.37, "elapsed_time": "0:48:24", "remaining_time": "0:40:37", "throughput": 5144.83, "total_tokens": 14942208} {"current_steps": 3649, "total_steps": 6710, "loss": 0.4865, "lr": 1.0784809466773871e-06, "epoch": 2.7190760059612518, "percentage": 54.38, "elapsed_time": "0:48:25", "remaining_time": "0:40:36", "throughput": 5144.85, "total_tokens": 14946304} {"current_steps": 3650, "total_steps": 6710, "loss": 0.4842, "lr": 1.0779012566435845e-06, "epoch": 2.7198211624441133, "percentage": 54.4, "elapsed_time": "0:48:25", "remaining_time": "0:40:36", "throughput": 5144.88, "total_tokens": 14950400} {"current_steps": 3651, "total_steps": 6710, "loss": 0.3947, "lr": 1.0773216043350552e-06, "epoch": 2.7205663189269744, "percentage": 54.41, "elapsed_time": "0:48:26", "remaining_time": "0:40:35", "throughput": 5144.9, "total_tokens": 14954496} {"current_steps": 3652, "total_steps": 6710, "loss": 0.3828, "lr": 1.0767419898788636e-06, "epoch": 2.721311475409836, "percentage": 54.43, "elapsed_time": "0:48:27", "remaining_time": "0:40:34", "throughput": 5144.93, "total_tokens": 14958592} {"current_steps": 3653, "total_steps": 6710, "loss": 0.3838, "lr": 1.0761624134020646e-06, "epoch": 2.7220566318926975, "percentage": 54.44, "elapsed_time": "0:48:28", "remaining_time": "0:40:33", "throughput": 5144.96, "total_tokens": 14962688} {"current_steps": 3654, "total_steps": 6710, "loss": 0.4215, "lr": 1.075582875031706e-06, "epoch": 2.722801788375559, "percentage": 54.46, "elapsed_time": "0:48:29", "remaining_time": "0:40:32", "throughput": 5144.98, "total_tokens": 14966784} {"current_steps": 3655, "total_steps": 6710, "loss": 0.2165, "lr": 1.0750033748948266e-06, "epoch": 2.72354694485842, "percentage": 54.47, "elapsed_time": "0:48:29", "remaining_time": "0:40:32", "throughput": 5145.01, "total_tokens": 14970880} {"current_steps": 3656, "total_steps": 6710, "loss": 0.2452, "lr": 1.074423913118457e-06, "epoch": 2.7242921013412817, "percentage": 54.49, "elapsed_time": "0:48:30", "remaining_time": "0:40:31", "throughput": 5145.03, "total_tokens": 14974976} {"current_steps": 3657, "total_steps": 6710, "loss": 0.3188, "lr": 1.0738444898296193e-06, "epoch": 2.725037257824143, "percentage": 54.5, "elapsed_time": "0:48:31", "remaining_time": "0:40:30", "throughput": 5145.05, "total_tokens": 14979072} {"current_steps": 3658, "total_steps": 6710, "loss": 0.4675, "lr": 1.0732651051553275e-06, "epoch": 2.7257824143070044, "percentage": 54.52, "elapsed_time": "0:48:32", "remaining_time": "0:40:29", "throughput": 5145.07, "total_tokens": 14983168} {"current_steps": 3659, "total_steps": 6710, "loss": 0.3714, "lr": 1.0726857592225872e-06, "epoch": 2.726527570789866, "percentage": 54.53, "elapsed_time": "0:48:32", "remaining_time": "0:40:28", "throughput": 5145.1, "total_tokens": 14987264} {"current_steps": 3660, "total_steps": 6710, "loss": 0.5777, "lr": 1.0721064521583939e-06, "epoch": 2.7272727272727275, "percentage": 54.55, "elapsed_time": "0:48:33", "remaining_time": "0:40:28", "throughput": 5145.12, "total_tokens": 14991360} {"current_steps": 3661, "total_steps": 6710, "loss": 0.4071, "lr": 1.0715271840897365e-06, "epoch": 2.7280178837555886, "percentage": 54.56, "elapsed_time": "0:48:34", "remaining_time": "0:40:27", "throughput": 5145.15, "total_tokens": 14995456} {"current_steps": 3662, "total_steps": 6710, "loss": 0.3918, "lr": 1.070947955143595e-06, "epoch": 2.72876304023845, "percentage": 54.58, "elapsed_time": "0:48:35", "remaining_time": "0:40:26", "throughput": 5145.15, "total_tokens": 14999552} {"current_steps": 3663, "total_steps": 6710, "loss": 0.3456, "lr": 1.0703687654469404e-06, "epoch": 2.7295081967213113, "percentage": 54.59, "elapsed_time": "0:48:36", "remaining_time": "0:40:25", "throughput": 5145.16, "total_tokens": 15003648} {"current_steps": 3664, "total_steps": 6710, "loss": 0.4295, "lr": 1.0697896151267348e-06, "epoch": 2.730253353204173, "percentage": 54.61, "elapsed_time": "0:48:36", "remaining_time": "0:40:24", "throughput": 5145.14, "total_tokens": 15007744} {"current_steps": 3665, "total_steps": 6710, "loss": 0.422, "lr": 1.0692105043099324e-06, "epoch": 2.7309985096870344, "percentage": 54.62, "elapsed_time": "0:48:37", "remaining_time": "0:40:24", "throughput": 5145.14, "total_tokens": 15011840} {"current_steps": 3666, "total_steps": 6710, "loss": 0.3713, "lr": 1.0686314331234784e-06, "epoch": 2.731743666169896, "percentage": 54.63, "elapsed_time": "0:48:38", "remaining_time": "0:40:23", "throughput": 5145.12, "total_tokens": 15015936} {"current_steps": 3667, "total_steps": 6710, "loss": 0.4, "lr": 1.0680524016943095e-06, "epoch": 2.732488822652757, "percentage": 54.65, "elapsed_time": "0:48:39", "remaining_time": "0:40:22", "throughput": 5145.12, "total_tokens": 15020032} {"current_steps": 3668, "total_steps": 6710, "loss": 0.3998, "lr": 1.0674734101493531e-06, "epoch": 2.7332339791356186, "percentage": 54.66, "elapsed_time": "0:48:40", "remaining_time": "0:40:21", "throughput": 5145.12, "total_tokens": 15024128} {"current_steps": 3669, "total_steps": 6710, "loss": 0.4227, "lr": 1.0668944586155288e-06, "epoch": 2.7339791356184797, "percentage": 54.68, "elapsed_time": "0:48:40", "remaining_time": "0:40:20", "throughput": 5145.12, "total_tokens": 15028224} {"current_steps": 3670, "total_steps": 6710, "loss": 0.3303, "lr": 1.0663155472197466e-06, "epoch": 2.7347242921013413, "percentage": 54.69, "elapsed_time": "0:48:41", "remaining_time": "0:40:20", "throughput": 5145.1, "total_tokens": 15032320} {"current_steps": 3671, "total_steps": 6710, "loss": 0.3732, "lr": 1.0657366760889083e-06, "epoch": 2.735469448584203, "percentage": 54.71, "elapsed_time": "0:48:42", "remaining_time": "0:40:19", "throughput": 5145.12, "total_tokens": 15036416} {"current_steps": 3672, "total_steps": 6710, "loss": 0.1829, "lr": 1.0651578453499064e-06, "epoch": 2.736214605067064, "percentage": 54.72, "elapsed_time": "0:48:43", "remaining_time": "0:40:18", "throughput": 5145.12, "total_tokens": 15040512} {"current_steps": 3673, "total_steps": 6710, "loss": 0.4336, "lr": 1.0645790551296245e-06, "epoch": 2.7369597615499255, "percentage": 54.74, "elapsed_time": "0:48:44", "remaining_time": "0:40:17", "throughput": 5145.12, "total_tokens": 15044608} {"current_steps": 3674, "total_steps": 6710, "loss": 0.4512, "lr": 1.0640003055549377e-06, "epoch": 2.737704918032787, "percentage": 54.75, "elapsed_time": "0:48:44", "remaining_time": "0:40:16", "throughput": 5145.11, "total_tokens": 15048704} {"current_steps": 3675, "total_steps": 6710, "loss": 0.3657, "lr": 1.063421596752712e-06, "epoch": 2.738450074515648, "percentage": 54.77, "elapsed_time": "0:48:45", "remaining_time": "0:40:16", "throughput": 5145.13, "total_tokens": 15052800} {"current_steps": 3676, "total_steps": 6710, "loss": 0.3709, "lr": 1.0628429288498045e-06, "epoch": 2.7391952309985097, "percentage": 54.78, "elapsed_time": "0:48:46", "remaining_time": "0:40:15", "throughput": 5145.13, "total_tokens": 15056896} {"current_steps": 3677, "total_steps": 6710, "loss": 0.4512, "lr": 1.0622643019730636e-06, "epoch": 2.7399403874813713, "percentage": 54.8, "elapsed_time": "0:48:47", "remaining_time": "0:40:14", "throughput": 5145.12, "total_tokens": 15060992} {"current_steps": 3678, "total_steps": 6710, "loss": 0.393, "lr": 1.0616857162493282e-06, "epoch": 2.7406855439642324, "percentage": 54.81, "elapsed_time": "0:48:48", "remaining_time": "0:40:13", "throughput": 5145.11, "total_tokens": 15065088} {"current_steps": 3679, "total_steps": 6710, "loss": 0.4627, "lr": 1.0611071718054283e-06, "epoch": 2.741430700447094, "percentage": 54.83, "elapsed_time": "0:48:48", "remaining_time": "0:40:12", "throughput": 5145.14, "total_tokens": 15069184} {"current_steps": 3680, "total_steps": 6710, "loss": 0.4651, "lr": 1.0605286687681857e-06, "epoch": 2.742175856929955, "percentage": 54.84, "elapsed_time": "0:48:49", "remaining_time": "0:40:12", "throughput": 5145.17, "total_tokens": 15073280} {"current_steps": 3681, "total_steps": 6710, "loss": 0.2185, "lr": 1.0599502072644114e-06, "epoch": 2.7429210134128166, "percentage": 54.86, "elapsed_time": "0:48:50", "remaining_time": "0:40:11", "throughput": 5145.19, "total_tokens": 15077376} {"current_steps": 3682, "total_steps": 6710, "loss": 0.3048, "lr": 1.0593717874209087e-06, "epoch": 2.743666169895678, "percentage": 54.87, "elapsed_time": "0:48:51", "remaining_time": "0:40:10", "throughput": 5145.22, "total_tokens": 15081472} {"current_steps": 3683, "total_steps": 6710, "loss": 0.2833, "lr": 1.0587934093644718e-06, "epoch": 2.7444113263785397, "percentage": 54.89, "elapsed_time": "0:48:51", "remaining_time": "0:40:09", "throughput": 5145.25, "total_tokens": 15085568} {"current_steps": 3684, "total_steps": 6710, "loss": 0.4278, "lr": 1.0582150732218843e-06, "epoch": 2.745156482861401, "percentage": 54.9, "elapsed_time": "0:48:52", "remaining_time": "0:40:08", "throughput": 5145.28, "total_tokens": 15089664} {"current_steps": 3685, "total_steps": 6710, "loss": 0.2376, "lr": 1.0576367791199227e-06, "epoch": 2.7459016393442623, "percentage": 54.92, "elapsed_time": "0:48:53", "remaining_time": "0:40:08", "throughput": 5145.31, "total_tokens": 15093760} {"current_steps": 3686, "total_steps": 6710, "loss": 0.2274, "lr": 1.057058527185353e-06, "epoch": 2.7466467958271235, "percentage": 54.93, "elapsed_time": "0:48:54", "remaining_time": "0:40:07", "throughput": 5145.34, "total_tokens": 15097856} {"current_steps": 3687, "total_steps": 6710, "loss": 0.3191, "lr": 1.0564803175449315e-06, "epoch": 2.747391952309985, "percentage": 54.95, "elapsed_time": "0:48:55", "remaining_time": "0:40:06", "throughput": 5145.35, "total_tokens": 15101952} {"current_steps": 3688, "total_steps": 6710, "loss": 0.631, "lr": 1.055902150325406e-06, "epoch": 2.7481371087928466, "percentage": 54.96, "elapsed_time": "0:48:55", "remaining_time": "0:40:05", "throughput": 5145.31, "total_tokens": 15106048} {"current_steps": 3689, "total_steps": 6710, "loss": 0.2641, "lr": 1.0553240256535155e-06, "epoch": 2.748882265275708, "percentage": 54.98, "elapsed_time": "0:48:56", "remaining_time": "0:40:04", "throughput": 5145.31, "total_tokens": 15110144} {"current_steps": 3690, "total_steps": 6710, "loss": 0.4577, "lr": 1.0547459436559886e-06, "epoch": 2.7496274217585692, "percentage": 54.99, "elapsed_time": "0:48:57", "remaining_time": "0:40:04", "throughput": 5145.33, "total_tokens": 15114240} {"current_steps": 3691, "total_steps": 6710, "loss": 0.2907, "lr": 1.0541679044595449e-06, "epoch": 2.7503725782414308, "percentage": 55.01, "elapsed_time": "0:48:58", "remaining_time": "0:40:03", "throughput": 5145.35, "total_tokens": 15118336} {"current_steps": 3692, "total_steps": 6710, "loss": 0.375, "lr": 1.053589908190895e-06, "epoch": 2.751117734724292, "percentage": 55.02, "elapsed_time": "0:48:59", "remaining_time": "0:40:02", "throughput": 5145.34, "total_tokens": 15122432} {"current_steps": 3693, "total_steps": 6710, "loss": 0.4219, "lr": 1.0530119549767396e-06, "epoch": 2.7518628912071534, "percentage": 55.04, "elapsed_time": "0:48:59", "remaining_time": "0:40:01", "throughput": 5145.31, "total_tokens": 15126528} {"current_steps": 3694, "total_steps": 6710, "loss": 0.2478, "lr": 1.0524340449437704e-06, "epoch": 2.752608047690015, "percentage": 55.05, "elapsed_time": "0:49:00", "remaining_time": "0:40:00", "throughput": 5145.29, "total_tokens": 15130624} {"current_steps": 3695, "total_steps": 6710, "loss": 0.4692, "lr": 1.0518561782186693e-06, "epoch": 2.7533532041728765, "percentage": 55.07, "elapsed_time": "0:49:01", "remaining_time": "0:40:00", "throughput": 5145.24, "total_tokens": 15134720} {"current_steps": 3696, "total_steps": 6710, "loss": 0.4034, "lr": 1.0512783549281089e-06, "epoch": 2.7540983606557377, "percentage": 55.08, "elapsed_time": "0:49:02", "remaining_time": "0:39:59", "throughput": 5145.25, "total_tokens": 15138816} {"current_steps": 3697, "total_steps": 6710, "loss": 0.2869, "lr": 1.050700575198752e-06, "epoch": 2.754843517138599, "percentage": 55.1, "elapsed_time": "0:49:03", "remaining_time": "0:39:58", "throughput": 5145.27, "total_tokens": 15142912} {"current_steps": 3698, "total_steps": 6710, "loss": 0.3275, "lr": 1.0501228391572522e-06, "epoch": 2.7555886736214603, "percentage": 55.11, "elapsed_time": "0:49:03", "remaining_time": "0:39:57", "throughput": 5145.24, "total_tokens": 15147008} {"current_steps": 3699, "total_steps": 6710, "loss": 0.3776, "lr": 1.0495451469302535e-06, "epoch": 2.756333830104322, "percentage": 55.13, "elapsed_time": "0:49:04", "remaining_time": "0:39:57", "throughput": 5145.2, "total_tokens": 15151104} {"current_steps": 3700, "total_steps": 6710, "loss": 0.2907, "lr": 1.04896749864439e-06, "epoch": 2.7570789865871834, "percentage": 55.14, "elapsed_time": "0:49:05", "remaining_time": "0:39:56", "throughput": 5145.2, "total_tokens": 15155200} {"current_steps": 3701, "total_steps": 6710, "loss": 0.4951, "lr": 1.048389894426286e-06, "epoch": 2.757824143070045, "percentage": 55.16, "elapsed_time": "0:49:06", "remaining_time": "0:39:55", "throughput": 5145.2, "total_tokens": 15159296} {"current_steps": 3702, "total_steps": 6710, "loss": 0.3894, "lr": 1.0478123344025566e-06, "epoch": 2.758569299552906, "percentage": 55.17, "elapsed_time": "0:49:07", "remaining_time": "0:39:54", "throughput": 5145.2, "total_tokens": 15163392} {"current_steps": 3703, "total_steps": 6710, "loss": 0.44, "lr": 1.0472348186998076e-06, "epoch": 2.7593144560357676, "percentage": 55.19, "elapsed_time": "0:49:07", "remaining_time": "0:39:53", "throughput": 5145.19, "total_tokens": 15167488} {"current_steps": 3704, "total_steps": 6710, "loss": 0.2329, "lr": 1.0466573474446339e-06, "epoch": 2.7600596125186287, "percentage": 55.2, "elapsed_time": "0:49:08", "remaining_time": "0:39:53", "throughput": 5145.22, "total_tokens": 15171584} {"current_steps": 3705, "total_steps": 6710, "loss": 0.4538, "lr": 1.0460799207636218e-06, "epoch": 2.7608047690014903, "percentage": 55.22, "elapsed_time": "0:49:09", "remaining_time": "0:39:52", "throughput": 5145.23, "total_tokens": 15175680} {"current_steps": 3706, "total_steps": 6710, "loss": 0.5946, "lr": 1.0455025387833472e-06, "epoch": 2.761549925484352, "percentage": 55.23, "elapsed_time": "0:49:10", "remaining_time": "0:39:51", "throughput": 5145.23, "total_tokens": 15179776} {"current_steps": 3707, "total_steps": 6710, "loss": 0.5334, "lr": 1.0449252016303765e-06, "epoch": 2.762295081967213, "percentage": 55.25, "elapsed_time": "0:49:11", "remaining_time": "0:39:50", "throughput": 5145.23, "total_tokens": 15183872} {"current_steps": 3708, "total_steps": 6710, "loss": 0.5862, "lr": 1.044347909431266e-06, "epoch": 2.7630402384500745, "percentage": 55.26, "elapsed_time": "0:49:11", "remaining_time": "0:39:49", "throughput": 5145.24, "total_tokens": 15187968} {"current_steps": 3709, "total_steps": 6710, "loss": 0.3146, "lr": 1.0437706623125619e-06, "epoch": 2.763785394932936, "percentage": 55.28, "elapsed_time": "0:49:12", "remaining_time": "0:39:49", "throughput": 5145.23, "total_tokens": 15192064} {"current_steps": 3710, "total_steps": 6710, "loss": 0.243, "lr": 1.0431934604008012e-06, "epoch": 2.764530551415797, "percentage": 55.29, "elapsed_time": "0:49:13", "remaining_time": "0:39:48", "throughput": 5145.21, "total_tokens": 15196160} {"current_steps": 3711, "total_steps": 6710, "loss": 0.3128, "lr": 1.0426163038225109e-06, "epoch": 2.7652757078986587, "percentage": 55.31, "elapsed_time": "0:49:14", "remaining_time": "0:39:47", "throughput": 5145.2, "total_tokens": 15200256} {"current_steps": 3712, "total_steps": 6710, "loss": 0.6257, "lr": 1.0420391927042075e-06, "epoch": 2.7660208643815203, "percentage": 55.32, "elapsed_time": "0:49:15", "remaining_time": "0:39:46", "throughput": 5145.2, "total_tokens": 15204352} {"current_steps": 3713, "total_steps": 6710, "loss": 0.448, "lr": 1.0414621271723988e-06, "epoch": 2.7667660208643814, "percentage": 55.34, "elapsed_time": "0:49:15", "remaining_time": "0:39:45", "throughput": 5145.22, "total_tokens": 15208448} {"current_steps": 3714, "total_steps": 6710, "loss": 0.333, "lr": 1.04088510735358e-06, "epoch": 2.767511177347243, "percentage": 55.35, "elapsed_time": "0:49:16", "remaining_time": "0:39:45", "throughput": 5145.25, "total_tokens": 15212544} {"current_steps": 3715, "total_steps": 6710, "loss": 0.4218, "lr": 1.0403081333742393e-06, "epoch": 2.768256333830104, "percentage": 55.37, "elapsed_time": "0:49:17", "remaining_time": "0:39:44", "throughput": 5145.28, "total_tokens": 15216640} {"current_steps": 3716, "total_steps": 6710, "loss": 0.4167, "lr": 1.0397312053608527e-06, "epoch": 2.7690014903129656, "percentage": 55.38, "elapsed_time": "0:49:18", "remaining_time": "0:39:43", "throughput": 5145.31, "total_tokens": 15220736} {"current_steps": 3717, "total_steps": 6710, "loss": 0.6147, "lr": 1.0391543234398879e-06, "epoch": 2.769746646795827, "percentage": 55.39, "elapsed_time": "0:49:18", "remaining_time": "0:39:42", "throughput": 5145.33, "total_tokens": 15224832} {"current_steps": 3718, "total_steps": 6710, "loss": 0.3341, "lr": 1.0385774877378007e-06, "epoch": 2.7704918032786887, "percentage": 55.41, "elapsed_time": "0:49:19", "remaining_time": "0:39:41", "throughput": 5145.36, "total_tokens": 15228928} {"current_steps": 3719, "total_steps": 6710, "loss": 0.5805, "lr": 1.0380006983810378e-06, "epoch": 2.77123695976155, "percentage": 55.42, "elapsed_time": "0:49:20", "remaining_time": "0:39:40", "throughput": 5145.38, "total_tokens": 15233024} {"current_steps": 3720, "total_steps": 6710, "loss": 0.636, "lr": 1.0374239554960356e-06, "epoch": 2.7719821162444114, "percentage": 55.44, "elapsed_time": "0:49:21", "remaining_time": "0:39:40", "throughput": 5145.41, "total_tokens": 15237120} {"current_steps": 3721, "total_steps": 6710, "loss": 0.5232, "lr": 1.0368472592092203e-06, "epoch": 2.7727272727272725, "percentage": 55.45, "elapsed_time": "0:49:22", "remaining_time": "0:39:39", "throughput": 5145.43, "total_tokens": 15241216} {"current_steps": 3722, "total_steps": 6710, "loss": 0.3785, "lr": 1.036270609647008e-06, "epoch": 2.773472429210134, "percentage": 55.47, "elapsed_time": "0:49:22", "remaining_time": "0:39:38", "throughput": 5145.42, "total_tokens": 15245312} {"current_steps": 3723, "total_steps": 6710, "loss": 0.6391, "lr": 1.035694006935804e-06, "epoch": 2.7742175856929956, "percentage": 55.48, "elapsed_time": "0:49:23", "remaining_time": "0:39:37", "throughput": 5145.41, "total_tokens": 15249408} {"current_steps": 3724, "total_steps": 6710, "loss": 0.3755, "lr": 1.0351174512020044e-06, "epoch": 2.774962742175857, "percentage": 55.5, "elapsed_time": "0:49:24", "remaining_time": "0:39:37", "throughput": 5145.41, "total_tokens": 15253504} {"current_steps": 3725, "total_steps": 6710, "loss": 0.4288, "lr": 1.0345409425719934e-06, "epoch": 2.7757078986587183, "percentage": 55.51, "elapsed_time": "0:49:25", "remaining_time": "0:39:36", "throughput": 5145.42, "total_tokens": 15257600} {"current_steps": 3726, "total_steps": 6710, "loss": 0.4494, "lr": 1.0339644811721467e-06, "epoch": 2.77645305514158, "percentage": 55.53, "elapsed_time": "0:49:26", "remaining_time": "0:39:35", "throughput": 5145.4, "total_tokens": 15261696} {"current_steps": 3727, "total_steps": 6710, "loss": 0.289, "lr": 1.0333880671288284e-06, "epoch": 2.777198211624441, "percentage": 55.54, "elapsed_time": "0:49:26", "remaining_time": "0:39:34", "throughput": 5145.42, "total_tokens": 15265792} {"current_steps": 3728, "total_steps": 6710, "loss": 0.5102, "lr": 1.0328117005683921e-06, "epoch": 2.7779433681073025, "percentage": 55.56, "elapsed_time": "0:49:27", "remaining_time": "0:39:33", "throughput": 5145.43, "total_tokens": 15269888} {"current_steps": 3729, "total_steps": 6710, "loss": 0.2461, "lr": 1.032235381617182e-06, "epoch": 2.778688524590164, "percentage": 55.57, "elapsed_time": "0:49:28", "remaining_time": "0:39:33", "throughput": 5145.45, "total_tokens": 15273984} {"current_steps": 3730, "total_steps": 6710, "loss": 0.4598, "lr": 1.0316591104015314e-06, "epoch": 2.7794336810730256, "percentage": 55.59, "elapsed_time": "0:49:29", "remaining_time": "0:39:32", "throughput": 5145.47, "total_tokens": 15278080} {"current_steps": 3731, "total_steps": 6710, "loss": 0.3797, "lr": 1.0310828870477627e-06, "epoch": 2.7801788375558867, "percentage": 55.6, "elapsed_time": "0:49:30", "remaining_time": "0:39:31", "throughput": 5145.48, "total_tokens": 15282176} {"current_steps": 3732, "total_steps": 6710, "loss": 0.3435, "lr": 1.0305067116821885e-06, "epoch": 2.7809239940387482, "percentage": 55.62, "elapsed_time": "0:49:30", "remaining_time": "0:39:30", "throughput": 5145.49, "total_tokens": 15286272} {"current_steps": 3733, "total_steps": 6710, "loss": 0.2807, "lr": 1.0299305844311102e-06, "epoch": 2.7816691505216093, "percentage": 55.63, "elapsed_time": "0:49:31", "remaining_time": "0:39:29", "throughput": 5145.51, "total_tokens": 15290368} {"current_steps": 3734, "total_steps": 6710, "loss": 0.4355, "lr": 1.0293545054208196e-06, "epoch": 2.782414307004471, "percentage": 55.65, "elapsed_time": "0:49:32", "remaining_time": "0:39:28", "throughput": 5145.53, "total_tokens": 15294464} {"current_steps": 3735, "total_steps": 6710, "loss": 0.3442, "lr": 1.0287784747775968e-06, "epoch": 2.7831594634873325, "percentage": 55.66, "elapsed_time": "0:49:33", "remaining_time": "0:39:28", "throughput": 5145.55, "total_tokens": 15298560} {"current_steps": 3736, "total_steps": 6710, "loss": 0.3611, "lr": 1.0282024926277119e-06, "epoch": 2.783904619970194, "percentage": 55.68, "elapsed_time": "0:49:33", "remaining_time": "0:39:27", "throughput": 5145.57, "total_tokens": 15302656} {"current_steps": 3737, "total_steps": 6710, "loss": 0.1518, "lr": 1.0276265590974245e-06, "epoch": 2.784649776453055, "percentage": 55.69, "elapsed_time": "0:49:34", "remaining_time": "0:39:26", "throughput": 5145.59, "total_tokens": 15306752} {"current_steps": 3738, "total_steps": 6710, "loss": 0.7174, "lr": 1.027050674312983e-06, "epoch": 2.7853949329359167, "percentage": 55.71, "elapsed_time": "0:49:35", "remaining_time": "0:39:25", "throughput": 5145.6, "total_tokens": 15310848} {"current_steps": 3739, "total_steps": 6710, "loss": 0.305, "lr": 1.0264748384006259e-06, "epoch": 2.7861400894187778, "percentage": 55.72, "elapsed_time": "0:49:36", "remaining_time": "0:39:24", "throughput": 5145.61, "total_tokens": 15314944} {"current_steps": 3740, "total_steps": 6710, "loss": 0.5918, "lr": 1.0258990514865807e-06, "epoch": 2.7868852459016393, "percentage": 55.74, "elapsed_time": "0:49:37", "remaining_time": "0:39:24", "throughput": 5145.64, "total_tokens": 15319040} {"current_steps": 3741, "total_steps": 6710, "loss": 0.3517, "lr": 1.0253233136970634e-06, "epoch": 2.787630402384501, "percentage": 55.75, "elapsed_time": "0:49:37", "remaining_time": "0:39:23", "throughput": 5145.66, "total_tokens": 15323136} {"current_steps": 3742, "total_steps": 6710, "loss": 0.3903, "lr": 1.0247476251582797e-06, "epoch": 2.788375558867362, "percentage": 55.77, "elapsed_time": "0:49:38", "remaining_time": "0:39:22", "throughput": 5145.68, "total_tokens": 15327232} {"current_steps": 3743, "total_steps": 6710, "loss": 0.4806, "lr": 1.0241719859964252e-06, "epoch": 2.7891207153502235, "percentage": 55.78, "elapsed_time": "0:49:39", "remaining_time": "0:39:21", "throughput": 5145.69, "total_tokens": 15331328} {"current_steps": 3744, "total_steps": 6710, "loss": 0.2539, "lr": 1.023596396337684e-06, "epoch": 2.789865871833085, "percentage": 55.8, "elapsed_time": "0:49:40", "remaining_time": "0:39:20", "throughput": 5145.7, "total_tokens": 15335424} {"current_steps": 3745, "total_steps": 6710, "loss": 0.5189, "lr": 1.0230208563082296e-06, "epoch": 2.790611028315946, "percentage": 55.81, "elapsed_time": "0:49:41", "remaining_time": "0:39:20", "throughput": 5145.7, "total_tokens": 15339520} {"current_steps": 3746, "total_steps": 6710, "loss": 0.4467, "lr": 1.022445366034224e-06, "epoch": 2.7913561847988078, "percentage": 55.83, "elapsed_time": "0:49:41", "remaining_time": "0:39:19", "throughput": 5145.7, "total_tokens": 15343616} {"current_steps": 3747, "total_steps": 6710, "loss": 0.2958, "lr": 1.0218699256418189e-06, "epoch": 2.7921013412816693, "percentage": 55.84, "elapsed_time": "0:49:42", "remaining_time": "0:39:18", "throughput": 5145.73, "total_tokens": 15347712} {"current_steps": 3748, "total_steps": 6710, "loss": 0.3731, "lr": 1.0212945352571552e-06, "epoch": 2.7928464977645304, "percentage": 55.86, "elapsed_time": "0:49:43", "remaining_time": "0:39:17", "throughput": 5145.76, "total_tokens": 15351808} {"current_steps": 3749, "total_steps": 6710, "loss": 0.2077, "lr": 1.0207191950063624e-06, "epoch": 2.793591654247392, "percentage": 55.87, "elapsed_time": "0:49:44", "remaining_time": "0:39:16", "throughput": 5145.79, "total_tokens": 15355904} {"current_steps": 3750, "total_steps": 6710, "loss": 0.4626, "lr": 1.0201439050155595e-06, "epoch": 2.794336810730253, "percentage": 55.89, "elapsed_time": "0:49:44", "remaining_time": "0:39:16", "throughput": 5145.8, "total_tokens": 15360000} {"current_steps": 3751, "total_steps": 6710, "loss": 0.3136, "lr": 1.0195686654108539e-06, "epoch": 2.7950819672131146, "percentage": 55.9, "elapsed_time": "0:49:45", "remaining_time": "0:39:15", "throughput": 5145.81, "total_tokens": 15364096} {"current_steps": 3752, "total_steps": 6710, "loss": 0.3001, "lr": 1.0189934763183422e-06, "epoch": 2.795827123695976, "percentage": 55.92, "elapsed_time": "0:49:46", "remaining_time": "0:39:14", "throughput": 5145.83, "total_tokens": 15368192} {"current_steps": 3753, "total_steps": 6710, "loss": 0.3619, "lr": 1.0184183378641104e-06, "epoch": 2.7965722801788377, "percentage": 55.93, "elapsed_time": "0:49:47", "remaining_time": "0:39:13", "throughput": 5145.83, "total_tokens": 15372288} {"current_steps": 3754, "total_steps": 6710, "loss": 0.35, "lr": 1.0178432501742321e-06, "epoch": 2.797317436661699, "percentage": 55.95, "elapsed_time": "0:49:48", "remaining_time": "0:39:12", "throughput": 5145.85, "total_tokens": 15376384} {"current_steps": 3755, "total_steps": 6710, "loss": 0.5892, "lr": 1.0172682133747716e-06, "epoch": 2.7980625931445604, "percentage": 55.96, "elapsed_time": "0:49:48", "remaining_time": "0:39:12", "throughput": 5145.85, "total_tokens": 15380480} {"current_steps": 3756, "total_steps": 6710, "loss": 0.3075, "lr": 1.01669322759178e-06, "epoch": 2.7988077496274215, "percentage": 55.98, "elapsed_time": "0:49:49", "remaining_time": "0:39:11", "throughput": 5145.83, "total_tokens": 15384576} {"current_steps": 3757, "total_steps": 6710, "loss": 0.4422, "lr": 1.016118292951299e-06, "epoch": 2.799552906110283, "percentage": 55.99, "elapsed_time": "0:49:50", "remaining_time": "0:39:10", "throughput": 5145.83, "total_tokens": 15388672} {"current_steps": 3758, "total_steps": 6710, "loss": 0.2474, "lr": 1.0155434095793583e-06, "epoch": 2.8002980625931446, "percentage": 56.01, "elapsed_time": "0:49:51", "remaining_time": "0:39:09", "throughput": 5145.83, "total_tokens": 15392768} {"current_steps": 3759, "total_steps": 6710, "loss": 0.5926, "lr": 1.0149685776019764e-06, "epoch": 2.801043219076006, "percentage": 56.02, "elapsed_time": "0:49:52", "remaining_time": "0:39:08", "throughput": 5145.83, "total_tokens": 15396864} {"current_steps": 3760, "total_steps": 6710, "loss": 0.3991, "lr": 1.0143937971451607e-06, "epoch": 2.8017883755588673, "percentage": 56.04, "elapsed_time": "0:49:52", "remaining_time": "0:39:08", "throughput": 5145.84, "total_tokens": 15400960} {"current_steps": 3761, "total_steps": 6710, "loss": 0.4812, "lr": 1.0138190683349067e-06, "epoch": 2.802533532041729, "percentage": 56.05, "elapsed_time": "0:49:53", "remaining_time": "0:39:07", "throughput": 5145.85, "total_tokens": 15405056} {"current_steps": 3762, "total_steps": 6710, "loss": 0.1837, "lr": 1.0132443912972e-06, "epoch": 2.80327868852459, "percentage": 56.07, "elapsed_time": "0:49:54", "remaining_time": "0:39:06", "throughput": 5145.86, "total_tokens": 15409152} {"current_steps": 3763, "total_steps": 6710, "loss": 0.353, "lr": 1.0126697661580128e-06, "epoch": 2.8040238450074515, "percentage": 56.08, "elapsed_time": "0:49:55", "remaining_time": "0:39:05", "throughput": 5145.85, "total_tokens": 15413248} {"current_steps": 3764, "total_steps": 6710, "loss": 0.2509, "lr": 1.0120951930433078e-06, "epoch": 2.804769001490313, "percentage": 56.1, "elapsed_time": "0:49:56", "remaining_time": "0:39:04", "throughput": 5145.85, "total_tokens": 15417344} {"current_steps": 3765, "total_steps": 6710, "loss": 0.6222, "lr": 1.0115206720790352e-06, "epoch": 2.8055141579731746, "percentage": 56.11, "elapsed_time": "0:49:56", "remaining_time": "0:39:04", "throughput": 5145.84, "total_tokens": 15421440} {"current_steps": 3766, "total_steps": 6710, "loss": 0.5037, "lr": 1.0109462033911345e-06, "epoch": 2.8062593144560357, "percentage": 56.13, "elapsed_time": "0:49:57", "remaining_time": "0:39:03", "throughput": 5145.84, "total_tokens": 15425536} {"current_steps": 3767, "total_steps": 6710, "loss": 0.4223, "lr": 1.0103717871055326e-06, "epoch": 2.8070044709388973, "percentage": 56.14, "elapsed_time": "0:49:58", "remaining_time": "0:39:02", "throughput": 5145.84, "total_tokens": 15429632} {"current_steps": 3768, "total_steps": 6710, "loss": 0.3531, "lr": 1.0097974233481461e-06, "epoch": 2.8077496274217584, "percentage": 56.15, "elapsed_time": "0:49:59", "remaining_time": "0:39:01", "throughput": 5145.81, "total_tokens": 15433728} {"current_steps": 3769, "total_steps": 6710, "loss": 0.3874, "lr": 1.0092231122448795e-06, "epoch": 2.80849478390462, "percentage": 56.17, "elapsed_time": "0:50:00", "remaining_time": "0:39:00", "throughput": 5145.81, "total_tokens": 15437824} {"current_steps": 3770, "total_steps": 6710, "loss": 0.5173, "lr": 1.008648853921626e-06, "epoch": 2.8092399403874815, "percentage": 56.18, "elapsed_time": "0:50:00", "remaining_time": "0:39:00", "throughput": 5145.82, "total_tokens": 15441920} {"current_steps": 3771, "total_steps": 6710, "loss": 0.4224, "lr": 1.0080746485042674e-06, "epoch": 2.809985096870343, "percentage": 56.2, "elapsed_time": "0:50:01", "remaining_time": "0:38:59", "throughput": 5145.83, "total_tokens": 15446016} {"current_steps": 3772, "total_steps": 6710, "loss": 0.3462, "lr": 1.0075004961186733e-06, "epoch": 2.810730253353204, "percentage": 56.21, "elapsed_time": "0:50:02", "remaining_time": "0:38:58", "throughput": 5145.86, "total_tokens": 15450112} {"current_steps": 3773, "total_steps": 6710, "loss": 0.3825, "lr": 1.006926396890702e-06, "epoch": 2.8114754098360657, "percentage": 56.23, "elapsed_time": "0:50:03", "remaining_time": "0:38:57", "throughput": 5145.89, "total_tokens": 15454208} {"current_steps": 3774, "total_steps": 6710, "loss": 0.4234, "lr": 1.0063523509462001e-06, "epoch": 2.812220566318927, "percentage": 56.24, "elapsed_time": "0:50:03", "remaining_time": "0:38:56", "throughput": 5145.91, "total_tokens": 15458304} {"current_steps": 3775, "total_steps": 6710, "loss": 0.49, "lr": 1.0057783584110026e-06, "epoch": 2.8129657228017884, "percentage": 56.26, "elapsed_time": "0:50:04", "remaining_time": "0:38:56", "throughput": 5145.93, "total_tokens": 15462400} {"current_steps": 3776, "total_steps": 6710, "loss": 0.5334, "lr": 1.005204419410933e-06, "epoch": 2.81371087928465, "percentage": 56.27, "elapsed_time": "0:50:05", "remaining_time": "0:38:55", "throughput": 5145.94, "total_tokens": 15466496} {"current_steps": 3777, "total_steps": 6710, "loss": 0.3545, "lr": 1.0046305340718024e-06, "epoch": 2.814456035767511, "percentage": 56.29, "elapsed_time": "0:50:06", "remaining_time": "0:38:54", "throughput": 5145.95, "total_tokens": 15470592} {"current_steps": 3778, "total_steps": 6710, "loss": 0.2042, "lr": 1.004056702519411e-06, "epoch": 2.8152011922503726, "percentage": 56.3, "elapsed_time": "0:50:07", "remaining_time": "0:38:53", "throughput": 5145.96, "total_tokens": 15474688} {"current_steps": 3779, "total_steps": 6710, "loss": 0.4588, "lr": 1.0034829248795468e-06, "epoch": 2.815946348733234, "percentage": 56.32, "elapsed_time": "0:50:07", "remaining_time": "0:38:52", "throughput": 5145.98, "total_tokens": 15478784} {"current_steps": 3780, "total_steps": 6710, "loss": 0.214, "lr": 1.0029092012779858e-06, "epoch": 2.8166915052160952, "percentage": 56.33, "elapsed_time": "0:50:08", "remaining_time": "0:38:52", "throughput": 5145.96, "total_tokens": 15482880} {"current_steps": 3781, "total_steps": 6710, "loss": 0.701, "lr": 1.0023355318404921e-06, "epoch": 2.817436661698957, "percentage": 56.35, "elapsed_time": "0:50:09", "remaining_time": "0:38:51", "throughput": 5145.98, "total_tokens": 15486976} {"current_steps": 3782, "total_steps": 6710, "loss": 0.4733, "lr": 1.0017619166928185e-06, "epoch": 2.8181818181818183, "percentage": 56.36, "elapsed_time": "0:50:10", "remaining_time": "0:38:50", "throughput": 5146.0, "total_tokens": 15491072} {"current_steps": 3783, "total_steps": 6710, "loss": 0.3842, "lr": 1.001188355960705e-06, "epoch": 2.8189269746646795, "percentage": 56.38, "elapsed_time": "0:50:11", "remaining_time": "0:38:49", "throughput": 5146.03, "total_tokens": 15495168} {"current_steps": 3784, "total_steps": 6710, "loss": 0.2516, "lr": 1.0006148497698807e-06, "epoch": 2.819672131147541, "percentage": 56.39, "elapsed_time": "0:50:11", "remaining_time": "0:38:48", "throughput": 5146.05, "total_tokens": 15499264} {"current_steps": 3785, "total_steps": 6710, "loss": 0.2967, "lr": 1.000041398246062e-06, "epoch": 2.820417287630402, "percentage": 56.41, "elapsed_time": "0:50:12", "remaining_time": "0:38:48", "throughput": 5146.08, "total_tokens": 15503360} {"current_steps": 3786, "total_steps": 6710, "loss": 0.4289, "lr": 9.994680015149537e-07, "epoch": 2.8211624441132637, "percentage": 56.42, "elapsed_time": "0:50:13", "remaining_time": "0:38:47", "throughput": 5146.08, "total_tokens": 15507456} {"current_steps": 3787, "total_steps": 6710, "loss": 0.6655, "lr": 9.988946597022484e-07, "epoch": 2.821907600596125, "percentage": 56.44, "elapsed_time": "0:50:14", "remaining_time": "0:38:46", "throughput": 5146.07, "total_tokens": 15511552} {"current_steps": 3788, "total_steps": 6710, "loss": 0.4919, "lr": 9.983213729336267e-07, "epoch": 2.8226527570789868, "percentage": 56.45, "elapsed_time": "0:50:15", "remaining_time": "0:38:45", "throughput": 5146.06, "total_tokens": 15515648} {"current_steps": 3789, "total_steps": 6710, "loss": 0.5285, "lr": 9.977481413347576e-07, "epoch": 2.823397913561848, "percentage": 56.47, "elapsed_time": "0:50:15", "remaining_time": "0:38:44", "throughput": 5146.05, "total_tokens": 15519744} {"current_steps": 3790, "total_steps": 6710, "loss": 0.4007, "lr": 9.971749650312967e-07, "epoch": 2.8241430700447094, "percentage": 56.48, "elapsed_time": "0:50:16", "remaining_time": "0:38:44", "throughput": 5146.04, "total_tokens": 15523840} {"current_steps": 3791, "total_steps": 6710, "loss": 0.3283, "lr": 9.96601844148889e-07, "epoch": 2.8248882265275705, "percentage": 56.5, "elapsed_time": "0:50:17", "remaining_time": "0:38:43", "throughput": 5146.02, "total_tokens": 15527936} {"current_steps": 3792, "total_steps": 6710, "loss": 0.4471, "lr": 9.960287788131665e-07, "epoch": 2.825633383010432, "percentage": 56.51, "elapsed_time": "0:50:18", "remaining_time": "0:38:42", "throughput": 5146.03, "total_tokens": 15532032} {"current_steps": 3793, "total_steps": 6710, "loss": 0.6394, "lr": 9.954557691497495e-07, "epoch": 2.8263785394932937, "percentage": 56.53, "elapsed_time": "0:50:19", "remaining_time": "0:38:41", "throughput": 5146.03, "total_tokens": 15536128} {"current_steps": 3794, "total_steps": 6710, "loss": 0.3189, "lr": 9.948828152842452e-07, "epoch": 2.827123695976155, "percentage": 56.54, "elapsed_time": "0:50:19", "remaining_time": "0:38:40", "throughput": 5146.04, "total_tokens": 15540224} {"current_steps": 3795, "total_steps": 6710, "loss": 0.2219, "lr": 9.943099173422494e-07, "epoch": 2.8278688524590163, "percentage": 56.56, "elapsed_time": "0:50:20", "remaining_time": "0:38:40", "throughput": 5146.04, "total_tokens": 15544320} {"current_steps": 3796, "total_steps": 6710, "loss": 0.7483, "lr": 9.937370754493455e-07, "epoch": 2.828614008941878, "percentage": 56.57, "elapsed_time": "0:50:21", "remaining_time": "0:38:39", "throughput": 5146.05, "total_tokens": 15548416} {"current_steps": 3797, "total_steps": 6710, "loss": 0.3301, "lr": 9.931642897311044e-07, "epoch": 2.829359165424739, "percentage": 56.59, "elapsed_time": "0:50:22", "remaining_time": "0:38:38", "throughput": 5146.06, "total_tokens": 15552512} {"current_steps": 3798, "total_steps": 6710, "loss": 0.3583, "lr": 9.92591560313085e-07, "epoch": 2.8301043219076005, "percentage": 56.6, "elapsed_time": "0:50:23", "remaining_time": "0:38:37", "throughput": 5146.08, "total_tokens": 15556608} {"current_steps": 3799, "total_steps": 6710, "loss": 0.4338, "lr": 9.920188873208343e-07, "epoch": 2.830849478390462, "percentage": 56.62, "elapsed_time": "0:50:23", "remaining_time": "0:38:36", "throughput": 5146.08, "total_tokens": 15560704} {"current_steps": 3800, "total_steps": 6710, "loss": 0.3258, "lr": 9.91446270879885e-07, "epoch": 2.8315946348733236, "percentage": 56.63, "elapsed_time": "0:50:24", "remaining_time": "0:38:36", "throughput": 5146.08, "total_tokens": 15564800} {"current_steps": 3801, "total_steps": 6710, "loss": 0.5587, "lr": 9.908737111157593e-07, "epoch": 2.8323397913561847, "percentage": 56.65, "elapsed_time": "0:50:25", "remaining_time": "0:38:35", "throughput": 5146.08, "total_tokens": 15568896} {"current_steps": 3802, "total_steps": 6710, "loss": 0.605, "lr": 9.903012081539667e-07, "epoch": 2.8330849478390463, "percentage": 56.66, "elapsed_time": "0:50:26", "remaining_time": "0:38:34", "throughput": 5146.09, "total_tokens": 15572992} {"current_steps": 3803, "total_steps": 6710, "loss": 0.3693, "lr": 9.897287621200036e-07, "epoch": 2.8338301043219074, "percentage": 56.68, "elapsed_time": "0:50:26", "remaining_time": "0:38:33", "throughput": 5146.11, "total_tokens": 15577088} {"current_steps": 3804, "total_steps": 6710, "loss": 0.7225, "lr": 9.891563731393543e-07, "epoch": 2.834575260804769, "percentage": 56.69, "elapsed_time": "0:50:27", "remaining_time": "0:38:32", "throughput": 5146.12, "total_tokens": 15581184} {"current_steps": 3805, "total_steps": 6710, "loss": 0.5215, "lr": 9.885840413374905e-07, "epoch": 2.8353204172876305, "percentage": 56.71, "elapsed_time": "0:50:28", "remaining_time": "0:38:32", "throughput": 5146.13, "total_tokens": 15585280} {"current_steps": 3806, "total_steps": 6710, "loss": 0.1976, "lr": 9.88011766839872e-07, "epoch": 2.836065573770492, "percentage": 56.72, "elapsed_time": "0:50:29", "remaining_time": "0:38:31", "throughput": 5146.14, "total_tokens": 15589376} {"current_steps": 3807, "total_steps": 6710, "loss": 0.2457, "lr": 9.87439549771945e-07, "epoch": 2.836810730253353, "percentage": 56.74, "elapsed_time": "0:50:30", "remaining_time": "0:38:30", "throughput": 5146.15, "total_tokens": 15593472} {"current_steps": 3808, "total_steps": 6710, "loss": 0.2075, "lr": 9.86867390259143e-07, "epoch": 2.8375558867362147, "percentage": 56.75, "elapsed_time": "0:50:30", "remaining_time": "0:38:29", "throughput": 5146.16, "total_tokens": 15597568} {"current_steps": 3809, "total_steps": 6710, "loss": 0.3211, "lr": 9.862952884268886e-07, "epoch": 2.838301043219076, "percentage": 56.77, "elapsed_time": "0:50:31", "remaining_time": "0:38:28", "throughput": 5146.18, "total_tokens": 15601664} {"current_steps": 3810, "total_steps": 6710, "loss": 0.4181, "lr": 9.857232444005894e-07, "epoch": 2.8390461997019374, "percentage": 56.78, "elapsed_time": "0:50:32", "remaining_time": "0:38:28", "throughput": 5146.19, "total_tokens": 15605760} {"current_steps": 3811, "total_steps": 6710, "loss": 0.4443, "lr": 9.851512583056422e-07, "epoch": 2.839791356184799, "percentage": 56.8, "elapsed_time": "0:50:33", "remaining_time": "0:38:27", "throughput": 5146.22, "total_tokens": 15609856} {"current_steps": 3812, "total_steps": 6710, "loss": 0.4768, "lr": 9.845793302674306e-07, "epoch": 2.84053651266766, "percentage": 56.81, "elapsed_time": "0:50:34", "remaining_time": "0:38:26", "throughput": 5146.24, "total_tokens": 15613952} {"current_steps": 3813, "total_steps": 6710, "loss": 0.3111, "lr": 9.84007460411325e-07, "epoch": 2.8412816691505216, "percentage": 56.83, "elapsed_time": "0:50:34", "remaining_time": "0:38:25", "throughput": 5146.27, "total_tokens": 15618048} {"current_steps": 3814, "total_steps": 6710, "loss": 0.3865, "lr": 9.834356488626833e-07, "epoch": 2.842026825633383, "percentage": 56.84, "elapsed_time": "0:50:35", "remaining_time": "0:38:24", "throughput": 5146.29, "total_tokens": 15622144} {"current_steps": 3815, "total_steps": 6710, "loss": 0.5931, "lr": 9.82863895746851e-07, "epoch": 2.8427719821162443, "percentage": 56.86, "elapsed_time": "0:50:36", "remaining_time": "0:38:24", "throughput": 5146.31, "total_tokens": 15626240} {"current_steps": 3816, "total_steps": 6710, "loss": 0.3641, "lr": 9.822922011891603e-07, "epoch": 2.843517138599106, "percentage": 56.87, "elapsed_time": "0:50:37", "remaining_time": "0:38:23", "throughput": 5146.32, "total_tokens": 15630336} {"current_steps": 3817, "total_steps": 6710, "loss": 0.2832, "lr": 9.817205653149307e-07, "epoch": 2.8442622950819674, "percentage": 56.89, "elapsed_time": "0:50:37", "remaining_time": "0:38:22", "throughput": 5146.3, "total_tokens": 15634432} {"current_steps": 3818, "total_steps": 6710, "loss": 0.4036, "lr": 9.811489882494684e-07, "epoch": 2.8450074515648285, "percentage": 56.9, "elapsed_time": "0:50:38", "remaining_time": "0:38:21", "throughput": 5146.29, "total_tokens": 15638528} {"current_steps": 3819, "total_steps": 6710, "loss": 0.57, "lr": 9.805774701180681e-07, "epoch": 2.84575260804769, "percentage": 56.92, "elapsed_time": "0:50:39", "remaining_time": "0:38:20", "throughput": 5146.31, "total_tokens": 15642624} {"current_steps": 3820, "total_steps": 6710, "loss": 0.3099, "lr": 9.800060110460104e-07, "epoch": 2.846497764530551, "percentage": 56.93, "elapsed_time": "0:50:40", "remaining_time": "0:38:20", "throughput": 5146.32, "total_tokens": 15646720} {"current_steps": 3821, "total_steps": 6710, "loss": 0.4878, "lr": 9.794346111585628e-07, "epoch": 2.8472429210134127, "percentage": 56.94, "elapsed_time": "0:50:41", "remaining_time": "0:38:19", "throughput": 5146.33, "total_tokens": 15650816} {"current_steps": 3822, "total_steps": 6710, "loss": 0.3675, "lr": 9.788632705809803e-07, "epoch": 2.8479880774962743, "percentage": 56.96, "elapsed_time": "0:50:41", "remaining_time": "0:38:18", "throughput": 5146.35, "total_tokens": 15654912} {"current_steps": 3823, "total_steps": 6710, "loss": 0.3497, "lr": 9.782919894385052e-07, "epoch": 2.848733233979136, "percentage": 56.97, "elapsed_time": "0:50:42", "remaining_time": "0:38:17", "throughput": 5146.36, "total_tokens": 15659008} {"current_steps": 3824, "total_steps": 6710, "loss": 0.3822, "lr": 9.777207678563658e-07, "epoch": 2.849478390461997, "percentage": 56.99, "elapsed_time": "0:50:43", "remaining_time": "0:38:16", "throughput": 5146.37, "total_tokens": 15663104} {"current_steps": 3825, "total_steps": 6710, "loss": 0.504, "lr": 9.771496059597785e-07, "epoch": 2.8502235469448585, "percentage": 57.0, "elapsed_time": "0:50:44", "remaining_time": "0:38:16", "throughput": 5146.38, "total_tokens": 15667200} {"current_steps": 3826, "total_steps": 6710, "loss": 0.2688, "lr": 9.76578503873946e-07, "epoch": 2.8509687034277196, "percentage": 57.02, "elapsed_time": "0:50:45", "remaining_time": "0:38:15", "throughput": 5146.4, "total_tokens": 15671296} {"current_steps": 3827, "total_steps": 6710, "loss": 0.2319, "lr": 9.760074617240579e-07, "epoch": 2.851713859910581, "percentage": 57.03, "elapsed_time": "0:50:45", "remaining_time": "0:38:14", "throughput": 5146.4, "total_tokens": 15675392} {"current_steps": 3828, "total_steps": 6710, "loss": 0.6592, "lr": 9.754364796352905e-07, "epoch": 2.8524590163934427, "percentage": 57.05, "elapsed_time": "0:50:46", "remaining_time": "0:38:13", "throughput": 5146.4, "total_tokens": 15679488} {"current_steps": 3829, "total_steps": 6710, "loss": 0.5338, "lr": 9.748655577328075e-07, "epoch": 2.8532041728763042, "percentage": 57.06, "elapsed_time": "0:50:47", "remaining_time": "0:38:12", "throughput": 5146.41, "total_tokens": 15683584} {"current_steps": 3830, "total_steps": 6710, "loss": 0.4517, "lr": 9.742946961417588e-07, "epoch": 2.8539493293591653, "percentage": 57.08, "elapsed_time": "0:50:48", "remaining_time": "0:38:12", "throughput": 5146.43, "total_tokens": 15687680} {"current_steps": 3831, "total_steps": 6710, "loss": 0.3264, "lr": 9.737238949872812e-07, "epoch": 2.854694485842027, "percentage": 57.09, "elapsed_time": "0:50:49", "remaining_time": "0:38:11", "throughput": 5146.44, "total_tokens": 15691776} {"current_steps": 3832, "total_steps": 6710, "loss": 0.7114, "lr": 9.731531543944988e-07, "epoch": 2.855439642324888, "percentage": 57.11, "elapsed_time": "0:50:49", "remaining_time": "0:38:10", "throughput": 5146.45, "total_tokens": 15695872} {"current_steps": 3833, "total_steps": 6710, "loss": 0.3614, "lr": 9.725824744885218e-07, "epoch": 2.8561847988077496, "percentage": 57.12, "elapsed_time": "0:50:50", "remaining_time": "0:38:09", "throughput": 5146.46, "total_tokens": 15699968} {"current_steps": 3834, "total_steps": 6710, "loss": 0.1757, "lr": 9.720118553944479e-07, "epoch": 2.856929955290611, "percentage": 57.14, "elapsed_time": "0:50:51", "remaining_time": "0:38:08", "throughput": 5146.46, "total_tokens": 15704064} {"current_steps": 3835, "total_steps": 6710, "loss": 0.52, "lr": 9.714412972373597e-07, "epoch": 2.8576751117734727, "percentage": 57.15, "elapsed_time": "0:50:52", "remaining_time": "0:38:08", "throughput": 5146.44, "total_tokens": 15708160} {"current_steps": 3836, "total_steps": 6710, "loss": 0.3471, "lr": 9.70870800142328e-07, "epoch": 2.8584202682563338, "percentage": 57.17, "elapsed_time": "0:50:53", "remaining_time": "0:38:07", "throughput": 5146.42, "total_tokens": 15712256} {"current_steps": 3837, "total_steps": 6710, "loss": 0.3156, "lr": 9.703003642344108e-07, "epoch": 2.8591654247391953, "percentage": 57.18, "elapsed_time": "0:50:53", "remaining_time": "0:38:06", "throughput": 5146.41, "total_tokens": 15716352} {"current_steps": 3838, "total_steps": 6710, "loss": 0.4504, "lr": 9.697299896386506e-07, "epoch": 2.8599105812220564, "percentage": 57.2, "elapsed_time": "0:50:54", "remaining_time": "0:38:05", "throughput": 5146.41, "total_tokens": 15720448} {"current_steps": 3839, "total_steps": 6710, "loss": 0.5673, "lr": 9.69159676480078e-07, "epoch": 2.860655737704918, "percentage": 57.21, "elapsed_time": "0:50:55", "remaining_time": "0:38:05", "throughput": 5146.4, "total_tokens": 15724544} {"current_steps": 3840, "total_steps": 6710, "loss": 0.6748, "lr": 9.685894248837094e-07, "epoch": 2.8614008941877795, "percentage": 57.23, "elapsed_time": "0:50:56", "remaining_time": "0:38:04", "throughput": 5146.42, "total_tokens": 15728640} {"current_steps": 3841, "total_steps": 6710, "loss": 0.4101, "lr": 9.680192349745484e-07, "epoch": 2.862146050670641, "percentage": 57.24, "elapsed_time": "0:50:57", "remaining_time": "0:38:03", "throughput": 5146.45, "total_tokens": 15732736} {"current_steps": 3842, "total_steps": 6710, "loss": 0.514, "lr": 9.674491068775849e-07, "epoch": 2.862891207153502, "percentage": 57.26, "elapsed_time": "0:50:57", "remaining_time": "0:38:02", "throughput": 5146.47, "total_tokens": 15736832} {"current_steps": 3843, "total_steps": 6710, "loss": 0.5623, "lr": 9.668790407177944e-07, "epoch": 2.8636363636363638, "percentage": 57.27, "elapsed_time": "0:50:58", "remaining_time": "0:38:01", "throughput": 5146.5, "total_tokens": 15740928} {"current_steps": 3844, "total_steps": 6710, "loss": 0.5269, "lr": 9.663090366201405e-07, "epoch": 2.864381520119225, "percentage": 57.29, "elapsed_time": "0:50:59", "remaining_time": "0:38:00", "throughput": 5146.51, "total_tokens": 15745024} {"current_steps": 3845, "total_steps": 6710, "loss": 0.5656, "lr": 9.657390947095708e-07, "epoch": 2.8651266766020864, "percentage": 57.3, "elapsed_time": "0:51:00", "remaining_time": "0:38:00", "throughput": 5146.53, "total_tokens": 15749120} {"current_steps": 3846, "total_steps": 6710, "loss": 0.4875, "lr": 9.651692151110218e-07, "epoch": 2.865871833084948, "percentage": 57.32, "elapsed_time": "0:51:00", "remaining_time": "0:37:59", "throughput": 5146.55, "total_tokens": 15753216} {"current_steps": 3847, "total_steps": 6710, "loss": 0.2065, "lr": 9.64599397949415e-07, "epoch": 2.866616989567809, "percentage": 57.33, "elapsed_time": "0:51:01", "remaining_time": "0:37:58", "throughput": 5146.55, "total_tokens": 15757312} {"current_steps": 3848, "total_steps": 6710, "loss": 0.2014, "lr": 9.640296433496576e-07, "epoch": 2.8673621460506706, "percentage": 57.35, "elapsed_time": "0:51:02", "remaining_time": "0:37:57", "throughput": 5146.55, "total_tokens": 15761408} {"current_steps": 3849, "total_steps": 6710, "loss": 0.212, "lr": 9.634599514366445e-07, "epoch": 2.868107302533532, "percentage": 57.36, "elapsed_time": "0:51:03", "remaining_time": "0:37:56", "throughput": 5146.55, "total_tokens": 15765504} {"current_steps": 3850, "total_steps": 6710, "loss": 0.438, "lr": 9.628903223352558e-07, "epoch": 2.8688524590163933, "percentage": 57.38, "elapsed_time": "0:51:04", "remaining_time": "0:37:56", "throughput": 5146.54, "total_tokens": 15769600} {"current_steps": 3851, "total_steps": 6710, "loss": 0.3717, "lr": 9.623207561703589e-07, "epoch": 2.869597615499255, "percentage": 57.39, "elapsed_time": "0:51:04", "remaining_time": "0:37:55", "throughput": 5146.53, "total_tokens": 15773696} {"current_steps": 3852, "total_steps": 6710, "loss": 0.4552, "lr": 9.617512530668063e-07, "epoch": 2.8703427719821164, "percentage": 57.41, "elapsed_time": "0:51:05", "remaining_time": "0:37:54", "throughput": 5146.55, "total_tokens": 15777792} {"current_steps": 3853, "total_steps": 6710, "loss": 0.3054, "lr": 9.611818131494374e-07, "epoch": 2.8710879284649775, "percentage": 57.42, "elapsed_time": "0:51:06", "remaining_time": "0:37:53", "throughput": 5146.56, "total_tokens": 15781888} {"current_steps": 3854, "total_steps": 6710, "loss": 0.2579, "lr": 9.606124365430777e-07, "epoch": 2.871833084947839, "percentage": 57.44, "elapsed_time": "0:51:07", "remaining_time": "0:37:53", "throughput": 5146.57, "total_tokens": 15785984} {"current_steps": 3855, "total_steps": 6710, "loss": 0.4851, "lr": 9.60043123372538e-07, "epoch": 2.8725782414307, "percentage": 57.45, "elapsed_time": "0:51:08", "remaining_time": "0:37:52", "throughput": 5146.55, "total_tokens": 15790080} {"current_steps": 3856, "total_steps": 6710, "loss": 0.3642, "lr": 9.59473873762616e-07, "epoch": 2.8733233979135617, "percentage": 57.47, "elapsed_time": "0:51:08", "remaining_time": "0:37:51", "throughput": 5146.55, "total_tokens": 15794176} {"current_steps": 3857, "total_steps": 6710, "loss": 0.3599, "lr": 9.589046878380957e-07, "epoch": 2.8740685543964233, "percentage": 57.48, "elapsed_time": "0:51:09", "remaining_time": "0:37:50", "throughput": 5146.56, "total_tokens": 15798272} {"current_steps": 3858, "total_steps": 6710, "loss": 0.356, "lr": 9.583355657237462e-07, "epoch": 2.874813710879285, "percentage": 57.5, "elapsed_time": "0:51:10", "remaining_time": "0:37:49", "throughput": 5146.56, "total_tokens": 15802368} {"current_steps": 3859, "total_steps": 6710, "loss": 0.4969, "lr": 9.577665075443234e-07, "epoch": 2.875558867362146, "percentage": 57.51, "elapsed_time": "0:51:11", "remaining_time": "0:37:49", "throughput": 5146.58, "total_tokens": 15806464} {"current_steps": 3860, "total_steps": 6710, "loss": 0.5609, "lr": 9.57197513424569e-07, "epoch": 2.8763040238450075, "percentage": 57.53, "elapsed_time": "0:51:12", "remaining_time": "0:37:48", "throughput": 5146.58, "total_tokens": 15810560} {"current_steps": 3861, "total_steps": 6710, "loss": 0.5185, "lr": 9.566285834892108e-07, "epoch": 2.8770491803278686, "percentage": 57.54, "elapsed_time": "0:51:12", "remaining_time": "0:37:47", "throughput": 5146.59, "total_tokens": 15814656} {"current_steps": 3862, "total_steps": 6710, "loss": 0.4096, "lr": 9.560597178629615e-07, "epoch": 2.87779433681073, "percentage": 57.56, "elapsed_time": "0:51:13", "remaining_time": "0:37:46", "throughput": 5146.57, "total_tokens": 15818752} {"current_steps": 3863, "total_steps": 6710, "loss": 0.439, "lr": 9.55490916670521e-07, "epoch": 2.8785394932935917, "percentage": 57.57, "elapsed_time": "0:51:14", "remaining_time": "0:37:45", "throughput": 5146.57, "total_tokens": 15822848} {"current_steps": 3864, "total_steps": 6710, "loss": 0.3444, "lr": 9.54922180036575e-07, "epoch": 2.8792846497764533, "percentage": 57.59, "elapsed_time": "0:51:15", "remaining_time": "0:37:45", "throughput": 5146.59, "total_tokens": 15826944} {"current_steps": 3865, "total_steps": 6710, "loss": 0.4767, "lr": 9.543535080857937e-07, "epoch": 2.8800298062593144, "percentage": 57.6, "elapsed_time": "0:51:16", "remaining_time": "0:37:44", "throughput": 5146.61, "total_tokens": 15831040} {"current_steps": 3866, "total_steps": 6710, "loss": 0.4757, "lr": 9.537849009428346e-07, "epoch": 2.880774962742176, "percentage": 57.62, "elapsed_time": "0:51:16", "remaining_time": "0:37:43", "throughput": 5146.61, "total_tokens": 15835136} {"current_steps": 3867, "total_steps": 6710, "loss": 0.313, "lr": 9.532163587323403e-07, "epoch": 2.881520119225037, "percentage": 57.63, "elapsed_time": "0:51:17", "remaining_time": "0:37:42", "throughput": 5146.61, "total_tokens": 15839232} {"current_steps": 3868, "total_steps": 6710, "loss": 0.328, "lr": 9.526478815789394e-07, "epoch": 2.8822652757078986, "percentage": 57.65, "elapsed_time": "0:51:18", "remaining_time": "0:37:41", "throughput": 5146.62, "total_tokens": 15843328} {"current_steps": 3869, "total_steps": 6710, "loss": 0.1241, "lr": 9.520794696072462e-07, "epoch": 2.88301043219076, "percentage": 57.66, "elapsed_time": "0:51:19", "remaining_time": "0:37:41", "throughput": 5146.63, "total_tokens": 15847424} {"current_steps": 3870, "total_steps": 6710, "loss": 0.1963, "lr": 9.515111229418605e-07, "epoch": 2.8837555886736217, "percentage": 57.68, "elapsed_time": "0:51:19", "remaining_time": "0:37:40", "throughput": 5146.65, "total_tokens": 15851520} {"current_steps": 3871, "total_steps": 6710, "loss": 0.4773, "lr": 9.509428417073685e-07, "epoch": 2.884500745156483, "percentage": 57.69, "elapsed_time": "0:51:20", "remaining_time": "0:37:39", "throughput": 5146.67, "total_tokens": 15855616} {"current_steps": 3872, "total_steps": 6710, "loss": 0.4135, "lr": 9.503746260283407e-07, "epoch": 2.8852459016393444, "percentage": 57.7, "elapsed_time": "0:51:21", "remaining_time": "0:37:38", "throughput": 5146.69, "total_tokens": 15859712} {"current_steps": 3873, "total_steps": 6710, "loss": 0.1512, "lr": 9.498064760293343e-07, "epoch": 2.8859910581222055, "percentage": 57.72, "elapsed_time": "0:51:22", "remaining_time": "0:37:37", "throughput": 5146.72, "total_tokens": 15863808} {"current_steps": 3874, "total_steps": 6710, "loss": 0.5241, "lr": 9.492383918348927e-07, "epoch": 2.886736214605067, "percentage": 57.73, "elapsed_time": "0:51:23", "remaining_time": "0:37:37", "throughput": 5146.75, "total_tokens": 15867904} {"current_steps": 3875, "total_steps": 6710, "loss": 0.2842, "lr": 9.486703735695424e-07, "epoch": 2.8874813710879286, "percentage": 57.75, "elapsed_time": "0:51:23", "remaining_time": "0:37:36", "throughput": 5146.77, "total_tokens": 15872000} {"current_steps": 3876, "total_steps": 6710, "loss": 0.1196, "lr": 9.481024213577981e-07, "epoch": 2.88822652757079, "percentage": 57.76, "elapsed_time": "0:51:24", "remaining_time": "0:37:35", "throughput": 5146.79, "total_tokens": 15876096} {"current_steps": 3877, "total_steps": 6710, "loss": 0.4437, "lr": 9.475345353241587e-07, "epoch": 2.8889716840536512, "percentage": 57.78, "elapsed_time": "0:51:25", "remaining_time": "0:37:34", "throughput": 5146.82, "total_tokens": 15880192} {"current_steps": 3878, "total_steps": 6710, "loss": 0.3483, "lr": 9.46966715593109e-07, "epoch": 2.889716840536513, "percentage": 57.79, "elapsed_time": "0:51:26", "remaining_time": "0:37:33", "throughput": 5146.82, "total_tokens": 15884288} {"current_steps": 3879, "total_steps": 6710, "loss": 0.5052, "lr": 9.463989622891191e-07, "epoch": 2.890461997019374, "percentage": 57.81, "elapsed_time": "0:51:27", "remaining_time": "0:37:32", "throughput": 5146.83, "total_tokens": 15888384} {"current_steps": 3880, "total_steps": 6710, "loss": 0.2268, "lr": 9.458312755366446e-07, "epoch": 2.8912071535022354, "percentage": 57.82, "elapsed_time": "0:51:27", "remaining_time": "0:37:32", "throughput": 5146.84, "total_tokens": 15892480} {"current_steps": 3881, "total_steps": 6710, "loss": 0.2962, "lr": 9.452636554601266e-07, "epoch": 2.891952309985097, "percentage": 57.84, "elapsed_time": "0:51:28", "remaining_time": "0:37:31", "throughput": 5146.85, "total_tokens": 15896576} {"current_steps": 3882, "total_steps": 6710, "loss": 0.433, "lr": 9.446961021839912e-07, "epoch": 2.892697466467958, "percentage": 57.85, "elapsed_time": "0:51:29", "remaining_time": "0:37:30", "throughput": 5146.86, "total_tokens": 15900672} {"current_steps": 3883, "total_steps": 6710, "loss": 0.5564, "lr": 9.441286158326501e-07, "epoch": 2.8934426229508197, "percentage": 57.87, "elapsed_time": "0:51:30", "remaining_time": "0:37:29", "throughput": 5146.88, "total_tokens": 15904768} {"current_steps": 3884, "total_steps": 6710, "loss": 0.2152, "lr": 9.435611965305007e-07, "epoch": 2.894187779433681, "percentage": 57.88, "elapsed_time": "0:51:30", "remaining_time": "0:37:28", "throughput": 5146.9, "total_tokens": 15908864} {"current_steps": 3885, "total_steps": 6710, "loss": 0.3137, "lr": 9.429938444019252e-07, "epoch": 2.8949329359165423, "percentage": 57.9, "elapsed_time": "0:51:31", "remaining_time": "0:37:28", "throughput": 5146.92, "total_tokens": 15912960} {"current_steps": 3886, "total_steps": 6710, "loss": 0.447, "lr": 9.424265595712912e-07, "epoch": 2.895678092399404, "percentage": 57.91, "elapsed_time": "0:51:32", "remaining_time": "0:37:27", "throughput": 5146.94, "total_tokens": 15917056} {"current_steps": 3887, "total_steps": 6710, "loss": 0.4268, "lr": 9.418593421629514e-07, "epoch": 2.8964232488822654, "percentage": 57.93, "elapsed_time": "0:51:33", "remaining_time": "0:37:26", "throughput": 5146.94, "total_tokens": 15921152} {"current_steps": 3888, "total_steps": 6710, "loss": 0.4339, "lr": 9.412921923012449e-07, "epoch": 2.8971684053651265, "percentage": 57.94, "elapsed_time": "0:51:34", "remaining_time": "0:37:25", "throughput": 5146.96, "total_tokens": 15925248} {"current_steps": 3889, "total_steps": 6710, "loss": 0.5682, "lr": 9.407251101104936e-07, "epoch": 2.897913561847988, "percentage": 57.96, "elapsed_time": "0:51:34", "remaining_time": "0:37:24", "throughput": 5146.98, "total_tokens": 15929344} {"current_steps": 3890, "total_steps": 6710, "loss": 0.3352, "lr": 9.401580957150065e-07, "epoch": 2.898658718330849, "percentage": 57.97, "elapsed_time": "0:51:35", "remaining_time": "0:37:24", "throughput": 5147.01, "total_tokens": 15933440} {"current_steps": 3891, "total_steps": 6710, "loss": 0.563, "lr": 9.395911492390777e-07, "epoch": 2.8994038748137108, "percentage": 57.99, "elapsed_time": "0:51:36", "remaining_time": "0:37:23", "throughput": 5147.03, "total_tokens": 15937536} {"current_steps": 3892, "total_steps": 6710, "loss": 0.512, "lr": 9.390242708069852e-07, "epoch": 2.9001490312965723, "percentage": 58.0, "elapsed_time": "0:51:37", "remaining_time": "0:37:22", "throughput": 5147.02, "total_tokens": 15941632} {"current_steps": 3893, "total_steps": 6710, "loss": 0.2136, "lr": 9.384574605429931e-07, "epoch": 2.900894187779434, "percentage": 58.02, "elapsed_time": "0:51:38", "remaining_time": "0:37:21", "throughput": 5147.03, "total_tokens": 15945728} {"current_steps": 3894, "total_steps": 6710, "loss": 0.3915, "lr": 9.378907185713501e-07, "epoch": 2.901639344262295, "percentage": 58.03, "elapsed_time": "0:51:38", "remaining_time": "0:37:20", "throughput": 5147.02, "total_tokens": 15949824} {"current_steps": 3895, "total_steps": 6710, "loss": 0.324, "lr": 9.373240450162904e-07, "epoch": 2.9023845007451565, "percentage": 58.05, "elapsed_time": "0:51:39", "remaining_time": "0:37:20", "throughput": 5147.02, "total_tokens": 15953920} {"current_steps": 3896, "total_steps": 6710, "loss": 0.4175, "lr": 9.367574400020326e-07, "epoch": 2.9031296572280176, "percentage": 58.06, "elapsed_time": "0:51:40", "remaining_time": "0:37:19", "throughput": 5147.03, "total_tokens": 15958016} {"current_steps": 3897, "total_steps": 6710, "loss": 0.3929, "lr": 9.36190903652781e-07, "epoch": 2.903874813710879, "percentage": 58.08, "elapsed_time": "0:51:41", "remaining_time": "0:37:18", "throughput": 5147.04, "total_tokens": 15962112} {"current_steps": 3898, "total_steps": 6710, "loss": 0.559, "lr": 9.356244360927242e-07, "epoch": 2.9046199701937407, "percentage": 58.09, "elapsed_time": "0:51:42", "remaining_time": "0:37:17", "throughput": 5147.05, "total_tokens": 15966208} {"current_steps": 3899, "total_steps": 6710, "loss": 0.5031, "lr": 9.350580374460356e-07, "epoch": 2.9053651266766023, "percentage": 58.11, "elapsed_time": "0:51:42", "remaining_time": "0:37:16", "throughput": 5147.06, "total_tokens": 15970304} {"current_steps": 3900, "total_steps": 6710, "loss": 0.2498, "lr": 9.344917078368742e-07, "epoch": 2.9061102831594634, "percentage": 58.12, "elapsed_time": "0:51:43", "remaining_time": "0:37:16", "throughput": 5147.04, "total_tokens": 15974400} {"current_steps": 3901, "total_steps": 6710, "loss": 0.3397, "lr": 9.339254473893837e-07, "epoch": 2.906855439642325, "percentage": 58.14, "elapsed_time": "0:51:44", "remaining_time": "0:37:15", "throughput": 5147.05, "total_tokens": 15978496} {"current_steps": 3902, "total_steps": 6710, "loss": 0.4586, "lr": 9.333592562276916e-07, "epoch": 2.907600596125186, "percentage": 58.15, "elapsed_time": "0:51:45", "remaining_time": "0:37:14", "throughput": 5147.06, "total_tokens": 15982592} {"current_steps": 3903, "total_steps": 6710, "loss": 0.2969, "lr": 9.327931344759117e-07, "epoch": 2.9083457526080476, "percentage": 58.17, "elapsed_time": "0:51:45", "remaining_time": "0:37:13", "throughput": 5147.08, "total_tokens": 15986688} {"current_steps": 3904, "total_steps": 6710, "loss": 0.4999, "lr": 9.322270822581417e-07, "epoch": 2.909090909090909, "percentage": 58.18, "elapsed_time": "0:51:46", "remaining_time": "0:37:12", "throughput": 5147.11, "total_tokens": 15990784} {"current_steps": 3905, "total_steps": 6710, "loss": 0.3503, "lr": 9.316610996984643e-07, "epoch": 2.9098360655737707, "percentage": 58.2, "elapsed_time": "0:51:47", "remaining_time": "0:37:12", "throughput": 5147.13, "total_tokens": 15994880} {"current_steps": 3906, "total_steps": 6710, "loss": 0.2671, "lr": 9.310951869209469e-07, "epoch": 2.910581222056632, "percentage": 58.21, "elapsed_time": "0:51:48", "remaining_time": "0:37:11", "throughput": 5147.16, "total_tokens": 15998976} {"current_steps": 3907, "total_steps": 6710, "loss": 0.3342, "lr": 9.30529344049642e-07, "epoch": 2.9113263785394934, "percentage": 58.23, "elapsed_time": "0:51:49", "remaining_time": "0:37:10", "throughput": 5147.18, "total_tokens": 16003072} {"current_steps": 3908, "total_steps": 6710, "loss": 0.3142, "lr": 9.299635712085863e-07, "epoch": 2.9120715350223545, "percentage": 58.24, "elapsed_time": "0:51:49", "remaining_time": "0:37:09", "throughput": 5147.18, "total_tokens": 16007168} {"current_steps": 3909, "total_steps": 6710, "loss": 0.2498, "lr": 9.293978685218007e-07, "epoch": 2.912816691505216, "percentage": 58.26, "elapsed_time": "0:51:50", "remaining_time": "0:37:08", "throughput": 5147.2, "total_tokens": 16011264} {"current_steps": 3910, "total_steps": 6710, "loss": 0.5198, "lr": 9.288322361132917e-07, "epoch": 2.9135618479880776, "percentage": 58.27, "elapsed_time": "0:51:51", "remaining_time": "0:37:08", "throughput": 5147.21, "total_tokens": 16015360} {"current_steps": 3911, "total_steps": 6710, "loss": 0.3844, "lr": 9.282666741070498e-07, "epoch": 2.914307004470939, "percentage": 58.29, "elapsed_time": "0:51:52", "remaining_time": "0:37:07", "throughput": 5147.19, "total_tokens": 16019456} {"current_steps": 3912, "total_steps": 6710, "loss": 0.269, "lr": 9.277011826270503e-07, "epoch": 2.9150521609538003, "percentage": 58.3, "elapsed_time": "0:51:53", "remaining_time": "0:37:06", "throughput": 5147.2, "total_tokens": 16023552} {"current_steps": 3913, "total_steps": 6710, "loss": 0.3105, "lr": 9.27135761797253e-07, "epoch": 2.915797317436662, "percentage": 58.32, "elapsed_time": "0:51:53", "remaining_time": "0:37:05", "throughput": 5147.2, "total_tokens": 16027648} {"current_steps": 3914, "total_steps": 6710, "loss": 0.4605, "lr": 9.265704117416022e-07, "epoch": 2.916542473919523, "percentage": 58.33, "elapsed_time": "0:51:54", "remaining_time": "0:37:04", "throughput": 5147.19, "total_tokens": 16031744} {"current_steps": 3915, "total_steps": 6710, "loss": 0.4565, "lr": 9.260051325840272e-07, "epoch": 2.9172876304023845, "percentage": 58.35, "elapsed_time": "0:51:55", "remaining_time": "0:37:04", "throughput": 5147.2, "total_tokens": 16035840} {"current_steps": 3916, "total_steps": 6710, "loss": 0.5665, "lr": 9.254399244484403e-07, "epoch": 2.918032786885246, "percentage": 58.36, "elapsed_time": "0:51:56", "remaining_time": "0:37:03", "throughput": 5147.22, "total_tokens": 16039936} {"current_steps": 3917, "total_steps": 6710, "loss": 0.5082, "lr": 9.248747874587391e-07, "epoch": 2.918777943368107, "percentage": 58.38, "elapsed_time": "0:51:57", "remaining_time": "0:37:02", "throughput": 5147.22, "total_tokens": 16044032} {"current_steps": 3918, "total_steps": 6710, "loss": 0.4132, "lr": 9.243097217388064e-07, "epoch": 2.9195230998509687, "percentage": 58.39, "elapsed_time": "0:51:57", "remaining_time": "0:37:01", "throughput": 5147.22, "total_tokens": 16048128} {"current_steps": 3919, "total_steps": 6710, "loss": 0.4195, "lr": 9.237447274125086e-07, "epoch": 2.9202682563338302, "percentage": 58.41, "elapsed_time": "0:51:58", "remaining_time": "0:37:00", "throughput": 5147.22, "total_tokens": 16052224} {"current_steps": 3920, "total_steps": 6710, "loss": 0.3878, "lr": 9.231798046036957e-07, "epoch": 2.9210134128166914, "percentage": 58.42, "elapsed_time": "0:51:59", "remaining_time": "0:37:00", "throughput": 5147.22, "total_tokens": 16056320} {"current_steps": 3921, "total_steps": 6710, "loss": 0.2668, "lr": 9.226149534362036e-07, "epoch": 2.921758569299553, "percentage": 58.44, "elapsed_time": "0:52:00", "remaining_time": "0:36:59", "throughput": 5147.22, "total_tokens": 16060416} {"current_steps": 3922, "total_steps": 6710, "loss": 0.3606, "lr": 9.220501740338514e-07, "epoch": 2.9225037257824145, "percentage": 58.45, "elapsed_time": "0:52:01", "remaining_time": "0:36:58", "throughput": 5147.22, "total_tokens": 16064512} {"current_steps": 3923, "total_steps": 6710, "loss": 0.5495, "lr": 9.214854665204429e-07, "epoch": 2.9232488822652756, "percentage": 58.46, "elapsed_time": "0:52:01", "remaining_time": "0:36:57", "throughput": 5147.23, "total_tokens": 16068608} {"current_steps": 3924, "total_steps": 6710, "loss": 0.5886, "lr": 9.209208310197656e-07, "epoch": 2.923994038748137, "percentage": 58.48, "elapsed_time": "0:52:02", "remaining_time": "0:36:57", "throughput": 5147.25, "total_tokens": 16072704} {"current_steps": 3925, "total_steps": 6710, "loss": 0.5362, "lr": 9.203562676555923e-07, "epoch": 2.9247391952309982, "percentage": 58.49, "elapsed_time": "0:52:03", "remaining_time": "0:36:56", "throughput": 5147.22, "total_tokens": 16076800} {"current_steps": 3926, "total_steps": 6710, "loss": 0.4718, "lr": 9.197917765516792e-07, "epoch": 2.92548435171386, "percentage": 58.51, "elapsed_time": "0:52:04", "remaining_time": "0:36:55", "throughput": 5147.19, "total_tokens": 16080896} {"current_steps": 3927, "total_steps": 6710, "loss": 0.2384, "lr": 9.192273578317662e-07, "epoch": 2.9262295081967213, "percentage": 58.52, "elapsed_time": "0:52:05", "remaining_time": "0:36:54", "throughput": 5147.18, "total_tokens": 16084992} {"current_steps": 3928, "total_steps": 6710, "loss": 0.501, "lr": 9.186630116195787e-07, "epoch": 2.926974664679583, "percentage": 58.54, "elapsed_time": "0:52:05", "remaining_time": "0:36:53", "throughput": 5147.2, "total_tokens": 16089088} {"current_steps": 3929, "total_steps": 6710, "loss": 0.4351, "lr": 9.180987380388249e-07, "epoch": 2.927719821162444, "percentage": 58.55, "elapsed_time": "0:52:06", "remaining_time": "0:36:53", "throughput": 5147.2, "total_tokens": 16093184} {"current_steps": 3930, "total_steps": 6710, "loss": 0.4049, "lr": 9.175345372131975e-07, "epoch": 2.9284649776453056, "percentage": 58.57, "elapsed_time": "0:52:07", "remaining_time": "0:36:52", "throughput": 5147.21, "total_tokens": 16097280} {"current_steps": 3931, "total_steps": 6710, "loss": 0.262, "lr": 9.169704092663736e-07, "epoch": 2.9292101341281667, "percentage": 58.58, "elapsed_time": "0:52:08", "remaining_time": "0:36:51", "throughput": 5147.2, "total_tokens": 16101376} {"current_steps": 3932, "total_steps": 6710, "loss": 0.44, "lr": 9.164063543220139e-07, "epoch": 2.929955290611028, "percentage": 58.6, "elapsed_time": "0:52:08", "remaining_time": "0:36:50", "throughput": 5147.19, "total_tokens": 16105472} {"current_steps": 3933, "total_steps": 6710, "loss": 0.3806, "lr": 9.158423725037635e-07, "epoch": 2.9307004470938898, "percentage": 58.61, "elapsed_time": "0:52:09", "remaining_time": "0:36:49", "throughput": 5147.2, "total_tokens": 16109568} {"current_steps": 3934, "total_steps": 6710, "loss": 0.4524, "lr": 9.152784639352512e-07, "epoch": 2.9314456035767513, "percentage": 58.63, "elapsed_time": "0:52:10", "remaining_time": "0:36:49", "throughput": 5147.22, "total_tokens": 16113664} {"current_steps": 3935, "total_steps": 6710, "loss": 0.2032, "lr": 9.147146287400896e-07, "epoch": 2.9321907600596124, "percentage": 58.64, "elapsed_time": "0:52:11", "remaining_time": "0:36:48", "throughput": 5147.24, "total_tokens": 16117760} {"current_steps": 3936, "total_steps": 6710, "loss": 0.1923, "lr": 9.141508670418759e-07, "epoch": 2.932935916542474, "percentage": 58.66, "elapsed_time": "0:52:12", "remaining_time": "0:36:47", "throughput": 5147.27, "total_tokens": 16121856} {"current_steps": 3937, "total_steps": 6710, "loss": 0.37, "lr": 9.135871789641901e-07, "epoch": 2.933681073025335, "percentage": 58.67, "elapsed_time": "0:52:12", "remaining_time": "0:36:46", "throughput": 5147.29, "total_tokens": 16125952} {"current_steps": 3938, "total_steps": 6710, "loss": 0.3849, "lr": 9.130235646305968e-07, "epoch": 2.9344262295081966, "percentage": 58.69, "elapsed_time": "0:52:13", "remaining_time": "0:36:45", "throughput": 5147.29, "total_tokens": 16130048} {"current_steps": 3939, "total_steps": 6710, "loss": 0.4036, "lr": 9.124600241646442e-07, "epoch": 2.935171385991058, "percentage": 58.7, "elapsed_time": "0:52:14", "remaining_time": "0:36:45", "throughput": 5147.3, "total_tokens": 16134144} {"current_steps": 3940, "total_steps": 6710, "loss": 0.2986, "lr": 9.118965576898647e-07, "epoch": 2.9359165424739198, "percentage": 58.72, "elapsed_time": "0:52:15", "remaining_time": "0:36:44", "throughput": 5147.31, "total_tokens": 16138240} {"current_steps": 3941, "total_steps": 6710, "loss": 0.2816, "lr": 9.113331653297742e-07, "epoch": 2.936661698956781, "percentage": 58.73, "elapsed_time": "0:52:16", "remaining_time": "0:36:43", "throughput": 5147.32, "total_tokens": 16142336} {"current_steps": 3942, "total_steps": 6710, "loss": 0.3673, "lr": 9.107698472078724e-07, "epoch": 2.9374068554396424, "percentage": 58.75, "elapsed_time": "0:52:16", "remaining_time": "0:36:42", "throughput": 5147.3, "total_tokens": 16146432} {"current_steps": 3943, "total_steps": 6710, "loss": 0.1599, "lr": 9.10206603447642e-07, "epoch": 2.9381520119225035, "percentage": 58.76, "elapsed_time": "0:52:17", "remaining_time": "0:36:41", "throughput": 5147.27, "total_tokens": 16150528} {"current_steps": 3944, "total_steps": 6710, "loss": 0.592, "lr": 9.096434341725505e-07, "epoch": 2.938897168405365, "percentage": 58.78, "elapsed_time": "0:52:18", "remaining_time": "0:36:41", "throughput": 5147.27, "total_tokens": 16154624} {"current_steps": 3945, "total_steps": 6710, "loss": 0.3724, "lr": 9.090803395060486e-07, "epoch": 2.9396423248882266, "percentage": 58.79, "elapsed_time": "0:52:19", "remaining_time": "0:36:40", "throughput": 5147.28, "total_tokens": 16158720} {"current_steps": 3946, "total_steps": 6710, "loss": 0.5156, "lr": 9.085173195715707e-07, "epoch": 2.940387481371088, "percentage": 58.81, "elapsed_time": "0:52:20", "remaining_time": "0:36:39", "throughput": 5147.29, "total_tokens": 16162816} {"current_steps": 3947, "total_steps": 6710, "loss": 0.1285, "lr": 9.079543744925348e-07, "epoch": 2.9411326378539493, "percentage": 58.82, "elapsed_time": "0:52:20", "remaining_time": "0:36:38", "throughput": 5147.31, "total_tokens": 16166912} {"current_steps": 3948, "total_steps": 6710, "loss": 0.4928, "lr": 9.073915043923424e-07, "epoch": 2.941877794336811, "percentage": 58.84, "elapsed_time": "0:52:21", "remaining_time": "0:36:37", "throughput": 5147.32, "total_tokens": 16171008} {"current_steps": 3949, "total_steps": 6710, "loss": 0.4775, "lr": 9.068287093943785e-07, "epoch": 2.942622950819672, "percentage": 58.85, "elapsed_time": "0:52:22", "remaining_time": "0:36:37", "throughput": 5147.32, "total_tokens": 16175104} {"current_steps": 3950, "total_steps": 6710, "loss": 0.4667, "lr": 9.062659896220122e-07, "epoch": 2.9433681073025335, "percentage": 58.87, "elapsed_time": "0:52:23", "remaining_time": "0:36:36", "throughput": 5147.31, "total_tokens": 16179200} {"current_steps": 3951, "total_steps": 6710, "loss": 0.3463, "lr": 9.057033451985953e-07, "epoch": 2.944113263785395, "percentage": 58.88, "elapsed_time": "0:52:24", "remaining_time": "0:36:35", "throughput": 5147.28, "total_tokens": 16183296} {"current_steps": 3952, "total_steps": 6710, "loss": 0.4096, "lr": 9.051407762474635e-07, "epoch": 2.944858420268256, "percentage": 58.9, "elapsed_time": "0:52:24", "remaining_time": "0:36:34", "throughput": 5147.26, "total_tokens": 16187392} {"current_steps": 3953, "total_steps": 6710, "loss": 0.4773, "lr": 9.045782828919366e-07, "epoch": 2.9456035767511177, "percentage": 58.91, "elapsed_time": "0:52:25", "remaining_time": "0:36:33", "throughput": 5147.27, "total_tokens": 16191488} {"current_steps": 3954, "total_steps": 6710, "loss": 0.543, "lr": 9.040158652553161e-07, "epoch": 2.9463487332339793, "percentage": 58.93, "elapsed_time": "0:52:26", "remaining_time": "0:36:33", "throughput": 5147.26, "total_tokens": 16195584} {"current_steps": 3955, "total_steps": 6710, "loss": 0.5208, "lr": 9.034535234608889e-07, "epoch": 2.9470938897168404, "percentage": 58.94, "elapsed_time": "0:52:27", "remaining_time": "0:36:32", "throughput": 5147.25, "total_tokens": 16199680} {"current_steps": 3956, "total_steps": 6710, "loss": 0.5226, "lr": 9.028912576319239e-07, "epoch": 2.947839046199702, "percentage": 58.96, "elapsed_time": "0:52:28", "remaining_time": "0:36:31", "throughput": 5147.24, "total_tokens": 16203776} {"current_steps": 3957, "total_steps": 6710, "loss": 0.2735, "lr": 9.023290678916735e-07, "epoch": 2.9485842026825635, "percentage": 58.97, "elapsed_time": "0:52:28", "remaining_time": "0:36:30", "throughput": 5147.24, "total_tokens": 16207872} {"current_steps": 3958, "total_steps": 6710, "loss": 0.4931, "lr": 9.01766954363374e-07, "epoch": 2.9493293591654246, "percentage": 58.99, "elapsed_time": "0:52:29", "remaining_time": "0:36:29", "throughput": 5147.23, "total_tokens": 16211968} {"current_steps": 3959, "total_steps": 6710, "loss": 0.5592, "lr": 9.012049171702447e-07, "epoch": 2.950074515648286, "percentage": 59.0, "elapsed_time": "0:52:30", "remaining_time": "0:36:29", "throughput": 5147.2, "total_tokens": 16216064} {"current_steps": 3960, "total_steps": 6710, "loss": 0.4669, "lr": 9.006429564354883e-07, "epoch": 2.9508196721311473, "percentage": 59.02, "elapsed_time": "0:52:31", "remaining_time": "0:36:28", "throughput": 5147.18, "total_tokens": 16220160} {"current_steps": 3961, "total_steps": 6710, "loss": 0.4667, "lr": 9.000810722822905e-07, "epoch": 2.951564828614009, "percentage": 59.03, "elapsed_time": "0:52:32", "remaining_time": "0:36:27", "throughput": 5147.16, "total_tokens": 16224256} {"current_steps": 3962, "total_steps": 6710, "loss": 0.5006, "lr": 8.995192648338202e-07, "epoch": 2.9523099850968704, "percentage": 59.05, "elapsed_time": "0:52:32", "remaining_time": "0:36:26", "throughput": 5147.17, "total_tokens": 16228352} {"current_steps": 3963, "total_steps": 6710, "loss": 0.3576, "lr": 8.9895753421323e-07, "epoch": 2.953055141579732, "percentage": 59.06, "elapsed_time": "0:52:33", "remaining_time": "0:36:25", "throughput": 5147.19, "total_tokens": 16232448} {"current_steps": 3964, "total_steps": 6710, "loss": 0.2671, "lr": 8.983958805436546e-07, "epoch": 2.953800298062593, "percentage": 59.08, "elapsed_time": "0:52:34", "remaining_time": "0:36:25", "throughput": 5147.22, "total_tokens": 16236544} {"current_steps": 3965, "total_steps": 6710, "loss": 0.2295, "lr": 8.978343039482129e-07, "epoch": 2.9545454545454546, "percentage": 59.09, "elapsed_time": "0:52:35", "remaining_time": "0:36:24", "throughput": 5147.24, "total_tokens": 16240640} {"current_steps": 3966, "total_steps": 6710, "loss": 0.6312, "lr": 8.972728045500064e-07, "epoch": 2.9552906110283157, "percentage": 59.11, "elapsed_time": "0:52:35", "remaining_time": "0:36:23", "throughput": 5147.27, "total_tokens": 16244736} {"current_steps": 3967, "total_steps": 6710, "loss": 0.3439, "lr": 8.967113824721202e-07, "epoch": 2.9560357675111772, "percentage": 59.12, "elapsed_time": "0:52:36", "remaining_time": "0:36:22", "throughput": 5147.29, "total_tokens": 16248832} {"current_steps": 3968, "total_steps": 6710, "loss": 0.354, "lr": 8.961500378376213e-07, "epoch": 2.956780923994039, "percentage": 59.14, "elapsed_time": "0:52:37", "remaining_time": "0:36:21", "throughput": 5147.27, "total_tokens": 16252928} {"current_steps": 3969, "total_steps": 6710, "loss": 0.2701, "lr": 8.955887707695615e-07, "epoch": 2.9575260804769004, "percentage": 59.15, "elapsed_time": "0:52:38", "remaining_time": "0:36:21", "throughput": 5147.26, "total_tokens": 16257024} {"current_steps": 3970, "total_steps": 6710, "loss": 0.4754, "lr": 8.950275813909734e-07, "epoch": 2.9582712369597615, "percentage": 59.17, "elapsed_time": "0:52:39", "remaining_time": "0:36:20", "throughput": 5147.27, "total_tokens": 16261120} {"current_steps": 3971, "total_steps": 6710, "loss": 0.1761, "lr": 8.944664698248739e-07, "epoch": 2.959016393442623, "percentage": 59.18, "elapsed_time": "0:52:39", "remaining_time": "0:36:19", "throughput": 5147.29, "total_tokens": 16265216} {"current_steps": 3972, "total_steps": 6710, "loss": 0.407, "lr": 8.939054361942633e-07, "epoch": 2.959761549925484, "percentage": 59.2, "elapsed_time": "0:52:40", "remaining_time": "0:36:18", "throughput": 5147.31, "total_tokens": 16269312} {"current_steps": 3973, "total_steps": 6710, "loss": 0.294, "lr": 8.93344480622124e-07, "epoch": 2.9605067064083457, "percentage": 59.21, "elapsed_time": "0:52:41", "remaining_time": "0:36:17", "throughput": 5147.33, "total_tokens": 16273408} {"current_steps": 3974, "total_steps": 6710, "loss": 0.1487, "lr": 8.927836032314208e-07, "epoch": 2.9612518628912072, "percentage": 59.23, "elapsed_time": "0:52:42", "remaining_time": "0:36:17", "throughput": 5147.32, "total_tokens": 16277504} {"current_steps": 3975, "total_steps": 6710, "loss": 0.2354, "lr": 8.922228041451028e-07, "epoch": 2.961997019374069, "percentage": 59.24, "elapsed_time": "0:52:43", "remaining_time": "0:36:16", "throughput": 5147.32, "total_tokens": 16281600} {"current_steps": 3976, "total_steps": 6710, "loss": 0.3393, "lr": 8.916620834861007e-07, "epoch": 2.96274217585693, "percentage": 59.25, "elapsed_time": "0:52:43", "remaining_time": "0:36:15", "throughput": 5147.31, "total_tokens": 16285696} {"current_steps": 3977, "total_steps": 6710, "loss": 0.4763, "lr": 8.911014413773288e-07, "epoch": 2.9634873323397914, "percentage": 59.27, "elapsed_time": "0:52:44", "remaining_time": "0:36:14", "throughput": 5147.31, "total_tokens": 16289792} {"current_steps": 3978, "total_steps": 6710, "loss": 0.3827, "lr": 8.905408779416835e-07, "epoch": 2.9642324888226526, "percentage": 59.28, "elapsed_time": "0:52:45", "remaining_time": "0:36:13", "throughput": 5147.33, "total_tokens": 16293888} {"current_steps": 3979, "total_steps": 6710, "loss": 0.2753, "lr": 8.899803933020448e-07, "epoch": 2.964977645305514, "percentage": 59.3, "elapsed_time": "0:52:46", "remaining_time": "0:36:13", "throughput": 5147.35, "total_tokens": 16297984} {"current_steps": 3980, "total_steps": 6710, "loss": 0.3226, "lr": 8.894199875812748e-07, "epoch": 2.9657228017883757, "percentage": 59.31, "elapsed_time": "0:52:47", "remaining_time": "0:36:12", "throughput": 5147.37, "total_tokens": 16302080} {"current_steps": 3981, "total_steps": 6710, "loss": 0.3183, "lr": 8.888596609022181e-07, "epoch": 2.966467958271237, "percentage": 59.33, "elapsed_time": "0:52:47", "remaining_time": "0:36:11", "throughput": 5147.39, "total_tokens": 16306176} {"current_steps": 3982, "total_steps": 6710, "loss": 0.1772, "lr": 8.882994133877027e-07, "epoch": 2.9672131147540983, "percentage": 59.34, "elapsed_time": "0:52:48", "remaining_time": "0:36:10", "throughput": 5147.4, "total_tokens": 16310272} {"current_steps": 3983, "total_steps": 6710, "loss": 0.4759, "lr": 8.877392451605385e-07, "epoch": 2.96795827123696, "percentage": 59.36, "elapsed_time": "0:52:49", "remaining_time": "0:36:09", "throughput": 5147.4, "total_tokens": 16314368} {"current_steps": 3984, "total_steps": 6710, "loss": 0.4347, "lr": 8.871791563435185e-07, "epoch": 2.968703427719821, "percentage": 59.37, "elapsed_time": "0:52:50", "remaining_time": "0:36:09", "throughput": 5147.41, "total_tokens": 16318464} {"current_steps": 3985, "total_steps": 6710, "loss": 0.5091, "lr": 8.866191470594182e-07, "epoch": 2.9694485842026825, "percentage": 59.39, "elapsed_time": "0:52:51", "remaining_time": "0:36:08", "throughput": 5147.43, "total_tokens": 16322560} {"current_steps": 3986, "total_steps": 6710, "loss": 0.3681, "lr": 8.860592174309955e-07, "epoch": 2.970193740685544, "percentage": 59.4, "elapsed_time": "0:52:51", "remaining_time": "0:36:07", "throughput": 5147.45, "total_tokens": 16326656} {"current_steps": 3987, "total_steps": 6710, "loss": 0.314, "lr": 8.854993675809912e-07, "epoch": 2.970938897168405, "percentage": 59.42, "elapsed_time": "0:52:52", "remaining_time": "0:36:06", "throughput": 5147.46, "total_tokens": 16330752} {"current_steps": 3988, "total_steps": 6710, "loss": 0.3608, "lr": 8.849395976321281e-07, "epoch": 2.9716840536512668, "percentage": 59.43, "elapsed_time": "0:52:53", "remaining_time": "0:36:05", "throughput": 5147.47, "total_tokens": 16334848} {"current_steps": 3989, "total_steps": 6710, "loss": 0.3462, "lr": 8.843799077071122e-07, "epoch": 2.9724292101341283, "percentage": 59.45, "elapsed_time": "0:52:54", "remaining_time": "0:36:05", "throughput": 5147.48, "total_tokens": 16338944} {"current_steps": 3990, "total_steps": 6710, "loss": 0.3561, "lr": 8.838202979286316e-07, "epoch": 2.9731743666169894, "percentage": 59.46, "elapsed_time": "0:52:54", "remaining_time": "0:36:04", "throughput": 5147.49, "total_tokens": 16343040} {"current_steps": 3991, "total_steps": 6710, "loss": 0.1837, "lr": 8.83260768419356e-07, "epoch": 2.973919523099851, "percentage": 59.48, "elapsed_time": "0:52:55", "remaining_time": "0:36:03", "throughput": 5147.48, "total_tokens": 16347136} {"current_steps": 3992, "total_steps": 6710, "loss": 0.4759, "lr": 8.827013193019387e-07, "epoch": 2.9746646795827125, "percentage": 59.49, "elapsed_time": "0:52:56", "remaining_time": "0:36:02", "throughput": 5147.47, "total_tokens": 16351232} {"current_steps": 3993, "total_steps": 6710, "loss": 0.5475, "lr": 8.821419506990152e-07, "epoch": 2.9754098360655736, "percentage": 59.51, "elapsed_time": "0:52:57", "remaining_time": "0:36:01", "throughput": 5147.49, "total_tokens": 16355328} {"current_steps": 3994, "total_steps": 6710, "loss": 0.3347, "lr": 8.815826627332026e-07, "epoch": 2.976154992548435, "percentage": 59.52, "elapsed_time": "0:52:58", "remaining_time": "0:36:01", "throughput": 5147.52, "total_tokens": 16359424} {"current_steps": 3995, "total_steps": 6710, "loss": 0.5609, "lr": 8.810234555271012e-07, "epoch": 2.9769001490312967, "percentage": 59.54, "elapsed_time": "0:52:58", "remaining_time": "0:36:00", "throughput": 5147.54, "total_tokens": 16363520} {"current_steps": 3996, "total_steps": 6710, "loss": 0.4451, "lr": 8.804643292032936e-07, "epoch": 2.977645305514158, "percentage": 59.55, "elapsed_time": "0:52:59", "remaining_time": "0:35:59", "throughput": 5147.56, "total_tokens": 16367616} {"current_steps": 3997, "total_steps": 6710, "loss": 0.4103, "lr": 8.799052838843432e-07, "epoch": 2.9783904619970194, "percentage": 59.57, "elapsed_time": "0:53:00", "remaining_time": "0:35:58", "throughput": 5147.58, "total_tokens": 16371712} {"current_steps": 3998, "total_steps": 6710, "loss": 0.3953, "lr": 8.793463196927973e-07, "epoch": 2.979135618479881, "percentage": 59.58, "elapsed_time": "0:53:01", "remaining_time": "0:35:57", "throughput": 5147.59, "total_tokens": 16375808} {"current_steps": 3999, "total_steps": 6710, "loss": 0.4151, "lr": 8.787874367511847e-07, "epoch": 2.979880774962742, "percentage": 59.6, "elapsed_time": "0:53:02", "remaining_time": "0:35:57", "throughput": 5147.59, "total_tokens": 16379904} {"current_steps": 4000, "total_steps": 6710, "loss": 0.3057, "lr": 8.782286351820171e-07, "epoch": 2.9806259314456036, "percentage": 59.61, "elapsed_time": "0:53:02", "remaining_time": "0:35:56", "throughput": 5147.6, "total_tokens": 16384000} {"current_steps": 4001, "total_steps": 6710, "loss": 0.3105, "lr": 8.77669915107787e-07, "epoch": 2.9813710879284647, "percentage": 59.63, "elapsed_time": "0:53:03", "remaining_time": "0:35:55", "throughput": 5147.59, "total_tokens": 16388096} {"current_steps": 4002, "total_steps": 6710, "loss": 0.5657, "lr": 8.771112766509701e-07, "epoch": 2.9821162444113263, "percentage": 59.64, "elapsed_time": "0:53:04", "remaining_time": "0:35:54", "throughput": 5147.58, "total_tokens": 16392192} {"current_steps": 4003, "total_steps": 6710, "loss": 0.4172, "lr": 8.765527199340242e-07, "epoch": 2.982861400894188, "percentage": 59.66, "elapsed_time": "0:53:05", "remaining_time": "0:35:54", "throughput": 5147.56, "total_tokens": 16396288} {"current_steps": 4004, "total_steps": 6710, "loss": 0.4203, "lr": 8.759942450793886e-07, "epoch": 2.9836065573770494, "percentage": 59.67, "elapsed_time": "0:53:06", "remaining_time": "0:35:53", "throughput": 5147.54, "total_tokens": 16400384} {"current_steps": 4005, "total_steps": 6710, "loss": 0.2512, "lr": 8.754358522094853e-07, "epoch": 2.9843517138599105, "percentage": 59.69, "elapsed_time": "0:53:06", "remaining_time": "0:35:52", "throughput": 5147.52, "total_tokens": 16404480} {"current_steps": 4006, "total_steps": 6710, "loss": 0.2672, "lr": 8.748775414467176e-07, "epoch": 2.985096870342772, "percentage": 59.7, "elapsed_time": "0:53:07", "remaining_time": "0:35:51", "throughput": 5147.54, "total_tokens": 16408576} {"current_steps": 4007, "total_steps": 6710, "loss": 0.5343, "lr": 8.743193129134716e-07, "epoch": 2.985842026825633, "percentage": 59.72, "elapsed_time": "0:53:08", "remaining_time": "0:35:50", "throughput": 5147.55, "total_tokens": 16412672} {"current_steps": 4008, "total_steps": 6710, "loss": 0.2833, "lr": 8.73761166732115e-07, "epoch": 2.9865871833084947, "percentage": 59.73, "elapsed_time": "0:53:09", "remaining_time": "0:35:50", "throughput": 5147.56, "total_tokens": 16416768} {"current_steps": 4009, "total_steps": 6710, "loss": 0.4046, "lr": 8.732031030249971e-07, "epoch": 2.9873323397913563, "percentage": 59.75, "elapsed_time": "0:53:10", "remaining_time": "0:35:49", "throughput": 5147.56, "total_tokens": 16420864} {"current_steps": 4010, "total_steps": 6710, "loss": 0.4044, "lr": 8.726451219144496e-07, "epoch": 2.988077496274218, "percentage": 59.76, "elapsed_time": "0:53:10", "remaining_time": "0:35:48", "throughput": 5147.57, "total_tokens": 16424960} {"current_steps": 4011, "total_steps": 6710, "loss": 0.402, "lr": 8.720872235227859e-07, "epoch": 2.988822652757079, "percentage": 59.78, "elapsed_time": "0:53:11", "remaining_time": "0:35:47", "throughput": 5147.58, "total_tokens": 16429056} {"current_steps": 4012, "total_steps": 6710, "loss": 0.6353, "lr": 8.715294079723014e-07, "epoch": 2.9895678092399405, "percentage": 59.79, "elapsed_time": "0:53:12", "remaining_time": "0:35:46", "throughput": 5147.57, "total_tokens": 16433152} {"current_steps": 4013, "total_steps": 6710, "loss": 0.362, "lr": 8.709716753852729e-07, "epoch": 2.9903129657228016, "percentage": 59.81, "elapsed_time": "0:53:13", "remaining_time": "0:35:46", "throughput": 5147.56, "total_tokens": 16437248} {"current_steps": 4014, "total_steps": 6710, "loss": 0.5468, "lr": 8.704140258839598e-07, "epoch": 2.991058122205663, "percentage": 59.82, "elapsed_time": "0:53:14", "remaining_time": "0:35:45", "throughput": 5147.56, "total_tokens": 16441344} {"current_steps": 4015, "total_steps": 6710, "loss": 0.5285, "lr": 8.698564595906029e-07, "epoch": 2.9918032786885247, "percentage": 59.84, "elapsed_time": "0:53:14", "remaining_time": "0:35:44", "throughput": 5147.54, "total_tokens": 16445440} {"current_steps": 4016, "total_steps": 6710, "loss": 0.4048, "lr": 8.692989766274242e-07, "epoch": 2.9925484351713862, "percentage": 59.85, "elapsed_time": "0:53:15", "remaining_time": "0:35:43", "throughput": 5147.53, "total_tokens": 16449536} {"current_steps": 4017, "total_steps": 6710, "loss": 0.3305, "lr": 8.687415771166284e-07, "epoch": 2.9932935916542474, "percentage": 59.87, "elapsed_time": "0:53:16", "remaining_time": "0:35:42", "throughput": 5147.52, "total_tokens": 16453632} {"current_steps": 4018, "total_steps": 6710, "loss": 0.5371, "lr": 8.681842611804016e-07, "epoch": 2.994038748137109, "percentage": 59.88, "elapsed_time": "0:53:17", "remaining_time": "0:35:42", "throughput": 5147.52, "total_tokens": 16457728} {"current_steps": 4019, "total_steps": 6710, "loss": 0.3375, "lr": 8.676270289409108e-07, "epoch": 2.99478390461997, "percentage": 59.9, "elapsed_time": "0:53:18", "remaining_time": "0:35:41", "throughput": 5147.51, "total_tokens": 16461824} {"current_steps": 4020, "total_steps": 6710, "loss": 0.6045, "lr": 8.670698805203057e-07, "epoch": 2.9955290611028316, "percentage": 59.91, "elapsed_time": "0:53:18", "remaining_time": "0:35:40", "throughput": 5147.51, "total_tokens": 16465920} {"current_steps": 4021, "total_steps": 6710, "loss": 0.3041, "lr": 8.665128160407173e-07, "epoch": 2.996274217585693, "percentage": 59.93, "elapsed_time": "0:53:19", "remaining_time": "0:35:39", "throughput": 5147.5, "total_tokens": 16470016} {"current_steps": 4022, "total_steps": 6710, "loss": 0.2505, "lr": 8.659558356242583e-07, "epoch": 2.9970193740685542, "percentage": 59.94, "elapsed_time": "0:53:20", "remaining_time": "0:35:38", "throughput": 5147.5, "total_tokens": 16474112} {"current_steps": 4023, "total_steps": 6710, "loss": 0.178, "lr": 8.653989393930221e-07, "epoch": 2.997764530551416, "percentage": 59.96, "elapsed_time": "0:53:21", "remaining_time": "0:35:38", "throughput": 5147.48, "total_tokens": 16478208} {"current_steps": 4024, "total_steps": 6710, "loss": 0.2724, "lr": 8.648421274690845e-07, "epoch": 2.9985096870342773, "percentage": 59.97, "elapsed_time": "0:53:22", "remaining_time": "0:35:37", "throughput": 5147.5, "total_tokens": 16482304} {"current_steps": 4025, "total_steps": 6710, "loss": 0.4506, "lr": 8.642853999745029e-07, "epoch": 2.9992548435171384, "percentage": 59.99, "elapsed_time": "0:53:22", "remaining_time": "0:35:36", "throughput": 5147.52, "total_tokens": 16486400} {"current_steps": 4026, "total_steps": 6710, "loss": 0.2749, "lr": 8.637287570313159e-07, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:53:23", "remaining_time": "0:35:35", "throughput": 5147.55, "total_tokens": 16490496} {"current_steps": 4027, "total_steps": 6710, "loss": 0.135, "lr": 8.631721987615435e-07, "epoch": 3.0007451564828616, "percentage": 60.01, "elapsed_time": "0:53:24", "remaining_time": "0:35:34", "throughput": 5147.57, "total_tokens": 16494592} {"current_steps": 4028, "total_steps": 6710, "loss": 0.2175, "lr": 8.626157252871878e-07, "epoch": 3.0014903129657227, "percentage": 60.03, "elapsed_time": "0:53:25", "remaining_time": "0:35:34", "throughput": 5147.59, "total_tokens": 16498688} {"current_steps": 4029, "total_steps": 6710, "loss": 0.1457, "lr": 8.620593367302308e-07, "epoch": 3.002235469448584, "percentage": 60.04, "elapsed_time": "0:53:25", "remaining_time": "0:35:33", "throughput": 5147.6, "total_tokens": 16502784} {"current_steps": 4030, "total_steps": 6710, "loss": 0.2917, "lr": 8.615030332126374e-07, "epoch": 3.0029806259314458, "percentage": 60.06, "elapsed_time": "0:53:26", "remaining_time": "0:35:32", "throughput": 5147.62, "total_tokens": 16506880} {"current_steps": 4031, "total_steps": 6710, "loss": 0.1429, "lr": 