{"current_steps": 5, "total_steps": 15680, "loss": 0.33850436210632323, "lr": 9.999998394288208e-06, "epoch": 0.0006377551020408163, "percentage": 0.03, "elapsed_time": "0:01:06", "remaining_time": "2 days, 9:36:10", "throughput": 4680.86, "total_tokens": 309624} {"current_steps": 10, "total_steps": 15680, "loss": 0.3195484161376953, "lr": 9.999991871085821e-06, "epoch": 0.0012755102040816326, "percentage": 0.06, "elapsed_time": "0:02:11", "remaining_time": "2 days, 9:16:03", "throughput": 4697.14, "total_tokens": 617984} {"current_steps": 15, "total_steps": 15680, "loss": 0.31821389198303224, "lr": 9.999980330042391e-06, "epoch": 0.001913265306122449, "percentage": 0.1, "elapsed_time": "0:03:09", "remaining_time": "2 days, 7:05:45", "throughput": 4855.67, "total_tokens": 922216} {"current_steps": 20, "total_steps": 15680, "loss": 0.3285261392593384, "lr": 9.999963771169503e-06, "epoch": 0.002551020408163265, "percentage": 0.13, "elapsed_time": "0:04:15", "remaining_time": "2 days, 7:38:36", "throughput": 4801.75, "total_tokens": 1228440} {"current_steps": 25, "total_steps": 15680, "loss": 0.3178420543670654, "lr": 9.999942194483775e-06, "epoch": 0.0031887755102040817, "percentage": 0.16, "elapsed_time": "0:05:14", "remaining_time": "2 days, 6:42:28", "throughput": 4878.18, "total_tokens": 1534256} {"current_steps": 30, "total_steps": 15680, "loss": 0.3137950897216797, "lr": 9.999915600006857e-06, "epoch": 0.003826530612244898, "percentage": 0.19, "elapsed_time": "0:06:10", "remaining_time": "2 days, 5:38:32", "throughput": 4973.7, "total_tokens": 1841184} {"current_steps": 35, "total_steps": 15680, "loss": 0.30161247253417967, "lr": 9.999883987765443e-06, "epoch": 0.004464285714285714, "percentage": 0.22, "elapsed_time": "0:07:24", "remaining_time": "2 days, 7:08:59", "throughput": 4805.75, "total_tokens": 2134520} {"current_steps": 40, "total_steps": 15680, "loss": 0.3267825126647949, "lr": 9.999847357791256e-06, "epoch": 0.00510204081632653, "percentage": 0.26, "elapsed_time": "0:08:32", "remaining_time": "2 days, 7:38:05", "throughput": 4759.37, "total_tokens": 2437936} {"current_steps": 45, "total_steps": 15680, "loss": 0.3393638849258423, "lr": 9.999805710121055e-06, "epoch": 0.005739795918367347, "percentage": 0.29, "elapsed_time": "0:09:31", "remaining_time": "2 days, 7:08:26", "throughput": 4820.36, "total_tokens": 2754040} {"current_steps": 50, "total_steps": 15680, "loss": 0.3237131118774414, "lr": 9.99975904479664e-06, "epoch": 0.006377551020408163, "percentage": 0.32, "elapsed_time": "0:10:41", "remaining_time": "2 days, 7:42:37", "throughput": 4739.91, "total_tokens": 3041032} {"current_steps": 55, "total_steps": 15680, "loss": 0.36842975616455076, "lr": 9.999707361864841e-06, "epoch": 0.00701530612244898, "percentage": 0.35, "elapsed_time": "0:11:29", "remaining_time": "2 days, 6:24:59", "throughput": 4865.93, "total_tokens": 3355376} {"current_steps": 60, "total_steps": 15680, "loss": 0.3665752410888672, "lr": 9.999650661377527e-06, "epoch": 0.007653061224489796, "percentage": 0.38, "elapsed_time": "0:12:28", "remaining_time": "2 days, 6:06:36", "throughput": 4885.59, "total_tokens": 3655680} {"current_steps": 65, "total_steps": 15680, "loss": 0.3658756256103516, "lr": 9.999588943391597e-06, "epoch": 0.008290816326530613, "percentage": 0.41, "elapsed_time": "0:13:41", "remaining_time": "2 days, 6:47:48", "throughput": 4829.31, "total_tokens": 3965648} {"current_steps": 70, "total_steps": 15680, "loss": 0.32802519798278806, "lr": 9.999522207968992e-06, "epoch": 0.008928571428571428, "percentage": 0.45, "elapsed_time": "0:14:34", "remaining_time": "2 days, 6:09:07", "throughput": 4891.48, "total_tokens": 4276160} {"current_steps": 75, "total_steps": 15680, "loss": 0.3478161573410034, "lr": 9.999450455176686e-06, "epoch": 0.009566326530612245, "percentage": 0.48, "elapsed_time": "0:15:36", "remaining_time": "2 days, 6:07:35", "throughput": 4895.2, "total_tokens": 4584392} {"current_steps": 80, "total_steps": 15680, "loss": 0.3187378168106079, "lr": 9.99937368508669e-06, "epoch": 0.01020408163265306, "percentage": 0.51, "elapsed_time": "0:16:44", "remaining_time": "2 days, 6:25:19", "throughput": 4868.69, "total_tokens": 4891664} {"current_steps": 85, "total_steps": 15680, "loss": 0.32980921268463137, "lr": 9.999291897776043e-06, "epoch": 0.010841836734693877, "percentage": 0.54, "elapsed_time": "0:17:58", "remaining_time": "2 days, 6:56:55", "throughput": 4813.12, "total_tokens": 5189440} {"current_steps": 90, "total_steps": 15680, "loss": 0.33111636638641356, "lr": 9.999205093326825e-06, "epoch": 0.011479591836734694, "percentage": 0.57, "elapsed_time": "0:19:06", "remaining_time": "2 days, 7:10:53", "throughput": 4782.87, "total_tokens": 5485064} {"current_steps": 95, "total_steps": 15680, "loss": 0.31922378540039065, "lr": 9.999113271826154e-06, "epoch": 0.01211734693877551, "percentage": 0.61, "elapsed_time": "0:20:08", "remaining_time": "2 days, 7:04:30", "throughput": 4782.97, "total_tokens": 5780584} {"current_steps": 100, "total_steps": 15680, "loss": 0.34738271236419677, "lr": 9.999016433366178e-06, "epoch": 0.012755102040816327, "percentage": 0.64, "elapsed_time": "0:21:16", "remaining_time": "2 days, 7:15:33", "throughput": 4765.34, "total_tokens": 6084648} {"current_steps": 105, "total_steps": 15680, "loss": 0.3142980098724365, "lr": 9.998914578044079e-06, "epoch": 0.013392857142857142, "percentage": 0.67, "elapsed_time": "0:22:17", "remaining_time": "2 days, 7:06:31", "throughput": 4778.02, "total_tokens": 6390464} {"current_steps": 110, "total_steps": 15680, "loss": 0.3406642436981201, "lr": 9.998807705962079e-06, "epoch": 0.01403061224489796, "percentage": 0.7, "elapsed_time": "0:23:27", "remaining_time": "2 days, 7:20:33", "throughput": 4753.78, "total_tokens": 6691224} {"current_steps": 115, "total_steps": 15680, "loss": 0.3410198211669922, "lr": 9.99869581722743e-06, "epoch": 0.014668367346938776, "percentage": 0.73, "elapsed_time": "0:24:38", "remaining_time": "2 days, 7:34:19", "throughput": 4734.18, "total_tokens": 6997664} {"current_steps": 120, "total_steps": 15680, "loss": 0.34250473976135254, "lr": 9.99857891195242e-06, "epoch": 0.015306122448979591, "percentage": 0.77, "elapsed_time": "0:25:39", "remaining_time": "2 days, 7:27:57", "throughput": 4743.41, "total_tokens": 7304528} {"current_steps": 125, "total_steps": 15680, "loss": 0.32828989028930666, "lr": 9.998456990254371e-06, "epoch": 0.01594387755102041, "percentage": 0.8, "elapsed_time": "0:26:51", "remaining_time": "2 days, 7:41:14", "throughput": 4725.71, "total_tokens": 7613176} {"current_steps": 130, "total_steps": 15680, "loss": 0.3207663059234619, "lr": 9.998330052255642e-06, "epoch": 0.016581632653061226, "percentage": 0.83, "elapsed_time": "0:27:41", "remaining_time": "2 days, 7:13:00", "throughput": 4772.68, "total_tokens": 7931376} {"current_steps": 135, "total_steps": 15680, "loss": 0.3120201349258423, "lr": 9.998198098083623e-06, "epoch": 0.01721938775510204, "percentage": 0.86, "elapsed_time": "0:28:36", "remaining_time": "2 days, 6:54:07", "throughput": 4789.48, "total_tokens": 8220976} {"current_steps": 140, "total_steps": 15680, "loss": 0.3055912733078003, "lr": 9.998061127870738e-06, "epoch": 0.017857142857142856, "percentage": 0.89, "elapsed_time": "0:29:52", "remaining_time": "2 days, 7:15:38", "throughput": 4749.43, "total_tokens": 8512112} {"current_steps": 145, "total_steps": 15680, "loss": 0.35830059051513674, "lr": 9.997919141754448e-06, "epoch": 0.018494897959183673, "percentage": 0.92, "elapsed_time": "0:30:56", "remaining_time": "2 days, 7:15:29", "throughput": 4740.73, "total_tokens": 8802400} {"current_steps": 150, "total_steps": 15680, "loss": 0.3327900171279907, "lr": 9.997772139877245e-06, "epoch": 0.01913265306122449, "percentage": 0.96, "elapsed_time": "0:32:13", "remaining_time": "2 days, 7:35:41", "throughput": 4712.6, "total_tokens": 9110000} {"current_steps": 155, "total_steps": 15680, "loss": 0.33315272331237794, "lr": 9.997620122386658e-06, "epoch": 0.019770408163265307, "percentage": 0.99, "elapsed_time": "0:33:18", "remaining_time": "2 days, 7:36:06", "throughput": 4710.9, "total_tokens": 9414456} {"current_steps": 160, "total_steps": 15680, "loss": 0.32426862716674804, "lr": 9.997463089435242e-06, "epoch": 0.02040816326530612, "percentage": 1.02, "elapsed_time": "0:34:18", "remaining_time": "2 days, 7:28:09", "throughput": 4724.75, "total_tokens": 9726616} {"current_steps": 165, "total_steps": 15680, "loss": 0.342034649848938, "lr": 9.997301041180597e-06, "epoch": 0.021045918367346938, "percentage": 1.05, "elapsed_time": "0:35:28", "remaining_time": "2 days, 7:35:50", "throughput": 4712.15, "total_tokens": 10030152} {"current_steps": 170, "total_steps": 15680, "loss": 0.3254104137420654, "lr": 9.997133977785342e-06, "epoch": 0.021683673469387755, "percentage": 1.08, "elapsed_time": "0:36:20", "remaining_time": "2 days, 7:15:39", "throughput": 4740.06, "total_tokens": 10335744} {"current_steps": 175, "total_steps": 15680, "loss": 0.35123443603515625, "lr": 9.996961899417145e-06, "epoch": 0.022321428571428572, "percentage": 1.12, "elapsed_time": "0:37:29", "remaining_time": "2 days, 7:21:09", "throughput": 4732.2, "total_tokens": 10643144} {"current_steps": 180, "total_steps": 15680, "loss": 0.3360785961151123, "lr": 9.996784806248694e-06, "epoch": 0.02295918367346939, "percentage": 1.15, "elapsed_time": "0:38:34", "remaining_time": "2 days, 7:21:36", "throughput": 4729.79, "total_tokens": 10946704} {"current_steps": 185, "total_steps": 15680, "loss": 0.3184788465499878, "lr": 9.996602698457716e-06, "epoch": 0.023596938775510203, "percentage": 1.18, "elapsed_time": "0:39:50", "remaining_time": "2 days, 7:37:07", "throughput": 4707.62, "total_tokens": 11253984} {"current_steps": 190, "total_steps": 15680, "loss": 0.3205930233001709, "lr": 9.996415576226967e-06, "epoch": 0.02423469387755102, "percentage": 1.21, "elapsed_time": "0:40:55", "remaining_time": "2 days, 7:36:09", "throughput": 4707.15, "total_tokens": 11557352} {"current_steps": 195, "total_steps": 15680, "loss": 0.2992743492126465, "lr": 9.996223439744238e-06, "epoch": 0.024872448979591837, "percentage": 1.24, "elapsed_time": "0:42:02", "remaining_time": "2 days, 7:39:10", "throughput": 4703.74, "total_tokens": 11867464} {"current_steps": 200, "total_steps": 15680, "loss": 0.3238770246505737, "lr": 9.996026289202352e-06, "epoch": 0.025510204081632654, "percentage": 1.28, "elapsed_time": "0:42:59", "remaining_time": "2 days, 7:27:05", "throughput": 4721.9, "total_tokens": 12178464} {"current_steps": 205, "total_steps": 15680, "loss": 0.36721694469451904, "lr": 9.995824124799164e-06, "epoch": 0.02614795918367347, "percentage": 1.31, "elapsed_time": "0:44:02", "remaining_time": "2 days, 7:24:21", "throughput": 4725.15, "total_tokens": 12485272} {"current_steps": 210, "total_steps": 15680, "loss": 0.3346077919006348, "lr": 9.995616946737558e-06, "epoch": 0.026785714285714284, "percentage": 1.34, "elapsed_time": "0:45:05", "remaining_time": "2 days, 7:21:30", "throughput": 4727.17, "total_tokens": 12788440} {"current_steps": 215, "total_steps": 15680, "loss": 0.3342667818069458, "lr": 9.995404755225454e-06, "epoch": 0.0274234693877551, "percentage": 1.37, "elapsed_time": "0:46:23", "remaining_time": "2 days, 7:36:57", "throughput": 4700.76, "total_tokens": 13084544} {"current_steps": 220, "total_steps": 15680, "loss": 0.30646519660949706, "lr": 9.995187550475799e-06, "epoch": 0.02806122448979592, "percentage": 1.4, "elapsed_time": "0:47:26", "remaining_time": "2 days, 7:33:35", "throughput": 4701.66, "total_tokens": 13382224} {"current_steps": 225, "total_steps": 15680, "loss": 0.30767092704772947, "lr": 9.994965332706574e-06, "epoch": 0.028698979591836735, "percentage": 1.43, "elapsed_time": "0:48:33", "remaining_time": "2 days, 7:35:45", "throughput": 4692.37, "total_tokens": 13672600} {"current_steps": 230, "total_steps": 15680, "loss": 0.34403650760650634, "lr": 9.994738102140791e-06, "epoch": 0.029336734693877552, "percentage": 1.47, "elapsed_time": "0:49:42", "remaining_time": "2 days, 7:39:09", "throughput": 4689.14, "total_tokens": 13985608} {"current_steps": 235, "total_steps": 15680, "loss": 0.32221179008483886, "lr": 9.994505859006489e-06, "epoch": 0.029974489795918366, "percentage": 1.5, "elapsed_time": "0:50:55", "remaining_time": "2 days, 7:46:55", "throughput": 4670.99, "total_tokens": 14272056} {"current_steps": 240, "total_steps": 15680, "loss": 0.3470602035522461, "lr": 9.994268603536743e-06, "epoch": 0.030612244897959183, "percentage": 1.53, "elapsed_time": "0:51:51", "remaining_time": "2 days, 7:36:29", "throughput": 4684.52, "total_tokens": 14577080} {"current_steps": 245, "total_steps": 15680, "loss": 0.32835218906402586, "lr": 9.994026335969654e-06, "epoch": 0.03125, "percentage": 1.56, "elapsed_time": "0:53:04", "remaining_time": "2 days, 7:43:53", "throughput": 4670.75, "total_tokens": 14874720} {"current_steps": 250, "total_steps": 15680, "loss": 0.32953906059265137, "lr": 9.993779056548357e-06, "epoch": 0.03188775510204082, "percentage": 1.59, "elapsed_time": "0:54:07", "remaining_time": "2 days, 7:40:41", "throughput": 4672.93, "total_tokens": 15175768} {"current_steps": 255, "total_steps": 15680, "loss": 0.33337490558624266, "lr": 9.99352676552101e-06, "epoch": 0.032525510204081634, "percentage": 1.63, "elapsed_time": "0:55:04", "remaining_time": "2 days, 7:31:05", "throughput": 4681.98, "total_tokens": 15469696} {"current_steps": 260, "total_steps": 15680, "loss": 0.3574438333511353, "lr": 9.993269463140805e-06, "epoch": 0.03316326530612245, "percentage": 1.66, "elapsed_time": "0:56:01", "remaining_time": "2 days, 7:22:53", "throughput": 4693.98, "total_tokens": 15779624} {"current_steps": 265, "total_steps": 15680, "loss": 0.33641748428344725, "lr": 9.993007149665968e-06, "epoch": 0.03380102040816327, "percentage": 1.69, "elapsed_time": "0:57:11", "remaining_time": "2 days, 7:26:35", "throughput": 4685.72, "total_tokens": 16077880} {"current_steps": 270, "total_steps": 15680, "loss": 0.3066434383392334, "lr": 9.992739825359743e-06, "epoch": 0.03443877551020408, "percentage": 1.72, "elapsed_time": "0:58:24", "remaining_time": "2 days, 7:33:36", "throughput": 4672.37, "total_tokens": 16374368} {"current_steps": 275, "total_steps": 15680, "loss": 0.3326112747192383, "lr": 9.992467490490411e-06, "epoch": 0.035076530612244895, "percentage": 1.75, "elapsed_time": "0:59:34", "remaining_time": "2 days, 7:37:04", "throughput": 4668.25, "total_tokens": 16685616} {"current_steps": 280, "total_steps": 15680, "loss": 0.34957115650177, "lr": 9.99219014533128e-06, "epoch": 0.03571428571428571, "percentage": 1.79, "elapsed_time": "1:00:23", "remaining_time": "2 days, 7:21:14", "throughput": 4694.15, "total_tokens": 17007744} {"current_steps": 285, "total_steps": 15680, "loss": 0.33728978633880613, "lr": 9.991907790160686e-06, "epoch": 0.03635204081632653, "percentage": 1.82, "elapsed_time": "1:01:35", "remaining_time": "2 days, 7:27:07", "throughput": 4687.22, "total_tokens": 17322144} {"current_steps": 290, "total_steps": 15680, "loss": 0.33463027477264407, "lr": 9.991620425261987e-06, "epoch": 0.036989795918367346, "percentage": 1.85, "elapsed_time": "1:02:42", "remaining_time": "2 days, 7:27:31", "throughput": 4687.01, "total_tokens": 17633104} {"current_steps": 295, "total_steps": 15680, "loss": 0.33530759811401367, "lr": 9.99132805092358e-06, "epoch": 0.03762755102040816, "percentage": 1.88, "elapsed_time": "1:03:40", "remaining_time": "2 days, 7:20:27", "throughput": 4694.8, "total_tokens": 17934608} {"current_steps": 300, "total_steps": 15680, "loss": 0.36384072303771975, "lr": 9.99103066743888e-06, "epoch": 0.03826530612244898, "percentage": 1.91, "elapsed_time": "1:04:51", "remaining_time": "2 days, 7:25:10", "throughput": 4684.34, "total_tokens": 18229648} {"current_steps": 305, "total_steps": 15680, "loss": 0.32778329849243165, "lr": 9.990728275106332e-06, "epoch": 0.0389030612244898, "percentage": 1.95, "elapsed_time": "1:05:59", "remaining_time": "2 days, 7:26:34", "throughput": 4681.39, "total_tokens": 18535656} {"current_steps": 310, "total_steps": 15680, "loss": 0.3228672981262207, "lr": 9.990420874229408e-06, "epoch": 0.039540816326530615, "percentage": 1.98, "elapsed_time": "1:07:06", "remaining_time": "2 days, 7:27:07", "throughput": 4680.18, "total_tokens": 18843904} {"current_steps": 315, "total_steps": 15680, "loss": 0.32550835609436035, "lr": 9.990108465116606e-06, "epoch": 0.04017857142857143, "percentage": 2.01, "elapsed_time": "1:08:20", "remaining_time": "2 days, 7:33:28", "throughput": 4669.18, "total_tokens": 19145520} {"current_steps": 320, "total_steps": 15680, "loss": 0.3454264163970947, "lr": 9.989791048081452e-06, "epoch": 0.04081632653061224, "percentage": 2.04, "elapsed_time": "1:09:25", "remaining_time": "2 days, 7:32:25", "throughput": 4668.7, "total_tokens": 19447640} {"current_steps": 325, "total_steps": 15680, "loss": 0.36098618507385255, "lr": 9.989468623442494e-06, "epoch": 0.04145408163265306, "percentage": 2.07, "elapsed_time": "1:10:28", "remaining_time": "2 days, 7:30:02", "throughput": 4670.07, "total_tokens": 19749576} {"current_steps": 330, "total_steps": 15680, "loss": 0.3276120662689209, "lr": 9.989141191523309e-06, "epoch": 0.042091836734693876, "percentage": 2.1, "elapsed_time": "1:11:25", "remaining_time": "2 days, 7:22:42", "throughput": 4674.66, "total_tokens": 20035464} {"current_steps": 335, "total_steps": 15680, "loss": 0.3200536251068115, "lr": 9.988808752652498e-06, "epoch": 0.04272959183673469, "percentage": 2.14, "elapsed_time": "1:12:37", "remaining_time": "2 days, 7:26:40", "throughput": 4664.92, "total_tokens": 20327480} {"current_steps": 340, "total_steps": 15680, "loss": 0.30787248611450196, "lr": 9.988471307163684e-06, "epoch": 0.04336734693877551, "percentage": 2.17, "elapsed_time": "1:13:39", "remaining_time": "2 days, 7:23:23", "throughput": 4665.64, "total_tokens": 20620464} {"current_steps": 345, "total_steps": 15680, "loss": 0.3384589195251465, "lr": 9.988128855395522e-06, "epoch": 0.04400510204081633, "percentage": 2.2, "elapsed_time": "1:14:46", "remaining_time": "2 days, 7:23:52", "throughput": 4664.43, "total_tokens": 20928144} {"current_steps": 350, "total_steps": 15680, "loss": 0.3512593746185303, "lr": 9.987781397691683e-06, "epoch": 0.044642857142857144, "percentage": 2.23, "elapsed_time": "1:15:55", "remaining_time": "2 days, 7:25:15", "throughput": 4663.13, "total_tokens": 21241216} {"current_steps": 355, "total_steps": 15680, "loss": 0.33603107929229736, "lr": 9.987428934400864e-06, "epoch": 0.04528061224489796, "percentage": 2.26, "elapsed_time": "1:17:09", "remaining_time": "2 days, 7:30:51", "throughput": 4653.27, "total_tokens": 21542400} {"current_steps": 360, "total_steps": 15680, "loss": 0.3387459754943848, "lr": 9.98707146587679e-06, "epoch": 0.04591836734693878, "percentage": 2.3, "elapsed_time": "1:18:17", "remaining_time": "2 days, 7:31:52", "throughput": 4649.66, "total_tokens": 21842576} {"current_steps": 365, "total_steps": 15680, "loss": 0.3367520809173584, "lr": 9.986708992478202e-06, "epoch": 0.046556122448979595, "percentage": 2.33, "elapsed_time": "1:19:15", "remaining_time": "2 days, 7:25:15", "throughput": 4659.56, "total_tokens": 22156256} {"current_steps": 370, "total_steps": 15680, "loss": 0.3515306949615479, "lr": 9.98634151456887e-06, "epoch": 0.047193877551020405, "percentage": 2.36, "elapsed_time": "1:20:21", "remaining_time": "2 days, 7:24:53", "throughput": 4660.39, "total_tokens": 22468688} {"current_steps": 375, "total_steps": 15680, "loss": 0.3335010528564453, "lr": 9.985969032517582e-06, "epoch": 0.04783163265306122, "percentage": 2.39, "elapsed_time": "1:21:28", "remaining_time": "2 days, 7:25:16", "throughput": 4659.84, "total_tokens": 22779688} {"current_steps": 380, "total_steps": 15680, "loss": 0.33521523475646975, "lr": 9.985591546698151e-06, "epoch": 0.04846938775510204, "percentage": 2.42, "elapsed_time": "1:22:33", "remaining_time": "2 days, 7:23:48", "throughput": 4660.75, "total_tokens": 23085304} {"current_steps": 385, "total_steps": 15680, "loss": 0.34557697772979734, "lr": 9.98520905748941e-06, "epoch": 0.049107142857142856, "percentage": 2.46, "elapsed_time": "1:23:32", "remaining_time": "2 days, 7:18:55", "throughput": 4666.01, "total_tokens": 23388632} {"current_steps": 390, "total_steps": 15680, "loss": 0.31669833660125735, "lr": 9.984821565275214e-06, "epoch": 0.04974489795918367, "percentage": 2.49, "elapsed_time": "1:24:24", "remaining_time": "2 days, 7:09:31", "throughput": 4679.67, "total_tokens": 23702200} {"current_steps": 395, "total_steps": 15680, "loss": 0.3379413843154907, "lr": 9.984429070444437e-06, "epoch": 0.05038265306122449, "percentage": 2.52, "elapsed_time": "1:25:38", "remaining_time": "2 days, 7:14:10", "throughput": 4669.31, "total_tokens": 23994432} {"current_steps": 400, "total_steps": 15680, "loss": 0.33236329555511473, "lr": 9.984031573390977e-06, "epoch": 0.05102040816326531, "percentage": 2.55, "elapsed_time": "1:26:39", "remaining_time": "2 days, 7:10:28", "throughput": 4672.48, "total_tokens": 24295472} {"current_steps": 405, "total_steps": 15680, "loss": 0.361618185043335, "lr": 9.983629074513749e-06, "epoch": 0.051658163265306124, "percentage": 2.58, "elapsed_time": "1:27:59", "remaining_time": "2 days, 7:18:40", "throughput": 4660.63, "total_tokens": 24605608} {"current_steps": 410, "total_steps": 15680, "loss": 0.33792781829833984, "lr": 9.983221574216688e-06, "epoch": 0.05229591836734694, "percentage": 2.61, "elapsed_time": "1:29:16", "remaining_time": "2 days, 7:24:38", "throughput": 4652.3, "total_tokens": 24917816} {"current_steps": 415, "total_steps": 15680, "loss": 0.34446349143981936, "lr": 9.98280907290875e-06, "epoch": 0.05293367346938776, "percentage": 2.65, "elapsed_time": "1:30:22", "remaining_time": "2 days, 7:24:24", "throughput": 4650.06, "total_tokens": 25215896} {"current_steps": 420, "total_steps": 15680, "loss": 0.31869771480560305, "lr": 9.98239157100391e-06, "epoch": 0.05357142857142857, "percentage": 2.68, "elapsed_time": "1:31:26", "remaining_time": "2 days, 7:22:12", "throughput": 4650.12, "total_tokens": 25511528} {"current_steps": 425, "total_steps": 15680, "loss": 0.32179903984069824, "lr": 9.981969068921157e-06, "epoch": 0.054209183673469385, "percentage": 2.71, "elapsed_time": "1:32:42", "remaining_time": "2 days, 7:27:24", "throughput": 4639.59, "total_tokens": 25805496} {"current_steps": 430, "total_steps": 15680, "loss": 0.32957944869995115, "lr": 9.981541567084506e-06, "epoch": 0.0548469387755102, "percentage": 2.74, "elapsed_time": "1:33:34", "remaining_time": "2 days, 7:18:30", "throughput": 4650.45, "total_tokens": 26108872} {"current_steps": 435, "total_steps": 15680, "loss": 0.3697628974914551, "lr": 9.98110906592298e-06, "epoch": 0.05548469387755102, "percentage": 2.77, "elapsed_time": "1:34:35", "remaining_time": "2 days, 7:14:56", "throughput": 4657.64, "total_tokens": 26433456} {"current_steps": 440, "total_steps": 15680, "loss": 0.35071864128112795, "lr": 9.980671565870628e-06, "epoch": 0.05612244897959184, "percentage": 2.81, "elapsed_time": "1:35:50", "remaining_time": "2 days, 7:19:50", "throughput": 4648.34, "total_tokens": 26732128} {"current_steps": 445, "total_steps": 15680, "loss": 0.3407757759094238, "lr": 9.98022906736651e-06, "epoch": 0.056760204081632654, "percentage": 2.84, "elapsed_time": "1:36:59", "remaining_time": "2 days, 7:20:29", "throughput": 4644.55, "total_tokens": 27028024} {"current_steps": 450, "total_steps": 15680, "loss": 0.34862961769104006, "lr": 9.979781570854704e-06, "epoch": 0.05739795918367347, "percentage": 2.87, "elapsed_time": "1:37:59", "remaining_time": "2 days, 7:16:37", "throughput": 4650.08, "total_tokens": 27341456} {"current_steps": 455, "total_steps": 15680, "loss": 0.361210036277771, "lr": 9.979329076784305e-06, "epoch": 0.05803571428571429, "percentage": 2.9, "elapsed_time": "1:39:07", "remaining_time": "2 days, 7:16:41", "throughput": 4647.16, "total_tokens": 27637416} {"current_steps": 460, "total_steps": 15680, "loss": 0.33243255615234374, "lr": 9.978871585609422e-06, "epoch": 0.058673469387755105, "percentage": 2.93, "elapsed_time": "1:40:19", "remaining_time": "2 days, 7:19:27", "throughput": 4640.97, "total_tokens": 27936360} {"current_steps": 465, "total_steps": 15680, "loss": 0.3394655704498291, "lr": 9.978409097789178e-06, "epoch": 0.05931122448979592, "percentage": 2.97, "elapsed_time": "1:41:10", "remaining_time": "2 days, 7:10:36", "throughput": 4652.86, "total_tokens": 28246160} {"current_steps": 470, "total_steps": 15680, "loss": 0.3474451541900635, "lr": 9.977941613787714e-06, "epoch": 0.05994897959183673, "percentage": 3.0, "elapsed_time": "1:42:24", "remaining_time": "2 days, 7:13:56", "throughput": 4646.62, "total_tokens": 28549672} {"current_steps": 475, "total_steps": 15680, "loss": 0.3277826070785522, "lr": 9.977469134074181e-06, "epoch": 0.06058673469387755, "percentage": 3.03, "elapsed_time": "1:43:37", "remaining_time": "2 days, 7:17:04", "throughput": 4640.31, "total_tokens": 28850928} {"current_steps": 480, "total_steps": 15680, "loss": 0.3291780471801758, "lr": 9.976991659122748e-06, "epoch": 0.061224489795918366, "percentage": 3.06, "elapsed_time": "1:44:44", "remaining_time": "2 days, 7:16:53", "throughput": 4639.17, "total_tokens": 29155440} {"current_steps": 485, "total_steps": 15680, "loss": 0.3117806434631348, "lr": 9.976509189412591e-06, "epoch": 0.06186224489795918, "percentage": 3.09, "elapsed_time": "1:45:44", "remaining_time": "2 days, 7:13:06", "throughput": 4642.25, "total_tokens": 29454808} {"current_steps": 490, "total_steps": 15680, "loss": 0.3248849153518677, "lr": 9.976021725427905e-06, "epoch": 0.0625, "percentage": 3.12, "elapsed_time": "1:46:54", "remaining_time": "2 days, 7:14:07", "throughput": 4638.48, "total_tokens": 29753184} {"current_steps": 495, "total_steps": 15680, "loss": 0.3143364191055298, "lr": 9.975529267657892e-06, "epoch": 0.06313775510204081, "percentage": 3.16, "elapsed_time": "1:48:07", "remaining_time": "2 days, 7:16:44", "throughput": 4632.84, "total_tokens": 30053816} {"current_steps": 500, "total_steps": 15680, "loss": 0.3483597755432129, "lr": 9.97503181659677e-06, "epoch": 0.06377551020408163, "percentage": 3.19, "elapsed_time": "1:48:57", "remaining_time": "2 days, 7:08:08", "throughput": 4645.39, "total_tokens": 30370832} {"current_steps": 505, "total_steps": 15680, "loss": 0.3520472288131714, "lr": 9.974529372743762e-06, "epoch": 0.06441326530612244, "percentage": 3.22, "elapsed_time": "1:49:50", "remaining_time": "2 days, 7:00:29", "throughput": 4655.05, "total_tokens": 30677376} {"current_steps": 510, "total_steps": 15680, "loss": 0.32537987232208254, "lr": 9.97402193660311e-06, "epoch": 0.06505102040816327, "percentage": 3.25, "elapsed_time": "1:50:55", "remaining_time": "2 days, 6:59:24", "throughput": 4655.58, "total_tokens": 30984552} {"current_steps": 515, "total_steps": 15680, "loss": 0.3295437812805176, "lr": 9.973509508684061e-06, "epoch": 0.06568877551020408, "percentage": 3.28, "elapsed_time": "1:52:01", "remaining_time": "2 days, 6:58:52", "throughput": 4655.13, "total_tokens": 31290592} {"current_steps": 520, "total_steps": 15680, "loss": 0.3507524013519287, "lr": 9.972992089500868e-06, "epoch": 0.0663265306122449, "percentage": 3.32, "elapsed_time": "1:53:12", "remaining_time": "2 days, 7:00:33", "throughput": 4649.4, "total_tokens": 31581920} {"current_steps": 525, "total_steps": 15680, "loss": 0.33227179050445554, "lr": 9.972469679572802e-06, "epoch": 0.06696428571428571, "percentage": 3.35, "elapsed_time": "1:54:09", "remaining_time": "2 days, 6:55:27", "throughput": 4654.67, "total_tokens": 31883032} {"current_steps": 530, "total_steps": 15680, "loss": 0.3360892772674561, "lr": 9.971942279424136e-06, "epoch": 0.06760204081632654, "percentage": 3.38, "elapsed_time": "1:55:08", "remaining_time": "2 days, 6:51:07", "throughput": 4660.87, "total_tokens": 32197784} {"current_steps": 535, "total_steps": 15680, "loss": 0.34338998794555664, "lr": 9.971409889584151e-06, "epoch": 0.06823979591836735, "percentage": 3.41, "elapsed_time": "1:56:17", "remaining_time": "2 days, 6:52:10", "throughput": 4658.21, "total_tokens": 32504160} {"current_steps": 540, "total_steps": 15680, "loss": 0.34417474269866943, "lr": 9.970872510587142e-06, "epoch": 0.06887755102040816, "percentage": 3.44, "elapsed_time": "1:57:22", "remaining_time": "2 days, 6:50:44", "throughput": 4658.24, "total_tokens": 32804584} {"current_steps": 545, "total_steps": 15680, "loss": 0.35027050971984863, "lr": 9.970330142972403e-06, "epoch": 0.06951530612244898, "percentage": 3.48, "elapsed_time": "1:58:38", "remaining_time": "2 days, 6:54:35", "throughput": 4651.95, "total_tokens": 33113264} {"current_steps": 550, "total_steps": 15680, "loss": 0.3356395483016968, "lr": 9.969782787284237e-06, "epoch": 0.07015306122448979, "percentage": 3.51, "elapsed_time": "1:59:39", "remaining_time": "2 days, 6:51:37", "throughput": 4655.79, "total_tokens": 33425640} {"current_steps": 555, "total_steps": 15680, "loss": 0.3323835849761963, "lr": 9.969230444071956e-06, "epoch": 0.07079081632653061, "percentage": 3.54, "elapsed_time": "2:00:37", "remaining_time": "2 days, 6:47:20", "throughput": 4660.49, "total_tokens": 33730696} {"current_steps": 560, "total_steps": 15680, "loss": 0.34821453094482424, "lr": 9.968673113889874e-06, "epoch": 0.07142857142857142, "percentage": 3.57, "elapsed_time": "2:01:34", "remaining_time": "2 days, 6:42:39", "throughput": 4665.78, "total_tokens": 34035864} {"current_steps": 565, "total_steps": 15680, "loss": 0.3442867279052734, "lr": 9.968110797297312e-06, "epoch": 0.07206632653061225, "percentage": 3.6, "elapsed_time": "2:02:45", "remaining_time": "2 days, 6:44:15", "throughput": 4662.17, "total_tokens": 34341288} {"current_steps": 570, "total_steps": 15680, "loss": 0.35814208984375, "lr": 9.967543494858591e-06, "epoch": 0.07270408163265306, "percentage": 3.64, "elapsed_time": "2:03:53", "remaining_time": "2 days, 6:44:10", "throughput": 4661.55, "total_tokens": 34651224} {"current_steps": 575, "total_steps": 15680, "loss": 0.34238247871398925, "lr": 9.966971207143041e-06, "epoch": 0.07334183673469388, "percentage": 3.67, "elapsed_time": "2:04:54", "remaining_time": "2 days, 6:41:24", "throughput": 4664.72, "total_tokens": 34960960} {"current_steps": 580, "total_steps": 15680, "loss": 0.3418263912200928, "lr": 9.966393934724992e-06, "epoch": 0.07397959183673469, "percentage": 3.7, "elapsed_time": "2:05:51", "remaining_time": "2 days, 6:36:44", "throughput": 4670.68, "total_tokens": 35271552} {"current_steps": 585, "total_steps": 15680, "loss": 0.330104398727417, "lr": 9.965811678183777e-06, "epoch": 0.07461734693877552, "percentage": 3.73, "elapsed_time": "2:07:00", "remaining_time": "2 days, 6:37:19", "throughput": 4669.05, "total_tokens": 35581248} {"current_steps": 590, "total_steps": 15680, "loss": 0.34459099769592283, "lr": 9.965224438103733e-06, "epoch": 0.07525510204081633, "percentage": 3.76, "elapsed_time": "2:08:04", "remaining_time": "2 days, 6:35:32", "throughput": 4671.45, "total_tokens": 35896192} {"current_steps": 595, "total_steps": 15680, "loss": 0.3336080551147461, "lr": 9.964632215074193e-06, "epoch": 0.07589285714285714, "percentage": 3.79, "elapsed_time": "2:09:12", "remaining_time": "2 days, 6:35:45", "throughput": 4670.76, "total_tokens": 36209472} {"current_steps": 600, "total_steps": 15680, "loss": 0.33786745071411134, "lr": 9.964035009689498e-06, "epoch": 0.07653061224489796, "percentage": 3.83, "elapsed_time": "2:10:13", "remaining_time": "2 days, 6:32:58", "throughput": 4673.08, "total_tokens": 36513008} {"current_steps": 605, "total_steps": 15680, "loss": 0.32400827407836913, "lr": 9.963432822548982e-06, "epoch": 0.07716836734693877, "percentage": 3.86, "elapsed_time": "2:11:09", "remaining_time": "2 days, 6:28:19", "throughput": 4675.98, "total_tokens": 36799952} {"current_steps": 610, "total_steps": 15680, "loss": 0.33402822017669676, "lr": 9.962825654256984e-06, "epoch": 0.0778061224489796, "percentage": 3.89, "elapsed_time": "2:12:06", "remaining_time": "2 days, 6:23:34", "throughput": 4680.84, "total_tokens": 37101008} {"current_steps": 615, "total_steps": 15680, "loss": 0.3186351776123047, "lr": 9.962213505422838e-06, "epoch": 0.0784438775510204, "percentage": 3.92, "elapsed_time": "2:13:22", "remaining_time": "2 days, 6:27:19", "throughput": 4674.07, "total_tokens": 37406416} {"current_steps": 620, "total_steps": 15680, "loss": 0.3287219047546387, "lr": 9.96159637666088e-06, "epoch": 0.07908163265306123, "percentage": 3.95, "elapsed_time": "2:14:31", "remaining_time": "2 days, 6:27:50", "throughput": 4670.62, "total_tokens": 37700984} {"current_steps": 625, "total_steps": 15680, "loss": 0.309468412399292, "lr": 9.96097426859044e-06, "epoch": 0.07971938775510204, "percentage": 3.99, "elapsed_time": "2:15:40", "remaining_time": "2 days, 6:28:05", "throughput": 4664.93, "total_tokens": 37974384} {"current_steps": 630, "total_steps": 15680, "loss": 0.31683375835418703, "lr": 9.960347181835848e-06, "epoch": 0.08035714285714286, "percentage": 4.02, "elapsed_time": "2:16:45", "remaining_time": "2 days, 6:26:51", "throughput": 4665.64, "total_tokens": 38282248} {"current_steps": 635, "total_steps": 15680, "loss": 0.32001914978027346, "lr": 9.95971511702643e-06, "epoch": 0.08099489795918367, "percentage": 4.05, "elapsed_time": "2:17:49", "remaining_time": "2 days, 6:25:34", "throughput": 4665.19, "total_tokens": 38580048} {"current_steps": 640, "total_steps": 15680, "loss": 0.3427865028381348, "lr": 9.959078074796505e-06, "epoch": 0.08163265306122448, "percentage": 4.08, "elapsed_time": "2:18:44", "remaining_time": "2 days, 6:20:17", "throughput": 4671.73, "total_tokens": 38888080} {"current_steps": 645, "total_steps": 15680, "loss": 0.3504422664642334, "lr": 9.958436055785391e-06, "epoch": 0.08227040816326531, "percentage": 4.11, "elapsed_time": "2:20:02", "remaining_time": "2 days, 6:24:11", "throughput": 4665.67, "total_tokens": 39201064} {"current_steps": 650, "total_steps": 15680, "loss": 0.3311141014099121, "lr": 9.9577890606374e-06, "epoch": 0.08290816326530612, "percentage": 4.15, "elapsed_time": "2:20:57", "remaining_time": "2 days, 6:19:33", "throughput": 4670.94, "total_tokens": 39506496} {"current_steps": 655, "total_steps": 15680, "loss": 0.34262380599975584, "lr": 9.957137090001834e-06, "epoch": 0.08354591836734694, "percentage": 4.18, "elapsed_time": "2:21:51", "remaining_time": "2 days, 6:14:03", "throughput": 4674.59, "total_tokens": 39787552} {"current_steps": 660, "total_steps": 15680, "loss": 0.3301884889602661, "lr": 9.956480144532992e-06, "epoch": 0.08418367346938775, "percentage": 4.21, "elapsed_time": "2:23:00", "remaining_time": "2 days, 6:14:40", "throughput": 4672.04, "total_tokens": 40090352} {"current_steps": 665, "total_steps": 15680, "loss": 0.3425352334976196, "lr": 9.955818224890166e-06, "epoch": 0.08482142857142858, "percentage": 4.24, "elapsed_time": "2:23:59", "remaining_time": "2 days, 6:11:18", "throughput": 4676.6, "total_tokens": 40405072} {"current_steps": 670, "total_steps": 15680, "loss": 0.3391813516616821, "lr": 9.955151331737638e-06, "epoch": 0.08545918367346939, "percentage": 4.27, "elapsed_time": "2:25:02", "remaining_time": "2 days, 6:09:21", "throughput": 4679.39, "total_tokens": 40722368} {"current_steps": 675, "total_steps": 15680, "loss": 0.32563443183898927, "lr": 9.954479465744681e-06, "epoch": 0.08609693877551021, "percentage": 4.3, "elapsed_time": "2:26:06", "remaining_time": "2 days, 6:07:48", "throughput": 4678.79, "total_tokens": 41015040} {"current_steps": 680, "total_steps": 15680, "loss": 0.3731600522994995, "lr": 9.95380262758556e-06, "epoch": 0.08673469387755102, "percentage": 4.34, "elapsed_time": "2:27:08", "remaining_time": "2 days, 6:05:42", "throughput": 4679.9, "total_tokens": 41315736} {"current_steps": 685, "total_steps": 15680, "loss": 0.3367309093475342, "lr": 9.953120817939532e-06, "epoch": 0.08737244897959184, "percentage": 4.37, "elapsed_time": "2:28:15", "remaining_time": "2 days, 6:05:17", "throughput": 4679.12, "total_tokens": 41621136} {"current_steps": 690, "total_steps": 15680, "loss": 0.3516701698303223, "lr": 9.952434037490835e-06, "epoch": 0.08801020408163265, "percentage": 4.4, "elapsed_time": "2:29:22", "remaining_time": "2 days, 6:05:04", "throughput": 4678.64, "total_tokens": 41931728} {"current_steps": 695, "total_steps": 15680, "loss": 0.32941617965698244, "lr": 9.951742286928706e-06, "epoch": 0.08864795918367346, "percentage": 4.43, "elapsed_time": "2:30:21", "remaining_time": "2 days, 6:01:59", "throughput": 4681.5, "total_tokens": 42235328} {"current_steps": 700, "total_steps": 15680, "loss": 0.31849193572998047, "lr": 9.951045566947361e-06, "epoch": 0.08928571428571429, "percentage": 4.46, "elapsed_time": "2:31:22", "remaining_time": "2 days, 5:59:18", "throughput": 4683.87, "total_tokens": 42539752} {"current_steps": 705, "total_steps": 15680, "loss": 0.3369591236114502, "lr": 9.950343878246011e-06, "epoch": 0.0899234693877551, "percentage": 4.5, "elapsed_time": "2:32:31", "remaining_time": "2 days, 5:59:40", "throughput": 4681.91, "total_tokens": 42844680} {"current_steps": 710, "total_steps": 15680, "loss": 0.3505253314971924, "lr": 9.949637221528847e-06, "epoch": 0.09056122448979592, "percentage": 4.53, "elapsed_time": "2:33:34", "remaining_time": "2 days, 5:58:05", "throughput": 4682.78, "total_tokens": 43149992} {"current_steps": 715, "total_steps": 15680, "loss": 0.34964261054992674, "lr": 9.94892559750505e-06, "epoch": 0.09119897959183673, "percentage": 4.56, "elapsed_time": "2:34:45", "remaining_time": "2 days, 5:59:10", "throughput": 4679.8, "total_tokens": 43455200} {"current_steps": 720, "total_steps": 15680, "loss": 0.34442615509033203, "lr": 9.948209006888782e-06, "epoch": 0.09183673469387756, "percentage": 4.59, "elapsed_time": "2:35:50", "remaining_time": "2 days, 5:58:01", "throughput": 4679.67, "total_tokens": 43756952} {"current_steps": 725, "total_steps": 15680, "loss": 0.37545912265777587, "lr": 9.947487450399196e-06, "epoch": 0.09247448979591837, "percentage": 4.62, "elapsed_time": "2:36:40", "remaining_time": "2 days, 5:51:44", "throughput": 4688.33, "total_tokens": 44071424} {"current_steps": 730, "total_steps": 15680, "loss": 0.3321858882904053, "lr": 9.946760928760419e-06, "epoch": 0.09311224489795919, "percentage": 4.66, "elapsed_time": "2:37:47", "remaining_time": "2 days, 5:51:26", "throughput": 4687.12, "total_tokens": 44374592} {"current_steps": 735, "total_steps": 15680, "loss": 0.32565453052520754, "lr": 9.946029442701572e-06, "epoch": 0.09375, "percentage": 4.69, "elapsed_time": "2:38:43", "remaining_time": "2 days, 5:47:22", "throughput": 4690.7, "total_tokens": 44671440} {"current_steps": 740, "total_steps": 15680, "loss": 0.3345797538757324, "lr": 9.945292992956747e-06, "epoch": 0.09438775510204081, "percentage": 4.72, "elapsed_time": "2:39:54", "remaining_time": "2 days, 5:48:15", "throughput": 4687.92, "total_tokens": 44976088} {"current_steps": 745, "total_steps": 15680, "loss": 0.34259605407714844, "lr": 9.944551580265025e-06, "epoch": 0.09502551020408163, "percentage": 4.75, "elapsed_time": "2:41:06", "remaining_time": "2 days, 5:49:44", "throughput": 4684.23, "total_tokens": 45280296} {"current_steps": 750, "total_steps": 15680, "loss": 0.35463581085205076, "lr": 9.943805205370467e-06, "epoch": 0.09566326530612244, "percentage": 4.78, "elapsed_time": "2:42:10", "remaining_time": "2 days, 5:48:13", "throughput": 4684.82, "total_tokens": 45583616} {"current_steps": 755, "total_steps": 15680, "loss": 0.3260321140289307, "lr": 9.94305386902211e-06, "epoch": 0.09630102040816327, "percentage": 4.82, "elapsed_time": "2:43:18", "remaining_time": "2 days, 5:48:09", "throughput": 4682.26, "total_tokens": 45876952} {"current_steps": 760, "total_steps": 15680, "loss": 0.33512492179870607, "lr": 9.942297571973973e-06, "epoch": 0.09693877551020408, "percentage": 4.85, "elapsed_time": "2:44:28", "remaining_time": "2 days, 5:48:48", "throughput": 4679.56, "total_tokens": 46178848} {"current_steps": 765, "total_steps": 15680, "loss": 0.32372226715087893, "lr": 9.941536314985054e-06, "epoch": 0.0975765306122449, "percentage": 4.88, "elapsed_time": "2:45:43", "remaining_time": "2 days, 5:51:12", "throughput": 4675.21, "total_tokens": 46489520} {"current_steps": 770, "total_steps": 15680, "loss": 0.3503239631652832, "lr": 9.940770098819329e-06, "epoch": 0.09821428571428571, "percentage": 4.91, "elapsed_time": "2:46:33", "remaining_time": "2 days, 5:45:11", "throughput": 4683.24, "total_tokens": 46802232} {"current_steps": 775, "total_steps": 15680, "loss": 0.32001385688781736, "lr": 9.939998924245742e-06, "epoch": 0.09885204081632654, "percentage": 4.94, "elapsed_time": "2:47:35", "remaining_time": "2 days, 5:43:18", "throughput": 4684.71, "total_tokens": 47109088} {"current_steps": 780, "total_steps": 15680, "loss": 0.3270054578781128, "lr": 9.93922279203823e-06, "epoch": 0.09948979591836735, "percentage": 4.97, "elapsed_time": "2:48:35", "remaining_time": "2 days, 5:40:34", "throughput": 4685.46, "total_tokens": 47396392} {"current_steps": 785, "total_steps": 15680, "loss": 0.33510923385620117, "lr": 9.938441702975689e-06, "epoch": 0.10012755102040816, "percentage": 5.01, "elapsed_time": "2:49:31", "remaining_time": "2 days, 5:36:43", "throughput": 4688.61, "total_tokens": 47691224} {"current_steps": 790, "total_steps": 15680, "loss": 0.33897085189819337, "lr": 9.937655657842001e-06, "epoch": 0.10076530612244898, "percentage": 5.04, "elapsed_time": "2:50:44", "remaining_time": "2 days, 5:38:00", "throughput": 4685.69, "total_tokens": 48000248} {"current_steps": 795, "total_steps": 15680, "loss": 0.3564270496368408, "lr": 9.936864657426014e-06, "epoch": 0.10140306122448979, "percentage": 5.07, "elapsed_time": "2:51:33", "remaining_time": "2 days, 5:32:16", "throughput": 4693.66, "total_tokens": 48316296} {"current_steps": 800, "total_steps": 15680, "loss": 0.3363536834716797, "lr": 9.936068702521553e-06, "epoch": 0.10204081632653061, "percentage": 5.1, "elapsed_time": "2:52:37", "remaining_time": "2 days, 5:30:47", "throughput": 4694.19, "total_tokens": 48619456} {"current_steps": 805, "total_steps": 15680, "loss": 0.3507491111755371, "lr": 9.935267793927416e-06, "epoch": 0.10267857142857142, "percentage": 5.13, "elapsed_time": "2:53:43", "remaining_time": "2 days, 5:30:04", "throughput": 4693.78, "total_tokens": 48924672} {"current_steps": 810, "total_steps": 15680, "loss": 0.3112443447113037, "lr": 9.93446193244737e-06, "epoch": 0.10331632653061225, "percentage": 5.17, "elapsed_time": "2:54:44", "remaining_time": "2 days, 5:27:56", "throughput": 4695.02, "total_tokens": 49225280} {"current_steps": 815, "total_steps": 15680, "loss": 0.3627671718597412, "lr": 9.933651118890151e-06, "epoch": 0.10395408163265306, "percentage": 5.2, "elapsed_time": "2:55:53", "remaining_time": "2 days, 5:28:10", "throughput": 4692.98, "total_tokens": 49527824} {"current_steps": 820, "total_steps": 15680, "loss": 0.31316590309143066, "lr": 9.93283535406947e-06, "epoch": 0.10459183673469388, "percentage": 5.23, "elapsed_time": "2:56:49", "remaining_time": "2 days, 5:24:20", "throughput": 4695.74, "total_tokens": 49818424} {"current_steps": 825, "total_steps": 15680, "loss": 0.3390337467193604, "lr": 9.932014638804001e-06, "epoch": 0.10522959183673469, "percentage": 5.26, "elapsed_time": "2:57:59", "remaining_time": "2 days, 5:24:49", "throughput": 4693.29, "total_tokens": 50120392} {"current_steps": 830, "total_steps": 15680, "loss": 0.3528244972229004, "lr": 9.931188973917393e-06, "epoch": 0.10586734693877552, "percentage": 5.29, "elapsed_time": "2:59:09", "remaining_time": "2 days, 5:25:22", "throughput": 4692.13, "total_tokens": 50437328} {"current_steps": 835, "total_steps": 15680, "loss": 0.3476259708404541, "lr": 9.930358360238255e-06, "epoch": 0.10650510204081633, "percentage": 5.33, "elapsed_time": "3:00:21", "remaining_time": "2 days, 5:26:21", "throughput": 4688.99, "total_tokens": 50739776} {"current_steps": 840, "total_steps": 15680, "loss": 0.32042813301086426, "lr": 9.929522798600168e-06, "epoch": 0.10714285714285714, "percentage": 5.36, "elapsed_time": "3:01:22", "remaining_time": "2 days, 5:24:13", "throughput": 4691.53, "total_tokens": 51054616} {"current_steps": 845, "total_steps": 15680, "loss": 0.33142428398132323, "lr": 9.928682289841674e-06, "epoch": 0.10778061224489796, "percentage": 5.39, "elapsed_time": "3:02:29", "remaining_time": "2 days, 5:23:46", "throughput": 4690.56, "total_tokens": 51357944} {"current_steps": 850, "total_steps": 15680, "loss": 0.35215234756469727, "lr": 9.927836834806284e-06, "epoch": 0.10841836734693877, "percentage": 5.42, "elapsed_time": "3:03:40", "remaining_time": "2 days, 5:24:32", "throughput": 4687.97, "total_tokens": 51662968} {"current_steps": 855, "total_steps": 15680, "loss": 0.3072350025177002, "lr": 9.926986434342471e-06, "epoch": 0.1090561224489796, "percentage": 5.45, "elapsed_time": "3:04:44", "remaining_time": "2 days, 5:23:23", "throughput": 4687.04, "total_tokens": 51955408} {"current_steps": 860, "total_steps": 15680, "loss": 0.33462932109832766, "lr": 9.926131089303672e-06, "epoch": 0.1096938775510204, "percentage": 5.48, "elapsed_time": "3:05:46", "remaining_time": "2 days, 5:21:29", "throughput": 4688.41, "total_tokens": 52261056} {"current_steps": 865, "total_steps": 15680, "loss": 0.32468724250793457, "lr": 9.925270800548285e-06, "epoch": 0.11033163265306123, "percentage": 5.52, "elapsed_time": "3:06:51", "remaining_time": "2 days, 5:20:16", "throughput": 4687.57, "total_tokens": 52553456} {"current_steps": 870, "total_steps": 15680, "loss": 0.38157219886779786, "lr": 9.924405568939667e-06, "epoch": 0.11096938775510204, "percentage": 5.55, "elapsed_time": "3:07:48", "remaining_time": "2 days, 5:17:06", "throughput": 4690.83, "total_tokens": 52859568} {"current_steps": 875, "total_steps": 15680, "loss": 0.31001625061035154, "lr": 9.923535395346145e-06, "epoch": 0.11160714285714286, "percentage": 5.58, "elapsed_time": "3:08:56", "remaining_time": "2 days, 5:16:57", "throughput": 4689.54, "total_tokens": 53163928} {"current_steps": 880, "total_steps": 15680, "loss": 0.30125041007995607, "lr": 9.92266028064099e-06, "epoch": 0.11224489795918367, "percentage": 5.61, "elapsed_time": "3:10:03", "remaining_time": "2 days, 5:16:30", "throughput": 4689.18, "total_tokens": 53474152} {"current_steps": 885, "total_steps": 15680, "loss": 0.32144479751586913, "lr": 9.921780225702448e-06, "epoch": 0.11288265306122448, "percentage": 5.64, "elapsed_time": "3:11:17", "remaining_time": "2 days, 5:17:49", "throughput": 4685.95, "total_tokens": 53781448} {"current_steps": 890, "total_steps": 15680, "loss": 0.3461263418197632, "lr": 9.920895231413714e-06, "epoch": 0.11352040816326531, "percentage": 5.68, "elapsed_time": "3:12:19", "remaining_time": "2 days, 5:16:06", "throughput": 4688.26, "total_tokens": 54101144} {"current_steps": 895, "total_steps": 15680, "loss": 0.3378733158111572, "lr": 9.92000529866294e-06, "epoch": 0.11415816326530612, "percentage": 5.71, "elapsed_time": "3:13:26", "remaining_time": "2 days, 5:15:33", "throughput": 4687.92, "total_tokens": 54410120} {"current_steps": 900, "total_steps": 15680, "loss": 0.3378178596496582, "lr": 9.919110428343235e-06, "epoch": 0.11479591836734694, "percentage": 5.74, "elapsed_time": "3:14:19", "remaining_time": "2 days, 5:11:21", "throughput": 4692.9, "total_tokens": 54718832} {"current_steps": 905, "total_steps": 15680, "loss": 0.3274667978286743, "lr": 9.918210621352667e-06, "epoch": 0.11543367346938775, "percentage": 5.77, "elapsed_time": "3:15:30", "remaining_time": "2 days, 5:11:59", "throughput": 4690.12, "total_tokens": 55019664} {"current_steps": 910, "total_steps": 15680, "loss": 0.35554866790771483, "lr": 9.917305878594251e-06, "epoch": 0.11607142857142858, "percentage": 5.8, "elapsed_time": "3:16:49", "remaining_time": "2 days, 5:14:44", "throughput": 4685.01, "total_tokens": 55329784} {"current_steps": 915, "total_steps": 15680, "loss": 0.3127890110015869, "lr": 9.916396200975966e-06, "epoch": 0.11670918367346939, "percentage": 5.84, "elapsed_time": "3:17:51", "remaining_time": "2 days, 5:12:41", "throughput": 4685.56, "total_tokens": 55623544} {"current_steps": 920, "total_steps": 15680, "loss": 0.33112030029296874, "lr": 9.91548158941073e-06, "epoch": 0.11734693877551021, "percentage": 5.87, "elapsed_time": "3:19:00", "remaining_time": "2 days, 5:12:43", "throughput": 4683.94, "total_tokens": 55927480} {"current_steps": 925, "total_steps": 15680, "loss": 0.3396120548248291, "lr": 9.914562044816424e-06, "epoch": 0.11798469387755102, "percentage": 5.9, "elapsed_time": "3:20:13", "remaining_time": "2 days, 5:13:55", "throughput": 4681.18, "total_tokens": 56238632} {"current_steps": 930, "total_steps": 15680, "loss": 0.34828312397003175, "lr": 9.913637568115873e-06, "epoch": 0.11862244897959184, "percentage": 5.93, "elapsed_time": "3:21:20", "remaining_time": "2 days, 5:13:24", "throughput": 4678.78, "total_tokens": 56523656} {"current_steps": 935, "total_steps": 15680, "loss": 0.3335379123687744, "lr": 9.912708160236854e-06, "epoch": 0.11926020408163265, "percentage": 5.96, "elapsed_time": "3:22:13", "remaining_time": "2 days, 5:09:13", "throughput": 4683.35, "total_tokens": 56827640} {"current_steps": 940, "total_steps": 15680, "loss": 0.3137048244476318, "lr": 9.911773822112094e-06, "epoch": 0.11989795918367346, "percentage": 5.99, "elapsed_time": "3:23:18", "remaining_time": "2 days, 5:08:05", "throughput": 4682.84, "total_tokens": 57124504} {"current_steps": 945, "total_steps": 15680, "loss": 0.3561995029449463, "lr": 9.910834554679266e-06, "epoch": 0.12053571428571429, "percentage": 6.03, "elapsed_time": "3:24:31", "remaining_time": "2 days, 5:09:00", "throughput": 4679.71, "total_tokens": 57425768} {"current_steps": 950, "total_steps": 15680, "loss": 0.35443639755249023, "lr": 9.909890358880991e-06, "epoch": 0.1211734693877551, "percentage": 6.06, "elapsed_time": "3:25:46", "remaining_time": "2 days, 5:10:36", "throughput": 4675.4, "total_tokens": 57725000} {"current_steps": 955, "total_steps": 15680, "loss": 0.3275070428848267, "lr": 9.908941235664835e-06, "epoch": 0.12181122448979592, "percentage": 6.09, "elapsed_time": "3:26:43", "remaining_time": "2 days, 5:07:33", "throughput": 4678.49, "total_tokens": 58031336} {"current_steps": 960, "total_steps": 15680, "loss": 0.3348393440246582, "lr": 9.907987185983307e-06, "epoch": 0.12244897959183673, "percentage": 6.12, "elapsed_time": "3:27:59", "remaining_time": "2 days, 5:09:08", "throughput": 4674.2, "total_tokens": 58330568} {"current_steps": 965, "total_steps": 15680, "loss": 0.32388012409210204, "lr": 9.907028210793868e-06, "epoch": 0.12308673469387756, "percentage": 6.15, "elapsed_time": "3:29:10", "remaining_time": "2 days, 5:09:37", "throughput": 4671.06, "total_tokens": 58623792} {"current_steps": 970, "total_steps": 15680, "loss": 0.3385571002960205, "lr": 9.906064311058911e-06, "epoch": 0.12372448979591837, "percentage": 6.19, "elapsed_time": "3:30:19", "remaining_time": "2 days, 5:09:26", "throughput": 4670.78, "total_tokens": 58940704} {"current_steps": 975, "total_steps": 15680, "loss": 0.31595683097839355, "lr": 9.90509548774578e-06, "epoch": 0.12436224489795919, "percentage": 6.22, "elapsed_time": "3:31:16", "remaining_time": "2 days, 5:06:23", "throughput": 4674.38, "total_tokens": 59253592} {"current_steps": 980, "total_steps": 15680, "loss": 0.31098217964172364, "lr": 9.904121741826757e-06, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "3:32:13", "remaining_time": "2 days, 5:03:23", "throughput": 4676.76, "total_tokens": 59551672} {"current_steps": 985, "total_steps": 15680, "loss": 0.3462122678756714, "lr": 9.903143074279061e-06, "epoch": 0.1256377551020408, "percentage": 6.28, "elapsed_time": "3:33:10", "remaining_time": "2 days, 5:00:13", "throughput": 4680.4, "total_tokens": 59863016} {"current_steps": 990, "total_steps": 15680, "loss": 0.3320111513137817, "lr": 9.902159486084857e-06, "epoch": 0.12627551020408162, "percentage": 6.31, "elapsed_time": "3:34:16", "remaining_time": "2 days, 4:59:28", "throughput": 4679.51, "total_tokens": 60161872} {"current_steps": 995, "total_steps": 15680, "loss": 0.3359437704086304, "lr": 9.90117097823124e-06, "epoch": 0.12691326530612246, "percentage": 6.35, "elapsed_time": "3:35:24", "remaining_time": "2 days, 4:59:15", "throughput": 4678.26, "total_tokens": 60465968} {"current_steps": 1000, "total_steps": 15680, "loss": 0.3319170713424683, "lr": 9.900177551710252e-06, "epoch": 0.12755102040816327, "percentage": 6.38, "elapsed_time": "3:36:34", "remaining_time": "2 days, 4:59:17", "throughput": 4676.51, "total_tokens": 60768400} {"current_steps": 1005, "total_steps": 15680, "loss": 0.3651275157928467, "lr": 9.899179207518863e-06, "epoch": 0.12818877551020408, "percentage": 6.41, "elapsed_time": "3:37:38", "remaining_time": "2 days, 4:57:57", "throughput": 4677.5, "total_tokens": 61080280} {"current_steps": 1010, "total_steps": 15680, "loss": 0.33693101406097414, "lr": 9.89817594665898e-06, "epoch": 0.1288265306122449, "percentage": 6.44, "elapsed_time": "3:38:50", "remaining_time": "2 days, 4:58:40", "throughput": 4675.94, "total_tokens": 61398592} {"current_steps": 1015, "total_steps": 15680, "loss": 0.32893297672271726, "lr": 9.897167770137449e-06, "epoch": 0.12946428571428573, "percentage": 6.47, "elapsed_time": "3:39:53", "remaining_time": "2 days, 4:56:58", "throughput": 4677.43, "total_tokens": 61709984} {"current_steps": 1020, "total_steps": 15680, "loss": 0.3443321943283081, "lr": 9.89615467896604e-06, "epoch": 0.13010204081632654, "percentage": 6.51, "elapsed_time": "3:40:55", "remaining_time": "2 days, 4:55:15", "throughput": 4678.96, "total_tokens": 62022072} {"current_steps": 1025, "total_steps": 15680, "loss": 0.31420562267303465, "lr": 9.895136674161466e-06, "epoch": 0.13073979591836735, "percentage": 6.54, "elapsed_time": "3:42:01", "remaining_time": "2 days, 4:54:24", "throughput": 4678.62, "total_tokens": 62326000} {"current_steps": 1030, "total_steps": 15680, "loss": 0.3463484287261963, "lr": 9.894113756745362e-06, "epoch": 0.13137755102040816, "percentage": 6.57, "elapsed_time": "3:43:12", "remaining_time": "2 days, 4:54:46", "throughput": 4677.01, "total_tokens": 62637088} {"current_steps": 1035, "total_steps": 15680, "loss": 0.3330828189849854, "lr": 9.893085927744302e-06, "epoch": 0.13201530612244897, "percentage": 6.6, "elapsed_time": "3:44:16", "remaining_time": "2 days, 4:53:26", "throughput": 4677.23, "total_tokens": 62939296} {"current_steps": 1040, "total_steps": 15680, "loss": 0.3249910831451416, "lr": 9.892053188189778e-06, "epoch": 0.1326530612244898, "percentage": 6.63, "elapsed_time": "3:45:31", "remaining_time": "2 days, 4:54:40", "throughput": 4673.67, "total_tokens": 63241312} {"current_steps": 1045, "total_steps": 15680, "loss": 0.332883358001709, "lr": 9.89101553911822e-06, "epoch": 0.13329081632653061, "percentage": 6.66, "elapsed_time": "3:46:40", "remaining_time": "2 days, 4:54:32", "throughput": 4672.04, "total_tokens": 63542296} {"current_steps": 1050, "total_steps": 15680, "loss": 0.32372775077819826, "lr": 9.889972981570984e-06, "epoch": 0.13392857142857142, "percentage": 6.7, "elapsed_time": "3:47:44", "remaining_time": "2 days, 4:53:12", "throughput": 4672.07, "total_tokens": 63841688} {"current_steps": 1055, "total_steps": 15680, "loss": 0.33316926956176757, "lr": 9.888925516594344e-06, "epoch": 0.13456632653061223, "percentage": 6.73, "elapsed_time": "3:48:52", "remaining_time": "2 days, 4:52:43", "throughput": 4671.65, "total_tokens": 64152120} {"current_steps": 1060, "total_steps": 15680, "loss": 0.34979519844055174, "lr": 9.887873145239505e-06, "epoch": 0.13520408163265307, "percentage": 6.76, "elapsed_time": "3:49:59", "remaining_time": "2 days, 4:52:05", "throughput": 4671.49, "total_tokens": 64463160} {"current_steps": 1065, "total_steps": 15680, "loss": 0.3216874122619629, "lr": 9.886815868562596e-06, "epoch": 0.13584183673469388, "percentage": 6.79, "elapsed_time": "3:51:00", "remaining_time": "2 days, 4:50:05", "throughput": 4672.93, "total_tokens": 64768464} {"current_steps": 1070, "total_steps": 15680, "loss": 0.31194138526916504, "lr": 9.885753687624671e-06, "epoch": 0.1364795918367347, "percentage": 6.82, "elapsed_time": "3:51:58", "remaining_time": "2 days, 4:47:22", "throughput": 4674.81, "total_tokens": 65065256} {"current_steps": 1075, "total_steps": 15680, "loss": 0.34079148769378664, "lr": 9.884686603491697e-06, "epoch": 0.1371173469387755, "percentage": 6.86, "elapsed_time": "3:52:59", "remaining_time": "2 days, 4:45:27", "throughput": 4676.4, "total_tokens": 65374104} {"current_steps": 1080, "total_steps": 15680, "loss": 0.33709142208099363, "lr": 9.883614617234574e-06, "epoch": 0.1377551020408163, "percentage": 6.89, "elapsed_time": "3:54:07", "remaining_time": "2 days, 4:44:54", "throughput": 4675.39, "total_tokens": 65675264} {"current_steps": 1085, "total_steps": 15680, "loss": 0.33071603775024416, "lr": 9.882537729929111e-06, "epoch": 0.13839285714285715, "percentage": 6.92, "elapsed_time": "3:55:10", "remaining_time": "2 days, 4:43:22", "throughput": 4675.89, "total_tokens": 65976824} {"current_steps": 1090, "total_steps": 15680, "loss": 0.33824639320373534, "lr": 9.88145594265604e-06, "epoch": 0.13903061224489796, "percentage": 6.95, "elapsed_time": "3:55:57", "remaining_time": "2 days, 4:38:17", "throughput": 4681.34, "total_tokens": 66274184} {"current_steps": 1095, "total_steps": 15680, "loss": 0.3228901863098145, "lr": 9.880369256501009e-06, "epoch": 0.13966836734693877, "percentage": 6.98, "elapsed_time": "3:56:50", "remaining_time": "2 days, 4:34:40", "throughput": 4683.57, "total_tokens": 66556608} {"current_steps": 1100, "total_steps": 15680, "loss": 0.3071782350540161, "lr": 9.879277672554586e-06, "epoch": 0.14030612244897958, "percentage": 7.02, "elapsed_time": "3:57:48", "remaining_time": "2 days, 4:32:08", "throughput": 4685.62, "total_tokens": 66858872} {"current_steps": 1105, "total_steps": 15680, "loss": 0.3458325624465942, "lr": 9.878181191912251e-06, "epoch": 0.14094387755102042, "percentage": 7.05, "elapsed_time": "3:58:46", "remaining_time": "2 days, 4:29:21", "throughput": 4688.2, "total_tokens": 67163584} {"current_steps": 1110, "total_steps": 15680, "loss": 0.3350841045379639, "lr": 9.877079815674397e-06, "epoch": 0.14158163265306123, "percentage": 7.08, "elapsed_time": "3:59:53", "remaining_time": "2 days, 4:28:53", "throughput": 4687.38, "total_tokens": 67468600} {"current_steps": 1115, "total_steps": 15680, "loss": 0.3193055152893066, "lr": 9.875973544946335e-06, "epoch": 0.14221938775510204, "percentage": 7.11, "elapsed_time": "4:00:58", "remaining_time": "2 days, 4:27:47", "throughput": 4687.72, "total_tokens": 67777000} {"current_steps": 1120, "total_steps": 15680, "loss": 0.29361796379089355, "lr": 9.874862380838284e-06, "epoch": 0.14285714285714285, "percentage": 7.14, "elapsed_time": "4:02:02", "remaining_time": "2 days, 4:26:30", "throughput": 4688.75, "total_tokens": 68091832} {"current_steps": 1125, "total_steps": 15680, "loss": 0.3391995429992676, "lr": 9.873746324465372e-06, "epoch": 0.1434948979591837, "percentage": 7.17, "elapsed_time": "4:03:01", "remaining_time": "2 days, 4:24:13", "throughput": 4690.98, "total_tokens": 68401992} {"current_steps": 1130, "total_steps": 15680, "loss": 0.3495980739593506, "lr": 9.872625376947642e-06, "epoch": 0.1441326530612245, "percentage": 7.21, "elapsed_time": "4:04:06", "remaining_time": "2 days, 4:23:10", "throughput": 4691.33, "total_tokens": 68711720} {"current_steps": 1135, "total_steps": 15680, "loss": 0.3603889226913452, "lr": 9.871499539410045e-06, "epoch": 0.1447704081632653, "percentage": 7.24, "elapsed_time": "4:05:03", "remaining_time": "2 days, 4:20:19", "throughput": 4694.44, "total_tokens": 69022608} {"current_steps": 1140, "total_steps": 15680, "loss": 0.33861393928527833, "lr": 9.870368812982433e-06, "epoch": 0.14540816326530612, "percentage": 7.27, "elapsed_time": "4:06:00", "remaining_time": "2 days, 4:17:34", "throughput": 4697.97, "total_tokens": 69342064} {"current_steps": 1145, "total_steps": 15680, "loss": 0.35953919887542723, "lr": 9.869233198799572e-06, "epoch": 0.14604591836734693, "percentage": 7.3, "elapsed_time": "4:07:07", "remaining_time": "2 days, 4:17:10", "throughput": 4697.12, "total_tokens": 69648560} {"current_steps": 1150, "total_steps": 15680, "loss": 0.3488070011138916, "lr": 9.86809269800113e-06, "epoch": 0.14668367346938777, "percentage": 7.33, "elapsed_time": "4:08:10", "remaining_time": "2 days, 4:15:32", "throughput": 4697.54, "total_tokens": 69946440} {"current_steps": 1155, "total_steps": 15680, "loss": 0.3258484363555908, "lr": 9.86694731173168e-06, "epoch": 0.14732142857142858, "percentage": 7.37, "elapsed_time": "4:09:13", "remaining_time": "2 days, 4:14:12", "throughput": 4697.97, "total_tokens": 70251592} {"current_steps": 1160, "total_steps": 15680, "loss": 0.32013731002807616, "lr": 9.865797041140695e-06, "epoch": 0.14795918367346939, "percentage": 7.4, "elapsed_time": "4:10:08", "remaining_time": "2 days, 4:10:59", "throughput": 4701.69, "total_tokens": 70563112} {"current_steps": 1165, "total_steps": 15680, "loss": 0.34639954566955566, "lr": 9.864641887382552e-06, "epoch": 0.1485969387755102, "percentage": 7.43, "elapsed_time": "4:11:19", "remaining_time": "2 days, 4:11:14", "throughput": 4700.41, "total_tokens": 70878168} {"current_steps": 1170, "total_steps": 15680, "loss": 0.34975519180297854, "lr": 9.863481851616528e-06, "epoch": 0.14923469387755103, "percentage": 7.46, "elapsed_time": "4:12:23", "remaining_time": "2 days, 4:10:06", "throughput": 4700.61, "total_tokens": 71184248} {"current_steps": 1175, "total_steps": 15680, "loss": 0.34158849716186523, "lr": 9.862316935006803e-06, "epoch": 0.14987244897959184, "percentage": 7.49, "elapsed_time": "4:13:23", "remaining_time": "2 days, 4:08:05", "throughput": 4701.99, "total_tokens": 71487968} {"current_steps": 1180, "total_steps": 15680, "loss": 0.3300424575805664, "lr": 9.86114713872245e-06, "epoch": 0.15051020408163265, "percentage": 7.53, "elapsed_time": "4:14:39", "remaining_time": "2 days, 4:09:20", "throughput": 4698.57, "total_tokens": 71793392} {"current_steps": 1185, "total_steps": 15680, "loss": 0.3214893102645874, "lr": 9.85997246393744e-06, "epoch": 0.15114795918367346, "percentage": 7.56, "elapsed_time": "4:15:40", "remaining_time": "2 days, 4:07:28", "throughput": 4698.97, "total_tokens": 72085568} {"current_steps": 1190, "total_steps": 15680, "loss": 0.34440088272094727, "lr": 9.858792911830643e-06, "epoch": 0.15178571428571427, "percentage": 7.59, "elapsed_time": "4:16:48", "remaining_time": "2 days, 4:06:56", "throughput": 4698.74, "total_tokens": 72398520} {"current_steps": 1195, "total_steps": 15680, "loss": 0.32814226150512693, "lr": 9.857608483585823e-06, "epoch": 0.1524234693877551, "percentage": 7.62, "elapsed_time": "4:17:58", "remaining_time": "2 days, 4:07:05", "throughput": 4696.13, "total_tokens": 72690904} {"current_steps": 1200, "total_steps": 15680, "loss": 0.3319169759750366, "lr": 9.856419180391636e-06, "epoch": 0.15306122448979592, "percentage": 7.65, "elapsed_time": "4:19:16", "remaining_time": "2 days, 4:08:34", "throughput": 4692.13, "total_tokens": 72992704} {"current_steps": 1205, "total_steps": 15680, "loss": 0.3418698310852051, "lr": 9.855225003441629e-06, "epoch": 0.15369897959183673, "percentage": 7.68, "elapsed_time": "4:20:18", "remaining_time": "2 days, 4:06:55", "throughput": 