8.609468148563532e-07, "epoch": 3.003725782414307, "percentage": 60.07, "elapsed_time": "0:53:27", "remaining_time": "0:35:31", "throughput": 5147.64, "total_tokens": 16510976} {"current_steps": 4032, "total_steps": 6710, "loss": 0.3231, "lr": 8.603906817833054e-07, "epoch": 3.0044709388971684, "percentage": 60.09, "elapsed_time": "0:53:28", "remaining_time": "0:35:30", "throughput": 5147.65, "total_tokens": 16515072} {"current_steps": 4033, "total_steps": 6710, "loss": 0.1416, "lr": 8.598346341154021e-07, "epoch": 3.00521609538003, "percentage": 60.1, "elapsed_time": "0:53:29", "remaining_time": "0:35:30", "throughput": 5147.64, "total_tokens": 16519168} {"current_steps": 4034, "total_steps": 6710, "loss": 0.1296, "lr": 8.59278671974533e-07, "epoch": 3.005961251862891, "percentage": 60.12, "elapsed_time": "0:53:29", "remaining_time": "0:35:29", "throughput": 5147.65, "total_tokens": 16523264} {"current_steps": 4035, "total_steps": 6710, "loss": 0.1979, "lr": 8.587227954825694e-07, "epoch": 3.0067064083457526, "percentage": 60.13, "elapsed_time": "0:53:30", "remaining_time": "0:35:28", "throughput": 5147.66, "total_tokens": 16527360} {"current_steps": 4036, "total_steps": 6710, "loss": 0.1263, "lr": 8.58167004761363e-07, "epoch": 3.007451564828614, "percentage": 60.15, "elapsed_time": "0:53:31", "remaining_time": "0:35:27", "throughput": 5147.67, "total_tokens": 16531456} {"current_steps": 4037, "total_steps": 6710, "loss": 0.0475, "lr": 8.576112999327467e-07, "epoch": 3.0081967213114753, "percentage": 60.16, "elapsed_time": "0:53:32", "remaining_time": "0:35:26", "throughput": 5147.66, "total_tokens": 16535552} {"current_steps": 4038, "total_steps": 6710, "loss": 0.2469, "lr": 8.570556811185357e-07, "epoch": 3.008941877794337, "percentage": 60.18, "elapsed_time": "0:53:33", "remaining_time": "0:35:26", "throughput": 5147.64, "total_tokens": 16539648} {"current_steps": 4039, "total_steps": 6710, "loss": 0.3672, "lr": 8.56500148440525e-07, "epoch": 3.0096870342771984, "percentage": 60.19, "elapsed_time": "0:53:33", "remaining_time": "0:35:25", "throughput": 5147.62, "total_tokens": 16543744} {"current_steps": 4040, "total_steps": 6710, "loss": 0.133, "lr": 8.559447020204917e-07, "epoch": 3.0104321907600595, "percentage": 60.21, "elapsed_time": "0:53:34", "remaining_time": "0:35:24", "throughput": 5147.61, "total_tokens": 16547840} {"current_steps": 4041, "total_steps": 6710, "loss": 0.146, "lr": 8.553893419801933e-07, "epoch": 3.011177347242921, "percentage": 60.22, "elapsed_time": "0:53:35", "remaining_time": "0:35:23", "throughput": 5147.63, "total_tokens": 16551936} {"current_steps": 4042, "total_steps": 6710, "loss": 0.087, "lr": 8.54834068441369e-07, "epoch": 3.0119225037257826, "percentage": 60.24, "elapsed_time": "0:53:36", "remaining_time": "0:35:22", "throughput": 5147.64, "total_tokens": 16556032} {"current_steps": 4043, "total_steps": 6710, "loss": 0.0929, "lr": 8.542788815257387e-07, "epoch": 3.0126676602086437, "percentage": 60.25, "elapsed_time": "0:53:37", "remaining_time": "0:35:22", "throughput": 5147.65, "total_tokens": 16560128} {"current_steps": 4044, "total_steps": 6710, "loss": 0.1187, "lr": 8.537237813550032e-07, "epoch": 3.0134128166915053, "percentage": 60.27, "elapsed_time": "0:53:37", "remaining_time": "0:35:21", "throughput": 5147.65, "total_tokens": 16564224} {"current_steps": 4045, "total_steps": 6710, "loss": 0.2024, "lr": 8.531687680508448e-07, "epoch": 3.0141579731743664, "percentage": 60.28, "elapsed_time": "0:53:38", "remaining_time": "0:35:20", "throughput": 5147.67, "total_tokens": 16568320} {"current_steps": 4046, "total_steps": 6710, "loss": 0.1773, "lr": 8.526138417349258e-07, "epoch": 3.014903129657228, "percentage": 60.3, "elapsed_time": "0:53:39", "remaining_time": "0:35:19", "throughput": 5147.67, "total_tokens": 16572416} {"current_steps": 4047, "total_steps": 6710, "loss": 0.1526, "lr": 8.520590025288902e-07, "epoch": 3.0156482861400895, "percentage": 60.31, "elapsed_time": "0:53:40", "remaining_time": "0:35:18", "throughput": 5147.66, "total_tokens": 16576512} {"current_steps": 4048, "total_steps": 6710, "loss": 0.166, "lr": 8.51504250554363e-07, "epoch": 3.0163934426229506, "percentage": 60.33, "elapsed_time": "0:53:41", "remaining_time": "0:35:18", "throughput": 5147.65, "total_tokens": 16580608} {"current_steps": 4049, "total_steps": 6710, "loss": 0.2102, "lr": 8.5094958593295e-07, "epoch": 3.017138599105812, "percentage": 60.34, "elapsed_time": "0:53:41", "remaining_time": "0:35:17", "throughput": 5147.64, "total_tokens": 16584704} {"current_steps": 4050, "total_steps": 6710, "loss": 0.153, "lr": 8.503950087862367e-07, "epoch": 3.0178837555886737, "percentage": 60.36, "elapsed_time": "0:53:42", "remaining_time": "0:35:16", "throughput": 5147.64, "total_tokens": 16588800} {"current_steps": 4051, "total_steps": 6710, "loss": 0.2685, "lr": 8.498405192357909e-07, "epoch": 3.018628912071535, "percentage": 60.37, "elapsed_time": "0:53:43", "remaining_time": "0:35:15", "throughput": 5147.65, "total_tokens": 16592896} {"current_steps": 4052, "total_steps": 6710, "loss": 0.1963, "lr": 8.492861174031607e-07, "epoch": 3.0193740685543964, "percentage": 60.39, "elapsed_time": "0:53:44", "remaining_time": "0:35:14", "throughput": 5147.65, "total_tokens": 16596992} {"current_steps": 4053, "total_steps": 6710, "loss": 0.2668, "lr": 8.487318034098749e-07, "epoch": 3.020119225037258, "percentage": 60.4, "elapsed_time": "0:53:44", "remaining_time": "0:35:14", "throughput": 5147.65, "total_tokens": 16601088} {"current_steps": 4054, "total_steps": 6710, "loss": 0.1093, "lr": 8.481775773774431e-07, "epoch": 3.020864381520119, "percentage": 60.42, "elapsed_time": "0:53:45", "remaining_time": "0:35:13", "throughput": 5147.63, "total_tokens": 16605184} {"current_steps": 4055, "total_steps": 6710, "loss": 0.0888, "lr": 8.476234394273558e-07, "epoch": 3.0216095380029806, "percentage": 60.43, "elapsed_time": "0:53:46", "remaining_time": "0:35:12", "throughput": 5147.62, "total_tokens": 16609280} {"current_steps": 4056, "total_steps": 6710, "loss": 0.0818, "lr": 8.470693896810838e-07, "epoch": 3.022354694485842, "percentage": 60.45, "elapsed_time": "0:53:47", "remaining_time": "0:35:11", "throughput": 5147.61, "total_tokens": 16613376} {"current_steps": 4057, "total_steps": 6710, "loss": 0.1423, "lr": 8.465154282600785e-07, "epoch": 3.0230998509687033, "percentage": 60.46, "elapsed_time": "0:53:48", "remaining_time": "0:35:11", "throughput": 5147.59, "total_tokens": 16617472} {"current_steps": 4058, "total_steps": 6710, "loss": 0.1961, "lr": 8.459615552857725e-07, "epoch": 3.023845007451565, "percentage": 60.48, "elapsed_time": "0:53:48", "remaining_time": "0:35:10", "throughput": 5147.62, "total_tokens": 16621568} {"current_steps": 4059, "total_steps": 6710, "loss": 0.2037, "lr": 8.454077708795788e-07, "epoch": 3.0245901639344264, "percentage": 60.49, "elapsed_time": "0:53:49", "remaining_time": "0:35:09", "throughput": 5147.64, "total_tokens": 16625664} {"current_steps": 4060, "total_steps": 6710, "loss": 0.2207, "lr": 8.448540751628907e-07, "epoch": 3.0253353204172875, "percentage": 60.51, "elapsed_time": "0:53:50", "remaining_time": "0:35:08", "throughput": 5147.66, "total_tokens": 16629760} {"current_steps": 4061, "total_steps": 6710, "loss": 0.2099, "lr": 8.443004682570823e-07, "epoch": 3.026080476900149, "percentage": 60.52, "elapsed_time": "0:53:51", "remaining_time": "0:35:07", "throughput": 5147.68, "total_tokens": 16633856} {"current_steps": 4062, "total_steps": 6710, "loss": 0.1712, "lr": 8.437469502835085e-07, "epoch": 3.0268256333830106, "percentage": 60.54, "elapsed_time": "0:53:52", "remaining_time": "0:35:06", "throughput": 5147.71, "total_tokens": 16637952} {"current_steps": 4063, "total_steps": 6710, "loss": 0.1372, "lr": 8.431935213635041e-07, "epoch": 3.0275707898658717, "percentage": 60.55, "elapsed_time": "0:53:52", "remaining_time": "0:35:06", "throughput": 5147.73, "total_tokens": 16642048} {"current_steps": 4064, "total_steps": 6710, "loss": 0.1396, "lr": 8.426401816183843e-07, "epoch": 3.0283159463487332, "percentage": 60.57, "elapsed_time": "0:53:53", "remaining_time": "0:35:05", "throughput": 5147.73, "total_tokens": 16646144} {"current_steps": 4065, "total_steps": 6710, "loss": 0.1552, "lr": 8.420869311694461e-07, "epoch": 3.029061102831595, "percentage": 60.58, "elapsed_time": "0:53:54", "remaining_time": "0:35:04", "throughput": 5147.74, "total_tokens": 16650240} {"current_steps": 4066, "total_steps": 6710, "loss": 0.3261, "lr": 8.415337701379647e-07, "epoch": 3.029806259314456, "percentage": 60.6, "elapsed_time": "0:53:55", "remaining_time": "0:35:03", "throughput": 5147.71, "total_tokens": 16654336} {"current_steps": 4067, "total_steps": 6710, "loss": 0.1085, "lr": 8.409806986451977e-07, "epoch": 3.0305514157973175, "percentage": 60.61, "elapsed_time": "0:53:56", "remaining_time": "0:35:03", "throughput": 5147.72, "total_tokens": 16658432} {"current_steps": 4068, "total_steps": 6710, "loss": 0.0935, "lr": 8.404277168123824e-07, "epoch": 3.031296572280179, "percentage": 60.63, "elapsed_time": "0:53:56", "remaining_time": "0:35:02", "throughput": 5147.74, "total_tokens": 16662528} {"current_steps": 4069, "total_steps": 6710, "loss": 0.1348, "lr": 8.398748247607361e-07, "epoch": 3.03204172876304, "percentage": 60.64, "elapsed_time": "0:53:57", "remaining_time": "0:35:01", "throughput": 5147.76, "total_tokens": 16666624} {"current_steps": 4070, "total_steps": 6710, "loss": 0.1586, "lr": 8.393220226114567e-07, "epoch": 3.0327868852459017, "percentage": 60.66, "elapsed_time": "0:53:58", "remaining_time": "0:35:00", "throughput": 5147.73, "total_tokens": 16670720} {"current_steps": 4071, "total_steps": 6710, "loss": 0.1911, "lr": 8.387693104857223e-07, "epoch": 3.0335320417287632, "percentage": 60.67, "elapsed_time": "0:53:59", "remaining_time": "0:34:59", "throughput": 5147.74, "total_tokens": 16674816} {"current_steps": 4072, "total_steps": 6710, "loss": 0.1974, "lr": 8.38216688504692e-07, "epoch": 3.0342771982116243, "percentage": 60.69, "elapsed_time": "0:54:00", "remaining_time": "0:34:59", "throughput": 5147.75, "total_tokens": 16678912} {"current_steps": 4073, "total_steps": 6710, "loss": 0.2769, "lr": 8.376641567895036e-07, "epoch": 3.035022354694486, "percentage": 60.7, "elapsed_time": "0:54:00", "remaining_time": "0:34:58", "throughput": 5147.78, "total_tokens": 16683008} {"current_steps": 4074, "total_steps": 6710, "loss": 0.2799, "lr": 8.371117154612765e-07, "epoch": 3.0357675111773474, "percentage": 60.72, "elapsed_time": "0:54:01", "remaining_time": "0:34:57", "throughput": 5147.79, "total_tokens": 16687104} {"current_steps": 4075, "total_steps": 6710, "loss": 0.0585, "lr": 8.365593646411095e-07, "epoch": 3.0365126676602086, "percentage": 60.73, "elapsed_time": "0:54:02", "remaining_time": "0:34:56", "throughput": 5147.8, "total_tokens": 16691200} {"current_steps": 4076, "total_steps": 6710, "loss": 0.1711, "lr": 8.360071044500826e-07, "epoch": 3.03725782414307, "percentage": 60.75, "elapsed_time": "0:54:03", "remaining_time": "0:34:55", "throughput": 5147.75, "total_tokens": 16695296} {"current_steps": 4077, "total_steps": 6710, "loss": 0.2193, "lr": 8.35454935009254e-07, "epoch": 3.0380029806259317, "percentage": 60.76, "elapsed_time": "0:54:04", "remaining_time": "0:34:55", "throughput": 5147.73, "total_tokens": 16699392} {"current_steps": 4078, "total_steps": 6710, "loss": 0.1547, "lr": 8.349028564396638e-07, "epoch": 3.0387481371087928, "percentage": 60.77, "elapsed_time": "0:54:04", "remaining_time": "0:34:54", "throughput": 5147.72, "total_tokens": 16703488} {"current_steps": 4079, "total_steps": 6710, "loss": 0.1077, "lr": 8.343508688623315e-07, "epoch": 3.0394932935916543, "percentage": 60.79, "elapsed_time": "0:54:05", "remaining_time": "0:34:53", "throughput": 5147.73, "total_tokens": 16707584} {"current_steps": 4080, "total_steps": 6710, "loss": 0.0763, "lr": 8.337989723982568e-07, "epoch": 3.0402384500745154, "percentage": 60.8, "elapsed_time": "0:54:06", "remaining_time": "0:34:52", "throughput": 5147.75, "total_tokens": 16711680} {"current_steps": 4081, "total_steps": 6710, "loss": 0.1279, "lr": 8.332471671684193e-07, "epoch": 3.040983606557377, "percentage": 60.82, "elapsed_time": "0:54:07", "remaining_time": "0:34:51", "throughput": 5147.75, "total_tokens": 16715776} {"current_steps": 4082, "total_steps": 6710, "loss": 0.1108, "lr": 8.326954532937789e-07, "epoch": 3.0417287630402385, "percentage": 60.83, "elapsed_time": "0:54:07", "remaining_time": "0:34:51", "throughput": 5147.77, "total_tokens": 16719872} {"current_steps": 4083, "total_steps": 6710, "loss": 0.1192, "lr": 8.321438308952747e-07, "epoch": 3.0424739195230996, "percentage": 60.85, "elapsed_time": "0:54:08", "remaining_time": "0:34:50", "throughput": 5147.78, "total_tokens": 16723968} {"current_steps": 4084, "total_steps": 6710, "loss": 0.1204, "lr": 8.315923000938264e-07, "epoch": 3.043219076005961, "percentage": 60.86, "elapsed_time": "0:54:09", "remaining_time": "0:34:49", "throughput": 5147.79, "total_tokens": 16728064} {"current_steps": 4085, "total_steps": 6710, "loss": 0.176, "lr": 8.310408610103338e-07, "epoch": 3.0439642324888228, "percentage": 60.88, "elapsed_time": "0:54:10", "remaining_time": "0:34:48", "throughput": 5147.81, "total_tokens": 16732160} {"current_steps": 4086, "total_steps": 6710, "loss": 0.1353, "lr": 8.30489513765676e-07, "epoch": 3.044709388971684, "percentage": 60.89, "elapsed_time": "0:54:11", "remaining_time": "0:34:47", "throughput": 5147.83, "total_tokens": 16736256} {"current_steps": 4087, "total_steps": 6710, "loss": 0.1407, "lr": 8.299382584807122e-07, "epoch": 3.0454545454545454, "percentage": 60.91, "elapsed_time": "0:54:11", "remaining_time": "0:34:47", "throughput": 5147.85, "total_tokens": 16740352} {"current_steps": 4088, "total_steps": 6710, "loss": 0.0518, "lr": 8.29387095276282e-07, "epoch": 3.046199701937407, "percentage": 60.92, "elapsed_time": "0:54:12", "remaining_time": "0:34:46", "throughput": 5147.88, "total_tokens": 16744448} {"current_steps": 4089, "total_steps": 6710, "loss": 0.2693, "lr": 8.288360242732036e-07, "epoch": 3.046944858420268, "percentage": 60.94, "elapsed_time": "0:54:13", "remaining_time": "0:34:45", "throughput": 5147.89, "total_tokens": 16748544} {"current_steps": 4090, "total_steps": 6710, "loss": 0.1561, "lr": 8.282850455922768e-07, "epoch": 3.0476900149031296, "percentage": 60.95, "elapsed_time": "0:54:14", "remaining_time": "0:34:44", "throughput": 5147.91, "total_tokens": 16752640} {"current_steps": 4091, "total_steps": 6710, "loss": 0.2194, "lr": 8.277341593542787e-07, "epoch": 3.048435171385991, "percentage": 60.97, "elapsed_time": "0:54:15", "remaining_time": "0:34:43", "throughput": 5147.92, "total_tokens": 16756736} {"current_steps": 4092, "total_steps": 6710, "loss": 0.1689, "lr": 8.271833656799683e-07, "epoch": 3.0491803278688523, "percentage": 60.98, "elapsed_time": "0:54:15", "remaining_time": "0:34:43", "throughput": 5147.94, "total_tokens": 16760832} {"current_steps": 4093, "total_steps": 6710, "loss": 0.2655, "lr": 8.266326646900835e-07, "epoch": 3.049925484351714, "percentage": 61.0, "elapsed_time": "0:54:16", "remaining_time": "0:34:42", "throughput": 5147.97, "total_tokens": 16764928} {"current_steps": 4094, "total_steps": 6710, "loss": 0.1919, "lr": 8.260820565053413e-07, "epoch": 3.0506706408345754, "percentage": 61.01, "elapsed_time": "0:54:17", "remaining_time": "0:34:41", "throughput": 5147.99, "total_tokens": 16769024} {"current_steps": 4095, "total_steps": 6710, "loss": 0.21, "lr": 8.255315412464396e-07, "epoch": 3.0514157973174365, "percentage": 61.03, "elapsed_time": "0:54:18", "remaining_time": "0:34:40", "throughput": 5148.02, "total_tokens": 16773120} {"current_steps": 4096, "total_steps": 6710, "loss": 0.3414, "lr": 8.249811190340548e-07, "epoch": 3.052160953800298, "percentage": 61.04, "elapsed_time": "0:54:18", "remaining_time": "0:34:39", "throughput": 5148.04, "total_tokens": 16777216} {"current_steps": 4097, "total_steps": 6710, "loss": 0.0898, "lr": 8.244307899888437e-07, "epoch": 3.0529061102831596, "percentage": 61.06, "elapsed_time": "0:54:19", "remaining_time": "0:34:39", "throughput": 5148.07, "total_tokens": 16781312} {"current_steps": 4098, "total_steps": 6710, "loss": 0.1696, "lr": 8.238805542314424e-07, "epoch": 3.0536512667660207, "percentage": 61.07, "elapsed_time": "0:54:20", "remaining_time": "0:34:38", "throughput": 5148.09, "total_tokens": 16785408} {"current_steps": 4099, "total_steps": 6710, "loss": 0.1369, "lr": 8.233304118824661e-07, "epoch": 3.0543964232488823, "percentage": 61.09, "elapsed_time": "0:54:21", "remaining_time": "0:34:37", "throughput": 5148.11, "total_tokens": 16789504} {"current_steps": 4100, "total_steps": 6710, "loss": 0.2774, "lr": 8.227803630625106e-07, "epoch": 3.055141579731744, "percentage": 61.1, "elapsed_time": "0:54:22", "remaining_time": "0:34:36", "throughput": 5148.13, "total_tokens": 16793600} {"current_steps": 4101, "total_steps": 6710, "loss": 0.2379, "lr": 8.222304078921501e-07, "epoch": 3.055886736214605, "percentage": 61.12, "elapsed_time": "0:54:22", "remaining_time": "0:34:35", "throughput": 5148.15, "total_tokens": 16797696} {"current_steps": 4102, "total_steps": 6710, "loss": 0.3326, "lr": 8.216805464919384e-07, "epoch": 3.0566318926974665, "percentage": 61.13, "elapsed_time": "0:54:23", "remaining_time": "0:34:34", "throughput": 5148.17, "total_tokens": 16801792} {"current_steps": 4103, "total_steps": 6710, "loss": 0.1411, "lr": 8.211307789824101e-07, "epoch": 3.057377049180328, "percentage": 61.15, "elapsed_time": "0:54:24", "remaining_time": "0:34:34", "throughput": 5148.2, "total_tokens": 16805888} {"current_steps": 4104, "total_steps": 6710, "loss": 0.1192, "lr": 8.205811054840768e-07, "epoch": 3.058122205663189, "percentage": 61.16, "elapsed_time": "0:54:25", "remaining_time": "0:34:33", "throughput": 5148.22, "total_tokens": 16809984} {"current_steps": 4105, "total_steps": 6710, "loss": 0.1726, "lr": 8.200315261174316e-07, "epoch": 3.0588673621460507, "percentage": 61.18, "elapsed_time": "0:54:25", "remaining_time": "0:34:32", "throughput": 5148.24, "total_tokens": 16814080} {"current_steps": 4106, "total_steps": 6710, "loss": 0.1314, "lr": 8.194820410029461e-07, "epoch": 3.0596125186289123, "percentage": 61.19, "elapsed_time": "0:54:26", "remaining_time": "0:34:31", "throughput": 5148.26, "total_tokens": 16818176} {"current_steps": 4107, "total_steps": 6710, "loss": 0.1247, "lr": 8.189326502610714e-07, "epoch": 3.0603576751117734, "percentage": 61.21, "elapsed_time": "0:54:27", "remaining_time": "0:34:30", "throughput": 5148.28, "total_tokens": 16822272} {"current_steps": 4108, "total_steps": 6710, "loss": 0.1379, "lr": 8.183833540122378e-07, "epoch": 3.061102831594635, "percentage": 61.22, "elapsed_time": "0:54:28", "remaining_time": "0:34:30", "throughput": 5148.31, "total_tokens": 16826368} {"current_steps": 4109, "total_steps": 6710, "loss": 0.2069, "lr": 8.178341523768552e-07, "epoch": 3.0618479880774965, "percentage": 61.24, "elapsed_time": "0:54:29", "remaining_time": "0:34:29", "throughput": 5148.32, "total_tokens": 16830464} {"current_steps": 4110, "total_steps": 6710, "loss": 0.1355, "lr": 8.172850454753123e-07, "epoch": 3.0625931445603576, "percentage": 61.25, "elapsed_time": "0:54:29", "remaining_time": "0:34:28", "throughput": 5148.32, "total_tokens": 16834560} {"current_steps": 4111, "total_steps": 6710, "loss": 0.2288, "lr": 8.167360334279773e-07, "epoch": 3.063338301043219, "percentage": 61.27, "elapsed_time": "0:54:30", "remaining_time": "0:34:27", "throughput": 5148.35, "total_tokens": 16838656} {"current_steps": 4112, "total_steps": 6710, "loss": 0.373, "lr": 8.161871163551974e-07, "epoch": 3.0640834575260807, "percentage": 61.28, "elapsed_time": "0:54:31", "remaining_time": "0:34:26", "throughput": 5148.37, "total_tokens": 16842752} {"current_steps": 4113, "total_steps": 6710, "loss": 0.1746, "lr": 8.156382943772994e-07, "epoch": 3.064828614008942, "percentage": 61.3, "elapsed_time": "0:54:32", "remaining_time": "0:34:26", "throughput": 5148.39, "total_tokens": 16846848} {"current_steps": 4114, "total_steps": 6710, "loss": 0.1441, "lr": 8.150895676145887e-07, "epoch": 3.0655737704918034, "percentage": 61.31, "elapsed_time": "0:54:33", "remaining_time": "0:34:25", "throughput": 5148.41, "total_tokens": 16850944} {"current_steps": 4115, "total_steps": 6710, "loss": 0.1455, "lr": 8.145409361873505e-07, "epoch": 3.066318926974665, "percentage": 61.33, "elapsed_time": "0:54:33", "remaining_time": "0:34:24", "throughput": 5148.43, "total_tokens": 16855040} {"current_steps": 4116, "total_steps": 6710, "loss": 0.0711, "lr": 8.139924002158486e-07, "epoch": 3.067064083457526, "percentage": 61.34, "elapsed_time": "0:54:34", "remaining_time": "0:34:23", "throughput": 5148.45, "total_tokens": 16859136} {"current_steps": 4117, "total_steps": 6710, "loss": 0.222, "lr": 8.134439598203262e-07, "epoch": 3.0678092399403876, "percentage": 61.36, "elapsed_time": "0:54:35", "remaining_time": "0:34:22", "throughput": 5148.48, "total_tokens": 16863232} {"current_steps": 4118, "total_steps": 6710, "loss": 0.1932, "lr": 8.128956151210049e-07, "epoch": 3.0685543964232487, "percentage": 61.37, "elapsed_time": "0:54:36", "remaining_time": "0:34:22", "throughput": 5148.49, "total_tokens": 16867328} {"current_steps": 4119, "total_steps": 6710, "loss": 0.1913, "lr": 8.123473662380857e-07, "epoch": 3.0692995529061102, "percentage": 61.39, "elapsed_time": "0:54:36", "remaining_time": "0:34:21", "throughput": 5148.52, "total_tokens": 16871424} {"current_steps": 4120, "total_steps": 6710, "loss": 0.3916, "lr": 8.117992132917493e-07, "epoch": 3.070044709388972, "percentage": 61.4, "elapsed_time": "0:54:37", "remaining_time": "0:34:20", "throughput": 5148.54, "total_tokens": 16875520} {"current_steps": 4121, "total_steps": 6710, "loss": 0.2593, "lr": 8.112511564021541e-07, "epoch": 3.070789865871833, "percentage": 61.42, "elapsed_time": "0:54:38", "remaining_time": "0:34:19", "throughput": 5148.57, "total_tokens": 16879616} {"current_steps": 4122, "total_steps": 6710, "loss": 0.2791, "lr": 8.107031956894384e-07, "epoch": 3.0715350223546944, "percentage": 61.43, "elapsed_time": "0:54:39", "remaining_time": "0:34:18", "throughput": 5148.59, "total_tokens": 16883712} {"current_steps": 4123, "total_steps": 6710, "loss": 0.1712, "lr": 8.101553312737191e-07, "epoch": 3.072280178837556, "percentage": 61.45, "elapsed_time": "0:54:40", "remaining_time": "0:34:18", "throughput": 5148.62, "total_tokens": 16887808} {"current_steps": 4124, "total_steps": 6710, "loss": 0.1126, "lr": 8.096075632750919e-07, "epoch": 3.073025335320417, "percentage": 61.46, "elapsed_time": "0:54:40", "remaining_time": "0:34:17", "throughput": 5148.64, "total_tokens": 16891904} {"current_steps": 4125, "total_steps": 6710, "loss": 0.2557, "lr": 8.090598918136315e-07, "epoch": 3.0737704918032787, "percentage": 61.48, "elapsed_time": "0:54:41", "remaining_time": "0:34:16", "throughput": 5148.66, "total_tokens": 16896000} {"current_steps": 4126, "total_steps": 6710, "loss": 0.19, "lr": 8.085123170093914e-07, "epoch": 3.07451564828614, "percentage": 61.49, "elapsed_time": "0:54:42", "remaining_time": "0:34:15", "throughput": 5148.69, "total_tokens": 16900096} {"current_steps": 4127, "total_steps": 6710, "loss": 0.1585, "lr": 8.079648389824043e-07, "epoch": 3.0752608047690013, "percentage": 61.51, "elapsed_time": "0:54:43", "remaining_time": "0:34:14", "throughput": 5148.71, "total_tokens": 16904192} {"current_steps": 4128, "total_steps": 6710, "loss": 0.2054, "lr": 8.074174578526805e-07, "epoch": 3.076005961251863, "percentage": 61.52, "elapsed_time": "0:54:43", "remaining_time": "0:34:14", "throughput": 5148.74, "total_tokens": 16908288} {"current_steps": 4129, "total_steps": 6710, "loss": 0.1267, "lr": 8.068701737402104e-07, "epoch": 3.0767511177347244, "percentage": 61.54, "elapsed_time": "0:54:44", "remaining_time": "0:34:13", "throughput": 5148.76, "total_tokens": 16912384} {"current_steps": 4130, "total_steps": 6710, "loss": 0.1152, "lr": 8.063229867649627e-07, "epoch": 3.0774962742175855, "percentage": 61.55, "elapsed_time": "0:54:45", "remaining_time": "0:34:12", "throughput": 5148.79, "total_tokens": 16916480} {"current_steps": 4131, "total_steps": 6710, "loss": 0.2474, "lr": 8.057758970468843e-07, "epoch": 3.078241430700447, "percentage": 61.56, "elapsed_time": "0:54:46", "remaining_time": "0:34:11", "throughput": 5148.8, "total_tokens": 16920576} {"current_steps": 4132, "total_steps": 6710, "loss": 0.2076, "lr": 8.05228904705901e-07, "epoch": 3.0789865871833086, "percentage": 61.58, "elapsed_time": "0:54:47", "remaining_time": "0:34:10", "throughput": 5148.82, "total_tokens": 16924672} {"current_steps": 4133, "total_steps": 6710, "loss": 0.1574, "lr": 8.046820098619179e-07, "epoch": 3.0797317436661698, "percentage": 61.59, "elapsed_time": "0:54:47", "remaining_time": "0:34:10", "throughput": 5148.85, "total_tokens": 16928768} {"current_steps": 4134, "total_steps": 6710, "loss": 0.2466, "lr": 8.04135212634818e-07, "epoch": 3.0804769001490313, "percentage": 61.61, "elapsed_time": "0:54:48", "remaining_time": "0:34:09", "throughput": 5148.87, "total_tokens": 16932864} {"current_steps": 4135, "total_steps": 6710, "loss": 0.1062, "lr": 8.035885131444633e-07, "epoch": 3.081222056631893, "percentage": 61.62, "elapsed_time": "0:54:49", "remaining_time": "0:34:08", "throughput": 5148.89, "total_tokens": 16936960} {"current_steps": 4136, "total_steps": 6710, "loss": 0.2359, "lr": 8.030419115106941e-07, "epoch": 3.081967213114754, "percentage": 61.64, "elapsed_time": "0:54:50", "remaining_time": "0:34:07", "throughput": 5148.91, "total_tokens": 16941056} {"current_steps": 4137, "total_steps": 6710, "loss": 0.2437, "lr": 8.024954078533298e-07, "epoch": 3.0827123695976155, "percentage": 61.65, "elapsed_time": "0:54:50", "remaining_time": "0:34:06", "throughput": 5148.94, "total_tokens": 16945152} {"current_steps": 4138, "total_steps": 6710, "loss": 0.1327, "lr": 8.019490022921674e-07, "epoch": 3.083457526080477, "percentage": 61.67, "elapsed_time": "0:54:51", "remaining_time": "0:34:06", "throughput": 5148.96, "total_tokens": 16949248} {"current_steps": 4139, "total_steps": 6710, "loss": 0.1784, "lr": 8.01402694946983e-07, "epoch": 3.084202682563338, "percentage": 61.68, "elapsed_time": "0:54:52", "remaining_time": "0:34:05", "throughput": 5148.98, "total_tokens": 16953344} {"current_steps": 4140, "total_steps": 6710, "loss": 0.2275, "lr": 8.00856485937531e-07, "epoch": 3.0849478390461997, "percentage": 61.7, "elapsed_time": "0:54:53", "remaining_time": "0:34:04", "throughput": 5149.0, "total_tokens": 16957440} {"current_steps": 4141, "total_steps": 6710, "loss": 0.0194, "lr": 8.003103753835446e-07, "epoch": 3.0856929955290613, "percentage": 61.71, "elapsed_time": "0:54:54", "remaining_time": "0:34:03", "throughput": 5149.02, "total_tokens": 16961536} {"current_steps": 4142, "total_steps": 6710, "loss": 0.199, "lr": 7.997643634047351e-07, "epoch": 3.0864381520119224, "percentage": 61.73, "elapsed_time": "0:54:54", "remaining_time": "0:34:02", "throughput": 5149.05, "total_tokens": 16965632} {"current_steps": 4143, "total_steps": 6710, "loss": 0.178, "lr": 7.992184501207918e-07, "epoch": 3.087183308494784, "percentage": 61.74, "elapsed_time": "0:54:55", "remaining_time": "0:34:02", "throughput": 5149.08, "total_tokens": 16969728} {"current_steps": 4144, "total_steps": 6710, "loss": 0.1487, "lr": 7.986726356513838e-07, "epoch": 3.0879284649776455, "percentage": 61.76, "elapsed_time": "0:54:56", "remaining_time": "0:34:01", "throughput": 5149.1, "total_tokens": 16973824} {"current_steps": 4145, "total_steps": 6710, "loss": 0.3045, "lr": 7.981269201161562e-07, "epoch": 3.0886736214605066, "percentage": 61.77, "elapsed_time": "0:54:57", "remaining_time": "0:34:00", "throughput": 5149.13, "total_tokens": 16977920} {"current_steps": 4146, "total_steps": 6710, "loss": 0.381, "lr": 7.975813036347347e-07, "epoch": 3.089418777943368, "percentage": 61.79, "elapsed_time": "0:54:58", "remaining_time": "0:33:59", "throughput": 5149.15, "total_tokens": 16982016} {"current_steps": 4147, "total_steps": 6710, "loss": 0.1523, "lr": 7.97035786326722e-07, "epoch": 3.0901639344262297, "percentage": 61.8, "elapsed_time": "0:54:58", "remaining_time": "0:33:58", "throughput": 5149.17, "total_tokens": 16986112} {"current_steps": 4148, "total_steps": 6710, "loss": 0.1934, "lr": 7.964903683116989e-07, "epoch": 3.090909090909091, "percentage": 61.82, "elapsed_time": "0:54:59", "remaining_time": "0:33:57", "throughput": 5149.18, "total_tokens": 16990208} {"current_steps": 4149, "total_steps": 6710, "loss": 0.1886, "lr": 7.959450497092258e-07, "epoch": 3.0916542473919524, "percentage": 61.83, "elapsed_time": "0:55:00", "remaining_time": "0:33:57", "throughput": 5149.2, "total_tokens": 16994304} {"current_steps": 4150, "total_steps": 6710, "loss": 0.2128, "lr": 7.953998306388399e-07, "epoch": 3.092399403874814, "percentage": 61.85, "elapsed_time": "0:55:01", "remaining_time": "0:33:56", "throughput": 5149.22, "total_tokens": 16998400} {"current_steps": 4151, "total_steps": 6710, "loss": 0.2478, "lr": 7.948547112200572e-07, "epoch": 3.093144560357675, "percentage": 61.86, "elapsed_time": "0:55:01", "remaining_time": "0:33:55", "throughput": 5149.24, "total_tokens": 17002496} {"current_steps": 4152, "total_steps": 6710, "loss": 0.0678, "lr": 7.943096915723719e-07, "epoch": 3.0938897168405366, "percentage": 61.88, "elapsed_time": "0:55:02", "remaining_time": "0:33:54", "throughput": 5149.27, "total_tokens": 17006592} {"current_steps": 4153, "total_steps": 6710, "loss": 0.1523, "lr": 7.937647718152562e-07, "epoch": 3.0946348733233977, "percentage": 61.89, "elapsed_time": "0:55:03", "remaining_time": "0:33:53", "throughput": 5149.29, "total_tokens": 17010688} {"current_steps": 4154, "total_steps": 6710, "loss": 0.2964, "lr": 7.932199520681605e-07, "epoch": 3.0953800298062593, "percentage": 61.91, "elapsed_time": "0:55:04", "remaining_time": "0:33:53", "throughput": 5149.3, "total_tokens": 17014784} {"current_steps": 4155, "total_steps": 6710, "loss": 0.0298, "lr": 7.926752324505129e-07, "epoch": 3.096125186289121, "percentage": 61.92, "elapsed_time": "0:55:05", "remaining_time": "0:33:52", "throughput": 5149.33, "total_tokens": 17018880} {"current_steps": 4156, "total_steps": 6710, "loss": 0.1723, "lr": 7.921306130817197e-07, "epoch": 3.096870342771982, "percentage": 61.94, "elapsed_time": "0:55:05", "remaining_time": "0:33:51", "throughput": 5149.35, "total_tokens": 17022976} {"current_steps": 4157, "total_steps": 6710, "loss": 0.245, "lr": 7.915860940811662e-07, "epoch": 3.0976154992548435, "percentage": 61.95, "elapsed_time": "0:55:06", "remaining_time": "0:33:50", "throughput": 5149.37, "total_tokens": 17027072} {"current_steps": 4158, "total_steps": 6710, "loss": 0.3018, "lr": 7.910416755682137e-07, "epoch": 3.098360655737705, "percentage": 61.97, "elapsed_time": "0:55:07", "remaining_time": "0:33:49", "throughput": 5149.39, "total_tokens": 17031168} {"current_steps": 4159, "total_steps": 6710, "loss": 0.1646, "lr": 7.904973576622033e-07, "epoch": 3.099105812220566, "percentage": 61.98, "elapsed_time": "0:55:08", "remaining_time": "0:33:49", "throughput": 5149.42, "total_tokens": 17035264} {"current_steps": 4160, "total_steps": 6710, "loss": 0.1683, "lr": 7.899531404824531e-07, "epoch": 3.0998509687034277, "percentage": 62.0, "elapsed_time": "0:55:08", "remaining_time": "0:33:48", "throughput": 5149.44, "total_tokens": 17039360} {"current_steps": 4161, "total_steps": 6710, "loss": 0.0213, "lr": 7.894090241482597e-07, "epoch": 3.1005961251862892, "percentage": 62.01, "elapsed_time": "0:55:09", "remaining_time": "0:33:47", "throughput": 5149.46, "total_tokens": 17043456} {"current_steps": 4162, "total_steps": 6710, "loss": 0.2669, "lr": 7.88865008778897e-07, "epoch": 3.1013412816691504, "percentage": 62.03, "elapsed_time": "0:55:10", "remaining_time": "0:33:46", "throughput": 5149.49, "total_tokens": 17047552} {"current_steps": 4163, "total_steps": 6710, "loss": 0.0581, "lr": 7.88321094493617e-07, "epoch": 3.102086438152012, "percentage": 62.04, "elapsed_time": "0:55:11", "remaining_time": "0:33:45", "throughput": 5149.51, "total_tokens": 17051648} {"current_steps": 4164, "total_steps": 6710, "loss": 0.1658, "lr": 7.877772814116502e-07, "epoch": 3.1028315946348735, "percentage": 62.06, "elapsed_time": "0:55:12", "remaining_time": "0:33:45", "throughput": 5149.53, "total_tokens": 17055744} {"current_steps": 4165, "total_steps": 6710, "loss": 0.097, "lr": 7.872335696522038e-07, "epoch": 3.1035767511177346, "percentage": 62.07, "elapsed_time": "0:55:12", "remaining_time": "0:33:44", "throughput": 5149.55, "total_tokens": 17059840} {"current_steps": 4166, "total_steps": 6710, "loss": 0.1136, "lr": 7.866899593344632e-07, "epoch": 3.104321907600596, "percentage": 62.09, "elapsed_time": "0:55:13", "remaining_time": "0:33:43", "throughput": 5149.56, "total_tokens": 17063936} {"current_steps": 4167, "total_steps": 6710, "loss": 0.2593, "lr": 7.861464505775918e-07, "epoch": 3.1050670640834577, "percentage": 62.1, "elapsed_time": "0:55:14", "remaining_time": "0:33:42", "throughput": 5149.58, "total_tokens": 17068032} {"current_steps": 4168, "total_steps": 6710, "loss": 0.296, "lr": 7.856030435007307e-07, "epoch": 3.105812220566319, "percentage": 62.12, "elapsed_time": "0:55:15", "remaining_time": "0:33:41", "throughput": 5149.6, "total_tokens": 17072128} {"current_steps": 4169, "total_steps": 6710, "loss": 0.3391, "lr": 7.850597382229985e-07, "epoch": 3.1065573770491803, "percentage": 62.13, "elapsed_time": "0:55:16", "remaining_time": "0:33:41", "throughput": 5149.62, "total_tokens": 17076224} {"current_steps": 4170, "total_steps": 6710, "loss": 0.1602, "lr": 7.845165348634918e-07, "epoch": 3.107302533532042, "percentage": 62.15, "elapsed_time": "0:55:16", "remaining_time": "0:33:40", "throughput": 5149.64, "total_tokens": 17080320} {"current_steps": 4171, "total_steps": 6710, "loss": 0.3899, "lr": 7.839734335412849e-07, "epoch": 3.108047690014903, "percentage": 62.16, "elapsed_time": "0:55:17", "remaining_time": "0:33:39", "throughput": 5149.66, "total_tokens": 17084416} {"current_steps": 4172, "total_steps": 6710, "loss": 0.1568, "lr": 7.834304343754287e-07, "epoch": 3.1087928464977646, "percentage": 62.18, "elapsed_time": "0:55:18", "remaining_time": "0:33:38", "throughput": 5149.68, "total_tokens": 17088512} {"current_steps": 4173, "total_steps": 6710, "loss": 0.3643, "lr": 7.828875374849526e-07, "epoch": 3.109538002980626, "percentage": 62.19, "elapsed_time": "0:55:19", "remaining_time": "0:33:37", "throughput": 5149.71, "total_tokens": 17092608} {"current_steps": 4174, "total_steps": 6710, "loss": 0.14, "lr": 7.823447429888641e-07, "epoch": 3.110283159463487, "percentage": 62.21, "elapsed_time": "0:55:19", "remaining_time": "0:33:37", "throughput": 5149.73, "total_tokens": 17096704} {"current_steps": 4175, "total_steps": 6710, "loss": 0.2393, "lr": 7.818020510061473e-07, "epoch": 3.1110283159463488, "percentage": 62.22, "elapsed_time": "0:55:20", "remaining_time": "0:33:36", "throughput": 5149.75, "total_tokens": 17100800} {"current_steps": 4176, "total_steps": 6710, "loss": 0.1479, "lr": 7.812594616557641e-07, "epoch": 3.1117734724292103, "percentage": 62.24, "elapsed_time": "0:55:21", "remaining_time": "0:33:35", "throughput": 5149.77, "total_tokens": 17104896} {"current_steps": 4177, "total_steps": 6710, "loss": 0.2165, "lr": 7.807169750566539e-07, "epoch": 3.1125186289120714, "percentage": 62.25, "elapsed_time": "0:55:22", "remaining_time": "0:33:34", "throughput": 5149.79, "total_tokens": 17108992} {"current_steps": 4178, "total_steps": 6710, "loss": 0.126, "lr": 7.801745913277337e-07, "epoch": 3.113263785394933, "percentage": 62.27, "elapsed_time": "0:55:23", "remaining_time": "0:33:33", "throughput": 5149.81, "total_tokens": 17113088} {"current_steps": 4179, "total_steps": 6710, "loss": 0.1754, "lr": 7.796323105878981e-07, "epoch": 3.1140089418777945, "percentage": 62.28, "elapsed_time": "0:55:23", "remaining_time": "0:33:33", "throughput": 5149.83, "total_tokens": 17117184} {"current_steps": 4180, "total_steps": 6710, "loss": 0.0908, "lr": 7.790901329560185e-07, "epoch": 3.1147540983606556, "percentage": 62.3, "elapsed_time": "0:55:24", "remaining_time": "0:33:32", "throughput": 5149.85, "total_tokens": 17121280} {"current_steps": 4181, "total_steps": 6710, "loss": 0.1343, "lr": 7.785480585509446e-07, "epoch": 3.115499254843517, "percentage": 62.31, "elapsed_time": "0:55:25", "remaining_time": "0:33:31", "throughput": 5149.87, "total_tokens": 17125376} {"current_steps": 4182, "total_steps": 6710, "loss": 0.1663, "lr": 7.78006087491503e-07, "epoch": 3.1162444113263787, "percentage": 62.32, "elapsed_time": "0:55:26", "remaining_time": "0:33:30", "throughput": 5149.89, "total_tokens": 17129472} {"current_steps": 4183, "total_steps": 6710, "loss": 0.1701, "lr": 7.774642198964968e-07, "epoch": 3.11698956780924, "percentage": 62.34, "elapsed_time": "0:55:26", "remaining_time": "0:33:29", "throughput": 5149.91, "total_tokens": 17133568} {"current_steps": 4184, "total_steps": 6710, "loss": 0.1043, "lr": 7.769224558847083e-07, "epoch": 3.1177347242921014, "percentage": 62.35, "elapsed_time": "0:55:27", "remaining_time": "0:33:29", "throughput": 5149.93, "total_tokens": 17137664} {"current_steps": 4185, "total_steps": 6710, "loss": 0.3054, "lr": 7.763807955748955e-07, "epoch": 3.118479880774963, "percentage": 62.37, "elapsed_time": "0:55:28", "remaining_time": "0:33:28", "throughput": 5149.95, "total_tokens": 17141760} {"current_steps": 4186, "total_steps": 6710, "loss": 0.1832, "lr": 7.758392390857939e-07, "epoch": 3.119225037257824, "percentage": 62.38, "elapsed_time": "0:55:29", "remaining_time": "0:33:27", "throughput": 5149.97, "total_tokens": 17145856} {"current_steps": 4187, "total_steps": 6710, "loss": 0.2066, "lr": 7.752977865361173e-07, "epoch": 3.1199701937406856, "percentage": 62.4, "elapsed_time": "0:55:30", "remaining_time": "0:33:26", "throughput": 5150.0, "total_tokens": 17149952} {"current_steps": 4188, "total_steps": 6710, "loss": 0.2513, "lr": 7.74756438044555e-07, "epoch": 3.1207153502235467, "percentage": 62.41, "elapsed_time": "0:55:30", "remaining_time": "0:33:25", "throughput": 5150.01, "total_tokens": 17154048} {"current_steps": 4189, "total_steps": 6710, "loss": 0.2331, "lr": 7.742151937297754e-07, "epoch": 3.1214605067064083, "percentage": 62.43, "elapsed_time": "0:55:31", "remaining_time": "0:33:25", "throughput": 5150.04, "total_tokens": 17158144} {"current_steps": 4190, "total_steps": 6710, "loss": 0.1747, "lr": 7.736740537104226e-07, "epoch": 3.12220566318927, "percentage": 62.44, "elapsed_time": "0:55:32", "remaining_time": "0:33:24", "throughput": 5150.06, "total_tokens": 17162240} {"current_steps": 4191, "total_steps": 6710, "loss": 0.2028, "lr": 7.731330181051186e-07, "epoch": 3.122950819672131, "percentage": 62.46, "elapsed_time": "0:55:33", "remaining_time": "0:33:23", "throughput": 5150.08, "total_tokens": 17166336} {"current_steps": 4192, "total_steps": 6710, "loss": 0.2991, "lr": 7.725920870324622e-07, "epoch": 3.1236959761549925, "percentage": 62.47, "elapsed_time": "0:55:33", "remaining_time": "0:33:22", "throughput": 5150.1, "total_tokens": 17170432} {"current_steps": 4193, "total_steps": 6710, "loss": 0.2576, "lr": 7.720512606110292e-07, "epoch": 3.124441132637854, "percentage": 62.49, "elapsed_time": "0:55:34", "remaining_time": "0:33:21", "throughput": 5150.13, "total_tokens": 17174528} {"current_steps": 4194, "total_steps": 6710, "loss": 0.0349, "lr": 7.715105389593728e-07, "epoch": 3.125186289120715, "percentage": 62.5, "elapsed_time": "0:55:35", "remaining_time": "0:33:21", "throughput": 5150.15, "total_tokens": 17178624} {"current_steps": 4195, "total_steps": 6710, "loss": 0.1668, "lr": 7.709699221960229e-07, "epoch": 3.1259314456035767, "percentage": 62.52, "elapsed_time": "0:55:36", "remaining_time": "0:33:20", "throughput": 5150.17, "total_tokens": 17182720} {"current_steps": 4196, "total_steps": 6710, "loss": 0.2616, "lr": 7.704294104394866e-07, "epoch": 3.1266766020864383, "percentage": 62.53, "elapsed_time": "0:55:37", "remaining_time": "0:33:19", "throughput": 5150.19, "total_tokens": 17186816} {"current_steps": 4197, "total_steps": 6710, "loss": 0.1545, "lr": 7.698890038082482e-07, "epoch": 3.1274217585692994, "percentage": 62.55, "elapsed_time": "0:55:37", "remaining_time": "0:33:18", "throughput": 5150.22, "total_tokens": 17190912} {"current_steps": 4198, "total_steps": 6710, "loss": 0.1944, "lr": 7.693487024207689e-07, "epoch": 3.128166915052161, "percentage": 62.56, "elapsed_time": "0:55:38", "remaining_time": "0:33:17", "throughput": 5150.24, "total_tokens": 17195008} {"current_steps": 4199, "total_steps": 6710, "loss": 0.0992, "lr": 7.688085063954853e-07, "epoch": 3.1289120715350225, "percentage": 62.58, "elapsed_time": "0:55:39", "remaining_time": "0:33:16", "throughput": 5150.26, "total_tokens": 17199104} {"current_steps": 4200, "total_steps": 6710, "loss": 0.154, "lr": 7.682684158508136e-07, "epoch": 3.1296572280178836, "percentage": 62.59, "elapsed_time": "0:55:40", "remaining_time": "0:33:16", "throughput": 5150.28, "total_tokens": 17203200} {"current_steps": 4201, "total_steps": 6710, "loss": 0.152, "lr": 7.677284309051447e-07, "epoch": 3.130402384500745, "percentage": 62.61, "elapsed_time": "0:55:41", "remaining_time": "0:33:15", "throughput": 5150.3, "total_tokens": 17207296} {"current_steps": 4202, "total_steps": 6710, "loss": 0.1461, "lr": 7.67188551676848e-07, "epoch": 3.1311475409836067, "percentage": 62.62, "elapsed_time": "0:55:41", "remaining_time": "0:33:14", "throughput": 5150.32, "total_tokens": 17211392} {"current_steps": 4203, "total_steps": 6710, "loss": 0.2459, "lr": 7.666487782842677e-07, "epoch": 3.131892697466468, "percentage": 62.64, "elapsed_time": "0:55:42", "remaining_time": "0:33:13", "throughput": 5150.34, "total_tokens": 17215488} {"current_steps": 4204, "total_steps": 6710, "loss": 0.1234, "lr": 7.661091108457269e-07, "epoch": 3.1326378539493294, "percentage": 62.65, "elapsed_time": "0:55:43", "remaining_time": "0:33:12", "throughput": 5150.37, "total_tokens": 17219584} {"current_steps": 4205, "total_steps": 6710, "loss": 0.1223, "lr": 7.655695494795243e-07, "epoch": 3.133383010432191, "percentage": 62.67, "elapsed_time": "0:55:44", "remaining_time": "0:33:12", "throughput": 5150.39, "total_tokens": 17223680} {"current_steps": 4206, "total_steps": 6710, "loss": 0.0309, "lr": 7.650300943039355e-07, "epoch": 3.134128166915052, "percentage": 62.68, "elapsed_time": "0:55:44", "remaining_time": "0:33:11", "throughput": 5150.42, "total_tokens": 17227776} {"current_steps": 4207, "total_steps": 6710, "loss": 0.0943, "lr": 7.644907454372131e-07, "epoch": 3.1348733233979136, "percentage": 62.7, "elapsed_time": "0:55:45", "remaining_time": "0:33:10", "throughput": 5150.44, "total_tokens": 17231872} {"current_steps": 4208, "total_steps": 6710, "loss": 0.1547, "lr": 7.639515029975862e-07, "epoch": 3.135618479880775, "percentage": 62.71, "elapsed_time": "0:55:46", "remaining_time": "0:33:09", "throughput": 5150.46, "total_tokens": 17235968} {"current_steps": 4209, "total_steps": 6710, "loss": 0.1743, "lr": 7.634123671032608e-07, "epoch": 3.1363636363636362, "percentage": 62.73, "elapsed_time": "0:55:47", "remaining_time": "0:33:08", "throughput": 5150.49, "total_tokens": 17240064} {"current_steps": 4210, "total_steps": 6710, "loss": 0.1819, "lr": 7.628733378724187e-07, "epoch": 3.137108792846498, "percentage": 62.74, "elapsed_time": "0:55:48", "remaining_time": "0:33:08", "throughput": 5150.51, "total_tokens": 17244160} {"current_steps": 4211, "total_steps": 6710, "loss": 0.0873, "lr": 7.623344154232196e-07, "epoch": 3.1378539493293593, "percentage": 62.76, "elapsed_time": "0:55:48", "remaining_time": "0:33:07", "throughput": 5150.53, "total_tokens": 17248256} {"current_steps": 4212, "total_steps": 6710, "loss": 0.1714, "lr": 7.617955998737988e-07, "epoch": 3.1385991058122205, "percentage": 62.77, "elapsed_time": "0:55:49", "remaining_time": "0:33:06", "throughput": 5150.55, "total_tokens": 17252352} {"current_steps": 4213, "total_steps": 6710, "loss": 0.0333, "lr": 7.612568913422686e-07, "epoch": 3.139344262295082, "percentage": 62.79, "elapsed_time": "0:55:50", "remaining_time": "0:33:05", "throughput": 5150.58, "total_tokens": 17256448} {"current_steps": 4214, "total_steps": 6710, "loss": 0.0626, "lr": 7.607182899467176e-07, "epoch": 3.1400894187779436, "percentage": 62.8, "elapsed_time": "0:55:51", "remaining_time": "0:33:04", "throughput": 5150.6, "total_tokens": 17260544} {"current_steps": 4215, "total_steps": 6710, "loss": 0.1614, "lr": 7.601797958052112e-07, "epoch": 3.1408345752608047, "percentage": 62.82, "elapsed_time": "0:55:51", "remaining_time": "0:33:04", "throughput": 5150.62, "total_tokens": 17264640} {"current_steps": 4216, "total_steps": 6710, "loss": 0.2243, "lr": 7.596414090357912e-07, "epoch": 3.1415797317436662, "percentage": 62.83, "elapsed_time": "0:55:52", "remaining_time": "0:33:03", "throughput": 5150.65, "total_tokens": 17268736} {"current_steps": 4217, "total_steps": 6710, "loss": 0.2353, "lr": 7.59103129756476e-07, "epoch": 3.1423248882265273, "percentage": 62.85, "elapsed_time": "0:55:53", "remaining_time": "0:33:02", "throughput": 5150.67, "total_tokens": 17272832} {"current_steps": 4218, "total_steps": 6710, "loss": 0.0925, "lr": 7.585649580852599e-07, "epoch": 3.143070044709389, "percentage": 62.86, "elapsed_time": "0:55:54", "remaining_time": "0:33:01", "throughput": 5150.7, "total_tokens": 17276928} {"current_steps": 4219, "total_steps": 6710, "loss": 0.108, "lr": 7.580268941401145e-07, "epoch": 3.1438152011922504, "percentage": 62.88, "elapsed_time": "0:55:55", "remaining_time": "0:33:00", "throughput": 5150.71, "total_tokens": 17281024} {"current_steps": 4220, "total_steps": 6710, "loss": 0.1947, "lr": 7.574889380389864e-07, "epoch": 3.144560357675112, "percentage": 62.89, "elapsed_time": "0:55:55", "remaining_time": "0:33:00", "throughput": 5150.73, "total_tokens": 17285120} {"current_steps": 4221, "total_steps": 6710, "loss": 0.3975, "lr": 7.569510898998002e-07, "epoch": 3.145305514157973, "percentage": 62.91, "elapsed_time": "0:55:56", "remaining_time": "0:32:59", "throughput": 5150.76, "total_tokens": 17289216} {"current_steps": 4222, "total_steps": 6710, "loss": 0.1267, "lr": 7.564133498404556e-07, "epoch": 3.1460506706408347, "percentage": 62.92, "elapsed_time": "0:55:57", "remaining_time": "0:32:58", "throughput": 5150.78, "total_tokens": 17293312} {"current_steps": 4223, "total_steps": 6710, "loss": 0.1794, "lr": 7.558757179788294e-07, "epoch": 3.1467958271236958, "percentage": 62.94, "elapsed_time": "0:55:58", "remaining_time": "0:32:57", "throughput": 5150.81, "total_tokens": 17297408} {"current_steps": 4224, "total_steps": 6710, "loss": 0.2392, "lr": 7.55338194432774e-07, "epoch": 3.1475409836065573, "percentage": 62.95, "elapsed_time": "0:55:58", "remaining_time": "0:32:56", "throughput": 5150.82, "total_tokens": 17301504} {"current_steps": 4225, "total_steps": 6710, "loss": 0.2005, "lr": 7.548007793201193e-07, "epoch": 3.148286140089419, "percentage": 62.97, "elapsed_time": "0:55:59", "remaining_time": "0:32:56", "throughput": 5150.85, "total_tokens": 17305600} {"current_steps": 4226, "total_steps": 6710, "loss": 0.2811, "lr": 7.542634727586691e-07, "epoch": 3.14903129657228, "percentage": 62.98, "elapsed_time": "0:56:00", "remaining_time": "0:32:55", "throughput": 5150.87, "total_tokens": 17309696} {"current_steps": 4227, "total_steps": 6710, "loss": 0.1711, "lr": 7.537262748662056e-07, "epoch": 3.1497764530551415, "percentage": 63.0, "elapsed_time": "0:56:01", "remaining_time": "0:32:54", "throughput": 5150.88, "total_tokens": 17313792} {"current_steps": 4228, "total_steps": 6710, "loss": 0.0526, "lr": 7.531891857604864e-07, "epoch": 3.150521609538003, "percentage": 63.01, "elapsed_time": "0:56:02", "remaining_time": "0:32:53", "throughput": 5150.91, "total_tokens": 17317888} {"current_steps": 4229, "total_steps": 6710, "loss": 0.2559, "lr": 7.526522055592455e-07, "epoch": 3.151266766020864, "percentage": 63.03, "elapsed_time": "0:56:02", "remaining_time": "0:32:52", "throughput": 5150.93, "total_tokens": 17321984} {"current_steps": 4230, "total_steps": 6710, "loss": 0.2256, "lr": 7.521153343801923e-07, "epoch": 3.1520119225037257, "percentage": 63.04, "elapsed_time": "0:56:03", "remaining_time": "0:32:52", "throughput": 5150.95, "total_tokens": 17326080} {"current_steps": 4231, "total_steps": 6710, "loss": 0.1021, "lr": 7.515785723410129e-07, "epoch": 3.1527570789865873, "percentage": 63.06, "elapsed_time": "0:56:04", "remaining_time": "0:32:51", "throughput": 5150.98, "total_tokens": 17330176} {"current_steps": 4232, "total_steps": 6710, "loss": 0.1736, "lr": 7.510419195593697e-07, "epoch": 3.1535022354694484, "percentage": 63.07, "elapsed_time": "0:56:05", "remaining_time": "0:32:50", "throughput": 5151.0, "total_tokens": 17334272} {"current_steps": 4233, "total_steps": 6710, "loss": 0.1708, "lr": 7.505053761529003e-07, "epoch": 3.15424739195231, "percentage": 63.08, "elapsed_time": "0:56:06", "remaining_time": "0:32:49", "throughput": 5151.02, "total_tokens": 17338368} {"current_steps": 4234, "total_steps": 6710, "loss": 0.3446, "lr": 7.499689422392194e-07, "epoch": 3.1549925484351715, "percentage": 63.1, "elapsed_time": "0:56:06", "remaining_time": "0:32:48", "throughput": 5151.04, "total_tokens": 17342464} {"current_steps": 4235, "total_steps": 6710, "loss": 0.1077, "lr": 7.494326179359168e-07, "epoch": 3.1557377049180326, "percentage": 63.11, "elapsed_time": "0:56:07", "remaining_time": "0:32:48", "throughput": 5151.07, "total_tokens": 17346560} {"current_steps": 4236, "total_steps": 6710, "loss": 0.1851, "lr": 7.488964033605589e-07, "epoch": 3.156482861400894, "percentage": 63.13, "elapsed_time": "0:56:08", "remaining_time": "0:32:47", "throughput": 5151.1, "total_tokens": 17350656} {"current_steps": 4237, "total_steps": 6710, "loss": 0.0414, "lr": 7.483602986306876e-07, "epoch": 3.1572280178837557, "percentage": 63.14, "elapsed_time": "0:56:09", "remaining_time": "0:32:46", "throughput": 5151.12, "total_tokens": 17354752} {"current_steps": 4238, "total_steps": 6710, "loss": 0.3151, "lr": 7.478243038638208e-07, "epoch": 3.157973174366617, "percentage": 63.16, "elapsed_time": "0:56:09", "remaining_time": "0:32:45", "throughput": 5151.14, "total_tokens": 17358848} {"current_steps": 4239, "total_steps": 6710, "loss": 0.1714, "lr": 7.472884191774526e-07, "epoch": 3.1587183308494784, "percentage": 63.17, "elapsed_time": "0:56:10", "remaining_time": "0:32:44", "throughput": 5151.17, "total_tokens": 17362944} {"current_steps": 4240, "total_steps": 6710, "loss": 0.1565, "lr": 7.467526446890525e-07, "epoch": 3.15946348733234, "percentage": 63.19, "elapsed_time": "0:56:11", "remaining_time": "0:32:44", "throughput": 5151.2, "total_tokens": 17367040} {"current_steps": 4241, "total_steps": 6710, "loss": 0.4034, "lr": 7.46216980516066e-07, "epoch": 3.160208643815201, "percentage": 63.2, "elapsed_time": "0:56:12", "remaining_time": "0:32:43", "throughput": 5151.22, "total_tokens": 17371136} {"current_steps": 4242, "total_steps": 6710, "loss": 0.2775, "lr": 7.456814267759147e-07, "epoch": 3.1609538002980626, "percentage": 63.22, "elapsed_time": "0:56:13", "remaining_time": "0:32:42", "throughput": 5151.25, "total_tokens": 17375232} {"current_steps": 4243, "total_steps": 6710, "loss": 0.3386, "lr": 7.451459835859958e-07, "epoch": 3.161698956780924, "percentage": 63.23, "elapsed_time": "0:56:13", "remaining_time": "0:32:41", "throughput": 5151.26, "total_tokens": 17379328} {"current_steps": 4244, "total_steps": 6710, "loss": 0.1241, "lr": 7.446106510636823e-07, "epoch": 3.1624441132637853, "percentage": 63.25, "elapsed_time": "0:56:14", "remaining_time": "0:32:40", "throughput": 5151.28, "total_tokens": 17383424} {"current_steps": 4245, "total_steps": 6710, "loss": 0.2233, "lr": 7.440754293263231e-07, "epoch": 3.163189269746647, "percentage": 63.26, "elapsed_time": "0:56:15", "remaining_time": "0:32:40", "throughput": 5151.3, "total_tokens": 17387520} {"current_steps": 4246, "total_steps": 6710, "loss": 0.0521, "lr": 7.435403184912424e-07, "epoch": 3.1639344262295084, "percentage": 63.28, "elapsed_time": "0:56:16", "remaining_time": "0:32:39", "throughput": 5151.33, "total_tokens": 17391616} {"current_steps": 4247, "total_steps": 6710, "loss": 0.0503, "lr": 7.430053186757401e-07, "epoch": 3.1646795827123695, "percentage": 63.29, "elapsed_time": "0:56:16", "remaining_time": "0:32:38", "throughput": 5151.34, "total_tokens": 17395712} {"current_steps": 4248, "total_steps": 6710, "loss": 0.187, "lr": 7.424704299970922e-07, "epoch": 3.165424739195231, "percentage": 63.31, "elapsed_time": "0:56:17", "remaining_time": "0:32:37", "throughput": 5151.35, "total_tokens": 17399808} {"current_steps": 4249, "total_steps": 6710, "loss": 0.1466, "lr": 7.419356525725502e-07, "epoch": 3.1661698956780926, "percentage": 63.32, "elapsed_time": "0:56:18", "remaining_time": "0:32:36", "throughput": 5151.37, "total_tokens": 17403904} {"current_steps": 4250, "total_steps": 6710, "loss": 0.1999, "lr": 7.414009865193411e-07, "epoch": 3.1669150521609537, "percentage": 63.34, "elapsed_time": "0:56:19", "remaining_time": "0:32:36", "throughput": 5151.4, "total_tokens": 17408000} {"current_steps": 4251, "total_steps": 6710, "loss": 0.1038, "lr": 7.408664319546674e-07, "epoch": 3.1676602086438153, "percentage": 63.35, "elapsed_time": "0:56:20", "remaining_time": "0:32:35", "throughput": 5151.42, "total_tokens": 17412096} {"current_steps": 4252, "total_steps": 6710, "loss": 0.2292, "lr": 7.403319889957079e-07, "epoch": 3.168405365126677, "percentage": 63.37, "elapsed_time": "0:56:20", "remaining_time": "0:32:34", "throughput": 5151.45, "total_tokens": 17416192} {"current_steps": 4253, "total_steps": 6710, "loss": 0.2647, "lr": 7.397976577596153e-07, "epoch": 3.169150521609538, "percentage": 63.38, "elapsed_time": "0:56:21", "remaining_time": "0:32:33", "throughput": 5151.47, "total_tokens": 17420288} {"current_steps": 4254, "total_steps": 6710, "loss": 0.1169, "lr": 7.392634383635191e-07, "epoch": 3.1698956780923995, "percentage": 63.4, "elapsed_time": "0:56:22", "remaining_time": "0:32:32", "throughput": 5151.49, "total_tokens": 17424384} {"current_steps": 4255, "total_steps": 6710, "loss": 0.1106, "lr": 7.387293309245244e-07, "epoch": 3.170640834575261, "percentage": 63.41, "elapsed_time": "0:56:23", "remaining_time": "0:32:31", "throughput": 5151.52, "total_tokens": 17428480} {"current_steps": 4256, "total_steps": 6710, "loss": 0.1772, "lr": 7.381953355597114e-07, "epoch": 3.171385991058122, "percentage": 63.43, "elapsed_time": "0:56:23", "remaining_time": "0:32:31", "throughput": 5151.54, "total_tokens": 17432576} {"current_steps": 4257, "total_steps": 6710, "loss": 0.167, "lr": 7.376614523861352e-07, "epoch": 3.1721311475409837, "percentage": 63.44, "elapsed_time": "0:56:24", "remaining_time": "0:32:30", "throughput": 5151.56, "total_tokens": 17436672} {"current_steps": 4258, "total_steps": 6710, "loss": 0.0734, "lr": 7.371276815208269e-07, "epoch": 3.172876304023845, "percentage": 63.46, "elapsed_time": "0:56:25", "remaining_time": "0:32:29", "throughput": 5151.58, "total_tokens": 17440768} {"current_steps": 4259, "total_steps": 6710, "loss": 0.2127, "lr": 7.365940230807933e-07, "epoch": 3.1736214605067063, "percentage": 63.47, "elapsed_time": "0:56:26", "remaining_time": "0:32:28", "throughput": 5151.6, "total_tokens": 17444864} {"current_steps": 4260, "total_steps": 6710, "loss": 0.0659, "lr": 7.360604771830157e-07, "epoch": 3.174366616989568, "percentage": 63.49, "elapsed_time": "0:56:27", "remaining_time": "0:32:27", "throughput": 5151.62, "total_tokens": 17448960} {"current_steps": 4261, "total_steps": 6710, "loss": 0.296, "lr": 7.355270439444514e-07, "epoch": 3.175111773472429, "percentage": 63.5, "elapsed_time": "0:56:27", "remaining_time": "0:32:27", "throughput": 5151.64, "total_tokens": 17453056} {"current_steps": 4262, "total_steps": 6710, "loss": 0.1302, "lr": 7.349937234820328e-07, "epoch": 3.1758569299552906, "percentage": 63.52, "elapsed_time": "0:56:28", "remaining_time": "0:32:26", "throughput": 5151.66, "total_tokens": 17457152} {"current_steps": 4263, "total_steps": 6710, "loss": 0.1931, "lr": 7.344605159126675e-07, "epoch": 3.176602086438152, "percentage": 63.53, "elapsed_time": "0:56:29", "remaining_time": "0:32:25", "throughput": 5151.69, "total_tokens": 17461248} {"current_steps": 4264, "total_steps": 6710, "loss": 0.2499, "lr": 7.339274213532385e-07, "epoch": 3.1773472429210132, "percentage": 63.55, "elapsed_time": "0:56:30", "remaining_time": "0:32:24", "throughput": 5151.71, "total_tokens": 17465344} {"current_steps": 4265, "total_steps": 6710, "loss": 0.1706, "lr": 7.333944399206039e-07, "epoch": 3.178092399403875, "percentage": 63.56, "elapsed_time": "0:56:30", "remaining_time": "0:32:23", "throughput": 5151.73, "total_tokens": 17469440} {"current_steps": 4266, "total_steps": 6710, "loss": 0.2093, "lr": 7.328615717315968e-07, "epoch": 3.1788375558867363, "percentage": 63.58, "elapsed_time": "0:56:31", "remaining_time": "0:32:23", "throughput": 5151.75, "total_tokens": 17473536} {"current_steps": 4267, "total_steps": 6710, "loss": 0.165, "lr": 7.323288169030259e-07, "epoch": 3.1795827123695974, "percentage": 63.59, "elapsed_time": "0:56:32", "remaining_time": "0:32:22", "throughput": 5151.78, "total_tokens": 17477632} {"current_steps": 4268, "total_steps": 6710, "loss": 0.1533, "lr": 7.317961755516748e-07, "epoch": 3.180327868852459, "percentage": 63.61, "elapsed_time": "0:56:33", "remaining_time": "0:32:21", "throughput": 5151.8, "total_tokens": 17481728} {"current_steps": 4269, "total_steps": 6710, "loss": 0.0737, "lr": 7.312636477943022e-07, "epoch": 3.1810730253353205, "percentage": 63.62, "elapsed_time": "0:56:34", "remaining_time": "0:32:20", "throughput": 5151.82, "total_tokens": 17485824} {"current_steps": 4270, "total_steps": 6710, "loss": 0.0886, "lr": 7.307312337476422e-07, "epoch": 3.1818181818181817, "percentage": 63.64, "elapsed_time": "0:56:34", "remaining_time": "0:32:19", "throughput": 5151.85, "total_tokens": 17489920} {"current_steps": 4271, "total_steps": 6710, "loss": 0.103, "lr": 7.301989335284035e-07, "epoch": 3.182563338301043, "percentage": 63.65, "elapsed_time": "0:56:35", "remaining_time": "0:32:19", "throughput": 5151.87, "total_tokens": 17494016} {"current_steps": 4272, "total_steps": 6710, "loss": 0.2059, "lr": 7.296667472532706e-07, "epoch": 3.1833084947839048, "percentage": 63.67, "elapsed_time": "0:56:36", "remaining_time": "0:32:18", "throughput": 5151.89, "total_tokens": 17498112} {"current_steps": 4273, "total_steps": 6710, "loss": 0.1339, "lr": 7.291346750389019e-07, "epoch": 3.184053651266766, "percentage": 63.68, "elapsed_time": "0:56:37", "remaining_time": "0:32:17", "throughput": 5151.92, "total_tokens": 17502208} {"current_steps": 4274, "total_steps": 6710, "loss": 0.1836, "lr": 7.286027170019322e-07, "epoch": 3.1847988077496274, "percentage": 63.7, "elapsed_time": "0:56:38", "remaining_time": "0:32:16", "throughput": 5151.94, "total_tokens": 17506304} {"current_steps": 4275, "total_steps": 6710, "loss": 0.1795, "lr": 7.280708732589695e-07, "epoch": 3.185543964232489, "percentage": 63.71, "elapsed_time": "0:56:38", "remaining_time": "0:32:15", "throughput": 5151.97, "total_tokens": 17510400} {"current_steps": 4276, "total_steps": 6710, "loss": 0.0808, "lr": 7.275391439265986e-07, "epoch": 3.18628912071535, "percentage": 63.73, "elapsed_time": "0:56:39", "remaining_time": "0:32:15", "throughput": 5151.99, "total_tokens": 17514496} {"current_steps": 4277, "total_steps": 6710, "loss": 0.1629, "lr": 7.270075291213782e-07, "epoch": 3.1870342771982116, "percentage": 63.74, "elapsed_time": "0:56:40", "remaining_time": "0:32:14", "throughput": 5152.02, "total_tokens": 17518592} {"current_steps": 4278, "total_steps": 6710, "loss": 0.2448, "lr": 7.264760289598419e-07, "epoch": 3.187779433681073, "percentage": 63.76, "elapsed_time": "0:56:41", "remaining_time": "0:32:13", "throughput": 5152.04, "total_tokens": 17522688} {"current_steps": 4279, "total_steps": 6710, "loss": 0.1676, "lr": 7.25944643558498e-07, "epoch": 3.1885245901639343, "percentage": 63.77, "elapsed_time": "0:56:41", "remaining_time": "0:32:12", "throughput": 5152.06, "total_tokens": 17526784} {"current_steps": 4280, "total_steps": 6710, "loss": 0.0409, "lr": 7.254133730338306e-07, "epoch": 3.189269746646796, "percentage": 63.79, "elapsed_time": "0:56:42", "remaining_time": "0:32:11", "throughput": 5152.08, "total_tokens": 17530880} {"current_steps": 4281, "total_steps": 6710, "loss": 0.1195, "lr": 7.24882217502298e-07, "epoch": 3.1900149031296574, "percentage": 63.8, "elapsed_time": "0:56:43", "remaining_time": "0:32:11", "throughput": 5152.1, "total_tokens": 17534976} {"current_steps": 4282, "total_steps": 6710, "loss": 0.2234, "lr": 7.243511770803321e-07, "epoch": 3.1907600596125185, "percentage": 63.82, "elapsed_time": "0:56:44", "remaining_time": "0:32:10", "throughput": 5152.12, "total_tokens": 17539072} {"current_steps": 4283, "total_steps": 6710, "loss": 0.1173, "lr": 7.238202518843424e-07, "epoch": 3.19150521609538, "percentage": 63.83, "elapsed_time": "0:56:45", "remaining_time": "0:32:09", "throughput": 5152.14, "total_tokens": 17543168} {"current_steps": 4284, "total_steps": 6710, "loss": 0.2849, "lr": 7.232894420307102e-07, "epoch": 3.1922503725782416, "percentage": 63.85, "elapsed_time": "0:56:45", "remaining_time": "0:32:08", "throughput": 5152.16, "total_tokens": 17547264} {"current_steps": 4285, "total_steps": 6710, "loss": 0.1773, "lr": 7.227587476357939e-07, "epoch": 3.1929955290611027, "percentage": 63.86, "elapsed_time": "0:56:46", "remaining_time": "0:32:07", "throughput": 5152.18, "total_tokens": 17551360} {"current_steps": 4286, "total_steps": 6710, "loss": 0.1304, "lr": 7.222281688159243e-07, "epoch": 3.1937406855439643, "percentage": 63.87, "elapsed_time": "0:56:47", "remaining_time": "0:32:07", "throughput": 5152.2, "total_tokens": 17555456} {"current_steps": 4287, "total_steps": 6710, "loss": 0.2022, "lr": 7.216977056874094e-07, "epoch": 3.194485842026826, "percentage": 63.89, "elapsed_time": "0:56:48", "remaining_time": "0:32:06", "throughput": 5152.22, "total_tokens": 17559552} {"current_steps": 4288, "total_steps": 6710, "loss": 0.1698, "lr": 7.211673583665297e-07, "epoch": 3.195230998509687, "percentage": 63.9, "elapsed_time": "0:56:48", "remaining_time": "0:32:05", "throughput": 5152.24, "total_tokens": 17563648} {"current_steps": 4289, "total_steps": 6710, "loss": 0.1354, "lr": 7.206371269695408e-07, "epoch": 3.1959761549925485, "percentage": 63.92, "elapsed_time": "0:56:49", "remaining_time": "0:32:04", "throughput": 5152.26, "total_tokens": 17567744} {"current_steps": 4290, "total_steps": 6710, "loss": 0.1313, "lr": 7.201070116126743e-07, "epoch": 3.19672131147541, "percentage": 63.93, "elapsed_time": "0:56:50", "remaining_time": "0:32:03", "throughput": 5152.28, "total_tokens": 17571840} {"current_steps": 4291, "total_steps": 6710, "loss": 0.2265, "lr": 7.19577012412134e-07, "epoch": 3.197466467958271, "percentage": 63.95, "elapsed_time": "0:56:51", "remaining_time": "0:32:03", "throughput": 5152.3, "total_tokens": 17575936} {"current_steps": 4292, "total_steps": 6710, "loss": 0.2047, "lr": 7.190471294841011e-07, "epoch": 3.1982116244411327, "percentage": 63.96, "elapsed_time": "0:56:52", "remaining_time": "0:32:02", "throughput": 5152.32, "total_tokens": 17580032} {"current_steps": 4293, "total_steps": 6710, "loss": 0.1813, "lr": 7.185173629447279e-07, "epoch": 3.198956780923994, "percentage": 63.98, "elapsed_time": "0:56:52", "remaining_time": "0:32:01", "throughput": 5152.35, "total_tokens": 17584128} {"current_steps": 4294, "total_steps": 6710, "loss": 0.1191, "lr": 7.179877129101443e-07, "epoch": 3.1997019374068554, "percentage": 63.99, "elapsed_time": "0:56:53", "remaining_time": "0:32:00", "throughput": 5152.37, "total_tokens": 17588224} {"current_steps": 4295, "total_steps": 6710, "loss": 0.165, "lr": 7.174581794964522e-07, "epoch": 3.200447093889717, "percentage": 64.01, "elapsed_time": "0:56:54", "remaining_time": "0:31:59", "throughput": 5152.39, "total_tokens": 17592320} {"current_steps": 4296, "total_steps": 6710, "loss": 0.1886, "lr": 7.169287628197307e-07, "epoch": 3.201192250372578, "percentage": 64.02, "elapsed_time": "0:56:55", "remaining_time": "0:31:59", "throughput": 5152.41, "total_tokens": 17596416} {"current_steps": 4297, "total_steps": 6710, "loss": 0.1239, "lr": 7.163994629960307e-07, "epoch": 3.2019374068554396, "percentage": 64.04, "elapsed_time": "0:56:55", "remaining_time": "0:31:58", "throughput": 5152.43, "total_tokens": 17600512} {"current_steps": 4298, "total_steps": 6710, "loss": 0.2994, "lr": 7.15870280141378e-07, "epoch": 3.202682563338301, "percentage": 64.05, "elapsed_time": "0:56:56", "remaining_time": "0:31:57", "throughput": 5152.46, "total_tokens": 17604608} {"current_steps": 4299, "total_steps": 6710, "loss": 0.0831, "lr": 7.153412143717747e-07, "epoch": 3.2034277198211623, "percentage": 64.07, "elapsed_time": "0:56:57", "remaining_time": "0:31:56", "throughput": 5152.48, "total_tokens": 17608704} {"current_steps": 4300, "total_steps": 6710, "loss": 0.1448, "lr": 7.148122658031945e-07, "epoch": 3.204172876304024, "percentage": 64.08, "elapsed_time": "0:56:58", "remaining_time": "0:31:55", "throughput": 5152.5, "total_tokens": 17612800} {"current_steps": 4301, "total_steps": 6710, "loss": 0.2095, "lr": 7.142834345515876e-07, "epoch": 3.2049180327868854, "percentage": 64.1, "elapsed_time": "0:56:59", "remaining_time": "0:31:55", "throughput": 5152.51, "total_tokens": 17616896} {"current_steps": 4302, "total_steps": 6710, "loss": 0.1772, "lr": 7.137547207328765e-07, "epoch": 3.2056631892697465, "percentage": 64.11, "elapsed_time": "0:56:59", "remaining_time": "0:31:54", "throughput": 5152.53, "total_tokens": 17620992} {"current_steps": 4303, "total_steps": 6710, "loss": 0.052, "lr": 7.132261244629607e-07, "epoch": 3.206408345752608, "percentage": 64.13, "elapsed_time": "0:57:00", "remaining_time": "0:31:53", "throughput": 5152.55, "total_tokens": 17625088} {"current_steps": 4304, "total_steps": 6710, "loss": 0.2164, "lr": 7.126976458577104e-07, "epoch": 3.2071535022354696, "percentage": 64.14, "elapsed_time": "0:57:01", "remaining_time": "0:31:52", "throughput": 5152.57, "total_tokens": 17629184} {"current_steps": 4305, "total_steps": 6710, "loss": 0.2553, "lr": 7.12169285032974e-07, "epoch": 3.2078986587183307, "percentage": 64.16, "elapsed_time": "0:57:02", "remaining_time": "0:31:51", "throughput": 5152.59, "total_tokens": 17633280} {"current_steps": 4306, "total_steps": 6710, "loss": 0.3587, "lr": 7.116410421045699e-07, "epoch": 3.2086438152011922, "percentage": 64.17, "elapsed_time": "0:57:02", "remaining_time": "0:31:51", "throughput": 5152.61, "total_tokens": 17637376} {"current_steps": 4307, "total_steps": 6710, "loss": 0.1345, "lr": 7.11112917188294e-07, "epoch": 3.209388971684054, "percentage": 64.19, "elapsed_time": "0:57:03", "remaining_time": "0:31:50", "throughput": 5152.64, "total_tokens": 17641472} {"current_steps": 4308, "total_steps": 6710, "loss": 0.3634, "lr": 7.105849103999147e-07, "epoch": 3.210134128166915, "percentage": 64.2, "elapsed_time": "0:57:04", "remaining_time": "0:31:49", "throughput": 5152.65, "total_tokens": 17645568} {"current_steps": 4309, "total_steps": 6710, "loss": 0.1955, "lr": 7.100570218551741e-07, "epoch": 3.2108792846497765, "percentage": 64.22, "elapsed_time": "0:57:05", "remaining_time": "0:31:48", "throughput": 5152.67, "total_tokens": 17649664} {"current_steps": 4310, "total_steps": 6710, "loss": 0.2181, "lr": 7.095292516697905e-07, "epoch": 3.211624441132638, "percentage": 64.23, "elapsed_time": "0:57:06", "remaining_time": "0:31:47", "throughput": 5152.69, "total_tokens": 17653760} {"current_steps": 4311, "total_steps": 6710, "loss": 0.0752, "lr": 7.090015999594538e-07, "epoch": 3.212369597615499, "percentage": 64.25, "elapsed_time": "0:57:06", "remaining_time": "0:31:47", "throughput": 5152.7, "total_tokens": 17657856} {"current_steps": 4312, "total_steps": 6710, "loss": 0.2234, "lr": 7.084740668398299e-07, "epoch": 3.2131147540983607, "percentage": 64.26, "elapsed_time": "0:57:07", "remaining_time": "0:31:46", "throughput": 5152.72, "total_tokens": 17661952} {"current_steps": 4313, "total_steps": 6710, "loss": 0.1871, "lr": 7.079466524265569e-07, "epoch": 3.2138599105812222, "percentage": 64.28, "elapsed_time": "0:57:08", "remaining_time": "0:31:45", "throughput": 5152.74, "total_tokens": 17666048} {"current_steps": 4314, "total_steps": 6710, "loss": 0.1852, "lr": 7.074193568352486e-07, "epoch": 3.2146050670640833, "percentage": 64.29, "elapsed_time": "0:57:09", "remaining_time": "0:31:44", "throughput": 5152.76, "total_tokens": 17670144} {"current_steps": 4315, "total_steps": 6710, "loss": 0.0949, "lr": 7.068921801814918e-07, "epoch": 3.215350223546945, "percentage": 64.31, "elapsed_time": "0:57:10", "remaining_time": "0:31:43", "throughput": 5152.79, "total_tokens": 17674240} {"current_steps": 4316, "total_steps": 6710, "loss": 0.1671, "lr": 7.063651225808468e-07, "epoch": 3.2160953800298064, "percentage": 64.32, "elapsed_time": "0:57:10", "remaining_time": "0:31:43", "throughput": 5152.8, "total_tokens": 17678336} {"current_steps": 4317, "total_steps": 6710, "loss": 0.059, "lr": 7.058381841488493e-07, "epoch": 3.2168405365126675, "percentage": 64.34, "elapsed_time": "0:57:11", "remaining_time": "0:31:42", "throughput": 5152.83, "total_tokens": 17682432} {"current_steps": 4318, "total_steps": 6710, "loss": 0.2371, "lr": 7.053113650010071e-07, "epoch": 3.217585692995529, "percentage": 64.35, "elapsed_time": "0:57:12", "remaining_time": "0:31:41", "throughput": 5152.85, "total_tokens": 17686528} {"current_steps": 4319, "total_steps": 6710, "loss": 0.0789, "lr": 7.047846652528039e-07, "epoch": 3.2183308494783907, "percentage": 64.37, "elapsed_time": "0:57:13", "remaining_time": "0:31:40", "throughput": 5152.87, "total_tokens": 17690624} {"current_steps": 4320, "total_steps": 6710, "loss": 0.2915, "lr": 7.042580850196943e-07, "epoch": 3.2190760059612518, "percentage": 64.38, "elapsed_time": "0:57:13", "remaining_time": "0:31:39", "throughput": 5152.88, "total_tokens": 17694720} {"current_steps": 4321, "total_steps": 6710, "loss": 0.1108, "lr": 7.037316244171101e-07, "epoch": 3.2198211624441133, "percentage": 64.4, "elapsed_time": "0:57:14", "remaining_time": "0:31:38", "throughput": 5152.9, "total_tokens": 17698816} {"current_steps": 4322, "total_steps": 6710, "loss": 0.1996, "lr": 7.032052835604539e-07, "epoch": 3.220566318926975, "percentage": 64.41, "elapsed_time": "0:57:15", "remaining_time": "0:31:38", "throughput": 5152.92, "total_tokens": 17702912} {"current_steps": 4323, "total_steps": 6710, "loss": 0.2559, "lr": 7.026790625651045e-07, "epoch": 3.221311475409836, "percentage": 64.43, "elapsed_time": "0:57:16", "remaining_time": "0:31:37", "throughput": 5152.94, "total_tokens": 17707008} {"current_steps": 4324, "total_steps": 6710, "loss": 0.2092, "lr": 7.021529615464123e-07, "epoch": 3.2220566318926975, "percentage": 64.44, "elapsed_time": "0:57:17", "remaining_time": "0:31:36", "throughput": 5152.96, "total_tokens": 17711104} {"current_steps": 4325, "total_steps": 6710, "loss": 0.0963, "lr": 7.016269806197035e-07, "epoch": 3.222801788375559, "percentage": 64.46, "elapsed_time": "0:57:17", "remaining_time": "0:31:35", "throughput": 5152.99, "total_tokens": 17715200} {"current_steps": 4326, "total_steps": 6710, "loss": 0.0914, "lr": 7.011011199002763e-07, "epoch": 3.22354694485842, "percentage": 64.47, "elapsed_time": "0:57:18", "remaining_time": "0:31:34", "throughput": 5153.01, "total_tokens": 17719296} {"current_steps": 4327, "total_steps": 6710, "loss": 0.276, "lr": 7.005753795034023e-07, "epoch": 3.2242921013412817, "percentage": 64.49, "elapsed_time": "0:57:19", "remaining_time": "0:31:34", "throughput": 5153.03, "total_tokens": 17723392} {"current_steps": 4328, "total_steps": 6710, "loss": 0.1727, "lr": 7.000497595443293e-07, "epoch": 3.225037257824143, "percentage": 64.5, "elapsed_time": "0:57:20", "remaining_time": "0:31:33", "throughput": 5153.05, "total_tokens": 17727488} {"current_steps": 4329, "total_steps": 6710, "loss": 0.151, "lr": 6.995242601382751e-07, "epoch": 3.2257824143070044, "percentage": 64.52, "elapsed_time": "0:57:20", "remaining_time": "0:31:32", "throughput": 5153.07, "total_tokens": 17731584} {"current_steps": 4330, "total_steps": 6710, "loss": 0.0459, "lr": 6.989988814004345e-07, "epoch": 3.226527570789866, "percentage": 64.53, "elapsed_time": "0:57:21", "remaining_time": "0:31:31", "throughput": 5153.09, "total_tokens": 17735680} {"current_steps": 4331, "total_steps": 6710, "loss": 0.0752, "lr": 6.984736234459731e-07, "epoch": 3.227272727272727, "percentage": 64.55, "elapsed_time": "0:57:22", "remaining_time": "0:31:30", "throughput": 5153.11, "total_tokens": 17739776} {"current_steps": 4332, "total_steps": 6710, "loss": 0.0427, "lr": 6.979484863900327e-07, "epoch": 3.2280178837555886, "percentage": 64.56, "elapsed_time": "0:57:23", "remaining_time": "0:31:30", "throughput": 5153.14, "total_tokens": 17743872} {"current_steps": 4333, "total_steps": 6710, "loss": 0.0538, "lr": 6.97423470347725e-07, "epoch": 3.22876304023845, "percentage": 64.58, "elapsed_time": "0:57:24", "remaining_time": "0:31:29", "throughput": 5153.16, "total_tokens": 17747968} {"current_steps": 4334, "total_steps": 6710, "loss": 0.0552, "lr": 6.96898575434139e-07, "epoch": 3.2295081967213113, "percentage": 64.59, "elapsed_time": "0:57:24", "remaining_time": "0:31:28", "throughput": 5153.18, "total_tokens": 17752064} {"current_steps": 4335, "total_steps": 6710, "loss": 0.1781, "lr": 6.963738017643347e-07, "epoch": 3.230253353204173, "percentage": 64.61, "elapsed_time": "0:57:25", "remaining_time": "0:31:27", "throughput": 5153.2, "total_tokens": 17756160} {"current_steps": 4336, "total_steps": 6710, "loss": 0.3021, "lr": 6.958491494533458e-07, "epoch": 3.2309985096870344, "percentage": 64.62, "elapsed_time": "0:57:26", "remaining_time": "0:31:26", "throughput": 5153.22, "total_tokens": 17760256} {"current_steps": 4337, "total_steps": 6710, "loss": 0.3497, "lr": 6.953246186161808e-07, "epoch": 3.2317436661698955, "percentage": 64.63, "elapsed_time": "0:57:27", "remaining_time": "0:31:26", "throughput": 5153.24, "total_tokens": 17764352} {"current_steps": 4338, "total_steps": 6710, "loss": 0.0512, "lr": 6.948002093678196e-07, "epoch": 3.232488822652757, "percentage": 64.65, "elapsed_time": "0:57:28", "remaining_time": "0:31:25", "throughput": 5153.26, "total_tokens": 17768448} {"current_steps": 4339, "total_steps": 6710, "loss": 0.3107, "lr": 6.942759218232175e-07, "epoch": 3.2332339791356186, "percentage": 64.66, "elapsed_time": "0:57:28", "remaining_time": "0:31:24", "throughput": 5153.28, "total_tokens": 17772544} {"current_steps": 4340, "total_steps": 6710, "loss": 0.067, "lr": 6.937517560973012e-07, "epoch": 3.2339791356184797, "percentage": 64.68, "elapsed_time": "0:57:29", "remaining_time": "0:31:23", "throughput": 5153.3, "total_tokens": 17776640} {"current_steps": 4341, "total_steps": 6710, "loss": 0.1648, "lr": 6.932277123049723e-07, "epoch": 3.2347242921013413, "percentage": 64.69, "elapsed_time": "0:57:30", "remaining_time": "0:31:22", "throughput": 5153.31, "total_tokens": 17780736} {"current_steps": 4342, "total_steps": 6710, "loss": 0.3631, "lr": 6.927037905611045e-07, "epoch": 3.235469448584203, "percentage": 64.71, "elapsed_time": "0:57:31", "remaining_time": "0:31:22", "throughput": 5153.33, "total_tokens": 17784832} {"current_steps": 4343, "total_steps": 6710, "loss": 0.0521, "lr": 6.921799909805449e-07, "epoch": 3.236214605067064, "percentage": 64.72, "elapsed_time": "0:57:31", "remaining_time": "0:31:21", "throughput": 5153.33, "total_tokens": 17788928} {"current_steps": 4344, "total_steps": 6710, "loss": 0.1983, "lr": 6.916563136781149e-07, "epoch": 3.2369597615499255, "percentage": 64.74, "elapsed_time": "0:57:32", "remaining_time": "0:31:20", "throughput": 5153.35, "total_tokens": 17793024} {"current_steps": 4345, "total_steps": 6710, "loss": 0.3553, "lr": 6.911327587686074e-07, "epoch": 3.237704918032787, "percentage": 64.75, "elapsed_time": "0:57:33", "remaining_time": "0:31:19", "throughput": 5153.37, "total_tokens": 17797120} {"current_steps": 4346, "total_steps": 6710, "loss": 0.0744, "lr": 6.906093263667909e-07, "epoch": 3.238450074515648, "percentage": 64.77, "elapsed_time": "0:57:34", "remaining_time": "0:31:18", "throughput": 5153.39, "total_tokens": 17801216} {"current_steps": 4347, "total_steps": 6710, "loss": 0.1371, "lr": 6.900860165874034e-07, "epoch": 3.2391952309985097, "percentage": 64.78, "elapsed_time": "0:57:35", "remaining_time": "0:31:18", "throughput": 5153.41, "total_tokens": 17805312} {"current_steps": 4348, "total_steps": 6710, "loss": 0.0636, "lr": 6.895628295451598e-07, "epoch": 3.2399403874813713, "percentage": 64.8, "elapsed_time": "0:57:35", "remaining_time": "0:31:17", "throughput": 5153.44, "total_tokens": 17809408} {"current_steps": 4349, "total_steps": 6710, "loss": 0.2522, "lr": 6.89039765354745e-07, "epoch": 3.2406855439642324, "percentage": 64.81, "elapsed_time": "0:57:36", "remaining_time": "0:31:16", "throughput": 5153.46, "total_tokens": 17813504} {"current_steps": 4350, "total_steps": 6710, "loss": 0.1268, "lr": 6.885168241308202e-07, "epoch": 3.241430700447094, "percentage": 64.83, "elapsed_time": "0:57:37", "remaining_time": "0:31:15", "throughput": 5153.48, "total_tokens": 17817600} {"current_steps": 4351, "total_steps": 6710, "loss": 0.2684, "lr": 6.879940059880163e-07, "epoch": 3.2421758569299555, "percentage": 64.84, "elapsed_time": "0:57:38", "remaining_time": "0:31:14", "throughput": 5153.5, "total_tokens": 17821696} {"current_steps": 4352, "total_steps": 6710, "loss": 0.1755, "lr": 6.874713110409396e-07, "epoch": 3.2429210134128166, "percentage": 64.86, "elapsed_time": "0:57:38", "remaining_time": "0:31:14", "throughput": 5153.52, "total_tokens": 17825792} {"current_steps": 4353, "total_steps": 6710, "loss": 0.0596, "lr": 6.869487394041685e-07, "epoch": 3.243666169895678, "percentage": 64.87, "elapsed_time": "0:57:39", "remaining_time": "0:31:13", "throughput": 5153.55, "total_tokens": 17829888} {"current_steps": 4354, "total_steps": 6710, "loss": 0.155, "lr": 6.864262911922538e-07, "epoch": 3.2444113263785397, "percentage": 64.89, "elapsed_time": "0:57:40", "remaining_time": "0:31:12", "throughput": 5153.57, "total_tokens": 17833984} {"current_steps": 4355, "total_steps": 6710, "loss": 0.1462, "lr": 6.85903966519721e-07, "epoch": 3.245156482861401, "percentage": 64.9, "elapsed_time": "0:57:41", "remaining_time": "0:31:11", "throughput": 5153.59, "total_tokens": 17838080} {"current_steps": 4356, "total_steps": 6710, "loss": 0.1708, "lr": 6.85381765501066e-07, "epoch": 3.2459016393442623, "percentage": 64.92, "elapsed_time": "0:57:42", "remaining_time": "0:31:10", "throughput": 5153.61, "total_tokens": 17842176} {"current_steps": 4357, "total_steps": 6710, "loss": 0.2448, "lr": 6.848596882507602e-07, "epoch": 3.246646795827124, "percentage": 64.93, "elapsed_time": "0:57:42", "remaining_time": "0:31:10", "throughput": 5153.64, "total_tokens": 17846272} {"current_steps": 4358, "total_steps": 6710, "loss": 0.0475, "lr": 6.843377348832459e-07, "epoch": 3.247391952309985, "percentage": 64.95, "elapsed_time": "0:57:43", "remaining_time": "0:31:09", "throughput": 5153.66, "total_tokens": 17850368} {"current_steps": 4359, "total_steps": 6710, "loss": 0.0409, "lr": 6.838159055129401e-07, "epoch": 3.2481371087928466, "percentage": 64.96, "elapsed_time": "0:57:44", "remaining_time": "0:31:08", "throughput": 5153.68, "total_tokens": 17854464} {"current_steps": 4360, "total_steps": 6710, "loss": 0.2325, "lr": 6.832942002542299e-07, "epoch": 3.248882265275708, "percentage": 64.98, "elapsed_time": "0:57:45", "remaining_time": "0:31:07", "throughput": 5153.7, "total_tokens": 17858560} {"current_steps": 4361, "total_steps": 6710, "loss": 0.2665, "lr": 6.827726192214781e-07, "epoch": 3.2496274217585692, "percentage": 64.99, "elapsed_time": "0:57:45", "remaining_time": "0:31:06", "throughput": 5153.72, "total_tokens": 17862656} {"current_steps": 4362, "total_steps": 6710, "loss": 0.0743, "lr": 6.822511625290184e-07, "epoch": 3.2503725782414308, "percentage": 65.01, "elapsed_time": "0:57:46", "remaining_time": "0:31:06", "throughput": 5153.75, "total_tokens": 17866752} {"current_steps": 4363, "total_steps": 6710, "loss": 0.1263, "lr": 6.817298302911576e-07, "epoch": 3.251117734724292, "percentage": 65.02, "elapsed_time": "0:57:47", "remaining_time": "0:31:05", "throughput": 5153.77, "total_tokens": 17870848} {"current_steps": 4364, "total_steps": 6710, "loss": 0.2117, "lr": 6.812086226221763e-07, "epoch": 3.2518628912071534, "percentage": 65.04, "elapsed_time": "0:57:48", "remaining_time": "0:31:04", "throughput": 5153.78, "total_tokens": 17874944} {"current_steps": 4365, "total_steps": 6710, "loss": 0.1068, "lr": 6.806875396363261e-07, "epoch": 3.252608047690015, "percentage": 65.05, "elapsed_time": "0:57:49", "remaining_time": "0:31:03", "throughput": 5153.8, "total_tokens": 17879040} {"current_steps": 4366, "total_steps": 6710, "loss": 0.2299, "lr": 6.801665814478326e-07, "epoch": 3.2533532041728765, "percentage": 65.07, "elapsed_time": "0:57:49", "remaining_time": "0:31:02", "throughput": 5153.82, "total_tokens": 17883136} {"current_steps": 4367, "total_steps": 6710, "loss": 0.0753, "lr": 6.796457481708932e-07, "epoch": 3.2540983606557377, "percentage": 65.08, "elapsed_time": "0:57:50", "remaining_time": "0:31:02", "throughput": 5153.85, "total_tokens": 17887232} {"current_steps": 4368, "total_steps": 6710, "loss": 0.0725, "lr": 6.791250399196789e-07, "epoch": 3.254843517138599, "percentage": 65.1, "elapsed_time": "0:57:51", "remaining_time": "0:31:01", "throughput": 5153.87, "total_tokens": 17891328} {"current_steps": 4369, "total_steps": 6710, "loss": 0.1134, "lr": 6.786044568083322e-07, "epoch": 3.2555886736214603, "percentage": 65.11, "elapsed_time": "0:57:52", "remaining_time": "0:31:00", "throughput": 5153.89, "total_tokens": 17895424} {"current_steps": 4370, "total_steps": 6710, "loss": 0.2378, "lr": 6.780839989509682e-07, "epoch": 3.256333830104322, "percentage": 65.13, "elapsed_time": "0:57:53", "remaining_time": "0:30:59", "throughput": 5153.9, "total_tokens": 17899520} {"current_steps": 4371, "total_steps": 6710, "loss": 0.1157, "lr": 6.775636664616763e-07, "epoch": 3.2570789865871834, "percentage": 65.14, "elapsed_time": "0:57:53", "remaining_time": "0:30:58", "throughput": 5153.92, "total_tokens": 17903616} {"current_steps": 4372, "total_steps": 6710, "loss": 0.0282, "lr": 6.770434594545154e-07, "epoch": 3.2578241430700445, "percentage": 65.16, "elapsed_time": "0:57:54", "remaining_time": "0:30:58", "throughput": 5153.94, "total_tokens": 17907712} {"current_steps": 4373, "total_steps": 6710, "loss": 0.029, "lr": 6.765233780435207e-07, "epoch": 3.258569299552906, "percentage": 65.17, "elapsed_time": "0:57:55", "remaining_time": "0:30:57", "throughput": 5153.97, "total_tokens": 17911808} {"current_steps": 4374, "total_steps": 6710, "loss": 0.1361, "lr": 6.760034223426953e-07, "epoch": 3.2593144560357676, "percentage": 65.19, "elapsed_time": "0:57:56", "remaining_time": "0:30:56", "throughput": 5153.99, "total_tokens": 17915904} {"current_steps": 4375, "total_steps": 6710, "loss": 0.1895, "lr": 6.754835924660191e-07, "epoch": 3.2600596125186287, "percentage": 65.2, "elapsed_time": "0:57:56", "remaining_time": "0:30:55", "throughput": 5154.01, "total_tokens": 17920000} {"current_steps": 4376, "total_steps": 6710, "loss": 0.2109, "lr": 6.749638885274412e-07, "epoch": 3.2608047690014903, "percentage": 65.22, "elapsed_time": "0:57:57", "remaining_time": "0:30:54", "throughput": 5154.03, "total_tokens": 17924096} {"current_steps": 4377, "total_steps": 6710, "loss": 0.0371, "lr": 6.744443106408857e-07, "epoch": 3.261549925484352, "percentage": 65.23, "elapsed_time": "0:57:58", "remaining_time": "0:30:54", "throughput": 5154.05, "total_tokens": 17928192} {"current_steps": 4378, "total_steps": 6710, "loss": 0.2784, "lr": 6.739248589202465e-07, "epoch": 3.262295081967213, "percentage": 65.25, "elapsed_time": "0:57:59", "remaining_time": "0:30:53", "throughput": 5154.05, "total_tokens": 17932288} {"current_steps": 4379, "total_steps": 6710, "loss": 0.2262, "lr": 6.734055334793923e-07, "epoch": 3.2630402384500745, "percentage": 65.26, "elapsed_time": "0:58:00", "remaining_time": "0:30:52", "throughput": 5154.07, "total_tokens": 17936384} {"current_steps": 4380, "total_steps": 6710, "loss": 0.0594, "lr": 6.728863344321626e-07, "epoch": 3.263785394932936, "percentage": 65.28, "elapsed_time": "0:58:00", "remaining_time": "0:30:51", "throughput": 5154.09, "total_tokens": 17940480} {"current_steps": 4381, "total_steps": 6710, "loss": 0.081, "lr": 6.723672618923687e-07, "epoch": 3.264530551415797, "percentage": 65.29, "elapsed_time": "0:58:01", "remaining_time": "0:30:50", "throughput": 5154.11, "total_tokens": 17944576} {"current_steps": 4382, "total_steps": 6710, "loss": 0.1629, "lr": 6.718483159737962e-07, "epoch": 3.2652757078986587, "percentage": 65.31, "elapsed_time": "0:58:02", "remaining_time": "0:30:50", "throughput": 5154.13, "total_tokens": 17948672} {"current_steps": 4383, "total_steps": 6710, "loss": 0.1836, "lr": 6.713294967902006e-07, "epoch": 3.2660208643815203, "percentage": 65.32, "elapsed_time": "0:58:03", "remaining_time": "0:30:49", "throughput": 5154.14, "total_tokens": 17952768} {"current_steps": 4384, "total_steps": 6710, "loss": 0.2406, "lr": 6.70810804455312e-07, "epoch": 3.2667660208643814, "percentage": 65.34, "elapsed_time": "0:58:03", "remaining_time": "0:30:48", "throughput": 5154.14, "total_tokens": 17956864} {"current_steps": 4385, "total_steps": 6710, "loss": 0.1637, "lr": 6.702922390828304e-07, "epoch": 3.267511177347243, "percentage": 65.35, "elapsed_time": "0:58:04", "remaining_time": "0:30:47", "throughput": 5154.16, "total_tokens": 17960960} {"current_steps": 4386, "total_steps": 6710, "loss": 0.1131, "lr": 6.697738007864303e-07, "epoch": 3.2682563338301045, "percentage": 65.37, "elapsed_time": "0:58:05", "remaining_time": "0:30:46", "throughput": 5154.18, "total_tokens": 17965056} {"current_steps": 4387, "total_steps": 6710, "loss": 0.0844, "lr": 6.692554896797554e-07, "epoch": 3.2690014903129656, "percentage": 65.38, "elapsed_time": "0:58:06", "remaining_time": "0:30:46", "throughput": 5154.2, "total_tokens": 17969152} {"current_steps": 4388, "total_steps": 6710, "loss": 0.1386, "lr": 6.687373058764243e-07, "epoch": 3.269746646795827, "percentage": 65.39, "elapsed_time": "0:58:07", "remaining_time": "0:30:45", "throughput": 5154.22, "total_tokens": 17973248} {"current_steps": 4389, "total_steps": 6710, "loss": 0.1358, "lr": 6.682192494900261e-07, "epoch": 3.2704918032786887, "percentage": 65.41, "elapsed_time": "0:58:07", "remaining_time": "0:30:44", "throughput": 5154.24, "total_tokens": 17977344} {"current_steps": 4390, "total_steps": 6710, "loss": 0.2675, "lr": 6.677013206341232e-07, "epoch": 3.27123695976155, "percentage": 65.42, "elapsed_time": "0:58:08", "remaining_time": "0:30:43", "throughput": 5154.26, "total_tokens": 17981440} {"current_steps": 4391, "total_steps": 6710, "loss": 0.1232, "lr": 6.671835194222487e-07, "epoch": 3.2719821162444114, "percentage": 65.44, "elapsed_time": "0:58:09", "remaining_time": "0:30:42", "throughput": 5154.28, "total_tokens": 17985536} {"current_steps": 4392, "total_steps": 6710, "loss": 0.2738, "lr": 6.666658459679079e-07, "epoch": 3.2727272727272725, "percentage": 65.45, "elapsed_time": "0:58:10", "remaining_time": "0:30:42", "throughput": 5154.3, "total_tokens": 17989632} {"current_steps": 4393, "total_steps": 6710, "loss": 0.2393, "lr": 6.661483003845797e-07, "epoch": 3.273472429210134, "percentage": 65.47, "elapsed_time": "0:58:10", "remaining_time": "0:30:41", "throughput": 5154.33, "total_tokens": 17993728} {"current_steps": 4394, "total_steps": 6710, "loss": 0.3609, "lr": 6.656308827857125e-07, "epoch": 3.2742175856929956, "percentage": 65.48, "elapsed_time": "0:58:11", "remaining_time": "0:30:40", "throughput": 5154.35, "total_tokens": 17997824} {"current_steps": 4395, "total_steps": 6710, "loss": 0.1772, "lr": 6.65113593284729e-07, "epoch": 3.274962742175857, "percentage": 65.5, "elapsed_time": "0:58:12", "remaining_time": "0:30:39", "throughput": 5154.36, "total_tokens": 18001920} {"current_steps": 4396, "total_steps": 6710, "loss": 0.2402, "lr": 6.645964319950218e-07, "epoch": 3.2757078986587183, "percentage": 65.51, "elapsed_time": "0:58:13", "remaining_time": "0:30:38", "throughput": 5154.38, "total_tokens": 18006016} {"current_steps": 4397, "total_steps": 6710, "loss": 0.2405, "lr": 6.640793990299577e-07, "epoch": 3.27645305514158, "percentage": 65.53, "elapsed_time": "0:58:14", "remaining_time": "0:30:38", "throughput": 5154.4, "total_tokens": 18010112} {"current_steps": 4398, "total_steps": 6710, "loss": 0.1258, "lr": 6.635624945028728e-07, "epoch": 3.277198211624441, "percentage": 65.54, "elapsed_time": "0:58:14", "remaining_time": "0:30:37", "throughput": 5154.42, "total_tokens": 18014208} {"current_steps": 4399, "total_steps": 6710, "loss": 0.123, "lr": 6.630457185270763e-07, "epoch": 3.2779433681073025, "percentage": 65.56, "elapsed_time": "0:58:15", "remaining_time": "0:30:36", "throughput": 5154.45, "total_tokens": 18018304} {"current_steps": 4400, "total_steps": 6710, "loss": 0.3894, "lr": 6.625290712158506e-07, "epoch": 3.278688524590164, "percentage": 65.57, "elapsed_time": "0:58:16", "remaining_time": "0:30:35", "throughput": 5154.46, "total_tokens": 18022400} {"current_steps": 4401, "total_steps": 6710, "loss": 0.0513, "lr": 6.620125526824462e-07, "epoch": 3.2794336810730256, "percentage": 65.59, "elapsed_time": "0:58:17", "remaining_time": "0:30:34", "throughput": 5154.49, "total_tokens": 18026496} {"current_steps": 4402, "total_steps": 6710, "loss": 0.0461, "lr": 6.614961630400894e-07, "epoch": 3.2801788375558867, "percentage": 65.6, "elapsed_time": "0:58:18", "remaining_time": "0:30:34", "throughput": 5154.51, "total_tokens": 18030592} {"current_steps": 4403, "total_steps": 6710, "loss": 0.1562, "lr": 6.609799024019755e-07, "epoch": 3.2809239940387482, "percentage": 65.62, "elapsed_time": "0:58:18", "remaining_time": "0:30:33", "throughput": 5154.53, "total_tokens": 18034688} {"current_steps": 4404, "total_steps": 6710, "loss": 0.083, "lr": 6.604637708812737e-07, "epoch": 3.2816691505216093, "percentage": 65.63, "elapsed_time": "0:58:19", "remaining_time": "0:30:32", "throughput": 5154.55, "total_tokens": 18038784} {"current_steps": 4405, "total_steps": 6710, "loss": 0.2799, "lr": 6.59947768591122e-07, "epoch": 3.282414307004471, "percentage": 65.65, "elapsed_time": "0:58:20", "remaining_time": "0:30:31", "throughput": 5154.57, "total_tokens": 18042880} {"current_steps": 4406, "total_steps": 6710, "loss": 0.245, "lr": 6.594318956446336e-07, "epoch": 3.2831594634873325, "percentage": 65.66, "elapsed_time": "0:58:21", "remaining_time": "0:30:30", "throughput": 5154.59, "total_tokens": 18046976} {"current_steps": 4407, "total_steps": 6710, "loss": 0.3338, "lr": 6.589161521548908e-07, "epoch": 3.2839046199701936, "percentage": 65.68, "elapsed_time": "0:58:21", "remaining_time": "0:30:30", "throughput": 5154.61, "total_tokens": 18051072} {"current_steps": 4408, "total_steps": 6710, "loss": 0.2385, "lr": 6.584005382349476e-07, "epoch": 3.284649776453055, "percentage": 65.69, "elapsed_time": "0:58:22", "remaining_time": "0:30:29", "throughput": 5154.63, "total_tokens": 18055168} {"current_steps": 4409, "total_steps": 6710, "loss": 0.1997, "lr": 6.578850539978313e-07, "epoch": 3.2853949329359167, "percentage": 65.71, "elapsed_time": "0:58:23", "remaining_time": "0:30:28", "throughput": 5154.65, "total_tokens": 18059264} {"current_steps": 4410, "total_steps": 6710, "loss": 0.2064, "lr": 6.573696995565385e-07, "epoch": 3.2861400894187778, "percentage": 65.72, "elapsed_time": "0:58:24", "remaining_time": "0:30:27", "throughput": 5154.67, "total_tokens": 18063360} {"current_steps": 4411, "total_steps": 6710, "loss": 0.2081, "lr": 6.568544750240401e-07, "epoch": 3.2868852459016393, "percentage": 65.74, "elapsed_time": "0:58:25", "remaining_time": "0:30:26", "throughput": 5154.7, "total_tokens": 18067456} {"current_steps": 4412, "total_steps": 6710, "loss": 0.2087, "lr": 6.563393805132756e-07, "epoch": 3.287630402384501, "percentage": 65.75, "elapsed_time": "0:58:25", "remaining_time": "0:30:26", "throughput": 5154.72, "total_tokens": 18071552} {"current_steps": 4413, "total_steps": 6710, "loss": 0.0767, "lr": 6.558244161371591e-07, "epoch": 3.288375558867362, "percentage": 65.77, "elapsed_time": "0:58:26", "remaining_time": "0:30:25", "throughput": 5154.74, "total_tokens": 18075648} {"current_steps": 4414, "total_steps": 6710, "loss": 0.2642, "lr": 6.553095820085722e-07, "epoch": 3.2891207153502235, "percentage": 65.78, "elapsed_time": "0:58:27", "remaining_time": "0:30:24", "throughput": 5154.76, "total_tokens": 18079744} {"current_steps": 4415, "total_steps": 6710, "loss": 0.1187, "lr": 6.54794878240372e-07, "epoch": 3.289865871833085, "percentage": 65.8, "elapsed_time": "0:58:28", "remaining_time": "0:30:23", "throughput": 5154.78, "total_tokens": 18083840} {"current_steps": 4416, "total_steps": 6710, "loss": 0.226, "lr": 6.542803049453841e-07, "epoch": 3.290611028315946, "percentage": 65.81, "elapsed_time": "0:58:28", "remaining_time": "0:30:22", "throughput": 5154.8, "total_tokens": 18087936} {"current_steps": 4417, "total_steps": 6710, "loss": 0.0875, "lr": 6.537658622364077e-07, "epoch": 3.2913561847988078, "percentage": 65.83, "elapsed_time": "0:58:29", "remaining_time": "0:30:22", "throughput": 5154.82, "total_tokens": 18092032} {"current_steps": 4418, "total_steps": 6710, "loss": 0.08, "lr": 6.532515502262119e-07, "epoch": 3.2921013412816693, "percentage": 65.84, "elapsed_time": "0:58:30", "remaining_time": "0:30:21", "throughput": 5154.84, "total_tokens": 18096128} {"current_steps": 4419, "total_steps": 6710, "loss": 0.2456, "lr": 6.527373690275368e-07, "epoch": 3.2928464977645304, "percentage": 65.86, "elapsed_time": "0:58:31", "remaining_time": "0:30:20", "throughput": 5154.86, "total_tokens": 18100224} {"current_steps": 4420, "total_steps": 6710, "loss": 0.1148, "lr": 6.522233187530958e-07, "epoch": 3.293591654247392, "percentage": 65.87, "elapsed_time": "0:58:32", "remaining_time": "0:30:19", "throughput": 5154.89, "total_tokens": 18104320} {"current_steps": 4421, "total_steps": 6710, "loss": 0.121, "lr": 6.517093995155713e-07, "epoch": 3.2943368107302535, "percentage": 65.89, "elapsed_time": "0:58:32", "remaining_time": "0:30:18", "throughput": 5154.91, "total_tokens": 18108416} {"current_steps": 4422, "total_steps": 6710, "loss": 0.0726, "lr": 6.511956114276192e-07, "epoch": 3.2950819672131146, "percentage": 65.9, "elapsed_time": "0:58:33", "remaining_time": "0:30:17", "throughput": 5154.93, "total_tokens": 18112512} {"current_steps": 4423, "total_steps": 6710, "loss": 0.0575, "lr": 6.506819546018642e-07, "epoch": 3.295827123695976, "percentage": 65.92, "elapsed_time": "0:58:34", "remaining_time": "0:30:17", "throughput": 5154.95, "total_tokens": 18116608} {"current_steps": 4424, "total_steps": 6710, "loss": 0.3577, "lr": 6.50168429150905e-07, "epoch": 3.2965722801788377, "percentage": 65.93, "elapsed_time": "0:58:35", "remaining_time": "0:30:16", "throughput": 5154.97, "total_tokens": 18120704} {"current_steps": 4425, "total_steps": 6710, "loss": 0.2668, "lr": 6.496550351873092e-07, "epoch": 3.297317436661699, "percentage": 65.95, "elapsed_time": "0:58:35", "remaining_time": "0:30:15", "throughput": 5154.99, "total_tokens": 18124800} {"current_steps": 4426, "total_steps": 6710, "loss": 0.0825, "lr": 6.491417728236161e-07, "epoch": 3.2980625931445604, "percentage": 65.96, "elapsed_time": "0:58:36", "remaining_time": "0:30:14", "throughput": 5155.0, "total_tokens": 18128896} {"current_steps": 4427, "total_steps": 6710, "loss": 0.14, "lr": 6.486286421723378e-07, "epoch": 3.2988077496274215, "percentage": 65.98, "elapsed_time": "0:58:37", "remaining_time": "0:30:13", "throughput": 5155.03, "total_tokens": 18132992} {"current_steps": 4428, "total_steps": 6710, "loss": 0.2442, "lr": 6.481156433459543e-07, "epoch": 3.299552906110283, "percentage": 65.99, "elapsed_time": "0:58:38", "remaining_time": "0:30:13", "throughput": 5155.05, "total_tokens": 18137088} {"current_steps": 4429, "total_steps": 6710, "loss": 0.2154, "lr": 6.476027764569202e-07, "epoch": 3.3002980625931446, "percentage": 66.01, "elapsed_time": "0:58:39", "remaining_time": "0:30:12", "throughput": 5155.07, "total_tokens": 18141184} {"current_steps": 4430, "total_steps": 6710, "loss": 0.2175, "lr": 6.470900416176585e-07, "epoch": 3.301043219076006, "percentage": 66.02, "elapsed_time": "0:58:39", "remaining_time": "0:30:11", "throughput": 5155.09, "total_tokens": 18145280} {"current_steps": 4431, "total_steps": 6710, "loss": 0.2066, "lr": 6.465774389405655e-07, "epoch": 3.3017883755588673, "percentage": 66.04, "elapsed_time": "0:58:40", "remaining_time": "0:30:10", "throughput": 5155.11, "total_tokens": 18149376} {"current_steps": 4432, "total_steps": 6710, "loss": 0.1393, "lr": 6.460649685380059e-07, "epoch": 3.302533532041729, "percentage": 66.05, "elapsed_time": "0:58:41", "remaining_time": "0:30:09", "throughput": 5155.13, "total_tokens": 18153472} {"current_steps": 4433, "total_steps": 6710, "loss": 0.1833, "lr": 6.455526305223183e-07, "epoch": 3.30327868852459, "percentage": 66.07, "elapsed_time": "0:58:42", "remaining_time": "0:30:09", "throughput": 5155.15, "total_tokens": 18157568} {"current_steps": 4434, "total_steps": 6710, "loss": 0.328, "lr": 6.450404250058104e-07, "epoch": 3.3040238450074515, "percentage": 66.08, "elapsed_time": "0:58:42", "remaining_time": "0:30:08", "throughput": 5155.17, "total_tokens": 18161664} {"current_steps": 4435, "total_steps": 6710, "loss": 0.2798, "lr": 6.445283521007604e-07, "epoch": 3.304769001490313, "percentage": 66.1, "elapsed_time": "0:58:43", "remaining_time": "0:30:07", "throughput": 5155.2, "total_tokens": 18165760} {"current_steps": 4436, "total_steps": 6710, "loss": 0.1779, "lr": 6.440164119194197e-07, "epoch": 3.3055141579731746, "percentage": 66.11, "elapsed_time": "0:58:44", "remaining_time": "0:30:06", "throughput": 5155.22, "total_tokens": 18169856} {"current_steps": 4437, "total_steps": 6710, "loss": 0.0396, "lr": 6.43504604574008e-07, "epoch": 3.3062593144560357, "percentage": 66.13, "elapsed_time": "0:58:45", "remaining_time": "0:30:05", "throughput": 5155.24, "total_tokens": 18173952} {"current_steps": 4438, "total_steps": 6710, "loss": 0.1087, "lr": 6.429929301767182e-07, "epoch": 3.3070044709388973, "percentage": 66.14, "elapsed_time": "0:58:46", "remaining_time": "0:30:05", "throughput": 5155.26, "total_tokens": 18178048} {"current_steps": 4439, "total_steps": 6710, "loss": 0.2903, "lr": 6.424813888397122e-07, "epoch": 3.3077496274217584, "percentage": 66.15, "elapsed_time": "0:58:46", "remaining_time": "0:30:04", "throughput": 5155.28, "total_tokens": 18182144} {"current_steps": 4440, "total_steps": 6710, "loss": 0.19, "lr": 6.419699806751248e-07, "epoch": 3.30849478390462, "percentage": 66.17, "elapsed_time": "0:58:47", "remaining_time": "0:30:03", "throughput": 5155.3, "total_tokens": 18186240} {"current_steps": 4441, "total_steps": 6710, "loss": 0.3125, "lr": 6.414587057950583e-07, "epoch": 3.3092399403874815, "percentage": 66.18, "elapsed_time": "0:58:48", "remaining_time": "0:30:02", "throughput": 5155.31, "total_tokens": 18190336} {"current_steps": 4442, "total_steps": 6710, "loss": 0.1334, "lr": 6.409475643115895e-07, "epoch": 3.3099850968703426, "percentage": 66.2, "elapsed_time": "0:58:49", "remaining_time": "0:30:01", "throughput": 5155.34, "total_tokens": 18194432} {"current_steps": 4443, "total_steps": 6710, "loss": 0.0672, "lr": 6.404365563367629e-07, "epoch": 3.310730253353204, "percentage": 66.21, "elapsed_time": "0:58:50", "remaining_time": "0:30:01", "throughput": 5155.36, "total_tokens": 18198528} {"current_steps": 4444, "total_steps": 6710, "loss": 0.1902, "lr": 6.399256819825965e-07, "epoch": 3.3114754098360657, "percentage": 66.23, "elapsed_time": "0:58:50", "remaining_time": "0:30:00", "throughput": 5155.38, "total_tokens": 18202624} {"current_steps": 4445, "total_steps": 6710, "loss": 0.249, "lr": 6.394149413610769e-07, "epoch": 3.312220566318927, "percentage": 66.24, "elapsed_time": "0:58:51", "remaining_time": "0:29:59", "throughput": 5155.4, "total_tokens": 18206720} {"current_steps": 4446, "total_steps": 6710, "loss": 0.1278, "lr": 6.389043345841617e-07, "epoch": 3.3129657228017884, "percentage": 66.26, "elapsed_time": "0:58:52", "remaining_time": "0:29:58", "throughput": 5155.42, "total_tokens": 18210816} {"current_steps": 4447, "total_steps": 6710, "loss": 0.0687, "lr": 6.383938617637803e-07, "epoch": 3.31371087928465, "percentage": 66.27, "elapsed_time": "0:58:53", "remaining_time": "0:29:57", "throughput": 5155.44, "total_tokens": 18214912} {"current_steps": 4448, "total_steps": 6710, "loss": 0.1713, "lr": 6.378835230118312e-07, "epoch": 3.314456035767511, "percentage": 66.29, "elapsed_time": "0:58:53", "remaining_time": "0:29:57", "throughput": 5155.45, "total_tokens": 18219008} {"current_steps": 4449, "total_steps": 6710, "loss": 0.1259, "lr": 6.373733184401854e-07, "epoch": 3.3152011922503726, "percentage": 66.3, "elapsed_time": "0:58:54", "remaining_time": "0:29:56", "throughput": 5155.47, "total_tokens": 18223104} {"current_steps": 4450, "total_steps": 6710, "loss": 0.1932, "lr": 6.36863248160682e-07, "epoch": 3.315946348733234, "percentage": 66.32, "elapsed_time": "0:58:55", "remaining_time": "0:29:55", "throughput": 5155.48, "total_tokens": 18227200} {"current_steps": 4451, "total_steps": 6710, "loss": 0.3571, "lr": 6.363533122851334e-07, "epoch": 3.3166915052160952, "percentage": 66.33, "elapsed_time": "0:58:56", "remaining_time": "0:29:54", "throughput": 5155.5, "total_tokens": 18231296} {"current_steps": 4452, "total_steps": 6710, "loss": 0.3134, "lr": 6.358435109253206e-07, "epoch": 3.317436661698957, "percentage": 66.35, "elapsed_time": "0:58:57", "remaining_time": "0:29:53", "throughput": 5155.52, "total_tokens": 18235392} {"current_steps": 4453, "total_steps": 6710, "loss": 0.1382, "lr": 6.353338441929951e-07, "epoch": 3.3181818181818183, "percentage": 66.36, "elapsed_time": "0:58:57", "remaining_time": "0:29:53", "throughput": 5155.54, "total_tokens": 18239488} {"current_steps": 4454, "total_steps": 6710, "loss": 0.1568, "lr": 6.348243121998812e-07, "epoch": 3.3189269746646795, "percentage": 66.38, "elapsed_time": "0:58:58", "remaining_time": "0:29:52", "throughput": 5155.56, "total_tokens": 18243584} {"current_steps": 4455, "total_steps": 6710, "loss": 0.2043, "lr": 6.343149150576697e-07, "epoch": 3.319672131147541, "percentage": 66.39, "elapsed_time": "0:58:59", "remaining_time": "0:29:51", "throughput": 5155.56, "total_tokens": 18247680} {"current_steps": 4456, "total_steps": 6710, "loss": 0.3589, "lr": 6.338056528780258e-07, "epoch": 3.3204172876304026, "percentage": 66.41, "elapsed_time": "0:59:00", "remaining_time": "0:29:50", "throughput": 5155.57, "total_tokens": 18251776} {"current_steps": 4457, "total_steps": 6710, "loss": 0.1323, "lr": 6.332965257725822e-07, "epoch": 3.3211624441132637, "percentage": 66.42, "elapsed_time": "0:59:00", "remaining_time": "0:29:49", "throughput": 5155.59, "total_tokens": 18255872} {"current_steps": 4458, "total_steps": 6710, "loss": 0.0958, "lr": 6.327875338529444e-07, "epoch": 3.321907600596125, "percentage": 66.44, "elapsed_time": "0:59:01", "remaining_time": "0:29:49", "throughput": 5155.61, "total_tokens": 18259968} {"current_steps": 4459, "total_steps": 6710, "loss": 0.1696, "lr": 6.322786772306859e-07, "epoch": 3.3226527570789868, "percentage": 66.45, "elapsed_time": "0:59:02", "remaining_time": "0:29:48", "throughput": 5155.63, "total_tokens": 18264064} {"current_steps": 4460, "total_steps": 6710, "loss": 0.142, "lr": 6.31769956017353e-07, "epoch": 3.323397913561848, "percentage": 66.47, "elapsed_time": "0:59:03", "remaining_time": "0:29:47", "throughput": 5155.65, "total_tokens": 18268160} {"current_steps": 4461, "total_steps": 6710, "loss": 0.1476, "lr": 6.312613703244599e-07, "epoch": 3.3241430700447094, "percentage": 66.48, "elapsed_time": "0:59:04", "remaining_time": "0:29:46", "throughput": 5155.67, "total_tokens": 18272256} {"current_steps": 4462, "total_steps": 6710, "loss": 0.2689, "lr": 6.307529202634924e-07, "epoch": 3.3248882265275705, "percentage": 66.5, "elapsed_time": "0:59:04", "remaining_time": "0:29:45", "throughput": 5155.69, "total_tokens": 18276352} {"current_steps": 4463, "total_steps": 6710, "loss": 0.2441, "lr": 6.302446059459069e-07, "epoch": 3.325633383010432, "percentage": 66.51, "elapsed_time": "0:59:05", "remaining_time": "0:29:45", "throughput": 5155.7, "total_tokens": 18280448} {"current_steps": 4464, "total_steps": 6710, "loss": 0.3234, "lr": 6.297364274831288e-07, "epoch": 3.3263785394932937, "percentage": 66.53, "elapsed_time": "0:59:06", "remaining_time": "0:29:44", "throughput": 5155.71, "total_tokens": 18284544} {"current_steps": 4465, "total_steps": 6710, "loss": 0.1379, "lr": 6.292283849865555e-07, "epoch": 3.327123695976155, "percentage": 66.54, "elapsed_time": "0:59:07", "remaining_time": "0:29:43", "throughput": 5155.73, "total_tokens": 18288640} {"current_steps": 4466, "total_steps": 6710, "loss": 0.2704, "lr": 6.287204785675524e-07, "epoch": 3.3278688524590163, "percentage": 66.56, "elapsed_time": "0:59:08", "remaining_time": "0:29:42", "throughput": 5155.75, "total_tokens": 18292736} {"current_steps": 4467, "total_steps": 6710, "loss": 0.2455, "lr": 6.282127083374575e-07, "epoch": 3.328614008941878, "percentage": 66.57, "elapsed_time": "0:59:08", "remaining_time": "0:29:41", "throughput": 5155.75, "total_tokens": 18296832} {"current_steps": 4468, "total_steps": 6710, "loss": 0.1337, "lr": 6.277050744075762e-07, "epoch": 3.329359165424739, "percentage": 66.59, "elapsed_time": "0:59:09", "remaining_time": "0:29:41", "throughput": 5155.77, "total_tokens": 18300928} {"current_steps": 4469, "total_steps": 6710, "loss": 0.1038, "lr": 6.271975768891865e-07, "epoch": 3.3301043219076005, "percentage": 66.6, "elapsed_time": "0:59:10", "remaining_time": "0:29:40", "throughput": 5155.79, "total_tokens": 18305024} {"current_steps": 4470, "total_steps": 6710, "loss": 0.1509, "lr": 6.266902158935347e-07, "epoch": 3.330849478390462, "percentage": 66.62, "elapsed_time": "0:59:11", "remaining_time": "0:29:39", "throughput": 5155.81, "total_tokens": 18309120} {"current_steps": 4471, "total_steps": 6710, "loss": 0.209, "lr": 6.261829915318387e-07, "epoch": 3.3315946348733236, "percentage": 66.63, "elapsed_time": "0:59:11", "remaining_time": "0:29:38", "throughput": 5155.83, "total_tokens": 18313216} {"current_steps": 4472, "total_steps": 6710, "loss": 0.2235, "lr": 6.256759039152857e-07, "epoch": 3.3323397913561847, "percentage": 66.65, "elapsed_time": "0:59:12", "remaining_time": "0:29:37", "throughput": 5155.84, "total_tokens": 18317312} {"current_steps": 4473, "total_steps": 6710, "loss": 0.1562, "lr": 6.25168953155032e-07, "epoch": 3.3330849478390463, "percentage": 66.66, "elapsed_time": "0:59:13", "remaining_time": "0:29:37", "throughput": 5155.86, "total_tokens": 18321408} {"current_steps": 4474, "total_steps": 6710, "loss": 0.1884, "lr": 6.24662139362206e-07, "epoch": 3.3338301043219074, "percentage": 66.68, "elapsed_time": "0:59:14", "remaining_time": "0:29:36", "throughput": 5155.87, "total_tokens": 18325504} {"current_steps": 4475, "total_steps": 6710, "loss": 0.1655, "lr": 6.241554626479039e-07, "epoch": 3.334575260804769, "percentage": 66.69, "elapsed_time": "0:59:15", "remaining_time": "0:29:35", "throughput": 5155.89, "total_tokens": 18329600} {"current_steps": 4476, "total_steps": 6710, "loss": 0.1708, "lr": 6.236489231231937e-07, "epoch": 3.3353204172876305, "percentage": 66.71, "elapsed_time": "0:59:15", "remaining_time": "0:29:34", "throughput": 5155.9, "total_tokens": 18333696} {"current_steps": 4477, "total_steps": 6710, "loss": 0.1189, "lr": 6.231425208991117e-07, "epoch": 3.3360655737704916, "percentage": 66.72, "elapsed_time": "0:59:16", "remaining_time": "0:29:33", "throughput": 5155.92, "total_tokens": 18337792} {"current_steps": 4478, "total_steps": 6710, "loss": 0.2112, "lr": 6.226362560866659e-07, "epoch": 3.336810730253353, "percentage": 66.74, "elapsed_time": "0:59:17", "remaining_time": "0:29:33", "throughput": 5155.94, "total_tokens": 18341888} {"current_steps": 4479, "total_steps": 6710, "loss": 0.0639, "lr": 6.221301287968322e-07, "epoch": 3.3375558867362147, "percentage": 66.75, "elapsed_time": "0:59:18", "remaining_time": "0:29:32", "throughput": 5155.96, "total_tokens": 18345984} {"current_steps": 4480, "total_steps": 6710, "loss": 0.0611, "lr": 6.216241391405574e-07, "epoch": 3.338301043219076, "percentage": 66.77, "elapsed_time": "0:59:18", "remaining_time": "0:29:31", "throughput": 5155.98, "total_tokens": 18350080} {"current_steps": 4481, "total_steps": 6710, "loss": 0.0741, "lr": 6.211182872287587e-07, "epoch": 3.3390461997019374, "percentage": 66.78, "elapsed_time": "0:59:19", "remaining_time": "0:29:30", "throughput": 5156.0, "total_tokens": 18354176} {"current_steps": 4482, "total_steps": 6710, "loss": 0.2098, "lr": 6.206125731723221e-07, "epoch": 3.339791356184799, "percentage": 66.8, "elapsed_time": "0:59:20", "remaining_time": "0:29:29", "throughput": 5156.01, "total_tokens": 18358272} {"current_steps": 4483, "total_steps": 6710, "loss": 0.1264, "lr": 6.201069970821037e-07, "epoch": 3.34053651266766, "percentage": 66.81, "elapsed_time": "0:59:21", "remaining_time": "0:29:29", "throughput": 5156.03, "total_tokens": 18362368} {"current_steps": 4484, "total_steps": 6710, "loss": 0.3029, "lr": 6.196015590689289e-07, "epoch": 3.3412816691505216, "percentage": 66.83, "elapsed_time": "0:59:22", "remaining_time": "0:29:28", "throughput": 5156.05, "total_tokens": 18366464} {"current_steps": 4485, "total_steps": 6710, "loss": 0.2296, "lr": 6.190962592435942e-07, "epoch": 3.342026825633383, "percentage": 66.84, "elapsed_time": "0:59:22", "remaining_time": "0:29:27", "throughput": 5156.07, "total_tokens": 18370560} {"current_steps": 4486, "total_steps": 6710, "loss": 0.2156, "lr": 6.185910977168642e-07, "epoch": 3.3427719821162443, "percentage": 66.86, "elapsed_time": "0:59:23", "remaining_time": "0:29:26", "throughput": 5156.09, "total_tokens": 18374656} {"current_steps": 4487, "total_steps": 6710, "loss": 0.4046, "lr": 6.180860745994746e-07, "epoch": 3.343517138599106, "percentage": 66.87, "elapsed_time": "0:59:24", "remaining_time": "0:29:25", "throughput": 5156.11, "total_tokens": 18378752} {"current_steps": 4488, "total_steps": 6710, "loss": 0.1756, "lr": 6.175811900021293e-07, "epoch": 3.3442622950819674, "percentage": 66.89, "elapsed_time": "0:59:25", "remaining_time": "0:29:25", "throughput": 5156.13, "total_tokens": 18382848} {"current_steps": 4489, "total_steps": 6710, "loss": 0.0682, "lr": 6.170764440355035e-07, "epoch": 3.3450074515648285, "percentage": 66.9, "elapsed_time": "0:59:26", "remaining_time": "0:29:24", "throughput": 5156.15, "total_tokens": 18386944} {"current_steps": 4490, "total_steps": 6710, "loss": 0.2264, "lr": 6.165718368102407e-07, "epoch": 3.34575260804769, "percentage": 66.92, "elapsed_time": "0:59:26", "remaining_time": "0:29:23", "throughput": 5156.17, "total_tokens": 18391040} {"current_steps": 4491, "total_steps": 6710, "loss": 0.0618, "lr": 6.160673684369538e-07, "epoch": 3.3464977645305516, "percentage": 66.93, "elapsed_time": "0:59:27", "remaining_time": "0:29:22", "throughput": 5156.19, "total_tokens": 18395136} {"current_steps": 4492, "total_steps": 6710, "loss": 0.1036, "lr": 6.155630390262268e-07, "epoch": 3.3472429210134127, "percentage": 66.94, "elapsed_time": "0:59:28", "remaining_time": "0:29:21", "throughput": 5156.21, "total_tokens": 18399232} {"current_steps": 4493, "total_steps": 6710, "loss": 0.2023, "lr": 6.150588486886115e-07, "epoch": 3.3479880774962743, "percentage": 66.96, "elapsed_time": "0:59:29", "remaining_time": "0:29:21", "throughput": 5156.23, "total_tokens": 18403328} {"current_steps": 4494, "total_steps": 6710, "loss": 0.2334, "lr": 6.145547975346315e-07, "epoch": 3.348733233979136, "percentage": 66.97, "elapsed_time": "0:59:29", "remaining_time": "0:29:20", "throughput": 5156.24, "total_tokens": 18407424} {"current_steps": 4495, "total_steps": 6710, "loss": 0.3185, "lr": 6.140508856747763e-07, "epoch": 3.349478390461997, "percentage": 66.99, "elapsed_time": "0:59:30", "remaining_time": "0:29:19", "throughput": 5156.25, "total_tokens": 18411520} {"current_steps": 4496, "total_steps": 6710, "loss": 0.1147, "lr": 6.135471132195086e-07, "epoch": 3.3502235469448585, "percentage": 67.0, "elapsed_time": "0:59:31", "remaining_time": "0:29:18", "throughput": 5156.27, "total_tokens": 18415616} {"current_steps": 4497, "total_steps": 6710, "loss": 0.3803, "lr": 6.13043480279258e-07, "epoch": 3.3509687034277196, "percentage": 67.02, "elapsed_time": "0:59:32", "remaining_time": "0:29:17", "throughput": 5156.29, "total_tokens": 18419712} {"current_steps": 4498, "total_steps": 6710, "loss": 0.0964, "lr": 6.125399869644251e-07, "epoch": 3.351713859910581, "percentage": 67.03, "elapsed_time": "0:59:33", "remaining_time": "0:29:17", "throughput": 5156.31, "total_tokens": 18423808} {"current_steps": 4499, "total_steps": 6710, "loss": 0.4207, "lr": 6.120366333853791e-07, "epoch": 3.3524590163934427, "percentage": 67.05, "elapsed_time": "0:59:33", "remaining_time": "0:29:16", "throughput": 5156.33, "total_tokens": 18427904} {"current_steps": 4500, "total_steps": 6710, "loss": 0.2439, "lr": 6.115334196524578e-07, "epoch": 3.3532041728763042, "percentage": 67.06, "elapsed_time": "0:59:34", "remaining_time": "0:29:15", "throughput": 5156.34, "total_tokens": 18432000} {"current_steps": 4501, "total_steps": 6710, "loss": 0.2999, "lr": 6.110303458759706e-07, "epoch": 3.3539493293591653, "percentage": 67.08, "elapsed_time": "0:59:35", "remaining_time": "0:29:14", "throughput": 5156.36, "total_tokens": 18436096} {"current_steps": 4502, "total_steps": 6710, "loss": 0.0654, "lr": 6.105274121661937e-07, "epoch": 3.354694485842027, "percentage": 67.09, "elapsed_time": "0:59:36", "remaining_time": "0:29:13", "throughput": 5156.38, "total_tokens": 18440192} {"current_steps": 4503, "total_steps": 6710, "loss": 0.1507, "lr": 6.100246186333748e-07, "epoch": 3.355439642324888, "percentage": 67.11, "elapsed_time": "0:59:36", "remaining_time": "0:29:13", "throughput": 5156.4, "total_tokens": 18444288} {"current_steps": 4504, "total_steps": 6710, "loss": 0.1643, "lr": 6.095219653877289e-07, "epoch": 3.3561847988077496, "percentage": 67.12, "elapsed_time": "0:59:37", "remaining_time": "0:29:12", "throughput": 5156.42, "total_tokens": 18448384} {"current_steps": 4505, "total_steps": 6710, "loss": 0.0892, "lr": 6.09019452539442e-07, "epoch": 3.356929955290611, "percentage": 67.14, "elapsed_time": "0:59:38", "remaining_time": "0:29:11", "throughput": 5156.44, "total_tokens": 18452480} {"current_steps": 4506, "total_steps": 6710, "loss": 0.1394, "lr": 6.085170801986681e-07, "epoch": 3.3576751117734727, "percentage": 67.15, "elapsed_time": "0:59:39", "remaining_time": "0:29:10", "throughput": 5156.46, "total_tokens": 18456576} {"current_steps": 4507, "total_steps": 6710, "loss": 0.1298, "lr": 6.080148484755305e-07, "epoch": 3.3584202682563338, "percentage": 67.17, "elapsed_time": "0:59:40", "remaining_time": "0:29:09", "throughput": 5156.47, "total_tokens": 18460672} {"current_steps": 4508, "total_steps": 6710, "loss": 0.0489, "lr": 6.075127574801226e-07, "epoch": 3.3591654247391953, "percentage": 67.18, "elapsed_time": "0:59:40", "remaining_time": "0:29:09", "throughput": 5156.49, "total_tokens": 18464768} {"current_steps": 4509, "total_steps": 6710, "loss": 0.1093, "lr": 6.070108073225062e-07, "epoch": 3.3599105812220564, "percentage": 67.2, "elapsed_time": "0:59:41", "remaining_time": "0:29:08", "throughput": 5156.5, "total_tokens": 18468864} {"current_steps": 4510, "total_steps": 6710, "loss": 0.1762, "lr": 6.06508998112712e-07, "epoch": 3.360655737704918, "percentage": 67.21, "elapsed_time": "0:59:42", "remaining_time": "0:29:07", "throughput": 5156.52, "total_tokens": 18472960} {"current_steps": 4511, "total_steps": 6710, "loss": 0.3333, "lr": 6.060073299607399e-07, "epoch": 3.3614008941877795, "percentage": 67.23, "elapsed_time": "0:59:43", "remaining_time": "0:29:06", "throughput": 5156.54, "total_tokens": 18477056} {"current_steps": 4512, "total_steps": 6710, "loss": 0.1146, "lr": 6.055058029765602e-07, "epoch": 3.3621460506706407, "percentage": 67.24, "elapsed_time": "0:59:44", "remaining_time": "0:29:05", "throughput": 5156.56, "total_tokens": 18481152} {"current_steps": 4513, "total_steps": 6710, "loss": 0.1966, "lr": 6.0500441727011e-07, "epoch": 3.362891207153502, "percentage": 67.26, "elapsed_time": "0:59:44", "remaining_time": "0:29:05", "throughput": 5156.57, "total_tokens": 18485248} {"current_steps": 4514, "total_steps": 6710, "loss": 0.1506, "lr": 6.045031729512978e-07, "epoch": 3.3636363636363638, "percentage": 67.27, "elapsed_time": "0:59:45", "remaining_time": "0:29:04", "throughput": 5156.59, "total_tokens": 18489344} {"current_steps": 4515, "total_steps": 6710, "loss": 0.2168, "lr": 6.040020701299989e-07, "epoch": 3.364381520119225, "percentage": 67.29, "elapsed_time": "0:59:46", "remaining_time": "0:29:03", "throughput": 5156.61, "total_tokens": 18493440} {"current_steps": 4516, "total_steps": 6710, "loss": 0.1479, "lr": 6.035011089160593e-07, "epoch": 3.3651266766020864, "percentage": 67.3, "elapsed_time": "0:59:47", "remaining_time": "0:29:02", "throughput": 5156.63, "total_tokens": 18497536} {"current_steps": 4517, "total_steps": 6710, "loss": 0.1597, "lr": 6.030002894192932e-07, "epoch": 3.365871833084948, "percentage": 67.32, "elapsed_time": "0:59:47", "remaining_time": "0:29:01", "throughput": 5156.65, "total_tokens": 18501632} {"current_steps": 4518, "total_steps": 6710, "loss": 0.1298, "lr": 6.024996117494831e-07, "epoch": 3.366616989567809, "percentage": 67.33, "elapsed_time": "0:59:48", "remaining_time": "0:29:01", "throughput": 5156.67, "total_tokens": 18505728} {"current_steps": 4519, "total_steps": 6710, "loss": 0.1653, "lr": 6.019990760163823e-07, "epoch": 3.3673621460506706, "percentage": 67.35, "elapsed_time": "0:59:49", "remaining_time": "0:29:00", "throughput": 5156.69, "total_tokens": 18509824} {"current_steps": 4520, "total_steps": 6710, "loss": 0.2201, "lr": 6.014986823297106e-07, "epoch": 3.368107302533532, "percentage": 67.36, "elapsed_time": "0:59:50", "remaining_time": "0:28:59", "throughput": 5156.7, "total_tokens": 18513920} {"current_steps": 4521, "total_steps": 6710, "loss": 0.3117, "lr": 6.009984307991594e-07, "epoch": 3.3688524590163933, "percentage": 67.38, "elapsed_time": "0:59:51", "remaining_time": "0:28:58", "throughput": 5156.72, "total_tokens": 18518016} {"current_steps": 4522, "total_steps": 6710, "loss": 0.2084, "lr": 6.004983215343854e-07, "epoch": 3.369597615499255, "percentage": 67.39, "elapsed_time": "0:59:51", "remaining_time": "0:28:57", "throughput": 5156.74, "total_tokens": 18522112} {"current_steps": 4523, "total_steps": 6710, "loss": 0.1479, "lr": 5.99998354645018e-07, "epoch": 3.3703427719821164, "percentage": 67.41, "elapsed_time": "0:59:52", "remaining_time": "0:28:57", "throughput": 5156.76, "total_tokens": 18526208} {"current_steps": 4524, "total_steps": 6710, "loss": 0.3165, "lr": 5.994985302406518e-07, "epoch": 3.3710879284649775, "percentage": 67.42, "elapsed_time": "0:59:53", "remaining_time": "0:28:56", "throughput": 5156.78, "total_tokens": 18530304} {"current_steps": 4525, "total_steps": 6710, "loss": 0.0966, "lr": 5.989988484308534e-07, "epoch": 3.371833084947839, "percentage": 67.44, "elapsed_time": "0:59:54", "remaining_time": "0:28:55", "throughput": 5156.8, "total_tokens": 18534400} {"current_steps": 4526, "total_steps": 6710, "loss": 0.1641, "lr": 5.98499309325156e-07, "epoch": 3.3725782414307006, "percentage": 67.45, "elapsed_time": "0:59:54", "remaining_time": "0:28:54", "throughput": 5156.81, "total_tokens": 18538496} {"current_steps": 4527, "total_steps": 6710, "loss": 0.3218, "lr": 5.979999130330617e-07, "epoch": 3.3733233979135617, "percentage": 67.47, "elapsed_time": "0:59:55", "remaining_time": "0:28:53", "throughput": 5156.83, "total_tokens": 18542592} {"current_steps": 4528, "total_steps": 6710, "loss": 0.1162, "lr": 5.975006596640425e-07, "epoch": 3.3740685543964233, "percentage": 67.48, "elapsed_time": "0:59:56", "remaining_time": "0:28:53", "throughput": 5156.84, "total_tokens": 18546688} {"current_steps": 4529, "total_steps": 6710, "loss": 0.1477, "lr": 5.970015493275375e-07, "epoch": 3.374813710879285, "percentage": 67.5, "elapsed_time": "0:59:57", "remaining_time": "0:28:52", "throughput": 5156.86, "total_tokens": 18550784} {"current_steps": 4530, "total_steps": 6710, "loss": 0.0205, "lr": 5.965025821329563e-07, "epoch": 3.375558867362146, "percentage": 67.51, "elapsed_time": "0:59:58", "remaining_time": "0:28:51", "throughput": 5156.87, "total_tokens": 18554880} {"current_steps": 4531, "total_steps": 6710, "loss": 0.0661, "lr": 5.960037581896751e-07, "epoch": 3.3763040238450075, "percentage": 67.53, "elapsed_time": "0:59:58", "remaining_time": "0:28:50", "throughput": 5156.88, "total_tokens": 18558976} {"current_steps": 4532, "total_steps": 6710, "loss": 0.103, "lr": 5.955050776070404e-07, "epoch": 3.3770491803278686, "percentage": 67.54, "elapsed_time": "0:59:59", "remaining_time": "0:28:49", "throughput": 5156.89, "total_tokens": 18563072} {"current_steps": 4533, "total_steps": 6710, "loss": 0.106, "lr": 5.950065404943661e-07, "epoch": 3.37779433681073, "percentage": 67.56, "elapsed_time": "1:00:00", "remaining_time": "0:28:49", "throughput": 5156.91, "total_tokens": 18567168} {"current_steps": 4534, "total_steps": 6710, "loss": 0.2297, "lr": 5.945081469609354e-07, "epoch": 3.3785394932935917, "percentage": 67.57, "elapsed_time": "1:00:01", "remaining_time": "0:28:48", "throughput": 5156.92, "total_tokens": 18571264} {"current_steps": 4535, "total_steps": 6710, "loss": 0.1373, "lr": 5.94009897115999e-07, "epoch": 3.3792846497764533, "percentage": 67.59, "elapsed_time": "1:00:02", "remaining_time": "0:28:47", "throughput": 5156.94, "total_tokens": 18575360} {"current_steps": 4536, "total_steps": 6710, "loss": 0.1309, "lr": 5.935117910687776e-07, "epoch": 3.3800298062593144, "percentage": 67.6, "elapsed_time": "1:00:02", "remaining_time": "0:28:46", "throughput": 5156.95, "total_tokens": 18579456} {"current_steps": 4537, "total_steps": 6710, "loss": 0.2036, "lr": 5.930138289284596e-07, "epoch": 3.380774962742176, "percentage": 67.62, "elapsed_time": "1:00:03", "remaining_time": "0:28:45", "throughput": 5156.98, "total_tokens": 18583552} {"current_steps": 4538, "total_steps": 6710, "loss": 0.0922, "lr": 5.925160108042009e-07, "epoch": 3.381520119225037, "percentage": 67.63, "elapsed_time": "1:00:04", "remaining_time": "0:28:45", "throughput": 5156.99, "total_tokens": 18587648} {"current_steps": 4539, "total_steps": 6710, "loss": 0.0111, "lr": 5.920183368051281e-07, "epoch": 3.3822652757078986, "percentage": 67.65, "elapsed_time": "1:00:05", "remaining_time": "0:28:44", "throughput": 5157.01, "total_tokens": 18591744} {"current_steps": 4540, "total_steps": 6710, "loss": 0.0701, "lr": 5.915208070403339e-07, "epoch": 3.38301043219076, "percentage": 67.66, "elapsed_time": "1:00:05", "remaining_time": "0:28:43", "throughput": 5157.02, "total_tokens": 18595840} {"current_steps": 4541, "total_steps": 6710, "loss": 0.3225, "lr": 5.910234216188811e-07, "epoch": 3.3837555886736217, "percentage": 67.68, "elapsed_time": "1:00:06", "remaining_time": "0:28:42", "throughput": 5157.04, "total_tokens": 18599936} {"current_steps": 4542, "total_steps": 6710, "loss": 0.2733, "lr": 5.905261806497993e-07, "epoch": 3.384500745156483, "percentage": 67.69, "elapsed_time": "1:00:07", "remaining_time": "0:28:41", "throughput": 5157.05, "total_tokens": 18604032} {"current_steps": 4543, "total_steps": 6710, "loss": 0.048, "lr": 5.900290842420883e-07, "epoch": 3.3852459016393444, "percentage": 67.7, "elapsed_time": "1:00:08", "remaining_time": "0:28:41", "throughput": 5157.06, "total_tokens": 18608128} {"current_steps": 4544, "total_steps": 6710, "loss": 0.1014, "lr": 5.895321325047146e-07, "epoch": 3.3859910581222055, "percentage": 67.72, "elapsed_time": "1:00:09", "remaining_time": "0:28:40", "throughput": 5157.08, "total_tokens": 18612224} {"current_steps": 4545, "total_steps": 6710, "loss": 0.1949, "lr": 5.890353255466131e-07, "epoch": 3.386736214605067, "percentage": 67.73, "elapsed_time": "1:00:09", "remaining_time": "0:28:39", "throughput": 5157.1, "total_tokens": 18616320} {"current_steps": 4546, "total_steps": 6710, "loss": 0.1081, "lr": 5.885386634766886e-07, "epoch": 3.3874813710879286, "percentage": 67.75, "elapsed_time": "1:00:10", "remaining_time": "0:28:38", "throughput": 5157.11, "total_tokens": 18620416} {"current_steps": 4547, "total_steps": 6710, "loss": 0.1044, "lr": 5.880421464038118e-07, "epoch": 3.3882265275707897, "percentage": 67.76, "elapsed_time": "1:00:11", "remaining_time": "0:28:37", "throughput": 5157.13, "total_tokens": 18624512} {"current_steps": 4548, "total_steps": 6710, "loss": 0.1026, "lr": 5.875457744368242e-07, "epoch": 3.3889716840536512, "percentage": 67.78, "elapsed_time": "1:00:12", "remaining_time": "0:28:37", "throughput": 5157.14, "total_tokens": 18628608} {"current_steps": 4549, "total_steps": 6710, "loss": 0.2331, "lr": 5.870495476845321e-07, "epoch": 3.389716840536513, "percentage": 67.79, "elapsed_time": "1:00:12", "remaining_time": "0:28:36", "throughput": 5157.15, "total_tokens": 18632704} {"current_steps": 4550, "total_steps": 6710, "loss": 0.2625, "lr": 5.865534662557137e-07, "epoch": 3.390461997019374, "percentage": 67.81, "elapsed_time": "1:00:13", "remaining_time": "0:28:35", "throughput": 5157.15, "total_tokens": 18636800} {"current_steps": 4551, "total_steps": 6710, "loss": 0.189, "lr": 5.860575302591124e-07, "epoch": 3.3912071535022354, "percentage": 67.82, "elapsed_time": "1:00:14", "remaining_time": "0:28:34", "throughput": 5157.16, "total_tokens": 18640896} {"current_steps": 4552, "total_steps": 6710, "loss": 0.1965, "lr": 5.855617398034418e-07, "epoch": 3.391952309985097, "percentage": 67.84, "elapsed_time": "1:00:15", "remaining_time": "0:28:33", "throughput": 5157.18, "total_tokens": 18644992} {"current_steps": 4553, "total_steps": 6710, "loss": 0.4157, "lr": 5.850660949973825e-07, "epoch": 3.392697466467958, "percentage": 67.85, "elapsed_time": "1:00:16", "remaining_time": "0:28:33", "throughput": 5157.2, "total_tokens": 18649088} {"current_steps": 4554, "total_steps": 6710, "loss": 0.2536, "lr": 5.845705959495828e-07, "epoch": 3.3934426229508197, "percentage": 67.87, "elapsed_time": "1:00:16", "remaining_time": "0:28:32", "throughput": 5157.22, "total_tokens": 18653184} {"current_steps": 4555, "total_steps": 6710, "loss": 0.267, "lr": 5.840752427686605e-07, "epoch": 3.394187779433681, "percentage": 67.88, "elapsed_time": "1:00:17", "remaining_time": "0:28:31", "throughput": 5157.24, "total_tokens": 18657280} {"current_steps": 4556, "total_steps": 6710, "loss": 0.2778, "lr": 5.835800355631996e-07, "epoch": 3.3949329359165423, "percentage": 67.9, "elapsed_time": "1:00:18", "remaining_time": "0:28:30", "throughput": 5157.26, "total_tokens": 18661376} {"current_steps": 4557, "total_steps": 6710, "loss": 0.2011, "lr": 5.830849744417539e-07, "epoch": 3.395678092399404, "percentage": 67.91, "elapsed_time": "1:00:19", "remaining_time": "0:28:29", "throughput": 5157.27, "total_tokens": 18665472} {"current_steps": 4558, "total_steps": 6710, "loss": 0.2435, "lr": 5.825900595128438e-07, "epoch": 3.3964232488822654, "percentage": 67.93, "elapsed_time": "1:00:20", "remaining_time": "0:28:29", "throughput": 5157.29, "total_tokens": 18669568} {"current_steps": 4559, "total_steps": 6710, "loss": 0.3691, "lr": 5.820952908849586e-07, "epoch": 3.3971684053651265, "percentage": 67.94, "elapsed_time": "1:00:20", "remaining_time": "0:28:28", "throughput": 5157.31, "total_tokens": 18673664} {"current_steps": 4560, "total_steps": 6710, "loss": 0.1504, "lr": 5.816006686665547e-07, "epoch": 3.397913561847988, "percentage": 67.96, "elapsed_time": "1:00:21", "remaining_time": "0:28:27", "throughput": 5157.33, "total_tokens": 18677760} {"current_steps": 4561, "total_steps": 6710, "loss": 0.1018, "lr": 5.811061929660577e-07, "epoch": 3.3986587183308496, "percentage": 67.97, "elapsed_time": "1:00:22", "remaining_time": "0:28:26", "throughput": 5157.34, "total_tokens": 18681856} {"current_steps": 4562, "total_steps": 6710, "loss": 0.2208, "lr": 5.806118638918588e-07, "epoch": 3.3994038748137108, "percentage": 67.99, "elapsed_time": "1:00:23", "remaining_time": "0:28:25", "throughput": 5157.36, "total_tokens": 18685952} {"current_steps": 4563, "total_steps": 6710, "loss": 0.0945, "lr": 5.801176815523196e-07, "epoch": 3.4001490312965723, "percentage": 68.0, "elapsed_time": "1:00:23", "remaining_time": "0:28:25", "throughput": 5157.38, "total_tokens": 18690048} {"current_steps": 4564, "total_steps": 6710, "loss": 0.1476, "lr": 5.79623646055768e-07, "epoch": 3.400894187779434, "percentage": 68.02, "elapsed_time": "1:00:24", "remaining_time": "0:28:24", "throughput": 5157.4, "total_tokens": 18694144} {"current_steps": 4565, "total_steps": 6710, "loss": 0.2297, "lr": 5.791297575104995e-07, "epoch": 3.401639344262295, "percentage": 68.03, "elapsed_time": "1:00:25", "remaining_time": "0:28:23", "throughput": 5157.41, "total_tokens": 18698240} {"current_steps": 4566, "total_steps": 6710, "loss": 0.149, "lr": 5.786360160247792e-07, "epoch": 3.4023845007451565, "percentage": 68.05, "elapsed_time": "1:00:26", "remaining_time": "0:28:22", "throughput": 5157.43, "total_tokens": 18702336} {"current_steps": 4567, "total_steps": 6710, "loss": 0.1841, "lr": 5.781424217068376e-07, "epoch": 3.4031296572280176, "percentage": 68.06, "elapsed_time": "1:00:27", "remaining_time": "0:28:21", "throughput": 5157.45, "total_tokens": 18706432} {"current_steps": 4568, "total_steps": 6710, "loss": 0.0983, "lr": 5.776489746648752e-07, "epoch": 3.403874813710879, "percentage": 68.08, "elapsed_time": "1:00:27", "remaining_time": "0:28:21", "throughput": 5157.46, "total_tokens": 18710528} {"current_steps": 4569, "total_steps": 6710, "loss": 0.1182, "lr": 5.771556750070581e-07, "epoch": 3.4046199701937407, "percentage": 68.09, "elapsed_time": "1:00:28", "remaining_time": "0:28:20", "throughput": 5157.48, "total_tokens": 18714624} {"current_steps": 4570, "total_steps": 6710, "loss": 0.2394, "lr": 5.766625228415221e-07, "epoch": 3.4053651266766023, "percentage": 68.11, "elapsed_time": "1:00:29", "remaining_time": "0:28:19", "throughput": 5157.5, "total_tokens": 18718720} {"current_steps": 4571, "total_steps": 6710, "loss": 0.2344, "lr": 5.761695182763689e-07, "epoch": 3.4061102831594634, "percentage": 68.12, "elapsed_time": "1:00:30", "remaining_time": "0:28:18", "throughput": 5157.52, "total_tokens": 18722816} {"current_steps": 4572, "total_steps": 6710, "loss": 0.1882, "lr": 5.756766614196686e-07, "epoch": 3.406855439642325, "percentage": 68.14, "elapsed_time": "1:00:30", "remaining_time": "0:28:17", "throughput": 5157.53, "total_tokens": 18726912} {"current_steps": 4573, "total_steps": 6710, "loss": 0.3477, "lr": 5.751839523794598e-07, "epoch": 3.407600596125186, "percentage": 68.15, "elapsed_time": "1:00:31", "remaining_time": "0:28:17", "throughput": 5157.55, "total_tokens": 18731008} {"current_steps": 4574, "total_steps": 6710, "loss": 0.1063, "lr": 5.746913912637466e-07, "epoch": 3.4083457526080476, "percentage": 68.17, "elapsed_time": "1:00:32", "remaining_time": "0:28:16", "throughput": 5157.57, "total_tokens": 18735104} {"current_steps": 4575, "total_steps": 6710, "loss": 0.1532, "lr": 5.741989781805035e-07, "epoch": 3.409090909090909, "percentage": 68.18, "elapsed_time": "1:00:33", "remaining_time": "0:28:15", "throughput": 5157.59, "total_tokens": 18739200} {"current_steps": 4576, "total_steps": 6710, "loss": 0.2176, "lr": 5.737067132376692e-07, "epoch": 3.4098360655737707, "percentage": 68.2, "elapsed_time": "1:00:34", "remaining_time": "0:28:14", "throughput": 5157.6, "total_tokens": 18743296} {"current_steps": 4577, "total_steps": 6710, "loss": 0.1527, "lr": 5.73214596543153e-07, "epoch": 3.410581222056632, "percentage": 68.21, "elapsed_time": "1:00:34", "remaining_time": "0:28:13", "throughput": 5157.62, "total_tokens": 18747392} {"current_steps": 4578, "total_steps": 6710, "loss": 0.2357, "lr": 5.727226282048293e-07, "epoch": 3.4113263785394934, "percentage": 68.23, "elapsed_time": "1:00:35", "remaining_time": "0:28:13", "throughput": 5157.63, "total_tokens": 18751488} {"current_steps": 4579, "total_steps": 6710, "loss": 0.067, "lr": 5.722308083305423e-07, "epoch": 3.4120715350223545, "percentage": 68.24, "elapsed_time": "1:00:36", "remaining_time": "0:28:12", "throughput": 5157.65, "total_tokens": 18755584} {"current_steps": 4580, "total_steps": 6710, "loss": 0.2218, "lr": 5.717391370281012e-07, "epoch": 3.412816691505216, "percentage": 68.26, "elapsed_time": "1:00:37", "remaining_time": "0:28:11", "throughput": 5157.67, "total_tokens": 18759680} {"current_steps": 4581, "total_steps": 6710, "loss": 0.158, "lr": 5.71247614405285e-07, "epoch": 3.4135618479880776, "percentage": 68.27, "elapsed_time": "1:00:38", "remaining_time": "0:28:10", "throughput": 5157.69, "total_tokens": 18763776} {"current_steps": 4582, "total_steps": 6710, "loss": 0.1397, "lr": 5.707562405698385e-07, "epoch": 3.4143070044709387, "percentage": 68.29, "elapsed_time": "1:00:38", "remaining_time": "0:28:09", "throughput": 5157.7, "total_tokens": 18767872} {"current_steps": 4583, "total_steps": 6710, "loss": 0.1519, "lr": 5.702650156294738e-07, "epoch": 3.4150521609538003, "percentage": 68.3, "elapsed_time": "1:00:39", "remaining_time": "0:28:09", "throughput": 5157.72, "total_tokens": 18771968} {"current_steps": 4584, "total_steps": 6710, "loss": 0.1341, "lr": 5.697739396918719e-07, "epoch": 3.415797317436662, "percentage": 68.32, "elapsed_time": "1:00:40", "remaining_time": "0:28:08", "throughput": 5157.74, "total_tokens": 18776064} {"current_steps": 4585, "total_steps": 6710, "loss": 0.1856, "lr": 5.692830128646793e-07, "epoch": 3.416542473919523, "percentage": 68.33, "elapsed_time": "1:00:41", "remaining_time": "0:28:07", "throughput": 5157.76, "total_tokens": 18780160} {"current_steps": 4586, "total_steps": 6710, "loss": 0.2283, "lr": 5.687922352555115e-07, "epoch": 3.4172876304023845, "percentage": 68.35, "elapsed_time": "1:00:41", "remaining_time": "0:28:06", "throughput": 5157.78, "total_tokens": 18784256} {"current_steps": 4587, "total_steps": 6710, "loss": 0.1429, "lr": 5.683016069719494e-07, "epoch": 3.418032786885246, "percentage": 68.36, "elapsed_time": "1:00:42", "remaining_time": "0:28:05", "throughput": 5157.79, "total_tokens": 18788352} {"current_steps": 4588, "total_steps": 6710, "loss": 0.1543, "lr": 5.678111281215437e-07, "epoch": 3.418777943368107, "percentage": 68.38, "elapsed_time": "1:00:43", "remaining_time": "0:28:05", "throughput": 5157.81, "total_tokens": 18792448} {"current_steps": 4589, "total_steps": 6710, "loss": 0.2579, "lr": 5.673207988118092e-07, "epoch": 3.4195230998509687, "percentage": 68.39, "elapsed_time": "1:00:44", "remaining_time": "0:28:04", "throughput": 5157.83, "total_tokens": 18796544} {"current_steps": 4590, "total_steps": 6710, "loss": 0.278, "lr": 5.668306191502307e-07, "epoch": 3.4202682563338302, "percentage": 68.41, "elapsed_time": "1:00:45", "remaining_time": "0:28:03", "throughput": 5157.84, "total_tokens": 18800640} {"current_steps": 4591, "total_steps": 6710, "loss": 0.3, "lr": 5.663405892442587e-07, "epoch": 3.4210134128166914, "percentage": 68.42, "elapsed_time": "1:00:45", "remaining_time": "0:28:02", "throughput": 5157.85, "total_tokens": 18804736} {"current_steps": 4592, "total_steps": 6710, "loss": 0.217, "lr": 5.65850709201311e-07, "epoch": 3.421758569299553, "percentage": 68.44, "elapsed_time": "1:00:46", "remaining_time": "0:28:01", "throughput": 5157.86, "total_tokens": 18808832} {"current_steps": 4593, "total_steps": 6710, "loss": 0.1173, "lr": 5.653609791287736e-07, "epoch": 3.4225037257824145, "percentage": 68.45, "elapsed_time": "1:00:47", "remaining_time": "0:28:01", "throughput": 5157.88, "total_tokens": 18812928} {"current_steps": 4594, "total_steps": 6710, "loss": 0.1901, "lr": 5.648713991339976e-07, "epoch": 3.4232488822652756, "percentage": 68.46, "elapsed_time": "1:00:48", "remaining_time": "0:28:00", "throughput": 5157.9, "total_tokens": 18817024} {"current_steps": 4595, "total_steps": 6710, "loss": 0.145, "lr": 5.64381969324304e-07, "epoch": 3.423994038748137, "percentage": 68.48, "elapsed_time": "1:00:48", "remaining_time": "0:27:59", "throughput": 5157.92, "total_tokens": 18821120} {"current_steps": 4596, "total_steps": 6710, "loss": 0.0586, "lr": 5.638926898069777e-07, "epoch": 3.4247391952309987, "percentage": 68.49, "elapsed_time": "1:00:49", "remaining_time": "0:27:58", "throughput": 5157.93, "total_tokens": 18825216} {"current_steps": 4597, "total_steps": 6710, "loss": 0.1108, "lr": 5.634035606892737e-07, "epoch": 3.42548435171386, "percentage": 68.51, "elapsed_time": "1:00:50", "remaining_time": "0:27:57", "throughput": 5157.95, "total_tokens": 18829312} {"current_steps": 4598, "total_steps": 6710, "loss": 0.2871, "lr": 5.629145820784119e-07, "epoch": 3.4262295081967213, "percentage": 68.52, "elapsed_time": "1:00:51", "remaining_time": "0:27:57", "throughput": 5157.97, "total_tokens": 18833408} {"current_steps": 4599, "total_steps": 6710, "loss": 0.2638, "lr": 5.624257540815793e-07, "epoch": 3.426974664679583, "percentage": 68.54, "elapsed_time": "1:00:52", "remaining_time": "0:27:56", "throughput": 5157.99, "total_tokens": 18837504} {"current_steps": 4600, "total_steps": 6710, "loss": 0.062, "lr": 5.619370768059318e-07, "epoch": 3.427719821162444, "percentage": 68.55, "elapsed_time": "1:00:52", "remaining_time": "0:27:55", "throughput": 5158.01, "total_tokens": 18841600} {"current_steps": 4601, "total_steps": 6710, "loss": 0.1389, "lr": 5.614485503585897e-07, "epoch": 3.4284649776453056, "percentage": 68.57, "elapsed_time": "1:00:53", "remaining_time": "0:27:54", "throughput": 5158.03, "total_tokens": 18845696} {"current_steps": 4602, "total_steps": 6710, "loss": 0.1134, "lr": 5.60960174846643e-07, "epoch": 3.429210134128167, "percentage": 68.58, "elapsed_time": "1:00:54", "remaining_time": "0:27:53", "throughput": 5158.05, "total_tokens": 18849792} {"current_steps": 4603, "total_steps": 6710, "loss": 0.2102, "lr": 5.604719503771452e-07, "epoch": 3.429955290611028, "percentage": 68.6, "elapsed_time": "1:00:55", "remaining_time": "0:27:53", "throughput": 5158.07, "total_tokens": 18853888} {"current_steps": 4604, "total_steps": 6710, "loss": 0.1512, "lr": 5.599838770571201e-07, "epoch": 3.4307004470938898, "percentage": 68.61, "elapsed_time": "1:00:56", "remaining_time": "0:27:52", "throughput": 5158.08, "total_tokens": 18857984} {"current_steps": 4605, "total_steps": 6710, "loss": 0.194, "lr": 5.594959549935558e-07, "epoch": 3.4314456035767513, "percentage": 68.63, "elapsed_time": "1:00:56", "remaining_time": "0:27:51", "throughput": 5158.1, "total_tokens": 18862080} {"current_steps": 4606, "total_steps": 6710, "loss": 0.1305, "lr": 5.590081842934091e-07, "epoch": 3.4321907600596124, "percentage": 68.64, "elapsed_time": "1:00:57", "remaining_time": "0:27:50", "throughput": 5158.12, "total_tokens": 18866176} {"current_steps": 4607, "total_steps": 6710, "loss": 0.2546, "lr": 5.585205650636023e-07, "epoch": 3.432935916542474, "percentage": 68.66, "elapsed_time": "1:00:58", "remaining_time": "0:27:49", "throughput": 5158.14, "total_tokens": 18870272} {"current_steps": 4608, "total_steps": 6710, "loss": 0.1402, "lr": 5.580330974110257e-07, "epoch": 3.433681073025335, "percentage": 68.67, "elapsed_time": "1:00:59", "remaining_time": "0:27:49", "throughput": 5158.15, "total_tokens": 18874368} {"current_steps": 4609, "total_steps": 6710, "loss": 0.239, "lr": 5.575457814425351e-07, "epoch": 3.4344262295081966, "percentage": 68.69, "elapsed_time": "1:00:59", "remaining_time": "0:27:48", "throughput": 5158.16, "total_tokens": 18878464} {"current_steps": 4610, "total_steps": 6710, "loss": 0.1426, "lr": 5.570586172649533e-07, "epoch": 3.435171385991058, "percentage": 68.7, "elapsed_time": "1:01:00", "remaining_time": "0:27:47", "throughput": 5158.18, "total_tokens": 18882560} {"current_steps": 4611, "total_steps": 6710, "loss": 0.0861, "lr": 5.565716049850713e-07, "epoch": 3.4359165424739198, "percentage": 68.72, "elapsed_time": "1:01:01", "remaining_time": "0:27:46", "throughput": 5158.2, "total_tokens": 18886656} {"current_steps": 4612, "total_steps": 6710, "loss": 0.2126, "lr": 5.560847447096444e-07, "epoch": 3.436661698956781, "percentage": 68.73, "elapsed_time": "1:01:02", "remaining_time": "0:27:45", "throughput": 5158.22, "total_tokens": 18890752} {"current_steps": 4613, "total_steps": 6710, "loss": 0.0906, "lr": 5.55598036545397e-07, "epoch": 3.4374068554396424, "percentage": 68.75, "elapsed_time": "1:01:03", "remaining_time": "0:27:45", "throughput": 5158.23, "total_tokens": 18894848} {"current_steps": 4614, "total_steps": 6710, "loss": 0.4006, "lr": 5.551114805990179e-07, "epoch": 3.4381520119225035, "percentage": 68.76, "elapsed_time": "1:01:03", "remaining_time": "0:27:44", "throughput": 5158.25, "total_tokens": 18898944} {"current_steps": 4615, "total_steps": 6710, "loss": 0.1802, "lr": 5.546250769771651e-07, "epoch": 3.438897168405365, "percentage": 68.78, "elapsed_time": "1:01:04", "remaining_time": "0:27:43", "throughput": 5158.27, "total_tokens": 18903040} {"current_steps": 4616, "total_steps": 6710, "loss": 0.2791, "lr": 5.541388257864601e-07, "epoch": 3.4396423248882266, "percentage": 68.79, "elapsed_time": "1:01:05", "remaining_time": "0:27:42", "throughput": 5158.29, "total_tokens": 18907136} {"current_steps": 4617, "total_steps": 6710, "loss": 0.1532, "lr": 5.536527271334936e-07, "epoch": 3.4403874813710877, "percentage": 68.81, "elapsed_time": "1:01:06", "remaining_time": "0:27:41", "throughput": 5158.3, "total_tokens": 18911232} {"current_steps": 4618, "total_steps": 6710, "loss": 0.2651, "lr": 5.531667811248219e-07, "epoch": 3.4411326378539493, "percentage": 68.82, "elapsed_time": "1:01:06", "remaining_time": "0:27:41", "throughput": 5158.32, "total_tokens": 18915328} {"current_steps": 4619, "total_steps": 6710, "loss": 0.0357, "lr": 5.52680987866967e-07, "epoch": 3.441877794336811, "percentage": 68.84, "elapsed_time": "1:01:07", "remaining_time": "0:27:40", "throughput": 5158.34, "total_tokens": 18919424} {"current_steps": 4620, "total_steps": 6710, "loss": 0.2369, "lr": 5.521953474664194e-07, "epoch": 3.442622950819672, "percentage": 68.85, "elapsed_time": "1:01:08", "remaining_time": "0:27:39", "throughput": 5158.36, "total_tokens": 18923520} {"current_steps": 4621, "total_steps": 6710, "loss": 0.0886, "lr": 5.517098600296339e-07, "epoch": 3.4433681073025335, "percentage": 68.87, "elapsed_time": "1:01:09", "remaining_time": "0:27:38", "throughput": 5158.38, "total_tokens": 18927616} {"current_steps": 4622, "total_steps": 6710, "loss": 0.147, "lr": 5.512245256630338e-07, "epoch": 3.444113263785395, "percentage": 68.88, "elapsed_time": "1:01:10", "remaining_time": "0:27:37", "throughput": 5158.4, "total_tokens": 18931712} {"current_steps": 4623, "total_steps": 6710, "loss": 0.2004, "lr": 5.507393444730069e-07, "epoch": 3.444858420268256, "percentage": 68.9, "elapsed_time": "1:01:10", "remaining_time": "0:27:37", "throughput": 5158.41, "total_tokens": 18935808} {"current_steps": 4624, "total_steps": 6710, "loss": 0.1985, "lr": 5.502543165659094e-07, "epoch": 3.4456035767511177, "percentage": 68.91, "elapsed_time": "1:01:11", "remaining_time": "0:27:36", "throughput": 5158.43, "total_tokens": 18939904} {"current_steps": 4625, "total_steps": 6710, "loss": 0.1709, "lr": 5.497694420480622e-07, "epoch": 3.4463487332339793, "percentage": 68.93, "elapsed_time": "1:01:12", "remaining_time": "0:27:35", "throughput": 5158.45, "total_tokens": 18944000} {"current_steps": 4626, "total_steps": 6710, "loss": 0.3801, "lr": 5.49284721025753e-07, "epoch": 3.4470938897168404, "percentage": 68.94, "elapsed_time": "1:01:13", "remaining_time": "0:27:34", "throughput": 5158.47, "total_tokens": 18948096} {"current_steps": 4627, "total_steps": 6710, "loss": 0.1317, "lr": 5.48800153605237e-07, "epoch": 3.447839046199702, "percentage": 68.96, "elapsed_time": "1:01:13", "remaining_time": "0:27:33", "throughput": 5158.48, "total_tokens": 18952192} {"current_steps": 4628, "total_steps": 6710, "loss": 0.3177, "lr": 5.483157398927338e-07, "epoch": 3.4485842026825635, "percentage": 68.97, "elapsed_time": "1:01:14", "remaining_time": "0:27:33", "throughput": 5158.49, "total_tokens": 18956288} {"current_steps": 4629, "total_steps": 6710, "loss": 0.1869, "lr": 5.47831479994432e-07, "epoch": 3.4493293591654246, "percentage": 68.99, "elapsed_time": "1:01:15", "remaining_time": "0:27:32", "throughput": 5158.5, "total_tokens": 18960384} {"current_steps": 4630, "total_steps": 6710, "loss": 0.0997, "lr": 5.473473740164827e-07, "epoch": 3.450074515648286, "percentage": 69.0, "elapsed_time": "1:01:16", "remaining_time": "0:27:31", "throughput": 5158.51, "total_tokens": 18964480} {"current_steps": 4631, "total_steps": 6710, "loss": 0.1905, "lr": 5.468634220650068e-07, "epoch": 3.4508196721311477, "percentage": 69.02, "elapsed_time": "1:01:17", "remaining_time": "0:27:30", "throughput": 5158.53, "total_tokens": 18968576} {"current_steps": 4632, "total_steps": 6710, "loss": 0.1103, "lr": 5.463796242460892e-07, "epoch": 3.451564828614009, "percentage": 69.03, "elapsed_time": "1:01:17", "remaining_time": "0:27:29", "throughput": 5158.54, "total_tokens": 18972672} {"current_steps": 4633, "total_steps": 6710, "loss": 0.1038, "lr": 5.458959806657827e-07, "epoch": 3.4523099850968704, "percentage": 69.05, "elapsed_time": "1:01:18", "remaining_time": "0:27:29", "throughput": 5158.56, "total_tokens": 18976768} {"current_steps": 4634, "total_steps": 6710, "loss": 0.0538, "lr": 5.454124914301046e-07, "epoch": 3.453055141579732, "percentage": 69.06, "elapsed_time": "1:01:19", "remaining_time": "0:27:28", "throughput": 5158.58, "total_tokens": 18980864} {"current_steps": 4635, "total_steps": 6710, "loss": 0.1592, "lr": 5.449291566450399e-07, "epoch": 3.453800298062593, "percentage": 69.08, "elapsed_time": "1:01:20", "remaining_time": "0:27:27", "throughput": 5158.6, "total_tokens": 18984960} {"current_steps": 4636, "total_steps": 6710, "loss": 0.0718, "lr": 5.444459764165389e-07, "epoch": 3.4545454545454546, "percentage": 69.09, "elapsed_time": "1:01:21", "remaining_time": "0:27:26", "throughput": 5158.62, "total_tokens": 18989056} {"current_steps": 4637, "total_steps": 6710, "loss": 0.1187, "lr": 5.439629508505173e-07, "epoch": 3.455290611028316, "percentage": 69.11, "elapsed_time": "1:01:21", "remaining_time": "0:27:25", "throughput": 5158.63, "total_tokens": 18993152} {"current_steps": 4638, "total_steps": 6710, "loss": 0.1422, "lr": 5.43480080052859e-07, "epoch": 3.4560357675111772, "percentage": 69.12, "elapsed_time": "1:01:22", "remaining_time": "0:27:25", "throughput": 5158.65, "total_tokens": 18997248} {"current_steps": 4639, "total_steps": 6710, "loss": 0.2164, "lr": 5.429973641294117e-07, "epoch": 3.456780923994039, "percentage": 69.14, "elapsed_time": "1:01:23", "remaining_time": "0:27:24", "throughput": 5158.67, "total_tokens": 19001344} {"current_steps": 4640, "total_steps": 6710, "loss": 0.1851, "lr": 5.425148031859912e-07, "epoch": 3.4575260804769004, "percentage": 69.15, "elapsed_time": "1:01:24", "remaining_time": "0:27:23", "throughput": 5158.68, "total_tokens": 19005440} {"current_steps": 4641, "total_steps": 6710, "loss": 0.1603, "lr": 5.420323973283772e-07, "epoch": 3.4582712369597615, "percentage": 69.17, "elapsed_time": "1:01:24", "remaining_time": "0:27:22", "throughput": 5158.7, "total_tokens": 19009536} {"current_steps": 4642, "total_steps": 6710, "loss": 0.0694, "lr": 5.41550146662318e-07, "epoch": 3.459016393442623, "percentage": 69.18, "elapsed_time": "1:01:25", "remaining_time": "0:27:21", "throughput": 5158.72, "total_tokens": 19013632} {"current_steps": 4643, "total_steps": 6710, "loss": 0.357, "lr": 5.410680512935245e-07, "epoch": 3.459761549925484, "percentage": 69.2, "elapsed_time": "1:01:26", "remaining_time": "0:27:21", "throughput": 5158.74, "total_tokens": 19017728} {"current_steps": 4644, "total_steps": 6710, "loss": 0.1808, "lr": 5.405861113276767e-07, "epoch": 3.4605067064083457, "percentage": 69.21, "elapsed_time": "1:01:27", "remaining_time": "0:27:20", "throughput": 5158.75, "total_tokens": 19021824} {"current_steps": 4645, "total_steps": 6710, "loss": 0.0908, "lr": 5.401043268704192e-07, "epoch": 3.4612518628912072, "percentage": 69.23, "elapsed_time": "1:01:28", "remaining_time": "0:27:19", "throughput": 5158.77, "total_tokens": 19025920} {"current_steps": 4646, "total_steps": 6710, "loss": 0.199, "lr": 5.396226980273617e-07, "epoch": 3.461997019374069, "percentage": 69.24, "elapsed_time": "1:01:28", "remaining_time": "0:27:18", "throughput": 5158.79, "total_tokens": 19030016} {"current_steps": 4647, "total_steps": 6710, "loss": 0.1216, "lr": 5.391412249040819e-07, "epoch": 3.46274217585693, "percentage": 69.25, "elapsed_time": "1:01:29", "remaining_time": "0:27:17", "throughput": 5158.81, "total_tokens": 19034112} {"current_steps": 4648, "total_steps": 6710, "loss": 0.0372, "lr": 5.38659907606121e-07, "epoch": 3.4634873323397914, "percentage": 69.27, "elapsed_time": "1:01:30", "remaining_time": "0:27:17", "throughput": 5158.83, "total_tokens": 19038208} {"current_steps": 4649, "total_steps": 6710, "loss": 0.3996, "lr": 5.381787462389883e-07, "epoch": 3.4642324888226526, "percentage": 69.28, "elapsed_time": "1:01:31", "remaining_time": "0:27:16", "throughput": 5158.85, "total_tokens": 19042304} {"current_steps": 4650, "total_steps": 6710, "loss": 0.0871, "lr": 5.376977409081569e-07, "epoch": 3.464977645305514, "percentage": 69.3, "elapsed_time": "1:01:31", "remaining_time": "0:27:15", "throughput": 5158.86, "total_tokens": 19046400} {"current_steps": 4651, "total_steps": 6710, "loss": 0.0834, "lr": 5.372168917190673e-07, "epoch": 3.4657228017883757, "percentage": 69.31, "elapsed_time": "1:01:32", "remaining_time": "0:27:14", "throughput": 5158.88, "total_tokens": 19050496} {"current_steps": 4652, "total_steps": 6710, "loss": 0.1551, "lr": 5.367361987771245e-07, "epoch": 3.4664679582712368, "percentage": 69.33, "elapsed_time": "1:01:33", "remaining_time": "0:27:13", "throughput": 5158.9, "total_tokens": 19054592} {"current_steps": 4653, "total_steps": 6710, "loss": 0.0687, "lr": 5.362556621877004e-07, "epoch": 3.4672131147540983, "percentage": 69.34, "elapsed_time": "1:01:34", "remaining_time": "0:27:13", "throughput": 5158.92, "total_tokens": 19058688} {"current_steps": 4654, "total_steps": 6710, "loss": 0.0935, "lr": 5.357752820561318e-07, "epoch": 3.46795827123696, "percentage": 69.36, "elapsed_time": "1:01:35", "remaining_time": "0:27:12", "throughput": 5158.94, "total_tokens": 19062784} {"current_steps": 4655, "total_steps": 6710, "loss": 0.131, "lr": 5.352950584877209e-07, "epoch": 3.468703427719821, "percentage": 69.37, "elapsed_time": "1:01:35", "remaining_time": "0:27:11", "throughput": 5158.96, "total_tokens": 19066880} {"current_steps": 4656, "total_steps": 6710, "loss": 0.1069, "lr": 5.348149915877376e-07, "epoch": 3.4694485842026825, "percentage": 69.39, "elapsed_time": "1:01:36", "remaining_time": "0:27:10", "throughput": 5158.97, "total_tokens": 19070976} {"current_steps": 4657, "total_steps": 6710, "loss": 0.3193, "lr": 5.34335081461414e-07, "epoch": 3.470193740685544, "percentage": 69.4, "elapsed_time": "1:01:37", "remaining_time": "0:27:09", "throughput": 5158.99, "total_tokens": 19075072} {"current_steps": 4658, "total_steps": 6710, "loss": 0.2273, "lr": 5.338553282139513e-07, "epoch": 3.470938897168405, "percentage": 69.42, "elapsed_time": "1:01:38", "remaining_time": "0:27:09", "throughput": 5159.01, "total_tokens": 19079168} {"current_steps": 4659, "total_steps": 6710, "loss": 0.1255, "lr": 5.333757319505141e-07, "epoch": 3.4716840536512668, "percentage": 69.43, "elapsed_time": "1:01:39", "remaining_time": "0:27:08", "throughput": 5159.03, "total_tokens": 19083264} {"current_steps": 4660, "total_steps": 6710, "loss": 0.1549, "lr": 5.32896292776234e-07, "epoch": 3.4724292101341283, "percentage": 69.45, "elapsed_time": "1:01:39", "remaining_time": "0:27:07", "throughput": 5159.05, "total_tokens": 19087360} {"current_steps": 4661, "total_steps": 6710, "loss": 0.1038, "lr": 5.324170107962067e-07, "epoch": 3.4731743666169894, "percentage": 69.46, "elapsed_time": "1:01:40", "remaining_time": "0:27:06", "throughput": 5159.07, "total_tokens": 19091456} {"current_steps": 4662, "total_steps": 6710, "loss": 0.1689, "lr": 5.319378861154949e-07, "epoch": 3.473919523099851, "percentage": 69.48, "elapsed_time": "1:01:41", "remaining_time": "0:27:05", "throughput": 5159.09, "total_tokens": 19095552} {"current_steps": 4663, "total_steps": 6710, "loss": 0.1883, "lr": 5.31458918839126e-07, "epoch": 3.4746646795827125, "percentage": 69.49, "elapsed_time": "1:01:42", "remaining_time": "0:27:05", "throughput": 5159.1, "total_tokens": 19099648} {"current_steps": 4664, "total_steps": 6710, "loss": 0.0892, "lr": 5.309801090720925e-07, "epoch": 3.4754098360655736, "percentage": 69.51, "elapsed_time": "1:01:42", "remaining_time": "0:27:04", "throughput": 5159.12, "total_tokens": 19103744} {"current_steps": 4665, "total_steps": 6710, "loss": 0.1199, "lr": 5.305014569193537e-07, "epoch": 3.476154992548435, "percentage": 69.52, "elapsed_time": "1:01:43", "remaining_time": "0:27:03", "throughput": 5159.14, "total_tokens": 19107840} {"current_steps": 4666, "total_steps": 6710, "loss": 0.168, "lr": 5.300229624858329e-07, "epoch": 3.4769001490312967, "percentage": 69.54, "elapsed_time": "1:01:44", "remaining_time": "0:27:02", "throughput": 5159.16, "total_tokens": 19111936} {"current_steps": 4667, "total_steps": 6710, "loss": 0.1003, "lr": 5.295446258764202e-07, "epoch": 3.477645305514158, "percentage": 69.55, "elapsed_time": "1:01:45", "remaining_time": "0:27:01", "throughput": 5159.18, "total_tokens": 19116032} {"current_steps": 4668, "total_steps": 6710, "loss": 0.1079, "lr": 5.290664471959696e-07, "epoch": 3.4783904619970194, "percentage": 69.57, "elapsed_time": "1:01:46", "remaining_time": "0:27:01", "throughput": 5159.2, "total_tokens": 19120128} {"current_steps": 4669, "total_steps": 6710, "loss": 0.3514, "lr": 5.285884265493025e-07, "epoch": 3.479135618479881, "percentage": 69.58, "elapsed_time": "1:01:46", "remaining_time": "0:27:00", "throughput": 5159.22, "total_tokens": 19124224} {"current_steps": 4670, "total_steps": 6710, "loss": 0.2684, "lr": 5.281105640412029e-07, "epoch": 3.479880774962742, "percentage": 69.6, "elapsed_time": "1:01:47", "remaining_time": "0:26:59", "throughput": 5159.24, "total_tokens": 19128320} {"current_steps": 4671, "total_steps": 6710, "loss": 0.0798, "lr": 5.276328597764227e-07, "epoch": 3.4806259314456036, "percentage": 69.61, "elapsed_time": "1:01:48", "remaining_time": "0:26:58", "throughput": 5159.25, "total_tokens": 19132416} {"current_steps": 4672, "total_steps": 6710, "loss": 0.1858, "lr": 5.271553138596775e-07, "epoch": 3.481371087928465, "percentage": 69.63, "elapsed_time": "1:01:49", "remaining_time": "0:26:57", "throughput": 5159.27, "total_tokens": 19136512} {"current_steps": 4673, "total_steps": 6710, "loss": 0.1743, "lr": 5.266779263956496e-07, "epoch": 3.4821162444113263, "percentage": 69.64, "elapsed_time": "1:01:49", "remaining_time": "0:26:57", "throughput": 5159.28, "total_tokens": 19140608} {"current_steps": 4674, "total_steps": 6710, "loss": 0.262, "lr": 5.26200697488985e-07, "epoch": 3.482861400894188, "percentage": 69.66, "elapsed_time": "1:01:50", "remaining_time": "0:26:56", "throughput": 5159.3, "total_tokens": 19144704} {"current_steps": 4675, "total_steps": 6710, "loss": 0.2106, "lr": 5.257236272442955e-07, "epoch": 3.4836065573770494, "percentage": 69.67, "elapsed_time": "1:01:51", "remaining_time": "0:26:55", "throughput": 5159.32, "total_tokens": 19148800} {"current_steps": 4676, "total_steps": 6710, "loss": 0.1812, "lr": 5.252467157661591e-07, "epoch": 3.4843517138599105, "percentage": 69.69, "elapsed_time": "1:01:52", "remaining_time": "0:26:54", "throughput": 5159.33, "total_tokens": 19152896} {"current_steps": 4677, "total_steps": 6710, "loss": 0.0627, "lr": 5.247699631591174e-07, "epoch": 3.485096870342772, "percentage": 69.7, "elapsed_time": "1:01:53", "remaining_time": "0:26:53", "throughput": 5159.35, "total_tokens": 19156992} {"current_steps": 4678, "total_steps": 6710, "loss": 0.1274, "lr": 5.242933695276789e-07, "epoch": 3.485842026825633, "percentage": 69.72, "elapsed_time": "1:01:53", "remaining_time": "0:26:53", "throughput": 5159.36, "total_tokens": 19161088} {"current_steps": 4679, "total_steps": 6710, "loss": 0.2799, "lr": 5.238169349763154e-07, "epoch": 3.4865871833084947, "percentage": 69.73, "elapsed_time": "1:01:54", "remaining_time": "0:26:52", "throughput": 5159.38, "total_tokens": 19165184} {"current_steps": 4680, "total_steps": 6710, "loss": 0.0443, "lr": 5.233406596094654e-07, "epoch": 3.4873323397913563, "percentage": 69.75, "elapsed_time": "1:01:55", "remaining_time": "0:26:51", "throughput": 5159.4, "total_tokens": 19169280} {"current_steps": 4681, "total_steps": 6710, "loss": 0.232, "lr": 5.228645435315318e-07, "epoch": 3.488077496274218, "percentage": 69.76, "elapsed_time": "1:01:56", "remaining_time": "0:26:50", "throughput": 5159.42, "total_tokens": 19173376} {"current_steps": 4682, "total_steps": 6710, "loss": 0.2109, "lr": 5.22388586846882e-07, "epoch": 3.488822652757079, "percentage": 69.78, "elapsed_time": "1:01:56", "remaining_time": "0:26:49", "throughput": 5159.44, "total_tokens": 19177472} {"current_steps": 4683, "total_steps": 6710, "loss": 0.1078, "lr": 5.219127896598504e-07, "epoch": 3.4895678092399405, "percentage": 69.79, "elapsed_time": "1:01:57", "remaining_time": "0:26:49", "throughput": 5159.46, "total_tokens": 19181568} {"current_steps": 4684, "total_steps": 6710, "loss": 0.1097, "lr": 5.214371520747336e-07, "epoch": 3.4903129657228016, "percentage": 69.81, "elapsed_time": "1:01:58", "remaining_time": "0:26:48", "throughput": 5159.47, "total_tokens": 19185664} {"current_steps": 4685, "total_steps": 6710, "loss": 0.2674, "lr": 5.209616741957956e-07, "epoch": 3.491058122205663, "percentage": 69.82, "elapsed_time": "1:01:59", "remaining_time": "0:26:47", "throughput": 5159.47, "total_tokens": 19189760} {"current_steps": 4686, "total_steps": 6710, "loss": 0.1045, "lr": 5.204863561272643e-07, "epoch": 3.4918032786885247, "percentage": 69.84, "elapsed_time": "1:02:00", "remaining_time": "0:26:46", "throughput": 5159.49, "total_tokens": 19193856} {"current_steps": 4687, "total_steps": 6710, "loss": 0.1266, "lr": 5.200111979733331e-07, "epoch": 3.492548435171386, "percentage": 69.85, "elapsed_time": "1:02:00", "remaining_time": "0:26:46", "throughput": 5159.51, "total_tokens": 19197952} {"current_steps": 4688, "total_steps": 6710, "loss": 0.2119, "lr": 5.195361998381597e-07, "epoch": 3.4932935916542474, "percentage": 69.87, "elapsed_time": "1:02:01", "remaining_time": "0:26:45", "throughput": 5159.52, "total_tokens": 19202048} {"current_steps": 4689, "total_steps": 6710, "loss": 0.1198, "lr": 5.190613618258675e-07, "epoch": 3.494038748137109, "percentage": 69.88, "elapsed_time": "1:02:02", "remaining_time": "0:26:44", "throughput": 5159.54, "total_tokens": 19206144} {"current_steps": 4690, "total_steps": 6710, "loss": 0.1619, "lr": 5.185866840405443e-07, "epoch": 3.49478390461997, "percentage": 69.9, "elapsed_time": "1:02:03", "remaining_time": "0:26:43", "throughput": 5159.56, "total_tokens": 19210240} {"current_steps": 4691, "total_steps": 6710, "loss": 0.2839, "lr": 5.181121665862422e-07, "epoch": 3.4955290611028316, "percentage": 69.91, "elapsed_time": "1:02:04", "remaining_time": "0:26:42", "throughput": 5159.58, "total_tokens": 19214336} {"current_steps": 4692, "total_steps": 6710, "loss": 0.1924, "lr": 5.176378095669797e-07, "epoch": 3.496274217585693, "percentage": 69.93, "elapsed_time": "1:02:04", "remaining_time": "0:26:42", "throughput": 5159.6, "total_tokens": 19218432} {"current_steps": 4693, "total_steps": 6710, "loss": 0.2082, "lr": 5.171636130867385e-07, "epoch": 3.4970193740685542, "percentage": 69.94, "elapsed_time": "1:02:05", "remaining_time": "0:26:41", "throughput": 5159.61, "total_tokens": 19222528} {"current_steps": 4694, "total_steps": 6710, "loss": 0.3694, "lr": 5.166895772494668e-07, "epoch": 3.497764530551416, "percentage": 69.96, "elapsed_time": "1:02:06", "remaining_time": "0:26:40", "throughput": 5159.63, "total_tokens": 19226624} {"current_steps": 4695, "total_steps": 6710, "loss": 0.1471, "lr": 5.162157021590756e-07, "epoch": 3.4985096870342773, "percentage": 69.97, "elapsed_time": "1:02:07", "remaining_time": "0:26:39", "throughput": 5159.64, "total_tokens": 19230720} {"current_steps": 4696, "total_steps": 6710, "loss": 0.1014, "lr": 5.15741987919443e-07, "epoch": 3.4992548435171384, "percentage": 69.99, "elapsed_time": "1:02:07", "remaining_time": "0:26:38", "throughput": 5159.66, "total_tokens": 19234816} {"current_steps": 4697, "total_steps": 6710, "loss": 0.1547, "lr": 5.152684346344087e-07, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "1:02:08", "remaining_time": "0:26:38", "throughput": 5159.68, "total_tokens": 19238912} {"current_steps": 4698, "total_steps": 6710, "loss": 0.0738, "lr": 5.147950424077804e-07, "epoch": 3.5007451564828616, "percentage": 70.01, "elapsed_time": "1:02:09", "remaining_time": "0:26:37", "throughput": 5159.7, "total_tokens": 19243008} {"current_steps": 4699, "total_steps": 6710, "loss": 0.1422, "lr": 5.143218113433285e-07, "epoch": 3.5014903129657227, "percentage": 70.03, "elapsed_time": "1:02:10", "remaining_time": "0:26:36", "throughput": 5159.72, "total_tokens": 19247104} {"current_steps": 4700, "total_steps": 6710, "loss": 0.1286, "lr": 5.13848741544789e-07, "epoch": 3.502235469448584, "percentage": 70.04, "elapsed_time": "1:02:11", "remaining_time": "0:26:35", "throughput": 5159.74, "total_tokens": 19251200} {"current_steps": 4701, "total_steps": 6710, "loss": 0.2259, "lr": 5.13375833115862e-07, "epoch": 3.5029806259314458, "percentage": 70.06, "elapsed_time": "1:02:11", "remaining_time": "0:26:34", "throughput": 5159.76, "total_tokens": 19255296} {"current_steps": 4702, "total_steps": 6710, "loss": 0.369, "lr": 5.129030861602119e-07, "epoch": 3.503725782414307, "percentage": 70.07, "elapsed_time": "1:02:12", "remaining_time": "0:26:34", "throughput": 5159.78, "total_tokens": 19259392} {"current_steps": 4703, "total_steps": 6710, "loss": 0.2039, "lr": 5.124305007814691e-07, "epoch": 3.5044709388971684, "percentage": 70.09, "elapsed_time": "1:02:13", "remaining_time": "0:26:33", "throughput": 5159.8, "total_tokens": 19263488} {"current_steps": 4704, "total_steps": 6710, "loss": 0.1903, "lr": 5.119580770832268e-07, "epoch": 3.50521609538003, "percentage": 70.1, "elapsed_time": "1:02:14", "remaining_time": "0:26:32", "throughput": 5159.82, "total_tokens": 19267584} {"current_steps": 4705, "total_steps": 6710, "loss": 0.2363, "lr": 5.114858151690445e-07, "epoch": 3.505961251862891, "percentage": 70.12, "elapsed_time": "1:02:14", "remaining_time": "0:26:31", "throughput": 5159.83, "total_tokens": 19271680} {"current_steps": 4706, "total_steps": 6710, "loss": 0.2495, "lr": 5.110137151424446e-07, "epoch": 3.5067064083457526, "percentage": 70.13, "elapsed_time": "1:02:15", "remaining_time": "0:26:30", "throughput": 5159.85, "total_tokens": 19275776} {"current_steps": 4707, "total_steps": 6710, "loss": 0.0818, "lr": 5.105417771069156e-07, "epoch": 3.5074515648286138, "percentage": 70.15, "elapsed_time": "1:02:16", "remaining_time": "0:26:30", "throughput": 5159.87, "total_tokens": 19279872} {"current_steps": 4708, "total_steps": 6710, "loss": 0.2074, "lr": 5.100700011659092e-07, "epoch": 3.5081967213114753, "percentage": 70.16, "elapsed_time": "1:02:17", "remaining_time": "0:26:29", "throughput": 5159.88, "total_tokens": 19283968} {"current_steps": 4709, "total_steps": 6710, "loss": 0.0482, "lr": 5.095983874228417e-07, "epoch": 3.508941877794337, "percentage": 70.18, "elapsed_time": "1:02:18", "remaining_time": "0:26:28", "throughput": 5159.9, "total_tokens": 19288064} {"current_steps": 4710, "total_steps": 6710, "loss": 0.1773, "lr": 5.091269359810956e-07, "epoch": 3.5096870342771984, "percentage": 70.19, "elapsed_time": "1:02:18", "remaining_time": "0:26:27", "throughput": 5159.92, "total_tokens": 19292160} {"current_steps": 4711, "total_steps": 6710, "loss": 0.1397, "lr": 5.086556469440144e-07, "epoch": 3.5104321907600595, "percentage": 70.21, "elapsed_time": "1:02:19", "remaining_time": "0:26:26", "throughput": 5159.94, "total_tokens": 19296256} {"current_steps": 4712, "total_steps": 6710, "loss": 0.059, "lr": 5.081845204149096e-07, "epoch": 3.511177347242921, "percentage": 70.22, "elapsed_time": "1:02:20", "remaining_time": "0:26:26", "throughput": 5159.96, "total_tokens": 19300352} {"current_steps": 4713, "total_steps": 6710, "loss": 0.1305, "lr": 5.077135564970545e-07, "epoch": 3.511922503725782, "percentage": 70.24, "elapsed_time": "1:02:21", "remaining_time": "0:26:25", "throughput": 5159.98, "total_tokens": 19304448} {"current_steps": 4714, "total_steps": 6710, "loss": 0.189, "lr": 5.072427552936885e-07, "epoch": 3.5126676602086437, "percentage": 70.25, "elapsed_time": "1:02:21", "remaining_time": "0:26:24", "throughput": 5159.99, "total_tokens": 19308544} {"current_steps": 4715, "total_steps": 6710, "loss": 0.32, "lr": 5.067721169080142e-07, "epoch": 3.5134128166915053, "percentage": 70.27, "elapsed_time": "1:02:22", "remaining_time": "0:26:23", "throughput": 5159.99, "total_tokens": 19312640} {"current_steps": 4716, "total_steps": 6710, "loss": 0.2394, "lr": 5.063016414431991e-07, "epoch": 3.514157973174367, "percentage": 70.28, "elapsed_time": "1:02:23", "remaining_time": "0:26:22", "throughput": 5160.01, "total_tokens": 19316736} {"current_steps": 4717, "total_steps": 6710, "loss": 0.1695, "lr": 5.058313290023749e-07, "epoch": 3.514903129657228, "percentage": 70.3, "elapsed_time": "1:02:24", "remaining_time": "0:26:22", "throughput": 5160.02, "total_tokens": 19320832} {"current_steps": 4718, "total_steps": 6710, "loss": 0.2709, "lr": 5.053611796886367e-07, "epoch": 3.5156482861400895, "percentage": 70.31, "elapsed_time": "1:02:25", "remaining_time": "0:26:21", "throughput": 5160.04, "total_tokens": 19324928} {"current_steps": 4719, "total_steps": 6710, "loss": 0.2141, "lr": 5.048911936050456e-07, "epoch": 3.5163934426229506, "percentage": 70.33, "elapsed_time": "1:02:25", "remaining_time": "0:26:20", "throughput": 5160.06, "total_tokens": 19329024} {"current_steps": 4720, "total_steps": 6710, "loss": 0.1784, "lr": 5.044213708546249e-07, "epoch": 3.517138599105812, "percentage": 70.34, "elapsed_time": "1:02:26", "remaining_time": "0:26:19", "throughput": 5160.08, "total_tokens": 19333120} {"current_steps": 4721, "total_steps": 6710, "loss": 0.2008, "lr": 5.039517115403641e-07, "epoch": 3.5178837555886737, "percentage": 70.36, "elapsed_time": "1:02:27", "remaining_time": "0:26:18", "throughput": 5160.1, "total_tokens": 19337216} {"current_steps": 4722, "total_steps": 6710, "loss": 0.0959, "lr": 5.034822157652149e-07, "epoch": 3.5186289120715353, "percentage": 70.37, "elapsed_time": "1:02:28", "remaining_time": "0:26:18", "throughput": 5160.12, "total_tokens": 19341312} {"current_steps": 4723, "total_steps": 6710, "loss": 0.1612, "lr": 5.030128836320955e-07, "epoch": 3.5193740685543964, "percentage": 70.39, "elapsed_time": "1:02:29", "remaining_time": "0:26:17", "throughput": 5160.14, "total_tokens": 19345408} {"current_steps": 4724, "total_steps": 6710, "loss": 0.0638, "lr": 5.025437152438852e-07, "epoch": 3.520119225037258, "percentage": 70.4, "elapsed_time": "1:02:29", "remaining_time": "0:26:16", "throughput": 5160.16, "total_tokens": 19349504} {"current_steps": 4725, "total_steps": 6710, "loss": 0.0688, "lr": 5.020747107034301e-07, "epoch": 3.520864381520119, "percentage": 70.42, "elapsed_time": "1:02:30", "remaining_time": "0:26:15", "throughput": 5160.17, "total_tokens": 19353600} {"current_steps": 4726, "total_steps": 6710, "loss": 0.083, "lr": 5.016058701135387e-07, "epoch": 3.5216095380029806, "percentage": 70.43, "elapsed_time": "1:02:31", "remaining_time": "0:26:14", "throughput": 5160.19, "total_tokens": 19357696} {"current_steps": 4727, "total_steps": 6710, "loss": 0.2916, "lr": 5.011371935769852e-07, "epoch": 3.522354694485842, "percentage": 70.45, "elapsed_time": "1:02:32", "remaining_time": "0:26:14", "throughput": 5160.2, "total_tokens": 19361792} {"current_steps": 4728, "total_steps": 6710, "loss": 0.1869, "lr": 5.00668681196506e-07, "epoch": 3.5230998509687033, "percentage": 70.46, "elapsed_time": "1:02:32", "remaining_time": "0:26:13", "throughput": 5160.22, "total_tokens": 19365888} {"current_steps": 4729, "total_steps": 6710, "loss": 0.0564, "lr": 5.002003330748024e-07, "epoch": 3.523845007451565, "percentage": 70.48, "elapsed_time": "1:02:33", "remaining_time": "0:26:12", "throughput": 5160.24, "total_tokens": 19369984} {"current_steps": 4730, "total_steps": 6710, "loss": 0.0968, "lr": 4.997321493145399e-07, "epoch": 3.5245901639344264, "percentage": 70.49, "elapsed_time": "1:02:34", "remaining_time": "0:26:11", "throughput": 5160.26, "total_tokens": 19374080} {"current_steps": 4731, "total_steps": 6710, "loss": 0.1903, "lr": 4.992641300183475e-07, "epoch": 3.5253353204172875, "percentage": 70.51, "elapsed_time": "1:02:35", "remaining_time": "0:26:10", "throughput": 5160.28, "total_tokens": 19378176} {"current_steps": 4732, "total_steps": 6710, "loss": 0.0337, "lr": 4.987962752888188e-07, "epoch": 3.526080476900149, "percentage": 70.52, "elapsed_time": "1:02:36", "remaining_time": "0:26:10", "throughput": 5159.77, "total_tokens": 19382272} {"current_steps": 4733, "total_steps": 6710, "loss": 0.2049, "lr": 4.983285852285104e-07, "epoch": 3.5268256333830106, "percentage": 70.54, "elapsed_time": "1:02:37", "remaining_time": "0:26:09", "throughput": 5159.79, "total_tokens": 19386368} {"current_steps": 4734, "total_steps": 6710, "loss": 0.1467, "lr": 4.978610599399439e-07, "epoch": 3.5275707898658717, "percentage": 70.55, "elapsed_time": "1:02:37", "remaining_time": "0:26:08", "throughput": 5159.8, "total_tokens": 19390464} {"current_steps": 4735, "total_steps": 6710, "loss": 0.1386, "lr": 4.973936995256038e-07, "epoch": 3.5283159463487332, "percentage": 70.57, "elapsed_time": "1:02:38", "remaining_time": "0:26:07", "throughput": 5159.82, "total_tokens": 19394560} {"current_steps": 4736, "total_steps": 6710, "loss": 0.408, "lr": 4.969265040879383e-07, "epoch": 3.529061102831595, "percentage": 70.58, "elapsed_time": "1:02:39", "remaining_time": "0:26:07", "throughput": 5159.84, "total_tokens": 19398656} {"current_steps": 4737, "total_steps": 6710, "loss": 0.3111, "lr": 4.964594737293611e-07, "epoch": 3.529806259314456, "percentage": 70.6, "elapsed_time": "1:02:40", "remaining_time": "0:26:06", "throughput": 5159.86, "total_tokens": 19402752} {"current_steps": 4738, "total_steps": 6710, "loss": 0.1156, "lr": 4.959926085522479e-07, "epoch": 3.5305514157973175, "percentage": 70.61, "elapsed_time": "1:02:41", "remaining_time": "0:26:05", "throughput": 5159.87, "total_tokens": 19406848} {"current_steps": 4739, "total_steps": 6710, "loss": 0.0942, "lr": 4.955259086589391e-07, "epoch": 3.531296572280179, "percentage": 70.63, "elapsed_time": "1:02:41", "remaining_time": "0:26:04", "throughput": 5159.89, "total_tokens": 19410944} {"current_steps": 4740, "total_steps": 6710, "loss": 0.3264, "lr": 4.950593741517382e-07, "epoch": 3.53204172876304, "percentage": 70.64, "elapsed_time": "1:02:42", "remaining_time": "0:26:03", "throughput": 5159.91, "total_tokens": 19415040} {"current_steps": 4741, "total_steps": 6710, "loss": 0.2718, "lr": 4.945930051329134e-07, "epoch": 3.5327868852459017, "percentage": 70.66, "elapsed_time": "1:02:43", "remaining_time": "0:26:03", "throughput": 5159.92, "total_tokens": 19419136} {"current_steps": 4742, "total_steps": 6710, "loss": 0.1273, "lr": 4.941268017046957e-07, "epoch": 3.533532041728763, "percentage": 70.67, "elapsed_time": "1:02:44", "remaining_time": "0:26:02", "throughput": 5159.94, "total_tokens": 19423232} {"current_steps": 4743, "total_steps": 6710, "loss": 0.1352, "lr": 4.93660763969281e-07, "epoch": 3.5342771982116243, "percentage": 70.69, "elapsed_time": "1:02:45", "remaining_time": "0:26:01", "throughput": 5159.96, "total_tokens": 19427328} {"current_steps": 4744, "total_steps": 6710, "loss": 0.1429, "lr": 4.931948920288271e-07, "epoch": 3.535022354694486, "percentage": 70.7, "elapsed_time": "1:02:45", "remaining_time": "0:26:00", "throughput": 5159.98, "total_tokens": 19431424} {"current_steps": 4745, "total_steps": 6710, "loss": 0.1185, "lr": 4.927291859854573e-07, "epoch": 3.5357675111773474, "percentage": 70.72, "elapsed_time": "1:02:46", "remaining_time": "0:25:59", "throughput": 5159.99, "total_tokens": 19435520} {"current_steps": 4746, "total_steps": 6710, "loss": 0.2191, "lr": 4.922636459412573e-07, "epoch": 3.5365126676602086, "percentage": 70.73, "elapsed_time": "1:02:47", "remaining_time": "0:25:59", "throughput": 5160.01, "total_tokens": 19439616} {"current_steps": 4747, "total_steps": 6710, "loss": 0.1689, "lr": 4.917982719982766e-07, "epoch": 3.53725782414307, "percentage": 70.75, "elapsed_time": "1:02:48", "remaining_time": "0:25:58", "throughput": 5160.03, "total_tokens": 19443712} {"current_steps": 4748, "total_steps": 6710, "loss": 0.1231, "lr": 4.913330642585289e-07, "epoch": 3.538002980625931, "percentage": 70.76, "elapsed_time": "1:02:48", "remaining_time": "0:25:57", "throughput": 5160.05, "total_tokens": 19447808} {"current_steps": 4749, "total_steps": 6710, "loss": 0.2521, "lr": 4.908680228239906e-07, "epoch": 3.5387481371087928, "percentage": 70.77, "elapsed_time": "1:02:49", "remaining_time": "0:25:56", "throughput": 5160.06, "total_tokens": 19451904} {"current_steps": 4750, "total_steps": 6710, "loss": 0.1053, "lr": 4.904031477966031e-07, "epoch": 3.5394932935916543, "percentage": 70.79, "elapsed_time": "1:02:50", "remaining_time": "0:25:55", "throughput": 5160.08, "total_tokens": 19456000} {"current_steps": 4751, "total_steps": 6710, "loss": 0.1175, "lr": 4.89938439278269e-07, "epoch": 3.540238450074516, "percentage": 70.8, "elapsed_time": "1:02:51", "remaining_time": "0:25:55", "throughput": 5160.1, "total_tokens": 19460096} {"current_steps": 4752, "total_steps": 6710, "loss": 0.2999, "lr": 4.894738973708565e-07, "epoch": 3.540983606557377, "percentage": 70.82, "elapsed_time": "1:02:52", "remaining_time": "0:25:54", "throughput": 5160.11, "total_tokens": 19464192} {"current_steps": 4753, "total_steps": 6710, "loss": 0.2203, "lr": 4.89009522176196e-07, "epoch": 3.5417287630402385, "percentage": 70.83, "elapsed_time": "1:02:52", "remaining_time": "0:25:53", "throughput": 5160.13, "total_tokens": 19468288} {"current_steps": 4754, "total_steps": 6710, "loss": 0.1467, "lr": 4.885453137960828e-07, "epoch": 3.5424739195230996, "percentage": 70.85, "elapsed_time": "1:02:53", "remaining_time": "0:25:52", "throughput": 5160.15, "total_tokens": 19472384} {"current_steps": 4755, "total_steps": 6710, "loss": 0.2189, "lr": 4.88081272332274e-07, "epoch": 3.543219076005961, "percentage": 70.86, "elapsed_time": "1:02:54", "remaining_time": "0:25:51", "throughput": 5160.17, "total_tokens": 19476480} {"current_steps": 4756, "total_steps": 6710, "loss": 0.2644, "lr": 4.876173978864903e-07, "epoch": 3.5439642324888228, "percentage": 70.88, "elapsed_time": "1:02:55", "remaining_time": "0:25:51", "throughput": 5160.18, "total_tokens": 19480576} {"current_steps": 4757, "total_steps": 6710, "loss": 0.2002, "lr": 4.871536905604174e-07, "epoch": 3.5447093889716843, "percentage": 70.89, "elapsed_time": "1:02:55", "remaining_time": "0:25:50", "throughput": 5160.2, "total_tokens": 19484672} {"current_steps": 4758, "total_steps": 6710, "loss": 0.2604, "lr": 4.866901504557022e-07, "epoch": 3.5454545454545454, "percentage": 70.91, "elapsed_time": "1:02:56", "remaining_time": "0:25:49", "throughput": 5160.22, "total_tokens": 19488768} {"current_steps": 4759, "total_steps": 6710, "loss": 0.0772, "lr": 4.862267776739573e-07, "epoch": 3.546199701937407, "percentage": 70.92, "elapsed_time": "1:02:57", "remaining_time": "0:25:48", "throughput": 5160.23, "total_tokens": 19492864} {"current_steps": 4760, "total_steps": 6710, "loss": 0.1083, "lr": 4.857635723167559e-07, "epoch": 3.546944858420268, "percentage": 70.94, "elapsed_time": "1:02:58", "remaining_time": "0:25:47", "throughput": 5160.25, "total_tokens": 19496960} {"current_steps": 4761, "total_steps": 6710, "loss": 0.2459, "lr": 4.85300534485637e-07, "epoch": 3.5476900149031296, "percentage": 70.95, "elapsed_time": "1:02:59", "remaining_time": "0:25:47", "throughput": 5160.26, "total_tokens": 19501056} {"current_steps": 4762, "total_steps": 6710, "loss": 0.1779, "lr": 4.848376642821014e-07, "epoch": 3.548435171385991, "percentage": 70.97, "elapsed_time": "1:02:59", "remaining_time": "0:25:46", "throughput": 5160.28, "total_tokens": 19505152} {"current_steps": 4763, "total_steps": 6710, "loss": 0.082, "lr": 4.843749618076131e-07, "epoch": 3.5491803278688527, "percentage": 70.98, "elapsed_time": "1:03:00", "remaining_time": "0:25:45", "throughput": 5160.29, "total_tokens": 19509248} {"current_steps": 4764, "total_steps": 6710, "loss": 0.0735, "lr": 4.839124271636007e-07, "epoch": 3.549925484351714, "percentage": 71.0, "elapsed_time": "1:03:01", "remaining_time": "0:25:44", "throughput": 5160.31, "total_tokens": 19513344} {"current_steps": 4765, "total_steps": 6710, "loss": 0.4204, "lr": 4.834500604514546e-07, "epoch": 3.5506706408345754, "percentage": 71.01, "elapsed_time": "1:03:02", "remaining_time": "0:25:43", "throughput": 5160.33, "total_tokens": 19517440} {"current_steps": 4766, "total_steps": 6710, "loss": 0.2371, "lr": 4.82987861772529e-07, "epoch": 3.5514157973174365, "percentage": 71.03, "elapsed_time": "1:03:02", "remaining_time": "0:25:43", "throughput": 5160.35, "total_tokens": 19521536} {"current_steps": 4767, "total_steps": 6710, "loss": 0.1705, "lr": 4.825258312281404e-07, "epoch": 3.552160953800298, "percentage": 71.04, "elapsed_time": "1:03:03", "remaining_time": "0:25:42", "throughput": 5160.36, "total_tokens": 19525632} {"current_steps": 4768, "total_steps": 6710, "loss": 0.3224, "lr": 4.820639689195704e-07, "epoch": 3.5529061102831596, "percentage": 71.06, "elapsed_time": "1:03:04", "remaining_time": "0:25:41", "throughput": 5160.38, "total_tokens": 19529728} {"current_steps": 4769, "total_steps": 6710, "loss": 0.2185, "lr": 4.816022749480616e-07, "epoch": 3.5536512667660207, "percentage": 71.07, "elapsed_time": "1:03:05", "remaining_time": "0:25:40", "throughput": 5160.39, "total_tokens": 19533824} {"current_steps": 4770, "total_steps": 6710, "loss": 0.1316, "lr": 4.811407494148214e-07, "epoch": 3.5543964232488823, "percentage": 71.09, "elapsed_time": "1:03:06", "remaining_time": "0:25:39", "throughput": 5160.41, "total_tokens": 19537920} {"current_steps": 4771, "total_steps": 6710, "loss": 0.1487, "lr": 4.806793924210186e-07, "epoch": 3.555141579731744, "percentage": 71.1, "elapsed_time": "1:03:06", "remaining_time": "0:25:39", "throughput": 5160.43, "total_tokens": 19542016} {"current_steps": 4772, "total_steps": 6710, "loss": 0.1639, "lr": 4.802182040677868e-07, "epoch": 3.555886736214605, "percentage": 71.12, "elapsed_time": "1:03:07", "remaining_time": "0:25:38", "throughput": 5160.45, "total_tokens": 19546112} {"current_steps": 4773, "total_steps": 6710, "loss": 0.1886, "lr": 4.797571844562214e-07, "epoch": 3.5566318926974665, "percentage": 71.13, "elapsed_time": "1:03:08", "remaining_time": "0:25:37", "throughput": 5160.45, "total_tokens": 19550208} {"current_steps": 4774, "total_steps": 6710, "loss": 0.1971, "lr": 4.792963336873808e-07, "epoch": 3.557377049180328, "percentage": 71.15, "elapsed_time": "1:03:09", "remaining_time": "0:25:36", "throughput": 5160.47, "total_tokens": 19554304} {"current_steps": 4775, "total_steps": 6710, "loss": 0.1745, "lr": 4.788356518622877e-07, "epoch": 3.558122205663189, "percentage": 71.16, "elapsed_time": "1:03:10", "remaining_time": "0:25:35", "throughput": 5160.49, "total_tokens": 19558400} {"current_steps": 4776, "total_steps": 6710, "loss": 0.1072, "lr": 4.783751390819257e-07, "epoch": 3.5588673621460507, "percentage": 71.18, "elapsed_time": "1:03:10", "remaining_time": "0:25:35", "throughput": 5160.5, "total_tokens": 19562496} {"current_steps": 4777, "total_steps": 6710, "loss": 0.1308, "lr": 4.779147954472442e-07, "epoch": 3.559612518628912, "percentage": 71.19, "elapsed_time": "1:03:11", "remaining_time": "0:25:34", "throughput": 5160.52, "total_tokens": 19566592} {"current_steps": 4778, "total_steps": 6710, "loss": 0.0899, "lr": 4.774546210591517e-07, "epoch": 3.5603576751117734, "percentage": 71.21, "elapsed_time": "1:03:12", "remaining_time": "0:25:33", "throughput": 5160.54, "total_tokens": 19570688} {"current_steps": 4779, "total_steps": 6710, "loss": 0.3379, "lr": 4.769946160185232e-07, "epoch": 3.561102831594635, "percentage": 71.22, "elapsed_time": "1:03:13", "remaining_time": "0:25:32", "throughput": 5160.55, "total_tokens": 19574784} {"current_steps": 4780, "total_steps": 6710, "loss": 0.2882, "lr": 4.765347804261941e-07, "epoch": 3.5618479880774965, "percentage": 71.24, "elapsed_time": "1:03:13", "remaining_time": "0:25:31", "throughput": 5160.56, "total_tokens": 19578880} {"current_steps": 4781, "total_steps": 6710, "loss": 0.1821, "lr": 4.760751143829648e-07, "epoch": 3.5625931445603576, "percentage": 71.25, "elapsed_time": "1:03:14", "remaining_time": "0:25:31", "throughput": 5160.57, "total_tokens": 19582976} {"current_steps": 4782, "total_steps": 6710, "loss": 0.1443, "lr": 4.7561561798959654e-07, "epoch": 3.563338301043219, "percentage": 71.27, "elapsed_time": "1:03:15", "remaining_time": "0:25:30", "throughput": 5160.59, "total_tokens": 19587072} {"current_steps": 4783, "total_steps": 6710, "loss": 0.1419, "lr": 4.751562913468141e-07, "epoch": 3.5640834575260802, "percentage": 71.28, "elapsed_time": "1:03:16", "remaining_time": "0:25:29", "throughput": 5160.61, "total_tokens": 19591168} {"current_steps": 4784, "total_steps": 6710, "loss": 0.149, "lr": 4.7469713455530587e-07, "epoch": 3.564828614008942, "percentage": 71.3, "elapsed_time": "1:03:17", "remaining_time": "0:25:28", "throughput": 5160.63, "total_tokens": 19595264} {"current_steps": 4785, "total_steps": 6710, "loss": 0.1525, "lr": 4.742381477157215e-07, "epoch": 3.5655737704918034, "percentage": 71.31, "elapsed_time": "1:03:17", "remaining_time": "0:25:27", "throughput": 5160.64, "total_tokens": 19599360} {"current_steps": 4786, "total_steps": 6710, "loss": 0.1225, "lr": 4.737793309286749e-07, "epoch": 3.566318926974665, "percentage": 71.33, "elapsed_time": "1:03:18", "remaining_time": "0:25:27", "throughput": 5160.66, "total_tokens": 19603456} {"current_steps": 4787, "total_steps": 6710, "loss": 0.1581, "lr": 4.7332068429474147e-07, "epoch": 3.567064083457526, "percentage": 71.34, "elapsed_time": "1:03:19", "remaining_time": "0:25:26", "throughput": 5160.68, "total_tokens": 19607552} {"current_steps": 4788, "total_steps": 6710, "loss": 0.1492, "lr": 4.728622079144603e-07, "epoch": 3.5678092399403876, "percentage": 71.36, "elapsed_time": "1:03:20", "remaining_time": "0:25:25", "throughput": 5160.7, "total_tokens": 19611648} {"current_steps": 4789, "total_steps": 6710, "loss": 0.1292, "lr": 4.7240390188833235e-07, "epoch": 3.5685543964232487, "percentage": 71.37, "elapsed_time": "1:03:20", "remaining_time": "0:25:24", "throughput": 5160.72, "total_tokens": 19615744} {"current_steps": 4790, "total_steps": 6710, "loss": 0.0592, "lr": 4.719457663168217e-07, "epoch": 3.5692995529061102, "percentage": 71.39, "elapsed_time": "1:03:21", "remaining_time": "0:25:23", "throughput": 5160.74, "total_tokens": 19619840} {"current_steps": 4791, "total_steps": 6710, "loss": 0.1957, "lr": 4.714878013003546e-07, "epoch": 3.570044709388972, "percentage": 71.4, "elapsed_time": "1:03:22", "remaining_time": "0:25:23", "throughput": 5160.76, "total_tokens": 19623936} {"current_steps": 4792, "total_steps": 6710, "loss": 0.1727, "lr": 4.7103000693932076e-07, "epoch": 3.5707898658718333, "percentage": 71.42, "elapsed_time": "1:03:23", "remaining_time": "0:25:22", "throughput": 5160.78, "total_tokens": 19628032} {"current_steps": 4793, "total_steps": 6710, "loss": 0.2349, "lr": 4.7057238333407183e-07, "epoch": 3.5715350223546944, "percentage": 71.43, "elapsed_time": "1:03:24", "remaining_time": "0:25:21", "throughput": 5160.8, "total_tokens": 19632128} {"current_steps": 4794, "total_steps": 6710, "loss": 0.1506, "lr": 4.7011493058492163e-07, "epoch": 3.572280178837556, "percentage": 71.45, "elapsed_time": "1:03:24", "remaining_time": "0:25:20", "throughput": 5160.81, "total_tokens": 19636224} {"current_steps": 4795, "total_steps": 6710, "loss": 0.2268, "lr": 4.6965764879214794e-07, "epoch": 3.573025335320417, "percentage": 71.46, "elapsed_time": "1:03:25", "remaining_time": "0:25:19", "throughput": 5160.83, "total_tokens": 19640320} {"current_steps": 4796, "total_steps": 6710, "loss": 0.1894, "lr": 4.692005380559894e-07, "epoch": 3.5737704918032787, "percentage": 71.48, "elapsed_time": "1:03:26", "remaining_time": "0:25:19", "throughput": 5160.85, "total_tokens": 19644416} {"current_steps": 4797, "total_steps": 6710, "loss": 0.1566, "lr": 4.6874359847664866e-07, "epoch": 3.57451564828614, "percentage": 