4692.52, "total_tokens": 73289816} {"current_steps": 1210, "total_steps": 15680, "loss": 0.33366372585296633, "lr": 9.85402595393424e-06, "epoch": 0.15433673469387754, "percentage": 7.72, "elapsed_time": "4:21:25", "remaining_time": "2 days, 4:06:15", "throughput": 4692.3, "total_tokens": 73600072} {"current_steps": 1215, "total_steps": 15680, "loss": 0.33455376625061034, "lr": 9.852822033072805e-06, "epoch": 0.15497448979591838, "percentage": 7.75, "elapsed_time": "4:22:35", "remaining_time": "2 days, 4:06:08", "throughput": 4691.0, "total_tokens": 73906704} {"current_steps": 1220, "total_steps": 15680, "loss": 0.3582612991333008, "lr": 9.85161324206554e-06, "epoch": 0.1556122448979592, "percentage": 7.78, "elapsed_time": "4:23:51", "remaining_time": "2 days, 4:07:22", "throughput": 4686.98, "total_tokens": 74201976} {"current_steps": 1225, "total_steps": 15680, "loss": 0.3431835174560547, "lr": 9.850399582125548e-06, "epoch": 0.15625, "percentage": 7.81, "elapsed_time": "4:24:45", "remaining_time": "2 days, 4:04:04", "throughput": 4689.99, "total_tokens": 74500840} {"current_steps": 1230, "total_steps": 15680, "loss": 0.34818758964538576, "lr": 9.849181054470827e-06, "epoch": 0.1568877551020408, "percentage": 7.84, "elapsed_time": "4:25:52", "remaining_time": "2 days, 4:03:24", "throughput": 4689.64, "total_tokens": 74809560} {"current_steps": 1235, "total_steps": 15680, "loss": 0.3170036792755127, "lr": 9.84795766032425e-06, "epoch": 0.15752551020408162, "percentage": 7.88, "elapsed_time": "4:27:00", "remaining_time": "2 days, 4:03:04", "throughput": 4688.54, "total_tokens": 75113704} {"current_steps": 1240, "total_steps": 15680, "loss": 0.3286417007446289, "lr": 9.84672940091358e-06, "epoch": 0.15816326530612246, "percentage": 7.91, "elapsed_time": "4:28:10", "remaining_time": "2 days, 4:02:51", "throughput": 4686.21, "total_tokens": 75401424} {"current_steps": 1245, "total_steps": 15680, "loss": 0.3288563251495361, "lr": 9.845496277471463e-06, "epoch": 0.15880102040816327, "percentage": 7.94, "elapsed_time": "4:29:09", "remaining_time": "2 days, 4:00:45", "throughput": 4687.81, "total_tokens": 75706752} {"current_steps": 1250, "total_steps": 15680, "loss": 0.3585826873779297, "lr": 9.84425829123542e-06, "epoch": 0.15943877551020408, "percentage": 7.97, "elapsed_time": "4:30:08", "remaining_time": "2 days, 3:58:32", "throughput": 4689.32, "total_tokens": 76007288} {"current_steps": 1255, "total_steps": 15680, "loss": 0.34567928314208984, "lr": 9.84301544344786e-06, "epoch": 0.1600765306122449, "percentage": 8.0, "elapsed_time": "4:31:08", "remaining_time": "2 days, 3:56:35", "throughput": 4691.15, "total_tokens": 76320024} {"current_steps": 1260, "total_steps": 15680, "loss": 0.3292954683303833, "lr": 9.841767735356069e-06, "epoch": 0.16071428571428573, "percentage": 8.04, "elapsed_time": "4:32:12", "remaining_time": "2 days, 3:55:14", "throughput": 4690.29, "total_tokens": 76603280} {"current_steps": 1265, "total_steps": 15680, "loss": 0.3470223665237427, "lr": 9.840515168212208e-06, "epoch": 0.16135204081632654, "percentage": 8.07, "elapsed_time": "4:33:08", "remaining_time": "2 days, 3:52:31", "throughput": 4692.99, "total_tokens": 76911416} {"current_steps": 1270, "total_steps": 15680, "loss": 0.35660953521728517, "lr": 9.839257743273313e-06, "epoch": 0.16198979591836735, "percentage": 8.1, "elapsed_time": "4:34:12", "remaining_time": "2 days, 3:51:13", "throughput": 4693.51, "total_tokens": 77218272} {"current_steps": 1275, "total_steps": 15680, "loss": 0.31610519886016847, "lr": 9.8379954618013e-06, "epoch": 0.16262755102040816, "percentage": 8.13, "elapsed_time": "4:35:20", "remaining_time": "2 days, 3:50:52", "throughput": 4691.95, "total_tokens": 77514744} {"current_steps": 1280, "total_steps": 15680, "loss": 0.3151726484298706, "lr": 9.836728325062956e-06, "epoch": 0.16326530612244897, "percentage": 8.16, "elapsed_time": "4:36:27", "remaining_time": "2 days, 3:50:13", "throughput": 4691.57, "total_tokens": 77823208} {"current_steps": 1285, "total_steps": 15680, "loss": 0.34789628982543946, "lr": 9.83545633432994e-06, "epoch": 0.1639030612244898, "percentage": 8.2, "elapsed_time": "4:37:37", "remaining_time": "2 days, 3:50:05", "throughput": 4690.51, "total_tokens": 78133400} {"current_steps": 1290, "total_steps": 15680, "loss": 0.31041646003723145, "lr": 9.834179490878789e-06, "epoch": 0.16454081632653061, "percentage": 8.23, "elapsed_time": "4:38:26", "remaining_time": "2 days, 3:46:03", "throughput": 4694.58, "total_tokens": 78430640} {"current_steps": 1295, "total_steps": 15680, "loss": 0.3281932592391968, "lr": 9.832897795990896e-06, "epoch": 0.16517857142857142, "percentage": 8.26, "elapsed_time": "4:39:32", "remaining_time": "2 days, 3:45:05", "throughput": 4694.25, "total_tokens": 78732032} {"current_steps": 1300, "total_steps": 15680, "loss": 0.32477402687072754, "lr": 9.83161125095254e-06, "epoch": 0.16581632653061223, "percentage": 8.29, "elapsed_time": "4:40:42", "remaining_time": "2 days, 3:45:03", "throughput": 4693.09, "total_tokens": 79043112} {"current_steps": 1305, "total_steps": 15680, "loss": 0.31569385528564453, "lr": 9.830319857054853e-06, "epoch": 0.16645408163265307, "percentage": 8.32, "elapsed_time": "4:41:48", "remaining_time": "2 days, 3:44:14", "throughput": 4693.0, "total_tokens": 79352128} {"current_steps": 1310, "total_steps": 15680, "loss": 0.3569095849990845, "lr": 9.82902361559384e-06, "epoch": 0.16709183673469388, "percentage": 8.35, "elapsed_time": "4:42:52", "remaining_time": "2 days, 3:42:54", "throughput": 4693.48, "total_tokens": 79658200} {"current_steps": 1315, "total_steps": 15680, "loss": 0.3371304988861084, "lr": 9.82772252787037e-06, "epoch": 0.1677295918367347, "percentage": 8.39, "elapsed_time": "4:43:52", "remaining_time": "2 days, 3:40:58", "throughput": 4695.24, "total_tokens": 79970224} {"current_steps": 1320, "total_steps": 15680, "loss": 0.35589327812194826, "lr": 9.826416595190177e-06, "epoch": 0.1683673469387755, "percentage": 8.42, "elapsed_time": "4:44:59", "remaining_time": "2 days, 3:40:17", "throughput": 4693.46, "total_tokens": 80254064} {"current_steps": 1325, "total_steps": 15680, "loss": 0.31534266471862793, "lr": 9.825105818863854e-06, "epoch": 0.1690051020408163, "percentage": 8.45, "elapsed_time": "4:46:10", "remaining_time": "2 days, 3:40:20", "throughput": 4691.54, "total_tokens": 80554360} {"current_steps": 1330, "total_steps": 15680, "loss": 0.35923516750335693, "lr": 9.823790200206857e-06, "epoch": 0.16964285714285715, "percentage": 8.48, "elapsed_time": "4:47:18", "remaining_time": "2 days, 3:39:54", "throughput": 4690.41, "total_tokens": 80855544} {"current_steps": 1335, "total_steps": 15680, "loss": 0.3390108585357666, "lr": 9.822469740539503e-06, "epoch": 0.17028061224489796, "percentage": 8.51, "elapsed_time": "4:48:18", "remaining_time": "2 days, 3:37:54", "throughput": 4691.69, "total_tokens": 81157864} {"current_steps": 1340, "total_steps": 15680, "loss": 0.36199450492858887, "lr": 9.821144441186964e-06, "epoch": 0.17091836734693877, "percentage": 8.55, "elapsed_time": "4:49:19", "remaining_time": "2 days, 3:36:12", "throughput": 4693.25, "total_tokens": 81472488} {"current_steps": 1345, "total_steps": 15680, "loss": 0.34079747200012206, "lr": 9.819814303479268e-06, "epoch": 0.17155612244897958, "percentage": 8.58, "elapsed_time": "4:50:35", "remaining_time": "2 days, 3:37:04", "throughput": 4690.67, "total_tokens": 81782968} {"current_steps": 1350, "total_steps": 15680, "loss": 0.32731170654296876, "lr": 9.818479328751303e-06, "epoch": 0.17219387755102042, "percentage": 8.61, "elapsed_time": "4:51:37", "remaining_time": "2 days, 3:35:32", "throughput": 4690.92, "total_tokens": 82079256} {"current_steps": 1355, "total_steps": 15680, "loss": 0.3492893218994141, "lr": 9.817139518342811e-06, "epoch": 0.17283163265306123, "percentage": 8.64, "elapsed_time": "4:52:41", "remaining_time": "2 days, 3:34:22", "throughput": 4691.68, "total_tokens": 82394552} {"current_steps": 1360, "total_steps": 15680, "loss": 0.3357325315475464, "lr": 9.815794873598384e-06, "epoch": 0.17346938775510204, "percentage": 8.67, "elapsed_time": "4:53:43", "remaining_time": "2 days, 3:32:48", "throughput": 4692.54, "total_tokens": 82700328} {"current_steps": 1365, "total_steps": 15680, "loss": 0.33596770763397216, "lr": 9.814445395867467e-06, "epoch": 0.17410714285714285, "percentage": 8.71, "elapsed_time": "4:54:42", "remaining_time": "2 days, 3:30:37", "throughput": 4693.7, "total_tokens": 82995568} {"current_steps": 1370, "total_steps": 15680, "loss": 0.3234375476837158, "lr": 9.813091086504356e-06, "epoch": 0.1747448979591837, "percentage": 8.74, "elapsed_time": "4:55:52", "remaining_time": "2 days, 3:30:31", "throughput": 4691.45, "total_tokens": 83286056} {"current_steps": 1375, "total_steps": 15680, "loss": 0.34646997451782224, "lr": 9.811731946868192e-06, "epoch": 0.1753826530612245, "percentage": 8.77, "elapsed_time": "4:57:05", "remaining_time": "2 days, 3:30:46", "throughput": 4689.7, "total_tokens": 83594600} {"current_steps": 1380, "total_steps": 15680, "loss": 0.3418739318847656, "lr": 9.810367978322971e-06, "epoch": 0.1760204081632653, "percentage": 8.8, "elapsed_time": "4:58:21", "remaining_time": "2 days, 3:31:37", "throughput": 4686.97, "total_tokens": 83902040} {"current_steps": 1385, "total_steps": 15680, "loss": 0.3338493347167969, "lr": 9.808999182237527e-06, "epoch": 0.17665816326530612, "percentage": 8.83, "elapsed_time": "4:59:23", "remaining_time": "2 days, 3:30:01", "throughput": 4686.72, "total_tokens": 84187696} {"current_steps": 1390, "total_steps": 15680, "loss": 0.35117316246032715, "lr": 9.807625559985546e-06, "epoch": 0.17729591836734693, "percentage": 8.86, "elapsed_time": "5:00:26", "remaining_time": "2 days, 3:28:38", "throughput": 4686.88, "total_tokens": 84486344} {"current_steps": 1395, "total_steps": 15680, "loss": 0.34419639110565187, "lr": 9.806247112945548e-06, "epoch": 0.17793367346938777, "percentage": 8.9, "elapsed_time": "5:01:36", "remaining_time": "2 days, 3:28:26", "throughput": 4685.51, "total_tokens": 84789144} {"current_steps": 1400, "total_steps": 15680, "loss": 0.32353553771972654, "lr": 9.804863842500906e-06, "epoch": 0.17857142857142858, "percentage": 8.93, "elapsed_time": "5:02:51", "remaining_time": "2 days, 3:29:07", "throughput": 4682.57, "total_tokens": 85088672} {"current_steps": 1405, "total_steps": 15680, "loss": 0.33654494285583497, "lr": 9.803475750039828e-06, "epoch": 0.17920918367346939, "percentage": 8.96, "elapsed_time": "5:03:53", "remaining_time": "2 days, 3:27:39", "throughput": 4683.34, "total_tokens": 85395520} {"current_steps": 1410, "total_steps": 15680, "loss": 0.35454869270324707, "lr": 9.80208283695536e-06, "epoch": 0.1798469387755102, "percentage": 8.99, "elapsed_time": "5:04:57", "remaining_time": "2 days, 3:26:19", "throughput": 4683.37, "total_tokens": 85693248} {"current_steps": 1415, "total_steps": 15680, "loss": 0.34549190998077395, "lr": 9.80068510464539e-06, "epoch": 0.18048469387755103, "percentage": 9.02, "elapsed_time": "5:05:59", "remaining_time": "2 days, 3:24:44", "throughput": 4684.09, "total_tokens": 85996488} {"current_steps": 1420, "total_steps": 15680, "loss": 0.3202133417129517, "lr": 9.799282554512637e-06, "epoch": 0.18112244897959184, "percentage": 9.06, "elapsed_time": "5:07:15", "remaining_time": "2 days, 3:25:36", "throughput": 4681.02, "total_tokens": 86298048} {"current_steps": 1425, "total_steps": 15680, "loss": 0.32825522422790526, "lr": 9.797875187964661e-06, "epoch": 0.18176020408163265, "percentage": 9.09, "elapsed_time": "5:08:12", "remaining_time": "2 days, 3:23:13", "throughput": 4683.14, "total_tokens": 86604512} {"current_steps": 1430, "total_steps": 15680, "loss": 0.3472906589508057, "lr": 9.79646300641385e-06, "epoch": 0.18239795918367346, "percentage": 9.12, "elapsed_time": "5:09:22", "remaining_time": "2 days, 3:22:51", "throughput": 4681.92, "total_tokens": 86906176} {"current_steps": 1435, "total_steps": 15680, "loss": 0.3585078716278076, "lr": 9.795046011277427e-06, "epoch": 0.18303571428571427, "percentage": 9.15, "elapsed_time": "5:10:17", "remaining_time": "2 days, 3:20:08", "throughput": 4685.2, "total_tokens": 87224464} {"current_steps": 1440, "total_steps": 15680, "loss": 0.3277950048446655, "lr": 9.793624203977446e-06, "epoch": 0.1836734693877551, "percentage": 9.18, "elapsed_time": "5:11:21", "remaining_time": "2 days, 3:19:00", "throughput": 4685.33, "total_tokens": 87529408} {"current_steps": 1445, "total_steps": 15680, "loss": 0.32544598579406736, "lr": 9.792197585940792e-06, "epoch": 0.18431122448979592, "percentage": 9.22, "elapsed_time": "5:12:18", "remaining_time": "2 days, 3:16:39", "throughput": 4687.03, "total_tokens": 87829336} {"current_steps": 1450, "total_steps": 15680, "loss": 0.35848388671875, "lr": 9.790766158599172e-06, "epoch": 0.18494897959183673, "percentage": 9.25, "elapsed_time": "5:13:33", "remaining_time": "2 days, 3:17:06", "throughput": 4685.08, "total_tokens": 88140344} {"current_steps": 1455, "total_steps": 15680, "loss": 0.346897554397583, "lr": 9.789329923389128e-06, "epoch": 0.18558673469387754, "percentage": 9.28, "elapsed_time": "5:14:37", "remaining_time": "2 days, 3:16:01", "throughput": 4685.01, "total_tokens": 88442888} {"current_steps": 1460, "total_steps": 15680, "loss": 0.34128966331481936, "lr": 9.787888881752018e-06, "epoch": 0.18622448979591838, "percentage": 9.31, "elapsed_time": "5:15:46", "remaining_time": "2 days, 3:15:32", "throughput": 4683.84, "total_tokens": 88741608} {"current_steps": 1465, "total_steps": 15680, "loss": 0.3022934913635254, "lr": 9.78644303513403e-06, "epoch": 0.1868622448979592, "percentage": 9.34, "elapsed_time": "5:16:52", "remaining_time": "2 days, 3:14:43", "throughput": 4682.85, "total_tokens": 89034512} {"current_steps": 1470, "total_steps": 15680, "loss": 0.33053126335144045, "lr": 9.784992384986173e-06, "epoch": 0.1875, "percentage": 9.38, "elapsed_time": "5:17:50", "remaining_time": "2 days, 3:12:25", "throughput": 4685.13, "total_tokens": 89346616} {"current_steps": 1475, "total_steps": 15680, "loss": 0.31446478366851804, "lr": 9.783536932764273e-06, "epoch": 0.1881377551020408, "percentage": 9.41, "elapsed_time": "5:18:59", "remaining_time": "2 days, 3:11:58", "throughput": 4683.58, "total_tokens": 89639184} {"current_steps": 1480, "total_steps": 15680, "loss": 0.3313866138458252, "lr": 9.782076679928981e-06, "epoch": 0.18877551020408162, "percentage": 9.44, "elapsed_time": "5:20:07", "remaining_time": "2 days, 3:11:32", "throughput": 4682.5, "total_tokens": 89941344} {"current_steps": 1485, "total_steps": 15680, "loss": 0.3180057525634766, "lr": 9.78061162794576e-06, "epoch": 0.18941326530612246, "percentage": 9.47, "elapsed_time": "5:21:10", "remaining_time": "2 days, 3:10:09", "throughput": 4683.05, "total_tokens": 90246672} {"current_steps": 1490, "total_steps": 15680, "loss": 0.35165953636169434, "lr": 9.779141778284893e-06, "epoch": 0.19005102040816327, "percentage": 9.5, "elapsed_time": "5:22:16", "remaining_time": "2 days, 3:09:06", "throughput": 4682.6, "total_tokens": 90543072} {"current_steps": 1495, "total_steps": 15680, "loss": 0.33533573150634766, "lr": 9.77766713242148e-06, "epoch": 0.19068877551020408, "percentage": 9.53, "elapsed_time": "5:23:11", "remaining_time": "2 days, 3:06:33", "throughput": 4685.61, "total_tokens": 90861600} {"current_steps": 1500, "total_steps": 15680, "loss": 0.343070387840271, "lr": 9.776187691835424e-06, "epoch": 0.1913265306122449, "percentage": 9.57, "elapsed_time": "5:24:23", "remaining_time": "2 days, 3:06:37", "throughput": 4683.85, "total_tokens": 91165096} {"current_steps": 1505, "total_steps": 15680, "loss": 0.3406609058380127, "lr": 9.774703458011453e-06, "epoch": 0.19196428571428573, "percentage": 9.6, "elapsed_time": "5:25:31", "remaining_time": "2 days, 3:05:57", "throughput": 4683.22, "total_tokens": 91469480} {"current_steps": 1510, "total_steps": 15680, "loss": 0.348543381690979, "lr": 9.773214432439098e-06, "epoch": 0.19260204081632654, "percentage": 9.63, "elapsed_time": "5:26:41", "remaining_time": "2 days, 3:05:40", "throughput": 4682.4, "total_tokens": 91781056} {"current_steps": 1515, "total_steps": 15680, "loss": 0.3520734071731567, "lr": 9.771720616612697e-06, "epoch": 0.19323979591836735, "percentage": 9.66, "elapsed_time": "5:27:53", "remaining_time": "2 days, 3:05:42", "throughput": 4680.83, "total_tokens": 92087768} {"current_steps": 1520, "total_steps": 15680, "loss": 0.3443084716796875, "lr": 9.770222012031404e-06, "epoch": 0.19387755102040816, "percentage": 9.69, "elapsed_time": "5:28:57", "remaining_time": "2 days, 3:04:25", "throughput": 4680.87, "total_tokens": 92386408} {"current_steps": 1525, "total_steps": 15680, "loss": 0.3578033447265625, "lr": 9.768718620199168e-06, "epoch": 0.19451530612244897, "percentage": 9.73, "elapsed_time": "5:29:55", "remaining_time": "2 days, 3:02:21", "throughput": 4683.06, "total_tokens": 92703640} {"current_steps": 1530, "total_steps": 15680, "loss": 0.3278501510620117, "lr": 9.76721044262475e-06, "epoch": 0.1951530612244898, "percentage": 9.76, "elapsed_time": "5:31:02", "remaining_time": "2 days, 3:01:31", "throughput": 4682.62, "total_tokens": 93006512} {"current_steps": 1535, "total_steps": 15680, "loss": 0.33351426124572753, "lr": 9.765697480821714e-06, "epoch": 0.19579081632653061, "percentage": 9.79, "elapsed_time": "5:32:05", "remaining_time": "2 days, 3:00:13", "throughput": 4683.27, "total_tokens": 93316656} {"current_steps": 1540, "total_steps": 15680, "loss": 0.3357309103012085, "lr": 9.764179736308419e-06, "epoch": 0.19642857142857142, "percentage": 9.82, "elapsed_time": "5:33:07", "remaining_time": "2 days, 2:58:38", "throughput": 4684.77, "total_tokens": 93635280} {"current_steps": 1545, "total_steps": 15680, "loss": 0.33041768074035643, "lr": 9.762657210608028e-06, "epoch": 0.19706632653061223, "percentage": 9.85, "elapsed_time": "5:33:59", "remaining_time": "2 days, 2:55:37", "throughput": 4687.75, "total_tokens": 93939712} {"current_steps": 1550, "total_steps": 15680, "loss": 0.3290611505508423, "lr": 9.761129905248505e-06, "epoch": 0.19770408163265307, "percentage": 9.89, "elapsed_time": "5:35:06", "remaining_time": "2 days, 2:54:50", "throughput": 4687.59, "total_tokens": 94249200} {"current_steps": 1555, "total_steps": 15680, "loss": 0.36706769466400146, "lr": 9.759597821762603e-06, "epoch": 0.19834183673469388, "percentage": 9.92, "elapsed_time": "5:36:05", "remaining_time": "2 days, 2:52:56", "throughput": 4689.25, "total_tokens": 94561768} {"current_steps": 1560, "total_steps": 15680, "loss": 0.3317730188369751, "lr": 9.758060961687879e-06, "epoch": 0.1989795918367347, "percentage": 9.95, "elapsed_time": "5:37:15", "remaining_time": "2 days, 2:52:39", "throughput": 4687.68, "total_tokens": 94858616} {"current_steps": 1565, "total_steps": 15680, "loss": 0.35649838447570803, "lr": 9.756519326566677e-06, "epoch": 0.1996173469387755, "percentage": 9.98, "elapsed_time": "5:38:23", "remaining_time": "2 days, 2:52:05", "throughput": 4686.09, "total_tokens": 95146448} {"current_steps": 1570, "total_steps": 15680, "loss": 0.34983410835266116, "lr": 9.754972917946138e-06, "epoch": 0.2002551020408163, "percentage": 10.01, "elapsed_time": "5:39:23", "remaining_time": "2 days, 2:50:16", "throughput": 4687.0, "total_tokens": 95445928} {"current_steps": 1575, "total_steps": 15680, "loss": 0.33331751823425293, "lr": 9.753421737378188e-06, "epoch": 0.20089285714285715, "percentage": 10.04, "elapsed_time": "5:40:37", "remaining_time": "2 days, 2:50:29", "throughput": 4684.68, "total_tokens": 95743248} {"current_steps": 1580, "total_steps": 15680, "loss": 0.3314680099487305, "lr": 9.751865786419546e-06, "epoch": 0.20153061224489796, "percentage": 10.08, "elapsed_time": "5:41:48", "remaining_time": "2 days, 2:50:14", "throughput": 4683.62, "total_tokens": 96051904} {"current_steps": 1585, "total_steps": 15680, "loss": 0.3457353115081787, "lr": 9.750305066631717e-06, "epoch": 0.20216836734693877, "percentage": 10.11, "elapsed_time": "5:42:55", "remaining_time": "2 days, 2:49:31", "throughput": 4683.16, "total_tokens": 96357912} {"current_steps": 1590, "total_steps": 15680, "loss": 0.36769120693206786, "lr": 9.748739579580995e-06, "epoch": 0.20280612244897958, "percentage": 10.14, "elapsed_time": "5:44:00", "remaining_time": "2 days, 2:48:30", "throughput": 4683.04, "total_tokens": 96661584} {"current_steps": 1595, "total_steps": 15680, "loss": 0.328265118598938, "lr": 9.747169326838451e-06, "epoch": 0.20344387755102042, "percentage": 10.17, "elapsed_time": "5:45:20", "remaining_time": "2 days, 2:49:34", "throughput": 4679.68, "total_tokens": 96963800} {"current_steps": 1600, "total_steps": 15680, "loss": 0.3056048393249512, "lr": 9.74559430997995e-06, "epoch": 0.20408163265306123, "percentage": 10.2, "elapsed_time": "5:46:21", "remaining_time": "2 days, 2:47:54", "throughput": 4680.7, "total_tokens": 97270552} {"current_steps": 1605, "total_steps": 15680, "loss": 0.3354539632797241, "lr": 9.744014530586124e-06, "epoch": 0.20471938775510204, "percentage": 10.24, "elapsed_time": "5:47:24", "remaining_time": "2 days, 2:46:35", "throughput": 4681.06, "total_tokens": 97574656} {"current_steps": 1610, "total_steps": 15680, "loss": 0.3385885715484619, "lr": 9.742429990242394e-06, "epoch": 0.20535714285714285, "percentage": 10.27, "elapsed_time": "5:48:32", "remaining_time": "2 days, 2:45:53", "throughput": 4680.34, "total_tokens": 97875664} {"current_steps": 1615, "total_steps": 15680, "loss": 0.33730876445770264, "lr": 9.740840690538961e-06, "epoch": 0.2059948979591837, "percentage": 10.3, "elapsed_time": "5:49:51", "remaining_time": "2 days, 2:46:58", "throughput": 4677.44, "total_tokens": 98188344} {"current_steps": 1620, "total_steps": 15680, "loss": 0.3308307409286499, "lr": 9.739246633070796e-06, "epoch": 0.2066326530612245, "percentage": 10.33, "elapsed_time": "5:50:58", "remaining_time": "2 days, 2:46:02", "throughput": 4676.76, "total_tokens": 98483392} {"current_steps": 1625, "total_steps": 15680, "loss": 0.33433582782745364, "lr": 9.737647819437645e-06, "epoch": 0.2072704081632653, "percentage": 10.36, "elapsed_time": "5:51:57", "remaining_time": "2 days, 2:44:09", "throughput": 4678.5, "total_tokens": 98797736} {"current_steps": 1630, "total_steps": 15680, "loss": 0.3261995792388916, "lr": 9.73604425124403e-06, "epoch": 0.20790816326530612, "percentage": 10.4, "elapsed_time": "5:53:06", "remaining_time": "2 days, 2:43:38", "throughput": 4677.31, "total_tokens": 99095392} {"current_steps": 1635, "total_steps": 15680, "loss": 0.3504668951034546, "lr": 9.734435930099246e-06, "epoch": 0.20854591836734693, "percentage": 10.43, "elapsed_time": "5:54:24", "remaining_time": "2 days, 2:44:24", "throughput": 4674.62, "total_tokens": 99402384} {"current_steps": 1640, "total_steps": 15680, "loss": 0.3475662708282471, "lr": 9.732822857617352e-06, "epoch": 0.20918367346938777, "percentage": 10.46, "elapsed_time": "5:55:36", "remaining_time": "2 days, 2:44:19", "throughput": 4673.76, "total_tokens": 99720720} {"current_steps": 1645, "total_steps": 15680, "loss": 0.32748582363128664, "lr": 9.731205035417183e-06, "epoch": 0.20982142857142858, "percentage": 10.49, "elapsed_time": "5:56:49", "remaining_time": "2 days, 2:44:20", "throughput": 4672.09, "total_tokens": 100025296} {"current_steps": 1650, "total_steps": 15680, "loss": 0.30248146057128905, "lr": 9.729582465122334e-06, "epoch": 0.21045918367346939, "percentage": 10.52, "elapsed_time": "5:57:52", "remaining_time": "2 days, 2:42:58", "throughput": 4672.28, "total_tokens": 100324064} {"current_steps": 1655, "total_steps": 15680, "loss": 0.3440696239471436, "lr": 9.727955148361166e-06, "epoch": 0.2110969387755102, "percentage": 10.55, "elapsed_time": "5:59:04", "remaining_time": "2 days, 2:42:55", "throughput": 4670.76, "total_tokens": 100629136} {"current_steps": 1660, "total_steps": 15680, "loss": 0.35681972503662107, "lr": 9.72632308676681e-06, "epoch": 0.21173469387755103, "percentage": 10.59, "elapsed_time": "6:00:19", "remaining_time": "2 days, 2:43:14", "throughput": 4668.62, "total_tokens": 100933584} {"current_steps": 1665, "total_steps": 15680, "loss": 0.339033842086792, "lr": 9.724686281977146e-06, "epoch": 0.21237244897959184, "percentage": 10.62, "elapsed_time": "6:01:12", "remaining_time": "2 days, 2:40:30", "throughput": 4670.9, "total_tokens": 101232000} {"current_steps": 1670, "total_steps": 15680, "loss": 0.32911860942840576, "lr": 9.72304473563483e-06, "epoch": 0.21301020408163265, "percentage": 10.65, "elapsed_time": "6:02:23", "remaining_time": "2 days, 2:40:09", "throughput": 4669.57, "total_tokens": 101532152} {"current_steps": 1675, "total_steps": 15680, "loss": 0.34564208984375, "lr": 9.721398449387265e-06, "epoch": 0.21364795918367346, "percentage": 10.68, "elapsed_time": "6:03:22", "remaining_time": "2 days, 2:38:15", "throughput": 4671.25, "total_tokens": 101844896} {"current_steps": 1680, "total_steps": 15680, "loss": 0.32876513004302976, "lr": 9.719747424886613e-06, "epoch": 0.21428571428571427, "percentage": 10.71, "elapsed_time": "6:04:25", "remaining_time": "2 days, 2:36:54", "throughput": 4671.4, "total_tokens": 102143320} {"current_steps": 1685, "total_steps": 15680, "loss": 0.32980966567993164, "lr": 9.718091663789795e-06, "epoch": 0.2149234693877551, "percentage": 10.75, "elapsed_time": "6:05:21", "remaining_time": "2 days, 2:34:30", "throughput": 4674.2, "total_tokens": 102464416} {"current_steps": 1690, "total_steps": 15680, "loss": 0.3364400386810303, "lr": 9.716431167758482e-06, "epoch": 0.21556122448979592, "percentage": 10.78, "elapsed_time": "6:06:30", "remaining_time": "2 days, 2:33:59", "throughput": 4672.85, "total_tokens": 102758392} {"current_steps": 1695, "total_steps": 15680, "loss": 0.31924474239349365, "lr": 9.714765938459097e-06, "epoch": 0.21619897959183673, "percentage": 10.81, "elapsed_time": "6:07:43", "remaining_time": "2 days, 2:34:02", "throughput": 4671.03, "total_tokens": 103060904} {"current_steps": 1700, "total_steps": 15680, "loss": 0.33878040313720703, "lr": 9.713095977562813e-06, "epoch": 0.21683673469387754, "percentage": 10.84, "elapsed_time": "6:08:50", "remaining_time": "2 days, 2:33:14", "throughput": 4670.76, "total_tokens": 103368528} {"current_steps": 1705, "total_steps": 15680, "loss": 0.3179375171661377, "lr": 9.711421286745554e-06, "epoch": 0.21747448979591838, "percentage": 10.87, "elapsed_time": "6:09:56", "remaining_time": "2 days, 2:32:14", "throughput": 4670.37, "total_tokens": 103666416} {"current_steps": 1710, "total_steps": 15680, "loss": 0.3452445507049561, "lr": 9.70974186768799e-06, "epoch": 0.2181122448979592, "percentage": 10.91, "elapsed_time": "6:10:55", "remaining_time": "2 days, 2:30:18", "throughput": 4670.82, "total_tokens": 103951664} {"current_steps": 1715, "total_steps": 15680, "loss": 0.34422879219055175, "lr": 9.708057722075532e-06, "epoch": 0.21875, "percentage": 10.94, "elapsed_time": "6:11:59", "remaining_time": "2 days, 2:29:06", "throughput": 4670.99, "total_tokens": 104255176} {"current_steps": 1720, "total_steps": 15680, "loss": 0.34129197597503663, "lr": 9.706368851598343e-06, "epoch": 0.2193877551020408, "percentage": 10.97, "elapsed_time": "6:13:06", "remaining_time": "2 days, 2:28:13", "throughput": 4670.37, "total_tokens": 104552216} {"current_steps": 1725, "total_steps": 15680, "loss": 0.32835357189178466, "lr": 9.704675257951316e-06, "epoch": 0.22002551020408162, "percentage": 11.0, "elapsed_time": "6:14:07", "remaining_time": "2 days, 2:26:39", "throughput": 4671.65, "total_tokens": 104868176} {"current_steps": 1730, "total_steps": 15680, "loss": 0.33469085693359374, "lr": 9.702976942834096e-06, "epoch": 0.22066326530612246, "percentage": 11.03, "elapsed_time": "6:15:09", "remaining_time": "2 days, 2:25:04", "throughput": 4671.91, "total_tokens": 105160960} {"current_steps": 1735, "total_steps": 15680, "loss": 0.3191352844238281, "lr": 9.701273907951058e-06, "epoch": 0.22130102040816327, "percentage": 11.07, "elapsed_time": "6:16:14", "remaining_time": "2 days, 2:24:02", "throughput": 4672.08, "total_tokens": 105470256} {"current_steps": 1740, "total_steps": 15680, "loss": 0.3543462038040161, "lr": 9.699566155011317e-06, "epoch": 0.22193877551020408, "percentage": 11.1, "elapsed_time": "6:17:21", "remaining_time": "2 days, 2:23:09", "throughput": 4672.04, "total_tokens": 105780200} {"current_steps": 1745, "total_steps": 15680, "loss": 0.32406888008117674, "lr": 9.697853685728721e-06, "epoch": 0.2225765306122449, "percentage": 11.13, "elapsed_time": "6:18:22", "remaining_time": "2 days, 2:21:36", "throughput": 4672.48, "total_tokens": 106078048} {"current_steps": 1750, "total_steps": 15680, "loss": 0.32779037952423096, "lr": 9.696136501821858e-06, "epoch": 0.22321428571428573, "percentage": 11.16, "elapsed_time": "6:19:30", "remaining_time": "2 days, 2:20:49", "throughput": 4671.48, "total_tokens": 106370016} {"current_steps": 1755, "total_steps": 15680, "loss": 0.3535364389419556, "lr": 9.694414605014035e-06, "epoch": 0.22385204081632654, "percentage": 11.19, "elapsed_time": "6:20:39", "remaining_time": "2 days, 2:20:23", "throughput": 4670.95, "total_tokens": 106684184} {"current_steps": 1760, "total_steps": 15680, "loss": 0.32790746688842776, "lr": 9.6926879970333e-06, "epoch": 0.22448979591836735, "percentage": 11.22, "elapsed_time": "6:21:33", "remaining_time": "2 days, 2:17:50", "throughput": 4673.64, "total_tokens": 106998216} {"current_steps": 1765, "total_steps": 15680, "loss": 0.33826274871826173, "lr": 9.690956679612422e-06, "epoch": 0.22512755102040816, "percentage": 11.26, "elapsed_time": "6:22:31", "remaining_time": "2 days, 2:15:43", "throughput": 4675.42, "total_tokens": 107306360} {"current_steps": 1770, "total_steps": 15680, "loss": 0.32278287410736084, "lr": 9.6892206544889e-06, "epoch": 0.22576530612244897, "percentage": 11.29, "elapsed_time": "6:23:37", "remaining_time": "2 days, 2:14:51", "throughput": 4675.04, "total_tokens": 107609480} {"current_steps": 1775, "total_steps": 15680, "loss": 0.3486739158630371, "lr": 9.687479923404959e-06, "epoch": 0.2264030612244898, "percentage": 11.32, "elapsed_time": "6:24:32", "remaining_time": "2 days, 2:12:22", "throughput": 4677.77, "total_tokens": 107926024} {"current_steps": 1780, "total_steps": 15680, "loss": 0.31470379829406736, "lr": 9.68573448810754e-06, "epoch": 0.22704081632653061, "percentage": 11.35, "elapsed_time": "6:25:36", "remaining_time": "2 days, 2:11:12", "throughput": 4678.03, "total_tokens": 108233416} {"current_steps": 1785, "total_steps": 15680, "loss": 0.32955155372619627, "lr": 9.683984350348313e-06, "epoch": 0.22767857142857142, "percentage": 11.38, "elapsed_time": "6:26:46", "remaining_time": "2 days, 2:10:46", "throughput": 4677.25, "total_tokens": 108542880} {"current_steps": 1790, "total_steps": 15680, "loss": 0.3453743696212769, "lr": 9.68222951188366e-06, "epoch": 0.22831632653061223, "percentage": 11.42, "elapsed_time": "6:27:53", "remaining_time": "2 days, 2:09:55", "throughput": 4676.77, "total_tokens": 108843736} {"current_steps": 1795, "total_steps": 15680, "loss": 0.32249295711517334, "lr": 9.680469974474685e-06, "epoch": 0.22895408163265307, "percentage": 11.45, "elapsed_time": "6:29:06", "remaining_time": "2 days, 2:09:56", "throughput": 4675.17, "total_tokens": 109150272} {"current_steps": 1800, "total_steps": 15680, "loss": 0.3216817855834961, "lr": 9.67870573988721e-06, "epoch": 0.22959183673469388, "percentage": 11.48, "elapsed_time": "6:30:09", "remaining_time": "2 days, 2:08:32", "throughput": 4675.68, "total_tokens": 109455200} {"current_steps": 1805, "total_steps": 15680, "loss": 0.3525111436843872, "lr": 9.676936809891763e-06, "epoch": 0.2302295918367347, "percentage": 11.51, "elapsed_time": "6:31:23", "remaining_time": "2 days, 2:08:38", "throughput": 4674.09, "total_tokens": 109764480} {"current_steps": 1810, "total_steps": 15680, "loss": 0.3223212003707886, "lr": 9.675163186263591e-06, "epoch": 0.2308673469387755, "percentage": 11.54, "elapsed_time": "6:32:34", "remaining_time": "2 days, 2:08:18", "throughput": 4672.82, "total_tokens": 110066288} {"current_steps": 1815, "total_steps": 15680, "loss": 0.31503829956054685, "lr": 9.673384870782649e-06, "epoch": 0.2315051020408163, "percentage": 11.58, "elapsed_time": "6:33:49", "remaining_time": "2 days, 2:08:25", "throughput": 4670.61, "total_tokens": 110362264} {"current_steps": 1820, "total_steps": 15680, "loss": 0.350568962097168, "lr": 9.6716018652336e-06, "epoch": 0.23214285714285715, "percentage": 11.61, "elapsed_time": "6:34:45", "remaining_time": "2 days, 2:06:11", "throughput": 4672.48, "total_tokens": 110668672} {"current_steps": 1825, "total_steps": 15680, "loss": 0.34694905281066896, "lr": 9.669814171405818e-06, "epoch": 0.23278061224489796, "percentage": 11.64, "elapsed_time": "6:35:51", "remaining_time": "2 days, 2:05:14", "throughput": 4672.1, "total_tokens": 110968352} {"current_steps": 1830, "total_steps": 15680, "loss": 0.3096019744873047, "lr": 9.668021791093372e-06, "epoch": 0.23341836734693877, "percentage": 11.67, "elapsed_time": "6:36:46", "remaining_time": "2 days, 2:02:57", "throughput": 4674.4, "total_tokens": 111282464} {"current_steps": 1835, "total_steps": 15680, "loss": 0.3228870153427124, "lr": 9.666224726095048e-06, "epoch": 0.23405612244897958, "percentage": 11.7, "elapsed_time": "6:37:50", "remaining_time": "2 days, 2:01:44", "throughput": 4674.75, "total_tokens": 111590336} {"current_steps": 1840, "total_steps": 15680, "loss": 0.3584311485290527, "lr": 9.66442297821432e-06, "epoch": 0.23469387755102042, "percentage": 11.73, "elapsed_time": "6:38:56", "remaining_time": "2 days, 2:00:45", "throughput": 4674.82, "total_tokens": 111899696} {"current_steps": 1845, "total_steps": 15680, "loss": 0.30771589279174805, "lr": 9.662616549259374e-06, "epoch": 0.23533163265306123, "percentage": 11.77, "elapsed_time": "6:40:08", "remaining_time": "2 days, 2:00:29", "throughput": 4672.8, "total_tokens": 112185968} {"current_steps": 1850, "total_steps": 15680, "loss": 0.36535985469818116, "lr": 9.660805441043082e-06, "epoch": 0.23596938775510204, "percentage": 11.8, "elapsed_time": "6:41:12", "remaining_time": "2 days, 1:59:21", "throughput": 4672.69, "total_tokens": 112485216} {"current_steps": 1855, "total_steps": 15680, "loss": 0.31926376819610597, "lr": 9.65898965538302e-06, "epoch": 0.23660714285714285, "percentage": 11.83, "elapsed_time": "6:42:22", "remaining_time": "2 days, 1:58:47", "throughput": 4671.99, "total_tokens": 112792024} {"current_steps": 1860, "total_steps": 15680, "loss": 0.3331429958343506, "lr": 9.657169194101457e-06, "epoch": 0.2372448979591837, "percentage": 11.86, "elapsed_time": "6:43:34", "remaining_time": "2 days, 1:58:38", "throughput": 4670.46, "total_tokens": 113094072} {"current_steps": 1865, "total_steps": 15680, "loss": 0.339237904548645, "lr": 9.655344059025351e-06, "epoch": 0.2378826530612245, "percentage": 11.89, "elapsed_time": "6:44:37", "remaining_time": "2 days, 1:57:18", "throughput": 4671.34, "total_tokens": 113410272} {"current_steps": 1870, "total_steps": 15680, "loss": 0.34667558670043946, "lr": 9.653514251986354e-06, "epoch": 0.2385204081632653, "percentage": 11.93, "elapsed_time": "6:45:38", "remaining_time": "2 days, 1:55:38", "throughput": 4671.89, "total_tokens": 113705304} {"current_steps": 1875, "total_steps": 15680, "loss": 0.321960973739624, "lr": 9.651679774820804e-06, "epoch": 0.23915816326530612, "percentage": 11.96, "elapsed_time": "6:46:28", "remaining_time": "2 days, 1:52:41", "throughput": 4675.05, "total_tokens": 114015568} {"current_steps": 1880, "total_steps": 15680, "loss": 0.3509210109710693, "lr": 9.649840629369728e-06, "epoch": 0.23979591836734693, "percentage": 11.99, "elapsed_time": "6:47:41", "remaining_time": "2 days, 1:52:38", "throughput": 4673.68, "total_tokens": 114325720} {"current_steps": 1885, "total_steps": 15680, "loss": 0.3434359073638916, "lr": 9.647996817478835e-06, "epoch": 0.24043367346938777, "percentage": 12.02, "elapsed_time": "6:48:57", "remaining_time": "2 days, 1:52:51", "throughput": 4671.74, "total_tokens": 114632136} {"current_steps": 1890, "total_steps": 15680, "loss": 0.32828240394592284, "lr": 9.646148340998521e-06, "epoch": 0.24107142857142858, "percentage": 12.05, "elapsed_time": "6:50:01", "remaining_time": "2 days, 1:51:38", "throughput": 4671.38, "total_tokens": 114922240} {"current_steps": 1895, "total_steps": 15680, "loss": 0.35318818092346194, "lr": 9.64429520178386e-06, "epoch": 0.24170918367346939, "percentage": 12.09, "elapsed_time": "6:51:06", "remaining_time": "2 days, 1:50:33", "throughput": 4670.93, "total_tokens": 115215224} {"current_steps": 1900, "total_steps": 15680, "loss": 0.335646915435791, "lr": 9.642437401694608e-06, "epoch": 0.2423469387755102, "percentage": 12.12, "elapsed_time": "6:52:20", "remaining_time": "2 days, 1:50:31", "throughput": 4669.64, "total_tokens": 115527552} {"current_steps": 1905, "total_steps": 15680, "loss": 0.32998104095458985, "lr": 9.640574942595195e-06, "epoch": 0.24298469387755103, "percentage": 12.15, "elapsed_time": "6:53:23", "remaining_time": "2 days, 1:49:10", "throughput": 4669.64, "total_tokens": 115821808} {"current_steps": 1910, "total_steps": 15680, "loss": 0.33642148971557617, "lr": 9.638707826354732e-06, "epoch": 0.24362244897959184, "percentage": 12.18, "elapsed_time": "6:54:26", "remaining_time": "2 days, 1:47:52", "throughput": 4669.57, "total_tokens": 116115216} {"current_steps": 1915, "total_steps": 15680, "loss": 0.32282869815826415, "lr": 9.636836054846997e-06, "epoch": 0.24426020408163265, "percentage": 12.21, "elapsed_time": "6:55:28", "remaining_time": "2 days, 1:46:23", "throughput": 4670.05, "total_tokens": 116415800} {"current_steps": 1920, "total_steps": 15680, "loss": 0.30709261894226075, "lr": 9.634959629950444e-06, "epoch": 0.24489795918367346, "percentage": 12.24, "elapsed_time": "6:56:40", "remaining_time": "2 days, 1:46:07", "throughput": 4668.68, "total_tokens": 116717552} {"current_steps": 1925, "total_steps": 15680, "loss": 0.3267780303955078, "lr": 9.6330785535482e-06, "epoch": 0.24553571428571427, "percentage": 12.28, "elapsed_time": "6:57:47", "remaining_time": "2 days, 1:45:17", "throughput": 4667.68, "total_tokens": 117006136} {"current_steps": 1930, "total_steps": 15680, "loss": 0.3533444404602051, "lr": 9.631192827528054e-06, "epoch": 0.2461734693877551, "percentage": 12.31, "elapsed_time": "6:59:00", "remaining_time": "2 days, 1:45:13", "throughput": 4666.23, "total_tokens": 117313624} {"current_steps": 1935, "total_steps": 15680, "loss": 0.31642513275146483, "lr": 9.629302453782462e-06, "epoch": 0.24681122448979592, "percentage": 12.34, "elapsed_time": "7:00:14", "remaining_time": "2 days, 1:45:08", "throughput": 4664.68, "total_tokens": 117618136} {"current_steps": 1940, "total_steps": 15680, "loss": 0.35641942024230955, "lr": 9.62740743420855e-06, "epoch": 0.24744897959183673, "percentage": 12.37, "elapsed_time": "7:01:17", "remaining_time": "2 days, 1:43:47", "throughput": 4664.79, "total_tokens": 117914104} {"current_steps": 1945, "total_steps": 15680, "loss": 0.3540866136550903, "lr": 9.625507770708098e-06, "epoch": 0.24808673469387754, "percentage": 12.4, "elapsed_time": "7:02:13", "remaining_time": "2 days, 1:41:38", "throughput": 4666.59, "total_tokens": 118221680} {"current_steps": 1950, "total_steps": 15680, "loss": 0.3389142036437988, "lr": 9.623603465187554e-06, "epoch": 0.24872448979591838, "percentage": 12.44, "elapsed_time": "7:03:21", "remaining_time": "2 days, 1:40:50", "throughput": 4666.01, "total_tokens": 118522328} {"current_steps": 1955, "total_steps": 15680, "loss": 0.3108387470245361, "lr": 9.621694519558021e-06, "epoch": 0.2493622448979592, "percentage": 12.47, "elapsed_time": "7:04:27", "remaining_time": "2 days, 1:39:55", "throughput": 4665.88, "total_tokens": 118829640} {"current_steps": 1960, "total_steps": 15680, "loss": 0.3287662982940674, "lr": 9.619780935735258e-06, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "7:05:37", "remaining_time": "2 days, 1:39:22", "throughput": 4664.99, "total_tokens": 119132240} {"current_steps": 1965, "total_steps": 15680, "loss": 0.32274279594421384, "lr": 9.617862715639685e-06, "epoch": 0.25063775510204084, "percentage": 12.53, "elapsed_time": "7:06:54", "remaining_time": "2 days, 1:39:37", "throughput": 4662.83, "total_tokens": 119434136} {"current_steps": 1970, "total_steps": 15680, "loss": 0.34737372398376465, "lr": 9.615939861196364e-06, "epoch": 0.2512755102040816, "percentage": 12.56, "elapsed_time": "7:08:05", "remaining_time": "2 days, 1:39:12", "throughput": 4662.51, "total_tokens": 119756744} {"current_steps": 1975, "total_steps": 15680, "loss": 0.3462496757507324, "lr": 9.614012374335014e-06, "epoch": 0.25191326530612246, "percentage": 12.6, "elapsed_time": "7:08:58", "remaining_time": "2 days, 1:36:45", "throughput": 4665.16, "total_tokens": 120074472} {"current_steps": 1980, "total_steps": 15680, "loss": 0.30801560878753664, "lr": 9.612080256990006e-06, "epoch": 0.25255102040816324, "percentage": 12.63, "elapsed_time": "7:09:57", "remaining_time": "2 days, 1:34:55", "throughput": 4666.06, "total_tokens": 120371440} {"current_steps": 1985, "total_steps": 15680, "loss": 0.3369981527328491, "lr": 9.610143511100354e-06, "epoch": 0.2531887755102041, "percentage": 12.66, "elapsed_time": "7:10:58", "remaining_time": "2 days, 1:33:26", "throughput": 4666.43, "total_tokens": 120668168} {"current_steps": 1990, "total_steps": 15680, "loss": 0.3087838411331177, "lr": 9.608202138609714e-06, "epoch": 0.2538265306122449, "percentage": 12.69, "elapsed_time": "7:12:05", "remaining_time": "2 days, 1:32:30", "throughput": 4665.83, "total_tokens": 120962704} {"current_steps": 1995, "total_steps": 15680, "loss": 0.3179054260253906, "lr": 9.606256141466394e-06, "epoch": 0.2544642857142857, "percentage": 12.72, "elapsed_time": "7:13:11", "remaining_time": "2 days, 1:31:33", "throughput": 4665.24, "total_tokens": 121257544} {"current_steps": 2000, "total_steps": 15680, "loss": 0.33051357269287107, "lr": 9.604305521623335e-06, "epoch": 0.25510204081632654, "percentage": 12.76, "elapsed_time": "7:14:17", "remaining_time": "2 days, 1:30:33", "throughput": 4664.99, "total_tokens": 121558016} {"current_steps": 2005, "total_steps": 15680, "loss": 0.3401334762573242, "lr": 9.602350281038123e-06, "epoch": 0.2557397959183674, "percentage": 12.79, "elapsed_time": "7:15:30", "remaining_time": "2 days, 1:30:20", "throughput": 4663.62, "total_tokens": 121861496} {"current_steps": 2010, "total_steps": 15680, "loss": 0.3431340932846069, "lr": 9.600390421672976e-06, "epoch": 0.25637755102040816, "percentage": 12.82, "elapsed_time": "7:16:28", "remaining_time": "2 days, 1:28:28", "throughput": 4664.7, "total_tokens": 122161632} {"current_steps": 2015, "total_steps": 15680, "loss": 0.3796668291091919, "lr": 9.59842594549475e-06, "epoch": 0.257015306122449, "percentage": 12.85, "elapsed_time": "7:17:27", "remaining_time": "2 days, 1:26:43", "throughput": 4666.11, "total_tokens": 122475304} {"current_steps": 2020, "total_steps": 15680, "loss": 0.3507995128631592, "lr": 9.596456854474933e-06, "epoch": 0.2576530612244898, "percentage": 12.88, "elapsed_time": "7:18:32", "remaining_time": "2 days, 1:25:36", "throughput": 4666.37, "total_tokens": 122785040} {"current_steps": 2025, "total_steps": 15680, "loss": 0.3719475746154785, "lr": 9.594483150589647e-06, "epoch": 0.2582908163265306, "percentage": 12.91, "elapsed_time": "7:19:29", "remaining_time": "2 days, 1:23:37", "throughput": 4667.15, "total_tokens": 123072088} {"current_steps": 2030, "total_steps": 15680, "loss": 0.32286806106567384, "lr": 9.592504835819642e-06, "epoch": 0.25892857142857145, "percentage": 12.95, "elapsed_time": "7:20:41", "remaining_time": "2 days, 1:23:19", "throughput": 4665.67, "total_tokens": 123369592} {"current_steps": 2035, "total_steps": 15680, "loss": 0.3350060939788818, "lr": 9.590521912150294e-06, "epoch": 0.25956632653061223, "percentage": 12.98, "elapsed_time": "7:21:58", "remaining_time": "2 days, 1:23:27", "throughput": 4664.01, "total_tokens": 123680416} {"current_steps": 2040, "total_steps": 15680, "loss": 0.3625217914581299, "lr": 9.588534381571606e-06, "epoch": 0.2602040816326531, "percentage": 13.01, "elapsed_time": "7:23:06", "remaining_time": "2 days, 1:22:45", "throughput": 4663.65, "total_tokens": 123991008} {"current_steps": 2045, "total_steps": 15680, "loss": 0.3413558006286621, "lr": 9.586542246078203e-06, "epoch": 0.26084183673469385, "percentage": 13.04, "elapsed_time": "7:24:14", "remaining_time": "2 days, 1:21:57", "throughput": 4663.15, "total_tokens": 124293272} {"current_steps": 2050, "total_steps": 15680, "loss": 0.32697596549987795, "lr": 9.584545507669333e-06, "epoch": 0.2614795918367347, "percentage": 13.07, "elapsed_time": "7:25:22", "remaining_time": "2 days, 1:21:11", "throughput": 4662.8, "total_tokens": 124601432} {"current_steps": 2055, "total_steps": 15680, "loss": 0.32872767448425294, "lr": 9.582544168348864e-06, "epoch": 0.26211734693877553, "percentage": 13.11, "elapsed_time": "7:26:30", "remaining_time": "2 days, 1:20:28", "throughput": 4662.35, "total_tokens": 124908560} {"current_steps": 2060, "total_steps": 15680, "loss": 0.31921873092651365, "lr": 9.580538230125275e-06, "epoch": 0.2627551020408163, "percentage": 13.14, "elapsed_time": "7:27:32", "remaining_time": "2 days, 1:18:57", "throughput": 4662.74, "total_tokens": 125204664} {"current_steps": 2065, "total_steps": 15680, "loss": 0.3307302951812744, "lr": 9.57852769501167e-06, "epoch": 0.26339285714285715, "percentage": 13.17, "elapsed_time": "7:28:34", "remaining_time": "2 days, 1:17:32", "throughput": 4663.16, "total_tokens": 125506080} {"current_steps": 2070, "total_steps": 15680, "loss": 0.3403089284896851, "lr": 9.576512565025759e-06, "epoch": 0.26403061224489793, "percentage": 13.2, "elapsed_time": "7:29:50", "remaining_time": "2 days, 1:17:37", "throughput": 4661.23, "total_tokens": 125807424} {"current_steps": 2075, "total_steps": 15680, "loss": 0.3476198673248291, "lr": 9.574492842189865e-06, "epoch": 0.26466836734693877, "percentage": 13.23, "elapsed_time": "7:30:53", "remaining_time": "2 days, 1:16:22", "throughput": 4661.88, "total_tokens": 126122304} {"current_steps": 2080, "total_steps": 15680, "loss": 0.3389333724975586, "lr": 9.572468528530923e-06, "epoch": 0.2653061224489796, "percentage": 13.27, "elapsed_time": "7:31:58", "remaining_time": "2 days, 1:15:13", "throughput": 4662.08, "total_tokens": 126428616} {"current_steps": 2085, "total_steps": 15680, "loss": 0.3335702419281006, "lr": 9.570439626080472e-06, "epoch": 0.2659438775510204, "percentage": 13.3, "elapsed_time": "7:33:13", "remaining_time": "2 days, 1:15:12", "throughput": 4660.38, "total_tokens": 126732032} {"current_steps": 2090, "total_steps": 15680, "loss": 0.3421825647354126, "lr": 9.568406136874657e-06, "epoch": 0.26658163265306123, "percentage": 13.33, "elapsed_time": "7:34:12", "remaining_time": "2 days, 1:13:25", "throughput": 4661.38, "total_tokens": 127033448} {"current_steps": 2095, "total_steps": 15680, "loss": 0.348024582862854, "lr": 9.566368062954227e-06, "epoch": 0.26721938775510207, "percentage": 13.36, "elapsed_time": "7:35:23", "remaining_time": "2 days, 1:13:00", "throughput": 4660.21, "total_tokens": 127334352} {"current_steps": 2100, "total_steps": 15680, "loss": 0.32784428596496584, "lr": 9.564325406364532e-06, "epoch": 0.26785714285714285, "percentage": 13.39, "elapsed_time": "7:36:31", "remaining_time": "2 days, 1:12:09", "throughput": 4659.5, "total_tokens": 127628856} {"current_steps": 2105, "total_steps": 15680, "loss": 0.31891841888427735, "lr": 9.562278169155518e-06, "epoch": 0.2684948979591837, "percentage": 13.42, "elapsed_time": "7:37:45", "remaining_time": "2 days, 1:12:06", "throughput": 4657.85, "total_tokens": 127932352} {"current_steps": 2110, "total_steps": 15680, "loss": 0.3372203826904297, "lr": 9.560226353381735e-06, "epoch": 0.26913265306122447, "percentage": 13.46, "elapsed_time": "7:38:42", "remaining_time": "2 days, 1:10:04", "throughput": 4658.77, "total_tokens": 128220496} {"current_steps": 2115, "total_steps": 15680, "loss": 0.31939680576324464, "lr": 9.55816996110232e-06, "epoch": 0.2697704081632653, "percentage": 13.49, "elapsed_time": "7:39:47", "remaining_time": "2 days, 1:08:59", "throughput": 4658.51, "total_tokens": 128517880} {"current_steps": 2120, "total_steps": 15680, "loss": 0.3233501434326172, "lr": 9.556108994381007e-06, "epoch": 0.27040816326530615, "percentage": 13.52, "elapsed_time": "7:40:38", "remaining_time": "2 days, 1:06:24", "throughput": 4660.8, "total_tokens": 128818952} {"current_steps": 2125, "total_steps": 15680, "loss": 0.35180096626281737, "lr": 9.55404345528612e-06, "epoch": 0.2710459183673469, "percentage": 13.55, "elapsed_time": "7:41:32", "remaining_time": "2 days, 1:04:07", "throughput": 4662.23, "total_tokens": 129110440} {"current_steps": 2130, "total_steps": 15680, "loss": 0.33643279075622556, "lr": 9.551973345890572e-06, "epoch": 0.27168367346938777, "percentage": 13.58, "elapsed_time": "7:42:26", "remaining_time": "2 days, 1:01:48", "throughput": 4663.91, "total_tokens": 129406776} {"current_steps": 2135, "total_steps": 15680, "loss": 0.37986087799072266, "lr": 9.549898668271862e-06, "epoch": 0.27232142857142855, "percentage": 13.62, "elapsed_time": "7:43:30", "remaining_time": "2 days, 1:00:38", "throughput": 4664.53, "total_tokens": 129723592} {"current_steps": 2140, "total_steps": 15680, "loss": 0.3238245964050293, "lr": 9.547819424512075e-06, "epoch": 0.2729591836734694, "percentage": 13.65, "elapsed_time": "7:44:36", "remaining_time": "2 days, 0:59:36", "throughput": 4664.42, "total_tokens": 130027232} {"current_steps": 2145, "total_steps": 15680, "loss": 0.3344579696655273, "lr": 9.545735616697875e-06, "epoch": 0.2735969387755102, "percentage": 13.68, "elapsed_time": "7:45:41", "remaining_time": "2 days, 0:58:33", "throughput": 4664.37, "total_tokens": 130331312} {"current_steps": 2150, "total_steps": 15680, "loss": 0.32822456359863283, "lr": 9.54364724692051e-06, "epoch": 0.274234693877551, "percentage": 13.71, "elapsed_time": "7:46:55", "remaining_time": "2 days, 0:58:19", "throughput": 4662.92, "total_tokens": 130631744} {"current_steps": 2155, "total_steps": 15680, "loss": 0.33201870918273924, "lr": 9.541554317275807e-06, "epoch": 0.27487244897959184, "percentage": 13.74, "elapsed_time": "7:48:09", "remaining_time": "2 days, 0:58:12", "throughput": 4661.24, "total_tokens": 130932192} {"current_steps": 2160, "total_steps": 15680, "loss": 0.3319772005081177, "lr": 9.539456829864164e-06, "epoch": 0.2755102040816326, "percentage": 13.78, "elapsed_time": "7:49:16", "remaining_time": "2 days, 0:57:17", "throughput": 4661.01, "total_tokens": 131236424} {"current_steps": 2165, "total_steps": 15680, "loss": 0.3271048069000244, "lr": 9.537354786790558e-06, "epoch": 0.27614795918367346, "percentage": 13.81, "elapsed_time": "7:50:20", "remaining_time": "2 days, 0:56:05", "throughput": 4661.12, "total_tokens": 131538720} {"current_steps": 2170, "total_steps": 15680, "loss": 0.3490221261978149, "lr": 9.535248190164537e-06, "epoch": 0.2767857142857143, "percentage": 13.84, "elapsed_time": "7:51:13", "remaining_time": "2 days, 0:53:43", "throughput": 4663.32, "total_tokens": 131847192} {"current_steps": 2175, "total_steps": 15680, "loss": 0.3301276206970215, "lr": 9.533137042100214e-06, "epoch": 0.2774234693877551, "percentage": 13.87, "elapsed_time": "7:52:18", "remaining_time": "2 days, 0:52:40", "throughput": 4663.35, "total_tokens": 132153528} {"current_steps": 2180, "total_steps": 15680, "loss": 0.34771027565002444, "lr": 9.531021344716275e-06, "epoch": 0.2780612244897959, "percentage": 13.9, "elapsed_time": "7:53:20", "remaining_time": "2 days, 0:51:14", "throughput": 4663.88, "total_tokens": 132455944} {"current_steps": 2185, "total_steps": 15680, "loss": 0.32829039096832274, "lr": 9.528901100135971e-06, "epoch": 0.27869897959183676, "percentage": 13.93, "elapsed_time": "7:54:29", "remaining_time": "2 days, 0:50:33", "throughput": 4663.08, "total_tokens": 132755232} {"current_steps": 2190, "total_steps": 15680, "loss": 0.3137925863265991, "lr": 9.526776310487116e-06, "epoch": 0.27933673469387754, "percentage": 13.97, "elapsed_time": "7:55:26", "remaining_time": "2 days, 0:48:40", "throughput": 4664.35, "total_tokens": 133059576} {"current_steps": 2195, "total_steps": 15680, "loss": 0.33733036518096926, "lr": 9.524646977902083e-06, "epoch": 0.2799744897959184, "percentage": 14.0, "elapsed_time": "7:56:35", "remaining_time": "2 days, 0:47:56", "throughput": 4663.83, "total_tokens": 133364448} {"current_steps": 2200, "total_steps": 15680, "loss": 0.34655616283416746, "lr": 9.522513104517807e-06, "epoch": 0.28061224489795916, "percentage": 14.03, "elapsed_time": "7:57:20", "remaining_time": "2 days, 0:44:50", "throughput": 4667.14, "total_tokens": 133671040} {"current_steps": 2205, "total_steps": 15680, "loss": 0.3232752561569214, "lr": 9.52037469247578e-06, "epoch": 0.28125, "percentage": 14.06, "elapsed_time": "7:58:14", "remaining_time": "2 days, 0:42:32", "throughput": 4668.85, "total_tokens": 133967984} {"current_steps": 2210, "total_steps": 15680, "loss": 0.3547585248947144, "lr": 9.518231743922049e-06, "epoch": 0.28188775510204084, "percentage": 14.09, "elapsed_time": "7:59:16", "remaining_time": "2 days, 0:41:14", "throughput": 4668.97, "total_tokens": 134265280} {"current_steps": 2215, "total_steps": 15680, "loss": 0.344525146484375, "lr": 9.516084261007207e-06, "epoch": 0.2825255102040816, "percentage": 14.13, "elapsed_time": "8:00:15", "remaining_time": "2 days, 0:39:32", "throughput": 4670.44, "total_tokens": 134583128} {"current_steps": 2220, "total_steps": 15680, "loss": 0.32808513641357423, "lr": 9.513932245886409e-06, "epoch": 0.28316326530612246, "percentage": 14.16, "elapsed_time": "8:01:15", "remaining_time": "2 days, 0:37:52", "throughput": 4671.04, "total_tokens": 134877664} {"current_steps": 2225, "total_steps": 15680, "loss": 0.3475784778594971, "lr": 9.511775700719347e-06, "epoch": 0.28380102040816324, "percentage": 14.19, "elapsed_time": "8:02:18", "remaining_time": "2 days, 0:36:34", "throughput": 4670.75, "total_tokens": 135163120} {"current_steps": 2230, "total_steps": 15680, "loss": 0.33773374557495117, "lr": 9.50961462767027e-06, "epoch": 0.2844387755102041, "percentage": 14.22, "elapsed_time": "8:03:16", "remaining_time": "2 days, 0:34:48", "throughput": 4672.15, "total_tokens": 135475328} {"current_steps": 2235, "total_steps": 15680, "loss": 0.3306095123291016, "lr": 9.507449028907961e-06, "epoch": 0.2850765306122449, "percentage": 14.25, "elapsed_time": "8:04:31", "remaining_time": "2 days, 0:34:46", "throughput": 4670.69, "total_tokens": 135785712} {"current_steps": 2240, "total_steps": 15680, "loss": 0.34046273231506347, "lr": 9.505278906605752e-06, "epoch": 0.2857142857142857, "percentage": 14.29, "elapsed_time": "8:05:32", "remaining_time": "2 days, 0:33:14", "throughput": 4671.15, "total_tokens": 136081960} {"current_steps": 2245, "total_steps": 15680, "loss": 0.30557568073272706, "lr": 9.503104262941515e-06, "epoch": 0.28635204081632654, "percentage": 14.32, "elapsed_time": "8:06:33", "remaining_time": "2 days, 0:31:43", "throughput": 4672.1, "total_tokens": 136392784} {"current_steps": 2250, "total_steps": 15680, "loss": 0.3169878005981445, "lr": 9.500925100097652e-06, "epoch": 0.2869897959183674, "percentage": 14.35, "elapsed_time": "8:07:34", "remaining_time": "2 days, 0:30:17", "throughput": 4673.02, "total_tokens": 136707440} {"current_steps": 2255, "total_steps": 15680, "loss": 0.3424893856048584, "lr": 9.498741420261109e-06, "epoch": 0.28762755102040816, "percentage": 14.38, "elapsed_time": "8:08:40", "remaining_time": "2 days, 0:29:18", "throughput": 4673.02, "total_tokens": 137016104} {"current_steps": 2260, "total_steps": 15680, "loss": 0.34136936664581297, "lr": 9.496553225623358e-06, "epoch": 0.288265306122449, "percentage": 14.41, "elapsed_time": "8:09:47", "remaining_time": "2 days, 0:28:22", "throughput": 4672.77, "total_tokens": 137319680} {"current_steps": 2265, "total_steps": 15680, "loss": 0.3330190896987915, "lr": 9.494360518380405e-06, "epoch": 0.2889030612244898, "percentage": 14.45, "elapsed_time": "8:10:59", "remaining_time": "2 days, 0:27:58", "throughput": 4671.49, "total_tokens": 137617704} {"current_steps": 2270, "total_steps": 15680, "loss": 0.3248729705810547, "lr": 9.49216330073279e-06, "epoch": 0.2895408163265306, "percentage": 14.48, "elapsed_time": "8:12:05", "remaining_time": "2 days, 0:27:01", "throughput": 4671.0, "total_tokens": 137913424} {"current_steps": 2275, "total_steps": 15680, "loss": 0.3313121795654297, "lr": 9.489961574885567e-06, "epoch": 0.29017857142857145, "percentage": 14.51, "elapsed_time": "8:13:12", "remaining_time": "2 days, 0:26:08", "throughput": 4670.67, "total_tokens": 138217224} {"current_steps": 2280, "total_steps": 15680, "loss": 0.33457436561584475, "lr": 9.487755343048328e-06, "epoch": 0.29081632653061223, "percentage": 14.54, "elapsed_time": "8:14:19", "remaining_time": "2 days, 0:25:15", "throughput": 4670.03, "total_tokens": 138511400} {"current_steps": 2285, "total_steps": 15680, "loss": 0.33912661075592043, "lr": 9.485544607435177e-06, "epoch": 0.2914540816326531, "percentage": 14.57, "elapsed_time": "8:15:25", "remaining_time": "2 days, 0:24:17", "throughput": 4669.51, "total_tokens": 138805184} {"current_steps": 2290, "total_steps": 15680, "loss": 0.33886494636535647, "lr": 9.483329370264743e-06, "epoch": 0.29209183673469385, "percentage": 14.6, "elapsed_time": "8:16:35", "remaining_time": "2 days, 0:23:37", "throughput": 4668.43, "total_tokens": 139096920} {"current_steps": 2295, "total_steps": 15680, "loss": 0.3412975549697876, "lr": 9.48110963376017e-06, "epoch": 0.2927295918367347, "percentage": 14.64, "elapsed_time": "8:17:48", "remaining_time": "2 days, 0:23:19", "throughput": 4666.85, "total_tokens": 139391024} {"current_steps": 2300, "total_steps": 15680, "loss": 0.3495046615600586, "lr": 9.47888540014912e-06, "epoch": 0.29336734693877553, "percentage": 14.67, "elapsed_time": "8:18:53", "remaining_time": "2 days, 0:22:13", "throughput": 4666.94, "total_tokens": 139696504} {"current_steps": 2305, "total_steps": 15680, "loss": 0.32523541450500487, "lr": 9.476656671663766e-06, "epoch": 0.2940051020408163, "percentage": 14.7, "elapsed_time": "8:20:02", "remaining_time": "2 days, 0:21:34", "throughput": 4666.01, "total_tokens": 139993480} {"current_steps": 2310, "total_steps": 15680, "loss": 0.31680908203125, "lr": 9.474423450540794e-06, "epoch": 0.29464285714285715, "percentage": 14.73, "elapsed_time": "8:21:03", "remaining_time": "2 days, 0:20:03", "throughput": 4666.58, "total_tokens": 140293864} {"current_steps": 2315, "total_steps": 15680, "loss": 0.35444614887237547, "lr": 9.472185739021396e-06, "epoch": 0.29528061224489793, "percentage": 14.76, "elapsed_time": "8:22:03", "remaining_time": "2 days, 0:18:30", "throughput": 4667.59, "total_tokens": 140604936} {"current_steps": 2320, "total_steps": 15680, "loss": 0.3213543653488159, "lr": 9.469943539351272e-06, "epoch": 0.29591836734693877, "percentage": 14.8, "elapsed_time": "8:23:07", "remaining_time": "2 days, 0:17:18", "throughput": 4667.62, "total_tokens": 140904200} {"current_steps": 2325, "total_steps": 15680, "loss": 0.34745540618896487, "lr": 9.467696853780625e-06, "epoch": 0.2965561224489796, "percentage": 14.83, "elapsed_time": "8:24:14", "remaining_time": "2 days, 0:16:25", "throughput": 4667.22, "total_tokens": 141205224} {"current_steps": 2330, "total_steps": 15680, "loss": 0.35611257553100584, "lr": 9.465445684564165e-06, "epoch": 0.2971938775510204, "percentage": 14.86, "elapsed_time": "8:25:28", "remaining_time": "2 days, 0:16:12", "throughput": 4665.95, "total_tokens": 141513120} {"current_steps": 2335, "total_steps": 15680, "loss": 0.3520667314529419, "lr": 9.463190033961092e-06, "epoch": 0.29783163265306123, "percentage": 14.89, "elapsed_time": "8:26:38", "remaining_time": "2 days, 0:15:35", "throughput": 4665.38, "total_tokens": 141822048} {"current_steps": 2340, "total_steps": 15680, "loss": 0.3467228889465332, "lr": 9.46092990423511e-06, "epoch": 0.29846938775510207, "percentage": 14.92, "elapsed_time": "8:27:39", "remaining_time": "2 days, 0:14:06", "throughput": 4666.1, "total_tokens": 142127800} {"current_steps": 2345, "total_steps": 15680, "loss": 0.33246798515319825, "lr": 9.45866529765442e-06, "epoch": 0.29910714285714285, "percentage": 14.96, "elapsed_time": "8:28:42", "remaining_time": "2 days, 0:12:45", "throughput": 4667.01, "total_tokens": 142446600} {"current_steps": 2350, "total_steps": 15680, "loss": 0.34263951778411866, "lr": 9.456396216491713e-06, "epoch": 0.2997448979591837, "percentage": 14.99, "elapsed_time": "8:29:47", "remaining_time": "2 days, 0:11:42", "throughput": 4667.15, "total_tokens": 142756616} {"current_steps": 2355, "total_steps": 15680, "loss": 0.3423199415206909, "lr": 9.454122663024167e-06, "epoch": 0.30038265306122447, "percentage": 15.02, "elapsed_time": "8:30:58", "remaining_time": "2 days, 0:11:10", "throughput": 4666.24, "total_tokens": 143058944} {"current_steps": 2360, "total_steps": 15680, "loss": 0.320352840423584, "lr": 9.451844639533453e-06, "epoch": 0.3010204081632653, "percentage": 15.05, "elapsed_time": "8:32:09", "remaining_time": "2 days, 0:10:37", "throughput": 4665.33, "total_tokens": 143361264} {"current_steps": 2365, "total_steps": 15680, "loss": 0.3393766641616821, "lr": 9.44956214830573e-06, "epoch": 0.30165816326530615, "percentage": 15.08, "elapsed_time": "8:33:13", "remaining_time": "2 days, 0:09:28", "throughput": 4665.47, "total_tokens": 143666552} {"current_steps": 2370, "total_steps": 15680, "loss": 0.3327906608581543, "lr": 9.447275191631631e-06, "epoch": 0.3022959183673469, "percentage": 15.11, "elapsed_time": "8:34:08", "remaining_time": "2 days, 0:07:28", "throughput": 4667.24, "total_tokens": 143979752} {"current_steps": 2375, "total_steps": 15680, "loss": 0.3404208183288574, "lr": 9.444983771806281e-06, "epoch": 0.30293367346938777, "percentage": 15.15, "elapsed_time": "8:34:59", "remaining_time": "2 days, 0:05:02", "throughput": 4669.65, "total_tokens": 144290592} {"current_steps": 2380, "total_steps": 15680, "loss": 0.30806612968444824, "lr": 9.44268789112928e-06, "epoch": 0.30357142857142855, "percentage": 15.18, "elapsed_time": "8:36:11", "remaining_time": "2 days, 0:04:37", "throughput": 4668.43, "total_tokens": 144589824} {"current_steps": 2385, "total_steps": 15680, "loss": 0.3120733261108398, "lr": 9.440387551904705e-06, "epoch": 0.3042091836734694, "percentage": 15.21, "elapsed_time": "8:37:13", "remaining_time": "2 days, 0:03:11", "throughput": 4669.06, "total_tokens": 144895296} {"current_steps": 2390, "total_steps": 15680, "loss": 0.3376578092575073, "lr": 9.438082756441103e-06, "epoch": 0.3048469387755102, "percentage": 15.24, "elapsed_time": "8:38:12", "remaining_time": "2 days, 0:01:35", "throughput": 4670.01, "total_tokens": 145203024} {"current_steps": 2395, "total_steps": 15680, "loss": 0.33997819423675535, "lr": 9.4357735070515e-06, "epoch": 0.305484693877551, "percentage": 15.27, "elapsed_time": "8:39:22", "remaining_time": "2 days, 0:00:55", "throughput": 4669.68, "total_tokens": 145517392} {"current_steps": 2400, "total_steps": 15680, "loss": 0.3264634132385254, "lr": 9.433459806053392e-06, "epoch": 0.30612244897959184, "percentage": 15.31, "elapsed_time": "8:40:24", "remaining_time": "1 day, 23:59:33", "throughput": 4669.81, "total_tokens": 145811144} {"current_steps": 2405, "total_steps": 