71.49, "elapsed_time": "1:03:27", "remaining_time": "0:25:18", "throughput": 5160.85, "total_tokens": 19648512} {"current_steps": 4798, "total_steps": 6710, "loss": 0.1489, "lr": 4.682868301542895e-07, "epoch": 3.5752608047690018, "percentage": 71.51, "elapsed_time": "1:03:28", "remaining_time": "0:25:17", "throughput": 5160.87, "total_tokens": 19652608} {"current_steps": 4799, "total_steps": 6710, "loss": 0.1915, "lr": 4.678302331890394e-07, "epoch": 3.576005961251863, "percentage": 71.52, "elapsed_time": "1:03:28", "remaining_time": "0:25:16", "throughput": 5160.88, "total_tokens": 19656704} {"current_steps": 4800, "total_steps": 6710, "loss": 0.113, "lr": 4.673738076809875e-07, "epoch": 3.5767511177347244, "percentage": 71.54, "elapsed_time": "1:03:29", "remaining_time": "0:25:15", "throughput": 5160.9, "total_tokens": 19660800} {"current_steps": 4801, "total_steps": 6710, "loss": 0.2356, "lr": 4.669175537301848e-07, "epoch": 3.5774962742175855, "percentage": 71.55, "elapsed_time": "1:03:30", "remaining_time": "0:25:15", "throughput": 5160.92, "total_tokens": 19664896} {"current_steps": 4802, "total_steps": 6710, "loss": 0.0949, "lr": 4.6646147143664665e-07, "epoch": 3.578241430700447, "percentage": 71.56, "elapsed_time": "1:03:31", "remaining_time": "0:25:14", "throughput": 5160.93, "total_tokens": 19668992} {"current_steps": 4803, "total_steps": 6710, "loss": 0.1368, "lr": 4.6600556090034845e-07, "epoch": 3.5789865871833086, "percentage": 71.58, "elapsed_time": "1:03:31", "remaining_time": "0:25:13", "throughput": 5160.94, "total_tokens": 19673088} {"current_steps": 4804, "total_steps": 6710, "loss": 0.2897, "lr": 4.655498222212304e-07, "epoch": 3.5797317436661698, "percentage": 71.59, "elapsed_time": "1:03:32", "remaining_time": "0:25:12", "throughput": 5160.96, "total_tokens": 19677184} {"current_steps": 4805, "total_steps": 6710, "loss": 0.1673, "lr": 4.6509425549919174e-07, "epoch": 3.5804769001490313, "percentage": 71.61, "elapsed_time": "1:03:33", "remaining_time": "0:25:11", "throughput": 5160.98, "total_tokens": 19681280} {"current_steps": 4806, "total_steps": 6710, "loss": 0.2019, "lr": 4.6463886083409765e-07, "epoch": 3.581222056631893, "percentage": 71.62, "elapsed_time": "1:03:34", "remaining_time": "0:25:11", "throughput": 5160.99, "total_tokens": 19685376} {"current_steps": 4807, "total_steps": 6710, "loss": 0.2626, "lr": 4.6418363832577277e-07, "epoch": 3.581967213114754, "percentage": 71.64, "elapsed_time": "1:03:35", "remaining_time": "0:25:10", "throughput": 5161.01, "total_tokens": 19689472} {"current_steps": 4808, "total_steps": 6710, "loss": 0.1083, "lr": 4.6372858807400595e-07, "epoch": 3.5827123695976155, "percentage": 71.65, "elapsed_time": "1:03:35", "remaining_time": "0:25:09", "throughput": 5161.03, "total_tokens": 19693568} {"current_steps": 4809, "total_steps": 6710, "loss": 0.2273, "lr": 4.6327371017854714e-07, "epoch": 3.583457526080477, "percentage": 71.67, "elapsed_time": "1:03:36", "remaining_time": "0:25:08", "throughput": 5161.05, "total_tokens": 19697664} {"current_steps": 4810, "total_steps": 6710, "loss": 0.3036, "lr": 4.6281900473910845e-07, "epoch": 3.584202682563338, "percentage": 71.68, "elapsed_time": "1:03:37", "remaining_time": "0:25:07", "throughput": 5161.06, "total_tokens": 19701760} {"current_steps": 4811, "total_steps": 6710, "loss": 0.3291, "lr": 4.623644718553652e-07, "epoch": 3.5849478390461997, "percentage": 71.7, "elapsed_time": "1:03:38", "remaining_time": "0:25:07", "throughput": 5161.08, "total_tokens": 19705856} {"current_steps": 4812, "total_steps": 6710, "loss": 0.2582, "lr": 4.6191011162695363e-07, "epoch": 3.585692995529061, "percentage": 71.71, "elapsed_time": "1:03:38", "remaining_time": "0:25:06", "throughput": 5161.1, "total_tokens": 19709952} {"current_steps": 4813, "total_steps": 6710, "loss": 0.1525, "lr": 4.614559241534734e-07, "epoch": 3.5864381520119224, "percentage": 71.73, "elapsed_time": "1:03:39", "remaining_time": "0:25:05", "throughput": 5161.12, "total_tokens": 19714048} {"current_steps": 4814, "total_steps": 6710, "loss": 0.1671, "lr": 4.610019095344849e-07, "epoch": 3.587183308494784, "percentage": 71.74, "elapsed_time": "1:03:40", "remaining_time": "0:25:04", "throughput": 5161.14, "total_tokens": 19718144} {"current_steps": 4815, "total_steps": 6710, "loss": 0.2237, "lr": 4.605480678695122e-07, "epoch": 3.5879284649776455, "percentage": 71.76, "elapsed_time": "1:03:41", "remaining_time": "0:25:03", "throughput": 5161.15, "total_tokens": 19722240} {"current_steps": 4816, "total_steps": 6710, "loss": 0.158, "lr": 4.600943992580402e-07, "epoch": 3.5886736214605066, "percentage": 71.77, "elapsed_time": "1:03:42", "remaining_time": "0:25:03", "throughput": 5161.17, "total_tokens": 19726336} {"current_steps": 4817, "total_steps": 6710, "loss": 0.2168, "lr": 4.596409037995163e-07, "epoch": 3.589418777943368, "percentage": 71.79, "elapsed_time": "1:03:42", "remaining_time": "0:25:02", "throughput": 5161.19, "total_tokens": 19730432} {"current_steps": 4818, "total_steps": 6710, "loss": 0.1558, "lr": 4.591875815933496e-07, "epoch": 3.5901639344262293, "percentage": 71.8, "elapsed_time": "1:03:43", "remaining_time": "0:25:01", "throughput": 5161.21, "total_tokens": 19734528} {"current_steps": 4819, "total_steps": 6710, "loss": 0.1429, "lr": 4.5873443273891217e-07, "epoch": 3.590909090909091, "percentage": 71.82, "elapsed_time": "1:03:44", "remaining_time": "0:25:00", "throughput": 5161.23, "total_tokens": 19738624} {"current_steps": 4820, "total_steps": 6710, "loss": 0.2205, "lr": 4.582814573355375e-07, "epoch": 3.5916542473919524, "percentage": 71.83, "elapsed_time": "1:03:45", "remaining_time": "0:24:59", "throughput": 5161.25, "total_tokens": 19742720} {"current_steps": 4821, "total_steps": 6710, "loss": 0.1146, "lr": 4.578286554825201e-07, "epoch": 3.592399403874814, "percentage": 71.85, "elapsed_time": "1:03:45", "remaining_time": "0:24:59", "throughput": 5161.26, "total_tokens": 19746816} {"current_steps": 4822, "total_steps": 6710, "loss": 0.1657, "lr": 4.573760272791186e-07, "epoch": 3.593144560357675, "percentage": 71.86, "elapsed_time": "1:03:46", "remaining_time": "0:24:58", "throughput": 5161.28, "total_tokens": 19750912} {"current_steps": 4823, "total_steps": 6710, "loss": 0.1815, "lr": 4.569235728245512e-07, "epoch": 3.5938897168405366, "percentage": 71.88, "elapsed_time": "1:03:47", "remaining_time": "0:24:57", "throughput": 5161.29, "total_tokens": 19755008} {"current_steps": 4824, "total_steps": 6710, "loss": 0.114, "lr": 4.564712922180002e-07, "epoch": 3.5946348733233977, "percentage": 71.89, "elapsed_time": "1:03:48", "remaining_time": "0:24:56", "throughput": 5161.31, "total_tokens": 19759104} {"current_steps": 4825, "total_steps": 6710, "loss": 0.1176, "lr": 4.5601918555860784e-07, "epoch": 3.5953800298062593, "percentage": 71.91, "elapsed_time": "1:03:49", "remaining_time": "0:24:55", "throughput": 5161.33, "total_tokens": 19763200} {"current_steps": 4826, "total_steps": 6710, "loss": 0.1419, "lr": 4.555672529454799e-07, "epoch": 3.596125186289121, "percentage": 71.92, "elapsed_time": "1:03:49", "remaining_time": "0:24:55", "throughput": 5161.35, "total_tokens": 19767296} {"current_steps": 4827, "total_steps": 6710, "loss": 0.0878, "lr": 4.55115494477683e-07, "epoch": 3.5968703427719824, "percentage": 71.94, "elapsed_time": "1:03:50", "remaining_time": "0:24:54", "throughput": 5161.36, "total_tokens": 19771392} {"current_steps": 4828, "total_steps": 6710, "loss": 0.2974, "lr": 4.546639102542452e-07, "epoch": 3.5976154992548435, "percentage": 71.95, "elapsed_time": "1:03:51", "remaining_time": "0:24:53", "throughput": 5161.38, "total_tokens": 19775488} {"current_steps": 4829, "total_steps": 6710, "loss": 0.063, "lr": 4.542125003741579e-07, "epoch": 3.598360655737705, "percentage": 71.97, "elapsed_time": "1:03:52", "remaining_time": "0:24:52", "throughput": 5161.39, "total_tokens": 19779584} {"current_steps": 4830, "total_steps": 6710, "loss": 0.2492, "lr": 4.5376126493637246e-07, "epoch": 3.599105812220566, "percentage": 71.98, "elapsed_time": "1:03:53", "remaining_time": "0:24:51", "throughput": 5161.4, "total_tokens": 19783680} {"current_steps": 4831, "total_steps": 6710, "loss": 0.096, "lr": 4.533102040398044e-07, "epoch": 3.5998509687034277, "percentage": 72.0, "elapsed_time": "1:03:53", "remaining_time": "0:24:51", "throughput": 5161.41, "total_tokens": 19787776} {"current_steps": 4832, "total_steps": 6710, "loss": 0.1015, "lr": 4.528593177833275e-07, "epoch": 3.6005961251862892, "percentage": 72.01, "elapsed_time": "1:03:54", "remaining_time": "0:24:50", "throughput": 5161.43, "total_tokens": 19791872} {"current_steps": 4833, "total_steps": 6710, "loss": 0.2664, "lr": 4.5240860626578066e-07, "epoch": 3.601341281669151, "percentage": 72.03, "elapsed_time": "1:03:55", "remaining_time": "0:24:49", "throughput": 5161.45, "total_tokens": 19795968} {"current_steps": 4834, "total_steps": 6710, "loss": 0.2546, "lr": 4.5195806958596227e-07, "epoch": 3.602086438152012, "percentage": 72.04, "elapsed_time": "1:03:56", "remaining_time": "0:24:48", "throughput": 5161.46, "total_tokens": 19800064} {"current_steps": 4835, "total_steps": 6710, "loss": 0.3872, "lr": 4.5150770784263403e-07, "epoch": 3.6028315946348735, "percentage": 72.06, "elapsed_time": "1:03:56", "remaining_time": "0:24:47", "throughput": 5161.48, "total_tokens": 19804160} {"current_steps": 4836, "total_steps": 6710, "loss": 0.3311, "lr": 4.510575211345174e-07, "epoch": 3.6035767511177346, "percentage": 72.07, "elapsed_time": "1:03:57", "remaining_time": "0:24:47", "throughput": 5161.48, "total_tokens": 19808256} {"current_steps": 4837, "total_steps": 6710, "loss": 0.1836, "lr": 4.506075095602977e-07, "epoch": 3.604321907600596, "percentage": 72.09, "elapsed_time": "1:03:58", "remaining_time": "0:24:46", "throughput": 5161.5, "total_tokens": 19812352} {"current_steps": 4838, "total_steps": 6710, "loss": 0.2994, "lr": 4.5015767321862e-07, "epoch": 3.6050670640834577, "percentage": 72.1, "elapsed_time": "1:03:59", "remaining_time": "0:24:45", "throughput": 5161.49, "total_tokens": 19816448} {"current_steps": 4839, "total_steps": 6710, "loss": 0.1382, "lr": 4.497080122080912e-07, "epoch": 3.605812220566319, "percentage": 72.12, "elapsed_time": "1:04:00", "remaining_time": "0:24:44", "throughput": 5161.51, "total_tokens": 19820544} {"current_steps": 4840, "total_steps": 6710, "loss": 0.076, "lr": 4.4925852662728114e-07, "epoch": 3.6065573770491803, "percentage": 72.13, "elapsed_time": "1:04:00", "remaining_time": "0:24:43", "throughput": 5161.53, "total_tokens": 19824640} {"current_steps": 4841, "total_steps": 6710, "loss": 0.1386, "lr": 4.488092165747196e-07, "epoch": 3.607302533532042, "percentage": 72.15, "elapsed_time": "1:04:01", "remaining_time": "0:24:43", "throughput": 5161.54, "total_tokens": 19828736} {"current_steps": 4842, "total_steps": 6710, "loss": 0.1512, "lr": 4.4836008214889913e-07, "epoch": 3.608047690014903, "percentage": 72.16, "elapsed_time": "1:04:02", "remaining_time": "0:24:42", "throughput": 5161.56, "total_tokens": 19832832} {"current_steps": 4843, "total_steps": 6710, "loss": 0.2796, "lr": 4.479111234482723e-07, "epoch": 3.6087928464977646, "percentage": 72.18, "elapsed_time": "1:04:03", "remaining_time": "0:24:41", "throughput": 5161.58, "total_tokens": 19836928} {"current_steps": 4844, "total_steps": 6710, "loss": 0.1541, "lr": 4.4746234057125567e-07, "epoch": 3.609538002980626, "percentage": 72.19, "elapsed_time": "1:04:03", "remaining_time": "0:24:40", "throughput": 5161.59, "total_tokens": 19841024} {"current_steps": 4845, "total_steps": 6710, "loss": 0.2254, "lr": 4.470137336162238e-07, "epoch": 3.610283159463487, "percentage": 72.21, "elapsed_time": "1:04:04", "remaining_time": "0:24:39", "throughput": 5161.61, "total_tokens": 19845120} {"current_steps": 4846, "total_steps": 6710, "loss": 0.0965, "lr": 4.4656530268151573e-07, "epoch": 3.6110283159463488, "percentage": 72.22, "elapsed_time": "1:04:05", "remaining_time": "0:24:39", "throughput": 5161.63, "total_tokens": 19849216} {"current_steps": 4847, "total_steps": 6710, "loss": 0.1593, "lr": 4.461170478654303e-07, "epoch": 3.61177347242921, "percentage": 72.24, "elapsed_time": "1:04:06", "remaining_time": "0:24:38", "throughput": 5161.64, "total_tokens": 19853312} {"current_steps": 4848, "total_steps": 6710, "loss": 0.143, "lr": 4.4566896926622776e-07, "epoch": 3.6125186289120714, "percentage": 72.25, "elapsed_time": "1:04:07", "remaining_time": "0:24:37", "throughput": 5161.66, "total_tokens": 19857408} {"current_steps": 4849, "total_steps": 6710, "loss": 0.1441, "lr": 4.4522106698213106e-07, "epoch": 3.613263785394933, "percentage": 72.27, "elapsed_time": "1:04:07", "remaining_time": "0:24:36", "throughput": 5161.68, "total_tokens": 19861504} {"current_steps": 4850, "total_steps": 6710, "loss": 0.0928, "lr": 4.447733411113228e-07, "epoch": 3.6140089418777945, "percentage": 72.28, "elapsed_time": "1:04:08", "remaining_time": "0:24:35", "throughput": 5161.7, "total_tokens": 19865600} {"current_steps": 4851, "total_steps": 6710, "loss": 0.0848, "lr": 4.4432579175194835e-07, "epoch": 3.6147540983606556, "percentage": 72.3, "elapsed_time": "1:04:09", "remaining_time": "0:24:35", "throughput": 5161.72, "total_tokens": 19869696} {"current_steps": 4852, "total_steps": 6710, "loss": 0.2419, "lr": 4.4387841900211293e-07, "epoch": 3.615499254843517, "percentage": 72.31, "elapsed_time": "1:04:10", "remaining_time": "0:24:34", "throughput": 5161.73, "total_tokens": 19873792} {"current_steps": 4853, "total_steps": 6710, "loss": 0.2532, "lr": 4.434312229598847e-07, "epoch": 3.6162444113263783, "percentage": 72.32, "elapsed_time": "1:04:11", "remaining_time": "0:24:33", "throughput": 5161.75, "total_tokens": 19877888} {"current_steps": 4854, "total_steps": 6710, "loss": 0.4199, "lr": 4.4298420372329177e-07, "epoch": 3.61698956780924, "percentage": 72.34, "elapsed_time": "1:04:11", "remaining_time": "0:24:32", "throughput": 5161.75, "total_tokens": 19881984} {"current_steps": 4855, "total_steps": 6710, "loss": 0.0928, "lr": 4.425373613903236e-07, "epoch": 3.6177347242921014, "percentage": 72.35, "elapsed_time": "1:04:12", "remaining_time": "0:24:31", "throughput": 5161.77, "total_tokens": 19886080} {"current_steps": 4856, "total_steps": 6710, "loss": 0.1019, "lr": 4.4209069605893215e-07, "epoch": 3.618479880774963, "percentage": 72.37, "elapsed_time": "1:04:13", "remaining_time": "0:24:31", "throughput": 5161.79, "total_tokens": 19890176} {"current_steps": 4857, "total_steps": 6710, "loss": 0.367, "lr": 4.416442078270286e-07, "epoch": 3.619225037257824, "percentage": 72.38, "elapsed_time": "1:04:14", "remaining_time": "0:24:30", "throughput": 5161.79, "total_tokens": 19894272} {"current_steps": 4858, "total_steps": 6710, "loss": 0.2057, "lr": 4.411978967924876e-07, "epoch": 3.6199701937406856, "percentage": 72.4, "elapsed_time": "1:04:14", "remaining_time": "0:24:29", "throughput": 5161.8, "total_tokens": 19898368} {"current_steps": 4859, "total_steps": 6710, "loss": 0.1076, "lr": 4.407517630531423e-07, "epoch": 3.6207153502235467, "percentage": 72.41, "elapsed_time": "1:04:15", "remaining_time": "0:24:28", "throughput": 5161.82, "total_tokens": 19902464} {"current_steps": 4860, "total_steps": 6710, "loss": 0.2341, "lr": 4.403058067067895e-07, "epoch": 3.6214605067064083, "percentage": 72.43, "elapsed_time": "1:04:16", "remaining_time": "0:24:28", "throughput": 5161.84, "total_tokens": 19906560} {"current_steps": 4861, "total_steps": 6710, "loss": 0.1014, "lr": 4.398600278511851e-07, "epoch": 3.62220566318927, "percentage": 72.44, "elapsed_time": "1:04:17", "remaining_time": "0:24:27", "throughput": 5161.86, "total_tokens": 19910656} {"current_steps": 4862, "total_steps": 6710, "loss": 0.3769, "lr": 4.39414426584048e-07, "epoch": 3.6229508196721314, "percentage": 72.46, "elapsed_time": "1:04:18", "remaining_time": "0:24:26", "throughput": 5161.87, "total_tokens": 19914752} {"current_steps": 4863, "total_steps": 6710, "loss": 0.2174, "lr": 4.389690030030562e-07, "epoch": 3.6236959761549925, "percentage": 72.47, "elapsed_time": "1:04:18", "remaining_time": "0:24:25", "throughput": 5161.89, "total_tokens": 19918848} {"current_steps": 4864, "total_steps": 6710, "loss": 0.0827, "lr": 4.385237572058508e-07, "epoch": 3.624441132637854, "percentage": 72.49, "elapsed_time": "1:04:19", "remaining_time": "0:24:24", "throughput": 5161.91, "total_tokens": 19922944} {"current_steps": 4865, "total_steps": 6710, "loss": 0.1636, "lr": 4.380786892900321e-07, "epoch": 3.625186289120715, "percentage": 72.5, "elapsed_time": "1:04:20", "remaining_time": "0:24:24", "throughput": 5161.92, "total_tokens": 19927040} {"current_steps": 4866, "total_steps": 6710, "loss": 0.1284, "lr": 4.3763379935316197e-07, "epoch": 3.6259314456035767, "percentage": 72.52, "elapsed_time": "1:04:21", "remaining_time": "0:24:23", "throughput": 5161.94, "total_tokens": 19931136} {"current_steps": 4867, "total_steps": 6710, "loss": 0.1992, "lr": 4.3718908749276436e-07, "epoch": 3.6266766020864383, "percentage": 72.53, "elapsed_time": "1:04:21", "remaining_time": "0:24:22", "throughput": 5161.96, "total_tokens": 19935232} {"current_steps": 4868, "total_steps": 6710, "loss": 0.1132, "lr": 4.3674455380632224e-07, "epoch": 3.6274217585693, "percentage": 72.55, "elapsed_time": "1:04:22", "remaining_time": "0:24:21", "throughput": 5161.98, "total_tokens": 19939328} {"current_steps": 4869, "total_steps": 6710, "loss": 0.0847, "lr": 4.363001983912815e-07, "epoch": 3.628166915052161, "percentage": 72.56, "elapsed_time": "1:04:23", "remaining_time": "0:24:20", "throughput": 5162.0, "total_tokens": 19943424} {"current_steps": 4870, "total_steps": 6710, "loss": 0.2441, "lr": 4.358560213450472e-07, "epoch": 3.6289120715350225, "percentage": 72.58, "elapsed_time": "1:04:24", "remaining_time": "0:24:20", "throughput": 5162.01, "total_tokens": 19947520} {"current_steps": 4871, "total_steps": 6710, "loss": 0.2217, "lr": 4.354120227649873e-07, "epoch": 3.6296572280178836, "percentage": 72.59, "elapsed_time": "1:04:25", "remaining_time": "0:24:19", "throughput": 5162.03, "total_tokens": 19951616} {"current_steps": 4872, "total_steps": 6710, "loss": 0.1225, "lr": 4.3496820274842796e-07, "epoch": 3.630402384500745, "percentage": 72.61, "elapsed_time": "1:04:25", "remaining_time": "0:24:18", "throughput": 5162.04, "total_tokens": 19955712} {"current_steps": 4873, "total_steps": 6710, "loss": 0.149, "lr": 4.3452456139265883e-07, "epoch": 3.6311475409836067, "percentage": 72.62, "elapsed_time": "1:04:26", "remaining_time": "0:24:17", "throughput": 5162.06, "total_tokens": 19959808} {"current_steps": 4874, "total_steps": 6710, "loss": 0.1408, "lr": 4.3408109879492887e-07, "epoch": 3.631892697466468, "percentage": 72.64, "elapsed_time": "1:04:27", "remaining_time": "0:24:16", "throughput": 5162.08, "total_tokens": 19963904} {"current_steps": 4875, "total_steps": 6710, "loss": 0.1409, "lr": 4.3363781505244783e-07, "epoch": 3.6326378539493294, "percentage": 72.65, "elapsed_time": "1:04:28", "remaining_time": "0:24:16", "throughput": 5162.1, "total_tokens": 19968000} {"current_steps": 4876, "total_steps": 6710, "loss": 0.0955, "lr": 4.3319471026238737e-07, "epoch": 3.633383010432191, "percentage": 72.67, "elapsed_time": "1:04:28", "remaining_time": "0:24:15", "throughput": 5162.1, "total_tokens": 19972096} {"current_steps": 4877, "total_steps": 6710, "loss": 0.3489, "lr": 4.3275178452187857e-07, "epoch": 3.634128166915052, "percentage": 72.68, "elapsed_time": "1:04:29", "remaining_time": "0:24:14", "throughput": 5162.12, "total_tokens": 19976192} {"current_steps": 4878, "total_steps": 6710, "loss": 0.1505, "lr": 4.3230903792801484e-07, "epoch": 3.6348733233979136, "percentage": 72.7, "elapsed_time": "1:04:30", "remaining_time": "0:24:13", "throughput": 5162.13, "total_tokens": 19980288} {"current_steps": 4879, "total_steps": 6710, "loss": 0.111, "lr": 4.318664705778482e-07, "epoch": 3.635618479880775, "percentage": 72.71, "elapsed_time": "1:04:31", "remaining_time": "0:24:12", "throughput": 5162.14, "total_tokens": 19984384} {"current_steps": 4880, "total_steps": 6710, "loss": 0.3359, "lr": 4.314240825683938e-07, "epoch": 3.6363636363636362, "percentage": 72.73, "elapsed_time": "1:04:32", "remaining_time": "0:24:12", "throughput": 5162.16, "total_tokens": 19988480} {"current_steps": 4881, "total_steps": 6710, "loss": 0.1611, "lr": 4.309818739966255e-07, "epoch": 3.637108792846498, "percentage": 72.74, "elapsed_time": "1:04:32", "remaining_time": "0:24:11", "throughput": 5162.17, "total_tokens": 19992576} {"current_steps": 4882, "total_steps": 6710, "loss": 0.1562, "lr": 4.3053984495947843e-07, "epoch": 3.637853949329359, "percentage": 72.76, "elapsed_time": "1:04:33", "remaining_time": "0:24:10", "throughput": 5162.19, "total_tokens": 19996672} {"current_steps": 4883, "total_steps": 6710, "loss": 0.0676, "lr": 4.300979955538492e-07, "epoch": 3.6385991058122205, "percentage": 72.77, "elapsed_time": "1:04:34", "remaining_time": "0:24:09", "throughput": 5162.21, "total_tokens": 20000768} {"current_steps": 4884, "total_steps": 6710, "loss": 0.2906, "lr": 4.2965632587659345e-07, "epoch": 3.639344262295082, "percentage": 72.79, "elapsed_time": "1:04:35", "remaining_time": "0:24:08", "throughput": 5162.22, "total_tokens": 20004864} {"current_steps": 4885, "total_steps": 6710, "loss": 0.0864, "lr": 4.2921483602452974e-07, "epoch": 3.6400894187779436, "percentage": 72.8, "elapsed_time": "1:04:36", "remaining_time": "0:24:08", "throughput": 5162.24, "total_tokens": 20008960} {"current_steps": 4886, "total_steps": 6710, "loss": 0.1864, "lr": 4.2877352609443425e-07, "epoch": 3.6408345752608047, "percentage": 72.82, "elapsed_time": "1:04:36", "remaining_time": "0:24:07", "throughput": 5162.25, "total_tokens": 20013056} {"current_steps": 4887, "total_steps": 6710, "loss": 0.0976, "lr": 4.2833239618304613e-07, "epoch": 3.6415797317436662, "percentage": 72.83, "elapsed_time": "1:04:37", "remaining_time": "0:24:06", "throughput": 5162.27, "total_tokens": 20017152} {"current_steps": 4888, "total_steps": 6710, "loss": 0.1131, "lr": 4.2789144638706357e-07, "epoch": 3.6423248882265273, "percentage": 72.85, "elapsed_time": "1:04:38", "remaining_time": "0:24:05", "throughput": 5162.28, "total_tokens": 20021248} {"current_steps": 4889, "total_steps": 6710, "loss": 0.2062, "lr": 4.274506768031468e-07, "epoch": 3.643070044709389, "percentage": 72.86, "elapsed_time": "1:04:39", "remaining_time": "0:24:04", "throughput": 5162.29, "total_tokens": 20025344} {"current_steps": 4890, "total_steps": 6710, "loss": 0.1498, "lr": 4.2701008752791483e-07, "epoch": 3.6438152011922504, "percentage": 72.88, "elapsed_time": "1:04:39", "remaining_time": "0:24:04", "throughput": 5162.3, "total_tokens": 20029440} {"current_steps": 4891, "total_steps": 6710, "loss": 0.2244, "lr": 4.2656967865794876e-07, "epoch": 3.644560357675112, "percentage": 72.89, "elapsed_time": "1:04:40", "remaining_time": "0:24:03", "throughput": 5162.32, "total_tokens": 20033536} {"current_steps": 4892, "total_steps": 6710, "loss": 0.2118, "lr": 4.261294502897889e-07, "epoch": 3.645305514157973, "percentage": 72.91, "elapsed_time": "1:04:41", "remaining_time": "0:24:02", "throughput": 5162.34, "total_tokens": 20037632} {"current_steps": 4893, "total_steps": 6710, "loss": 0.1418, "lr": 4.256894025199361e-07, "epoch": 3.6460506706408347, "percentage": 72.92, "elapsed_time": "1:04:42", "remaining_time": "0:24:01", "throughput": 5162.36, "total_tokens": 20041728} {"current_steps": 4894, "total_steps": 6710, "loss": 0.074, "lr": 4.2524953544485284e-07, "epoch": 3.6467958271236958, "percentage": 72.94, "elapsed_time": "1:04:43", "remaining_time": "0:24:00", "throughput": 5162.37, "total_tokens": 20045824} {"current_steps": 4895, "total_steps": 6710, "loss": 0.3055, "lr": 4.2480984916096023e-07, "epoch": 3.6475409836065573, "percentage": 72.95, "elapsed_time": "1:04:43", "remaining_time": "0:24:00", "throughput": 5162.39, "total_tokens": 20049920} {"current_steps": 4896, "total_steps": 6710, "loss": 0.1972, "lr": 4.2437034376464137e-07, "epoch": 3.648286140089419, "percentage": 72.97, "elapsed_time": "1:04:44", "remaining_time": "0:23:59", "throughput": 5162.41, "total_tokens": 20054016} {"current_steps": 4897, "total_steps": 6710, "loss": 0.111, "lr": 4.2393101935223834e-07, "epoch": 3.6490312965722804, "percentage": 72.98, "elapsed_time": "1:04:45", "remaining_time": "0:23:58", "throughput": 5162.42, "total_tokens": 20058112} {"current_steps": 4898, "total_steps": 6710, "loss": 0.1372, "lr": 4.2349187602005543e-07, "epoch": 3.6497764530551415, "percentage": 73.0, "elapsed_time": "1:04:46", "remaining_time": "0:23:57", "throughput": 5162.44, "total_tokens": 20062208} {"current_steps": 4899, "total_steps": 6710, "loss": 0.2175, "lr": 4.2305291386435424e-07, "epoch": 3.650521609538003, "percentage": 73.01, "elapsed_time": "1:04:46", "remaining_time": "0:23:56", "throughput": 5162.46, "total_tokens": 20066304} {"current_steps": 4900, "total_steps": 6710, "loss": 0.2616, "lr": 4.226141329813596e-07, "epoch": 3.651266766020864, "percentage": 73.03, "elapsed_time": "1:04:47", "remaining_time": "0:23:56", "throughput": 5162.47, "total_tokens": 20070400} {"current_steps": 4901, "total_steps": 6710, "loss": 0.2073, "lr": 4.22175533467255e-07, "epoch": 3.6520119225037257, "percentage": 73.04, "elapsed_time": "1:04:48", "remaining_time": "0:23:55", "throughput": 5162.49, "total_tokens": 20074496} {"current_steps": 4902, "total_steps": 6710, "loss": 0.2428, "lr": 4.2173711541818443e-07, "epoch": 3.6527570789865873, "percentage": 73.06, "elapsed_time": "1:04:49", "remaining_time": "0:23:54", "throughput": 5162.51, "total_tokens": 20078592} {"current_steps": 4903, "total_steps": 6710, "loss": 0.2096, "lr": 4.212988789302529e-07, "epoch": 3.653502235469449, "percentage": 73.07, "elapsed_time": "1:04:50", "remaining_time": "0:23:53", "throughput": 5162.52, "total_tokens": 20082688} {"current_steps": 4904, "total_steps": 6710, "loss": 0.1211, "lr": 4.2086082409952393e-07, "epoch": 3.65424739195231, "percentage": 73.08, "elapsed_time": "1:04:50", "remaining_time": "0:23:52", "throughput": 5162.54, "total_tokens": 20086784} {"current_steps": 4905, "total_steps": 6710, "loss": 0.1131, "lr": 4.2042295102202356e-07, "epoch": 3.6549925484351715, "percentage": 73.1, "elapsed_time": "1:04:51", "remaining_time": "0:23:52", "throughput": 5162.55, "total_tokens": 20090880} {"current_steps": 4906, "total_steps": 6710, "loss": 0.2246, "lr": 4.199852597937354e-07, "epoch": 3.6557377049180326, "percentage": 73.11, "elapsed_time": "1:04:52", "remaining_time": "0:23:51", "throughput": 5162.57, "total_tokens": 20094976} {"current_steps": 4907, "total_steps": 6710, "loss": 0.1319, "lr": 4.1954775051060577e-07, "epoch": 3.656482861400894, "percentage": 73.13, "elapsed_time": "1:04:53", "remaining_time": "0:23:50", "throughput": 5162.59, "total_tokens": 20099072} {"current_steps": 4908, "total_steps": 6710, "loss": 0.1379, "lr": 4.191104232685386e-07, "epoch": 3.6572280178837557, "percentage": 73.14, "elapsed_time": "1:04:53", "remaining_time": "0:23:49", "throughput": 5162.6, "total_tokens": 20103168} {"current_steps": 4909, "total_steps": 6710, "loss": 0.1983, "lr": 4.1867327816340023e-07, "epoch": 3.657973174366617, "percentage": 73.16, "elapsed_time": "1:04:54", "remaining_time": "0:23:48", "throughput": 5162.62, "total_tokens": 20107264} {"current_steps": 4910, "total_steps": 6710, "loss": 0.2582, "lr": 4.182363152910154e-07, "epoch": 3.6587183308494784, "percentage": 73.17, "elapsed_time": "1:04:55", "remaining_time": "0:23:48", "throughput": 5162.63, "total_tokens": 20111360} {"current_steps": 4911, "total_steps": 6710, "loss": 0.1602, "lr": 4.177995347471692e-07, "epoch": 3.65946348733234, "percentage": 73.19, "elapsed_time": "1:04:56", "remaining_time": "0:23:47", "throughput": 5162.65, "total_tokens": 20115456} {"current_steps": 4912, "total_steps": 6710, "loss": 0.18, "lr": 4.173629366276083e-07, "epoch": 3.660208643815201, "percentage": 73.2, "elapsed_time": "1:04:57", "remaining_time": "0:23:46", "throughput": 5162.66, "total_tokens": 20119552} {"current_steps": 4913, "total_steps": 6710, "loss": 0.2272, "lr": 4.169265210280364e-07, "epoch": 3.6609538002980626, "percentage": 73.22, "elapsed_time": "1:04:57", "remaining_time": "0:23:45", "throughput": 5162.68, "total_tokens": 20123648} {"current_steps": 4914, "total_steps": 6710, "loss": 0.1298, "lr": 4.164902880441202e-07, "epoch": 3.661698956780924, "percentage": 73.23, "elapsed_time": "1:04:58", "remaining_time": "0:23:44", "throughput": 5162.69, "total_tokens": 20127744} {"current_steps": 4915, "total_steps": 6710, "loss": 0.2149, "lr": 4.160542377714842e-07, "epoch": 3.6624441132637853, "percentage": 73.25, "elapsed_time": "1:04:59", "remaining_time": "0:23:44", "throughput": 5162.7, "total_tokens": 20131840} {"current_steps": 4916, "total_steps": 6710, "loss": 0.0692, "lr": 4.156183703057147e-07, "epoch": 3.663189269746647, "percentage": 73.26, "elapsed_time": "1:05:00", "remaining_time": "0:23:43", "throughput": 5162.71, "total_tokens": 20135936} {"current_steps": 4917, "total_steps": 6710, "loss": 0.0584, "lr": 4.151826857423559e-07, "epoch": 3.663934426229508, "percentage": 73.28, "elapsed_time": "1:05:01", "remaining_time": "0:23:42", "throughput": 5162.72, "total_tokens": 20140032} {"current_steps": 4918, "total_steps": 6710, "loss": 0.0399, "lr": 4.1474718417691393e-07, "epoch": 3.6646795827123695, "percentage": 73.29, "elapsed_time": "1:05:01", "remaining_time": "0:23:41", "throughput": 5162.74, "total_tokens": 20144128} {"current_steps": 4919, "total_steps": 6710, "loss": 0.1403, "lr": 4.1431186570485354e-07, "epoch": 3.665424739195231, "percentage": 73.31, "elapsed_time": "1:05:02", "remaining_time": "0:23:40", "throughput": 5162.75, "total_tokens": 20148224} {"current_steps": 4920, "total_steps": 6710, "loss": 0.1251, "lr": 4.1387673042159905e-07, "epoch": 3.6661698956780926, "percentage": 73.32, "elapsed_time": "1:05:03", "remaining_time": "0:23:40", "throughput": 5162.77, "total_tokens": 20152320} {"current_steps": 4921, "total_steps": 6710, "loss": 0.1774, "lr": 4.1344177842253616e-07, "epoch": 3.6669150521609537, "percentage": 73.34, "elapsed_time": "1:05:04", "remaining_time": "0:23:39", "throughput": 5162.78, "total_tokens": 20156416} {"current_steps": 4922, "total_steps": 6710, "loss": 0.0902, "lr": 4.1300700980300854e-07, "epoch": 3.6676602086438153, "percentage": 73.35, "elapsed_time": "1:05:04", "remaining_time": "0:23:38", "throughput": 5162.79, "total_tokens": 20160512} {"current_steps": 4923, "total_steps": 6710, "loss": 0.1439, "lr": 4.125724246583214e-07, "epoch": 3.6684053651266764, "percentage": 73.37, "elapsed_time": "1:05:05", "remaining_time": "0:23:37", "throughput": 5162.81, "total_tokens": 20164608} {"current_steps": 4924, "total_steps": 6710, "loss": 0.1573, "lr": 4.121380230837382e-07, "epoch": 3.669150521609538, "percentage": 73.38, "elapsed_time": "1:05:06", "remaining_time": "0:23:36", "throughput": 5162.83, "total_tokens": 20168704} {"current_steps": 4925, "total_steps": 6710, "loss": 0.2321, "lr": 4.1170380517448397e-07, "epoch": 3.6698956780923995, "percentage": 73.4, "elapsed_time": "1:05:07", "remaining_time": "0:23:36", "throughput": 5162.84, "total_tokens": 20172800} {"current_steps": 4926, "total_steps": 6710, "loss": 0.2299, "lr": 4.11269771025741e-07, "epoch": 3.670640834575261, "percentage": 73.41, "elapsed_time": "1:05:08", "remaining_time": "0:23:35", "throughput": 5162.86, "total_tokens": 20176896} {"current_steps": 4927, "total_steps": 6710, "loss": 0.1584, "lr": 4.1083592073265344e-07, "epoch": 3.671385991058122, "percentage": 73.43, "elapsed_time": "1:05:08", "remaining_time": "0:23:34", "throughput": 5162.88, "total_tokens": 20180992} {"current_steps": 4928, "total_steps": 6710, "loss": 0.2439, "lr": 4.1040225439032395e-07, "epoch": 3.6721311475409837, "percentage": 73.44, "elapsed_time": "1:05:09", "remaining_time": "0:23:33", "throughput": 5162.89, "total_tokens": 20185088} {"current_steps": 4929, "total_steps": 6710, "loss": 0.2788, "lr": 4.09968772093816e-07, "epoch": 3.672876304023845, "percentage": 73.46, "elapsed_time": "1:05:10", "remaining_time": "0:23:32", "throughput": 5162.9, "total_tokens": 20189184} {"current_steps": 4930, "total_steps": 6710, "loss": 0.1815, "lr": 4.0953547393815145e-07, "epoch": 3.6736214605067063, "percentage": 73.47, "elapsed_time": "1:05:11", "remaining_time": "0:23:32", "throughput": 5162.92, "total_tokens": 20193280} {"current_steps": 4931, "total_steps": 6710, "loss": 0.0828, "lr": 4.0910236001831207e-07, "epoch": 3.674366616989568, "percentage": 73.49, "elapsed_time": "1:05:11", "remaining_time": "0:23:31", "throughput": 5162.93, "total_tokens": 20197376} {"current_steps": 4932, "total_steps": 6710, "loss": 0.2445, "lr": 4.086694304292405e-07, "epoch": 3.6751117734724295, "percentage": 73.5, "elapsed_time": "1:05:12", "remaining_time": "0:23:30", "throughput": 5162.95, "total_tokens": 20201472} {"current_steps": 4933, "total_steps": 6710, "loss": 0.1632, "lr": 4.0823668526583674e-07, "epoch": 3.6758569299552906, "percentage": 73.52, "elapsed_time": "1:05:13", "remaining_time": "0:23:29", "throughput": 5162.96, "total_tokens": 20205568} {"current_steps": 4934, "total_steps": 6710, "loss": 0.2141, "lr": 4.078041246229629e-07, "epoch": 3.676602086438152, "percentage": 73.53, "elapsed_time": "1:05:14", "remaining_time": "0:23:28", "throughput": 5162.98, "total_tokens": 20209664} {"current_steps": 4935, "total_steps": 6710, "loss": 0.0673, "lr": 4.073717485954383e-07, "epoch": 3.6773472429210132, "percentage": 73.55, "elapsed_time": "1:05:15", "remaining_time": "0:23:28", "throughput": 5162.98, "total_tokens": 20213760} {"current_steps": 4936, "total_steps": 6710, "loss": 0.3226, "lr": 4.0693955727804364e-07, "epoch": 3.678092399403875, "percentage": 73.56, "elapsed_time": "1:05:15", "remaining_time": "0:23:27", "throughput": 5162.99, "total_tokens": 20217856} {"current_steps": 4937, "total_steps": 6710, "loss": 0.2883, "lr": 4.065075507655182e-07, "epoch": 3.6788375558867363, "percentage": 73.58, "elapsed_time": "1:05:16", "remaining_time": "0:23:26", "throughput": 5163.01, "total_tokens": 20221952} {"current_steps": 4938, "total_steps": 6710, "loss": 0.24, "lr": 4.0607572915256023e-07, "epoch": 3.679582712369598, "percentage": 73.59, "elapsed_time": "1:05:17", "remaining_time": "0:23:25", "throughput": 5163.03, "total_tokens": 20226048} {"current_steps": 4939, "total_steps": 6710, "loss": 0.2401, "lr": 4.0564409253382927e-07, "epoch": 3.680327868852459, "percentage": 73.61, "elapsed_time": "1:05:18", "remaining_time": "0:23:24", "throughput": 5163.04, "total_tokens": 20230144} {"current_steps": 4940, "total_steps": 6710, "loss": 0.1877, "lr": 4.052126410039417e-07, "epoch": 3.6810730253353205, "percentage": 73.62, "elapsed_time": "1:05:19", "remaining_time": "0:23:24", "throughput": 5163.06, "total_tokens": 20234240} {"current_steps": 4941, "total_steps": 6710, "loss": 0.1701, "lr": 4.047813746574761e-07, "epoch": 3.6818181818181817, "percentage": 73.64, "elapsed_time": "1:05:19", "remaining_time": "0:23:23", "throughput": 5163.08, "total_tokens": 20238336} {"current_steps": 4942, "total_steps": 6710, "loss": 0.3906, "lr": 4.04350293588968e-07, "epoch": 3.682563338301043, "percentage": 73.65, "elapsed_time": "1:05:20", "remaining_time": "0:23:22", "throughput": 5163.1, "total_tokens": 20242432} {"current_steps": 4943, "total_steps": 6710, "loss": 0.12, "lr": 4.039193978929144e-07, "epoch": 3.6833084947839048, "percentage": 73.67, "elapsed_time": "1:05:21", "remaining_time": "0:23:21", "throughput": 5163.12, "total_tokens": 20246528} {"current_steps": 4944, "total_steps": 6710, "loss": 0.2213, "lr": 4.034886876637702e-07, "epoch": 3.684053651266766, "percentage": 73.68, "elapsed_time": "1:05:22", "remaining_time": "0:23:20", "throughput": 5163.13, "total_tokens": 20250624} {"current_steps": 4945, "total_steps": 6710, "loss": 0.2337, "lr": 4.030581629959504e-07, "epoch": 3.6847988077496274, "percentage": 73.7, "elapsed_time": "1:05:22", "remaining_time": "0:23:20", "throughput": 5163.15, "total_tokens": 20254720} {"current_steps": 4946, "total_steps": 6710, "loss": 0.0987, "lr": 4.026278239838291e-07, "epoch": 3.685543964232489, "percentage": 73.71, "elapsed_time": "1:05:23", "remaining_time": "0:23:19", "throughput": 5163.17, "total_tokens": 20258816} {"current_steps": 4947, "total_steps": 6710, "loss": 0.1146, "lr": 4.021976707217391e-07, "epoch": 3.68628912071535, "percentage": 73.73, "elapsed_time": "1:05:24", "remaining_time": "0:23:18", "throughput": 5163.18, "total_tokens": 20262912} {"current_steps": 4948, "total_steps": 6710, "loss": 0.1981, "lr": 4.017677033039741e-07, "epoch": 3.6870342771982116, "percentage": 73.74, "elapsed_time": "1:05:25", "remaining_time": "0:23:17", "throughput": 5163.2, "total_tokens": 20267008} {"current_steps": 4949, "total_steps": 6710, "loss": 0.2309, "lr": 4.0133792182478493e-07, "epoch": 3.687779433681073, "percentage": 73.76, "elapsed_time": "1:05:26", "remaining_time": "0:23:17", "throughput": 5163.22, "total_tokens": 20271104} {"current_steps": 4950, "total_steps": 6710, "loss": 0.2633, "lr": 4.009083263783836e-07, "epoch": 3.6885245901639343, "percentage": 73.77, "elapsed_time": "1:05:26", "remaining_time": "0:23:16", "throughput": 5163.24, "total_tokens": 20275200} {"current_steps": 4951, "total_steps": 6710, "loss": 0.2393, "lr": 4.0047891705894003e-07, "epoch": 3.689269746646796, "percentage": 73.79, "elapsed_time": "1:05:27", "remaining_time": "0:23:15", "throughput": 5163.26, "total_tokens": 20279296} {"current_steps": 4952, "total_steps": 6710, "loss": 0.2093, "lr": 4.0004969396058453e-07, "epoch": 3.690014903129657, "percentage": 73.8, "elapsed_time": "1:05:28", "remaining_time": "0:23:14", "throughput": 5163.28, "total_tokens": 20283392} {"current_steps": 4953, "total_steps": 6710, "loss": 0.0964, "lr": 3.9962065717740457e-07, "epoch": 3.6907600596125185, "percentage": 73.82, "elapsed_time": "1:05:29", "remaining_time": "0:23:13", "throughput": 5163.3, "total_tokens": 20287488} {"current_steps": 4954, "total_steps": 6710, "loss": 0.1058, "lr": 3.991918068034492e-07, "epoch": 3.69150521609538, "percentage": 73.83, "elapsed_time": "1:05:29", "remaining_time": "0:23:13", "throughput": 5163.32, "total_tokens": 20291584} {"current_steps": 4955, "total_steps": 6710, "loss": 0.4056, "lr": 3.9876314293272475e-07, "epoch": 3.6922503725782416, "percentage": 73.85, "elapsed_time": "1:05:30", "remaining_time": "0:23:12", "throughput": 5163.32, "total_tokens": 20295680} {"current_steps": 4956, "total_steps": 6710, "loss": 0.0469, "lr": 3.983346656591981e-07, "epoch": 3.6929955290611027, "percentage": 73.86, "elapsed_time": "1:05:31", "remaining_time": "0:23:11", "throughput": 5163.34, "total_tokens": 20299776} {"current_steps": 4957, "total_steps": 6710, "loss": 0.2449, "lr": 3.979063750767942e-07, "epoch": 3.6937406855439643, "percentage": 73.87, "elapsed_time": "1:05:32", "remaining_time": "0:23:10", "throughput": 5163.36, "total_tokens": 20303872} {"current_steps": 4958, "total_steps": 6710, "loss": 0.2246, "lr": 3.974782712793969e-07, "epoch": 3.6944858420268254, "percentage": 73.89, "elapsed_time": "1:05:33", "remaining_time": "0:23:09", "throughput": 5163.37, "total_tokens": 20307968} {"current_steps": 4959, "total_steps": 6710, "loss": 0.259, "lr": 3.970503543608506e-07, "epoch": 3.695230998509687, "percentage": 73.9, "elapsed_time": "1:05:33", "remaining_time": "0:23:09", "throughput": 5163.39, "total_tokens": 20312064} {"current_steps": 4960, "total_steps": 6710, "loss": 0.2912, "lr": 3.966226244149568e-07, "epoch": 3.6959761549925485, "percentage": 73.92, "elapsed_time": "1:05:34", "remaining_time": "0:23:08", "throughput": 5163.41, "total_tokens": 20316160} {"current_steps": 4961, "total_steps": 6710, "loss": 0.0693, "lr": 3.961950815354777e-07, "epoch": 3.69672131147541, "percentage": 73.93, "elapsed_time": "1:05:35", "remaining_time": "0:23:07", "throughput": 5163.43, "total_tokens": 20320256} {"current_steps": 4962, "total_steps": 6710, "loss": 0.2284, "lr": 3.9576772581613314e-07, "epoch": 3.697466467958271, "percentage": 73.95, "elapsed_time": "1:05:36", "remaining_time": "0:23:06", "throughput": 5163.44, "total_tokens": 20324352} {"current_steps": 4963, "total_steps": 6710, "loss": 0.1422, "lr": 3.953405573506032e-07, "epoch": 3.6982116244411327, "percentage": 73.96, "elapsed_time": "1:05:36", "remaining_time": "0:23:05", "throughput": 5163.45, "total_tokens": 20328448} {"current_steps": 4964, "total_steps": 6710, "loss": 0.1105, "lr": 3.949135762325258e-07, "epoch": 3.698956780923994, "percentage": 73.98, "elapsed_time": "1:05:37", "remaining_time": "0:23:05", "throughput": 5163.47, "total_tokens": 20332544} {"current_steps": 4965, "total_steps": 6710, "loss": 0.1371, "lr": 3.944867825554981e-07, "epoch": 3.6997019374068554, "percentage": 73.99, "elapsed_time": "1:05:38", "remaining_time": "0:23:04", "throughput": 5163.49, "total_tokens": 20336640} {"current_steps": 4966, "total_steps": 6710, "loss": 0.2158, "lr": 3.9406017641307735e-07, "epoch": 3.700447093889717, "percentage": 74.01, "elapsed_time": "1:05:39", "remaining_time": "0:23:03", "throughput": 5163.5, "total_tokens": 20340736} {"current_steps": 4967, "total_steps": 6710, "loss": 0.255, "lr": 3.93633757898777e-07, "epoch": 3.7011922503725785, "percentage": 74.02, "elapsed_time": "1:05:40", "remaining_time": "0:23:02", "throughput": 5163.51, "total_tokens": 20344832} {"current_steps": 4968, "total_steps": 6710, "loss": 0.0937, "lr": 3.9320752710607244e-07, "epoch": 3.7019374068554396, "percentage": 74.04, "elapsed_time": "1:05:40", "remaining_time": "0:23:01", "throughput": 5163.53, "total_tokens": 20348928} {"current_steps": 4969, "total_steps": 6710, "loss": 0.1147, "lr": 3.9278148412839557e-07, "epoch": 3.702682563338301, "percentage": 74.05, "elapsed_time": "1:05:41", "remaining_time": "0:23:01", "throughput": 5163.55, "total_tokens": 20353024} {"current_steps": 4970, "total_steps": 6710, "loss": 0.2115, "lr": 3.9235562905913876e-07, "epoch": 3.7034277198211623, "percentage": 74.07, "elapsed_time": "1:05:42", "remaining_time": "0:23:00", "throughput": 5163.57, "total_tokens": 20357120} {"current_steps": 4971, "total_steps": 6710, "loss": 0.1802, "lr": 3.919299619916518e-07, "epoch": 3.704172876304024, "percentage": 74.08, "elapsed_time": "1:05:43", "remaining_time": "0:22:59", "throughput": 5163.58, "total_tokens": 20361216} {"current_steps": 4972, "total_steps": 6710, "loss": 0.2082, "lr": 3.915044830192448e-07, "epoch": 3.7049180327868854, "percentage": 74.1, "elapsed_time": "1:05:44", "remaining_time": "0:22:58", "throughput": 5163.6, "total_tokens": 20365312} {"current_steps": 4973, "total_steps": 6710, "loss": 0.2668, "lr": 3.9107919223518533e-07, "epoch": 3.705663189269747, "percentage": 74.11, "elapsed_time": "1:05:44", "remaining_time": "0:22:57", "throughput": 5163.62, "total_tokens": 20369408} {"current_steps": 4974, "total_steps": 6710, "loss": 0.3143, "lr": 3.906540897326998e-07, "epoch": 3.706408345752608, "percentage": 74.13, "elapsed_time": "1:05:45", "remaining_time": "0:22:57", "throughput": 5163.63, "total_tokens": 20373504} {"current_steps": 4975, "total_steps": 6710, "loss": 0.2963, "lr": 3.902291756049743e-07, "epoch": 3.7071535022354696, "percentage": 74.14, "elapsed_time": "1:05:46", "remaining_time": "0:22:56", "throughput": 5163.65, "total_tokens": 20377600} {"current_steps": 4976, "total_steps": 6710, "loss": 0.3476, "lr": 3.8980444994515266e-07, "epoch": 3.7078986587183307, "percentage": 74.16, "elapsed_time": "1:05:47", "remaining_time": "0:22:55", "throughput": 5163.66, "total_tokens": 20381696} {"current_steps": 4977, "total_steps": 6710, "loss": 0.2124, "lr": 3.8937991284633823e-07, "epoch": 3.7086438152011922, "percentage": 74.17, "elapsed_time": "1:05:47", "remaining_time": "0:22:54", "throughput": 5163.68, "total_tokens": 20385792} {"current_steps": 4978, "total_steps": 6710, "loss": 0.0821, "lr": 3.889555644015919e-07, "epoch": 3.709388971684054, "percentage": 74.19, "elapsed_time": "1:05:48", "remaining_time": "0:22:53", "throughput": 5163.7, "total_tokens": 20389888} {"current_steps": 4979, "total_steps": 6710, "loss": 0.2532, "lr": 3.88531404703935e-07, "epoch": 3.710134128166915, "percentage": 74.2, "elapsed_time": "1:05:49", "remaining_time": "0:22:53", "throughput": 5163.71, "total_tokens": 20393984} {"current_steps": 4980, "total_steps": 6710, "loss": 0.1187, "lr": 3.881074338463449e-07, "epoch": 3.7108792846497765, "percentage": 74.22, "elapsed_time": "1:05:50", "remaining_time": "0:22:52", "throughput": 5163.73, "total_tokens": 20398080} {"current_steps": 4981, "total_steps": 6710, "loss": 0.2117, "lr": 3.8768365192176015e-07, "epoch": 3.711624441132638, "percentage": 74.23, "elapsed_time": "1:05:51", "remaining_time": "0:22:51", "throughput": 5163.74, "total_tokens": 20402176} {"current_steps": 4982, "total_steps": 6710, "loss": 0.1564, "lr": 3.8726005902307587e-07, "epoch": 3.712369597615499, "percentage": 74.25, "elapsed_time": "1:05:51", "remaining_time": "0:22:50", "throughput": 5163.76, "total_tokens": 20406272} {"current_steps": 4983, "total_steps": 6710, "loss": 0.2454, "lr": 3.8683665524314767e-07, "epoch": 3.7131147540983607, "percentage": 74.26, "elapsed_time": "1:05:52", "remaining_time": "0:22:49", "throughput": 5163.78, "total_tokens": 20410368} {"current_steps": 4984, "total_steps": 6710, "loss": 0.1939, "lr": 3.864134406747881e-07, "epoch": 3.7138599105812222, "percentage": 74.28, "elapsed_time": "1:05:53", "remaining_time": "0:22:49", "throughput": 5163.8, "total_tokens": 20414464} {"current_steps": 4985, "total_steps": 6710, "loss": 0.3971, "lr": 3.859904154107687e-07, "epoch": 3.7146050670640833, "percentage": 74.29, "elapsed_time": "1:05:54", "remaining_time": "0:22:48", "throughput": 5163.81, "total_tokens": 20418560} {"current_steps": 4986, "total_steps": 6710, "loss": 0.0546, "lr": 3.8556757954382e-07, "epoch": 3.715350223546945, "percentage": 74.31, "elapsed_time": "1:05:54", "remaining_time": "0:22:47", "throughput": 5163.83, "total_tokens": 20422656} {"current_steps": 4987, "total_steps": 6710, "loss": 0.125, "lr": 3.8514493316663014e-07, "epoch": 3.716095380029806, "percentage": 74.32, "elapsed_time": "1:05:55", "remaining_time": "0:22:46", "throughput": 5163.85, "total_tokens": 20426752} {"current_steps": 4988, "total_steps": 6710, "loss": 0.0377, "lr": 3.84722476371847e-07, "epoch": 3.7168405365126675, "percentage": 74.34, "elapsed_time": "1:05:56", "remaining_time": "0:22:45", "throughput": 5163.87, "total_tokens": 20430848} {"current_steps": 4989, "total_steps": 6710, "loss": 0.0536, "lr": 3.843002092520752e-07, "epoch": 3.717585692995529, "percentage": 74.35, "elapsed_time": "1:05:57", "remaining_time": "0:22:45", "throughput": 5163.89, "total_tokens": 20434944} {"current_steps": 4990, "total_steps": 6710, "loss": 0.2299, "lr": 3.8387813189987967e-07, "epoch": 3.7183308494783907, "percentage": 74.37, "elapsed_time": "1:05:58", "remaining_time": "0:22:44", "throughput": 5163.9, "total_tokens": 20439040} {"current_steps": 4991, "total_steps": 6710, "loss": 0.1158, "lr": 3.8345624440778215e-07, "epoch": 3.7190760059612518, "percentage": 74.38, "elapsed_time": "1:05:58", "remaining_time": "0:22:43", "throughput": 5163.92, "total_tokens": 20443136} {"current_steps": 4992, "total_steps": 6710, "loss": 0.2156, "lr": 3.8303454686826323e-07, "epoch": 3.7198211624441133, "percentage": 74.4, "elapsed_time": "1:05:59", "remaining_time": "0:22:42", "throughput": 5163.91, "total_tokens": 20447232} {"current_steps": 4993, "total_steps": 6710, "loss": 0.1239, "lr": 3.8261303937376273e-07, "epoch": 3.7205663189269744, "percentage": 74.41, "elapsed_time": "1:06:00", "remaining_time": "0:22:41", "throughput": 5163.93, "total_tokens": 20451328} {"current_steps": 4994, "total_steps": 6710, "loss": 0.1887, "lr": 3.8219172201667766e-07, "epoch": 3.721311475409836, "percentage": 74.43, "elapsed_time": "1:06:01", "remaining_time": "0:22:41", "throughput": 5163.94, "total_tokens": 20455424} {"current_steps": 4995, "total_steps": 6710, "loss": 0.2329, "lr": 3.817705948893638e-07, "epoch": 3.7220566318926975, "percentage": 74.44, "elapsed_time": "1:06:01", "remaining_time": "0:22:40", "throughput": 5163.96, "total_tokens": 20459520} {"current_steps": 4996, "total_steps": 6710, "loss": 0.1306, "lr": 3.8134965808413487e-07, "epoch": 3.722801788375559, "percentage": 74.46, "elapsed_time": "1:06:02", "remaining_time": "0:22:39", "throughput": 5163.98, "total_tokens": 20463616} {"current_steps": 4997, "total_steps": 6710, "loss": 0.2342, "lr": 3.8092891169326405e-07, "epoch": 3.72354694485842, "percentage": 74.47, "elapsed_time": "1:06:03", "remaining_time": "0:22:38", "throughput": 5163.99, "total_tokens": 20467712} {"current_steps": 4998, "total_steps": 6710, "loss": 0.2353, "lr": 3.80508355808981e-07, "epoch": 3.7242921013412817, "percentage": 74.49, "elapsed_time": "1:06:04", "remaining_time": "0:22:37", "throughput": 5164.01, "total_tokens": 20471808} {"current_steps": 4999, "total_steps": 6710, "loss": 0.1455, "lr": 3.8008799052347555e-07, "epoch": 3.725037257824143, "percentage": 74.5, "elapsed_time": "1:06:05", "remaining_time": "0:22:37", "throughput": 5164.02, "total_tokens": 20475904} {"current_steps": 5000, "total_steps": 6710, "loss": 0.2434, "lr": 3.79667815928894e-07, "epoch": 3.7257824143070044, "percentage": 74.52, "elapsed_time": "1:06:05", "remaining_time": "0:22:36", "throughput": 5164.04, "total_tokens": 20480000} {"current_steps": 5001, "total_steps": 6710, "loss": 0.0708, "lr": 3.792478321173422e-07, "epoch": 3.726527570789866, "percentage": 74.53, "elapsed_time": "1:06:06", "remaining_time": "0:22:35", "throughput": 5164.06, "total_tokens": 20484096} {"current_steps": 5002, "total_steps": 6710, "loss": 0.0632, "lr": 3.7882803918088335e-07, "epoch": 3.7272727272727275, "percentage": 74.55, "elapsed_time": "1:06:07", "remaining_time": "0:22:34", "throughput": 5164.07, "total_tokens": 20488192} {"current_steps": 5003, "total_steps": 6710, "loss": 0.1784, "lr": 3.784084372115386e-07, "epoch": 3.7280178837555886, "percentage": 74.56, "elapsed_time": "1:06:08", "remaining_time": "0:22:33", "throughput": 5164.08, "total_tokens": 20492288} {"current_steps": 5004, "total_steps": 6710, "loss": 0.1385, "lr": 3.7798902630128864e-07, "epoch": 3.72876304023845, "percentage": 74.58, "elapsed_time": "1:06:09", "remaining_time": "0:22:33", "throughput": 5164.09, "total_tokens": 20496384} {"current_steps": 5005, "total_steps": 6710, "loss": 0.0981, "lr": 3.775698065420703e-07, "epoch": 3.7295081967213113, "percentage": 74.59, "elapsed_time": "1:06:09", "remaining_time": "0:22:32", "throughput": 5164.1, "total_tokens": 20500480} {"current_steps": 5006, "total_steps": 6710, "loss": 0.2636, "lr": 3.7715077802578106e-07, "epoch": 3.730253353204173, "percentage": 74.61, "elapsed_time": "1:06:10", "remaining_time": "0:22:31", "throughput": 5164.11, "total_tokens": 20504576} {"current_steps": 5007, "total_steps": 6710, "loss": 0.1031, "lr": 3.767319408442731e-07, "epoch": 3.7309985096870344, "percentage": 74.62, "elapsed_time": "1:06:11", "remaining_time": "0:22:30", "throughput": 5164.13, "total_tokens": 20508672} {"current_steps": 5008, "total_steps": 6710, "loss": 0.1713, "lr": 3.763132950893597e-07, "epoch": 3.731743666169896, "percentage": 74.63, "elapsed_time": "1:06:12", "remaining_time": "0:22:29", "throughput": 5164.15, "total_tokens": 20512768} {"current_steps": 5009, "total_steps": 6710, "loss": 0.2067, "lr": 3.758948408528104e-07, "epoch": 3.732488822652757, "percentage": 74.65, "elapsed_time": "1:06:12", "remaining_time": "0:22:29", "throughput": 5164.16, "total_tokens": 20516864} {"current_steps": 5010, "total_steps": 6710, "loss": 0.0719, "lr": 3.7547657822635394e-07, "epoch": 3.7332339791356186, "percentage": 74.66, "elapsed_time": "1:06:13", "remaining_time": "0:22:28", "throughput": 5164.18, "total_tokens": 20520960} {"current_steps": 5011, "total_steps": 6710, "loss": 0.2725, "lr": 3.750585073016763e-07, "epoch": 3.7339791356184797, "percentage": 74.68, "elapsed_time": "1:06:14", "remaining_time": "0:22:27", "throughput": 5164.18, "total_tokens": 20525056} {"current_steps": 5012, "total_steps": 6710, "loss": 0.295, "lr": 3.746406281704211e-07, "epoch": 3.7347242921013413, "percentage": 74.69, "elapsed_time": "1:06:15", "remaining_time": "0:22:26", "throughput": 5164.2, "total_tokens": 20529152} {"current_steps": 5013, "total_steps": 6710, "loss": 0.1085, "lr": 3.7422294092419113e-07, "epoch": 3.735469448584203, "percentage": 74.71, "elapsed_time": "1:06:16", "remaining_time": "0:22:25", "throughput": 5164.21, "total_tokens": 20533248} {"current_steps": 5014, "total_steps": 6710, "loss": 0.1433, "lr": 3.7380544565454575e-07, "epoch": 3.736214605067064, "percentage": 74.72, "elapsed_time": "1:06:16", "remaining_time": "0:22:25", "throughput": 5164.23, "total_tokens": 20537344} {"current_steps": 5015, "total_steps": 6710, "loss": 0.1912, "lr": 3.733881424530038e-07, "epoch": 3.7369597615499255, "percentage": 74.74, "elapsed_time": "1:06:17", "remaining_time": "0:22:24", "throughput": 5164.25, "total_tokens": 20541440} {"current_steps": 5016, "total_steps": 6710, "loss": 0.3898, "lr": 3.7297103141104007e-07, "epoch": 3.737704918032787, "percentage": 74.75, "elapsed_time": "1:06:18", "remaining_time": "0:22:23", "throughput": 5164.26, "total_tokens": 20545536} {"current_steps": 5017, "total_steps": 6710, "loss": 0.1447, "lr": 3.725541126200892e-07, "epoch": 3.738450074515648, "percentage": 74.77, "elapsed_time": "1:06:19", "remaining_time": "0:22:22", "throughput": 5164.28, "total_tokens": 20549632} {"current_steps": 5018, "total_steps": 6710, "loss": 0.1616, "lr": 3.721373861715424e-07, "epoch": 3.7391952309985097, "percentage": 74.78, "elapsed_time": "1:06:19", "remaining_time": "0:22:21", "throughput": 5164.3, "total_tokens": 20553728} {"current_steps": 5019, "total_steps": 6710, "loss": 0.2611, "lr": 3.7172085215674865e-07, "epoch": 3.7399403874813713, "percentage": 74.8, "elapsed_time": "1:06:20", "remaining_time": "0:22:21", "throughput": 5164.32, "total_tokens": 20557824} {"current_steps": 5020, "total_steps": 6710, "loss": 0.1981, "lr": 3.713045106670159e-07, "epoch": 3.7406855439642324, "percentage": 74.81, "elapsed_time": "1:06:21", "remaining_time": "0:22:20", "throughput": 5164.33, "total_tokens": 20561920} {"current_steps": 5021, "total_steps": 6710, "loss": 0.1355, "lr": 3.708883617936089e-07, "epoch": 3.741430700447094, "percentage": 74.83, "elapsed_time": "1:06:22", "remaining_time": "0:22:19", "throughput": 5164.35, "total_tokens": 20566016} {"current_steps": 5022, "total_steps": 6710, "loss": 0.1101, "lr": 3.7047240562775046e-07, "epoch": 3.742175856929955, "percentage": 74.84, "elapsed_time": "1:06:23", "remaining_time": "0:22:18", "throughput": 5164.37, "total_tokens": 20570112} {"current_steps": 5023, "total_steps": 6710, "loss": 0.2309, "lr": 3.7005664226062067e-07, "epoch": 3.7429210134128166, "percentage": 74.86, "elapsed_time": "1:06:23", "remaining_time": "0:22:18", "throughput": 5164.38, "total_tokens": 20574208} {"current_steps": 5024, "total_steps": 6710, "loss": 0.0944, "lr": 3.696410717833587e-07, "epoch": 3.743666169895678, "percentage": 74.87, "elapsed_time": "1:06:24", "remaining_time": "0:22:17", "throughput": 5164.38, "total_tokens": 20578304} {"current_steps": 5025, "total_steps": 6710, "loss": 0.2557, "lr": 3.6922569428705965e-07, "epoch": 3.7444113263785397, "percentage": 74.89, "elapsed_time": "1:06:25", "remaining_time": "0:22:16", "throughput": 5164.39, "total_tokens": 20582400} {"current_steps": 5026, "total_steps": 6710, "loss": 0.1083, "lr": 3.688105098627781e-07, "epoch": 3.745156482861401, "percentage": 74.9, "elapsed_time": "1:06:26", "remaining_time": "0:22:15", "throughput": 5164.41, "total_tokens": 20586496} {"current_steps": 5027, "total_steps": 6710, "loss": 0.1863, "lr": 3.6839551860152477e-07, "epoch": 3.7459016393442623, "percentage": 74.92, "elapsed_time": "1:06:27", "remaining_time": "0:22:14", "throughput": 5164.43, "total_tokens": 20590592} {"current_steps": 5028, "total_steps": 6710, "loss": 0.1929, "lr": 3.6798072059426927e-07, "epoch": 3.7466467958271235, "percentage": 74.93, "elapsed_time": "1:06:27", "remaining_time": "0:22:14", "throughput": 5164.44, "total_tokens": 20594688} {"current_steps": 5029, "total_steps": 6710, "loss": 0.099, "lr": 3.67566115931938e-07, "epoch": 3.747391952309985, "percentage": 74.95, "elapsed_time": "1:06:28", "remaining_time": "0:22:13", "throughput": 5164.46, "total_tokens": 20598784} {"current_steps": 5030, "total_steps": 6710, "loss": 0.1976, "lr": 3.671517047054149e-07, "epoch": 3.7481371087928466, "percentage": 74.96, "elapsed_time": "1:06:29", "remaining_time": "0:22:12", "throughput": 5164.48, "total_tokens": 20602880} {"current_steps": 5031, "total_steps": 6710, "loss": 0.1481, "lr": 3.667374870055425e-07, "epoch": 3.748882265275708, "percentage": 74.98, "elapsed_time": "1:06:30", "remaining_time": "0:22:11", "throughput": 5164.49, "total_tokens": 20606976} {"current_steps": 5032, "total_steps": 6710, "loss": 0.3021, "lr": 3.6632346292311977e-07, "epoch": 3.7496274217585692, "percentage": 74.99, "elapsed_time": "1:06:30", "remaining_time": "0:22:10", "throughput": 5164.51, "total_tokens": 20611072} {"current_steps": 5033, "total_steps": 6710, "loss": 0.1204, "lr": 3.6590963254890463e-07, "epoch": 3.7503725782414308, "percentage": 75.01, "elapsed_time": "1:06:31", "remaining_time": "0:22:10", "throughput": 5164.53, "total_tokens": 20615168} {"current_steps": 5034, "total_steps": 6710, "loss": 0.0996, "lr": 3.654959959736104e-07, "epoch": 3.751117734724292, "percentage": 75.02, "elapsed_time": "1:06:32", "remaining_time": "0:22:09", "throughput": 5164.55, "total_tokens": 20619264} {"current_steps": 5035, "total_steps": 6710, "loss": 0.1348, "lr": 3.6508255328791003e-07, "epoch": 3.7518628912071534, "percentage": 75.04, "elapsed_time": "1:06:33", "remaining_time": "0:22:08", "throughput": 5164.56, "total_tokens": 20623360} {"current_steps": 5036, "total_steps": 6710, "loss": 0.2279, "lr": 3.6466930458243247e-07, "epoch": 3.752608047690015, "percentage": 75.05, "elapsed_time": "1:06:34", "remaining_time": "0:22:07", "throughput": 5164.58, "total_tokens": 20627456} {"current_steps": 5037, "total_steps": 6710, "loss": 0.2311, "lr": 3.642562499477656e-07, "epoch": 3.7533532041728765, "percentage": 75.07, "elapsed_time": "1:06:34", "remaining_time": "0:22:06", "throughput": 5164.6, "total_tokens": 20631552} {"current_steps": 5038, "total_steps": 6710, "loss": 0.2357, "lr": 3.638433894744535e-07, "epoch": 3.7540983606557377, "percentage": 75.08, "elapsed_time": "1:06:35", "remaining_time": "0:22:06", "throughput": 5164.61, "total_tokens": 20635648} {"current_steps": 5039, "total_steps": 6710, "loss": 0.2439, "lr": 3.634307232529978e-07, "epoch": 3.754843517138599, "percentage": 75.1, "elapsed_time": "1:06:36", "remaining_time": "0:22:05", "throughput": 5164.63, "total_tokens": 20639744} {"current_steps": 5040, "total_steps": 6710, "loss": 0.2729, "lr": 3.630182513738585e-07, "epoch": 3.7555886736214603, "percentage": 75.11, "elapsed_time": "1:06:37", "remaining_time": "0:22:04", "throughput": 5164.64, "total_tokens": 20643840} {"current_steps": 5041, "total_steps": 6710, "loss": 0.3049, "lr": 3.6260597392745194e-07, "epoch": 3.756333830104322, "percentage": 75.13, "elapsed_time": "1:06:37", "remaining_time": "0:22:03", "throughput": 5164.66, "total_tokens": 20647936} {"current_steps": 5042, "total_steps": 6710, "loss": 0.0486, "lr": 3.6219389100415265e-07, "epoch": 3.7570789865871834, "percentage": 75.14, "elapsed_time": "1:06:38", "remaining_time": "0:22:02", "throughput": 5164.68, "total_tokens": 20652032} {"current_steps": 5043, "total_steps": 6710, "loss": 0.0348, "lr": 3.617820026942917e-07, "epoch": 3.757824143070045, "percentage": 75.16, "elapsed_time": "1:06:39", "remaining_time": "0:22:02", "throughput": 5164.7, "total_tokens": 20656128} {"current_steps": 5044, "total_steps": 6710, "loss": 0.2922, "lr": 3.6137030908815847e-07, "epoch": 3.758569299552906, "percentage": 75.17, "elapsed_time": "1:06:40", "remaining_time": "0:22:01", "throughput": 5164.71, "total_tokens": 20660224} {"current_steps": 5045, "total_steps": 6710, "loss": 0.1469, "lr": 3.6095881027599896e-07, "epoch": 3.7593144560357676, "percentage": 75.19, "elapsed_time": "1:06:41", "remaining_time": "0:22:00", "throughput": 5164.73, "total_tokens": 20664320} {"current_steps": 5046, "total_steps": 6710, "loss": 0.1296, "lr": 3.605475063480164e-07, "epoch": 3.7600596125186287, "percentage": 75.2, "elapsed_time": "1:06:41", "remaining_time": "0:21:59", "throughput": 5164.74, "total_tokens": 20668416} {"current_steps": 5047, "total_steps": 6710, "loss": 0.0676, "lr": 3.6013639739437155e-07, "epoch": 3.7608047690014903, "percentage": 75.22, "elapsed_time": "1:06:42", "remaining_time": "0:21:58", "throughput": 5164.75, "total_tokens": 20672512} {"current_steps": 5048, "total_steps": 6710, "loss": 0.0977, "lr": 3.5972548350518276e-07, "epoch": 3.761549925484352, "percentage": 75.23, "elapsed_time": "1:06:43", "remaining_time": "0:21:58", "throughput": 5164.77, "total_tokens": 20676608} {"current_steps": 5049, "total_steps": 6710, "loss": 0.1031, "lr": 3.593147647705253e-07, "epoch": 3.762295081967213, "percentage": 75.25, "elapsed_time": "1:06:44", "remaining_time": "0:21:57", "throughput": 5164.79, "total_tokens": 20680704} {"current_steps": 5050, "total_steps": 6710, "loss": 0.1173, "lr": 3.5890424128043095e-07, "epoch": 3.7630402384500745, "percentage": 75.26, "elapsed_time": "1:06:44", "remaining_time": "0:21:56", "throughput": 5164.81, "total_tokens": 20684800} {"current_steps": 5051, "total_steps": 6710, "loss": 0.1394, "lr": 3.5849391312489033e-07, "epoch": 3.763785394932936, "percentage": 75.28, "elapsed_time": "1:06:45", "remaining_time": "0:21:55", "throughput": 5164.83, "total_tokens": 20688896} {"current_steps": 5052, "total_steps": 6710, "loss": 0.0688, "lr": 3.580837803938496e-07, "epoch": 3.764530551415797, "percentage": 75.29, "elapsed_time": "1:06:46", "remaining_time": "0:21:54", "throughput": 5164.84, "total_tokens": 20692992} {"current_steps": 5053, "total_steps": 6710, "loss": 0.256, "lr": 3.5767384317721323e-07, "epoch": 3.7652757078986587, "percentage": 75.31, "elapsed_time": "1:06:47", "remaining_time": "0:21:54", "throughput": 5164.86, "total_tokens": 20697088} {"current_steps": 5054, "total_steps": 6710, "loss": 0.2777, "lr": 3.57264101564842e-07, "epoch": 3.7660208643815203, "percentage": 75.32, "elapsed_time": "1:06:48", "remaining_time": "0:21:53", "throughput": 5164.88, "total_tokens": 20701184} {"current_steps": 5055, "total_steps": 6710, "loss": 0.188, "lr": 3.568545556465547e-07, "epoch": 3.7667660208643814, "percentage": 75.34, "elapsed_time": "1:06:48", "remaining_time": "0:21:52", "throughput": 5164.89, "total_tokens": 20705280} {"current_steps": 5056, "total_steps": 6710, "loss": 0.2191, "lr": 3.5644520551212646e-07, "epoch": 3.767511177347243, "percentage": 75.35, "elapsed_time": "1:06:49", "remaining_time": "0:21:51", "throughput": 5164.91, "total_tokens": 20709376} {"current_steps": 5057, "total_steps": 6710, "loss": 0.2145, "lr": 3.5603605125128934e-07, "epoch": 3.768256333830104, "percentage": 75.37, "elapsed_time": "1:06:50", "remaining_time": "0:21:50", "throughput": 5164.93, "total_tokens": 20713472} {"current_steps": 5058, "total_steps": 6710, "loss": 0.0699, "lr": 3.5562709295373364e-07, "epoch": 3.7690014903129656, "percentage": 75.38, "elapsed_time": "1:06:51", "remaining_time": "0:21:50", "throughput": 5164.94, "total_tokens": 20717568} {"current_steps": 5059, "total_steps": 6710, "loss": 0.2737, "lr": 3.552183307091052e-07, "epoch": 3.769746646795827, "percentage": 75.39, "elapsed_time": "1:06:51", "remaining_time": "0:21:49", "throughput": 5164.96, "total_tokens": 20721664} {"current_steps": 5060, "total_steps": 6710, "loss": 0.1501, "lr": 3.5480976460700867e-07, "epoch": 3.7704918032786887, "percentage": 75.41, "elapsed_time": "1:06:52", "remaining_time": "0:21:48", "throughput": 5164.98, "total_tokens": 20725760} {"current_steps": 5061, "total_steps": 6710, "loss": 0.1436, "lr": 3.544013947370033e-07, "epoch": 3.77123695976155, "percentage": 75.42, "elapsed_time": "1:06:53", "remaining_time": "0:21:47", "throughput": 5164.99, "total_tokens": 20729856} {"current_steps": 5062, "total_steps": 6710, "loss": 0.1336, "lr": 3.539932211886077e-07, "epoch": 3.7719821162444114, "percentage": 75.44, "elapsed_time": "1:06:54", "remaining_time": "0:21:46", "throughput": 5165.01, "total_tokens": 20733952} {"current_steps": 5063, "total_steps": 6710, "loss": 0.1579, "lr": 3.535852440512957e-07, "epoch": 3.7727272727272725, "percentage": 75.45, "elapsed_time": "1:06:55", "remaining_time": "0:21:46", "throughput": 5165.03, "total_tokens": 20738048} {"current_steps": 5064, "total_steps": 6710, "loss": 0.0743, "lr": 3.5317746341449954e-07, "epoch": 3.773472429210134, "percentage": 75.47, "elapsed_time": "1:06:55", "remaining_time": "0:21:45", "throughput": 5165.04, "total_tokens": 20742144} {"current_steps": 5065, "total_steps": 6710, "loss": 0.2007, "lr": 3.5276987936760726e-07, "epoch": 3.7742175856929956, "percentage": 75.48, "elapsed_time": "1:06:56", "remaining_time": "0:21:44", "throughput": 5165.06, "total_tokens": 20746240} {"current_steps": 5066, "total_steps": 6710, "loss": 0.2058, "lr": 3.523624919999638e-07, "epoch": 3.774962742175857, "percentage": 75.5, "elapsed_time": "1:06:57", "remaining_time": "0:21:43", "throughput": 5165.08, "total_tokens": 20750336} {"current_steps": 5067, "total_steps": 6710, "loss": 0.0718, "lr": 3.5195530140087225e-07, "epoch": 3.7757078986587183, "percentage": 75.51, "elapsed_time": "1:06:58", "remaining_time": "0:21:42", "throughput": 5165.1, "total_tokens": 20754432} {"current_steps": 5068, "total_steps": 6710, "loss": 0.1817, "lr": 3.515483076595909e-07, "epoch": 3.77645305514158, "percentage": 75.53, "elapsed_time": "1:06:58", "remaining_time": "0:21:42", "throughput": 5165.11, "total_tokens": 20758528} {"current_steps": 5069, "total_steps": 6710, "loss": 0.0188, "lr": 3.511415108653364e-07, "epoch": 3.777198211624441, "percentage": 75.54, "elapsed_time": "1:06:59", "remaining_time": "0:21:41", "throughput": 5165.12, "total_tokens": 20762624} {"current_steps": 5070, "total_steps": 6710, "loss": 0.1338, "lr": 3.507349111072807e-07, "epoch": 3.7779433681073025, "percentage": 75.56, "elapsed_time": "1:07:00", "remaining_time": "0:21:40", "throughput": 5165.12, "total_tokens": 20766720} {"current_steps": 5071, "total_steps": 6710, "loss": 0.1326, "lr": 3.503285084745542e-07, "epoch": 3.778688524590164, "percentage": 75.57, "elapsed_time": "1:07:01", "remaining_time": "0:21:39", "throughput": 5165.13, "total_tokens": 20770816} {"current_steps": 5072, "total_steps": 6710, "loss": 0.1153, "lr": 3.499223030562429e-07, "epoch": 3.7794336810730256, "percentage": 75.59, "elapsed_time": "1:07:02", "remaining_time": "0:21:38", "throughput": 5165.15, "total_tokens": 20774912} {"current_steps": 5073, "total_steps": 6710, "loss": 0.1737, "lr": 3.4951629494138995e-07, "epoch": 3.7801788375558867, "percentage": 75.6, "elapsed_time": "1:07:02", "remaining_time": "0:21:38", "throughput": 5165.16, "total_tokens": 20779008} {"current_steps": 5074, "total_steps": 6710, "loss": 0.1448, "lr": 3.4911048421899464e-07, "epoch": 3.7809239940387482, "percentage": 75.62, "elapsed_time": "1:07:03", "remaining_time": "0:21:37", "throughput": 5165.18, "total_tokens": 20783104} {"current_steps": 5075, "total_steps": 6710, "loss": 0.2543, "lr": 3.487048709780147e-07, "epoch": 3.7816691505216093, "percentage": 75.63, "elapsed_time": "1:07:04", "remaining_time": "0:21:36", "throughput": 5165.19, "total_tokens": 20787200} {"current_steps": 5076, "total_steps": 6710, "loss": 0.1367, "lr": 3.4829945530736263e-07, "epoch": 3.782414307004471, "percentage": 75.65, "elapsed_time": "1:07:05", "remaining_time": "0:21:35", "throughput": 5165.21, "total_tokens": 20791296} {"current_steps": 5077, "total_steps": 6710, "loss": 0.1821, "lr": 3.4789423729590846e-07, "epoch": 3.7831594634873325, "percentage": 75.66, "elapsed_time": "1:07:06", "remaining_time": "0:21:34", "throughput": 5165.22, "total_tokens": 20795392} {"current_steps": 5078, "total_steps": 6710, "loss": 0.1448, "lr": 3.474892170324795e-07, "epoch": 3.783904619970194, "percentage": 75.68, "elapsed_time": "1:07:06", "remaining_time": "0:21:34", "throughput": 5165.24, "total_tokens": 20799488} {"current_steps": 5079, "total_steps": 6710, "loss": 0.1989, "lr": 3.4708439460585817e-07, "epoch": 3.784649776453055, "percentage": 75.69, "elapsed_time": "1:07:07", "remaining_time": "0:21:33", "throughput": 5165.25, "total_tokens": 20803584} {"current_steps": 5080, "total_steps": 6710, "loss": 0.2117, "lr": 3.466797701047854e-07, "epoch": 3.7853949329359167, "percentage": 75.71, "elapsed_time": "1:07:08", "remaining_time": "0:21:32", "throughput": 5165.27, "total_tokens": 20807680} {"current_steps": 5081, "total_steps": 6710, "loss": 0.1188, "lr": 3.462753436179568e-07, "epoch": 3.7861400894187778, "percentage": 75.72, "elapsed_time": "1:07:09", "remaining_time": "0:21:31", "throughput": 5165.27, "total_tokens": 20811776} {"current_steps": 5082, "total_steps": 6710, "loss": 0.2074, "lr": 3.458711152340266e-07, "epoch": 3.7868852459016393, "percentage": 75.74, "elapsed_time": "1:07:09", "remaining_time": "0:21:30", "throughput": 5165.28, "total_tokens": 20815872} {"current_steps": 5083, "total_steps": 6710, "loss": 0.1013, "lr": 3.454670850416039e-07, "epoch": 3.787630402384501, "percentage": 75.75, "elapsed_time": "1:07:10", "remaining_time": "0:21:30", "throughput": 5165.29, "total_tokens": 20819968} {"current_steps": 5084, "total_steps": 6710, "loss": 0.1206, "lr": 3.4506325312925473e-07, "epoch": 3.788375558867362, "percentage": 75.77, "elapsed_time": "1:07:11", "remaining_time": "0:21:29", "throughput": 5165.29, "total_tokens": 20824064} {"current_steps": 5085, "total_steps": 6710, "loss": 0.1348, "lr": 3.446596195855026e-07, "epoch": 3.7891207153502235, "percentage": 75.78, "elapsed_time": "1:07:12", "remaining_time": "0:21:28", "throughput": 5165.3, "total_tokens": 20828160} {"current_steps": 5086, "total_steps": 6710, "loss": 0.1852, "lr": 3.4425618449882624e-07, "epoch": 3.789865871833085, "percentage": 75.8, "elapsed_time": "1:07:13", "remaining_time": "0:21:27", "throughput": 5165.3, "total_tokens": 20832256} {"current_steps": 5087, "total_steps": 6710, "loss": 0.3128, "lr": 3.438529479576627e-07, "epoch": 3.790611028315946, "percentage": 75.81, "elapsed_time": "1:07:13", "remaining_time": "0:21:27", "throughput": 5165.32, "total_tokens": 20836352} {"current_steps": 5088, "total_steps": 6710, "loss": 0.1466, "lr": 3.4344991005040255e-07, "epoch": 3.7913561847988078, "percentage": 75.83, "elapsed_time": "1:07:14", "remaining_time": "0:21:26", "throughput": 5165.33, "total_tokens": 20840448} {"current_steps": 5089, "total_steps": 6710, "loss": 0.1275, "lr": 3.430470708653959e-07, "epoch": 3.7921013412816693, "percentage": 75.84, "elapsed_time": "1:07:15", "remaining_time": "0:21:25", "throughput": 5165.35, "total_tokens": 20844544} {"current_steps": 5090, "total_steps": 6710, "loss": 0.0718, "lr": 3.426444304909471e-07, "epoch": 3.7928464977645304, "percentage": 75.86, "elapsed_time": "1:07:16", "remaining_time": "0:21:24", "throughput": 5165.36, "total_tokens": 20848640} {"current_steps": 5091, "total_steps": 6710, "loss": 0.2119, "lr": 3.4224198901531863e-07, "epoch": 3.793591654247392, "percentage": 75.87, "elapsed_time": "1:07:17", "remaining_time": "0:21:23", "throughput": 5165.38, "total_tokens": 20852736} {"current_steps": 5092, "total_steps": 6710, "loss": 0.1836, "lr": 3.4183974652672784e-07, "epoch": 3.794336810730253, "percentage": 75.89, "elapsed_time": "1:07:17", "remaining_time": "0:21:23", "throughput": 5165.4, "total_tokens": 20856832} {"current_steps": 5093, "total_steps": 6710, "loss": 0.1216, "lr": 3.414377031133498e-07, "epoch": 3.7950819672131146, "percentage": 75.9, "elapsed_time": "1:07:18", "remaining_time": "0:21:22", "throughput": 5165.41, "total_tokens": 20860928} {"current_steps": 5094, "total_steps": 6710, "loss": 0.2032, "lr": 3.410358588633149e-07, "epoch": 3.795827123695976, "percentage": 75.92, "elapsed_time": "1:07:19", "remaining_time": "0:21:21", "throughput": 5165.43, "total_tokens": 20865024} {"current_steps": 5095, "total_steps": 6710, "loss": 0.2488, "lr": 3.406342138647099e-07, "epoch": 3.7965722801788377, "percentage": 75.93, "elapsed_time": "1:07:20", "remaining_time": "0:21:20", "throughput": 5165.44, "total_tokens": 20869120} {"current_steps": 5096, "total_steps": 6710, "loss": 0.105, "lr": 3.402327682055792e-07, "epoch": 3.797317436661699, "percentage": 75.95, "elapsed_time": "1:07:20", "remaining_time": "0:21:19", "throughput": 5165.46, "total_tokens": 20873216} {"current_steps": 5097, "total_steps": 6710, "loss": 0.2523, "lr": 3.398315219739216e-07, "epoch": 3.7980625931445604, "percentage": 75.96, "elapsed_time": "1:07:21", "remaining_time": "0:21:19", "throughput": 5165.46, "total_tokens": 20877312} {"current_steps": 5098, "total_steps": 6710, "loss": 0.2032, "lr": 3.3943047525769394e-07, "epoch": 3.7988077496274215, "percentage": 75.98, "elapsed_time": "1:07:22", "remaining_time": "0:21:18", "throughput": 5165.48, "total_tokens": 20881408} {"current_steps": 5099, "total_steps": 6710, "loss": 0.2047, "lr": 3.390296281448077e-07, "epoch": 3.799552906110283, "percentage": 75.99, "elapsed_time": "1:07:23", "remaining_time": "0:21:17", "throughput": 5165.5, "total_tokens": 20885504} {"current_steps": 5100, "total_steps": 6710, "loss": 0.4058, "lr": 3.3862898072313274e-07, "epoch": 3.8002980625931446, "percentage": 76.01, "elapsed_time": "1:07:24", "remaining_time": "0:21:16", "throughput": 5165.51, "total_tokens": 20889600} {"current_steps": 5101, "total_steps": 6710, "loss": 0.2269, "lr": 3.382285330804921e-07, "epoch": 3.801043219076006, "percentage": 76.02, "elapsed_time": "1:07:24", "remaining_time": "0:21:15", "throughput": 5165.53, "total_tokens": 20893696} {"current_steps": 5102, "total_steps": 6710, "loss": 0.1574, "lr": 3.3782828530466814e-07, "epoch": 3.8017883755588673, "percentage": 76.04, "elapsed_time": "1:07:25", "remaining_time": "0:21:15", "throughput": 5165.54, "total_tokens": 20897792} {"current_steps": 5103, "total_steps": 6710, "loss": 0.1426, "lr": 3.3742823748339745e-07, "epoch": 3.802533532041729, "percentage": 76.05, "elapsed_time": "1:07:26", "remaining_time": "0:21:14", "throughput": 5165.56, "total_tokens": 20901888} {"current_steps": 5104, "total_steps": 6710, "loss": 0.1752, "lr": 3.3702838970437314e-07, "epoch": 3.80327868852459, "percentage": 76.07, "elapsed_time": "1:07:27", "remaining_time": "0:21:13", "throughput": 5165.58, "total_tokens": 20905984} {"current_steps": 5105, "total_steps": 6710, "loss": 0.1692, "lr": 3.3662874205524524e-07, "epoch": 3.8040238450074515, "percentage": 76.08, "elapsed_time": "1:07:27", "remaining_time": "0:21:12", "throughput": 5165.59, "total_tokens": 20910080} {"current_steps": 5106, "total_steps": 6710, "loss": 0.0482, "lr": 3.36229294623619e-07, "epoch": 3.804769001490313, "percentage": 76.1, "elapsed_time": "1:07:28", "remaining_time": "0:21:11", "throughput": 5165.61, "total_tokens": 20914176} {"current_steps": 5107, "total_steps": 6710, "loss": 0.0863, "lr": 3.358300474970565e-07, "epoch": 3.8055141579731746, "percentage": 76.11, "elapsed_time": "1:07:29", "remaining_time": "0:21:11", "throughput": 5165.62, "total_tokens": 20918272} {"current_steps": 5108, "total_steps": 6710, "loss": 0.1653, "lr": 3.35431000763075e-07, "epoch": 3.8062593144560357, "percentage": 76.13, "elapsed_time": "1:07:30", "remaining_time": "0:21:10", "throughput": 5165.64, "total_tokens": 20922368} {"current_steps": 5109, "total_steps": 6710, "loss": 0.1839, "lr": 3.350321545091491e-07, "epoch": 3.8070044709388973, "percentage": 76.14, "elapsed_time": "1:07:31", "remaining_time": "0:21:09", "throughput": 5165.65, "total_tokens": 20926464} {"current_steps": 5110, "total_steps": 6710, "loss": 0.1474, "lr": 3.346335088227083e-07, "epoch": 3.8077496274217584, "percentage": 76.15, "elapsed_time": "1:07:31", "remaining_time": "0:21:08", "throughput": 5165.67, "total_tokens": 20930560} {"current_steps": 5111, "total_steps": 6710, "loss": 0.0664, "lr": 3.3423506379113845e-07, "epoch": 3.80849478390462, "percentage": 76.17, "elapsed_time": "1:07:32", "remaining_time": "0:21:07", "throughput": 5165.68, "total_tokens": 20934656} {"current_steps": 5112, "total_steps": 6710, "loss": 0.0559, "lr": 3.3383681950178203e-07, "epoch": 3.8092399403874815, "percentage": 76.18, "elapsed_time": "1:07:33", "remaining_time": "0:21:07", "throughput": 5165.7, "total_tokens": 20938752} {"current_steps": 5113, "total_steps": 6710, "loss": 0.1842, "lr": 3.3343877604193634e-07, "epoch": 3.809985096870343, "percentage": 76.2, "elapsed_time": "1:07:34", "remaining_time": "0:21:06", "throughput": 5165.71, "total_tokens": 20942848} {"current_steps": 5114, "total_steps": 6710, "loss": 0.0839, "lr": 3.3304093349885674e-07, "epoch": 3.810730253353204, "percentage": 76.21, "elapsed_time": "1:07:34", "remaining_time": "0:21:05", "throughput": 5165.73, "total_tokens": 20946944} {"current_steps": 5115, "total_steps": 6710, "loss": 0.2827, "lr": 3.3264329195975124e-07, "epoch": 3.8114754098360657, "percentage": 76.23, "elapsed_time": "1:07:35", "remaining_time": "0:21:04", "throughput": 5165.75, "total_tokens": 20951040} {"current_steps": 5116, "total_steps": 6710, "loss": 0.2139, "lr": 3.322458515117871e-07, "epoch": 3.812220566318927, "percentage": 76.24, "elapsed_time": "1:07:36", "remaining_time": "0:21:03", "throughput": 5165.76, "total_tokens": 20955136} {"current_steps": 5117, "total_steps": 6710, "loss": 0.1918, "lr": 3.3184861224208524e-07, "epoch": 3.8129657228017884, "percentage": 76.26, "elapsed_time": "1:07:37", "remaining_time": "0:21:03", "throughput": 5165.78, "total_tokens": 20959232} {"current_steps": 5118, "total_steps": 6710, "loss": 0.1801, "lr": 3.3145157423772415e-07, "epoch": 3.81371087928465, "percentage": 76.27, "elapsed_time": "1:07:38", "remaining_time": "0:21:02", "throughput": 5165.79, "total_tokens": 20963328} {"current_steps": 5119, "total_steps": 6710, "loss": 0.1179, "lr": 3.3105473758573675e-07, "epoch": 3.814456035767511, "percentage": 76.29, "elapsed_time": "1:07:38", "remaining_time": "0:21:01", "throughput": 5165.81, "total_tokens": 20967424} {"current_steps": 5120, "total_steps": 6710, "loss": 0.1277, "lr": 3.30658102373113e-07, "epoch": 3.8152011922503726, "percentage": 76.3, "elapsed_time": "1:07:39", "remaining_time": "0:21:00", "throughput": 5165.82, "total_tokens": 20971520} {"current_steps": 5121, "total_steps": 6710, "loss": 0.2126, "lr": 3.3026166868679793e-07, "epoch": 3.815946348733234, "percentage": 76.32, "elapsed_time": "1:07:40", "remaining_time": "0:20:59", "throughput": 5165.84, "total_tokens": 20975616} {"current_steps": 5122, "total_steps": 6710, "loss": 0.172, "lr": 3.298654366136922e-07, "epoch": 3.8166915052160952, "percentage": 76.33, "elapsed_time": "1:07:41", "remaining_time": "0:20:59", "throughput": 5165.85, "total_tokens": 20979712} {"current_steps": 5123, "total_steps": 6710, "loss": 0.0488, "lr": 3.294694062406535e-07, "epoch": 3.817436661698957, "percentage": 76.35, "elapsed_time": "1:07:42", "remaining_time": "0:20:58", "throughput": 5165.87, "total_tokens": 20983808} {"current_steps": 5124, "total_steps": 6710, "loss": 0.3035, "lr": 3.290735776544937e-07, "epoch": 3.8181818181818183, "percentage": 76.36, "elapsed_time": "1:07:42", "remaining_time": "0:20:57", "throughput": 5165.88, "total_tokens": 20987904} {"current_steps": 5125, "total_steps": 6710, "loss": 0.1833, "lr": 3.2867795094198214e-07, "epoch": 3.8189269746646795, "percentage": 76.38, "elapsed_time": "1:07:43", "remaining_time": "0:20:56", "throughput": 5165.9, "total_tokens": 20992000} {"current_steps": 5126, "total_steps": 6710, "loss": 0.1139, "lr": 3.2828252618984214e-07, "epoch": 3.819672131147541, "percentage": 76.39, "elapsed_time": "1:07:44", "remaining_time": "0:20:55", "throughput": 5165.92, "total_tokens": 20996096} {"current_steps": 5127, "total_steps": 6710, "loss": 0.1161, "lr": 3.278873034847549e-07, "epoch": 3.820417287630402, "percentage": 76.41, "elapsed_time": "1:07:45", "remaining_time": "0:20:55", "throughput": 5165.92, "total_tokens": 21000192} {"current_steps": 5128, "total_steps": 6710, "loss": 0.1992, "lr": 3.2749228291335435e-07, "epoch": 3.8211624441132637, "percentage": 76.42, "elapsed_time": "1:07:45", "remaining_time": "0:20:54", "throughput": 5165.94, "total_tokens": 21004288} {"current_steps": 5129, "total_steps": 6710, "loss": 0.2023, "lr": 3.2709746456223307e-07, "epoch": 3.821907600596125, "percentage": 76.44, "elapsed_time": "1:07:46", "remaining_time": "0:20:53", "throughput": 5165.95, "total_tokens": 21008384} {"current_steps": 5130, "total_steps": 6710, "loss": 0.3235, "lr": 3.267028485179377e-07, "epoch": 3.8226527570789868, "percentage": 76.45, "elapsed_time": "1:07:47", "remaining_time": "0:20:52", "throughput": 5165.97, "total_tokens": 21012480} {"current_steps": 5131, "total_steps": 6710, "loss": 0.088, "lr": 3.263084348669704e-07, "epoch": 3.823397913561848, "percentage": 76.47, "elapsed_time": "1:07:48", "remaining_time": "0:20:51", "throughput": 5165.98, "total_tokens": 21016576} {"current_steps": 5132, "total_steps": 6710, "loss": 0.2573, "lr": 3.2591422369579045e-07, "epoch": 3.8241430700447094, "percentage": 76.48, "elapsed_time": "1:07:49", "remaining_time": "0:20:51", "throughput": 5166.0, "total_tokens": 21020672} {"current_steps": 5133, "total_steps": 6710, "loss": 0.0916, "lr": 3.255202150908107e-07, "epoch": 3.8248882265275705, "percentage": 76.5, "elapsed_time": "1:07:49", "remaining_time": "0:20:50", "throughput": 5166.01, "total_tokens": 21024768} {"current_steps": 5134, "total_steps": 6710, "loss": 0.2449, "lr": 3.251264091384017e-07, "epoch": 3.825633383010432, "percentage": 76.51, "elapsed_time": "1:07:50", "remaining_time": "0:20:49", "throughput": 5166.02, "total_tokens": 21028864} {"current_steps": 5135, "total_steps": 6710, "loss": 0.1346, "lr": 3.247328059248875e-07, "epoch": 3.8263785394932937, "percentage": 76.53, "elapsed_time": "1:07:51", "remaining_time": "0:20:48", "throughput": 5166.04, "total_tokens": 21032960} {"current_steps": 5136, "total_steps": 6710, "loss": 0.1421, "lr": 3.2433940553654965e-07, "epoch": 3.827123695976155, "percentage": 76.54, "elapsed_time": "1:07:52", "remaining_time": "0:20:47", "throughput": 5166.06, "total_tokens": 21037056} {"current_steps": 5137, "total_steps": 6710, "loss": 0.1914, "lr": 3.2394620805962397e-07, "epoch": 3.8278688524590163, "percentage": 76.56, "elapsed_time": "1:07:52", "remaining_time": "0:20:47", "throughput": 5166.08, "total_tokens": 21041152} {"current_steps": 5138, "total_steps": 6710, "loss": 0.2803, "lr": 3.235532135803017e-07, "epoch": 3.828614008941878, "percentage": 76.57, "elapsed_time": "1:07:53", "remaining_time": "0:20:46", "throughput": 5166.09, "total_tokens": 21045248} {"current_steps": 5139, "total_steps": 6710, "loss": 0.1143, "lr": 3.231604221847308e-07, "epoch": 3.829359165424739, "percentage": 76.59, "elapsed_time": "1:07:54", "remaining_time": "0:20:45", "throughput": 5166.11, "total_tokens": 21049344} {"current_steps": 5140, "total_steps": 6710, "loss": 0.1222, "lr": 3.227678339590132e-07, "epoch": 3.8301043219076005, "percentage": 76.6, "elapsed_time": "1:07:55", "remaining_time": "0:20:44", "throughput": 5166.13, "total_tokens": 21053440} {"current_steps": 5141, "total_steps": 6710, "loss": 0.1329, "lr": 3.2237544898920807e-07, "epoch": 3.830849478390462, "percentage": 76.62, "elapsed_time": "1:07:56", "remaining_time": "0:20:43", "throughput": 5166.14, "total_tokens": 21057536} {"current_steps": 5142, "total_steps": 6710, "loss": 0.0994, "lr": 3.2198326736132765e-07, "epoch": 3.8315946348733236, "percentage": 76.63, "elapsed_time": "1:07:56", "remaining_time": "0:20:43", "throughput": 5166.16, "total_tokens": 21061632} {"current_steps": 5143, "total_steps": 6710, "loss": 0.2369, "lr": 3.2159128916134223e-07, "epoch": 3.8323397913561847, "percentage": 76.65, "elapsed_time": "1:07:57", "remaining_time": "0:20:42", "throughput": 5166.17, "total_tokens": 21065728} {"current_steps": 5144, "total_steps": 6710, "loss": 0.0736, "lr": 3.211995144751751e-07, "epoch": 3.8330849478390463, "percentage": 76.66, "elapsed_time": "1:07:58", "remaining_time": "0:20:41", "throughput": 5166.18, "total_tokens": 21069824} {"current_steps": 5145, "total_steps": 6710, "loss": 0.1019, "lr": 3.208079433887071e-07, "epoch": 3.8338301043219074, "percentage": 76.68, "elapsed_time": "1:07:59", "remaining_time": "0:20:40", "throughput": 5166.19, "total_tokens": 21073920} {"current_steps": 5146, "total_steps": 6710, "loss": 0.244, "lr": 3.204165759877724e-07, "epoch": 3.834575260804769, "percentage": 76.69, "elapsed_time": "1:07:59", "remaining_time": "0:20:40", "throughput": 5166.21, "total_tokens": 21078016} {"current_steps": 5147, "total_steps": 6710, "loss": 0.2363, "lr": 3.2002541235816256e-07, "epoch": 3.8353204172876305, "percentage": 76.71, "elapsed_time": "1:08:00", "remaining_time": "0:20:39", "throughput": 5166.22, "total_tokens": 21082112} {"current_steps": 5148, "total_steps": 6710, "loss": 0.0844, "lr": 3.196344525856229e-07, "epoch": 3.836065573770492, "percentage": 76.72, "elapsed_time": "1:08:01", "remaining_time": "0:20:38", "throughput": 5166.23, "total_tokens": 21086208} {"current_steps": 5149, "total_steps": 6710, "loss": 0.1454, "lr": 3.192436967558543e-07, "epoch": 3.836810730253353, "percentage": 76.74, "elapsed_time": "1:08:02", "remaining_time": "0:20:37", "throughput": 5166.25, "total_tokens": 21090304} {"current_steps": 5150, "total_steps": 6710, "loss": 0.1105, "lr": 3.188531449545139e-07, "epoch": 3.8375558867362147, "percentage": 76.75, "elapsed_time": "1:08:03", "remaining_time": "0:20:36", "throughput": 5166.26, "total_tokens": 21094400} {"current_steps": 5151, "total_steps": 6710, "loss": 0.0635, "lr": 3.1846279726721273e-07, "epoch": 3.838301043219076, "percentage": 76.77, "elapsed_time": "1:08:03", "remaining_time": "0:20:36", "throughput": 5166.28, "total_tokens": 21098496} {"current_steps": 5152, "total_steps": 6710, "loss": 0.1298, "lr": 3.180726537795187e-07, "epoch": 3.8390461997019374, "percentage": 76.78, "elapsed_time": "1:08:04", "remaining_time": "0:20:35", "throughput": 5166.29, "total_tokens": 21102592} {"current_steps": 5153, "total_steps": 6710, "loss": 0.1064, "lr": 3.1768271457695286e-07, "epoch": 3.839791356184799, "percentage": 76.8, "elapsed_time": "1:08:05", "remaining_time": "0:20:34", "throughput": 5166.31, "total_tokens": 21106688} {"current_steps": 5154, "total_steps": 6710, "loss": 0.131, "lr": 3.1729297974499434e-07, "epoch": 3.84053651266766, "percentage": 76.81, "elapsed_time": "1:08:06", "remaining_time": "0:20:33", "throughput": 5166.33, "total_tokens": 21110784} {"current_steps": 5155, "total_steps": 6710, "loss": 0.0412, "lr": 3.169034493690738e-07, "epoch": 3.8412816691505216, "percentage": 76.83, "elapsed_time": "1:08:07", "remaining_time": "0:20:32", "throughput": 5166.34, "total_tokens": 21114880} {"current_steps": 5156, "total_steps": 6710, "loss": 0.1742, "lr": 3.165141235345806e-07, "epoch": 3.842026825633383, "percentage": 76.84, "elapsed_time": "1:08:07", "remaining_time": "0:20:32", "throughput": 5166.36, "total_tokens": 21118976} {"current_steps": 5157, "total_steps": 6710, "loss": 0.2302, "lr": 3.1612500232685724e-07, "epoch": 3.8427719821162443, "percentage": 76.86, "elapsed_time": "1:08:08", "remaining_time": "0:20:31", "throughput": 5166.37, "total_tokens": 21123072} {"current_steps": 5158, "total_steps": 6710, "loss": 0.049, "lr": 3.1573608583120125e-07, "epoch": 3.843517138599106, "percentage": 76.87, "elapsed_time": "1:08:09", "remaining_time": "0:20:30", "throughput": 5166.39, "total_tokens": 21127168} {"current_steps": 5159, "total_steps": 6710, "loss": 0.0398, "lr": 3.1534737413286705e-07, "epoch": 3.8442622950819674, "percentage": 76.89, "elapsed_time": "1:08:10", "remaining_time": "0:20:29", "throughput": 5166.41, "total_tokens": 21131264} {"current_steps": 5160, "total_steps": 6710, "loss": 0.0601, "lr": 3.14958867317062e-07, "epoch": 3.8450074515648285, "percentage": 76.9, "elapsed_time": "1:08:10", "remaining_time": "0:20:28", "throughput": 5166.42, "total_tokens": 21135360} {"current_steps": 5161, "total_steps": 6710, "loss": 0.0811, "lr": 3.1457056546895045e-07, "epoch": 3.84575260804769, "percentage": 76.92, "elapsed_time": "1:08:11", "remaining_time": "0:20:28", "throughput": 5166.43, "total_tokens": 21139456} {"current_steps": 5162, "total_steps": 6710, "loss": 0.2419, "lr": 3.1418246867365015e-07, "epoch": 3.846497764530551, "percentage": 76.93, "elapsed_time": "1:08:12", "remaining_time": "0:20:27", "throughput": 5166.44, "total_tokens": 21143552} {"current_steps": 5163, "total_steps": 6710, "loss": 0.2113, "lr": 3.137945770162354e-07, "epoch": 3.8472429210134127, "percentage": 76.94, "elapsed_time": "1:08:13", "remaining_time": "0:20:26", "throughput": 5166.46, "total_tokens": 21147648} {"current_steps": 5164, "total_steps": 6710, "loss": 0.1305, "lr": 3.13406890581734e-07, "epoch": 3.8479880774962743, "percentage": 76.96, "elapsed_time": "1:08:14", "remaining_time": "0:20:25", "throughput": 5166.47, "total_tokens": 21151744} {"current_steps": 5165, "total_steps": 6710, "loss": 0.2488, "lr": 3.130194094551306e-07, "epoch": 3.848733233979136, "percentage": 76.97, "elapsed_time": "1:08:14", "remaining_time": "0:20:24", "throughput": 5166.49, "total_tokens": 21155840} {"current_steps": 5166, "total_steps": 6710, "loss": 0.2367, "lr": 3.1263213372136324e-07, "epoch": 3.849478390461997, "percentage": 76.99, "elapsed_time": "1:08:15", "remaining_time": "0:20:24", "throughput": 5166.5, "total_tokens": 21159936} {"current_steps": 5167, "total_steps": 6710, "loss": 0.1149, "lr": 3.122450634653251e-07, "epoch": 3.8502235469448585, "percentage": 77.0, "elapsed_time": "1:08:16", "remaining_time": "0:20:23", "throughput": 5166.52, "total_tokens": 21164032} {"current_steps": 5168, "total_steps": 6710, "loss": 0.1834, "lr": 3.1185819877186594e-07, "epoch": 3.8509687034277196, "percentage": 77.02, "elapsed_time": "1:08:17", "remaining_time": "0:20:22", "throughput": 5166.52, "total_tokens": 21168128} {"current_steps": 5169, "total_steps": 6710, "loss": 0.079, "lr": 3.1147153972578796e-07, "epoch": 3.851713859910581, "percentage": 77.03, "elapsed_time": "1:08:17", "remaining_time": "0:20:21", "throughput": 5166.54, "total_tokens": 21172224} {"current_steps": 5170, "total_steps": 6710, "loss": 0.1235, "lr": 3.110850864118504e-07, "epoch": 3.8524590163934427, "percentage": 77.05, "elapsed_time": "1:08:18", "remaining_time": "0:20:20", "throughput": 5166.55, "total_tokens": 21176320} {"current_steps": 5171, "total_steps": 6710, "loss": 0.1735, "lr": 3.106988389147661e-07, "epoch": 3.8532041728763042, "percentage": 77.06, "elapsed_time": "1:08:19", "remaining_time": "0:20:20", "throughput": 5166.57, "total_tokens": 21180416} {"current_steps": 5172, "total_steps": 6710, "loss": 0.2869, "lr": 3.1031279731920385e-07, "epoch": 3.8539493293591653, "percentage": 77.08, "elapsed_time": "1:08:20", "remaining_time": "0:20:19", "throughput": 5166.58, "total_tokens": 21184512} {"current_steps": 5173, "total_steps": 6710, "loss": 0.1477, "lr": 3.0992696170978593e-07, "epoch": 3.854694485842027, "percentage": 77.09, "elapsed_time": "1:08:21", "remaining_time": "0:20:18", "throughput": 5166.6, "total_tokens": 21188608} {"current_steps": 5174, "total_steps": 6710, "loss": 0.1501, "lr": 3.095413321710912e-07, "epoch": 3.855439642324888, "percentage": 77.11, "elapsed_time": "1:08:21", "remaining_time": "0:20:17", "throughput": 5166.61, "total_tokens": 21192704} {"current_steps": 5175, "total_steps": 6710, "loss": 0.2362, "lr": 3.091559087876518e-07, "epoch": 3.8561847988077496, "percentage": 77.12, "elapsed_time": "1:08:22", "remaining_time": "0:20:16", "throughput": 5166.63, "total_tokens": 21196800} {"current_steps": 5176, "total_steps": 6710, "loss": 0.0446, "lr": 3.087706916439552e-07, "epoch": 3.856929955290611, "percentage": 77.14, "elapsed_time": "1:08:23", "remaining_time": "0:20:16", "throughput": 5166.65, "total_tokens": 21200896} {"current_steps": 5177, "total_steps": 6710, "loss": 0.1218, "lr": 3.0838568082444424e-07, "epoch": 3.8576751117734727, "percentage": 77.15, "elapsed_time": "1:08:24", "remaining_time": "0:20:15", "throughput": 5166.66, "total_tokens": 21204992} {"current_steps": 5178, "total_steps": 6710, "loss": 0.0322, "lr": 3.0800087641351546e-07, "epoch": 3.8584202682563338, "percentage": 77.17, "elapsed_time": "1:08:24", "remaining_time": "0:20:14", "throughput": 5166.67, "total_tokens": 21209088} {"current_steps": 5179, "total_steps": 6710, "loss": 0.2138, "lr": 3.076162784955214e-07, "epoch": 3.8591654247391953, "percentage": 77.18, "elapsed_time": "1:08:25", "remaining_time": "0:20:13", "throughput": 5166.69, "total_tokens": 21213184} {"current_steps": 5180, "total_steps": 6710, "loss": 0.2116, "lr": 3.0723188715476806e-07, "epoch": 3.8599105812220564, "percentage": 77.2, "elapsed_time": "1:08:26", "remaining_time": "0:20:12", "throughput": 5166.7, "total_tokens": 21217280} {"current_steps": 5181, "total_steps": 6710, "loss": 0.1996, "lr": 3.0684770247551757e-07, "epoch": 3.860655737704918, "percentage": 77.21, "elapsed_time": "1:08:27", "remaining_time": "0:20:12", "throughput": 5166.72, "total_tokens": 21221376} {"current_steps": 5182, "total_steps": 6710, "loss": 0.0574, "lr": 3.064637245419848e-07, "epoch": 3.8614008941877795, "percentage": 77.23, "elapsed_time": "1:08:28", "remaining_time": "0:20:11", "throughput": 5166.74, "total_tokens": 21225472} {"current_steps": 5183, "total_steps": 6710, "loss": 0.1104, "lr": 3.060799534383413e-07, "epoch": 3.862146050670641, "percentage": 77.24, "elapsed_time": "1:08:28", "remaining_time": "0:20:10", "throughput": 5166.74, "total_tokens": 21229568} {"current_steps": 5184, "total_steps": 6710, "loss": 0.1929, "lr": 3.056963892487119e-07, "epoch": 3.862891207153502, "percentage": 77.26, "elapsed_time": "1:08:29", "remaining_time": "0:20:09", "throughput": 5166.76, "total_tokens": 21233664} {"current_steps": 5185, "total_steps": 6710, "loss": 0.0605, "lr": 3.0531303205717733e-07, "epoch": 3.8636363636363638, "percentage": 77.27, "elapsed_time": "1:08:30", "remaining_time": "0:20:08", "throughput": 5166.77, "total_tokens": 21237760} {"current_steps": 5186, "total_steps": 6710, "loss": 0.256, "lr": 3.049298819477717e-07, "epoch": 3.864381520119225, "percentage": 77.29, "elapsed_time": "1:08:31", "remaining_time": "0:20:08", "throughput": 5166.79, "total_tokens": 21241856} {"current_steps": 5187, "total_steps": 6710, "loss": 0.106, "lr": 3.0454693900448406e-07, "epoch": 3.8651266766020864, "percentage": 77.3, "elapsed_time": "1:08:32", "remaining_time": "0:20:07", "throughput": 5166.8, "total_tokens": 21245952} {"current_steps": 5188, "total_steps": 6710, "loss": 0.4012, "lr": 3.0416420331125877e-07, "epoch": 3.865871833084948, "percentage": 77.32, "elapsed_time": "1:08:32", "remaining_time": "0:20:06", "throughput": 5166.82, "total_tokens": 21250048} {"current_steps": 5189, "total_steps": 6710, "loss": 0.0621, "lr": 3.037816749519938e-07, "epoch": 3.866616989567809, "percentage": 77.33, "elapsed_time": "1:08:33", "remaining_time": "0:20:05", "throughput": 5166.83, "total_tokens": 21254144} {"current_steps": 5190, "total_steps": 6710, "loss": 0.1477, "lr": 3.033993540105426e-07, "epoch": 3.8673621460506706, "percentage": 77.35, "elapsed_time": "1:08:34", "remaining_time": "0:20:04", "throughput": 5166.85, "total_tokens": 21258240} {"current_steps": 5191, "total_steps": 6710, "loss": 0.1619, "lr": 3.0301724057071186e-07, "epoch": 3.868107302533532, "percentage": 77.36, "elapsed_time": "1:08:35", "remaining_time": "0:20:04", "throughput": 5166.86, "total_tokens": 21262336} {"current_steps": 5192, "total_steps": 6710, "loss": 0.1156, "lr": 3.0263533471626443e-07, "epoch": 3.8688524590163933, "percentage": 77.38, "elapsed_time": "1:08:35", "remaining_time": "0:20:03", "throughput": 5166.88, "total_tokens": 21266432} {"current_steps": 5193, "total_steps": 6710, "loss": 0.1014, "lr": 3.022536365309166e-07, "epoch": 3.869597615499255, "percentage": 77.39, "elapsed_time": "1:08:36", "remaining_time": "0:20:02", "throughput": 5166.89, "total_tokens": 21270528} {"current_steps": 5194, "total_steps": 6710, "loss": 0.1191, "lr": 3.0187214609833856e-07, "epoch": 3.8703427719821164, "percentage": 77.41, "elapsed_time": "1:08:37", "remaining_time": "0:20:01", "throughput": 5166.91, "total_tokens": 21274624} {"current_steps": 5195, "total_steps": 6710, "loss": 0.2084, "lr": 3.014908635021573e-07, "epoch": 3.8710879284649775, "percentage": 77.42, "elapsed_time": "1:08:38", "remaining_time": "0:20:00", "throughput": 5166.93, "total_tokens": 21278720} {"current_steps": 5196, "total_steps": 6710, "loss": 0.1299, "lr": 3.0110978882595077e-07, "epoch": 3.871833084947839, "percentage": 77.44, "elapsed_time": "1:08:39", "remaining_time": "0:20:00", "throughput": 5166.94, "total_tokens": 21282816} {"current_steps": 5197, "total_steps": 6710, "loss": 0.1651, "lr": 3.007289221532547e-07, "epoch": 3.8725782414307, "percentage": 77.45, "elapsed_time": "1:08:39", "remaining_time": "0:19:59", "throughput": 5166.95, "total_tokens": 21286912} {"current_steps": 5198, "total_steps": 6710, "loss": 0.2609, "lr": 3.003482635675568e-07, "epoch": 3.8733233979135617, "percentage": 77.47, "elapsed_time": "1:08:40", "remaining_time": "0:19:58", "throughput": 5166.97, "total_tokens": 21291008} {"current_steps": 5199, "total_steps": 6710, "loss": 0.1516, "lr": 2.9996781315230125e-07, "epoch": 3.8740685543964233, "percentage": 77.48, "elapsed_time": "1:08:41", "remaining_time": "0:19:57", "throughput": 5166.98, "total_tokens": 21295104} {"current_steps": 5200, "total_steps": 6710, "loss": 0.16, "lr": 2.995875709908842e-07, "epoch": 3.874813710879285, "percentage": 77.5, "elapsed_time": "1:08:42", "remaining_time": "0:19:57", "throughput": 5167.0, "total_tokens": 21299200} {"current_steps": 5201, "total_steps": 6710, "loss": 0.3773, "lr": 2.9920753716665876e-07, "epoch": 3.875558867362146, "percentage": 77.51, "elapsed_time": "1:08:42", "remaining_time": "0:19:56", "throughput": 5167.01, "total_tokens": 21303296} {"current_steps": 5202, "total_steps": 6710, "loss": 0.1197, "lr": 2.988277117629304e-07, "epoch": 3.8763040238450075, "percentage": 77.53, "elapsed_time": "1:08:43", "remaining_time": "0:19:55", "throughput": 5167.03, "total_tokens": 21307392} {"current_steps": 5203, "total_steps": 6710, "loss": 0.2286, "lr": 2.9844809486295923e-07, "epoch": 3.8770491803278686, "percentage": 77.54, "elapsed_time": "1:08:44", "remaining_time": "0:19:54", "throughput": 5167.04, "total_tokens": 21311488} {"current_steps": 5204, "total_steps": 6710, "loss": 0.0916, "lr": 2.980686865499606e-07, "epoch": 3.87779433681073, "percentage": 77.56, "elapsed_time": "1:08:45", "remaining_time": "0:19:53", "throughput": 5167.06, "total_tokens": 21315584} {"current_steps": 5205, "total_steps": 6710, "loss": 0.1397, "lr": 2.97689486907103e-07, "epoch": 3.8785394932935917, "percentage": 77.57, "elapsed_time": "1:08:46", "remaining_time": "0:19:53", "throughput": 5167.07, "total_tokens": 21319680} {"current_steps": 5206, "total_steps": 6710, "loss": 0.1619, "lr": 2.9731049601751035e-07, "epoch": 3.8792846497764533, "percentage": 77.59, "elapsed_time": "1:08:46", "remaining_time": "0:19:52", "throughput": 5167.09, "total_tokens": 21323776} {"current_steps": 5207, "total_steps": 6710, "loss": 0.1085, "lr": 2.969317139642594e-07, "epoch": 3.8800298062593144, "percentage": 77.6, "elapsed_time": "1:08:47", "remaining_time": "0:19:51", "throughput": 5167.11, "total_tokens": 21327872} {"current_steps": 5208, "total_steps": 6710, "loss": 0.1919, "lr": 2.9655314083038303e-07, "epoch": 3.880774962742176, "percentage": 77.62, "elapsed_time": "1:08:48", "remaining_time": "0:19:50", "throughput": 5167.12, "total_tokens": 21331968} {"current_steps": 5209, "total_steps": 6710, "loss": 0.2353, "lr": 2.961747766988657e-07, "epoch": 3.881520119225037, "percentage": 77.63, "elapsed_time": "1:08:49", "remaining_time": "0:19:49", "throughput": 5167.13, "total_tokens": 21336064} {"current_steps": 5210, "total_steps": 6710, "loss": 0.1693, "lr": 2.9579662165264853e-07, "epoch": 3.8822652757078986, "percentage": 77.65, "elapsed_time": "1:08:49", "remaining_time": "0:19:49", "throughput": 5167.15, "total_tokens": 21340160} {"current_steps": 5211, "total_steps": 6710, "loss": 0.2483, "lr": 2.954186757746251e-07, "epoch": 3.88301043219076, "percentage": 77.66, "elapsed_time": "1:08:50", "remaining_time": "0:19:48", "throughput": 5167.16, "total_tokens": 21344256} {"current_steps": 5212, "total_steps": 6710, "loss": 0.1957, "lr": 2.950409391476447e-07, "epoch": 3.8837555886736217, "percentage": 77.68, "elapsed_time": "1:08:51", "remaining_time": "0:19:47", "throughput": 5167.18, "total_tokens": 21348352} {"current_steps": 5213, "total_steps": 6710, "loss": 0.2017, "lr": 2.9466341185450955e-07, "epoch": 3.884500745156483, "percentage": 77.69, "elapsed_time": "1:08:52", "remaining_time": "0:19:46", "throughput": 5167.2, "total_tokens": 21352448} {"current_steps": 5214, "total_steps": 6710, "loss": 0.1872, "lr": 2.942860939779757e-07, "epoch": 3.8852459016393444, "percentage": 77.7, "elapsed_time": "1:08:53", "remaining_time": "0:19:45", "throughput": 5167.21, "total_tokens": 21356544} {"current_steps": 5215, "total_steps": 6710, "loss": 0.1437, "lr": 2.939089856007549e-07, "epoch": 3.8859910581222055, "percentage": 77.72, "elapsed_time": "1:08:53", "remaining_time": "0:19:45", "throughput": 5167.23, "total_tokens": 21360640} {"current_steps": 5216, "total_steps": 6710, "loss": 0.2721, "lr": 2.9353208680551124e-07, "epoch": 3.886736214605067, "percentage": 77.73, "elapsed_time": "1:08:54", "remaining_time": "0:19:44", "throughput": 5167.24, "total_tokens": 21364736} {"current_steps": 5217, "total_steps": 6710, "loss": 0.1671, "lr": 2.931553976748643e-07, "epoch": 3.8874813710879286, "percentage": 77.75, "elapsed_time": "1:08:55", "remaining_time": "0:19:43", "throughput": 5167.26, "total_tokens": 21368832} {"current_steps": 5218, "total_steps": 6710, "loss": 0.1406, "lr": 2.927789182913862e-07, "epoch": 3.88822652757079, "percentage": 77.76, "elapsed_time": "1:08:56", "remaining_time": "0:19:42", "throughput": 5167.27, "total_tokens": 21372928} {"current_steps": 5219, "total_steps": 6710, "loss": 0.1163, "lr": 2.9240264873760473e-07, "epoch": 3.8889716840536512, "percentage": 77.78, "elapsed_time": "1:08:56", "remaining_time": "0:19:41", "throughput": 5167.28, "total_tokens": 21377024} {"current_steps": 5220, "total_steps": 6710, "loss": 0.2495, "lr": 2.9202658909600056e-07, "epoch": 3.889716840536513, "percentage": 77.79, "elapsed_time": "1:08:57", "remaining_time": "0:19:41", "throughput": 5167.3, "total_tokens": 21381120} {"current_steps": 5221, "total_steps": 6710, "loss": 0.2193, "lr": 2.916507394490084e-07, "epoch": 3.890461997019374, "percentage": 77.81, "elapsed_time": "1:08:58", "remaining_time": "0:19:40", "throughput": 5167.32, "total_tokens": 21385216} {"current_steps": 5222, "total_steps": 6710, "loss": 0.2178, "lr": 2.9127509987901787e-07, "epoch": 3.8912071535022354, "percentage": 77.82, "elapsed_time": "1:08:59", "remaining_time": "0:19:39", "throughput": 5167.32, "total_tokens": 21389312} {"current_steps": 5223, "total_steps": 6710, "loss": 0.2654, "lr": 2.9089967046837074e-07, "epoch": 3.891952309985097, "percentage": 77.84, "elapsed_time": "1:09:00", "remaining_time": "0:19:38", "throughput": 5167.34, "total_tokens": 21393408} {"current_steps": 5224, "total_steps": 6710, "loss": 0.0661, "lr": 2.9052445129936477e-07, "epoch": 3.892697466467958, "percentage": 77.85, "elapsed_time": "1:09:00", "remaining_time": "0:19:37", "throughput": 5167.35, "total_tokens": 21397504} {"current_steps": 5225, "total_steps": 6710, "loss": 0.1448, "lr": 2.9014944245425003e-07, "epoch": 3.8934426229508197, "percentage": 77.87, "elapsed_time": "1:09:01", "remaining_time": "0:19:37", "throughput": 5167.37, "total_tokens": 21401600} {"current_steps": 5226, "total_steps": 6710, "loss": 0.1463, "lr": 2.897746440152317e-07, "epoch": 3.894187779433681, "percentage": 77.88, "elapsed_time": "1:09:02", "remaining_time": "0:19:36", "throughput": 5167.38, "total_tokens": 21405696} {"current_steps": 5227, "total_steps": 6710, "loss": 0.05, "lr": 2.8940005606446776e-07, "epoch": 3.8949329359165423, "percentage": 77.9, "elapsed_time": "1:09:03", "remaining_time": "0:19:35", "throughput": 5167.4, "total_tokens": 21409792} {"current_steps": 5228, "total_steps": 6710, "loss": 0.1909, "lr": 2.8902567868407115e-07, "epoch": 3.895678092399404, "percentage": 77.91, "elapsed_time": "1:09:04", "remaining_time": "0:19:34", "throughput": 5167.41, "total_tokens": 21413888} {"current_steps": 5229, "total_steps": 6710, "loss": 0.1893, "lr": 2.886515119561079e-07, "epoch": 3.8964232488822654, "percentage": 77.93, "elapsed_time": "1:09:04", "remaining_time": "0:19:33", "throughput": 5167.43, "total_tokens": 21417984} {"current_steps": 5230, "total_steps": 6710, "loss": 0.1491, "lr": 2.882775559625972e-07, "epoch": 3.8971684053651265, "percentage": 77.94, "elapsed_time": "1:09:05", "remaining_time": "0:19:33", "throughput": 5167.44, "total_tokens": 21422080} {"current_steps": 5231, "total_steps": 6710, "loss": 0.0373, "lr": 2.879038107855141e-07, "epoch": 3.897913561847988, "percentage": 77.96, "elapsed_time": "1:09:06", "remaining_time": "0:19:32", "throughput": 5167.46, "total_tokens": 21426176} {"current_steps": 5232, "total_steps": 6710, "loss": 0.1792, "lr": 2.875302765067853e-07, "epoch": 3.898658718330849, "percentage": 77.97, "elapsed_time": "1:09:07", "remaining_time": "0:19:31", "throughput": 5167.47, "total_tokens": 21430272} {"current_steps": 5233, "total_steps": 6710, "loss": 0.2626, "lr": 2.871569532082928e-07, "epoch": 3.8994038748137108, "percentage": 77.99, "elapsed_time": "1:09:07", "remaining_time": "0:19:30", "throughput": 5167.49, "total_tokens": 21434368} {"current_steps": 5234, "total_steps": 6710, "loss": 0.0881, "lr": 2.8678384097187124e-07, "epoch": 3.9001490312965723, "percentage": 78.0, "elapsed_time": "1:09:08", "remaining_time": "0:19:29", "throughput": 5167.51, "total_tokens": 21438464} {"current_steps": 5235, "total_steps": 6710, "loss": 0.2729, "lr": 2.8641093987931036e-07, "epoch": 3.900894187779434, "percentage": 78.02, "elapsed_time": "1:09:09", "remaining_time": "0:19:29", "throughput": 5167.52, "total_tokens": 21442560} {"current_steps": 5236, "total_steps": 6710, "loss": 0.1363, "lr": 2.8603825001235137e-07, "epoch": 3.901639344262295, "percentage": 78.03, "elapsed_time": "1:09:10", "remaining_time": "0:19:28", "throughput": 5167.53, "total_tokens": 21446656} {"current_steps": 5237, "total_steps": 6710, "loss": 0.1304, "lr": 2.856657714526917e-07, "epoch": 3.9023845007451565, "percentage": 78.05, "elapsed_time": "1:09:11", "remaining_time": "0:19:27", "throughput": 5167.55, "total_tokens": 21450752} {"current_steps": 5238, "total_steps": 6710, "loss": 0.2242, "lr": 2.8529350428198043e-07, "epoch": 3.9031296572280176, "percentage": 78.06, "elapsed_time": "1:09:11", "remaining_time": "0:19:26", "throughput": 5167.56, "total_tokens": 21454848} {"current_steps": 5239, "total_steps": 6710, "loss": 0.1766, "lr": 2.8492144858182206e-07, "epoch": 3.903874813710879, "percentage": 78.08, "elapsed_time": "1:09:12", "remaining_time": "0:19:25", "throughput": 5167.58, "total_tokens": 21458944} {"current_steps": 5240, "total_steps": 6710, "loss": 0.1496, "lr": 2.8454960443377355e-07, "epoch": 3.9046199701937407, "percentage": 78.09, "elapsed_time": "1:09:13", "remaining_time": "0:19:25", "throughput": 5167.59, "total_tokens": 21463040} {"current_steps": 5241, "total_steps": 6710, "loss": 0.1858, "lr": 2.841779719193452e-07, "epoch": 3.9053651266766023, "percentage": 78.11, "elapsed_time": "1:09:14", "remaining_time": "0:19:24", "throughput": 5167.6, "total_tokens": 21467136} {"current_steps": 5242, "total_steps": 6710, "loss": 0.2303, "lr": 2.8380655112000237e-07, "epoch": 3.9061102831594634, "percentage": 78.12, "elapsed_time": "1:09:14", "remaining_time": "0:19:23", "throughput": 5167.61, "total_tokens": 21471232} {"current_steps": 5243, "total_steps": 6710, "loss": 0.3115, "lr": 2.8343534211716233e-07, "epoch": 3.906855439642325, "percentage": 78.14, "elapsed_time": "1:09:15", "remaining_time": "0:19:22", "throughput": 5167.63, "total_tokens": 21475328} {"current_steps": 5244, "total_steps": 6710, "loss": 0.16, "lr": 2.830643449921976e-07, "epoch": 3.907600596125186, "percentage": 78.15, "elapsed_time": "1:09:16", "remaining_time": "0:19:21", "throughput": 5167.64, "total_tokens": 21479424} {"current_steps": 5245, "total_steps": 6710, "loss": 0.1659, "lr": 2.8269355982643273e-07, "epoch": 3.9083457526080476, "percentage": 78.17, "elapsed_time": "1:09:17", "remaining_time": "0:19:21", "throughput": 5167.66, "total_tokens": 21483520} {"current_steps": 5246, "total_steps": 6710, "loss": 0.1977, "lr": 2.823229867011469e-07, "epoch": 3.909090909090909, "percentage": 78.18, "elapsed_time": "1:09:18", "remaining_time": "0:19:20", "throughput": 5167.68, "total_tokens": 21487616} {"current_steps": 5247, "total_steps": 6710, "loss": 0.3062, "lr": 2.8195262569757245e-07, "epoch": 3.9098360655737707, "percentage": 78.2, "elapsed_time": "1:09:18", "remaining_time": "0:19:19", "throughput": 5167.69, "total_tokens": 21491712} {"current_steps": 5248, "total_steps": 6710, "loss": 0.2225, "lr": 2.8158247689689433e-07, "epoch": 3.910581222056632, "percentage": 78.21, "elapsed_time": "1:09:19", "remaining_time": "0:19:18", "throughput": 5167.71, "total_tokens": 21495808} {"current_steps": 5249, "total_steps": 6710, "loss": 0.1545, "lr": 2.812125403802529e-07, "epoch": 3.9113263785394934, "percentage": 78.23, "elapsed_time": "1:09:20", "remaining_time": "0:19:18", "throughput": 5167.72, "total_tokens": 21499904} {"current_steps": 5250, "total_steps": 6710, "loss": 0.1545, "lr": 2.8084281622874036e-07, "epoch": 3.9120715350223545, "percentage": 78.24, "elapsed_time": "1:09:21", "remaining_time": "0:19:17", "throughput": 5167.74, "total_tokens": 21504000} {"current_steps": 5251, "total_steps": 6710, "loss": 0.1163, "lr": 2.804733045234029e-07, "epoch": 3.912816691505216, "percentage": 78.26, "elapsed_time": "1:09:21", "remaining_time": "0:19:16", "throughput": 5167.74, "total_tokens": 21508096} {"current_steps": 5252, "total_steps": 6710, "loss": 0.1452, "lr": 2.801040053452396e-07, "epoch": 3.9135618479880776, "percentage": 78.27, "elapsed_time": "1:09:22", "remaining_time": "0:19:15", "throughput": 5167.76, "total_tokens": 21512192} {"current_steps": 5253, "total_steps": 6710, "loss": 0.07, "lr": 2.7973491877520453e-07, "epoch": 3.914307004470939, "percentage": 78.29, "elapsed_time": "1:09:23", "remaining_time": "0:19:14", "throughput": 5167.78, "total_tokens": 21516288} {"current_steps": 5254, "total_steps": 6710, "loss": 0.1597, "lr": 2.793660448942033e-07, "epoch": 3.9150521609538003, "percentage": 78.3, "elapsed_time": "1:09:24", "remaining_time": "0:19:14", "throughput": 5167.79, "total_tokens": 21520384} {"current_steps": 5255, "total_steps": 6710, "loss": 0.2127, "lr": 2.789973837830962e-07, "epoch": 3.915797317436662, "percentage": 78.32, "elapsed_time": "1:09:25", "remaining_time": "0:19:13", "throughput": 5167.81, "total_tokens": 21524480} {"current_steps": 5256, "total_steps": 6710, "loss": 0.0644, "lr": 2.786289355226958e-07, "epoch": 3.916542473919523, "percentage": 78.33, "elapsed_time": "1:09:25", "remaining_time": "0:19:12", "throughput": 5167.82, "total_tokens": 21528576} {"current_steps": 5257, "total_steps": 6710, "loss": 0.3301, "lr": 2.7826070019376927e-07, "epoch": 3.9172876304023845, "percentage": 78.35, "elapsed_time": "1:09:26", "remaining_time": "0:19:11", "throughput": 5167.83, "total_tokens": 21532672} {"current_steps": 5258, "total_steps": 6710, "loss": 0.2124, "lr": 2.778926778770362e-07, "epoch": 3.918032786885246, "percentage": 78.36, "elapsed_time": "1:09:27", "remaining_time": "0:19:10", "throughput": 5167.85, "total_tokens": 21536768} {"current_steps": 5259, "total_steps": 6710, "loss": 0.1784, "lr": 2.775248686531692e-07, "epoch": 3.918777943368107, "percentage": 78.38, "elapsed_time": "1:09:28", "remaining_time": "0:19:10", "throughput": 5167.86, "total_tokens": 21540864} {"current_steps": 5260, "total_steps": 6710, "loss": 0.2092, "lr": 2.771572726027955e-07, "epoch": 3.9195230998509687, "percentage": 78.39, "elapsed_time": "1:09:29", "remaining_time": "0:19:09", "throughput": 5167.88, "total_tokens": 21544960} {"current_steps": 5261, "total_steps": 6710, "loss": 0.2987, "lr": 2.7678988980649384e-07, "epoch": 3.9202682563338302, "percentage": 78.41, "elapsed_time": "1:09:29", "remaining_time": "0:19:08", "throughput": 5167.89, "total_tokens": 21549056} {"current_steps": 5262, "total_steps": 6710, "loss": 0.158, "lr": 2.764227203447985e-07, "epoch": 3.9210134128166914, "percentage": 78.42, "elapsed_time": "1:09:30", "remaining_time": "0:19:07", "throughput": 5167.91, "total_tokens": 21553152} {"current_steps": 5263, "total_steps": 6710, "loss": 0.3821, "lr": 2.760557642981941e-07, "epoch": 3.921758569299553, "percentage": 78.44, "elapsed_time": "1:09:31", "remaining_time": "0:19:06", "throughput": 5167.92, "total_tokens": 21557248} {"current_steps": 5264, "total_steps": 6710, "loss": 0.2215, "lr": 2.756890217471211e-07, "epoch": 3.9225037257824145, "percentage": 78.45, "elapsed_time": "1:09:32", "remaining_time": "0:19:06", "throughput": 5167.94, "total_tokens": 21561344} {"current_steps": 5265, "total_steps": 6710, "loss": 0.068, "lr": 2.7532249277197153e-07, "epoch": 3.9232488822652756, "percentage": 78.46, "elapsed_time": "1:09:32", "remaining_time": "0:19:05", "throughput": 5167.95, "total_tokens": 21565440} {"current_steps": 5266, "total_steps": 6710, "loss": 0.1922, "lr": 2.749561774530915e-07, "epoch": 3.923994038748137, "percentage": 78.48, "elapsed_time": "1:09:33", "remaining_time": "0:19:04", "throughput": 5167.97, "total_tokens": 21569536} {"current_steps": 5267, "total_steps": 6710, "loss": 0.1229, "lr": 2.745900758707799e-07, "epoch": 3.9247391952309982, "percentage": 78.49, "elapsed_time": "1:09:34", "remaining_time": "0:19:03", "throughput": 5167.98, "total_tokens": 21573632} {"current_steps": 5268, "total_steps": 6710, "loss": 0.1545, "lr": 2.742241881052883e-07, "epoch": 3.92548435171386, "percentage": 78.51, "elapsed_time": "1:09:35", "remaining_time": "0:19:02", "throughput": 5168.0, "total_tokens": 21577728} {"current_steps": 5269, "total_steps": 6710, "loss": 0.1112, "lr": 2.7385851423682274e-07, "epoch": 3.9262295081967213, "percentage": 78.52, "elapsed_time": "1:09:36", "remaining_time": "0:19:02", "throughput": 5168.0, "total_tokens": 21581824} {"current_steps": 5270, "total_steps": 6710, "loss": 0.2239, "lr": 2.734930543455408e-07, "epoch": 3.926974664679583, "percentage": 78.54, "elapsed_time": "1:09:36", "remaining_time": "0:19:01", "throughput": 5168.01, "total_tokens": 21585920} {"current_steps": 5271, "total_steps": 6710, "loss": 0.3699, "lr": 2.7312780851155464e-07, "epoch": 3.927719821162444, "percentage": 78.55, "elapsed_time": "1:09:37", "remaining_time": "0:19:00", "throughput": 5168.01, "total_tokens": 21590016} {"current_steps": 5272, "total_steps": 6710, "loss": 0.1699, "lr": 2.7276277681492783e-07, "epoch": 3.9284649776453056, "percentage": 78.57, "elapsed_time": "1:09:38", "remaining_time": "0:18:59", "throughput": 5168.02, "total_tokens": 21594112} {"current_steps": 5273, "total_steps": 6710, "loss": 0.1581, "lr": 2.723979593356789e-07, "epoch": 3.9292101341281667, "percentage": 78.58, "elapsed_time": "1:09:39", "remaining_time": "0:18:58", "throughput": 5168.02, "total_tokens": 21598208} {"current_steps": 5274, "total_steps": 6710, "loss": 0.2054, "lr": 2.7203335615377786e-07, "epoch": 3.929955290611028, "percentage": 78.6, "elapsed_time": "1:09:40", "remaining_time": "0:18:58", "throughput": 5168.01, "total_tokens": 21602304} {"current_steps": 5275, "total_steps": 6710, "loss": 0.1813, "lr": 2.716689673491482e-07, "epoch": 3.9307004470938898, "percentage": 78.61, "elapsed_time": "1:09:40", "remaining_time": "0:18:57", "throughput": 5168.01, "total_tokens": 21606400} {"current_steps": 5276, "total_steps": 6710, "loss": 0.0625, "lr": 2.7130479300166725e-07, "epoch": 3.9314456035767513, "percentage": 78.63, "elapsed_time": "1:09:41", "remaining_time": "0:18:56", "throughput": 5168.01, "total_tokens": 21610496} {"current_steps": 5277, "total_steps": 6710, "loss": 0.1595, "lr": 2.709408331911641e-07, "epoch": 3.9321907600596124, "percentage": 78.64, "elapsed_time": "1:09:42", "remaining_time": "0:18:55", "throughput": 5168.02, "total_tokens": 21614592} {"current_steps": 5278, "total_steps": 6710, "loss": 0.2597, "lr": 2.7057708799742137e-07, "epoch": 3.932935916542474, "percentage": 78.66, "elapsed_time": "1:09:43", "remaining_time": "0:18:54", "throughput": 5168.02, "total_tokens": 21618688} {"current_steps": 5279, "total_steps": 6710, "loss": 0.0825, "lr": 2.7021355750017435e-07, "epoch": 3.933681073025335, "percentage": 78.67, "elapsed_time": "1:09:43", "remaining_time": "0:18:54", "throughput": 5168.03, "total_tokens": 21622784} {"current_steps": 5280, "total_steps": 6710, "loss": 0.1629, "lr": 2.698502417791121e-07, "epoch": 3.9344262295081966, "percentage": 78.69, "elapsed_time": "1:09:44", "remaining_time": "0:18:53", "throughput": 5168.03, "total_tokens": 21626880} {"current_steps": 5281, "total_steps": 6710, "loss": 0.1954, "lr": 2.694871409138755e-07, "epoch": 3.935171385991058, "percentage": 78.7, "elapsed_time": "1:09:45", "remaining_time": "0:18:52", "throughput": 5168.04, "total_tokens": 21630976} {"current_steps": 5282, "total_steps": 6710, "loss": 0.0752, "lr": 2.6912425498405947e-07, "epoch": 3.9359165424739198, "percentage": 78.72, "elapsed_time": "1:09:46", "remaining_time": "0:18:51", "throughput": 5168.04, "total_tokens": 21635072} {"current_steps": 5283, "total_steps": 6710, "loss": 0.0414, "lr": 2.687615840692104e-07, "epoch": 3.936661698956781, "percentage": 78.73, "elapsed_time": "1:09:47", "remaining_time": "0:18:50", "throughput": 5168.05, "total_tokens": 21639168} {"current_steps": 5284, "total_steps": 6710, "loss": 0.2734, "lr": 2.683991282488292e-07, "epoch": 3.9374068554396424, "percentage": 78.75, "elapsed_time": "1:09:47", "remaining_time": "0:18:50", "throughput": 5168.05, "total_tokens": 21643264} {"current_steps": 5285, "total_steps": 6710, "loss": 0.101, "lr": 2.6803688760236827e-07, "epoch": 3.9381520119225035, "percentage": 78.76, "elapsed_time": "1:09:48", "remaining_time": "0:18:49", "throughput": 5168.06, "total_tokens": 21647360} {"current_steps": 5286, "total_steps": 6710, "loss": 0.2675, "lr": 2.6767486220923304e-07, "epoch": 3.938897168405365, "percentage": 78.78, "elapsed_time": "1:09:49", "remaining_time": "0:18:48", "throughput": 5168.07, "total_tokens": 21651456} {"current_steps": 5287, "total_steps": 6710, "loss": 0.326, "lr": 2.6731305214878296e-07, "epoch": 3.9396423248882266, "percentage": 78.79, "elapsed_time": "1:09:50", "remaining_time": "0:18:47", "throughput": 5168.07, "total_tokens": 21655552} {"current_steps": 5288, "total_steps": 6710, "loss": 0.1267, "lr": 2.669514575003283e-07, "epoch": 3.940387481371088, "percentage": 78.81, "elapsed_time": "1:09:51", "remaining_time": "0:18:47", "throughput": 5168.08, "total_tokens": 21659648} {"current_steps": 5289, "total_steps": 6710, "loss": 0.0784, "lr": 2.665900783431345e-07, "epoch": 3.9411326378539493, "percentage": 78.82, "elapsed_time": "1:09:51", "remaining_time": "0:18:46", "throughput": 5168.09, "total_tokens": 21663744} {"current_steps": 5290, "total_steps": 6710, "loss": 0.1231, "lr": 2.6622891475641705e-07, "epoch": 3.941877794336811, "percentage": 78.84, "elapsed_time": "1:09:52", "remaining_time": "0:18:45", "throughput": 5168.1, "total_tokens": 21667840} {"current_steps": 5291, "total_steps": 6710, "loss": 0.2125, "lr": 2.658679668193466e-07, "epoch": 3.942622950819672, "percentage": 78.85, "elapsed_time": "1:09:53", "remaining_time": "0:18:44", "throughput": 5168.11, "total_tokens": 21671936} {"current_steps": 5292, "total_steps": 6710, "loss": 0.2069, "lr": 2.655072346110449e-07, "epoch": 3.9433681073025335, "percentage": 78.87, "elapsed_time": "1:09:54", "remaining_time": "0:18:43", "throughput": 5168.09, "total_tokens": 21676032} {"current_steps": 5293, "total_steps": 6710, "loss": 0.1829, "lr": 2.651467182105874e-07, "epoch": 3.944113263785395, "percentage": 78.88, "elapsed_time": "1:09:54", "remaining_time": "0:18:43", "throughput": 5168.1, "total_tokens": 21680128} {"current_steps": 5294, "total_steps": 6710, "loss": 0.3034, "lr": 2.647864176970019e-07, "epoch": 3.944858420268256, "percentage": 78.9, "elapsed_time": "1:09:55", "remaining_time": "0:18:42", "throughput": 5168.12, "total_tokens": 21684224} {"current_steps": 5295, "total_steps": 6710, "loss": 0.1746, "lr": 2.644263331492683e-07, "epoch": 3.9456035767511177, "percentage": 78.91, "elapsed_time": "1:09:56", "remaining_time": "0:18:41", "throughput": 5168.13, "total_tokens": 21688320} {"current_steps": 5296, "total_steps": 6710, "loss": 0.1116, "lr": 2.640664646463205e-07, "epoch": 3.9463487332339793, "percentage": 78.93, "elapsed_time": "1:09:57", "remaining_time": "0:18:40", "throughput": 5168.14, "total_tokens": 21692416} {"current_steps": 5297, "total_steps": 6710, "loss": 0.1164, "lr": 2.6370681226704344e-07, "epoch": 3.9470938897168404, "percentage": 78.94, "elapsed_time": "1:09:58", "remaining_time": "0:18:39", "throughput": 5168.15, "total_tokens": 21696512} {"current_steps": 5298, "total_steps": 6710, "loss": 0.108, "lr": 2.633473760902762e-07, "epoch": 3.947839046199702, "percentage": 78.96, "elapsed_time": "1:09:58", "remaining_time": "0:18:39", "throughput": 5168.16, "total_tokens": 21700608} {"current_steps": 5299, "total_steps": 6710, "loss": 0.2341, "lr": 2.6298815619480914e-07, "epoch": 3.9485842026825635, "percentage": 78.97, "elapsed_time": "1:09:59", "remaining_time": "0:18:38", "throughput": 5168.16, "total_tokens": 21704704} {"current_steps": 5300, "total_steps": 6710, "loss": 0.1148, "lr": 2.6262915265938657e-07, "epoch": 3.9493293591654246, "percentage": 78.99, "elapsed_time": "1:10:00", "remaining_time": "0:18:37", "throughput": 5168.16, "total_tokens": 21708800} {"current_steps": 5301, "total_steps": 6710, "loss": 0.114, "lr": 2.6227036556270414e-07, "epoch": 3.950074515648286, "percentage": 79.0, "elapsed_time": "1:10:01", "remaining_time": "0:18:36", "throughput": 5168.18, "total_tokens": 21712896} {"current_steps": 5302, "total_steps": 6710, "loss": 0.2155, "lr": 2.619117949834106e-07, "epoch": 3.9508196721311473, "percentage": 79.02, "elapsed_time": "1:10:02", "remaining_time": "0:18:35", "throughput": 5168.19, "total_tokens": 21716992} {"current_steps": 5303, "total_steps": 6710, "loss": 0.2292, "lr": 2.615534410001068e-07, "epoch": 3.951564828614009, "percentage": 79.03, "elapsed_time": "1:10:02", "remaining_time": "0:18:35", "throughput": 5168.21, "total_tokens": 21721088} {"current_steps": 5304, "total_steps": 6710, "loss": 0.1463, "lr": 2.611953036913471e-07, "epoch": 3.9523099850968704, "percentage": 79.05, "elapsed_time": "1:10:03", "remaining_time": "0:18:34", "throughput": 5168.22, "total_tokens": 21725184} {"current_steps": 5305, "total_steps": 6710, "loss": 0.3142, "lr": 2.608373831356377e-07, "epoch": 3.953055141579732, "percentage": 79.06, "elapsed_time": "1:10:04", "remaining_time": "0:18:33", "throughput": 5168.23, "total_tokens": 21729280} {"current_steps": 5306, "total_steps": 6710, "loss": 0.2542, "lr": 2.6047967941143684e-07, "epoch": 3.953800298062593, "percentage": 79.08, "elapsed_time": "1:10:05", "remaining_time": "0:18:32", "throughput": 5168.25, "total_tokens": 21733376} {"current_steps": 5307, "total_steps": 6710, "loss": 0.2036, "lr": 2.601221925971563e-07, "epoch": 3.9545454545454546, "percentage": 79.09, "elapsed_time": "1:10:05", "remaining_time": "0:18:31", "throughput": 5168.26, "total_tokens": 21737472} {"current_steps": 5308, "total_steps": 6710, "loss": 0.4095, "lr": 2.597649227711592e-07, "epoch": 3.9552906110283157, "percentage": 79.11, "elapsed_time": "1:10:06", "remaining_time": "0:18:31", "throughput": 5168.28, "total_tokens": 21741568} {"current_steps": 5309, "total_steps": 6710, "loss": 0.1308, "lr": 2.5940787001176234e-07, "epoch": 3.9560357675111772, "percentage": 79.12, "elapsed_time": "1:10:07", "remaining_time": "0:18:30", "throughput": 5168.29, "total_tokens": 21745664} {"current_steps": 5310, "total_steps": 6710, "loss": 0.3563, "lr": 2.5905103439723344e-07, "epoch": 3.956780923994039, "percentage": 79.14, "elapsed_time": "1:10:08", "remaining_time": "0:18:29", "throughput": 5168.3, "total_tokens": 21749760} {"current_steps": 5311, "total_steps": 6710, "loss": 0.1882, "lr": 2.5869441600579416e-07, "epoch": 3.9575260804769004, "percentage": 79.15, "elapsed_time": "1:10:09", "remaining_time": "0:18:28", "throughput": 5168.31, "total_tokens": 21753856} {"current_steps": 5312, "total_steps": 6710, "loss": 0.0728, "lr": 2.5833801491561743e-07, "epoch": 3.9582712369597615, "percentage": 79.17, "elapsed_time": "1:10:09", "remaining_time": "0:18:27", "throughput": 5168.33, "total_tokens": 21757952} {"current_steps": 5313, "total_steps": 6710, "loss": 0.2258, "lr": 2.579818312048286e-07, "epoch": 3.959016393442623, "percentage": 79.18, "elapsed_time": "1:10:10", "remaining_time": "0:18:27", "throughput": 5168.34, "total_tokens": 21762048} {"current_steps": 5314, "total_steps": 6710, "loss": 0.1085, "lr": 2.5762586495150635e-07, "epoch": 3.959761549925484, "percentage": 79.2, "elapsed_time": "1:10:11", "remaining_time": "0:18:26", "throughput": 5168.35, "total_tokens": 21766144} {"current_steps": 5315, "total_steps": 6710, "loss": 0.2091, "lr": 2.572701162336803e-07, "epoch": 3.9605067064083457, "percentage": 79.21, "elapsed_time": "1:10:12", "remaining_time": "0:18:25", "throughput": 5168.36, "total_tokens": 21770240} {"current_steps": 5316, "total_steps": 6710, "loss": 0.1901, "lr": 2.569145851293342e-07, "epoch": 3.9612518628912072, "percentage": 79.23, "elapsed_time": "1:10:12", "remaining_time": "0:18:24", "throughput": 5168.37, "total_tokens": 21774336} {"current_steps": 5317, "total_steps": 6710, "loss": 0.1279, "lr": 2.565592717164017e-07, "epoch": 3.961997019374069, "percentage": 79.24, "elapsed_time": "1:10:13", "remaining_time": "0:18:23", "throughput": 5168.39, "total_tokens": 21778432} {"current_steps": 5318, "total_steps": 6710, "loss": 0.1859, "lr": 2.5620417607277097e-07, "epoch": 3.96274217585693, "percentage": 79.25, "elapsed_time": "1:10:14", "remaining_time": "0:18:23", "throughput": 5168.39, "total_tokens": 21782528} {"current_steps": 5319, "total_steps": 6710, "loss": 0.1012, "lr": 2.558492982762807e-07, "epoch": 3.9634873323397914, "percentage": 79.27, "elapsed_time": "1:10:15", "remaining_time": "0:18:22", "throughput": 5168.39, "total_tokens": 21786624} {"current_steps": 5320, "total_steps": 6710, "loss": 0.0789, "lr": 2.554946384047236e-07, "epoch": 3.9642324888226526, "percentage": 79.28, "elapsed_time": "1:10:16", "remaining_time": "0:18:21", "throughput": 5168.41, "total_tokens": 21790720} {"current_steps": 5321, "total_steps": 6710, "loss": 0.0792, "lr": 2.551401965358431e-07, "epoch": 3.964977645305514, "percentage": 79.3, "elapsed_time": "1:10:16", "remaining_time": "0:18:20", "throughput": 5168.42, "total_tokens": 21794816} {"current_steps": 5322, "total_steps": 6710, "loss": 0.0356, "lr": 2.5478597274733523e-07, "epoch": 3.9657228017883757, "percentage": 79.31, "elapsed_time": "1:10:17", "remaining_time": "0:18:19", "throughput": 5168.44, "total_tokens": 21798912} {"current_steps": 5323, "total_steps": 6710, "loss": 0.0606, "lr": 2.544319671168488e-07, "epoch": 3.966467958271237, "percentage": 79.33, "elapsed_time": "1:10:18", "remaining_time": "0:18:19", "throughput": 5168.45, "total_tokens": 21803008} {"current_steps": 5324, "total_steps": 6710, "loss": 0.168, "lr": 2.540781797219838e-07, "epoch": 3.9672131147540983, "percentage": 79.34, "elapsed_time": "1:10:19", "remaining_time": "0:18:18", "throughput": 5168.47, "total_tokens": 21807104} {"current_steps": 5325, "total_steps": 6710, "loss": 0.175, "lr": 2.537246106402938e-07, "epoch": 3.96795827123696, "percentage": 79.36, "elapsed_time": "1:10:20", "remaining_time": "0:18:17", "throughput": 5168.48, "total_tokens": 21811200} {"current_steps": 5326, "total_steps": 6710, "loss": 0.317, "lr": 2.533712599492827e-07, "epoch": 3.968703427719821, "percentage": 79.37, "elapsed_time": "1:10:20", "remaining_time": "0:18:16", "throughput": 5168.49, "total_tokens": 21815296} {"current_steps": 5327, "total_steps": 6710, "loss": 0.1836, "lr": 2.530181277264085e-07, "epoch": 3.9694485842026825, "percentage": 79.39, "elapsed_time": "1:10:21", "remaining_time": "0:18:16", "throughput": 5168.5, "total_tokens": 21819392} {"current_steps": 5328, "total_steps": 6710, "loss": 0.1517, "lr": 2.526652140490797e-07, "epoch": 3.970193740685544, "percentage": 79.4, "elapsed_time": "1:10:22", "remaining_time": "0:18:15", "throughput": 5168.52, "total_tokens": 21823488} {"current_steps": 5329, "total_steps": 6710, "loss": 0.1307, "lr": 2.523125189946575e-07, "epoch": 3.970938897168405, "percentage": 79.42, "elapsed_time": "1:10:23", "remaining_time": "0:18:14", "throughput": 5168.53, "total_tokens": 21827584} {"current_steps": 5330, "total_steps": 6710, "loss": 0.0917, "lr": 2.5196004264045504e-07, "epoch": 3.9716840536512668, "percentage": 79.43, "elapsed_time": "1:10:23", "remaining_time": "0:18:13", "throughput": 5168.55, "total_tokens": 21831680} {"current_steps": 5331, "total_steps": 6710, "loss": 0.1298, "lr": 2.5160778506373814e-07, "epoch": 3.9724292101341283, "percentage": 79.45, "elapsed_time": "1:10:24", "remaining_time": "0:18:12", "throughput": 5168.56, "total_tokens": 21835776} {"current_steps": 5332, "total_steps": 6710, "loss": 0.0394, "lr": 2.5125574634172397e-07, "epoch": 3.9731743666169894, "percentage": 79.46, "elapsed_time": "1:10:25", "remaining_time": "0:18:12", "throughput": 5168.57, "total_tokens": 21839872} {"current_steps": 5333, "total_steps": 6710, "loss": 0.1875, "lr": 2.5090392655158156e-07, "epoch": 3.973919523099851, "percentage": 79.48, "elapsed_time": "1:10:26", "remaining_time": "0:18:11", "throughput": 5168.55, "total_tokens": 21843968} {"current_steps": 5334, "total_steps": 6710, "loss": 0.1655, "lr": 2.505523257704329e-07, "epoch": 3.9746646795827125, "percentage": 79.49, "elapsed_time": "1:10:27", "remaining_time": "0:18:10", "throughput": 5168.57, "total_tokens": 21848064} {"current_steps": 5335, "total_steps": 6710, "loss": 0.0786, "lr": 2.502009440753508e-07, "epoch": 3.9754098360655736, "percentage": 79.51, "elapsed_time": "1:10:27", "remaining_time": "0:18:09", "throughput": 5168.58, "total_tokens": 21852160} {"current_steps": 5336, "total_steps": 6710, "loss": 0.1122, "lr": 2.4984978154336134e-07, "epoch": 3.976154992548435, "percentage": 79.52, "elapsed_time": "1:10:28", "remaining_time": "0:18:08", "throughput": 5168.6, "total_tokens": 21856256} {"current_steps": 5337, "total_steps": 6710, "loss": 0.2496, "lr": 2.49498838251441e-07, "epoch": 3.9769001490312967, "percentage": 79.54, "elapsed_time": "1:10:29", "remaining_time": "0:18:08", "throughput": 5168.61, "total_tokens": 21860352} {"current_steps": 5338, "total_steps": 6710, "loss": 0.397, "lr": 2.4914811427652007e-07, "epoch": 3.977645305514158, "percentage": 79.55, "elapsed_time": "1:10:30", "remaining_time": "0:18:07", "throughput": 5168.62, "total_tokens": 21864448} {"current_steps": 5339, "total_steps": 6710, "loss": 0.2169, "lr": 2.48797609695479e-07, "epoch": 3.9783904619970194, "percentage": 79.57, "elapsed_time": "1:10:31", "remaining_time": "0:18:06", "throughput": 5168.63, "total_tokens": 21868544} {"current_steps": 5340, "total_steps": 6710, "loss": 0.1104, "lr": 2.4844732458515097e-07, "epoch": 3.979135618479881, "percentage": 79.58, "elapsed_time": "1:10:31", "remaining_time": "0:18:05", "throughput": 5168.65, "total_tokens": 21872640} {"current_steps": 5341, "total_steps": 6710, "loss": 0.1101, "lr": 2.4809725902232145e-07, "epoch": 3.979880774962742, "percentage": 79.6, "elapsed_time": "1:10:32", "remaining_time": "0:18:04", "throughput": 5168.66, "total_tokens": 21876736} {"current_steps": 5342, "total_steps": 6710, "loss": 0.1667, "lr": 2.477474130837265e-07, "epoch": 3.9806259314456036, "percentage": 79.61, "elapsed_time": "1:10:33", "remaining_time": "0:18:04", "throughput": 5168.67, "total_tokens": 21880832} {"current_steps": 5343, "total_steps": 6710, "loss": 0.2525, "lr": 2.47397786846056e-07, "epoch": 3.9813710879284647, "percentage": 79.63, "elapsed_time": "1:10:34", "remaining_time": "0:18:03", "throughput": 5168.69, "total_tokens": 21884928} {"current_steps": 5344, "total_steps": 6710, "loss": 0.1291, "lr": 2.4704838038594927e-07, "epoch": 3.9821162444113263, "percentage": 79.64, "elapsed_time": "1:10:34", "remaining_time": "0:18:02", "throughput": 5168.7, "total_tokens": 21889024} {"current_steps": 5345, "total_steps": 6710, "loss": 0.2516, "lr": 2.466991937799995e-07, "epoch": 3.982861400894188, "percentage": 79.66, "elapsed_time": "1:10:35", "remaining_time": "0:18:01", "throughput": 5168.72, "total_tokens": 21893120} {"current_steps": 5346, "total_steps": 6710, "loss": 0.131, "lr": 2.463502271047505e-07, "epoch": 3.9836065573770494, "percentage": 79.67, "elapsed_time": "1:10:36", "remaining_time": "0:18:00", "throughput": 5168.73, "total_tokens": 21897216} {"current_steps": 5347, "total_steps": 6710, "loss": 0.2509, "lr": 2.460014804366986e-07, "epoch": 3.9843517138599105, "percentage": 79.69, "elapsed_time": "1:10:37", "remaining_time": "0:18:00", "throughput": 5168.74, "total_tokens": 21901312} {"current_steps": 5348, "total_steps": 6710, "loss": 0.3511, "lr": 2.4565295385229117e-07, "epoch": 3.985096870342772, "percentage": 79.7, "elapsed_time": "1:10:38", "remaining_time": "0:17:59", "throughput": 5168.76, "total_tokens": 21905408} {"current_steps": 5349, "total_steps": 6710, "loss": 0.2292, "lr": 2.4530464742792817e-07, "epoch": 3.985842026825633, "percentage": 79.72, "elapsed_time": "1:10:38", "remaining_time": "0:17:58", "throughput": 5168.77, "total_tokens": 21909504} {"current_steps": 5350, "total_steps": 6710, "loss": 0.2006, "lr": 2.449565612399606e-07, "epoch": 3.9865871833084947, "percentage": 79.73, "elapsed_time": "1:10:39", "remaining_time": "0:17:57", "throughput": 5168.78, "total_tokens": 21913600} {"current_steps": 5351, "total_steps": 6710, "loss": 0.2215, "lr": 2.446086953646912e-07, "epoch": 3.9873323397913563, "percentage": 79.75, "elapsed_time": "1:10:40", "remaining_time": "0:17:56", "throughput": 5168.8, "total_tokens": 21917696} {"current_steps": 5352, "total_steps": 6710, "loss": 0.1945, "lr": 2.4426104987837527e-07, "epoch": 3.988077496274218, "percentage": 79.76, "elapsed_time": "1:10:41", "remaining_time": "0:17:56", "throughput": 5168.81, "total_tokens": 21921792} {"current_steps": 5353, "total_steps": 6710, "loss": 0.1366, "lr": 2.439136248572184e-07, "epoch": 3.988822652757079, "percentage": 79.78, "elapsed_time": "1:10:41", "remaining_time": "0:17:55", "throughput": 5168.83, "total_tokens": 21925888} {"current_steps": 5354, "total_steps": 6710, "loss": 0.0903, "lr": 2.4356642037737937e-07, "epoch": 3.9895678092399405, "percentage": 79.79, "elapsed_time": "1:10:42", "remaining_time": "0:17:54", "throughput": 5168.84, "total_tokens": 21929984} {"current_steps": 5355, "total_steps": 6710, "loss": 0.2491, "lr": 2.4321943651496733e-07, "epoch": 3.9903129657228016, "percentage": 79.81, "elapsed_time": "1:10:43", "remaining_time": "0:17:53", "throughput": 5168.85, "total_tokens": 21934080} {"current_steps": 5356, "total_steps": 6710, "loss": 0.2654, "lr": 2.4287267334604447e-07, "epoch": 3.991058122205663, "percentage": 79.82, "elapsed_time": "1:10:44", "remaining_time": "0:17:52", "throughput": 5168.87, "total_tokens": 21938176} {"current_steps": 5357, "total_steps": 6710, "loss": 0.1184, "lr": 2.4252613094662245e-07, "epoch": 3.9918032786885247, "percentage": 79.84, "elapsed_time": "1:10:45", "remaining_time": "0:17:52", "throughput": 5168.88, "total_tokens": 21942272} {"current_steps": 5358, "total_steps": 6710, "loss": 0.1818, "lr": 2.4217980939266696e-07, "epoch": 3.9925484351713862, "percentage": 79.85, "elapsed_time": "1:10:45", "remaining_time": "0:17:51", "throughput": 5168.89, "total_tokens": 21946368} {"current_steps": 5359, "total_steps": 6710, "loss": 0.1041, "lr": 2.4183370876009374e-07, "epoch": 3.9932935916542474, "percentage": 79.87, "elapsed_time": "1:10:46", "remaining_time": "0:17:50", "throughput": 5168.9, "total_tokens": 21950464} {"current_steps": 5360, "total_steps": 6710, "loss": 0.1985, "lr": 2.4148782912477006e-07, "epoch": 3.994038748137109, "percentage": 79.88, "elapsed_time": "1:10:47", "remaining_time": "0:17:49", "throughput": 5168.91, "total_tokens": 21954560} {"current_steps": 5361, "total_steps": 6710, "loss": 0.0903, "lr": 2.411421705625161e-07, "epoch": 3.99478390461997, "percentage": 79.9, "elapsed_time": "1:10:48", "remaining_time": "0:17:48", "throughput": 5168.92, "total_tokens": 21958656} {"current_steps": 5362, "total_steps": 6710, "loss": 0.2721, "lr": 2.4079673314910177e-07, "epoch": 3.9955290611028316, "percentage": 79.91, "elapsed_time": "1:10:48", "remaining_time": "0:17:48", "throughput": 5168.94, "total_tokens": 21962752} {"current_steps": 5363, "total_steps": 6710, "loss": 0.1261, "lr": 2.4045151696025034e-07, "epoch": 3.996274217585693, "percentage": 79.93, "elapsed_time": "1:10:49", "remaining_time": "0:17:47", "throughput": 5168.95, "total_tokens": 21966848} {"current_steps": 5364, "total_steps": 6710, "loss": 0.2068, "lr": 2.401065220716349e-07, "epoch": 3.9970193740685542, "percentage": 79.94, "elapsed_time": "1:10:50", "remaining_time": "0:17:46", "throughput": 5168.96, "total_tokens": 21970944} {"current_steps": 5365, "total_steps": 6710, "loss": 0.1061, "lr": 2.397617485588814e-07, "epoch": 3.997764530551416, "percentage": 79.96, "elapsed_time": "1:10:51", "remaining_time": "0:17:45", "throughput": 5168.98, "total_tokens": 21975040} {"current_steps": 5366, "total_steps": 6710, "loss": 0.2057, "lr": 2.3941719649756637e-07, "epoch": 3.9985096870342773, "percentage": 79.97, "elapsed_time": "1:10:52", "remaining_time": "0:17:45", "throughput": 5168.99, "total_tokens": 21979136} {"current_steps": 5367, "total_steps": 6710, "loss": 0.0964, "lr": 2.390728659632177e-07, "epoch": 3.9992548435171384, "percentage": 79.99, "elapsed_time": "1:10:52", "remaining_time": "0:17:44", "throughput": 5169.0, "total_tokens": 21983232} {"current_steps": 5368, "total_steps": 6710, "loss": 0.1162, "lr": 2.387287570313158e-07, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:10:53", "remaining_time": "0:17:43", "throughput": 5169.03, "total_tokens": 21987328} {"current_steps": 5369, "total_steps": 6710, "loss": 0.1092, "lr": 2.3838486977729114e-07, "epoch": 4.0007451564828616, "percentage": 80.01, "elapsed_time": "1:10:54", "remaining_time": "0:17:42", "throughput": 5169.03, "total_tokens": 21991424} {"current_steps": 5370, "total_steps": 6710, "loss": 0.3052, "lr": 2.3804120427652733e-07, "epoch": 4.001490312965723, "percentage": 80.03, "elapsed_time": "1:10:55", "remaining_time": "0:17:41", "throughput": 5169.05, "total_tokens": 21995520} {"current_steps": 5371, "total_steps": 6710, "loss": 0.0736, "lr": 2.3769776060435691e-07, "epoch": 4.002235469448584, "percentage": 80.04, "elapsed_time": "1:10:56", "remaining_time": "0:17:41", "throughput": 5169.06, "total_tokens": 21999616} {"current_steps": 5372, "total_steps": 6710, "loss": 0.0774, "lr": 2.373545388360661e-07, "epoch": 4.002980625931445, "percentage": 80.06, "elapsed_time": "1:10:56", "remaining_time": "0:17:40", "throughput": 5169.08, "total_tokens": 22003712} {"current_steps": 5373, "total_steps": 6710, "loss": 0.0771, "lr": 2.3701153904689106e-07, "epoch": 4.003725782414307, "percentage": 80.07, "elapsed_time": "1:10:57", "remaining_time": "0:17:39", "throughput": 5169.09, "total_tokens": 22007808} {"current_steps": 5374, "total_steps": 6710, "loss": 0.1206, "lr": 2.366687613120204e-07, "epoch": 4.004470938897168, "percentage": 80.09, "elapsed_time": "1:10:58", "remaining_time": "0:17:38", "throughput": 5169.09, "total_tokens": 22011904} {"current_steps": 5375, "total_steps": 6710, "loss": 0.0864, "lr": 2.3632620570659266e-07, "epoch": 4.00521609538003, "percentage": 80.1, "elapsed_time": "1:10:59", "remaining_time": "0:17:37", "throughput": 5169.1, "total_tokens": 22016000} {"current_steps": 5376, "total_steps": 6710, "loss": 0.0224, "lr": 2.359838723056994e-07, "epoch": 4.0059612518628915, "percentage": 80.12, "elapsed_time": "1:10:59", "remaining_time": "0:17:37", "throughput": 5169.12, "total_tokens": 22020096} {"current_steps": 5377, "total_steps": 6710, "loss": 0.0512, "lr": 2.3564176118438183e-07, "epoch": 4.006706408345752, "percentage": 80.13, "elapsed_time": "1:11:00", "remaining_time": "0:17:36", "throughput": 5169.13, "total_tokens": 22024192} {"current_steps": 5378, "total_steps": 6710, "loss": 0.0393, "lr": 2.3529987241763323e-07, "epoch": 4.007451564828614, "percentage": 80.15, "elapsed_time": "1:11:01", "remaining_time": "0:17:35", "throughput": 5169.14, "total_tokens": 22028288} {"current_steps": 5379, "total_steps": 6710, "loss": 0.1498, "lr": 2.3495820608039842e-07, "epoch": 4.008196721311475, "percentage": 80.16, "elapsed_time": "1:11:02", "remaining_time": "0:17:34", "throughput": 5169.16, "total_tokens": 22032384} {"current_steps": 5380, "total_steps": 6710, "loss": 0.1503, "lr": 2.3461676224757256e-07, "epoch": 4.008941877794337, "percentage": 80.18, "elapsed_time": "1:11:03", "remaining_time": "0:17:33", "throughput": 5169.17, "total_tokens": 22036480} {"current_steps": 5381, "total_steps": 6710, "loss": 0.0779, "lr": 2.3427554099400327e-07, "epoch": 4.009687034277198, "percentage": 80.19, "elapsed_time": "1:11:03", "remaining_time": "0:17:33", "throughput": 5169.19, "total_tokens": 22040576} {"current_steps": 5382, "total_steps": 6710, "loss": 0.1502, "lr": 2.3393454239448804e-07, "epoch": 4.01043219076006, "percentage": 80.21, "elapsed_time": "1:11:04", "remaining_time": "0:17:32", "throughput": 5169.2, "total_tokens": 22044672} {"current_steps": 5383, "total_steps": 6710, "loss": 0.1081, "lr": 2.335937665237771e-07, "epoch": 4.011177347242921, "percentage": 80.22, "elapsed_time": "1:11:05", "remaining_time": "0:17:31", "throughput": 5169.21, "total_tokens": 22048768} {"current_steps": 5384, "total_steps": 6710, "loss": 0.0724, "lr": 2.332532134565696e-07, "epoch": 4.011922503725782, "percentage": 80.24, "elapsed_time": "1:11:06", "remaining_time": "0:17:30", "throughput": 5169.23, "total_tokens": 22052864} {"current_steps": 5385, "total_steps": 6710, "loss": 0.178, "lr": 2.329128832675183e-07, "epoch": 4.012667660208644, "percentage": 80.25, "elapsed_time": "1:11:06", "remaining_time": "0:17:29", "throughput": 5169.24, "total_tokens": 22056960} {"current_steps": 5386, "total_steps": 6710, "loss": 0.0594, "lr": 2.3257277603122561e-07, "epoch": 4.013412816691505, "percentage": 80.27, "elapsed_time": "1:11:07", "remaining_time": "0:17:29", "throughput": 5169.26, "total_tokens": 22061056} {"current_steps": 5387, "total_steps": 6710, "loss": 0.0542, "lr": 2.3223289182224523e-07, "epoch": 4.014157973174367, "percentage": 80.28, "elapsed_time": "1:11:08", "remaining_time": "0:17:28", "throughput": 5169.27, "total_tokens": 22065152} {"current_steps": 5388, "total_steps": 6710, "loss": 0.0522, "lr": 2.3189323071508272e-07, "epoch": 4.014903129657228, "percentage": 80.3, "elapsed_time": "1:11:09", "remaining_time": "0:17:27", "throughput": 5169.28, "total_tokens": 22069248} {"current_steps": 5389, "total_steps": 6710, "loss": 0.1551, "lr": 2.3155379278419363e-07, "epoch": 4.015648286140089, "percentage": 80.31, "elapsed_time": "1:11:10", "remaining_time": "0:17:26", "throughput": 5169.3, "total_tokens": 22073344} {"current_steps": 5390, "total_steps": 6710, "loss": 0.1149, "lr": 2.3121457810398595e-07, "epoch": 4.016393442622951, "percentage": 80.33, "elapsed_time": "1:11:10", "remaining_time": "0:17:25", "throughput": 5169.31, "total_tokens": 22077440} {"current_steps": 5391, "total_steps": 6710, "loss": 0.0861, "lr": 2.3087558674881716e-07, "epoch": 4.017138599105812, "percentage": 80.34, "elapsed_time": "1:11:11", "remaining_time": "0:17:25", "throughput": 5169.32, "total_tokens": 22081536} {"current_steps": 5392, "total_steps": 6710, "loss": 0.1355, "lr": 2.3053681879299724e-07, "epoch": 4.017883755588674, "percentage": 80.36, "elapsed_time": "1:11:12", "remaining_time": "0:17:24", "throughput": 5169.34, "total_tokens": 22085632} {"current_steps": 5393, "total_steps": 6710, "loss": 0.1672, "lr": 2.3019827431078626e-07, "epoch": 4.018628912071535, "percentage": 80.37, "elapsed_time": "1:11:13", "remaining_time": "0:17:23", "throughput": 5169.35, "total_tokens": 22089728} {"current_steps": 5394, "total_steps": 6710, "loss": 0.0363, "lr": 2.2985995337639538e-07, "epoch": 4.019374068554397, "percentage": 80.39, "elapsed_time": "1:11:13", "remaining_time": "0:17:22", "throughput": 5169.36, "total_tokens": 22093824} {"current_steps": 5395, "total_steps": 6710, "loss": 0.0106, "lr": 2.295218560639874e-07, "epoch": 4.0201192250372575, "percentage": 80.4, "elapsed_time": "1:11:14", "remaining_time": "0:17:21", "throughput": 5169.37, "total_tokens": 22097920} {"current_steps": 5396, "total_steps": 6710, "loss": 0.0458, "lr": 2.2918398244767505e-07, "epoch": 4.020864381520119, "percentage": 80.42, "elapsed_time": "1:11:15", "remaining_time": "0:17:21", "throughput": 5169.38, "total_tokens": 22102016} {"current_steps": 5397, "total_steps": 6710, "loss": 0.0322, "lr": 2.2884633260152375e-07, "epoch": 4.021609538002981, "percentage": 80.43, "elapsed_time": "1:11:16", "remaining_time": "0:17:20", "throughput": 5169.39, "total_tokens": 22106112} {"current_steps": 5398, "total_steps": 6710, "loss": 0.0493, "lr": 2.285089065995473e-07, "epoch": 4.022354694485842, "percentage": 80.45, "elapsed_time": "1:11:17", "remaining_time": "0:17:19", "throughput": 5169.41, "total_tokens": 22110208} {"current_steps": 5399, "total_steps": 6710, "loss": 0.0958, "lr": 2.2817170451571307e-07, "epoch": 4.023099850968704, "percentage": 80.46, "elapsed_time": "1:11:17", "remaining_time": "0:17:18", "throughput": 5169.42, "total_tokens": 22114304} {"current_steps": 5400, "total_steps": 6710, "loss": 0.0479, "lr": 2.2783472642393736e-07, "epoch": 4.023845007451565, "percentage": 80.48, "elapsed_time": "1:11:18", "remaining_time": "0:17:17", "throughput": 5169.43, "total_tokens": 22118400} {"current_steps": 5401, "total_steps": 6710, "loss": 0.0621, "lr": 2.2749797239808886e-07, "epoch": 4.024590163934426, "percentage": 80.49, "elapsed_time": "1:11:19", "remaining_time": "0:17:17", "throughput": 5169.45, "total_tokens": 22122496} {"current_steps": 5402, "total_steps": 6710, "loss": 0.0729, "lr": 2.2716144251198572e-07, "epoch": 4.0253353204172875, "percentage": 80.51, "elapsed_time": "1:11:20", "remaining_time": "0:17:16", "throughput": 5169.46, "total_tokens": 22126592} {"current_steps": 5403, "total_steps": 6710, "loss": 0.093, "lr": 2.2682513683939852e-07, "epoch": 4.026080476900149, "percentage": 80.52, "elapsed_time": "1:11:21", "remaining_time": "0:17:15", "throughput": 5169.47, "total_tokens": 22130688} {"current_steps": 5404, "total_steps": 6710, "loss": 0.0193, "lr": 2.2648905545404735e-07, "epoch": 4.026825633383011, "percentage": 80.54, "elapsed_time": "1:11:21", "remaining_time": "0:17:14", "throughput": 5169.47, "total_tokens": 22134784} {"current_steps": 5405, "total_steps": 6710, "loss": 0.0189, "lr": 2.2615319842960352e-07, "epoch": 4.027570789865872, "percentage": 80.55, "elapsed_time": "1:11:22", "remaining_time": "0:17:14", "throughput": 5169.48, "total_tokens": 22138880} {"current_steps": 5406, "total_steps": 6710, "loss": 0.0587, "lr": 2.258175658396898e-07, "epoch": 4.028315946348733, "percentage": 80.57, "elapsed_time": "1:11:23", "remaining_time": "0:17:13", "throughput": 5169.49, "total_tokens": 22142976} {"current_steps": 5407, "total_steps": 6710, "loss": 0.0813, "lr": 2.2548215775787862e-07, "epoch": 4.029061102831594, "percentage": 80.58, "elapsed_time": "1:11:24", "remaining_time": "0:17:12", "throughput": 5169.5, "total_tokens": 22147072} {"current_steps": 5408, "total_steps": 6710, "loss": 0.0988, "lr": 2.2514697425769448e-07, "epoch": 4.029806259314456, "percentage": 80.6, "elapsed_time": "1:11:24", "remaining_time": "0:17:11", "throughput": 5169.52, "total_tokens": 22151168} {"current_steps": 5409, "total_steps": 6710, "loss": 0.1126, "lr": 2.2481201541261142e-07, "epoch": 4.0305514157973175, "percentage": 80.61, "elapsed_time": "1:11:25", "remaining_time": "0:17:10", "throughput": 5169.53, "total_tokens": 22155264} {"current_steps": 5410, "total_steps": 6710, "loss": 0.0592, "lr": 2.2447728129605564e-07, "epoch": 4.031296572280179, "percentage": 80.63, "elapsed_time": "1:11:26", "remaining_time": "0:17:10", "throughput": 5169.55, "total_tokens": 22159360} {"current_steps": 5411, "total_steps": 6710, "loss": 0.1205, "lr": 2.241427719814021e-07, "epoch": 4.032041728763041, "percentage": 80.64, "elapsed_time": "1:11:27", "remaining_time": "0:17:09", "throughput": 5169.56, "total_tokens": 22163456} {"current_steps": 5412, "total_steps": 6710, "loss": 0.0662, "lr": 2.2380848754197854e-07, "epoch": 4.032786885245901, "percentage": 80.66, "elapsed_time": "1:11:28", "remaining_time": "0:17:08", "throughput": 5169.57, "total_tokens": 22167552} {"current_steps": 5413, "total_steps": 6710, "loss": 0.0725, "lr": 2.2347442805106216e-07, "epoch": 4.033532041728763, "percentage": 80.67, "elapsed_time": "1:11:28", "remaining_time": "0:17:07", "throughput": 5169.59, "total_tokens": 22171648} {"current_steps": 5414, "total_steps": 6710, "loss": 0.0439, "lr": 2.2314059358188088e-07, "epoch": 4.034277198211624, "percentage": 80.69, "elapsed_time": "1:11:29", "remaining_time": "0:17:06", "throughput": 5169.6, "total_tokens": 22175744} {"current_steps": 5415, "total_steps": 6710, "loss": 0.0809, "lr": 2.228069842076143e-07, "epoch": 4.035022354694486, "percentage": 80.7, "elapsed_time": "1:11:30", "remaining_time": "0:17:06", "throughput": 5169.61, "total_tokens": 22179840} {"current_steps": 5416, "total_steps": 6710, "loss": 0.0298, "lr": 2.2247360000139121e-07, "epoch": 4.0357675111773474, "percentage": 80.72, "elapsed_time": "1:11:31", "remaining_time": "0:17:05", "throughput": 5169.62, "total_tokens": 22183936} {"current_steps": 5417, "total_steps": 6710, "loss": 0.0163, "lr": 2.221404410362925e-07, "epoch": 4.036512667660209, "percentage": 80.73, "elapsed_time": "1:11:31", "remaining_time": "0:17:04", "throughput": 5169.63, "total_tokens": 22188032} {"current_steps": 5418, "total_steps": 6710, "loss": 0.0908, "lr": 2.2180750738534846e-07, "epoch": 4.03725782414307, "percentage": 80.75, "elapsed_time": "1:11:32", "remaining_time": "0:17:03", "throughput": 5169.65, "total_tokens": 22192128} {"current_steps": 5419, "total_steps": 6710, "loss": 0.0932, "lr": 2.214747991215409e-07, "epoch": 4.038002980625931, "percentage": 80.76, "elapsed_time": "1:11:33", "remaining_time": "0:17:02", "throughput": 5169.66, "total_tokens": 22196224} {"current_steps": 5420, "total_steps": 6710, "loss": 0.0324, "lr": 2.2114231631780156e-07, "epoch": 4.038748137108793, "percentage": 80.77, "elapsed_time": "1:11:34", "remaining_time": "0:17:02", "throughput": 5169.67, "total_tokens": 22200320} {"current_steps": 5421, "total_steps": 6710, "loss": 0.0929, "lr": 2.2081005904701343e-07, "epoch": 4.039493293591654, "percentage": 80.79, "elapsed_time": "1:11:35", "remaining_time": "0:17:01", "throughput": 5169.68, "total_tokens": 22204416} {"current_steps": 5422, "total_steps": 6710, "loss": 0.0455, "lr": 2.204780273820094e-07, "epoch": 4.040238450074516, "percentage": 80.8, "elapsed_time": "1:11:35", "remaining_time": "0:17:00", "throughput": 5169.7, "total_tokens": 22208512} {"current_steps": 5423, "total_steps": 6710, "loss": 0.1512, "lr": 2.2014622139557296e-07, "epoch": 4.040983606557377, "percentage": 80.82, "elapsed_time": "1:11:36", "remaining_time": "0:16:59", "throughput": 5169.71, "total_tokens": 22212608} {"current_steps": 5424, "total_steps": 6710, "loss": 0.1047, "lr": 2.198146411604392e-07, "epoch": 4.041728763040238, "percentage": 80.83, "elapsed_time": "1:11:37", "remaining_time": "0:16:58", "throughput": 5169.72, "total_tokens": 22216704} {"current_steps": 5425, "total_steps": 6710, "loss": 0.0841, "lr": 2.1948328674929158e-07, "epoch": 4.0424739195231, "percentage": 80.85, "elapsed_time": "1:11:38", "remaining_time": "0:16:58", "throughput": 5169.73, "total_tokens": 22220800} {"current_steps": 5426, "total_steps": 6710, "loss": 0.0681, "lr": 2.1915215823476637e-07, "epoch": 4.043219076005961, "percentage": 80.86, "elapsed_time": "1:11:39", "remaining_time": "0:16:57", "throughput": 5169.75, "total_tokens": 22224896} {"current_steps": 5427, "total_steps": 6710, "loss": 0.2161, "lr": 2.1882125568944882e-07, "epoch": 4.043964232488823, "percentage": 80.88, "elapsed_time": "1:11:39", "remaining_time": "0:16:56", "throughput": 5169.76, "total_tokens": 22228992} {"current_steps": 5428, "total_steps": 6710, "loss": 0.0724, "lr": 2.1849057918587545e-07, "epoch": 4.044709388971684, "percentage": 80.89, "elapsed_time": "1:11:40", "remaining_time": "0:16:55", "throughput": 5169.77, "total_tokens": 22233088} {"current_steps": 5429, "total_steps": 6710, "loss": 0.12, "lr": 2.181601287965325e-07, "epoch": 4.045454545454546, "percentage": 80.91, "elapsed_time": "1:11:41", "remaining_time": "0:16:54", "throughput": 5169.78, "total_tokens": 22237184} {"current_steps": 5430, "total_steps": 6710, "loss": 0.0846, "lr": 2.178299045938577e-07, "epoch": 4.0461997019374065, "percentage": 80.92, "elapsed_time": "1:11:42", "remaining_time": "0:16:54", "throughput": 5169.8, "total_tokens": 22241280} {"current_steps": 5431, "total_steps": 6710, "loss": 0.0983, "lr": 2.1749990665023812e-07, "epoch": 4.046944858420268, "percentage": 80.94, "elapsed_time": "1:11:42", "remaining_time": "0:16:53", "throughput": 5169.81, "total_tokens": 22245376} {"current_steps": 5432, "total_steps": 6710, "loss": 0.0403, "lr": 2.1717013503801134e-07, "epoch": 4.04769001490313, "percentage": 80.95, "elapsed_time": "1:11:43", "remaining_time": "0:16:52", "throughput": 5169.82, "total_tokens": 22249472} {"current_steps": 5433, "total_steps": 6710, "loss": 0.1586, "lr": 2.1684058982946635e-07, "epoch": 4.048435171385991, "percentage": 80.97, "elapsed_time": "1:11:44", "remaining_time": "0:16:51", "throughput": 5169.84, "total_tokens": 22253568} {"current_steps": 5434, "total_steps": 6710, "loss": 0.1643, "lr": 2.1651127109684117e-07, "epoch": 4.049180327868853, "percentage": 80.98, "elapsed_time": "1:11:45", "remaining_time": "0:16:50", "throughput": 5169.85, "total_tokens": 22257664} {"current_steps": 5435, "total_steps": 6710, "loss": 0.1109, "lr": 2.1618217891232556e-07, "epoch": 4.049925484351714, "percentage": 81.0, "elapsed_time": "1:11:46", "remaining_time": "0:16:50", "throughput": 5169.86, "total_tokens": 22261760} {"current_steps": 5436, "total_steps": 6710, "loss": 0.0985, "lr": 2.1585331334805808e-07, "epoch": 4.050670640834575, "percentage": 81.01, "elapsed_time": "1:11:46", "remaining_time": "0:16:49", "throughput": 5169.87, "total_tokens": 22265856} {"current_steps": 5437, "total_steps": 6710, "loss": 0.1703, "lr": 2.155246744761294e-07, "epoch": 4.0514157973174365, "percentage": 81.03, "elapsed_time": "1:11:47", "remaining_time": "0:16:48", "throughput": 5169.89, "total_tokens": 22269952} {"current_steps": 5438, "total_steps": 6710, "loss": 0.0541, "lr": 2.1519626236857827e-07, "epoch": 4.052160953800298, "percentage": 81.04, "elapsed_time": "1:11:48", "remaining_time": "0:16:47", "throughput": 5169.9, "total_tokens": 22274048} {"current_steps": 5439, "total_steps": 6710, "loss": 0.1487, "lr": 2.1486807709739585e-07, "epoch": 4.05290611028316, "percentage": 81.06, "elapsed_time": "1:11:49", "remaining_time": "0:16:46", "throughput": 5169.92, "total_tokens": 22278144} {"current_steps": 5440, "total_steps": 6710, "loss": 0.1238, "lr": 2.145401187345221e-07, "epoch": 4.053651266766021, "percentage": 81.07, "elapsed_time": "1:11:49", "remaining_time": "0:16:46", "throughput": 5169.93, "total_tokens": 22282240} {"current_steps": 5441, "total_steps": 6710, "loss": 0.0305, "lr": 2.1421238735184855e-07, "epoch": 4.054396423248882, "percentage": 81.09, "elapsed_time": "1:11:50", "remaining_time": "0:16:45", "throughput": 5169.94, "total_tokens": 22286336} {"current_steps": 5442, "total_steps": 6710, "loss": 0.0785, "lr": 2.138848830212159e-07, "epoch": 4.055141579731743, "percentage": 81.1, "elapsed_time": "1:11:51", "remaining_time": "0:16:44", "throughput": 5169.95, "total_tokens": 22290432} {"current_steps": 5443, "total_steps": 6710, "loss": 0.1237, "lr": 2.1355760581441496e-07, "epoch": 4.055886736214605, "percentage": 81.12, "elapsed_time": "1:11:52", "remaining_time": "0:16:43", "throughput": 5169.97, "total_tokens": 22294528} {"current_steps": 5444, "total_steps": 6710, "loss": 0.1064, "lr": 2.1323055580318815e-07, "epoch": 4.0566318926974665, "percentage": 81.13, "elapsed_time": "1:11:53", "remaining_time": "0:16:43", "throughput": 5169.98, "total_tokens": 22298624} {"current_steps": 5445, "total_steps": 6710, "loss": 0.1668, "lr": 2.1290373305922637e-07, "epoch": 4.057377049180328, "percentage": 81.15, "elapsed_time": "1:11:53", "remaining_time": "0:16:42", "throughput": 5169.99, "total_tokens": 22302720} {"current_steps": 5446, "total_steps": 6710, "loss": 0.1343, "lr": 2.1257713765417215e-07, "epoch": 4.05812220566319, "percentage": 81.16, "elapsed_time": "1:11:54", "remaining_time": "0:16:41", "throughput": 5170.01, "total_tokens": 22306816} {"current_steps": 5447, "total_steps": 6710, "loss": 0.1029, "lr": 2.1225076965961682e-07, "epoch": 4.05886736214605, "percentage": 81.18, "elapsed_time": "1:11:55", "remaining_time": "0:16:40", "throughput": 5170.02, "total_tokens": 22310912} {"current_steps": 5448, "total_steps": 6710, "loss": 0.2669, "lr": 2.1192462914710333e-07, "epoch": 4.059612518628912, "percentage": 81.19, "elapsed_time": "1:11:56", "remaining_time": "0:16:39", "throughput": 5170.04, "total_tokens": 22315008} {"current_steps": 5449, "total_steps": 6710, "loss": 0.0393, "lr": 2.115987161881236e-07, "epoch": 4.060357675111773, "percentage": 81.21, "elapsed_time": "1:11:57", "remaining_time": "0:16:39", "throughput": 5169.58, "total_tokens": 22319104} {"current_steps": 5450, "total_steps": 6710, "loss": 0.0251, "lr": 2.1127303085411985e-07, "epoch": 4.061102831594635, "percentage": 81.22, "elapsed_time": "1:11:58", "remaining_time": "0:16:38", "throughput": 5169.6, "total_tokens": 22323200} {"current_steps": 5451, "total_steps": 6710, "loss": 0.0493, "lr": 2.109475732164856e-07, "epoch": 4.0618479880774965, "percentage": 81.24, "elapsed_time": "1:11:58", "remaining_time": "0:16:37", "throughput": 5169.6, "total_tokens": 22327296} {"current_steps": 5452, "total_steps": 6710, "loss": 0.0724, "lr": 2.106223433465622e-07, "epoch": 4.062593144560358, "percentage": 81.25, "elapsed_time": "1:11:59", "remaining_time": "0:16:36", "throughput": 5169.59, "total_tokens": 22331392} {"current_steps": 5453, "total_steps": 6710, "loss": 0.0649, "lr": 2.102973413156431e-07, "epoch": 4.063338301043219, "percentage": 81.27, "elapsed_time": "1:12:00", "remaining_time": "0:16:35", "throughput": 5169.6, "total_tokens": 22335488} {"current_steps": 5454, "total_steps": 6710, "loss": 0.0434, "lr": 2.099725671949708e-07, "epoch": 4.06408345752608, "percentage": 81.28, "elapsed_time": "1:12:01", "remaining_time": "0:16:35", "throughput": 5169.61, "total_tokens": 22339584} {"current_steps": 5455, "total_steps": 6710, "loss": 0.0501, "lr": 2.0964802105573847e-07, "epoch": 4.064828614008942, "percentage": 81.3, "elapsed_time": "1:12:02", "remaining_time": "0:16:34", "throughput": 5169.62, "total_tokens": 22343680} {"current_steps": 5456, "total_steps": 6710, "loss": 0.1004, "lr": 2.093237029690884e-07, "epoch": 4.065573770491803, "percentage": 81.31, "elapsed_time": "1:12:02", "remaining_time": "0:16:33", "throughput": 5169.62, "total_tokens": 22347776} {"current_steps": 5457, "total_steps": 6710, "loss": 0.0243, "lr": 2.0899961300611394e-07, "epoch": 4.066318926974665, "percentage": 81.33, "elapsed_time": "1:12:03", "remaining_time": "0:16:32", "throughput": 5169.63, "total_tokens": 22351872} {"current_steps": 5458, "total_steps": 6710, "loss": 0.0631, "lr": 2.0867575123785774e-07, "epoch": 4.0670640834575265, "percentage": 81.34, "elapsed_time": "1:12:04", "remaining_time": "0:16:31", "throughput": 5169.64, "total_tokens": 22355968} {"current_steps": 5459, "total_steps": 6710, "loss": 0.0234, "lr": 2.0835211773531233e-07, "epoch": 4.067809239940387, "percentage": 81.36, "elapsed_time": "1:12:05", "remaining_time": "0:16:31", "throughput": 5169.66, "total_tokens": 22360064} {"current_steps": 5460, "total_steps": 6710, "loss": 0.0102, "lr": 2.0802871256942108e-07, "epoch": 4.068554396423249, "percentage": 81.37, "elapsed_time": "1:12:06", "remaining_time": "0:16:30", "throughput": 5169.67, "total_tokens": 22364160} {"current_steps": 5461, "total_steps": 6710, "loss": 0.0996, "lr": 2.0770553581107606e-07, "epoch": 4.06929955290611, "percentage": 81.39, "elapsed_time": "1:12:06", "remaining_time": "0:16:29", "throughput": 5169.68, "total_tokens": 22368256} {"current_steps": 5462, "total_steps": 6710, "loss": 0.2122, "lr": 2.0738258753112056e-07, "epoch": 4.070044709388972, "percentage": 81.4, "elapsed_time": "1:12:07", "remaining_time": "0:16:28", "throughput": 5169.69, "total_tokens": 22372352} {"current_steps": 5463, "total_steps": 6710, "loss": 0.0625, "lr": 2.0705986780034645e-07, "epoch": 4.070789865871833, "percentage": 81.42, "elapsed_time": "1:12:08", "remaining_time": "0:16:28", "throughput": 5169.7, "total_tokens": 22376448} {"current_steps": 5464, "total_steps": 6710, "loss": 0.0827, "lr": 2.0673737668949728e-07, "epoch": 4.071535022354695, "percentage": 81.43, "elapsed_time": "1:12:09", "remaining_time": "0:16:27", "throughput": 5169.72, "total_tokens": 22380544} {"current_steps": 5465, "total_steps": 6710, "loss": 0.0769, "lr": 2.06415114269264e-07, "epoch": 4.0722801788375556, "percentage": 81.45, "elapsed_time": "1:12:09", "remaining_time": "0:16:26", "throughput": 5169.73, "total_tokens": 22384640} {"current_steps": 5466, "total_steps": 6710, "loss": 0.0499, "lr": 2.0609308061028982e-07, "epoch": 4.073025335320417, "percentage": 81.46, "elapsed_time": "1:12:10", "remaining_time": "0:16:25", "throughput": 5169.74, "total_tokens": 22388736} {"current_steps": 5467, "total_steps": 6710, "loss": 0.0521, "lr": 2.0577127578316633e-07, "epoch": 4.073770491803279, "percentage": 81.48, "elapsed_time": "1:12:11", "remaining_time": "0:16:24", "throughput": 5169.75, "total_tokens": 22392832} {"current_steps": 5468, "total_steps": 6710, "loss": 0.0418, "lr": 2.0544969985843586e-07, "epoch": 4.07451564828614, "percentage": 81.49, "elapsed_time": "1:12:12", "remaining_time": "0:16:24", "throughput": 5169.76, "total_tokens": 22396928} {"current_steps": 5469, "total_steps": 6710, "loss": 0.0744, "lr": 2.0512835290658991e-07, "epoch": 4.075260804769002, "percentage": 81.51, "elapsed_time": "1:12:13", "remaining_time": "0:16:23", "throughput": 5169.78, "total_tokens": 22401024} {"current_steps": 5470, "total_steps": 6710, "loss": 0.038, "lr": 2.0480723499806995e-07, "epoch": 4.076005961251863, "percentage": 81.52, "elapsed_time": "1:12:13", "remaining_time": "0:16:22", "throughput": 5169.79, "total_tokens": 22405120} {"current_steps": 5471, "total_steps": 6710, "loss": 0.0244, "lr": 2.0448634620326756e-07, "epoch": 4.076751117734724, "percentage": 81.54, "elapsed_time": "1:12:14", "remaining_time": "0:16:21", "throughput": 5169.79, "total_tokens": 22409216} {"current_steps": 5472, "total_steps": 6710, "loss": 0.1464, "lr": 2.0416568659252345e-07, "epoch": 4.0774962742175855, "percentage": 81.55, "elapsed_time": "1:12:15", "remaining_time": "0:16:20", "throughput": 5169.8, "total_tokens": 22413312} {"current_steps": 5473, "total_steps": 6710, "loss": 0.0832, "lr": 2.03845256236129e-07, "epoch": 4.078241430700447, "percentage": 81.56, "elapsed_time": "1:12:16", "remaining_time": "0:16:20", "throughput": 5169.81, "total_tokens": 22417408} {"current_steps": 5474, "total_steps": 6710, "loss": 0.1406, "lr": 2.0352505520432442e-07, "epoch": 4.078986587183309, "percentage": 81.58, "elapsed_time": "1:12:16", "remaining_time": "0:16:19", "throughput": 5169.82, "total_tokens": 22421504} {"current_steps": 5475, "total_steps": 6710, "loss": 0.0214, "lr": 2.0320508356730038e-07, "epoch": 4.07973174366617, "percentage": 81.59, "elapsed_time": "1:12:17", "remaining_time": "0:16:18", "throughput": 5169.83, "total_tokens": 22425600} {"current_steps": 5476, "total_steps": 6710, "loss": 0.2617, "lr": 2.02885341395197e-07, "epoch": 4.080476900149031, "percentage": 81.61, "elapsed_time": "1:12:18", "remaining_time": "0:16:17", "throughput": 5169.85, "total_tokens": 22429696} {"current_steps": 5477, "total_steps": 6710, "loss": 0.0628, "lr": 2.0256582875810338e-07, "epoch": 4.081222056631892, "percentage": 81.62, "elapsed_time": "1:12:19", "remaining_time": "0:16:16", "throughput": 5169.86, "total_tokens": 22433792} {"current_steps": 5478, "total_steps": 6710, "loss": 0.0263, "lr": 2.0224654572606014e-07, "epoch": 4.081967213114754, "percentage": 81.64, "elapsed_time": "1:12:20", "remaining_time": "0:16:16", "throughput": 5169.87, "total_tokens": 22437888} {"current_steps": 5479, "total_steps": 6710, "loss": 0.0169, "lr": 2.0192749236905508e-07, "epoch": 4.0827123695976155, "percentage": 81.65, "elapsed_time": "1:12:20", "remaining_time": "0:16:15", "throughput": 5169.88, "total_tokens": 22441984} {"current_steps": 5480, "total_steps": 6710, "loss": 0.112, "lr": 2.016086687570279e-07, "epoch": 4.083457526080477, "percentage": 81.67, "elapsed_time": "1:12:21", "remaining_time": "0:16:14", "throughput": 5169.89, "total_tokens": 22446080} {"current_steps": 5481, "total_steps": 6710, "loss": 0.0313, "lr": 2.0129007495986647e-07, "epoch": 4.084202682563339, "percentage": 81.68, "elapsed_time": "1:12:22", "remaining_time": "0:16:13", "throughput": 5169.91, "total_tokens": 22450176} {"current_steps": 5482, "total_steps": 6710, "loss": 0.1986, "lr": 2.0097171104740922e-07, "epoch": 4.084947839046199, "percentage": 81.7, "elapsed_time": "1:12:23", "remaining_time": "0:16:12", "throughput": 5169.92, "total_tokens": 22454272} {"current_steps": 5483, "total_steps": 6710, "loss": 0.0694, "lr": 2.0065357708944342e-07, "epoch": 4.085692995529061, "percentage": 81.71, "elapsed_time": "1:12:24", "remaining_time": "0:16:12", "throughput": 5169.93, "total_tokens": 22458368} {"current_steps": 5484, "total_steps": 6710, "loss": 0.1424, "lr": 2.0033567315570684e-07, "epoch": 4.086438152011922, "percentage": 81.73, "elapsed_time": "1:12:24", "remaining_time": "0:16:11", "throughput": 5169.94, "total_tokens": 22462464} {"current_steps": 5485, "total_steps": 6710, "loss": 0.0622, "lr": 2.00017999315886e-07, "epoch": 4.087183308494784, "percentage": 81.74, "elapsed_time": "1:12:25", "remaining_time": "0:16:10", "throughput": 5169.95, "total_tokens": 22466560} {"current_steps": 5486, "total_steps": 6710, "loss": 0.0753, "lr": 1.9970055563961686e-07, "epoch": 4.0879284649776455, "percentage": 81.76, "elapsed_time": "1:12:26", "remaining_time": "0:16:09", "throughput": 5169.96, "total_tokens": 22470656} {"current_steps": 5487, "total_steps": 6710, "loss": 0.1298, "lr": 1.9938334219648608e-07, "epoch": 4.088673621460507, "percentage": 81.77, "elapsed_time": "1:12:27", "remaining_time": "0:16:08", "throughput": 5169.97, "total_tokens": 22474752} {"current_steps": 5488, "total_steps": 6710, "loss": 0.0343, "lr": 1.990663590560285e-07, "epoch": 4.089418777943368, "percentage": 81.79, "elapsed_time": "1:12:27", "remaining_time": "0:16:08", "throughput": 5169.99, "total_tokens": 22478848} {"current_steps": 5489, "total_steps": 6710, "loss": 0.0863, "lr": 1.9874960628772963e-07, "epoch": 4.090163934426229, "percentage": 81.8, "elapsed_time": "1:12:28", "remaining_time": "0:16:07", "throughput": 5169.99, "total_tokens": 22482944} {"current_steps": 5490, "total_steps": 6710, "loss": 0.0975, "lr": 1.9843308396102338e-07, "epoch": 4.090909090909091, "percentage": 81.82, "elapsed_time": "1:12:29", "remaining_time": "0:16:06", "throughput": 5170.0, "total_tokens": 22487040} {"current_steps": 5491, "total_steps": 6710, "loss": 0.0647, "lr": 1.9811679214529464e-07, "epoch": 4.091654247391952, "percentage": 81.83, "elapsed_time": "1:12:30", "remaining_time": "0:16:05", "throughput": 5170.0, "total_tokens": 22491136} {"current_steps": 5492, "total_steps": 6710, "loss": 0.1384, "lr": 1.9780073090987547e-07, "epoch": 4.092399403874814, "percentage": 81.85, "elapsed_time": "1:12:31", "remaining_time": "0:16:04", "throughput": 5170.02, "total_tokens": 22495232} {"current_steps": 5493, "total_steps": 6710, "loss": 0.0699, "lr": 1.9748490032404977e-07, "epoch": 4.0931445603576755, "percentage": 81.86, "elapsed_time": "1:12:31", "remaining_time": "0:16:04", "throughput": 5170.03, "total_tokens": 22499328} {"current_steps": 5494, "total_steps": 6710, "loss": 0.077, "lr": 1.9716930045704922e-07, "epoch": 4.093889716840536, "percentage": 81.88, "elapsed_time": "1:12:32", "remaining_time": "0:16:03", "throughput": 5170.04, "total_tokens": 22503424} {"current_steps": 5495, "total_steps": 6710, "loss": 0.0174, "lr": 1.9685393137805625e-07, "epoch": 4.094634873323398, "percentage": 81.89, "elapsed_time": "1:12:33", "remaining_time": "0:16:02", "throughput": 5170.05, "total_tokens": 22507520} {"current_steps": 5496, "total_steps": 6710, "loss": 0.0957, "lr": 1.965387931562017e-07, "epoch": 4.095380029806259, "percentage": 81.91, "elapsed_time": "1:12:34", "remaining_time": "0:16:01", "throughput": 5170.06, "total_tokens": 22511616} {"current_steps": 5497, "total_steps": 6710, "loss": 0.0618, "lr": 1.962238858605657e-07, "epoch": 4.096125186289121, "percentage": 81.92, "elapsed_time": "1:12:35", "remaining_time": "0:16:01", "throughput": 5170.07, "total_tokens": 22515712} {"current_steps": 5498, "total_steps": 6710, "loss": 0.1136, "lr": 1.959092095601789e-07, "epoch": 4.096870342771982, "percentage": 81.94, "elapsed_time": "1:12:35", "remaining_time": "0:16:00", "throughput": 5170.08, "total_tokens": 22519808} {"current_steps": 5499, "total_steps": 6710, "loss": 0.08, "lr": 1.9559476432401998e-07, "epoch": 4.097615499254844, "percentage": 81.95, "elapsed_time": "1:12:36", "remaining_time": "0:15:59", "throughput": 5170.09, "total_tokens": 22523904} {"current_steps": 5500, "total_steps": 6710, "loss": 0.0926, "lr": 1.9528055022101797e-07, "epoch": 4.098360655737705, "percentage": 81.97, "elapsed_time": "1:12:37", "remaining_time": "0:15:58", "throughput": 5170.1, "total_tokens": 22528000} {"current_steps": 5501, "total_steps": 6710, "loss": 0.0554, "lr": 1.9496656732005057e-07, "epoch": 4.099105812220566, "percentage": 81.98, "elapsed_time": "1:12:38", "remaining_time": "0:15:57", "throughput": 5170.11, "total_tokens": 22532096} {"current_steps": 5502, "total_steps": 6710, "loss": 0.0808, "lr": 1.9465281568994548e-07, "epoch": 4.099850968703428, "percentage": 82.0, "elapsed_time": "1:12:38", "remaining_time": "0:15:57", "throughput": 5170.11, "total_tokens": 22536192} {"current_steps": 5503, "total_steps": 6710, "loss": 0.0599, "lr": 1.943392953994791e-07, "epoch": 4.100596125186289, "percentage": 82.01, "elapsed_time": "1:12:39", "remaining_time": "0:15:56", "throughput": 5170.12, "total_tokens": 22540288} {"current_steps": 5504, "total_steps": 6710, "loss": 0.0786, "lr": 1.9402600651737684e-07, "epoch": 4.101341281669151, "percentage": 82.03, "elapsed_time": "1:12:40", "remaining_time": "0:15:55", "throughput": 5170.12, "total_tokens": 22544384} {"current_steps": 5505, "total_steps": 6710, "loss": 0.1004, "lr": 1.9371294911231507e-07, "epoch": 4.102086438152012, "percentage": 82.04, "elapsed_time": "1:12:41", "remaining_time": "0:15:54", "throughput": 5170.12, "total_tokens": 22548480} {"current_steps": 5506, "total_steps": 6710, "loss": 0.0475, "lr": 1.934001232529166e-07, "epoch": 4.102831594634873, "percentage": 82.06, "elapsed_time": "1:12:42", "remaining_time": "0:15:53", "throughput": 5170.13, "total_tokens": 22552576} {"current_steps": 5507, "total_steps": 6710, "loss": 0.0786, "lr": 1.9308752900775633e-07, "epoch": 4.103576751117735, "percentage": 82.07, "elapsed_time": "1:12:42", "remaining_time": "0:15:53", "throughput": 5170.13, "total_tokens": 22556672} {"current_steps": 5508, "total_steps": 6710, "loss": 0.0564, "lr": 1.9277516644535642e-07, "epoch": 4.104321907600596, "percentage": 82.09, "elapsed_time": "1:12:43", "remaining_time": "0:15:52", "throughput": 5170.14, "total_tokens": 22560768} {"current_steps": 5509, "total_steps": 6710, "loss": 0.1442, "lr": 1.9246303563418957e-07, "epoch": 4.105067064083458, "percentage": 82.1, "elapsed_time": "1:12:44", "remaining_time": "0:15:51", "throughput": 5170.15, "total_tokens": 22564864} {"current_steps": 5510, "total_steps": 6710, "loss": 0.0707, "lr": 1.9215113664267662e-07, "epoch": 4.105812220566319, "percentage": 82.12, "elapsed_time": "1:12:45", "remaining_time": "0:15:50", "throughput": 5170.16, "total_tokens": 22568960} {"current_steps": 5511, "total_steps": 6710, "loss": 0.062, "lr": 1.9183946953918841e-07, "epoch": 4.10655737704918, "percentage": 82.13, "elapsed_time": "1:12:46", "remaining_time": "0:15:49", "throughput": 5170.17, "total_tokens": 22573056} {"current_steps": 5512, "total_steps": 6710, "loss": 0.0256, "lr": 1.9152803439204407e-07, "epoch": 4.1073025335320414, "percentage": 82.15, "elapsed_time": "1:12:46", "remaining_time": "0:15:49", "throughput": 5170.18, "total_tokens": 22577152} {"current_steps": 5513, "total_steps": 6710, "loss": 0.1329, "lr": 1.9121683126951313e-07, "epoch": 4.108047690014903, "percentage": 82.16, "elapsed_time": "1:12:47", "remaining_time": "0:15:48", "throughput": 5170.19, "total_tokens": 22581248} {"current_steps": 5514, "total_steps": 6710, "loss": 0.077, "lr": 1.909058602398131e-07, "epoch": 4.1087928464977646, "percentage": 82.18, "elapsed_time": "1:12:48", "remaining_time": "0:15:47", "throughput": 5170.2, "total_tokens": 22585344} {"current_steps": 5515, "total_steps": 6710, "loss": 0.0205, "lr": 1.905951213711109e-07, "epoch": 4.109538002980626, "percentage": 82.19, "elapsed_time": "1:12:49", "remaining_time": "0:15:46", "throughput": 5170.21, "total_tokens": 22589440} {"current_steps": 5516, "total_steps": 6710, "loss": 0.053, "lr": 1.902846147315232e-07, "epoch": 4.110283159463488, "percentage": 82.21, "elapsed_time": "1:12:49", "remaining_time": "0:15:45", "throughput": 5170.22, "total_tokens": 22593536} {"current_steps": 5517, "total_steps": 6710, "loss": 0.048, "lr": 1.8997434038911467e-07, "epoch": 4.111028315946348, "percentage": 82.22, "elapsed_time": "1:12:51", "remaining_time": "0:15:45", "throughput": 5169.72, "total_tokens": 22597632} {"current_steps": 5518, "total_steps": 6710, "loss": 0.1012, "lr": 1.8966429841190057e-07, "epoch": 4.11177347242921, "percentage": 82.24, "elapsed_time": "1:12:51", "remaining_time": "0:15:44", "throughput": 5169.73, "total_tokens": 22601728} {"current_steps": 5519, "total_steps": 6710, "loss": 0.0862, "lr": 1.893544888678432e-07, "epoch": 4.112518628912071, "percentage": 82.25, "elapsed_time": "1:12:52", "remaining_time": "0:15:43", "throughput": 5169.74, "total_tokens": 22605824} {"current_steps": 5520, "total_steps": 6710, "loss": 0.0546, "lr": 1.890449118248558e-07, "epoch": 4.113263785394933, "percentage": 82.27, "elapsed_time": "1:12:53", "remaining_time": "0:15:42", "throughput": 5169.75, "total_tokens": 22609920} {"current_steps": 5521, "total_steps": 6710, "loss": 0.0824, "lr": 1.887355673507993e-07, "epoch": 4.1140089418777945, "percentage": 82.28, "elapsed_time": "1:12:54", "remaining_time": "0:15:42", "throughput": 5169.75, "total_tokens": 22614016} {"current_steps": 5522, "total_steps": 6710, "loss": 0.0594, "lr": 1.8842645551348488e-07, "epoch": 4.114754098360656, "percentage": 82.3, "elapsed_time": "1:12:55", "remaining_time": "0:15:41", "throughput": 5169.76, "total_tokens": 22618112} {"current_steps": 5523, "total_steps": 6710, "loss": 0.0765, "lr": 1.8811757638067168e-07, "epoch": 4.115499254843517, "percentage": 82.31, "elapsed_time": "1:12:55", "remaining_time": "0:15:40", "throughput": 5169.77, "total_tokens": 22622208} {"current_steps": 5524, "total_steps": 6710, "loss": 0.03, "lr": 1.8780893002006806e-07, "epoch": 4.116244411326378, "percentage": 82.32, "elapsed_time": "1:12:56", "remaining_time": "0:15:39", "throughput": 5169.78, "total_tokens": 22626304} {"current_steps": 5525, "total_steps": 6710, "loss": 0.1111, "lr": 1.8750051649933195e-07, "epoch": 4.11698956780924, "percentage": 82.34, "elapsed_time": "1:12:57", "remaining_time": "0:15:38", "throughput": 5169.79, "total_tokens": 22630400} {"current_steps": 5526, "total_steps": 6710, "loss": 0.0776, "lr": 1.871923358860693e-07, "epoch": 4.117734724292101, "percentage": 82.35, "elapsed_time": "1:12:58", "remaining_time": "0:15:38", "throughput": 5169.8, "total_tokens": 22634496} {"current_steps": 5527, "total_steps": 6710, "loss": 0.0546, "lr": 1.868843882478359e-07, "epoch": 4.118479880774963, "percentage": 82.37, "elapsed_time": "1:12:59", "remaining_time": "0:15:37", "throughput": 5169.81, "total_tokens": 22638592} {"current_steps": 5528, "total_steps": 6710, "loss": 0.102, "lr": 1.8657667365213572e-07, "epoch": 4.1192250372578245, "percentage": 82.38, "elapsed_time": "1:12:59", "remaining_time": "0:15:36", "throughput": 5169.81, "total_tokens": 22642688} {"current_steps": 5529, "total_steps": 6710, "loss": 0.0928, "lr": 1.8626919216642254e-07, "epoch": 4.119970193740685, "percentage": 82.4, "elapsed_time": "1:13:00", "remaining_time": "0:15:35", "throughput": 5169.81, "total_tokens": 22646784} {"current_steps": 5530, "total_steps": 6710, "loss": 0.2572, "lr": 1.85961943858098e-07, "epoch": 4.120715350223547, "percentage": 82.41, "elapsed_time": "1:13:01", "remaining_time": "0:15:34", "throughput": 5169.82, "total_tokens": 22650880} {"current_steps": 5531, "total_steps": 6710, "loss": 0.1033, "lr": 1.8565492879451307e-07, "epoch": 4.121460506706408, "percentage": 82.43, "elapsed_time": "1:13:02", "remaining_time": "0:15:34", "throughput": 5169.82, "total_tokens": 22654976} {"current_steps": 5532, "total_steps": 6710, "loss": 0.0449, "lr": 1.8534814704296813e-07, "epoch": 4.12220566318927, "percentage": 82.44, "elapsed_time": "1:13:02", "remaining_time": "0:15:33", "throughput": 5169.84, "total_tokens": 22659072} {"current_steps": 5533, "total_steps": 6710, "loss": 0.0836, "lr": 1.8504159867071173e-07, "epoch": 4.122950819672131, "percentage": 82.46, "elapsed_time": "1:13:03", "remaining_time": "0:15:32", "throughput": 5169.85, "total_tokens": 22663168} {"current_steps": 5534, "total_steps": 6710, "loss": 0.0346, "lr": 1.8473528374494135e-07, "epoch": 4.123695976154993, "percentage": 82.47, "elapsed_time": "1:13:04", "remaining_time": "0:15:31", "throughput": 5169.85, "total_tokens": 22667264} {"current_steps": 5535, "total_steps": 6710, "loss": 0.0647, "lr": 1.8442920233280314e-07, "epoch": 4.124441132637854, "percentage": 82.49, "elapsed_time": "1:13:05", "remaining_time": "0:15:30", "throughput": 5169.87, "total_tokens": 22671360} {"current_steps": 5536, "total_steps": 6710, "loss": 0.1356, "lr": 1.841233545013929e-07, "epoch": 4.125186289120715, "percentage": 82.5, "elapsed_time": "1:13:06", "remaining_time": "0:15:30", "throughput": 5169.88, "total_tokens": 22675456} {"current_steps": 5537, "total_steps": 6710, "loss": 0.0931, "lr": 1.8381774031775406e-07, "epoch": 4.125931445603577, "percentage": 82.52, "elapsed_time": "1:13:06", "remaining_time": "0:15:29", "throughput": 5169.89, "total_tokens": 22679552} {"current_steps": 5538, "total_steps": 6710, "loss": 0.1325, "lr": 1.8351235984888013e-07, "epoch": 4.126676602086438, "percentage": 82.53, "elapsed_time": "1:13:07", "remaining_time": "0:15:28", "throughput": 5169.89, "total_tokens": 22683648} {"current_steps": 5539, "total_steps": 6710, "loss": 0.1943, "lr": 1.83207213161712e-07, "epoch": 4.1274217585693, "percentage": 82.55, "elapsed_time": "1:13:08", "remaining_time": "0:15:27", "throughput": 5169.9, "total_tokens": 22687744} {"current_steps": 5540, "total_steps": 6710, "loss": 0.1024, "lr": 1.829023003231406e-07, "epoch": 4.128166915052161, "percentage": 82.56, "elapsed_time": "1:13:09", "remaining_time": "0:15:26", "throughput": 5169.91, "total_tokens": 22691840} {"current_steps": 5541, "total_steps": 6710, "loss": 0.0998, "lr": 1.8259762140000483e-07, "epoch": 4.128912071535022, "percentage": 82.58, "elapsed_time": "1:13:09", "remaining_time": "0:15:26", "throughput": 5169.92, "total_tokens": 22695936} {"current_steps": 5542, "total_steps": 6710, "loss": 0.1498, "lr": 1.8229317645909197e-07, "epoch": 4.129657228017884, "percentage": 82.59, "elapsed_time": "1:13:11", "remaining_time": "0:15:25", "throughput": 5169.58, "total_tokens": 22700032} {"current_steps": 5543, "total_steps": 6710, "loss": 0.074, "lr": 1.8198896556713934e-07, "epoch": 4.130402384500745, "percentage": 82.61, "elapsed_time": "1:13:11", "remaining_time": "0:15:24", "throughput": 5169.59, "total_tokens": 22704128} {"current_steps": 5544, "total_steps": 6710, "loss": 0.1001, "lr": 1.8168498879083132e-07, "epoch": 4.131147540983607, "percentage": 82.62, "elapsed_time": "1:13:12", "remaining_time": "0:15:23", "throughput": 5169.6, "total_tokens": 22708224} {"current_steps": 5545, "total_steps": 6710, "loss": 0.1424, "lr": 1.8138124619680286e-07, "epoch": 4.131892697466468, "percentage": 82.64, "elapsed_time": "1:13:13", "remaining_time": "0:15:23", "throughput": 5169.61, "total_tokens": 22712320} {"current_steps": 5546, "total_steps": 6710, "loss": 0.0704, "lr": 1.8107773785163528e-07, "epoch": 4.13263785394933, "percentage": 82.65, "elapsed_time": "1:13:14", "remaining_time": "0:15:22", "throughput": 5169.63, "total_tokens": 22716416} {"current_steps": 5547, "total_steps": 6710, "loss": 0.1157, "lr": 1.807744638218606e-07, "epoch": 4.1333830104321905, "percentage": 82.67, "elapsed_time": "1:13:14", "remaining_time": "0:15:21", "throughput": 5169.64, "total_tokens": 22720512} {"current_steps": 5548, "total_steps": 6710, "loss": 0.0116, "lr": 1.8047142417395815e-07, "epoch": 4.134128166915052, "percentage": 82.68, "elapsed_time": "1:13:15", "remaining_time": "0:15:20", "throughput": 5169.64, "total_tokens": 22724608} {"current_steps": 5549, "total_steps": 6710, "loss": 0.038, "lr": 1.8016861897435692e-07, "epoch": 4.134873323397914, "percentage": 82.7, "elapsed_time": "1:13:16", "remaining_time": "0:15:19", "throughput": 5169.66, "total_tokens": 22728704} {"current_steps": 5550, "total_steps": 6710, "loss": 0.0742, "lr": 1.7986604828943377e-07, "epoch": 4.135618479880775, "percentage": 82.71, "elapsed_time": "1:13:17", "remaining_time": "0:15:19", "throughput": 5169.67, "total_tokens": 22732800} {"current_steps": 5551, "total_steps": 6710, "loss": 0.123, "lr": 1.7956371218551387e-07, "epoch": 4.136363636363637, "percentage": 82.73, "elapsed_time": "1:13:18", "remaining_time": "0:15:18", "throughput": 5169.68, "total_tokens": 22736896} {"current_steps": 5552, "total_steps": 6710, "loss": 0.1477, "lr": 1.7926161072887208e-07, "epoch": 4.137108792846497, "percentage": 82.74, "elapsed_time": "1:13:18", "remaining_time": "0:15:17", "throughput": 5169.7, "total_tokens": 22740992} {"current_steps": 5553, "total_steps": 6710, "loss": 0.1877, "lr": 1.789597439857309e-07, "epoch": 4.137853949329359, "percentage": 82.76, "elapsed_time": "1:13:19", "remaining_time": "0:15:16", "throughput": 5169.71, "total_tokens": 22745088} {"current_steps": 5554, "total_steps": 6710, "loss": 0.0659, "lr": 1.786581120222619e-07, "epoch": 4.1385991058122205, "percentage": 82.77, "elapsed_time": "1:13:20", "remaining_time": "0:15:15", "throughput": 5169.73, "total_tokens": 22749184} {"current_steps": 5555, "total_steps": 6710, "loss": 0.0227, "lr": 1.783567149045845e-07, "epoch": 4.139344262295082, "percentage": 82.79, "elapsed_time": "1:13:21", "remaining_time": "0:15:15", "throughput": 5169.74, "total_tokens": 22753280} {"current_steps": 5556, "total_steps": 6710, "loss": 0.053, "lr": 1.7805555269876775e-07, "epoch": 4.140089418777944, "percentage": 82.8, "elapsed_time": "1:13:22", "remaining_time": "0:15:14", "throughput": 5169.76, "total_tokens": 22757376} {"current_steps": 5557, "total_steps": 6710, "loss": 0.1174, "lr": 1.7775462547082817e-07, "epoch": 4.140834575260805, "percentage": 82.82, "elapsed_time": "1:13:22", "remaining_time": "0:15:13", "throughput": 5169.77, "total_tokens": 22761472} {"current_steps": 5558, "total_steps": 6710, "loss": 0.055, "lr": 1.774539332867313e-07, "epoch": 4.141579731743666, "percentage": 82.83, "elapsed_time": "1:13:23", "remaining_time": "0:15:12", "throughput": 5169.78, "total_tokens": 22765568} {"current_steps": 5559, "total_steps": 6710, "loss": 0.0455, "lr": 1.7715347621239055e-07, "epoch": 4.142324888226527, "percentage": 82.85, "elapsed_time": "1:13:24", "remaining_time": "0:15:11", "throughput": 5169.8, "total_tokens": 22769664} {"current_steps": 5560, "total_steps": 6710, "loss": 0.0093, "lr": 1.768532543136689e-07, "epoch": 4.143070044709389, "percentage": 82.86, "elapsed_time": "1:13:25", "remaining_time": "0:15:11", "throughput": 5169.81, "total_tokens": 22773760} {"current_steps": 5561, "total_steps": 6710, "loss": 0.0663, "lr": 1.7655326765637692e-07, "epoch": 4.14381520119225, "percentage": 82.88, "elapsed_time": "1:13:25", "remaining_time": "0:15:10", "throughput": 5169.82, "total_tokens": 22777856} {"current_steps": 5562, "total_steps": 6710, "loss": 0.0743, "lr": 1.762535163062734e-07, "epoch": 