15680, "loss": 0.347784423828125, "lr": 9.431141655768733e-06, "epoch": 0.3067602040816326, "percentage": 15.34, "elapsed_time": "8:41:24", "remaining_time": "1 day, 23:58:02", "throughput": 4670.57, "total_tokens": 146115888} {"current_steps": 2410, "total_steps": 15680, "loss": 0.3411884784698486, "lr": 9.428819058523953e-06, "epoch": 0.30739795918367346, "percentage": 15.37, "elapsed_time": "8:42:39", "remaining_time": "1 day, 23:57:50", "throughput": 4669.07, "total_tokens": 146418576} {"current_steps": 2415, "total_steps": 15680, "loss": 0.33095855712890626, "lr": 9.42649201664994e-06, "epoch": 0.3080357142857143, "percentage": 15.4, "elapsed_time": "8:43:43", "remaining_time": "1 day, 23:56:40", "throughput": 4668.95, "total_tokens": 146713496} {"current_steps": 2420, "total_steps": 15680, "loss": 0.3445183277130127, "lr": 9.424160532482042e-06, "epoch": 0.3086734693877551, "percentage": 15.43, "elapsed_time": "8:44:41", "remaining_time": "1 day, 23:54:58", "throughput": 4670.19, "total_tokens": 147025448} {"current_steps": 2425, "total_steps": 15680, "loss": 0.35089085102081297, "lr": 9.421824608360068e-06, "epoch": 0.3093112244897959, "percentage": 15.47, "elapsed_time": "8:45:46", "remaining_time": "1 day, 23:53:49", "throughput": 4670.44, "total_tokens": 147333872} {"current_steps": 2430, "total_steps": 15680, "loss": 0.32887113094329834, "lr": 9.419484246628279e-06, "epoch": 0.30994897959183676, "percentage": 15.5, "elapsed_time": "8:46:49", "remaining_time": "1 day, 23:52:36", "throughput": 4670.56, "total_tokens": 147634248} {"current_steps": 2435, "total_steps": 15680, "loss": 0.33138527870178225, "lr": 9.417139449635394e-06, "epoch": 0.31058673469387754, "percentage": 15.53, "elapsed_time": "8:48:00", "remaining_time": "1 day, 23:52:04", "throughput": 4669.23, "total_tokens": 147924552} {"current_steps": 2440, "total_steps": 15680, "loss": 0.32412359714508054, "lr": 9.414790219734578e-06, "epoch": 0.3112244897959184, "percentage": 15.56, "elapsed_time": "8:49:05", "remaining_time": "1 day, 23:50:59", "throughput": 4669.4, "total_tokens": 148233704} {"current_steps": 2445, "total_steps": 15680, "loss": 0.32866530418395995, "lr": 9.41243655928345e-06, "epoch": 0.31186224489795916, "percentage": 15.59, "elapsed_time": "8:49:53", "remaining_time": "1 day, 23:48:21", "throughput": 4671.83, "total_tokens": 148534120} {"current_steps": 2450, "total_steps": 15680, "loss": 0.3428959846496582, "lr": 9.410078470644069e-06, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "8:51:10", "remaining_time": "1 day, 23:48:19", "throughput": 4669.82, "total_tokens": 148828048} {"current_steps": 2455, "total_steps": 15680, "loss": 0.3676748275756836, "lr": 9.407715956182942e-06, "epoch": 0.31313775510204084, "percentage": 15.66, "elapsed_time": "8:52:23", "remaining_time": "1 day, 23:47:56", "throughput": 4668.83, "total_tokens": 149136848} {"current_steps": 2460, "total_steps": 15680, "loss": 0.30690693855285645, "lr": 9.405349018271021e-06, "epoch": 0.3137755102040816, "percentage": 15.69, "elapsed_time": "8:53:26", "remaining_time": "1 day, 23:46:40", "throughput": 4669.29, "total_tokens": 149445896} {"current_steps": 2465, "total_steps": 15680, "loss": 0.35631861686706545, "lr": 9.40297765928369e-06, "epoch": 0.31441326530612246, "percentage": 15.72, "elapsed_time": "8:54:31", "remaining_time": "1 day, 23:45:39", "throughput": 4669.06, "total_tokens": 149745824} {"current_steps": 2470, "total_steps": 15680, "loss": 0.3548426628112793, "lr": 9.400601881600776e-06, "epoch": 0.31505102040816324, "percentage": 15.75, "elapsed_time": "8:55:41", "remaining_time": "1 day, 23:44:57", "throughput": 4668.48, "total_tokens": 150051240} {"current_steps": 2475, "total_steps": 15680, "loss": 0.30653972625732423, "lr": 9.398221687606535e-06, "epoch": 0.3156887755102041, "percentage": 15.78, "elapsed_time": "8:56:43", "remaining_time": "1 day, 23:43:36", "throughput": 4668.82, "total_tokens": 150352384} {"current_steps": 2480, "total_steps": 15680, "loss": 0.3408294439315796, "lr": 9.395837079689661e-06, "epoch": 0.3163265306122449, "percentage": 15.82, "elapsed_time": "8:57:56", "remaining_time": "1 day, 23:43:14", "throughput": 4667.37, "total_tokens": 150646432} {"current_steps": 2485, "total_steps": 15680, "loss": 0.33505294322967527, "lr": 9.393448060243272e-06, "epoch": 0.3169642857142857, "percentage": 15.85, "elapsed_time": "8:59:10", "remaining_time": "1 day, 23:42:54", "throughput": 4665.86, "total_tokens": 150940672} {"current_steps": 2490, "total_steps": 15680, "loss": 0.31870713233947756, "lr": 9.391054631664918e-06, "epoch": 0.31760204081632654, "percentage": 15.88, "elapsed_time": "9:00:13", "remaining_time": "1 day, 23:41:39", "throughput": 4666.1, "total_tokens": 151244112} {"current_steps": 2495, "total_steps": 15680, "loss": 0.3533759117126465, "lr": 9.388656796356569e-06, "epoch": 0.3182397959183674, "percentage": 15.91, "elapsed_time": "9:01:26", "remaining_time": "1 day, 23:41:16", "throughput": 4664.83, "total_tokens": 151543264} {"current_steps": 2500, "total_steps": 15680, "loss": 0.33388419151306153, "lr": 9.386254556724622e-06, "epoch": 0.31887755102040816, "percentage": 15.94, "elapsed_time": "9:02:24", "remaining_time": "1 day, 23:39:35", "throughput": 4665.4, "total_tokens": 151833704} {"current_steps": 2505, "total_steps": 15680, "loss": 0.2864094257354736, "lr": 9.383847915179892e-06, "epoch": 0.319515306122449, "percentage": 15.98, "elapsed_time": "9:03:27", "remaining_time": "1 day, 23:38:18", "throughput": 4665.51, "total_tokens": 152130248} {"current_steps": 2510, "total_steps": 15680, "loss": 0.3475051403045654, "lr": 9.381436874137613e-06, "epoch": 0.3201530612244898, "percentage": 16.01, "elapsed_time": "9:04:33", "remaining_time": "1 day, 23:37:17", "throughput": 4665.64, "total_tokens": 152442352} {"current_steps": 2515, "total_steps": 15680, "loss": 0.3537461757659912, "lr": 9.37902143601743e-06, "epoch": 0.3207908163265306, "percentage": 16.04, "elapsed_time": "9:05:19", "remaining_time": "1 day, 23:34:34", "throughput": 4668.75, "total_tokens": 152760032} {"current_steps": 2520, "total_steps": 15680, "loss": 0.348602819442749, "lr": 9.376601603243408e-06, "epoch": 0.32142857142857145, "percentage": 16.07, "elapsed_time": "9:06:10", "remaining_time": "1 day, 23:32:15", "throughput": 4670.91, "total_tokens": 153068600} {"current_steps": 2525, "total_steps": 15680, "loss": 0.3363666534423828, "lr": 9.374177378244014e-06, "epoch": 0.32206632653061223, "percentage": 16.1, "elapsed_time": "9:07:29", "remaining_time": "1 day, 23:32:24", "throughput": 4669.05, "total_tokens": 153377984} {"current_steps": 2530, "total_steps": 15680, "loss": 0.3585888624191284, "lr": 9.37174876345213e-06, "epoch": 0.3227040816326531, "percentage": 16.14, "elapsed_time": "9:08:34", "remaining_time": "1 day, 23:31:14", "throughput": 4669.41, "total_tokens": 153689064} {"current_steps": 2535, "total_steps": 15680, "loss": 0.31468565464019777, "lr": 9.369315761305039e-06, "epoch": 0.32334183673469385, "percentage": 16.17, "elapsed_time": "9:09:39", "remaining_time": "1 day, 23:30:12", "throughput": 4669.09, "total_tokens": 153984552} {"current_steps": 2540, "total_steps": 15680, "loss": 0.34476327896118164, "lr": 9.36687837424443e-06, "epoch": 0.3239795918367347, "percentage": 16.2, "elapsed_time": "9:10:54", "remaining_time": "1 day, 23:29:59", "throughput": 4667.64, "total_tokens": 154287496} {"current_steps": 2545, "total_steps": 15680, "loss": 0.3406651973724365, "lr": 9.364436604716389e-06, "epoch": 0.32461734693877553, "percentage": 16.23, "elapsed_time": "9:12:03", "remaining_time": "1 day, 23:29:14", "throughput": 4666.91, "total_tokens": 154585272} {"current_steps": 2550, "total_steps": 15680, "loss": 0.3554771661758423, "lr": 9.361990455171405e-06, "epoch": 0.3252551020408163, "percentage": 16.26, "elapsed_time": "9:13:12", "remaining_time": "1 day, 23:28:28", "throughput": 4666.32, "total_tokens": 154886344} {"current_steps": 2555, "total_steps": 15680, "loss": 0.32879574298858644, "lr": 9.359539928064358e-06, "epoch": 0.32589285714285715, "percentage": 16.29, "elapsed_time": "9:14:25", "remaining_time": "1 day, 23:28:04", "throughput": 4665.02, "total_tokens": 155183904} {"current_steps": 2560, "total_steps": 15680, "loss": 0.32778658866882326, "lr": 9.357085025854525e-06, "epoch": 0.32653061224489793, "percentage": 16.33, "elapsed_time": "9:15:27", "remaining_time": "1 day, 23:26:41", "throughput": 4665.25, "total_tokens": 155479896} {"current_steps": 2565, "total_steps": 15680, "loss": 0.3326746702194214, "lr": 9.354625751005568e-06, "epoch": 0.32716836734693877, "percentage": 16.36, "elapsed_time": "9:16:32", "remaining_time": "1 day, 23:25:35", "throughput": 4664.86, "total_tokens": 155769320} {"current_steps": 2570, "total_steps": 15680, "loss": 0.3629491090774536, "lr": 9.352162105985544e-06, "epoch": 0.3278061224489796, "percentage": 16.39, "elapsed_time": "9:17:41", "remaining_time": "1 day, 23:24:54", "throughput": 4664.11, "total_tokens": 156069912} {"current_steps": 2575, "total_steps": 15680, "loss": 0.35565996170043945, "lr": 9.349694093266893e-06, "epoch": 0.3284438775510204, "percentage": 16.42, "elapsed_time": "9:18:42", "remaining_time": "1 day, 23:23:25", "throughput": 4665.03, "total_tokens": 156382408} {"current_steps": 2580, "total_steps": 15680, "loss": 0.31146578788757323, "lr": 9.347221715326437e-06, "epoch": 0.32908163265306123, "percentage": 16.45, "elapsed_time": "9:19:47", "remaining_time": "1 day, 23:22:19", "throughput": 4664.94, "total_tokens": 156682336} {"current_steps": 2585, "total_steps": 15680, "loss": 0.3354040145874023, "lr": 9.344744974645382e-06, "epoch": 0.32971938775510207, "percentage": 16.49, "elapsed_time": "9:20:59", "remaining_time": "1 day, 23:21:53", "throughput": 4664.0, "total_tokens": 156989784} {"current_steps": 2590, "total_steps": 15680, "loss": 0.3347164630889893, "lr": 9.342263873709307e-06, "epoch": 0.33035714285714285, "percentage": 16.52, "elapsed_time": "9:22:06", "remaining_time": "1 day, 23:20:56", "throughput": 4663.68, "total_tokens": 157290608} {"current_steps": 2595, "total_steps": 15680, "loss": 0.33094253540039065, "lr": 9.339778415008171e-06, "epoch": 0.3309948979591837, "percentage": 16.55, "elapsed_time": "9:23:04", "remaining_time": "1 day, 23:19:15", "throughput": 4664.73, "total_tokens": 157596152} {"current_steps": 2600, "total_steps": 15680, "loss": 0.31957478523254396, "lr": 9.337288601036307e-06, "epoch": 0.33163265306122447, "percentage": 16.58, "elapsed_time": "9:23:56", "remaining_time": "1 day, 23:17:03", "throughput": 4666.77, "total_tokens": 157906568} {"current_steps": 2605, "total_steps": 15680, "loss": 0.35186176300048827, "lr": 9.334794434292416e-06, "epoch": 0.3322704081632653, "percentage": 16.61, "elapsed_time": "9:24:55", "remaining_time": "1 day, 23:15:28", "throughput": 4667.89, "total_tokens": 158220672} {"current_steps": 2610, "total_steps": 15680, "loss": 0.3774047136306763, "lr": 9.33229591727957e-06, "epoch": 0.33290816326530615, "percentage": 16.65, "elapsed_time": "9:26:06", "remaining_time": "1 day, 23:14:54", "throughput": 4667.26, "total_tokens": 158532136} {"current_steps": 2615, "total_steps": 15680, "loss": 0.31768646240234377, "lr": 9.329793052505203e-06, "epoch": 0.3335459183673469, "percentage": 16.68, "elapsed_time": "9:27:16", "remaining_time": "1 day, 23:14:10", "throughput": 4666.24, "total_tokens": 158820376} {"current_steps": 2620, "total_steps": 15680, "loss": 0.32222609519958495, "lr": 9.327285842481114e-06, "epoch": 0.33418367346938777, "percentage": 16.71, "elapsed_time": "9:28:23", "remaining_time": "1 day, 23:13:15", "throughput": 4665.8, "total_tokens": 159119232} {"current_steps": 2625, "total_steps": 15680, "loss": 0.33108365535736084, "lr": 9.324774289723469e-06, "epoch": 0.33482142857142855, "percentage": 16.74, "elapsed_time": "9:29:24", "remaining_time": "1 day, 23:11:53", "throughput": 4666.29, "total_tokens": 159423616} {"current_steps": 2630, "total_steps": 15680, "loss": 0.311852240562439, "lr": 9.322258396752781e-06, "epoch": 0.3354591836734694, "percentage": 16.77, "elapsed_time": "9:30:26", "remaining_time": "1 day, 23:10:29", "throughput": 4666.87, "total_tokens": 159729448} {"current_steps": 2635, "total_steps": 15680, "loss": 0.33764641284942626, "lr": 9.319738166093925e-06, "epoch": 0.3360969387755102, "percentage": 16.8, "elapsed_time": "9:31:31", "remaining_time": "1 day, 23:09:24", "throughput": 4666.97, "total_tokens": 160035936} {"current_steps": 2640, "total_steps": 15680, "loss": 0.35221052169799805, "lr": 9.31721360027613e-06, "epoch": 0.336734693877551, "percentage": 16.84, "elapsed_time": "9:32:26", "remaining_time": "1 day, 23:07:32", "throughput": 4668.39, "total_tokens": 160344704} {"current_steps": 2645, "total_steps": 15680, "loss": 0.3359955072402954, "lr": 9.314684701832974e-06, "epoch": 0.33737244897959184, "percentage": 16.87, "elapsed_time": "9:33:25", "remaining_time": "1 day, 23:05:55", "throughput": 4669.49, "total_tokens": 160656000} {"current_steps": 2650, "total_steps": 15680, "loss": 0.3358307838439941, "lr": 9.312151473302381e-06, "epoch": 0.3380102040816326, "percentage": 16.9, "elapsed_time": "9:34:19", "remaining_time": "1 day, 23:03:56", "throughput": 4671.46, "total_tokens": 160975440} {"current_steps": 2655, "total_steps": 15680, "loss": 0.32498579025268554, "lr": 9.309613917226627e-06, "epoch": 0.33864795918367346, "percentage": 16.93, "elapsed_time": "9:35:13", "remaining_time": "1 day, 23:01:58", "throughput": 4673.13, "total_tokens": 161287256} {"current_steps": 2660, "total_steps": 15680, "loss": 0.3317585468292236, "lr": 9.307072036152324e-06, "epoch": 0.3392857142857143, "percentage": 16.96, "elapsed_time": "9:36:09", "remaining_time": "1 day, 23:00:06", "throughput": 4674.43, "total_tokens": 161591088} {"current_steps": 2665, "total_steps": 15680, "loss": 0.35298595428466795, "lr": 9.304525832630426e-06, "epoch": 0.3399234693877551, "percentage": 17.0, "elapsed_time": "9:36:55", "remaining_time": "1 day, 22:57:31", "throughput": 4677.07, "total_tokens": 161899864} {"current_steps": 2670, "total_steps": 15680, "loss": 0.3207338809967041, "lr": 9.30197530921623e-06, "epoch": 0.3405612244897959, "percentage": 17.03, "elapsed_time": "9:37:54", "remaining_time": "1 day, 22:55:55", "throughput": 4677.57, "total_tokens": 162190664} {"current_steps": 2675, "total_steps": 15680, "loss": 0.36296284198760986, "lr": 9.29942046846936e-06, "epoch": 0.34119897959183676, "percentage": 17.06, "elapsed_time": "9:38:56", "remaining_time": "1 day, 22:54:38", "throughput": 4677.86, "total_tokens": 162492848} {"current_steps": 2680, "total_steps": 15680, "loss": 0.34287004470825194, "lr": 9.29686131295378e-06, "epoch": 0.34183673469387754, "percentage": 17.09, "elapsed_time": "9:40:00", "remaining_time": "1 day, 22:53:28", "throughput": 4678.09, "total_tokens": 162799640} {"current_steps": 2685, "total_steps": 15680, "loss": 0.32772340774536135, "lr": 9.294297845237778e-06, "epoch": 0.3424744897959184, "percentage": 17.12, "elapsed_time": "9:41:10", "remaining_time": "1 day, 22:52:47", "throughput": 4677.06, "total_tokens": 163091384} {"current_steps": 2690, "total_steps": 15680, "loss": 0.33747942447662355, "lr": 9.291730067893978e-06, "epoch": 0.34311224489795916, "percentage": 17.16, "elapsed_time": "9:42:16", "remaining_time": "1 day, 22:51:47", "throughput": 4677.32, "total_tokens": 163408824} {"current_steps": 2695, "total_steps": 15680, "loss": 0.34053735733032225, "lr": 9.28915798349932e-06, "epoch": 0.34375, "percentage": 17.19, "elapsed_time": "9:43:16", "remaining_time": "1 day, 22:50:17", "throughput": 4678.01, "total_tokens": 163712008} {"current_steps": 2700, "total_steps": 15680, "loss": 0.3610675573348999, "lr": 9.28658159463507e-06, "epoch": 0.34438775510204084, "percentage": 17.22, "elapsed_time": "9:44:18", "remaining_time": "1 day, 22:49:00", "throughput": 4678.5, "total_tokens": 164021160} {"current_steps": 2705, "total_steps": 15680, "loss": 0.3434394598007202, "lr": 9.284000903886818e-06, "epoch": 0.3450255102040816, "percentage": 17.25, "elapsed_time": "9:45:24", "remaining_time": "1 day, 22:48:00", "throughput": 4678.38, "total_tokens": 164325600} {"current_steps": 2710, "total_steps": 15680, "loss": 0.3025984287261963, "lr": 9.281415913844465e-06, "epoch": 0.34566326530612246, "percentage": 17.28, "elapsed_time": "9:46:27", "remaining_time": "1 day, 22:46:45", "throughput": 4678.36, "total_tokens": 164618672} {"current_steps": 2715, "total_steps": 15680, "loss": 0.32732648849487306, "lr": 9.278826627102228e-06, "epoch": 0.34630102040816324, "percentage": 17.32, "elapsed_time": "9:47:39", "remaining_time": "1 day, 22:46:17", "throughput": 4677.22, "total_tokens": 164918320} {"current_steps": 2720, "total_steps": 15680, "loss": 0.35390415191650393, "lr": 9.276233046258637e-06, "epoch": 0.3469387755102041, "percentage": 17.35, "elapsed_time": "9:48:51", "remaining_time": "1 day, 22:45:44", "throughput": 4676.31, "total_tokens": 165221192} {"current_steps": 2725, "total_steps": 15680, "loss": 0.3319819927215576, "lr": 9.273635173916535e-06, "epoch": 0.3475765306122449, "percentage": 17.38, "elapsed_time": "9:50:02", "remaining_time": "1 day, 22:45:07", "throughput": 4675.37, "total_tokens": 165519432} {"current_steps": 2730, "total_steps": 15680, "loss": 0.32244267463684084, "lr": 9.271033012683063e-06, "epoch": 0.3482142857142857, "percentage": 17.41, "elapsed_time": "9:51:08", "remaining_time": "1 day, 22:44:07", "throughput": 4675.01, "total_tokens": 165814768} {"current_steps": 2735, "total_steps": 15680, "loss": 0.36324148178100585, "lr": 9.268426565169677e-06, "epoch": 0.34885204081632654, "percentage": 17.44, "elapsed_time": "9:52:19", "remaining_time": "1 day, 22:43:30", "throughput": 4674.22, "total_tokens": 166118744} {"current_steps": 2740, "total_steps": 15680, "loss": 0.3284599304199219, "lr": 9.265815833992126e-06, "epoch": 0.3494897959183674, "percentage": 17.47, "elapsed_time": "9:53:28", "remaining_time": "1 day, 22:42:45", "throughput": 4673.36, "total_tokens": 166410816} {"current_steps": 2745, "total_steps": 15680, "loss": 0.3294307470321655, "lr": 9.263200821770462e-06, "epoch": 0.35012755102040816, "percentage": 17.51, "elapsed_time": "9:54:38", "remaining_time": "1 day, 22:42:04", "throughput": 4672.36, "total_tokens": 166702848} {"current_steps": 2750, "total_steps": 15680, "loss": 0.3194013833999634, "lr": 9.260581531129032e-06, "epoch": 0.350765306122449, "percentage": 17.54, "elapsed_time": "9:55:47", "remaining_time": "1 day, 22:41:16", "throughput": 4671.87, "total_tokens": 167006248} {"current_steps": 2755, "total_steps": 15680, "loss": 0.3320168972015381, "lr": 9.257957964696475e-06, "epoch": 0.3514030612244898, "percentage": 17.57, "elapsed_time": "9:56:54", "remaining_time": "1 day, 22:40:23", "throughput": 4671.7, "total_tokens": 167315752} {"current_steps": 2760, "total_steps": 15680, "loss": 0.3254489183425903, "lr": 9.255330125105728e-06, "epoch": 0.3520408163265306, "percentage": 17.6, "elapsed_time": "9:58:03", "remaining_time": "1 day, 22:39:35", "throughput": 4671.46, "total_tokens": 167627704} {"current_steps": 2765, "total_steps": 15680, "loss": 0.35499675273895265, "lr": 9.252698014994008e-06, "epoch": 0.35267857142857145, "percentage": 17.63, "elapsed_time": "9:59:14", "remaining_time": "1 day, 22:38:57", "throughput": 4670.68, "total_tokens": 167929672} {"current_steps": 2770, "total_steps": 15680, "loss": 0.3320456504821777, "lr": 9.250061637002822e-06, "epoch": 0.35331632653061223, "percentage": 17.67, "elapsed_time": "10:00:21", "remaining_time": "1 day, 22:38:05", "throughput": 4670.12, "total_tokens": 168226976} {"current_steps": 2775, "total_steps": 15680, "loss": 0.3739363193511963, "lr": 9.24742099377796e-06, "epoch": 0.3539540816326531, "percentage": 17.7, "elapsed_time": "10:01:25", "remaining_time": "1 day, 22:36:55", "throughput": 4670.55, "total_tokens": 168540912} {"current_steps": 2780, "total_steps": 15680, "loss": 0.33939266204833984, "lr": 9.244776087969492e-06, "epoch": 0.35459183673469385, "percentage": 17.73, "elapsed_time": "10:02:38", "remaining_time": "1 day, 22:36:28", "throughput": 4669.34, "total_tokens": 168838760} {"current_steps": 2785, "total_steps": 15680, "loss": 0.3214082717895508, "lr": 9.242126922231763e-06, "epoch": 0.3552295918367347, "percentage": 17.76, "elapsed_time": "10:03:40", "remaining_time": "1 day, 22:35:08", "throughput": 4669.56, "total_tokens": 169136064} {"current_steps": 2790, "total_steps": 15680, "loss": 0.335541296005249, "lr": 9.239473499223399e-06, "epoch": 0.35586734693877553, "percentage": 17.79, "elapsed_time": "10:04:46", "remaining_time": "1 day, 22:34:07", "throughput": 4669.43, "total_tokens": 169438592} {"current_steps": 2795, "total_steps": 15680, "loss": 0.35208282470703123, "lr": 9.236815821607295e-06, "epoch": 0.3565051020408163, "percentage": 17.83, "elapsed_time": "10:05:46", "remaining_time": "1 day, 22:32:37", "throughput": 4670.42, "total_tokens": 169753176} {"current_steps": 2800, "total_steps": 15680, "loss": 0.35019755363464355, "lr": 9.234153892050616e-06, "epoch": 0.35714285714285715, "percentage": 17.86, "elapsed_time": "10:06:59", "remaining_time": "1 day, 22:32:07", "throughput": 4669.46, "total_tokens": 170057392} {"current_steps": 2805, "total_steps": 15680, "loss": 0.32256550788879396, "lr": 9.231487713224793e-06, "epoch": 0.35778061224489793, "percentage": 17.89, "elapsed_time": "10:08:07", "remaining_time": "1 day, 22:31:20", "throughput": 4669.22, "total_tokens": 170370160} {"current_steps": 2810, "total_steps": 15680, "loss": 0.35767345428466796, "lr": 9.228817287805523e-06, "epoch": 0.35841836734693877, "percentage": 17.92, "elapsed_time": "10:09:03", "remaining_time": "1 day, 22:29:30", "throughput": 4670.31, "total_tokens": 170668320} {"current_steps": 2815, "total_steps": 15680, "loss": 0.3371246814727783, "lr": 9.226142618472765e-06, "epoch": 0.3590561224489796, "percentage": 17.95, "elapsed_time": "10:10:02", "remaining_time": "1 day, 22:28:01", "throughput": 4671.04, "total_tokens": 170973560} {"current_steps": 2820, "total_steps": 15680, "loss": 0.32080750465393065, "lr": 9.223463707910736e-06, "epoch": 0.3596938775510204, "percentage": 17.98, "elapsed_time": "10:10:57", "remaining_time": "1 day, 22:26:10", "throughput": 4671.94, "total_tokens": 171263632} {"current_steps": 2825, "total_steps": 15680, "loss": 0.3442652463912964, "lr": 9.22078055880791e-06, "epoch": 0.36033163265306123, "percentage": 18.02, "elapsed_time": "10:12:05", "remaining_time": "1 day, 22:25:18", "throughput": 4671.44, "total_tokens": 171562192} {"current_steps": 2830, "total_steps": 15680, "loss": 0.317061185836792, "lr": 9.218093173857014e-06, "epoch": 0.36096938775510207, "percentage": 18.05, "elapsed_time": "10:13:10", "remaining_time": "1 day, 22:24:11", "throughput": 4671.29, "total_tokens": 171858536} {"current_steps": 2835, "total_steps": 15680, "loss": 0.37257728576660154, "lr": 9.21540155575503e-06, "epoch": 0.36160714285714285, "percentage": 18.08, "elapsed_time": "10:14:07", "remaining_time": "1 day, 22:22:32", "throughput": 4672.33, "total_tokens": 172165192} {"current_steps": 2840, "total_steps": 15680, "loss": 0.3401576042175293, "lr": 9.212705707203177e-06, "epoch": 0.3622448979591837, "percentage": 18.11, "elapsed_time": "10:15:13", "remaining_time": "1 day, 22:21:32", "throughput": 4672.35, "total_tokens": 172474456} {"current_steps": 2845, "total_steps": 15680, "loss": 0.35530571937561034, "lr": 9.210005630906936e-06, "epoch": 0.36288265306122447, "percentage": 18.14, "elapsed_time": "10:16:27", "remaining_time": "1 day, 22:21:07", "throughput": 4671.66, "total_tokens": 172794016} {"current_steps": 2850, "total_steps": 15680, "loss": 0.3370820999145508, "lr": 9.207301329576017e-06, "epoch": 0.3635204081632653, "percentage": 18.18, "elapsed_time": "10:17:39", "remaining_time": "1 day, 22:20:30", "throughput": 4670.88, "total_tokens": 173098728} {"current_steps": 2855, "total_steps": 15680, "loss": 0.3250255584716797, "lr": 9.204592805924378e-06, "epoch": 0.36415816326530615, "percentage": 18.21, "elapsed_time": "10:18:48", "remaining_time": "1 day, 22:19:46", "throughput": 4670.38, "total_tokens": 173405192} {"current_steps": 2860, "total_steps": 15680, "loss": 0.35407509803771975, "lr": 9.201880062670207e-06, "epoch": 0.3647959183673469, "percentage": 18.24, "elapsed_time": "10:19:55", "remaining_time": "1 day, 22:18:51", "throughput": 4670.11, "total_tokens": 173709184} {"current_steps": 2865, "total_steps": 15680, "loss": 0.35567197799682615, "lr": 9.199163102535937e-06, "epoch": 0.36543367346938777, "percentage": 18.27, "elapsed_time": "10:21:13", "remaining_time": "1 day, 22:18:40", "throughput": 4668.4, "total_tokens": 174005904} {"current_steps": 2870, "total_steps": 15680, "loss": 0.3214565277099609, "lr": 9.196441928248222e-06, "epoch": 0.36607142857142855, "percentage": 18.3, "elapsed_time": "10:22:21", "remaining_time": "1 day, 22:17:49", "throughput": 4667.96, "total_tokens": 174307712} {"current_steps": 2875, "total_steps": 15680, "loss": 0.33814573287963867, "lr": 9.193716542537956e-06, "epoch": 0.3667091836734694, "percentage": 18.34, "elapsed_time": "10:23:28", "remaining_time": "1 day, 22:16:53", "throughput": 4668.03, "total_tokens": 174623384} {"current_steps": 2880, "total_steps": 15680, "loss": 0.3294132947921753, "lr": 9.19098694814025e-06, "epoch": 0.3673469387755102, "percentage": 18.37, "elapsed_time": "10:24:31", "remaining_time": "1 day, 22:15:37", "throughput": 4668.2, "total_tokens": 174922208} {"current_steps": 2885, "total_steps": 15680, "loss": 0.351007080078125, "lr": 9.188253147794443e-06, "epoch": 0.367984693877551, "percentage": 18.4, "elapsed_time": "10:25:37", "remaining_time": "1 day, 22:14:41", "throughput": 4668.07, "total_tokens": 175229896} {"current_steps": 2890, "total_steps": 15680, "loss": 0.34029929637908934, "lr": 9.185515144244097e-06, "epoch": 0.36862244897959184, "percentage": 18.43, "elapsed_time": "10:26:37", "remaining_time": "1 day, 22:13:13", "throughput": 4668.66, "total_tokens": 175532040} {"current_steps": 2895, "total_steps": 15680, "loss": 0.3353889942169189, "lr": 9.182772940236986e-06, "epoch": 0.3692602040816326, "percentage": 18.46, "elapsed_time": "10:27:48", "remaining_time": "1 day, 22:12:31", "throughput": 4668.02, "total_tokens": 175835776} {"current_steps": 2900, "total_steps": 15680, "loss": 0.31960842609405515, "lr": 9.180026538525106e-06, "epoch": 0.36989795918367346, "percentage": 18.49, "elapsed_time": "10:28:48", "remaining_time": "1 day, 22:11:04", "throughput": 4668.71, "total_tokens": 176141928} {"current_steps": 2905, "total_steps": 15680, "loss": 0.35578694343566897, "lr": 9.177275941864663e-06, "epoch": 0.3705357142857143, "percentage": 18.53, "elapsed_time": "10:29:54", "remaining_time": "1 day, 22:10:03", "throughput": 4668.6, "total_tokens": 176446368} {"current_steps": 2910, "total_steps": 15680, "loss": 0.33559885025024416, "lr": 9.174521153016072e-06, "epoch": 0.3711734693877551, "percentage": 18.56, "elapsed_time": "10:30:53", "remaining_time": "1 day, 22:08:34", "throughput": 4669.47, "total_tokens": 176756824} {"current_steps": 2915, "total_steps": 15680, "loss": 0.33328685760498045, "lr": 9.171762174743954e-06, "epoch": 0.3718112244897959, "percentage": 18.59, "elapsed_time": "10:31:58", "remaining_time": "1 day, 22:07:26", "throughput": 4669.67, "total_tokens": 177065320} {"current_steps": 2920, "total_steps": 15680, "loss": 0.33100380897521975, "lr": 9.168999009817141e-06, "epoch": 0.37244897959183676, "percentage": 18.62, "elapsed_time": "10:33:08", "remaining_time": "1 day, 22:06:43", "throughput": 4669.02, "total_tokens": 177368072} {"current_steps": 2925, "total_steps": 15680, "loss": 0.3455332040786743, "lr": 9.166231661008658e-06, "epoch": 0.37308673469387754, "percentage": 18.65, "elapsed_time": "10:34:23", "remaining_time": "1 day, 22:06:21", "throughput": 4668.14, "total_tokens": 177684296} {"current_steps": 2930, "total_steps": 15680, "loss": 0.33367528915405276, "lr": 9.163460131095735e-06, "epoch": 0.3737244897959184, "percentage": 18.69, "elapsed_time": "10:35:32", "remaining_time": "1 day, 22:05:36", "throughput": 4667.48, "total_tokens": 177984512} {"current_steps": 2935, "total_steps": 15680, "loss": 0.3466202259063721, "lr": 9.160684422859794e-06, "epoch": 0.37436224489795916, "percentage": 18.72, "elapsed_time": "10:36:43", "remaining_time": "1 day, 22:04:54", "throughput": 4666.89, "total_tokens": 178290584} {"current_steps": 2940, "total_steps": 15680, "loss": 0.3054463863372803, "lr": 9.157904539086454e-06, "epoch": 0.375, "percentage": 18.75, "elapsed_time": "10:37:35", "remaining_time": "1 day, 22:02:54", "throughput": 4668.26, "total_tokens": 178587696} {"current_steps": 2945, "total_steps": 15680, "loss": 0.32589786052703856, "lr": 9.15512048256552e-06, "epoch": 0.37563775510204084, "percentage": 18.78, "elapsed_time": "10:38:37", "remaining_time": "1 day, 22:01:35", "throughput": 4668.81, "total_tokens": 178896720} {"current_steps": 2950, "total_steps": 15680, "loss": 0.3620042324066162, "lr": 9.15233225609099e-06, "epoch": 0.3762755102040816, "percentage": 18.81, "elapsed_time": "10:39:38", "remaining_time": "1 day, 22:00:13", "throughput": 4669.3, "total_tokens": 179201000} {"current_steps": 2955, "total_steps": 15680, "loss": 0.2974902629852295, "lr": 9.149539862461044e-06, "epoch": 0.37691326530612246, "percentage": 18.85, "elapsed_time": "10:40:46", "remaining_time": "1 day, 21:59:19", "throughput": 4669.03, "total_tokens": 179506648} {"current_steps": 2960, "total_steps": 15680, "loss": 0.30786125659942626, "lr": 9.14674330447804e-06, "epoch": 0.37755102040816324, "percentage": 18.88, "elapsed_time": "10:41:51", "remaining_time": "1 day, 21:58:17", "throughput": 4668.54, "total_tokens": 179794472} {"current_steps": 2965, "total_steps": 15680, "loss": 0.34150445461273193, "lr": 9.143942584948525e-06, "epoch": 0.3781887755102041, "percentage": 18.91, "elapsed_time": "10:43:00", "remaining_time": "1 day, 21:57:28", "throughput": 4667.95, "total_tokens": 180093352} {"current_steps": 2970, "total_steps": 15680, "loss": 0.30869088172912595, "lr": 9.141137706683212e-06, "epoch": 0.3788265306122449, "percentage": 18.94, "elapsed_time": "10:44:10", "remaining_time": "1 day, 21:56:41", "throughput": 4667.32, "total_tokens": 180392080} {"current_steps": 2975, "total_steps": 15680, "loss": 0.3172877073287964, "lr": 9.138328672496994e-06, "epoch": 0.3794642857142857, "percentage": 18.97, "elapsed_time": "10:45:14", "remaining_time": "1 day, 21:55:33", "throughput": 4667.44, "total_tokens": 180697368} {"current_steps": 2980, "total_steps": 15680, "loss": 0.36992654800415037, "lr": 9.135515485208933e-06, "epoch": 0.38010204081632654, "percentage": 19.01, "elapsed_time": "10:46:22", "remaining_time": "1 day, 21:54:39", "throughput": 4667.19, "total_tokens": 181003232} {"current_steps": 2985, "total_steps": 15680, "loss": 0.36478912830352783, "lr": 9.132698147642258e-06, "epoch": 0.3807397959183674, "percentage": 19.04, "elapsed_time": "10:47:24", "remaining_time": "1 day, 21:53:24", "throughput": 4667.4, "total_tokens": 181304680} {"current_steps": 2990, "total_steps": 15680, "loss": 0.3404196262359619, "lr": 9.129876662624366e-06, "epoch": 0.38137755102040816, "percentage": 19.07, "elapsed_time": "10:48:34", "remaining_time": "1 day, 21:52:38", "throughput": 4667.12, "total_tokens": 181618216} {"current_steps": 2995, "total_steps": 15680, "loss": 0.377862811088562, "lr": 9.127051032986814e-06, "epoch": 0.382015306122449, "percentage": 19.1, "elapsed_time": "10:49:31", "remaining_time": "1 day, 21:51:01", "throughput": 4668.13, "total_tokens": 181925896} {"current_steps": 3000, "total_steps": 15680, "loss": 0.3464046478271484, "lr": 9.124221261565316e-06, "epoch": 0.3826530612244898, "percentage": 19.13, "elapsed_time": "10:50:42", "remaining_time": "1 day, 21:50:20", "throughput": 4667.37, "total_tokens": 182226640} {"current_steps": 3005, "total_steps": 15680, "loss": 0.33391451835632324, "lr": 9.121387351199748e-06, "epoch": 0.3832908163265306, "percentage": 19.16, "elapsed_time": "10:51:41", "remaining_time": "1 day, 21:48:50", "throughput": 4668.37, "total_tokens": 182541464} {"current_steps": 3010, "total_steps": 15680, "loss": 0.3343007564544678, "lr": 9.118549304734136e-06, "epoch": 0.38392857142857145, "percentage": 19.2, "elapsed_time": "10:52:37", "remaining_time": "1 day, 21:47:05", "throughput": 4669.37, "total_tokens": 182840416} {"current_steps": 3015, "total_steps": 15680, "loss": 0.32906546592712405, "lr": 9.115707125016658e-06, "epoch": 0.38456632653061223, "percentage": 19.23, "elapsed_time": "10:53:47", "remaining_time": "1 day, 21:46:20", "throughput": 4668.97, "total_tokens": 183150872} {"current_steps": 3020, "total_steps": 15680, "loss": 0.3491034984588623, "lr": 9.112860814899637e-06, "epoch": 0.3852040816326531, "percentage": 19.26, "elapsed_time": "10:55:06", "remaining_time": "1 day, 21:46:16", "throughput": 4667.31, "total_tokens": 183456848} {"current_steps": 3025, "total_steps": 15680, "loss": 0.33542647361755373, "lr": 9.110010377239552e-06, "epoch": 0.38584183673469385, "percentage": 19.29, "elapsed_time": "10:56:13", "remaining_time": "1 day, 21:45:16", "throughput": 4666.98, "total_tokens": 183754136} {"current_steps": 3030, "total_steps": 15680, "loss": 0.3634347438812256, "lr": 9.107155814897007e-06, "epoch": 0.3864795918367347, "percentage": 19.32, "elapsed_time": "10:57:19", "remaining_time": "1 day, 21:44:18", "throughput": 4666.74, "total_tokens": 184055568} {"current_steps": 3035, "total_steps": 15680, "loss": 0.3365731716156006, "lr": 9.10429713073676e-06, "epoch": 0.38711734693877553, "percentage": 19.36, "elapsed_time": "10:58:24", "remaining_time": "1 day, 21:43:11", "throughput": 4666.56, "total_tokens": 184350472} {"current_steps": 3040, "total_steps": 15680, "loss": 0.3240904569625854, "lr": 9.101434327627696e-06, "epoch": 0.3877551020408163, "percentage": 19.39, "elapsed_time": "10:59:40", "remaining_time": "1 day, 21:42:52", "throughput": 4665.14, "total_tokens": 184649680} {"current_steps": 3045, "total_steps": 15680, "loss": 0.3177307605743408, "lr": 9.098567408442844e-06, "epoch": 0.38839285714285715, "percentage": 19.42, "elapsed_time": "11:00:41", "remaining_time": "1 day, 21:41:27", "throughput": 4665.51, "total_tokens": 184945944} {"current_steps": 3050, "total_steps": 15680, "loss": 0.3542469024658203, "lr": 9.095696376059353e-06, "epoch": 0.38903061224489793, "percentage": 19.45, "elapsed_time": "11:01:43", "remaining_time": "1 day, 21:40:09", "throughput": 4665.93, "total_tokens": 185251256} {"current_steps": 3055, "total_steps": 15680, "loss": 0.35657784938812254, "lr": 9.092821233358507e-06, "epoch": 0.38966836734693877, "percentage": 19.48, "elapsed_time": "11:02:44", "remaining_time": "1 day, 21:38:48", "throughput": 4666.3, "total_tokens": 185551480} {"current_steps": 3060, "total_steps": 15680, "loss": 0.3421341419219971, "lr": 9.08994198322571e-06, "epoch": 0.3903061224489796, "percentage": 19.52, "elapsed_time": "11:03:51", "remaining_time": "1 day, 21:37:50", "throughput": 4666.12, "total_tokens": 185856064} {"current_steps": 3065, "total_steps": 15680, "loss": 0.3498190402984619, "lr": 9.087058628550492e-06, "epoch": 0.3909438775510204, "percentage": 19.55, "elapsed_time": "11:05:01", "remaining_time": "1 day, 21:37:07", "throughput": 4665.48, "total_tokens": 186159872} {"current_steps": 3070, "total_steps": 15680, "loss": 0.3342771291732788, "lr": 9.084171172226502e-06, "epoch": 0.39158163265306123, "percentage": 19.58, "elapsed_time": "11:06:07", "remaining_time": "1 day, 21:36:08", "throughput": 4665.55, "total_tokens": 186472704} {"current_steps": 3075, "total_steps": 15680, "loss": 0.3412167549133301, "lr": 9.081279617151502e-06, "epoch": 0.39221938775510207, "percentage": 19.61, "elapsed_time": "11:07:13", "remaining_time": "1 day, 21:35:06", "throughput": 4665.51, "total_tokens": 186778176} {"current_steps": 3080, "total_steps": 15680, "loss": 0.3425647735595703, "lr": 9.078383966227369e-06, "epoch": 0.39285714285714285, "percentage": 19.64, "elapsed_time": "11:08:12", "remaining_time": "1 day, 21:33:32", "throughput": 4665.86, "total_tokens": 187063736} {"current_steps": 3085, "total_steps": 15680, "loss": 0.3367135047912598, "lr": 9.075484222360094e-06, "epoch": 0.3934948979591837, "percentage": 19.67, "elapsed_time": "11:09:17", "remaining_time": "1 day, 21:32:27", "throughput": 4665.89, "total_tokens": 187368624} {"current_steps": 3090, "total_steps": 15680, "loss": 0.3358824014663696, "lr": 9.07258038845977e-06, "epoch": 0.39413265306122447, "percentage": 19.71, "elapsed_time": "11:10:20", "remaining_time": "1 day, 21:31:17", "throughput": 4665.82, "total_tokens": 187663328} {"current_steps": 3095, "total_steps": 15680, "loss": 0.33083035945892336, "lr": 9.069672467440598e-06, "epoch": 0.3947704081632653, "percentage": 19.74, "elapsed_time": "11:11:32", "remaining_time": "1 day, 21:30:39", "throughput": 4665.19, "total_tokens": 187973304} {"current_steps": 3100, "total_steps": 15680, "loss": 0.33884828090667723, "lr": 9.066760462220878e-06, "epoch": 0.39540816326530615, "percentage": 19.77, "elapsed_time": "11:12:39", "remaining_time": "1 day, 21:29:40", "throughput": 4665.16, "total_tokens": 188282120} {"current_steps": 3105, "total_steps": 15680, "loss": 0.3614191055297852, "lr": 9.063844375723014e-06, "epoch": 0.3960459183673469, "percentage": 19.8, "elapsed_time": "11:13:32", "remaining_time": "1 day, 21:27:46", "throughput": 4666.62, "total_tokens": 188588584} {"current_steps": 3110, "total_steps": 15680, "loss": 0.3382896423339844, "lr": 9.060924210873501e-06, "epoch": 0.39668367346938777, "percentage": 19.83, "elapsed_time": "11:14:39", "remaining_time": "1 day, 21:26:49", "throughput": 4666.03, "total_tokens": 188877960} {"current_steps": 3115, "total_steps": 15680, "loss": 0.3252332448959351, "lr": 9.057999970602926e-06, "epoch": 0.39732142857142855, "percentage": 19.87, "elapsed_time": "11:15:32", "remaining_time": "1 day, 21:24:55", "throughput": 4667.49, "total_tokens": 189183784} {"current_steps": 3120, "total_steps": 15680, "loss": 0.32281057834625243, "lr": 9.055071657845973e-06, "epoch": 0.3979591836734694, "percentage": 19.9, "elapsed_time": "11:16:47", "remaining_time": "1 day, 21:24:29", "throughput": 4666.51, "total_tokens": 189493632} {"current_steps": 3125, "total_steps": 15680, "loss": 0.30558199882507325, "lr": 9.052139275541404e-06, "epoch": 0.3985969387755102, "percentage": 19.93, "elapsed_time": "11:17:59", "remaining_time": "1 day, 21:23:53", "throughput": 4665.35, "total_tokens": 189783792} {"current_steps": 3130, "total_steps": 15680, "loss": 0.3246393442153931, "lr": 9.049202826632072e-06, "epoch": 0.399234693877551, "percentage": 19.96, "elapsed_time": "11:19:10", "remaining_time": "1 day, 21:23:14", "throughput": 4664.57, "total_tokens": 190085928} {"current_steps": 3135, "total_steps": 15680, "loss": 0.324275541305542, "lr": 9.046262314064907e-06, "epoch": 0.39987244897959184, "percentage": 19.99, "elapsed_time": "11:20:17", "remaining_time": "1 day, 21:22:14", "throughput": 4664.24, "total_tokens": 190382216} {"current_steps": 3140, "total_steps": 15680, "loss": 0.3147127151489258, "lr": 9.04331774079092e-06, "epoch": 0.4005102040816326, "percentage": 20.03, "elapsed_time": "11:21:21", "remaining_time": "1 day, 21:21:04", "throughput": 4664.13, "total_tokens": 190675216} {"current_steps": 3145, "total_steps": 15680, "loss": 0.32260823249816895, "lr": 9.040369109765196e-06, "epoch": 0.40114795918367346, "percentage": 20.06, "elapsed_time": "11:22:35", "remaining_time": "1 day, 21:20:37", "throughput": 4662.71, "total_tokens": 190965104} {"current_steps": 3150, "total_steps": 15680, "loss": 0.3365804195404053, "lr": 9.037416423946891e-06, "epoch": 0.4017857142857143, "percentage": 20.09, "elapsed_time": "11:23:36", "remaining_time": "1 day, 21:19:14", "throughput": 4663.03, "total_tokens": 191261352} {"current_steps": 3155, "total_steps": 15680, "loss": 0.33006772994995115, "lr": 9.034459686299232e-06, "epoch": 0.4024234693877551, "percentage": 20.12, "elapsed_time": "11:24:42", "remaining_time": "1 day, 21:18:14", "throughput": 4662.96, "total_tokens": 191568288} {"current_steps": 3160, "total_steps": 15680, "loss": 0.3405275344848633, "lr": 9.031498899789513e-06, "epoch": 0.4030612244897959, "percentage": 20.15, "elapsed_time": "11:25:59", "remaining_time": "1 day, 21:17:53", "throughput": 4661.87, "total_tokens": 191879040} {"current_steps": 3165, "total_steps": 15680, "loss": 0.34804649353027345, "lr": 9.028534067389087e-06, "epoch": 0.40369897959183676, "percentage": 20.18, "elapsed_time": "11:26:57", "remaining_time": "1 day, 21:16:23", "throughput": 4662.65, "total_tokens": 192184496} {"current_steps": 3170, "total_steps": 15680, "loss": 0.31906704902648925, "lr": 9.025565192073374e-06, "epoch": 0.40433673469387754, "percentage": 20.22, "elapsed_time": "11:28:02", "remaining_time": "1 day, 21:15:17", "throughput": 4662.99, "total_tokens": 192501256} {"current_steps": 3175, "total_steps": 15680, "loss": 0.3202676773071289, "lr": 9.022592276821843e-06, "epoch": 0.4049744897959184, "percentage": 20.25, "elapsed_time": "11:29:10", "remaining_time": "1 day, 21:14:23", "throughput": 4662.58, "total_tokens": 192801104} {"current_steps": 3180, "total_steps": 15680, "loss": 0.3559399604797363, "lr": 9.019615324618027e-06, "epoch": 0.40561224489795916, "percentage": 20.28, "elapsed_time": "11:30:07", "remaining_time": "1 day, 21:12:46", "throughput": 4663.43, "total_tokens": 193101872} {"current_steps": 3185, "total_steps": 15680, "loss": 0.3301278591156006, "lr": 9.016634338449504e-06, "epoch": 0.40625, "percentage": 20.31, "elapsed_time": "11:31:12", "remaining_time": "1 day, 21:11:38", "throughput": 4663.41, "total_tokens": 193401672} {"current_steps": 3190, "total_steps": 15680, "loss": 0.3401746988296509, "lr": 9.0136493213079e-06, "epoch": 0.40688775510204084, "percentage": 20.34, "elapsed_time": "11:32:21", "remaining_time": "1 day, 21:10:51", "throughput": 4662.98, "total_tokens": 193709256} {"current_steps": 3195, "total_steps": 15680, "loss": 0.324747896194458, "lr": 9.01066027618889e-06, "epoch": 0.4075255102040816, "percentage": 20.38, "elapsed_time": "11:33:27", "remaining_time": "1 day, 21:09:47", "throughput": 4662.77, "total_tokens": 194004880} {"current_steps": 3200, "total_steps": 15680, "loss": 0.3389841318130493, "lr": 9.007667206092188e-06, "epoch": 0.40816326530612246, "percentage": 20.41, "elapsed_time": "11:34:42", "remaining_time": "1 day, 21:09:22", "throughput": 4661.46, "total_tokens": 194301520} {"current_steps": 3205, "total_steps": 15680, "loss": 0.3330172061920166, "lr": 9.00467011402155e-06, "epoch": 0.40880102040816324, "percentage": 20.44, "elapsed_time": "11:36:00", "remaining_time": "1 day, 21:09:07", "throughput": 4660.08, "total_tokens": 194608512} {"current_steps": 3210, "total_steps": 15680, "loss": 0.3154860019683838, "lr": 9.001669002984767e-06, "epoch": 0.4094387755102041, "percentage": 20.47, "elapsed_time": "11:37:12", "remaining_time": "1 day, 21:08:28", "throughput": 4658.88, "total_tokens": 194893256} {"current_steps": 3215, "total_steps": 15680, "loss": 0.3542327880859375, "lr": 8.998663875993666e-06, "epoch": 0.4100765306122449, "percentage": 20.5, "elapsed_time": "11:38:16", "remaining_time": "1 day, 21:07:16", "throughput": 4658.99, "total_tokens": 195193368} {"current_steps": 3220, "total_steps": 15680, "loss": 0.32598466873168946, "lr": 8.995654736064096e-06, "epoch": 0.4107142857142857, "percentage": 20.54, "elapsed_time": "11:39:20", "remaining_time": "1 day, 21:06:09", "throughput": 4658.89, "total_tokens": 195489920} {"current_steps": 3225, "total_steps": 15680, "loss": 0.32182776927948, "lr": 8.992641586215944e-06, "epoch": 0.41135204081632654, "percentage": 20.57, "elapsed_time": "11:40:28", "remaining_time": "1 day, 21:05:15", "throughput": 4658.56, "total_tokens": 195793216} {"current_steps": 3230, "total_steps": 15680, "loss": 0.34074854850769043, "lr": 8.989624429473116e-06, "epoch": 0.4119897959183674, "percentage": 20.6, "elapsed_time": "11:41:32", "remaining_time": "1 day, 21:04:04", "throughput": 4658.82, "total_tokens": 196100528} {"current_steps": 3235, "total_steps": 15680, "loss": 0.3286905765533447, "lr": 8.986603268863536e-06, "epoch": 0.41262755102040816, "percentage": 20.63, "elapsed_time": "11:42:36", "remaining_time": "1 day, 21:02:55", "throughput": 4658.68, "total_tokens": 196393664} {"current_steps": 3240, "total_steps": 15680, "loss": 0.34261574745178225, "lr": 8.983578107419153e-06, "epoch": 0.413265306122449, "percentage": 20.66, "elapsed_time": "11:43:38", "remaining_time": "1 day, 21:01:36", "throughput": 4659.09, "total_tokens": 196697800} {"current_steps": 3245, "total_steps": 15680, "loss": 0.3467216491699219, "lr": 8.980548948175926e-06, "epoch": 0.4139030612244898, "percentage": 20.7, "elapsed_time": "11:44:39", "remaining_time": "1 day, 21:00:18", "throughput": 4659.55, "total_tokens": 197005264} {"current_steps": 3250, "total_steps": 15680, "loss": 0.3394784688949585, "lr": 8.97751579417383e-06, "epoch": 0.4145408163265306, "percentage": 20.73, "elapsed_time": "11:45:50", "remaining_time": "1 day, 20:59:35", "throughput": 4658.66, "total_tokens": 197297408} {"current_steps": 3255, "total_steps": 15680, "loss": 0.34244298934936523, "lr": 8.974478648456845e-06, "epoch": 0.41517857142857145, "percentage": 20.76, "elapsed_time": "11:47:04", "remaining_time": "1 day, 20:59:02", "throughput": 4657.95, "total_tokens": 197610888} {"current_steps": 3260, "total_steps": 15680, "loss": 0.33392794132232667, "lr": 8.971437514072959e-06, "epoch": 0.41581632653061223, "percentage": 20.79, "elapsed_time": "11:48:10", "remaining_time": "1 day, 20:58:00", "throughput": 4657.62, "total_tokens": 197904104} {"current_steps": 3265, "total_steps": 15680, "loss": 0.3191607713699341, "lr": 8.968392394074164e-06, "epoch": 0.4164540816326531, "percentage": 20.82, "elapsed_time": "11:49:04", "remaining_time": "1 day, 20:56:12", "throughput": 4659.23, "total_tokens": 198223760} {"current_steps": 3270, "total_steps": 15680, "loss": 0.324001145362854, "lr": 8.965343291516448e-06, "epoch": 0.41709183673469385, "percentage": 20.85, "elapsed_time": "11:50:13", "remaining_time": "1 day, 20:55:23", "throughput": 4658.62, "total_tokens": 198520776} {"current_steps": 3275, "total_steps": 15680, "loss": 0.33489012718200684, "lr": 8.962290209459801e-06, "epoch": 0.4177295918367347, "percentage": 20.89, "elapsed_time": "11:51:12", "remaining_time": "1 day, 20:53:52", "throughput": 4659.45, "total_tokens": 198828432} {"current_steps": 3280, "total_steps": 15680, "loss": 0.3072980403900146, "lr": 8.959233150968203e-06, "epoch": 0.41836734693877553, "percentage": 20.92, "elapsed_time": "11:52:10", "remaining_time": "1 day, 20:52:22", "throughput": 4660.01, "total_tokens": 199125336} {"current_steps": 3285, "total_steps": 15680, "loss": 0.33353633880615235, "lr": 8.956172119109625e-06, "epoch": 0.4190051020408163, "percentage": 20.95, "elapsed_time": "11:53:19", "remaining_time": "1 day, 20:51:30", "throughput": 4659.86, "total_tokens": 199438904} {"current_steps": 3290, "total_steps": 15680, "loss": 0.34106614589691164, "lr": 8.953107116956027e-06, "epoch": 0.41964285714285715, "percentage": 20.98, "elapsed_time": "11:54:27", "remaining_time": "1 day, 20:50:38", "throughput": 4659.73, "total_tokens": 199752248} {"current_steps": 3295, "total_steps": 15680, "loss": 0.34395198822021483, "lr": 8.950038147583353e-06, "epoch": 0.42028061224489793, "percentage": 21.01, "elapsed_time": "11:55:36", "remaining_time": "1 day, 20:49:47", "throughput": 4659.4, "total_tokens": 200059536} {"current_steps": 3300, "total_steps": 15680, "loss": 0.33737869262695314, "lr": 8.946965214071528e-06, "epoch": 0.42091836734693877, "percentage": 21.05, "elapsed_time": "11:56:48", "remaining_time": "1 day, 20:49:07", "throughput": 4658.45, "total_tokens": 200353952} {"current_steps": 3305, "total_steps": 15680, "loss": 0.35701279640197753, "lr": 8.943888319504456e-06, "epoch": 0.4215561224489796, "percentage": 21.08, "elapsed_time": "11:57:50", "remaining_time": "1 day, 20:47:49", "throughput": 4658.99, "total_tokens": 200664080} {"current_steps": 3310, "total_steps": 15680, "loss": 0.3449193000793457, "lr": 8.940807466970014e-06, "epoch": 0.4221938775510204, "percentage": 21.11, "elapsed_time": "11:58:56", "remaining_time": "1 day, 20:46:49", "throughput": 4659.09, "total_tokens": 200978760} {"current_steps": 3315, "total_steps": 15680, "loss": 0.34102916717529297, "lr": 8.937722659560054e-06, "epoch": 0.42283163265306123, "percentage": 21.14, "elapsed_time": "12:00:12", "remaining_time": "1 day, 20:46:21", "throughput": 4657.96, "total_tokens": 201280168} {"current_steps": 3320, "total_steps": 15680, "loss": 0.33057827949523927, "lr": 8.934633900370395e-06, "epoch": 0.42346938775510207, "percentage": 21.17, "elapsed_time": "12:01:10", "remaining_time": "1 day, 20:44:53", "throughput": 4658.78, "total_tokens": 201590040} {"current_steps": 3325, "total_steps": 15680, "loss": 0.34342374801635744, "lr": 8.931541192500822e-06, "epoch": 0.42410714285714285, "percentage": 21.21, "elapsed_time": "12:02:10", "remaining_time": "1 day, 20:43:26", "throughput": 4659.36, "total_tokens": 201892176} {"current_steps": 3330, "total_steps": 15680, "loss": 0.3427203893661499, "lr": 8.928444539055086e-06, "epoch": 0.4247448979591837, "percentage": 21.24, "elapsed_time": "12:03:17", "remaining_time": "1 day, 20:42:27", "throughput": 4659.43, "total_tokens": 202205768} {"current_steps": 3335, "total_steps": 15680, "loss": 0.3572682857513428, "lr": 8.92534394314089e-06, "epoch": 0.42538265306122447, "percentage": 21.27, "elapsed_time": "12:04:20", "remaining_time": "1 day, 20:41:16", "throughput": 4659.86, "total_tokens": 202521176} {"current_steps": 3340, "total_steps": 15680, "loss": 0.3468234300613403, "lr": 8.922239407869904e-06, "epoch": 0.4260204081632653, "percentage": 21.3, "elapsed_time": "12:05:25", "remaining_time": "1 day, 20:40:11", "throughput": 4660.06, "total_tokens": 202832992} {"current_steps": 3345, "total_steps": 15680, "loss": 0.35007805824279786, "lr": 8.919130936357743e-06, "epoch": 0.42665816326530615, "percentage": 21.33, "elapsed_time": "12:06:29", "remaining_time": "1 day, 20:39:01", "throughput": 4660.06, "total_tokens": 203131248} {"current_steps": 3350, "total_steps": 15680, "loss": 0.32661712169647217, "lr": 8.916018531723975e-06, "epoch": 0.4272959183673469, "percentage": 21.36, "elapsed_time": "12:07:38", "remaining_time": "1 day, 20:38:10", "throughput": 4659.81, "total_tokens": 203441272} {"current_steps": 3355, "total_steps": 15680, "loss": 0.3261438846588135, "lr": 8.91290219709212e-06, "epoch": 0.42793367346938777, "percentage": 21.4, "elapsed_time": "12:08:49", "remaining_time": "1 day, 20:37:23", "throughput": 4659.39, "total_tokens": 203750872} {"current_steps": 3360, "total_steps": 15680, "loss": 0.3584270000457764, "lr": 8.909781935589629e-06, "epoch": 0.42857142857142855, "percentage": 21.43, "elapsed_time": "12:09:54", "remaining_time": "1 day, 20:36:18", "throughput": 4659.7, "total_tokens": 204067096} {"current_steps": 3365, "total_steps": 15680, "loss": 0.33870534896850585, "lr": 8.906657750347909e-06, "epoch": 0.4292091836734694, "percentage": 21.46, "elapsed_time": "12:10:44", "remaining_time": "1 day, 20:34:19", "throughput": 4661.54, "total_tokens": 204383624} {"current_steps": 3370, "total_steps": 15680, "loss": 0.3180680751800537, "lr": 8.903529644502297e-06, "epoch": 0.4298469387755102, "percentage": 21.49, "elapsed_time": "12:11:56", "remaining_time": "1 day, 20:33:38", "throughput": 4660.97, "total_tokens": 204692960} {"current_steps": 3375, "total_steps": 15680, "loss": 0.33640327453613283, "lr": 8.900397621192063e-06, "epoch": 0.430484693877551, "percentage": 21.52, "elapsed_time": "12:13:11", "remaining_time": "1 day, 20:33:10", "throughput": 4659.91, "total_tokens": 204997448} {"current_steps": 3380, "total_steps": 15680, "loss": 0.33349683284759524, "lr": 8.897261683560413e-06, "epoch": 0.43112244897959184, "percentage": 21.56, "elapsed_time": "12:14:25", "remaining_time": "1 day, 20:32:35", "throughput": 4659.06, "total_tokens": 205302480} {"current_steps": 3385, "total_steps": 15680, "loss": 0.36110312938690187, "lr": 8.89412183475448e-06, "epoch": 0.4317602040816326, "percentage": 21.59, "elapsed_time": "12:15:28", "remaining_time": "1 day, 20:31:23", "throughput": 4659.33, "total_tokens": 205609000} {"current_steps": 3390, "total_steps": 15680, "loss": 0.3305992126464844, "lr": 8.890978077925323e-06, "epoch": 0.43239795918367346, "percentage": 21.62, "elapsed_time": "12:16:40", "remaining_time": "1 day, 20:30:43", "throughput": 4658.46, "total_tokens": 205906960} {"current_steps": 3395, "total_steps": 15680, "loss": 0.33739218711853025, "lr": 8.887830416227918e-06, "epoch": 0.4330357142857143, "percentage": 21.65, "elapsed_time": "12:17:55", "remaining_time": "1 day, 20:30:14", "throughput": 4657.4, "total_tokens": 206210696} {"current_steps": 3400, "total_steps": 15680, "loss": 0.3457144021987915, "lr": 8.884678852821165e-06, "epoch": 0.4336734693877551, "percentage": 21.68, "elapsed_time": "12:18:54", "remaining_time": "1 day, 20:28:46", "throughput": 4658.0, "total_tokens": 206510688} {"current_steps": 3405, "total_steps": 15680, "loss": 0.3492433547973633, "lr": 8.881523390867876e-06, "epoch": 0.4343112244897959, "percentage": 21.72, "elapsed_time": "12:20:03", "remaining_time": "1 day, 20:27:55", "throughput": 4657.84, "total_tokens": 206826344} {"current_steps": 3410, "total_steps": 15680, "loss": 0.3448661804199219, "lr": 8.878364033534781e-06, "epoch": 0.43494897959183676, "percentage": 21.75, "elapsed_time": "12:21:09", "remaining_time": "1 day, 20:26:51", "throughput": 4657.88, "total_tokens": 207133176} {"current_steps": 3415, "total_steps": 15680, "loss": 0.3526355266571045, "lr": 8.875200783992514e-06, "epoch": 0.43558673469387754, "percentage": 21.78, "elapsed_time": "12:22:16", "remaining_time": "1 day, 20:25:52", "throughput": 4657.85, "total_tokens": 207443552} {"current_steps": 3420, "total_steps": 15680, "loss": 0.3426992654800415, "lr": 8.872033645415617e-06, "epoch": 0.4362244897959184, "percentage": 21.81, "elapsed_time": "12:23:15", "remaining_time": "1 day, 20:24:25", "throughput": 4658.63, "total_tokens": 207753784} {"current_steps": 3425, "total_steps": 15680, "loss": 0.32737252712249754, "lr": 8.868862620982534e-06, "epoch": 0.43686224489795916, "percentage": 21.84, "elapsed_time": "12:24:26", "remaining_time": "1 day, 20:23:42", "throughput": 4658.0, "total_tokens": 208057576} {"current_steps": 3430, "total_steps": 15680, "loss": 0.35897324085235593, "lr": 8.86568771387561e-06, "epoch": 0.4375, "percentage": 21.88, "elapsed_time": "12:25:38", "remaining_time": "1 day, 20:23:00", "throughput": 4657.68, "total_tokens": 208378240} {"current_steps": 3435, "total_steps": 15680, "loss": 0.3397051334381104, "lr": 8.862508927281086e-06, "epoch": 0.43813775510204084, "percentage": 21.91, "elapsed_time": "12:26:46", "remaining_time": "1 day, 20:22:03", "throughput": 4657.35, "total_tokens": 208677608} {"current_steps": 3440, "total_steps": 15680, "loss": 0.3317503690719604, "lr": 8.859326264389098e-06, "epoch": 0.4387755102040816, "percentage": 21.94, "elapsed_time": "12:27:48", "remaining_time": "1 day, 20:20:49", "throughput": 4657.56, "total_tokens": 208979040} {"current_steps": 3445, "total_steps": 15680, "loss": 0.32828850746154786, "lr": 8.856139728393667e-06, "epoch": 0.43941326530612246, "percentage": 21.97, "elapsed_time": "12:28:51", "remaining_time": "1 day, 20:19:36", "throughput": 4657.79, "total_tokens": 209282536} {"current_steps": 3450, "total_steps": 15680, "loss": 0.3224157810211182, "lr": 8.852949322492708e-06, "epoch": 0.44005102040816324, "percentage": 22.0, "elapsed_time": "12:30:01", "remaining_time": "1 day, 20:18:46", "throughput": 4657.41, "total_tokens": 209589696} {"current_steps": 3455, "total_steps": 15680, "loss": 0.3120415687561035, "lr": 8.849755049888014e-06, "epoch": 0.4406887755102041, "percentage": 22.03, "elapsed_time": "12:30:53", "remaining_time": "1 day, 20:16:54", "throughput": 4658.81, "total_tokens": 209895168} {"current_steps": 3460, "total_steps": 15680, "loss": 0.35138235092163084, "lr": 8.84655691378526e-06, "epoch": 0.4413265306122449, "percentage": 22.07, "elapsed_time": "12:32:01", "remaining_time": "1 day, 20:15:59", "throughput": 4658.74, "total_tokens": 210209408} {"current_steps": 3465, "total_steps": 15680, "loss": 0.3106915712356567, "lr": 8.843354917394e-06, "epoch": 0.4419642857142857, "percentage": 22.1, "elapsed_time": "12:33:05", "remaining_time": "1 day, 20:14:50", "throughput": 4658.83, "total_tokens": 210511320} {"current_steps": 3470, "total_steps": 15680, "loss": 0.3368816375732422, "lr": 8.840149063927663e-06, "epoch": 0.44260204081632654, "percentage": 22.13, "elapsed_time": "12:34:14", "remaining_time": "1 day, 20:13:57", "throughput": 4658.37, "total_tokens": 210811088} {"current_steps": 3475, "total_steps": 15680, "loss": 0.339404559135437, "lr": 8.836939356603542e-06, "epoch": 0.4432397959183674, "percentage": 22.16, "elapsed_time": "12:35:15", "remaining_time": "1 day, 20:12:37", "throughput": 4658.83, "total_tokens": 211116448} {"current_steps": 3480, "total_steps": 15680, "loss": 0.3408853530883789, "lr": 8.833725798642809e-06, "epoch": 0.44387755102040816, "percentage": 22.19, "elapsed_time": "12:36:15", "remaining_time": "1 day, 20:11:14", "throughput": 4659.4, "total_tokens": 211422040} {"current_steps": 3485, "total_steps": 15680, "loss": 0.3162368297576904, "lr": 8.830508393270487e-06, "epoch": 0.444515306122449, "percentage": 22.23, "elapsed_time": "12:37:23", "remaining_time": "1 day, 20:10:18", "throughput": 4658.99, "total_tokens": 211719672} {"current_steps": 3490, "total_steps": 15680, "loss": 0.3251905679702759, "lr": 8.827287143715472e-06, "epoch": 0.4451530612244898, "percentage": 22.26, "elapsed_time": "12:38:29", "remaining_time": "1 day, 20:09:17", "throughput": 4658.99, "total_tokens": 212028616} {"current_steps": 3495, "total_steps": 15680, "loss": 0.33139405250549314, "lr": 8.824062053210512e-06, "epoch": 0.4457908163265306, "percentage": 22.29, "elapsed_time": "12:39:42", "remaining_time": "1 day, 20:08:40", "throughput": 4657.84, "total_tokens": 212317040} {"current_steps": 3500, "total_steps": 15680, "loss": 0.33382697105407716, "lr": 8.820833124992207e-06, "epoch": 0.44642857142857145, "percentage": 22.32, "elapsed_time": "12:40:49", "remaining_time": "1 day, 20:07:41", "throughput": 4657.57, "total_tokens": 212617704} {"current_steps": 3505, "total_steps": 15680, "loss": 0.33900742530822753, "lr": 8.817600362301018e-06, "epoch": 0.44706632653061223, "percentage": 22.35, "elapsed_time": "12:41:38", "remaining_time": "1 day, 20:05:39", "throughput": 4659.39, "total_tokens": 212928504} {"current_steps": 3510, "total_steps": 15680, "loss": 0.34448800086975095, "lr": 8.814363768381242e-06, "epoch": 0.4477040816326531, "percentage": 22.39, "elapsed_time": "12:42:36", "remaining_time": "1 day, 20:04:07", "throughput": 4660.16, "total_tokens": 213231112} {"current_steps": 3515, "total_steps": 15680, "loss": 0.31914894580841063, "lr": 8.81112334648103e-06, "epoch": 0.44834183673469385, "percentage": 22.42, "elapsed_time": "12:43:46", "remaining_time": "1 day, 20:03:19", "throughput": 4659.63, "total_tokens": 213533896} {"current_steps": 3520, "total_steps": 15680, "loss": 0.3257153034210205, "lr": 8.807879099852372e-06, "epoch": 0.4489795918367347, "percentage": 22.45, "elapsed_time": "12:44:46", "remaining_time": "1 day, 20:01:58", "throughput": 4660.01, "total_tokens": 213833744} {"current_steps": 3525, "total_steps": 15680, "loss": 0.3289602041244507, "lr": 8.804631031751096e-06, "epoch": 0.44961734693877553, "percentage": 22.48, "elapsed_time": "12:45:55", "remaining_time": "1 day, 20:01:06", "throughput": 4659.7, "total_tokens": 214140608} {"current_steps": 3530, "total_steps": 15680, "loss": 0.32906880378723147, "lr": 8.801379145436866e-06, "epoch": 0.4502551020408163, "percentage": 22.51, "elapsed_time": "12:46:58", "remaining_time": "1 day, 19:59:51", "throughput": 4659.98, "total_tokens": 214444440} {"current_steps": 3535, "total_steps": 15680, "loss": 0.3326809167861938, "lr": 8.798123444173174e-06, "epoch": 0.45089285714285715, "percentage": 22.54, "elapsed_time": "12:47:59", "remaining_time": "1 day, 19:58:32", "throughput": 4660.73, "total_tokens": 214764408} {"current_steps": 3540, "total_steps": 15680, "loss": 0.3165797233581543, "lr": 8.794863931227346e-06, "epoch": 0.45153061224489793, "percentage": 22.58, "elapsed_time": "12:48:58", "remaining_time": "1 day, 19:57:06", "throughput": 4661.33, "total_tokens": 215066664} {"current_steps": 3545, "total_steps": 15680, "loss": 0.32453289031982424, "lr": 8.79160060987053e-06, "epoch": 0.45216836734693877, "percentage": 22.61, "elapsed_time": "12:49:57", "remaining_time": "1 day, 19:55:41", "throughput": 4662.02, "total_tokens": 215375520} {"current_steps": 3550, "total_steps": 15680, "loss": 0.33482890129089354, "lr": 8.788333483377699e-06, "epoch": 0.4528061224489796, "percentage": 22.64, "elapsed_time": "12:51:04", "remaining_time": "1 day, 19:54:40", "throughput": 4662.0, "total_tokens": 215684472} {"current_steps": 3555, "total_steps": 15680, "loss": 0.32947793006896975, "lr": 8.785062555027637e-06, "epoch": 0.4534438775510204, "percentage": 22.67, "elapsed_time": "12:52:12", "remaining_time": "1 day, 19:53:45", "throughput": 4661.5, "total_tokens": 215978352} {"current_steps": 3560, "total_steps": 15680, "loss": 0.3068972587585449, "lr": 8.781787828102958e-06, "epoch": 0.45408163265306123, "percentage": 22.7, "elapsed_time": "12:53:16", "remaining_time": "1 day, 19:52:36", "throughput": 4661.57, "total_tokens": 216279984} {"current_steps": 3565, "total_steps": 15680, "loss": 0.3233363151550293, "lr": 8.778509305890069e-06, "epoch": 0.45471938775510207, "percentage": 22.74, "elapsed_time": "12:54:21", "remaining_time": "1 day, 19:51:29", "throughput": 4661.7, "total_tokens": 216587936} {"current_steps": 3570, "total_steps": 15680, "loss": 0.31778683662414553, "lr": 8.775226991679205e-06, "epoch": 0.45535714285714285, "percentage": 22.77, "elapsed_time": "12:55:27", "remaining_time": "1 day, 19:50:30", "throughput": 4661.37, "total_tokens": 216883960} {"current_steps": 3575, "total_steps": 15680, "loss": 0.359822940826416, "lr": 8.77194088876439e-06, "epoch": 0.4559948979591837, "percentage": 22.8, "elapsed_time": "12:56:40", "remaining_time": "1 day, 19:49:51", "throughput": 4660.64, "total_tokens": 217190424} {"current_steps": 3580, "total_steps": 15680, "loss": 0.3432753086090088, "lr": 8.768651000443463e-06, "epoch": 0.45663265306122447, "percentage": 22.83, "elapsed_time": "12:57:48", "remaining_time": "1 day, 19:48:53", "throughput": 4660.39, "total_tokens": 217492848} {"current_steps": 3585, "total_steps": 15680, "loss": 0.3330278158187866, "lr": 8.765357330018056e-06, "epoch": 0.4572704081632653, "percentage": 22.86, "elapsed_time": "12:58:53", "remaining_time": "1 day, 19:47:48", "throughput": 4660.52, "total_tokens": 217802264} {"current_steps": 3590, "total_steps": 15680, "loss": 0.31818888187408445, "lr": 8.762059880793595e-06, "epoch": 0.45790816326530615, "percentage": 22.9, "elapsed_time": "13:00:02", "remaining_time": "1 day, 19:46:56", "throughput": 4660.05, "total_tokens": 218101968} {"current_steps": 3595, "total_steps": 15680, "loss": 0.34148919582366943, "lr": 8.758758656079303e-06, "epoch": 0.4585459183673469, "percentage": 22.93, "elapsed_time": "13:00:58", "remaining_time": "1 day, 19:45:19", "throughput": 4661.02, "total_tokens": 218407680} {"current_steps": 3600, "total_steps": 15680, "loss": 0.34990203380584717, "lr": 8.755453659188186e-06, "epoch": 0.45918367346938777, "percentage": 22.96, "elapsed_time": "13:02:03", "remaining_time": "1 day, 19:44:13", "throughput": 4661.09, "total_tokens": 218713272} {"current_steps": 3605, "total_steps": 15680, "loss": 0.3203828573226929, "lr": 8.752144893437045e-06, "epoch": 0.45982142857142855, "percentage": 22.99, "elapsed_time": "13:03:13", "remaining_time": "1 day, 19:43:25", "throughput": 4660.69, "total_tokens": 219022144} {"current_steps": 3610, "total_steps": 15680, "loss": 0.32918357849121094, "lr": 8.748832362146454e-06, "epoch": 0.4604591836734694, "percentage": 23.02, "elapsed_time": "13:04:28", "remaining_time": "1 day, 19:42:53", "throughput": 4659.72, "total_tokens": 219326448} {"current_steps": 3615, "total_steps": 15680, "loss": 0.3219877243041992, "lr": 8.745516068640767e-06, "epoch": 0.4610969387755102, "percentage": 23.05, "elapsed_time": "13:05:31", "remaining_time": "1 day, 19:41:41", "throughput": 4659.81, "total_tokens": 219624856} {"current_steps": 3620, "total_steps": 15680, "loss": 0.3326474666595459, "lr": 8.742196016248121e-06, "epoch": 0.461734693877551, "percentage": 23.09, "elapsed_time": "13:06:26", "remaining_time": "1 day, 19:40:03", "throughput": 4660.73, "total_tokens": 219925872} {"current_steps": 3625, "total_steps": 15680, "loss": 0.3078127384185791, "lr": 8.738872208300417e-06, "epoch": 0.46237244897959184, "percentage": 23.12, "elapsed_time": "13:07:34", "remaining_time": "1 day, 19:39:06", "throughput": 4660.15, "total_tokens": 220214592} {"current_steps": 3630, "total_steps": 15680, "loss": 0.3348182439804077, "lr": 8.735544648133331e-06, "epoch": 0.4630102040816326, "percentage": 23.15, "elapsed_time": "13:08:40", "remaining_time": "1 day, 19:38:03", "throughput": 4660.14, "total_tokens": 220521248} {"current_steps": 3635, "total_steps": 15680, "loss": 0.35152287483215333, "lr": 8.7322133390863e-06, "epoch": 0.46364795918367346, "percentage": 23.18, "elapsed_time": "13:09:54", "remaining_time": "1 day, 19:37:26", "throughput": 4659.0, "total_tokens": 220810352} {"current_steps": 3640, "total_steps": 15680, "loss": 0.3194485902786255, "lr": 8.728878284502526e-06, "epoch": 0.4642857142857143, "percentage": 23.21, "elapsed_time": "13:11:01", "remaining_time": "1 day, 19:36:27", "throughput": 4658.68, "total_tokens": 221106400} {"current_steps": 3645, "total_steps": 15680, "loss": 0.33799190521240235, "lr": 8.725539487728969e-06, "epoch": 0.4649234693877551, "percentage": 23.25, "elapsed_time": "13:12:06", "remaining_time": "1 day, 19:35:23", "throughput": 4658.85, "total_tokens": 221420712} {"current_steps": 3650, "total_steps": 15680, "loss": 0.31893162727355956, "lr": 8.722196952116346e-06, "epoch": 0.4655612244897959, "percentage": 23.28, "elapsed_time": "13:13:12", "remaining_time": "1 day, 19:34:21", "throughput": 4658.8, "total_tokens": 221725936} {"current_steps": 3655, "total_steps": 15680, "loss": 0.3435813426971436, "lr": 8.718850681019125e-06, "epoch": 0.46619897959183676, "percentage": 23.31, "elapsed_time": "13:14:18", "remaining_time": "1 day, 19:33:17", "throughput": 4658.57, "total_tokens": 222021640} {"current_steps": 3660, "total_steps": 15680, "loss": 0.3304643392562866, "lr": 8.715500677795519e-06, "epoch": 0.46683673469387754, "percentage": 23.34, "elapsed_time": "13:15:37", "remaining_time": "1 day, 19:32:57", "throughput": 4657.01, "total_tokens": 222314448} {"current_steps": 3665, "total_steps": 15680, "loss": 0.3191221714019775, "lr": 8.712146945807494e-06, "epoch": 0.4674744897959184, "percentage": 23.37, "elapsed_time": "13:16:35", "remaining_time": "1 day, 19:31:28", "throughput": 4657.83, "total_tokens": 222623648} {"current_steps": 3670, "total_steps": 15680, "loss": 0.32197272777557373, "lr": 8.708789488420753e-06, "epoch": 0.46811224489795916, "percentage": 23.41, "elapsed_time": "13:17:50", "remaining_time": "1 day, 19:30:55", "throughput": 4656.77, "total_tokens": 222922432} {"current_steps": 3675, "total_steps": 15680, "loss": 0.31526567935943606, "lr": 8.705428309004737e-06, "epoch": 0.46875, "percentage": 23.44, "elapsed_time": "13:18:58", "remaining_time": "1 day, 19:30:00", "throughput": 4656.56, "total_tokens": 223229936} {"current_steps": 3680, "total_steps": 15680, "loss": 0.3370952606201172, "lr": 8.702063410932628e-06, "epoch": 0.46938775510204084, "percentage": 23.47, "elapsed_time": "13:20:14", "remaining_time": "1 day, 19:29:27", "throughput": 4655.48, "total_tokens": 223528488} {"current_steps": 3685, "total_steps": 15680, "loss": 0.30045714378356936, "lr": 8.698694797581335e-06, "epoch": 0.4700255102040816, "percentage": 23.5, "elapsed_time": "13:21:28", "remaining_time": "1 day, 19:28:53", "throughput": 4654.34, "total_tokens": 223821368} {"current_steps": 3690, "total_steps": 15680, "loss": 0.34927806854248045, "lr": 8.695322472331497e-06, "epoch": 0.47066326530612246, "percentage": 23.53, "elapsed_time": "13:22:34", "remaining_time": "1 day, 19:27:49", "throughput": 4654.36, "total_tokens": 224128912} {"current_steps": 3695, "total_steps": 15680, "loss": 0.3163304328918457, "lr": 8.691946438567476e-06, "epoch": 0.47130102040816324, "percentage": 23.57, "elapsed_time": "13:23:28", "remaining_time": "1 day, 19:26:08", "throughput": 4655.64, "total_tokens": 224441784} {"current_steps": 3700, "total_steps": 15680, "loss": 0.33351778984069824, "lr": 8.688566699677362e-06, "epoch": 0.4719387755102041, "percentage": 23.6, "elapsed_time": "13:24:21", "remaining_time": "1 day, 19:24:22", "throughput": 4657.04, "total_tokens": 224754568} {"current_steps": 3705, "total_steps": 15680, "loss": 0.32537355422973635, "lr": 8.685183259052951e-06, "epoch": 0.4725765306122449, "percentage": 23.63, "elapsed_time": "13:25:28", "remaining_time": "1 day, 19:23:23", "throughput": 4656.66, "total_tokens": 225050008} {"current_steps": 3710, "total_steps": 15680, "loss": 0.3055689334869385, "lr": 8.68179612008977e-06, "epoch": 0.4732142857142857, "percentage": 23.66, "elapsed_time": "13:26:31", "remaining_time": "1 day, 19:22:11", "throughput": 4656.96, "total_tokens": 225357160} {"current_steps": 3715, "total_steps": 15680, "loss": 0.32492766380310056, "lr": 8.678405286187046e-06, "epoch": 0.47385204081632654, "percentage": 23.69, "elapsed_time": "13:27:27", "remaining_time": "1 day, 19:20:34", "throughput": 4657.97, "total_tokens": 225664864} {"current_steps": 3720, "total_steps": 15680, "loss": 0.31012744903564454, "lr": 8.675010760747717e-06, "epoch": 0.4744897959183674, "percentage": 23.72, "elapsed_time": "13:28:31", "remaining_time": "1 day, 19:19:27", "throughput": 4658.23, "total_tokens": 225978576} {"current_steps": 3725, "total_steps": 15680, "loss": 0.35015435218811036, "lr": 8.671612547178428e-06, "epoch": 0.47512755102040816, "percentage": 23.76, "elapsed_time": "13:29:36", "remaining_time": "1 day, 19:18:20", "throughput": 4658.43, "total_tokens": 226288696} {"current_steps": 3730, "total_steps": 15680, "loss": 0.3316817045211792, "lr": 8.668210648889523e-06, "epoch": 0.475765306122449, "percentage": 23.79, "elapsed_time": "13:30:44", "remaining_time": "1 day, 19:17:26", "throughput": 4658.0, "total_tokens": 226587976} {"current_steps": 3735, "total_steps": 15680, "loss": 0.31617088317871095, "lr": 8.664805069295046e-06, "epoch": 0.4764030612244898, "percentage": 23.82, "elapsed_time": "13:31:47", "remaining_time": "1 day, 19:16:13", "throughput": 4657.99, "total_tokens": 226879712} {"current_steps": 3740, "total_steps": 15680, "loss": 0.3001605987548828, "lr": 8.661395811812732e-06, "epoch": 0.4770408163265306, "percentage": 23.85, "elapsed_time": "13:32:48", "remaining_time": "1 day, 19:14:54", "throughput": 4658.38, "total_tokens": 227183312} {"current_steps": 3745, "total_steps": 15680, "loss": 0.32870779037475584, "lr": 8.657982879864007e-06, "epoch": 0.47767857142857145, "percentage": 23.88, "elapsed_time": "13:33:56", "remaining_time": "1 day, 19:13:56", "throughput": 4658.1, "total_tokens": 227483608} {"current_steps": 3750, "total_steps": 15680, "loss": 0.3120705604553223, "lr": 8.654566276873992e-06, "epoch": 0.47831632653061223, "percentage": 23.92, "elapsed_time": "13:35:05", "remaining_time": "1 day, 19:13:04", "throughput": 4657.52, "total_tokens": 227777824} {"current_steps": 3755, "total_steps": 15680, "loss": 0.33093512058258057, "lr": 8.651146006271483e-06, "epoch": 0.4789540816326531, "percentage": 23.95, "elapsed_time": "13:36:17", "remaining_time": "1 day, 19:12:22", "throughput": 4656.82, "total_tokens": 228081080} {"current_steps": 3760, "total_steps": 15680, "loss": 0.33283772468566897, "lr": 8.64772207148896e-06, "epoch": 0.47959183673469385, "percentage": 23.98, "elapsed_time": "13:37:30", "remaining_time": "1 day, 19:11:40", "throughput": 4656.21, "total_tokens": 228389848} {"current_steps": 3765, "total_steps": 15680, "loss": 0.33153154850006106, "lr": 8.644294475962583e-06, "epoch": 0.4802295918367347, "percentage": 24.01, "elapsed_time": "13:38:35", "remaining_time": "1 day, 19:10:33", "throughput": 4656.13, "total_tokens": 228686136} {"current_steps": 3770, "total_steps": 15680, "loss": 0.3430925846099854, "lr": 8.640863223132183e-06, "epoch": 0.48086734693877553, "percentage": 24.04, "elapsed_time": "13:39:35", "remaining_time": "1 day, 19:09:12", "throughput": 4656.55, "total_tokens": 228987808} {"current_steps": 3775, "total_steps": 15680, "loss": 0.3659370899200439, "lr": 8.63742831644126e-06, "epoch": 0.4815051020408163, "percentage": 24.08, "elapsed_time": "13:40:42", "remaining_time": "1 day, 19:08:13", "throughput": 4656.53, "total_tokens": 229298856} {"current_steps": 3780, "total_steps": 15680, "loss": 0.34424939155578616, "lr": 8.633989759336984e-06, "epoch": 0.48214285714285715, "percentage": 24.11, "elapsed_time": "13:41:50", "remaining_time": "1 day, 19:07:17", "throughput": 4656.2, "total_tokens": 229600528} {"current_steps": 3785, "total_steps": 15680, "loss": 0.3644766330718994, "lr": 8.630547555270187e-06, "epoch": 0.48278061224489793, "percentage": 24.14, "elapsed_time": "13:42:52", "remaining_time": "1 day, 19:06:01", "throughput": 4656.54, "total_tokens": 229905632} {"current_steps": 3790, "total_steps": 15680, "loss": 0.32773098945617674, "lr": 8.627101707695365e-06, "epoch": 0.48341836734693877, "percentage": 24.17, "elapsed_time": "13:43:55", "remaining_time": "1 day, 19:04:49", "throughput": 4656.88, "total_tokens": 230215496} {"current_steps": 3795, "total_steps": 15680, "loss": 0.3321268320083618, "lr": 8.62365222007066e-06, "epoch": 0.4840561224489796, "percentage": 24.2, "elapsed_time": "13:44:53", "remaining_time": "1 day, 19:03:21", "throughput": 4657.47, "total_tokens": 230515376} {"current_steps": 3800, "total_steps": 15680, "loss": 0.3428853988647461, "lr": 8.620199095857877e-06, "epoch": 0.4846938775510204, "percentage": 24.23, "elapsed_time": "13:46:04", "remaining_time": "1 day, 19:02:35", "throughput": 4656.8, "total_tokens": 230814064} {"current_steps": 3805, "total_steps": 15680, "loss": 0.3223045587539673, "lr": 8.616742338522467e-06, "epoch": 0.48533163265306123, "percentage": 24.27, "elapsed_time": "13:47:04", "remaining_time": "1 day, 19:01:11", "throughput": 4657.14, "total_tokens": 231106232} {"current_steps": 3810, "total_steps": 15680, "loss": 0.30772149562835693, "lr": 8.613281951533527e-06, "epoch": 0.48596938775510207, "percentage": 24.3, "elapsed_time": "13:48:11", "remaining_time": "1 day, 19:00:14", "throughput": 4657.07, "total_tokens": 231418568} {"current_steps": 3815, "total_steps": 15680, "loss": 0.3534107685089111, "lr": 8.609817938363799e-06, "epoch": 0.48660714285714285, "percentage": 24.33, "elapsed_time": "13:49:09", "remaining_time": "1 day, 18:58:45", "throughput": 4657.83, "total_tokens": 231724240} {"current_steps": 3820, "total_steps": 15680, "loss": 0.3601125001907349, "lr": 8.60635030248966e-06, "epoch": 0.4872448979591837, "percentage": 24.36, "elapsed_time": "13:50:20", "remaining_time": "1 day, 18:57:57", "throughput": 4657.42, "total_tokens": 232033184} {"current_steps": 3825, "total_steps": 15680, "loss": 0.3287564992904663, "lr": 8.602879047391127e-06, "epoch": 0.48788265306122447, "percentage": 24.39, "elapsed_time": "13:51:27", "remaining_time": "1 day, 18:56:59", "throughput": 4657.1, "total_tokens": 232332512} {"current_steps": 3830, "total_steps": 15680, "loss": 0.33783981800079343, "lr": 8.599404176551843e-06, "epoch": 0.4885204081632653, "percentage": 24.43, "elapsed_time": "13:52:41", "remaining_time": "1 day, 18:56:19", "throughput": 4656.47, "total_tokens": 232642256} {"current_steps": 3835, "total_steps": 15680, "loss": 0.32908217906951903, "lr": 8.595925693459086e-06, "epoch": 0.48915816326530615, "percentage": 24.46, "elapsed_time": "13:53:49", "remaining_time": "1 day, 18:55:23", "throughput": 4655.99, "total_tokens": 232936208} {"current_steps": 3840, "total_steps": 15680, "loss": 0.3408887624740601, "lr": 8.59244360160376e-06, "epoch": 0.4897959183673469, "percentage": 24.49, "elapsed_time": "13:54:42", "remaining_time": "1 day, 18:53:40", "throughput": 4657.42, "total_tokens": 233254512} {"current_steps": 3845, "total_steps": 15680, "loss": 0.3298821449279785, "lr": 8.588957904480381e-06, "epoch": 0.49043367346938777, "percentage": 24.52, "elapsed_time": "13:55:53", "remaining_time": "1 day, 18:52:53", "throughput": 4656.74, "total_tokens": 233551432} {"current_steps": 3850, "total_steps": 15680, "loss": 0.3687849521636963, "lr": 8.585468605587094e-06, "epoch": 0.49107142857142855, "percentage": 24.55, "elapsed_time": "13:57:01", "remaining_time": "1 day, 18:51:58", "throughput": 4656.06, "total_tokens": 233836184} {"current_steps": 3855, "total_steps": 15680, "loss": 0.34029111862182615, "lr": 8.581975708425652e-06, "epoch": 0.4917091836734694, "percentage": 24.59, "elapsed_time": "13:58:13", "remaining_time": "1 day, 18:51:13", "throughput": 4655.65, "total_tokens": 234149936} {"current_steps": 3860, "total_steps": 15680, "loss": 0.32351346015930177, "lr": 8.578479216501422e-06, "epoch": 0.4923469387755102, "percentage": 24.62, "elapsed_time": "13:59:26", "remaining_time": "1 day, 18:50:30", "throughput": 4654.8, "total_tokens": 234445496} {"current_steps": 3865, "total_steps": 15680, "loss": 0.3432778835296631, "lr": 8.574979133323378e-06, "epoch": 0.492984693877551, "percentage": 24.65, "elapsed_time": "14:00:33", "remaining_time": "1 day, 18:49:30", "throughput": 4654.98, "total_tokens": 234765680} {"current_steps": 3870, "total_steps": 15680, "loss": 0.3516408443450928, "lr": 8.571475462404098e-06, "epoch": 0.49362244897959184, "percentage": 24.68, "elapsed_time": "14:01:36", "remaining_time": "1 day, 18:48:20", "throughput": 4655.19, "total_tokens": 235072624} {"current_steps": 3875, "total_steps": 15680, "loss": 0.3464944839477539, "lr": 8.567968207259759e-06, "epoch": 0.4942602040816326, "percentage": 24.71, "elapsed_time": "14:02:34", "remaining_time": "1 day, 18:46:52", "throughput": 4655.95, "total_tokens": 235380696} {"current_steps": 3880, "total_steps": 15680, "loss": 0.3397261619567871, "lr": 8.564457371410139e-06, "epoch": 0.49489795918367346, "percentage": 24.74, "elapsed_time": "14:03:32", "remaining_time": "1 day, 18:45:24", "throughput": 4656.81, "total_tokens": 235692760} {"current_steps": 3885, "total_steps": 15680, "loss": 0.34970316886901853, "lr": 8.560942958378604e-06, "epoch": 0.4955357142857143, "percentage": 24.78, "elapsed_time": "14:04:36", "remaining_time": "1 day, 18:44:15", "throughput": 4657.03, "total_tokens": 236001480} {"current_steps": 3890, "total_steps": 15680, "loss": 0.35130982398986815, "lr": 8.557424971692117e-06, "epoch": 0.4961734693877551, "percentage": 24.81, "elapsed_time": "14:05:47", "remaining_time": "1 day, 18:43:26", "throughput": 4656.55, "total_tokens": 236306648} {"current_steps": 3895, "total_steps": 15680, "loss": 0.3193791389465332, "lr": 8.55390341488122e-06, "epoch": 0.4968112244897959, "percentage": 24.84, "elapsed_time": "14:06:50", "remaining_time": "1 day, 18:42:15", "throughput": 4656.62, "total_tokens": 236604488} {"current_steps": 3900, "total_steps": 15680, "loss": 0.3339862823486328, "lr": 8.550378291480041e-06, "epoch": 0.49744897959183676, "percentage": 24.87, "elapsed_time": "14:07:51", "remaining_time": "1 day, 18:40:58", "throughput": 4656.93, "total_tokens": 236905912} {"current_steps": 3905, "total_steps": 15680, "loss": 0.32977321147918703, "lr": 8.54684960502629e-06, "epoch": 0.49808673469387754, "percentage": 24.9, "elapsed_time": "14:08:54", "remaining_time": "1 day, 18:39:46", "throughput": 4656.9, "total_tokens": 237197104} {"current_steps": 3910, "total_steps": 15680, "loss": 0.32253079414367675, "lr": 8.543317359061247e-06, "epoch": 0.4987244897959184, "percentage": 24.94, "elapsed_time": "14:09:56", "remaining_time": "1 day, 18:38:30", "throughput": 4657.32, "total_tokens": 237505528} {"current_steps": 3915, "total_steps": 15680, "loss": 0.3567155361175537, "lr": 8.539781557129772e-06, "epoch": 0.49936224489795916, "percentage": 24.97, "elapsed_time": "14:10:57", "remaining_time": "1 day, 18:37:14", "throughput": 4657.74, "total_tokens": 237813768} {"current_steps": 3920, "total_steps": 15680, "loss": 0.34138736724853513, "lr": 8.536242202780285e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "14:11:56", "remaining_time": "1 day, 18:35:49", "throughput": 4658.55, "total_tokens": 238128160} {"current_steps": 3925, "total_steps": 15680, "loss": 0.33693814277648926, "lr": 8.532699299564777e-06, "epoch": 0.5006377551020408, "percentage": 25.03, "elapsed_time": "14:13:09", "remaining_time": "1 day, 18:35:06", "throughput": 4657.73, "total_tokens": 238424680} {"current_steps": 3930, "total_steps": 15680, "loss": 0.3420262813568115, "lr": 8.529152851038798e-06, "epoch": 0.5012755102040817, "percentage": 25.06, "elapsed_time": "14:14:08", "remaining_time": "1 day, 18:33:44", "throughput": 4658.22, "total_tokens": 238728160} {"current_steps": 3935, "total_steps": 15680, "loss": 0.3414464473724365, "lr": 8.52560286076146e-06, "epoch": 0.5019132653061225, "percentage": 25.1, "elapsed_time": "14:15:12", "remaining_time": "1 day, 18:32:36", "throughput": 4658.21, "total_tokens": 239026280} {"current_steps": 3940, "total_steps": 15680, "loss": 0.3040300369262695, "lr": 8.522049332295421e-06, "epoch": 0.5025510204081632, "percentage": 25.13, "elapsed_time": "14:16:15", "remaining_time": "1 day, 18:31:22", "throughput": 4658.48, "total_tokens": 239330112} {"current_steps": 3945, "total_steps": 15680, "loss": 0.30737330913543703, "lr": 8.5184922692069e-06, "epoch": 0.5031887755102041, "percentage": 25.16, "elapsed_time": "14:17:22", "remaining_time": "1 day, 18:30:22", "throughput": 4658.12, "total_tokens": 239623416} {"current_steps": 3950, "total_steps": 15680, "loss": 0.34375686645507814, "lr": 8.514931675065654e-06, "epoch": 0.5038265306122449, "percentage": 25.19, "elapsed_time": "14:18:17", "remaining_time": "1 day, 18:28:46", "throughput": 4659.46, "total_tokens": 239949088} {"current_steps": 3955, "total_steps": 15680, "loss": 0.3413503646850586, "lr": 8.51136755344499e-06, "epoch": 0.5044642857142857, "percentage": 25.22, "elapsed_time": "14:19:30", "remaining_time": "1 day, 18:28:04", "throughput": 4658.71, "total_tokens": 240249752} {"current_steps": 3960, "total_steps": 15680, "loss": 0.34429771900177003, "lr": 8.507799907921754e-06, "epoch": 0.5051020408163265, "percentage": 25.26, "elapsed_time": "14:20:34", "remaining_time": "1 day, 18:26:57", "throughput": 4658.93, "total_tokens": 240561680} {"current_steps": 3965, "total_steps": 15680, "loss": 0.2996108055114746, "lr": 8.504228742076325e-06, "epoch": 0.5057397959183674, "percentage": 25.29, "elapsed_time": "14:21:41", "remaining_time": "1 day, 18:25:57", "throughput": 4658.9, "total_tokens": 240872848} {"current_steps": 3970, "total_steps": 15680, "loss": 0.3469754934310913, "lr": 8.500654059492618e-06, "epoch": 0.5063775510204082, "percentage": 25.32, "elapsed_time": "14:22:52", "remaining_time": "1 day, 18:25:09", "throughput": 4658.34, "total_tokens": 241173696} {"current_steps": 3975, "total_steps": 15680, "loss": 0.33405184745788574, "lr": 8.497075863758079e-06, "epoch": 0.5070153061224489, "percentage": 25.35, "elapsed_time": "14:23:46", "remaining_time": "1 day, 18:23:30", "throughput": 4659.34, "total_tokens": 241476848} {"current_steps": 3980, "total_steps": 15680, "loss": 0.34064507484436035, "lr": 8.493494158463674e-06, "epoch": 0.5076530612244898, "percentage": 25.38, "elapsed_time": "14:24:49", "remaining_time": "1 day, 18:22:18", "throughput": 4659.34, "total_tokens": 241769888} {"current_steps": 3985, "total_steps": 15680, "loss": 0.32036867141723635, "lr": 8.489908947203897e-06, "epoch": 0.5082908163265306, "percentage": 25.41, "elapsed_time": "14:25:52", "remaining_time": "1 day, 18:21:08", "throughput": 4659.51, "total_tokens": 242074176} {"current_steps": 3990, "total_steps": 15680, "loss": 0.33285179138183596, "lr": 8.486320233576757e-06, "epoch": 0.5089285714285714, "percentage": 25.45, "elapsed_time": "14:26:57", "remaining_time": "1 day, 18:20:02", "throughput": 4659.25, "total_tokens": 242362680} {"current_steps": 3995, "total_steps": 15680, "loss": 0.3297649145126343, "lr": 8.482728021183777e-06, "epoch": 0.5095663265306123, "percentage": 25.48, "elapsed_time": "14:27:58", "remaining_time": "1 day, 18:18:43", "throughput": 4659.42, "total_tokens": 242654240} {"current_steps": 4000, "total_steps": 15680, "loss": 0.3276358127593994, "lr": 8.479132313629996e-06, "epoch": 0.5102040816326531, "percentage": 25.51, "elapsed_time": "14:29:08", "remaining_time": "1 day, 18:17:52", "throughput": 4658.94, "total_tokens": 242954720} {"current_steps": 4005, "total_steps": 15680, "loss": 0.3316447019577026, "lr": 8.475533114523954e-06, "epoch": 0.5108418367346939, "percentage": 25.54, "elapsed_time": "14:30:08", "remaining_time": "1 day, 18:16:34", "throughput": 4659.49, "total_tokens": 243266952} {"current_steps": 4010, "total_steps": 15680, "loss": 0.34278225898742676, "lr": 8.471930427477704e-06, "epoch": 0.5114795918367347, "percentage": 25.57, "elapsed_time": "14:31:14", "remaining_time": "1 day, 18:15:31", "throughput": 4659.27, "total_tokens": 243562512} {"current_steps": 4015, "total_steps": 15680, "loss": 0.3474293231964111, "lr": 8.468324256106789e-06, "epoch": 0.5121173469387755, "percentage": 25.61, "elapsed_time": "14:31:59", "remaining_time": "1 day, 18:13:26", "throughput": 4661.12, "total_tokens": 243867856} {"current_steps": 4020, "total_steps": 15680, "loss": 0.3270159482955933, "lr": 8.464714604030256e-06, "epoch": 0.5127551020408163, "percentage": 25.64, "elapsed_time": "14:32:57", "remaining_time": "1 day, 18:11:59", "throughput": 4661.51, "total_tokens": 244155792} {"current_steps": 4025, "total_steps": 15680, "loss": 0.32132925987243655, "lr": 8.461101474870642e-06, "epoch": 0.5133928571428571, "percentage": 25.67, "elapsed_time": "14:33:56", "remaining_time": "1 day, 18:10:36", "throughput": 4661.95, "total_tokens": 244454032} {"current_steps": 4030, "total_steps": 15680, "loss": 0.33786468505859374, "lr": 8.457484872253976e-06, "epoch": 0.514030612244898, "percentage": 25.7, "elapsed_time": "14:35:10", "remaining_time": "1 day, 18:09:58", "throughput": 4661.11, "total_tokens": 244756848} {"current_steps": 4035, "total_steps": 15680, "loss": 0.3316938877105713, "lr": 8.453864799809772e-06, "epoch": 0.5146683673469388, "percentage": 25.73, "elapsed_time": "14:36:06", "remaining_time": "1 day, 18:08:25", "throughput": 4662.08, "total_tokens": 245066784} {"current_steps": 4040, "total_steps": 15680, "loss": 0.3056922435760498, "lr": 8.450241261171022e-06, "epoch": 0.5153061224489796, "percentage": 25.77, "elapsed_time": "14:37:13", "remaining_time": "1 day, 18:07:28", "throughput": 4661.44, "total_tokens": 245349960} {"current_steps": 4045, "total_steps": 15680, "loss": 0.3409639835357666, "lr": 8.446614259974201e-06, "epoch": 0.5159438775510204, "percentage": 25.8, "elapsed_time": "14:38:15", "remaining_time": "1 day, 18:06:11", "throughput": 4661.83, "total_tokens": 245655704} {"current_steps": 4050, "total_steps": 15680, "loss": 0.32842864990234377, "lr": 8.44298379985926e-06, "epoch": 0.5165816326530612, "percentage": 25.83, "elapsed_time": "14:39:22", "remaining_time": "1 day, 18:05:14", "throughput": 4661.45, "total_tokens": 245951352} {"current_steps": 4055, "total_steps": 15680, "loss": 0.32632737159729003, "lr": 8.439349884469621e-06, "epoch": 0.517219387755102, "percentage": 25.86, "elapsed_time": "14:40:38", "remaining_time": "1 day, 18:04:40", "throughput": 4660.6, "total_tokens": 246260984} {"current_steps": 4060, "total_steps": 15680, "loss": 0.3498189926147461, "lr": 8.435712517452167e-06, "epoch": 0.5178571428571429, "percentage": 25.89, "elapsed_time": "14:41:41", "remaining_time": "1 day, 18:03:27", "throughput": 4661.14, "total_tokens": 246580168} {"current_steps": 4065, "total_steps": 15680, "loss": 0.32159740924835206, "lr": 8.432071702457253e-06, "epoch": 0.5184948979591837, "percentage": 25.92, "elapsed_time": "14:42:51", "remaining_time": "1 day, 18:02:36", "throughput": 4660.46, "total_tokens": 246871632} {"current_steps": 4070, "total_steps": 15680, "loss": 0.3185391426086426, "lr": 8.428427443138689e-06, "epoch": 0.5191326530612245, "percentage": 25.96, "elapsed_time": "14:43:59", "remaining_time": "1 day, 18:01:40", "throughput": 4660.18, "total_tokens": 247174896} {"current_steps": 4075, "total_steps": 15680, "loss": 0.3615418910980225, "lr": 8.424779743153747e-06, "epoch": 0.5197704081632653, "percentage": 25.99, "elapsed_time": "14:45:17", "remaining_time": "1 day, 18:01:11", "throughput": 4659.15, "total_tokens": 247484000} {"current_steps": 4080, "total_steps": 15680, "loss": 0.3403435230255127, "lr": 8.421128606163145e-06, "epoch": 0.5204081632653061, "percentage": 26.02, "elapsed_time": "14:46:27", "remaining_time": "1 day, 18:00:19", "throughput": 4658.68, "total_tokens": 247782864} {"current_steps": 4085, "total_steps": 15680, "loss": 0.3410142183303833, "lr": 8.417474035831055e-06, "epoch": 0.5210459183673469, "percentage": 26.05, "elapsed_time": "14:47:43", "remaining_time": "1 day, 17:59:45", "throughput": 4657.79, "total_tokens": 248091320} {"current_steps": 4090, "total_steps": 15680, "loss": 0.3152641296386719, "lr": 8.413816035825095e-06, "epoch": 0.5216836734693877, "percentage": 26.08, "elapsed_time": "14:48:51", "remaining_time": "1 day, 17:58:47", "throughput": 4657.33, "total_tokens": 248381832} {"current_steps": 4095, "total_steps": 15680, "loss": 0.3589243173599243, "lr": 8.410154609816324e-06, "epoch": 0.5223214285714286, "percentage": 26.12, "elapsed_time": "14:49:54", "remaining_time": "1 day, 17:57:36", "throughput": 4657.67, "total_tokens": 248693944} {"current_steps": 4100, "total_steps": 15680, "loss": 0.3444381237030029, "lr": 8.406489761479235e-06, "epoch": 0.5229591836734694, "percentage": 26.15, "elapsed_time": "14:51:07", "remaining_time": "1 day, 17:56:53", "throughput": 4656.83, "total_tokens": 248989360} {"current_steps": 4105, "total_steps": 15680, "loss": 0.3539252519607544, "lr": 8.402821494491762e-06, "epoch": 0.5235969387755102, "percentage": 26.18, "elapsed_time": "14:52:05", "remaining_time": "1 day, 17:55:26", "throughput": 4657.51, "total_tokens": 249294192} {"current_steps": 4110, "total_steps": 15680, "loss": 0.3387748718261719, "lr": 8.399149812535269e-06, "epoch": 0.5242346938775511, "percentage": 26.21, "elapsed_time": "14:52:55", "remaining_time": "1 day, 17:53:39", "throughput": 4658.84, "total_tokens": 249599112} {"current_steps": 4115, "total_steps": 15680, "loss": 0.3216937780380249, "lr": 8.395474719294541e-06, "epoch": 0.5248724489795918, "percentage": 26.24, "elapsed_time": "14:53:53", "remaining_time": "1 day, 17:52:13", "throughput": 4659.33, "total_tokens": 249894528} {"current_steps": 4120, "total_steps": 15680, "loss": 0.3277886390686035, "lr": 8.391796218457794e-06, "epoch": 0.5255102040816326, "percentage": 26.28, "elapsed_time": "14:54:48", "remaining_time": "1 day, 17:50:41", "throughput": 4660.15, "total_tokens": 250198456} {"current_steps": 4125, "total_steps": 15680, "loss": 0.3698796510696411, "lr": 8.388114313716658e-06, "epoch": 0.5261479591836735, "percentage": 26.31, "elapsed_time": "14:55:55", "remaining_time": "1 day, 17:49:39", "throughput": 4660.14, "total_tokens": 250505920} {"current_steps": 4130, "total_steps": 15680, "loss": 0.34650416374206544, "lr": 8.384429008766183e-06, "epoch": 0.5267857142857143, "percentage": 26.34, "elapsed_time": "14:56:57", "remaining_time": "1 day, 17:48:25", "throughput": 4660.61, "total_tokens": 250820328} {"current_steps": 4135, "total_steps": 15680, "loss": 0.31575334072113037, "lr": 8.380740307304831e-06, "epoch": 0.5274234693877551, "percentage": 26.37, "elapsed_time": "14:57:54", "remaining_time": "1 day, 17:46:59", "throughput": 4661.23, "total_tokens": 251122984} {"current_steps": 4140, "total_steps": 15680, "loss": 0.3536393642425537, "lr": 8.377048213034469e-06, "epoch": 0.5280612244897959, "percentage": 26.4, "elapsed_time": "14:59:09", "remaining_time": "1 day, 17:46:21", "throughput": 4660.3, "total_tokens": 251421264} {"current_steps": 4145, "total_steps": 15680, "loss": 0.35466365814208983, "lr": 8.373352729660373e-06, "epoch": 0.5286989795918368, "percentage": 26.43, "elapsed_time": "15:00:22", "remaining_time": "1 day, 17:45:37", "throughput": 4659.75, "total_tokens": 251730568} {"current_steps": 4150, "total_steps": 15680, "loss": 0.3340321063995361, "lr": 8.369653860891218e-06, "epoch": 0.5293367346938775, "percentage": 26.47, "elapsed_time": "15:01:28", "remaining_time": "1 day, 17:44:34", "throughput": 4659.7, "total_tokens": 252036272} {"current_steps": 4155, "total_steps": 15680, "loss": 0.3348118543624878, "lr": 8.365951610439078e-06, "epoch": 0.5299744897959183, "percentage": 26.5, "elapsed_time": "15:02:24", "remaining_time": "1 day, 17:43:03", "throughput": 4660.51, "total_tokens": 252339592} {"current_steps": 4160, "total_steps": 15680, "loss": 0.3383298397064209, "lr": 8.362245982019419e-06, "epoch": 0.5306122448979592, "percentage": 26.53, "elapsed_time": "15:03:15", "remaining_time": "1 day, 17:41:18", "throughput": 4661.82, "total_tokens": 252647808} {"current_steps": 4165, "total_steps": 15680, "loss": 0.3288172721862793, "lr": 8.358536979351098e-06, "epoch": 0.53125, "percentage": 26.56, "elapsed_time": "15:04:15", "remaining_time": "1 day, 17:40:01", "throughput": 4662.29, "total_tokens": 252955704} {"current_steps": 4170, "total_steps": 15680, "loss": 0.33261590003967284, "lr": 8.35482460615636e-06, "epoch": 0.5318877551020408, "percentage": 26.59, "elapsed_time": "15:05:31", "remaining_time": "1 day, 17:39:26", "throughput": 4661.28, "total_tokens": 253256544} {"current_steps": 4175, "total_steps": 15680, "loss": 0.3089122295379639, "lr": 8.351108866160827e-06, "epoch": 0.5325255102040817, "percentage": 26.63, "elapsed_time": "15:06:35", "remaining_time": "1 day, 17:38:15", "throughput": 4661.49, "total_tokens": 253562032} {"current_steps": 4180, "total_steps": 15680, "loss": 0.3515080213546753, "lr": 8.347389763093507e-06, "epoch": 0.5331632653061225, "percentage": 26.66, "elapsed_time": "15:07:35", "remaining_time": "1 day, 17:36:58", "throughput": 4661.82, "total_tokens": 253862712} {"current_steps": 4185, "total_steps": 15680, "loss": 0.3021442651748657, "lr": 8.34366730068678e-06, "epoch": 0.5338010204081632, "percentage": 26.69, "elapsed_time": "15:08:42", "remaining_time": "1 day, 17:35:59", "throughput": 4661.85, "total_tokens": 254178096} {"current_steps": 4190, "total_steps": 15680, "loss": 0.3398129940032959, "lr": 8.339941482676394e-06, "epoch": 0.5344387755102041, "percentage": 26.72, "elapsed_time": "15:09:56", "remaining_time": "1 day, 17:35:18", "throughput": 4660.93, "total_tokens": 254472504} {"current_steps": 4195, "total_steps": 15680, "loss": 0.33443522453308105, "lr": 8.336212312801469e-06, "epoch": 0.5350765306122449, "percentage": 26.75, "elapsed_time": "15:10:46", "remaining_time": "1 day, 17:33:30", "throughput": 4662.34, "total_tokens": 254780208} {"current_steps": 4200, "total_steps": 15680, "loss": 0.32670321464538576, "lr": 8.332479794804489e-06, "epoch": 0.5357142857142857, "percentage": 26.79, "elapsed_time": "15:12:02", "remaining_time": "1 day, 17:32:53", "throughput": 4661.52, "total_tokens": 255088280} {"current_steps": 4205, "total_steps": 15680, "loss": 0.3391838312149048, "lr": 8.328743932431293e-06, "epoch": 0.5363520408163265, "percentage": 26.82, "elapsed_time": "15:13:02", "remaining_time": "1 day, 17:31:34", "throughput": 4662.09, "total_tokens": 255398952} {"current_steps": 4210, "total_steps": 15680, "loss": 0.33151419162750245, "lr": 8.325004729431083e-06, "epoch": 0.5369897959183674, "percentage": 26.85, "elapsed_time": "15:14:00", "remaining_time": "1 day, 17:30:11", "throughput": 4662.77, "total_tokens": 255709048} {"current_steps": 4215, "total_steps": 15680, "loss": 0.32023797035217283, "lr": 8.32126218955641e-06, "epoch": 0.5376275510204082, "percentage": 26.88, "elapsed_time": "15:15:13", "remaining_time": "1 day, 17:29:28", "throughput": 4661.99, "total_tokens": 256007488} {"current_steps": 4220, "total_steps": 15680, "loss": 0.33050549030303955, "lr": 8.317516316563172e-06, "epoch": 0.5382653061224489, "percentage": 26.91, "elapsed_time": "15:16:16", "remaining_time": "1 day, 17:28:15", "throughput": 4662.24, "total_tokens": 256312784} {"current_steps": 4225, "total_steps": 15680, "loss": 0.3239306449890137, "lr": 8.313767114210615e-06, "epoch": 0.5389030612244898, "percentage": 26.95, "elapsed_time": "15:17:23", "remaining_time": "1 day, 17:27:17", "throughput": 4661.94, "total_tokens": 256610864} {"current_steps": 4230, "total_steps": 15680, "loss": 0.32516295909881593, "lr": 8.310014586261329e-06, "epoch": 0.5395408163265306, "percentage": 26.98, "elapsed_time": "15:18:37", "remaining_time": "1 day, 17:26:34", "throughput": 4661.05, "total_tokens": 256905128} {"current_steps": 4235, "total_steps": 15680, "loss": 0.321623706817627, "lr": 8.306258736481231e-06, "epoch": 0.5401785714285714, "percentage": 27.01, "elapsed_time": "15:19:27", "remaining_time": "1 day, 17:24:48", "throughput": 4662.55, "total_tokens": 257220440} {"current_steps": 4240, "total_steps": 15680, "loss": 0.3558704376220703, "lr": 8.302499568639583e-06, "epoch": 0.5408163265306123, "percentage": 27.04, "elapsed_time": "15:20:27", "remaining_time": "1 day, 17:23:30", "throughput": 4663.06, "total_tokens": 257529992} {"current_steps": 4245, "total_steps": 15680, "loss": 0.3280658721923828, "lr": 8.298737086508973e-06, "epoch": 0.5414540816326531, "percentage": 27.07, "elapsed_time": "15:21:31", "remaining_time": "1 day, 17:22:22", "throughput": 4663.07, "total_tokens": 257830008} {"current_steps": 4250, "total_steps": 15680, "loss": 0.32333903312683104, "lr": 8.294971293865315e-06, "epoch": 0.5420918367346939, "percentage": 27.1, "elapsed_time": "15:22:43", "remaining_time": "1 day, 17:21:34", "throughput": 4662.55, "total_tokens": 258134680} {"current_steps": 4255, "total_steps": 15680, "loss": 0.337364649772644, "lr": 8.29120219448784e-06, "epoch": 0.5427295918367347, "percentage": 27.14, "elapsed_time": "15:23:54", "remaining_time": "1 day, 17:20:45", "throughput": 4662.09, "total_tokens": 258440416} {"current_steps": 4260, "total_steps": 15680, "loss": 0.33406877517700195, "lr": 8.287429792159108e-06, "epoch": 0.5433673469387755, "percentage": 27.17, "elapsed_time": "15:25:07", "remaining_time": "1 day, 17:20:01", "throughput": 4661.24, "total_tokens": 258733896} {"current_steps": 4265, "total_steps": 15680, "loss": 0.32870163917541506, "lr": 8.283654090664986e-06, "epoch": 0.5440051020408163, "percentage": 27.2, "elapsed_time": "15:26:16", "remaining_time": "1 day, 17:19:06", "throughput": 4661.01, "total_tokens": 259042576} {"current_steps": 4270, "total_steps": 15680, "loss": 0.3245696544647217, "lr": 8.279875093794652e-06, "epoch": 0.5446428571428571, "percentage": 27.23, "elapsed_time": "15:27:24", "remaining_time": "1 day, 17:18:10", "throughput": 4660.78, "total_tokens": 259348728} {"current_steps": 4275, "total_steps": 15680, "loss": 0.35511810779571534, "lr": 8.276092805340596e-06, "epoch": 0.545280612244898, "percentage": 27.26, "elapsed_time": "15:28:26", "remaining_time": "1 day, 17:16:56", "throughput": 4661.03, "total_tokens": 259651088} {"current_steps": 4280, "total_steps": 15680, "loss": 0.3598794460296631, "lr": 8.27230722909861e-06, "epoch": 0.5459183673469388, "percentage": 27.3, "elapsed_time": "15:29:28", "remaining_time": "1 day, 17:15:42", "throughput": 4661.37, "total_tokens": 259958224} {"current_steps": 4285, "total_steps": 15680, "loss": 0.33161163330078125, "lr": 8.268518368867781e-06, "epoch": 0.5465561224489796, "percentage": 27.33, "elapsed_time": "15:30:33", "remaining_time": "1 day, 17:14:38", "throughput": 4661.16, "total_tokens": 260251048} {"current_steps": 4290, "total_steps": 15680, "loss": 0.3262234449386597, "lr": 8.264726228450495e-06, "epoch": 0.5471938775510204, "percentage": 27.36, "elapsed_time": "15:31:45", "remaining_time": "1 day, 17:13:49", "throughput": 4660.65, "total_tokens": 260554448} {"current_steps": 4295, "total_steps": 15680, "loss": 0.30494074821472167, "lr": 8.260930811652433e-06, "epoch": 0.5478316326530612, "percentage": 27.39, "elapsed_time": "15:32:54", "remaining_time": "1 day, 17:12:54", "throughput": 4660.33, "total_tokens": 260860120} {"current_steps": 4300, "total_steps": 15680, "loss": 0.3426995754241943, "lr": 8.257132122282557e-06, "epoch": 0.548469387755102, "percentage": 27.42, "elapsed_time": "15:34:00", "remaining_time": "1 day, 17:11:51", "throughput": 4660.07, "total_tokens": 261152392} {"current_steps": 4305, "total_steps": 15680, "loss": 0.35701465606689453, "lr": 8.253330164153118e-06, "epoch": 0.5491071428571429, "percentage": 27.46, "elapsed_time": "15:35:03", "remaining_time": "1 day, 17:10:39", "throughput": 4660.33, "total_tokens": 261458776} {"current_steps": 4310, "total_steps": 15680, "loss": 0.3199004650115967, "lr": 8.24952494107965e-06, "epoch": 0.5497448979591837, "percentage": 27.49, "elapsed_time": "15:36:14", "remaining_time": "1 day, 17:09:52", "throughput": 4659.52, "total_tokens": 261748456} {"current_steps": 4315, "total_steps": 15680, "loss": 0.32810063362121583, "lr": 8.245716456880954e-06, "epoch": 0.5503826530612245, "percentage": 27.52, "elapsed_time": "15:37:24", "remaining_time": "1 day, 17:08:58", "throughput": 4659.16, "total_tokens": 262052304} {"current_steps": 4320, "total_steps": 15680, "loss": 0.30528922080993653, "lr": 8.241904715379115e-06, "epoch": 0.5510204081632653, "percentage": 27.55, "elapsed_time": "15:38:30", "remaining_time": "1 day, 17:07:55", "throughput": 4658.81, "total_tokens": 262339992} {"current_steps": 4325, "total_steps": 15680, "loss": 0.3237664222717285, "lr": 8.23808972039948e-06, "epoch": 0.5516581632653061, "percentage": 27.58, "elapsed_time": "15:39:45", "remaining_time": "1 day, 17:07:15", "throughput": 4658.0, "total_tokens": 262641960} {"current_steps": 4330, "total_steps": 15680, "loss": 0.345841646194458, "lr": 8.234271475770662e-06, "epoch": 0.5522959183673469, "percentage": 27.61, "elapsed_time": "15:40:45", "remaining_time": "1 day, 17:05:56", "throughput": 4658.42, "total_tokens": 262946000} {"current_steps": 4335, "total_steps": 15680, "loss": 0.35211758613586425, "lr": 8.230449985324538e-06, "epoch": 0.5529336734693877, "percentage": 27.65, "elapsed_time": "15:41:37", "remaining_time": "1 day, 17:04:18", "throughput": 4659.37, "total_tokens": 263244136} {"current_steps": 4340, "total_steps": 15680, "loss": 0.3599707126617432, "lr": 8.226625252896239e-06, "epoch": 0.5535714285714286, "percentage": 27.68, "elapsed_time": "15:42:38", "remaining_time": "1 day, 17:03:02", "throughput": 4659.91, "total_tokens": 263558408} {"current_steps": 4345, "total_steps": 15680, "loss": 0.34988815784454347, "lr": 8.222797282324152e-06, "epoch": 0.5542091836734694, "percentage": 27.71, "elapsed_time": "15:43:44", "remaining_time": "1 day, 17:01:58", "throughput": 4659.98, "total_tokens": 263867960} {"current_steps": 4350, "total_steps": 15680, "loss": 0.31808695793151853, "lr": 8.218966077449912e-06, "epoch": 0.5548469387755102, "percentage": 27.74, "elapsed_time": "15:44:54", "remaining_time": "1 day, 17:01:05", "throughput": 4659.59, "total_tokens": 264172056} {"current_steps": 4355, "total_steps": 15680, "loss": 0.32405288219451905, "lr": 8.215131642118401e-06, "epoch": 0.5554846938775511, "percentage": 27.77, "elapsed_time": "15:45:48", "remaining_time": "1 day, 16:59:33", "throughput": 4660.61, "total_tokens": 264484880} {"current_steps": 4360, "total_steps": 15680, "loss": 0.34016482830047606, "lr": 8.211293980177744e-06, "epoch": 0.5561224489795918, "percentage": 27.81, "elapsed_time": "15:46:52", "remaining_time": "1 day, 16:58:23", "throughput": 4660.7, "total_tokens": 264784920} {"current_steps": 4365, "total_steps": 15680, "loss": 0.3228370904922485, "lr": 8.2074530954793e-06, "epoch": 0.5567602040816326, "percentage": 27.84, "elapsed_time": "15:47:58", "remaining_time": "1 day, 16:57:21", "throughput": 4660.57, "total_tokens": 265087688} {"current_steps": 4370, "total_steps": 15680, "loss": 0.33140063285827637, "lr": 8.203608991877669e-06, "epoch": 0.5573979591836735, "percentage": 27.87, "elapsed_time": "15:49:03", "remaining_time": "1 day, 16:56:14", "throughput": 4660.34, "total_tokens": 265373784} {"current_steps": 4375, "total_steps": 15680, "loss": 0.3155759334564209, "lr": 8.199761673230674e-06, "epoch": 0.5580357142857143, "percentage": 27.9, "elapsed_time": "15:50:07", "remaining_time": "1 day, 16:55:07", "throughput": 4660.54, "total_tokens": 265686896} {"current_steps": 4380, "total_steps": 15680, "loss": 0.3315152168273926, "lr": 8.195911143399368e-06, "epoch": 0.5586734693877551, "percentage": 27.93, "elapsed_time": "15:51:14", "remaining_time": "1 day, 16:54:06", "throughput": 4660.23, "total_tokens": 265979352} {"current_steps": 4385, "total_steps": 15680, "loss": 0.3102290153503418, "lr": 8.192057406248028e-06, "epoch": 0.5593112244897959, "percentage": 27.97, "elapsed_time": "15:52:14", "remaining_time": "1 day, 16:52:47", "throughput": 4660.47, "total_tokens": 266271928} {"current_steps": 4390, "total_steps": 15680, "loss": 0.33108863830566404, "lr": 8.18820046564415e-06, "epoch": 0.5599489795918368, "percentage": 28.0, "elapsed_time": "15:53:11", "remaining_time": "1 day, 16:51:21", "throughput": 4661.18, "total_tokens": 266577400} {"current_steps": 4395, "total_steps": 15680, "loss": 0.3300520658493042, "lr": 8.184340325458439e-06, "epoch": 0.5605867346938775, "percentage": 28.03, "elapsed_time": "15:54:10", "remaining_time": "1 day, 16:50:00", "throughput": 4661.66, "total_tokens": 266880024} {"current_steps": 4400, "total_steps": 15680, "loss": 0.3358687162399292, "lr": 8.180476989564818e-06, "epoch": 0.5612244897959183, "percentage": 28.06, "elapsed_time": "15:55:12", "remaining_time": "1 day, 16:48:47", "throughput": 4661.96, "total_tokens": 267187080} {"current_steps": 4405, "total_steps": 15680, "loss": 0.33371782302856445, "lr": 8.176610461840415e-06, "epoch": 0.5618622448979592, "percentage": 28.09, "elapsed_time": "15:56:22", "remaining_time": "1 day, 16:47:55", "throughput": 4661.43, "total_tokens": 267483488} {"current_steps": 4410, "total_steps": 15680, "loss": 0.34981279373168944, "lr": 8.17274074616556e-06, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "15:57:19", "remaining_time": "1 day, 16:46:30", "throughput": 4661.9, "total_tokens": 267778744} {"current_steps": 4415, "total_steps": 15680, "loss": 0.3423975229263306, "lr": 8.16886784642378e-06, "epoch": 0.5631377551020408, "percentage": 28.16, "elapsed_time": "15:58:32", "remaining_time": "1 day, 16:45:43", "throughput": 4661.24, "total_tokens": 268078000} {"current_steps": 4420, "total_steps": 15680, "loss": 0.3394098997116089, "lr": 8.164991766501804e-06, "epoch": 0.5637755102040817, "percentage": 28.19, "elapsed_time": "15:59:42", "remaining_time": "1 day, 16:44:51", "throughput": 4660.87, "total_tokens": 268384416} {"current_steps": 4425, "total_steps": 15680, "loss": 0.315293288230896, "lr": 8.16111251028955e-06, "epoch": 0.5644132653061225, "percentage": 28.22, "elapsed_time": "16:00:50", "remaining_time": "1 day, 16:43:54", "throughput": 4660.4, "total_tokens": 268675008} {"current_steps": 4430, "total_steps": 15680, "loss": 0.32767605781555176, "lr": 8.157230081680118e-06, "epoch": 0.5650510204081632, "percentage": 28.25, "elapsed_time": "16:01:50", "remaining_time": "1 day, 16:42:36", "throughput": 4660.97, "total_tokens": 268986712} {"current_steps": 4435, "total_steps": 15680, "loss": 0.34493412971496584, "lr": 8.153344484569798e-06, "epoch": 0.5656887755102041, "percentage": 28.28, "elapsed_time": "16:02:58", "remaining_time": "1 day, 16:41:37", "throughput": 4660.72, "total_tokens": 269287992} {"current_steps": 4440, "total_steps": 15680, "loss": 0.34345855712890627, "lr": 8.14945572285806e-06, "epoch": 0.5663265306122449, "percentage": 28.32, "elapsed_time": "16:03:56", "remaining_time": "1 day, 16:40:14", "throughput": 4661.24, "total_tokens": 269589840} {"current_steps": 4445, "total_steps": 15680, "loss": 0.3244961738586426, "lr": 8.145563800447547e-06, "epoch": 0.5669642857142857, "percentage": 28.35, "elapsed_time": "16:04:54", "remaining_time": "1 day, 16:38:52", "throughput": 4661.86, "total_tokens": 269897656} {"current_steps": 4450, "total_steps": 15680, "loss": 0.33897535800933837, "lr": 8.141668721244073e-06, "epoch": 0.5676020408163265, "percentage": 28.38, "elapsed_time": "16:05:57", "remaining_time": "1 day, 16:37:40", "throughput": 4662.16, "total_tokens": 270205176} {"current_steps": 4455, "total_steps": 15680, "loss": 0.32180759906768797, "lr": 8.137770489156624e-06, "epoch": 0.5682397959183674, "percentage": 28.41, "elapsed_time": "16:06:58", "remaining_time": "1 day, 16:36:25", "throughput": 4662.41, "total_tokens": 270504888} {"current_steps": 4460, "total_steps": 15680, "loss": 0.31485824584960936, "lr": 8.133869108097349e-06, "epoch": 0.5688775510204082, "percentage": 28.44, "elapsed_time": "16:07:58", "remaining_time": "1 day, 16:35:07", "throughput": 4662.97, "total_tokens": 270817528} {"current_steps": 4465, "total_steps": 15680, "loss": 0.3301039934158325, "lr": 8.129964581981554e-06, "epoch": 0.5695153061224489, "percentage": 28.48, "elapsed_time": "16:09:04", "remaining_time": "1 day, 16:34:05", "throughput": 4662.74, "total_tokens": 271113568} {"current_steps": 4470, "total_steps": 15680, "loss": 0.34999229907989504, "lr": 8.126056914727705e-06, "epoch": 0.5701530612244898, "percentage": 28.51, "elapsed_time": "16:10:03", "remaining_time": "1 day, 16:32:44", "throughput": 4663.33, "total_tokens": 271422464} {"current_steps": 4475, "total_steps": 15680, "loss": 0.343953537940979, "lr": 8.122146110257419e-06, "epoch": 0.5707908163265306, "percentage": 28.54, "elapsed_time": "16:11:07", "remaining_time": "1 day, 16:31:35", "throughput": 4663.38, "total_tokens": 271721272} {"current_steps": 4480, "total_steps": 15680, "loss": 0.3216872692108154, "lr": 8.11823217249546e-06, "epoch": 0.5714285714285714, "percentage": 28.57, "elapsed_time": "16:12:18", "remaining_time": "1 day, 16:30:46", "throughput": 4663.0, "total_tokens": 272032224} {"current_steps": 4485, "total_steps": 15680, "loss": 0.34439973831176757, "lr": 8.114315105369739e-06, "epoch": 0.5720663265306123, "percentage": 28.6, "elapsed_time": "16:13:15", "remaining_time": "1 day, 16:29:21", "throughput": 4663.74, "total_tokens": 272342792} {"current_steps": 4490, "total_steps": 15680, "loss": 0.3304832935333252, "lr": 8.110394912811308e-06, "epoch": 0.5727040816326531, "percentage": 28.64, "elapsed_time": "16:14:13", "remaining_time": "1 day, 16:27:58", "throughput": 4664.35, "total_tokens": 272647752} {"current_steps": 4495, "total_steps": 15680, "loss": 0.3181920528411865, "lr": 8.106471598754353e-06, "epoch": 0.5733418367346939, "percentage": 28.67, "elapsed_time": "16:15:11", "remaining_time": "1 day, 16:26:35", "throughput": 4664.95, "total_tokens": 272952752} {"current_steps": 4500, "total_steps": 15680, "loss": 0.3237417221069336, "lr": 8.102545167136191e-06, "epoch": 0.5739795918367347, "percentage": 28.7, "elapsed_time": "16:16:08", "remaining_time": "1 day, 16:25:09", "throughput": 4665.67, "total_tokens": 273259992} {"current_steps": 4505, "total_steps": 15680, "loss": 0.3160714626312256, "lr": 8.098615621897272e-06, "epoch": 0.5746173469387755, "percentage": 28.73, "elapsed_time": "16:17:15", "remaining_time": "1 day, 16:24:09", "throughput": 4665.2, "total_tokens": 273546088} {"current_steps": 4510, "total_steps": 15680, "loss": 0.3343855142593384, "lr": 8.094682966981172e-06, "epoch": 0.5752551020408163, "percentage": 28.76, "elapsed_time": "16:18:21", "remaining_time": "1 day, 16:23:07", "throughput": 4665.06, "total_tokens": 273846816} {"current_steps": 4515, "total_steps": 15680, "loss": 0.30679736137390134, "lr": 8.090747206334582e-06, "epoch": 0.5758928571428571, "percentage": 28.79, "elapsed_time": "16:19:23", "remaining_time": "1 day, 16:21:54", "throughput": 4665.29, "total_tokens": 274148336} {"current_steps": 4520, "total_steps": 15680, "loss": 0.3471099853515625, "lr": 8.086808343907313e-06, "epoch": 0.576530612244898, "percentage": 28.83, "elapsed_time": "16:20:14", "remaining_time": "1 day, 16:20:14", "throughput": 4666.36, "total_tokens": 274448928} {"current_steps": 4525, "total_steps": 15680, "loss": 0.31707210540771485, "lr": 8.082866383652288e-06, "epoch": 0.5771683673469388, "percentage": 28.86, "elapsed_time": "16:21:18", "remaining_time": "1 day, 16:19:07", "throughput": 4666.54, "total_tokens": 274760712} {"current_steps": 4530, "total_steps": 15680, "loss": 0.3436100482940674, "lr": 8.07892132952554e-06, "epoch": 0.5778061224489796, "percentage": 28.89, "elapsed_time": "16:22:34", "remaining_time": "1 day, 16:18:27", "throughput": 4665.77, "total_tokens": 275066192} {"current_steps": 4535, "total_steps": 15680, "loss": 0.3058030128479004, "lr": 8.074973185486206e-06, "epoch": 0.5784438775510204, "percentage": 28.92, "elapsed_time": "16:23:30", "remaining_time": "1 day, 16:17:01", "throughput": 4666.33, "total_tokens": 275363072} {"current_steps": 4540, "total_steps": 15680, "loss": 0.34128503799438475, "lr": 8.071021955496526e-06, "epoch": 0.5790816326530612, "percentage": 28.95, "elapsed_time": "16:24:38", "remaining_time": "1 day, 16:16:04", "throughput": 4666.02, "total_tokens": 275663040} {"current_steps": 4545, "total_steps": 15680, "loss": 0.3404224872589111, "lr": 8.067067643521834e-06, "epoch": 0.579719387755102, "percentage": 28.99, "elapsed_time": "16:25:35", "remaining_time": "1 day, 16:14:37", "throughput": 4666.87, "total_tokens": 275975912} {"current_steps": 4550, "total_steps": 15680, "loss": 0.3541407108306885, "lr": 8.063110253530557e-06, "epoch": 0.5803571428571429, "percentage": 29.02, "elapsed_time": "16:26:44", "remaining_time": "1 day, 16:13:44", "throughput": 4666.47, "total_tokens": 276277248} {"current_steps": 4555, "total_steps": 15680, "loss": 0.32312707901000975, "lr": 8.059149789494215e-06, "epoch": 0.5809948979591837, "percentage": 29.05, "elapsed_time": "16:27:49", "remaining_time": "1 day, 16:12:36", "throughput": 4666.13, "total_tokens": 276556904} {"current_steps": 4560, "total_steps": 15680, "loss": 0.3319542646408081, "lr": 8.055186255387409e-06, "epoch": 0.5816326530612245, "percentage": 29.08, "elapsed_time": "16:29:04", "remaining_time": "1 day, 16:11:57", "throughput": 4665.28, "total_tokens": 276857984} {"current_steps": 4565, "total_steps": 15680, "loss": 0.3470942974090576, "lr": 8.051219655187818e-06, "epoch": 0.5822704081632653, "percentage": 29.11, "elapsed_time": "16:30:06", "remaining_time": "1 day, 16:10:45", "throughput": 4665.74, "total_tokens": 277177000} {"current_steps": 4570, "total_steps": 15680, "loss": 0.33258297443389895, "lr": 8.04724999287621e-06, "epoch": 0.5829081632653061, "percentage": 29.15, "elapsed_time": "16:31:19", "remaining_time": "1 day, 16:09:59", "throughput": 4665.1, "total_tokens": 277478560} {"current_steps": 4575, "total_steps": 15680, "loss": 0.3166254997253418, "lr": 8.043277272436415e-06, "epoch": 0.5835459183673469, "percentage": 29.18, "elapsed_time": "16:32:21", "remaining_time": "1 day, 16:08:46", "throughput": 4665.35, "total_tokens": 277781656} {"current_steps": 4580, "total_steps": 15680, "loss": 0.3375540733337402, "lr": 8.039301497855331e-06, "epoch": 0.5841836734693877, "percentage": 29.21, "elapsed_time": "16:33:25", "remaining_time": "1 day, 16:07:37", "throughput": 4665.29, "total_tokens": 278074920} {"current_steps": 4585, "total_steps": 15680, "loss": 0.33584496974945066, "lr": 8.035322673122934e-06, "epoch": 0.5848214285714286, "percentage": 29.24, "elapsed_time": "16:34:32", "remaining_time": "1 day, 16:06:38", "throughput": 4665.21, "total_tokens": 278385592} {"current_steps": 4590, "total_steps": 15680, "loss": 0.3267554044723511, "lr": 8.031340802232246e-06, "epoch": 0.5854591836734694, "percentage": 29.27, "elapsed_time": "16:35:43", "remaining_time": "1 day, 16:05:48", "throughput": 4664.77, "total_tokens": 278690728} {"current_steps": 4595, "total_steps": 15680, "loss": 0.33541412353515626, "lr": 8.027355889179356e-06, "epoch": 0.5860969387755102, "percentage": 29.3, "elapsed_time": "16:36:43", "remaining_time": "1 day, 16:04:29", "throughput": 4665.28, "total_tokens": 278997912} {"current_steps": 4600, "total_steps": 15680, "loss": 0.3400087833404541, "lr": 8.0233679379634e-06, "epoch": 0.5867346938775511, "percentage": 29.34, "elapsed_time": "16:37:56", "remaining_time": "1 day, 16:03:43", "throughput": 4664.64, "total_tokens": 279300264} {"current_steps": 4605, "total_steps": 15680, "loss": 0.3251744270324707, "lr": 8.019376952586567e-06, "epoch": 0.5873724489795918, "percentage": 29.37, "elapsed_time": "16:39:06", "remaining_time": "1 day, 16:02:51", "throughput": 4664.2, "total_tokens": 279603888} {"current_steps": 4610, "total_steps": 15680, "loss": 0.34337458610534666, "lr": 8.01538293705409e-06, "epoch": 0.5880102040816326, "percentage": 29.4, "elapsed_time": "16:40:09", "remaining_time": "1 day, 16:01:40", "throughput": 4664.33, "total_tokens": 279902336} {"current_steps": 4615, "total_steps": 15680, "loss": 0.3512176752090454, "lr": 8.011385895374239e-06, "epoch": 0.5886479591836735, "percentage": 29.43, "elapsed_time": "16:41:19", "remaining_time": "1 day, 16:00:47", "throughput": 4663.95, "total_tokens": 280206616} {"current_steps": 4620, "total_steps": 15680, "loss": 0.3329361915588379, "lr": 8.007385831558329e-06, "epoch": 0.5892857142857143, "percentage": 29.46, "elapsed_time": "16:42:30", "remaining_time": "1 day, 15:59:57", "throughput": 4663.39, "total_tokens": 280506992} {"current_steps": 4625, "total_steps": 15680, "loss": 0.3576455593109131, "lr": 8.003382749620704e-06, "epoch": 0.5899234693877551, "percentage": 29.5, "elapsed_time": "16:43:50", "remaining_time": "1 day, 15:59:27", "throughput": 4662.21, "total_tokens": 280808544} {"current_steps": 4630, "total_steps": 15680, "loss": 0.3338657855987549, "lr": 7.99937665357873e-06, "epoch": 0.5905612244897959, "percentage": 29.53, "elapsed_time": "16:44:52", "remaining_time": "1 day, 15:58:14", "throughput": 4662.53, "total_tokens": 281115176} {"current_steps": 4635, "total_steps": 15680, "loss": 0.30156421661376953, "lr": 7.995367547452811e-06, "epoch": 0.5911989795918368, "percentage": 29.56, "elapsed_time": "16:45:57", "remaining_time": "1 day, 15:57:09", "throughput": 4662.24, "total_tokens": 281402488} {"current_steps": 4640, "total_steps": 15680, "loss": 0.334645938873291, "lr": 7.991355435266362e-06, "epoch": 0.5918367346938775, "percentage": 29.59, "elapsed_time": "16:47:01", "remaining_time": "1 day, 15:56:01", "throughput": 4662.44, "total_tokens": 281710624} {"current_steps": 4645, "total_steps": 15680, "loss": 0.3482946872711182, "lr": 7.987340321045816e-06, "epoch": 0.5924744897959183, "percentage": 29.62, "elapsed_time": "16:48:05", "remaining_time": "1 day, 15:54:52", "throughput": 4662.51, "total_tokens": 282012216} {"current_steps": 4650, "total_steps": 15680, "loss": 0.33052778244018555, "lr": 7.983322208820624e-06, "epoch": 0.5931122448979592, "percentage": 29.66, "elapsed_time": "16:49:15", "remaining_time": "1 day, 15:53:59", "throughput": 4661.96, "total_tokens": 282306456} {"current_steps": 4655, "total_steps": 15680, "loss": 0.375149130821228, "lr": 7.97930110262324e-06, "epoch": 0.59375, "percentage": 29.69, "elapsed_time": "16:50:09", "remaining_time": "1 day, 15:52:27", "throughput": 4663.03, "total_tokens": 282621480} {"current_steps": 4660, "total_steps": 15680, "loss": 0.3693304300308228, "lr": 7.975277006489126e-06, "epoch": 0.5943877551020408, "percentage": 29.72, "elapsed_time": "16:51:03", "remaining_time": "1 day, 15:50:57", "throughput": 4663.87, "total_tokens": 282926240} {"current_steps": 4665, "total_steps": 15680, "loss": 0.3131096839904785, "lr": 7.971249924456742e-06, "epoch": 0.5950255102040817, "percentage": 29.75, "elapsed_time": "16:52:12", "remaining_time": "1 day, 15:50:01", "throughput": 4663.46, "total_tokens": 283222512} {"current_steps": 4670, "total_steps": 15680, "loss": 0.3460294008255005, "lr": 7.967219860567547e-06, "epoch": 0.5956632653061225, "percentage": 29.78, "elapsed_time": "16:53:10", "remaining_time": "1 day, 15:48:40", "throughput": 4663.85, "total_tokens": 283518112} {"current_steps": 4675, "total_steps": 15680, "loss": 0.33358302116394045, "lr": 7.963186818865993e-06, "epoch": 0.5963010204081632, "percentage": 29.82, "elapsed_time": "16:54:24", "remaining_time": "1 day, 15:47:54", "throughput": 4662.94, "total_tokens": 283805976} {"current_steps": 4680, "total_steps": 15680, "loss": 0.33843064308166504, "lr": 7.959150803399519e-06, "epoch": 0.5969387755102041, "percentage": 29.85, "elapsed_time": "16:55:31", "remaining_time": "1 day, 15:46:55", "throughput": 4662.85, "total_tokens": 284115784} {"current_steps": 4685, "total_steps": 15680, "loss": 0.33420662879943847, "lr": 7.955111818218544e-06, "epoch": 0.5975765306122449, "percentage": 29.88, "elapsed_time": "16:56:52", "remaining_time": "1 day, 15:46:26", "throughput": 4661.53, "total_tokens": 284410904} {"current_steps": 4690, "total_steps": 15680, "loss": 0.3390709638595581, "lr": 7.951069867376477e-06, "epoch": 0.5982142857142857, "percentage": 29.91, "elapsed_time": "16:57:59", "remaining_time": "1 day, 15:45:27", "throughput": 4661.54, "total_tokens": 284725216} {"current_steps": 4695, "total_steps": 15680, "loss": 0.35746586322784424, "lr": 7.947024954929696e-06, "epoch": 0.5988520408163265, "percentage": 29.94, "elapsed_time": "16:59:03", "remaining_time": "1 day, 15:44:19", "throughput": 4661.66, "total_tokens": 285031680} {"current_steps": 4700, "total_steps": 15680, "loss": 0.32452802658081054, "lr": 7.942977084937552e-06, "epoch": 0.5994897959183674, "percentage": 29.97, "elapsed_time": "17:00:07", "remaining_time": "1 day, 15:43:10", "throughput": 4661.71, "total_tokens": 285330936} {"current_steps": 4705, "total_steps": 15680, "loss": 0.3147572040557861, "lr": 7.938926261462366e-06, "epoch": 0.6001275510204082, "percentage": 30.01, "elapsed_time": "17:01:09", "remaining_time": "1 day, 15:41:58", "throughput": 4662.06, "total_tokens": 285641568} {"current_steps": 4710, "total_steps": 15680, "loss": 0.3319873809814453, "lr": 7.934872488569423e-06, "epoch": 0.6007653061224489, "percentage": 30.04, "elapsed_time": "17:02:21", "remaining_time": "1 day, 15:41:09", "throughput": 4661.47, "total_tokens": 285940128} {"current_steps": 4715, "total_steps": 15680, "loss": 0.3462022304534912, "lr": 7.930815770326968e-06, "epoch": 0.6014030612244898, "percentage": 30.07, "elapsed_time": "17:03:26", "remaining_time": "1 day, 15:40:03", "throughput": 4661.36, "total_tokens": 286236152} {"current_steps": 4720, "total_steps": 15680, "loss": 0.30179471969604493, "lr": 7.926756110806197e-06, "epoch": 0.6020408163265306, "percentage": 30.1, "elapsed_time": "17:04:21", "remaining_time": "1 day, 15:38:36", "throughput": 4662.09, "total_tokens": 286540184} {"current_steps": 4725, "total_steps": 15680, "loss": 0.33141958713531494, "lr": 7.922693514081267e-06, "epoch": 0.6026785714285714, "percentage": 30.13, "elapsed_time": "17:05:20", "remaining_time": "1 day, 15:37:15", "throughput": 4662.44, "total_tokens": 286833736} {"current_steps": 4730, "total_steps": 15680, "loss": 0.338878870010376, "lr": 7.918627984229274e-06, "epoch": 0.6033163265306123, "percentage": 30.17, "elapsed_time": "17:06:21", "remaining_time": "1 day, 15:36:02", "throughput": 4662.72, "total_tokens": 287138016} {"current_steps": 4735, "total_steps": 15680, "loss": 0.35114235877990724, "lr": 7.914559525330262e-06, "epoch": 0.6039540816326531, "percentage": 30.2, "elapsed_time": "17:07:23", "remaining_time": "1 day, 15:34:50", "throughput": 4663.1, "total_tokens": 287450896} {"current_steps": 4740, "total_steps": 15680, "loss": 0.330631947517395, "lr": 7.910488141467215e-06, "epoch": 0.6045918367346939, "percentage": 30.23, "elapsed_time": "17:08:21", "remaining_time": "1 day, 15:33:26", "throughput": 4663.81, "total_tokens": 287761752} {"current_steps": 4745, "total_steps": 15680, "loss": 0.3229456901550293, "lr": 7.906413836726049e-06, "epoch": 0.6052295918367347, "percentage": 30.26, "elapsed_time": "17:09:29", "remaining_time": "1 day, 15:32:30", "throughput": 4663.48, "total_tokens": 288062320} {"current_steps": 4750, "total_steps": 15680, "loss": 0.3303380012512207, "lr": 7.902336615195614e-06, "epoch": 0.6058673469387755, "percentage": 30.29, "elapsed_time": "17:10:32", "remaining_time": "1 day, 15:31:19", "throughput": 4663.54, "total_tokens": 288357504} {"current_steps": 4755, "total_steps": 15680, "loss": 0.33974905014038087, "lr": 7.89825648096769e-06, "epoch": 0.6065051020408163, "percentage": 30.33, "elapsed_time": "17:11:47", "remaining_time": "1 day, 15:30:36", "throughput": 4662.7, "total_tokens": 288654072} {"current_steps": 4760, "total_steps": 15680, "loss": 0.3210566282272339, "lr": 7.89417343813697e-06, "epoch": 0.6071428571428571, "percentage": 30.36, "elapsed_time": "17:12:49", "remaining_time": "1 day, 15:29:25", "throughput": 4662.8, "total_tokens": 288951872} {"current_steps": 4765, "total_steps": 15680, "loss": 0.32726516723632815, "lr": 7.890087490801077e-06, "epoch": 0.607780612244898, "percentage": 30.39, "elapsed_time": "17:13:59", "remaining_time": "1 day, 15:28:32", "throughput": 4662.23, "total_tokens": 289243832} {"current_steps": 4770, "total_steps": 15680, "loss": 0.3283411979675293, "lr": 7.885998643060544e-06, "epoch": 0.6084183673469388, "percentage": 30.42, "elapsed_time": "17:14:58", "remaining_time": "1 day, 15:27:12", "throughput": 4662.71, "total_tokens": 289548232} {"current_steps": 4775, "total_steps": 15680, "loss": 0.3176594257354736, "lr": 7.881906899018815e-06, "epoch": 0.6090561224489796, "percentage": 30.45, "elapsed_time": "17:15:48", "remaining_time": "1 day, 15:25:32", "throughput": 4664.16, "total_tokens": 289868800} {"current_steps": 4780, "total_steps": 15680, "loss": 0.33094594478607176, "lr": 7.87781226278224e-06, "epoch": 0.6096938775510204, "percentage": 30.48, "elapsed_time": "17:16:49", "remaining_time": "1 day, 15:24:18", "throughput": 4664.31, "total_tokens": 290163856} {"current_steps": 4785, "total_steps": 15680, "loss": 0.3263236999511719, "lr": 7.873714738460075e-06, "epoch": 