4.144560357675112, "percentage": 82.89, "elapsed_time": "1:13:26", "remaining_time": "0:15:09", "throughput": 5169.84, "total_tokens": 22781952} {"current_steps": 5563, "total_steps": 6710, "loss": 0.1028, "lr": 1.7595400032906662e-07, "epoch": 4.1453055141579735, "percentage": 82.91, "elapsed_time": "1:13:27", "remaining_time": "0:15:08", "throughput": 5169.85, "total_tokens": 22786048} {"current_steps": 5564, "total_steps": 6710, "loss": 0.053, "lr": 1.756547197904121e-07, "epoch": 4.146050670640834, "percentage": 82.92, "elapsed_time": "1:13:28", "remaining_time": "0:15:07", "throughput": 5169.86, "total_tokens": 22790144} {"current_steps": 5565, "total_steps": 6710, "loss": 0.0037, "lr": 1.7535567475591487e-07, "epoch": 4.146795827123696, "percentage": 82.94, "elapsed_time": "1:13:29", "remaining_time": "0:15:07", "throughput": 5169.87, "total_tokens": 22794240} {"current_steps": 5566, "total_steps": 6710, "loss": 0.0818, "lr": 1.7505686529112707e-07, "epoch": 4.147540983606557, "percentage": 82.95, "elapsed_time": "1:13:29", "remaining_time": "0:15:06", "throughput": 5169.89, "total_tokens": 22798336} {"current_steps": 5567, "total_steps": 6710, "loss": 0.0555, "lr": 1.7475829146155032e-07, "epoch": 4.148286140089419, "percentage": 82.97, "elapsed_time": "1:13:30", "remaining_time": "0:15:05", "throughput": 5169.9, "total_tokens": 22802432} {"current_steps": 5568, "total_steps": 6710, "loss": 0.0326, "lr": 1.744599533326341e-07, "epoch": 4.14903129657228, "percentage": 82.98, "elapsed_time": "1:13:31", "remaining_time": "0:15:04", "throughput": 5169.91, "total_tokens": 22806528} {"current_steps": 5569, "total_steps": 6710, "loss": 0.077, "lr": 1.741618509697758e-07, "epoch": 4.149776453055142, "percentage": 83.0, "elapsed_time": "1:13:32", "remaining_time": "0:15:03", "throughput": 5169.92, "total_tokens": 22810624} {"current_steps": 5570, "total_steps": 6710, "loss": 0.0689, "lr": 1.7386398443832234e-07, "epoch": 4.150521609538003, "percentage": 83.01, "elapsed_time": "1:13:32", "remaining_time": "0:15:03", "throughput": 5169.93, "total_tokens": 22814720} {"current_steps": 5571, "total_steps": 6710, "loss": 0.0534, "lr": 1.7356635380356742e-07, "epoch": 4.151266766020864, "percentage": 83.03, "elapsed_time": "1:13:33", "remaining_time": "0:15:02", "throughput": 5169.95, "total_tokens": 22818816} {"current_steps": 5572, "total_steps": 6710, "loss": 0.0297, "lr": 1.7326895913075473e-07, "epoch": 4.152011922503726, "percentage": 83.04, "elapsed_time": "1:13:34", "remaining_time": "0:15:01", "throughput": 5169.96, "total_tokens": 22822912} {"current_steps": 5573, "total_steps": 6710, "loss": 0.0876, "lr": 1.729718004850743e-07, "epoch": 4.152757078986587, "percentage": 83.06, "elapsed_time": "1:13:35", "remaining_time": "0:15:00", "throughput": 5169.97, "total_tokens": 22827008} {"current_steps": 5574, "total_steps": 6710, "loss": 0.0353, "lr": 1.7267487793166602e-07, "epoch": 4.153502235469449, "percentage": 83.07, "elapsed_time": "1:13:36", "remaining_time": "0:15:00", "throughput": 5169.99, "total_tokens": 22831104} {"current_steps": 5575, "total_steps": 6710, "loss": 0.2736, "lr": 1.723781915356171e-07, "epoch": 4.15424739195231, "percentage": 83.08, "elapsed_time": "1:13:36", "remaining_time": "0:14:59", "throughput": 5169.99, "total_tokens": 22835200} {"current_steps": 5576, "total_steps": 6710, "loss": 0.1126, "lr": 1.7208174136196368e-07, "epoch": 4.154992548435171, "percentage": 83.1, "elapsed_time": "1:13:37", "remaining_time": "0:14:58", "throughput": 5170.01, "total_tokens": 22839296} {"current_steps": 5577, "total_steps": 6710, "loss": 0.0555, "lr": 1.7178552747568966e-07, "epoch": 4.155737704918033, "percentage": 83.11, "elapsed_time": "1:13:38", "remaining_time": "0:14:57", "throughput": 5170.02, "total_tokens": 22843392} {"current_steps": 5578, "total_steps": 6710, "loss": 0.0834, "lr": 1.7148954994172685e-07, "epoch": 4.156482861400894, "percentage": 83.13, "elapsed_time": "1:13:39", "remaining_time": "0:14:56", "throughput": 5170.03, "total_tokens": 22847488} {"current_steps": 5579, "total_steps": 6710, "loss": 0.0161, "lr": 1.7119380882495623e-07, "epoch": 4.157228017883756, "percentage": 83.14, "elapsed_time": "1:13:40", "remaining_time": "0:14:56", "throughput": 5170.04, "total_tokens": 22851584} {"current_steps": 5580, "total_steps": 6710, "loss": 0.0606, "lr": 1.7089830419020584e-07, "epoch": 4.157973174366617, "percentage": 83.16, "elapsed_time": "1:13:40", "remaining_time": "0:14:55", "throughput": 5170.06, "total_tokens": 22855680} {"current_steps": 5581, "total_steps": 6710, "loss": 0.0362, "lr": 1.7060303610225287e-07, "epoch": 4.158718330849478, "percentage": 83.17, "elapsed_time": "1:13:41", "remaining_time": "0:14:54", "throughput": 5170.07, "total_tokens": 22859776} {"current_steps": 5582, "total_steps": 6710, "loss": 0.045, "lr": 1.7030800462582167e-07, "epoch": 4.1594634873323395, "percentage": 83.19, "elapsed_time": "1:13:42", "remaining_time": "0:14:53", "throughput": 5170.08, "total_tokens": 22863872} {"current_steps": 5583, "total_steps": 6710, "loss": 0.0587, "lr": 1.7001320982558577e-07, "epoch": 4.160208643815201, "percentage": 83.2, "elapsed_time": "1:13:43", "remaining_time": "0:14:52", "throughput": 5170.1, "total_tokens": 22867968} {"current_steps": 5584, "total_steps": 6710, "loss": 0.1417, "lr": 1.6971865176616615e-07, "epoch": 4.160953800298063, "percentage": 83.22, "elapsed_time": "1:13:43", "remaining_time": "0:14:52", "throughput": 5170.11, "total_tokens": 22872064} {"current_steps": 5585, "total_steps": 6710, "loss": 0.0481, "lr": 1.6942433051213208e-07, "epoch": 4.161698956780924, "percentage": 83.23, "elapsed_time": "1:13:44", "remaining_time": "0:14:51", "throughput": 5170.13, "total_tokens": 22876160} {"current_steps": 5586, "total_steps": 6710, "loss": 0.0159, "lr": 1.6913024612800034e-07, "epoch": 4.162444113263786, "percentage": 83.25, "elapsed_time": "1:13:45", "remaining_time": "0:14:50", "throughput": 5170.14, "total_tokens": 22880256} {"current_steps": 5587, "total_steps": 6710, "loss": 0.03, "lr": 1.6883639867823694e-07, "epoch": 4.163189269746646, "percentage": 83.26, "elapsed_time": "1:13:46", "remaining_time": "0:14:49", "throughput": 5170.16, "total_tokens": 22884352} {"current_steps": 5588, "total_steps": 6710, "loss": 0.1144, "lr": 1.685427882272553e-07, "epoch": 4.163934426229508, "percentage": 83.28, "elapsed_time": "1:13:47", "remaining_time": "0:14:48", "throughput": 5170.17, "total_tokens": 22888448} {"current_steps": 5589, "total_steps": 6710, "loss": 0.0993, "lr": 1.6824941483941649e-07, "epoch": 4.1646795827123695, "percentage": 83.29, "elapsed_time": "1:13:47", "remaining_time": "0:14:48", "throughput": 5170.19, "total_tokens": 22892544} {"current_steps": 5590, "total_steps": 6710, "loss": 0.1227, "lr": 1.6795627857903064e-07, "epoch": 4.165424739195231, "percentage": 83.31, "elapsed_time": "1:13:48", "remaining_time": "0:14:47", "throughput": 5170.2, "total_tokens": 22896640} {"current_steps": 5591, "total_steps": 6710, "loss": 0.0758, "lr": 1.6766337951035467e-07, "epoch": 4.166169895678093, "percentage": 83.32, "elapsed_time": "1:13:49", "remaining_time": "0:14:46", "throughput": 5170.21, "total_tokens": 22900736} {"current_steps": 5592, "total_steps": 6710, "loss": 0.1833, "lr": 1.673707176975947e-07, "epoch": 4.166915052160954, "percentage": 83.34, "elapsed_time": "1:13:50", "remaining_time": "0:14:45", "throughput": 5170.22, "total_tokens": 22904832} {"current_steps": 5593, "total_steps": 6710, "loss": 0.0817, "lr": 1.6707829320490393e-07, "epoch": 4.167660208643815, "percentage": 83.35, "elapsed_time": "1:13:50", "remaining_time": "0:14:44", "throughput": 5170.24, "total_tokens": 22908928} {"current_steps": 5594, "total_steps": 6710, "loss": 0.0871, "lr": 1.667861060963842e-07, "epoch": 4.168405365126676, "percentage": 83.37, "elapsed_time": "1:13:51", "remaining_time": "0:14:44", "throughput": 5170.25, "total_tokens": 22913024} {"current_steps": 5595, "total_steps": 6710, "loss": 0.0223, "lr": 1.6649415643608487e-07, "epoch": 4.169150521609538, "percentage": 83.38, "elapsed_time": "1:13:52", "remaining_time": "0:14:43", "throughput": 5170.26, "total_tokens": 22917120} {"current_steps": 5596, "total_steps": 6710, "loss": 0.0697, "lr": 1.662024442880032e-07, "epoch": 4.1698956780923995, "percentage": 83.4, "elapsed_time": "1:13:53", "remaining_time": "0:14:42", "throughput": 5170.28, "total_tokens": 22921216} {"current_steps": 5597, "total_steps": 6710, "loss": 0.1197, "lr": 1.6591096971608489e-07, "epoch": 4.170640834575261, "percentage": 83.41, "elapsed_time": "1:13:54", "remaining_time": "0:14:41", "throughput": 5170.29, "total_tokens": 22925312} {"current_steps": 5598, "total_steps": 6710, "loss": 0.0653, "lr": 1.6561973278422294e-07, "epoch": 4.171385991058123, "percentage": 83.43, "elapsed_time": "1:13:54", "remaining_time": "0:14:40", "throughput": 5170.3, "total_tokens": 22929408} {"current_steps": 5599, "total_steps": 6710, "loss": 0.0922, "lr": 1.6532873355625924e-07, "epoch": 4.172131147540983, "percentage": 83.44, "elapsed_time": "1:13:55", "remaining_time": "0:14:40", "throughput": 5170.32, "total_tokens": 22933504} {"current_steps": 5600, "total_steps": 6710, "loss": 0.1049, "lr": 1.6503797209598189e-07, "epoch": 4.172876304023845, "percentage": 83.46, "elapsed_time": "1:13:56", "remaining_time": "0:14:39", "throughput": 5170.33, "total_tokens": 22937600} {"current_steps": 5601, "total_steps": 6710, "loss": 0.0221, "lr": 1.6474744846712853e-07, "epoch": 4.173621460506706, "percentage": 83.47, "elapsed_time": "1:13:57", "remaining_time": "0:14:38", "throughput": 5170.35, "total_tokens": 22941696} {"current_steps": 5602, "total_steps": 6710, "loss": 0.0512, "lr": 1.6445716273338366e-07, "epoch": 4.174366616989568, "percentage": 83.49, "elapsed_time": "1:13:57", "remaining_time": "0:14:37", "throughput": 5170.36, "total_tokens": 22945792} {"current_steps": 5603, "total_steps": 6710, "loss": 0.0995, "lr": 1.6416711495838038e-07, "epoch": 4.1751117734724295, "percentage": 83.5, "elapsed_time": "1:13:58", "remaining_time": "0:14:36", "throughput": 5170.38, "total_tokens": 22949888} {"current_steps": 5604, "total_steps": 6710, "loss": 0.0925, "lr": 1.6387730520569883e-07, "epoch": 4.175856929955291, "percentage": 83.52, "elapsed_time": "1:13:59", "remaining_time": "0:14:36", "throughput": 5170.37, "total_tokens": 22953984} {"current_steps": 5605, "total_steps": 6710, "loss": 0.2431, "lr": 1.635877335388679e-07, "epoch": 4.176602086438152, "percentage": 83.53, "elapsed_time": "1:14:00", "remaining_time": "0:14:35", "throughput": 5170.38, "total_tokens": 22958080} {"current_steps": 5606, "total_steps": 6710, "loss": 0.0673, "lr": 1.6329840002136347e-07, "epoch": 4.177347242921013, "percentage": 83.55, "elapsed_time": "1:14:01", "remaining_time": "0:14:34", "throughput": 5170.4, "total_tokens": 22962176} {"current_steps": 5607, "total_steps": 6710, "loss": 0.0512, "lr": 1.6300930471660924e-07, "epoch": 4.178092399403875, "percentage": 83.56, "elapsed_time": "1:14:01", "remaining_time": "0:14:33", "throughput": 5170.41, "total_tokens": 22966272} {"current_steps": 5608, "total_steps": 6710, "loss": 0.0124, "lr": 1.6272044768797734e-07, "epoch": 4.178837555886736, "percentage": 83.58, "elapsed_time": "1:14:02", "remaining_time": "0:14:33", "throughput": 5170.43, "total_tokens": 22970368} {"current_steps": 5609, "total_steps": 6710, "loss": 0.0822, "lr": 1.624318289987871e-07, "epoch": 4.179582712369598, "percentage": 83.59, "elapsed_time": "1:14:03", "remaining_time": "0:14:32", "throughput": 5170.44, "total_tokens": 22974464} {"current_steps": 5610, "total_steps": 6710, "loss": 0.0392, "lr": 1.6214344871230593e-07, "epoch": 4.180327868852459, "percentage": 83.61, "elapsed_time": "1:14:04", "remaining_time": "0:14:31", "throughput": 5170.46, "total_tokens": 22978560} {"current_steps": 5611, "total_steps": 6710, "loss": 0.1737, "lr": 1.6185530689174876e-07, "epoch": 4.18107302533532, "percentage": 83.62, "elapsed_time": "1:14:05", "remaining_time": "0:14:30", "throughput": 5170.44, "total_tokens": 22982656} {"current_steps": 5612, "total_steps": 6710, "loss": 0.0424, "lr": 1.6156740360027874e-07, "epoch": 4.181818181818182, "percentage": 83.64, "elapsed_time": "1:14:05", "remaining_time": "0:14:29", "throughput": 5170.45, "total_tokens": 22986752} {"current_steps": 5613, "total_steps": 6710, "loss": 0.0987, "lr": 1.612797389010054e-07, "epoch": 4.182563338301043, "percentage": 83.65, "elapsed_time": "1:14:06", "remaining_time": "0:14:29", "throughput": 5170.47, "total_tokens": 22990848} {"current_steps": 5614, "total_steps": 6710, "loss": 0.0541, "lr": 1.609923128569879e-07, "epoch": 4.183308494783905, "percentage": 83.67, "elapsed_time": "1:14:07", "remaining_time": "0:14:28", "throughput": 5170.48, "total_tokens": 22994944} {"current_steps": 5615, "total_steps": 6710, "loss": 0.0962, "lr": 1.6070512553123142e-07, "epoch": 4.184053651266766, "percentage": 83.68, "elapsed_time": "1:14:08", "remaining_time": "0:14:27", "throughput": 5170.48, "total_tokens": 22999040} {"current_steps": 5616, "total_steps": 6710, "loss": 0.1365, "lr": 1.6041817698668957e-07, "epoch": 4.184798807749628, "percentage": 83.7, "elapsed_time": "1:14:08", "remaining_time": "0:14:26", "throughput": 5170.49, "total_tokens": 23003136} {"current_steps": 5617, "total_steps": 6710, "loss": 0.0841, "lr": 1.6013146728626375e-07, "epoch": 4.1855439642324885, "percentage": 83.71, "elapsed_time": "1:14:09", "remaining_time": "0:14:25", "throughput": 5170.5, "total_tokens": 23007232} {"current_steps": 5618, "total_steps": 6710, "loss": 0.153, "lr": 1.5984499649280255e-07, "epoch": 4.18628912071535, "percentage": 83.73, "elapsed_time": "1:14:10", "remaining_time": "0:14:25", "throughput": 5170.51, "total_tokens": 23011328} {"current_steps": 5619, "total_steps": 6710, "loss": 0.122, "lr": 1.595587646691027e-07, "epoch": 4.187034277198212, "percentage": 83.74, "elapsed_time": "1:14:11", "remaining_time": "0:14:24", "throughput": 5170.53, "total_tokens": 23015424} {"current_steps": 5620, "total_steps": 6710, "loss": 0.0674, "lr": 1.5927277187790787e-07, "epoch": 4.187779433681073, "percentage": 83.76, "elapsed_time": "1:14:12", "remaining_time": "0:14:23", "throughput": 5170.53, "total_tokens": 23019520} {"current_steps": 5621, "total_steps": 6710, "loss": 0.1316, "lr": 1.5898701818191018e-07, "epoch": 4.188524590163935, "percentage": 83.77, "elapsed_time": "1:14:12", "remaining_time": "0:14:22", "throughput": 5170.54, "total_tokens": 23023616} {"current_steps": 5622, "total_steps": 6710, "loss": 0.0582, "lr": 1.5870150364374852e-07, "epoch": 4.189269746646795, "percentage": 83.79, "elapsed_time": "1:14:13", "remaining_time": "0:14:21", "throughput": 5170.55, "total_tokens": 23027712} {"current_steps": 5623, "total_steps": 6710, "loss": 0.0769, "lr": 1.5841622832600976e-07, "epoch": 4.190014903129657, "percentage": 83.8, "elapsed_time": "1:14:14", "remaining_time": "0:14:21", "throughput": 5170.56, "total_tokens": 23031808} {"current_steps": 5624, "total_steps": 6710, "loss": 0.0973, "lr": 1.5813119229122847e-07, "epoch": 4.1907600596125185, "percentage": 83.82, "elapsed_time": "1:14:15", "remaining_time": "0:14:20", "throughput": 5170.57, "total_tokens": 23035904} {"current_steps": 5625, "total_steps": 6710, "loss": 0.0713, "lr": 1.5784639560188623e-07, "epoch": 4.19150521609538, "percentage": 83.83, "elapsed_time": "1:14:15", "remaining_time": "0:14:19", "throughput": 5170.58, "total_tokens": 23040000} {"current_steps": 5626, "total_steps": 6710, "loss": 0.0877, "lr": 1.5756183832041333e-07, "epoch": 4.192250372578242, "percentage": 83.85, "elapsed_time": "1:14:16", "remaining_time": "0:14:18", "throughput": 5170.59, "total_tokens": 23044096} {"current_steps": 5627, "total_steps": 6710, "loss": 0.1011, "lr": 1.572775205091856e-07, "epoch": 4.192995529061103, "percentage": 83.86, "elapsed_time": "1:14:17", "remaining_time": "0:14:17", "throughput": 5170.6, "total_tokens": 23048192} {"current_steps": 5628, "total_steps": 6710, "loss": 0.0157, "lr": 1.5699344223052846e-07, "epoch": 4.193740685543964, "percentage": 83.87, "elapsed_time": "1:14:18", "remaining_time": "0:14:17", "throughput": 5170.62, "total_tokens": 23052288} {"current_steps": 5629, "total_steps": 6710, "loss": 0.0446, "lr": 1.567096035467132e-07, "epoch": 4.194485842026825, "percentage": 83.89, "elapsed_time": "1:14:19", "remaining_time": "0:14:16", "throughput": 5170.63, "total_tokens": 23056384} {"current_steps": 5630, "total_steps": 6710, "loss": 0.0433, "lr": 1.564260045199599e-07, "epoch": 4.195230998509687, "percentage": 83.9, "elapsed_time": "1:14:19", "remaining_time": "0:14:15", "throughput": 5170.64, "total_tokens": 23060480} {"current_steps": 5631, "total_steps": 6710, "loss": 0.0681, "lr": 1.5614264521243497e-07, "epoch": 4.1959761549925485, "percentage": 83.92, "elapsed_time": "1:14:20", "remaining_time": "0:14:14", "throughput": 5170.65, "total_tokens": 23064576} {"current_steps": 5632, "total_steps": 6710, "loss": 0.0595, "lr": 1.558595256862533e-07, "epoch": 4.19672131147541, "percentage": 83.93, "elapsed_time": "1:14:21", "remaining_time": "0:14:13", "throughput": 5170.66, "total_tokens": 23068672} {"current_steps": 5633, "total_steps": 6710, "loss": 0.0271, "lr": 1.5557664600347647e-07, "epoch": 4.197466467958272, "percentage": 83.95, "elapsed_time": "1:14:22", "remaining_time": "0:14:13", "throughput": 5170.67, "total_tokens": 23072768} {"current_steps": 5634, "total_steps": 6710, "loss": 0.0938, "lr": 1.5529400622611336e-07, "epoch": 4.198211624441132, "percentage": 83.96, "elapsed_time": "1:14:23", "remaining_time": "0:14:12", "throughput": 5170.68, "total_tokens": 23076864} {"current_steps": 5635, "total_steps": 6710, "loss": 0.0938, "lr": 1.5501160641612139e-07, "epoch": 4.198956780923994, "percentage": 83.98, "elapsed_time": "1:14:23", "remaining_time": "0:14:11", "throughput": 5170.69, "total_tokens": 23080960} {"current_steps": 5636, "total_steps": 6710, "loss": 0.0311, "lr": 1.5472944663540392e-07, "epoch": 4.199701937406855, "percentage": 83.99, "elapsed_time": "1:14:24", "remaining_time": "0:14:10", "throughput": 5170.7, "total_tokens": 23085056} {"current_steps": 5637, "total_steps": 6710, "loss": 0.1758, "lr": 1.5444752694581288e-07, "epoch": 4.200447093889717, "percentage": 84.01, "elapsed_time": "1:14:25", "remaining_time": "0:14:09", "throughput": 5170.71, "total_tokens": 23089152} {"current_steps": 5638, "total_steps": 6710, "loss": 0.0801, "lr": 1.5416584740914675e-07, "epoch": 4.2011922503725785, "percentage": 84.02, "elapsed_time": "1:14:26", "remaining_time": "0:14:09", "throughput": 5170.72, "total_tokens": 23093248} {"current_steps": 5639, "total_steps": 6710, "loss": 0.1041, "lr": 1.5388440808715225e-07, "epoch": 4.20193740685544, "percentage": 84.04, "elapsed_time": "1:14:26", "remaining_time": "0:14:08", "throughput": 5170.73, "total_tokens": 23097344} {"current_steps": 5640, "total_steps": 6710, "loss": 0.0346, "lr": 1.5360320904152195e-07, "epoch": 4.202682563338301, "percentage": 84.05, "elapsed_time": "1:14:27", "remaining_time": "0:14:07", "throughput": 5170.75, "total_tokens": 23101440} {"current_steps": 5641, "total_steps": 6710, "loss": 0.0439, "lr": 1.533222503338974e-07, "epoch": 4.203427719821162, "percentage": 84.07, "elapsed_time": "1:14:28", "remaining_time": "0:14:06", "throughput": 5170.76, "total_tokens": 23105536} {"current_steps": 5642, "total_steps": 6710, "loss": 0.1136, "lr": 1.5304153202586672e-07, "epoch": 4.204172876304024, "percentage": 84.08, "elapsed_time": "1:14:29", "remaining_time": "0:14:06", "throughput": 5170.77, "total_tokens": 23109632} {"current_steps": 5643, "total_steps": 6710, "loss": 0.2737, "lr": 1.527610541789648e-07, "epoch": 4.204918032786885, "percentage": 84.1, "elapsed_time": "1:14:30", "remaining_time": "0:14:05", "throughput": 5170.78, "total_tokens": 23113728} {"current_steps": 5644, "total_steps": 6710, "loss": 0.0634, "lr": 1.52480816854675e-07, "epoch": 4.205663189269747, "percentage": 84.11, "elapsed_time": "1:14:30", "remaining_time": "0:14:04", "throughput": 5170.8, "total_tokens": 23117824} {"current_steps": 5645, "total_steps": 6710, "loss": 0.046, "lr": 1.5220082011442704e-07, "epoch": 4.2064083457526085, "percentage": 84.13, "elapsed_time": "1:14:31", "remaining_time": "0:14:03", "throughput": 5170.81, "total_tokens": 23121920} {"current_steps": 5646, "total_steps": 6710, "loss": 0.1432, "lr": 1.5192106401959838e-07, "epoch": 4.207153502235469, "percentage": 84.14, "elapsed_time": "1:14:32", "remaining_time": "0:14:02", "throughput": 5170.82, "total_tokens": 23126016} {"current_steps": 5647, "total_steps": 6710, "loss": 0.0302, "lr": 1.516415486315134e-07, "epoch": 4.207898658718331, "percentage": 84.16, "elapsed_time": "1:14:33", "remaining_time": "0:14:02", "throughput": 5170.84, "total_tokens": 23130112} {"current_steps": 5648, "total_steps": 6710, "loss": 0.1181, "lr": 1.5136227401144412e-07, "epoch": 4.208643815201192, "percentage": 84.17, "elapsed_time": "1:14:33", "remaining_time": "0:14:01", "throughput": 5170.85, "total_tokens": 23134208} {"current_steps": 5649, "total_steps": 6710, "loss": 0.068, "lr": 1.510832402206093e-07, "epoch": 4.209388971684054, "percentage": 84.19, "elapsed_time": "1:14:34", "remaining_time": "0:14:00", "throughput": 5170.86, "total_tokens": 23138304} {"current_steps": 5650, "total_steps": 6710, "loss": 0.0846, "lr": 1.5080444732017502e-07, "epoch": 4.210134128166915, "percentage": 84.2, "elapsed_time": "1:14:35", "remaining_time": "0:13:59", "throughput": 5170.87, "total_tokens": 23142400} {"current_steps": 5651, "total_steps": 6710, "loss": 0.0484, "lr": 1.5052589537125504e-07, "epoch": 4.210879284649776, "percentage": 84.22, "elapsed_time": "1:14:36", "remaining_time": "0:13:58", "throughput": 5170.89, "total_tokens": 23146496} {"current_steps": 5652, "total_steps": 6710, "loss": 0.0185, "lr": 1.502475844349094e-07, "epoch": 4.211624441132638, "percentage": 84.23, "elapsed_time": "1:14:37", "remaining_time": "0:13:58", "throughput": 5170.9, "total_tokens": 23150592} {"current_steps": 5653, "total_steps": 6710, "loss": 0.0881, "lr": 1.499695145721468e-07, "epoch": 4.212369597615499, "percentage": 84.25, "elapsed_time": "1:14:37", "remaining_time": "0:13:57", "throughput": 5170.92, "total_tokens": 23154688} {"current_steps": 5654, "total_steps": 6710, "loss": 0.0454, "lr": 1.496916858439211e-07, "epoch": 4.213114754098361, "percentage": 84.26, "elapsed_time": "1:14:38", "remaining_time": "0:13:56", "throughput": 5170.93, "total_tokens": 23158784} {"current_steps": 5655, "total_steps": 6710, "loss": 0.1081, "lr": 1.4941409831113487e-07, "epoch": 4.213859910581222, "percentage": 84.28, "elapsed_time": "1:14:39", "remaining_time": "0:13:55", "throughput": 5170.95, "total_tokens": 23162880} {"current_steps": 5656, "total_steps": 6710, "loss": 0.1462, "lr": 1.4913675203463692e-07, "epoch": 4.214605067064084, "percentage": 84.29, "elapsed_time": "1:14:40", "remaining_time": "0:13:54", "throughput": 5170.96, "total_tokens": 23166976} {"current_steps": 5657, "total_steps": 6710, "loss": 0.0928, "lr": 1.488596470752242e-07, "epoch": 4.215350223546944, "percentage": 84.31, "elapsed_time": "1:14:40", "remaining_time": "0:13:54", "throughput": 5170.97, "total_tokens": 23171072} {"current_steps": 5658, "total_steps": 6710, "loss": 0.0185, "lr": 1.485827834936393e-07, "epoch": 4.216095380029806, "percentage": 84.32, "elapsed_time": "1:14:41", "remaining_time": "0:13:53", "throughput": 5170.99, "total_tokens": 23175168} {"current_steps": 5659, "total_steps": 6710, "loss": 0.06, "lr": 1.483061613505733e-07, "epoch": 4.2168405365126675, "percentage": 84.34, "elapsed_time": "1:14:42", "remaining_time": "0:13:52", "throughput": 5171.0, "total_tokens": 23179264} {"current_steps": 5660, "total_steps": 6710, "loss": 0.0646, "lr": 1.480297807066637e-07, "epoch": 4.217585692995529, "percentage": 84.35, "elapsed_time": "1:14:43", "remaining_time": "0:13:51", "throughput": 5171.01, "total_tokens": 23183360} {"current_steps": 5661, "total_steps": 6710, "loss": 0.0642, "lr": 1.477536416224945e-07, "epoch": 4.218330849478391, "percentage": 84.37, "elapsed_time": "1:14:44", "remaining_time": "0:13:50", "throughput": 5171.02, "total_tokens": 23187456} {"current_steps": 5662, "total_steps": 6710, "loss": 0.0229, "lr": 1.4747774415859825e-07, "epoch": 4.219076005961252, "percentage": 84.38, "elapsed_time": "1:14:44", "remaining_time": "0:13:50", "throughput": 5171.03, "total_tokens": 23191552} {"current_steps": 5663, "total_steps": 6710, "loss": 0.0296, "lr": 1.4720208837545283e-07, "epoch": 4.219821162444113, "percentage": 84.4, "elapsed_time": "1:14:45", "remaining_time": "0:13:49", "throughput": 5171.04, "total_tokens": 23195648} {"current_steps": 5664, "total_steps": 6710, "loss": 0.0429, "lr": 1.4692667433348448e-07, "epoch": 4.220566318926974, "percentage": 84.41, "elapsed_time": "1:14:46", "remaining_time": "0:13:48", "throughput": 5171.06, "total_tokens": 23199744} {"current_steps": 5665, "total_steps": 6710, "loss": 0.0943, "lr": 1.466515020930656e-07, "epoch": 4.221311475409836, "percentage": 84.43, "elapsed_time": "1:14:47", "remaining_time": "0:13:47", "throughput": 5171.07, "total_tokens": 23203840} {"current_steps": 5666, "total_steps": 6710, "loss": 0.0522, "lr": 1.4637657171451657e-07, "epoch": 4.2220566318926975, "percentage": 84.44, "elapsed_time": "1:14:48", "remaining_time": "0:13:46", "throughput": 5171.09, "total_tokens": 23207936} {"current_steps": 5667, "total_steps": 6710, "loss": 0.0226, "lr": 1.4610188325810305e-07, "epoch": 4.222801788375559, "percentage": 84.46, "elapsed_time": "1:14:48", "remaining_time": "0:13:46", "throughput": 5171.1, "total_tokens": 23212032} {"current_steps": 5668, "total_steps": 6710, "loss": 0.1781, "lr": 1.4582743678403968e-07, "epoch": 4.223546944858421, "percentage": 84.47, "elapsed_time": "1:14:49", "remaining_time": "0:13:45", "throughput": 5171.11, "total_tokens": 23216128} {"current_steps": 5669, "total_steps": 6710, "loss": 0.0283, "lr": 1.455532323524865e-07, "epoch": 4.224292101341281, "percentage": 84.49, "elapsed_time": "1:14:50", "remaining_time": "0:13:44", "throughput": 5171.12, "total_tokens": 23220224} {"current_steps": 5670, "total_steps": 6710, "loss": 0.0693, "lr": 1.45279270023551e-07, "epoch": 4.225037257824143, "percentage": 84.5, "elapsed_time": "1:14:51", "remaining_time": "0:13:43", "throughput": 5171.14, "total_tokens": 23224320} {"current_steps": 5671, "total_steps": 6710, "loss": 0.1989, "lr": 1.450055498572882e-07, "epoch": 4.225782414307004, "percentage": 84.52, "elapsed_time": "1:14:51", "remaining_time": "0:13:42", "throughput": 5171.15, "total_tokens": 23228416} {"current_steps": 5672, "total_steps": 6710, "loss": 0.096, "lr": 1.4473207191369896e-07, "epoch": 4.226527570789866, "percentage": 84.53, "elapsed_time": "1:14:52", "remaining_time": "0:13:42", "throughput": 5171.16, "total_tokens": 23232512} {"current_steps": 5673, "total_steps": 6710, "loss": 0.026, "lr": 1.4445883625273216e-07, "epoch": 4.2272727272727275, "percentage": 84.55, "elapsed_time": "1:14:53", "remaining_time": "0:13:41", "throughput": 5171.18, "total_tokens": 23236608} {"current_steps": 5674, "total_steps": 6710, "loss": 0.0819, "lr": 1.4418584293428253e-07, "epoch": 4.228017883755589, "percentage": 84.56, "elapsed_time": "1:14:54", "remaining_time": "0:13:40", "throughput": 5171.19, "total_tokens": 23240704} {"current_steps": 5675, "total_steps": 6710, "loss": 0.0378, "lr": 1.4391309201819248e-07, "epoch": 4.22876304023845, "percentage": 84.58, "elapsed_time": "1:14:55", "remaining_time": "0:13:39", "throughput": 5171.2, "total_tokens": 23244800} {"current_steps": 5676, "total_steps": 6710, "loss": 0.0369, "lr": 1.4364058356425098e-07, "epoch": 4.229508196721311, "percentage": 84.59, "elapsed_time": "1:14:55", "remaining_time": "0:13:39", "throughput": 5171.22, "total_tokens": 23248896} {"current_steps": 5677, "total_steps": 6710, "loss": 0.1008, "lr": 1.433683176321933e-07, "epoch": 4.230253353204173, "percentage": 84.61, "elapsed_time": "1:14:56", "remaining_time": "0:13:38", "throughput": 5171.22, "total_tokens": 23252992} {"current_steps": 5678, "total_steps": 6710, "loss": 0.0333, "lr": 1.4309629428170268e-07, "epoch": 4.230998509687034, "percentage": 84.62, "elapsed_time": "1:14:57", "remaining_time": "0:13:37", "throughput": 5171.23, "total_tokens": 23257088} {"current_steps": 5679, "total_steps": 6710, "loss": 0.0626, "lr": 1.4282451357240823e-07, "epoch": 4.231743666169896, "percentage": 84.63, "elapsed_time": "1:14:58", "remaining_time": "0:13:36", "throughput": 5171.23, "total_tokens": 23261184} {"current_steps": 5680, "total_steps": 6710, "loss": 0.0854, "lr": 1.4255297556388673e-07, "epoch": 4.2324888226527575, "percentage": 84.65, "elapsed_time": "1:14:58", "remaining_time": "0:13:35", "throughput": 5171.22, "total_tokens": 23265280} {"current_steps": 5681, "total_steps": 6710, "loss": 0.0482, "lr": 1.4228168031566041e-07, "epoch": 4.233233979135618, "percentage": 84.66, "elapsed_time": "1:14:59", "remaining_time": "0:13:35", "throughput": 5171.22, "total_tokens": 23269376} {"current_steps": 5682, "total_steps": 6710, "loss": 0.0608, "lr": 1.420106278871998e-07, "epoch": 4.23397913561848, "percentage": 84.68, "elapsed_time": "1:15:00", "remaining_time": "0:13:34", "throughput": 5171.21, "total_tokens": 23273472} {"current_steps": 5683, "total_steps": 6710, "loss": 0.028, "lr": 1.417398183379211e-07, "epoch": 4.234724292101341, "percentage": 84.69, "elapsed_time": "1:15:01", "remaining_time": "0:13:33", "throughput": 5171.22, "total_tokens": 23277568} {"current_steps": 5684, "total_steps": 6710, "loss": 0.0103, "lr": 1.4146925172718802e-07, "epoch": 4.235469448584203, "percentage": 84.71, "elapsed_time": "1:15:02", "remaining_time": "0:13:32", "throughput": 5171.23, "total_tokens": 23281664} {"current_steps": 5685, "total_steps": 6710, "loss": 0.0768, "lr": 1.4119892811431059e-07, "epoch": 4.236214605067064, "percentage": 84.72, "elapsed_time": "1:15:02", "remaining_time": "0:13:31", "throughput": 5171.23, "total_tokens": 23285760} {"current_steps": 5686, "total_steps": 6710, "loss": 0.077, "lr": 1.4092884755854573e-07, "epoch": 4.236959761549926, "percentage": 84.74, "elapsed_time": "1:15:03", "remaining_time": "0:13:31", "throughput": 5171.24, "total_tokens": 23289856} {"current_steps": 5687, "total_steps": 6710, "loss": 0.0179, "lr": 1.4065901011909688e-07, "epoch": 4.237704918032787, "percentage": 84.75, "elapsed_time": "1:15:04", "remaining_time": "0:13:30", "throughput": 5171.24, "total_tokens": 23293952} {"current_steps": 5688, "total_steps": 6710, "loss": 0.0708, "lr": 1.403894158551143e-07, "epoch": 4.238450074515648, "percentage": 84.77, "elapsed_time": "1:15:05", "remaining_time": "0:13:29", "throughput": 5171.25, "total_tokens": 23298048} {"current_steps": 5689, "total_steps": 6710, "loss": 0.1781, "lr": 1.4012006482569535e-07, "epoch": 4.23919523099851, "percentage": 84.78, "elapsed_time": "1:15:06", "remaining_time": "0:13:28", "throughput": 5171.27, "total_tokens": 23302144} {"current_steps": 5690, "total_steps": 6710, "loss": 0.0396, "lr": 1.3985095708988317e-07, "epoch": 4.239940387481371, "percentage": 84.8, "elapsed_time": "1:15:06", "remaining_time": "0:13:27", "throughput": 5171.28, "total_tokens": 23306240} {"current_steps": 5691, "total_steps": 6710, "loss": 0.0349, "lr": 1.3958209270666863e-07, "epoch": 4.240685543964233, "percentage": 84.81, "elapsed_time": "1:15:07", "remaining_time": "0:13:27", "throughput": 5171.29, "total_tokens": 23310336} {"current_steps": 5692, "total_steps": 6710, "loss": 0.0366, "lr": 1.3931347173498824e-07, "epoch": 4.2414307004470935, "percentage": 84.83, "elapsed_time": "1:15:08", "remaining_time": "0:13:26", "throughput": 5171.3, "total_tokens": 23314432} {"current_steps": 5693, "total_steps": 6710, "loss": 0.2066, "lr": 1.3904509423372626e-07, "epoch": 4.242175856929955, "percentage": 84.84, "elapsed_time": "1:15:09", "remaining_time": "0:13:25", "throughput": 5171.31, "total_tokens": 23318528} {"current_steps": 5694, "total_steps": 6710, "loss": 0.0607, "lr": 1.3877696026171215e-07, "epoch": 4.242921013412817, "percentage": 84.86, "elapsed_time": "1:15:09", "remaining_time": "0:13:24", "throughput": 5171.32, "total_tokens": 23322624} {"current_steps": 5695, "total_steps": 6710, "loss": 0.0892, "lr": 1.3850906987772333e-07, "epoch": 4.243666169895678, "percentage": 84.87, "elapsed_time": "1:15:10", "remaining_time": "0:13:23", "throughput": 5171.33, "total_tokens": 23326720} {"current_steps": 5696, "total_steps": 6710, "loss": 0.069, "lr": 1.38241423140483e-07, "epoch": 4.24441132637854, "percentage": 84.89, "elapsed_time": "1:15:11", "remaining_time": "0:13:23", "throughput": 5171.34, "total_tokens": 23330816} {"current_steps": 5697, "total_steps": 6710, "loss": 0.014, "lr": 1.3797402010866158e-07, "epoch": 4.245156482861401, "percentage": 84.9, "elapsed_time": "1:15:12", "remaining_time": "0:13:22", "throughput": 5171.35, "total_tokens": 23334912} {"current_steps": 5698, "total_steps": 6710, "loss": 0.0069, "lr": 1.3770686084087547e-07, "epoch": 4.245901639344262, "percentage": 84.92, "elapsed_time": "1:15:13", "remaining_time": "0:13:21", "throughput": 5171.36, "total_tokens": 23339008} {"current_steps": 5699, "total_steps": 6710, "loss": 0.0435, "lr": 1.3743994539568774e-07, "epoch": 4.2466467958271235, "percentage": 84.93, "elapsed_time": "1:15:13", "remaining_time": "0:13:20", "throughput": 5171.37, "total_tokens": 23343104} {"current_steps": 5700, "total_steps": 6710, "loss": 0.1268, "lr": 1.3717327383160865e-07, "epoch": 4.247391952309985, "percentage": 84.95, "elapsed_time": "1:15:14", "remaining_time": "0:13:19", "throughput": 5171.37, "total_tokens": 23347200} {"current_steps": 5701, "total_steps": 6710, "loss": 0.0447, "lr": 1.3690684620709396e-07, "epoch": 4.248137108792847, "percentage": 84.96, "elapsed_time": "1:15:15", "remaining_time": "0:13:19", "throughput": 5171.38, "total_tokens": 23351296} {"current_steps": 5702, "total_steps": 6710, "loss": 0.0372, "lr": 1.3664066258054707e-07, "epoch": 4.248882265275708, "percentage": 84.98, "elapsed_time": "1:15:16", "remaining_time": "0:13:18", "throughput": 5171.39, "total_tokens": 23355392} {"current_steps": 5703, "total_steps": 6710, "loss": 0.1508, "lr": 1.3637472301031684e-07, "epoch": 4.24962742175857, "percentage": 84.99, "elapsed_time": "1:15:17", "remaining_time": "0:13:17", "throughput": 5171.4, "total_tokens": 23359488} {"current_steps": 5704, "total_steps": 6710, "loss": 0.0412, "lr": 1.3610902755469947e-07, "epoch": 4.25037257824143, "percentage": 85.01, "elapsed_time": "1:15:17", "remaining_time": "0:13:16", "throughput": 5171.41, "total_tokens": 23363584} {"current_steps": 5705, "total_steps": 6710, "loss": 0.1869, "lr": 1.3584357627193705e-07, "epoch": 4.251117734724292, "percentage": 85.02, "elapsed_time": "1:15:18", "remaining_time": "0:13:16", "throughput": 5171.42, "total_tokens": 23367680} {"current_steps": 5706, "total_steps": 6710, "loss": 0.0785, "lr": 1.355783692202184e-07, "epoch": 4.251862891207153, "percentage": 85.04, "elapsed_time": "1:15:19", "remaining_time": "0:13:15", "throughput": 5171.43, "total_tokens": 23371776} {"current_steps": 5707, "total_steps": 6710, "loss": 0.0689, "lr": 1.3531340645767944e-07, "epoch": 4.252608047690015, "percentage": 85.05, "elapsed_time": "1:15:20", "remaining_time": "0:13:14", "throughput": 5171.44, "total_tokens": 23375872} {"current_steps": 5708, "total_steps": 6710, "loss": 0.0187, "lr": 1.3504868804240082e-07, "epoch": 4.2533532041728765, "percentage": 85.07, "elapsed_time": "1:15:20", "remaining_time": "0:13:13", "throughput": 5171.44, "total_tokens": 23379968} {"current_steps": 5709, "total_steps": 6710, "loss": 0.135, "lr": 1.347842140324114e-07, "epoch": 4.254098360655738, "percentage": 85.08, "elapsed_time": "1:15:21", "remaining_time": "0:13:12", "throughput": 5171.45, "total_tokens": 23384064} {"current_steps": 5710, "total_steps": 6710, "loss": 0.0305, "lr": 1.3451998448568537e-07, "epoch": 4.254843517138599, "percentage": 85.1, "elapsed_time": "1:15:22", "remaining_time": "0:13:12", "throughput": 5171.47, "total_tokens": 23388160} {"current_steps": 5711, "total_steps": 6710, "loss": 0.0722, "lr": 1.342559994601443e-07, "epoch": 4.25558867362146, "percentage": 85.11, "elapsed_time": "1:15:23", "remaining_time": "0:13:11", "throughput": 5171.47, "total_tokens": 23392256} {"current_steps": 5712, "total_steps": 6710, "loss": 0.3268, "lr": 1.3399225901365498e-07, "epoch": 4.256333830104322, "percentage": 85.13, "elapsed_time": "1:15:24", "remaining_time": "0:13:10", "throughput": 5171.48, "total_tokens": 23396352} {"current_steps": 5713, "total_steps": 6710, "loss": 0.076, "lr": 1.3372876320403182e-07, "epoch": 4.257078986587183, "percentage": 85.14, "elapsed_time": "1:15:24", "remaining_time": "0:13:09", "throughput": 5171.49, "total_tokens": 23400448} {"current_steps": 5714, "total_steps": 6710, "loss": 0.0237, "lr": 1.3346551208903464e-07, "epoch": 4.257824143070045, "percentage": 85.16, "elapsed_time": "1:15:25", "remaining_time": "0:13:08", "throughput": 5171.5, "total_tokens": 23404544} {"current_steps": 5715, "total_steps": 6710, "loss": 0.005, "lr": 1.3320250572636973e-07, "epoch": 4.2585692995529065, "percentage": 85.17, "elapsed_time": "1:15:26", "remaining_time": "0:13:08", "throughput": 5171.51, "total_tokens": 23408640} {"current_steps": 5716, "total_steps": 6710, "loss": 0.0719, "lr": 1.3293974417369043e-07, "epoch": 4.259314456035767, "percentage": 85.19, "elapsed_time": "1:15:27", "remaining_time": "0:13:07", "throughput": 5171.52, "total_tokens": 23412736} {"current_steps": 5717, "total_steps": 6710, "loss": 0.0585, "lr": 1.326772274885954e-07, "epoch": 4.260059612518629, "percentage": 85.2, "elapsed_time": "1:15:28", "remaining_time": "0:13:06", "throughput": 5171.53, "total_tokens": 23416832} {"current_steps": 5718, "total_steps": 6710, "loss": 0.0232, "lr": 1.3241495572863082e-07, "epoch": 4.26080476900149, "percentage": 85.22, "elapsed_time": "1:15:28", "remaining_time": "0:13:05", "throughput": 5171.53, "total_tokens": 23420928} {"current_steps": 5719, "total_steps": 6710, "loss": 0.169, "lr": 1.3215292895128794e-07, "epoch": 4.261549925484352, "percentage": 85.23, "elapsed_time": "1:15:29", "remaining_time": "0:13:04", "throughput": 5171.54, "total_tokens": 23425024} {"current_steps": 5720, "total_steps": 6710, "loss": 0.039, "lr": 1.3189114721400582e-07, "epoch": 4.262295081967213, "percentage": 85.25, "elapsed_time": "1:15:30", "remaining_time": "0:13:04", "throughput": 5171.55, "total_tokens": 23429120} {"current_steps": 5721, "total_steps": 6710, "loss": 0.057, "lr": 1.3162961057416754e-07, "epoch": 4.263040238450074, "percentage": 85.26, "elapsed_time": "1:15:31", "remaining_time": "0:13:03", "throughput": 5171.56, "total_tokens": 23433216} {"current_steps": 5722, "total_steps": 6710, "loss": 0.0316, "lr": 1.313683190891049e-07, "epoch": 4.263785394932936, "percentage": 85.28, "elapsed_time": "1:15:31", "remaining_time": "0:13:02", "throughput": 5171.56, "total_tokens": 23437312} {"current_steps": 5723, "total_steps": 6710, "loss": 0.0597, "lr": 1.3110727281609405e-07, "epoch": 4.264530551415797, "percentage": 85.29, "elapsed_time": "1:15:32", "remaining_time": "0:13:01", "throughput": 5171.57, "total_tokens": 23441408} {"current_steps": 5724, "total_steps": 6710, "loss": 0.0552, "lr": 1.3084647181235893e-07, "epoch": 4.265275707898659, "percentage": 85.31, "elapsed_time": "1:15:33", "remaining_time": "0:13:00", "throughput": 5171.58, "total_tokens": 23445504} {"current_steps": 5725, "total_steps": 6710, "loss": 0.0071, "lr": 1.305859161350688e-07, "epoch": 4.26602086438152, "percentage": 85.32, "elapsed_time": "1:15:34", "remaining_time": "0:13:00", "throughput": 5171.59, "total_tokens": 23449600} {"current_steps": 5726, "total_steps": 6710, "loss": 0.1031, "lr": 1.303256058413388e-07, "epoch": 4.266766020864382, "percentage": 85.34, "elapsed_time": "1:15:35", "remaining_time": "0:12:59", "throughput": 5171.6, "total_tokens": 23453696} {"current_steps": 5727, "total_steps": 6710, "loss": 0.1152, "lr": 1.3006554098823148e-07, "epoch": 4.267511177347243, "percentage": 85.35, "elapsed_time": "1:15:35", "remaining_time": "0:12:58", "throughput": 5171.6, "total_tokens": 23457792} {"current_steps": 5728, "total_steps": 6710, "loss": 0.0661, "lr": 1.2980572163275432e-07, "epoch": 4.268256333830104, "percentage": 85.37, "elapsed_time": "1:15:36", "remaining_time": "0:12:57", "throughput": 5171.61, "total_tokens": 23461888} {"current_steps": 5729, "total_steps": 6710, "loss": 0.2261, "lr": 1.2954614783186216e-07, "epoch": 4.269001490312966, "percentage": 85.38, "elapsed_time": "1:15:37", "remaining_time": "0:12:56", "throughput": 5171.62, "total_tokens": 23465984} {"current_steps": 5730, "total_steps": 6710, "loss": 0.0478, "lr": 1.2928681964245487e-07, "epoch": 4.269746646795827, "percentage": 85.39, "elapsed_time": "1:15:38", "remaining_time": "0:12:56", "throughput": 5171.62, "total_tokens": 23470080} {"current_steps": 5731, "total_steps": 6710, "loss": 0.1743, "lr": 1.2902773712137954e-07, "epoch": 4.270491803278689, "percentage": 85.41, "elapsed_time": "1:15:39", "remaining_time": "0:12:55", "throughput": 5171.63, "total_tokens": 23474176} {"current_steps": 5732, "total_steps": 6710, "loss": 0.0265, "lr": 1.2876890032542875e-07, "epoch": 4.27123695976155, "percentage": 85.42, "elapsed_time": "1:15:39", "remaining_time": "0:12:54", "throughput": 5171.64, "total_tokens": 23478272} {"current_steps": 5733, "total_steps": 6710, "loss": 0.0569, "lr": 1.2851030931134113e-07, "epoch": 4.271982116244411, "percentage": 85.44, "elapsed_time": "1:15:40", "remaining_time": "0:12:53", "throughput": 5171.64, "total_tokens": 23482368} {"current_steps": 5734, "total_steps": 6710, "loss": 0.037, "lr": 1.2825196413580223e-07, "epoch": 4.2727272727272725, "percentage": 85.45, "elapsed_time": "1:15:41", "remaining_time": "0:12:53", "throughput": 5171.65, "total_tokens": 23486464} {"current_steps": 5735, "total_steps": 6710, "loss": 0.1055, "lr": 1.279938648554424e-07, "epoch": 4.273472429210134, "percentage": 85.47, "elapsed_time": "1:15:42", "remaining_time": "0:12:52", "throughput": 5171.66, "total_tokens": 23490560} {"current_steps": 5736, "total_steps": 6710, "loss": 0.0705, "lr": 1.2773601152683945e-07, "epoch": 4.274217585692996, "percentage": 85.48, "elapsed_time": "1:15:42", "remaining_time": "0:12:51", "throughput": 5171.67, "total_tokens": 23494656} {"current_steps": 5737, "total_steps": 6710, "loss": 0.142, "lr": 1.2747840420651622e-07, "epoch": 4.274962742175857, "percentage": 85.5, "elapsed_time": "1:15:43", "remaining_time": "0:12:50", "throughput": 5171.68, "total_tokens": 23498752} {"current_steps": 5738, "total_steps": 6710, "loss": 0.0347, "lr": 1.2722104295094255e-07, "epoch": 4.275707898658719, "percentage": 85.51, "elapsed_time": "1:15:44", "remaining_time": "0:12:49", "throughput": 5171.69, "total_tokens": 23502848} {"current_steps": 5739, "total_steps": 6710, "loss": 0.0558, "lr": 1.2696392781653327e-07, "epoch": 4.276453055141579, "percentage": 85.53, "elapsed_time": "1:15:45", "remaining_time": "0:12:49", "throughput": 5171.7, "total_tokens": 23506944} {"current_steps": 5740, "total_steps": 6710, "loss": 0.0282, "lr": 1.2670705885965056e-07, "epoch": 4.277198211624441, "percentage": 85.54, "elapsed_time": "1:15:46", "remaining_time": "0:12:48", "throughput": 5171.71, "total_tokens": 23511040} {"current_steps": 5741, "total_steps": 6710, "loss": 0.1982, "lr": 1.264504361366016e-07, "epoch": 4.2779433681073025, "percentage": 85.56, "elapsed_time": "1:15:46", "remaining_time": "0:12:47", "throughput": 5171.72, "total_tokens": 23515136} {"current_steps": 5742, "total_steps": 6710, "loss": 0.0781, "lr": 1.2619405970363956e-07, "epoch": 4.278688524590164, "percentage": 85.57, "elapsed_time": "1:15:47", "remaining_time": "0:12:46", "throughput": 5171.74, "total_tokens": 23519232} {"current_steps": 5743, "total_steps": 6710, "loss": 0.0724, "lr": 1.2593792961696467e-07, "epoch": 4.279433681073026, "percentage": 85.59, "elapsed_time": "1:15:48", "remaining_time": "0:12:45", "throughput": 5171.75, "total_tokens": 23523328} {"current_steps": 5744, "total_steps": 6710, "loss": 0.0404, "lr": 1.2568204593272182e-07, "epoch": 4.280178837555887, "percentage": 85.6, "elapsed_time": "1:15:49", "remaining_time": "0:12:45", "throughput": 5171.75, "total_tokens": 23527424} {"current_steps": 5745, "total_steps": 6710, "loss": 0.102, "lr": 1.25426408707003e-07, "epoch": 4.280923994038748, "percentage": 85.62, "elapsed_time": "1:15:50", "remaining_time": "0:12:44", "throughput": 5171.76, "total_tokens": 23531520} {"current_steps": 5746, "total_steps": 6710, "loss": 0.0524, "lr": 1.2517101799584542e-07, "epoch": 4.281669150521609, "percentage": 85.63, "elapsed_time": "1:15:50", "remaining_time": "0:12:43", "throughput": 5171.77, "total_tokens": 23535616} {"current_steps": 5747, "total_steps": 6710, "loss": 0.0298, "lr": 1.249158738552332e-07, "epoch": 4.282414307004471, "percentage": 85.65, "elapsed_time": "1:15:51", "remaining_time": "0:12:42", "throughput": 5171.78, "total_tokens": 23539712} {"current_steps": 5748, "total_steps": 6710, "loss": 0.1002, "lr": 1.2466097634109485e-07, "epoch": 4.2831594634873325, "percentage": 85.66, "elapsed_time": "1:15:52", "remaining_time": "0:12:41", "throughput": 5171.79, "total_tokens": 23543808} {"current_steps": 5749, "total_steps": 6710, "loss": 0.0887, "lr": 1.2440632550930614e-07, "epoch": 4.283904619970194, "percentage": 85.68, "elapsed_time": "1:15:53", "remaining_time": "0:12:41", "throughput": 5171.8, "total_tokens": 23547904} {"current_steps": 5750, "total_steps": 6710, "loss": 0.0418, "lr": 1.2415192141568819e-07, "epoch": 4.284649776453055, "percentage": 85.69, "elapsed_time": "1:15:53", "remaining_time": "0:12:40", "throughput": 5171.81, "total_tokens": 23552000} {"current_steps": 5751, "total_steps": 6710, "loss": 0.1683, "lr": 1.238977641160087e-07, "epoch": 4.285394932935916, "percentage": 85.71, "elapsed_time": "1:15:54", "remaining_time": "0:12:39", "throughput": 5171.82, "total_tokens": 23556096} {"current_steps": 5752, "total_steps": 6710, "loss": 0.0718, "lr": 1.2364385366598023e-07, "epoch": 4.286140089418778, "percentage": 85.72, "elapsed_time": "1:15:55", "remaining_time": "0:12:38", "throughput": 5171.83, "total_tokens": 23560192} {"current_steps": 5753, "total_steps": 6710, "loss": 0.0611, "lr": 1.2339019012126182e-07, "epoch": 4.286885245901639, "percentage": 85.74, "elapsed_time": "1:15:56", "remaining_time": "0:12:37", "throughput": 5171.84, "total_tokens": 23564288} {"current_steps": 5754, "total_steps": 6710, "loss": 0.0579, "lr": 1.2313677353745863e-07, "epoch": 4.287630402384501, "percentage": 85.75, "elapsed_time": "1:15:57", "remaining_time": "0:12:37", "throughput": 5171.85, "total_tokens": 23568384} {"current_steps": 5755, "total_steps": 6710, "loss": 0.0274, "lr": 1.2288360397012104e-07, "epoch": 4.288375558867362, "percentage": 85.77, "elapsed_time": "1:15:57", "remaining_time": "0:12:36", "throughput": 5171.86, "total_tokens": 23572480} {"current_steps": 5756, "total_steps": 6710, "loss": 0.1147, "lr": 1.2263068147474592e-07, "epoch": 4.289120715350224, "percentage": 85.78, "elapsed_time": "1:15:58", "remaining_time": "0:12:35", "throughput": 5171.87, "total_tokens": 23576576} {"current_steps": 5757, "total_steps": 6710, "loss": 0.0667, "lr": 1.2237800610677545e-07, "epoch": 4.289865871833085, "percentage": 85.8, "elapsed_time": "1:15:59", "remaining_time": "0:12:34", "throughput": 5171.87, "total_tokens": 23580672} {"current_steps": 5758, "total_steps": 6710, "loss": 0.091, "lr": 1.221255779215981e-07, "epoch": 4.290611028315946, "percentage": 85.81, "elapsed_time": "1:16:00", "remaining_time": "0:12:33", "throughput": 5171.87, "total_tokens": 23584768} {"current_steps": 5759, "total_steps": 6710, "loss": 0.1346, "lr": 1.218733969745478e-07, "epoch": 4.291356184798808, "percentage": 85.83, "elapsed_time": "1:16:00", "remaining_time": "0:12:33", "throughput": 5171.88, "total_tokens": 23588864} {"current_steps": 5760, "total_steps": 6710, "loss": 0.0313, "lr": 1.2162146332090424e-07, "epoch": 4.292101341281669, "percentage": 85.84, "elapsed_time": "1:16:01", "remaining_time": "0:12:32", "throughput": 5171.88, "total_tokens": 23592960} {"current_steps": 5761, "total_steps": 6710, "loss": 0.0579, "lr": 1.2136977701589377e-07, "epoch": 4.292846497764531, "percentage": 85.86, "elapsed_time": "1:16:02", "remaining_time": "0:12:31", "throughput": 5171.89, "total_tokens": 23597056} {"current_steps": 5762, "total_steps": 6710, "loss": 0.0838, "lr": 1.2111833811468675e-07, "epoch": 4.2935916542473915, "percentage": 85.87, "elapsed_time": "1:16:03", "remaining_time": "0:12:30", "throughput": 5171.9, "total_tokens": 23601152} {"current_steps": 5763, "total_steps": 6710, "loss": 0.1343, "lr": 1.2086714667240124e-07, "epoch": 4.294336810730253, "percentage": 85.89, "elapsed_time": "1:16:04", "remaining_time": "0:12:29", "throughput": 5171.91, "total_tokens": 23605248} {"current_steps": 5764, "total_steps": 6710, "loss": 0.0368, "lr": 1.2061620274409977e-07, "epoch": 4.295081967213115, "percentage": 85.9, "elapsed_time": "1:16:04", "remaining_time": "0:12:29", "throughput": 5171.92, "total_tokens": 23609344} {"current_steps": 5765, "total_steps": 6710, "loss": 0.1502, "lr": 1.2036550638479125e-07, "epoch": 4.295827123695976, "percentage": 85.92, "elapsed_time": "1:16:05", "remaining_time": "0:12:28", "throughput": 5171.93, "total_tokens": 23613440} {"current_steps": 5766, "total_steps": 6710, "loss": 0.1131, "lr": 1.201150576494299e-07, "epoch": 4.296572280178838, "percentage": 85.93, "elapsed_time": "1:16:06", "remaining_time": "0:12:27", "throughput": 5171.94, "total_tokens": 23617536} {"current_steps": 5767, "total_steps": 6710, "loss": 0.0405, "lr": 1.1986485659291626e-07, "epoch": 4.297317436661699, "percentage": 85.95, "elapsed_time": "1:16:07", "remaining_time": "0:12:26", "throughput": 5171.95, "total_tokens": 23621632} {"current_steps": 5768, "total_steps": 6710, "loss": 0.1654, "lr": 1.1961490327009564e-07, "epoch": 4.29806259314456, "percentage": 85.96, "elapsed_time": "1:16:08", "remaining_time": "0:12:26", "throughput": 5171.96, "total_tokens": 23625728} {"current_steps": 5769, "total_steps": 6710, "loss": 0.0098, "lr": 1.1936519773576017e-07, "epoch": 4.2988077496274215, "percentage": 85.98, "elapsed_time": "1:16:08", "remaining_time": "0:12:25", "throughput": 5171.97, "total_tokens": 23629824} {"current_steps": 5770, "total_steps": 6710, "loss": 0.0267, "lr": 1.1911574004464687e-07, "epoch": 4.299552906110283, "percentage": 85.99, "elapsed_time": "1:16:09", "remaining_time": "0:12:24", "throughput": 5171.97, "total_tokens": 23633920} {"current_steps": 5771, "total_steps": 6710, "loss": 0.0885, "lr": 1.1886653025143816e-07, "epoch": 4.300298062593145, "percentage": 86.01, "elapsed_time": "1:16:10", "remaining_time": "0:12:23", "throughput": 5171.98, "total_tokens": 23638016} {"current_steps": 5772, "total_steps": 6710, "loss": 0.0634, "lr": 1.186175684107635e-07, "epoch": 4.301043219076006, "percentage": 86.02, "elapsed_time": "1:16:11", "remaining_time": "0:12:22", "throughput": 5171.99, "total_tokens": 23642112} {"current_steps": 5773, "total_steps": 6710, "loss": 0.0723, "lr": 1.1836885457719618e-07, "epoch": 4.301788375558868, "percentage": 86.04, "elapsed_time": "1:16:11", "remaining_time": "0:12:22", "throughput": 5172.0, "total_tokens": 23646208} {"current_steps": 5774, "total_steps": 6710, "loss": 0.1378, "lr": 1.181203888052572e-07, "epoch": 4.302533532041728, "percentage": 86.05, "elapsed_time": "1:16:12", "remaining_time": "0:12:21", "throughput": 5172.0, "total_tokens": 23650304} {"current_steps": 5775, "total_steps": 6710, "loss": 0.2264, "lr": 1.1787217114941075e-07, "epoch": 4.30327868852459, "percentage": 86.07, "elapsed_time": "1:16:13", "remaining_time": "0:12:20", "throughput": 5172.01, "total_tokens": 23654400} {"current_steps": 5776, "total_steps": 6710, "loss": 0.0603, "lr": 1.176242016640687e-07, "epoch": 4.3040238450074515, "percentage": 86.08, "elapsed_time": "1:16:14", "remaining_time": "0:12:19", "throughput": 5172.03, "total_tokens": 23658496} {"current_steps": 5777, "total_steps": 6710, "loss": 0.11, "lr": 1.1737648040358735e-07, "epoch": 4.304769001490313, "percentage": 86.1, "elapsed_time": "1:16:15", "remaining_time": "0:12:18", "throughput": 5172.03, "total_tokens": 23662592} {"current_steps": 5778, "total_steps": 6710, "loss": 0.0642, "lr": 1.1712900742226933e-07, "epoch": 4.305514157973175, "percentage": 86.11, "elapsed_time": "1:16:15", "remaining_time": "0:12:18", "throughput": 5172.03, "total_tokens": 23666688} {"current_steps": 5779, "total_steps": 6710, "loss": 0.0867, "lr": 1.1688178277436236e-07, "epoch": 4.306259314456036, "percentage": 86.13, "elapsed_time": "1:16:16", "remaining_time": "0:12:17", "throughput": 5172.04, "total_tokens": 23670784} {"current_steps": 5780, "total_steps": 6710, "loss": 0.1668, "lr": 1.1663480651405962e-07, "epoch": 4.307004470938897, "percentage": 86.14, "elapsed_time": "1:16:17", "remaining_time": "0:12:16", "throughput": 5172.05, "total_tokens": 23674880} {"current_steps": 5781, "total_steps": 6710, "loss": 0.062, "lr": 1.1638807869550032e-07, "epoch": 4.307749627421758, "percentage": 86.15, "elapsed_time": "1:16:18", "remaining_time": "0:12:15", "throughput": 5172.05, "total_tokens": 23678976} {"current_steps": 5782, "total_steps": 6710, "loss": 0.1565, "lr": 1.1614159937276881e-07, "epoch": 4.30849478390462, "percentage": 86.17, "elapsed_time": "1:16:19", "remaining_time": "0:12:14", "throughput": 5172.06, "total_tokens": 23683072} {"current_steps": 5783, "total_steps": 6710, "loss": 0.0396, "lr": 1.1589536859989537e-07, "epoch": 4.3092399403874815, "percentage": 86.18, "elapsed_time": "1:16:19", "remaining_time": "0:12:14", "throughput": 5172.06, "total_tokens": 23687168} {"current_steps": 5784, "total_steps": 6710, "loss": 0.1147, "lr": 1.15649386430855e-07, "epoch": 4.309985096870343, "percentage": 86.2, "elapsed_time": "1:16:20", "remaining_time": "0:12:13", "throughput": 5172.05, "total_tokens": 23691264} {"current_steps": 5785, "total_steps": 6710, "loss": 0.0988, "lr": 1.1540365291956942e-07, "epoch": 4.310730253353205, "percentage": 86.21, "elapsed_time": "1:16:21", "remaining_time": "0:12:12", "throughput": 5172.03, "total_tokens": 23695360} {"current_steps": 5786, "total_steps": 6710, "loss": 0.1019, "lr": 1.1515816811990488e-07, "epoch": 4.311475409836065, "percentage": 86.23, "elapsed_time": "1:16:22", "remaining_time": "0:12:11", "throughput": 5172.03, "total_tokens": 23699456} {"current_steps": 5787, "total_steps": 6710, "loss": 0.1257, "lr": 1.1491293208567317e-07, "epoch": 4.312220566318927, "percentage": 86.24, "elapsed_time": "1:16:23", "remaining_time": "0:12:10", "throughput": 5172.03, "total_tokens": 23703552} {"current_steps": 5788, "total_steps": 6710, "loss": 0.0617, "lr": 1.1466794487063226e-07, "epoch": 4.312965722801788, "percentage": 86.26, "elapsed_time": "1:16:23", "remaining_time": "0:12:10", "throughput": 5172.03, "total_tokens": 23707648} {"current_steps": 5789, "total_steps": 6710, "loss": 0.0903, "lr": 1.1442320652848476e-07, "epoch": 4.31371087928465, "percentage": 86.27, "elapsed_time": "1:16:24", "remaining_time": "0:12:09", "throughput": 5172.04, "total_tokens": 23711744} {"current_steps": 5790, "total_steps": 6710, "loss": 0.0888, "lr": 1.1417871711287914e-07, "epoch": 4.3144560357675115, "percentage": 86.29, "elapsed_time": "1:16:25", "remaining_time": "0:12:08", "throughput": 5172.04, "total_tokens": 23715840} {"current_steps": 5791, "total_steps": 6710, "loss": 0.1925, "lr": 1.1393447667740907e-07, "epoch": 4.315201192250372, "percentage": 86.3, "elapsed_time": "1:16:26", "remaining_time": "0:12:07", "throughput": 5172.05, "total_tokens": 23719936} {"current_steps": 5792, "total_steps": 6710, "loss": 0.098, "lr": 1.1369048527561405e-07, "epoch": 4.315946348733234, "percentage": 86.32, "elapsed_time": "1:16:26", "remaining_time": "0:12:07", "throughput": 5172.05, "total_tokens": 23724032} {"current_steps": 5793, "total_steps": 6710, "loss": 0.0424, "lr": 1.1344674296097855e-07, "epoch": 4.316691505216095, "percentage": 86.33, "elapsed_time": "1:16:27", "remaining_time": "0:12:06", "throughput": 5172.06, "total_tokens": 23728128} {"current_steps": 5794, "total_steps": 6710, "loss": 0.0441, "lr": 1.1320324978693286e-07, "epoch": 4.317436661698957, "percentage": 86.35, "elapsed_time": "1:16:28", "remaining_time": "0:12:05", "throughput": 5172.07, "total_tokens": 23732224} {"current_steps": 5795, "total_steps": 6710, "loss": 0.023, "lr": 1.1296000580685196e-07, "epoch": 4.318181818181818, "percentage": 86.36, "elapsed_time": "1:16:29", "remaining_time": "0:12:04", "throughput": 5172.08, "total_tokens": 23736320} {"current_steps": 5796, "total_steps": 6710, "loss": 0.0883, "lr": 1.1271701107405732e-07, "epoch": 4.31892697466468, "percentage": 86.38, "elapsed_time": "1:16:30", "remaining_time": "0:12:03", "throughput": 5172.08, "total_tokens": 23740416} {"current_steps": 5797, "total_steps": 6710, "loss": 0.0584, "lr": 1.124742656418147e-07, "epoch": 4.3196721311475414, "percentage": 86.39, "elapsed_time": "1:16:30", "remaining_time": "0:12:03", "throughput": 5172.09, "total_tokens": 23744512} {"current_steps": 5798, "total_steps": 6710, "loss": 0.1337, "lr": 1.1223176956333556e-07, "epoch": 4.320417287630402, "percentage": 86.41, "elapsed_time": "1:16:31", "remaining_time": "0:12:02", "throughput": 5172.1, "total_tokens": 23748608} {"current_steps": 5799, "total_steps": 6710, "loss": 0.0279, "lr": 1.1198952289177709e-07, "epoch": 4.321162444113264, "percentage": 86.42, "elapsed_time": "1:16:32", "remaining_time": "0:12:01", "throughput": 5172.11, "total_tokens": 23752704} {"current_steps": 5800, "total_steps": 6710, "loss": 0.0823, "lr": 1.1174752568024111e-07, "epoch": 4.321907600596125, "percentage": 86.44, "elapsed_time": "1:16:33", "remaining_time": "0:12:00", "throughput": 5172.12, "total_tokens": 23756800} {"current_steps": 5801, "total_steps": 6710, "loss": 0.0555, "lr": 1.1150577798177575e-07, "epoch": 4.322652757078987, "percentage": 86.45, "elapsed_time": "1:16:34", "remaining_time": "0:11:59", "throughput": 5172.13, "total_tokens": 23760896} {"current_steps": 5802, "total_steps": 6710, "loss": 0.0745, "lr": 1.1126427984937308e-07, "epoch": 4.323397913561848, "percentage": 86.47, "elapsed_time": "1:16:34", "remaining_time": "0:11:59", "throughput": 5172.14, "total_tokens": 23764992} {"current_steps": 5803, "total_steps": 6710, "loss": 0.0926, "lr": 1.110230313359717e-07, "epoch": 4.324143070044709, "percentage": 86.48, "elapsed_time": "1:16:35", "remaining_time": "0:11:58", "throughput": 5172.15, "total_tokens": 23769088} {"current_steps": 5804, "total_steps": 6710, "loss": 0.0191, "lr": 1.1078203249445474e-07, "epoch": 4.3248882265275705, "percentage": 86.5, "elapsed_time": "1:16:36", "remaining_time": "0:11:57", "throughput": 5172.16, "total_tokens": 23773184} {"current_steps": 5805, "total_steps": 6710, "loss": 0.0487, "lr": 1.1054128337765119e-07, "epoch": 4.325633383010432, "percentage": 86.51, "elapsed_time": "1:16:37", "remaining_time": "0:11:56", "throughput": 5172.17, "total_tokens": 23777280} {"current_steps": 5806, "total_steps": 6710, "loss": 0.0498, "lr": 1.103007840383348e-07, "epoch": 4.326378539493294, "percentage": 86.53, "elapsed_time": "1:16:37", "remaining_time": "0:11:55", "throughput": 5172.18, "total_tokens": 23781376} {"current_steps": 5807, "total_steps": 6710, "loss": 0.0293, "lr": 1.1006053452922452e-07, "epoch": 4.327123695976155, "percentage": 86.54, "elapsed_time": "1:16:38", "remaining_time": "0:11:55", "throughput": 5172.19, "total_tokens": 23785472} {"current_steps": 5808, "total_steps": 6710, "loss": 0.0105, "lr": 1.0982053490298517e-07, "epoch": 4.327868852459017, "percentage": 86.56, "elapsed_time": "1:16:39", "remaining_time": "0:11:54", "throughput": 5172.2, "total_tokens": 23789568} {"current_steps": 5809, "total_steps": 6710, "loss": 0.0104, "lr": 1.095807852122259e-07, "epoch": 4.328614008941877, "percentage": 86.57, "elapsed_time": "1:16:40", "remaining_time": "0:11:53", "throughput": 5172.21, "total_tokens": 23793664} {"current_steps": 5810, "total_steps": 6710, "loss": 0.0473, "lr": 1.0934128550950204e-07, "epoch": 4.329359165424739, "percentage": 86.59, "elapsed_time": "1:16:41", "remaining_time": "0:11:52", "throughput": 5172.22, "total_tokens": 23797760} {"current_steps": 5811, "total_steps": 6710, "loss": 0.0565, "lr": 1.0910203584731328e-07, "epoch": 4.3301043219076005, "percentage": 86.6, "elapsed_time": "1:16:41", "remaining_time": "0:11:51", "throughput": 5172.23, "total_tokens": 23801856} {"current_steps": 5812, "total_steps": 6710, "loss": 0.145, "lr": 1.0886303627810512e-07, "epoch": 4.330849478390462, "percentage": 86.62, "elapsed_time": "1:16:42", "remaining_time": "0:11:51", "throughput": 5172.24, "total_tokens": 23805952} {"current_steps": 5813, "total_steps": 6710, "loss": 0.1182, "lr": 1.0862428685426806e-07, "epoch": 4.331594634873324, "percentage": 86.63, "elapsed_time": "1:16:43", "remaining_time": "0:11:50", "throughput": 5172.25, "total_tokens": 23810048} {"current_steps": 5814, "total_steps": 6710, "loss": 0.0086, "lr": 1.0838578762813732e-07, "epoch": 4.332339791356185, "percentage": 86.65, "elapsed_time": "1:16:44", "remaining_time": "0:11:49", "throughput": 5172.26, "total_tokens": 23814144} {"current_steps": 5815, "total_steps": 6710, "loss": 0.0255, "lr": 1.0814753865199354e-07, "epoch": 4.333084947839046, "percentage": 86.66, "elapsed_time": "1:16:44", "remaining_time": "0:11:48", "throughput": 5172.27, "total_tokens": 23818240} {"current_steps": 5816, "total_steps": 6710, "loss": 0.0235, "lr": 1.0790953997806316e-07, "epoch": 4.333830104321907, "percentage": 86.68, "elapsed_time": "1:16:45", "remaining_time": "0:11:47", "throughput": 5172.28, "total_tokens": 23822336} {"current_steps": 5817, "total_steps": 6710, "loss": 0.0885, "lr": 1.0767179165851683e-07, "epoch": 4.334575260804769, "percentage": 86.69, "elapsed_time": "1:16:46", "remaining_time": "0:11:47", "throughput": 5172.28, "total_tokens": 23826432} {"current_steps": 5818, "total_steps": 6710, "loss": 0.0558, "lr": 1.0743429374547045e-07, "epoch": 4.3353204172876305, "percentage": 86.71, "elapsed_time": "1:16:47", "remaining_time": "0:11:46", "throughput": 5172.29, "total_tokens": 23830528} {"current_steps": 5819, "total_steps": 6710, "loss": 0.1669, "lr": 1.0719704629098577e-07, "epoch": 4.336065573770492, "percentage": 86.72, "elapsed_time": "1:16:48", "remaining_time": "0:11:45", "throughput": 5172.3, "total_tokens": 23834624} {"current_steps": 5820, "total_steps": 6710, "loss": 0.0766, "lr": 1.0696004934706878e-07, "epoch": 4.336810730253354, "percentage": 86.74, "elapsed_time": "1:16:48", "remaining_time": "0:11:44", "throughput": 5172.31, "total_tokens": 23838720} {"current_steps": 5821, "total_steps": 6710, "loss": 0.0057, "lr": 1.0672330296567113e-07, "epoch": 4.337555886736214, "percentage": 86.75, "elapsed_time": "1:16:49", "remaining_time": "0:11:44", "throughput": 5172.32, "total_tokens": 23842816} {"current_steps": 5822, "total_steps": 6710, "loss": 0.0925, "lr": 1.0648680719868895e-07, "epoch": 4.338301043219076, "percentage": 86.77, "elapsed_time": "1:16:50", "remaining_time": "0:11:43", "throughput": 5172.33, "total_tokens": 23846912} {"current_steps": 5823, "total_steps": 6710, "loss": 0.0231, "lr": 1.0625056209796425e-07, "epoch": 4.339046199701937, "percentage": 86.78, "elapsed_time": "1:16:51", "remaining_time": "0:11:42", "throughput": 5172.34, "total_tokens": 23851008} {"current_steps": 5824, "total_steps": 6710, "loss": 0.0461, "lr": 1.0601456771528351e-07, "epoch": 4.339791356184799, "percentage": 86.8, "elapsed_time": "1:16:52", "remaining_time": "0:11:41", "throughput": 5172.35, "total_tokens": 23855104} {"current_steps": 5825, "total_steps": 6710, "loss": 0.0504, "lr": 1.0577882410237814e-07, "epoch": 4.3405365126676605, "percentage": 86.81, "elapsed_time": "1:16:52", "remaining_time": "0:11:40", "throughput": 5172.36, "total_tokens": 23859200} {"current_steps": 5826, "total_steps": 6710, "loss": 0.13, "lr": 1.0554333131092511e-07, "epoch": 4.341281669150522, "percentage": 86.83, "elapsed_time": "1:16:53", "remaining_time": "0:11:40", "throughput": 5172.35, "total_tokens": 23863296} {"current_steps": 5827, "total_steps": 6710, "loss": 0.075, "lr": 1.0530808939254581e-07, "epoch": 4.342026825633383, "percentage": 86.84, "elapsed_time": "1:16:54", "remaining_time": "0:11:39", "throughput": 5172.36, "total_tokens": 23867392} {"current_steps": 5828, "total_steps": 6710, "loss": 0.083, "lr": 1.0507309839880756e-07, "epoch": 4.342771982116244, "percentage": 86.86, "elapsed_time": "1:16:55", "remaining_time": "0:11:38", "throughput": 5172.37, "total_tokens": 23871488} {"current_steps": 5829, "total_steps": 6710, "loss": 0.0559, "lr": 1.0483835838122125e-07, "epoch": 4.343517138599106, "percentage": 86.87, "elapsed_time": "1:16:55", "remaining_time": "0:11:37", "throughput": 5172.37, "total_tokens": 23875584} {"current_steps": 5830, "total_steps": 6710, "loss": 0.0426, "lr": 1.046038693912442e-07, "epoch": 4.344262295081967, "percentage": 86.89, "elapsed_time": "1:16:56", "remaining_time": "0:11:36", "throughput": 5172.38, "total_tokens": 23879680} {"current_steps": 5831, "total_steps": 6710, "loss": 0.0302, "lr": 1.0436963148027765e-07, "epoch": 4.345007451564829, "percentage": 86.9, "elapsed_time": "1:16:57", "remaining_time": "0:11:36", "throughput": 5172.39, "total_tokens": 23883776} {"current_steps": 5832, "total_steps": 6710, "loss": 0.0233, "lr": 1.0413564469966858e-07, "epoch": 4.34575260804769, "percentage": 86.92, "elapsed_time": "1:16:58", "remaining_time": "0:11:35", "throughput": 5172.4, "total_tokens": 23887872} {"current_steps": 5833, "total_steps": 6710, "loss": 0.1163, "lr": 1.0390190910070846e-07, "epoch": 4.346497764530551, "percentage": 86.93, "elapsed_time": "1:16:59", "remaining_time": "0:11:34", "throughput": 5172.41, "total_tokens": 23891968} {"current_steps": 5834, "total_steps": 6710, "loss": 0.0244, "lr": 1.036684247346334e-07, "epoch": 4.347242921013413, "percentage": 86.94, "elapsed_time": "1:16:59", "remaining_time": "0:11:33", "throughput": 5172.41, "total_tokens": 23896064} {"current_steps": 5835, "total_steps": 6710, "loss": 0.0534, "lr": 1.034351916526255e-07, "epoch": 4.347988077496274, "percentage": 86.96, "elapsed_time": "1:17:00", "remaining_time": "0:11:32", "throughput": 5172.42, "total_tokens": 23900160} {"current_steps": 5836, "total_steps": 6710, "loss": 0.0871, "lr": 1.0320220990581054e-07, "epoch": 4.348733233979136, "percentage": 86.97, "elapsed_time": "1:17:01", "remaining_time": "0:11:32", "throughput": 5172.43, "total_tokens": 23904256} {"current_steps": 5837, "total_steps": 6710, "loss": 0.0542, "lr": 1.0296947954526015e-07, "epoch": 4.349478390461997, "percentage": 86.99, "elapsed_time": "1:17:02", "remaining_time": "0:11:31", "throughput": 5172.45, "total_tokens": 23908352} {"current_steps": 5838, "total_steps": 6710, "loss": 0.0078, "lr": 1.0273700062199035e-07, "epoch": 4.350223546944858, "percentage": 87.0, "elapsed_time": "1:17:03", "remaining_time": "0:11:30", "throughput": 5172.46, "total_tokens": 23912448} {"current_steps": 5839, "total_steps": 6710, "loss": 0.0197, "lr": 1.0250477318696231e-07, "epoch": 4.35096870342772, "percentage": 87.02, "elapsed_time": "1:17:03", "remaining_time": "0:11:29", "throughput": 5172.47, "total_tokens": 23916544} {"current_steps": 5840, "total_steps": 6710, "loss": 0.0358, "lr": 1.0227279729108184e-07, "epoch": 4.351713859910581, "percentage": 87.03, "elapsed_time": "1:17:04", "remaining_time": "0:11:28", "throughput": 5172.47, "total_tokens": 23920640} {"current_steps": 5841, "total_steps": 6710, "loss": 0.0381, "lr": 1.0204107298519964e-07, "epoch": 4.352459016393443, "percentage": 87.05, "elapsed_time": "1:17:05", "remaining_time": "0:11:28", "throughput": 5172.48, "total_tokens": 23924736} {"current_steps": 5842, "total_steps": 6710, "loss": 0.1503, "lr": 1.0180960032011134e-07, "epoch": 4.353204172876304, "percentage": 87.06, "elapsed_time": "1:17:06", "remaining_time": "0:11:27", "throughput": 5172.49, "total_tokens": 23928832} {"current_steps": 5843, "total_steps": 6710, "loss": 0.0309, "lr": 1.015783793465576e-07, "epoch": 4.353949329359166, "percentage": 87.08, "elapsed_time": "1:17:06", "remaining_time": "0:11:26", "throughput": 5172.5, "total_tokens": 23932928} {"current_steps": 5844, "total_steps": 6710, "loss": 0.1143, "lr": 1.0134741011522357e-07, "epoch": 4.3546944858420265, "percentage": 87.09, "elapsed_time": "1:17:07", "remaining_time": "0:11:25", "throughput": 5172.51, "total_tokens": 23937024} {"current_steps": 5845, "total_steps": 6710, "loss": 0.0885, "lr": 1.0111669267673901e-07, "epoch": 4.355439642324888, "percentage": 87.11, "elapsed_time": "1:17:08", "remaining_time": "0:11:24", "throughput": 5172.52, "total_tokens": 23941120} {"current_steps": 5846, "total_steps": 6710, "loss": 0.0627, "lr": 1.0088622708167961e-07, "epoch": 4.35618479880775, "percentage": 87.12, "elapsed_time": "1:17:09", "remaining_time": "0:11:24", "throughput": 5172.54, "total_tokens": 23945216} {"current_steps": 5847, "total_steps": 6710, "loss": 0.1611, "lr": 1.0065601338056425e-07, "epoch": 4.356929955290611, "percentage": 87.14, "elapsed_time": "1:17:10", "remaining_time": "0:11:23", "throughput": 5172.54, "total_tokens": 23949312} {"current_steps": 5848, "total_steps": 6710, "loss": 0.1704, "lr": 1.004260516238581e-07, "epoch": 4.357675111773473, "percentage": 87.15, "elapsed_time": "1:17:10", "remaining_time": "0:11:22", "throughput": 5172.55, "total_tokens": 23953408} {"current_steps": 5849, "total_steps": 6710, "loss": 0.0156, "lr": 1.0019634186197003e-07, "epoch": 4.358420268256334, "percentage": 87.17, "elapsed_time": "1:17:11", "remaining_time": "0:11:21", "throughput": 5172.57, "total_tokens": 23957504} {"current_steps": 5850, "total_steps": 6710, "loss": 0.1878, "lr": 9.996688414525419e-08, "epoch": 4.359165424739195, "percentage": 87.18, "elapsed_time": "1:17:12", "remaining_time": "0:11:21", "throughput": 5172.58, "total_tokens": 23961600} {"current_steps": 5851, "total_steps": 6710, "loss": 0.0825, "lr": 9.973767852400936e-08, "epoch": 4.359910581222056, "percentage": 87.2, "elapsed_time": "1:17:13", "remaining_time": "0:11:20", "throughput": 5172.59, "total_tokens": 23965696} {"current_steps": 5852, "total_steps": 6710, "loss": 0.0221, "lr": 9.950872504847886e-08, "epoch": 4.360655737704918, "percentage": 87.21, "elapsed_time": "1:17:13", "remaining_time": "0:11:19", "throughput": 5172.6, "total_tokens": 23969792} {"current_steps": 5853, "total_steps": 6710, "loss": 0.0122, "lr": 9.928002376885127e-08, "epoch": 4.3614008941877795, "percentage": 87.23, "elapsed_time": "1:17:14", "remaining_time": "0:11:18", "throughput": 5172.6, "total_tokens": 23973888} {"current_steps": 5854, "total_steps": 6710, "loss": 0.1987, "lr": 9.905157473525898e-08, "epoch": 4.362146050670641, "percentage": 87.24, "elapsed_time": "1:17:15", "remaining_time": "0:11:17", "throughput": 5172.59, "total_tokens": 23977984} {"current_steps": 5855, "total_steps": 6710, "loss": 0.0464, "lr": 9.882337799778055e-08, "epoch": 4.362891207153503, "percentage": 87.26, "elapsed_time": "1:17:16", "remaining_time": "0:11:17", "throughput": 5172.6, "total_tokens": 23982080} {"current_steps": 5856, "total_steps": 6710, "loss": 0.0525, "lr": 9.85954336064375e-08, "epoch": 4.363636363636363, "percentage": 87.27, "elapsed_time": "1:17:17", "remaining_time": "0:11:16", "throughput": 5172.61, "total_tokens": 23986176} {"current_steps": 5857, "total_steps": 6710, "loss": 0.2091, "lr": 9.836774161119721e-08, "epoch": 4.364381520119225, "percentage": 87.29, "elapsed_time": "1:17:17", "remaining_time": "0:11:15", "throughput": 5172.62, "total_tokens": 23990272} {"current_steps": 5858, "total_steps": 6710, "loss": 0.0594, "lr": 9.814030206197117e-08, "epoch": 4.365126676602086, "percentage": 87.3, "elapsed_time": "1:17:18", "remaining_time": "0:11:14", "throughput": 5172.64, "total_tokens": 23994368} {"current_steps": 5859, "total_steps": 6710, "loss": 0.0351, "lr": 9.791311500861614e-08, "epoch": 4.365871833084948, "percentage": 87.32, "elapsed_time": "1:17:19", "remaining_time": "0:11:13", "throughput": 5172.65, "total_tokens": 23998464} {"current_steps": 5860, "total_steps": 6710, "loss": 0.0826, "lr": 9.76861805009327e-08, "epoch": 4.3666169895678095, "percentage": 87.33, "elapsed_time": "1:17:20", "remaining_time": "0:11:13", "throughput": 5172.66, "total_tokens": 24002560} {"current_steps": 5861, "total_steps": 6710, "loss": 0.0926, "lr": 9.745949858866705e-08, "epoch": 4.36736214605067, "percentage": 87.35, "elapsed_time": "1:17:21", "remaining_time": "0:11:12", "throughput": 5172.66, "total_tokens": 24006656} {"current_steps": 5862, "total_steps": 6710, "loss": 0.1162, "lr": 9.723306932150914e-08, "epoch": 4.368107302533532, "percentage": 87.36, "elapsed_time": "1:17:21", "remaining_time": "0:11:11", "throughput": 5172.67, "total_tokens": 24010752} {"current_steps": 5863, "total_steps": 6710, "loss": 0.1043, "lr": 9.700689274909373e-08, "epoch": 4.368852459016393, "percentage": 87.38, "elapsed_time": "1:17:22", "remaining_time": "0:11:10", "throughput": 5172.68, "total_tokens": 24014848} {"current_steps": 5864, "total_steps": 6710, "loss": 0.1337, "lr": 9.678096892100072e-08, "epoch": 4.369597615499255, "percentage": 87.39, "elapsed_time": "1:17:23", "remaining_time": "0:11:09", "throughput": 5172.68, "total_tokens": 24018944} {"current_steps": 5865, "total_steps": 6710, "loss": 0.2264, "lr": 9.655529788675385e-08, "epoch": 4.370342771982116, "percentage": 87.41, "elapsed_time": "1:17:24", "remaining_time": "0:11:09", "throughput": 5172.69, "total_tokens": 24023040} {"current_steps": 5866, "total_steps": 6710, "loss": 0.0878, "lr": 9.632987969582216e-08, "epoch": 4.371087928464978, "percentage": 87.42, "elapsed_time": "1:17:24", "remaining_time": "0:11:08", "throughput": 5172.7, "total_tokens": 24027136} {"current_steps": 5867, "total_steps": 6710, "loss": 0.1578, "lr": 9.610471439761862e-08, "epoch": 4.3718330849478395, "percentage": 87.44, "elapsed_time": "1:17:25", "remaining_time": "0:11:07", "throughput": 5172.7, "total_tokens": 24031232} {"current_steps": 5868, "total_steps": 6710, "loss": 0.0477, "lr": 9.587980204150166e-08, "epoch": 4.3725782414307, "percentage": 87.45, "elapsed_time": "1:17:26", "remaining_time": "0:11:06", "throughput": 5172.71, "total_tokens": 24035328} {"current_steps": 5869, "total_steps": 6710, "loss": 0.0418, "lr": 9.565514267677282e-08, "epoch": 4.373323397913562, "percentage": 87.47, "elapsed_time": "1:17:27", "remaining_time": "0:11:05", "throughput": 5172.72, "total_tokens": 24039424} {"current_steps": 5870, "total_steps": 6710, "loss": 0.0546, "lr": 9.543073635267977e-08, "epoch": 4.374068554396423, "percentage": 87.48, "elapsed_time": "1:17:28", "remaining_time": "0:11:05", "throughput": 5172.73, "total_tokens": 24043520} {"current_steps": 5871, "total_steps": 6710, "loss": 0.0875, "lr": 9.520658311841347e-08, "epoch": 4.374813710879285, "percentage": 87.5, "elapsed_time": "1:17:28", "remaining_time": "0:11:04", "throughput": 5172.73, "total_tokens": 24047616} {"current_steps": 5872, "total_steps": 6710, "loss": 0.0509, "lr": 9.498268302311001e-08, "epoch": 4.375558867362146, "percentage": 87.51, "elapsed_time": "1:17:29", "remaining_time": "0:11:03", "throughput": 5172.74, "total_tokens": 24051712} {"current_steps": 5873, "total_steps": 6710, "loss": 0.0952, "lr": 9.475903611585028e-08, "epoch": 4.376304023845007, "percentage": 87.53, "elapsed_time": "1:17:30", "remaining_time": "0:11:02", "throughput": 5172.75, "total_tokens": 24055808} {"current_steps": 5874, "total_steps": 6710, "loss": 0.0603, "lr": 9.453564244565866e-08, "epoch": 4.377049180327869, "percentage": 87.54, "elapsed_time": "1:17:31", "remaining_time": "0:11:01", "throughput": 5172.75, "total_tokens": 24059904} {"current_steps": 5875, "total_steps": 6710, "loss": 0.136, "lr": 9.43125020615053e-08, "epoch": 4.37779433681073, "percentage": 87.56, "elapsed_time": "1:17:32", "remaining_time": "0:11:01", "throughput": 5172.76, "total_tokens": 24064000} {"current_steps": 5876, "total_steps": 6710, "loss": 0.0622, "lr": 9.408961501230343e-08, "epoch": 4.378539493293592, "percentage": 87.57, "elapsed_time": "1:17:32", "remaining_time": "0:11:00", "throughput": 5172.77, "total_tokens": 24068096} {"current_steps": 5877, "total_steps": 6710, "loss": 0.1115, "lr": 9.38669813469123e-08, "epoch": 4.379284649776453, "percentage": 87.59, "elapsed_time": "1:17:33", "remaining_time": "0:10:59", "throughput": 5172.78, "total_tokens": 24072192} {"current_steps": 5878, "total_steps": 6710, "loss": 0.115, "lr": 9.364460111413426e-08, "epoch": 4.380029806259315, "percentage": 87.6, "elapsed_time": "1:17:34", "remaining_time": "0:10:58", "throughput": 5172.79, "total_tokens": 24076288} {"current_steps": 5879, "total_steps": 6710, "loss": 0.128, "lr": 9.342247436271657e-08, "epoch": 4.3807749627421755, "percentage": 87.62, "elapsed_time": "1:17:35", "remaining_time": "0:10:58", "throughput": 5172.8, "total_tokens": 24080384} {"current_steps": 5880, "total_steps": 6710, "loss": 0.123, "lr": 9.320060114135152e-08, "epoch": 4.381520119225037, "percentage": 87.63, "elapsed_time": "1:17:35", "remaining_time": "0:10:57", "throughput": 5172.81, "total_tokens": 24084480} {"current_steps": 5881, "total_steps": 6710, "loss": 0.1504, "lr": 9.297898149867466e-08, "epoch": 4.382265275707899, "percentage": 87.65, "elapsed_time": "1:17:36", "remaining_time": "0:10:56", "throughput": 5172.83, "total_tokens": 24088576} {"current_steps": 5882, "total_steps": 6710, "loss": 0.063, "lr": 9.275761548326739e-08, "epoch": 4.38301043219076, "percentage": 87.66, "elapsed_time": "1:17:37", "remaining_time": "0:10:55", "throughput": 5172.84, "total_tokens": 24092672} {"current_steps": 5883, "total_steps": 6710, "loss": 0.1991, "lr": 9.253650314365384e-08, "epoch": 4.383755588673622, "percentage": 87.68, "elapsed_time": "1:17:38", "remaining_time": "0:10:54", "throughput": 5172.81, "total_tokens": 24096768} {"current_steps": 5884, "total_steps": 6710, "loss": 0.1294, "lr": 9.231564452830396e-08, "epoch": 4.384500745156483, "percentage": 87.69, "elapsed_time": "1:17:39", "remaining_time": "0:10:54", "throughput": 5172.81, "total_tokens": 24100864} {"current_steps": 5885, "total_steps": 6710, "loss": 0.0544, "lr": 9.209503968563127e-08, "epoch": 4.385245901639344, "percentage": 87.7, "elapsed_time": "1:17:39", "remaining_time": "0:10:53", "throughput": 5172.81, "total_tokens": 24104960} {"current_steps": 5886, "total_steps": 6710, "loss": 0.1997, "lr": 9.187468866399429e-08, "epoch": 4.3859910581222055, "percentage": 87.72, "elapsed_time": "1:17:40", "remaining_time": "0:10:52", "throughput": 5172.82, "total_tokens": 24109056} {"current_steps": 5887, "total_steps": 6710, "loss": 0.1516, "lr": 9.165459151169509e-08, "epoch": 4.386736214605067, "percentage": 87.73, "elapsed_time": "1:17:41", "remaining_time": "0:10:51", "throughput": 5172.79, "total_tokens": 24113152} {"current_steps": 5888, "total_steps": 6710, "loss": 0.1395, "lr": 9.14347482769809e-08, "epoch": 4.387481371087929, "percentage": 87.75, "elapsed_time": "1:17:42", "remaining_time": "0:10:50", "throughput": 5172.78, "total_tokens": 24117248} {"current_steps": 5889, "total_steps": 6710, "loss": 0.0541, "lr": 9.12151590080429e-08, "epoch": 4.38822652757079, "percentage": 87.76, "elapsed_time": "1:17:43", "remaining_time": "0:10:50", "throughput": 5172.79, "total_tokens": 24121344} {"current_steps": 5890, "total_steps": 6710, "loss": 0.0903, "lr": 9.099582375301619e-08, "epoch": 4.388971684053652, "percentage": 87.78, "elapsed_time": "1:17:43", "remaining_time": "0:10:49", "throughput": 5172.8, "total_tokens": 24125440} {"current_steps": 5891, "total_steps": 6710, "loss": 0.0839, "lr": 9.077674255998121e-08, "epoch": 4.389716840536512, "percentage": 87.79, "elapsed_time": "1:17:44", "remaining_time": "0:10:48", "throughput": 5172.81, "total_tokens": 24129536} {"current_steps": 5892, "total_steps": 6710, "loss": 0.0167, "lr": 9.055791547696161e-08, "epoch": 4.390461997019374, "percentage": 87.81, "elapsed_time": "1:17:45", "remaining_time": "0:10:47", "throughput": 5172.82, "total_tokens": 24133632} {"current_steps": 5893, "total_steps": 6710, "loss": 0.1165, "lr": 9.033934255192625e-08, "epoch": 4.3912071535022354, "percentage": 87.82, "elapsed_time": "1:17:46", "remaining_time": "0:10:46", "throughput": 5172.83, "total_tokens": 24137728} {"current_steps": 5894, "total_steps": 6710, "loss": 0.0532, "lr": 9.012102383278765e-08, "epoch": 4.391952309985097, "percentage": 87.84, "elapsed_time": "1:17:47", "remaining_time": "0:10:46", "throughput": 5172.84, "total_tokens": 24141824} {"current_steps": 5895, "total_steps": 6710, "loss": 0.0353, "lr": 8.99029593674032e-08, "epoch": 4.3926974664679586, "percentage": 87.85, "elapsed_time": "1:17:47", "remaining_time": "0:10:45", "throughput": 5172.85, "total_tokens": 24145920} {"current_steps": 5896, "total_steps": 6710, "loss": 0.0849, "lr": 8.968514920357358e-08, "epoch": 4.39344262295082, "percentage": 87.87, "elapsed_time": "1:17:48", "remaining_time": "0:10:44", "throughput": 5172.85, "total_tokens": 24150016} {"current_steps": 5897, "total_steps": 6710, "loss": 0.0402, "lr": 8.946759338904473e-08, "epoch": 4.394187779433681, "percentage": 87.88, "elapsed_time": "1:17:49", "remaining_time": "0:10:43", "throughput": 5172.87, "total_tokens": 24154112} {"current_steps": 5898, "total_steps": 6710, "loss": 0.1097, "lr": 8.925029197150644e-08, "epoch": 4.394932935916542, "percentage": 87.9, "elapsed_time": "1:17:50", "remaining_time": "0:10:42", "throughput": 5172.87, "total_tokens": 24158208} {"current_steps": 5899, "total_steps": 6710, "loss": 0.0208, "lr": 8.903324499859242e-08, "epoch": 4.395678092399404, "percentage": 87.91, "elapsed_time": "1:17:50", "remaining_time": "0:10:42", "throughput": 5172.88, "total_tokens": 24162304} {"current_steps": 5900, "total_steps": 6710, "loss": 0.062, "lr": 8.88164525178814e-08, "epoch": 4.396423248882265, "percentage": 87.93, "elapsed_time": "1:17:51", "remaining_time": "0:10:41", "throughput": 5172.88, "total_tokens": 24166400} {"current_steps": 5901, "total_steps": 6710, "loss": 0.1509, "lr": 8.859991457689523e-08, "epoch": 4.397168405365127, "percentage": 87.94, "elapsed_time": "1:17:52", "remaining_time": "0:10:40", "throughput": 5172.88, "total_tokens": 24170496} {"current_steps": 5902, "total_steps": 6710, "loss": 0.1755, "lr": 8.838363122310123e-08, "epoch": 4.397913561847988, "percentage": 87.96, "elapsed_time": "1:17:53", "remaining_time": "0:10:39", "throughput": 5172.89, "total_tokens": 24174592} {"current_steps": 5903, "total_steps": 6710, "loss": 0.0992, "lr": 8.816760250390965e-08, "epoch": 4.398658718330849, "percentage": 87.97, "elapsed_time": "1:17:54", "remaining_time": "0:10:38", "throughput": 5172.88, "total_tokens": 24178688} {"current_steps": 5904, "total_steps": 6710, "loss": 0.0801, "lr": 8.79518284666761e-08, "epoch": 4.399403874813711, "percentage": 87.99, "elapsed_time": "1:17:54", "remaining_time": "0:10:38", "throughput": 5172.89, "total_tokens": 24182784} {"current_steps": 5905, "total_steps": 6710, "loss": 0.0624, "lr": 8.773630915869955e-08, "epoch": 4.400149031296572, "percentage": 88.0, "elapsed_time": "1:17:55", "remaining_time": "0:10:37", "throughput": 5172.89, "total_tokens": 24186880} {"current_steps": 5906, "total_steps": 6710, "loss": 0.1075, "lr": 8.752104462722317e-08, "epoch": 4.400894187779434, "percentage": 88.02, "elapsed_time": "1:17:56", "remaining_time": "0:10:36", "throughput": 5172.89, "total_tokens": 24190976} {"current_steps": 5907, "total_steps": 6710, "loss": 0.0685, "lr": 8.730603491943476e-08, "epoch": 4.401639344262295, "percentage": 88.03, "elapsed_time": "1:17:57", "remaining_time": "0:10:35", "throughput": 5172.89, "total_tokens": 24195072} {"current_steps": 5908, "total_steps": 6710, "loss": 0.0211, "lr": 8.709128008246568e-08, "epoch": 4.402384500745156, "percentage": 88.05, "elapsed_time": "1:17:58", "remaining_time": "0:10:35", "throughput": 5172.88, "total_tokens": 24199168} {"current_steps": 5909, "total_steps": 6710, "loss": 0.0667, "lr": 8.687678016339227e-08, "epoch": 4.403129657228018, "percentage": 88.06, "elapsed_time": "1:17:58", "remaining_time": "0:10:34", "throughput": 5172.88, "total_tokens": 24203264} {"current_steps": 5910, "total_steps": 6710, "loss": 0.0628, "lr": 8.666253520923373e-08, "epoch": 4.403874813710879, "percentage": 88.08, "elapsed_time": "1:17:59", "remaining_time": "0:10:33", "throughput": 5172.88, "total_tokens": 24207360} {"current_steps": 5911, "total_steps": 6710, "loss": 0.0497, "lr": 8.644854526695473e-08, "epoch": 4.404619970193741, "percentage": 88.09, "elapsed_time": "1:18:00", "remaining_time": "0:10:32", "throughput": 5172.89, "total_tokens": 24211456} {"current_steps": 5912, "total_steps": 6710, "loss": 0.1084, "lr": 8.623481038346287e-08, "epoch": 4.405365126676602, "percentage": 88.11, "elapsed_time": "1:18:01", "remaining_time": "0:10:31", "throughput": 5172.89, "total_tokens": 24215552} {"current_steps": 5913, "total_steps": 6710, "loss": 0.0645, "lr": 8.602133060561068e-08, "epoch": 4.406110283159464, "percentage": 88.12, "elapsed_time": "1:18:02", "remaining_time": "0:10:31", "throughput": 5172.88, "total_tokens": 24219648} {"current_steps": 5914, "total_steps": 6710, "loss": 0.0377, "lr": 8.580810598019434e-08, "epoch": 4.4068554396423245, "percentage": 88.14, "elapsed_time": "1:18:02", "remaining_time": "0:10:30", "throughput": 5172.88, "total_tokens": 24223744} {"current_steps": 5915, "total_steps": 6710, "loss": 0.0962, "lr": 8.559513655395438e-08, "epoch": 4.407600596125186, "percentage": 88.15, "elapsed_time": "1:18:03", "remaining_time": "0:10:29", "throughput": 5172.88, "total_tokens": 24227840} {"current_steps": 5916, "total_steps": 6710, "loss": 0.1001, "lr": 8.538242237357497e-08, "epoch": 4.408345752608048, "percentage": 88.17, "elapsed_time": "1:18:04", "remaining_time": "0:10:28", "throughput": 5172.88, "total_tokens": 24231936} {"current_steps": 5917, "total_steps": 6710, "loss": 0.0175, "lr": 8.516996348568465e-08, "epoch": 4.409090909090909, "percentage": 88.18, "elapsed_time": "1:18:05", "remaining_time": "0:10:27", "throughput": 5172.88, "total_tokens": 24236032} {"current_steps": 5918, "total_steps": 6710, "loss": 0.0869, "lr": 8.495775993685604e-08, "epoch": 4.409836065573771, "percentage": 88.2, "elapsed_time": "1:18:06", "remaining_time": "0:10:27", "throughput": 5172.88, "total_tokens": 24240128} {"current_steps": 5919, "total_steps": 6710, "loss": 0.0768, "lr": 8.474581177360553e-08, "epoch": 4.410581222056632, "percentage": 88.21, "elapsed_time": "1:18:06", "remaining_time": "0:10:26", "throughput": 5172.88, "total_tokens": 24244224} {"current_steps": 5920, "total_steps": 6710, "loss": 0.0762, "lr": 8.453411904239372e-08, "epoch": 4.411326378539493, "percentage": 88.23, "elapsed_time": "1:18:07", "remaining_time": "0:10:25", "throughput": 5172.88, "total_tokens": 24248320} {"current_steps": 5921, "total_steps": 6710, "loss": 0.0524, "lr": 8.432268178962518e-08, "epoch": 4.4120715350223545, "percentage": 88.24, "elapsed_time": "1:18:08", "remaining_time": "0:10:24", "throughput": 5172.88, "total_tokens": 24252416} {"current_steps": 5922, "total_steps": 6710, "loss": 0.0861, "lr": 8.411150006164881e-08, "epoch": 4.412816691505216, "percentage": 88.26, "elapsed_time": "1:18:09", "remaining_time": "0:10:23", "throughput": 5172.87, "total_tokens": 24256512} {"current_steps": 5923, "total_steps": 6710, "loss": 0.0989, "lr": 8.390057390475645e-08, "epoch": 4.413561847988078, "percentage": 88.27, "elapsed_time": "1:18:09", "remaining_time": "0:10:23", "throughput": 5172.87, "total_tokens": 24260608} {"current_steps": 5924, "total_steps": 6710, "loss": 0.1095, "lr": 8.368990336518515e-08, "epoch": 4.414307004470939, "percentage": 88.29, "elapsed_time": "1:18:10", "remaining_time": "0:10:22", "throughput": 5172.87, "total_tokens": 24264704} {"current_steps": 5925, "total_steps": 6710, "loss": 0.0744, "lr": 8.347948848911519e-08, "epoch": 4.415052160953801, "percentage": 88.3, "elapsed_time": "1:18:11", "remaining_time": "0:10:21", "throughput": 5172.87, "total_tokens": 24268800} {"current_steps": 5926, "total_steps": 6710, "loss": 0.1134, "lr": 8.326932932267093e-08, "epoch": 4.415797317436661, "percentage": 88.32, "elapsed_time": "1:18:12", "remaining_time": "0:10:20", "throughput": 5172.86, "total_tokens": 24272896} {"current_steps": 5927, "total_steps": 6710, "loss": 0.0323, "lr": 8.305942591192107e-08, "epoch": 4.416542473919523, "percentage": 88.33, "elapsed_time": "1:18:13", "remaining_time": "0:10:19", "throughput": 5172.86, "total_tokens": 24276992} {"current_steps": 5928, "total_steps": 6710, "loss": 0.0508, "lr": 8.284977830287755e-08, "epoch": 4.4172876304023845, "percentage": 88.35, "elapsed_time": "1:18:13", "remaining_time": "0:10:19", "throughput": 5172.86, "total_tokens": 24281088} {"current_steps": 5929, "total_steps": 6710, "loss": 0.1571, "lr": 8.264038654149694e-08, "epoch": 4.418032786885246, "percentage": 88.36, "elapsed_time": "1:18:14", "remaining_time": "0:10:18", "throughput": 5172.85, "total_tokens": 24285184} {"current_steps": 5930, "total_steps": 6710, "loss": 0.0186, "lr": 8.243125067367921e-08, "epoch": 4.418777943368108, "percentage": 88.38, "elapsed_time": "1:18:15", "remaining_time": "0:10:17", "throughput": 5172.85, "total_tokens": 24289280} {"current_steps": 5931, "total_steps": 6710, "loss": 0.096, "lr": 8.222237074526865e-08, "epoch": 4.419523099850968, "percentage": 88.39, "elapsed_time": "1:18:16", "remaining_time": "0:10:16", "throughput": 5172.85, "total_tokens": 24293376} {"current_steps": 5932, "total_steps": 6710, "loss": 0.0374, "lr": 8.201374680205306e-08, "epoch": 4.42026825633383, "percentage": 88.41, "elapsed_time": "1:18:17", "remaining_time": "0:10:16", "throughput": 5172.85, "total_tokens": 24297472} {"current_steps": 5933, "total_steps": 6710, "loss": 0.1365, "lr": 8.180537888976423e-08, "epoch": 4.421013412816691, "percentage": 88.42, "elapsed_time": "1:18:17", "remaining_time": "0:10:15", "throughput": 5172.85, "total_tokens": 24301568} {"current_steps": 5934, "total_steps": 6710, "loss": 0.0726, "lr": 8.159726705407822e-08, "epoch": 4.421758569299553, "percentage": 88.44, "elapsed_time": "1:18:18", "remaining_time": "0:10:14", "throughput": 5172.86, "total_tokens": 24305664} {"current_steps": 5935, "total_steps": 6710, "loss": 0.1825, "lr": 8.138941134061413e-08, "epoch": 4.4225037257824145, "percentage": 88.45, "elapsed_time": "1:18:19", "remaining_time": "0:10:13", "throughput": 5172.86, "total_tokens": 24309760} {"current_steps": 5936, "total_steps": 6710, "loss": 0.0667, "lr": 8.118181179493617e-08, "epoch": 4.423248882265276, "percentage": 88.46, "elapsed_time": "1:18:20", "remaining_time": "0:10:12", "throughput": 5172.86, "total_tokens": 24313856} {"current_steps": 5937, "total_steps": 6710, "loss": 0.1308, "lr": 8.097446846255061e-08, "epoch": 4.423994038748138, "percentage": 88.48, "elapsed_time": "1:18:21", "remaining_time": "0:10:12", "throughput": 5172.87, "total_tokens": 24317952} {"current_steps": 5938, "total_steps": 6710, "loss": 0.0806, "lr": 8.076738138890954e-08, "epoch": 4.424739195230998, "percentage": 88.49, "elapsed_time": "1:18:21", "remaining_time": "0:10:11", "throughput": 5172.87, "total_tokens": 24322048} {"current_steps": 5939, "total_steps": 6710, "loss": 0.1078, "lr": 8.056055061940724e-08, "epoch": 4.42548435171386, "percentage": 88.51, "elapsed_time": "1:18:22", "remaining_time": "0:10:10", "throughput": 5172.87, "total_tokens": 24326144} {"current_steps": 5940, "total_steps": 6710, "loss": 0.0695, "lr": 8.03539761993831e-08, "epoch": 4.426229508196721, "percentage": 88.52, "elapsed_time": "1:18:23", "remaining_time": "0:10:09", "throughput": 5172.88, "total_tokens": 24330240} {"current_steps": 5941, "total_steps": 6710, "loss": 0.0659, "lr": 8.01476581741191e-08, "epoch": 4.426974664679583, "percentage": 88.54, "elapsed_time": "1:18:24", "remaining_time": "0:10:08", "throughput": 5172.88, "total_tokens": 24334336} {"current_steps": 5942, "total_steps": 6710, "loss": 0.0959, "lr": 7.994159658884213e-08, "epoch": 4.4277198211624444, "percentage": 88.55, "elapsed_time": "1:18:25", "remaining_time": "0:10:08", "throughput": 5172.88, "total_tokens": 24338432} {"current_steps": 5943, "total_steps": 6710, "loss": 0.1182, "lr": 7.973579148872216e-08, "epoch": 4.428464977645305, "percentage": 88.57, "elapsed_time": "1:18:25", "remaining_time": "0:10:07", "throughput": 5172.89, "total_tokens": 24342528} {"current_steps": 5944, "total_steps": 6710, "loss": 0.1199, "lr": 7.953024291887282e-08, "epoch": 4.429210134128167, "percentage": 88.58, "elapsed_time": "1:18:26", "remaining_time": "0:10:06", "throughput": 5172.9, "total_tokens": 24346624} {"current_steps": 5945, "total_steps": 6710, "loss": 