0.6103316326530612, "percentage": 30.52, "elapsed_time": "17:17:57", "remaining_time": "1 day, 15:23:20", "throughput": 4664.0, "total_tokens": 290462384} {"current_steps": 4790, "total_steps": 15680, "loss": 0.3235758304595947, "lr": 7.86961433016447e-06, "epoch": 0.610969387755102, "percentage": 30.55, "elapsed_time": "17:19:09", "remaining_time": "1 day, 15:22:30", "throughput": 4663.63, "total_tokens": 290775128} {"current_steps": 4795, "total_steps": 15680, "loss": 0.31907784938812256, "lr": 7.865511042010469e-06, "epoch": 0.6116071428571429, "percentage": 30.58, "elapsed_time": "17:20:12", "remaining_time": "1 day, 15:21:21", "throughput": 4663.58, "total_tokens": 291066008} {"current_steps": 4800, "total_steps": 15680, "loss": 0.3359909772872925, "lr": 7.861404878116014e-06, "epoch": 0.6122448979591837, "percentage": 30.61, "elapsed_time": "17:21:24", "remaining_time": "1 day, 15:20:30", "throughput": 4662.86, "total_tokens": 291355224} {"current_steps": 4805, "total_steps": 15680, "loss": 0.3385308265686035, "lr": 7.857295842601921e-06, "epoch": 0.6128826530612245, "percentage": 30.64, "elapsed_time": "17:22:11", "remaining_time": "1 day, 15:18:46", "throughput": 4664.28, "total_tokens": 291666904} {"current_steps": 4810, "total_steps": 15680, "loss": 0.3188408136367798, "lr": 7.853183939591898e-06, "epoch": 0.6135204081632653, "percentage": 30.68, "elapsed_time": "17:23:15", "remaining_time": "1 day, 15:17:36", "throughput": 4664.19, "total_tokens": 291954960} {"current_steps": 4815, "total_steps": 15680, "loss": 0.33262321949005125, "lr": 7.849069173212526e-06, "epoch": 0.6141581632653061, "percentage": 30.71, "elapsed_time": "17:24:30", "remaining_time": "1 day, 15:16:54", "throughput": 4663.52, "total_tokens": 292263992} {"current_steps": 4820, "total_steps": 15680, "loss": 0.3587038516998291, "lr": 7.844951547593261e-06, "epoch": 0.6147959183673469, "percentage": 30.74, "elapsed_time": "17:25:43", "remaining_time": "1 day, 15:16:08", "throughput": 4662.95, "total_tokens": 292570608} {"current_steps": 4825, "total_steps": 15680, "loss": 0.34357218742370604, "lr": 7.840831066866423e-06, "epoch": 0.6154336734693877, "percentage": 30.77, "elapsed_time": "17:26:42", "remaining_time": "1 day, 15:14:50", "throughput": 4663.63, "total_tokens": 292889008} {"current_steps": 4830, "total_steps": 15680, "loss": 0.30017411708831787, "lr": 7.83670773516721e-06, "epoch": 0.6160714285714286, "percentage": 30.8, "elapsed_time": "17:27:48", "remaining_time": "1 day, 15:13:46", "throughput": 4663.57, "total_tokens": 293192336} {"current_steps": 4835, "total_steps": 15680, "loss": 0.34011092185974123, "lr": 7.83258155663367e-06, "epoch": 0.6167091836734694, "percentage": 30.84, "elapsed_time": "17:28:37", "remaining_time": "1 day, 15:12:05", "throughput": 4664.9, "total_tokens": 293504568} {"current_steps": 4840, "total_steps": 15680, "loss": 0.32102341651916505, "lr": 7.828452535406707e-06, "epoch": 0.6173469387755102, "percentage": 30.87, "elapsed_time": "17:29:40", "remaining_time": "1 day, 15:10:56", "throughput": 4664.92, "total_tokens": 293801056} {"current_steps": 4845, "total_steps": 15680, "loss": 0.28260757923126223, "lr": 7.82432067563009e-06, "epoch": 0.6179846938775511, "percentage": 30.9, "elapsed_time": "17:30:44", "remaining_time": "1 day, 15:09:48", "throughput": 4665.02, "total_tokens": 294104640} {"current_steps": 4850, "total_steps": 15680, "loss": 0.3284600019454956, "lr": 7.820185981450422e-06, "epoch": 0.6186224489795918, "percentage": 30.93, "elapsed_time": "17:31:52", "remaining_time": "1 day, 15:08:50", "throughput": 4664.99, "total_tokens": 294420608} {"current_steps": 4855, "total_steps": 15680, "loss": 0.35275702476501464, "lr": 7.816048457017163e-06, "epoch": 0.6192602040816326, "percentage": 30.96, "elapsed_time": "17:33:02", "remaining_time": "1 day, 15:07:55", "throughput": 4664.74, "total_tokens": 294729432} {"current_steps": 4860, "total_steps": 15680, "loss": 0.32400710582733155, "lr": 7.811908106482601e-06, "epoch": 0.6198979591836735, "percentage": 30.99, "elapsed_time": "17:34:13", "remaining_time": "1 day, 15:07:02", "throughput": 4664.22, "total_tokens": 295026480} {"current_steps": 4865, "total_steps": 15680, "loss": 0.3197571039199829, "lr": 7.807764934001875e-06, "epoch": 0.6205357142857143, "percentage": 31.03, "elapsed_time": "17:35:18", "remaining_time": "1 day, 15:05:59", "throughput": 4664.25, "total_tokens": 295335136} {"current_steps": 4870, "total_steps": 15680, "loss": 0.30578064918518066, "lr": 7.803618943732943e-06, "epoch": 0.6211734693877551, "percentage": 31.06, "elapsed_time": "17:36:22", "remaining_time": "1 day, 15:04:50", "throughput": 4664.1, "total_tokens": 295621456} {"current_steps": 4875, "total_steps": 15680, "loss": 0.33724274635314944, "lr": 7.799470139836593e-06, "epoch": 0.6218112244897959, "percentage": 31.09, "elapsed_time": "17:37:29", "remaining_time": "1 day, 15:03:50", "throughput": 4663.98, "total_tokens": 295928456} {"current_steps": 4880, "total_steps": 15680, "loss": 0.3247530460357666, "lr": 7.795318526476448e-06, "epoch": 0.6224489795918368, "percentage": 31.12, "elapsed_time": "17:38:23", "remaining_time": "1 day, 15:02:20", "throughput": 4664.83, "total_tokens": 296232464} {"current_steps": 4885, "total_steps": 15680, "loss": 0.3155781030654907, "lr": 7.791164107818933e-06, "epoch": 0.6230867346938775, "percentage": 31.15, "elapsed_time": "17:39:24", "remaining_time": "1 day, 15:01:06", "throughput": 4665.06, "total_tokens": 296533328} {"current_steps": 4890, "total_steps": 15680, "loss": 0.3392642021179199, "lr": 7.787006888033304e-06, "epoch": 0.6237244897959183, "percentage": 31.19, "elapsed_time": "17:40:34", "remaining_time": "1 day, 15:00:12", "throughput": 4664.7, "total_tokens": 296836440} {"current_steps": 4895, "total_steps": 15680, "loss": 0.33809504508972166, "lr": 7.782846871291619e-06, "epoch": 0.6243622448979592, "percentage": 31.22, "elapsed_time": "17:41:33", "remaining_time": "1 day, 14:58:54", "throughput": 4665.05, "total_tokens": 297135096} {"current_steps": 4900, "total_steps": 15680, "loss": 0.33953664302825926, "lr": 7.778684061768744e-06, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "17:42:40", "remaining_time": "1 day, 14:57:52", "throughput": 4664.81, "total_tokens": 297429472} {"current_steps": 4905, "total_steps": 15680, "loss": 0.33265602588653564, "lr": 7.774518463642351e-06, "epoch": 0.6256377551020408, "percentage": 31.28, "elapsed_time": "17:43:38", "remaining_time": "1 day, 14:56:33", "throughput": 4664.98, "total_tokens": 297713592} {"current_steps": 4910, "total_steps": 15680, "loss": 0.3128589391708374, "lr": 7.770350081092906e-06, "epoch": 0.6262755102040817, "percentage": 31.31, "elapsed_time": "17:44:46", "remaining_time": "1 day, 14:55:34", "throughput": 4664.77, "total_tokens": 298015744} {"current_steps": 4915, "total_steps": 15680, "loss": 0.32480950355529786, "lr": 7.766178918303675e-06, "epoch": 0.6269132653061225, "percentage": 31.35, "elapsed_time": "17:45:49", "remaining_time": "1 day, 14:54:24", "throughput": 4664.99, "total_tokens": 298324856} {"current_steps": 4920, "total_steps": 15680, "loss": 0.3458104610443115, "lr": 7.762004979460711e-06, "epoch": 0.6275510204081632, "percentage": 31.38, "elapsed_time": "17:46:54", "remaining_time": "1 day, 14:53:20", "throughput": 4664.95, "total_tokens": 298626488} {"current_steps": 4925, "total_steps": 15680, "loss": 0.32567148208618163, "lr": 7.75782826875285e-06, "epoch": 0.6281887755102041, "percentage": 31.41, "elapsed_time": "17:48:10", "remaining_time": "1 day, 14:52:38", "throughput": 4664.24, "total_tokens": 298934448} {"current_steps": 4930, "total_steps": 15680, "loss": 0.3416671991348267, "lr": 7.753648790371716e-06, "epoch": 0.6288265306122449, "percentage": 31.44, "elapsed_time": "17:49:16", "remaining_time": "1 day, 14:51:35", "throughput": 4664.24, "total_tokens": 299242480} {"current_steps": 4935, "total_steps": 15680, "loss": 0.32350864410400393, "lr": 7.749466548511706e-06, "epoch": 0.6294642857142857, "percentage": 31.47, "elapsed_time": "17:50:24", "remaining_time": "1 day, 14:50:35", "throughput": 4664.07, "total_tokens": 299546696} {"current_steps": 4940, "total_steps": 15680, "loss": 0.3141555070877075, "lr": 7.745281547369992e-06, "epoch": 0.6301020408163265, "percentage": 31.51, "elapsed_time": "17:51:21", "remaining_time": "1 day, 14:49:14", "throughput": 4664.74, "total_tokens": 299857664} {"current_steps": 4945, "total_steps": 15680, "loss": 0.33570907115936277, "lr": 7.741093791146517e-06, "epoch": 0.6307397959183674, "percentage": 31.54, "elapsed_time": "17:52:29", "remaining_time": "1 day, 14:48:14", "throughput": 4664.58, "total_tokens": 300162488} {"current_steps": 4950, "total_steps": 15680, "loss": 0.31252236366271974, "lr": 7.736903284043985e-06, "epoch": 0.6313775510204082, "percentage": 31.57, "elapsed_time": "17:53:30", "remaining_time": "1 day, 14:47:01", "throughput": 4664.92, "total_tokens": 300470800} {"current_steps": 4955, "total_steps": 15680, "loss": 0.32289905548095704, "lr": 7.73271003026786e-06, "epoch": 0.6320153061224489, "percentage": 31.6, "elapsed_time": "17:54:45", "remaining_time": "1 day, 14:46:18", "throughput": 4664.14, "total_tokens": 300771088} {"current_steps": 4960, "total_steps": 15680, "loss": 0.3148157596588135, "lr": 7.72851403402637e-06, "epoch": 0.6326530612244898, "percentage": 31.63, "elapsed_time": "17:55:46", "remaining_time": "1 day, 14:45:04", "throughput": 4664.64, "total_tokens": 301087160} {"current_steps": 4965, "total_steps": 15680, "loss": 0.3344589710235596, "lr": 7.724315299530485e-06, "epoch": 0.6332908163265306, "percentage": 31.66, "elapsed_time": "17:56:54", "remaining_time": "1 day, 14:44:05", "throughput": 4664.49, "total_tokens": 301394496} {"current_steps": 4970, "total_steps": 15680, "loss": 0.346239709854126, "lr": 7.720113830993934e-06, "epoch": 0.6339285714285714, "percentage": 31.7, "elapsed_time": "17:58:01", "remaining_time": "1 day, 14:43:03", "throughput": 4664.31, "total_tokens": 301692832} {"current_steps": 4975, "total_steps": 15680, "loss": 0.3092792987823486, "lr": 7.71590963263318e-06, "epoch": 0.6345663265306123, "percentage": 31.73, "elapsed_time": "17:59:18", "remaining_time": "1 day, 14:42:23", "throughput": 4663.41, "total_tokens": 301993848} {"current_steps": 4980, "total_steps": 15680, "loss": 0.3285883903503418, "lr": 7.711702708667432e-06, "epoch": 0.6352040816326531, "percentage": 31.76, "elapsed_time": "18:00:28", "remaining_time": "1 day, 14:41:30", "throughput": 4662.89, "total_tokens": 302288504} {"current_steps": 4985, "total_steps": 15680, "loss": 0.3152578353881836, "lr": 7.70749306331863e-06, "epoch": 0.6358418367346939, "percentage": 31.79, "elapsed_time": "18:01:34", "remaining_time": "1 day, 14:40:26", "throughput": 4662.92, "total_tokens": 302596976} {"current_steps": 4990, "total_steps": 15680, "loss": 0.3586283683776855, "lr": 7.703280700811447e-06, "epoch": 0.6364795918367347, "percentage": 31.82, "elapsed_time": "18:02:36", "remaining_time": "1 day, 14:39:14", "throughput": 4662.93, "total_tokens": 302885624} {"current_steps": 4995, "total_steps": 15680, "loss": 0.34339160919189454, "lr": 7.699065625373285e-06, "epoch": 0.6371173469387755, "percentage": 31.86, "elapsed_time": "18:03:42", "remaining_time": "1 day, 14:38:11", "throughput": 4662.57, "total_tokens": 303170080} {"current_steps": 5000, "total_steps": 15680, "loss": 0.31816675662994387, "lr": 7.694847841234268e-06, "epoch": 0.6377551020408163, "percentage": 31.89, "elapsed_time": "18:04:50", "remaining_time": "1 day, 14:37:12", "throughput": 4662.18, "total_tokens": 303462440} {"current_steps": 5005, "total_steps": 15680, "loss": 0.356259822845459, "lr": 7.690627352627232e-06, "epoch": 0.6383928571428571, "percentage": 31.92, "elapsed_time": "18:05:51", "remaining_time": "1 day, 14:36:00", "throughput": 4662.55, "total_tokens": 303774280} {"current_steps": 5010, "total_steps": 15680, "loss": 0.3103009223937988, "lr": 7.686404163787734e-06, "epoch": 0.639030612244898, "percentage": 31.95, "elapsed_time": "18:07:03", "remaining_time": "1 day, 14:35:08", "throughput": 4661.95, "total_tokens": 304067248} {"current_steps": 5015, "total_steps": 15680, "loss": 0.3121501445770264, "lr": 7.68217827895404e-06, "epoch": 0.6396683673469388, "percentage": 31.98, "elapsed_time": "18:07:55", "remaining_time": "1 day, 14:33:35", "throughput": 4662.88, "total_tokens": 304370400} {"current_steps": 5020, "total_steps": 15680, "loss": 0.3567068576812744, "lr": 7.677949702367122e-06, "epoch": 0.6403061224489796, "percentage": 32.02, "elapsed_time": "18:08:59", "remaining_time": "1 day, 14:32:29", "throughput": 4662.93, "total_tokens": 304674832} {"current_steps": 5025, "total_steps": 15680, "loss": 0.3278343200683594, "lr": 7.673718438270649e-06, "epoch": 0.6409438775510204, "percentage": 32.05, "elapsed_time": "18:10:11", "remaining_time": "1 day, 14:31:38", "throughput": 4662.51, "total_tokens": 304981880} {"current_steps": 5030, "total_steps": 15680, "loss": 0.3229900598526001, "lr": 7.66948449091099e-06, "epoch": 0.6415816326530612, "percentage": 32.08, "elapsed_time": "18:11:17", "remaining_time": "1 day, 14:30:34", "throughput": 4662.48, "total_tokens": 305285928} {"current_steps": 5035, "total_steps": 15680, "loss": 0.3233805656433105, "lr": 7.66524786453721e-06, "epoch": 0.642219387755102, "percentage": 32.11, "elapsed_time": "18:12:29", "remaining_time": "1 day, 14:29:44", "throughput": 4661.91, "total_tokens": 305584664} {"current_steps": 5040, "total_steps": 15680, "loss": 0.3556224346160889, "lr": 7.661008563401056e-06, "epoch": 0.6428571428571429, "percentage": 32.14, "elapsed_time": "18:13:26", "remaining_time": "1 day, 14:28:22", "throughput": 4662.16, "total_tokens": 305868632} {"current_steps": 5045, "total_steps": 15680, "loss": 0.34767487049102785, "lr": 7.656766591756964e-06, "epoch": 0.6434948979591837, "percentage": 32.17, "elapsed_time": "18:14:29", "remaining_time": "1 day, 14:27:12", "throughput": 4662.46, "total_tokens": 306179728} {"current_steps": 5050, "total_steps": 15680, "loss": 0.33482675552368163, "lr": 7.652521953862051e-06, "epoch": 0.6441326530612245, "percentage": 32.21, "elapsed_time": "18:15:16", "remaining_time": "1 day, 14:25:30", "throughput": 4663.79, "total_tokens": 306489360} {"current_steps": 5055, "total_steps": 15680, "loss": 0.3288681745529175, "lr": 7.648274653976102e-06, "epoch": 0.6447704081632653, "percentage": 32.24, "elapsed_time": "18:16:18", "remaining_time": "1 day, 14:24:18", "throughput": 4663.97, "total_tokens": 306789736} {"current_steps": 5060, "total_steps": 15680, "loss": 0.32494688034057617, "lr": 7.644024696361587e-06, "epoch": 0.6454081632653061, "percentage": 32.27, "elapsed_time": "18:17:16", "remaining_time": "1 day, 14:22:59", "throughput": 4664.52, "total_tokens": 307097616} {"current_steps": 5065, "total_steps": 15680, "loss": 0.33415367603302004, "lr": 7.639772085283629e-06, "epoch": 0.6460459183673469, "percentage": 32.3, "elapsed_time": "18:18:18", "remaining_time": "1 day, 14:21:47", "throughput": 4664.88, "total_tokens": 307408752} {"current_steps": 5070, "total_steps": 15680, "loss": 0.3211622714996338, "lr": 7.635516825010022e-06, "epoch": 0.6466836734693877, "percentage": 32.33, "elapsed_time": "18:19:24", "remaining_time": "1 day, 14:20:44", "throughput": 4664.68, "total_tokens": 307705200} {"current_steps": 5075, "total_steps": 15680, "loss": 0.3212575435638428, "lr": 7.631258919811215e-06, "epoch": 0.6473214285714286, "percentage": 32.37, "elapsed_time": "18:20:23", "remaining_time": "1 day, 14:19:26", "throughput": 4665.27, "total_tokens": 308018488} {"current_steps": 5080, "total_steps": 15680, "loss": 0.3299903869628906, "lr": 7.626998373960317e-06, "epoch": 0.6479591836734694, "percentage": 32.4, "elapsed_time": "18:21:34", "remaining_time": "1 day, 14:18:34", "throughput": 4664.85, "total_tokens": 308322376} {"current_steps": 5085, "total_steps": 15680, "loss": 0.3272510290145874, "lr": 7.6227351917330835e-06, "epoch": 0.6485969387755102, "percentage": 32.43, "elapsed_time": "18:22:37", "remaining_time": "1 day, 14:17:23", "throughput": 4665.03, "total_tokens": 308624608} {"current_steps": 5090, "total_steps": 15680, "loss": 0.35759220123291013, "lr": 7.618469377407911e-06, "epoch": 0.6492346938775511, "percentage": 32.46, "elapsed_time": "18:23:32", "remaining_time": "1 day, 14:15:57", "throughput": 4665.84, "total_tokens": 308935880} {"current_steps": 5095, "total_steps": 15680, "loss": 0.3380232572555542, "lr": 7.614200935265845e-06, "epoch": 0.6498724489795918, "percentage": 32.49, "elapsed_time": "18:24:42", "remaining_time": "1 day, 14:15:04", "throughput": 4665.28, "total_tokens": 309228488} {"current_steps": 5100, "total_steps": 15680, "loss": 0.3147365808486938, "lr": 7.609929869590566e-06, "epoch": 0.6505102040816326, "percentage": 32.53, "elapsed_time": "18:25:51", "remaining_time": "1 day, 14:14:07", "throughput": 4665.17, "total_tokens": 309541768} {"current_steps": 5105, "total_steps": 15680, "loss": 0.32534070014953614, "lr": 7.605656184668385e-06, "epoch": 0.6511479591836735, "percentage": 32.56, "elapsed_time": "18:26:51", "remaining_time": "1 day, 14:12:52", "throughput": 4665.62, "total_tokens": 309852264} {"current_steps": 5110, "total_steps": 15680, "loss": 0.3319838285446167, "lr": 7.6013798847882455e-06, "epoch": 0.6517857142857143, "percentage": 32.59, "elapsed_time": "18:27:44", "remaining_time": "1 day, 14:11:20", "throughput": 4666.64, "total_tokens": 310164128} {"current_steps": 5115, "total_steps": 15680, "loss": 0.33452045917510986, "lr": 7.597100974241711e-06, "epoch": 0.6524234693877551, "percentage": 32.62, "elapsed_time": "18:28:57", "remaining_time": "1 day, 14:10:32", "throughput": 4666.05, "total_tokens": 310465392} {"current_steps": 5120, "total_steps": 15680, "loss": 0.3549307346343994, "lr": 7.592819457322967e-06, "epoch": 0.6530612244897959, "percentage": 32.65, "elapsed_time": "18:29:59", "remaining_time": "1 day, 14:09:21", "throughput": 4666.17, "total_tokens": 310764976} {"current_steps": 5125, "total_steps": 15680, "loss": 0.32546820640563967, "lr": 7.588535338328816e-06, "epoch": 0.6536989795918368, "percentage": 32.68, "elapsed_time": "18:31:10", "remaining_time": "1 day, 14:08:28", "throughput": 4665.78, "total_tokens": 311068176} {"current_steps": 5130, "total_steps": 15680, "loss": 0.33570246696472167, "lr": 7.584248621558669e-06, "epoch": 0.6543367346938775, "percentage": 32.72, "elapsed_time": "18:32:13", "remaining_time": "1 day, 14:07:19", "throughput": 4665.95, "total_tokens": 311375264} {"current_steps": 5135, "total_steps": 15680, "loss": 0.3122812509536743, "lr": 7.579959311314549e-06, "epoch": 0.6549744897959183, "percentage": 32.75, "elapsed_time": "18:33:27", "remaining_time": "1 day, 14:06:32", "throughput": 4665.1, "total_tokens": 311663640} {"current_steps": 5140, "total_steps": 15680, "loss": 0.33909385204315184, "lr": 7.575667411901074e-06, "epoch": 0.6556122448979592, "percentage": 32.78, "elapsed_time": "18:34:22", "remaining_time": "1 day, 14:05:07", "throughput": 4665.87, "total_tokens": 311971384} {"current_steps": 5145, "total_steps": 15680, "loss": 0.30200581550598143, "lr": 7.571372927625469e-06, "epoch": 0.65625, "percentage": 32.81, "elapsed_time": "18:35:31", "remaining_time": "1 day, 14:04:09", "throughput": 4665.66, "total_tokens": 312278304} {"current_steps": 5150, "total_steps": 15680, "loss": 0.3463855504989624, "lr": 7.567075862797546e-06, "epoch": 0.6568877551020408, "percentage": 32.84, "elapsed_time": "18:36:43", "remaining_time": "1 day, 14:03:18", "throughput": 4665.21, "total_tokens": 312583576} {"current_steps": 5155, "total_steps": 15680, "loss": 0.3354689121246338, "lr": 7.562776221729709e-06, "epoch": 0.6575255102040817, "percentage": 32.88, "elapsed_time": "18:37:42", "remaining_time": "1 day, 14:02:02", "throughput": 4665.68, "total_tokens": 312893440} {"current_steps": 5160, "total_steps": 15680, "loss": 0.3523919105529785, "lr": 7.558474008736951e-06, "epoch": 0.6581632653061225, "percentage": 32.91, "elapsed_time": "18:38:43", "remaining_time": "1 day, 14:00:49", "throughput": 4665.9, "total_tokens": 313192904} {"current_steps": 5165, "total_steps": 15680, "loss": 0.3369914054870605, "lr": 7.554169228136842e-06, "epoch": 0.6588010204081632, "percentage": 32.94, "elapsed_time": "18:39:47", "remaining_time": "1 day, 13:59:42", "throughput": 4665.87, "total_tokens": 313489048} {"current_steps": 5170, "total_steps": 15680, "loss": 0.3480203151702881, "lr": 7.549861884249529e-06, "epoch": 0.6594387755102041, "percentage": 32.97, "elapsed_time": "18:40:59", "remaining_time": "1 day, 13:58:49", "throughput": 4665.5, "total_tokens": 313797432} {"current_steps": 5175, "total_steps": 15680, "loss": 0.3440972566604614, "lr": 7.545551981397733e-06, "epoch": 0.6600765306122449, "percentage": 33.0, "elapsed_time": "18:42:12", "remaining_time": "1 day, 13:58:01", "throughput": 4665.15, "total_tokens": 314115728} {"current_steps": 5180, "total_steps": 15680, "loss": 0.3330733060836792, "lr": 7.541239523906742e-06, "epoch": 0.6607142857142857, "percentage": 33.04, "elapsed_time": "18:43:14", "remaining_time": "1 day, 13:56:49", "throughput": 4665.49, "total_tokens": 314426512} {"current_steps": 5185, "total_steps": 15680, "loss": 0.31601767539978026, "lr": 7.536924516104411e-06, "epoch": 0.6613520408163265, "percentage": 33.07, "elapsed_time": "18:44:29", "remaining_time": "1 day, 13:56:04", "throughput": 4664.6, "total_tokens": 314716736} {"current_steps": 5190, "total_steps": 15680, "loss": 0.32779479026794434, "lr": 7.532606962321149e-06, "epoch": 0.6619897959183674, "percentage": 33.1, "elapsed_time": "18:45:26", "remaining_time": "1 day, 13:54:45", "throughput": 4665.02, "total_tokens": 315014520} {"current_steps": 5195, "total_steps": 15680, "loss": 0.3065429925918579, "lr": 7.528286866889924e-06, "epoch": 0.6626275510204082, "percentage": 33.13, "elapsed_time": "18:46:35", "remaining_time": "1 day, 13:53:48", "throughput": 4664.78, "total_tokens": 315320568} {"current_steps": 5200, "total_steps": 15680, "loss": 0.34712815284729004, "lr": 7.523964234146251e-06, "epoch": 0.6632653061224489, "percentage": 33.16, "elapsed_time": "18:47:29", "remaining_time": "1 day, 13:52:19", "throughput": 4665.74, "total_tokens": 315634520} {"current_steps": 5205, "total_steps": 15680, "loss": 0.3406857967376709, "lr": 7.519639068428199e-06, "epoch": 0.6639030612244898, "percentage": 33.2, "elapsed_time": "18:48:34", "remaining_time": "1 day, 13:51:14", "throughput": 4665.74, "total_tokens": 315938296} {"current_steps": 5210, "total_steps": 15680, "loss": 0.3166226625442505, "lr": 7.515311374076368e-06, "epoch": 0.6645408163265306, "percentage": 33.23, "elapsed_time": "18:49:42", "remaining_time": "1 day, 13:50:15", "throughput": 4665.55, "total_tokens": 316243072} {"current_steps": 5215, "total_steps": 15680, "loss": 0.33198843002319334, "lr": 7.5109811554339054e-06, "epoch": 0.6651785714285714, "percentage": 33.26, "elapsed_time": "18:50:50", "remaining_time": "1 day, 13:49:17", "throughput": 4665.38, "total_tokens": 316550280} {"current_steps": 5220, "total_steps": 15680, "loss": 0.3436640739440918, "lr": 7.506648416846485e-06, "epoch": 0.6658163265306123, "percentage": 33.29, "elapsed_time": "18:51:42", "remaining_time": "1 day, 13:47:45", "throughput": 4666.52, "total_tokens": 316868448} {"current_steps": 5225, "total_steps": 15680, "loss": 0.3301560878753662, "lr": 7.502313162662316e-06, "epoch": 0.6664540816326531, "percentage": 33.32, "elapsed_time": "18:52:55", "remaining_time": "1 day, 13:46:56", "throughput": 4665.89, "total_tokens": 317168256} {"current_steps": 5230, "total_steps": 15680, "loss": 0.31626310348510744, "lr": 7.4979753972321265e-06, "epoch": 0.6670918367346939, "percentage": 33.35, "elapsed_time": "18:54:08", "remaining_time": "1 day, 13:46:06", "throughput": 4665.51, "total_tokens": 317480320} {"current_steps": 5235, "total_steps": 15680, "loss": 0.31904003620147703, "lr": 7.493635124909167e-06, "epoch": 0.6677295918367347, "percentage": 33.39, "elapsed_time": "18:55:28", "remaining_time": "1 day, 13:45:31", "throughput": 4664.54, "total_tokens": 317786664} {"current_steps": 5240, "total_steps": 15680, "loss": 0.32049336433410647, "lr": 7.489292350049205e-06, "epoch": 0.6683673469387755, "percentage": 33.42, "elapsed_time": "18:56:25", "remaining_time": "1 day, 13:44:10", "throughput": 4665.09, "total_tokens": 318090448} {"current_steps": 5245, "total_steps": 15680, "loss": 0.3046008348464966, "lr": 7.484947077010519e-06, "epoch": 0.6690051020408163, "percentage": 33.45, "elapsed_time": "18:57:29", "remaining_time": "1 day, 13:43:02", "throughput": 4665.36, "total_tokens": 318407360} {"current_steps": 5250, "total_steps": 15680, "loss": 0.3047685146331787, "lr": 7.480599310153891e-06, "epoch": 0.6696428571428571, "percentage": 33.48, "elapsed_time": "18:58:33", "remaining_time": "1 day, 13:41:56", "throughput": 4665.06, "total_tokens": 318686592} {"current_steps": 5255, "total_steps": 15680, "loss": 0.3419510364532471, "lr": 7.476249053842613e-06, "epoch": 0.670280612244898, "percentage": 33.51, "elapsed_time": "18:59:40", "remaining_time": "1 day, 13:40:54", "throughput": 4664.86, "total_tokens": 318984160} {"current_steps": 5260, "total_steps": 15680, "loss": 0.32067461013793946, "lr": 7.471896312442467e-06, "epoch": 0.6709183673469388, "percentage": 33.55, "elapsed_time": "19:00:51", "remaining_time": "1 day, 13:40:01", "throughput": 4664.33, "total_tokens": 319279088} {"current_steps": 5265, "total_steps": 15680, "loss": 0.3092599153518677, "lr": 7.467541090321735e-06, "epoch": 0.6715561224489796, "percentage": 33.58, "elapsed_time": "19:01:57", "remaining_time": "1 day, 13:38:57", "throughput": 4664.28, "total_tokens": 319582768} {"current_steps": 5270, "total_steps": 15680, "loss": 0.34105687141418456, "lr": 7.463183391851186e-06, "epoch": 0.6721938775510204, "percentage": 33.61, "elapsed_time": "19:02:45", "remaining_time": "1 day, 13:37:18", "throughput": 4665.46, "total_tokens": 319887592} {"current_steps": 5275, "total_steps": 15680, "loss": 0.3312492370605469, "lr": 7.4588232214040744e-06, "epoch": 0.6728316326530612, "percentage": 33.64, "elapsed_time": "19:04:00", "remaining_time": "1 day, 13:36:33", "throughput": 4664.6, "total_tokens": 320179160} {"current_steps": 5280, "total_steps": 15680, "loss": 0.31220436096191406, "lr": 7.454460583356138e-06, "epoch": 0.673469387755102, "percentage": 33.67, "elapsed_time": "19:05:01", "remaining_time": "1 day, 13:35:20", "throughput": 4664.66, "total_tokens": 320468448} {"current_steps": 5285, "total_steps": 15680, "loss": 0.32859785556793214, "lr": 7.4500954820855854e-06, "epoch": 0.6741071428571429, "percentage": 33.71, "elapsed_time": "19:06:03", "remaining_time": "1 day, 13:34:10", "throughput": 4664.9, "total_tokens": 320776112} {"current_steps": 5290, "total_steps": 15680, "loss": 0.3388023853302002, "lr": 7.445727921973104e-06, "epoch": 0.6747448979591837, "percentage": 33.74, "elapsed_time": "19:07:23", "remaining_time": "1 day, 13:33:34", "throughput": 4663.95, "total_tokens": 321083768} {"current_steps": 5295, "total_steps": 15680, "loss": 0.349368953704834, "lr": 7.441357907401841e-06, "epoch": 0.6753826530612245, "percentage": 33.77, "elapsed_time": "19:08:40", "remaining_time": "1 day, 13:32:52", "throughput": 4663.18, "total_tokens": 321388456} {"current_steps": 5300, "total_steps": 15680, "loss": 0.3301686763763428, "lr": 7.436985442757415e-06, "epoch": 0.6760204081632653, "percentage": 33.8, "elapsed_time": "19:09:36", "remaining_time": "1 day, 13:31:30", "throughput": 4663.89, "total_tokens": 321699936} {"current_steps": 5305, "total_steps": 15680, "loss": 0.3316835403442383, "lr": 7.432610532427899e-06, "epoch": 0.6766581632653061, "percentage": 33.83, "elapsed_time": "19:10:27", "remaining_time": "1 day, 13:29:57", "throughput": 4665.03, "total_tokens": 322016888} {"current_steps": 5310, "total_steps": 15680, "loss": 0.3472487688064575, "lr": 7.428233180803821e-06, "epoch": 0.6772959183673469, "percentage": 33.86, "elapsed_time": "19:11:27", "remaining_time": "1 day, 13:28:42", "throughput": 4665.45, "total_tokens": 322323416} {"current_steps": 5315, "total_steps": 15680, "loss": 0.3495924949645996, "lr": 7.423853392278158e-06, "epoch": 0.6779336734693877, "percentage": 33.9, "elapsed_time": "19:12:31", "remaining_time": "1 day, 13:27:34", "throughput": 4665.4, "total_tokens": 322618320} {"current_steps": 5320, "total_steps": 15680, "loss": 0.3318294286727905, "lr": 7.419471171246334e-06, "epoch": 0.6785714285714286, "percentage": 33.93, "elapsed_time": "19:13:26", "remaining_time": "1 day, 13:26:10", "throughput": 4666.05, "total_tokens": 322920944} {"current_steps": 5325, "total_steps": 15680, "loss": 0.33146181106567385, "lr": 7.415086522106215e-06, "epoch": 0.6792091836734694, "percentage": 33.96, "elapsed_time": "19:14:27", "remaining_time": "1 day, 13:24:57", "throughput": 4666.41, "total_tokens": 323229392} {"current_steps": 5330, "total_steps": 15680, "loss": 0.3333503246307373, "lr": 7.410699449258102e-06, "epoch": 0.6798469387755102, "percentage": 33.99, "elapsed_time": "19:15:30", "remaining_time": "1 day, 13:23:49", "throughput": 4666.61, "total_tokens": 323539944} {"current_steps": 5335, "total_steps": 15680, "loss": 0.31888589859008787, "lr": 7.406309957104727e-06, "epoch": 0.6804846938775511, "percentage": 34.02, "elapsed_time": "19:16:32", "remaining_time": "1 day, 13:22:38", "throughput": 4666.85, "total_tokens": 323845648} {"current_steps": 5340, "total_steps": 15680, "loss": 0.32655973434448243, "lr": 7.401918050051256e-06, "epoch": 0.6811224489795918, "percentage": 34.06, "elapsed_time": "19:17:38", "remaining_time": "1 day, 13:21:34", "throughput": 4666.87, "total_tokens": 324152360} {"current_steps": 5345, "total_steps": 15680, "loss": 0.3464339256286621, "lr": 7.39752373250527e-06, "epoch": 0.6817602040816326, "percentage": 34.09, "elapsed_time": "19:18:48", "remaining_time": "1 day, 13:20:38", "throughput": 4666.63, "total_tokens": 324461336} {"current_steps": 5350, "total_steps": 15680, "loss": 0.3387403726577759, "lr": 7.393127008876777e-06, "epoch": 0.6823979591836735, "percentage": 34.12, "elapsed_time": "19:19:53", "remaining_time": "1 day, 13:19:33", "throughput": 4666.61, "total_tokens": 324765688} {"current_steps": 5355, "total_steps": 15680, "loss": 0.33055853843688965, "lr": 7.388727883578195e-06, "epoch": 0.6830357142857143, "percentage": 34.15, "elapsed_time": "19:20:59", "remaining_time": "1 day, 13:18:31", "throughput": 4666.5, "total_tokens": 325067576} {"current_steps": 5360, "total_steps": 15680, "loss": 0.3409270763397217, "lr": 7.384326361024352e-06, "epoch": 0.6836734693877551, "percentage": 34.18, "elapsed_time": "19:22:05", "remaining_time": "1 day, 13:17:27", "throughput": 4666.54, "total_tokens": 325377208} {"current_steps": 5365, "total_steps": 15680, "loss": 0.34844231605529785, "lr": 7.3799224456324865e-06, "epoch": 0.6843112244897959, "percentage": 34.22, "elapsed_time": "19:23:00", "remaining_time": "1 day, 13:16:02", "throughput": 4667.32, "total_tokens": 325686680} {"current_steps": 5370, "total_steps": 15680, "loss": 0.34676122665405273, "lr": 7.375516141822232e-06, "epoch": 0.6849489795918368, "percentage": 34.25, "elapsed_time": "19:23:56", "remaining_time": "1 day, 13:14:40", "throughput": 4668.0, "total_tokens": 325995200} {"current_steps": 5375, "total_steps": 15680, "loss": 0.3110495090484619, "lr": 7.371107454015626e-06, "epoch": 0.6855867346938775, "percentage": 34.28, "elapsed_time": "19:25:06", "remaining_time": "1 day, 13:13:45", "throughput": 4667.71, "total_tokens": 326303576} {"current_steps": 5380, "total_steps": 15680, "loss": 0.35372376441955566, "lr": 7.3666963866370886e-06, "epoch": 0.6862244897959183, "percentage": 34.31, "elapsed_time": "19:26:13", "remaining_time": "1 day, 13:12:44", "throughput": 4667.65, "total_tokens": 326611640} {"current_steps": 5385, "total_steps": 15680, "loss": 0.327644419670105, "lr": 7.3622829441134395e-06, "epoch": 0.6868622448979592, "percentage": 34.34, "elapsed_time": "19:27:20", "remaining_time": "1 day, 13:11:42", "throughput": 4667.59, "total_tokens": 326919968} {"current_steps": 5390, "total_steps": 15680, "loss": 0.3390071392059326, "lr": 7.357867130873875e-06, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "19:28:20", "remaining_time": "1 day, 13:10:27", "throughput": 4668.08, "total_tokens": 327232832} {"current_steps": 5395, "total_steps": 15680, "loss": 0.32433485984802246, "lr": 7.353448951349971e-06, "epoch": 0.6881377551020408, "percentage": 34.41, "elapsed_time": "19:29:25", "remaining_time": "1 day, 13:09:23", "throughput": 4668.11, "total_tokens": 327541008} {"current_steps": 5400, "total_steps": 15680, "loss": 0.3259130477905273, "lr": 7.349028409975681e-06, "epoch": 0.6887755102040817, "percentage": 34.44, "elapsed_time": "19:30:37", "remaining_time": "1 day, 13:08:30", "throughput": 4667.43, "total_tokens": 327827272} {"current_steps": 5405, "total_steps": 15680, "loss": 0.327258038520813, "lr": 7.344605511187322e-06, "epoch": 0.6894132653061225, "percentage": 34.47, "elapsed_time": "19:31:33", "remaining_time": "1 day, 13:07:08", "throughput": 4667.85, "total_tokens": 328118504} {"current_steps": 5410, "total_steps": 15680, "loss": 0.3184638023376465, "lr": 7.3401802594235894e-06, "epoch": 0.6900510204081632, "percentage": 34.5, "elapsed_time": "19:32:43", "remaining_time": "1 day, 13:06:13", "throughput": 4667.51, "total_tokens": 328421136} {"current_steps": 5415, "total_steps": 15680, "loss": 0.327569317817688, "lr": 7.3357526591255265e-06, "epoch": 0.6906887755102041, "percentage": 34.53, "elapsed_time": "19:33:53", "remaining_time": "1 day, 13:05:17", "throughput": 4667.08, "total_tokens": 328718016} {"current_steps": 5420, "total_steps": 15680, "loss": 0.33679890632629395, "lr": 7.331322714736543e-06, "epoch": 0.6913265306122449, "percentage": 34.57, "elapsed_time": "19:35:03", "remaining_time": "1 day, 13:04:21", "throughput": 4666.67, "total_tokens": 329015224} {"current_steps": 5425, "total_steps": 15680, "loss": 0.3472728252410889, "lr": 7.326890430702396e-06, "epoch": 0.6919642857142857, "percentage": 34.6, "elapsed_time": "19:36:11", "remaining_time": "1 day, 13:03:23", "throughput": 4666.38, "total_tokens": 329314184} {"current_steps": 5430, "total_steps": 15680, "loss": 0.3267884016036987, "lr": 7.3224558114711905e-06, "epoch": 0.6926020408163265, "percentage": 34.63, "elapsed_time": "19:37:21", "remaining_time": "1 day, 13:02:26", "throughput": 4666.14, "total_tokens": 329621696} {"current_steps": 5435, "total_steps": 15680, "loss": 0.30158908367156984, "lr": 7.31801886149338e-06, "epoch": 0.6932397959183674, "percentage": 34.66, "elapsed_time": "19:38:29", "remaining_time": "1 day, 13:01:27", "throughput": 4665.84, "total_tokens": 329919672} {"current_steps": 5440, "total_steps": 15680, "loss": 0.34727749824523924, "lr": 7.313579585221752e-06, "epoch": 0.6938775510204082, "percentage": 34.69, "elapsed_time": "19:39:24", "remaining_time": "1 day, 13:00:04", "throughput": 4666.64, "total_tokens": 330233896} {"current_steps": 5445, "total_steps": 15680, "loss": 0.33589582443237304, "lr": 7.309137987111428e-06, "epoch": 0.6945153061224489, "percentage": 34.73, "elapsed_time": "19:40:27", "remaining_time": "1 day, 12:58:55", "throughput": 4666.66, "total_tokens": 330530192} {"current_steps": 5450, "total_steps": 15680, "loss": 0.3435753345489502, "lr": 7.304694071619866e-06, "epoch": 0.6951530612244898, "percentage": 34.76, "elapsed_time": "19:41:22", "remaining_time": "1 day, 12:57:31", "throughput": 4667.41, "total_tokens": 330839440} {"current_steps": 5455, "total_steps": 15680, "loss": 0.33095269203186034, "lr": 7.300247843206844e-06, "epoch": 0.6957908163265306, "percentage": 34.79, "elapsed_time": "19:42:18", "remaining_time": "1 day, 12:56:09", "throughput": 4667.75, "total_tokens": 331125736} {"current_steps": 5460, "total_steps": 15680, "loss": 0.3572857856750488, "lr": 7.2957993063344615e-06, "epoch": 0.6964285714285714, "percentage": 34.82, "elapsed_time": "19:43:16", "remaining_time": "1 day, 12:54:50", "throughput": 4668.38, "total_tokens": 331437480} {"current_steps": 5465, "total_steps": 15680, "loss": 0.32533111572265627, "lr": 7.291348465467136e-06, "epoch": 0.6970663265306123, "percentage": 34.85, "elapsed_time": "19:44:26", "remaining_time": "1 day, 12:53:56", "throughput": 4667.95, "total_tokens": 331737480} {"current_steps": 5470, "total_steps": 15680, "loss": 0.3380601167678833, "lr": 7.286895325071599e-06, "epoch": 0.6977040816326531, "percentage": 34.89, "elapsed_time": "19:45:30", "remaining_time": "1 day, 12:52:47", "throughput": 4668.16, "total_tokens": 332047296} {"current_steps": 5475, "total_steps": 15680, "loss": 0.30793912410736085, "lr": 7.282439889616887e-06, "epoch": 0.6983418367346939, "percentage": 34.92, "elapsed_time": "19:46:37", "remaining_time": "1 day, 12:51:47", "throughput": 4667.96, "total_tokens": 332348792} {"current_steps": 5480, "total_steps": 15680, "loss": 0.33248081207275393, "lr": 7.277982163574339e-06, "epoch": 0.6989795918367347, "percentage": 34.95, "elapsed_time": "19:47:36", "remaining_time": "1 day, 12:50:31", "throughput": 4668.3, "total_tokens": 332647496} {"current_steps": 5485, "total_steps": 15680, "loss": 0.327709436416626, "lr": 7.273522151417598e-06, "epoch": 0.6996173469387755, "percentage": 34.98, "elapsed_time": "19:48:49", "remaining_time": "1 day, 12:49:40", "throughput": 4667.88, "total_tokens": 332958368} {"current_steps": 5490, "total_steps": 15680, "loss": 0.327768611907959, "lr": 7.2690598576225954e-06, "epoch": 0.7002551020408163, "percentage": 35.01, "elapsed_time": "19:50:06", "remaining_time": "1 day, 12:48:57", "throughput": 4667.0, "total_tokens": 333253504} {"current_steps": 5495, "total_steps": 15680, "loss": 0.3356297254562378, "lr": 7.264595286667554e-06, "epoch": 0.7008928571428571, "percentage": 35.04, "elapsed_time": "19:51:13", "remaining_time": "1 day, 12:47:56", "throughput": 4666.49, "total_tokens": 333529432} {"current_steps": 5500, "total_steps": 15680, "loss": 0.31958589553833006, "lr": 7.2601284430329836e-06, "epoch": 0.701530612244898, "percentage": 35.08, "elapsed_time": "19:52:20", "remaining_time": "1 day, 12:46:55", "throughput": 4666.4, "total_tokens": 333837952} {"current_steps": 5505, "total_steps": 15680, "loss": 0.31284639835357664, "lr": 7.255659331201673e-06, "epoch": 0.7021683673469388, "percentage": 35.11, "elapsed_time": "19:53:29", "remaining_time": "1 day, 12:45:57", "throughput": 4666.12, "total_tokens": 334139480} {"current_steps": 5510, "total_steps": 15680, "loss": 0.3290869235992432, "lr": 7.251187955658691e-06, "epoch": 0.7028061224489796, "percentage": 35.14, "elapsed_time": "19:54:32", "remaining_time": "1 day, 12:44:48", "throughput": 4666.12, "total_tokens": 334432600} {"current_steps": 5515, "total_steps": 15680, "loss": 0.3378335237503052, "lr": 7.246714320891371e-06, "epoch": 0.7034438775510204, "percentage": 35.17, "elapsed_time": "19:55:44", "remaining_time": "1 day, 12:43:56", "throughput": 4665.69, "total_tokens": 334738240} {"current_steps": 5520, "total_steps": 15680, "loss": 0.32679245471954343, "lr": 7.24223843138932e-06, "epoch": 0.7040816326530612, "percentage": 35.2, "elapsed_time": "19:56:54", "remaining_time": "1 day, 12:43:00", "throughput": 4665.25, "total_tokens": 335033688} {"current_steps": 5525, "total_steps": 15680, "loss": 0.3354485988616943, "lr": 7.237760291644405e-06, "epoch": 0.704719387755102, "percentage": 35.24, "elapsed_time": "19:57:54", "remaining_time": "1 day, 12:41:45", "throughput": 4665.63, "total_tokens": 335339536} {"current_steps": 5530, "total_steps": 15680, "loss": 0.3378009796142578, "lr": 7.233279906150752e-06, "epoch": 0.7053571428571429, "percentage": 35.27, "elapsed_time": "19:59:00", "remaining_time": "1 day, 12:40:42", "throughput": 4665.23, "total_tokens": 335617824} {"current_steps": 5535, "total_steps": 15680, "loss": 0.3126326322555542, "lr": 7.228797279404744e-06, "epoch": 0.7059948979591837, "percentage": 35.3, "elapsed_time": "20:00:05", "remaining_time": "1 day, 12:39:37", "throughput": 4665.3, "total_tokens": 335926560} {"current_steps": 5540, "total_steps": 15680, "loss": 0.3219478130340576, "lr": 7.224312415905005e-06, "epoch": 0.7066326530612245, "percentage": 35.33, "elapsed_time": "20:01:15", "remaining_time": "1 day, 12:38:41", "throughput": 4665.11, "total_tokens": 336238896} {"current_steps": 5545, "total_steps": 15680, "loss": 0.31927881240844724, "lr": 7.219825320152411e-06, "epoch": 0.7072704081632653, "percentage": 35.36, "elapsed_time": "20:02:21", "remaining_time": "1 day, 12:37:38", "throughput": 4665.06, "total_tokens": 336545928} {"current_steps": 5550, "total_steps": 15680, "loss": 0.33097076416015625, "lr": 7.2153359966500765e-06, "epoch": 0.7079081632653061, "percentage": 35.4, "elapsed_time": "20:03:25", "remaining_time": "1 day, 12:36:32", "throughput": 4665.31, "total_tokens": 336863184} {"current_steps": 5555, "total_steps": 15680, "loss": 0.3214916229248047, "lr": 7.210844449903352e-06, "epoch": 0.7085459183673469, "percentage": 35.43, "elapsed_time": "20:04:32", "remaining_time": "1 day, 12:35:28", "throughput": 4665.22, "total_tokens": 337164816} {"current_steps": 5560, "total_steps": 15680, "loss": 0.3146527767181396, "lr": 7.206350684419814e-06, "epoch": 0.7091836734693877, "percentage": 35.46, "elapsed_time": "20:05:29", "remaining_time": "1 day, 12:34:10", "throughput": 4665.82, "total_tokens": 337478608} {"current_steps": 5565, "total_steps": 15680, "loss": 0.3411190748214722, "lr": 7.2018547047092745e-06, "epoch": 0.7098214285714286, "percentage": 35.49, "elapsed_time": "20:06:40", "remaining_time": "1 day, 12:33:15", "throughput": 4665.61, "total_tokens": 337792616} {"current_steps": 5570, "total_steps": 15680, "loss": 0.3246105194091797, "lr": 7.1973565152837635e-06, "epoch": 0.7104591836734694, "percentage": 35.52, "elapsed_time": "20:07:39", "remaining_time": "1 day, 12:31:58", "throughput": 4666.05, "total_tokens": 338097400} {"current_steps": 5575, "total_steps": 15680, "loss": 0.33641302585601807, "lr": 7.192856120657524e-06, "epoch": 0.7110969387755102, "percentage": 35.55, "elapsed_time": "20:08:52", "remaining_time": "1 day, 12:31:09", "throughput": 4665.51, "total_tokens": 338401176} {"current_steps": 5580, "total_steps": 15680, "loss": 0.30387799739837645, "lr": 7.18835352534702e-06, "epoch": 0.7117346938775511, "percentage": 35.59, "elapsed_time": "20:10:03", "remaining_time": "1 day, 12:30:15", "throughput": 4664.86, "total_tokens": 338686568} {"current_steps": 5585, "total_steps": 15680, "loss": 0.319439697265625, "lr": 7.183848733870917e-06, "epoch": 0.7123724489795918, "percentage": 35.62, "elapsed_time": "20:11:07", "remaining_time": "1 day, 12:29:07", "throughput": 4665.05, "total_tokens": 338995184} {"current_steps": 5590, "total_steps": 15680, "loss": 0.3119250059127808, "lr": 7.179341750750092e-06, "epoch": 0.7130102040816326, "percentage": 35.65, "elapsed_time": "20:12:10", "remaining_time": "1 day, 12:27:58", "throughput": 4665.25, "total_tokens": 339304344} {"current_steps": 5595, "total_steps": 15680, "loss": 0.37570886611938475, "lr": 7.174832580507614e-06, "epoch": 0.7136479591836735, "percentage": 35.68, "elapsed_time": "20:13:09", "remaining_time": "1 day, 12:26:42", "throughput": 4665.54, "total_tokens": 339600024} {"current_steps": 5600, "total_steps": 15680, "loss": 0.3130634784698486, "lr": 7.170321227668752e-06, "epoch": 0.7142857142857143, "percentage": 35.71, "elapsed_time": "20:14:15", "remaining_time": "1 day, 12:25:39", "throughput": 4665.37, "total_tokens": 339897768} {"current_steps": 5605, "total_steps": 15680, "loss": 0.3177204608917236, "lr": 7.165807696760964e-06, "epoch": 0.7149234693877551, "percentage": 35.75, "elapsed_time": "20:15:21", "remaining_time": "1 day, 12:24:37", "throughput": 4665.29, "total_tokens": 340201488} {"current_steps": 5610, "total_steps": 15680, "loss": 0.31652255058288575, "lr": 7.16129199231389e-06, "epoch": 0.7155612244897959, "percentage": 35.78, "elapsed_time": "20:16:26", "remaining_time": "1 day, 12:23:31", "throughput": 4665.43, "total_tokens": 340513480} {"current_steps": 5615, "total_steps": 15680, "loss": 0.32903294563293456, "lr": 7.15677411885936e-06, "epoch": 0.7161989795918368, "percentage": 35.81, "elapsed_time": "20:17:35", "remaining_time": "1 day, 12:22:33", "throughput": 4665.15, "total_tokens": 340814592} {"current_steps": 5620, "total_steps": 15680, "loss": 0.34875319004058836, "lr": 7.152254080931372e-06, "epoch": 0.7168367346938775, "percentage": 35.84, "elapsed_time": "20:18:45", "remaining_time": "1 day, 12:21:37", "throughput": 4664.91, "total_tokens": 341125176} {"current_steps": 5625, "total_steps": 15680, "loss": 0.36013131141662597, "lr": 7.1477318830661e-06, "epoch": 0.7174744897959183, "percentage": 35.87, "elapsed_time": "20:19:54", "remaining_time": "1 day, 12:20:39", "throughput": 4664.67, "total_tokens": 341427632} {"current_steps": 5630, "total_steps": 15680, "loss": 0.3343724250793457, "lr": 7.143207529801888e-06, "epoch": 0.7181122448979592, "percentage": 35.91, "elapsed_time": "20:21:00", "remaining_time": "1 day, 12:19:35", "throughput": 4664.46, "total_tokens": 341719568} {"current_steps": 5635, "total_steps": 15680, "loss": 0.3392931938171387, "lr": 7.1386810256792374e-06, "epoch": 0.71875, "percentage": 35.94, "elapsed_time": "20:22:13", "remaining_time": "1 day, 12:18:45", "throughput": 4663.87, "total_tokens": 342019008} {"current_steps": 5640, "total_steps": 15680, "loss": 0.29196462631225584, "lr": 7.134152375240812e-06, "epoch": 0.7193877551020408, "percentage": 35.97, "elapsed_time": "20:23:25", "remaining_time": "1 day, 12:17:52", "throughput": 4663.34, "total_tokens": 342315160} {"current_steps": 5645, "total_steps": 15680, "loss": 0.3171334505081177, "lr": 7.1296215830314295e-06, "epoch": 0.7200255102040817, "percentage": 36.0, "elapsed_time": "20:24:26", "remaining_time": "1 day, 12:16:39", "throughput": 4663.56, "total_tokens": 342614960} {"current_steps": 5650, "total_steps": 15680, "loss": 0.3042132377624512, "lr": 7.125088653598057e-06, "epoch": 0.7206632653061225, "percentage": 36.03, "elapsed_time": "20:25:30", "remaining_time": "1 day, 12:15:33", "throughput": 4663.53, "total_tokens": 342912480} {"current_steps": 5655, "total_steps": 15680, "loss": 0.3171056270599365, "lr": 7.1205535914898035e-06, "epoch": 0.7213010204081632, "percentage": 36.07, "elapsed_time": "20:26:35", "remaining_time": "1 day, 12:14:28", "throughput": 4663.53, "total_tokens": 343216744} {"current_steps": 5660, "total_steps": 15680, "loss": 0.3005784034729004, "lr": 7.116016401257921e-06, "epoch": 0.7219387755102041, "percentage": 36.1, "elapsed_time": "20:27:39", "remaining_time": "1 day, 12:13:20", "throughput": 4663.66, "total_tokens": 343522224} {"current_steps": 5665, "total_steps": 15680, "loss": 0.33109331130981445, "lr": 7.1114770874558e-06, "epoch": 0.7225765306122449, "percentage": 36.13, "elapsed_time": "20:28:44", "remaining_time": "1 day, 12:12:15", "throughput": 4663.81, "total_tokens": 343836648} {"current_steps": 5670, "total_steps": 15680, "loss": 0.3131404399871826, "lr": 7.1069356546389555e-06, "epoch": 0.7232142857142857, "percentage": 36.16, "elapsed_time": "20:29:58", "remaining_time": "1 day, 12:11:26", "throughput": 4663.01, "total_tokens": 344124648} {"current_steps": 5675, "total_steps": 15680, "loss": 0.34466369152069093, "lr": 7.1023921073650325e-06, "epoch": 0.7238520408163265, "percentage": 36.19, "elapsed_time": "20:30:55", "remaining_time": "1 day, 12:10:06", "throughput": 4663.33, "total_tokens": 344412648} {"current_steps": 5680, "total_steps": 15680, "loss": 0.3497285842895508, "lr": 7.0978464501938e-06, "epoch": 0.7244897959183674, "percentage": 36.22, "elapsed_time": "20:32:02", "remaining_time": "1 day, 12:09:05", "throughput": 4663.16, "total_tokens": 344714768} {"current_steps": 5685, "total_steps": 15680, "loss": 0.3339118242263794, "lr": 7.093298687687141e-06, "epoch": 0.7251275510204082, "percentage": 36.26, "elapsed_time": "20:33:08", "remaining_time": "1 day, 12:08:02", "throughput": 4663.23, "total_tokens": 345026816} {"current_steps": 5690, "total_steps": 15680, "loss": 0.36696739196777345, "lr": 7.088748824409053e-06, "epoch": 0.7257653061224489, "percentage": 36.29, "elapsed_time": "20:34:12", "remaining_time": "1 day, 12:06:54", "throughput": 4663.29, "total_tokens": 345326376} {"current_steps": 5695, "total_steps": 15680, "loss": 0.3174098491668701, "lr": 7.084196864925643e-06, "epoch": 0.7264030612244898, "percentage": 36.32, "elapsed_time": "20:35:15", "remaining_time": "1 day, 12:05:45", "throughput": 4663.45, "total_tokens": 345631752} {"current_steps": 5700, "total_steps": 15680, "loss": 0.33266453742980956, "lr": 7.079642813805118e-06, "epoch": 0.7270408163265306, "percentage": 36.35, "elapsed_time": "20:36:17", "remaining_time": "1 day, 12:04:36", "throughput": 4663.67, "total_tokens": 345940288} {"current_steps": 5705, "total_steps": 15680, "loss": 0.33375253677368166, "lr": 7.075086675617788e-06, "epoch": 0.7276785714285714, "percentage": 36.38, "elapsed_time": "20:37:21", "remaining_time": "1 day, 12:03:28", "throughput": 4663.81, "total_tokens": 346246208} {"current_steps": 5710, "total_steps": 15680, "loss": 0.3297909736633301, "lr": 7.070528454936054e-06, "epoch": 0.7283163265306123, "percentage": 36.42, "elapsed_time": "20:38:19", "remaining_time": "1 day, 12:02:12", "throughput": 4664.15, "total_tokens": 346546152} {"current_steps": 5715, "total_steps": 15680, "loss": 0.3185250759124756, "lr": 7.065968156334413e-06, "epoch": 0.7289540816326531, "percentage": 36.45, "elapsed_time": "20:39:26", "remaining_time": "1 day, 12:01:09", "throughput": 4663.82, "total_tokens": 346831096} {"current_steps": 5720, "total_steps": 15680, "loss": 0.32861080169677737, "lr": 7.061405784389438e-06, "epoch": 0.7295918367346939, "percentage": 36.48, "elapsed_time": "20:40:17", "remaining_time": "1 day, 11:59:39", "throughput": 4664.67, "total_tokens": 347131824} {"current_steps": 5725, "total_steps": 15680, "loss": 0.33352041244506836, "lr": 7.05684134367979e-06, "epoch": 0.7302295918367347, "percentage": 36.51, "elapsed_time": "20:41:21", "remaining_time": "1 day, 11:58:33", "throughput": 4664.7, "total_tokens": 347433720} {"current_steps": 5730, "total_steps": 15680, "loss": 0.3256068706512451, "lr": 7.052274838786204e-06, "epoch": 0.7308673469387755, "percentage": 36.54, "elapsed_time": "20:42:25", "remaining_time": "1 day, 11:57:26", "throughput": 4664.79, "total_tokens": 347739456} {"current_steps": 5735, "total_steps": 15680, "loss": 0.3421637535095215, "lr": 7.047706274291488e-06, "epoch": 0.7315051020408163, "percentage": 36.58, "elapsed_time": "20:43:31", "remaining_time": "1 day, 11:56:23", "throughput": 4664.7, "total_tokens": 348042144} {"current_steps": 5740, "total_steps": 15680, "loss": 0.3239234447479248, "lr": 7.043135654780513e-06, "epoch": 0.7321428571428571, "percentage": 36.61, "elapsed_time": "20:44:33", "remaining_time": "1 day, 11:55:12", "throughput": 4664.99, "total_tokens": 348349184} {"current_steps": 5745, "total_steps": 15680, "loss": 0.3468273878097534, "lr": 7.038562984840216e-06, "epoch": 0.732780612244898, "percentage": 36.64, "elapsed_time": "20:45:43", "remaining_time": "1 day, 11:54:16", "throughput": 4664.71, "total_tokens": 348657576} {"current_steps": 5750, "total_steps": 15680, "loss": 0.35527334213256834, "lr": 7.033988269059593e-06, "epoch": 0.7334183673469388, "percentage": 36.67, "elapsed_time": "20:46:58", "remaining_time": "1 day, 11:53:28", "throughput": 4664.08, "total_tokens": 348959448} {"current_steps": 5755, "total_steps": 15680, "loss": 0.3083681583404541, "lr": 7.029411512029687e-06, "epoch": 0.7340561224489796, "percentage": 36.7, "elapsed_time": "20:48:04", "remaining_time": "1 day, 11:52:25", "throughput": 4664.2, "total_tokens": 349278664} {"current_steps": 5760, "total_steps": 15680, "loss": 0.3165610313415527, "lr": 7.024832718343594e-06, "epoch": 0.7346938775510204, "percentage": 36.73, "elapsed_time": "20:48:56", "remaining_time": "1 day, 11:50:56", "throughput": 4665.16, "total_tokens": 349589600} {"current_steps": 5765, "total_steps": 15680, "loss": 0.30977587699890136, "lr": 7.020251892596456e-06, "epoch": 0.7353316326530612, "percentage": 36.77, "elapsed_time": "20:49:52", "remaining_time": "1 day, 11:49:37", "throughput": 4665.38, "total_tokens": 349870128} {"current_steps": 5770, "total_steps": 15680, "loss": 0.33393781185150145, "lr": 7.015669039385449e-06, "epoch": 0.735969387755102, "percentage": 36.8, "elapsed_time": "20:50:48", "remaining_time": "1 day, 11:48:16", "throughput": 4665.98, "total_tokens": 350175688} {"current_steps": 5775, "total_steps": 15680, "loss": 0.36183881759643555, "lr": 7.011084163309786e-06, "epoch": 0.7366071428571429, "percentage": 36.83, "elapsed_time": "20:51:56", "remaining_time": "1 day, 11:47:15", "throughput": 4665.78, "total_tokens": 350475216} {"current_steps": 5780, "total_steps": 15680, "loss": 0.33647539615631106, "lr": 7.006497268970712e-06, "epoch": 0.7372448979591837, "percentage": 36.86, "elapsed_time": "20:53:02", "remaining_time": "1 day, 11:46:13", "throughput": 4665.77, "total_tokens": 350786336} {"current_steps": 5785, "total_steps": 15680, "loss": 0.3370200634002686, "lr": 7.001908360971495e-06, "epoch": 0.7378826530612245, "percentage": 36.89, "elapsed_time": "20:53:57", "remaining_time": "1 day, 11:44:49", "throughput": 4666.58, "total_tokens": 351099720} {"current_steps": 5790, "total_steps": 15680, "loss": 0.3196087121963501, "lr": 6.997317443917424e-06, "epoch": 0.7385204081632653, "percentage": 36.93, "elapsed_time": "20:55:02", "remaining_time": "1 day, 11:43:45", "throughput": 4666.41, "total_tokens": 351392808} {"current_steps": 5795, "total_steps": 15680, "loss": 0.34132537841796873, "lr": 6.9927245224158066e-06, "epoch": 0.7391581632653061, "percentage": 36.96, "elapsed_time": "20:56:14", "remaining_time": "1 day, 11:42:51", "throughput": 4666.04, "total_tokens": 351698480} {"current_steps": 5800, "total_steps": 15680, "loss": 0.33192293643951415, "lr": 6.988129601075961e-06, "epoch": 0.7397959183673469, "percentage": 36.99, "elapsed_time": "20:57:21", "remaining_time": "1 day, 11:41:50", "throughput": 4665.88, "total_tokens": 352000720} {"current_steps": 5805, "total_steps": 15680, "loss": 0.34473247528076173, "lr": 6.983532684509208e-06, "epoch": 0.7404336734693877, "percentage": 37.02, "elapsed_time": "20:58:26", "remaining_time": "1 day, 11:40:45", "throughput": 4665.77, "total_tokens": 352294224} {"current_steps": 5810, "total_steps": 15680, "loss": 0.32946100234985354, "lr": 6.978933777328878e-06, "epoch": 0.7410714285714286, "percentage": 37.05, "elapsed_time": "20:59:42", "remaining_time": "1 day, 11:39:58", "throughput": 4665.18, "total_tokens": 352604544} {"current_steps": 5815, "total_steps": 15680, "loss": 0.33791561126708985, "lr": 6.974332884150292e-06, "epoch": 0.7417091836734694, "percentage": 37.09, "elapsed_time": "21:00:55", "remaining_time": "1 day, 11:39:08", "throughput": 4664.73, "total_tokens": 352914192} {"current_steps": 5820, "total_steps": 15680, "loss": 0.3198561191558838, "lr": 6.96973000959077e-06, "epoch": 0.7423469387755102, "percentage": 37.12, "elapsed_time": "21:01:58", "remaining_time": "1 day, 11:37:58", "throughput": 4665.04, "total_tokens": 353228696} {"current_steps": 5825, "total_steps": 15680, "loss": 0.3436471462249756, "lr": 6.965125158269619e-06, "epoch": 0.7429846938775511, "percentage": 37.15, "elapsed_time": "21:03:05", "remaining_time": "1 day, 11:36:56", "throughput": 4664.88, "total_tokens": 353528736} {"current_steps": 5830, "total_steps": 15680, "loss": 0.35364034175872805, "lr": 6.9605183348081265e-06, "epoch": 0.7436224489795918, "percentage": 37.18, "elapsed_time": "21:03:58", "remaining_time": "1 day, 11:35:31", "throughput": 4665.72, "total_tokens": 353839872} {"current_steps": 5835, "total_steps": 15680, "loss": 0.34197463989257815, "lr": 6.955909543829564e-06, "epoch": 0.7442602040816326, "percentage": 37.21, "elapsed_time": "21:05:08", "remaining_time": "1 day, 11:34:34", "throughput": 4665.47, "total_tokens": 354148056} {"current_steps": 5840, "total_steps": 15680, "loss": 0.32314419746398926, "lr": 6.951298789959172e-06, "epoch": 0.7448979591836735, "percentage": 37.24, "elapsed_time": "21:06:19", "remaining_time": "1 day, 11:33:39", "throughput": 4665.04, "total_tokens": 354445568} {"current_steps": 5845, "total_steps": 15680, "loss": 0.3016700267791748, "lr": 6.946686077824167e-06, "epoch": 0.7455357142857143, "percentage": 37.28, "elapsed_time": "21:07:23", "remaining_time": "1 day, 11:32:33", "throughput": 4664.79, "total_tokens": 354726728} {"current_steps": 5850, "total_steps": 15680, "loss": 0.3447637319564819, "lr": 6.942071412053728e-06, "epoch": 0.7461734693877551, "percentage": 37.31, "elapsed_time": "21:08:22", "remaining_time": "1 day, 11:31:18", "throughput": 4665.31, "total_tokens": 355041640} {"current_steps": 5855, "total_steps": 15680, "loss": 0.30813610553741455, "lr": 6.937454797278991e-06, "epoch": 0.7468112244897959, "percentage": 37.34, "elapsed_time": "21:09:25", "remaining_time": "1 day, 11:30:09", "throughput": 4665.41, "total_tokens": 355341584} {"current_steps": 5860, "total_steps": 15680, "loss": 0.332719612121582, "lr": 6.932836238133054e-06, "epoch": 0.7474489795918368, "percentage": 37.37, "elapsed_time": "21:10:42", "remaining_time": "1 day, 11:29:24", "throughput": 4664.67, "total_tokens": 355644760} {"current_steps": 5865, "total_steps": 15680, "loss": 0.3112212657928467, "lr": 6.928215739250963e-06, "epoch": 0.7480867346938775, "percentage": 37.4, "elapsed_time": "21:11:56", "remaining_time": "1 day, 11:28:34", "throughput": 4663.97, "total_tokens": 355938224} {"current_steps": 5870, "total_steps": 15680, "loss": 0.3458071708679199, "lr": 6.923593305269711e-06, "epoch": 0.7487244897959183, "percentage": 37.44, "elapsed_time": "21:12:58", "remaining_time": "1 day, 11:27:24", "throughput": 4664.0, "total_tokens": 356230344} {"current_steps": 5875, "total_steps": 15680, "loss": 0.3587623119354248, "lr": 6.9189689408282345e-06, "epoch": 0.7493622448979592, "percentage": 37.47, "elapsed_time": "21:14:06", "remaining_time": "1 day, 11:26:23", "throughput": 4663.95, "total_tokens": 356541344} {"current_steps": 5880, "total_steps": 15680, "loss": 0.3423443794250488, "lr": 6.914342650567405e-06, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "21:15:14", "remaining_time": "1 day, 11:25:24", "throughput": 4663.87, "total_tokens": 356855496} {"current_steps": 5885, "total_steps": 15680, "loss": 0.3316153287887573, "lr": 6.9097144391300285e-06, "epoch": 0.7506377551020408, "percentage": 37.53, "elapsed_time": "21:16:07", "remaining_time": "1 day, 11:23:58", "throughput": 4664.76, "total_tokens": 357168744} {"current_steps": 5890, "total_steps": 15680, "loss": 0.3190103054046631, "lr": 6.905084311160837e-06, "epoch": 0.7512755102040817, "percentage": 37.56, "elapsed_time": "21:17:15", "remaining_time": "1 day, 11:22:59", "throughput": 4664.55, "total_tokens": 357471984} {"current_steps": 5895, "total_steps": 15680, "loss": 0.3483097076416016, "lr": 6.90045227130649e-06, "epoch": 0.7519132653061225, "percentage": 37.6, "elapsed_time": "21:18:13", "remaining_time": "1 day, 11:21:42", "throughput": 4665.08, "total_tokens": 357782784} {"current_steps": 5900, "total_steps": 15680, "loss": 0.323588228225708, "lr": 6.8958183242155615e-06, "epoch": 0.7525510204081632, "percentage": 37.63, "elapsed_time": "21:19:11", "remaining_time": "1 day, 11:20:24", "throughput": 4665.59, "total_tokens": 358089800} {"current_steps": 5905, "total_steps": 15680, "loss": 0.33099820613861086, "lr": 6.891182474538539e-06, "epoch": 0.7531887755102041, "percentage": 37.66, "elapsed_time": "21:20:13", "remaining_time": "1 day, 11:19:14", "throughput": 4665.87, "total_tokens": 358399920} {"current_steps": 5910, "total_steps": 15680, "loss": 0.32611565589904784, "lr": 6.886544726927826e-06, "epoch": 0.7538265306122449, "percentage": 37.69, "elapsed_time": "21:21:19", "remaining_time": "1 day, 11:18:11", "throughput": 4665.82, "total_tokens": 358705672} {"current_steps": 5915, "total_steps": 15680, "loss": 0.3351559638977051, "lr": 6.881905086037721e-06, "epoch": 0.7544642857142857, "percentage": 37.72, "elapsed_time": "21:22:26", "remaining_time": "1 day, 11:17:10", "throughput": 4665.76, "total_tokens": 359014616} {"current_steps": 5920, "total_steps": 15680, "loss": 0.31889750957489016, "lr": 6.877263556524432e-06, "epoch": 0.7551020408163265, "percentage": 37.76, "elapsed_time": "21:23:31", "remaining_time": "1 day, 11:16:04", "throughput": 4665.82, "total_tokens": 359320984} {"current_steps": 5925, "total_steps": 15680, "loss": 0.29836535453796387, "lr": 6.872620143046056e-06, "epoch": 0.7557397959183674, "percentage": 37.79, "elapsed_time": "21:24:38", "remaining_time": "1 day, 11:15:03", "throughput": 4665.61, "total_tokens": 359619040} {"current_steps": 5930, "total_steps": 15680, "loss": 0.32633788585662843, "lr": 6.867974850262582e-06, "epoch": 0.7563775510204082, "percentage": 37.82, "elapsed_time": "21:25:29", "remaining_time": "1 day, 11:13:35", "throughput": 4666.58, "total_tokens": 359932688} {"current_steps": 5935, "total_steps": 15680, "loss": 0.3186999559402466, "lr": 6.863327682835887e-06, "epoch": 0.7570153061224489, "percentage": 37.85, "elapsed_time": "21:26:29", "remaining_time": "1 day, 11:12:21", "throughput": 4667.07, "total_tokens": 360249184} {"current_steps": 5940, "total_steps": 15680, "loss": 0.34361996650695803, "lr": 6.858678645429728e-06, "epoch": 0.7576530612244898, "percentage": 37.88, "elapsed_time": "21:27:43", "remaining_time": "1 day, 11:11:30", "throughput": 4666.53, "total_tokens": 360550856} {"current_steps": 5945, "total_steps": 15680, "loss": 0.3265536308288574, "lr": 6.85402774270974e-06, "epoch": 0.7582908163265306, "percentage": 37.91, "elapsed_time": "21:28:48", "remaining_time": "1 day, 11:10:26", "throughput": 4666.44, "total_tokens": 360848560} {"current_steps": 5950, "total_steps": 15680, "loss": 0.31394202709198, "lr": 6.849374979343426e-06, "epoch": 0.7589285714285714, "percentage": 37.95, "elapsed_time": "21:29:45", "remaining_time": "1 day, 11:09:08", "throughput": 4667.0, "total_tokens": 361158960} {"current_steps": 5955, "total_steps": 15680, "loss": 0.3174293518066406, "lr": 6.84472036000016e-06, "epoch": 0.7595663265306123, "percentage": 37.98, "elapsed_time": "21:30:47", "remaining_time": "1 day, 11:07:58", "throughput": 4667.22, "total_tokens": 361465312} {"current_steps": 5960, "total_steps": 15680, "loss": 0.3175032138824463, "lr": 6.840063889351177e-06, "epoch": 0.7602040816326531, "percentage": 38.01, "elapsed_time": "21:31:58", "remaining_time": "1 day, 11:07:03", "throughput": 4666.84, "total_tokens": 361767408} {"current_steps": 5965, "total_steps": 15680, "loss": 0.3279739856719971, "lr": 6.835405572069572e-06, "epoch": 0.7608418367346939, "percentage": 38.04, "elapsed_time": "21:33:18", "remaining_time": "1 day, 11:06:22", "throughput": 4666.05, "total_tokens": 362078816} {"current_steps": 5970, "total_steps": 15680, "loss": 0.3344055414199829, "lr": 6.830745412830291e-06, "epoch": 0.7614795918367347, "percentage": 38.07, "elapsed_time": "21:34:27", "remaining_time": "1 day, 11:05:22", "throughput": 4665.92, "total_tokens": 362387792} {"current_steps": 5975, "total_steps": 15680, "loss": 0.32223589420318605, "lr": 6.826083416310129e-06, "epoch": 0.7621173469387755, "percentage": 38.11, "elapsed_time": "21:35:42", "remaining_time": "1 