0.1305, "lr": 7.932495092435252e-08, "epoch": 4.429955290611028, "percentage": 88.6, "elapsed_time": "1:18:27", "remaining_time": "0:10:05", "throughput": 5172.9, "total_tokens": 24350720} {"current_steps": 5946, "total_steps": 6710, "loss": 0.0498, "lr": 7.911991555016208e-08, "epoch": 4.43070044709389, "percentage": 88.61, "elapsed_time": "1:18:28", "remaining_time": "0:10:04", "throughput": 5172.91, "total_tokens": 24354816} {"current_steps": 5947, "total_steps": 6710, "loss": 0.0638, "lr": 7.891513684124704e-08, "epoch": 4.431445603576751, "percentage": 88.63, "elapsed_time": "1:18:28", "remaining_time": "0:10:04", "throughput": 5172.91, "total_tokens": 24358912} {"current_steps": 5948, "total_steps": 6710, "loss": 0.054, "lr": 7.871061484249626e-08, "epoch": 4.432190760059613, "percentage": 88.64, "elapsed_time": "1:18:29", "remaining_time": "0:10:03", "throughput": 5172.92, "total_tokens": 24363008} {"current_steps": 5949, "total_steps": 6710, "loss": 0.0145, "lr": 7.850634959874286e-08, "epoch": 4.4329359165424735, "percentage": 88.66, "elapsed_time": "1:18:30", "remaining_time": "0:10:02", "throughput": 5172.91, "total_tokens": 24367104} {"current_steps": 5950, "total_steps": 6710, "loss": 0.168, "lr": 7.830234115476232e-08, "epoch": 4.433681073025335, "percentage": 88.67, "elapsed_time": "1:18:31", "remaining_time": "0:10:01", "throughput": 5172.91, "total_tokens": 24371200} {"current_steps": 5951, "total_steps": 6710, "loss": 0.0452, "lr": 7.809858955527563e-08, "epoch": 4.434426229508197, "percentage": 88.69, "elapsed_time": "1:18:32", "remaining_time": "0:10:00", "throughput": 5172.92, "total_tokens": 24375296} {"current_steps": 5952, "total_steps": 6710, "loss": 0.1961, "lr": 7.789509484494598e-08, "epoch": 4.435171385991058, "percentage": 88.7, "elapsed_time": "1:18:32", "remaining_time": "0:10:00", "throughput": 5172.92, "total_tokens": 24379392} {"current_steps": 5953, "total_steps": 6710, "loss": 0.0364, "lr": 7.769185706838128e-08, "epoch": 4.43591654247392, "percentage": 88.72, "elapsed_time": "1:18:33", "remaining_time": "0:09:59", "throughput": 5172.92, "total_tokens": 24383488} {"current_steps": 5954, "total_steps": 6710, "loss": 0.0146, "lr": 7.748887627013244e-08, "epoch": 4.436661698956781, "percentage": 88.73, "elapsed_time": "1:18:34", "remaining_time": "0:09:58", "throughput": 5172.92, "total_tokens": 24387584} {"current_steps": 5955, "total_steps": 6710, "loss": 0.0513, "lr": 7.72861524946944e-08, "epoch": 4.437406855439642, "percentage": 88.75, "elapsed_time": "1:18:35", "remaining_time": "0:09:57", "throughput": 5172.92, "total_tokens": 24391680} {"current_steps": 5956, "total_steps": 6710, "loss": 0.3304, "lr": 7.708368578650565e-08, "epoch": 4.4381520119225035, "percentage": 88.76, "elapsed_time": "1:18:36", "remaining_time": "0:09:57", "throughput": 5172.92, "total_tokens": 24395776} {"current_steps": 5957, "total_steps": 6710, "loss": 0.1604, "lr": 7.688147618994835e-08, "epoch": 4.438897168405365, "percentage": 88.78, "elapsed_time": "1:18:36", "remaining_time": "0:09:56", "throughput": 5172.92, "total_tokens": 24399872} {"current_steps": 5958, "total_steps": 6710, "loss": 0.1036, "lr": 7.66795237493484e-08, "epoch": 4.439642324888227, "percentage": 88.79, "elapsed_time": "1:18:37", "remaining_time": "0:09:55", "throughput": 5172.91, "total_tokens": 24403968} {"current_steps": 5959, "total_steps": 6710, "loss": 0.0371, "lr": 7.647782850897484e-08, "epoch": 4.440387481371088, "percentage": 88.81, "elapsed_time": "1:18:38", "remaining_time": "0:09:54", "throughput": 5172.91, "total_tokens": 24408064} {"current_steps": 5960, "total_steps": 6710, "loss": 0.1127, "lr": 7.62763905130412e-08, "epoch": 4.44113263785395, "percentage": 88.82, "elapsed_time": "1:18:39", "remaining_time": "0:09:53", "throughput": 5172.9, "total_tokens": 24412160} {"current_steps": 5961, "total_steps": 6710, "loss": 0.0918, "lr": 7.607520980570396e-08, "epoch": 4.44187779433681, "percentage": 88.84, "elapsed_time": "1:18:40", "remaining_time": "0:09:53", "throughput": 5172.9, "total_tokens": 24416256} {"current_steps": 5962, "total_steps": 6710, "loss": 0.2152, "lr": 7.587428643106313e-08, "epoch": 4.442622950819672, "percentage": 88.85, "elapsed_time": "1:18:40", "remaining_time": "0:09:52", "throughput": 5172.9, "total_tokens": 24420352} {"current_steps": 5963, "total_steps": 6710, "loss": 0.1465, "lr": 7.567362043316303e-08, "epoch": 4.4433681073025335, "percentage": 88.87, "elapsed_time": "1:18:41", "remaining_time": "0:09:51", "throughput": 5172.9, "total_tokens": 24424448} {"current_steps": 5964, "total_steps": 6710, "loss": 0.0552, "lr": 7.547321185599032e-08, "epoch": 4.444113263785395, "percentage": 88.88, "elapsed_time": "1:18:42", "remaining_time": "0:09:50", "throughput": 5172.9, "total_tokens": 24428544} {"current_steps": 5965, "total_steps": 6710, "loss": 0.0925, "lr": 7.527306074347678e-08, "epoch": 4.444858420268257, "percentage": 88.9, "elapsed_time": "1:18:43", "remaining_time": "0:09:49", "throughput": 5172.89, "total_tokens": 24432640} {"current_steps": 5966, "total_steps": 6710, "loss": 0.1723, "lr": 7.507316713949636e-08, "epoch": 4.445603576751118, "percentage": 88.91, "elapsed_time": "1:18:44", "remaining_time": "0:09:49", "throughput": 5172.89, "total_tokens": 24436736} {"current_steps": 5967, "total_steps": 6710, "loss": 0.0904, "lr": 7.48735310878676e-08, "epoch": 4.446348733233979, "percentage": 88.93, "elapsed_time": "1:18:44", "remaining_time": "0:09:48", "throughput": 5172.89, "total_tokens": 24440832} {"current_steps": 5968, "total_steps": 6710, "loss": 0.0274, "lr": 7.467415263235175e-08, "epoch": 4.44709388971684, "percentage": 88.94, "elapsed_time": "1:18:45", "remaining_time": "0:09:47", "throughput": 5172.88, "total_tokens": 24444928} {"current_steps": 5969, "total_steps": 6710, "loss": 0.1665, "lr": 7.447503181665455e-08, "epoch": 4.447839046199702, "percentage": 88.96, "elapsed_time": "1:18:46", "remaining_time": "0:09:46", "throughput": 5172.88, "total_tokens": 24449024} {"current_steps": 5970, "total_steps": 6710, "loss": 0.1465, "lr": 7.427616868442427e-08, "epoch": 4.4485842026825635, "percentage": 88.97, "elapsed_time": "1:18:47", "remaining_time": "0:09:45", "throughput": 5172.88, "total_tokens": 24453120} {"current_steps": 5971, "total_steps": 6710, "loss": 0.1908, "lr": 7.4077563279253e-08, "epoch": 4.449329359165425, "percentage": 88.99, "elapsed_time": "1:18:47", "remaining_time": "0:09:45", "throughput": 5172.88, "total_tokens": 24457216} {"current_steps": 5972, "total_steps": 6710, "loss": 0.0081, "lr": 7.387921564467701e-08, "epoch": 4.450074515648286, "percentage": 89.0, "elapsed_time": "1:18:48", "remaining_time": "0:09:44", "throughput": 5172.88, "total_tokens": 24461312} {"current_steps": 5973, "total_steps": 6710, "loss": 0.0707, "lr": 7.3681125824175e-08, "epoch": 4.450819672131147, "percentage": 89.02, "elapsed_time": "1:18:49", "remaining_time": "0:09:43", "throughput": 5172.88, "total_tokens": 24465408} {"current_steps": 5974, "total_steps": 6710, "loss": 0.0419, "lr": 7.348329386117001e-08, "epoch": 4.451564828614009, "percentage": 89.03, "elapsed_time": "1:18:50", "remaining_time": "0:09:42", "throughput": 5172.88, "total_tokens": 24469504} {"current_steps": 5975, "total_steps": 6710, "loss": 0.0839, "lr": 7.328571979902791e-08, "epoch": 4.45230998509687, "percentage": 89.05, "elapsed_time": "1:18:51", "remaining_time": "0:09:41", "throughput": 5172.88, "total_tokens": 24473600} {"current_steps": 5976, "total_steps": 6710, "loss": 0.1159, "lr": 7.308840368105891e-08, "epoch": 4.453055141579732, "percentage": 89.06, "elapsed_time": "1:18:51", "remaining_time": "0:09:41", "throughput": 5172.87, "total_tokens": 24477696} {"current_steps": 5977, "total_steps": 6710, "loss": 0.0098, "lr": 7.289134555051522e-08, "epoch": 4.4538002980625935, "percentage": 89.08, "elapsed_time": "1:18:52", "remaining_time": "0:09:40", "throughput": 5172.87, "total_tokens": 24481792} {"current_steps": 5978, "total_steps": 6710, "loss": 0.1456, "lr": 7.269454545059423e-08, "epoch": 4.454545454545454, "percentage": 89.09, "elapsed_time": "1:18:53", "remaining_time": "0:09:39", "throughput": 5172.88, "total_tokens": 24485888} {"current_steps": 5979, "total_steps": 6710, "loss": 0.0646, "lr": 7.249800342443534e-08, "epoch": 4.455290611028316, "percentage": 89.11, "elapsed_time": "1:18:54", "remaining_time": "0:09:38", "throughput": 5172.88, "total_tokens": 24489984} {"current_steps": 5980, "total_steps": 6710, "loss": 0.0633, "lr": 7.230171951512253e-08, "epoch": 4.456035767511177, "percentage": 89.12, "elapsed_time": "1:18:55", "remaining_time": "0:09:38", "throughput": 5172.88, "total_tokens": 24494080} {"current_steps": 5981, "total_steps": 6710, "loss": 0.1042, "lr": 7.210569376568222e-08, "epoch": 4.456780923994039, "percentage": 89.14, "elapsed_time": "1:18:55", "remaining_time": "0:09:37", "throughput": 5172.88, "total_tokens": 24498176} {"current_steps": 5982, "total_steps": 6710, "loss": 0.0546, "lr": 7.190992621908449e-08, "epoch": 4.4575260804769, "percentage": 89.15, "elapsed_time": "1:18:56", "remaining_time": "0:09:36", "throughput": 5172.86, "total_tokens": 24502272} {"current_steps": 5983, "total_steps": 6710, "loss": 0.0356, "lr": 7.171441691824349e-08, "epoch": 4.458271236959762, "percentage": 89.17, "elapsed_time": "1:18:57", "remaining_time": "0:09:35", "throughput": 5172.87, "total_tokens": 24506368} {"current_steps": 5984, "total_steps": 6710, "loss": 0.0682, "lr": 7.15191659060159e-08, "epoch": 4.459016393442623, "percentage": 89.18, "elapsed_time": "1:18:58", "remaining_time": "0:09:34", "throughput": 5172.87, "total_tokens": 24510464} {"current_steps": 5985, "total_steps": 6710, "loss": 0.0458, "lr": 7.132417322520236e-08, "epoch": 4.459761549925484, "percentage": 89.2, "elapsed_time": "1:18:59", "remaining_time": "0:09:34", "throughput": 5172.87, "total_tokens": 24514560} {"current_steps": 5986, "total_steps": 6710, "loss": 0.0557, "lr": 7.112943891854643e-08, "epoch": 4.460506706408346, "percentage": 89.21, "elapsed_time": "1:18:59", "remaining_time": "0:09:33", "throughput": 5172.87, "total_tokens": 24518656} {"current_steps": 5987, "total_steps": 6710, "loss": 0.0322, "lr": 7.09349630287355e-08, "epoch": 4.461251862891207, "percentage": 89.23, "elapsed_time": "1:19:00", "remaining_time": "0:09:32", "throughput": 5172.87, "total_tokens": 24522752} {"current_steps": 5988, "total_steps": 6710, "loss": 0.1317, "lr": 7.074074559839994e-08, "epoch": 4.461997019374069, "percentage": 89.24, "elapsed_time": "1:19:01", "remaining_time": "0:09:31", "throughput": 5172.87, "total_tokens": 24526848} {"current_steps": 5989, "total_steps": 6710, "loss": 0.0143, "lr": 7.054678667011345e-08, "epoch": 4.46274217585693, "percentage": 89.25, "elapsed_time": "1:19:02", "remaining_time": "0:09:30", "throughput": 5172.83, "total_tokens": 24530944} {"current_steps": 5990, "total_steps": 6710, "loss": 0.1412, "lr": 7.035308628639367e-08, "epoch": 4.463487332339791, "percentage": 89.27, "elapsed_time": "1:19:03", "remaining_time": "0:09:30", "throughput": 5172.83, "total_tokens": 24535040} {"current_steps": 5991, "total_steps": 6710, "loss": 0.0897, "lr": 7.015964448970055e-08, "epoch": 4.4642324888226526, "percentage": 89.28, "elapsed_time": "1:19:03", "remaining_time": "0:09:29", "throughput": 5172.83, "total_tokens": 24539136} {"current_steps": 5992, "total_steps": 6710, "loss": 0.0541, "lr": 6.996646132243823e-08, "epoch": 4.464977645305514, "percentage": 89.3, "elapsed_time": "1:19:04", "remaining_time": "0:09:28", "throughput": 5172.83, "total_tokens": 24543232} {"current_steps": 5993, "total_steps": 6710, "loss": 0.0539, "lr": 6.977353682695379e-08, "epoch": 4.465722801788376, "percentage": 89.31, "elapsed_time": "1:19:05", "remaining_time": "0:09:27", "throughput": 5172.84, "total_tokens": 24547328} {"current_steps": 5994, "total_steps": 6710, "loss": 0.0578, "lr": 6.958087104553771e-08, "epoch": 4.466467958271237, "percentage": 89.33, "elapsed_time": "1:19:06", "remaining_time": "0:09:26", "throughput": 5172.84, "total_tokens": 24551424} {"current_steps": 5995, "total_steps": 6710, "loss": 0.0401, "lr": 6.938846402042343e-08, "epoch": 4.467213114754099, "percentage": 89.34, "elapsed_time": "1:19:07", "remaining_time": "0:09:26", "throughput": 5172.84, "total_tokens": 24555520} {"current_steps": 5996, "total_steps": 6710, "loss": 0.0412, "lr": 6.919631579378832e-08, "epoch": 4.467958271236959, "percentage": 89.36, "elapsed_time": "1:19:07", "remaining_time": "0:09:25", "throughput": 5172.84, "total_tokens": 24559616} {"current_steps": 5997, "total_steps": 6710, "loss": 0.0815, "lr": 6.900442640775259e-08, "epoch": 4.468703427719821, "percentage": 89.37, "elapsed_time": "1:19:08", "remaining_time": "0:09:24", "throughput": 5172.84, "total_tokens": 24563712} {"current_steps": 5998, "total_steps": 6710, "loss": 0.0673, "lr": 6.881279590437939e-08, "epoch": 4.4694485842026825, "percentage": 89.39, "elapsed_time": "1:19:09", "remaining_time": "0:09:23", "throughput": 5172.84, "total_tokens": 24567808} {"current_steps": 5999, "total_steps": 6710, "loss": 0.0228, "lr": 6.862142432567595e-08, "epoch": 4.470193740685544, "percentage": 89.4, "elapsed_time": "1:19:10", "remaining_time": "0:09:22", "throughput": 5172.84, "total_tokens": 24571904} {"current_steps": 6000, "total_steps": 6710, "loss": 0.0813, "lr": 6.843031171359191e-08, "epoch": 4.470938897168406, "percentage": 89.42, "elapsed_time": "1:19:10", "remaining_time": "0:09:22", "throughput": 5172.84, "total_tokens": 24576000} {"current_steps": 6001, "total_steps": 6710, "loss": 0.0673, "lr": 6.823945811002098e-08, "epoch": 4.471684053651266, "percentage": 89.43, "elapsed_time": "1:19:11", "remaining_time": "0:09:21", "throughput": 5172.84, "total_tokens": 24580096} {"current_steps": 6002, "total_steps": 6710, "loss": 0.1604, "lr": 6.804886355679913e-08, "epoch": 4.472429210134128, "percentage": 89.45, "elapsed_time": "1:19:12", "remaining_time": "0:09:20", "throughput": 5172.83, "total_tokens": 24584192} {"current_steps": 6003, "total_steps": 6710, "loss": 0.0616, "lr": 6.785852809570656e-08, "epoch": 4.473174366616989, "percentage": 89.46, "elapsed_time": "1:19:13", "remaining_time": "0:09:19", "throughput": 5172.83, "total_tokens": 24588288} {"current_steps": 6004, "total_steps": 6710, "loss": 0.0314, "lr": 6.766845176846559e-08, "epoch": 4.473919523099851, "percentage": 89.48, "elapsed_time": "1:19:14", "remaining_time": "0:09:19", "throughput": 5172.83, "total_tokens": 24592384} {"current_steps": 6005, "total_steps": 6710, "loss": 0.0673, "lr": 6.747863461674276e-08, "epoch": 4.4746646795827125, "percentage": 89.49, "elapsed_time": "1:19:14", "remaining_time": "0:09:18", "throughput": 5172.83, "total_tokens": 24596480} {"current_steps": 6006, "total_steps": 6710, "loss": 0.1398, "lr": 6.728907668214685e-08, "epoch": 4.475409836065574, "percentage": 89.51, "elapsed_time": "1:19:15", "remaining_time": "0:09:17", "throughput": 5172.82, "total_tokens": 24600576} {"current_steps": 6007, "total_steps": 6710, "loss": 0.0967, "lr": 6.709977800623103e-08, "epoch": 4.476154992548436, "percentage": 89.52, "elapsed_time": "1:19:16", "remaining_time": "0:09:16", "throughput": 5172.82, "total_tokens": 24604672} {"current_steps": 6008, "total_steps": 6710, "loss": 0.0867, "lr": 6.691073863049042e-08, "epoch": 4.476900149031296, "percentage": 89.54, "elapsed_time": "1:19:17", "remaining_time": "0:09:15", "throughput": 5172.82, "total_tokens": 24608768} {"current_steps": 6009, "total_steps": 6710, "loss": 0.0517, "lr": 6.672195859636382e-08, "epoch": 4.477645305514158, "percentage": 89.55, "elapsed_time": "1:19:18", "remaining_time": "0:09:15", "throughput": 5172.82, "total_tokens": 24612864} {"current_steps": 6010, "total_steps": 6710, "loss": 0.0214, "lr": 6.653343794523342e-08, "epoch": 4.478390461997019, "percentage": 89.57, "elapsed_time": "1:19:18", "remaining_time": "0:09:14", "throughput": 5172.82, "total_tokens": 24616960} {"current_steps": 6011, "total_steps": 6710, "loss": 0.0727, "lr": 6.63451767184238e-08, "epoch": 4.479135618479881, "percentage": 89.58, "elapsed_time": "1:19:19", "remaining_time": "0:09:13", "throughput": 5172.82, "total_tokens": 24621056} {"current_steps": 6012, "total_steps": 6710, "loss": 0.1228, "lr": 6.615717495720389e-08, "epoch": 4.4798807749627425, "percentage": 89.6, "elapsed_time": "1:19:20", "remaining_time": "0:09:12", "throughput": 5172.82, "total_tokens": 24625152} {"current_steps": 6013, "total_steps": 6710, "loss": 0.0074, "lr": 6.596943270278433e-08, "epoch": 4.480625931445603, "percentage": 89.61, "elapsed_time": "1:19:21", "remaining_time": "0:09:11", "throughput": 5172.81, "total_tokens": 24629248} {"current_steps": 6014, "total_steps": 6710, "loss": 0.0886, "lr": 6.578194999631998e-08, "epoch": 4.481371087928465, "percentage": 89.63, "elapsed_time": "1:19:22", "remaining_time": "0:09:11", "throughput": 5172.81, "total_tokens": 24633344} {"current_steps": 6015, "total_steps": 6710, "loss": 0.0726, "lr": 6.559472687890838e-08, "epoch": 4.482116244411326, "percentage": 89.64, "elapsed_time": "1:19:22", "remaining_time": "0:09:10", "throughput": 5172.82, "total_tokens": 24637440} {"current_steps": 6016, "total_steps": 6710, "loss": 0.078, "lr": 6.540776339158978e-08, "epoch": 4.482861400894188, "percentage": 89.66, "elapsed_time": "1:19:23", "remaining_time": "0:09:09", "throughput": 5172.82, "total_tokens": 24641536} {"current_steps": 6017, "total_steps": 6710, "loss": 0.2231, "lr": 6.522105957534857e-08, "epoch": 4.483606557377049, "percentage": 89.67, "elapsed_time": "1:19:24", "remaining_time": "0:09:08", "throughput": 5172.82, "total_tokens": 24645632} {"current_steps": 6018, "total_steps": 6710, "loss": 0.0186, "lr": 6.503461547111096e-08, "epoch": 4.484351713859911, "percentage": 89.69, "elapsed_time": "1:19:25", "remaining_time": "0:09:07", "throughput": 5172.83, "total_tokens": 24649728} {"current_steps": 6019, "total_steps": 6710, "loss": 0.0539, "lr": 6.484843111974698e-08, "epoch": 4.485096870342772, "percentage": 89.7, "elapsed_time": "1:19:26", "remaining_time": "0:09:07", "throughput": 5172.83, "total_tokens": 24653824} {"current_steps": 6020, "total_steps": 6710, "loss": 0.1688, "lr": 6.466250656206971e-08, "epoch": 4.485842026825633, "percentage": 89.72, "elapsed_time": "1:19:26", "remaining_time": "0:09:06", "throughput": 5172.84, "total_tokens": 24657920} {"current_steps": 6021, "total_steps": 6710, "loss": 0.1793, "lr": 6.447684183883501e-08, "epoch": 4.486587183308495, "percentage": 89.73, "elapsed_time": "1:19:27", "remaining_time": "0:09:05", "throughput": 5172.85, "total_tokens": 24662016} {"current_steps": 6022, "total_steps": 6710, "loss": 0.0965, "lr": 6.4291436990742e-08, "epoch": 4.487332339791356, "percentage": 89.75, "elapsed_time": "1:19:28", "remaining_time": "0:09:04", "throughput": 5172.86, "total_tokens": 24666112} {"current_steps": 6023, "total_steps": 6710, "loss": 0.0791, "lr": 6.410629205843275e-08, "epoch": 4.488077496274218, "percentage": 89.76, "elapsed_time": "1:19:29", "remaining_time": "0:09:03", "throughput": 5172.86, "total_tokens": 24670208} {"current_steps": 6024, "total_steps": 6710, "loss": 0.0773, "lr": 6.392140708249228e-08, "epoch": 4.488822652757079, "percentage": 89.78, "elapsed_time": "1:19:29", "remaining_time": "0:09:03", "throughput": 5172.87, "total_tokens": 24674304} {"current_steps": 6025, "total_steps": 6710, "loss": 0.0538, "lr": 6.373678210344874e-08, "epoch": 4.48956780923994, "percentage": 89.79, "elapsed_time": "1:19:30", "remaining_time": "0:09:02", "throughput": 5172.88, "total_tokens": 24678400} {"current_steps": 6026, "total_steps": 6710, "loss": 0.1537, "lr": 6.355241716177338e-08, "epoch": 4.490312965722802, "percentage": 89.81, "elapsed_time": "1:19:31", "remaining_time": "0:09:01", "throughput": 5172.89, "total_tokens": 24682496} {"current_steps": 6027, "total_steps": 6710, "loss": 0.1315, "lr": 6.336831229787996e-08, "epoch": 4.491058122205663, "percentage": 89.82, "elapsed_time": "1:19:32", "remaining_time": "0:09:00", "throughput": 5172.9, "total_tokens": 24686592} {"current_steps": 6028, "total_steps": 6710, "loss": 0.0948, "lr": 6.318446755212592e-08, "epoch": 4.491803278688525, "percentage": 89.84, "elapsed_time": "1:19:33", "remaining_time": "0:09:00", "throughput": 5172.91, "total_tokens": 24690688} {"current_steps": 6029, "total_steps": 6710, "loss": 0.0801, "lr": 6.300088296481099e-08, "epoch": 4.492548435171386, "percentage": 89.85, "elapsed_time": "1:19:33", "remaining_time": "0:08:59", "throughput": 5172.92, "total_tokens": 24694784} {"current_steps": 6030, "total_steps": 6710, "loss": 0.1233, "lr": 6.281755857617894e-08, "epoch": 4.493293591654248, "percentage": 89.87, "elapsed_time": "1:19:34", "remaining_time": "0:08:58", "throughput": 5172.9, "total_tokens": 24698880} {"current_steps": 6031, "total_steps": 6710, "loss": 0.0796, "lr": 6.263449442641484e-08, "epoch": 4.4940387481371085, "percentage": 89.88, "elapsed_time": "1:19:35", "remaining_time": "0:08:57", "throughput": 5172.91, "total_tokens": 24702976} {"current_steps": 6032, "total_steps": 6710, "loss": 0.1604, "lr": 6.24516905556484e-08, "epoch": 4.49478390461997, "percentage": 89.9, "elapsed_time": "1:19:36", "remaining_time": "0:08:56", "throughput": 5172.91, "total_tokens": 24707072} {"current_steps": 6033, "total_steps": 6710, "loss": 0.1241, "lr": 6.22691470039509e-08, "epoch": 4.495529061102832, "percentage": 89.91, "elapsed_time": "1:19:37", "remaining_time": "0:08:56", "throughput": 5172.92, "total_tokens": 24711168} {"current_steps": 6034, "total_steps": 6710, "loss": 0.073, "lr": 6.208686381133783e-08, "epoch": 4.496274217585693, "percentage": 89.93, "elapsed_time": "1:19:37", "remaining_time": "0:08:55", "throughput": 5172.93, "total_tokens": 24715264} {"current_steps": 6035, "total_steps": 6710, "loss": 0.0812, "lr": 6.190484101776666e-08, "epoch": 4.497019374068555, "percentage": 89.94, "elapsed_time": "1:19:38", "remaining_time": "0:08:54", "throughput": 5172.94, "total_tokens": 24719360} {"current_steps": 6036, "total_steps": 6710, "loss": 0.0399, "lr": 6.172307866313787e-08, "epoch": 4.497764530551416, "percentage": 89.96, "elapsed_time": "1:19:39", "remaining_time": "0:08:53", "throughput": 5172.95, "total_tokens": 24723456} {"current_steps": 6037, "total_steps": 6710, "loss": 0.1668, "lr": 6.154157678729553e-08, "epoch": 4.498509687034277, "percentage": 89.97, "elapsed_time": "1:19:40", "remaining_time": "0:08:52", "throughput": 5172.96, "total_tokens": 24727552} {"current_steps": 6038, "total_steps": 6710, "loss": 0.0524, "lr": 6.136033543002559e-08, "epoch": 4.4992548435171384, "percentage": 89.99, "elapsed_time": "1:19:40", "remaining_time": "0:08:52", "throughput": 5172.97, "total_tokens": 24731648} {"current_steps": 6039, "total_steps": 6710, "loss": 0.078, "lr": 6.11793546310581e-08, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "1:19:41", "remaining_time": "0:08:51", "throughput": 5172.98, "total_tokens": 24735744} {"current_steps": 6040, "total_steps": 6710, "loss": 0.1009, "lr": 6.099863443006476e-08, "epoch": 4.5007451564828616, "percentage": 90.01, "elapsed_time": "1:19:42", "remaining_time": "0:08:50", "throughput": 5172.99, "total_tokens": 24739840} {"current_steps": 6041, "total_steps": 6710, "loss": 0.1124, "lr": 6.081817486666114e-08, "epoch": 4.501490312965723, "percentage": 90.03, "elapsed_time": "1:19:43", "remaining_time": "0:08:49", "throughput": 5172.99, "total_tokens": 24743936} {"current_steps": 6042, "total_steps": 6710, "loss": 0.075, "lr": 6.063797598040516e-08, "epoch": 4.502235469448584, "percentage": 90.04, "elapsed_time": "1:19:44", "remaining_time": "0:08:48", "throughput": 5173.0, "total_tokens": 24748032} {"current_steps": 6043, "total_steps": 6710, "loss": 0.0717, "lr": 6.045803781079746e-08, "epoch": 4.502980625931445, "percentage": 90.06, "elapsed_time": "1:19:44", "remaining_time": "0:08:48", "throughput": 5173.01, "total_tokens": 24752128} {"current_steps": 6044, "total_steps": 6710, "loss": 0.2154, "lr": 6.027836039728216e-08, "epoch": 4.503725782414307, "percentage": 90.07, "elapsed_time": "1:19:45", "remaining_time": "0:08:47", "throughput": 5173.02, "total_tokens": 24756224} {"current_steps": 6045, "total_steps": 6710, "loss": 0.1024, "lr": 6.009894377924569e-08, "epoch": 4.504470938897168, "percentage": 90.09, "elapsed_time": "1:19:46", "remaining_time": "0:08:46", "throughput": 5173.03, "total_tokens": 24760320} {"current_steps": 6046, "total_steps": 6710, "loss": 0.0777, "lr": 5.991978799601727e-08, "epoch": 4.50521609538003, "percentage": 90.1, "elapsed_time": "1:19:47", "remaining_time": "0:08:45", "throughput": 5173.04, "total_tokens": 24764416} {"current_steps": 6047, "total_steps": 6710, "loss": 0.0094, "lr": 5.974089308686912e-08, "epoch": 4.5059612518628915, "percentage": 90.12, "elapsed_time": "1:19:47", "remaining_time": "0:08:44", "throughput": 5173.05, "total_tokens": 24768512} {"current_steps": 6048, "total_steps": 6710, "loss": 0.0738, "lr": 5.956225909101651e-08, "epoch": 4.506706408345753, "percentage": 90.13, "elapsed_time": "1:19:48", "remaining_time": "0:08:44", "throughput": 5173.06, "total_tokens": 24772608} {"current_steps": 6049, "total_steps": 6710, "loss": 0.125, "lr": 5.938388604761716e-08, "epoch": 4.507451564828614, "percentage": 90.15, "elapsed_time": "1:19:49", "remaining_time": "0:08:43", "throughput": 5173.07, "total_tokens": 24776704} {"current_steps": 6050, "total_steps": 6710, "loss": 0.039, "lr": 5.920577399577188e-08, "epoch": 4.508196721311475, "percentage": 90.16, "elapsed_time": "1:19:50", "remaining_time": "0:08:42", "throughput": 5173.08, "total_tokens": 24780800} {"current_steps": 6051, "total_steps": 6710, "loss": 0.0095, "lr": 5.9027922974523727e-08, "epoch": 4.508941877794337, "percentage": 90.18, "elapsed_time": "1:19:51", "remaining_time": "0:08:41", "throughput": 5173.09, "total_tokens": 24784896} {"current_steps": 6052, "total_steps": 6710, "loss": 0.0553, "lr": 5.8850333022859445e-08, "epoch": 4.509687034277198, "percentage": 90.19, "elapsed_time": "1:19:51", "remaining_time": "0:08:40", "throughput": 5173.1, "total_tokens": 24788992} {"current_steps": 6053, "total_steps": 6710, "loss": 0.0533, "lr": 5.8673004179707615e-08, "epoch": 4.51043219076006, "percentage": 90.21, "elapsed_time": "1:19:52", "remaining_time": "0:08:40", "throughput": 5173.11, "total_tokens": 24793088} {"current_steps": 6054, "total_steps": 6710, "loss": 0.0344, "lr": 5.8495936483940055e-08, "epoch": 4.511177347242921, "percentage": 90.22, "elapsed_time": "1:19:53", "remaining_time": "0:08:39", "throughput": 5173.12, "total_tokens": 24797184} {"current_steps": 6055, "total_steps": 6710, "loss": 0.1614, "lr": 5.831912997437142e-08, "epoch": 4.511922503725782, "percentage": 90.24, "elapsed_time": "1:19:54", "remaining_time": "0:08:38", "throughput": 5173.13, "total_tokens": 24801280} {"current_steps": 6056, "total_steps": 6710, "loss": 0.0436, "lr": 5.8142584689758616e-08, "epoch": 4.512667660208644, "percentage": 90.25, "elapsed_time": "1:19:55", "remaining_time": "0:08:37", "throughput": 5173.14, "total_tokens": 24805376} {"current_steps": 6057, "total_steps": 6710, "loss": 0.2147, "lr": 5.796630066880235e-08, "epoch": 4.513412816691505, "percentage": 90.27, "elapsed_time": "1:19:55", "remaining_time": "0:08:37", "throughput": 5173.15, "total_tokens": 24809472} {"current_steps": 6058, "total_steps": 6710, "loss": 0.0733, "lr": 5.7790277950144494e-08, "epoch": 4.514157973174367, "percentage": 90.28, "elapsed_time": "1:19:56", "remaining_time": "0:08:36", "throughput": 5173.16, "total_tokens": 24813568} {"current_steps": 6059, "total_steps": 6710, "loss": 0.0546, "lr": 5.7614516572370855e-08, "epoch": 4.514903129657228, "percentage": 90.3, "elapsed_time": "1:19:57", "remaining_time": "0:08:35", "throughput": 5173.17, "total_tokens": 24817664} {"current_steps": 6060, "total_steps": 6710, "loss": 0.0693, "lr": 5.743901657400963e-08, "epoch": 4.515648286140089, "percentage": 90.31, "elapsed_time": "1:19:58", "remaining_time": "0:08:34", "throughput": 5173.18, "total_tokens": 24821760} {"current_steps": 6061, "total_steps": 6710, "loss": 0.2132, "lr": 5.7263777993531584e-08, "epoch": 4.516393442622951, "percentage": 90.33, "elapsed_time": "1:19:58", "remaining_time": "0:08:33", "throughput": 5173.19, "total_tokens": 24825856} {"current_steps": 6062, "total_steps": 6710, "loss": 0.0882, "lr": 5.7088800869350424e-08, "epoch": 4.517138599105812, "percentage": 90.34, "elapsed_time": "1:19:59", "remaining_time": "0:08:33", "throughput": 5173.2, "total_tokens": 24829952} {"current_steps": 6063, "total_steps": 6710, "loss": 0.047, "lr": 5.691408523982214e-08, "epoch": 4.517883755588674, "percentage": 90.36, "elapsed_time": "1:20:00", "remaining_time": "0:08:32", "throughput": 5173.2, "total_tokens": 24834048} {"current_steps": 6064, "total_steps": 6710, "loss": 0.1839, "lr": 5.673963114324582e-08, "epoch": 4.518628912071535, "percentage": 90.37, "elapsed_time": "1:20:01", "remaining_time": "0:08:31", "throughput": 5173.21, "total_tokens": 24838144} {"current_steps": 6065, "total_steps": 6710, "loss": 0.1043, "lr": 5.6565438617862815e-08, "epoch": 4.519374068554397, "percentage": 90.39, "elapsed_time": "1:20:02", "remaining_time": "0:08:30", "throughput": 5173.22, "total_tokens": 24842240} {"current_steps": 6066, "total_steps": 6710, "loss": 0.0324, "lr": 5.6391507701857864e-08, "epoch": 4.5201192250372575, "percentage": 90.4, "elapsed_time": "1:20:02", "remaining_time": "0:08:29", "throughput": 5173.23, "total_tokens": 24846336} {"current_steps": 6067, "total_steps": 6710, "loss": 0.006, "lr": 5.6217838433357265e-08, "epoch": 4.520864381520119, "percentage": 90.42, "elapsed_time": "1:20:03", "remaining_time": "0:08:29", "throughput": 5173.24, "total_tokens": 24850432} {"current_steps": 6068, "total_steps": 6710, "loss": 0.1344, "lr": 5.6044430850430986e-08, "epoch": 4.521609538002981, "percentage": 90.43, "elapsed_time": "1:20:04", "remaining_time": "0:08:28", "throughput": 5173.25, "total_tokens": 24854528} {"current_steps": 6069, "total_steps": 6710, "loss": 0.0827, "lr": 5.5871284991091125e-08, "epoch": 4.522354694485842, "percentage": 90.45, "elapsed_time": "1:20:05", "remaining_time": "0:08:27", "throughput": 5173.26, "total_tokens": 24858624} {"current_steps": 6070, "total_steps": 6710, "loss": 0.1251, "lr": 5.5698400893292456e-08, "epoch": 4.523099850968704, "percentage": 90.46, "elapsed_time": "1:20:05", "remaining_time": "0:08:26", "throughput": 5173.27, "total_tokens": 24862720} {"current_steps": 6071, "total_steps": 6710, "loss": 0.0523, "lr": 5.5525778594932165e-08, "epoch": 4.523845007451564, "percentage": 90.48, "elapsed_time": "1:20:06", "remaining_time": "0:08:25", "throughput": 5173.24, "total_tokens": 24866816} {"current_steps": 6072, "total_steps": 6710, "loss": 0.0792, "lr": 5.5353418133850813e-08, "epoch": 4.524590163934426, "percentage": 90.49, "elapsed_time": "1:20:07", "remaining_time": "0:08:25", "throughput": 5173.25, "total_tokens": 24870912} {"current_steps": 6073, "total_steps": 6710, "loss": 0.047, "lr": 5.5181319547830545e-08, "epoch": 4.5253353204172875, "percentage": 90.51, "elapsed_time": "1:20:08", "remaining_time": "0:08:24", "throughput": 5173.26, "total_tokens": 24875008} {"current_steps": 6074, "total_steps": 6710, "loss": 0.0997, "lr": 5.500948287459673e-08, "epoch": 4.526080476900149, "percentage": 90.52, "elapsed_time": "1:20:09", "remaining_time": "0:08:23", "throughput": 5173.27, "total_tokens": 24879104} {"current_steps": 6075, "total_steps": 6710, "loss": 0.0769, "lr": 5.483790815181744e-08, "epoch": 4.526825633383011, "percentage": 90.54, "elapsed_time": "1:20:09", "remaining_time": "0:08:22", "throughput": 5173.28, "total_tokens": 24883200} {"current_steps": 6076, "total_steps": 6710, "loss": 0.0763, "lr": 5.466659541710273e-08, "epoch": 4.527570789865872, "percentage": 90.55, "elapsed_time": "1:20:10", "remaining_time": "0:08:21", "throughput": 5173.29, "total_tokens": 24887296} {"current_steps": 6077, "total_steps": 6710, "loss": 0.0375, "lr": 5.449554470800603e-08, "epoch": 4.528315946348734, "percentage": 90.57, "elapsed_time": "1:20:11", "remaining_time": "0:08:21", "throughput": 5173.3, "total_tokens": 24891392} {"current_steps": 6078, "total_steps": 6710, "loss": 0.0475, "lr": 5.43247560620222e-08, "epoch": 4.529061102831594, "percentage": 90.58, "elapsed_time": "1:20:12", "remaining_time": "0:08:20", "throughput": 5173.31, "total_tokens": 24895488} {"current_steps": 6079, "total_steps": 6710, "loss": 0.1378, "lr": 5.415422951659005e-08, "epoch": 4.529806259314456, "percentage": 90.6, "elapsed_time": "1:20:13", "remaining_time": "0:08:19", "throughput": 5173.32, "total_tokens": 24899584} {"current_steps": 6080, "total_steps": 6710, "loss": 0.0963, "lr": 5.398396510908982e-08, "epoch": 4.5305514157973175, "percentage": 90.61, "elapsed_time": "1:20:13", "remaining_time": "0:08:18", "throughput": 5173.33, "total_tokens": 24903680} {"current_steps": 6081, "total_steps": 6710, "loss": 0.0851, "lr": 5.3813962876844704e-08, "epoch": 4.531296572280179, "percentage": 90.63, "elapsed_time": "1:20:14", "remaining_time": "0:08:18", "throughput": 5173.34, "total_tokens": 24907776} {"current_steps": 6082, "total_steps": 6710, "loss": 0.0731, "lr": 5.364422285712045e-08, "epoch": 4.532041728763041, "percentage": 90.64, "elapsed_time": "1:20:15", "remaining_time": "0:08:17", "throughput": 5173.34, "total_tokens": 24911872} {"current_steps": 6083, "total_steps": 6710, "loss": 0.0615, "lr": 5.3474745087125216e-08, "epoch": 4.532786885245901, "percentage": 90.66, "elapsed_time": "1:20:16", "remaining_time": "0:08:16", "throughput": 5173.35, "total_tokens": 24915968} {"current_steps": 6084, "total_steps": 6710, "loss": 0.1153, "lr": 5.3305529604010115e-08, "epoch": 4.533532041728763, "percentage": 90.67, "elapsed_time": "1:20:16", "remaining_time": "0:08:15", "throughput": 5173.36, "total_tokens": 24920064} {"current_steps": 6085, "total_steps": 6710, "loss": 0.1637, "lr": 5.313657644486783e-08, "epoch": 4.534277198211624, "percentage": 90.69, "elapsed_time": "1:20:17", "remaining_time": "0:08:14", "throughput": 5173.37, "total_tokens": 24924160} {"current_steps": 6086, "total_steps": 6710, "loss": 0.0213, "lr": 5.296788564673444e-08, "epoch": 4.535022354694486, "percentage": 90.7, "elapsed_time": "1:20:18", "remaining_time": "0:08:14", "throughput": 5173.38, "total_tokens": 24928256} {"current_steps": 6087, "total_steps": 6710, "loss": 0.0118, "lr": 5.2799457246588e-08, "epoch": 4.5357675111773474, "percentage": 90.72, "elapsed_time": "1:20:19", "remaining_time": "0:08:13", "throughput": 5173.39, "total_tokens": 24932352} {"current_steps": 6088, "total_steps": 6710, "loss": 0.1129, "lr": 5.263129128134939e-08, "epoch": 4.536512667660209, "percentage": 90.73, "elapsed_time": "1:20:20", "remaining_time": "0:08:12", "throughput": 5173.4, "total_tokens": 24936448} {"current_steps": 6089, "total_steps": 6710, "loss": 0.0383, "lr": 5.2463387787881764e-08, "epoch": 4.53725782414307, "percentage": 90.75, "elapsed_time": "1:20:20", "remaining_time": "0:08:11", "throughput": 5173.41, "total_tokens": 24940544} {"current_steps": 6090, "total_steps": 6710, "loss": 0.0077, "lr": 5.229574680299054e-08, "epoch": 4.538002980625931, "percentage": 90.76, "elapsed_time": "1:20:21", "remaining_time": "0:08:10", "throughput": 5173.42, "total_tokens": 24944640} {"current_steps": 6091, "total_steps": 6710, "loss": 0.1638, "lr": 5.212836836342411e-08, "epoch": 4.538748137108793, "percentage": 90.77, "elapsed_time": "1:20:22", "remaining_time": "0:08:10", "throughput": 5173.43, "total_tokens": 24948736} {"current_steps": 6092, "total_steps": 6710, "loss": 0.0812, "lr": 5.196125250587269e-08, "epoch": 4.539493293591654, "percentage": 90.79, "elapsed_time": "1:20:23", "remaining_time": "0:08:09", "throughput": 5173.44, "total_tokens": 24952832} {"current_steps": 6093, "total_steps": 6710, "loss": 0.0854, "lr": 5.1794399266969775e-08, "epoch": 4.540238450074516, "percentage": 90.8, "elapsed_time": "1:20:24", "remaining_time": "0:08:08", "throughput": 5173.45, "total_tokens": 24956928} {"current_steps": 6094, "total_steps": 6710, "loss": 0.1092, "lr": 5.162780868329026e-08, "epoch": 4.540983606557377, "percentage": 90.82, "elapsed_time": "1:20:24", "remaining_time": "0:08:07", "throughput": 5173.46, "total_tokens": 24961024} {"current_steps": 6095, "total_steps": 6710, "loss": 0.1084, "lr": 5.1461480791352437e-08, "epoch": 4.541728763040238, "percentage": 90.83, "elapsed_time": "1:20:25", "remaining_time": "0:08:06", "throughput": 5173.47, "total_tokens": 24965120} {"current_steps": 6096, "total_steps": 6710, "loss": 0.0129, "lr": 5.129541562761631e-08, "epoch": 4.5424739195231, "percentage": 90.85, "elapsed_time": "1:20:26", "remaining_time": "0:08:06", "throughput": 5173.48, "total_tokens": 24969216} {"current_steps": 6097, "total_steps": 6710, "loss": 0.1661, "lr": 5.112961322848456e-08, "epoch": 4.543219076005961, "percentage": 90.86, "elapsed_time": "1:20:27", "remaining_time": "0:08:05", "throughput": 5173.49, "total_tokens": 24973312} {"current_steps": 6098, "total_steps": 6710, "loss": 0.1584, "lr": 5.096407363030215e-08, "epoch": 4.543964232488823, "percentage": 90.88, "elapsed_time": "1:20:27", "remaining_time": "0:08:04", "throughput": 5173.5, "total_tokens": 24977408} {"current_steps": 6099, "total_steps": 6710, "loss": 0.0675, "lr": 5.079879686935685e-08, "epoch": 4.544709388971684, "percentage": 90.89, "elapsed_time": "1:20:28", "remaining_time": "0:08:03", "throughput": 5173.51, "total_tokens": 24981504} {"current_steps": 6100, "total_steps": 6710, "loss": 0.0315, "lr": 5.0633782981878434e-08, "epoch": 4.545454545454545, "percentage": 90.91, "elapsed_time": "1:20:29", "remaining_time": "0:08:02", "throughput": 5173.51, "total_tokens": 24985600} {"current_steps": 6101, "total_steps": 6710, "loss": 0.0413, "lr": 5.0469032004038796e-08, "epoch": 4.5461997019374065, "percentage": 90.92, "elapsed_time": "1:20:30", "remaining_time": "0:08:02", "throughput": 5173.52, "total_tokens": 24989696} {"current_steps": 6102, "total_steps": 6710, "loss": 0.0806, "lr": 5.0304543971952807e-08, "epoch": 4.546944858420268, "percentage": 90.94, "elapsed_time": "1:20:31", "remaining_time": "0:08:01", "throughput": 5173.53, "total_tokens": 24993792} {"current_steps": 6103, "total_steps": 6710, "loss": 0.17, "lr": 5.014031892167731e-08, "epoch": 4.54769001490313, "percentage": 90.95, "elapsed_time": "1:20:31", "remaining_time": "0:08:00", "throughput": 5173.54, "total_tokens": 24997888} {"current_steps": 6104, "total_steps": 6710, "loss": 0.1367, "lr": 4.9976356889211844e-08, "epoch": 4.548435171385991, "percentage": 90.97, "elapsed_time": "1:20:32", "remaining_time": "0:07:59", "throughput": 5173.55, "total_tokens": 25001984} {"current_steps": 6105, "total_steps": 6710, "loss": 0.0209, "lr": 4.98126579104978e-08, "epoch": 4.549180327868853, "percentage": 90.98, "elapsed_time": "1:20:33", "remaining_time": "0:07:58", "throughput": 5173.56, "total_tokens": 25006080} {"current_steps": 6106, "total_steps": 6710, "loss": 0.0187, "lr": 4.9649222021419254e-08, "epoch": 4.549925484351714, "percentage": 91.0, "elapsed_time": "1:20:34", "remaining_time": "0:07:58", "throughput": 5173.57, "total_tokens": 25010176} {"current_steps": 6107, "total_steps": 6710, "loss": 0.0727, "lr": 4.948604925780254e-08, "epoch": 4.550670640834575, "percentage": 91.01, "elapsed_time": "1:20:34", "remaining_time": "0:07:57", "throughput": 5173.58, "total_tokens": 25014272} {"current_steps": 6108, "total_steps": 6710, "loss": 0.0631, "lr": 4.932313965541613e-08, "epoch": 4.5514157973174365, "percentage": 91.03, "elapsed_time": "1:20:35", "remaining_time": "0:07:56", "throughput": 5173.59, "total_tokens": 25018368} {"current_steps": 6109, "total_steps": 6710, "loss": 0.0701, "lr": 4.916049324997133e-08, "epoch": 4.552160953800298, "percentage": 91.04, "elapsed_time": "1:20:36", "remaining_time": "0:07:55", "throughput": 5173.6, "total_tokens": 25022464} {"current_steps": 6110, "total_steps": 6710, "loss": 0.1519, "lr": 4.899811007712099e-08, "epoch": 4.55290611028316, "percentage": 91.06, "elapsed_time": "1:20:37", "remaining_time": "0:07:55", "throughput": 5173.61, "total_tokens": 25026560} {"current_steps": 6111, "total_steps": 6710, "loss": 0.0523, "lr": 4.88359901724611e-08, "epoch": 4.553651266766021, "percentage": 91.07, "elapsed_time": "1:20:38", "remaining_time": "0:07:54", "throughput": 5173.62, "total_tokens": 25030656} {"current_steps": 6112, "total_steps": 6710, "loss": 0.0221, "lr": 4.867413357152892e-08, "epoch": 4.554396423248882, "percentage": 91.09, "elapsed_time": "1:20:38", "remaining_time": "0:07:53", "throughput": 5173.63, "total_tokens": 25034752} {"current_steps": 6113, "total_steps": 6710, "loss": 0.0434, "lr": 4.85125403098051e-08, "epoch": 4.555141579731743, "percentage": 91.1, "elapsed_time": "1:20:39", "remaining_time": "0:07:52", "throughput": 5173.61, "total_tokens": 25038848} {"current_steps": 6114, "total_steps": 6710, "loss": 0.1508, "lr": 4.835121042271157e-08, "epoch": 4.555886736214605, "percentage": 91.12, "elapsed_time": "1:20:40", "remaining_time": "0:07:51", "throughput": 5173.62, "total_tokens": 25042944} {"current_steps": 6115, "total_steps": 6710, "loss": 0.0903, "lr": 4.8190143945613526e-08, "epoch": 4.5566318926974665, "percentage": 91.13, "elapsed_time": "1:20:41", "remaining_time": "0:07:51", "throughput": 5173.63, "total_tokens": 25047040} {"current_steps": 6116, "total_steps": 6710, "loss": 0.0337, "lr": 4.802934091381745e-08, "epoch": 4.557377049180328, "percentage": 91.15, "elapsed_time": "1:20:42", "remaining_time": "0:07:50", "throughput": 5173.64, "total_tokens": 25051136} {"current_steps": 6117, "total_steps": 6710, "loss": 0.0883, "lr": 4.786880136257277e-08, "epoch": 4.55812220566319, "percentage": 91.16, "elapsed_time": "1:20:42", "remaining_time": "0:07:49", "throughput": 5173.65, "total_tokens": 25055232} {"current_steps": 6118, "total_steps": 6710, "loss": 0.1164, "lr": 4.770852532707093e-08, "epoch": 4.558867362146051, "percentage": 91.18, "elapsed_time": "1:20:43", "remaining_time": "0:07:48", "throughput": 5173.66, "total_tokens": 25059328} {"current_steps": 6119, "total_steps": 6710, "loss": 0.0236, "lr": 4.754851284244521e-08, "epoch": 4.559612518628912, "percentage": 91.19, "elapsed_time": "1:20:44", "remaining_time": "0:07:47", "throughput": 5173.67, "total_tokens": 25063424} {"current_steps": 6120, "total_steps": 6710, "loss": 0.0344, "lr": 4.7388763943772007e-08, "epoch": 4.560357675111773, "percentage": 91.21, "elapsed_time": "1:20:45", "remaining_time": "0:07:47", "throughput": 5173.68, "total_tokens": 25067520} {"current_steps": 6121, "total_steps": 6710, "loss": 0.0206, "lr": 4.722927866606886e-08, "epoch": 4.561102831594635, "percentage": 91.22, "elapsed_time": "1:20:45", "remaining_time": "0:07:46", "throughput": 5173.69, "total_tokens": 25071616} {"current_steps": 6122, "total_steps": 6710, "loss": 0.0981, "lr": 4.707005704429668e-08, "epoch": 4.5618479880774965, "percentage": 91.24, "elapsed_time": "1:20:46", "remaining_time": "0:07:45", "throughput": 5173.7, "total_tokens": 25075712} {"current_steps": 6123, "total_steps": 6710, "loss": 0.1265, "lr": 4.6911099113357424e-08, "epoch": 4.562593144560358, "percentage": 91.25, "elapsed_time": "1:20:47", "remaining_time": "0:07:44", "throughput": 5173.71, "total_tokens": 25079808} {"current_steps": 6124, "total_steps": 6710, "loss": 0.0441, "lr": 4.67524049080964e-08, "epoch": 4.563338301043219, "percentage": 91.27, "elapsed_time": "1:20:48", "remaining_time": "0:07:43", "throughput": 5173.72, "total_tokens": 25083904} {"current_steps": 6125, "total_steps": 6710, "loss": 0.0534, "lr": 4.659397446329983e-08, "epoch": 4.56408345752608, "percentage": 91.28, "elapsed_time": "1:20:49", "remaining_time": "0:07:43", "throughput": 5173.73, "total_tokens": 25088000} {"current_steps": 6126, "total_steps": 6710, "loss": 0.0032, "lr": 4.643580781369742e-08, "epoch": 4.564828614008942, "percentage": 91.3, "elapsed_time": "1:20:49", "remaining_time": "0:07:42", "throughput": 5173.74, "total_tokens": 25092096} {"current_steps": 6127, "total_steps": 6710, "loss": 0.0145, "lr": 4.627790499396004e-08, "epoch": 4.565573770491803, "percentage": 91.31, "elapsed_time": "1:20:50", "remaining_time": "0:07:41", "throughput": 5173.75, "total_tokens": 25096192} {"current_steps": 6128, "total_steps": 6710, "loss": 0.0112, "lr": 4.6120266038701125e-08, "epoch": 4.566318926974665, "percentage": 91.33, "elapsed_time": "1:20:51", "remaining_time": "0:07:40", "throughput": 5173.75, "total_tokens": 25100288} {"current_steps": 6129, "total_steps": 6710, "loss": 0.0442, "lr": 4.59628909824765e-08, "epoch": 4.5670640834575265, "percentage": 91.34, "elapsed_time": "1:20:52", "remaining_time": "0:07:39", "throughput": 5173.75, "total_tokens": 25104384} {"current_steps": 6130, "total_steps": 6710, "loss": 0.1162, "lr": 4.580577985978357e-08, "epoch": 4.567809239940387, "percentage": 91.36, "elapsed_time": "1:20:53", "remaining_time": "0:07:39", "throughput": 5173.76, "total_tokens": 25108480} {"current_steps": 6131, "total_steps": 6710, "loss": 0.0425, "lr": 4.564893270506257e-08, "epoch": 4.568554396423249, "percentage": 91.37, "elapsed_time": "1:20:53", "remaining_time": "0:07:38", "throughput": 5173.77, "total_tokens": 25112576} {"current_steps": 6132, "total_steps": 6710, "loss": 0.0486, "lr": 4.5492349552695295e-08, "epoch": 4.56929955290611, "percentage": 91.39, "elapsed_time": "1:20:54", "remaining_time": "0:07:37", "throughput": 5173.78, "total_tokens": 25116672} {"current_steps": 6133, "total_steps": 6710, "loss": 0.0736, "lr": 4.533603043700596e-08, "epoch": 4.570044709388972, "percentage": 91.4, "elapsed_time": "1:20:55", "remaining_time": "0:07:36", "throughput": 5173.79, "total_tokens": 25120768} {"current_steps": 6134, "total_steps": 6710, "loss": 0.0468, "lr": 4.5179975392260905e-08, "epoch": 4.570789865871833, "percentage": 91.42, "elapsed_time": "1:20:56", "remaining_time": "0:07:36", "throughput": 5173.79, "total_tokens": 25124864} {"current_steps": 6135, "total_steps": 6710, "loss": 0.076, "lr": 4.5024184452668316e-08, "epoch": 4.571535022354695, "percentage": 91.43, "elapsed_time": "1:20:56", "remaining_time": "0:07:35", "throughput": 5173.8, "total_tokens": 25128960} {"current_steps": 6136, "total_steps": 6710, "loss": 0.0555, "lr": 4.4868657652378936e-08, "epoch": 4.5722801788375556, "percentage": 91.45, "elapsed_time": "1:20:57", "remaining_time": "0:07:34", "throughput": 5173.8, "total_tokens": 25133056} {"current_steps": 6137, "total_steps": 6710, "loss": 0.2106, "lr": 4.471339502548508e-08, "epoch": 4.573025335320417, "percentage": 91.46, "elapsed_time": "1:20:58", "remaining_time": "0:07:33", "throughput": 5173.8, "total_tokens": 25137152} {"current_steps": 6138, "total_steps": 6710, "loss": 0.1264, "lr": 4.4558396606021734e-08, "epoch": 4.573770491803279, "percentage": 91.48, "elapsed_time": "1:20:59", "remaining_time": "0:07:32", "throughput": 5173.8, "total_tokens": 25141248} {"current_steps": 6139, "total_steps": 6710, "loss": 0.1163, "lr": 4.4403662427965206e-08, "epoch": 4.57451564828614, "percentage": 91.49, "elapsed_time": "1:21:00", "remaining_time": "0:07:32", "throughput": 5173.79, "total_tokens": 25145344} {"current_steps": 6140, "total_steps": 6710, "loss": 0.0512, "lr": 4.4249192525234744e-08, "epoch": 4.575260804769002, "percentage": 91.51, "elapsed_time": "1:21:00", "remaining_time": "0:07:31", "throughput": 5173.8, "total_tokens": 25149440} {"current_steps": 6141, "total_steps": 6710, "loss": 0.1375, "lr": 4.409498693169104e-08, "epoch": 4.576005961251862, "percentage": 91.52, "elapsed_time": "1:21:01", "remaining_time": "0:07:30", "throughput": 5173.81, "total_tokens": 25153536} {"current_steps": 6142, "total_steps": 6710, "loss": 0.1184, "lr": 4.394104568113719e-08, "epoch": 4.576751117734724, "percentage": 91.54, "elapsed_time": "1:21:02", "remaining_time": "0:07:29", "throughput": 5173.81, "total_tokens": 25157632} {"current_steps": 6143, "total_steps": 6710, "loss": 0.0612, "lr": 4.378736880731815e-08, "epoch": 4.5774962742175855, "percentage": 91.55, "elapsed_time": "1:21:03", "remaining_time": "0:07:28", "throughput": 5173.82, "total_tokens": 25161728} {"current_steps": 6144, "total_steps": 6710, "loss": 0.0022, "lr": 4.363395634392101e-08, "epoch": 4.578241430700447, "percentage": 91.56, "elapsed_time": "1:21:04", "remaining_time": "0:07:28", "throughput": 5173.83, "total_tokens": 25165824} {"current_steps": 6145, "total_steps": 6710, "loss": 0.0689, "lr": 4.348080832457496e-08, "epoch": 4.578986587183309, "percentage": 91.58, "elapsed_time": "1:21:04", "remaining_time": "0:07:27", "throughput": 5173.83, "total_tokens": 25169920} {"current_steps": 6146, "total_steps": 6710, "loss": 0.1907, "lr": 4.3327924782850804e-08, "epoch": 4.57973174366617, "percentage": 91.59, "elapsed_time": "1:21:05", "remaining_time": "0:07:26", "throughput": 5173.85, "total_tokens": 25174016} {"current_steps": 6147, "total_steps": 6710, "loss": 0.0139, "lr": 4.317530575226214e-08, "epoch": 4.580476900149032, "percentage": 91.61, "elapsed_time": "1:21:06", "remaining_time": "0:07:25", "throughput": 5173.86, "total_tokens": 25178112} {"current_steps": 6148, "total_steps": 6710, "loss": 0.0618, "lr": 4.3022951266263743e-08, "epoch": 4.581222056631892, "percentage": 91.62, "elapsed_time": "1:21:07", "remaining_time": "0:07:24", "throughput": 5173.87, "total_tokens": 25182208} {"current_steps": 6149, "total_steps": 6710, "loss": 0.0321, "lr": 4.287086135825319e-08, "epoch": 4.581967213114754, "percentage": 91.64, "elapsed_time": "1:21:07", "remaining_time": "0:07:24", "throughput": 5173.88, "total_tokens": 25186304} {"current_steps": 6150, "total_steps": 6710, "loss": 0.0358, "lr": 4.271903606156938e-08, "epoch": 4.5827123695976155, "percentage": 91.65, "elapsed_time": "1:21:08", "remaining_time": "0:07:23", "throughput": 5173.89, "total_tokens": 25190400} {"current_steps": 6151, "total_steps": 6710, "loss": 0.1302, "lr": 4.256747540949388e-08, "epoch": 4.583457526080477, "percentage": 91.67, "elapsed_time": "1:21:09", "remaining_time": "0:07:22", "throughput": 5173.9, "total_tokens": 25194496} {"current_steps": 6152, "total_steps": 6710, "loss": 0.0359, "lr": 4.2416179435249423e-08, "epoch": 4.584202682563339, "percentage": 91.68, "elapsed_time": "1:21:10", "remaining_time": "0:07:21", "throughput": 5173.91, "total_tokens": 25198592} {"current_steps": 6153, "total_steps": 6710, "loss": 0.024, "lr": 4.226514817200142e-08, "epoch": 4.584947839046199, "percentage": 91.7, "elapsed_time": "1:21:11", "remaining_time": "0:07:20", "throughput": 5173.92, "total_tokens": 25202688} {"current_steps": 6154, "total_steps": 6710, "loss": 0.0287, "lr": 4.211438165285686e-08, "epoch": 4.585692995529061, "percentage": 91.71, "elapsed_time": "1:21:11", "remaining_time": "0:07:20", "throughput": 5173.9, "total_tokens": 25206784} {"current_steps": 6155, "total_steps": 6710, "loss": 0.0711, "lr": 4.196387991086487e-08, "epoch": 4.586438152011922, "percentage": 91.73, "elapsed_time": "1:21:12", "remaining_time": "0:07:19", "throughput": 5173.91, "total_tokens": 25210880} {"current_steps": 6156, "total_steps": 6710, "loss": 0.0767, "lr": 4.1813642979016686e-08, "epoch": 4.587183308494784, "percentage": 91.74, "elapsed_time": "1:21:13", "remaining_time": "0:07:18", "throughput": 5173.91, "total_tokens": 25214976} {"current_steps": 6157, "total_steps": 6710, "loss": 0.0806, "lr": 4.1663670890245004e-08, "epoch": 4.5879284649776455, "percentage": 91.76, "elapsed_time": "1:21:14", "remaining_time": "0:07:17", "throughput": 5173.92, "total_tokens": 25219072} {"current_steps": 6158, "total_steps": 6710, "loss": 0.0655, "lr": 4.151396367742505e-08, "epoch": 4.588673621460507, "percentage": 91.77, "elapsed_time": "1:21:15", "remaining_time": "0:07:16", "throughput": 5173.92, "total_tokens": 25223168} {"current_steps": 6159, "total_steps": 6710, "loss": 0.0821, "lr": 4.136452137337363e-08, "epoch": 4.589418777943368, "percentage": 91.79, "elapsed_time": "1:21:15", "remaining_time": "0:07:16", "throughput": 5173.93, "total_tokens": 25227264} {"current_steps": 6160, "total_steps": 6710, "loss": 0.1553, "lr": 4.121534401084953e-08, "epoch": 4.590163934426229, "percentage": 91.8, "elapsed_time": "1:21:16", "remaining_time": "0:07:15", "throughput": 5173.94, "total_tokens": 25231360} {"current_steps": 6161, "total_steps": 6710, "loss": 0.0803, "lr": 4.106643162255369e-08, "epoch": 4.590909090909091, "percentage": 91.82, "elapsed_time": "1:21:17", "remaining_time": "0:07:14", "throughput": 5173.95, "total_tokens": 25235456} {"current_steps": 6162, "total_steps": 6710, "loss": 0.0666, "lr": 4.091778424112833e-08, "epoch": 4.591654247391952, "percentage": 91.83, "elapsed_time": "1:21:18", "remaining_time": "0:07:13", "throughput": 5173.95, "total_tokens": 25239552} {"current_steps": 6163, "total_steps": 6710, "loss": 0.0705, "lr": 4.0769401899158486e-08, "epoch": 4.592399403874814, "percentage": 91.85, "elapsed_time": "1:21:18", "remaining_time": "0:07:13", "throughput": 5173.96, "total_tokens": 25243648} {"current_steps": 6164, "total_steps": 6710, "loss": 0.0864, "lr": 4.0621284629170225e-08, "epoch": 4.5931445603576755, "percentage": 91.86, "elapsed_time": "1:21:19", "remaining_time": "0:07:12", "throughput": 5173.97, "total_tokens": 25247744} {"current_steps": 6165, "total_steps": 6710, "loss": 0.1502, "lr": 4.0473432463632444e-08, "epoch": 4.593889716840536, "percentage": 91.88, "elapsed_time": "1:21:20", "remaining_time": "0:07:11", "throughput": 5173.98, "total_tokens": 25251840} {"current_steps": 6166, "total_steps": 6710, "loss": 0.0731, "lr": 4.032584543495477e-08, "epoch": 4.594634873323398, "percentage": 91.89, "elapsed_time": "1:21:21", "remaining_time": "0:07:10", "throughput": 5173.99, "total_tokens": 25255936} {"current_steps": 6167, "total_steps": 6710, "loss": 0.0059, "lr": 4.017852357548965e-08, "epoch": 4.595380029806259, "percentage": 91.91, "elapsed_time": "1:21:22", "remaining_time": "0:07:09", "throughput": 5174.0, "total_tokens": 25260032} {"current_steps": 6168, "total_steps": 6710, "loss": 0.0504, "lr": 4.003146691753099e-08, "epoch": 4.596125186289121, "percentage": 91.92, "elapsed_time": "1:21:22", "remaining_time": "0:07:09", "throughput": 5174.0, "total_tokens": 25264128} {"current_steps": 6169, "total_steps": 6710, "loss": 0.0252, "lr": 3.988467549331493e-08, "epoch": 4.596870342771982, "percentage": 91.94, "elapsed_time": "1:21:23", "remaining_time": "0:07:08", "throughput": 5174.01, "total_tokens": 25268224} {"current_steps": 6170, "total_steps": 6710, "loss": 0.0578, "lr": 3.9738149335018795e-08, "epoch": 4.597615499254843, "percentage": 91.95, "elapsed_time": "1:21:24", "remaining_time": "0:07:07", "throughput": 5174.02, "total_tokens": 25272320} {"current_steps": 6171, "total_steps": 6710, "loss": 0.1317, "lr": 3.959188847476259e-08, "epoch": 4.598360655737705, "percentage": 91.97, "elapsed_time": "1:21:25", "remaining_time": "0:07:06", "throughput": 5174.03, "total_tokens": 25276416} {"current_steps": 6172, "total_steps": 6710, "loss": 0.0515, "lr": 3.9445892944607463e-08, "epoch": 4.599105812220566, "percentage": 91.98, "elapsed_time": "1:21:26", "remaining_time": "0:07:05", "throughput": 5174.04, "total_tokens": 25280512} {"current_steps": 6173, "total_steps": 6710, "loss": 0.0328, "lr": 3.930016277655657e-08, "epoch": 4.599850968703428, "percentage": 92.0, "elapsed_time": "1:21:26", "remaining_time": "0:07:05", "throughput": 5174.05, "total_tokens": 25284608} {"current_steps": 6174, "total_steps": 6710, "loss": 0.1014, "lr": 3.915469800255534e-08, "epoch": 4.600596125186289, "percentage": 92.01, "elapsed_time": "1:21:27", "remaining_time": "0:07:04", "throughput": 5174.05, "total_tokens": 25288704} {"current_steps": 6175, "total_steps": 6710, "loss": 0.2209, "lr": 3.900949865449033e-08, "epoch": 4.601341281669151, "percentage": 92.03, "elapsed_time": "1:21:28", "remaining_time": "0:07:03", "throughput": 5174.06, "total_tokens": 25292800} {"current_steps": 6176, "total_steps": 6710, "loss": 0.0479, "lr": 3.8864564764190535e-08, "epoch": 4.602086438152012, "percentage": 92.04, "elapsed_time": "1:21:29", "remaining_time": "0:07:02", "throughput": 5174.07, "total_tokens": 25296896} {"current_steps": 6177, "total_steps": 6710, "loss": 0.1041, "lr": 3.871989636342638e-08, "epoch": 4.602831594634873, "percentage": 92.06, "elapsed_time": "1:21:29", "remaining_time": "0:07:01", "throughput": 5174.08, "total_tokens": 25300992} {"current_steps": 6178, "total_steps": 6710, "loss": 0.0394, "lr": 3.857549348391054e-08, "epoch": 4.603576751117735, "percentage": 92.07, "elapsed_time": "1:21:30", "remaining_time": "0:07:01", "throughput": 5174.08, "total_tokens": 25305088} {"current_steps": 6179, "total_steps": 6710, "loss": 0.1021, "lr": 3.8431356157296595e-08, "epoch": 4.604321907600596, "percentage": 92.09, "elapsed_time": "1:21:31", "remaining_time": "0:07:00", "throughput": 5174.09, "total_tokens": 25309184} {"current_steps": 6180, "total_steps": 6710, "loss": 0.0471, "lr": 3.8287484415180934e-08, "epoch": 4.605067064083458, "percentage": 92.1, "elapsed_time": "1:21:32", "remaining_time": "0:06:59", "throughput": 5174.09, "total_tokens": 25313280} {"current_steps": 6181, "total_steps": 6710, "loss": 0.1482, "lr": 3.814387828910096e-08, "epoch": 4.605812220566319, "percentage": 92.12, "elapsed_time": "1:21:33", "remaining_time": "0:06:58", "throughput": 5174.1, "total_tokens": 25317376} {"current_steps": 6182, "total_steps": 6710, "loss": 0.108, "lr": 3.800053781053623e-08, "epoch": 4.60655737704918, "percentage": 92.13, "elapsed_time": "1:21:33", "remaining_time": "0:06:57", "throughput": 5174.11, "total_tokens": 25321472} {"current_steps": 6183, "total_steps": 6710, "loss": 0.0363, "lr": 3.785746301090826e-08, "epoch": 4.6073025335320414, "percentage": 92.15, "elapsed_time": "1:21:34", "remaining_time": "0:06:57", "throughput": 5174.12, "total_tokens": 25325568} {"current_steps": 6184, "total_steps": 6710, "loss": 0.0553, "lr": 3.771465392157961e-08, "epoch": 4.608047690014903, "percentage": 92.16, "elapsed_time": "1:21:35", "remaining_time": "0:06:56", "throughput": 5174.13, "total_tokens": 25329664} {"current_steps": 6185, "total_steps": 6710, "loss": 0.0367, "lr": 3.7572110573855514e-08, "epoch": 4.6087928464977646, "percentage": 92.18, "elapsed_time": "1:21:36", "remaining_time": "0:06:55", "throughput": 5174.14, "total_tokens": 25333760} {"current_steps": 6186, "total_steps": 6710, "loss": 0.1026, "lr": 3.742983299898223e-08, "epoch": 4.609538002980626, "percentage": 92.19, "elapsed_time": "1:21:37", "remaining_time": "0:06:54", "throughput": 5174.14, "total_tokens": 25337856} {"current_steps": 6187, "total_steps": 6710, "loss": 0.0338, "lr": 3.728782122814814e-08, "epoch": 4.610283159463488, "percentage": 92.21, "elapsed_time": "1:21:37", "remaining_time": "0:06:54", "throughput": 5174.15, "total_tokens": 25341952} {"current_steps": 6188, "total_steps": 6710, "loss": 0.0383, "lr": 3.714607529248307e-08, "epoch": 4.611028315946349, "percentage": 92.22, "elapsed_time": "1:21:38", "remaining_time": "0:06:53", "throughput": 5174.14, "total_tokens": 25346048} {"current_steps": 6189, "total_steps": 6710, "loss": 0.0651, "lr": 3.700459522305883e-08, "epoch": 4.61177347242921, "percentage": 92.24, "elapsed_time": "1:21:39", "remaining_time": "0:06:52", "throughput": 5174.07, "total_tokens": 25350144} {"current_steps": 6190, "total_steps": 6710, "loss": 0.0146, "lr": 3.6863381050888935e-08, "epoch": 4.612518628912071, "percentage": 92.25, "elapsed_time": "1:21:40", "remaining_time": "0:06:51", "throughput": 5173.98, "total_tokens": 25354240} {"current_steps": 6191, "total_steps": 6710, "loss": 0.1061, "lr": 3.67224328069285e-08, "epoch": 4.613263785394933, "percentage": 92.27, "elapsed_time": "1:21:41", "remaining_time": "0:06:50", "throughput": 5173.98, "total_tokens": 25358336} {"current_steps": 6192, "total_steps": 6710, "loss": 0.1533, "lr": 3.6581750522074464e-08, "epoch": 4.6140089418777945, "percentage": 92.28, "elapsed_time": "1:21:41", "remaining_time": "0:06:50", "throughput": 5173.94, "total_tokens": 25362432} {"current_steps": 6193, "total_steps": 6710, "loss": 0.042, "lr": 3.644133422716509e-08, "epoch": 4.614754098360656, "percentage": 92.3, "elapsed_time": "1:21:42", "remaining_time": "0:06:49", "throughput": 5173.92, "total_tokens": 25366528} {"current_steps": 6194, "total_steps": 6710, "loss": 0.0631, "lr": 3.630118395298102e-08, "epoch": 4.615499254843517, "percentage": 92.31, "elapsed_time": "1:21:43", "remaining_time": "0:06:48", "throughput": 5173.92, "total_tokens": 25370624} {"current_steps": 6195, "total_steps": 6710, "loss": 0.1043, "lr": 3.6161299730243794e-08, "epoch": 4.616244411326378, "percentage": 92.32, "elapsed_time": "1:21:44", "remaining_time": "0:06:47", "throughput": 5173.91, "total_tokens": 25374720} {"current_steps": 6196, "total_steps": 6710, "loss": 0.0447, "lr": 3.6021681589617495e-08, "epoch": 4.61698956780924, "percentage": 92.34, "elapsed_time": "1:21:45", "remaining_time": "0:06:46", "throughput": 5173.92, "total_tokens": 25378816} {"current_steps": 6197, "total_steps": 6710, "loss": 0.0125, "lr": 3.588232956170695e-08, "epoch": 4.617734724292101, "percentage": 92.35, "elapsed_time": "1:21:45", "remaining_time": "0:06:46", "throughput": 5173.92, "total_tokens": 25382912} {"current_steps": 6198, "total_steps": 6710, "loss": 0.1678, "lr": 3.574324367705953e-08, "epoch": 4.618479880774963, "percentage": 92.37, "elapsed_time": "1:21:46", "remaining_time": "0:06:45", "throughput": 5173.93, "total_tokens": 25387008} {"current_steps": 6199, "total_steps": 6710, "loss": 0.0957, "lr": 3.560442396616362e-08, "epoch": 4.6192250372578245, "percentage": 92.38, "elapsed_time": "1:21:47", "remaining_time": "0:06:44", "throughput": 5173.93, "total_tokens": 25391104} {"current_steps": 6200, "total_steps": 6710, "loss": 0.1321, "lr": 3.5465870459449325e-08, "epoch": 4.619970193740685, "percentage": 92.4, "elapsed_time": "1:21:48", "remaining_time": "0:06:43", "throughput": 5173.94, "total_tokens": 25395200} {"current_steps": 6201, "total_steps": 6710, "loss": 0.0572, "lr": 3.5327583187289017e-08, "epoch": 4.620715350223547, "percentage": 92.41, "elapsed_time": "1:21:49", "remaining_time": "0:06:42", "throughput": 5173.95, "total_tokens": 25399296} {"current_steps": 6202, "total_steps": 6710, "loss": 0.2033, "lr": 3.518956217999594e-08, "epoch": 4.621460506706408, "percentage": 92.43, "elapsed_time": "1:21:49", "remaining_time": "0:06:42", "throughput": 5173.96, "total_tokens": 25403392} {"current_steps": 6203, "total_steps": 6710, "loss": 0.1106, "lr": 3.505180746782535e-08, "epoch": 4.62220566318927, "percentage": 92.44, "elapsed_time": "1:21:50", "remaining_time": "0:06:41", "throughput": 5173.97, "total_tokens": 25407488} {"current_steps": 6204, "total_steps": 6710, "loss": 0.0559, "lr": 3.4914319080973924e-08, "epoch": 4.622950819672131, "percentage": 92.46, "elapsed_time": "1:21:51", "remaining_time": "0:06:40", "throughput": 5173.98, "total_tokens": 25411584} {"current_steps": 6205, "total_steps": 6710, "loss": 0.0062, "lr": 3.47770970495806e-08, "epoch": 4.623695976154993, "percentage": 92.47, "elapsed_time": "1:21:52", "remaining_time": "0:06:39", "throughput": 5173.98, "total_tokens": 25415680} {"current_steps": 6206, "total_steps": 6710, "loss": 0.0862, "lr": 3.4640141403724794e-08, "epoch": 4.624441132637854, "percentage": 92.49, "elapsed_time": "1:21:52", "remaining_time": "0:06:38", "throughput": 5173.99, "total_tokens": 25419776} {"current_steps": 6207, "total_steps": 6710, "loss": 0.129, "lr": 3.45034521734286e-08, "epoch": 4.625186289120715, "percentage": 92.5, "elapsed_time": "1:21:53", "remaining_time": "0:06:38", "throughput": 5174.0, "total_tokens": 25423872} {"current_steps": 6208, "total_steps": 6710, "loss": 0.0922, "lr": 3.436702938865485e-08, "epoch": 4.625931445603577, "percentage": 92.52, "elapsed_time": "1:21:54", "remaining_time": "0:06:37", "throughput": 5174.01, "total_tokens": 25427968} {"current_steps": 6209, "total_steps": 6710, "loss": 0.0858, "lr": 3.4230873079308945e-08, "epoch": 4.626676602086438, "percentage": 92.53, "elapsed_time": "1:21:55", "remaining_time": "0:06:36", "throughput": 5174.02, "total_tokens": 25432064} {"current_steps": 6210, "total_steps": 6710, "loss": 0.0764, "lr": 3.409498327523686e-08, "epoch": 4.6274217585693, "percentage": 92.55, "elapsed_time": "1:21:56", "remaining_time": "0:06:35", "throughput": 5174.04, "total_tokens": 25436160} {"current_steps": 6211, "total_steps": 6710, "loss": 0.0561, "lr": 3.395936000622685e-08, "epoch": 4.6281669150521605, "percentage": 92.56, "elapsed_time": "1:21:56", "remaining_time": "0:06:35", "throughput": 5174.05, "total_tokens": 25440256} {"current_steps": 6212, "total_steps": 6710, "loss": 0.186, "lr": 3.382400330200833e-08, "epoch": 4.628912071535022, "percentage": 92.58, "elapsed_time": "1:21:57", "remaining_time": "0:06:34", "throughput": 5174.06, "total_tokens": 25444352} {"current_steps": 6213, "total_steps": 6710, "loss": 0.0787, "lr": 3.3688913192252564e-08, "epoch": 4.629657228017884, "percentage": 92.59, "elapsed_time": "1:21:58", "remaining_time": "0:06:33", "throughput": 5174.07, "total_tokens": 25448448} {"current_steps": 6214, "total_steps": 6710, "loss": 0.0967, "lr": 3.3554089706572394e-08, "epoch": 4.630402384500745, "percentage": 92.61, "elapsed_time": "1:21:59", "remaining_time": "0:06:32", "throughput": 5174.06, "total_tokens": 25452544} {"current_steps": 6215, "total_steps": 6710, "loss": 0.0813, "lr": 3.341953287452182e-08, "epoch": 4.631147540983607, "percentage": 92.62, "elapsed_time": "1:22:00", "remaining_time": "0:06:31", "throughput": 5174.05, "total_tokens": 25456640} {"current_steps": 6216, "total_steps": 6710, "loss": 0.0858, "lr": 3.3285242725596965e-08, "epoch": 4.631892697466468, "percentage": 92.64, "elapsed_time": "1:22:00", "remaining_time": "0:06:31", "throughput": 5174.06, "total_tokens": 25460736} {"current_steps": 6217, "total_steps": 6710, "loss": 0.0549, "lr": 3.315121928923498e-08, "epoch": 4.63263785394933, "percentage": 92.65, "elapsed_time": "1:22:01", "remaining_time": "0:06:30", "throughput": 5174.07, "total_tokens": 25464832} {"current_steps": 6218, "total_steps": 6710, "loss": 0.1678, "lr": 3.3017462594814586e-08, "epoch": 4.6333830104321905, "percentage": 92.67, "elapsed_time": "1:22:02", "remaining_time": "0:06:29", "throughput": 5174.08, "total_tokens": 25468928} {"current_steps": 6219, "total_steps": 6710, "loss": 0.0957, "lr": 3.288397267165677e-08, "epoch": 4.634128166915052, "percentage": 92.68, "elapsed_time": "1:22:03", "remaining_time": "0:06:28", "throughput": 5174.08, "total_tokens": 25473024} {"current_steps": 6220, "total_steps": 6710, "loss": 0.0471, "lr": 3.275074954902299e-08, "epoch": 4.634873323397914, "percentage": 92.7, "elapsed_time": "1:22:03", "remaining_time": "0:06:27", "throughput": 5174.09, "total_tokens": 25477120} {"current_steps": 6221, "total_steps": 6710, "loss": 0.0544, "lr": 3.261779325611683e-08, "epoch": 4.635618479880775, "percentage": 92.71, "elapsed_time": "1:22:04", "remaining_time": "0:06:27", "throughput": 5174.1, "total_tokens": 25481216} {"current_steps": 6222, "total_steps": 6710, "loss": 0.0612, "lr": 3.248510382208317e-08, "epoch": 4.636363636363637, "percentage": 92.73, "elapsed_time": "1:22:05", "remaining_time": "0:06:26", "throughput": 5174.11, "total_tokens": 25485312} {"current_steps": 6223, "total_steps": 6710, "loss": 0.0787, "lr": 3.235268127600874e-08, "epoch": 4.637108792846497, "percentage": 92.74, "elapsed_time": "1:22:06", "remaining_time": "0:06:25", "throughput": 5174.12, "total_tokens": 25489408} {"current_steps": 6224, "total_steps": 6710, "loss": 0.04, "lr": 3.222052564692116e-08, "epoch": 4.637853949329359, "percentage": 92.76, "elapsed_time": "1:22:07", "remaining_time": "0:06:24", "throughput": 5174.13, "total_tokens": 25493504} {"current_steps": 6225, "total_steps": 6710, "loss": 0.0317, "lr": 3.2088636963790166e-08, "epoch": 4.6385991058122205, "percentage": 92.77, "elapsed_time": "1:22:07", "remaining_time": "0:06:23", "throughput": 5174.13, "total_tokens": 25497600} {"current_steps": 6226, "total_steps": 6710, "loss": 0.0976, "lr": 3.19570152555268e-08, "epoch": 4.639344262295082, "percentage": 92.79, "elapsed_time": "1:22:08", "remaining_time": "0:06:23", "throughput": 5174.13, "total_tokens": 25501696} {"current_steps": 6227, "total_steps": 6710, "loss": 0.0359, "lr": 3.182566055098299e-08, "epoch": 4.640089418777944, "percentage": 92.8, "elapsed_time": "1:22:09", "remaining_time": "0:06:22", "throughput": 5174.14, "total_tokens": 25505792} {"current_steps": 6228, "total_steps": 6710, "loss": 0.1728, "lr": 3.1694572878953195e-08, "epoch": 4.640834575260805, "percentage": 92.82, "elapsed_time": "1:22:10", "remaining_time": "0:06:21", "throughput": 5174.14, "total_tokens": 25509888} {"current_steps": 6229, "total_steps": 6710, "loss": 0.1272, "lr": 3.156375226817221e-08, "epoch": 4.641579731743666, "percentage": 92.83, "elapsed_time": "1:22:11", "remaining_time": "0:06:20", "throughput": 5174.14, "total_tokens": 25513984} {"current_steps": 6230, "total_steps": 6710, "loss": 0.0144, "lr": 3.1433198747317374e-08, "epoch": 4.642324888226527, "percentage": 92.85, "elapsed_time": "1:22:11", "remaining_time": "0:06:19", "throughput": 5174.15, "total_tokens": 25518080} {"current_steps": 6231, "total_steps": 6710, "loss": 0.1125, "lr": 3.130291234500663e-08, "epoch": 4.643070044709389, "percentage": 92.86, "elapsed_time": "1:22:12", "remaining_time": "0:06:19", "throughput": 5174.16, "total_tokens": 25522176} {"current_steps": 6232, "total_steps": 6710, "loss": 0.1808, "lr": 3.117289308980004e-08, "epoch": 4.64381520119225, "percentage": 92.88, "elapsed_time": "1:22:13", "remaining_time": "0:06:18", "throughput": 5174.16, "total_tokens": 25526272} {"current_steps": 6233, "total_steps": 6710, "loss": 0.0948, "lr": 3.104314101019815e-08, "epoch": 4.644560357675112, "percentage": 92.89, "elapsed_time": "1:22:14", "remaining_time": "0:06:17", "throughput": 5174.17, "total_tokens": 25530368} {"current_steps": 6234, "total_steps": 6710, "loss": 0.1485, "lr": 3.091365613464403e-08, "epoch": 4.6453055141579735, "percentage": 92.91, "elapsed_time": "1:22:14", "remaining_time": "0:06:16", "throughput": 5174.17, "total_tokens": 25534464} {"current_steps": 6235, "total_steps": 6710, "loss": 0.0193, "lr": 3.078443849152138e-08, "epoch": 4.646050670640834, "percentage": 92.92, "elapsed_time": "1:22:15", "remaining_time": "0:06:16", "throughput": 5174.16, "total_tokens": 25538560} {"current_steps": 6236, "total_steps": 6710, "loss": 0.0407, "lr": 3.0655488109156e-08, "epoch": 4.646795827123696, "percentage": 92.94, "elapsed_time": "1:22:16", "remaining_time": "0:06:15", "throughput": 5174.17, "total_tokens": 25542656} {"current_steps": 6237, "total_steps": 6710, "loss": 0.0897, "lr": 3.0526805015814456e-08, "epoch": 4.647540983606557, "percentage": 92.95, "elapsed_time": "1:22:17", "remaining_time": "0:06:14", "throughput": 5174.17, "total_tokens": 25546752} {"current_steps": 6238, "total_steps": 6710, "loss": 0.1073, "lr": 3.0398389239705004e-08, "epoch": 4.648286140089419, "percentage": 92.97, "elapsed_time": "1:22:18", "remaining_time": "0:06:13", "throughput": 5174.16, "total_tokens": 25550848} {"current_steps": 6239, "total_steps": 6710, "loss": 0.1139, "lr": 3.027024080897736e-08, "epoch": 4.64903129657228, "percentage": 92.98, "elapsed_time": "1:22:18", "remaining_time": "0:06:12", "throughput": 5174.17, "total_tokens": 25554944} {"current_steps": 6240, "total_steps": 6710, "loss": 0.1328, "lr": 3.014235975172253e-08, "epoch": 4.649776453055141, "percentage": 93.0, "elapsed_time": "1:22:19", "remaining_time": "0:06:12", "throughput": 5174.18, "total_tokens": 25559040} {"current_steps": 6241, "total_steps": 6710, "loss": 0.1061, "lr": 3.001474609597321e-08, "epoch": 4.650521609538003, "percentage": 93.01, "elapsed_time": "1:22:20", "remaining_time": "0:06:11", "throughput": 5174.19, "total_tokens": 25563136} {"current_steps": 6242, "total_steps": 6710, "loss": 0.1081, "lr": 2.988739986970274e-08, "epoch": 4.651266766020864, "percentage": 93.03, "elapsed_time": "1:22:21", "remaining_time": "0:06:10", "throughput": 5174.2, "total_tokens": 25567232} {"current_steps": 6243, "total_steps": 6710, "loss": 0.0885, "lr": 2.9760321100826828e-08, "epoch": 4.652011922503726, "percentage": 93.04, "elapsed_time": "1:22:22", "remaining_time": "0:06:09", "throughput": 5174.2, "total_tokens": 25571328} {"current_steps": 6244, "total_steps": 6710, "loss": 0.2088, "lr": 2.963350981720181e-08, "epoch": 4.652757078986587, "percentage": 93.06, "elapsed_time": "1:22:22", "remaining_time": "0:06:08", "throughput": 5174.21, "total_tokens": 25575424} {"current_steps": 6245, "total_steps": 6710, "loss": 0.062, "lr": 2.950696604662559e-08, "epoch": 4.653502235469449, "percentage": 93.07, "elapsed_time": "1:22:23", "remaining_time": "0:06:08", "throughput": 5174.22, "total_tokens": 25579520} {"current_steps": 6246, "total_steps": 6710, "loss": 0.0821, "lr": 2.9380689816837642e-08, "epoch": 4.65424739195231, "percentage": 93.08, "elapsed_time": "1:22:24", "remaining_time": "0:06:07", "throughput": 5174.23, "total_tokens": 25583616} {"current_steps": 6247, "total_steps": 6710, "loss": 0.1123, "lr": 2.9254681155518188e-08, "epoch": 4.654992548435171, "percentage": 93.1, "elapsed_time": "1:22:25", "remaining_time": "0:06:06", "throughput": 5174.22, "total_tokens": 25587712} {"current_steps": 6248, "total_steps": 6710, "loss": 0.0969, "lr": 2.9128940090289854e-08, "epoch": 4.655737704918033, "percentage": 93.11, "elapsed_time": "1:22:26", "remaining_time": "0:06:05", "throughput": 5174.23, "total_tokens": 25591808} {"current_steps": 6249, "total_steps": 6710, "loss": 0.2076, "lr": 2.900346664871531e-08, "epoch": 4.656482861400894, "percentage": 93.13, "elapsed_time": "1:22:26", "remaining_time": "0:06:04", "throughput": 5174.23, "total_tokens": 25595904} {"current_steps": 6250, "total_steps": 6710, "loss": 0.0504, "lr": 2.8878260858299785e-08, "epoch": 4.657228017883756, "percentage": 93.14, "elapsed_time": "1:22:27", "remaining_time": "0:06:04", "throughput": 5174.24, "total_tokens": 25600000} {"current_steps": 6251, "total_steps": 6710, "loss": 0.0606, "lr": 2.8753322746488955e-08, "epoch": 4.657973174366617, "percentage": 93.16, "elapsed_time": "1:22:28", "remaining_time": "0:06:03", "throughput": 5174.25, "total_tokens": 25604096} {"current_steps": 6252, "total_steps": 6710, "loss": 0.0416, "lr": 2.862865234067036e-08, "epoch": 4.658718330849478, "percentage": 93.17, "elapsed_time": "1:22:29", "remaining_time": "0:06:02", "throughput": 5174.24, "total_tokens": 25608192} {"current_steps": 6253, "total_steps": 6710, "loss": 0.0669, "lr": 2.8504249668172555e-08, "epoch": 4.6594634873323395, "percentage": 93.19, "elapsed_time": "1:22:29", "remaining_time": "0:06:01", "throughput": 5174.25, "total_tokens": 25612288} {"current_steps": 6254, "total_steps": 6710, "loss": 0.0489, "lr": 2.8380114756265396e-08, "epoch": 4.660208643815201, "percentage": 93.2, "elapsed_time": "1:22:30", "remaining_time": "0:06:00", "throughput": 5174.26, "total_tokens": 25616384} {"current_steps": 6255, "total_steps": 6710, "loss": 0.0836, "lr": 2.825624763216031e-08, "epoch": 4.660953800298063, "percentage": 93.22, "elapsed_time": "1:22:31", "remaining_time": "0:06:00", "throughput": 5174.27, "total_tokens": 25620480} {"current_steps": 6256, "total_steps": 6710, "loss": 0.1504, "lr": 2.8132648323009743e-08, "epoch": 4.661698956780924, "percentage": 93.23, "elapsed_time": "1:22:32", "remaining_time": "0:05:59", "throughput": 5174.28, "total_tokens": 25624576} {"current_steps": 6257, "total_steps": 6710, "loss": 0.1681, "lr": 2.8009316855907577e-08, "epoch": 4.662444113263786, "percentage": 93.25, "elapsed_time": "1:22:33", "remaining_time": "0:05:58", "throughput": 5174.29, "total_tokens": 25628672} {"current_steps": 6258, "total_steps": 6710, "loss": 0.0248, "lr": 2.7886253257888852e-08, "epoch": 4.663189269746647, "percentage": 93.26, "elapsed_time": "1:22:33", "remaining_time": "0:05:57", "throughput": 5174.3, "total_tokens": 25632768} {"current_steps": 6259, "total_steps": 6710, "loss": 0.0149, "lr": 2.7763457555930324e-08, "epoch": 4.663934426229508, "percentage": 93.28, "elapsed_time": "1:22:34", "remaining_time": "0:05:57", "throughput": 5174.3, "total_tokens": 25636864} {"current_steps": 6260, "total_steps": 6710, "loss": 0.102, "lr": 2.764092977694921e-08, "epoch": 4.6646795827123695, "percentage": 93.29, "elapsed_time": "1:22:35", "remaining_time": "0:05:56", "throughput": 5174.31, "total_tokens": 25640960} {"current_steps": 6261, "total_steps": 6710, "loss": 0.0361, "lr": 2.751866994780486e-08, "epoch": 4.665424739195231, "percentage": 93.31, "elapsed_time": "1:22:36", "remaining_time": "0:05:55", "throughput": 5174.32, "total_tokens": 25645056} {"current_steps": 6262, "total_steps": 6710, "loss": 0.0272, "lr": 2.7396678095297225e-08, "epoch": 4.666169895678093, "percentage": 93.32, "elapsed_time": "1:22:37", "remaining_time": "0:05:54", "throughput": 5174.31, "total_tokens": 25649152} {"current_steps": 6263, "total_steps": 6710, "loss": 0.1167, "lr": 2.7274954246167967e-08, "epoch": 4.666915052160954, "percentage": 93.34, "elapsed_time": "1:22:37", "remaining_time": "0:05:53", "throughput": 5174.3, "total_tokens": 25653248} {"current_steps": 6264, "total_steps": 6710, "loss": 0.1156, "lr": 2.715349842709991e-08, "epoch": 4.667660208643815, "percentage": 93.35, "elapsed_time": "1:22:38", "remaining_time": "0:05:53", "throughput": 5174.3, "total_tokens": 25657344} {"current_steps": 6265, "total_steps": 6710, "loss": 0.0372, "lr": 2.703231066471676e-08, "epoch": 4.668405365126676, "percentage": 93.37, "elapsed_time": "1:22:39", "remaining_time": "0:05:52", "throughput": 5174.31, "total_tokens": 25661440} {"current_steps": 6266, "total_steps": 6710, "loss": 0.0737, "lr": 2.691139098558393e-08, "epoch": 4.669150521609538, "percentage": 93.38, "elapsed_time": "1:22:40", "remaining_time": "0:05:51", "throughput": 5174.29, "total_tokens": 25665536} {"current_steps": 6267, "total_steps": 6710, "loss": 0.1249, "lr": 2.679073941620772e-08, "epoch": 4.6698956780923995, "percentage": 93.4, "elapsed_time": "1:22:41", "remaining_time": "0:05:50", "throughput": 5174.28, "total_tokens": 25669632} {"current_steps": 6268, "total_steps": 6710, "loss": 0.0656, "lr": 2.6670355983035996e-08, "epoch": 4.670640834575261, "percentage": 93.41, "elapsed_time": "1:22:41", "remaining_time": "0:05:49", "throughput": 5174.28, "total_tokens": 25673728} {"current_steps": 6269, "total_steps": 6710, "loss": 0.0657, "lr": 2.6550240712457653e-08, "epoch": 4.671385991058123, "percentage": 93.43, "elapsed_time": "1:22:42", "remaining_time": "0:05:49", "throughput": 5174.29, "total_tokens": 25677824} {"current_steps": 6270, "total_steps": 6710, "loss": 0.1601, "lr": 2.6430393630802742e-08, "epoch": 4.672131147540983, "percentage": 93.44, "elapsed_time": "1:22:43", "remaining_time": "0:05:48", "throughput": 5174.3, "total_tokens": 25681920} {"current_steps": 6271, "total_steps": 6710, "loss": 0.0732, "lr": 2.6310814764342607e-08, "epoch": 4.672876304023845, "percentage": 93.46, "elapsed_time": "1:22:44", "remaining_time": "0:05:47", "throughput": 5174.27, "total_tokens": 25686016} {"current_steps": 6272, "total_steps": 6710, "loss": 0.0795, "lr": 2.6191504139289613e-08, "epoch": 4.673621460506706, "percentage": 93.47, "elapsed_time": "1:22:44", "remaining_time": "0:05:46", "throughput": 5174.26, "total_tokens": 25690112} {"current_steps": 6273, "total_steps": 6710, "loss": 0.1594, "lr": 2.607246178179812e-08, "epoch": 4.674366616989568, "percentage": 93.49, "elapsed_time": "1:22:45", "remaining_time": "0:05:45", "throughput": 5174.25, "total_tokens": 25694208} {"current_steps": 6274, "total_steps": 6710, "loss": 0.0402, "lr": 2.595368771796225e-08, "epoch": 4.6751117734724295, "percentage": 93.5, "elapsed_time": "1:22:46", "remaining_time": "0:05:45", "throughput": 5174.24, "total_tokens": 25698304} {"current_steps": 6275, "total_steps": 6710, "loss": 0.1033, "lr": 2.583518197381868e-08, "epoch": 4.675856929955291, "percentage": 93.52, "elapsed_time": "1:22:47", "remaining_time": "0:05:44", "throughput": 5174.22, "total_tokens": 25702400} {"current_steps": 6276, "total_steps": 6710, "loss": 0.0413, "lr": 2.5716944575344406e-08, "epoch": 4.676602086438152, "percentage": 93.53, "elapsed_time": "1:22:48", "remaining_time": "0:05:43", "throughput": 5174.22, "total_tokens": 25706496} {"current_steps": 6277, "total_steps": 6710, "loss": 0.0275, "lr": 2.559897554845814e-08, "epoch": 4.677347242921013, "percentage": 93.55, "elapsed_time": "1:22:49", "remaining_time": "0:05:42", "throughput": 5174.2, "total_tokens": 25710592} {"current_steps": 6278, "total_steps": 6710, "loss": 0.0472, "lr": 2.5481274919019332e-08, "epoch": 4.678092399403875, "percentage": 93.56, "elapsed_time": "1:22:49", "remaining_time": "0:05:41", "throughput": 5174.16, "total_tokens": 25714688} {"current_steps": 6279, "total_steps": 6710, "loss": 0.032, "lr": 2.5363842712829018e-08, "epoch": 4.678837555886736, "percentage": 93.58, "elapsed_time": "1:22:50", "remaining_time": "0:05:41", "throughput": 5174.14, "total_tokens": 25718784} {"current_steps": 6280, "total_steps": 6710, "loss": 0.0787, "lr": 2.524667895562896e-08, "epoch": 4.679582712369598, "percentage": 93.59, "elapsed_time": "1:22:51", "remaining_time": "0:05:40", "throughput": 5174.12, "total_tokens": 25722880} {"current_steps": 6281, "total_steps": 6710, "loss": 0.1451, "lr": 2.5129783673102508e-08, "epoch": 4.6803278688524586, "percentage": 93.61, "elapsed_time": "1:22:52", "remaining_time": "0:05:39", "throughput": 5174.11, "total_tokens": 25726976} {"current_steps": 6282, "total_steps": 6710, "loss": 0.091, "lr": 2.5013156890873745e-08, "epoch": 4.68107302533532, "percentage": 93.62, "elapsed_time": "1:22:53", "remaining_time": "0:05:38", "throughput": 5174.09, "total_tokens": 25731072} {"current_steps": 6283, "total_steps": 6710, "loss": 0.0938, "lr": 2.4896798634508195e-08, "epoch": 4.681818181818182, "percentage": 93.64, "elapsed_time": "1:22:53", "remaining_time": "0:05:38", "throughput": 5174.09, "total_tokens": 25735168} {"current_steps": 6284, "total_steps": 6710, "loss": 0.0368, "lr": 2.4780708929512537e-08, "epoch": 4.682563338301043, "percentage": 93.65, "elapsed_time": "1:22:54", "remaining_time": "0:05:37", "throughput": 5174.09, "total_tokens": 25739264} {"current_steps": 6285, "total_steps": 6710, "loss": 0.0877, "lr": 2.4664887801334054e-08, "epoch": 4.683308494783905, "percentage": 93.67, "elapsed_time": "1:22:55", "remaining_time": "0:05:36", "throughput": 5174.08, "total_tokens": 25743360} {"current_steps": 6286, "total_steps": 6710, "loss": 0.068, "lr": 2.4549335275362157e-08, "epoch": 4.684053651266766, "percentage": 93.68, "elapsed_time": "1:22:56", "remaining_time": "0:05:35", "throughput": 5174.09, "total_tokens": 25747456} {"current_steps": 6287, "total_steps": 6710, "loss": 0.1305, "lr": 2.443405137692631e-08, "epoch": 4.684798807749628, "percentage": 93.7, "elapsed_time": "1:22:57", "remaining_time": "0:05:34", "throughput": 5174.09, "total_tokens": 25751552} {"current_steps": 6288, "total_steps": 6710, "loss": 0.047, "lr": 2.4319036131297825e-08, "epoch": 4.6855439642324885, "percentage": 93.71, "elapsed_time": "1:22:57", "remaining_time": "0:05:34", "throughput": 5174.09, "total_tokens": 25755648} {"current_steps": 6289, "total_steps": 6710, "loss": 0.0353, "lr": 2.4204289563688478e-08, "epoch": 4.68628912071535, "percentage": 93.73, "elapsed_time": "1:22:58", "remaining_time": "0:05:33", "throughput": 5174.09, "total_tokens": 25759744} {"current_steps": 6290, "total_steps": 6710, "loss": 0.0474, "lr": 2.4089811699252176e-08, "epoch": 4.687034277198212, "percentage": 93.74, "elapsed_time": "1:22:59", "remaining_time": "0:05:32", "throughput": 5174.09, "total_tokens": 25763840} {"current_steps": 6291, "total_steps": 6710, "loss": 0.0864, "lr": 2.3975602563082732e-08, "epoch": 4.687779433681073, "percentage": 93.76, "elapsed_time": "1:23:00", "remaining_time": "0:05:31", "throughput": 5174.09, "total_tokens": 25767936} {"current_steps": 6292, "total_steps": 6710, "loss": 0.0978, "lr": 2.3861662180215822e-08, "epoch": 4.688524590163935, "percentage": 93.77, "elapsed_time": "1:23:00", "remaining_time": "0:05:30", "throughput": 5174.09, "total_tokens": 25772032} {"current_steps": 6293, "total_steps": 6710, "loss": 0.2382, "lr": 2.374799057562799e-08, "epoch": 4.689269746646795, "percentage": 93.79, "elapsed_time": "1:23:01", "remaining_time": "0:05:30", "throughput": 5174.1, "total_tokens": 25776128} {"current_steps": 6294, "total_steps": 6710, "loss": 0.1466, "lr": 2.36345877742368e-08, "epoch": 4.690014903129657, "percentage": 93.8, "elapsed_time": "1:23:02", "remaining_time": "0:05:29", "throughput": 5174.09, "total_tokens": 25780224} {"current_steps": 6295, "total_steps": 6710, "loss": 0.139, "lr": 2.3521453800901122e-08, "epoch": 4.6907600596125185, "percentage": 93.82, "elapsed_time": "1:23:03", "remaining_time": "0:05:28", "throughput": 5174.08, "total_tokens": 25784320} {"current_steps": 6296, "total_steps": 6710, "loss": 0.0046, "lr": 2.3408588680420424e-08, "epoch": 4.69150521609538, "percentage": 93.83, "elapsed_time": "1:23:04", "remaining_time": "0:05:27", "throughput": 5174.08, "total_tokens": 25788416} {"current_steps": 6297, "total_steps": 6710, "loss": 0.1507, "lr": 2.3295992437535884e-08, "epoch": 4.692250372578242, "percentage": 93.85, "elapsed_time": "1:23:04", "remaining_time": "0:05:26", "throughput": 5174.08, "total_tokens": 25792512} {"current_steps": 6298, "total_steps": 6710, "loss": 0.07, "lr": 2.3183665096929153e-08, "epoch": 4.692995529061103, "percentage": 93.86, "elapsed_time": "1:23:05", "remaining_time": "0:05:26", "throughput": 5174.0, "total_tokens": 25796608} {"current_steps": 6299, "total_steps": 6710, "loss": 0.1348, "lr": 2.3071606683223307e-08, "epoch": 4.693740685543965, "percentage": 93.87, "elapsed_time": "1:23:06", "remaining_time": "0:05:25", "throughput": 5174.01, "total_tokens": 25800704} {"current_steps": 6300, "total_steps": 6710, "loss": 0.0261, "lr": 2.295981722098245e-08, "epoch": 4.694485842026825, "percentage": 93.89, "elapsed_time": "1:23:07", "remaining_time": "0:05:24", "throughput": 5174.01, "total_tokens": 25804800} {"current_steps": 6301, "total_steps": 6710, "loss": 0.0089, "lr": 2.2848296734711424e-08, "epoch": 4.695230998509687, "percentage": 93.9, "elapsed_time": "1:23:08", "remaining_time": "0:05:23", "throughput": 5173.97, "total_tokens": 25808896} {"current_steps": 6302, "total_steps": 6710, "loss": 0.1018, "lr": 2.2737045248856505e-08, "epoch": 4.6959761549925485, "percentage": 93.92, "elapsed_time": "1:23:09", "remaining_time": "0:05:22", "throughput": 5173.97, "total_tokens": 25812992} {"current_steps": 6303, "total_steps": 6710, "loss": 0.1963, "lr": 2.2626062787804437e-08, "epoch": 4.69672131147541, "percentage": 93.93, "elapsed_time": "1:23:09", "remaining_time": "0:05:22", "throughput": 5173.98, "total_tokens": 25817088} {"current_steps": 6304, "total_steps": 6710, "loss": 0.0979, "lr": 2.2515349375883816e-08, "epoch": 4.697466467958272, "percentage": 93.95, "elapsed_time": "1:23:10", "remaining_time": "0:05:21", "throughput": 5173.97, "total_tokens": 25821184} {"current_steps": 6305, "total_steps": 6710, "loss": 0.0886, "lr": 2.240490503736356e-08, "epoch": 4.698211624441132, "percentage": 93.96, "elapsed_time": "1:23:11", "remaining_time": "0:05:20", "throughput": 5173.98, "total_tokens": 25825280} {"current_steps": 6306, "total_steps": 6710, "loss": 0.1635, "lr": 2.2294729796454028e-08, "epoch": 4.698956780923994, "percentage": 93.98, "elapsed_time": "1:23:12", "remaining_time": "0:05:19", "throughput": 5173.99, "total_tokens": 25829376} {"current_steps": 6307, "total_steps": 6710, "loss": 0.1414, "lr": 2.2184823677306318e-08, "epoch": 4.699701937406855, "percentage": 93.99, "elapsed_time": "1:23:12", "remaining_time": "0:05:19", "throughput": 5173.97, "total_tokens": 25833472} {"current_steps": 6308, "total_steps": 6710, "loss": 0.0699, "lr": 2.207518670401254e-08, "epoch": 4.700447093889717, "percentage": 94.01, "elapsed_time": "1:23:13", "remaining_time": "0:05:18", "throughput": 5173.98, "total_tokens": 25837568} {"current_steps": 6309, "total_steps": 6710, "loss": 0.0315, "lr": 2.1965818900606118e-08, "epoch": 4.7011922503725785, "percentage": 94.02, "elapsed_time": "1:23:14", "remaining_time": "0:05:17", "throughput": 5173.98, "total_tokens": 25841664} {"current_steps": 6310, "total_steps": 6710, "loss": 0.0057, "lr": 2.1856720291061063e-08, "epoch": 4.701937406855439, "percentage": 94.04, "elapsed_time": "1:23:15", "remaining_time": "0:05:16", "throughput": 5173.96, "total_tokens": 25845760} {"current_steps": 6311, "total_steps": 6710, "loss": 0.006, "lr": 2.1747890899292688e-08, "epoch": 4.702682563338301, "percentage": 94.05, "elapsed_time": "1:23:16", "remaining_time": "0:05:15", "throughput": 5173.96, "total_tokens": 25849856} {"current_steps": 6312, "total_steps": 6710, "loss": 0.0113, "lr": 2.1639330749157055e-08, "epoch": 4.703427719821162, "percentage": 94.07, "elapsed_time": "1:23:16", "remaining_time": "0:05:15", "throughput": 5173.96, "total_tokens": 25853952} {"current_steps": 6313, "total_steps": 6710, "loss": 0.0834, "lr": 2.1531039864451652e-08, "epoch": 4.704172876304024, "percentage": 94.08, "elapsed_time": "1:23:17", "remaining_time": "0:05:14", "throughput": 5173.97, "total_tokens": 25858048} {"current_steps": 6314, "total_steps": 6710, "loss": 0.3098, "lr": 2.142301826891416e-08, "epoch": 4.704918032786885, "percentage": 94.1, "elapsed_time": "1:23:18", "remaining_time": "0:05:13", "throughput": 5173.97, "total_tokens": 25862144} {"current_steps": 6315, "total_steps": 6710, "loss": 0.0273, "lr": 2.1315265986223967e-08, "epoch": 4.705663189269747, "percentage": 94.11, "elapsed_time": "1:23:19", "remaining_time": "0:05:12", "throughput": 5173.96, "total_tokens": 25866240} {"current_steps": 6316, "total_steps": 6710, "loss": 0.0394, "lr": 2.120778304000093e-08, "epoch": 4.7064083457526085, "percentage": 94.13, "elapsed_time": "1:23:20", "remaining_time": "0:05:11", "throughput": 5173.96, "total_tokens": 25870336} {"current_steps": 6317, "total_steps": 6710, "loss": 0.1311, "lr": 2.1100569453806203e-08, "epoch": 4.707153502235469, "percentage": 94.14, "elapsed_time": "1:23:20", "remaining_time": "0:05:11", "throughput": 5173.96, "total_tokens": 25874432} {"current_steps": 6318, "total_steps": 6710, "loss": 0.0681, "lr": 2.099362525114196e-08, "epoch": 4.707898658718331, "percentage": 94.16, "elapsed_time": "1:23:21", "remaining_time": "0:05:10", "throughput": 5173.97, "total_tokens": 25878528} {"current_steps": 6319, "total_steps": 6710, "loss": 0.0423, "lr": 2.0886950455450834e-08, "epoch": 4.708643815201192, "percentage": 94.17, "elapsed_time": "1:23:22", "remaining_time": "0:05:09", "throughput": 5173.96, "total_tokens": 25882624} {"current_steps": 6320, "total_steps": 6710, "loss": 0.0682, "lr": 2.078054509011676e-08, "epoch": 4.709388971684054, "percentage": 94.19, "elapsed_time": "1:23:23", "remaining_time": "0:05:08", "throughput": 5173.97, "total_tokens": 25886720} {"current_steps": 6321, "total_steps": 6710, "loss": 0.1312, "lr": 2.0674409178464695e-08, "epoch": 4.710134128166915, "percentage": 94.2, "elapsed_time": "1:23:24", "remaining_time": "0:05:07", "throughput": 5173.97, "total_tokens": 25890816} {"current_steps": 6322, "total_steps": 6710, "loss": 0.0369, "lr": 2.0568542743760328e-08, "epoch": 4.710879284649776, "percentage": 94.22, "elapsed_time": "1:23:24", "remaining_time": "0:05:07", "throughput": 5173.97, "total_tokens": 25894912} {"current_steps": 6323, "total_steps": 6710, "loss": 0.1026, "lr": 2.0462945809210238e-08, "epoch": 4.711624441132638, "percentage": 94.23, "elapsed_time": "1:23:25", "remaining_time": "0:05:06", "throughput": 5173.95, "total_tokens": 25899008} {"current_steps": 6324, "total_steps": 6710, "loss": 0.0843, "lr": 2.0357618397962158e-08, "epoch": 4.712369597615499, "percentage": 94.25, "elapsed_time": "1:23:26", "remaining_time": "0:05:05", "throughput": 5173.96, "total_tokens": 25903104} {"current_steps": 6325, "total_steps": 6710, "loss": 0.1089, "lr": 2.0252560533104565e-08, "epoch": 4.713114754098361, "percentage": 94.26, "elapsed_time": "1:23:27", "remaining_time": "0:05:04", "throughput": 5173.96, "total_tokens": 25907200} {"current_steps": 6326, "total_steps": 6710, "loss": 0.0414, "lr": 2.0147772237666953e-08, "epoch": 4.713859910581222, "percentage": 94.28, "elapsed_time": "1:23:28", "remaining_time": "0:05:03", "throughput": 5173.96, "total_tokens": 25911296} {"current_steps": 6327, "total_steps": 6710, "loss": 0.0207, "lr": 2.0043253534619417e-08, "epoch": 4.714605067064084, "percentage": 94.29, "elapsed_time": "1:23:28", "remaining_time": "0:05:03", "throughput": 5173.95, "total_tokens": 25915392} {"current_steps": 6328, "total_steps": 6710, "loss": 0.021, "lr": 1.9939004446873495e-08, "epoch": 4.715350223546945, "percentage": 