day, 11:04:33", "throughput": 4665.23, "total_tokens": 362684544} {"current_steps": 5980, "total_steps": 15680, "loss": 0.3272323369979858, "lr": 6.821419587187727e-06, "epoch": 0.7627551020408163, "percentage": 38.14, "elapsed_time": "21:36:34", "remaining_time": "1 day, 11:03:08", "throughput": 4666.2, "total_tokens": 363005704} {"current_steps": 5985, "total_steps": 15680, "loss": 0.33120250701904297, "lr": 6.816753930143558e-06, "epoch": 0.7633928571428571, "percentage": 38.17, "elapsed_time": "21:37:37", "remaining_time": "1 day, 11:02:00", "throughput": 4666.4, "total_tokens": 363314248} {"current_steps": 5990, "total_steps": 15680, "loss": 0.3483760833740234, "lr": 6.812086449859941e-06, "epoch": 0.764030612244898, "percentage": 38.2, "elapsed_time": "21:38:37", "remaining_time": "1 day, 11:00:46", "throughput": 4666.65, "total_tokens": 363612824} {"current_steps": 5995, "total_steps": 15680, "loss": 0.3102273464202881, "lr": 6.807417151021015e-06, "epoch": 0.7646683673469388, "percentage": 38.23, "elapsed_time": "21:39:46", "remaining_time": "1 day, 10:59:48", "throughput": 4666.21, "total_tokens": 363903136} {"current_steps": 6000, "total_steps": 15680, "loss": 0.3180234909057617, "lr": 6.802746038312749e-06, "epoch": 0.7653061224489796, "percentage": 38.27, "elapsed_time": "21:40:58", "remaining_time": "1 day, 10:58:53", "throughput": 4665.94, "total_tokens": 364214792} {"current_steps": 6005, "total_steps": 15680, "loss": 0.308447003364563, "lr": 6.79807311642293e-06, "epoch": 0.7659438775510204, "percentage": 38.3, "elapsed_time": "21:42:03", "remaining_time": "1 day, 10:57:49", "throughput": 4665.89, "total_tokens": 364516496} {"current_steps": 6010, "total_steps": 15680, "loss": 0.3338149070739746, "lr": 6.793398390041159e-06, "epoch": 0.7665816326530612, "percentage": 38.33, "elapsed_time": "21:42:57", "remaining_time": "1 day, 10:56:25", "throughput": 4666.48, "total_tokens": 364812400} {"current_steps": 6015, "total_steps": 15680, "loss": 0.32828316688537595, "lr": 6.788721863858856e-06, "epoch": 0.767219387755102, "percentage": 38.36, "elapsed_time": "21:44:05", "remaining_time": "1 day, 10:55:25", "throughput": 4666.31, "total_tokens": 365116488} {"current_steps": 6020, "total_steps": 15680, "loss": 0.34796159267425536, "lr": 6.784043542569236e-06, "epoch": 0.7678571428571429, "percentage": 38.39, "elapsed_time": "21:45:17", "remaining_time": "1 day, 10:54:32", "throughput": 4665.83, "total_tokens": 365417272} {"current_steps": 6025, "total_steps": 15680, "loss": 0.33051772117614747, "lr": 6.7793634308673265e-06, "epoch": 0.7684948979591837, "percentage": 38.42, "elapsed_time": "21:46:17", "remaining_time": "1 day, 10:53:18", "throughput": 4666.34, "total_tokens": 365734064} {"current_steps": 6030, "total_steps": 15680, "loss": 0.36424710750579836, "lr": 6.7746815334499426e-06, "epoch": 0.7691326530612245, "percentage": 38.46, "elapsed_time": "21:47:28", "remaining_time": "1 day, 10:52:24", "throughput": 4666.09, "total_tokens": 366049464} {"current_steps": 6035, "total_steps": 15680, "loss": 0.32325961589813235, "lr": 6.7699978550156954e-06, "epoch": 0.7697704081632653, "percentage": 38.49, "elapsed_time": "21:48:35", "remaining_time": "1 day, 10:51:22", "throughput": 4665.85, "total_tokens": 366343576} {"current_steps": 6040, "total_steps": 15680, "loss": 0.3155065059661865, "lr": 6.765312400264985e-06, "epoch": 0.7704081632653061, "percentage": 38.52, "elapsed_time": "21:49:48", "remaining_time": "1 day, 10:50:28", "throughput": 4665.29, "total_tokens": 366636248} {"current_steps": 6045, "total_steps": 15680, "loss": 0.337229585647583, "lr": 6.760625173899992e-06, "epoch": 0.7710459183673469, "percentage": 38.55, "elapsed_time": "21:51:04", "remaining_time": "1 day, 10:49:42", "throughput": 4664.62, "total_tokens": 366941976} {"current_steps": 6050, "total_steps": 15680, "loss": 0.32468380928039553, "lr": 6.755936180624674e-06, "epoch": 0.7716836734693877, "percentage": 38.58, "elapsed_time": "21:52:15", "remaining_time": "1 day, 10:48:45", "throughput": 4664.34, "total_tokens": 367248712} {"current_steps": 6055, "total_steps": 15680, "loss": 0.32178239822387694, "lr": 6.751245425144765e-06, "epoch": 0.7723214285714286, "percentage": 38.62, "elapsed_time": "21:53:29", "remaining_time": "1 day, 10:47:54", "throughput": 4663.81, "total_tokens": 367551760} {"current_steps": 6060, "total_steps": 15680, "loss": 0.32709217071533203, "lr": 6.746552912167766e-06, "epoch": 0.7729591836734694, "percentage": 38.65, "elapsed_time": "21:54:32", "remaining_time": "1 day, 10:46:46", "throughput": 4663.84, "total_tokens": 367848936} {"current_steps": 6065, "total_steps": 15680, "loss": 0.3186192035675049, "lr": 6.741858646402941e-06, "epoch": 0.7735969387755102, "percentage": 38.68, "elapsed_time": "21:55:31", "remaining_time": "1 day, 10:45:31", "throughput": 4664.09, "total_tokens": 368142096} {"current_steps": 6070, "total_steps": 15680, "loss": 0.3359341621398926, "lr": 6.737162632561311e-06, "epoch": 0.7742346938775511, "percentage": 38.71, "elapsed_time": "21:56:32", "remaining_time": "1 day, 10:44:21", "throughput": 4664.29, "total_tokens": 368445424} {"current_steps": 6075, "total_steps": 15680, "loss": 0.31608850955963136, "lr": 6.732464875355657e-06, "epoch": 0.7748724489795918, "percentage": 38.74, "elapsed_time": "21:57:37", "remaining_time": "1 day, 10:43:15", "throughput": 4664.12, "total_tokens": 368733496} {"current_steps": 6080, "total_steps": 15680, "loss": 0.3017498254776001, "lr": 6.7277653795005085e-06, "epoch": 0.7755102040816326, "percentage": 38.78, "elapsed_time": "21:58:50", "remaining_time": "1 day, 10:42:23", "throughput": 4663.6, "total_tokens": 369034840} {"current_steps": 6085, "total_steps": 15680, "loss": 0.32140769958496096, "lr": 6.723064149712131e-06, "epoch": 0.7761479591836735, "percentage": 38.81, "elapsed_time": "22:00:03", "remaining_time": "1 day, 10:41:30", "throughput": 4663.02, "total_tokens": 369326688} {"current_steps": 6090, "total_steps": 15680, "loss": 0.3158728122711182, "lr": 6.718361190708542e-06, "epoch": 0.7767857142857143, "percentage": 38.84, "elapsed_time": "22:01:11", "remaining_time": "1 day, 10:40:29", "throughput": 4662.71, "total_tokens": 369618520} {"current_steps": 6095, "total_steps": 15680, "loss": 0.33606772422790526, "lr": 6.713656507209489e-06, "epoch": 0.7774234693877551, "percentage": 38.87, "elapsed_time": "22:02:28", "remaining_time": "1 day, 10:39:44", "throughput": 4662.03, "total_tokens": 369926744} {"current_steps": 6100, "total_steps": 15680, "loss": 0.34429340362548827, "lr": 6.708950103936448e-06, "epoch": 0.7780612244897959, "percentage": 38.9, "elapsed_time": "22:03:28", "remaining_time": "1 day, 10:38:30", "throughput": 4662.15, "total_tokens": 370215696} {"current_steps": 6105, "total_steps": 15680, "loss": 0.3338142395019531, "lr": 6.704241985612625e-06, "epoch": 0.7786989795918368, "percentage": 38.93, "elapsed_time": "22:04:36", "remaining_time": "1 day, 10:37:30", "throughput": 4662.03, "total_tokens": 370522096} {"current_steps": 6110, "total_steps": 15680, "loss": 0.35149459838867186, "lr": 6.699532156962945e-06, "epoch": 0.7793367346938775, "percentage": 38.97, "elapsed_time": "22:05:42", "remaining_time": "1 day, 10:36:26", "throughput": 4662.04, "total_tokens": 370830696} {"current_steps": 6115, "total_steps": 15680, "loss": 0.310459041595459, "lr": 6.6948206227140525e-06, "epoch": 0.7799744897959183, "percentage": 39.0, "elapsed_time": "22:06:50", "remaining_time": "1 day, 10:35:26", "throughput": 4661.7, "total_tokens": 371121648} {"current_steps": 6120, "total_steps": 15680, "loss": 0.33449711799621584, "lr": 6.690107387594298e-06, "epoch": 0.7806122448979592, "percentage": 39.03, "elapsed_time": "22:07:56", "remaining_time": "1 day, 10:34:22", "throughput": 4661.59, "total_tokens": 371420784} {"current_steps": 6125, "total_steps": 15680, "loss": 0.34175596237182615, "lr": 6.685392456333744e-06, "epoch": 0.78125, "percentage": 39.06, "elapsed_time": "22:09:01", "remaining_time": "1 day, 10:33:16", "throughput": 4661.74, "total_tokens": 371734544} {"current_steps": 6130, "total_steps": 15680, "loss": 0.3424098491668701, "lr": 6.680675833664151e-06, "epoch": 0.7818877551020408, "percentage": 39.09, "elapsed_time": "22:10:05", "remaining_time": "1 day, 10:32:10", "throughput": 4661.85, "total_tokens": 372041800} {"current_steps": 6135, "total_steps": 15680, "loss": 0.3392969608306885, "lr": 6.67595752431898e-06, "epoch": 0.7825255102040817, "percentage": 39.13, "elapsed_time": "22:11:10", "remaining_time": "1 day, 10:31:05", "throughput": 4661.85, "total_tokens": 372345688} {"current_steps": 6140, "total_steps": 15680, "loss": 0.3433082580566406, "lr": 6.671237533033388e-06, "epoch": 0.7831632653061225, "percentage": 39.16, "elapsed_time": "22:12:15", "remaining_time": "1 day, 10:29:59", "throughput": 4661.91, "total_tokens": 372652808} {"current_steps": 6145, "total_steps": 15680, "loss": 0.3486523151397705, "lr": 6.66651586454421e-06, "epoch": 0.7838010204081632, "percentage": 39.19, "elapsed_time": "22:13:29", "remaining_time": "1 day, 10:29:08", "throughput": 4661.42, "total_tokens": 372959856} {"current_steps": 6150, "total_steps": 15680, "loss": 0.32809312343597413, "lr": 6.661792523589972e-06, "epoch": 0.7844387755102041, "percentage": 39.22, "elapsed_time": "22:14:25", "remaining_time": "1 day, 10:27:48", "throughput": 4661.85, "total_tokens": 373252488} {"current_steps": 6155, "total_steps": 15680, "loss": 0.31272296905517577, "lr": 6.65706751491088e-06, "epoch": 0.7850765306122449, "percentage": 39.25, "elapsed_time": "22:15:23", "remaining_time": "1 day, 10:26:32", "throughput": 4661.99, "total_tokens": 373532416} {"current_steps": 6160, "total_steps": 15680, "loss": 0.32628664970397947, "lr": 6.652340843248806e-06, "epoch": 0.7857142857142857, "percentage": 39.29, "elapsed_time": "22:16:25", "remaining_time": "1 day, 10:25:22", "throughput": 4662.24, "total_tokens": 373842496} {"current_steps": 6165, "total_steps": 15680, "loss": 0.3464928150177002, "lr": 6.647612513347297e-06, "epoch": 0.7863520408163265, "percentage": 39.32, "elapsed_time": "22:17:27", "remaining_time": "1 day, 10:24:12", "throughput": 4662.4, "total_tokens": 374144912} {"current_steps": 6170, "total_steps": 15680, "loss": 0.3017390727996826, "lr": 6.642882529951561e-06, "epoch": 0.7869897959183674, "percentage": 39.35, "elapsed_time": "22:18:28", "remaining_time": "1 day, 10:23:02", "throughput": 4662.57, "total_tokens": 374445840} {"current_steps": 6175, "total_steps": 15680, "loss": 0.32829220294952394, "lr": 6.638150897808469e-06, "epoch": 0.7876275510204082, "percentage": 39.38, "elapsed_time": "22:19:33", "remaining_time": "1 day, 10:21:56", "throughput": 4662.63, "total_tokens": 374751360} {"current_steps": 6180, "total_steps": 15680, "loss": 0.35643610954284666, "lr": 6.6334176216665406e-06, "epoch": 0.7882653061224489, "percentage": 39.41, "elapsed_time": "22:20:46", "remaining_time": "1 day, 10:21:03", "throughput": 4662.35, "total_tokens": 375070264} {"current_steps": 6185, "total_steps": 15680, "loss": 0.3124289035797119, "lr": 6.628682706275953e-06, "epoch": 0.7889030612244898, "percentage": 39.45, "elapsed_time": "22:21:56", "remaining_time": "1 day, 10:20:06", "throughput": 4662.22, "total_tokens": 375387304} {"current_steps": 6190, "total_steps": 15680, "loss": 0.31171629428863523, "lr": 6.623946156388523e-06, "epoch": 0.7895408163265306, "percentage": 39.48, "elapsed_time": "22:22:59", "remaining_time": "1 day, 10:18:58", "throughput": 4662.4, "total_tokens": 375695664} {"current_steps": 6195, "total_steps": 15680, "loss": 0.3073967218399048, "lr": 6.619207976757708e-06, "epoch": 0.7901785714285714, "percentage": 39.51, "elapsed_time": "22:24:10", "remaining_time": "1 day, 10:18:02", "throughput": 4662.08, "total_tokens": 376000720} {"current_steps": 6200, "total_steps": 15680, "loss": 0.33098201751708983, "lr": 6.614468172138603e-06, "epoch": 0.7908163265306123, "percentage": 39.54, "elapsed_time": "22:25:18", "remaining_time": "1 day, 10:17:01", "throughput": 4661.98, "total_tokens": 376307968} {"current_steps": 6205, "total_steps": 15680, "loss": 0.36113386154174804, "lr": 6.609726747287934e-06, "epoch": 0.7914540816326531, "percentage": 39.57, "elapsed_time": "22:26:25", "remaining_time": "1 day, 10:15:59", "throughput": 4661.89, "total_tokens": 376615000} {"current_steps": 6210, "total_steps": 15680, "loss": 0.33744571208953855, "lr": 6.60498370696405e-06, "epoch": 0.7920918367346939, "percentage": 39.6, "elapsed_time": "22:27:32", "remaining_time": "1 day, 10:14:56", "throughput": 4661.88, "total_tokens": 376925336} {"current_steps": 6215, "total_steps": 15680, "loss": 0.32979750633239746, "lr": 6.600239055926923e-06, "epoch": 0.7927295918367347, "percentage": 39.64, "elapsed_time": "22:28:39", "remaining_time": "1 day, 10:13:54", "throughput": 4661.88, "total_tokens": 377234936} {"current_steps": 6220, "total_steps": 15680, "loss": 0.31255078315734863, "lr": 6.595492798938146e-06, "epoch": 0.7933673469387755, "percentage": 39.67, "elapsed_time": "22:29:58", "remaining_time": "1 day, 10:13:10", "throughput": 4661.16, "total_tokens": 377545848} {"current_steps": 6225, "total_steps": 15680, "loss": 0.31581578254699705, "lr": 6.5907449407609145e-06, "epoch": 0.7940051020408163, "percentage": 39.7, "elapsed_time": "22:30:53", "remaining_time": "1 day, 10:11:50", "throughput": 4661.81, "total_tokens": 377855984} {"current_steps": 6230, "total_steps": 15680, "loss": 0.34901602268218995, "lr": 6.585995486160038e-06, "epoch": 0.7946428571428571, "percentage": 39.73, "elapsed_time": "22:32:07", "remaining_time": "1 day, 10:10:58", "throughput": 4661.16, "total_tokens": 378147568} {"current_steps": 6235, "total_steps": 15680, "loss": 0.32438206672668457, "lr": 6.581244439901926e-06, "epoch": 0.795280612244898, "percentage": 39.76, "elapsed_time": "22:33:21", "remaining_time": "1 day, 10:10:07", "throughput": 4660.55, "total_tokens": 378444336} {"current_steps": 6240, "total_steps": 15680, "loss": 0.33559203147888184, "lr": 6.576491806754583e-06, "epoch": 0.7959183673469388, "percentage": 39.8, "elapsed_time": "22:34:36", "remaining_time": "1 day, 10:09:16", "throughput": 4659.97, "total_tokens": 378743920} {"current_steps": 6245, "total_steps": 15680, "loss": 0.3278643131256104, "lr": 6.571737591487611e-06, "epoch": 0.7965561224489796, "percentage": 39.83, "elapsed_time": "22:35:47", "remaining_time": "1 day, 10:08:21", "throughput": 4659.37, "total_tokens": 379029696} {"current_steps": 6250, "total_steps": 15680, "loss": 0.3245952844619751, "lr": 6.566981798872196e-06, "epoch": 0.7971938775510204, "percentage": 39.86, "elapsed_time": "22:36:42", "remaining_time": "1 day, 10:06:59", "throughput": 4659.93, "total_tokens": 379328424} {"current_steps": 6255, "total_steps": 15680, "loss": 0.3304758071899414, "lr": 6.562224433681108e-06, "epoch": 0.7978316326530612, "percentage": 39.89, "elapsed_time": "22:37:50", "remaining_time": "1 day, 10:05:59", "throughput": 4659.73, "total_tokens": 379631176} {"current_steps": 6260, "total_steps": 15680, "loss": 0.32650887966156006, "lr": 6.557465500688696e-06, "epoch": 0.798469387755102, "percentage": 39.92, "elapsed_time": "22:38:49", "remaining_time": "1 day, 10:04:45", "throughput": 4660.07, "total_tokens": 379935264} {"current_steps": 6265, "total_steps": 15680, "loss": 0.332712984085083, "lr": 6.55270500467088e-06, "epoch": 0.7991071428571429, "percentage": 39.96, "elapsed_time": "22:39:50", "remaining_time": "1 day, 10:03:33", "throughput": 4660.18, "total_tokens": 380227320} {"current_steps": 6270, "total_steps": 15680, "loss": 0.3316300392150879, "lr": 6.5479429504051526e-06, "epoch": 0.7997448979591837, "percentage": 39.99, "elapsed_time": "22:40:53", "remaining_time": "1 day, 10:02:25", "throughput": 4660.55, "total_tokens": 380549496} {"current_steps": 6275, "total_steps": 15680, "loss": 0.33006997108459474, "lr": 6.543179342670565e-06, "epoch": 0.8003826530612245, "percentage": 40.02, "elapsed_time": "22:41:52", "remaining_time": "1 day, 10:01:10", "throughput": 4660.97, "total_tokens": 380858120} {"current_steps": 6280, "total_steps": 15680, "loss": 0.3384885311126709, "lr": 6.53841418624773e-06, "epoch": 0.8010204081632653, "percentage": 40.05, "elapsed_time": "22:42:49", "remaining_time": "1 day, 9:59:53", "throughput": 4661.55, "total_tokens": 381172088} {"current_steps": 6285, "total_steps": 15680, "loss": 0.31926870346069336, "lr": 6.53364748591882e-06, "epoch": 0.8016581632653061, "percentage": 40.08, "elapsed_time": "22:44:04", "remaining_time": "1 day, 9:59:03", "throughput": 4661.03, "total_tokens": 381480256} {"current_steps": 6290, "total_steps": 15680, "loss": 0.3026753902435303, "lr": 6.528879246467546e-06, "epoch": 0.8022959183673469, "percentage": 40.11, "elapsed_time": "22:45:24", "remaining_time": "1 day, 9:58:20", "throughput": 4660.27, "total_tokens": 381790184} {"current_steps": 6295, "total_steps": 15680, "loss": 0.32082395553588866, "lr": 6.524109472679172e-06, "epoch": 0.8029336734693877, "percentage": 40.15, "elapsed_time": "22:46:25", "remaining_time": "1 day, 9:57:09", "throughput": 4660.58, "total_tokens": 382099120} {"current_steps": 6300, "total_steps": 15680, "loss": 0.3002665042877197, "lr": 6.519338169340499e-06, "epoch": 0.8035714285714286, "percentage": 40.18, "elapsed_time": "22:47:35", "remaining_time": "1 day, 9:56:11", "throughput": 4660.17, "total_tokens": 382391256} {"current_steps": 6305, "total_steps": 15680, "loss": 0.35150899887084963, "lr": 6.514565341239861e-06, "epoch": 0.8042091836734694, "percentage": 40.21, "elapsed_time": "22:48:49", "remaining_time": "1 day, 9:55:20", "throughput": 4659.63, "total_tokens": 382694608} {"current_steps": 6310, "total_steps": 15680, "loss": 0.3224548578262329, "lr": 6.509790993167129e-06, "epoch": 0.8048469387755102, "percentage": 40.24, "elapsed_time": "22:49:57", "remaining_time": "1 day, 9:54:19", "throughput": 4659.48, "total_tokens": 382998672} {"current_steps": 6315, "total_steps": 15680, "loss": 0.32113525867462156, "lr": 6.505015129913689e-06, "epoch": 0.8054846938775511, "percentage": 40.27, "elapsed_time": "22:51:03", "remaining_time": "1 day, 9:53:14", "throughput": 4659.45, "total_tokens": 383300808} {"current_steps": 6320, "total_steps": 15680, "loss": 0.31710638999938967, "lr": 6.5002377562724585e-06, "epoch": 0.8061224489795918, "percentage": 40.31, "elapsed_time": "22:52:06", "remaining_time": "1 day, 9:52:05", "throughput": 4659.49, "total_tokens": 383597304} {"current_steps": 6325, "total_steps": 15680, "loss": 0.3188472747802734, "lr": 6.495458877037861e-06, "epoch": 0.8067602040816326, "percentage": 40.34, "elapsed_time": "22:53:02", "remaining_time": "1 day, 9:50:47", "throughput": 4660.08, "total_tokens": 383907680} {"current_steps": 6330, "total_steps": 15680, "loss": 0.3157522678375244, "lr": 6.490678497005839e-06, "epoch": 0.8073979591836735, "percentage": 40.37, "elapsed_time": "22:54:13", "remaining_time": "1 day, 9:49:51", "throughput": 4659.64, "total_tokens": 384204280} {"current_steps": 6335, "total_steps": 15680, "loss": 0.33968181610107423, "lr": 6.485896620973836e-06, "epoch": 0.8080357142857143, "percentage": 40.4, "elapsed_time": "22:55:18", "remaining_time": "1 day, 9:48:46", "throughput": 4659.72, "total_tokens": 384514248} {"current_steps": 6340, "total_steps": 15680, "loss": 0.31825881004333495, "lr": 6.481113253740799e-06, "epoch": 0.8086734693877551, "percentage": 40.43, "elapsed_time": "22:56:31", "remaining_time": "1 day, 9:47:52", "throughput": 4659.29, "total_tokens": 384818136} {"current_steps": 6345, "total_steps": 15680, "loss": 0.32604708671569826, "lr": 6.4763284001071715e-06, "epoch": 0.8093112244897959, "percentage": 40.47, "elapsed_time": "22:57:42", "remaining_time": "1 day, 9:46:56", "throughput": 4658.79, "total_tokens": 385109072} {"current_steps": 6350, "total_steps": 15680, "loss": 0.3351900577545166, "lr": 6.4715420648748875e-06, "epoch": 0.8099489795918368, "percentage": 40.5, "elapsed_time": "22:58:28", "remaining_time": "1 day, 9:45:23", "throughput": 4660.03, "total_tokens": 385425072} {"current_steps": 6355, "total_steps": 15680, "loss": 0.31918950080871583, "lr": 6.46675425284737e-06, "epoch": 0.8105867346938775, "percentage": 40.53, "elapsed_time": "22:59:30", "remaining_time": "1 day, 9:44:12", "throughput": 4660.46, "total_tokens": 385746512} {"current_steps": 6360, "total_steps": 15680, "loss": 0.33324904441833497, "lr": 6.461964968829521e-06, "epoch": 0.8112244897959183, "percentage": 40.56, "elapsed_time": "23:00:38", "remaining_time": "1 day, 9:43:11", "throughput": 4660.24, "total_tokens": 386044952} {"current_steps": 6365, "total_steps": 15680, "loss": 0.3209887981414795, "lr": 6.457174217627722e-06, "epoch": 0.8118622448979592, "percentage": 40.59, "elapsed_time": "23:01:45", "remaining_time": "1 day, 9:42:09", "throughput": 4660.05, "total_tokens": 386342120} {"current_steps": 6370, "total_steps": 15680, "loss": 0.33527679443359376, "lr": 6.452382004049829e-06, "epoch": 0.8125, "percentage": 40.62, "elapsed_time": "23:02:56", "remaining_time": "1 day, 9:41:13", "throughput": 4659.72, "total_tokens": 386646536} {"current_steps": 6375, "total_steps": 15680, "loss": 0.3298801422119141, "lr": 6.447588332905159e-06, "epoch": 0.8131377551020408, "percentage": 40.66, "elapsed_time": "23:03:54", "remaining_time": "1 day, 9:39:58", "throughput": 4660.09, "total_tokens": 386949672} {"current_steps": 6380, "total_steps": 15680, "loss": 0.31019001007080077, "lr": 6.4427932090044975e-06, "epoch": 0.8137755102040817, "percentage": 40.69, "elapsed_time": "23:04:55", "remaining_time": "1 day, 9:38:47", "throughput": 4660.28, "total_tokens": 387249864} {"current_steps": 6385, "total_steps": 15680, "loss": 0.30964839458465576, "lr": 6.437996637160086e-06, "epoch": 0.8144132653061225, "percentage": 40.72, "elapsed_time": "23:05:59", "remaining_time": "1 day, 9:37:39", "throughput": 4660.47, "total_tokens": 387560656} {"current_steps": 6390, "total_steps": 15680, "loss": 0.3111919403076172, "lr": 6.433198622185621e-06, "epoch": 0.8150510204081632, "percentage": 40.75, "elapsed_time": "23:07:05", "remaining_time": "1 day, 9:36:36", "throughput": 4660.48, "total_tokens": 387871280} {"current_steps": 6395, "total_steps": 15680, "loss": 0.32283749580383303, "lr": 6.428399168896244e-06, "epoch": 0.8156887755102041, "percentage": 40.78, "elapsed_time": "23:08:17", "remaining_time": "1 day, 9:35:40", "throughput": 4660.08, "total_tokens": 388172504} {"current_steps": 6400, "total_steps": 15680, "loss": 0.3457418203353882, "lr": 6.423598282108541e-06, "epoch": 0.8163265306122449, "percentage": 40.82, "elapsed_time": "23:09:23", "remaining_time": "1 day, 9:34:36", "throughput": 4659.98, "total_tokens": 388470624} {"current_steps": 6405, "total_steps": 15680, "loss": 0.3063065767288208, "lr": 6.41879596664054e-06, "epoch": 0.8169642857142857, "percentage": 40.85, "elapsed_time": "23:10:31", "remaining_time": "1 day, 9:33:36", "throughput": 4659.56, "total_tokens": 388756200} {"current_steps": 6410, "total_steps": 15680, "loss": 0.3302279472351074, "lr": 6.413992227311695e-06, "epoch": 0.8176020408163265, "percentage": 40.88, "elapsed_time": "23:11:40", "remaining_time": "1 day, 9:32:36", "throughput": 4659.4, "total_tokens": 389061280} {"current_steps": 6415, "total_steps": 15680, "loss": 0.34242465496063235, "lr": 6.409187068942899e-06, "epoch": 0.8182397959183674, "percentage": 40.91, "elapsed_time": "23:12:49", "remaining_time": "1 day, 9:31:36", "throughput": 4659.13, "total_tokens": 389359968} {"current_steps": 6420, "total_steps": 15680, "loss": 0.3474923610687256, "lr": 6.4043804963564616e-06, "epoch": 0.8188775510204082, "percentage": 40.94, "elapsed_time": "23:13:55", "remaining_time": "1 day, 9:30:33", "throughput": 4658.97, "total_tokens": 389657360} {"current_steps": 6425, "total_steps": 15680, "loss": 0.32995893955230715, "lr": 6.399572514376114e-06, "epoch": 0.8195153061224489, "percentage": 40.98, "elapsed_time": "23:15:04", "remaining_time": "1 day, 9:29:33", "throughput": 4658.72, "total_tokens": 389956520} {"current_steps": 6430, "total_steps": 15680, "loss": 0.34971914291381834, "lr": 6.394763127827001e-06, "epoch": 0.8201530612244898, "percentage": 41.01, "elapsed_time": "23:16:09", "remaining_time": "1 day, 9:28:27", "throughput": 4658.78, "total_tokens": 390262136} {"current_steps": 6435, "total_steps": 15680, "loss": 0.31062195301055906, "lr": 6.389952341535681e-06, "epoch": 0.8207908163265306, "percentage": 41.04, "elapsed_time": "23:17:09", "remaining_time": "1 day, 9:27:15", "throughput": 4658.96, "total_tokens": 390557592} {"current_steps": 6440, "total_steps": 15680, "loss": 0.3330610036849976, "lr": 6.385140160330113e-06, "epoch": 0.8214285714285714, "percentage": 41.07, "elapsed_time": "23:18:20", "remaining_time": "1 day, 9:26:19", "throughput": 4658.63, "total_tokens": 390863264} {"current_steps": 6445, "total_steps": 15680, "loss": 0.3594696521759033, "lr": 6.380326589039653e-06, "epoch": 0.8220663265306123, "percentage": 41.1, "elapsed_time": "23:19:23", "remaining_time": "1 day, 9:25:11", "throughput": 4658.82, "total_tokens": 391172112} {"current_steps": 6450, "total_steps": 15680, "loss": 0.3546117305755615, "lr": 6.375511632495062e-06, "epoch": 0.8227040816326531, "percentage": 41.14, "elapsed_time": "23:20:28", "remaining_time": "1 day, 9:24:05", "throughput": 4658.81, "total_tokens": 391471568} {"current_steps": 6455, "total_steps": 15680, "loss": 0.31263294219970705, "lr": 6.370695295528482e-06, "epoch": 0.8233418367346939, "percentage": 41.17, "elapsed_time": "23:21:47", "remaining_time": "1 day, 9:23:20", "throughput": 4658.03, "total_tokens": 391776424} {"current_steps": 6460, "total_steps": 15680, "loss": 0.31137876510620116, "lr": 6.365877582973442e-06, "epoch": 0.8239795918367347, "percentage": 41.2, "elapsed_time": "23:22:52", "remaining_time": "1 day, 9:22:14", "throughput": 4657.95, "total_tokens": 392070888} {"current_steps": 6465, "total_steps": 15680, "loss": 0.3098623514175415, "lr": 6.361058499664856e-06, "epoch": 0.8246173469387755, "percentage": 41.23, "elapsed_time": "23:24:02", "remaining_time": "1 day, 9:21:16", "throughput": 4657.58, "total_tokens": 392367136} {"current_steps": 6470, "total_steps": 15680, "loss": 0.33841404914855955, "lr": 6.3562380504390095e-06, "epoch": 0.8252551020408163, "percentage": 41.26, "elapsed_time": "23:25:06", "remaining_time": "1 day, 9:20:09", "throughput": 4657.68, "total_tokens": 392670760} {"current_steps": 6475, "total_steps": 15680, "loss": 0.3283223628997803, "lr": 6.35141624013356e-06, "epoch": 0.8258928571428571, "percentage": 41.29, "elapsed_time": "23:26:11", "remaining_time": "1 day, 9:19:04", "throughput": 4657.6, "total_tokens": 392969760} {"current_steps": 6480, "total_steps": 15680, "loss": 0.3258841037750244, "lr": 6.34659307358753e-06, "epoch": 0.826530612244898, "percentage": 41.33, "elapsed_time": "23:27:19", "remaining_time": "1 day, 9:18:03", "throughput": 4657.47, "total_tokens": 393274232} {"current_steps": 6485, "total_steps": 15680, "loss": 0.3115019083023071, "lr": 6.341768555641306e-06, "epoch": 0.8271683673469388, "percentage": 41.36, "elapsed_time": "23:28:34", "remaining_time": "1 day, 9:17:11", "throughput": 4656.94, "total_tokens": 393577920} {"current_steps": 6490, "total_steps": 15680, "loss": 0.33711268901824953, "lr": 6.3369426911366275e-06, "epoch": 0.8278061224489796, "percentage": 41.39, "elapsed_time": "23:29:32", "remaining_time": "1 day, 9:15:56", "throughput": 4657.36, "total_tokens": 393884184} {"current_steps": 6495, "total_steps": 15680, "loss": 0.32443020343780515, "lr": 6.332115484916586e-06, "epoch": 0.8284438775510204, "percentage": 41.42, "elapsed_time": "23:30:50", "remaining_time": "1 day, 9:15:09", "throughput": 4656.66, "total_tokens": 394188088} {"current_steps": 6500, "total_steps": 15680, "loss": 0.32749388217926023, "lr": 6.327286941825621e-06, "epoch": 0.8290816326530612, "percentage": 41.45, "elapsed_time": "23:31:58", "remaining_time": "1 day, 9:14:08", "throughput": 4656.52, "total_tokens": 394492024} {"current_steps": 6505, "total_steps": 15680, "loss": 0.3317603588104248, "lr": 6.322457066709511e-06, "epoch": 0.829719387755102, "percentage": 41.49, "elapsed_time": "23:33:00", "remaining_time": "1 day, 9:12:58", "throughput": 4656.61, "total_tokens": 394788840} {"current_steps": 6510, "total_steps": 15680, "loss": 0.333458685874939, "lr": 6.317625864415374e-06, "epoch": 0.8303571428571429, "percentage": 41.52, "elapsed_time": "23:34:04", "remaining_time": "1 day, 9:11:52", "throughput": 4656.59, "total_tokens": 395087728} {"current_steps": 6515, "total_steps": 15680, "loss": 0.3259648323059082, "lr": 6.312793339791662e-06, "epoch": 0.8309948979591837, "percentage": 41.55, "elapsed_time": "23:35:07", "remaining_time": "1 day, 9:10:43", "throughput": 4656.81, "total_tokens": 395396384} {"current_steps": 6520, "total_steps": 15680, "loss": 0.3173699140548706, "lr": 6.307959497688146e-06, "epoch": 0.8316326530612245, "percentage": 41.58, "elapsed_time": "23:36:01", "remaining_time": "1 day, 9:09:22", "throughput": 4657.59, "total_tokens": 395713712} {"current_steps": 6525, "total_steps": 15680, "loss": 0.30993361473083497, "lr": 6.303124342955928e-06, "epoch": 0.8322704081632653, "percentage": 41.61, "elapsed_time": "23:37:05", "remaining_time": "1 day, 9:08:16", "throughput": 4657.7, "total_tokens": 396025264} {"current_steps": 6530, "total_steps": 15680, "loss": 0.35101368427276614, "lr": 6.29828788044742e-06, "epoch": 0.8329081632653061, "percentage": 41.65, "elapsed_time": "23:38:10", "remaining_time": "1 day, 9:07:11", "throughput": 4657.71, "total_tokens": 396326840} {"current_steps": 6535, "total_steps": 15680, "loss": 0.3599194765090942, "lr": 6.293450115016353e-06, "epoch": 0.8335459183673469, "percentage": 41.68, "elapsed_time": "23:39:25", "remaining_time": "1 day, 9:06:18", "throughput": 4657.21, "total_tokens": 396631624} {"current_steps": 6540, "total_steps": 15680, "loss": 0.30787858963012693, "lr": 6.288611051517761e-06, "epoch": 0.8341836734693877, "percentage": 41.71, "elapsed_time": "23:40:26", "remaining_time": "1 day, 9:05:09", "throughput": 4657.45, "total_tokens": 396939384} {"current_steps": 6545, "total_steps": 15680, "loss": 0.33837013244628905, "lr": 6.283770694807983e-06, "epoch": 0.8348214285714286, "percentage": 41.74, "elapsed_time": "23:41:25", "remaining_time": "1 day, 9:03:54", "throughput": 4657.81, "total_tokens": 397242280} {"current_steps": 6550, "total_steps": 15680, "loss": 0.32402629852294923, "lr": 6.2789290497446546e-06, "epoch": 0.8354591836734694, "percentage": 41.77, "elapsed_time": "23:42:18", "remaining_time": "1 day, 9:02:32", "throughput": 4658.45, "total_tokens": 397544432} {"current_steps": 6555, "total_steps": 15680, "loss": 0.3160156011581421, "lr": 6.274086121186704e-06, "epoch": 0.8360969387755102, "percentage": 41.8, "elapsed_time": "23:43:20", "remaining_time": "1 day, 9:01:22", "throughput": 4658.63, "total_tokens": 397846616} {"current_steps": 6560, "total_steps": 15680, "loss": 0.3336780071258545, "lr": 6.269241913994348e-06, "epoch": 0.8367346938775511, "percentage": 41.84, "elapsed_time": "23:44:24", "remaining_time": "1 day, 9:00:17", "throughput": 4658.6, "total_tokens": 398146648} {"current_steps": 6565, "total_steps": 15680, "loss": 0.31669230461120607, "lr": 6.264396433029089e-06, "epoch": 0.8373724489795918, "percentage": 41.87, "elapsed_time": "23:45:26", "remaining_time": "1 day, 8:59:06", "throughput": 4658.95, "total_tokens": 398463520} {"current_steps": 6570, "total_steps": 15680, "loss": 0.33449468612670896, "lr": 6.2595496831537025e-06, "epoch": 0.8380102040816326, "percentage": 41.9, "elapsed_time": "23:46:42", "remaining_time": "1 day, 8:58:17", "throughput": 4658.29, "total_tokens": 398761768} {"current_steps": 6575, "total_steps": 15680, "loss": 0.3276800632476807, "lr": 6.254701669232243e-06, "epoch": 0.8386479591836735, "percentage": 41.93, "elapsed_time": "23:47:48", "remaining_time": "1 day, 8:57:13", "throughput": 4658.2, "total_tokens": 399063288} {"current_steps": 6580, "total_steps": 15680, "loss": 0.3333900451660156, "lr": 6.24985239613003e-06, "epoch": 0.8392857142857143, "percentage": 41.96, "elapsed_time": "23:48:49", "remaining_time": "1 day, 8:56:01", "throughput": 4658.43, "total_tokens": 399362432} {"current_steps": 6585, "total_steps": 15680, "loss": 0.3394115447998047, "lr": 6.24500186871365e-06, "epoch": 0.8399234693877551, "percentage": 42.0, "elapsed_time": "23:49:50", "remaining_time": "1 day, 8:54:51", "throughput": 4658.74, "total_tokens": 399677872} {"current_steps": 6590, "total_steps": 15680, "loss": 0.30324516296386717, "lr": 6.240150091850941e-06, "epoch": 0.8405612244897959, "percentage": 42.03, "elapsed_time": "23:50:59", "remaining_time": "1 day, 8:53:51", "throughput": 4658.54, "total_tokens": 399979672} {"current_steps": 6595, "total_steps": 15680, "loss": 0.30373287200927734, "lr": 6.235297070411004e-06, "epoch": 0.8411989795918368, "percentage": 42.06, "elapsed_time": "23:51:53", "remaining_time": "1 day, 8:52:30", "throughput": 4658.97, "total_tokens": 400268008} {"current_steps": 6600, "total_steps": 15680, "loss": 0.32518959045410156, "lr": 6.230442809264186e-06, "epoch": 0.8418367346938775, "percentage": 42.09, "elapsed_time": "23:53:06", "remaining_time": "1 day, 8:51:36", "throughput": 4658.48, "total_tokens": 400566488} {"current_steps": 6605, "total_steps": 15680, "loss": 0.3347949981689453, "lr": 6.225587313282071e-06, "epoch": 0.8424744897959183, "percentage": 42.12, "elapsed_time": "23:54:13", "remaining_time": "1 day, 8:50:34", "throughput": 4658.29, "total_tokens": 400862976} {"current_steps": 6610, "total_steps": 15680, "loss": 0.3171133041381836, "lr": 6.220730587337496e-06, "epoch": 0.8431122448979592, "percentage": 42.16, "elapsed_time": "23:55:12", "remaining_time": "1 day, 8:49:20", "throughput": 4658.5, "total_tokens": 401154544} {"current_steps": 6615, "total_steps": 15680, "loss": 0.318402099609375, "lr": 6.21587263630452e-06, "epoch": 0.84375, "percentage": 42.19, "elapsed_time": "23:56:11", "remaining_time": "1 day, 8:48:07", "throughput": 4658.97, "total_tokens": 401472632} {"current_steps": 6620, "total_steps": 15680, "loss": 0.3207444429397583, "lr": 6.2110134650584355e-06, "epoch": 0.8443877551020408, "percentage": 42.22, "elapsed_time": "23:57:19", "remaining_time": "1 day, 8:47:06", "throughput": 4658.73, "total_tokens": 401768440} {"current_steps": 6625, "total_steps": 15680, "loss": 0.32271835803985593, "lr": 6.2061530784757625e-06, "epoch": 0.8450255102040817, "percentage": 42.25, "elapsed_time": "23:58:25", "remaining_time": "1 day, 8:46:01", "throughput": 4658.66, "total_tokens": 402067584} {"current_steps": 6630, "total_steps": 15680, "loss": 0.3248939275741577, "lr": 6.201291481434238e-06, "epoch": 0.8456632653061225, "percentage": 42.28, "elapsed_time": "23:59:32", "remaining_time": "1 day, 8:44:59", "throughput": 4658.63, "total_tokens": 402378216} {"current_steps": 6635, "total_steps": 15680, "loss": 0.3274501323699951, "lr": 6.196428678812816e-06, "epoch": 0.8463010204081632, "percentage": 42.32, "elapsed_time": "1 day, 0:00:51", "remaining_time": "1 day, 8:44:12", "throughput": 4658.01, "total_tokens": 402690616} {"current_steps": 6640, "total_steps": 15680, "loss": 0.3477298736572266, "lr": 6.191564675491653e-06, "epoch": 0.8469387755102041, "percentage": 42.35, "elapsed_time": "1 day, 0:01:55", "remaining_time": "1 day, 8:43:05", "throughput": 4658.01, "total_tokens": 402988264} {"current_steps": 6645, "total_steps": 15680, "loss": 0.3256032466888428, "lr": 6.1866994763521215e-06, "epoch": 0.8475765306122449, "percentage": 42.38, "elapsed_time": "1 day, 0:03:05", "remaining_time": "1 day, 8:42:08", "throughput": 4657.66, "total_tokens": 403287792} {"current_steps": 6650, "total_steps": 15680, "loss": 0.3299060344696045, "lr": 6.1818330862767864e-06, "epoch": 0.8482142857142857, "percentage": 42.41, "elapsed_time": "1 day, 0:04:22", "remaining_time": "1 day, 8:41:18", "throughput": 4657.15, "total_tokens": 403598584} {"current_steps": 6655, "total_steps": 15680, "loss": 0.3210991621017456, "lr": 6.176965510149409e-06, "epoch": 0.8488520408163265, "percentage": 42.44, "elapsed_time": "1 day, 0:05:22", "remaining_time": "1 day, 8:40:06", "throughput": 4657.39, "total_tokens": 403901864} {"current_steps": 6660, "total_steps": 15680, "loss": 0.325441312789917, "lr": 6.172096752854943e-06, "epoch": 0.8494897959183674, "percentage": 42.47, "elapsed_time": "1 day, 0:06:17", "remaining_time": "1 day, 8:38:47", "throughput": 4658.15, "total_tokens": 404221656} {"current_steps": 6665, "total_steps": 15680, "loss": 0.33939661979675295, "lr": 6.1672268192795285e-06, "epoch": 0.8501275510204082, "percentage": 42.51, "elapsed_time": "1 day, 0:07:26", "remaining_time": "1 day, 8:37:47", "throughput": 4657.94, "total_tokens": 404524552} {"current_steps": 6670, "total_steps": 15680, "loss": 0.33211517333984375, "lr": 6.16235571431048e-06, "epoch": 0.8507653061224489, "percentage": 42.54, "elapsed_time": "1 day, 0:08:21", "remaining_time": "1 day, 8:36:29", "throughput": 4658.65, "total_tokens": 404845408} {"current_steps": 6675, "total_steps": 15680, "loss": 0.34074184894561765, "lr": 6.157483442836294e-06, "epoch": 0.8514030612244898, "percentage": 42.57, "elapsed_time": "1 day, 0:09:26", "remaining_time": "1 day, 8:35:22", "throughput": 4658.74, "total_tokens": 405152056} {"current_steps": 6680, "total_steps": 15680, "loss": 0.3007451295852661, "lr": 6.1526100097466345e-06, "epoch": 0.8520408163265306, "percentage": 42.6, "elapsed_time": "1 day, 0:10:32", "remaining_time": "1 day, 8:34:19", "throughput": 4658.63, "total_tokens": 405452704} {"current_steps": 6685, "total_steps": 15680, "loss": 0.3128827571868896, "lr": 6.147735419932334e-06, "epoch": 0.8526785714285714, "percentage": 42.63, "elapsed_time": "1 day, 0:11:42", "remaining_time": "1 day, 8:33:20", "throughput": 4658.46, "total_tokens": 405763768} {"current_steps": 6690, "total_steps": 15680, "loss": 0.329839825630188, "lr": 6.142859678285378e-06, "epoch": 0.8533163265306123, "percentage": 42.67, "elapsed_time": "1 day, 0:12:50", "remaining_time": "1 day, 8:32:19", "throughput": 4658.3, "total_tokens": 406067088} {"current_steps": 6695, "total_steps": 15680, "loss": 0.33551831245422364, "lr": 6.13798278969892e-06, "epoch": 0.8539540816326531, "percentage": 42.7, "elapsed_time": "1 day, 0:13:41", "remaining_time": "1 day, 8:30:55", "throughput": 4659.19, "total_tokens": 406381664} {"current_steps": 6700, "total_steps": 15680, "loss": 0.3395432949066162, "lr": 6.133104759067257e-06, "epoch": 0.8545918367346939, "percentage": 42.73, "elapsed_time": "1 day, 0:14:47", "remaining_time": "1 day, 8:29:51", "throughput": 4659.16, "total_tokens": 406688472} {"current_steps": 6705, "total_steps": 15680, "loss": 0.31645817756652833, "lr": 6.1282255912858315e-06, "epoch": 0.8552295918367347, "percentage": 42.76, "elapsed_time": "1 day, 0:16:01", "remaining_time": "1 day, 8:28:58", "throughput": 4658.7, "total_tokens": 406991872} {"current_steps": 6710, "total_steps": 15680, "loss": 0.35752263069152834, "lr": 6.1233452912512295e-06, "epoch": 0.8558673469387755, "percentage": 42.79, "elapsed_time": "1 day, 0:17:10", "remaining_time": "1 day, 8:27:57", "throughput": 4658.64, "total_tokens": 407305736} {"current_steps": 6715, "total_steps": 15680, "loss": 0.32277803421020507, "lr": 6.118463863861174e-06, "epoch": 0.8565051020408163, "percentage": 42.83, "elapsed_time": "1 day, 0:18:08", "remaining_time": "1 day, 8:26:43", "throughput": 4658.97, "total_tokens": 407606096} {"current_steps": 6720, "total_steps": 15680, "loss": 0.3247419595718384, "lr": 6.113581314014517e-06, "epoch": 0.8571428571428571, "percentage": 42.86, "elapsed_time": "1 day, 0:19:13", "remaining_time": "1 day, 8:25:38", "throughput": 4658.95, "total_tokens": 407909024} {"current_steps": 6725, "total_steps": 15680, "loss": 0.3387800931930542, "lr": 6.10869764661124e-06, "epoch": 0.857780612244898, "percentage": 42.89, "elapsed_time": "1 day, 0:20:22", "remaining_time": "1 day, 8:24:38", "throughput": 4658.82, "total_tokens": 408218712} {"current_steps": 6730, "total_steps": 15680, "loss": 0.31037344932556155, "lr": 6.103812866552444e-06, "epoch": 0.8584183673469388, "percentage": 42.92, "elapsed_time": "1 day, 0:21:28", "remaining_time": "1 day, 8:23:34", "throughput": 4658.7, "total_tokens": 408515880} {"current_steps": 6735, "total_steps": 15680, "loss": 0.32601146697998046, "lr": 6.0989269787403445e-06, "epoch": 0.8590561224489796, "percentage": 42.95, "elapsed_time": "1 day, 0:22:34", "remaining_time": "1 day, 8:22:29", "throughput": 4658.59, "total_tokens": 408812200} {"current_steps": 6740, "total_steps": 15680, "loss": 0.33951191902160643, "lr": 6.094039988078273e-06, "epoch": 0.8596938775510204, "percentage": 42.98, "elapsed_time": "1 day, 0:23:23", "remaining_time": "1 day, 8:21:03", "throughput": 4659.48, "total_tokens": 409120600} {"current_steps": 6745, "total_steps": 15680, "loss": 0.32826507091522217, "lr": 6.089151899470668e-06, "epoch": 0.8603316326530612, "percentage": 43.02, "elapsed_time": "1 day, 0:24:26", "remaining_time": "1 day, 8:19:56", "throughput": 4659.67, "total_tokens": 409431152} {"current_steps": 6750, "total_steps": 15680, "loss": 0.3277494192123413, "lr": 6.084262717823064e-06, "epoch": 0.860969387755102, "percentage": 43.05, "elapsed_time": "1 day, 0:25:33", "remaining_time": "1 day, 8:18:52", "throughput": 4659.65, "total_tokens": 409740144} {"current_steps": 6755, "total_steps": 15680, "loss": 0.3410026550292969, "lr": 6.079372448042098e-06, "epoch": 0.8616071428571429, "percentage": 43.08, "elapsed_time": "1 day, 0:26:35", "remaining_time": "1 day, 8:17:43", "throughput": 4659.9, "total_tokens": 410051832} {"current_steps": 6760, "total_steps": 15680, "loss": 0.34213569164276125, "lr": 6.074481095035498e-06, "epoch": 0.8622448979591837, "percentage": 43.11, "elapsed_time": "1 day, 0:27:23", "remaining_time": "1 day, 8:16:15", "throughput": 4660.81, "total_tokens": 410351752} {"current_steps": 6765, "total_steps": 15680, "loss": 0.3385669946670532, "lr": 6.069588663712077e-06, "epoch": 0.8628826530612245, "percentage": 43.14, "elapsed_time": "1 day, 0:28:35", "remaining_time": "1 day, 8:15:20", "throughput": 4660.37, "total_tokens": 410653368} {"current_steps": 6770, "total_steps": 15680, "loss": 0.33953258991241453, "lr": 6.064695158981732e-06, "epoch": 0.8635204081632653, "percentage": 43.18, "elapsed_time": "1 day, 0:29:54", "remaining_time": "1 day, 8:14:32", "throughput": 4659.66, "total_tokens": 410953864} {"current_steps": 6775, "total_steps": 15680, "loss": 0.33167431354522703, "lr": 6.059800585755436e-06, "epoch": 0.8641581632653061, "percentage": 43.21, "elapsed_time": "1 day, 0:30:52", "remaining_time": "1 day, 8:13:18", "throughput": 4660.07, "total_tokens": 411263728} {"current_steps": 6780, "total_steps": 15680, "loss": 0.3388916015625, "lr": 6.054904948945238e-06, "epoch": 0.8647959183673469, "percentage": 43.24, "elapsed_time": "1 day, 0:32:01", "remaining_time": "1 day, 8:12:18", "throughput": 4659.94, "total_tokens": 411574240} {"current_steps": 6785, "total_steps": 15680, "loss": 0.3238846778869629, "lr": 6.050008253464247e-06, "epoch": 0.8654336734693877, "percentage": 43.27, "elapsed_time": "1 day, 0:33:04", "remaining_time": "1 day, 8:11:09", "throughput": 4660.19, "total_tokens": 411886128} {"current_steps": 6790, "total_steps": 15680, "loss": 0.31720457077026365, "lr": 6.045110504226643e-06, "epoch": 0.8660714285714286, "percentage": 43.3, "elapsed_time": "1 day, 0:34:13", "remaining_time": "1 day, 8:10:09", "throughput": 4659.92, "total_tokens": 412184528} {"current_steps": 6795, "total_steps": 15680, "loss": 0.32110598087310793, "lr": 6.0402117061476574e-06, "epoch": 0.8667091836734694, "percentage": 43.34, "elapsed_time": "1 day, 0:35:17", "remaining_time": "1 day, 8:09:03", "throughput": 4659.96, "total_tokens": 412488296} {"current_steps": 6800, "total_steps": 15680, "loss": 0.3190933704376221, "lr": 6.035311864143576e-06, "epoch": 0.8673469387755102, "percentage": 43.37, "elapsed_time": "1 day, 0:36:24", "remaining_time": "1 day, 8:08:00", "throughput": 4659.88, "total_tokens": 412792448} {"current_steps": 6805, "total_steps": 15680, "loss": 0.3117242336273193, "lr": 6.030410983131733e-06, "epoch": 0.8679846938775511, "percentage": 43.4, "elapsed_time": "1 day, 0:37:28", "remaining_time": "1 day, 8:06:54", "throughput": 4659.86, "total_tokens": 413089200} {"current_steps": 6810, "total_steps": 15680, "loss": 0.3140235424041748, "lr": 6.025509068030504e-06, "epoch": 0.8686224489795918, "percentage": 43.43, "elapsed_time": "1 day, 0:38:35", "remaining_time": "1 day, 8:05:51", "throughput": 4659.74, "total_tokens": 413392544} {"current_steps": 6815, "total_steps": 15680, "loss": 0.33549013137817385, "lr": 6.020606123759305e-06, "epoch": 0.8692602040816326, "percentage": 43.46, "elapsed_time": "1 day, 0:39:38", "remaining_time": "1 day, 8:04:44", "throughput": 4659.99, "total_tokens": 413708784} {"current_steps": 6820, "total_steps": 15680, "loss": 0.32853450775146487, "lr": 6.0157021552385805e-06, "epoch": 0.8698979591836735, "percentage": 43.49, "elapsed_time": "1 day, 0:40:48", "remaining_time": "1 day, 8:03:45", "throughput": 4659.71, "total_tokens": 414010272} {"current_steps": 6825, "total_steps": 15680, "loss": 0.34289889335632323, "lr": 6.010797167389808e-06, "epoch": 0.8705357142857143, "percentage": 43.53, "elapsed_time": "1 day, 0:41:40", "remaining_time": "1 day, 8:02:22", "throughput": 4660.46, "total_tokens": 414315712} {"current_steps": 6830, "total_steps": 15680, "loss": 0.324583101272583, "lr": 6.005891165135484e-06, "epoch": 0.8711734693877551, "percentage": 43.56, "elapsed_time": "1 day, 0:42:54", "remaining_time": "1 day, 8:01:28", "throughput": 4659.99, "total_tokens": 414619040} {"current_steps": 6835, "total_steps": 15680, "loss": 0.3294857978820801, "lr": 6.000984153399123e-06, "epoch": 0.8718112244897959, "percentage": 43.59, "elapsed_time": "1 day, 0:44:03", "remaining_time": "1 day, 8:00:29", "throughput": 4659.75, "total_tokens": 414921552} {"current_steps": 6840, "total_steps": 15680, "loss": 0.31545100212097166, "lr": 5.996076137105258e-06, "epoch": 0.8724489795918368, "percentage": 43.62, "elapsed_time": "1 day, 0:45:06", "remaining_time": "1 day, 7:59:21", "throughput": 4659.84, "total_tokens": 415222344} {"current_steps": 6845, "total_steps": 15680, "loss": 0.3479300498962402, "lr": 5.991167121179422e-06, "epoch": 0.8730867346938775, "percentage": 43.65, "elapsed_time": "1 day, 0:46:19", "remaining_time": "1 day, 7:58:26", "throughput": 4659.48, "total_tokens": 415531568} {"current_steps": 6850, "total_steps": 15680, "loss": 0.3386786937713623, "lr": 5.986257110548157e-06, "epoch": 0.8737244897959183, "percentage": 43.69, "elapsed_time": "1 day, 0:47:27", "remaining_time": "1 day, 7:57:24", "throughput": 4659.24, "total_tokens": 415827216} {"current_steps": 6855, "total_steps": 15680, "loss": 0.35399162769317627, "lr": 5.981346110139001e-06, "epoch": 0.8743622448979592, "percentage": 43.72, "elapsed_time": "1 day, 0:48:44", "remaining_time": "1 day, 7:56:34", "throughput": 4658.8, "total_tokens": 416142632} {"current_steps": 6860, "total_steps": 15680, "loss": 0.3396456718444824, "lr": 5.976434124880487e-06, "epoch": 0.875, "percentage": 43.75, "elapsed_time": "1 day, 0:49:44", "remaining_time": "1 day, 7:55:22", "throughput": 4659.16, "total_tokens": 416454960} {"current_steps": 6865, "total_steps": 15680, "loss": 0.35317091941833495, "lr": 5.971521159702136e-06, "epoch": 0.8756377551020408, "percentage": 43.78, "elapsed_time": "1 day, 0:50:45", "remaining_time": "1 day, 7:54:12", "throughput": 4659.4, "total_tokens": 416763704} {"current_steps": 6870, "total_steps": 15680, "loss": 0.3282179355621338, "lr": 5.966607219534448e-06, "epoch": 0.8762755102040817, "percentage": 43.81, "elapsed_time": "1 day, 0:51:56", "remaining_time": "1 day, 7:53:14", "throughput": 4659.19, "total_tokens": 417073280} {"current_steps": 6875, "total_steps": 15680, "loss": 0.3264785289764404, "lr": 5.9616923093089095e-06, "epoch": 0.8769132653061225, "percentage": 43.85, "elapsed_time": "1 day, 0:52:49", "remaining_time": "1 day, 7:51:53", "throughput": 4659.86, "total_tokens": 417380120} {"current_steps": 6880, "total_steps": 15680, "loss": 0.3343611240386963, "lr": 5.956776433957974e-06, "epoch": 0.8775510204081632, "percentage": 43.88, "elapsed_time": "1 day, 0:53:55", "remaining_time": "1 day, 7:50:50", "throughput": 4659.84, "total_tokens": 417687864} {"current_steps": 6885, "total_steps": 15680, "loss": 0.33244986534118653, "lr": 5.951859598415063e-06, "epoch": 0.8781887755102041, "percentage": 43.91, "elapsed_time": "1 day, 0:54:58", "remaining_time": "1 day, 7:49:41", "throughput": 4659.87, "total_tokens": 417982568} {"current_steps": 6890, "total_steps": 15680, "loss": 0.34135990142822265, "lr": 5.94694180761457e-06, "epoch": 0.8788265306122449, "percentage": 43.94, "elapsed_time": "1 day, 0:56:13", "remaining_time": "1 day, 7:48:49", "throughput": 4659.4, "total_tokens": 418288616} {"current_steps": 6895, "total_steps": 15680, "loss": 0.32839064598083495, "lr": 5.942023066491839e-06, "epoch": 0.8794642857142857, "percentage": 43.97, "elapsed_time": "1 day, 0:57:15", "remaining_time": "1 day, 7:47:40", "throughput": 4659.69, "total_tokens": 418606240} {"current_steps": 6900, "total_steps": 15680, "loss": 0.32634963989257815, "lr": 5.937103379983169e-06, "epoch": 0.8801020408163265, "percentage": 44.01, "elapsed_time": "1 day, 0:58:29", "remaining_time": "1 day, 7:46:47", "throughput": 4659.22, "total_tokens": 418910840} {"current_steps": 6905, "total_steps": 15680, "loss": 0.3340644836425781, "lr": 5.93218275302581e-06, "epoch": 0.8807397959183674, "percentage": 44.04, "elapsed_time": "1 day, 0:59:29", "remaining_time": "1 day, 7:45:35", "throughput": 4659.56, "total_tokens": 419219648} {"current_steps": 6910, "total_steps": 15680, "loss": 0.31465539932250974, "lr": 5.927261190557955e-06, "epoch": 0.8813775510204082, "percentage": 44.07, "elapsed_time": "1 day, 1:00:40", "remaining_time": "1 day, 7:44:36", "throughput": 4659.28, "total_tokens": 419522896} {"current_steps": 6915, "total_steps": 15680, "loss": 0.31777148246765136, "lr": 5.922338697518736e-06, "epoch": 0.8820153061224489, "percentage": 44.1, "elapsed_time": "1 day, 1:01:48", "remaining_time": "1 day, 7:43:34", "throughput": 4659.23, "total_tokens": 419833632} {"current_steps": 6920, "total_steps": 15680, "loss": 0.34000697135925295, "lr": 5.917415278848217e-06, "epoch": 0.8826530612244898, "percentage": 44.13, "elapsed_time": "1 day, 1:03:05", "remaining_time": "1 day, 7:42:45", "throughput": 4658.7, "total_tokens": 420149256} {"current_steps": 6925, "total_steps": 15680, "loss": 0.3393259048461914, "lr": 5.9124909394873955e-06, "epoch": 0.8832908163265306, "percentage": 44.16, "elapsed_time": "1 day, 1:04:03", "remaining_time": "1 day, 7:41:31", "throughput": 4659.09, "total_tokens": 420454576} {"current_steps": 6930, "total_steps": 15680, "loss": 0.3432659387588501, "lr": 5.907565684378187e-06, "epoch": 0.8839285714285714, "percentage": 44.2, "elapsed_time": "1 day, 1:05:17", "remaining_time": "1 day, 7:40:37", "throughput": 4658.53, "total_tokens": 420748952} {"current_steps": 6935, "total_steps": 15680, "loss": 0.3281343698501587, "lr": 5.902639518463429e-06, "epoch": 0.8845663265306123, "percentage": 44.23, "elapsed_time": "1 day, 1:06:18", "remaining_time": "1 day, 7:39:26", "throughput": 4658.88, "total_tokens": 421061672} {"current_steps": 6940, "total_steps": 15680, "loss": 0.3060306072235107, "lr": 5.897712446686875e-06, "epoch": 0.8852040816326531, "percentage": 44.26, "elapsed_time": "1 day, 1:07:23", "remaining_time": "1 day, 7:38:21", "throughput": 4658.76, "total_tokens": 421354016} {"current_steps": 6945, "total_steps": 15680, "loss": 0.32022268772125245, "lr": 5.892784473993184e-06, "epoch": 0.8858418367346939, "percentage": 44.29, "elapsed_time": "1 day, 1:08:25", "remaining_time": "1 day, 7:37:12", "throughput": 4658.97, "total_tokens": 421664096} {"current_steps": 6950, "total_steps": 15680, "loss": 0.3388242721557617, "lr": 5.887855605327921e-06, "epoch": 0.8864795918367347, "percentage": 44.32, "elapsed_time": "1 day, 1:09:24", "remaining_time": "1 day, 7:35:59", "throughput": 4659.42, "total_tokens": 421977680} {"current_steps": 6955, "total_steps": 15680, "loss": 0.3288001298904419, "lr": 5.882925845637551e-06, "epoch": 0.8871173469387755, "percentage": 44.36, "elapsed_time": "1 day, 1:10:35", "remaining_time": "1 day, 7:35:01", "throughput": 4659.1, "total_tokens": 422278024} {"current_steps": 6960, "total_steps": 15680, "loss": 0.3016238212585449, "lr": 5.877995199869433e-06, "epoch": 0.8877551020408163, "percentage": 44.39, "elapsed_time": "1 day, 1:11:49", "remaining_time": "1 day, 7:34:07", "throughput": 4658.61, "total_tokens": 422579688} {"current_steps": 6965, "total_steps": 15680, "loss": 0.3010798454284668, "lr": 5.87306367297181e-06, "epoch": 0.8883928571428571, "percentage": 44.42, "elapsed_time": "1 day, 1:12:46", "remaining_time": "1 day, 7:32:52", "throughput": 4658.99, "total_tokens": 422882808} {"current_steps": 6970, "total_steps": 15680, "loss": 0.3299619197845459, "lr": 5.868131269893818e-06, "epoch": 0.889030612244898, "percentage": 44.45, "elapsed_time": "1 day, 1:13:49", "remaining_time": "1 day, 7:31:43", "throughput": 4659.16, "total_tokens": 423187696} {"current_steps": 6975, "total_steps": 15680, "loss": 0.3324789047241211, "lr": 5.863197995585468e-06, "epoch": 0.8896683673469388, "percentage": 44.48, "elapsed_time": "1 day, 1:15:04", "remaining_time": "1 day, 7:30:51", "throughput": 4658.6, "total_tokens": 423489032} {"current_steps": 6980, "total_steps": 15680, "loss": 0.3130115270614624, "lr": 5.858263854997642e-06, "epoch": 0.8903061224489796, "percentage": 44.52, "elapsed_time": "1 day, 1:16:20", "remaining_time": "1 day, 7:29:59", "throughput": 4658.07, "total_tokens": 423791448} {"current_steps": 6985, "total_steps": 15680, "loss": 0.33639523983001707, "lr": 5.853328853082098e-06, "epoch": 0.8909438775510204, "percentage": 44.55, "elapsed_time": "1 day, 1:17:33", "remaining_time": "1 day, 7:29:04", "throughput": 4657.67, "total_tokens": 424099240} {"current_steps": 6990, "total_steps": 15680, "loss": 0.31321704387664795, "lr": 5.848392994791452e-06, "epoch": 0.8915816326530612, "percentage": 44.58, "elapsed_time": "1 day, 1:18:43", "remaining_time": "1 day, 7:28:05", "throughput": 4657.39, "total_tokens": 424398816} {"current_steps": 6995, "total_steps": 15680, "loss": 0.32476589679718015, "lr": 5.843456285079185e-06, "epoch": 0.892219387755102, "percentage": 44.61, "elapsed_time": "1 day, 1:19:46", "remaining_time": "1 day, 7:26:57", "throughput": 4657.39, "total_tokens": 424692664} {"current_steps": 7000, "total_steps": 15680, "loss": 0.3245981216430664, "lr": 5.838518728899627e-06, "epoch": 0.8928571428571429, "percentage": 44.64, "elapsed_time": "1 day, 1:20:46", "remaining_time": "1 day, 7:25:45", "throughput": 4657.64, "total_tokens": 424992552} {"current_steps": 7005, "total_steps": 15680, "loss": 0.3225821256637573, "lr": 5.833580331207964e-06, "epoch": 0.8934948979591837, "percentage": 44.67, "elapsed_time": "1 day, 1:21:56", "remaining_time": "1 day, 7:24:46", "throughput": 4657.31, "total_tokens": 425287872} {"current_steps": 7010, "total_steps": 15680, "loss": 0.34339883327484133, "lr": 5.828641096960223e-06, "epoch": 0.8941326530612245, "percentage": 44.71, "elapsed_time": "1 day, 1:23:07", "remaining_time": "1 day, 7:23:47", "throughput": 4657.03, "total_tokens": 425592264} {"current_steps": 7015, "total_steps": 15680, "loss": 0.32695627212524414, "lr": 5.823701031113267e-06, "epoch": 0.8947704081632653, "percentage": 44.74, "elapsed_time": "1 day, 1:24:06", "remaining_time": "1 day, 7:22:35", "throughput": 4657.46, "total_tokens": 425906136} {"current_steps": 7020, "total_steps": 15680, "loss": 0.32545430660247804, "lr": 5.8187601386248004e-06, "epoch": 0.8954081632653061, "percentage": 44.77, "elapsed_time": "1 day, 1:25:07", "remaining_time": "1 day, 7:21:25", "throughput": 4657.54, "total_tokens": 426201056} {"current_steps": 7025, "total_steps": 15680, "loss": 0.3182164430618286, "lr": 5.8138184244533516e-06, "epoch": 0.8960459183673469, "percentage": 44.8, "elapsed_time": "1 day, 1:26:19", "remaining_time": "1 day, 7:20:27", "throughput": 4657.15, "total_tokens": 426497408} {"current_steps": 7030, "total_steps": 15680, "loss": 0.31878080368041994, "lr": 5.808875893558277e-06, "epoch": 0.8966836734693877, "percentage": 44.83, "elapsed_time": "1 day, 1:27:25", "remaining_time": "1 day, 7:19:24", "throughput": 4657.02, "total_tokens": 426794296} {"current_steps": 7035, "total_steps": 15680, "loss": 0.31372628211975095, "lr": 5.8039325508997524e-06, "epoch": 0.8973214285714286, "percentage": 44.87, "elapsed_time": "1 day, 1:28:30", "remaining_time": "1 day, 7:18:18", "throughput": 4657.03, "total_tokens": 427098144} {"current_steps": 7040, "total_steps": 15680, "loss": 0.3209484577178955, "lr": 5.798988401438765e-06, "epoch": 0.8979591836734694, "percentage": 44.9, "elapsed_time": "1 day, 1:29:29", "remaining_time": "1 day, 7:17:05", "throughput": 4657.44, "total_tokens": 427409712} {"current_steps": 7045, "total_steps": 15680, "loss": 0.2963754177093506, "lr": 5.7940434501371175e-06, "epoch": 0.8985969387755102, "percentage": 44.93, "elapsed_time": "1 day, 1:30:32", "remaining_time": "1 day, 7:15:58", "throughput": 4657.64, "total_tokens": 427722720} {"current_steps": 7050, "total_steps": 15680, "loss": 0.336498761177063, "lr": 5.78909770195741e-06, "epoch": 0.8992346938775511, "percentage": 44.96, "elapsed_time": "1 day, 1:31:36", "remaining_time": "1 day, 7:14:51", "throughput": 4657.82, "total_tokens": 428037344} {"current_steps": 7055, "total_steps": 15680, "loss": 0.3361975193023682, "lr": 5.7841511618630484e-06, "epoch": 0.8998724489795918, "percentage": 44.99, "elapsed_time": "1 day, 1:32:35", "remaining_time": "1 day, 7:13:38", "throughput": 4658.13, "total_tokens": 428338744} {"current_steps": 7060, "total_steps": 15680, "loss": 0.3048173189163208, "lr": 5.779203834818232e-06, "epoch": 0.9005102040816326, "percentage": 45.03, "elapsed_time": "1 day, 1:33:45", "remaining_time": "1 day, 7:12:39", "throughput": 4657.8, "total_tokens": 428636752} {"current_steps": 7065, "total_steps": 15680, "loss": 0.3191343069076538, "lr": 5.774255725787946e-06, "epoch": 0.9011479591836735, "percentage": 45.06, "elapsed_time": "1 day, 1:34:54", "remaining_time": "1 day, 7:11:38", "throughput": 4657.68, "total_tokens": 428944496} {"current_steps": 7070, "total_steps": 15680, "loss": 0.3296975135803223, "lr": 5.769306839737968e-06, "epoch": 0.9017857142857143, "percentage": 45.09, "elapsed_time": "1 day, 1:35:55", "remaining_time": "1 day, 7:10:28", "throughput": 4657.92, "total_tokens": 429250792} {"current_steps": 7075, "total_steps": 15680, "loss": 0.3285045623779297, "lr": 5.764357181634847e-06, "epoch": 0.9024234693877551, "percentage": 45.12, "elapsed_time": "1 day, 1:36:58", "remaining_time": "1 day, 7:09:20", "throughput": 4658.12, "total_tokens": 429563984} {"current_steps": 7080, "total_steps": 15680, "loss": 0.34009225368499757, "lr": 5.759406756445911e-06, "epoch": 0.9030612244897959, "percentage": 45.15, "elapsed_time": "1 day, 1:38:09", "remaining_time": "1 day, 7:08:22", "throughput": 4657.81, "total_tokens": 429866120} {"current_steps": 7085, "total_steps": 15680, "loss": 0.3277864456176758, "lr": 5.754455569139258e-06, "epoch": 0.9036989795918368, "percentage": 45.18, "elapsed_time": "1 day, 1:39:09", "remaining_time": "1 day, 7:07:11", "throughput": 4658.1, "total_tokens": 430171480} {"current_steps": 7090, "total_steps": 15680, "loss": 0.33977360725402833, "lr": 5.74950362468375e-06, "epoch": 0.9043367346938775, "percentage": 45.22, "elapsed_time": "1 day, 1:40:23", "remaining_time": "1 day, 7:06:17", "throughput": 4657.6, "total_tokens": 430471856} {"current_steps": 7095, "total_steps": 15680, "loss": 0.3126554250717163, "lr": 5.74455092804901e-06, "epoch": 0.9049744897959183, "percentage": 45.25, "elapsed_time": "1 day, 1:41:24", "remaining_time": "1 day, 7:05:07", "throughput": 4657.69, "total_tokens": 430765624} {"current_steps": 7100, "total_steps": 15680, "loss": 0.3299864768981934, "lr": 5.739597484205415e-06, "epoch": 0.9056122448979592, "percentage": 45.28, "elapsed_time": "1 day, 1:42:33", "remaining_time": "1 day, 7:04:06", "throughput": 4657.6, "total_tokens": 431077520} {"current_steps": 7105, "total_steps": 15680, "loss": 0.3100090980529785, "lr": 5.734643298124091e-06, "epoch": 0.90625, "percentage": 45.31, "elapsed_time": "1 day, 1:43:30", "remaining_time": "1 day, 7:02:51", "throughput": 4658.12, "total_tokens": 431392784} {"current_steps": 7110, "total_steps": 15680, "loss": 0.34330143928527834, "lr": 5.7296883747769096e-06, "epoch": 0.9068877551020408, "percentage": 45.34, "elapsed_time": "1 day, 1:44:36", "remaining_time": "1 day, 7:01:47", "throughput": 4658.12, "total_tokens": 431698568} {"current_steps": 7115, "total_steps": 15680, "loss": 0.33743948936462403, "lr": 5.724732719136481e-06, "epoch": 0.9075255102040817, "percentage": 45.38, "elapsed_time": "1 day, 1:45:42", "remaining_time": "1 day, 7:00:42", "throughput": 4658.1, "total_tokens": 432004008} {"current_steps": 7120, "total_steps": 15680, "loss": 0.3645359516143799, "lr": 5.719776336176156e-06, "epoch": 0.9081632653061225, "percentage": 45.41, "elapsed_time": "1 day, 1:46:44", "remaining_time": "1 day, 6:59:34", "throughput": 4658.33, "total_tokens": 432315232} {"current_steps": 7125, "total_steps": 15680, "loss": 0.3343202114105225, "lr": 5.714819230870008e-06, "epoch": 0.9088010204081632, "percentage": 45.44, "elapsed_time": "1 day, 1:47:59", "remaining_time": "1 day, 6:58:40", "throughput": 4657.91, "total_tokens": 432623952} {"current_steps": 7130, "total_steps": 15680, "loss": 0.3022934436798096, "lr": 5.709861408192838e-06, "epoch": 0.9094387755102041, "percentage": 45.47, "elapsed_time": "1 day, 1:49:13", "remaining_time": "1 day, 6:57:46", "throughput": 4657.4, "total_tokens": 432923000} {"current_steps": 7135, "total_steps": 15680, "loss": 0.3636758327484131, "lr": 5.704902873120169e-06, "epoch": 0.9100765306122449, "percentage": 45.5, "elapsed_time": "1 day, 1:50:23", "remaining_time": "1 day, 6:56:46", "throughput": 4657.15, "total_tokens": 433223992} {"current_steps": 7140, "total_steps": 15680, "loss": 0.3100710391998291, "lr": 5.699943630628237e-06, "epoch": 0.9107142857142857, "percentage": 45.54, "elapsed_time": "1 day, 1:51:21", "remaining_time": "1 day, 6:55:33", "throughput": 4657.49, "total_tokens": 433527848} {"current_steps": 7145, "total_steps": 15680, "loss": 0.33217525482177734, "lr": 5.694983685693987e-06, "epoch": 0.9113520408163265, "percentage": 45.57, "elapsed_time": "1 day, 1:52:22", "remaining_time": "1 day, 6:54:22", "throughput": 4657.7, "total_tokens": 433827296} {"current_steps": 7150, "total_steps": 15680, "loss": 0.3236429452896118, "lr": 5.690023043295071e-06, "epoch": 0.9119897959183674, "percentage": 45.6, "elapsed_time": "1 day, 1:53:36", "remaining_time": "1 day, 6:53:28", "throughput": 4657.18, "total_tokens": 434126264} {"current_steps": 7155, "total_steps": 15680, "loss": 0.34194958209991455, "lr": 5.6850617084098416e-06, "epoch": 0.9126275510204082, "percentage": 45.63, "elapsed_time": "1 day, 1:54:45", "remaining_time": "1 day, 6:52:27", "throughput": 4656.97, "total_tokens": 434426760} {"current_steps": 7160, "total_steps": 15680, "loss": 0.3341176509857178, "lr": 5.6800996860173404e-06, "epoch": 0.9132653061224489, "percentage": 45.66, "elapsed_time": "1 day, 1:55:37", "remaining_time": "1 day, 6:51:05", "throughput": 4657.65, "total_tokens": 434731896} {"current_steps": 7165, "total_steps": 15680, "loss": 0.316843056678772, "lr": 5.675136981097309e-06, "epoch": 0.9139030612244898, "percentage": 45.7, "elapsed_time": "1 day, 1:56:35", "remaining_time": "1 day, 6:49:53", "throughput": 4657.92, "total_tokens": 435030744} {"current_steps": 7170, "total_steps": 15680, "loss": 0.31385073661804197, "lr": 5.670173598630163e-06, "epoch": 0.9145408163265306, "percentage": 45.73, "elapsed_time": "1 day, 1:57:39", "remaining_time": "1 day, 6:48:46", "throughput": 4657.94, "total_tokens": 435328592} {"current_steps": 7175, "total_steps": 15680, "loss": 0.331546688079834, "lr": 5.6652095435970074e-06, "epoch": 0.9151785714285714, "percentage": 45.76, "elapsed_time": "1 day, 1:58:40", "remaining_time": "1 day, 6:47:36", "throughput": 4658.27, "total_tokens": 435645672} {"current_steps": 7180, "total_steps": 15680, "loss": 0.30263442993164064, "lr": 5.6602448209796165e-06, "epoch": 0.9158163265306123, "percentage": 45.79, "elapsed_time": "1 day, 1:59:49", "remaining_time": "1 day, 6:46:34", "throughput": 4657.95, "total_tokens": 435933128} {"current_steps": 7185, "total_steps": 15680, "loss": 0.33107576370239256, "lr": 5.655279435760436e-06, "epoch": 0.9164540816326531, "percentage": 45.82, "elapsed_time": "1 day, 2:01:02", "remaining_time": "1 day, 6:45:39", "throughput": 4657.6, "total_tokens": 436241608} {"current_steps": 7190, "total_steps": 15680, "loss": 0.350404691696167, "lr": 5.650313392922578e-06, "epoch": 0.9170918367346939, "percentage": 45.85, "elapsed_time": "1 day, 2:02:05", "remaining_time": "1 day, 6:44:31", "throughput": 4657.72, "total_tokens": 436545304} {"current_steps": 7195, "total_steps": 15680, "loss": 0.30472793579101565, "lr": 5.64534669744981e-06, "epoch": 0.9177295918367347, "percentage": 45.89, "elapsed_time": "1 day, 2:03:12", "remaining_time": "1 day, 6:43:28", "throughput": 4657.59, "total_tokens": 436846352} {"current_steps": 7200, "total_steps": 15680, "loss": 0.3401020050048828, "lr": 5.640379354326563e-06, "epoch": 0.9183673469387755, "percentage": 45.92, "elapsed_time": "1 day, 2:04:12", "remaining_time": "1 day, 6:42:16", "throughput": 4657.87, "total_tokens": 437151096} {"current_steps": 7205, "total_steps": 15680, "loss": 0.3340470314025879, "lr": 5.63541136853791e-06, "epoch": 0.9190051020408163, "percentage": 45.95, "elapsed_time": "1 day, 2:05:20", "remaining_time": "1 day, 6:41:15", "throughput": 4657.74, "total_tokens": 437457208} {"current_steps": 7210, "total_steps": 15680, "loss": 0.3098969221115112, "lr": 5.630442745069568e-06, "epoch": 0.9196428571428571, "percentage": 45.98, "elapsed_time": "1 day, 2:06:29", "remaining_time": "1 day, 6:40:15", "throughput": 4657.5, "total_tokens": 437757936} {"current_steps": 7215, "total_steps": 15680, "loss": 0.3573422908782959, "lr": 5.625473488907905e-06, "epoch": 0.920280612244898, "percentage": 46.01, "elapsed_time": "1 day, 2:07:25", "remaining_time": "1 day, 6:38:58", "throughput": 4657.93, "total_tokens": 438057032} {"current_steps": 7220, "total_steps": 15680, "loss": 0.33810203075408934, "lr": 5.620503605039912e-06, "epoch": 0.9209183673469388, "percentage": 46.05, "elapsed_time": "1 day, 2:08:37", "remaining_time": "1 day, 6:38:01", "throughput": 4657.54, "total_tokens": 438355976} {"current_steps": 7225, "total_steps": 15680, "loss": 0.3303686141967773, "lr": 5.615533098453215e-06, "epoch": 0.9215561224489796, "percentage": 46.08, "elapsed_time": "1 day, 2:09:53", "remaining_time": "1 day, 6:37:08", "throughput": 4656.98, "total_tokens": 438655912} {"current_steps": 7230, "total_steps": 15680, "loss": 0.30500807762146, "lr": 5.610561974136065e-06, "epoch": 0.9221938775510204, "percentage": 46.11, "elapsed_time": "1 day, 2:10:50", "remaining_time": "1 day, 6:35:54", "throughput": 4657.4, "total_tokens": 438963328} {"current_steps": 7235, "total_steps": 15680, "loss": 0.30874583721160886, "lr": 5.605590237077332e-06, "epoch": 0.9228316326530612, "percentage": 46.14, "elapsed_time": "1 day, 2:12:06", "remaining_time": "1 day, 6:35:01", "throughput": 4656.81, "total_tokens": 439259696} {"current_steps": 7240, "total_steps": 15680, "loss": 0.33132448196411135, "lr": 5.600617892266503e-06, "epoch": 0.923469387755102, "percentage": 46.17, "elapsed_time": "1 day, 2:13:15", "remaining_time": "1 day, 6:34:01", "throughput": 4656.62, "total_tokens": 439564888} {"current_steps": 7245, "total_steps": 15680, "loss": 0.33731722831726074, "lr": 5.5956449446936715e-06, "epoch": 0.9241071428571429, "percentage": 46.21, "elapsed_time": "1 day, 2:14:23", "remaining_time": "1 day, 6:32:59", "throughput": 4656.51, "total_tokens": 439871352} {"current_steps": 7250, "total_steps": 15680, "loss": 0.30220632553100585, "lr": 5.590671399349539e-06, "epoch": 0.9247448979591837, "percentage": 46.24, "elapsed_time": "1 day, 2:15:29", "remaining_time": "1 day, 6:31:54", "throughput": 4656.51, "total_tokens": 440175224} {"current_steps": 7255, "total_steps": 15680, "loss": 0.33912243843078616, "lr": 5.585697261225404e-06, "epoch": 0.9253826530612245, "percentage": 46.27, "elapsed_time": "1 day, 2:16:42", "remaining_time": "1 day, 6:30:59", "throughput": 4656.13, "total_tokens": 440483888} {"current_steps": 7260, "total_steps": 15680, "loss": 0.3079514980316162, "lr": 5.58072253531316e-06, "epoch": 0.9260204081632653, "percentage": 46.3, "elapsed_time": "1 day, 2:17:46", "remaining_time": "1 day, 6:29:52", "throughput": 4656.27, "total_tokens": 440792440} {"current_steps": 7265, "total_steps": 15680, "loss": 0.3464851140975952, "lr": 5.575747226605298e-06, "epoch": 0.9266581632653061, "percentage": 46.33, "elapsed_time": "1 day, 2:18:52", "remaining_time": "1 day, 6:28:47", "throughput": 4656.26, "total_tokens": 441096904} {"current_steps": 7270, "total_steps": 15680, "loss": 0.3171382427215576, "lr": 5.570771340094883e-06, "epoch": 0.9272959183673469, "percentage": 46.36, "elapsed_time": "1 day, 2:19:55", "remaining_time": "1 day, 6:27:39", "throughput": 4656.26, "total_tokens": 441390952} {"current_steps": 7275, "total_steps": 15680, "loss": 0.3248934268951416, "lr": 5.565794880775565e-06, "epoch": 0.9279336734693877, "percentage": 46.4, "elapsed_time": "1 day, 2:20:58", "remaining_time": "1 day, 6:26:32", "throughput": 4656.45, "total_tokens": 441705680} {"current_steps": 7280, "total_steps": 15680, "loss": 0.34633026123046873, "lr": 5.560817853641568e-06, "epoch": 0.9285714285714286, "percentage": 46.43, "elapsed_time": "1 day, 2:22:09", "remaining_time": "1 day, 6:25:33", "throughput": 4656.22, "total_tokens": 442011840} {"current_steps": 7285, "total_steps": 15680, "loss": 0.3423534154891968, "lr": 5.5558402636876885e-06, "epoch": 0.9292091836734694, "percentage": 46.46, "elapsed_time": "1 day, 2:23:17", "remaining_time": "1 day, 6:24:32", "throughput": 4656.05, "total_tokens": 442315264} {"current_steps": 7290, "total_steps": 15680, "loss": 0.3233125925064087, "lr": 5.550862115909287e-06, "epoch": 0.9298469387755102, "percentage": 46.49, "elapsed_time": "1 day, 2:24:18", "remaining_time": "1 day, 6:23:22", "throughput": 4656.1, "total_tokens": 442602968} {"current_steps": 7295, "total_steps": 15680, "loss": 0.3399376630783081, "lr": 5.545883415302276e-06, "epoch": 0.9304846938775511, "percentage": 46.52, "elapsed_time": "1 day, 2:25:31", "remaining_time": "1 day, 6:22:26", "throughput": 4655.78, "total_tokens": 442912720} {"current_steps": 7300, "total_steps": 15680, "loss": 0.3292389869689941, "lr": 5.540904166863136e-06, "epoch": 0.9311224489795918, "percentage": 46.56, "elapsed_time": "1 day, 2:26:40", "remaining_time": "1 day, 6:21:25", "throughput": 4655.57, "total_tokens": 443214392} {"current_steps": 7305, "total_steps": 15680, "loss": 0.32429957389831543, "lr": 5.535924375588887e-06, "epoch": 0.9317602040816326, "percentage": 46.59, "elapsed_time": "1 day, 2:27:46", "remaining_time": "1 day, 6:20:20", "throughput": 4655.56, "total_tokens": 443518360} {"current_steps": 7310, "total_steps": 15680, "loss": 0.34727861881256106, "lr": 5.530944046477098e-06, "epoch": 0.9323979591836735, "percentage": 46.62, "elapsed_time": "1 day, 2:28:54", "remaining_time": "1 day, 6:19:19", "throughput": 4655.43, "total_tokens": 443824776} {"current_steps": 7315, "total_steps": 15680, "loss": 0.31817402839660647, "lr": 5.525963184525877e-06, "epoch": 0.9330357142857143, "percentage": 46.65, "elapsed_time": "1 day, 2:29:54", "remaining_time": "1 day, 6:18:07", "throughput": 4655.72, "total_tokens": 444132048} {"current_steps": 7320, "total_steps": 15680, "loss": 0.33860623836517334, "lr": 5.5209817947338685e-06, "epoch": 0.9336734693877551, "percentage": 46.68, "elapsed_time": "1 day, 2:31:12", "remaining_time": "1 day, 6:17:16", "throughput": 4655.18, "total_tokens": 444440104} {"current_steps": 7325, "total_steps": 15680, "loss": 0.3216454029083252, "lr": 5.5159998821002425e-06, "epoch": 0.9343112244897959, "percentage": 46.72, "elapsed_time": "1 day, 2:32:24", "remaining_time": "1 day, 6:16:19", "throughput": 4654.7, "total_tokens": 444730064} {"current_steps": 7330, "total_steps": 15680, "loss": 0.3319781064987183, "lr": 5.511017451624698e-06, "epoch": 0.9349489795918368, "percentage": 46.75, "elapsed_time": "1 day, 2:33:25", "remaining_time": "1 day, 6:15:09", "throughput": 4654.78, "total_tokens": 445022400} {"current_steps": 7335, "total_steps": 15680, "loss": 0.32101285457611084, "lr": 5.506034508307453e-06, "epoch": 0.9355867346938775, "percentage": 46.78, "elapsed_time": "1 day, 2:34:26", "remaining_time": "1 day, 6:13:59", "throughput": 4654.84, "total_tokens": 445313984} {"current_steps": 7340, "total_steps": 15680, "loss": 0.34318544864654543, "lr": 5.501051057149234e-06, "epoch": 0.9362244897959183, "percentage": 46.81, "elapsed_time": "1 day, 2:35:39", "remaining_time": "1 day, 6:13:02", "throughput": 4654.43, "total_tokens": 445611808} {"current_steps": 7345, "total_steps": 15680, "loss": 0.31019752025604247, "lr": 5.496067103151288e-06, "epoch": 0.9368622448979592, "percentage": 46.84, "elapsed_time": "1 day, 2:36:39", "remaining_time": "1 day, 6:11:52", "throughput": 4654.55, "total_tokens": 445903928} {"current_steps": 7350, "total_steps": 15680, "loss": 0.32934820652008057, "lr": 5.491082651315359e-06, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "1 day, 2:37:52", "remaining_time": "1 day, 6:10:55", "throughput": 4654.29, "total_tokens": 446217904} {"current_steps": 7355, "total_steps": 15680, "loss": 0.33247902393341067, "lr": 5.4860977066436915e-06, "epoch": 0.9381377551020408, "percentage": 46.91, "elapsed_time": "1 day, 2:38:54", "remaining_time": "1 day, 6:09:47", "throughput": 4654.61, "total_tokens": 446539136} {"current_steps": 7360, "total_steps": 15680, "loss": 0.3279747247695923, "lr": 5.481112274139026e-06, "epoch": 0.9387755102040817, "percentage": 46.94, "elapsed_time": "1 day, 2:40:04", "remaining_time": "1 day, 6:08:46", "throughput": 4654.24, "total_tokens": 446828760} {"current_steps": 7365, "total_steps": 15680, "loss": 0.3111677885055542, "lr": 5.476126358804594e-06, "epoch": 0.9394132653061225, "percentage": 46.97, "elapsed_time": "1 day, 2:41:12", "remaining_time": "1 day, 6:07:45", "throughput": 4654.02, "total_tokens": 447125808} {"current_steps": 7370, "total_steps": 15680, "loss": 0.3141068458557129, "lr": 5.471139965644108e-06, "epoch": 0.9400510204081632, "percentage": 47.0, "elapsed_time": "1 day, 2:42:19", "remaining_time": "1 day, 6:06:42", "throughput": 4653.86, "total_tokens": 447421784} {"current_steps": 7375, "total_steps": 15680, "loss": 0.32782411575317383, "lr": 5.46615309966176e-06, "epoch": 0.9406887755102041, "percentage": 47.03, "elapsed_time": "1 day, 2:43:14", "remaining_time": "1 day, 6:05:24", "throughput": 4654.49, "total_tokens": 447734880} {"current_steps": 7380, "total_steps": 15680, "loss": 0.36186442375183103, "lr": 5.461165765862223e-06, "epoch": 0.9413265306122449, "percentage": 47.07, "elapsed_time": "1 day, 2:44:24", "remaining_time": "1 day, 6:04:24", "throughput": 4654.22, "total_tokens": 448036040} {"current_steps": 7385, "total_steps": 15680, "loss": 0.3144784688949585, "lr": 5.456177969250632e-06, "epoch": 0.9419642857142857, "percentage": 47.1, "elapsed_time": "1 day, 2:45:30", "remaining_time": "1 day, 6:03:20", "throughput": 4654.18, "total_tokens": 448339064} {"current_steps": 7390, "total_steps": 15680, "loss": 0.33200769424438475, "lr": 5.451189714832588e-06, "epoch": 0.9426020408163265, "percentage": 47.13, "elapsed_time": "1 day, 2:46:37", "remaining_time": "1 day, 6:02:16", "throughput": 4654.03, "total_tokens": 448634848} {"current_steps": 7395, "total_steps": 15680, "loss": 0.352520227432251, "lr": 5.446201007614156e-06, "epoch": 0.9432397959183674, "percentage": 47.16, "elapsed_time": "1 day, 2:47:41", "remaining_time": "1 day, 6:01:10", "throughput": 4654.0, "total_tokens": 448932160} {"current_steps": 7400, "total_steps": 15680, "loss": 0.3336463928222656, "lr": 5.441211852601849e-06, "epoch": 0.9438775510204082, "percentage": 47.19, "elapsed_time": "1 day, 2:48:45", "remaining_time": "1 day, 6:00:04", "throughput": 4653.97, "total_tokens": 449228936} {"current_steps": 7405, "total_steps": 15680, "loss": 0.33085658550262453, "lr": 5.4362222548026325e-06, "epoch": 0.9445153061224489, "percentage": 47.23, "elapsed_time": "1 day, 2:49:51", "remaining_time": "1 day, 5:59:00", "throughput": 4654.07, "total_tokens": 449545320} {"current_steps": 7410, "total_steps": 15680, "loss": 0.3475645065307617, "lr": 5.43123221922392e-06, "epoch": 0.9451530612244898, "percentage": 47.26, "elapsed_time": "1 day, 2:50:53", "remaining_time": "1 day, 5:57:50", "throughput": 4654.44, "total_tokens": 449867272} {"current_steps": 7415, "total_steps": 15680, "loss": 0.33647613525390624, "lr": 5.426241750873557e-06, "epoch": 0.9457908163265306, "percentage": 47.29, "elapsed_time": "1 day, 2:52:09", "remaining_time": "1 day, 5:56:58", "throughput": 4653.92, "total_tokens": 450173248} {"current_steps": 7420, "total_steps": 15680, "loss": 0.30979266166687014, "lr": 5.42125085475983e-06, "epoch": 0.9464285714285714, "percentage": 47.32, "elapsed_time": "1 day, 2:53:15", "remaining_time": "1 day, 5:55:53", "throughput": 4653.89, "total_tokens": 450477304} {"current_steps": 7425, "total_steps": 15680, "loss": 0.31366941928863523, "lr": 5.4162595358914475e-06, "epoch": 0.9470663265306123, "percentage": 47.35, "elapsed_time": "1 day, 2:54:21", "remaining_time": "1 day, 5:54:48", "throughput": 4653.73, "total_tokens": 450766696} {"current_steps": 7430, "total_steps": 15680, "loss": 0.2894803524017334, "lr": 5.41126779927755e-06, "epoch": 0.9477040816326531, "percentage": 47.39, "elapsed_time": "1 day, 2:55:35", "remaining_time": "1 day, 5:53:54", "throughput": 4653.37, "total_tokens": 451078288} {"current_steps": 7435, "total_steps": 15680, "loss": 0.3030913591384888, "lr": 5.4062756499276945e-06, "epoch": 0.9483418367346939, "percentage": 47.42, "elapsed_time": "1 day, 2:56:40", "remaining_time": "1 day, 5:52:48", "throughput": 4653.33, "total_tokens": 451375832} {"current_steps": 7440, "total_steps": 15680, "loss": 0.32454471588134765, "lr": 5.401283092851848e-06, "epoch": 0.9489795918367347, "percentage": 47.45, "elapsed_time": "1 day, 2:57:46", "remaining_time": "1 day, 5:51:43", "throughput": 4653.37, "total_tokens": 451683696} {"current_steps": 7445, "total_steps": 15680, "loss": 0.33219094276428224, "lr": 5.396290133060394e-06, "epoch": 0.9496173469387755, "percentage": 47.48, "elapsed_time": "1 day, 2:58:44", "remaining_time": "1 day, 5:50:30", "throughput": 4653.7, "total_tokens": 451988336} {"current_steps": 7450, "total_steps": 15680, "loss": 0.3516712188720703, "lr": 5.391296775564114e-06, "epoch": 0.9502551020408163, "percentage": 47.51, "elapsed_time": "1 day, 2:59:53", "remaining_time": "1 day, 5:49:29", "throughput": 4653.38, "total_tokens": 452279800} {"current_steps": 7455, "total_steps": 15680, "loss": 0.3267823219299316, "lr": 5.386303025374192e-06, "epoch": 0.9508928571428571, "percentage": 47.54, "elapsed_time": "1 day, 3:00:49", "remaining_time": "1 day, 5:48:13", "throughput": 4653.71, "total_tokens": 452569432} {"current_steps": 7460, "total_steps": 15680, "loss": 0.32781100273132324, "lr": 5.381308887502204e-06, "epoch": 0.951530612244898, "percentage": 47.58, "elapsed_time": "1 day, 3:02:00", "remaining_time": "1 day, 5:47:15", "throughput": 4653.46, "total_tokens": 452875960} {"current_steps": 7465, "total_steps": 15680, "loss": 0.31268844604492185, "lr": 5.376314366960118e-06, "epoch": 0.9521683673469388, "percentage": 47.61, "elapsed_time": "1 day, 3:03:02", "remaining_time": "1 day, 5:46:06", "throughput": 4653.53, "total_tokens": 453174224} {"current_steps": 7470, "total_steps": 15680, "loss": 0.3634037017822266, "lr": 5.371319468760283e-06, "epoch": 0.9528061224489796, "percentage": 47.64, "elapsed_time": "1 day, 3:04:12", "remaining_time": "1 day, 5:45:06", "throughput": 4653.31, "total_tokens": 453475112} {"current_steps": 7475, "total_steps": 15680, "loss": 0.35582818984985354, "lr": 5.366324197915426e-06, "epoch": 0.9534438775510204, "percentage": 47.67, "elapsed_time": "1 day, 3:05:22", "remaining_time": "1 day, 5:44:06", "throughput": 4653.18, "total_tokens": 453791072} {"current_steps": 7480, "total_steps": 15680, "loss": 0.32398262023925783, "lr": 5.361328559438655e-06, "epoch": 0.9540816326530612, "percentage": 47.7, "elapsed_time": "1 day, 3:06:30", "remaining_time": "1 day, 5:43:04", "throughput": 4653.0, "total_tokens": 454089208} {"current_steps": 7485, "total_steps": 15680, "loss": 0.3262059688568115, "lr": 5.3563325583434376e-06, "epoch": 0.954719387755102, "percentage": 47.74, "elapsed_time": "1 day, 3:07:47", "remaining_time": "1 day, 5:42:11", "throughput": 4652.46, "total_tokens": 454392432} {"current_steps": 7490, "total_steps": 15680, "loss": 0.3240252733230591, "lr": 5.351336199643612e-06, "epoch": 0.9553571428571429, "percentage": 47.77, "elapsed_time": "1 day, 3:09:04", "remaining_time": "1 day, 5:41:18", "throughput": 4651.88, "total_tokens": 454693328} {"current_steps": 7495, "total_steps": 15680, "loss": 0.34021596908569335, "lr": 5.346339488353374e-06, "epoch": 0.9559948979591837, "percentage": 47.8, "elapsed_time": "1 day, 3:10:08", "remaining_time": "1 day, 5:40:12", "throughput": 4651.91, "total_tokens": 454996912} {"current_steps": 7500, "total_steps": 15680, "loss": 0.31961989402770996, "lr": 5.341342429487271e-06, "epoch": 0.9566326530612245, "percentage": 47.83, "elapsed_time": "1 day, 3:11:14", "remaining_time": "1 day, 5:39:07", "throughput": 4651.89, "total_tokens": 455298984} {"current_steps": 7505, "total_steps": 15680, "loss": 0.3159759283065796, "lr": 5.336345028060199e-06, "epoch": 0.9572704081632653, "percentage": 47.86, "elapsed_time": "1 day, 3:12:29", "remaining_time": "1 day, 5:38:13", "throughput": 4651.47, "total_tokens": 455607960} {"current_steps": 7510, "total_steps": 15680, "loss": 0.33841490745544434, "lr": 5.331347289087402e-06, "epoch": 0.9579081632653061, "percentage": 47.9, "elapsed_time": "1 day, 3:13:28", "remaining_time": "1 day, 5:37:01", "throughput": 4651.65, "total_tokens": 455902144} {"current_steps": 7515, "total_steps": 15680, "loss": 0.30366837978363037, "lr": 5.326349217584459e-06, "epoch": 0.9585459183673469, "percentage": 47.93, "elapsed_time": "1 day, 3:14:32", "remaining_time": "1 day, 5:35:55", "throughput": 4651.73, "total_tokens": 456206152} {"current_steps": 7520, "total_steps": 15680, "loss": 0.31577486991882325, "lr": 5.321350818567285e-06, "epoch": 0.9591836734693877, "percentage": 47.96, "elapsed_time": "1 day, 3:15:44", "remaining_time": "1 day, 5:34:56", "throughput": 4651.36, "total_tokens": 456504376} {"current_steps": 7525, "total_steps": 15680, "loss": 0.31000518798828125, "lr": 5.3163520970521194e-06, "epoch": 0.9598214285714286, "percentage": 47.99, "elapsed_time": "1 day, 3:16:44", "remaining_time": "1 day, 5:33:46", "throughput": 4651.61, "total_tokens": 456809144} {"current_steps": 7530, "total_steps": 15680, "loss": 0.319872522354126, "lr": 5.311353058055533e-06, "epoch": 0.9604591836734694, "percentage": 48.02, "elapsed_time": "1 day, 3:17:59", "remaining_time": "1 day, 5:32:51", "throughput": 4651.09, "total_tokens": 457106664} {"current_steps": 7535, "total_steps": 15680, "loss": 0.3212242126464844, "lr": 5.306353706594407e-06, "epoch": 0.9610969387755102, "percentage": 48.05, "elapsed_time": "1 day, 3:19:08", "remaining_time": "1 day, 5:31:50", "throughput": 4650.81, "total_tokens": 457401712} {"current_steps": 7540, "total_steps": 15680, "loss": 0.3323201179504395, "lr": 5.3013540476859404e-06, "epoch": 0.9617346938775511, "percentage": 48.09, "elapsed_time": "1 day, 3:20:22", "remaining_time": "1 day, 5:30:54", "throughput": 4650.42, "total_tokens": 457706640} {"current_steps": 7545, "total_steps": 15680, "loss": 0.28949751853942873, "lr": 5.2963540863476404e-06, "epoch": 0.9623724489795918, "percentage": 48.12, "elapsed_time": "1 day, 3:21:32", "remaining_time": "1 day, 5:29:54", "throughput": 4650.24, "total_tokens": 458015200} {"current_steps": 7550, "total_steps": 15680, "loss": 0.3134197473526001, "lr": 5.291353827597317e-06, "epoch": 0.9630102040816326, "percentage": 48.15, "elapsed_time": "1 day, 3:22:39", "remaining_time": "1 day, 5:28:50", "throughput": 4650.18, "total_tokens": 458318128} {"current_steps": 7555, "total_steps": 15680, "loss": 0.3190800428390503, "lr": 5.28635327645308e-06, "epoch": 0.9636479591836735, "percentage": 48.18, "elapsed_time": "1 day, 3:23:37", "remaining_time": "1 day, 5:27:37", "throughput": 4650.6, "total_tokens": 458630192} {"current_steps": 7560, "total_steps": 15680, "loss": 0.32537388801574707, "lr": 5.281352437933331e-06, "epoch": 0.9642857142857143, "percentage": 48.21, "elapsed_time": "1 day, 3:24:34", "remaining_time": "1 day, 5:26:23", "throughput": 4651.09, "total_tokens": 458941680} {"current_steps": 7565, "total_steps": 15680, "loss": 0.33820252418518065, "lr": 5.276351317056762e-06, "epoch": 0.9649234693877551, "percentage": 48.25, "elapsed_time": "1 day, 3:25:49", "remaining_time": "1 day, 5:25:28", "throughput": 4650.56, "total_tokens": 459239448} {"current_steps": 7570, "total_steps": 15680, "loss": 0.32301039695739747, "lr": 5.271349918842344e-06, "epoch": 0.9655612244897959, "percentage": 48.28, "elapsed_time": "1 day, 3:26:55", "remaining_time": "1 day, 5:24:24", "throughput": 4650.42, "total_tokens": 459535592} {"current_steps": 7575, "total_steps": 15680, "loss": 0.34938960075378417, "lr": 5.266348248309332e-06, "epoch": 0.9661989795918368, "percentage": 48.31, "elapsed_time": "1 day, 3:28:00", "remaining_time": "1 day, 5:23:18", "throughput": 4650.46, "total_tokens": 459839392} {"current_steps": 7580, "total_steps": 15680, "loss": 0.32122604846954345, "lr": 5.2613463104772535e-06, "epoch": 0.9668367346938775, "percentage": 48.34, "elapsed_time": "1 day, 3:29:11", "remaining_time": "1 day, 5:22:20", "throughput": 4650.19, "total_tokens": 460145248} {"current_steps": 7585, "total_steps": 15680, "loss": 0.3423152446746826, "lr": 5.256344110365896e-06, "epoch": 0.9674744897959183, "percentage": 48.37, "elapsed_time": "1 day, 3:30:08", "remaining_time": "1 day, 5:21:05", "throughput": 4650.62, "total_tokens": 460450360} {"current_steps": 7590, "total_steps": 15680, "loss": 0.32942781448364256, "lr": 5.251341652995325e-06, "epoch": 0.9681122448979592, "percentage": 48.41, "elapsed_time": "1 day, 3:31:22", "remaining_time": "1 day, 5:20:09", "throughput": 4650.2, "total_tokens": 460751656} {"current_steps": 7595, "total_steps": 15680, "loss": 0.3291962146759033, "lr": 5.246338943385849e-06, "epoch": 0.96875, "percentage": 48.44, "elapsed_time": "1 day, 3:32:20", "remaining_time": "1 day, 5:18:57", "throughput": 4650.58, "total_tokens": 461062480} {"current_steps": 7600, "total_steps": 15680, "loss": 0.31624937057495117, "lr": 5.24133598655804e-06, "epoch": 0.9693877551020408, "percentage": 48.47, "elapsed_time": "1 day, 3:33:21", "remaining_time": "1 day, 5:17:46", "throughput": 4650.77, "total_tokens": 461362320} {"current_steps": 7605, "total_steps": 15680, "loss": 0.35048661231994627, "lr": 5.2363327875327115e-06, "epoch": 0.9700255102040817, "percentage": 48.5, "elapsed_time": "1 day, 3:34:18", "remaining_time": "1 day, 5:16:32", "throughput": 4651.13, "total_tokens": 461662608} {"current_steps": 7610, "total_steps": 15680, "loss": 0.307574200630188, "lr": 5.231329351330927e-06, "epoch": 0.9706632653061225, "percentage": 48.53, "elapsed_time": "1 day, 3:35:13", "remaining_time": "1 day, 5:15:16", "throughput": 4651.46, "total_tokens": 461951816} {"current_steps": 7615, "total_steps": 15680, "loss": 0.33936357498168945, "lr": 5.226325682973984e-06, "epoch": 0.9713010204081632, "percentage": 48.57, "elapsed_time": "1 day, 3:36:09", "remaining_time": "1 day, 5:14:01", "throughput": 4651.99, "total_tokens": 462266560} {"current_steps": 7620, "total_steps": 15680, "loss": 0.30183818340301516, "lr": 5.221321787483409e-06, "epoch": 0.9719387755102041, "percentage": 48.6, "elapsed_time": "1 day, 3:37:08", "remaining_time": "1 day, 5:12:49", "throughput": 4652.14, "total_tokens": 462553424} {"current_steps": 7625, "total_steps": 15680, "loss": 0.3296989440917969, "lr": 5.216317669880965e-06, "epoch": 0.9725765306122449, "percentage": 48.63, "elapsed_time": "1 day, 3:38:14", "remaining_time": "1 day, 5:11:45", "throughput": 4652.25, "total_tokens": 462874408} {"current_steps": 7630, "total_steps": 15680, "loss": 0.3277259826660156, "lr": 5.21131333518863e-06, "epoch": 0.9732142857142857, "percentage": 48.66, "elapsed_time": "1 day, 3:39:10", "remaining_time": "1 day, 5:10:30", "throughput": 4652.7, "total_tokens": 463178672} {"current_steps": 7635, "total_steps": 15680, "loss": 0.32791035175323485, "lr": 5.206308788428604e-06, "epoch": 0.9738520408163265, "percentage": 48.69, "elapsed_time": "1 day, 3:40:11", "remaining_time": "1 day, 5:09:20", "throughput": 4652.94, "total_tokens": 463487760} {"current_steps": 7640, "total_steps": 15680, "loss": 0.3223903656005859, "lr": 5.201304034623303e-06, "epoch": 0.9744897959183674, "percentage": 48.72, "elapsed_time": "1 day, 3:41:11", "remaining_time": "1 day, 5:08:09", "throughput": 4653.17, "total_tokens": 463788224} {"current_steps": 7645, "total_steps": 15680, "loss": 0.34218950271606446, "lr": 5.1962990787953436e-06, "epoch": 0.9751275510204082, "percentage": 48.76, "elapsed_time": "1 day, 3:42:16", "remaining_time": "1 day, 5:07:04", "throughput": 4653.17, "total_tokens": 464093352} {"current_steps": 7650, "total_steps": 15680, "loss": 0.3228957414627075, "lr": 5.191293925967548e-06, "epoch": 0.9757653061224489, "percentage": 48.79, "elapsed_time": "1 day, 3:43:26", "remaining_time": "1 day, 5:06:04", "throughput": 4653.01, "total_tokens": 464402904} {"current_steps": 7655, "total_steps": 15680, "loss": 0.3238239049911499, "lr": 5.186288581162939e-06, "epoch": 0.9764030612244898, "percentage": 48.82, "elapsed_time": "1 day, 3:44:44", "remaining_time": "1 day, 5:05:12", "throughput": 4652.41, "total_tokens": 464703560} {"current_steps": 7660, "total_steps": 15680, "loss": 0.327274751663208, "lr": 5.181283049404728e-06, "epoch": 0.9770408163265306, "percentage": 48.85, "elapsed_time": "1 day, 3:45:50", "remaining_time": "1 day, 5:04:07", "throughput": 4652.3, "total_tokens": 464999088} {"current_steps": 7665, "total_steps": 15680, "loss": 0.3050973415374756, "lr": 5.1762773357163175e-06, "epoch": 0.9776785714285714, "percentage": 48.88, "elapsed_time": "1 day, 3:46:50", "remaining_time": "1 day, 5:02:57", "throughput": 4652.63, "total_tokens": 465311888} {"current_steps": 7670, "total_steps": 15680, "loss": 0.3465284824371338, "lr": 5.171271445121286e-06, "epoch": 0.9783163265306123, "percentage": 48.92, "elapsed_time": "1 day, 3:47:43", "remaining_time": "1 day, 5:01:39", "throughput": 4653.3, "total_tokens": 465625424} {"current_steps": 7675, "total_steps": 15680, "loss": 0.34261624813079833, "lr": 5.166265382643402e-06, "epoch": 0.9789540816326531, "percentage": 48.95, "elapsed_time": "1 day, 3:48:38", "remaining_time": "1 day, 5:00:23", "throughput": 4653.72, "total_tokens": 465924320} {"current_steps": 7680, "total_steps": 15680, "loss": 0.32228875160217285, "lr": 5.161259153306592e-06, "epoch": 0.9795918367346939, "percentage": 48.98, "elapsed_time": "1 day, 3:49:45", "remaining_time": "1 day, 4:59:19", "throughput": 4653.62, "total_tokens": 466225272} {"current_steps": 7685, "total_steps": 15680, "loss": 0.3042541742324829, "lr": 5.156252762134959e-06, "epoch": 0.9802295918367347, "percentage": 49.01, "elapsed_time": "1 day, 3:50:45", "remaining_time": "1 day, 4:58:08", "throughput": 4653.81, "total_tokens": 466522448} {"current_steps": 7690, "total_steps": 15680, "loss": 0.326982307434082, "lr": 5.1512462141527675e-06, "epoch": 0.9808673469387755, "percentage": 49.04, "elapsed_time": "1 day, 3:51:46", "remaining_time": "1 day, 4:57:00", "throughput": 4654.01, "total_tokens": 466829432} {"current_steps": 7695, "total_steps": 15680, "loss": 0.3118090867996216, "lr": 5.146239514384437e-06, "epoch": 0.9815051020408163, "percentage": 49.08, "elapsed_time": "1 day, 3:52:45", "remaining_time": "1 day, 4:55:48", "throughput": 4654.23, "total_tokens": 467125040} {"current_steps": 7700, "total_steps": 15680, "loss": 0.31283886432647706, "lr": 5.14123266785454e-06, "epoch": 0.9821428571428571, "percentage": 49.11, "elapsed_time": "1 day, 3:53:48", "remaining_time": "1 day, 4:54:40", "throughput": 4654.38, "total_tokens": 467430568} {"current_steps": 7705, "total_steps": 15680, "loss": 0.3235911846160889, "lr": 5.136225679587797e-06, "epoch": 0.982780612244898, "percentage": 49.14, "elapsed_time": "1 day, 3:54:48", "remaining_time": "1 day, 4:53:30", "throughput": 4654.57, "total_tokens": 467731488} {"current_steps": 7710, "total_steps": 15680, "loss": 0.3317469596862793, "lr": 5.131218554609072e-06, "epoch": 0.9834183673469388, "percentage": 49.17, "elapsed_time": "1 day, 3:55:40", "remaining_time": "1 day, 4:52:11", "throughput": 4655.31, "total_tokens": 468049016} {"current_steps": 7715, "total_steps": 15680, "loss": 0.3359741449356079, "lr": 5.126211297943362e-06, "epoch": 0.9840561224489796, "percentage": 49.2, "elapsed_time": "1 day, 3:56:53", "remaining_time": "1 day, 4:51:13", "throughput": 4655.04, "total_tokens": 468358808} {"current_steps": 7720, "total_steps": 15680, "loss": 0.3237119197845459, "lr": 5.121203914615799e-06, "epoch": 0.9846938775510204, "percentage": 49.23, "elapsed_time": "1 day, 3:57:55", "remaining_time": "1 day, 4:50:04", "throughput": 4655.24, "total_tokens": 468666280} {"current_steps": 7725, "total_steps": 15680, "loss": 0.33925719261169435, "lr": 5.116196409651645e-06, "epoch": 0.9853316326530612, "percentage": 49.27, "elapsed_time": "1 day, 3:59:01", "remaining_time": "1 day, 4:49:01", "throughput": 4655.08, "total_tokens": 468960272} {"current_steps": 7730, "total_steps": 15680, "loss": 0.3303224086761475, "lr": 5.111188788076278e-06, "epoch": 0.985969387755102, "percentage": 49.3, "elapsed_time": "1 day, 4:00:16", "remaining_time": "1 day, 4:48:05", "throughput": 4654.55, "total_tokens": 469255544} {"current_steps": 7735, "total_steps": 15680, "loss": 0.29469146728515627, "lr": 5.106181054915196e-06, "epoch": 0.9866071428571429, "percentage": 49.33, "elapsed_time": "1 day, 4:01:28", "remaining_time": "1 day, 4:47:07", "throughput": 4654.19, "total_tokens": 469554832} {"current_steps": 7740, "total_steps": 15680, "loss": 0.3403113126754761, "lr": 5.10117321519401e-06, "epoch": 0.9872448979591837, "percentage": 49.36, "elapsed_time": "1 day, 4:02:39", "remaining_time": "1 day, 4:46:07", "throughput": 4653.97, "total_tokens": 469860760} {"current_steps": 7745, "total_steps": 15680, "loss": 0.35056252479553224, "lr": 5.0961652739384356e-06, "epoch": 0.9878826530612245, "percentage": 49.39, "elapsed_time": "1 day, 4:03:40", "remaining_time": "1 day, 4:44:58", "throughput": 4654.23, "total_tokens": 470173952} {"current_steps": 7750, "total_steps": 15680, "loss": 0.2968605995178223, "lr": 5.091157236174295e-06, "epoch": 0.9885204081632653, "percentage": 49.43, "elapsed_time": "1 day, 4:04:34", "remaining_time": "1 day, 4:43:42", "throughput": 4654.79, "total_tokens": 470483144} {"current_steps": 7755, "total_steps": 15680, "loss": 0.31652278900146485, "lr": 5.086149106927499e-06, "epoch": 0.9891581632653061, "percentage": 49.46, "elapsed_time": "1 day, 4:05:47", "remaining_time": "1 day, 4:42:44", "throughput": 4654.3, "total_tokens": 470768664} {"current_steps": 7760, "total_steps": 15680, "loss": 0.3348564624786377, "lr": 5.081140891224061e-06, "epoch": 0.9897959183673469, "percentage": 49.49, "elapsed_time": "1 day, 4:06:48", "remaining_time": "1 day, 4:41:35", "throughput": 4654.43, "total_tokens": 471069616} {"current_steps": 7765, "total_steps": 15680, "loss": 0.32708206176757815, "lr": 5.076132594090068e-06, "epoch": 0.9904336734693877, "percentage": 49.52, "elapsed_time": "1 day, 4:07:56", "remaining_time": "1 day, 4:40:32", "throughput": 4654.34, "total_tokens": 471374728} {"current_steps": 7770, "total_steps": 15680, "loss": 0.3107258081436157, "lr": 5.071124220551703e-06, "epoch": 0.9910714285714286, "percentage": 49.55, "elapsed_time": "1 day, 4:08:51", "remaining_time": "1 day, 4:39:17", "throughput": 4654.72, "total_tokens": 471671400} {"current_steps": 7775, "total_steps": 15680, "loss": 0.3611313343048096, "lr": 5.066115775635213e-06, "epoch": 0.9917091836734694, "percentage": 49.59, "elapsed_time": "1 day, 4:09:48", "remaining_time": "1 day, 4:38:04", "throughput": 4655.21, "total_tokens": 471987080} {"current_steps": 7780, "total_steps": 15680, "loss": 0.3070375442504883, "lr": 5.061107264366926e-06, "epoch": 0.9923469387755102, "percentage": 49.62, "elapsed_time": "1 day, 4:10:56", "remaining_time": "1 day, 4:37:01", "throughput": 4655.25, "total_tokens": 472305712} {"current_steps": 7785, "total_steps": 15680, "loss": 0.32773163318634035, "lr": 5.05609869177323e-06, "epoch": 0.9929846938775511, "percentage": 49.65, "elapsed_time": "1 day, 4:11:53", "remaining_time": "1 day, 4:35:47", "throughput": 4655.67, "total_tokens": 472612736} {"current_steps": 7790, "total_steps": 15680, "loss": 0.3287439107894897, "lr": 5.05109006288058e-06, "epoch": 0.9936224489795918, "percentage": 49.68, "elapsed_time": "1 day, 4:13:05", "remaining_time": "1 day, 4:34:49", "throughput": 4655.36, "total_tokens": 472917496} {"current_steps": 7795, "total_steps": 15680, "loss": 0.32365686893463136, "lr": 5.046081382715484e-06, "epoch": 0.9942602040816326, "percentage": 49.71, "elapsed_time": "1 day, 4:14:21", "remaining_time": "1 day, 4:33:54", "throughput": 4654.86, "total_tokens": 473218584} {"current_steps": 7800, "total_steps": 15680, "loss": 0.3211040496826172, "lr": 5.0410726563045005e-06, "epoch": 0.9948979591836735, "percentage": 49.74, "elapsed_time": "1 day, 4:15:31", "remaining_time": "1 day, 4:32:55", "throughput": 4654.56, "total_tokens": 473517592} {"current_steps": 7805, "total_steps": 15680, "loss": 0.32327837944030763, "lr": 5.036063888674239e-06, "epoch": 0.9955357142857143, "percentage": 49.78, "elapsed_time": "1 day, 4:16:33", "remaining_time": "1 day, 4:31:46", "throughput": 4654.66, "total_tokens": 473813360} {"current_steps": 7810, "total_steps": 15680, "loss": 0.30079605579376223, "lr": 5.031055084851349e-06, "epoch": 0.9961734693877551, "percentage": 49.81, "elapsed_time": "1 day, 4:17:38", "remaining_time": "1 day, 4:30:40", "throughput": 4654.76, "total_tokens": 474124592} {"current_steps": 7815, "total_steps": 15680, "loss": 0.3088978290557861, "lr": 5.0260462498625084e-06, "epoch": 0.9968112244897959, "percentage": 49.84, "elapsed_time": "1 day, 4:18:36", "remaining_time": "1 day, 4:29:28", "throughput": 4655.08, "total_tokens": 474430976} {"current_steps": 7820, "total_steps": 15680, "loss": 0.33654088973999025, "lr": 5.021037388734439e-06, "epoch": 0.9974489795918368, "percentage": 49.87, "elapsed_time": "1 day, 4:19:38", "remaining_time": "1 day, 4:28:20", "throughput": 4655.22, "total_tokens": 474733096} {"current_steps": 7825, "total_steps": 15680, "loss": 0.29360170364379884, "lr": 5.016028506493881e-06, "epoch": 0.9980867346938775, "percentage": 49.9, "elapsed_time": "1 day, 4:20:41", "remaining_time": "1 day, 4:27:12", "throughput": 4655.27, "total_tokens": 475031800} {"current_steps": 7830, "total_steps": 15680, "loss": 0.3257938861846924, "lr": 5.011019608167596e-06, "epoch": 0.9987244897959183, "percentage": 49.94, "elapsed_time": "1 day, 4:21:54", "remaining_time": "1 day, 4:26:15", "throughput": 4654.84, "total_tokens": 475328464} {"current_steps": 7835, "total_steps": 15680, "loss": 0.3119340896606445, "lr": 5.006010698782365e-06, "epoch": 0.9993622448979592, "percentage": 49.97, "elapsed_time": "1 day, 4:23:02", "remaining_time": "1 day, 4:25:13", "throughput": 4654.66, "total_tokens": 475626552} {"current_steps": 7840, "total_steps": 15680, "loss": 0.30375056266784667, "lr": 5.001001783364978e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "1 day, 4:24:02", "remaining_time": "1 day, 4:24:02", "throughput": 4655.03, "total_tokens": 475942160} {"current_steps": 7845, "total_steps": 15680, "loss": 0.267057466506958, "lr": 4.995992866942232e-06, "epoch": 1.000637755102041, "percentage": 50.03, "elapsed_time": "1 day, 4:25:33", "remaining_time": "1 day, 4:23:22", "throughput": 4653.82, "total_tokens": 476239480} {"current_steps": 7850, "total_steps": 15680, "loss": 0.2515033960342407, "lr": 4.990983954540925e-06, "epoch": 1.0012755102040816, "percentage": 50.06, "elapsed_time": "1 day, 4:26:35", "remaining_time": "1 day, 4:22:14", "throughput": 4653.96, "total_tokens": 476545208} {"current_steps": 7855, "total_steps": 15680, "loss": 0.28331613540649414, "lr": 4.985975051187848e-06, "epoch": 1.0019132653061225, "percentage": 50.1, "elapsed_time": "1 day, 4:27:35", "remaining_time": "1 day, 4:21:04", "throughput": 4654.3, "total_tokens": 476859168} {"current_steps": 7860, "total_steps": 15680, "loss": 0.24894070625305176, "lr": 4.980966161909785e-06, "epoch": 1.0025510204081634, "percentage": 50.13, "elapsed_time": "1 day, 4:28:51", "remaining_time": "1 day, 4:20:09", "throughput": 4653.78, "total_tokens": 477158016} {"current_steps": 7865, "total_steps": 15680, "loss": 0.2599456310272217, "lr": 4.975957291733511e-06, "epoch": 1.003188775510204, "percentage": 50.16, "elapsed_time": "1 day, 4:30:00", "remaining_time": "1 day, 4:19:08", "throughput": 4653.64, "total_tokens": 477467600} {"current_steps": 7870, "total_steps": 15680, "loss": 0.26632611751556395, "lr": 4.970948445685772e-06, "epoch": 1.003826530612245, "percentage": 50.19, "elapsed_time": "1 day, 4:31:14", "remaining_time": "1 day, 4:18:11", "throughput": 4653.29, "total_tokens": 477774896} {"current_steps": 7875, "total_steps": 15680, "loss": 0.25829689502716063, "lr": 4.965939628793295e-06, "epoch": 1.0044642857142858, "percentage": 50.22, "elapsed_time": "1 day, 4:32:25", "remaining_time": "1 day, 4:17:11", "throughput": 4653.13, "total_tokens": 478085696} {"current_steps": 7880, "total_steps": 15680, "loss": 0.27562432289123534, "lr": 4.960930846082783e-06, "epoch": 1.0051020408163265, "percentage": 50.26, "elapsed_time": "1 day, 4:33:27", "remaining_time": "1 day, 4:16:03", "throughput": 4653.31, "total_tokens": 478395512} {"current_steps": 7885, "total_steps": 15680, "loss": 0.28523437976837157, "lr": 4.955922102580894e-06, "epoch": 1.0057397959183674, "percentage": 50.29, "elapsed_time": "1 day, 4:34:43", "remaining_time": "1 day, 4:15:09", "throughput": 4652.8, "total_tokens": 478696016} {"current_steps": 7890, "total_steps": 15680, "loss": 0.2536736488342285, "lr": 4.9509134033142525e-06, "epoch": 1.0063775510204083, "percentage": 50.32, "elapsed_time": "1 day, 4:35:50", "remaining_time": "1 day, 4:14:05", "throughput": 4652.76, "total_tokens": 479003496} {"current_steps": 7895, "total_steps": 15680, "loss": 0.2690150260925293, "lr": 4.945904753309441e-06, "epoch": 1.007015306122449, "percentage": 50.35, "elapsed_time": "1 day, 4:36:54", "remaining_time": "1 day, 4:12:59", "throughput": 4652.83, "total_tokens": 479311408} {"current_steps": 7900, "total_steps": 15680, "loss": 0.24584484100341797, "lr": 4.940896157592985e-06, "epoch": 1.0076530612244898, "percentage": 50.38, "elapsed_time": "1 day, 4:38:01", "remaining_time": "1 day, 4:11:56", "throughput": 4652.94, "total_tokens": 479633944} {"current_steps": 7905, "total_steps": 15680, "loss": 0.25741584300994874, "lr": 4.935887621191364e-06, "epoch": 1.0082908163265305, "percentage": 50.41, "elapsed_time": "1 day, 4:39:13", "remaining_time": "1 day, 4:10:57", "throughput": 4652.72, "total_tokens": 479943672} {"current_steps": 7910, "total_steps": 15680, "loss": 0.25302848815917967, "lr": 4.930879149130993e-06, "epoch": 1.0089285714285714, "percentage": 50.45, "elapsed_time": "1 day, 4:40:12", "remaining_time": "1 day, 4:09:45", "throughput": 4653.0, "total_tokens": 480246768} {"current_steps": 7915, "total_steps": 15680, "loss": 0.2453629970550537, "lr": 4.925870746438223e-06, "epoch": 1.0095663265306123, "percentage": 50.48, "elapsed_time": "1 day, 4:41:13", "remaining_time": "1 day, 4:08:35", "throughput": 4653.25, "total_tokens": 480555560} {"current_steps": 7920, "total_steps": 15680, "loss": 0.24580702781677247, "lr": 4.920862418139335e-06, "epoch": 1.010204081632653, "percentage": 50.51, "elapsed_time": "1 day, 4:42:21", "remaining_time": "1 day, 4:07:33", "throughput": 4653.25, "total_tokens": 480874576} {"current_steps": 7925, "total_steps": 15680, "loss": 0.25847864151000977, "lr": 4.91585416926054e-06, "epoch": 1.0108418367346939, "percentage": 50.54, "elapsed_time": "1 day, 4:43:22", "remaining_time": "1 day, 4:06:24", "throughput": 4653.31, "total_tokens": 481165672} {"current_steps": 7930, "total_steps": 15680, "loss": 0.28442893028259275, "lr": 4.91084600482796e-06, "epoch": 1.0114795918367347, "percentage": 50.57, "elapsed_time": "1 day, 4:44:31", "remaining_time": "1 day, 4:05:22", "throughput": 4653.21, "total_tokens": 481472544} {"current_steps": 7935, "total_steps": 15680, "loss": 0.2587409496307373, "lr": 4.905837929867643e-06, "epoch": 1.0121173469387754, "percentage": 50.61, "elapsed_time": "1 day, 4:45:36", "remaining_time": "1 day, 4:04:16", "throughput": 4653.3, "total_tokens": 481783768} {"current_steps": 7940, "total_steps": 15680, "loss": 0.2645289421081543, "lr": 4.900829949405539e-06, "epoch": 1.0127551020408163, "percentage": 50.64, "elapsed_time": "1 day, 4:46:51", "remaining_time": "1 day, 4:03:21", "throughput": 4652.92, "total_tokens": 482093968} {"current_steps": 7945, "total_steps": 15680, "loss": 0.2553886651992798, "lr": 4.895822068467505e-06, "epoch": 1.0133928571428572, "percentage": 50.67, "elapsed_time": "1 day, 4:47:53", "remaining_time": "1 day, 4:02:13", "throughput": 4653.02, "total_tokens": 482395560} {"current_steps": 7950, "total_steps": 15680, "loss": 0.2639014482498169, "lr": 4.890814292079303e-06, "epoch": 1.0140306122448979, "percentage": 50.7, "elapsed_time": "1 day, 4:48:58", "remaining_time": "1 day, 4:01:07", "throughput": 4653.01, "total_tokens": 482696040} {"current_steps": 7955, "total_steps": 15680, "loss": 0.2515778303146362, "lr": 4.885806625266585e-06, "epoch": 1.0146683673469388, "percentage": 50.73, "elapsed_time": "1 day, 4:50:14", "remaining_time": "1 day, 4:00:13", "throughput": 4652.49, "total_tokens": 482997952} {"current_steps": 7960, "total_steps": 15680, "loss": 0.2634756088256836, "lr": 4.8807990730548905e-06, "epoch": 1.0153061224489797, "percentage": 50.77, "elapsed_time": "1 day, 4:51:20", "remaining_time": "1 day, 3:59:08", "throughput": 4652.47, "total_tokens": 483299448} {"current_steps": 7965, "total_steps": 15680, "loss": 0.2525560617446899, "lr": 4.8757916404696545e-06, "epoch": 1.0159438775510203, "percentage": 50.8, "elapsed_time": "1 day, 4:52:30", "remaining_time": "1 day, 3:58:07", "throughput": 4652.19, "total_tokens": 483598280} {"current_steps": 7970, "total_steps": 15680, "loss": 0.26147069931030276, "lr": 4.870784332536181e-06, "epoch": 1.0165816326530612, "percentage": 50.83, "elapsed_time": "1 day, 4:53:30", "remaining_time": "1 day, 3:56:56", "throughput": 4652.46, "total_tokens": 483902832} {"current_steps": 7975, "total_steps": 15680, "loss": 0.2916694164276123, "lr": 4.865777154279653e-06, "epoch": 1.0172193877551021, "percentage": 50.86, "elapsed_time": "1 day, 4:54:31", "remaining_time": "1 day, 3:55:48", "throughput": 4652.68, "total_tokens": 484213240} {"current_steps": 7980, "total_steps": 15680, "loss": 0.2569180965423584, "lr": 4.8607701107251274e-06, "epoch": 1.0178571428571428, "percentage": 50.89, "elapsed_time": "1 day, 4:55:47", "remaining_time": "1 day, 3:54:53", "throughput": 4652.23, "total_tokens": 484520120} {"current_steps": 7985, "total_steps": 15680, "loss": 0.26433415412902833, "lr": 4.855763206897516e-06, "epoch": 1.0184948979591837, "percentage": 50.92, "elapsed_time": "1 day, 4:56:59", "remaining_time": "1 day, 3:53:54", "throughput": 4651.86, "total_tokens": 484814000} {"current_steps": 7990, "total_steps": 15680, "loss": 0.25423283576965333, "lr": 4.850756447821602e-06, "epoch": 1.0191326530612246, "percentage": 50.96, "elapsed_time": "1 day, 4:57:56", "remaining_time": "1 day, 3:52:40", "throughput": 4652.17, "total_tokens": 485110200} {"current_steps": 7995, "total_steps": 15680, "loss": 0.2718416929244995, "lr": 4.845749838522016e-06, "epoch": 1.0197704081632653, "percentage": 50.99, "elapsed_time": "1 day, 4:59:03", "remaining_time": "1 day, 3:51:38", "throughput": 4652.12, "total_tokens": 485420576} {"current_steps": 8000, "total_steps": 15680, "loss": 0.26037960052490233, "lr": 4.84074338402324e-06, "epoch": 1.0204081632653061, "percentage": 51.02, "elapsed_time": "1 day, 5:00:01", "remaining_time": "1 day, 3:50:25", "throughput": 4652.64, "total_tokens": 485740608} {"current_steps": 8005, "total_steps": 15680, "loss": 0.2492842674255371, "lr": 4.835737089349599e-06, "epoch": 1.021045918367347, "percentage": 51.05, "elapsed_time": "1 day, 5:01:02", "remaining_time": "1 day, 3:49:16", "throughput": 4652.83, "total_tokens": 486046816} {"current_steps": 8010, "total_steps": 15680, "loss": 0.261875057220459, "lr": 4.8307309595252624e-06, "epoch": 1.0216836734693877, "percentage": 51.08, "elapsed_time": "1 day, 5:02:07", "remaining_time": "1 day, 3:48:10", "throughput": 4652.89, "total_tokens": 486355088} {"current_steps": 8015, "total_steps": 15680, "loss": 0.24945347309112548, "lr": 4.82572499957423e-06, "epoch": 1.0223214285714286, "percentage": 51.12, "elapsed_time": "1 day, 5:03:08", "remaining_time": "1 day, 3:47:01", "throughput": 4653.16, "total_tokens": 486668640} {"current_steps": 8020, "total_steps": 15680, "loss": 0.2600055694580078, "lr": 4.820719214520329e-06, "epoch": 1.0229591836734695, "percentage": 51.15, "elapsed_time": "1 day, 5:04:03", "remaining_time": "1 day, 3:45:46", "throughput": 4653.63, "total_tokens": 486972232} {"current_steps": 8025, "total_steps": 15680, "loss": 0.2600249290466309, "lr": 4.815713609387221e-06, "epoch": 1.0235969387755102, "percentage": 51.18, "elapsed_time": "1 day, 5:05:15", "remaining_time": "1 day, 3:44:47", "throughput": 4653.17, "total_tokens": 487258464} {"current_steps": 8030, "total_steps": 15680, "loss": 0.25761544704437256, "lr": 4.810708189198374e-06, "epoch": 1.024234693877551, "percentage": 51.21, "elapsed_time": "1 day, 5:06:20", "remaining_time": "1 day, 3:43:42", "throughput": 4653.2, "total_tokens": 487564392} {"current_steps": 8035, "total_steps": 15680, "loss": 0.26144454479217527, "lr": 4.80570295897708e-06, "epoch": 1.0248724489795917, "percentage": 51.24, "elapsed_time": "1 day, 5:07:28", "remaining_time": "1 day, 3:42:39", "throughput": 4653.05, "total_tokens": 487865256} {"current_steps": 8040, "total_steps": 15680, "loss": 0.2451169013977051, "lr": 4.800697923746437e-06, "epoch": 1.0255102040816326, "percentage": 51.28, "elapsed_time": "1 day, 5:08:37", "remaining_time": "1 day, 3:41:37", "throughput": 4652.93, "total_tokens": 488171848} {"current_steps": 8045, "total_steps": 15680, "loss": 0.24808902740478517, "lr": 4.795693088529345e-06, "epoch": 1.0261479591836735, "percentage": 51.31, "elapsed_time": "1 day, 5:09:42", "remaining_time": "1 day, 3:40:32", "throughput": 4652.92, "total_tokens": 488475712} {"current_steps": 8050, "total_steps": 15680, "loss": 0.23900938034057617, "lr": 4.790688458348509e-06, "epoch": 1.0267857142857142, "percentage": 51.34, "elapsed_time": "1 day, 5:10:51", "remaining_time": "1 day, 3:39:30", "throughput": 4652.67, "total_tokens": 488771280} {"current_steps": 8055, "total_steps": 15680, "loss": 0.2610027313232422, "lr": 4.7856840382264234e-06, "epoch": 1.027423469387755, "percentage": 51.37, "elapsed_time": "1 day, 5:12:00", "remaining_time": "1 day, 3:38:29", "throughput": 4652.42, "total_tokens": 489065984} {"current_steps": 8060, "total_steps": 15680, "loss": 0.2779052257537842, "lr": 4.780679833185372e-06, "epoch": 1.028061224489796, "percentage": 51.4, "elapsed_time": "1 day, 5:12:57", "remaining_time": "1 day, 3:37:16", "throughput": 4652.81, "total_tokens": 489372736} {"current_steps": 8065, "total_steps": 15680, "loss": 0.246592378616333, "lr": 4.775675848247427e-06, "epoch": 1.0286989795918366, "percentage": 51.43, "elapsed_time": "1 day, 5:14:09", "remaining_time": "1 day, 3:36:17", "throughput": 4652.32, "total_tokens": 489656160} {"current_steps": 8070, "total_steps": 15680, "loss": 0.2661409854888916, "lr": 4.770672088434433e-06, "epoch": 1.0293367346938775, "percentage": 51.47, "elapsed_time": "1 day, 5:15:19", "remaining_time": "1 day, 3:35:15", "throughput": 4652.11, "total_tokens": 489956800} {"current_steps": 8075, "total_steps": 15680, "loss": 0.25893139839172363, "lr": 4.765668558768015e-06, "epoch": 1.0299744897959184, "percentage": 51.5, "elapsed_time": "1 day, 5:16:18", "remaining_time": "1 day, 3:34:05", "throughput": 4652.31, "total_tokens": 490255024} {"current_steps": 8080, "total_steps": 15680, "loss": 0.2638129234313965, "lr": 4.760665264269566e-06, "epoch": 1.030612244897959, "percentage": 51.53, "elapsed_time": "1 day, 5:17:30", "remaining_time": "1 day, 3:33:05", "throughput": 4651.97, "total_tokens": 490550736} {"current_steps": 8085, "total_steps": 15680, "loss": 0.2742192506790161, "lr": 4.755662209960238e-06, "epoch": 1.03125, "percentage": 51.56, "elapsed_time": "1 day, 5:18:32", "remaining_time": "1 day, 3:31:57", "throughput": 4652.06, "total_tokens": 490851432} {"current_steps": 8090, "total_steps": 15680, "loss": 0.2618445634841919, "lr": 4.750659400860945e-06, "epoch": 1.031887755102041, "percentage": 51.59, "elapsed_time": "1 day, 5:19:28", "remaining_time": "1 day, 3:30:43", "throughput": 4652.52, "total_tokens": 491159256} {"current_steps": 8095, "total_steps": 15680, "loss": 0.2552893400192261, "lr": 4.74565684199236e-06, "epoch": 1.0325255102040816, "percentage": 51.63, "elapsed_time": "1 day, 5:20:36", "remaining_time": "1 day, 3:29:41", "throughput": 4652.46, "total_tokens": 491470608} {"current_steps": 8100, "total_steps": 15680, "loss": 0.2529830694198608, "lr": 4.740654538374896e-06, "epoch": 1.0331632653061225, "percentage": 51.66, "elapsed_time": "1 day, 5:21:36", "remaining_time": "1 day, 3:28:31", "throughput": 4652.58, "total_tokens": 491763560} {"current_steps": 8105, "total_steps": 15680, "loss": 0.25743880271911623, "lr": 4.735652495028714e-06, "epoch": 1.0338010204081634, "percentage": 51.69, "elapsed_time": "1 day, 5:22:53", "remaining_time": "1 day, 3:27:37", "throughput": 4652.05, "total_tokens": 492064832} {"current_steps": 8110, "total_steps": 15680, "loss": 0.2751675367355347, "lr": 4.7306507169737176e-06, "epoch": 1.034438775510204, "percentage": 51.72, "elapsed_time": "1 day, 5:23:59", "remaining_time": "1 day, 3:26:32", "throughput": 4652.11, "total_tokens": 492377080} {"current_steps": 8115, "total_steps": 15680, "loss": 0.25722560882568357, "lr": 4.725649209229537e-06, "epoch": 1.035076530612245, "percentage": 51.75, "elapsed_time": "1 day, 5:25:12", "remaining_time": "1 day, 3:25:34", "throughput": 4651.76, "total_tokens": 492681472} {"current_steps": 8120, "total_steps": 15680, "loss": 0.24139046669006348, "lr": 4.720647976815536e-06, "epoch": 1.0357142857142858, "percentage": 51.79, "elapsed_time": "1 day, 5:26:10", "remaining_time": "1 day, 3:24:22", "throughput": 4651.96, "total_tokens": 492970464} {"current_steps": 8125, "total_steps": 15680, "loss": 0.275927734375, "lr": 4.7156470247508e-06, "epoch": 1.0363520408163265, "percentage": 51.82, "elapsed_time": "1 day, 5:27:17", "remaining_time": "1 day, 3:23:18", "throughput": 4651.93, "total_tokens": 493277120} {"current_steps": 8130, "total_steps": 15680, "loss": 0.2354154109954834, "lr": 4.710646358054133e-06, "epoch": 1.0369897959183674, "percentage": 51.85, "elapsed_time": "1 day, 5:28:30", "remaining_time": "1 day, 3:22:20", "throughput": 4651.62, "total_tokens": 493583608} {"current_steps": 8135, "total_steps": 15680, "loss": 0.258892822265625, "lr": 4.705645981744055e-06, "epoch": 1.0376275510204083, "percentage": 51.88, "elapsed_time": "1 day, 5:29:43", "remaining_time": "1 day, 3:21:22", "throughput": 4651.27, "total_tokens": 493890512} {"current_steps": 8140, "total_steps": 15680, "loss": 0.25546367168426515, "lr": 4.700645900838793e-06, "epoch": 1.038265306122449, "percentage": 51.91, "elapsed_time": "1 day, 5:30:56", "remaining_time": "1 day, 3:20:24", "throughput": 4650.86, "total_tokens": 494183480} {"current_steps": 8145, "total_steps": 15680, "loss": 0.2416550874710083, "lr": 4.695646120356275e-06, "epoch": 1.0389030612244898, "percentage": 51.95, "elapsed_time": "1 day, 5:32:03", "remaining_time": "1 day, 3:19:20", "throughput": 4650.88, "total_tokens": 494496488} {"current_steps": 8150, "total_steps": 15680, "loss": 0.24819722175598144, "lr": 4.69064664531413e-06, "epoch": 1.0395408163265305, "percentage": 51.98, "elapsed_time": "1 day, 5:33:02", "remaining_time": "1 day, 3:18:09", "throughput": 4651.34, "total_tokens": 494818504} {"current_steps": 8155, "total_steps": 15680, "loss": 0.23823702335357666, "lr": 4.685647480729684e-06, "epoch": 1.0401785714285714, "percentage": 52.01, "elapsed_time": "1 day, 5:34:15", "remaining_time": "1 day, 3:17:11", "throughput": 4651.0, "total_tokens": 495124752} {"current_steps": 8160, "total_steps": 15680, "loss": 0.266727876663208, "lr": 4.680648631619945e-06, "epoch": 1.0408163265306123, "percentage": 52.04, "elapsed_time": "1 day, 5:35:25", "remaining_time": "1 day, 3:16:10", "throughput": 4650.68, "total_tokens": 495417592} {"current_steps": 8165, "total_steps": 15680, "loss": 0.2604006052017212, "lr": 4.675650103001606e-06, "epoch": 1.041454081632653, "percentage": 52.07, "elapsed_time": "1 day, 5:36:22", "remaining_time": "1 day, 3:14:57", "throughput": 4651.07, "total_tokens": 495721688} {"current_steps": 8170, "total_steps": 15680, "loss": 0.2684458017349243, "lr": 4.670651899891043e-06, "epoch": 1.0420918367346939, "percentage": 52.1, "elapsed_time": "1 day, 5:37:19", "remaining_time": "1 day, 3:13:45", "throughput": 4651.45, "total_tokens": 496029336} {"current_steps": 8175, "total_steps": 15680, "loss": 0.23414976596832277, "lr": 4.6656540273042986e-06, "epoch": 1.0427295918367347, "percentage": 52.14, "elapsed_time": "1 day, 5:38:25", "remaining_time": "1 day, 3:12:40", "throughput": 4651.3, "total_tokens": 496320248} {"current_steps": 8180, "total_steps": 15680, "loss": 0.26569809913635256, "lr": 4.66065649025709e-06, "epoch": 1.0433673469387754, "percentage": 52.17, "elapsed_time": "1 day, 5:39:42", "remaining_time": "1 day, 3:11:45", "throughput": 4650.8, "total_tokens": 496622736} {"current_steps": 8185, "total_steps": 15680, "loss": 0.27560110092163087, "lr": 4.655659293764793e-06, "epoch": 1.0440051020408163, "percentage": 52.2, "elapsed_time": "1 day, 5:40:35", "remaining_time": "1 day, 3:10:29", "throughput": 4651.44, "total_tokens": 496940704} {"current_steps": 8190, "total_steps": 15680, "loss": 0.2756011724472046, "lr": 4.6506624428424405e-06, "epoch": 1.0446428571428572, "percentage": 52.23, "elapsed_time": "1 day, 5:41:45", "remaining_time": "1 day, 3:09:28", "throughput": 4651.15, "total_tokens": 497235288} {"current_steps": 8195, "total_steps": 15680, "loss": 0.27366573810577394, "lr": 4.645665942504728e-06, "epoch": 1.0452806122448979, "percentage": 52.26, "elapsed_time": "1 day, 5:42:52", "remaining_time": "1 day, 3:08:24", "throughput": 4651.03, "total_tokens": 497531328} {"current_steps": 8200, "total_steps": 15680, "loss": 0.2521559715270996, "lr": 4.640669797765987e-06, "epoch": 1.0459183673469388, "percentage": 52.3, "elapsed_time": "1 day, 5:43:59", "remaining_time": "1 day, 3:07:21", "throughput": 4650.81, "total_tokens": 497820552} {"current_steps": 8205, "total_steps": 15680, "loss": 0.25814969539642335, "lr": 4.6356740136402e-06, "epoch": 1.0465561224489797, "percentage": 52.33, "elapsed_time": "1 day, 5:44:55", "remaining_time": "1 day, 3:06:06", "throughput": 4651.29, "total_tokens": 498130520} {"current_steps": 8210, "total_steps": 15680, "loss": 0.2693226099014282, "lr": 4.630678595140985e-06, "epoch": 1.0471938775510203, "percentage": 52.36, "elapsed_time": "1 day, 5:46:03", "remaining_time": "1 day, 3:05:04", "throughput": 4651.09, "total_tokens": 498428464} {"current_steps": 8215, "total_steps": 15680, "loss": 0.2454256534576416, "lr": 4.625683547281592e-06, "epoch": 1.0478316326530612, "percentage": 52.39, "elapsed_time": "1 day, 5:47:17", "remaining_time": "1 day, 3:04:07", "throughput": 4650.81, "total_tokens": 498741112} {"current_steps": 8220, "total_steps": 15680, "loss": 0.2583413362503052, "lr": 4.620688875074902e-06, "epoch": 1.0484693877551021, "percentage": 52.42, "elapsed_time": "1 day, 5:48:23", "remaining_time": "1 day, 3:03:02", "throughput": 4650.75, "total_tokens": 499042560} {"current_steps": 8225, "total_steps": 15680, "loss": 0.24875664710998535, "lr": 4.615694583533418e-06, "epoch": 1.0491071428571428, "percentage": 52.46, "elapsed_time": "1 day, 5:49:22", "remaining_time": "1 day, 3:01:51", "throughput": 4651.0, "total_tokens": 499340840} {"current_steps": 8230, "total_steps": 15680, "loss": 0.2657691717147827, "lr": 4.610700677669259e-06, "epoch": 1.0497448979591837, "percentage": 52.49, "elapsed_time": "1 day, 5:50:19", "remaining_time": "1 day, 3:00:38", "throughput": 4651.44, "total_tokens": 499653984} {"current_steps": 8235, "total_steps": 15680, "loss": 0.26746602058410646, "lr": 4.605707162494157e-06, "epoch": 1.0503826530612246, "percentage": 52.52, "elapsed_time": "1 day, 5:51:24", "remaining_time": "1 day, 2:59:33", "throughput": 4651.41, "total_tokens": 499955880} {"current_steps": 8240, "total_steps": 15680, "loss": 0.25636651515960696, "lr": 4.600714043019456e-06, "epoch": 1.0510204081632653, "percentage": 52.55, "elapsed_time": "1 day, 5:52:24", "remaining_time": "1 day, 2:58:22", "throughput": 4651.68, "total_tokens": 500260776} {"current_steps": 8245, "total_steps": 15680, "loss": 0.2619192600250244, "lr": 4.5957213242560985e-06, "epoch": 1.0516581632653061, "percentage": 52.58, "elapsed_time": "1 day, 5:53:29", "remaining_time": "1 day, 2:57:17", "throughput": 4651.65, "total_tokens": 500560728} {"current_steps": 8250, "total_steps": 15680, "loss": 0.24567170143127443, "lr": 4.5907290112146265e-06, "epoch": 1.052295918367347, "percentage": 52.61, "elapsed_time": "1 day, 5:54:25", "remaining_time": "1 day, 2:56:04", "throughput": 4652.05, "total_tokens": 500864232} {"current_steps": 8255, "total_steps": 15680, "loss": 0.25845234394073485, "lr": 4.585737108905178e-06, "epoch": 1.0529336734693877, "percentage": 52.65, "elapsed_time": "1 day, 5:55:14", "remaining_time": "1 day, 2:54:44", "throughput": 4652.78, "total_tokens": 501171944} {"current_steps": 8260, "total_steps": 15680, "loss": 0.26011834144592283, "lr": 4.5807456223374695e-06, "epoch": 1.0535714285714286, "percentage": 52.68, "elapsed_time": "1 day, 5:56:24", "remaining_time": "1 day, 2:53:43", "throughput": 4652.63, "total_tokens": 501482344} {"current_steps": 8265, "total_steps": 15680, "loss": 0.24192533493041993, "lr": 4.57575455652081e-06, "epoch": 1.0542091836734695, "percentage": 52.71, "elapsed_time": "1 day, 5:57:39", "remaining_time": "1 day, 2:52:46", "throughput": 4652.07, "total_tokens": 501767928} {"current_steps": 8270, "total_steps": 15680, "loss": 0.2520601749420166, "lr": 4.570763916464084e-06, "epoch": 1.0548469387755102, "percentage": 52.74, "elapsed_time": "1 day, 5:58:41", "remaining_time": "1 day, 2:51:38", "throughput": 4652.12, "total_tokens": 502063992} {"current_steps": 8275, "total_steps": 15680, "loss": 0.27521862983703616, "lr": 4.565773707175743e-06, "epoch": 1.055484693877551, "percentage": 52.77, "elapsed_time": "1 day, 5:59:35", "remaining_time": "1 day, 2:50:23", "throughput": 4652.68, "total_tokens": 502375752} {"current_steps": 8280, "total_steps": 15680, "loss": 0.2762296676635742, "lr": 4.560783933663814e-06, "epoch": 1.0561224489795917, "percentage": 52.81, "elapsed_time": "1 day, 6:00:35", "remaining_time": "1 day, 2:49:13", "throughput": 4652.89, "total_tokens": 502676192} {"current_steps": 8285, "total_steps": 15680, "loss": 0.2601089239120483, "lr": 4.5557946009358846e-06, "epoch": 1.0567602040816326, "percentage": 52.84, "elapsed_time": "1 day, 6:01:45", "remaining_time": "1 day, 2:48:12", "throughput": 4652.73, "total_tokens": 502984856} {"current_steps": 8290, "total_steps": 15680, "loss": 0.23802318572998046, "lr": 4.550805713999094e-06, "epoch": 1.0573979591836735, "percentage": 52.87, "elapsed_time": "1 day, 6:02:49", "remaining_time": "1 day, 2:47:05", "throughput": 4652.86, "total_tokens": 503296512} {"current_steps": 8295, "total_steps": 15680, "loss": 0.27293121814727783, "lr": 4.545817277860143e-06, "epoch": 1.0580357142857142, "percentage": 52.9, "elapsed_time": "1 day, 6:03:52", "remaining_time": "1 day, 2:45:59", "throughput": 4652.82, "total_tokens": 503588512} {"current_steps": 8300, "total_steps": 15680, "loss": 0.27684831619262695, "lr": 4.540829297525272e-06, "epoch": 1.058673469387755, "percentage": 52.93, "elapsed_time": "1 day, 6:04:48", "remaining_time": "1 day, 2:44:45", "throughput": 4653.33, "total_tokens": 503900680} {"current_steps": 8305, "total_steps": 15680, "loss": 0.24174211025238038, "lr": 4.53584177800027e-06, "epoch": 1.059311224489796, "percentage": 52.97, "elapsed_time": "1 day, 6:05:44", "remaining_time": "1 day, 2:43:32", "throughput": 4653.74, "total_tokens": 504207016} {"current_steps": 8310, "total_steps": 15680, "loss": 0.24687228202819825, "lr": 4.530854724290461e-06, "epoch": 1.0599489795918366, "percentage": 53.0, "elapsed_time": "1 day, 6:06:57", "remaining_time": "1 day, 2:42:33", "throughput": 4653.49, "total_tokens": 504518576} {"current_steps": 8315, "total_steps": 15680, "loss": 0.2555249691009521, "lr": 4.5258681414007005e-06, "epoch": 1.0605867346938775, "percentage": 53.03, "elapsed_time": "1 day, 6:08:05", "remaining_time": "1 day, 2:41:31", "throughput": 4653.28, "total_tokens": 504814448} {"current_steps": 8320, "total_steps": 15680, "loss": 0.24149341583251954, "lr": 4.5208820343353726e-06, "epoch": 1.0612244897959184, "percentage": 53.06, "elapsed_time": "1 day, 6:09:20", "remaining_time": "1 day, 2:40:33", "throughput": 4652.8, "total_tokens": 505109024} {"current_steps": 8325, "total_steps": 15680, "loss": 0.24489209651947022, "lr": 4.515896408098387e-06, "epoch": 1.061862244897959, "percentage": 53.09, "elapsed_time": "1 day, 6:10:32", "remaining_time": "1 day, 2:39:34", "throughput": 