94.31, "elapsed_time": "1:23:29", "remaining_time": "0:05:02", "throughput": 5173.95, "total_tokens": 25919488} {"current_steps": 6329, "total_steps": 6710, "loss": 0.142, "lr": 1.9835024997281322e-08, "epoch": 4.716095380029806, "percentage": 94.32, "elapsed_time": "1:23:30", "remaining_time": "0:05:01", "throughput": 5173.94, "total_tokens": 25923584} {"current_steps": 6330, "total_steps": 6710, "loss": 0.1267, "lr": 1.9731315208635638e-08, "epoch": 4.7168405365126675, "percentage": 94.34, "elapsed_time": "1:23:31", "remaining_time": "0:05:00", "throughput": 5173.93, "total_tokens": 25927680} {"current_steps": 6331, "total_steps": 6710, "loss": 0.0349, "lr": 1.9627875103670618e-08, "epoch": 4.717585692995529, "percentage": 94.35, "elapsed_time": "1:23:32", "remaining_time": "0:05:00", "throughput": 5173.93, "total_tokens": 25931776} {"current_steps": 6332, "total_steps": 6710, "loss": 0.1263, "lr": 1.9524704705061043e-08, "epoch": 4.718330849478391, "percentage": 94.37, "elapsed_time": "1:23:32", "remaining_time": "0:04:59", "throughput": 5173.93, "total_tokens": 25935872} {"current_steps": 6333, "total_steps": 6710, "loss": 0.0797, "lr": 1.942180403542257e-08, "epoch": 4.719076005961252, "percentage": 94.38, "elapsed_time": "1:23:33", "remaining_time": "0:04:58", "throughput": 5173.93, "total_tokens": 25939968} {"current_steps": 6334, "total_steps": 6710, "loss": 0.0767, "lr": 1.9319173117311742e-08, "epoch": 4.719821162444113, "percentage": 94.4, "elapsed_time": "1:23:34", "remaining_time": "0:04:57", "throughput": 5173.92, "total_tokens": 25944064} {"current_steps": 6335, "total_steps": 6710, "loss": 0.0976, "lr": 1.921681197322611e-08, "epoch": 4.720566318926974, "percentage": 94.41, "elapsed_time": "1:23:35", "remaining_time": "0:04:56", "throughput": 5173.93, "total_tokens": 25948160} {"current_steps": 6336, "total_steps": 6710, "loss": 0.0484, "lr": 1.911472062560371e-08, "epoch": 4.721311475409836, "percentage": 94.43, "elapsed_time": "1:23:35", "remaining_time": "0:04:56", "throughput": 5173.94, "total_tokens": 25952256} {"current_steps": 6337, "total_steps": 6710, "loss": 0.1318, "lr": 1.9012899096823996e-08, "epoch": 4.7220566318926975, "percentage": 94.44, "elapsed_time": "1:23:36", "remaining_time": "0:04:55", "throughput": 5173.94, "total_tokens": 25956352} {"current_steps": 6338, "total_steps": 6710, "loss": 0.0499, "lr": 1.891134740920675e-08, "epoch": 4.722801788375559, "percentage": 94.46, "elapsed_time": "1:23:37", "remaining_time": "0:04:54", "throughput": 5173.94, "total_tokens": 25960448} {"current_steps": 6339, "total_steps": 6710, "loss": 0.0227, "lr": 1.8810065585012915e-08, "epoch": 4.723546944858421, "percentage": 94.47, "elapsed_time": "1:23:38", "remaining_time": "0:04:53", "throughput": 5173.95, "total_tokens": 25964544} {"current_steps": 6340, "total_steps": 6710, "loss": 0.0323, "lr": 1.8709053646444318e-08, "epoch": 4.724292101341281, "percentage": 94.49, "elapsed_time": "1:23:39", "remaining_time": "0:04:52", "throughput": 5173.96, "total_tokens": 25968640} {"current_steps": 6341, "total_steps": 6710, "loss": 0.0294, "lr": 1.860831161564325e-08, "epoch": 4.725037257824143, "percentage": 94.5, "elapsed_time": "1:23:39", "remaining_time": "0:04:52", "throughput": 5173.97, "total_tokens": 25972736} {"current_steps": 6342, "total_steps": 6710, "loss": 0.1123, "lr": 1.850783951469315e-08, "epoch": 4.725782414307004, "percentage": 94.52, "elapsed_time": "1:23:40", "remaining_time": "0:04:51", "throughput": 5173.97, "total_tokens": 25976832} {"current_steps": 6343, "total_steps": 6710, "loss": 0.1031, "lr": 1.8407637365618346e-08, "epoch": 4.726527570789866, "percentage": 94.53, "elapsed_time": "1:23:41", "remaining_time": "0:04:50", "throughput": 5173.98, "total_tokens": 25980928} {"current_steps": 6344, "total_steps": 6710, "loss": 0.1238, "lr": 1.8307705190383773e-08, "epoch": 4.7272727272727275, "percentage": 94.55, "elapsed_time": "1:23:42", "remaining_time": "0:04:49", "throughput": 5173.94, "total_tokens": 25985024} {"current_steps": 6345, "total_steps": 6710, "loss": 0.0574, "lr": 1.8208043010895375e-08, "epoch": 4.728017883755589, "percentage": 94.56, "elapsed_time": "1:23:43", "remaining_time": "0:04:48", "throughput": 5173.95, "total_tokens": 25989120} {"current_steps": 6346, "total_steps": 6710, "loss": 0.0196, "lr": 1.810865084899957e-08, "epoch": 4.72876304023845, "percentage": 94.58, "elapsed_time": "1:23:43", "remaining_time": "0:04:48", "throughput": 5173.95, "total_tokens": 25993216} {"current_steps": 6347, "total_steps": 6710, "loss": 0.0427, "lr": 1.8009528726484064e-08, "epoch": 4.729508196721311, "percentage": 94.59, "elapsed_time": "1:23:44", "remaining_time": "0:04:47", "throughput": 5173.96, "total_tokens": 25997312} {"current_steps": 6348, "total_steps": 6710, "loss": 0.0225, "lr": 1.791067666507704e-08, "epoch": 4.730253353204173, "percentage": 94.61, "elapsed_time": "1:23:45", "remaining_time": "0:04:46", "throughput": 5173.97, "total_tokens": 26001408} {"current_steps": 6349, "total_steps": 6710, "loss": 0.0468, "lr": 1.781209468644754e-08, "epoch": 4.730998509687034, "percentage": 94.62, "elapsed_time": "1:23:46", "remaining_time": "0:04:45", "throughput": 5173.98, "total_tokens": 26005504} {"current_steps": 6350, "total_steps": 6710, "loss": 0.0834, "lr": 1.771378281220551e-08, "epoch": 4.731743666169896, "percentage": 94.63, "elapsed_time": "1:23:46", "remaining_time": "0:04:44", "throughput": 5173.99, "total_tokens": 26009600} {"current_steps": 6351, "total_steps": 6710, "loss": 0.0265, "lr": 1.7615741063901764e-08, "epoch": 4.732488822652757, "percentage": 94.65, "elapsed_time": "1:23:47", "remaining_time": "0:04:44", "throughput": 5174.0, "total_tokens": 26013696} {"current_steps": 6352, "total_steps": 6710, "loss": 0.0614, "lr": 1.7517969463027446e-08, "epoch": 4.733233979135618, "percentage": 94.66, "elapsed_time": "1:23:48", "remaining_time": "0:04:43", "throughput": 5174.01, "total_tokens": 26017792} {"current_steps": 6353, "total_steps": 6710, "loss": 0.121, "lr": 1.742046803101499e-08, "epoch": 4.73397913561848, "percentage": 94.68, "elapsed_time": "1:23:49", "remaining_time": "0:04:42", "throughput": 5174.02, "total_tokens": 26021888} {"current_steps": 6354, "total_steps": 6710, "loss": 0.2127, "lr": 1.7323236789237307e-08, "epoch": 4.734724292101341, "percentage": 94.69, "elapsed_time": "1:23:50", "remaining_time": "0:04:41", "throughput": 5174.03, "total_tokens": 26025984} {"current_steps": 6355, "total_steps": 6710, "loss": 0.0142, "lr": 1.7226275759008175e-08, "epoch": 4.735469448584203, "percentage": 94.71, "elapsed_time": "1:23:50", "remaining_time": "0:04:41", "throughput": 5174.04, "total_tokens": 26030080} {"current_steps": 6356, "total_steps": 6710, "loss": 0.045, "lr": 1.7129584961582263e-08, "epoch": 4.736214605067064, "percentage": 94.72, "elapsed_time": "1:23:51", "remaining_time": "0:04:40", "throughput": 5174.05, "total_tokens": 26034176} {"current_steps": 6357, "total_steps": 6710, "loss": 0.0978, "lr": 1.7033164418154696e-08, "epoch": 4.736959761549926, "percentage": 94.74, "elapsed_time": "1:23:52", "remaining_time": "0:04:39", "throughput": 5174.05, "total_tokens": 26038272} {"current_steps": 6358, "total_steps": 6710, "loss": 0.0956, "lr": 1.6937014149861902e-08, "epoch": 4.737704918032787, "percentage": 94.75, "elapsed_time": "1:23:53", "remaining_time": "0:04:38", "throughput": 5174.05, "total_tokens": 26042368} {"current_steps": 6359, "total_steps": 6710, "loss": 0.0632, "lr": 1.6841134177780216e-08, "epoch": 4.738450074515648, "percentage": 94.77, "elapsed_time": "1:23:54", "remaining_time": "0:04:37", "throughput": 5174.05, "total_tokens": 26046464} {"current_steps": 6360, "total_steps": 6710, "loss": 0.1254, "lr": 1.6745524522927546e-08, "epoch": 4.73919523099851, "percentage": 94.78, "elapsed_time": "1:23:54", "remaining_time": "0:04:37", "throughput": 5174.05, "total_tokens": 26050560} {"current_steps": 6361, "total_steps": 6710, "loss": 0.0447, "lr": 1.6650185206261992e-08, "epoch": 4.739940387481371, "percentage": 94.8, "elapsed_time": "1:23:55", "remaining_time": "0:04:36", "throughput": 5174.04, "total_tokens": 26054656} {"current_steps": 6362, "total_steps": 6710, "loss": 0.1077, "lr": 1.6555116248682946e-08, "epoch": 4.740685543964233, "percentage": 94.81, "elapsed_time": "1:23:56", "remaining_time": "0:04:35", "throughput": 5174.04, "total_tokens": 26058752} {"current_steps": 6363, "total_steps": 6710, "loss": 0.0353, "lr": 1.6460317671029984e-08, "epoch": 4.7414307004470935, "percentage": 94.83, "elapsed_time": "1:23:57", "remaining_time": "0:04:34", "throughput": 5174.04, "total_tokens": 26062848} {"current_steps": 6364, "total_steps": 6710, "loss": 0.0283, "lr": 1.6365789494083574e-08, "epoch": 4.742175856929955, "percentage": 94.84, "elapsed_time": "1:23:58", "remaining_time": "0:04:33", "throughput": 5174.05, "total_tokens": 26066944} {"current_steps": 6365, "total_steps": 6710, "loss": 0.1131, "lr": 1.627153173856505e-08, "epoch": 4.742921013412817, "percentage": 94.86, "elapsed_time": "1:23:58", "remaining_time": "0:04:33", "throughput": 5174.05, "total_tokens": 26071040} {"current_steps": 6366, "total_steps": 6710, "loss": 0.0367, "lr": 1.617754442513636e-08, "epoch": 4.743666169895678, "percentage": 94.87, "elapsed_time": "1:23:59", "remaining_time": "0:04:32", "throughput": 5174.06, "total_tokens": 26075136} {"current_steps": 6367, "total_steps": 6710, "loss": 0.2459, "lr": 1.608382757440033e-08, "epoch": 4.74441132637854, "percentage": 94.89, "elapsed_time": "1:24:00", "remaining_time": "0:04:31", "throughput": 5174.05, "total_tokens": 26079232} {"current_steps": 6368, "total_steps": 6710, "loss": 0.182, "lr": 1.5990381206900108e-08, "epoch": 4.745156482861401, "percentage": 94.9, "elapsed_time": "1:24:01", "remaining_time": "0:04:30", "throughput": 5174.05, "total_tokens": 26083328} {"current_steps": 6369, "total_steps": 6710, "loss": 0.0297, "lr": 1.5897205343120003e-08, "epoch": 4.745901639344263, "percentage": 94.92, "elapsed_time": "1:24:01", "remaining_time": "0:04:29", "throughput": 5174.06, "total_tokens": 26087424} {"current_steps": 6370, "total_steps": 6710, "loss": 0.0222, "lr": 1.580430000348479e-08, "epoch": 4.7466467958271235, "percentage": 94.93, "elapsed_time": "1:24:02", "remaining_time": "0:04:29", "throughput": 5174.06, "total_tokens": 26091520} {"current_steps": 6371, "total_steps": 6710, "loss": 0.0641, "lr": 1.571166520835998e-08, "epoch": 4.747391952309985, "percentage": 94.95, "elapsed_time": "1:24:03", "remaining_time": "0:04:28", "throughput": 5174.07, "total_tokens": 26095616} {"current_steps": 6372, "total_steps": 6710, "loss": 0.029, "lr": 1.561930097805156e-08, "epoch": 4.748137108792847, "percentage": 94.96, "elapsed_time": "1:24:04", "remaining_time": "0:04:27", "throughput": 5174.08, "total_tokens": 26099712} {"current_steps": 6373, "total_steps": 6710, "loss": 0.2809, "lr": 1.55272073328068e-08, "epoch": 4.748882265275708, "percentage": 94.98, "elapsed_time": "1:24:05", "remaining_time": "0:04:26", "throughput": 5174.09, "total_tokens": 26103808} {"current_steps": 6374, "total_steps": 6710, "loss": 0.0395, "lr": 1.543538429281316e-08, "epoch": 4.74962742175857, "percentage": 94.99, "elapsed_time": "1:24:05", "remaining_time": "0:04:25", "throughput": 5174.09, "total_tokens": 26107904} {"current_steps": 6375, "total_steps": 6710, "loss": 0.0749, "lr": 1.534383187819871e-08, "epoch": 4.75037257824143, "percentage": 95.01, "elapsed_time": "1:24:06", "remaining_time": "0:04:25", "throughput": 5174.1, "total_tokens": 26112000} {"current_steps": 6376, "total_steps": 6710, "loss": 0.0684, "lr": 1.5252550109032678e-08, "epoch": 4.751117734724292, "percentage": 95.02, "elapsed_time": "1:24:07", "remaining_time": "0:04:24", "throughput": 5174.11, "total_tokens": 26116096} {"current_steps": 6377, "total_steps": 6710, "loss": 0.0107, "lr": 1.5161539005324465e-08, "epoch": 4.751862891207153, "percentage": 95.04, "elapsed_time": "1:24:08", "remaining_time": "0:04:23", "throughput": 5174.12, "total_tokens": 26120192} {"current_steps": 6378, "total_steps": 6710, "loss": 0.235, "lr": 1.507079858702451e-08, "epoch": 4.752608047690015, "percentage": 95.05, "elapsed_time": "1:24:09", "remaining_time": "0:04:22", "throughput": 5174.13, "total_tokens": 26124288} {"current_steps": 6379, "total_steps": 6710, "loss": 0.0586, "lr": 1.4980328874023703e-08, "epoch": 4.7533532041728765, "percentage": 95.07, "elapsed_time": "1:24:09", "remaining_time": "0:04:22", "throughput": 5174.14, "total_tokens": 26128384} {"current_steps": 6380, "total_steps": 6710, "loss": 0.2122, "lr": 1.4890129886153681e-08, "epoch": 4.754098360655737, "percentage": 95.08, "elapsed_time": "1:24:10", "remaining_time": "0:04:21", "throughput": 5174.15, "total_tokens": 26132480} {"current_steps": 6381, "total_steps": 6710, "loss": 0.0161, "lr": 1.4800201643186407e-08, "epoch": 4.754843517138599, "percentage": 95.1, "elapsed_time": "1:24:11", "remaining_time": "0:04:20", "throughput": 5174.16, "total_tokens": 26136576} {"current_steps": 6382, "total_steps": 6710, "loss": 0.0428, "lr": 1.4710544164835277e-08, "epoch": 4.75558867362146, "percentage": 95.11, "elapsed_time": "1:24:12", "remaining_time": "0:04:19", "throughput": 5174.16, "total_tokens": 26140672} {"current_steps": 6383, "total_steps": 6710, "loss": 0.0169, "lr": 1.46211574707536e-08, "epoch": 4.756333830104322, "percentage": 95.13, "elapsed_time": "1:24:12", "remaining_time": "0:04:18", "throughput": 5174.17, "total_tokens": 26144768} {"current_steps": 6384, "total_steps": 6710, "loss": 0.0354, "lr": 1.4532041580535422e-08, "epoch": 4.757078986587183, "percentage": 95.14, "elapsed_time": "1:24:13", "remaining_time": "0:04:18", "throughput": 5174.18, "total_tokens": 26148864} {"current_steps": 6385, "total_steps": 6710, "loss": 0.0601, "lr": 1.4443196513715952e-08, "epoch": 4.757824143070045, "percentage": 95.16, "elapsed_time": "1:24:14", "remaining_time": "0:04:17", "throughput": 5174.19, "total_tokens": 26152960} {"current_steps": 6386, "total_steps": 6710, "loss": 0.0043, "lr": 1.4354622289770443e-08, "epoch": 4.7585692995529065, "percentage": 95.17, "elapsed_time": "1:24:15", "remaining_time": "0:04:16", "throughput": 5174.19, "total_tokens": 26157056} {"current_steps": 6387, "total_steps": 6710, "loss": 0.0321, "lr": 1.4266318928114892e-08, "epoch": 4.759314456035767, "percentage": 95.19, "elapsed_time": "1:24:16", "remaining_time": "0:04:15", "throughput": 5174.19, "total_tokens": 26161152} {"current_steps": 6388, "total_steps": 6710, "loss": 0.1248, "lr": 1.4178286448106315e-08, "epoch": 4.760059612518629, "percentage": 95.2, "elapsed_time": "1:24:16", "remaining_time": "0:04:14", "throughput": 5174.2, "total_tokens": 26165248} {"current_steps": 6389, "total_steps": 6710, "loss": 0.1206, "lr": 1.4090524869041777e-08, "epoch": 4.76080476900149, "percentage": 95.22, "elapsed_time": "1:24:17", "remaining_time": "0:04:14", "throughput": 5174.2, "total_tokens": 26169344} {"current_steps": 6390, "total_steps": 6710, "loss": 0.0735, "lr": 1.4003034210159499e-08, "epoch": 4.761549925484352, "percentage": 95.23, "elapsed_time": "1:24:18", "remaining_time": "0:04:13", "throughput": 5174.2, "total_tokens": 26173440} {"current_steps": 6391, "total_steps": 6710, "loss": 0.032, "lr": 1.3915814490637752e-08, "epoch": 4.762295081967213, "percentage": 95.25, "elapsed_time": "1:24:19", "remaining_time": "0:04:12", "throughput": 5174.21, "total_tokens": 26177536} {"current_steps": 6392, "total_steps": 6710, "loss": 0.0581, "lr": 1.3828865729596103e-08, "epoch": 4.763040238450074, "percentage": 95.26, "elapsed_time": "1:24:20", "remaining_time": "0:04:11", "throughput": 5174.21, "total_tokens": 26181632} {"current_steps": 6393, "total_steps": 6710, "loss": 0.1221, "lr": 1.3742187946094026e-08, "epoch": 4.763785394932936, "percentage": 95.28, "elapsed_time": "1:24:20", "remaining_time": "0:04:10", "throughput": 5174.22, "total_tokens": 26185728} {"current_steps": 6394, "total_steps": 6710, "loss": 0.0894, "lr": 1.3655781159132159e-08, "epoch": 4.764530551415797, "percentage": 95.29, "elapsed_time": "1:24:21", "remaining_time": "0:04:10", "throughput": 5174.23, "total_tokens": 26189824} {"current_steps": 6395, "total_steps": 6710, "loss": 0.0568, "lr": 1.356964538765118e-08, "epoch": 4.765275707898659, "percentage": 95.31, "elapsed_time": "1:24:22", "remaining_time": "0:04:09", "throughput": 5174.23, "total_tokens": 26193920} {"current_steps": 6396, "total_steps": 6710, "loss": 0.0774, "lr": 1.3483780650532796e-08, "epoch": 4.76602086438152, "percentage": 95.32, "elapsed_time": "1:24:23", "remaining_time": "0:04:08", "throughput": 5174.24, "total_tokens": 26198016} {"current_steps": 6397, "total_steps": 6710, "loss": 0.0952, "lr": 1.3398186966599307e-08, "epoch": 4.766766020864382, "percentage": 95.34, "elapsed_time": "1:24:23", "remaining_time": "0:04:07", "throughput": 5174.25, "total_tokens": 26202112} {"current_steps": 6398, "total_steps": 6710, "loss": 0.1572, "lr": 1.3312864354613347e-08, "epoch": 4.767511177347243, "percentage": 95.35, "elapsed_time": "1:24:24", "remaining_time": "0:04:06", "throughput": 5174.25, "total_tokens": 26206208} {"current_steps": 6399, "total_steps": 6710, "loss": 0.1141, "lr": 1.3227812833278147e-08, "epoch": 4.768256333830104, "percentage": 95.37, "elapsed_time": "1:24:25", "remaining_time": "0:04:06", "throughput": 5174.26, "total_tokens": 26210304} {"current_steps": 6400, "total_steps": 6710, "loss": 0.0949, "lr": 1.3143032421237961e-08, "epoch": 4.769001490312966, "percentage": 95.38, "elapsed_time": "1:24:26", "remaining_time": "0:04:05", "throughput": 5174.27, "total_tokens": 26214400} {"current_steps": 6401, "total_steps": 6710, "loss": 0.0804, "lr": 1.3058523137076812e-08, "epoch": 4.769746646795827, "percentage": 95.39, "elapsed_time": "1:24:27", "remaining_time": "0:04:04", "throughput": 5174.27, "total_tokens": 26218496} {"current_steps": 6402, "total_steps": 6710, "loss": 0.0941, "lr": 1.2974284999320019e-08, "epoch": 4.770491803278689, "percentage": 95.41, "elapsed_time": "1:24:27", "remaining_time": "0:04:03", "throughput": 5174.26, "total_tokens": 26222592} {"current_steps": 6403, "total_steps": 6710, "loss": 0.2099, "lr": 1.2890318026433091e-08, "epoch": 4.77123695976155, "percentage": 95.42, "elapsed_time": "1:24:28", "remaining_time": "0:04:03", "throughput": 5174.27, "total_tokens": 26226688} {"current_steps": 6404, "total_steps": 6710, "loss": 0.069, "lr": 1.2806622236822136e-08, "epoch": 4.771982116244411, "percentage": 95.44, "elapsed_time": "1:24:29", "remaining_time": "0:04:02", "throughput": 5174.28, "total_tokens": 26230784} {"current_steps": 6405, "total_steps": 6710, "loss": 0.1485, "lr": 1.2723197648834145e-08, "epoch": 4.7727272727272725, "percentage": 95.45, "elapsed_time": "1:24:30", "remaining_time": "0:04:01", "throughput": 5174.29, "total_tokens": 26234880} {"current_steps": 6406, "total_steps": 6710, "loss": 0.2116, "lr": 1.2640044280755882e-08, "epoch": 4.773472429210134, "percentage": 95.47, "elapsed_time": "1:24:31", "remaining_time": "0:04:00", "throughput": 5174.3, "total_tokens": 26238976} {"current_steps": 6407, "total_steps": 6710, "loss": 0.1087, "lr": 1.2557162150815816e-08, "epoch": 4.774217585692996, "percentage": 95.48, "elapsed_time": "1:24:31", "remaining_time": "0:03:59", "throughput": 5174.3, "total_tokens": 26243072} {"current_steps": 6408, "total_steps": 6710, "loss": 0.1641, "lr": 1.247455127718164e-08, "epoch": 4.774962742175857, "percentage": 95.5, "elapsed_time": "1:24:32", "remaining_time": "0:03:59", "throughput": 5174.31, "total_tokens": 26247168} {"current_steps": 6409, "total_steps": 6710, "loss": 0.0345, "lr": 1.2392211677962617e-08, "epoch": 4.775707898658719, "percentage": 95.51, "elapsed_time": "1:24:33", "remaining_time": "0:03:58", "throughput": 5174.32, "total_tokens": 26251264} {"current_steps": 6410, "total_steps": 6710, "loss": 0.109, "lr": 1.23101433712082e-08, "epoch": 4.776453055141579, "percentage": 95.53, "elapsed_time": "1:24:34", "remaining_time": "0:03:57", "throughput": 5174.33, "total_tokens": 26255360} {"current_steps": 6411, "total_steps": 6710, "loss": 0.0285, "lr": 1.2228346374908163e-08, "epoch": 4.777198211624441, "percentage": 95.54, "elapsed_time": "1:24:34", "remaining_time": "0:03:56", "throughput": 5174.34, "total_tokens": 26259456} {"current_steps": 6412, "total_steps": 6710, "loss": 0.0453, "lr": 1.2146820706993023e-08, "epoch": 4.7779433681073025, "percentage": 95.56, "elapsed_time": "1:24:35", "remaining_time": "0:03:55", "throughput": 5174.35, "total_tokens": 26263552} {"current_steps": 6413, "total_steps": 6710, "loss": 0.0867, "lr": 1.2065566385333905e-08, "epoch": 4.778688524590164, "percentage": 95.57, "elapsed_time": "1:24:36", "remaining_time": "0:03:55", "throughput": 5174.36, "total_tokens": 26267648} {"current_steps": 6414, "total_steps": 6710, "loss": 0.1252, "lr": 1.1984583427742391e-08, "epoch": 4.779433681073026, "percentage": 95.59, "elapsed_time": "1:24:37", "remaining_time": "0:03:54", "throughput": 5174.36, "total_tokens": 26271744} {"current_steps": 6415, "total_steps": 6710, "loss": 0.074, "lr": 1.1903871851970255e-08, "epoch": 4.780178837555887, "percentage": 95.6, "elapsed_time": "1:24:38", "remaining_time": "0:03:53", "throughput": 5174.37, "total_tokens": 26275840} {"current_steps": 6416, "total_steps": 6710, "loss": 0.1519, "lr": 1.182343167571029e-08, "epoch": 4.780923994038748, "percentage": 95.62, "elapsed_time": "1:24:38", "remaining_time": "0:03:52", "throughput": 5174.38, "total_tokens": 26279936} {"current_steps": 6417, "total_steps": 6710, "loss": 0.0176, "lr": 1.1743262916595472e-08, "epoch": 4.781669150521609, "percentage": 95.63, "elapsed_time": "1:24:39", "remaining_time": "0:03:51", "throughput": 5174.39, "total_tokens": 26284032} {"current_steps": 6418, "total_steps": 6710, "loss": 0.0987, "lr": 1.1663365592199244e-08, "epoch": 4.782414307004471, "percentage": 95.65, "elapsed_time": "1:24:40", "remaining_time": "0:03:51", "throughput": 5174.4, "total_tokens": 26288128} {"current_steps": 6419, "total_steps": 6710, "loss": 0.0053, "lr": 1.158373972003593e-08, "epoch": 4.7831594634873325, "percentage": 95.66, "elapsed_time": "1:24:41", "remaining_time": "0:03:50", "throughput": 5174.39, "total_tokens": 26292224} {"current_steps": 6420, "total_steps": 6710, "loss": 0.026, "lr": 1.1504385317559763e-08, "epoch": 4.783904619970194, "percentage": 95.68, "elapsed_time": "1:24:42", "remaining_time": "0:03:49", "throughput": 5174.4, "total_tokens": 26296320} {"current_steps": 6421, "total_steps": 6710, "loss": 0.0292, "lr": 1.1425302402166272e-08, "epoch": 4.784649776453055, "percentage": 95.69, "elapsed_time": "1:24:42", "remaining_time": "0:03:48", "throughput": 5174.4, "total_tokens": 26300416} {"current_steps": 6422, "total_steps": 6710, "loss": 0.0641, "lr": 1.1346490991190479e-08, "epoch": 4.785394932935916, "percentage": 95.71, "elapsed_time": "1:24:43", "remaining_time": "0:03:47", "throughput": 5174.41, "total_tokens": 26304512} {"current_steps": 6423, "total_steps": 6710, "loss": 0.1746, "lr": 1.1267951101908841e-08, "epoch": 4.786140089418778, "percentage": 95.72, "elapsed_time": "1:24:44", "remaining_time": "0:03:47", "throughput": 5174.41, "total_tokens": 26308608} {"current_steps": 6424, "total_steps": 6710, "loss": 0.0755, "lr": 1.1189682751537451e-08, "epoch": 4.786885245901639, "percentage": 95.74, "elapsed_time": "1:24:45", "remaining_time": "0:03:46", "throughput": 5174.41, "total_tokens": 26312704} {"current_steps": 6425, "total_steps": 6710, "loss": 0.1071, "lr": 1.1111685957233553e-08, "epoch": 4.787630402384501, "percentage": 95.75, "elapsed_time": "1:24:45", "remaining_time": "0:03:45", "throughput": 5174.42, "total_tokens": 26316800} {"current_steps": 6426, "total_steps": 6710, "loss": 0.1292, "lr": 1.1033960736094584e-08, "epoch": 4.788375558867362, "percentage": 95.77, "elapsed_time": "1:24:46", "remaining_time": "0:03:44", "throughput": 5174.42, "total_tokens": 26320896} {"current_steps": 6427, "total_steps": 6710, "loss": 0.1205, "lr": 1.0956507105158442e-08, "epoch": 4.789120715350224, "percentage": 95.78, "elapsed_time": "1:24:47", "remaining_time": "0:03:44", "throughput": 5174.43, "total_tokens": 26324992} {"current_steps": 6428, "total_steps": 6710, "loss": 0.1666, "lr": 1.0879325081403491e-08, "epoch": 4.789865871833085, "percentage": 95.8, "elapsed_time": "1:24:48", "remaining_time": "0:03:43", "throughput": 5174.43, "total_tokens": 26329088} {"current_steps": 6429, "total_steps": 6710, "loss": 0.1453, "lr": 1.0802414681748557e-08, "epoch": 4.790611028315946, "percentage": 95.81, "elapsed_time": "1:24:49", "remaining_time": "0:03:42", "throughput": 5174.44, "total_tokens": 26333184} {"current_steps": 6430, "total_steps": 6710, "loss": 0.1413, "lr": 1.0725775923053073e-08, "epoch": 4.791356184798808, "percentage": 95.83, "elapsed_time": "1:24:49", "remaining_time": "0:03:41", "throughput": 5174.44, "total_tokens": 26337280} {"current_steps": 6431, "total_steps": 6710, "loss": 0.0943, "lr": 1.0649408822116515e-08, "epoch": 4.792101341281669, "percentage": 95.84, "elapsed_time": "1:24:50", "remaining_time": "0:03:40", "throughput": 5174.45, "total_tokens": 26341376} {"current_steps": 6432, "total_steps": 6710, "loss": 0.0489, "lr": 1.0573313395679519e-08, "epoch": 4.792846497764531, "percentage": 95.86, "elapsed_time": "1:24:51", "remaining_time": "0:03:40", "throughput": 5174.45, "total_tokens": 26345472} {"current_steps": 6433, "total_steps": 6710, "loss": 0.1184, "lr": 1.0497489660422356e-08, "epoch": 4.7935916542473915, "percentage": 95.87, "elapsed_time": "1:24:52", "remaining_time": "0:03:39", "throughput": 5174.46, "total_tokens": 26349568} {"current_steps": 6434, "total_steps": 6710, "loss": 0.0322, "lr": 1.042193763296645e-08, "epoch": 4.794336810730253, "percentage": 95.89, "elapsed_time": "1:24:53", "remaining_time": "0:03:38", "throughput": 5174.46, "total_tokens": 26353664} {"current_steps": 6435, "total_steps": 6710, "loss": 0.06, "lr": 1.0346657329873138e-08, "epoch": 4.795081967213115, "percentage": 95.9, "elapsed_time": "1:24:53", "remaining_time": "0:03:37", "throughput": 5174.47, "total_tokens": 26357760} {"current_steps": 6436, "total_steps": 6710, "loss": 0.1109, "lr": 1.02716487676445e-08, "epoch": 4.795827123695976, "percentage": 95.92, "elapsed_time": "1:24:54", "remaining_time": "0:03:36", "throughput": 5174.47, "total_tokens": 26361856} {"current_steps": 6437, "total_steps": 6710, "loss": 0.0727, "lr": 1.0196911962722793e-08, "epoch": 4.796572280178838, "percentage": 95.93, "elapsed_time": "1:24:55", "remaining_time": "0:03:36", "throughput": 5174.48, "total_tokens": 26365952} {"current_steps": 6438, "total_steps": 6710, "loss": 0.0885, "lr": 1.012244693149103e-08, "epoch": 4.797317436661699, "percentage": 95.95, "elapsed_time": "1:24:56", "remaining_time": "0:03:35", "throughput": 5174.49, "total_tokens": 26370048} {"current_steps": 6439, "total_steps": 6710, "loss": 0.0887, "lr": 1.0048253690272402e-08, "epoch": 4.798062593144561, "percentage": 95.96, "elapsed_time": "1:24:56", "remaining_time": "0:03:34", "throughput": 5174.49, "total_tokens": 26374144} {"current_steps": 6440, "total_steps": 6710, "loss": 0.0573, "lr": 9.974332255330565e-09, "epoch": 4.7988077496274215, "percentage": 95.98, "elapsed_time": "1:24:57", "remaining_time": "0:03:33", "throughput": 5174.5, "total_tokens": 26378240} {"current_steps": 6441, "total_steps": 6710, "loss": 0.0622, "lr": 9.90068264286978e-09, "epoch": 4.799552906110283, "percentage": 95.99, "elapsed_time": "1:24:58", "remaining_time": "0:03:32", "throughput": 5174.48, "total_tokens": 26382336} {"current_steps": 6442, "total_steps": 6710, "loss": 0.0644, "lr": 9.827304869034354e-09, "epoch": 4.800298062593145, "percentage": 96.01, "elapsed_time": "1:24:59", "remaining_time": "0:03:32", "throughput": 5174.47, "total_tokens": 26386432} {"current_steps": 6443, "total_steps": 6710, "loss": 0.0641, "lr": 9.754198949909477e-09, "epoch": 4.801043219076006, "percentage": 96.02, "elapsed_time": "1:25:00", "remaining_time": "0:03:31", "throughput": 5174.46, "total_tokens": 26390528} {"current_steps": 6444, "total_steps": 6710, "loss": 0.1725, "lr": 9.681364901520247e-09, "epoch": 4.801788375558868, "percentage": 96.04, "elapsed_time": "1:25:00", "remaining_time": "0:03:30", "throughput": 5174.46, "total_tokens": 26394624} {"current_steps": 6445, "total_steps": 6710, "loss": 0.0815, "lr": 9.608802739832363e-09, "epoch": 4.802533532041728, "percentage": 96.05, "elapsed_time": "1:25:01", "remaining_time": "0:03:29", "throughput": 5174.47, "total_tokens": 26398720} {"current_steps": 6446, "total_steps": 6710, "loss": 0.1232, "lr": 9.53651248075227e-09, "epoch": 4.80327868852459, "percentage": 96.07, "elapsed_time": "1:25:02", "remaining_time": "0:03:28", "throughput": 5174.48, "total_tokens": 26402816} {"current_steps": 6447, "total_steps": 6710, "loss": 0.024, "lr": 9.464494140126318e-09, "epoch": 4.8040238450074515, "percentage": 96.08, "elapsed_time": "1:25:03", "remaining_time": "0:03:28", "throughput": 5174.49, "total_tokens": 26406912} {"current_steps": 6448, "total_steps": 6710, "loss": 0.0247, "lr": 9.392747733741464e-09, "epoch": 4.804769001490313, "percentage": 96.1, "elapsed_time": "1:25:04", "remaining_time": "0:03:27", "throughput": 5174.5, "total_tokens": 26411008} {"current_steps": 6449, "total_steps": 6710, "loss": 0.222, "lr": 9.321273277324988e-09, "epoch": 4.805514157973175, "percentage": 96.11, "elapsed_time": "1:25:04", "remaining_time": "0:03:26", "throughput": 5174.5, "total_tokens": 26415104} {"current_steps": 6450, "total_steps": 6710, "loss": 0.0258, "lr": 9.250070786544774e-09, "epoch": 4.806259314456035, "percentage": 96.13, "elapsed_time": "1:25:05", "remaining_time": "0:03:25", "throughput": 5174.5, "total_tokens": 26419200} {"current_steps": 6451, "total_steps": 6710, "loss": 0.1243, "lr": 9.179140277008613e-09, "epoch": 4.807004470938897, "percentage": 96.14, "elapsed_time": "1:25:06", "remaining_time": "0:03:25", "throughput": 5174.51, "total_tokens": 26423296} {"current_steps": 6452, "total_steps": 6710, "loss": 0.0411, "lr": 9.108481764265181e-09, "epoch": 4.807749627421758, "percentage": 96.15, "elapsed_time": "1:25:07", "remaining_time": "0:03:24", "throughput": 5174.52, "total_tokens": 26427392} {"current_steps": 6453, "total_steps": 6710, "loss": 0.0636, "lr": 9.038095263803338e-09, "epoch": 4.80849478390462, "percentage": 96.17, "elapsed_time": "1:25:08", "remaining_time": "0:03:23", "throughput": 5174.52, "total_tokens": 26431488} {"current_steps": 6454, "total_steps": 6710, "loss": 0.0463, "lr": 8.967980791052406e-09, "epoch": 4.8092399403874815, "percentage": 96.18, "elapsed_time": "1:25:08", "remaining_time": "0:03:22", "throughput": 5174.53, "total_tokens": 26435584} {"current_steps": 6455, "total_steps": 6710, "loss": 0.0141, "lr": 8.898138361381759e-09, "epoch": 4.809985096870343, "percentage": 96.2, "elapsed_time": "1:25:09", "remaining_time": "0:03:21", "throughput": 5174.54, "total_tokens": 26439680} {"current_steps": 6456, "total_steps": 6710, "loss": 0.0835, "lr": 8.828567990101372e-09, "epoch": 4.810730253353205, "percentage": 96.21, "elapsed_time": "1:25:10", "remaining_time": "0:03:21", "throughput": 5174.54, "total_tokens": 26443776} {"current_steps": 6457, "total_steps": 6710, "loss": 0.1276, "lr": 8.759269692461686e-09, "epoch": 4.811475409836065, "percentage": 96.23, "elapsed_time": "1:25:11", "remaining_time": "0:03:20", "throughput": 5174.55, "total_tokens": 26447872} {"current_steps": 6458, "total_steps": 6710, "loss": 0.1133, "lr": 8.690243483653188e-09, "epoch": 4.812220566318927, "percentage": 96.24, "elapsed_time": "1:25:11", "remaining_time": "0:03:19", "throughput": 5174.56, "total_tokens": 26451968} {"current_steps": 6459, "total_steps": 6710, "loss": 0.1491, "lr": 8.621489378807246e-09, "epoch": 4.812965722801788, "percentage": 96.26, "elapsed_time": "1:25:12", "remaining_time": "0:03:18", "throughput": 5174.56, "total_tokens": 26456064} {"current_steps": 6460, "total_steps": 6710, "loss": 0.0516, "lr": 8.553007392994999e-09, "epoch": 4.81371087928465, "percentage": 96.27, "elapsed_time": "1:25:13", "remaining_time": "0:03:17", "throughput": 5174.57, "total_tokens": 26460160} {"current_steps": 6461, "total_steps": 6710, "loss": 0.0887, "lr": 8.484797541228329e-09, "epoch": 4.8144560357675115, "percentage": 96.29, "elapsed_time": "1:25:14", "remaining_time": "0:03:17", "throughput": 5174.57, "total_tokens": 26464256} {"current_steps": 6462, "total_steps": 6710, "loss": 0.1269, "lr": 8.416859838459162e-09, "epoch": 4.815201192250372, "percentage": 96.3, "elapsed_time": "1:25:15", "remaining_time": "0:03:16", "throughput": 5174.57, "total_tokens": 26468352} {"current_steps": 6463, "total_steps": 6710, "loss": 0.0452, "lr": 8.349194299580171e-09, "epoch": 4.815946348733234, "percentage": 96.32, "elapsed_time": "1:25:15", "remaining_time": "0:03:15", "throughput": 5174.58, "total_tokens": 26472448} {"current_steps": 6464, "total_steps": 6710, "loss": 0.0238, "lr": 8.281800939423796e-09, "epoch": 4.816691505216095, "percentage": 96.33, "elapsed_time": "1:25:16", "remaining_time": "0:03:14", "throughput": 5174.58, "total_tokens": 26476544} {"current_steps": 6465, "total_steps": 6710, "loss": 0.0176, "lr": 8.214679772763356e-09, "epoch": 4.817436661698957, "percentage": 96.35, "elapsed_time": "1:25:17", "remaining_time": "0:03:13", "throughput": 5174.59, "total_tokens": 26480640} {"current_steps": 6466, "total_steps": 6710, "loss": 0.0702, "lr": 8.147830814312225e-09, "epoch": 4.818181818181818, "percentage": 96.36, "elapsed_time": "1:25:18", "remaining_time": "0:03:13", "throughput": 5174.6, "total_tokens": 26484736} {"current_steps": 6467, "total_steps": 6710, "loss": 0.0604, "lr": 8.081254078724233e-09, "epoch": 4.81892697466468, "percentage": 96.38, "elapsed_time": "1:25:19", "remaining_time": "0:03:12", "throughput": 5174.6, "total_tokens": 26488832} {"current_steps": 6468, "total_steps": 6710, "loss": 0.0403, "lr": 8.01494958059354e-09, "epoch": 4.8196721311475414, "percentage": 96.39, "elapsed_time": "1:25:19", "remaining_time": "0:03:11", "throughput": 5174.61, "total_tokens": 26492928} {"current_steps": 6469, "total_steps": 6710, "loss": 0.0451, "lr": 7.948917334454216e-09, "epoch": 4.820417287630402, "percentage": 96.41, "elapsed_time": "1:25:20", "remaining_time": "0:03:10", "throughput": 5174.62, "total_tokens": 26497024} {"current_steps": 6470, "total_steps": 6710, "loss": 0.082, "lr": 7.883157354781484e-09, "epoch": 4.821162444113264, "percentage": 96.42, "elapsed_time": "1:25:21", "remaining_time": "0:03:09", "throughput": 5174.63, "total_tokens": 26501120} {"current_steps": 6471, "total_steps": 6710, "loss": 0.0539, "lr": 7.817669655990067e-09, "epoch": 4.821907600596125, "percentage": 96.44, "elapsed_time": "1:25:22", "remaining_time": "0:03:09", "throughput": 5174.63, "total_tokens": 26505216} {"current_steps": 6472, "total_steps": 6710, "loss": 0.1748, "lr": 7.752454252435427e-09, "epoch": 4.822652757078987, "percentage": 96.45, "elapsed_time": "1:25:22", "remaining_time": "0:03:08", "throughput": 5174.64, "total_tokens": 26509312} {"current_steps": 6473, "total_steps": 6710, "loss": 0.076, "lr": 7.687511158413346e-09, "epoch": 4.823397913561848, "percentage": 96.47, "elapsed_time": "1:25:23", "remaining_time": "0:03:07", "throughput": 5174.64, "total_tokens": 26513408} {"current_steps": 6474, "total_steps": 6710, "loss": 0.1139, "lr": 7.622840388159525e-09, "epoch": 4.824143070044709, "percentage": 96.48, "elapsed_time": "1:25:24", "remaining_time": "0:03:06", "throughput": 5174.64, "total_tokens": 26517504} {"current_steps": 6475, "total_steps": 6710, "loss": 0.1338, "lr": 7.558441955850677e-09, "epoch": 4.8248882265275705, "percentage": 96.5, "elapsed_time": "1:25:25", "remaining_time": "0:03:06", "throughput": 5174.64, "total_tokens": 26521600} {"current_steps": 6476, "total_steps": 6710, "loss": 0.0183, "lr": 7.494315875603008e-09, "epoch": 4.825633383010432, "percentage": 96.51, "elapsed_time": "1:25:26", "remaining_time": "0:03:05", "throughput": 5174.65, "total_tokens": 26525696} {"current_steps": 6477, "total_steps": 6710, "loss": 0.025, "lr": 7.4304621614737506e-09, "epoch": 4.826378539493294, "percentage": 96.53, "elapsed_time": "1:25:26", "remaining_time": "0:03:04", "throughput": 5174.66, "total_tokens": 26529792} {"current_steps": 6478, "total_steps": 6710, "loss": 0.2156, "lr": 7.36688082745976e-09, "epoch": 4.827123695976155, "percentage": 96.54, "elapsed_time": "1:25:27", "remaining_time": "0:03:03", "throughput": 5174.66, "total_tokens": 26533888} {"current_steps": 6479, "total_steps": 6710, "loss": 0.0101, "lr": 7.3035718874987785e-09, "epoch": 4.827868852459017, "percentage": 96.56, "elapsed_time": "1:25:28", "remaining_time": "0:03:02", "throughput": 5174.67, "total_tokens": 26537984} {"current_steps": 6480, "total_steps": 6710, "loss": 0.0168, "lr": 7.240535355468453e-09, "epoch": 4.828614008941877, "percentage": 96.57, "elapsed_time": "1:25:29", "remaining_time": "0:03:02", "throughput": 5174.67, "total_tokens": 26542080} {"current_steps": 6481, "total_steps": 6710, "loss": 0.1092, "lr": 7.177771245186899e-09, "epoch": 4.829359165424739, "percentage": 96.59, "elapsed_time": "1:25:30", "remaining_time": "0:03:01", "throughput": 5174.68, "total_tokens": 26546176} {"current_steps": 6482, "total_steps": 6710, "loss": 0.0148, "lr": 7.115279570412415e-09, "epoch": 4.8301043219076005, "percentage": 96.6, "elapsed_time": "1:25:30", "remaining_time": "0:03:00", "throughput": 5174.68, "total_tokens": 26550272} {"current_steps": 6483, "total_steps": 6710, "loss": 0.0284, "lr": 7.053060344843626e-09, "epoch": 4.830849478390462, "percentage": 96.62, "elapsed_time": "1:25:31", "remaining_time": "0:02:59", "throughput": 5174.68, "total_tokens": 26554368} {"current_steps": 6484, "total_steps": 6710, "loss": 0.1465, "lr": 6.991113582119485e-09, "epoch": 4.831594634873324, "percentage": 96.63, "elapsed_time": "1:25:32", "remaining_time": "0:02:58", "throughput": 5174.67, "total_tokens": 26558464} {"current_steps": 6485, "total_steps": 6710, "loss": 0.0231, "lr": 6.9294392958191295e-09, "epoch": 4.832339791356185, "percentage": 96.65, "elapsed_time": "1:25:33", "remaining_time": "0:02:58", "throughput": 5174.67, "total_tokens": 26562560} {"current_steps": 6486, "total_steps": 6710, "loss": 0.0331, "lr": 6.868037499461883e-09, "epoch": 4.833084947839046, "percentage": 96.66, "elapsed_time": "1:25:33", "remaining_time": "0:02:57", "throughput": 5174.68, "total_tokens": 26566656} {"current_steps": 6487, "total_steps": 6710, "loss": 0.0483, "lr": 6.806908206507673e-09, "epoch": 4.833830104321907, "percentage": 96.68, "elapsed_time": "1:25:34", "remaining_time": "0:02:56", "throughput": 5174.68, "total_tokens": 26570752} {"current_steps": 6488, "total_steps": 6710, "loss": 0.0423, "lr": 6.746051430356476e-09, "epoch": 4.834575260804769, "percentage": 96.69, "elapsed_time": "1:25:35", "remaining_time": "0:02:55", "throughput": 5174.69, "total_tokens": 26574848} {"current_steps": 6489, "total_steps": 6710, "loss": 0.0068, "lr": 6.685467184348177e-09, "epoch": 4.8353204172876305, "percentage": 96.71, "elapsed_time": "1:25:36", "remaining_time": "0:02:54", "throughput": 5174.7, "total_tokens": 26578944} {"current_steps": 6490, "total_steps": 6710, "loss": 0.0227, "lr": 6.625155481763679e-09, "epoch": 4.836065573770492, "percentage": 96.72, "elapsed_time": "1:25:37", "remaining_time": "0:02:54", "throughput": 5174.7, "total_tokens": 26583040} {"current_steps": 6491, "total_steps": 6710, "loss": 0.0206, "lr": 6.565116335823518e-09, "epoch": 4.836810730253353, "percentage": 96.74, "elapsed_time": "1:25:37", "remaining_time": "0:02:53", "throughput": 5174.71, "total_tokens": 26587136} {"current_steps": 6492, "total_steps": 6710, "loss": 0.0189, "lr": 6.5053497596889725e-09, "epoch": 4.837555886736214, "percentage": 96.75, "elapsed_time": "1:25:38", "remaining_time": "0:02:52", "throughput": 5174.71, "total_tokens": 26591232} {"current_steps": 6493, "total_steps": 6710, "loss": 0.044, "lr": 6.445855766460951e-09, "epoch": 4.838301043219076, "percentage": 96.77, "elapsed_time": "1:25:39", "remaining_time": "0:02:51", "throughput": 5174.72, "total_tokens": 26595328} {"current_steps": 6494, "total_steps": 6710, "loss": 0.0453, "lr": 6.386634369181105e-09, "epoch": 4.839046199701937, "percentage": 96.78, "elapsed_time": "1:25:40", "remaining_time": "0:02:50", "throughput": 5174.73, "total_tokens": 26599424} {"current_steps": 6495, "total_steps": 6710, "loss": 0.0667, "lr": 6.327685580831272e-09, "epoch": 4.839791356184799, "percentage": 96.8, "elapsed_time": "1:25:41", "remaining_time": "0:02:50", "throughput": 5174.73, "total_tokens": 26603520} {"current_steps": 6496, "total_steps": 6710, "loss": 0.0969, "lr": 6.269009414333199e-09, "epoch": 4.8405365126676605, "percentage": 96.81, "elapsed_time": "1:25:41", "remaining_time": "0:02:49", "throughput": 5174.74, "total_tokens": 26607616} {"current_steps": 6497, "total_steps": 6710, "loss": 0.1699, "lr": 6.210605882549514e-09, "epoch": 4.841281669150522, "percentage": 96.83, "elapsed_time": "1:25:42", "remaining_time": "0:02:48", "throughput": 5174.74, "total_tokens": 26611712} {"current_steps": 6498, "total_steps": 6710, "loss": 0.0063, "lr": 6.1524749982823374e-09, "epoch": 4.842026825633383, "percentage": 96.84, "elapsed_time": "1:25:43", "remaining_time": "0:02:47", "throughput": 5174.75, "total_tokens": 26615808} {"current_steps": 6499, "total_steps": 6710, "loss": 0.1183, "lr": 6.094616774274531e-09, "epoch": 4.842771982116244, "percentage": 96.86, "elapsed_time": "1:25:44", "remaining_time": "0:02:47", "throughput": 5174.76, "total_tokens": 26619904} {"current_steps": 6500, "total_steps": 6710, "loss": 0.0567, "lr": 6.037031223209005e-09, "epoch": 4.843517138599106, "percentage": 96.87, "elapsed_time": "1:25:44", "remaining_time": "0:02:46", "throughput": 5174.76, "total_tokens": 26624000} {"current_steps": 6501, "total_steps": 6710, "loss": 0.1015, "lr": 5.9797183577089966e-09, "epoch": 4.844262295081967, "percentage": 96.89, "elapsed_time": "1:25:45", "remaining_time": "0:02:45", "throughput": 5174.77, "total_tokens": 26628096} {"current_steps": 6502, "total_steps": 6710, "loss": 0.0495, "lr": 5.922678190337788e-09, "epoch": 4.845007451564829, "percentage": 96.9, "elapsed_time": "1:25:46", "remaining_time": "0:02:44", "throughput": 5174.78, "total_tokens": 26632192} {"current_steps": 6503, "total_steps": 6710, "loss": 0.0289, "lr": 5.8659107335989894e-09, "epoch": 4.84575260804769, "percentage": 96.92, "elapsed_time": "1:25:47", "remaining_time": "0:02:43", "throughput": 5174.78, "total_tokens": 26636288} {"current_steps": 6504, "total_steps": 6710, "loss": 0.1957, "lr": 5.809415999936535e-09, "epoch": 4.846497764530551, "percentage": 96.93, "elapsed_time": "1:25:48", "remaining_time": "0:02:43", "throughput": 5174.78, "total_tokens": 26640384} {"current_steps": 6505, "total_steps": 6710, "loss": 0.0827, "lr": 5.7531940017342695e-09, "epoch": 4.847242921013413, "percentage": 96.94, "elapsed_time": "1:25:48", "remaining_time": "0:02:42", "throughput": 5174.79, "total_tokens": 26644480} {"current_steps": 6506, "total_steps": 6710, "loss": 0.0407, "lr": 5.697244751316638e-09, "epoch": 4.847988077496274, "percentage": 96.96, "elapsed_time": "1:25:49", "remaining_time": "0:02:41", "throughput": 5174.8, "total_tokens": 26648576} {"current_steps": 6507, "total_steps": 6710, "loss": 0.0718, "lr": 5.641568260948138e-09, "epoch": 4.848733233979136, "percentage": 96.97, "elapsed_time": "1:25:50", "remaining_time": "0:02:40", "throughput": 5174.8, "total_tokens": 26652672} {"current_steps": 6508, "total_steps": 6710, "loss": 0.1371, "lr": 5.586164542833311e-09, "epoch": 4.849478390461997, "percentage": 96.99, "elapsed_time": "1:25:51", "remaining_time": "0:02:39", "throughput": 5174.81, "total_tokens": 26656768} {"current_steps": 6509, "total_steps": 6710, "loss": 0.055, "lr": 5.531033609117303e-09, "epoch": 4.850223546944859, "percentage": 97.0, "elapsed_time": "1:25:52", "remaining_time": "0:02:39", "throughput": 5174.81, "total_tokens": 26660864} {"current_steps": 6510, "total_steps": 6710, "loss": 0.0956, "lr": 5.476175471884892e-09, "epoch": 4.85096870342772, "percentage": 97.02, "elapsed_time": "1:25:52", "remaining_time": "0:02:38", "throughput": 5174.82, "total_tokens": 26664960} {"current_steps": 6511, "total_steps": 6710, "loss": 0.1845, "lr": 5.421590143161459e-09, "epoch": 4.851713859910581, "percentage": 97.03, "elapsed_time": "1:25:53", "remaining_time": "0:02:37", "throughput": 5174.82, "total_tokens": 26669056} {"current_steps": 6512, "total_steps": 6710, "loss": 0.0579, "lr": 5.367277634912571e-09, "epoch": 4.852459016393443, "percentage": 97.05, "elapsed_time": "1:25:54", "remaining_time": "0:02:36", "throughput": 5174.83, "total_tokens": 26673152} {"current_steps": 6513, "total_steps": 6710, "loss": 0.0702, "lr": 5.313237959043982e-09, "epoch": 4.853204172876304, "percentage": 97.06, "elapsed_time": "1:25:55", "remaining_time": "0:02:35", "throughput": 5174.83, "total_tokens": 26677248} {"current_steps": 6514, "total_steps": 6710, "loss": 0.0199, "lr": 5.259471127401494e-09, "epoch": 4.853949329359166, "percentage": 97.08, "elapsed_time": "1:25:55", "remaining_time": "0:02:35", "throughput": 5174.84, "total_tokens": 26681344} {"current_steps": 6515, "total_steps": 6710, "loss": 0.0865, "lr": 5.205977151771097e-09, "epoch": 4.8546944858420265, "percentage": 97.09, "elapsed_time": "1:25:56", "remaining_time": "0:02:34", "throughput": 5174.85, "total_tokens": 26685440} {"current_steps": 6516, "total_steps": 6710, "loss": 0.1002, "lr": 5.152756043879242e-09, "epoch": 4.855439642324888, "percentage": 97.11, "elapsed_time": "1:25:57", "remaining_time": "0:02:33", "throughput": 5174.86, "total_tokens": 26689536} {"current_steps": 6517, "total_steps": 6710, "loss": 0.0769, "lr": 5.099807815392155e-09, "epoch": 4.85618479880775, "percentage": 97.12, "elapsed_time": "1:25:58", "remaining_time": "0:02:32", "throughput": 5174.86, "total_tokens": 26693632} {"current_steps": 6518, "total_steps": 6710, "loss": 0.0785, "lr": 5.047132477916522e-09, "epoch": 4.856929955290611, "percentage": 97.14, "elapsed_time": "1:25:59", "remaining_time": "0:02:31", "throughput": 5174.86, "total_tokens": 26697728} {"current_steps": 6519, "total_steps": 6710, "loss": 0.0379, "lr": 4.994730042999357e-09, "epoch": 4.857675111773473, "percentage": 97.15, "elapsed_time": "1:25:59", "remaining_time": "0:02:31", "throughput": 5174.86, "total_tokens": 26701824} {"current_steps": 6520, "total_steps": 6710, "loss": 0.1983, "lr": 4.9426005221274445e-09, "epoch": 4.858420268256334, "percentage": 97.17, "elapsed_time": "1:26:00", "remaining_time": "0:02:30", "throughput": 5174.86, "total_tokens": 26705920} {"current_steps": 6521, "total_steps": 6710, "loss": 0.0939, "lr": 4.890743926728031e-09, "epoch": 4.859165424739195, "percentage": 97.18, "elapsed_time": "1:26:01", "remaining_time": "0:02:29", "throughput": 5174.87, "total_tokens": 26710016} {"current_steps": 6522, "total_steps": 6710, "loss": 0.0383, "lr": 4.8391602681684135e-09, "epoch": 4.859910581222056, "percentage": 97.2, "elapsed_time": "1:26:02", "remaining_time": "0:02:28", "throughput": 5174.87, "total_tokens": 26714112} {"current_steps": 6523, "total_steps": 6710, "loss": 0.1287, "lr": 4.787849557756074e-09, "epoch": 4.860655737704918, "percentage": 97.21, "elapsed_time": "1:26:03", "remaining_time": "0:02:28", "throughput": 5174.88, "total_tokens": 26718208} {"current_steps": 6524, "total_steps": 6710, "loss": 0.0048, "lr": 4.736811806738684e-09, "epoch": 4.8614008941877795, "percentage": 97.23, "elapsed_time": "1:26:03", "remaining_time": "0:02:27", "throughput": 5174.89, "total_tokens": 26722304} {"current_steps": 6525, "total_steps": 6710, "loss": 0.1364, "lr": 4.686047026304097e-09, "epoch": 4.862146050670641, "percentage": 97.24, "elapsed_time": "1:26:04", "remaining_time": "0:02:26", "throughput": 5174.88, "total_tokens": 26726400} {"current_steps": 6526, "total_steps": 6710, "loss": 0.0141, "lr": 4.635555227580496e-09, "epoch": 4.862891207153503, "percentage": 97.26, "elapsed_time": "1:26:05", "remaining_time": "0:02:25", "throughput": 5174.88, "total_tokens": 26730496} {"current_steps": 6527, "total_steps": 6710, "loss": 0.0886, "lr": 4.585336421635833e-09, "epoch": 4.863636363636363, "percentage": 97.27, "elapsed_time": "1:26:06", "remaining_time": "0:02:24", "throughput": 5174.89, "total_tokens": 26734592} {"current_steps": 6528, "total_steps": 6710, "loss": 0.0588, "lr": 4.5353906194783856e-09, "epoch": 4.864381520119225, "percentage": 97.29, "elapsed_time": "1:26:06", "remaining_time": "0:02:24", "throughput": 5174.9, "total_tokens": 26738688} {"current_steps": 6529, "total_steps": 6710, "loss": 0.0531, "lr": 4.485717832056896e-09, "epoch": 4.865126676602086, "percentage": 97.3, "elapsed_time": "1:26:07", "remaining_time": "0:02:23", "throughput": 5174.91, "total_tokens": 26742784} {"current_steps": 6530, "total_steps": 6710, "loss": 0.0637, "lr": 4.436318070259598e-09, "epoch": 4.865871833084948, "percentage": 97.32, "elapsed_time": "1:26:08", "remaining_time": "0:02:22", "throughput": 5174.92, "total_tokens": 26746880} {"current_steps": 6531, "total_steps": 6710, "loss": 0.0408, "lr": 4.387191344915609e-09, "epoch": 4.8666169895678095, "percentage": 97.33, "elapsed_time": "1:26:09", "remaining_time": "0:02:21", "throughput": 5174.92, "total_tokens": 26750976} {"current_steps": 6532, "total_steps": 6710, "loss": 0.0353, "lr": 4.338337666793813e-09, "epoch": 4.86736214605067, "percentage": 97.35, "elapsed_time": "1:26:10", "remaining_time": "0:02:20", "throughput": 5174.93, "total_tokens": 26755072} {"current_steps": 6533, "total_steps": 6710, "loss": 0.0244, "lr": 4.289757046603143e-09, "epoch": 4.868107302533532, "percentage": 97.36, "elapsed_time": "1:26:10", "remaining_time": "0:02:20", "throughput": 5174.94, "total_tokens": 26759168} {"current_steps": 6534, "total_steps": 6710, "loss": 0.0965, "lr": 4.241449494992861e-09, "epoch": 4.868852459016393, "percentage": 97.38, "elapsed_time": "1:26:11", "remaining_time": "0:02:19", "throughput": 5174.94, "total_tokens": 26763264} {"current_steps": 6535, "total_steps": 6710, "loss": 0.1235, "lr": 4.193415022552411e-09, "epoch": 4.869597615499255, "percentage": 97.39, "elapsed_time": "1:26:12", "remaining_time": "0:02:18", "throughput": 5174.95, "total_tokens": 26767360} {"current_steps": 6536, "total_steps": 6710, "loss": 0.1071, "lr": 4.145653639811287e-09, "epoch": 4.870342771982116, "percentage": 97.41, "elapsed_time": "1:26:13", "remaining_time": "0:02:17", "throughput": 5174.96, "total_tokens": 26771456} {"current_steps": 6537, "total_steps": 6710, "loss": 0.0082, "lr": 4.098165357239031e-09, "epoch": 4.871087928464978, "percentage": 97.42, "elapsed_time": "1:26:14", "remaining_time": "0:02:16", "throughput": 5174.97, "total_tokens": 26775552} {"current_steps": 6538, "total_steps": 6710, "loss": 0.0633, "lr": 4.050950185245512e-09, "epoch": 4.8718330849478395, "percentage": 97.44, "elapsed_time": "1:26:14", "remaining_time": "0:02:16", "throughput": 5174.97, "total_tokens": 26779648} {"current_steps": 6539, "total_steps": 6710, "loss": 0.0039, "lr": 4.004008134180504e-09, "epoch": 4.8725782414307, "percentage": 97.45, "elapsed_time": "1:26:15", "remaining_time": "0:02:15", "throughput": 5174.97, "total_tokens": 26783744} {"current_steps": 6540, "total_steps": 6710, "loss": 0.1162, "lr": 3.95733921433411e-09, "epoch": 4.873323397913562, "percentage": 97.47, "elapsed_time": "1:26:16", "remaining_time": "0:02:14", "throughput": 5174.97, "total_tokens": 26787840} {"current_steps": 6541, "total_steps": 6710, "loss": 0.0384, "lr": 3.910943435936482e-09, "epoch": 4.874068554396423, "percentage": 97.48, "elapsed_time": "1:26:17", "remaining_time": "0:02:13", "throughput": 5174.98, "total_tokens": 26791936} {"current_steps": 6542, "total_steps": 6710, "loss": 0.0299, "lr": 3.864820809158093e-09, "epoch": 4.874813710879285, "percentage": 97.5, "elapsed_time": "1:26:17", "remaining_time": "0:02:12", "throughput": 5174.99, "total_tokens": 26796032} {"current_steps": 6543, "total_steps": 6710, "loss": 0.0964, "lr": 3.818971344109051e-09, "epoch": 4.875558867362146, "percentage": 97.51, "elapsed_time": "1:26:18", "remaining_time": "0:02:12", "throughput": 5175.0, "total_tokens": 26800128} {"current_steps": 6544, "total_steps": 6710, "loss": 0.0665, "lr": 3.7733950508400676e-09, "epoch": 4.876304023845007, "percentage": 97.53, "elapsed_time": "1:26:19", "remaining_time": "0:02:11", "throughput": 5175.0, "total_tokens": 26804224} {"current_steps": 6545, "total_steps": 6710, "loss": 0.0743, "lr": 3.728091939341621e-09, "epoch": 4.877049180327869, "percentage": 97.54, "elapsed_time": "1:26:20", "remaining_time": "0:02:10", "throughput": 5175.01, "total_tokens": 26808320} {"current_steps": 6546, "total_steps": 6710, "loss": 0.089, "lr": 3.6830620195447973e-09, "epoch": 4.87779433681073, "percentage": 97.56, "elapsed_time": "1:26:21", "remaining_time": "0:02:09", "throughput": 5175.01, "total_tokens": 26812416} {"current_steps": 6547, "total_steps": 6710, "loss": 0.0658, "lr": 3.6383053013201718e-09, "epoch": 4.878539493293592, "percentage": 97.57, "elapsed_time": "1:26:21", "remaining_time": "0:02:09", "throughput": 5175.02, "total_tokens": 26816512} {"current_steps": 6548, "total_steps": 6710, "loss": 0.1307, "lr": 3.5938217944787858e-09, "epoch": 4.879284649776453, "percentage": 97.59, "elapsed_time": "1:26:22", "remaining_time": "0:02:08", "throughput": 5175.02, "total_tokens": 26820608} {"current_steps": 6549, "total_steps": 6710, "loss": 0.0191, "lr": 3.5496115087718663e-09, "epoch": 4.880029806259315, "percentage": 97.6, "elapsed_time": "1:26:23", "remaining_time": "0:02:07", "throughput": 5175.03, "total_tokens": 26824704} {"current_steps": 6550, "total_steps": 6710, "loss": 0.0675, "lr": 3.5056744538905507e-09, "epoch": 4.8807749627421755, "percentage": 97.62, "elapsed_time": "1:26:24", "remaining_time": "0:02:06", "throughput": 5175.03, "total_tokens": 26828800} {"current_steps": 6551, "total_steps": 6710, "loss": 0.1672, "lr": 3.4620106394661625e-09, "epoch": 4.881520119225037, "percentage": 97.63, "elapsed_time": "1:26:25", "remaining_time": "0:02:05", "throughput": 5175.04, "total_tokens": 26832896} {"current_steps": 6552, "total_steps": 6710, "loss": 0.1124, "lr": 3.4186200750700725e-09, "epoch": 4.882265275707899, "percentage": 97.65, "elapsed_time": "1:26:25", "remaining_time": "0:02:05", "throughput": 5175.05, "total_tokens": 26836992} {"current_steps": 6553, "total_steps": 6710, "loss": 0.1443, "lr": 3.3755027702138397e-09, "epoch": 4.88301043219076, "percentage": 97.66, "elapsed_time": "1:26:26", "remaining_time": "0:02:04", "throughput": 5175.05, "total_tokens": 26841088} {"current_steps": 6554, "total_steps": 6710, "loss": 0.1008, "lr": 3.332658734349209e-09, "epoch": 4.883755588673622, "percentage": 97.68, "elapsed_time": "1:26:27", "remaining_time": "0:02:03", "throughput": 5175.06, "total_tokens": 26845184} {"current_steps": 6555, "total_steps": 6710, "loss": 0.1778, "lr": 3.290087976867695e-09, "epoch": 4.884500745156483, "percentage": 97.69, "elapsed_time": "1:26:28", "remaining_time": "0:02:02", "throughput": 5175.07, "total_tokens": 26849280} {"current_steps": 6556, "total_steps": 6710, "loss": 0.0655, "lr": 3.2477905071012783e-09, "epoch": 4.885245901639344, "percentage": 97.7, "elapsed_time": "1:26:28", "remaining_time": "0:02:01", "throughput": 5175.07, "total_tokens": 26853376} {"current_steps": 6557, "total_steps": 6710, "loss": 0.1138, "lr": 3.2057663343217083e-09, "epoch": 4.8859910581222055, "percentage": 97.72, "elapsed_time": "1:26:29", "remaining_time": "0:02:01", "throughput": 5175.08, "total_tokens": 26857472} {"current_steps": 6558, "total_steps": 6710, "loss": 0.1768, "lr": 3.1640154677410606e-09, "epoch": 4.886736214605067, "percentage": 97.73, "elapsed_time": "1:26:30", "remaining_time": "0:02:00", "throughput": 5175.08, "total_tokens": 26861568} {"current_steps": 6559, "total_steps": 6710, "loss": 0.0259, "lr": 3.122537916511459e-09, "epoch": 4.887481371087929, "percentage": 97.75, "elapsed_time": "1:26:31", "remaining_time": "0:01:59", "throughput": 5175.09, "total_tokens": 26865664} {"current_steps": 6560, "total_steps": 6710, "loss": 0.101, "lr": 3.0813336897250744e-09, "epoch": 4.88822652757079, "percentage": 97.76, "elapsed_time": "1:26:32", "remaining_time": "0:01:58", "throughput": 5175.1, "total_tokens": 26869760} {"current_steps": 6561, "total_steps": 6710, "loss": 0.0707, "lr": 3.040402796413988e-09, "epoch": 4.888971684053651, "percentage": 97.78, "elapsed_time": "1:26:32", "remaining_time": "0:01:57", "throughput": 5175.11, "total_tokens": 26873856} {"current_steps": 6562, "total_steps": 6710, "loss": 0.0515, "lr": 2.9997452455508836e-09, "epoch": 4.889716840536512, "percentage": 97.79, "elapsed_time": "1:26:33", "remaining_time": "0:01:57", "throughput": 5175.11, "total_tokens": 26877952} {"current_steps": 6563, "total_steps": 6710, "loss": 0.0818, "lr": 2.9593610460479373e-09, "epoch": 4.890461997019374, "percentage": 97.81, "elapsed_time": "1:26:34", "remaining_time": "0:01:56", "throughput": 5175.12, "total_tokens": 26882048} {"current_steps": 6564, "total_steps": 6710, "loss": 0.0383, "lr": 2.919250206757651e-09, "epoch": 4.8912071535022354, "percentage": 97.82, "elapsed_time": "1:26:35", "remaining_time": "0:01:55", "throughput": 5175.12, "total_tokens": 26886144} {"current_steps": 6565, "total_steps": 6710, "loss": 0.0859, "lr": 2.8794127364727144e-09, "epoch": 4.891952309985097, "percentage": 97.84, "elapsed_time": "1:26:36", "remaining_time": "0:01:54", "throughput": 5175.13, "total_tokens": 26890240} {"current_steps": 6566, "total_steps": 6710, "loss": 0.015, "lr": 2.8398486439257243e-09, "epoch": 4.8926974664679586, "percentage": 97.85, "elapsed_time": "1:26:36", "remaining_time": "0:01:53", "throughput": 5175.12, "total_tokens": 26894336} {"current_steps": 6567, "total_steps": 6710, "loss": 0.05, "lr": 2.8005579377894665e-09, "epoch": 4.89344262295082, "percentage": 97.87, "elapsed_time": "1:26:37", "remaining_time": "0:01:53", "throughput": 5175.13, "total_tokens": 26898432} {"current_steps": 6568, "total_steps": 6710, "loss": 0.0294, "lr": 2.761540626676773e-09, "epoch": 4.894187779433681, "percentage": 97.88, "elapsed_time": "1:26:38", "remaining_time": "0:01:52", "throughput": 5175.14, "total_tokens": 26902528} {"current_steps": 6569, "total_steps": 6710, "loss": 0.0793, "lr": 2.722796719140386e-09, "epoch": 4.894932935916542, "percentage": 97.9, "elapsed_time": "1:26:39", "remaining_time": "0:01:51", "throughput": 5175.14, "total_tokens": 26906624} {"current_steps": 6570, "total_steps": 6710, "loss": 0.0695, "lr": 2.6843262236732337e-09, "epoch": 4.895678092399404, "percentage": 97.91, "elapsed_time": "1:26:39", "remaining_time": "0:01:50", "throughput": 5175.15, "total_tokens": 26910720} {"current_steps": 6571, "total_steps": 6710, "loss": 0.0029, "lr": 2.6461291487085705e-09, "epoch": 4.896423248882265, "percentage": 97.93, "elapsed_time": "1:26:40", "remaining_time": "0:01:50", "throughput": 5175.15, "total_tokens": 26914816} {"current_steps": 6572, "total_steps": 6710, "loss": 0.129, "lr": 2.608205502619143e-09, "epoch": 4.897168405365127, "percentage": 97.94, "elapsed_time": "1:26:41", "remaining_time": "0:01:49", "throughput": 5175.16, "total_tokens": 26918912} {"current_steps": 6573, "total_steps": 6710, "loss": 0.1059, "lr": 2.570555293718302e-09, "epoch": 4.897913561847988, "percentage": 97.96, "elapsed_time": "1:26:42", "remaining_time": "0:01:48", "throughput": 5175.17, "total_tokens": 26923008} {"current_steps": 6574, "total_steps": 6710, "loss": 0.0741, "lr": 2.533178530259306e-09, "epoch": 4.898658718330849, "percentage": 97.97, "elapsed_time": "1:26:43", "remaining_time": "0:01:47", "throughput": 5175.18, "total_tokens": 26927104} {"current_steps": 6575, "total_steps": 6710, "loss": 0.0947, "lr": 2.496075220435046e-09, "epoch": 4.899403874813711, "percentage": 97.99, "elapsed_time": "1:26:43", "remaining_time": "0:01:46", "throughput": 5175.18, "total_tokens": 26931200} {"current_steps": 6576, "total_steps": 6710, "loss": 0.066, "lr": 2.4592453723792932e-09, "epoch": 4.900149031296572, "percentage": 98.0, "elapsed_time": "1:26:44", "remaining_time": "0:01:46", "throughput": 5175.19, "total_tokens": 26935296} {"current_steps": 6577, "total_steps": 6710, "loss": 0.0993, "lr": 2.4226889941650346e-09, "epoch": 4.900894187779434, "percentage": 98.02, "elapsed_time": "1:26:45", "remaining_time": "0:01:45", "throughput": 5175.19, "total_tokens": 26939392} {"current_steps": 6578, "total_steps": 6710, "loss": 0.0817, "lr": 2.3864060938058596e-09, "epoch": 4.901639344262295, "percentage": 98.03, "elapsed_time": "1:26:46", "remaining_time": "0:01:44", "throughput": 5175.2, "total_tokens": 26943488} {"current_steps": 6579, "total_steps": 6710, "loss": 0.0019, "lr": 2.350396679255268e-09, "epoch": 4.902384500745157, "percentage": 98.05, "elapsed_time": "1:26:47", "remaining_time": "0:01:43", "throughput": 5175.21, "total_tokens": 26947584} {"current_steps": 6580, "total_steps": 6710, "loss": 0.1118, "lr": 2.314660758406806e-09, "epoch": 4.903129657228018, "percentage": 98.06, "elapsed_time": "1:26:47", "remaining_time": "0:01:42", "throughput": 5175.21, "total_tokens": 26951680} {"current_steps": 6581, "total_steps": 6710, "loss": 0.0211, "lr": 2.2791983390939297e-09, "epoch": 4.903874813710879, "percentage": 98.08, "elapsed_time": "1:26:48", "remaining_time": "0:01:42", "throughput": 5175.22, "total_tokens": 26955776} {"current_steps": 6582, "total_steps": 6710, "loss": 0.1401, "lr": 2.2440094290902826e-09, "epoch": 4.904619970193741, "percentage": 98.09, "elapsed_time": "1:26:49", "remaining_time": "0:01:41", "throughput": 5175.22, "total_tokens": 26959872} {"current_steps": 6583, "total_steps": 6710, "loss": 0.0536, "lr": 2.209094036109416e-09, "epoch": 4.905365126676602, "percentage": 98.11, "elapsed_time": "1:26:50", "remaining_time": "0:01:40", "throughput": 5175.23, "total_tokens": 26963968} {"current_steps": 6584, "total_steps": 6710, "loss": 0.0534, "lr": 2.1744521678053463e-09, "epoch": 4.906110283159464, "percentage": 98.12, "elapsed_time": "1:26:50", "remaining_time": "0:01:39", "throughput": 5175.24, "total_tokens": 26968064} {"current_steps": 6585, "total_steps": 6710, "loss": 0.0416, "lr": 2.1400838317715833e-09, "epoch": 4.9068554396423245, "percentage": 98.14, "elapsed_time": "1:26:51", "remaining_time": "0:01:38", "throughput": 5175.24, "total_tokens": 26972160} {"current_steps": 6586, "total_steps": 6710, "loss": 0.0893, "lr": 2.105989035541961e-09, "epoch": 4.907600596125186, "percentage": 98.15, "elapsed_time": "1:26:52", "remaining_time": "0:01:38", "throughput": 5175.25, "total_tokens": 26976256} {"current_steps": 6587, "total_steps": 6710, "loss": 0.0376, "lr": 2.0721677865902236e-09, "epoch": 4.908345752608048, "percentage": 98.17, "elapsed_time": "1:26:53", "remaining_time": "0:01:37", "throughput": 5175.26, "total_tokens": 26980352} {"current_steps": 6588, "total_steps": 6710, "loss": 0.0777, "lr": 2.03862009233044e-09, "epoch": 4.909090909090909, "percentage": 98.18, "elapsed_time": "1:26:54", "remaining_time": "0:01:36", "throughput": 5175.26, "total_tokens": 26984448} {"current_steps": 6589, "total_steps": 6710, "loss": 0.0603, "lr": 2.0053459601163116e-09, "epoch": 4.909836065573771, "percentage": 98.2, "elapsed_time": "1:26:54", "remaining_time": "0:01:35", "throughput": 5175.27, "total_tokens": 26988544} {"current_steps": 6590, "total_steps": 6710, "loss": 0.0567, "lr": 1.972345397241726e-09, "epoch": 4.910581222056632, "percentage": 98.21, "elapsed_time": "1:26:55", "remaining_time": "0:01:34", "throughput": 5175.28, "total_tokens": 26992640} {"current_steps": 6591, "total_steps": 6710, "loss": 0.0434, "lr": 1.9396184109408966e-09, "epoch": 4.911326378539493, "percentage": 98.23, "elapsed_time": "1:26:56", "remaining_time": "0:01:34", "throughput": 5175.29, "total_tokens": 26996736} {"current_steps": 6592, "total_steps": 6710, "loss": 0.07, "lr": 1.9071650083875293e-09, "epoch": 4.9120715350223545, "percentage": 98.24, "elapsed_time": "1:26:57", "remaining_time": "0:01:33", "throughput": 5175.29, "total_tokens": 27000832} {"current_steps": 6593, "total_steps": 6710, "loss": 0.0266, "lr": 1.874985196695933e-09, "epoch": 4.912816691505216, "percentage": 98.26, "elapsed_time": "1:26:58", "remaining_time": "0:01:32", "throughput": 5175.3, "total_tokens": 27004928} {"current_steps": 6594, "total_steps": 6710, "loss": 0.075, "lr": 1.8430789829199104e-09, "epoch": 4.913561847988078, "percentage": 98.27, "elapsed_time": "1:26:58", "remaining_time": "0:01:31", "throughput": 5175.31, "total_tokens": 27009024} {"current_steps": 6595, "total_steps": 6710, "loss": 0.0373, "lr": 1.8114463740535882e-09, "epoch": 4.914307004470939, "percentage": 98.29, "elapsed_time": "1:26:59", "remaining_time": "0:01:31", "throughput": 5175.31, "total_tokens": 27013120} {"current_steps": 6596, "total_steps": 6710, "loss": 0.0664, "lr": 1.7800873770311422e-09, "epoch": 4.915052160953801, "percentage": 98.3, "elapsed_time": "1:27:00", "remaining_time": "0:01:30", "throughput": 5175.32, "total_tokens": 27017216} {"current_steps": 6597, "total_steps": 6710, "loss": 0.0738, "lr": 1.7490019987265183e-09, "epoch": 4.915797317436661, "percentage": 98.32, "elapsed_time": "1:27:01", "remaining_time": "0:01:29", "throughput": 5175.32, "total_tokens": 27021312} {"current_steps": 6598, "total_steps": 6710, "loss": 0.1897, "lr": 1.7181902459539878e-09, "epoch": 4.916542473919523, "percentage": 98.33, "elapsed_time": "1:27:01", "remaining_time": "0:01:28", "throughput": 5175.33, "total_tokens": 27025408} {"current_steps": 6599, "total_steps": 6710, "loss": 0.0353, "lr": 1.6876521254677315e-09, "epoch": 4.9172876304023845, "percentage": 98.35, "elapsed_time": "1:27:02", "remaining_time": "0:01:27", "throughput": 5175.33, "total_tokens": 27029504} {"current_steps": 6600, "total_steps": 6710, "loss": 0.1283, "lr": 1.6573876439618387e-09, "epoch": 4.918032786885246, "percentage": 98.36, "elapsed_time": "1:27:03", "remaining_time": "0:01:27", "throughput": 5175.34, "total_tokens": 27033600} {"current_steps": 6601, "total_steps": 6710, "loss": 0.0889, "lr": 1.627396808070586e-09, "epoch": 4.918777943368108, "percentage": 98.38, "elapsed_time": "1:27:04", "remaining_time": "0:01:26", "throughput": 5175.34, "total_tokens": 27037696} {"current_steps": 6602, "total_steps": 6710, "loss": 0.1263, "lr": 1.5976796243681592e-09, "epoch": 4.919523099850968, "percentage": 98.39, "elapsed_time": "1:27:05", "remaining_time": "0:01:25", "throughput": 5175.32, "total_tokens": 27041792} {"current_steps": 6603, "total_steps": 6710, "loss": 0.0994, "lr": 1.568236099368653e-09, "epoch": 4.92026825633383, "percentage": 98.41, "elapsed_time": "1:27:05", "remaining_time": "0:01:24", "throughput": 5175.32, "total_tokens": 27045888} {"current_steps": 6604, "total_steps": 6710, "loss": 0.0473, "lr": 1.5390662395264876e-09, "epoch": 4.921013412816691, "percentage": 98.42, "elapsed_time": "1:27:06", "remaining_time": "0:01:23", "throughput": 5175.33, "total_tokens": 27049984} {"current_steps": 6605, "total_steps": 6710, "loss": 0.1375, "lr": 1.5101700512357154e-09, "epoch": 4.921758569299553, "percentage": 98.44, "elapsed_time": "1:27:07", "remaining_time": "0:01:23", "throughput": 5175.34, "total_tokens": 27054080} {"current_steps": 6606, "total_steps": 6710, "loss": 0.0312, "lr": 1.4815475408307134e-09, "epoch": 4.9225037257824145, "percentage": 98.45, "elapsed_time": "1:27:08", "remaining_time": "0:01:22", "throughput": 5175.34, "total_tokens": 27058176} {"current_steps": 6607, "total_steps": 6710, "loss": 0.0878, "lr": 1.4531987145857685e-09, "epoch": 4.923248882265276, "percentage": 98.46, "elapsed_time": "1:27:09", "remaining_time": "0:01:21", "throughput": 5175.33, "total_tokens": 27062272} {"current_steps": 6608, "total_steps": 6710, "loss": 0.1139, "lr": 1.4251235787150764e-09, "epoch": 4.923994038748138, "percentage": 98.48, "elapsed_time": "1:27:09", "remaining_time": "0:01:20", "throughput": 5175.33, "total_tokens": 27066368} {"current_steps": 6609, "total_steps": 6710, "loss": 0.1193, "lr": 1.3973221393728808e-09, "epoch": 4.924739195230998, "percentage": 98.49, "elapsed_time": "1:27:10", "remaining_time": "0:01:19", "throughput": 5175.33, "total_tokens": 27070464} {"current_steps": 6610, "total_steps": 6710, "loss": 0.0663, "lr": 1.3697944026534736e-09, "epoch": 4.92548435171386, "percentage": 98.51, "elapsed_time": "1:27:11", "remaining_time": "0:01:19", "throughput": 5175.34, "total_tokens": 27074560} {"current_steps": 6611, "total_steps": 6710, "loss": 0.1527, "lr": 1.3425403745911946e-09, "epoch": 4.926229508196721, "percentage": 98.52, "elapsed_time": "1:27:12", "remaining_time": "0:01:18", "throughput": 5175.35, "total_tokens": 27078656} {"current_steps": 6612, "total_steps": 6710, "loss": 0.0095, "lr": 1.3155600611601537e-09, "epoch": 4.926974664679583, "percentage": 98.54, "elapsed_time": "1:27:13", "remaining_time": "0:01:17", "throughput": 5175.35, "total_tokens": 27082752} {"current_steps": 6613, "total_steps": 6710, "loss": 0.1544, "lr": 1.2888534682749255e-09, "epoch": 4.9277198211624444, "percentage": 98.55, "elapsed_time": "1:27:13", "remaining_time": "0:01:16", "throughput": 5175.36, "total_tokens": 27086848} {"current_steps": 6614, "total_steps": 6710, "loss": 0.0809, "lr": 1.262420601789438e-09, "epoch": 4.928464977645305, "percentage": 98.57, "elapsed_time": "1:27:14", "remaining_time": "0:01:15", "throughput": 5175.36, "total_tokens": 27090944} {"current_steps": 6615, "total_steps": 6710, "loss": 0.0468, "lr": 1.2362614674982232e-09, "epoch": 4.929210134128167, "percentage": 98.58, "elapsed_time": "1:27:15", "remaining_time": "0:01:15", "throughput": 5175.36, "total_tokens": 27095040} {"current_steps": 6616, "total_steps": 6710, "loss": 0.1265, "lr": 1.2103760711355827e-09, "epoch": 4.929955290611028, "percentage": 98.6, "elapsed_time": "1:27:16", "remaining_time": "0:01:14", "throughput": 5175.36, "total_tokens": 27099136} {"current_steps": 6617, "total_steps": 6710, "loss": 0.0646, "lr": 1.1847644183754504e-09, "epoch": 4.93070044709389, "percentage": 98.61, "elapsed_time": "1:27:16", "remaining_time": "0:01:13", "throughput": 5175.37, "total_tokens": 27103232} {"current_steps": 6618, "total_steps": 6710, "loss": 0.1306, "lr": 1.1594265148325012e-09, "epoch": 4.931445603576751, "percentage": 98.63, "elapsed_time": "1:27:17", "remaining_time": "0:01:12", "throughput": 5175.37, "total_tokens": 27107328} {"current_steps": 6619, "total_steps": 6710, "loss": 0.0293, "lr": 1.1343623660606262e-09, "epoch": 4.932190760059613, "percentage": 98.64, "elapsed_time": "1:27:18", "remaining_time": "0:01:12", "throughput": 5175.38, "total_tokens": 27111424} {"current_steps": 6620, "total_steps": 6710, "loss": 0.0201, "lr": 1.1095719775541802e-09, "epoch": 4.9329359165424735, "percentage": 98.66, "elapsed_time": "1:27:19", "remaining_time": "0:01:11", "throughput": 5175.39, "total_tokens": 27115520} {"current_steps": 6621, "total_steps": 6710, "loss": 0.1, "lr": 1.0850553547475663e-09, "epoch": 4.933681073025335, "percentage": 98.67, "elapsed_time": "1:27:20", "remaining_time": "0:01:10", "throughput": 5175.4, "total_tokens": 27119616} {"current_steps": 6622, "total_steps": 6710, "loss": 0.0123, "lr": 1.0608125030148187e-09, "epoch": 4.934426229508197, "percentage": 98.69, "elapsed_time": "1:27:20", "remaining_time": "0:01:09", "throughput": 5175.4, "total_tokens": 27123712} {"current_steps": 6623, "total_steps": 6710, "loss": 0.0251, "lr": 1.0368434276702976e-09, "epoch": 4.935171385991058, "percentage": 98.7, "elapsed_time": "1:27:21", "remaining_time": "0:01:08", "throughput": 5175.4, "total_tokens": 27127808} {"current_steps": 6624, "total_steps": 6710, "loss": 0.1068, "lr": 1.0131481339678563e-09, "epoch": 4.93591654247392, "percentage": 98.72, "elapsed_time": "1:27:22", "remaining_time": "0:01:08", "throughput": 5175.41, "total_tokens": 27131904} {"current_steps": 6625, "total_steps": 6710, "loss": 0.0093, "lr": 9.897266271020889e-10, "epoch": 4.936661698956781, "percentage": 98.73, "elapsed_time": "1:27:23", "remaining_time": "0:01:07", "throughput": 5175.42, "total_tokens": 27136000} {"current_steps": 6626, "total_steps": 6710, "loss": 0.0625, "lr": 9.665789122069446e-10, "epoch": 4.937406855439642, "percentage": 98.75, "elapsed_time": "1:27:24", "remaining_time": "0:01:06", "throughput": 5175.42, "total_tokens": 27140096} {"current_steps": 6627, "total_steps": 6710, "loss": 0.025, "lr": 9.437049943565591e-10, "epoch": 4.9381520119225035, "percentage": 98.76, "elapsed_time": "1:27:24", "remaining_time": "0:01:05", "throughput": 5175.43, "total_tokens": 27144192} {"current_steps": 6628, "total_steps": 6710, "loss": 0.0468, "lr": 9.211048785651155e-10, "epoch": 4.938897168405365, "percentage": 98.78, "elapsed_time": "1:27:25", "remaining_time": "0:01:04", "throughput": 5175.44, "total_tokens": 27148288} {"current_steps": 6629, "total_steps": 6710, "loss": 0.0663, "lr": 8.987785697867068e-10, "epoch": 4.939642324888227, "percentage": 98.79, "elapsed_time": "1:27:26", "remaining_time": "0:01:04", "throughput": 5175.44, "total_tokens": 27152384} {"current_steps": 6630, "total_steps": 6710, "loss": 0.1424, "lr": 8.767260729154737e-10, "epoch": 4.940387481371088, "percentage": 98.81, "elapsed_time": "1:27:27", "remaining_time": "0:01:03", "throughput": 5175.45, "total_tokens": 27156480} {"current_steps": 6631, "total_steps": 6710, "loss": 0.1371, "lr": 8.549473927853269e-10, "epoch": 4.941132637853949, "percentage": 98.82, "elapsed_time": "1:27:27", "remaining_time": "0:01:02", "throughput": 5175.45, "total_tokens": 27160576} {"current_steps": 6632, "total_steps": 6710, "loss": 0.16, "lr": 8.334425341703645e-10, "epoch": 4.94187779433681, "percentage": 98.84, "elapsed_time": "1:27:28", "remaining_time": "0:01:01", "throughput": 5175.46, "total_tokens": 27164672} {"current_steps": 6633, "total_steps": 6710, "loss": 0.046, "lr": 8.122115017847321e-10, "epoch": 4.942622950819672, "percentage": 98.85, "elapsed_time": "1:27:29", "remaining_time": "0:01:00", "throughput": 5175.47, "total_tokens": 27168768} {"current_steps": 6634, "total_steps": 6710, "loss": 0.0633, "lr": 7.912543002823459e-10, "epoch": 4.9433681073025335, "percentage": 98.87, "elapsed_time": "1:27:30", "remaining_time": "0:01:00", "throughput": 5175.47, "total_tokens": 27172864} {"current_steps": 6635, "total_steps": 6710, "loss": 0.1017, "lr": 7.705709342571699e-10, "epoch": 4.944113263785395, "percentage": 98.88, "elapsed_time": "1:27:31", "remaining_time": "0:00:59", "throughput": 5175.48, "total_tokens": 27176960} {"current_steps": 6636, "total_steps": 6710, "loss": 0.0234, "lr": 7.501614082430775e-10, "epoch": 4.944858420268257, "percentage": 98.9, "elapsed_time": "1:27:31", "remaining_time": "0:00:58", "throughput": 5175.48, "total_tokens": 27181056} {"current_steps": 6637, "total_steps": 6710, "loss": 0.0257, "lr": 7.300257267141286e-10, "epoch": 4.945603576751118, "percentage": 98.91, "elapsed_time": "1:27:32", "remaining_time": "0:00:57", "throughput": 5175.49, "total_tokens": 27185152} {"current_steps": 6638, "total_steps": 6710, "loss": 0.0492, "lr": 7.10163894084015e-10, "epoch": 4.946348733233979, "percentage": 98.93, "elapsed_time": "1:27:33", "remaining_time": "0:00:56", "throughput": 5175.49, "total_tokens": 27189248} {"current_steps": 6639, "total_steps": 6710, "loss": 0.102, "lr": 6.905759147067536e-10, "epoch": 4.94709388971684, "percentage": 98.94, "elapsed_time": "1:27:34", "remaining_time": "0:00:56", "throughput": 5175.5, "total_tokens": 27193344} {"current_steps": 6640, "total_steps": 6710, "loss": 0.0343, "lr": 6.712617928761322e-10, "epoch": 4.947839046199702, "percentage": 98.96, "elapsed_time": "1:27:35", "remaining_time": "0:00:55", "throughput": 5175.51, "total_tokens": 27197440} {"current_steps": 6641, "total_steps": 6710, "loss": 0.0558, "lr": 6.522215328259862e-10, "epoch": 4.9485842026825635, "percentage": 98.97, "elapsed_time": "1:27:35", "remaining_time": "0:00:54", "throughput": 5175.51, "total_tokens": 27201536} {"current_steps": 6642, "total_steps": 6710, "loss": 0.1552, "lr": 6.334551387299215e-10, "epoch": 4.949329359165425, "percentage": 98.99, "elapsed_time": "1:27:36", "remaining_time": "0:00:53", "throughput": 5175.52, "total_tokens": 27205632} {"current_steps": 6643, "total_steps": 6710, "loss": 0.0394, "lr": 6.149626147018695e-10, "epoch": 4.950074515648286, "percentage": 99.0, "elapsed_time": "1:27:37", "remaining_time": "0:00:53", "throughput": 5175.53, "total_tokens": 27209728} {"current_steps": 6644, "total_steps": 6710, "loss": 0.0737, "lr": 5.967439647952544e-10, "epoch": 4.950819672131147, "percentage": 99.02, "elapsed_time": "1:27:38", "remaining_time": "0:00:52", "throughput": 5175.53, "total_tokens": 27213824} {"current_steps": 6645, "total_steps": 6710, "loss": 0.0899, "lr": 5.787991930039649e-10, "epoch": 4.951564828614009, "percentage": 99.03, "elapsed_time": "1:27:38", "remaining_time": "0:00:51", "throughput": 5175.53, "total_tokens": 27217920} {"current_steps": 6646, "total_steps": 6710, "loss": 0.1603, "lr": 5.611283032616599e-10, "epoch": 4.95230998509687, "percentage": 99.05, "elapsed_time": "1:27:39", "remaining_time": "0:00:50", "throughput": 5175.54, "total_tokens": 27222016} {"current_steps": 6647, "total_steps": 6710, "loss": 0.0208, "lr": 5.437312994417687e-10, "epoch": 4.953055141579732, "percentage": 99.06, "elapsed_time": "1:27:40", "remaining_time": "0:00:49", "throughput": 5175.54, "total_tokens": 27226112} {"current_steps": 6648, "total_steps": 6710, "loss": 0.0574, "lr": 5.266081853579075e-10, "epoch": 4.9538002980625935, "percentage": 99.08, "elapsed_time": "1:27:41", "remaining_time": "0:00:49", "throughput": 5175.52, "total_tokens": 27230208} {"current_steps": 6649, "total_steps": 6710, "loss": 0.0713, "lr": 5.097589647634627e-10, "epoch": 4.954545454545455, "percentage": 99.09, "elapsed_time": "1:27:42", "remaining_time": "0:00:48", "throughput": 5175.53, "total_tokens": 27234304} {"current_steps": 6650, "total_steps": 6710, "loss": 0.1415, "lr": 4.931836413521463e-10, "epoch": 4.955290611028316, "percentage": 99.11, "elapsed_time": "1:27:42", "remaining_time": "0:00:47", "throughput": 5175.53, "total_tokens": 27238400} {"current_steps": 6651, "total_steps": 6710, "loss": 0.0157, "lr": 4.768822187571631e-10, "epoch": 4.956035767511177, "percentage": 99.12, "elapsed_time": "1:27:43", "remaining_time": "0:00:46", "throughput": 5175.54, "total_tokens": 27242496} {"current_steps": 6652, "total_steps": 6710, "loss": 0.0847, "lr": 4.608547005520436e-10, "epoch": 4.956780923994039, "percentage": 99.14, "elapsed_time": "1:27:44", "remaining_time": "0:00:45", "throughput": 5175.54, "total_tokens": 27246592} {"current_steps": 6653, "total_steps": 6710, "loss": 0.1314, "lr": 4.451010902499497e-10, "epoch": 4.9575260804769, "percentage": 99.15, "elapsed_time": "1:27:45", "remaining_time": "0:00:45", "throughput": 5175.55, "total_tokens": 27250688} {"current_steps": 6654, "total_steps": 6710, "loss": 0.0123, "lr": 4.2962139130450777e-10, "epoch": 4.958271236959762, "percentage": 99.17, "elapsed_time": "1:27:46", "remaining_time": "0:00:44", "throughput": 5175.56, "total_tokens": 27254784} {"current_steps": 6655, "total_steps": 6710, "loss": 0.1044, "lr": 4.14415607108698e-10, "epoch": 4.959016393442623, "percentage": 99.18, "elapsed_time": "1:27:46", "remaining_time": "0:00:43", "throughput": 5175.56, "total_tokens": 27258880} {"current_steps": 6656, "total_steps": 6710, "loss": 0.023, "lr": 3.994837409958263e-10, "epoch": 4.959761549925484, "percentage": 99.2, "elapsed_time": "1:27:47", "remaining_time": "0:00:42", "throughput": 5175.57, "total_tokens": 27262976} {"current_steps": 6657, "total_steps": 6710, "loss": 0.1072, "lr": 3.84825796238969e-10, "epoch": 4.960506706408346, "percentage": 99.21, "elapsed_time": "1:27:48", "remaining_time": "0:00:41", "throughput": 5175.58, "total_tokens": 27267072} {"current_steps": 6658, "total_steps": 6710, "loss": 0.0103, "lr": 3.704417760515278e-10, "epoch": 4.961251862891207, "percentage": 99.23, "elapsed_time": "1:27:49", "remaining_time": "0:00:41", "throughput": 5175.58, "total_tokens": 27271168} {"current_steps": 6659, "total_steps": 6710, "loss": 0.0321, "lr": 3.563316835862585e-10, "epoch": 4.961997019374069, "percentage": 99.24, "elapsed_time": "1:27:49", "remaining_time": "0:00:40", "throughput": 5175.59, "total_tokens": 27275264} {"current_steps": 6660, "total_steps": 6710, "loss": 0.0363, "lr": 3.424955219363812e-10, "epoch": 4.96274217585693, "percentage": 99.25, "elapsed_time": "1:27:50", "remaining_time": "0:00:39", "throughput": 5175.59, "total_tokens": 27279360} {"current_steps": 6661, "total_steps": 6710, "loss": 0.0467, "lr": 3.289332941348866e-10, "epoch": 4.963487332339791, "percentage": 99.27, "elapsed_time": "1:27:51", "remaining_time": "0:00:38", "throughput": 5175.6, "total_tokens": 27283456} {"current_steps": 6662, "total_steps": 6710, "loss": 0.0568, "lr": 3.156450031545355e-10, "epoch": 4.9642324888226526, "percentage": 99.28, "elapsed_time": "1:27:52", "remaining_time": "0:00:37", "throughput": 5175.61, "total_tokens": 27287552} {"current_steps": 6663, "total_steps": 6710, "loss": 0.0134, "lr": 3.0263065190841436e-10, "epoch": 4.964977645305514, "percentage": 99.3, "elapsed_time": "1:27:53", "remaining_time": "0:00:37", "throughput": 5175.61, "total_tokens": 27291648} {"current_steps": 6664, "total_steps": 6710, "loss": 0.1847, "lr": 2.8989024324938e-10, "epoch": 4.965722801788376, "percentage": 99.31, "elapsed_time": "1:27:53", "remaining_time": "0:00:36", "throughput": 5175.62, "total_tokens": 27295744} {"current_steps": 6665, "total_steps": 6710, "loss": 0.0523, "lr": 2.774237799700596e-10, "epoch": 4.966467958271237, "percentage": 99.33, "elapsed_time": "1:27:54", "remaining_time": "0:00:35", "throughput": 5175.63, "total_tokens": 27299840} {"current_steps": 6666, "total_steps": 6710, "loss": 0.0336, "lr": 2.652312648032673e-10, "epoch": 4.967213114754099, "percentage": 99.34, "elapsed_time": "1:27:55", "remaining_time": "0:00:34", "throughput": 5175.63, "total_tokens": 27303936} {"current_steps": 6667, "total_steps": 6710, "loss": 0.0643, "lr": 2.5331270042172615e-10, "epoch": 4.967958271236959, "percentage": 99.36, "elapsed_time": "1:27:56", "remaining_time": "0:00:34", "throughput": 5175.64, "total_tokens": 27308032} {"current_steps": 6668, "total_steps": 6710, "loss": 0.0234, "lr": 2.4166808943792977e-10, "epoch": 4.968703427719821, "percentage": 99.37, "elapsed_time": "1:27:57", "remaining_time": "0:00:33", "throughput": 5175.65, "total_tokens": 27312128} {"current_steps": 6669, "total_steps": 6710, "loss": 0.0502, "lr": 2.3029743440455832e-10, "epoch": 4.9694485842026825, "percentage": 99.39, "elapsed_time": "1:27:57", "remaining_time": "0:00:32", "throughput": 5175.65, "total_tokens": 27316224} {"current_steps": 6670, "total_steps": 6710, "loss": 0.0307, "lr": 2.1920073781420138e-10, "epoch": 4.970193740685544, "percentage": 99.4, "elapsed_time": "1:27:58", "remaining_time": "0:00:31", "throughput": 5175.66, "total_tokens": 27320320} {"current_steps": 6671, "total_steps": 6710, "loss": 0.0972, "lr": 2.0837800209935755e-10, "epoch": 4.970938897168406, "percentage": 99.42, "elapsed_time": "1:27:59", "remaining_time": "0:00:30", "throughput": 5175.66, "total_tokens": 27324416} {"current_steps": 6672, "total_steps": 6710, "loss": 0.1437, "lr": 1.978292296322959e-10, "epoch": 4.971684053651266, "percentage": 99.43, "elapsed_time": "1:28:00", "remaining_time": "0:00:30", "throughput": 5175.67, "total_tokens": 27328512} {"current_steps": 6673, "total_steps": 6710, "loss": 0.1426, "lr": 1.8755442272533343e-10, "epoch": 4.972429210134128, "percentage": 99.45, "elapsed_time": "1:28:00", "remaining_time": "0:00:29", "throughput": 5175.67, "total_tokens": 27332608} {"current_steps": 6674, "total_steps": 6710, "loss": 0.0695, "lr": 1.7755358363097387e-10, "epoch": 4.973174366616989, "percentage": 99.46, "elapsed_time": "1:28:01", "remaining_time": "0:00:28", "throughput": 5175.68, "total_tokens": 27336704} {"current_steps": 6675, "total_steps": 6710, "loss": 0.0764, "lr": 1.6782671454149136e-10, "epoch": 4.973919523099851, "percentage": 99.48, "elapsed_time": "1:28:02", "remaining_time": "0:00:27", "throughput": 5175.69, "total_tokens": 27340800} {"current_steps": 6676, "total_steps": 6710, "loss": 0.1918, "lr": 1.5837381758893043e-10, "epoch": 4.9746646795827125, "percentage": 99.49, "elapsed_time": "1:28:03", "remaining_time": "0:00:26", "throughput": 5175.7, "total_tokens": 27344896} {"current_steps": 6677, "total_steps": 6710, "loss": 0.0425, "lr": 1.491948948455224e-10, "epoch": 4.975409836065574, "percentage": 99.51, "elapsed_time": "1:28:04", "remaining_time": "0:00:26", "throughput": 5175.7, "total_tokens": 27348992} {"current_steps": 6678, "total_steps": 6710, "loss": 0.0295, "lr": 1.4028994832326891e-10, "epoch": 4.976154992548436, "percentage": 99.52, "elapsed_time": "1:28:04", "remaining_time": "0:00:25", "throughput": 5175.66, "total_tokens": 27353088} {"current_steps": 6679, "total_steps": 6710, "loss": 0.0466, "lr": 1.3165897997421962e-10, "epoch": 4.976900149031296, "percentage": 99.54, "elapsed_time": "1:28:05", "remaining_time": "0:00:24", "throughput": 5175.67, "total_tokens": 27357184} {"current_steps": 6680, "total_steps": 6710, "loss": 0.0476, "lr": 1.2330199169047208e-10, "epoch": 4.977645305514158, "percentage": 99.55, "elapsed_time": "1:28:06", "remaining_time": "0:00:23", "throughput": 5175.68, "total_tokens": 27361280} {"current_steps": 6681, "total_steps": 6710, "loss": 0.0233, "lr": 1.152189853038943e-10, "epoch": 4.978390461997019, "percentage": 99.57, "elapsed_time": "1:28:07", "remaining_time": "0:00:22", "throughput": 5175.69, "total_tokens": 27365376} {"current_steps": 6682, "total_steps": 6710, "loss": 0.0282, "lr": 1.0740996258612468e-10, "epoch": 4.979135618479881, "percentage": 99.58, "elapsed_time": "1:28:08", "remaining_time": "0:00:22", "throughput": 5175.69, "total_tokens": 27369472} {"current_steps": 6683, "total_steps": 6710, "loss": 0.0423, "lr": 9.98749252492659e-11, "epoch": 4.9798807749627425, "percentage": 99.6, "elapsed_time": "1:28:08", "remaining_time": "0:00:21", "throughput": 5175.7, "total_tokens": 27373568} {"current_steps": 6684, "total_steps": 6710, "loss": 0.0664, "lr": 9.261387494477469e-11, "epoch": 4.980625931445603, "percentage": 99.61, "elapsed_time": "1:28:09", "remaining_time": "0:00:20", "throughput": 5175.69, "total_tokens": 27377664} {"current_steps": 6685, "total_steps": 6710, "loss": 0.0587, "lr": 8.562681326457211e-11, "epoch": 4.981371087928465, "percentage": 99.63, "elapsed_time": "1:28:10", "remaining_time": "0:00:19", "throughput": 5175.67, "total_tokens": 27381760} {"current_steps": 6686, "total_steps": 6710, "loss": 0.0185, "lr": 7.891374174007204e-11, "epoch": 4.982116244411326, "percentage": 99.64, "elapsed_time": "1:28:11", "remaining_time": "0:00:18", "throughput": 5175.65, "total_tokens": 27385856} {"current_steps": 6687, "total_steps": 6710, "loss": 0.0857, "lr": 7.247466184301389e-11, "epoch": 4.982861400894188, "percentage": 99.66, "elapsed_time": "1:28:12", "remaining_time": "0:00:18", "throughput": 5175.65, "total_tokens": 27389952} {"current_steps": 6688, "total_steps": 6710, "loss": 0.2016, "lr": 6.630957498476864e-11, "epoch": 4.983606557377049, "percentage": 99.67, "elapsed_time": "1:28:12", "remaining_time": "0:00:17", "throughput": 5175.65, "total_tokens": 27394048} {"current_steps": 6689, "total_steps": 6710, "loss": 0.0376, "lr": 6.04184825167553e-11, "epoch": 4.984351713859911, "percentage": 99.69, "elapsed_time": "1:28:13", "remaining_time": "0:00:16", "throughput": 5175.64, "total_tokens": 27398144} {"current_steps": 6690, "total_steps": 6710, "loss": 0.0251, "lr": 5.4801385730302026e-11, "epoch": 4.985096870342772, "percentage": 99.7, "elapsed_time": "1:28:14", "remaining_time": "0:00:15", "throughput": 5175.64, "total_tokens": 27402240} {"current_steps": 6691, "total_steps": 6710, "loss": 0.1344, "lr": 4.9458285856923696e-11, "epoch": 4.985842026825633, "percentage": 99.72, "elapsed_time": "1:28:15", "remaining_time": "0:00:15", "throughput": 5175.64, "total_tokens": 27406336} {"current_steps": 6692, "total_steps": 6710, "loss": 0.1312, "lr": 4.4389184067628046e-11, "epoch": 4.986587183308495, "percentage": 99.73, "elapsed_time": "1:28:16", "remaining_time": "0:00:14", "throughput": 5175.63, "total_tokens": 27410432} {"current_steps": 6693, "total_steps": 6710, "loss": 0.1498, "lr": 3.959408147374833e-11, "epoch": 4.987332339791356, "percentage": 99.75, "elapsed_time": "1:28:16", "remaining_time": "0:00:13", "throughput": 5175.64, "total_tokens": 27414528} {"current_steps": 6694, "total_steps": 6710, "loss": 0.033, "lr": 3.5072979126388185e-11, "epoch": 4.988077496274218, "percentage": 99.76, "elapsed_time": "1:28:17", "remaining_time": "0:00:12", "throughput": 5175.64, "total_tokens": 27418624} {"current_steps": 6695, "total_steps": 6710, "loss": 0.0266, "lr": 3.082587801656045e-11, "epoch": 4.988822652757079, "percentage": 99.78, "elapsed_time": "1:28:18", "remaining_time": "0:00:11", "throughput": 5175.65, "total_tokens": 27422720} {"current_steps": 6696, "total_steps": 6710, "loss": 0.0233, "lr": 2.685277907518713e-11, "epoch": 4.98956780923994, "percentage": 99.79, "elapsed_time": "1:28:19", "remaining_time": "0:00:11", "throughput": 5175.66, "total_tokens": 27426816} {"current_steps": 6697, "total_steps": 6710, "loss": 0.0505, "lr": 2.315368317337696e-11, "epoch": 4.990312965722802, "percentage": 99.81, "elapsed_time": "1:28:19", "remaining_time": "0:00:10", "throughput": 5175.67, "total_tokens": 27430912} {"current_steps": 6698, "total_steps": 6710, "loss": 0.201, "lr": 1.972859112200909e-11, "epoch": 4.991058122205663, "percentage": 99.82, "elapsed_time": "1:28:20", "remaining_time": "0:00:09", "throughput": 5175.67, "total_tokens": 27435008} {"current_steps": 6699, "total_steps": 6710, "loss": 0.0866, "lr": 1.6577503671594275e-11, "epoch": 4.991803278688525, "percentage": 99.84, "elapsed_time": "1:28:21", "remaining_time": "0:00:08", "throughput": 5175.68, "total_tokens": 27439104} {"current_steps": 6700, "total_steps": 6710, "loss": 0.0877, "lr": 1.3700421513246354e-11, "epoch": 4.992548435171386, "percentage": 99.85, "elapsed_time": "1:28:22", "remaining_time": "0:00:07", "throughput": 5175.68, "total_tokens": 27443200} {"current_steps": 6701, "total_steps": 6710, "loss": 0.1189, "lr": 1.1097345277294446e-11, "epoch": 4.993293591654247, "percentage": 99.87, "elapsed_time": "1:28:23", "remaining_time": "0:00:07", "throughput": 5175.69, "total_tokens": 27447296} {"current_steps": 6702, "total_steps": 6710, "loss": 0.1817, "lr": 8.768275534670744e-12, "epoch": 4.9940387481371085, "percentage": 99.88, "elapsed_time": "1:28:23", "remaining_time": "0:00:06", "throughput": 5175.69, "total_tokens": 27451392} {"current_steps": 6703, "total_steps": 6710, "loss": 0.0773, "lr": 6.713212795661506e-12, "epoch": 4.99478390461997, "percentage": 99.9, "elapsed_time": "1:28:24", "remaining_time": "0:00:05", "throughput": 5175.7, "total_tokens": 27455488} {"current_steps": 6704, "total_steps": 6710, "loss": 0.1651, "lr": 4.932157511017277e-12, "epoch": 4.995529061102832, "percentage": 99.91, "elapsed_time": "1:28:25", "remaining_time": "0:00:04", "throughput": 5175.71, "total_tokens": 27459584} {"current_steps": 6705, "total_steps": 6710, "loss": 0.0579, "lr": 3.4251100708426744e-12, "epoch": 4.996274217585693, "percentage": 99.93, "elapsed_time": "1:28:26", "remaining_time": "0:00:03", "throughput": 5175.71, "total_tokens": 27463680} {"current_steps": 6706, "total_steps": 6710, "loss": 0.2015, "lr": 2.192070805706603e-12, "epoch": 4.997019374068555, "percentage": 99.94, "elapsed_time": "1:28:27", "remaining_time": "0:00:03", "throughput": 5175.72, "total_tokens": 27467776} {"current_steps": 6707, "total_steps": 6710, "loss": 0.1377, "lr": 1.2330399859483699e-12, "epoch": 4.997764530551416, "percentage": 99.96, "elapsed_time": "1:28:27", "remaining_time": "0:00:02", "throughput": 5175.73, "total_tokens": 27471872} {"current_steps": 6708, "total_steps": 6710, "loss": 0.0779, "lr": 5.480178215389042e-13, "epoch": 4.998509687034277, "percentage": 99.97, "elapsed_time": "1:28:28", "remaining_time": "0:00:01", "throughput": 5175.74, "total_tokens": 27475968} {"current_steps": 6709, "total_steps": 6710, "loss": 0.0729, "lr": 1.3700446291342594e-13, "epoch": 4.9992548435171384, "percentage": 99.99, "elapsed_time": "1:28:29", "remaining_time": "0:00:00", "throughput": 5175.74, "total_tokens": 27480064} {"current_steps": 6710, "total_steps": 6710, "loss": 0.1431, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:28:30", "remaining_time": "0:00:00", "throughput": 5175.75, "total_tokens": 27484160} {"current_steps": 6710, "total_steps": 6710, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:37:00", "remaining_time": "0:00:00", "throughput": 4721.84, "total_tokens": 27484160}