4652.38, "total_tokens": 505399152} {"current_steps": 8330, "total_steps": 15680, "loss": 0.27535414695739746, "lr": 4.510911267693164e-06, "epoch": 1.0625, "percentage": 53.12, "elapsed_time": "1 day, 6:11:34", "remaining_time": "1 day, 2:38:27", "throughput": 4652.4, "total_tokens": 505692008} {"current_steps": 8335, "total_steps": 15680, "loss": 0.25455851554870607, "lr": 4.505926618122641e-06, "epoch": 1.063137755102041, "percentage": 53.16, "elapsed_time": "1 day, 6:12:41", "remaining_time": "1 day, 2:37:23", "throughput": 4652.36, "total_tokens": 506000168} {"current_steps": 8340, "total_steps": 15680, "loss": 0.2708827018737793, "lr": 4.5009424643892644e-06, "epoch": 1.0637755102040816, "percentage": 53.19, "elapsed_time": "1 day, 6:13:35", "remaining_time": "1 day, 2:36:07", "throughput": 4652.9, "total_tokens": 506306912} {"current_steps": 8345, "total_steps": 15680, "loss": 0.24709620475769042, "lr": 4.4959588114949785e-06, "epoch": 1.0644132653061225, "percentage": 53.22, "elapsed_time": "1 day, 6:14:31", "remaining_time": "1 day, 2:34:54", "throughput": 4653.19, "total_tokens": 506598448} {"current_steps": 8350, "total_steps": 15680, "loss": 0.24962987899780273, "lr": 4.490975664441227e-06, "epoch": 1.0650510204081634, "percentage": 53.25, "elapsed_time": "1 day, 6:15:33", "remaining_time": "1 day, 2:33:46", "throughput": 4653.35, "total_tokens": 506905000} {"current_steps": 8355, "total_steps": 15680, "loss": 0.2546701431274414, "lr": 4.4859930282289475e-06, "epoch": 1.065688775510204, "percentage": 53.28, "elapsed_time": "1 day, 6:16:28", "remaining_time": "1 day, 2:32:32", "throughput": 4653.9, "total_tokens": 507222320} {"current_steps": 8360, "total_steps": 15680, "loss": 0.28885631561279296, "lr": 4.48101090785856e-06, "epoch": 1.066326530612245, "percentage": 53.32, "elapsed_time": "1 day, 6:17:42", "remaining_time": "1 day, 2:31:34", "throughput": 4653.46, "total_tokens": 507517176} {"current_steps": 8365, "total_steps": 15680, "loss": 0.26137232780456543, "lr": 4.4760293083299736e-06, "epoch": 1.0669642857142858, "percentage": 53.35, "elapsed_time": "1 day, 6:18:48", "remaining_time": "1 day, 2:30:30", "throughput": 4653.26, "total_tokens": 507804944} {"current_steps": 8370, "total_steps": 15680, "loss": 0.2702186584472656, "lr": 4.471048234642572e-06, "epoch": 1.0676020408163265, "percentage": 53.38, "elapsed_time": "1 day, 6:19:48", "remaining_time": "1 day, 2:29:20", "throughput": 4653.48, "total_tokens": 508107408} {"current_steps": 8375, "total_steps": 15680, "loss": 0.26437246799468994, "lr": 4.466067691795208e-06, "epoch": 1.0682397959183674, "percentage": 53.41, "elapsed_time": "1 day, 6:21:01", "remaining_time": "1 day, 2:28:22", "throughput": 4653.18, "total_tokens": 508414640} {"current_steps": 8380, "total_steps": 15680, "loss": 0.2574469566345215, "lr": 4.4610876847862034e-06, "epoch": 1.068877551020408, "percentage": 53.44, "elapsed_time": "1 day, 6:22:15", "remaining_time": "1 day, 2:27:24", "throughput": 4652.82, "total_tokens": 508717400} {"current_steps": 8385, "total_steps": 15680, "loss": 0.27723989486694334, "lr": 4.456108218613346e-06, "epoch": 1.069515306122449, "percentage": 53.48, "elapsed_time": "1 day, 6:23:14", "remaining_time": "1 day, 2:26:14", "throughput": 4653.09, "total_tokens": 509023408} {"current_steps": 8390, "total_steps": 15680, "loss": 0.2590214252471924, "lr": 4.451129298273877e-06, "epoch": 1.0701530612244898, "percentage": 53.51, "elapsed_time": "1 day, 6:24:16", "remaining_time": "1 day, 2:25:05", "throughput": 4653.29, "total_tokens": 509332808} {"current_steps": 8395, "total_steps": 15680, "loss": 0.25503556728363036, "lr": 4.4461509287644885e-06, "epoch": 1.0707908163265305, "percentage": 53.54, "elapsed_time": "1 day, 6:25:20", "remaining_time": "1 day, 2:23:59", "throughput": 4653.39, "total_tokens": 509641560} {"current_steps": 8400, "total_steps": 15680, "loss": 0.23296217918395995, "lr": 4.441173115081327e-06, "epoch": 1.0714285714285714, "percentage": 53.57, "elapsed_time": "1 day, 6:26:25", "remaining_time": "1 day, 2:22:53", "throughput": 4653.38, "total_tokens": 509941488} {"current_steps": 8405, "total_steps": 15680, "loss": 0.27005853652954104, "lr": 4.43619586221997e-06, "epoch": 1.0720663265306123, "percentage": 53.6, "elapsed_time": "1 day, 6:27:22", "remaining_time": "1 day, 2:21:42", "throughput": 4653.61, "total_tokens": 510234680} {"current_steps": 8410, "total_steps": 15680, "loss": 0.23705193996429444, "lr": 4.4312191751754415e-06, "epoch": 1.072704081632653, "percentage": 53.64, "elapsed_time": "1 day, 6:28:35", "remaining_time": "1 day, 2:20:43", "throughput": 4653.27, "total_tokens": 510535432} {"current_steps": 8415, "total_steps": 15680, "loss": 0.2547664403915405, "lr": 4.426243058942196e-06, "epoch": 1.0733418367346939, "percentage": 53.67, "elapsed_time": "1 day, 6:29:34", "remaining_time": "1 day, 2:19:32", "throughput": 4653.44, "total_tokens": 510829424} {"current_steps": 8420, "total_steps": 15680, "loss": 0.2672074556350708, "lr": 4.42126751851411e-06, "epoch": 1.0739795918367347, "percentage": 53.7, "elapsed_time": "1 day, 6:30:41", "remaining_time": "1 day, 2:18:28", "throughput": 4653.38, "total_tokens": 511132368} {"current_steps": 8425, "total_steps": 15680, "loss": 0.269744348526001, "lr": 4.4162925588844895e-06, "epoch": 1.0746173469387754, "percentage": 53.73, "elapsed_time": "1 day, 6:31:46", "remaining_time": "1 day, 2:17:23", "throughput": 4653.29, "total_tokens": 511428392} {"current_steps": 8430, "total_steps": 15680, "loss": 0.25969829559326174, "lr": 4.4113181850460504e-06, "epoch": 1.0752551020408163, "percentage": 53.76, "elapsed_time": "1 day, 6:32:55", "remaining_time": "1 day, 2:16:21", "throughput": 4653.16, "total_tokens": 511735696} {"current_steps": 8435, "total_steps": 15680, "loss": 0.2720786571502686, "lr": 4.406344401990927e-06, "epoch": 1.0758928571428572, "percentage": 53.79, "elapsed_time": "1 day, 6:33:50", "remaining_time": "1 day, 2:15:07", "throughput": 4653.64, "total_tokens": 512041384} {"current_steps": 8440, "total_steps": 15680, "loss": 0.2635928153991699, "lr": 4.401371214710658e-06, "epoch": 1.0765306122448979, "percentage": 53.83, "elapsed_time": "1 day, 6:34:44", "remaining_time": "1 day, 2:13:52", "throughput": 4654.02, "total_tokens": 512335736} {"current_steps": 8445, "total_steps": 15680, "loss": 0.24565181732177735, "lr": 4.396398628196181e-06, "epoch": 1.0771683673469388, "percentage": 53.86, "elapsed_time": "1 day, 6:35:58", "remaining_time": "1 day, 2:12:54", "throughput": 4653.63, "total_tokens": 512636824} {"current_steps": 8450, "total_steps": 15680, "loss": 0.2619929313659668, "lr": 4.391426647437836e-06, "epoch": 1.0778061224489797, "percentage": 53.89, "elapsed_time": "1 day, 6:37:03", "remaining_time": "1 day, 2:11:49", "throughput": 4653.58, "total_tokens": 512931896} {"current_steps": 8455, "total_steps": 15680, "loss": 0.24539623260498047, "lr": 4.386455277425355e-06, "epoch": 1.0784438775510203, "percentage": 53.92, "elapsed_time": "1 day, 6:38:02", "remaining_time": "1 day, 2:10:39", "throughput": 4653.82, "total_tokens": 513237216} {"current_steps": 8460, "total_steps": 15680, "loss": 0.2395007610321045, "lr": 4.381484523147852e-06, "epoch": 1.0790816326530612, "percentage": 53.95, "elapsed_time": "1 day, 6:39:16", "remaining_time": "1 day, 2:09:41", "throughput": 4653.52, "total_tokens": 513545312} {"current_steps": 8465, "total_steps": 15680, "loss": 0.24681005477905274, "lr": 4.376514389593827e-06, "epoch": 1.0797193877551021, "percentage": 53.99, "elapsed_time": "1 day, 6:40:25", "remaining_time": "1 day, 2:08:39", "throughput": 4653.24, "total_tokens": 513836768} {"current_steps": 8470, "total_steps": 15680, "loss": 0.26409809589385985, "lr": 4.3715448817511565e-06, "epoch": 1.0803571428571428, "percentage": 54.02, "elapsed_time": "1 day, 6:41:32", "remaining_time": "1 day, 2:07:35", "throughput": 4653.15, "total_tokens": 514138696} {"current_steps": 8475, "total_steps": 15680, "loss": 0.25276215076446534, "lr": 4.3665760046070885e-06, "epoch": 1.0809948979591837, "percentage": 54.05, "elapsed_time": "1 day, 6:42:42", "remaining_time": "1 day, 2:06:34", "throughput": 4653.02, "total_tokens": 514447760} {"current_steps": 8480, "total_steps": 15680, "loss": 0.24439802169799804, "lr": 4.361607763148236e-06, "epoch": 1.0816326530612246, "percentage": 54.08, "elapsed_time": "1 day, 6:43:46", "remaining_time": "1 day, 2:05:28", "throughput": 4652.99, "total_tokens": 514743056} {"current_steps": 8485, "total_steps": 15680, "loss": 0.2473681688308716, "lr": 4.356640162360582e-06, "epoch": 1.0822704081632653, "percentage": 54.11, "elapsed_time": "1 day, 6:44:57", "remaining_time": "1 day, 2:04:27", "throughput": 4652.73, "total_tokens": 515046088} {"current_steps": 8490, "total_steps": 15680, "loss": 0.25981926918029785, "lr": 4.3516732072294545e-06, "epoch": 1.0829081632653061, "percentage": 54.15, "elapsed_time": "1 day, 6:46:08", "remaining_time": "1 day, 2:03:27", "throughput": 4652.54, "total_tokens": 515354392} {"current_steps": 8495, "total_steps": 15680, "loss": 0.2604411840438843, "lr": 4.346706902739544e-06, "epoch": 1.083545918367347, "percentage": 54.18, "elapsed_time": "1 day, 6:47:06", "remaining_time": "1 day, 2:02:15", "throughput": 4652.82, "total_tokens": 515653976} {"current_steps": 8500, "total_steps": 15680, "loss": 0.2681291580200195, "lr": 4.3417412538748824e-06, "epoch": 1.0841836734693877, "percentage": 54.21, "elapsed_time": "1 day, 6:48:14", "remaining_time": "1 day, 2:01:13", "throughput": 4652.7, "total_tokens": 515960096} {"current_steps": 8505, "total_steps": 15680, "loss": 0.24369583129882813, "lr": 4.336776265618844e-06, "epoch": 1.0848214285714286, "percentage": 54.24, "elapsed_time": "1 day, 6:49:31", "remaining_time": "1 day, 2:00:17", "throughput": 4652.2, "total_tokens": 516259976} {"current_steps": 8510, "total_steps": 15680, "loss": 0.2504972696304321, "lr": 4.331811942954143e-06, "epoch": 1.0854591836734695, "percentage": 54.27, "elapsed_time": "1 day, 6:50:25", "remaining_time": "1 day, 1:59:02", "throughput": 4652.61, "total_tokens": 516557400} {"current_steps": 8515, "total_steps": 15680, "loss": 0.25997779369354246, "lr": 4.3268482908628245e-06, "epoch": 1.0860969387755102, "percentage": 54.3, "elapsed_time": "1 day, 6:51:25", "remaining_time": "1 day, 1:57:53", "throughput": 4652.82, "total_tokens": 516859248} {"current_steps": 8520, "total_steps": 15680, "loss": 0.23948345184326172, "lr": 4.321885314326258e-06, "epoch": 1.086734693877551, "percentage": 54.34, "elapsed_time": "1 day, 6:52:34", "remaining_time": "1 day, 1:56:51", "throughput": 4652.68, "total_tokens": 517168080} {"current_steps": 8525, "total_steps": 15680, "loss": 0.25132384300231936, "lr": 4.316923018325137e-06, "epoch": 1.087372448979592, "percentage": 54.37, "elapsed_time": "1 day, 6:53:41", "remaining_time": "1 day, 1:55:47", "throughput": 4652.54, "total_tokens": 517462696} {"current_steps": 8530, "total_steps": 15680, "loss": 0.2746640682220459, "lr": 4.3119614078394756e-06, "epoch": 1.0880102040816326, "percentage": 54.4, "elapsed_time": "1 day, 6:54:56", "remaining_time": "1 day, 1:54:50", "throughput": 4652.2, "total_tokens": 517771872} {"current_steps": 8535, "total_steps": 15680, "loss": 0.25914363861083983, "lr": 4.3070004878485925e-06, "epoch": 1.0886479591836735, "percentage": 54.43, "elapsed_time": "1 day, 6:55:59", "remaining_time": "1 day, 1:53:43", "throughput": 4652.22, "total_tokens": 518070000} {"current_steps": 8540, "total_steps": 15680, "loss": 0.2593933343887329, "lr": 4.30204026333112e-06, "epoch": 1.0892857142857142, "percentage": 54.46, "elapsed_time": "1 day, 6:57:02", "remaining_time": "1 day, 1:52:36", "throughput": 4652.45, "total_tokens": 518386712} {"current_steps": 8545, "total_steps": 15680, "loss": 0.2581711053848267, "lr": 4.297080739264987e-06, "epoch": 1.089923469387755, "percentage": 54.5, "elapsed_time": "1 day, 6:57:54", "remaining_time": "1 day, 1:51:20", "throughput": 4653.07, "total_tokens": 518698160} {"current_steps": 8550, "total_steps": 15680, "loss": 0.25314912796020506, "lr": 4.292121920627423e-06, "epoch": 1.090561224489796, "percentage": 54.53, "elapsed_time": "1 day, 6:59:04", "remaining_time": "1 day, 1:50:18", "throughput": 4652.82, "total_tokens": 518996176} {"current_steps": 8555, "total_steps": 15680, "loss": 0.25922203063964844, "lr": 4.287163812394952e-06, "epoch": 1.0911989795918366, "percentage": 54.56, "elapsed_time": "1 day, 7:00:18", "remaining_time": "1 day, 1:49:21", "throughput": 4652.45, "total_tokens": 519299072} {"current_steps": 8560, "total_steps": 15680, "loss": 0.2555856227874756, "lr": 4.282206419543379e-06, "epoch": 1.0918367346938775, "percentage": 54.59, "elapsed_time": "1 day, 7:01:35", "remaining_time": "1 day, 1:48:25", "throughput": 4651.87, "total_tokens": 519593872} {"current_steps": 8565, "total_steps": 15680, "loss": 0.2524415493011475, "lr": 4.2772497470477934e-06, "epoch": 1.0924744897959184, "percentage": 54.62, "elapsed_time": "1 day, 7:02:36", "remaining_time": "1 day, 1:47:16", "throughput": 4652.08, "total_tokens": 519899040} {"current_steps": 8570, "total_steps": 15680, "loss": 0.25772848129272463, "lr": 4.272293799882565e-06, "epoch": 1.093112244897959, "percentage": 54.66, "elapsed_time": "1 day, 7:03:42", "remaining_time": "1 day, 1:46:12", "throughput": 4652.04, "total_tokens": 520204488} {"current_steps": 8575, "total_steps": 15680, "loss": 0.26155643463134765, "lr": 4.267338583021331e-06, "epoch": 1.09375, "percentage": 54.69, "elapsed_time": "1 day, 7:04:40", "remaining_time": "1 day, 1:45:00", "throughput": 4652.34, "total_tokens": 520506248} {"current_steps": 8580, "total_steps": 15680, "loss": 0.2655954360961914, "lr": 4.262384101436997e-06, "epoch": 1.094387755102041, "percentage": 54.72, "elapsed_time": "1 day, 7:05:52", "remaining_time": "1 day, 1:44:01", "throughput": 4652.14, "total_tokens": 520817536} {"current_steps": 8585, "total_steps": 15680, "loss": 0.25361220836639403, "lr": 4.257430360101734e-06, "epoch": 1.0950255102040816, "percentage": 54.75, "elapsed_time": "1 day, 7:07:01", "remaining_time": "1 day, 1:42:59", "throughput": 4651.92, "total_tokens": 521116136} {"current_steps": 8590, "total_steps": 15680, "loss": 0.2651734590530396, "lr": 4.252477363986963e-06, "epoch": 1.0956632653061225, "percentage": 54.78, "elapsed_time": "1 day, 7:08:03", "remaining_time": "1 day, 1:41:51", "throughput": 4652.0, "total_tokens": 521413200} {"current_steps": 8595, "total_steps": 15680, "loss": 0.25967419147491455, "lr": 4.247525118063366e-06, "epoch": 1.0963010204081634, "percentage": 54.82, "elapsed_time": "1 day, 7:09:06", "remaining_time": "1 day, 1:40:44", "throughput": 4652.12, "total_tokens": 521719080} {"current_steps": 8600, "total_steps": 15680, "loss": 0.2496013879776001, "lr": 4.242573627300866e-06, "epoch": 1.096938775510204, "percentage": 54.85, "elapsed_time": "1 day, 7:10:11", "remaining_time": "1 day, 1:39:38", "throughput": 4652.17, "total_tokens": 522027776} {"current_steps": 8605, "total_steps": 15680, "loss": 0.23990926742553711, "lr": 4.237622896668628e-06, "epoch": 1.097576530612245, "percentage": 54.88, "elapsed_time": "1 day, 7:11:15", "remaining_time": "1 day, 1:38:32", "throughput": 4652.2, "total_tokens": 522328536} {"current_steps": 8610, "total_steps": 15680, "loss": 0.2499545097351074, "lr": 4.232672931135058e-06, "epoch": 1.0982142857142858, "percentage": 54.91, "elapsed_time": "1 day, 7:12:23", "remaining_time": "1 day, 1:37:29", "throughput": 4651.99, "total_tokens": 522618664} {"current_steps": 8615, "total_steps": 15680, "loss": 0.25888404846191404, "lr": 4.227723735667793e-06, "epoch": 1.0988520408163265, "percentage": 54.94, "elapsed_time": "1 day, 7:13:25", "remaining_time": "1 day, 1:36:21", "throughput": 4652.1, "total_tokens": 522921736} {"current_steps": 8620, "total_steps": 15680, "loss": 0.2819283723831177, "lr": 4.222775315233693e-06, "epoch": 1.0994897959183674, "percentage": 54.97, "elapsed_time": "1 day, 7:14:38", "remaining_time": "1 day, 1:35:22", "throughput": 4651.85, "total_tokens": 523233512} {"current_steps": 8625, "total_steps": 15680, "loss": 0.2621577739715576, "lr": 4.217827674798845e-06, "epoch": 1.100127551020408, "percentage": 55.01, "elapsed_time": "1 day, 7:15:49", "remaining_time": "1 day, 1:34:22", "throughput": 4651.66, "total_tokens": 523541032} {"current_steps": 8630, "total_steps": 15680, "loss": 0.26994221210479735, "lr": 4.2128808193285555e-06, "epoch": 1.100765306122449, "percentage": 55.04, "elapsed_time": "1 day, 7:17:03", "remaining_time": "1 day, 1:33:24", "throughput": 4651.29, "total_tokens": 523846904} {"current_steps": 8635, "total_steps": 15680, "loss": 0.262078070640564, "lr": 4.2079347537873325e-06, "epoch": 1.1014030612244898, "percentage": 55.07, "elapsed_time": "1 day, 7:18:18", "remaining_time": "1 day, 1:32:26", "throughput": 4650.85, "total_tokens": 524142576} {"current_steps": 8640, "total_steps": 15680, "loss": 0.2705439329147339, "lr": 4.2029894831389036e-06, "epoch": 1.1020408163265305, "percentage": 55.1, "elapsed_time": "1 day, 7:19:26", "remaining_time": "1 day, 1:31:23", "throughput": 4650.77, "total_tokens": 524450280} {"current_steps": 8645, "total_steps": 15680, "loss": 0.25299763679504395, "lr": 4.198045012346192e-06, "epoch": 1.1026785714285714, "percentage": 55.13, "elapsed_time": "1 day, 7:20:39", "remaining_time": "1 day, 1:30:24", "throughput": 4650.56, "total_tokens": 524764680} {"current_steps": 8650, "total_steps": 15680, "loss": 0.2784655809402466, "lr": 4.1931013463713165e-06, "epoch": 1.1033163265306123, "percentage": 55.17, "elapsed_time": "1 day, 7:21:41", "remaining_time": "1 day, 1:29:16", "throughput": 4650.61, "total_tokens": 525060152} {"current_steps": 8655, "total_steps": 15680, "loss": 0.23096976280212403, "lr": 4.188158490175596e-06, "epoch": 1.103954081632653, "percentage": 55.2, "elapsed_time": "1 day, 7:22:45", "remaining_time": "1 day, 1:28:10", "throughput": 4650.67, "total_tokens": 525366264} {"current_steps": 8660, "total_steps": 15680, "loss": 0.24602036476135253, "lr": 4.1832164487195295e-06, "epoch": 1.1045918367346939, "percentage": 55.23, "elapsed_time": "1 day, 7:23:52", "remaining_time": "1 day, 1:27:06", "throughput": 4650.71, "total_tokens": 525679368} {"current_steps": 8665, "total_steps": 15680, "loss": 0.2634816408157349, "lr": 4.1782752269627995e-06, "epoch": 1.1052295918367347, "percentage": 55.26, "elapsed_time": "1 day, 7:24:47", "remaining_time": "1 day, 1:25:53", "throughput": 4651.17, "total_tokens": 525989064} {"current_steps": 8670, "total_steps": 15680, "loss": 0.25561840534210206, "lr": 4.17333482986427e-06, "epoch": 1.1058673469387754, "percentage": 55.29, "elapsed_time": "1 day, 7:26:00", "remaining_time": "1 day, 1:24:54", "throughput": 4650.9, "total_tokens": 526300736} {"current_steps": 8675, "total_steps": 15680, "loss": 0.2742323875427246, "lr": 4.16839526238197e-06, "epoch": 1.1065051020408163, "percentage": 55.33, "elapsed_time": "1 day, 7:27:10", "remaining_time": "1 day, 1:23:52", "throughput": 4650.73, "total_tokens": 526603144} {"current_steps": 8680, "total_steps": 15680, "loss": 0.2627676248550415, "lr": 4.1634565294731045e-06, "epoch": 1.1071428571428572, "percentage": 55.36, "elapsed_time": "1 day, 7:28:20", "remaining_time": "1 day, 1:22:51", "throughput": 4650.57, "total_tokens": 526911344} {"current_steps": 8685, "total_steps": 15680, "loss": 0.2641258478164673, "lr": 4.158518636094037e-06, "epoch": 1.1077806122448979, "percentage": 55.39, "elapsed_time": "1 day, 7:29:21", "remaining_time": "1 day, 1:21:42", "throughput": 4650.88, "total_tokens": 527229720} {"current_steps": 8690, "total_steps": 15680, "loss": 0.2487846851348877, "lr": 4.153581587200287e-06, "epoch": 1.1084183673469388, "percentage": 55.42, "elapsed_time": "1 day, 7:30:38", "remaining_time": "1 day, 1:20:47", "throughput": 4650.37, "total_tokens": 527532776} {"current_steps": 8695, "total_steps": 15680, "loss": 0.2532509803771973, "lr": 4.148645387746526e-06, "epoch": 1.1090561224489797, "percentage": 55.45, "elapsed_time": "1 day, 7:31:38", "remaining_time": "1 day, 1:19:36", "throughput": 4650.61, "total_tokens": 527834776} {"current_steps": 8700, "total_steps": 15680, "loss": 0.25780043601989744, "lr": 4.143710042686579e-06, "epoch": 1.1096938775510203, "percentage": 55.48, "elapsed_time": "1 day, 7:32:50", "remaining_time": "1 day, 1:18:37", "throughput": 4650.32, "total_tokens": 528137192} {"current_steps": 8705, "total_steps": 15680, "loss": 0.26498196125030515, "lr": 4.138775556973406e-06, "epoch": 1.1103316326530612, "percentage": 55.52, "elapsed_time": "1 day, 7:34:02", "remaining_time": "1 day, 1:17:37", "throughput": 4650.03, "total_tokens": 528440456} {"current_steps": 8710, "total_steps": 15680, "loss": 0.26532301902770994, "lr": 4.133841935559109e-06, "epoch": 1.1109693877551021, "percentage": 55.55, "elapsed_time": "1 day, 7:35:05", "remaining_time": "1 day, 1:16:30", "throughput": 4650.13, "total_tokens": 528746080} {"current_steps": 8715, "total_steps": 15680, "loss": 0.24462313652038575, "lr": 4.1289091833949235e-06, "epoch": 1.1116071428571428, "percentage": 55.58, "elapsed_time": "1 day, 7:36:00", "remaining_time": "1 day, 1:15:17", "throughput": 4650.35, "total_tokens": 529028272} {"current_steps": 8720, "total_steps": 15680, "loss": 0.26124532222747804, "lr": 4.123977305431209e-06, "epoch": 1.1122448979591837, "percentage": 55.61, "elapsed_time": "1 day, 7:37:08", "remaining_time": "1 day, 1:14:13", "throughput": 4650.22, "total_tokens": 529326792} {"current_steps": 8725, "total_steps": 15680, "loss": 0.26501011848449707, "lr": 4.119046306617449e-06, "epoch": 1.1128826530612246, "percentage": 55.64, "elapsed_time": "1 day, 7:38:13", "remaining_time": "1 day, 1:13:08", "throughput": 4650.17, "total_tokens": 529624760} {"current_steps": 8730, "total_steps": 15680, "loss": 0.28026351928710935, "lr": 4.114116191902248e-06, "epoch": 1.1135204081632653, "percentage": 55.68, "elapsed_time": "1 day, 7:39:24", "remaining_time": "1 day, 1:12:07", "throughput": 4650.01, "total_tokens": 529934352} {"current_steps": 8735, "total_steps": 15680, "loss": 0.276874041557312, "lr": 4.109186966233315e-06, "epoch": 1.1141581632653061, "percentage": 55.71, "elapsed_time": "1 day, 7:40:33", "remaining_time": "1 day, 1:11:05", "throughput": 4649.88, "total_tokens": 530240440} {"current_steps": 8740, "total_steps": 15680, "loss": 0.2529959201812744, "lr": 4.104258634557478e-06, "epoch": 1.114795918367347, "percentage": 55.74, "elapsed_time": "1 day, 7:41:47", "remaining_time": "1 day, 1:10:07", "throughput": 4649.5, "total_tokens": 530544176} {"current_steps": 8745, "total_steps": 15680, "loss": 0.24083590507507324, "lr": 4.09933120182066e-06, "epoch": 1.1154336734693877, "percentage": 55.77, "elapsed_time": "1 day, 7:42:59", "remaining_time": "1 day, 1:09:07", "throughput": 4649.03, "total_tokens": 530825680} {"current_steps": 8750, "total_steps": 15680, "loss": 0.2577672958374023, "lr": 4.094404672967882e-06, "epoch": 1.1160714285714286, "percentage": 55.8, "elapsed_time": "1 day, 7:44:04", "remaining_time": "1 day, 1:08:01", "throughput": 4649.05, "total_tokens": 531129632} {"current_steps": 8755, "total_steps": 15680, "loss": 0.2546741008758545, "lr": 4.089479052943261e-06, "epoch": 1.1167091836734695, "percentage": 55.84, "elapsed_time": "1 day, 7:45:11", "remaining_time": "1 day, 1:06:57", "throughput": 4648.89, "total_tokens": 531421264} {"current_steps": 8760, "total_steps": 15680, "loss": 0.2510077476501465, "lr": 4.084554346690003e-06, "epoch": 1.1173469387755102, "percentage": 55.87, "elapsed_time": "1 day, 7:46:22", "remaining_time": "1 day, 1:05:57", "throughput": 4648.63, "total_tokens": 531722392} {"current_steps": 8765, "total_steps": 15680, "loss": 0.2494870662689209, "lr": 4.079630559150392e-06, "epoch": 1.117984693877551, "percentage": 55.9, "elapsed_time": "1 day, 7:47:38", "remaining_time": "1 day, 1:04:59", "throughput": 4648.27, "total_tokens": 532031576} {"current_steps": 8770, "total_steps": 15680, "loss": 0.2718391418457031, "lr": 4.074707695265792e-06, "epoch": 1.118622448979592, "percentage": 55.93, "elapsed_time": "1 day, 7:48:34", "remaining_time": "1 day, 1:03:47", "throughput": 4648.75, "total_tokens": 532346776} {"current_steps": 8775, "total_steps": 15680, "loss": 0.24614083766937256, "lr": 4.069785759976645e-06, "epoch": 1.1192602040816326, "percentage": 55.96, "elapsed_time": "1 day, 7:49:30", "remaining_time": "1 day, 1:02:34", "throughput": 4649.2, "total_tokens": 532659184} {"current_steps": 8780, "total_steps": 15680, "loss": 0.23855199813842773, "lr": 4.0648647582224504e-06, "epoch": 1.1198979591836735, "percentage": 55.99, "elapsed_time": "1 day, 7:50:43", "remaining_time": "1 day, 1:01:35", "throughput": 4648.87, "total_tokens": 532964288} {"current_steps": 8785, "total_steps": 15680, "loss": 0.24307601451873778, "lr": 4.059944694941783e-06, "epoch": 1.1205357142857142, "percentage": 56.03, "elapsed_time": "1 day, 7:51:51", "remaining_time": "1 day, 1:00:32", "throughput": 4648.67, "total_tokens": 533257496} {"current_steps": 8790, "total_steps": 15680, "loss": 0.2722148895263672, "lr": 4.0550255750722674e-06, "epoch": 1.121173469387755, "percentage": 56.06, "elapsed_time": "1 day, 7:52:58", "remaining_time": "1 day, 0:59:28", "throughput": 4648.71, "total_tokens": 533572624} {"current_steps": 8795, "total_steps": 15680, "loss": 0.25997745990753174, "lr": 4.050107403550582e-06, "epoch": 1.121811224489796, "percentage": 56.09, "elapsed_time": "1 day, 7:54:04", "remaining_time": "1 day, 0:58:24", "throughput": 4648.66, "total_tokens": 533874248} {"current_steps": 8800, "total_steps": 15680, "loss": 0.2595637083053589, "lr": 4.0451901853124596e-06, "epoch": 1.1224489795918366, "percentage": 56.12, "elapsed_time": "1 day, 7:55:09", "remaining_time": "1 day, 0:57:18", "throughput": 4648.55, "total_tokens": 534163736} {"current_steps": 8805, "total_steps": 15680, "loss": 0.24140620231628418, "lr": 4.04027392529267e-06, "epoch": 1.1230867346938775, "percentage": 56.15, "elapsed_time": "1 day, 7:56:17", "remaining_time": "1 day, 0:56:15", "throughput": 4648.38, "total_tokens": 534459272} {"current_steps": 8810, "total_steps": 15680, "loss": 0.26332621574401854, "lr": 4.035358628425022e-06, "epoch": 1.1237244897959184, "percentage": 56.19, "elapsed_time": "1 day, 7:57:07", "remaining_time": "1 day, 0:54:57", "throughput": 4649.09, "total_tokens": 534773128} {"current_steps": 8815, "total_steps": 15680, "loss": 0.25716571807861327, "lr": 4.030444299642363e-06, "epoch": 1.124362244897959, "percentage": 56.22, "elapsed_time": "1 day, 7:58:17", "remaining_time": "1 day, 0:53:56", "throughput": 4648.95, "total_tokens": 535081112} {"current_steps": 8820, "total_steps": 15680, "loss": 0.25978541374206543, "lr": 4.02553094387656e-06, "epoch": 1.125, "percentage": 56.25, "elapsed_time": "1 day, 7:59:27", "remaining_time": "1 day, 0:52:54", "throughput": 4648.66, "total_tokens": 535374072} {"current_steps": 8825, "total_steps": 15680, "loss": 0.2957251787185669, "lr": 4.020618566058514e-06, "epoch": 1.125637755102041, "percentage": 56.28, "elapsed_time": "1 day, 8:00:18", "remaining_time": "1 day, 0:51:38", "throughput": 4649.34, "total_tokens": 535689208} {"current_steps": 8830, "total_steps": 15680, "loss": 0.24315261840820312, "lr": 4.015707171118136e-06, "epoch": 1.1262755102040816, "percentage": 56.31, "elapsed_time": "1 day, 8:01:23", "remaining_time": "1 day, 0:50:32", "throughput": 4649.35, "total_tokens": 535993008} {"current_steps": 8835, "total_steps": 15680, "loss": 0.26010923385620116, "lr": 4.010796763984355e-06, "epoch": 1.1269132653061225, "percentage": 56.35, "elapsed_time": "1 day, 8:02:29", "remaining_time": "1 day, 0:49:27", "throughput": 4649.26, "total_tokens": 536287536} {"current_steps": 8840, "total_steps": 15680, "loss": 0.2572501182556152, "lr": 4.005887349585106e-06, "epoch": 1.1275510204081634, "percentage": 56.38, "elapsed_time": "1 day, 8:03:30", "remaining_time": "1 day, 0:48:19", "throughput": 4649.51, "total_tokens": 536601616} {"current_steps": 8845, "total_steps": 15680, "loss": 0.24611384868621827, "lr": 4.000978932847332e-06, "epoch": 1.128188775510204, "percentage": 56.41, "elapsed_time": "1 day, 8:04:43", "remaining_time": "1 day, 0:47:20", "throughput": 4649.16, "total_tokens": 536903984} {"current_steps": 8850, "total_steps": 15680, "loss": 0.253182053565979, "lr": 3.996071518696969e-06, "epoch": 1.128826530612245, "percentage": 56.44, "elapsed_time": "1 day, 8:05:49", "remaining_time": "1 day, 0:46:15", "throughput": 4649.09, "total_tokens": 537200032} {"current_steps": 8855, "total_steps": 15680, "loss": 0.2547412395477295, "lr": 3.99116511205895e-06, "epoch": 1.1294642857142858, "percentage": 56.47, "elapsed_time": "1 day, 8:06:52", "remaining_time": "1 day, 0:45:08", "throughput": 4649.27, "total_tokens": 537511520} {"current_steps": 8860, "total_steps": 15680, "loss": 0.25578083992004397, "lr": 3.986259717857201e-06, "epoch": 1.1301020408163265, "percentage": 56.51, "elapsed_time": "1 day, 8:07:49", "remaining_time": "1 day, 0:43:56", "throughput": 4649.59, "total_tokens": 537814664} {"current_steps": 8865, "total_steps": 15680, "loss": 0.24348747730255127, "lr": 3.9813553410146225e-06, "epoch": 1.1307397959183674, "percentage": 56.54, "elapsed_time": "1 day, 8:08:52", "remaining_time": "1 day, 0:42:50", "throughput": 4649.64, "total_tokens": 538115864} {"current_steps": 8870, "total_steps": 15680, "loss": 0.25777478218078614, "lr": 3.9764519864531026e-06, "epoch": 1.131377551020408, "percentage": 56.57, "elapsed_time": "1 day, 8:10:06", "remaining_time": "1 day, 0:41:51", "throughput": 4649.27, "total_tokens": 538415760} {"current_steps": 8875, "total_steps": 15680, "loss": 0.2522728681564331, "lr": 3.971549659093499e-06, "epoch": 1.132015306122449, "percentage": 56.6, "elapsed_time": "1 day, 8:11:09", "remaining_time": "1 day, 0:40:44", "throughput": 4649.33, "total_tokens": 538716616} {"current_steps": 8880, "total_steps": 15680, "loss": 0.24546959400177001, "lr": 3.966648363855637e-06, "epoch": 1.1326530612244898, "percentage": 56.63, "elapsed_time": "1 day, 8:12:18", "remaining_time": "1 day, 0:39:42", "throughput": 4649.21, "total_tokens": 539024984} {"current_steps": 8885, "total_steps": 15680, "loss": 0.2723077774047852, "lr": 3.961748105658312e-06, "epoch": 1.1332908163265305, "percentage": 56.66, "elapsed_time": "1 day, 8:13:29", "remaining_time": "1 day, 0:38:40", "throughput": 4648.98, "total_tokens": 539325304} {"current_steps": 8890, "total_steps": 15680, "loss": 0.25560190677642824, "lr": 3.956848889419276e-06, "epoch": 1.1339285714285714, "percentage": 56.7, "elapsed_time": "1 day, 8:14:43", "remaining_time": "1 day, 0:37:42", "throughput": 4648.65, "total_tokens": 539631960} {"current_steps": 8895, "total_steps": 15680, "loss": 0.24716031551361084, "lr": 3.951950720055231e-06, "epoch": 1.1345663265306123, "percentage": 56.73, "elapsed_time": "1 day, 8:15:50", "remaining_time": "1 day, 0:36:37", "throughput": 4648.5, "total_tokens": 539923576} {"current_steps": 8900, "total_steps": 15680, "loss": 0.24239625930786132, "lr": 3.947053602481834e-06, "epoch": 1.135204081632653, "percentage": 56.76, "elapsed_time": "1 day, 8:16:59", "remaining_time": "1 day, 0:35:36", "throughput": 4648.15, "total_tokens": 540207120} {"current_steps": 8905, "total_steps": 15680, "loss": 0.2518806457519531, "lr": 3.9421575416136866e-06, "epoch": 1.1358418367346939, "percentage": 56.79, "elapsed_time": "1 day, 8:18:07", "remaining_time": "1 day, 0:34:32", "throughput": 4648.15, "total_tokens": 540519408} {"current_steps": 8910, "total_steps": 15680, "loss": 0.23644161224365234, "lr": 3.937262542364324e-06, "epoch": 1.1364795918367347, "percentage": 56.82, "elapsed_time": "1 day, 8:19:14", "remaining_time": "1 day, 0:33:28", "throughput": 4648.04, "total_tokens": 540821840} {"current_steps": 8915, "total_steps": 15680, "loss": 0.24362196922302246, "lr": 3.932368609646223e-06, "epoch": 1.1371173469387754, "percentage": 56.86, "elapsed_time": "1 day, 8:20:24", "remaining_time": "1 day, 0:32:26", "throughput": 4647.87, "total_tokens": 541125600} {"current_steps": 8920, "total_steps": 15680, "loss": 0.2587940216064453, "lr": 3.927475748370784e-06, "epoch": 1.1377551020408163, "percentage": 56.89, "elapsed_time": "1 day, 8:21:44", "remaining_time": "1 day, 0:31:32", "throughput": 4647.31, "total_tokens": 541430368} {"current_steps": 8925, "total_steps": 15680, "loss": 0.2494271755218506, "lr": 3.922583963448336e-06, "epoch": 1.1383928571428572, "percentage": 56.92, "elapsed_time": "1 day, 8:22:53", "remaining_time": "1 day, 0:30:30", "throughput": 4647.1, "total_tokens": 541730480} {"current_steps": 8930, "total_steps": 15680, "loss": 0.24280223846435547, "lr": 3.9176932597881286e-06, "epoch": 1.1390306122448979, "percentage": 56.95, "elapsed_time": "1 day, 8:23:58", "remaining_time": "1 day, 0:29:24", "throughput": 4647.19, "total_tokens": 542040136} {"current_steps": 8935, "total_steps": 15680, "loss": 0.2466367721557617, "lr": 3.912803642298323e-06, "epoch": 1.1396683673469388, "percentage": 56.98, "elapsed_time": "1 day, 8:25:01", "remaining_time": "1 day, 0:28:17", "throughput": 4647.28, "total_tokens": 542342080} {"current_steps": 8940, "total_steps": 15680, "loss": 0.2512343883514404, "lr": 3.90791511588599e-06, "epoch": 1.1403061224489797, "percentage": 57.02, "elapsed_time": "1 day, 8:26:18", "remaining_time": "1 day, 0:27:20", "throughput": 4646.87, "total_tokens": 542652920} {"current_steps": 8945, "total_steps": 15680, "loss": 0.23715415000915527, "lr": 3.903027685457112e-06, "epoch": 1.1409438775510203, "percentage": 57.05, "elapsed_time": "1 day, 8:27:21", "remaining_time": "1 day, 0:26:13", "throughput": 4646.99, "total_tokens": 542959840} {"current_steps": 8950, "total_steps": 15680, "loss": 0.26971964836120604, "lr": 3.898141355916563e-06, "epoch": 1.1415816326530612, "percentage": 57.08, "elapsed_time": "1 day, 8:28:28", "remaining_time": "1 day, 0:25:09", "throughput": 4646.87, "total_tokens": 543258480} {"current_steps": 8955, "total_steps": 15680, "loss": 0.24709455966949462, "lr": 3.893256132168117e-06, "epoch": 1.1422193877551021, "percentage": 57.11, "elapsed_time": "1 day, 8:29:39", "remaining_time": "1 day, 0:24:09", "throughput": 4646.67, "total_tokens": 543565848} {"current_steps": 8960, "total_steps": 15680, "loss": 0.27740399837493895, "lr": 3.888372019114438e-06, "epoch": 1.1428571428571428, "percentage": 57.14, "elapsed_time": "1 day, 8:30:53", "remaining_time": "1 day, 0:23:10", "throughput": 4646.36, "total_tokens": 543874712} {"current_steps": 8965, "total_steps": 15680, "loss": 0.24256086349487305, "lr": 3.8834890216570715e-06, "epoch": 1.1434948979591837, "percentage": 57.17, "elapsed_time": "1 day, 8:31:58", "remaining_time": "1 day, 0:22:04", "throughput": 4646.42, "total_tokens": 544181184} {"current_steps": 8970, "total_steps": 15680, "loss": 0.26886234283447263, "lr": 3.878607144696449e-06, "epoch": 1.1441326530612246, "percentage": 57.21, "elapsed_time": "1 day, 8:32:59", "remaining_time": "1 day, 0:20:56", "throughput": 4646.71, "total_tokens": 544499280} {"current_steps": 8975, "total_steps": 15680, "loss": 0.24144067764282226, "lr": 3.873726393131877e-06, "epoch": 1.1447704081632653, "percentage": 57.24, "elapsed_time": "1 day, 8:34:04", "remaining_time": "1 day, 0:19:50", "throughput": 4646.64, "total_tokens": 544791656} {"current_steps": 8980, "total_steps": 15680, "loss": 0.25340542793273924, "lr": 3.868846771861528e-06, "epoch": 1.1454081632653061, "percentage": 57.27, "elapsed_time": "1 day, 8:35:14", "remaining_time": "1 day, 0:18:48", "throughput": 4646.37, "total_tokens": 545087336} {"current_steps": 8985, "total_steps": 15680, "loss": 0.2459954261779785, "lr": 3.86396828578244e-06, "epoch": 1.146045918367347, "percentage": 57.3, "elapsed_time": "1 day, 8:36:21", "remaining_time": "1 day, 0:17:44", "throughput": 4646.34, "total_tokens": 545394440} {"current_steps": 8990, "total_steps": 15680, "loss": 0.26397042274475097, "lr": 3.859090939790521e-06, "epoch": 1.1466836734693877, "percentage": 57.33, "elapsed_time": "1 day, 8:37:30", "remaining_time": "1 day, 0:16:42", "throughput": 4646.14, "total_tokens": 545693688} {"current_steps": 8995, "total_steps": 15680, "loss": 0.25994985103607177, "lr": 3.854214738780523e-06, "epoch": 1.1473214285714286, "percentage": 57.37, "elapsed_time": "1 day, 8:38:36", "remaining_time": "1 day, 0:15:37", "throughput": 4646.15, "total_tokens": 545998160} {"current_steps": 9000, "total_steps": 15680, "loss": 0.26729607582092285, "lr": 3.849339687646055e-06, "epoch": 1.1479591836734695, "percentage": 57.4, "elapsed_time": "1 day, 8:39:51", "remaining_time": "1 day, 0:14:39", "throughput": 4645.88, "total_tokens": 546317448} {"current_steps": 9005, "total_steps": 15680, "loss": 0.23711986541748048, "lr": 3.844465791279575e-06, "epoch": 1.1485969387755102, "percentage": 57.43, "elapsed_time": "1 day, 8:40:58", "remaining_time": "1 day, 0:13:34", "throughput": 4645.68, "total_tokens": 546603024} {"current_steps": 9010, "total_steps": 15680, "loss": 0.25211658477783205, "lr": 3.839593054572374e-06, "epoch": 1.149234693877551, "percentage": 57.46, "elapsed_time": "1 day, 8:42:06", "remaining_time": "1 day, 0:12:31", "throughput": 4645.47, "total_tokens": 546895864} {"current_steps": 9015, "total_steps": 15680, "loss": 0.23781025409698486, "lr": 3.834721482414586e-06, "epoch": 1.149872448979592, "percentage": 57.49, "elapsed_time": "1 day, 8:43:13", "remaining_time": "1 day, 0:11:27", "throughput": 4645.32, "total_tokens": 547189024} {"current_steps": 9020, "total_steps": 15680, "loss": 0.2751111268997192, "lr": 3.829851079695174e-06, "epoch": 1.1505102040816326, "percentage": 57.53, "elapsed_time": "1 day, 8:44:25", "remaining_time": "1 day, 0:10:26", "throughput": 4645.18, "total_tokens": 547503640} {"current_steps": 9025, "total_steps": 15680, "loss": 0.2480980396270752, "lr": 3.824981851301924e-06, "epoch": 1.1511479591836735, "percentage": 57.56, "elapsed_time": "1 day, 8:45:22", "remaining_time": "1 day, 0:09:15", "throughput": 4645.52, "total_tokens": 547811248} {"current_steps": 9030, "total_steps": 15680, "loss": 0.2552891731262207, "lr": 3.820113802121453e-06, "epoch": 1.1517857142857142, "percentage": 57.59, "elapsed_time": "1 day, 8:46:27", "remaining_time": "1 day, 0:08:10", "throughput": 4645.54, "total_tokens": 548116528} {"current_steps": 9035, "total_steps": 15680, "loss": 0.25223641395568847, "lr": 3.815246937039182e-06, "epoch": 1.152423469387755, "percentage": 57.62, "elapsed_time": "1 day, 8:47:32", "remaining_time": "1 day, 0:07:04", "throughput": 4645.61, "total_tokens": 548427008} {"current_steps": 9040, "total_steps": 15680, "loss": 0.2701232433319092, "lr": 3.810381260939354e-06, "epoch": 1.153061224489796, "percentage": 57.65, "elapsed_time": "1 day, 8:48:35", "remaining_time": "1 day, 0:05:57", "throughput": 4645.79, "total_tokens": 548739432} {"current_steps": 9045, "total_steps": 15680, "loss": 0.25761349201202394, "lr": 3.8055167787050134e-06, "epoch": 1.1536989795918366, "percentage": 57.68, "elapsed_time": "1 day, 8:49:31", "remaining_time": "1 day, 0:04:45", "throughput": 4646.09, "total_tokens": 549036680} {"current_steps": 9050, "total_steps": 15680, "loss": 0.296785306930542, "lr": 3.8006534952180062e-06, "epoch": 1.1543367346938775, "percentage": 57.72, "elapsed_time": "1 day, 8:50:33", "remaining_time": "1 day, 0:03:37", "throughput": 4646.32, "total_tokens": 549349696} {"current_steps": 9055, "total_steps": 15680, "loss": 0.26458353996276857, "lr": 3.79579141535898e-06, "epoch": 1.1549744897959184, "percentage": 57.75, "elapsed_time": "1 day, 8:51:40", "remaining_time": "1 day, 0:02:33", "throughput": 4646.31, "total_tokens": 549661760} {"current_steps": 9060, "total_steps": 15680, "loss": 0.2598105907440186, "lr": 3.7909305440073707e-06, "epoch": 1.155612244897959, "percentage": 57.78, "elapsed_time": "1 day, 8:52:42", "remaining_time": "1 day, 0:01:25", "throughput": 4646.48, "total_tokens": 549966736} {"current_steps": 9065, "total_steps": 15680, "loss": 0.2434762239456177, "lr": 3.786070886041401e-06, "epoch": 1.15625, "percentage": 57.81, "elapsed_time": "1 day, 8:54:00", "remaining_time": "1 day, 0:00:29", "throughput": 4645.86, "total_tokens": 550258880} {"current_steps": 9070, "total_steps": 15680, "loss": 0.2483445882797241, "lr": 3.7812124463380766e-06, "epoch": 1.156887755102041, "percentage": 57.84, "elapsed_time": "1 day, 8:55:14", "remaining_time": "23:59:30", "throughput": 4645.6, "total_tokens": 550571984} {"current_steps": 9075, "total_steps": 15680, "loss": 0.25247507095336913, "lr": 3.7763552297731845e-06, "epoch": 1.1575255102040816, "percentage": 57.88, "elapsed_time": "1 day, 8:56:26", "remaining_time": "23:58:29", "throughput": 4645.38, "total_tokens": 550878272} {"current_steps": 9080, "total_steps": 15680, "loss": 0.28102898597717285, "lr": 3.771499241221277e-06, "epoch": 1.1581632653061225, "percentage": 57.91, "elapsed_time": "1 day, 8:57:21", "remaining_time": "23:57:17", "throughput": 4645.83, "total_tokens": 551189928} {"current_steps": 9085, "total_steps": 15680, "loss": 0.25998654365539553, "lr": 3.766644485555679e-06, "epoch": 1.1588010204081634, "percentage": 57.94, "elapsed_time": "1 day, 8:58:33", "remaining_time": "23:56:16", "throughput": 4645.55, "total_tokens": 551490536} {"current_steps": 9090, "total_steps": 15680, "loss": 0.24906582832336427, "lr": 3.7617909676484788e-06, "epoch": 1.159438775510204, "percentage": 57.97, "elapsed_time": "1 day, 8:59:46", "remaining_time": "23:55:16", "throughput": 4645.32, "total_tokens": 551800888} {"current_steps": 9095, "total_steps": 15680, "loss": 0.25821330547332766, "lr": 3.7569386923705173e-06, "epoch": 1.160076530612245, "percentage": 58.0, "elapsed_time": "1 day, 9:00:53", "remaining_time": "23:54:12", "throughput": 4645.31, "total_tokens": 552112808} {"current_steps": 9100, "total_steps": 15680, "loss": 0.23380570411682128, "lr": 3.752087664591394e-06, "epoch": 1.1607142857142858, "percentage": 58.04, "elapsed_time": "1 day, 9:01:42", "remaining_time": "23:52:55", "throughput": 4645.95, "total_tokens": 552415496} {"current_steps": 9105, "total_steps": 15680, "loss": 0.27939319610595703, "lr": 3.7472378891794537e-06, "epoch": 1.1613520408163265, "percentage": 58.07, "elapsed_time": "1 day, 9:02:56", "remaining_time": "23:51:56", "throughput": 4645.57, "total_tokens": 552715160} {"current_steps": 9110, "total_steps": 15680, "loss": 0.2548710107803345, "lr": 3.7423893710017826e-06, "epoch": 1.1619897959183674, "percentage": 58.1, "elapsed_time": "1 day, 9:04:00", "remaining_time": "23:50:50", "throughput": 4645.71, "total_tokens": 553027504} {"current_steps": 9115, "total_steps": 15680, "loss": 0.27686965465545654, "lr": 3.7375421149242102e-06, "epoch": 1.162627551020408, "percentage": 58.13, "elapsed_time": "1 day, 9:05:06", "remaining_time": "23:49:45", "throughput": 4645.58, "total_tokens": 553319712} {"current_steps": 9120, "total_steps": 15680, "loss": 0.27753410339355467, "lr": 3.7326961258112963e-06, "epoch": 1.163265306122449, "percentage": 58.16, "elapsed_time": "1 day, 9:06:06", "remaining_time": "23:48:36", "throughput": 4645.75, "total_tokens": 553618416} {"current_steps": 9125, "total_steps": 15680, "loss": 0.2638828754425049, "lr": 3.7278514085263275e-06, "epoch": 1.1639030612244898, "percentage": 58.2, "elapsed_time": "1 day, 9:07:17", "remaining_time": "23:47:34", "throughput": 4645.53, "total_tokens": 553920520} {"current_steps": 9130, "total_steps": 15680, "loss": 0.2771193742752075, "lr": 3.7230079679313157e-06, "epoch": 1.1645408163265305, "percentage": 58.23, "elapsed_time": "1 day, 9:08:13", "remaining_time": "23:46:23", "throughput": 4645.89, "total_tokens": 554225448} {"current_steps": 9135, "total_steps": 15680, "loss": 0.25243654251098635, "lr": 3.7181658088869954e-06, "epoch": 1.1651785714285714, "percentage": 58.26, "elapsed_time": "1 day, 9:09:21", "remaining_time": "23:45:19", "throughput": 4645.79, "total_tokens": 554527792} {"current_steps": 9140, "total_steps": 15680, "loss": 0.27841687202453613, "lr": 3.7133249362528075e-06, "epoch": 1.1658163265306123, "percentage": 58.29, "elapsed_time": "1 day, 9:10:20", "remaining_time": "23:44:09", "throughput": 4646.0, "total_tokens": 554827168} {"current_steps": 9145, "total_steps": 15680, "loss": 0.23977646827697754, "lr": 3.708485354886906e-06, "epoch": 1.166454081632653, "percentage": 58.32, "elapsed_time": "1 day, 9:11:27", "remaining_time": "23:43:05", "throughput": 4645.91, "total_tokens": 555129232} {"current_steps": 9150, "total_steps": 15680, "loss": 0.25014777183532716, "lr": 3.7036470696461535e-06, "epoch": 1.1670918367346939, "percentage": 58.35, "elapsed_time": "1 day, 9:12:37", "remaining_time": "23:42:03", "throughput": 4645.66, "total_tokens": 555422128} {"current_steps": 9155, "total_steps": 15680, "loss": 0.23124778270721436, "lr": 3.698810085386101e-06, "epoch": 1.1677295918367347, "percentage": 58.39, "elapsed_time": "1 day, 9:13:44", "remaining_time": "23:40:59", "throughput": 4645.48, "total_tokens": 555712664} {"current_steps": 9160, "total_steps": 15680, "loss": 0.23919620513916015, "lr": 3.693974406961004e-06, "epoch": 1.1683673469387754, "percentage": 58.42, "elapsed_time": "1 day, 9:14:54", "remaining_time": "23:39:57", "throughput": 4645.23, "total_tokens": 556008712} {"current_steps": 9165, "total_steps": 15680, "loss": 0.25184340476989747, "lr": 3.689140039223802e-06, "epoch": 1.1690051020408163, "percentage": 58.45, "elapsed_time": "1 day, 9:16:00", "remaining_time": "23:38:52", "throughput": 4645.24, "total_tokens": 556316288} {"current_steps": 9170, "total_steps": 15680, "loss": 0.24816541671752929, "lr": 3.6843069870261196e-06, "epoch": 1.1696428571428572, "percentage": 58.48, "elapsed_time": "1 day, 9:17:03", "remaining_time": "23:37:45", "throughput": 4645.41, "total_tokens": 556629264} {"current_steps": 9175, "total_steps": 15680, "loss": 0.2609705448150635, "lr": 3.6794752552182654e-06, "epoch": 1.1702806122448979, "percentage": 58.51, "elapsed_time": "1 day, 9:18:20", "remaining_time": "23:36:48", "throughput": 4644.95, "total_tokens": 556930672} {"current_steps": 9180, "total_steps": 15680, "loss": 0.2458580732345581, "lr": 3.674644848649217e-06, "epoch": 1.1709183673469388, "percentage": 58.55, "elapsed_time": "1 day, 9:19:21", "remaining_time": "23:35:40", "throughput": 4645.01, "total_tokens": 557224256} {"current_steps": 9185, "total_steps": 15680, "loss": 0.2798786163330078, "lr": 3.669815772166625e-06, "epoch": 1.1715561224489797, "percentage": 58.58, "elapsed_time": "1 day, 9:20:27", "remaining_time": "23:34:35", "throughput": 4645.02, "total_tokens": 557531800} {"current_steps": 9190, "total_steps": 15680, "loss": 0.24728355407714844, "lr": 3.6649880306168073e-06, "epoch": 1.1721938775510203, "percentage": 58.61, "elapsed_time": "1 day, 9:21:34", "remaining_time": "23:33:31", "throughput": 4644.97, "total_tokens": 557835696} {"current_steps": 9195, "total_steps": 15680, "loss": 0.24804656505584716, "lr": 3.6601616288447352e-06, "epoch": 1.1728316326530612, "percentage": 58.64, "elapsed_time": "1 day, 9:22:45", "remaining_time": "23:32:29", "throughput": 4644.79, "total_tokens": 558143680} {"current_steps": 9200, "total_steps": 15680, "loss": 0.23939886093139648, "lr": 3.655336571694044e-06, "epoch": 1.1734693877551021, "percentage": 58.67, "elapsed_time": "1 day, 9:23:48", "remaining_time": "23:31:22", "throughput": 4644.78, "total_tokens": 558435040} {"current_steps": 9205, "total_steps": 15680, "loss": 0.24841651916503907, "lr": 3.6505128640070152e-06, "epoch": 1.1741071428571428, "percentage": 58.71, "elapsed_time": "1 day, 9:24:57", "remaining_time": "23:30:20", "throughput": 4644.7, "total_tokens": 558748312} {"current_steps": 9210, "total_steps": 15680, "loss": 0.2559295654296875, "lr": 3.6456905106245743e-06, "epoch": 1.1747448979591837, "percentage": 58.74, "elapsed_time": "1 day, 9:26:01", "remaining_time": "23:29:13", "throughput": 4644.84, "total_tokens": 559058256} {"current_steps": 9215, "total_steps": 15680, "loss": 0.2709405183792114, "lr": 3.6408695163862895e-06, "epoch": 1.1753826530612246, "percentage": 58.77, "elapsed_time": "1 day, 9:27:10", "remaining_time": "23:28:10", "throughput": 4644.67, "total_tokens": 559360120} {"current_steps": 9220, "total_steps": 15680, "loss": 0.2672729969024658, "lr": 3.6360498861303693e-06, "epoch": 1.1760204081632653, "percentage": 58.8, "elapsed_time": "1 day, 9:28:17", "remaining_time": "23:27:06", "throughput": 4644.61, "total_tokens": 559663176} {"current_steps": 9225, "total_steps": 15680, "loss": 0.26173014640808107, "lr": 3.631231624693645e-06, "epoch": 1.1766581632653061, "percentage": 58.83, "elapsed_time": "1 day, 9:29:17", "remaining_time": "23:25:57", "throughput": 4644.85, "total_tokens": 559969824} {"current_steps": 9230, "total_steps": 15680, "loss": 0.2579504013061523, "lr": 3.6264147369115788e-06, "epoch": 1.177295918367347, "percentage": 58.86, "elapsed_time": "1 day, 9:30:27", "remaining_time": "23:24:55", "throughput": 4644.66, "total_tokens": 560272344} {"current_steps": 9235, "total_steps": 15680, "loss": 0.24934630393981932, "lr": 3.621599227618258e-06, "epoch": 1.1779336734693877, "percentage": 58.9, "elapsed_time": "1 day, 9:31:38", "remaining_time": "23:23:54", "throughput": 4644.35, "total_tokens": 560567064} {"current_steps": 9240, "total_steps": 15680, "loss": 0.2503244161605835, "lr": 3.6167851016463762e-06, "epoch": 1.1785714285714286, "percentage": 58.93, "elapsed_time": "1 day, 9:32:39", "remaining_time": "23:22:45", "throughput": 4644.44, "total_tokens": 560860256} {"current_steps": 9245, "total_steps": 15680, "loss": 0.24509780406951903, "lr": 3.61197236382725e-06, "epoch": 1.1792091836734695, "percentage": 58.96, "elapsed_time": "1 day, 9:33:38", "remaining_time": "23:21:35", "throughput": 4644.76, "total_tokens": 561172000} {"current_steps": 9250, "total_steps": 15680, "loss": 0.26144001483917234, "lr": 3.6071610189907975e-06, "epoch": 1.1798469387755102, "percentage": 58.99, "elapsed_time": "1 day, 9:34:40", "remaining_time": "23:20:28", "throughput": 4644.85, "total_tokens": 561472240} {"current_steps": 9255, "total_steps": 15680, "loss": 0.2761153936386108, "lr": 3.602351071965536e-06, "epoch": 1.180484693877551, "percentage": 59.02, "elapsed_time": "1 day, 9:35:46", "remaining_time": "23:19:23", "throughput": 4644.87, "total_tokens": 561781768} {"current_steps": 9260, "total_steps": 15680, "loss": 0.25878252983093264, "lr": 3.597542527578586e-06, "epoch": 1.181122448979592, "percentage": 59.06, "elapsed_time": "1 day, 9:36:46", "remaining_time": "23:18:14", "throughput": 4645.12, "total_tokens": 562087760} {"current_steps": 9265, "total_steps": 15680, "loss": 0.282159686088562, "lr": 3.5927353906556583e-06, "epoch": 1.1817602040816326, "percentage": 59.09, "elapsed_time": "1 day, 9:37:48", "remaining_time": "23:17:06", "throughput": 4645.3, "total_tokens": 562399704} {"current_steps": 9270, "total_steps": 15680, "loss": 0.23938889503479005, "lr": 3.587929666021048e-06, "epoch": 1.1823979591836735, "percentage": 59.12, "elapsed_time": "1 day, 9:38:57", "remaining_time": "23:16:03", "throughput": 4645.22, "total_tokens": 562710120} {"current_steps": 9275, "total_steps": 15680, "loss": 0.24919326305389405, "lr": 3.5831253584976377e-06, "epoch": 1.1830357142857142, "percentage": 59.15, "elapsed_time": "1 day, 9:40:03", "remaining_time": "23:14:59", "throughput": 4645.14, "total_tokens": 563009640} {"current_steps": 9280, "total_steps": 15680, "loss": 0.25875191688537597, "lr": 3.578322472906882e-06, "epoch": 1.183673469387755, "percentage": 59.18, "elapsed_time": "1 day, 9:41:07", "remaining_time": "23:13:52", "throughput": 4645.22, "total_tokens": 563313456} {"current_steps": 9285, "total_steps": 15680, "loss": 0.2727609872817993, "lr": 3.5735210140688163e-06, "epoch": 1.184311224489796, "percentage": 59.22, "elapsed_time": "1 day, 9:42:14", "remaining_time": "23:12:48", "throughput": 4645.22, "total_tokens": 563624904} {"current_steps": 9290, "total_steps": 15680, "loss": 0.2516184329986572, "lr": 3.568720986802039e-06, "epoch": 1.1849489795918366, "percentage": 59.25, "elapsed_time": "1 day, 9:43:24", "remaining_time": "23:11:46", "throughput": 4644.93, "total_tokens": 563914608} {"current_steps": 9295, "total_steps": 15680, "loss": 0.24294590950012207, "lr": 3.56392239592371e-06, "epoch": 1.1855867346938775, "percentage": 59.28, "elapsed_time": "1 day, 9:44:17", "remaining_time": "23:10:32", "throughput": 4645.48, "total_tokens": 564227864} {"current_steps": 9300, "total_steps": 15680, "loss": 0.23285303115844727, "lr": 3.559125246249552e-06, "epoch": 1.1862244897959184, "percentage": 59.31, "elapsed_time": "1 day, 9:45:23", "remaining_time": "23:09:27", "throughput": 4645.43, "total_tokens": 564530856} {"current_steps": 9305, "total_steps": 15680, "loss": 0.24616332054138185, "lr": 3.554329542593841e-06, "epoch": 1.186862244897959, "percentage": 59.34, "elapsed_time": "1 day, 9:46:30", "remaining_time": "23:08:23", "throughput": 4645.42, "total_tokens": 564840936} {"current_steps": 9310, "total_steps": 15680, "loss": 0.2721709728240967, "lr": 3.549535289769399e-06, "epoch": 1.1875, "percentage": 59.38, "elapsed_time": "1 day, 9:47:26", "remaining_time": "23:07:12", "throughput": 4645.79, "total_tokens": 565145832} {"current_steps": 9315, "total_steps": 15680, "loss": 0.25292162895202636, "lr": 3.544742492587593e-06, "epoch": 1.188137755102041, "percentage": 59.41, "elapsed_time": "1 day, 9:48:38", "remaining_time": "23:06:11", "throughput": 4645.55, "total_tokens": 565450120} {"current_steps": 9320, "total_steps": 15680, "loss": 0.24716696739196778, "lr": 3.5399511558583323e-06, "epoch": 1.1887755102040816, "percentage": 59.44, "elapsed_time": "1 day, 9:49:38", "remaining_time": "23:05:01", "throughput": 4645.84, "total_tokens": 565760960} {"current_steps": 9325, "total_steps": 15680, "loss": 0.27025156021118163, "lr": 3.5351612843900555e-06, "epoch": 1.1894132653061225, "percentage": 59.47, "elapsed_time": "1 day, 9:50:38", "remaining_time": "23:03:52", "throughput": 4645.99, "total_tokens": 566059608} {"current_steps": 9330, "total_steps": 15680, "loss": 0.24979643821716307, "lr": 3.5303728829897336e-06, "epoch": 1.1900510204081634, "percentage": 59.5, "elapsed_time": "1 day, 9:51:47", "remaining_time": "23:02:50", "throughput": 4645.71, "total_tokens": 566349128} {"current_steps": 9335, "total_steps": 15680, "loss": 0.2737593650817871, "lr": 3.5255859564628637e-06, "epoch": 1.190688775510204, "percentage": 59.53, "elapsed_time": "1 day, 9:52:56", "remaining_time": "23:01:47", "throughput": 4645.61, "total_tokens": 566657304} {"current_steps": 9340, "total_steps": 15680, "loss": 0.27191920280456544, "lr": 3.5208005096134567e-06, "epoch": 1.191326530612245, "percentage": 59.57, "elapsed_time": "1 day, 9:54:01", "remaining_time": "23:00:41", "throughput": 4645.65, "total_tokens": 566961464} {"current_steps": 9345, "total_steps": 15680, "loss": 0.281893253326416, "lr": 3.516016547244047e-06, "epoch": 1.1919642857142858, "percentage": 59.6, "elapsed_time": "1 day, 9:55:06", "remaining_time": "22:59:36", "throughput": 4645.73, "total_tokens": 567275376} {"current_steps": 9350, "total_steps": 15680, "loss": 0.23227195739746093, "lr": 3.5112340741556737e-06, "epoch": 1.1926020408163265, "percentage": 59.63, "elapsed_time": "1 day, 9:56:16", "remaining_time": "22:58:34", "throughput": 4645.5, "total_tokens": 567570008} {"current_steps": 9355, "total_steps": 15680, "loss": 0.25134925842285155, "lr": 3.5064530951478822e-06, "epoch": 1.1932397959183674, "percentage": 59.66, "elapsed_time": "1 day, 9:57:19", "remaining_time": "22:57:27", "throughput": 4645.49, "total_tokens": 567862344} {"current_steps": 9360, "total_steps": 15680, "loss": 0.257344913482666, "lr": 3.501673615018717e-06, "epoch": 1.193877551020408, "percentage": 59.69, "elapsed_time": "1 day, 9:58:36", "remaining_time": "22:56:29", "throughput": 4645.04, "total_tokens": 568165880} {"current_steps": 9365, "total_steps": 15680, "loss": 0.2674292802810669, "lr": 3.496895638564724e-06, "epoch": 1.194515306122449, "percentage": 59.73, "elapsed_time": "1 day, 9:59:24", "remaining_time": "22:55:12", "throughput": 4645.79, "total_tokens": 568478840} {"current_steps": 9370, "total_steps": 15680, "loss": 0.26298508644104, "lr": 3.492119170580933e-06, "epoch": 1.1951530612244898, "percentage": 59.76, "elapsed_time": "1 day, 10:00:26", "remaining_time": "22:54:05", "throughput": 4645.98, "total_tokens": 568791504} {"current_steps": 9375, "total_steps": 15680, "loss": 0.23578338623046874, "lr": 3.4873442158608638e-06, "epoch": 1.1957908163265305, "percentage": 59.79, "elapsed_time": "1 day, 10:01:36", "remaining_time": "22:53:03", "throughput": 4645.72, "total_tokens": 569086712} {"current_steps": 9380, "total_steps": 15680, "loss": 0.24221220016479492, "lr": 3.4825707791965213e-06, "epoch": 1.1964285714285714, "percentage": 59.82, "elapsed_time": "1 day, 10:02:48", "remaining_time": "22:52:02", "throughput": 4645.47, "total_tokens": 569390656} {"current_steps": 9385, "total_steps": 15680, "loss": 0.25411770343780515, "lr": 3.477798865378375e-06, "epoch": 1.1970663265306123, "percentage": 59.85, "elapsed_time": "1 day, 10:03:50", "remaining_time": "22:50:54", "throughput": 4645.64, "total_tokens": 569697440} {"current_steps": 9390, "total_steps": 15680, "loss": 0.2513757228851318, "lr": 3.4730284791953793e-06, "epoch": 1.197704081632653, "percentage": 59.89, "elapsed_time": "1 day, 10:05:00", "remaining_time": "22:49:52", "throughput": 4645.59, "total_tokens": 570015832} {"current_steps": 9395, "total_steps": 15680, "loss": 0.2546231746673584, "lr": 3.4682596254349487e-06, "epoch": 1.1983418367346939, "percentage": 59.92, "elapsed_time": "1 day, 10:06:09", "remaining_time": "22:48:49", "throughput": 4645.45, "total_tokens": 570318520} {"current_steps": 9400, "total_steps": 15680, "loss": 0.2677803039550781, "lr": 3.4634923088829586e-06, "epoch": 1.1989795918367347, "percentage": 59.95, "elapsed_time": "1 day, 10:07:16", "remaining_time": "22:47:45", "throughput": 4645.36, "total_tokens": 570618864} {"current_steps": 9405, "total_steps": 15680, "loss": 0.2581784725189209, "lr": 3.4587265343237474e-06, "epoch": 1.1996173469387754, "percentage": 59.98, "elapsed_time": "1 day, 10:08:19", "remaining_time": "22:46:38", "throughput": 4645.49, "total_tokens": 570930248} {"current_steps": 9410, "total_steps": 15680, "loss": 0.26486501693725584, "lr": 3.4539623065401014e-06, "epoch": 1.2002551020408163, "percentage": 60.01, "elapsed_time": "1 day, 10:09:24", "remaining_time": "22:45:32", "throughput": 4645.61, "total_tokens": 571244312} {"current_steps": 9415, "total_steps": 15680, "loss": 0.26423025131225586, "lr": 3.4491996303132553e-06, "epoch": 1.2008928571428572, "percentage": 60.04, "elapsed_time": "1 day, 10:10:29", "remaining_time": "22:44:27", "throughput": 4645.6, "total_tokens": 571546144} {"current_steps": 9420, "total_steps": 15680, "loss": 0.26038737297058107, "lr": 3.444438510422889e-06, "epoch": 1.2015306122448979, "percentage": 60.08, "elapsed_time": "1 day, 10:11:40", "remaining_time": "22:43:25", "throughput": 4645.4, "total_tokens": 571850512} {"current_steps": 9425, "total_steps": 15680, "loss": 0.25277788639068605, "lr": 3.4396789516471152e-06, "epoch": 1.2021683673469388, "percentage": 60.11, "elapsed_time": "1 day, 10:12:52", "remaining_time": "22:42:24", "throughput": 4645.21, "total_tokens": 572162672} {"current_steps": 9430, "total_steps": 15680, "loss": 0.26095411777496336, "lr": 3.4349209587624876e-06, "epoch": 1.2028061224489797, "percentage": 60.14, "elapsed_time": "1 day, 10:13:47", "remaining_time": "22:41:12", "throughput": 4645.69, "total_tokens": 572478112} {"current_steps": 9435, "total_steps": 15680, "loss": 0.2607147216796875, "lr": 3.4301645365439827e-06, "epoch": 1.2034438775510203, "percentage": 60.17, "elapsed_time": "1 day, 10:14:52", "remaining_time": "22:40:06", "throughput": 4645.63, "total_tokens": 572768984} {"current_steps": 9440, "total_steps": 15680, "loss": 0.24343760013580323, "lr": 3.4254096897650026e-06, "epoch": 1.2040816326530612, "percentage": 60.2, "elapsed_time": "1 day, 10:16:01", "remaining_time": "22:39:04", "throughput": 4645.4, "total_tokens": 573065496} {"current_steps": 9445, "total_steps": 15680, "loss": 0.2628458499908447, "lr": 3.4206564231973664e-06, "epoch": 1.2047193877551021, "percentage": 60.24, "elapsed_time": "1 day, 10:17:05", "remaining_time": "22:37:58", "throughput": 4645.49, "total_tokens": 573373352} {"current_steps": 9450, "total_steps": 15680, "loss": 0.2423173427581787, "lr": 3.4159047416113133e-06, "epoch": 1.2053571428571428, "percentage": 60.27, "elapsed_time": "1 day, 10:18:10", "remaining_time": "22:36:52", "throughput": 4645.41, "total_tokens": 573665624} {"current_steps": 9455, "total_steps": 15680, "loss": 0.2351745843887329, "lr": 3.4111546497754834e-06, "epoch": 1.2059948979591837, "percentage": 60.3, "elapsed_time": "1 day, 10:19:18", "remaining_time": "22:35:48", "throughput": 4645.25, "total_tokens": 573958232} {"current_steps": 9460, "total_steps": 15680, "loss": 0.27458600997924804, "lr": 3.406406152456926e-06, "epoch": 1.2066326530612246, "percentage": 60.33, "elapsed_time": "1 day, 10:20:17", "remaining_time": "22:34:39", "throughput": 4645.55, "total_tokens": 574272616} {"current_steps": 9465, "total_steps": 15680, "loss": 0.25125956535339355, "lr": 3.4016592544210937e-06, "epoch": 1.2072704081632653, "percentage": 60.36, "elapsed_time": "1 day, 10:21:19", "remaining_time": "22:33:31", "throughput": 4645.67, "total_tokens": 574572872} {"current_steps": 9470, "total_steps": 15680, "loss": 0.27151367664337156, "lr": 3.3969139604318257e-06, "epoch": 1.2079081632653061, "percentage": 60.4, "elapsed_time": "1 day, 10:22:27", "remaining_time": "22:32:27", "throughput": 4645.68, "total_tokens": 574889856} {"current_steps": 9475, "total_steps": 15680, "loss": 0.266917085647583, "lr": 3.3921702752513576e-06, "epoch": 1.208545918367347, "percentage": 60.43, "elapsed_time": "1 day, 10:23:39", "remaining_time": "22:31:27", "throughput": 4645.43, "total_tokens": 575194832} {"current_steps": 9480, "total_steps": 15680, "loss": 0.261753511428833, "lr": 3.3874282036403106e-06, "epoch": 1.2091836734693877, "percentage": 60.46, "elapsed_time": "1 day, 10:24:40", "remaining_time": "22:30:18", "throughput": 4645.61, "total_tokens": 575499512} {"current_steps": 9485, "total_steps": 15680, "loss": 0.24433953762054444, "lr": 3.3826877503576805e-06, "epoch": 1.2098214285714286, "percentage": 60.49, "elapsed_time": "1 day, 10:25:53", "remaining_time": "22:29:18", "throughput": 4645.2, "total_tokens": 575788032} {"current_steps": 9490, "total_steps": 15680, "loss": 0.2573875427246094, "lr": 3.3779489201608468e-06, "epoch": 1.2104591836734695, "percentage": 60.52, "elapsed_time": "1 day, 10:27:07", "remaining_time": "22:28:19", "throughput": 4644.86, "total_tokens": 576091944} {"current_steps": 9495, "total_steps": 15680, "loss": 0.23786654472351074, "lr": 3.373211717805557e-06, "epoch": 1.2110969387755102, "percentage": 60.55, "elapsed_time": "1 day, 10:28:12", "remaining_time": "22:27:13", "throughput": 4644.75, "total_tokens": 576380232} {"current_steps": 9500, "total_steps": 15680, "loss": 0.2816202640533447, "lr": 3.3684761480459218e-06, "epoch": 1.211734693877551, "percentage": 60.59, "elapsed_time": "1 day, 10:29:18", "remaining_time": "22:26:08", "throughput": 4644.8, "total_tokens": 576690824} {"current_steps": 9505, "total_steps": 15680, "loss": 0.2572930335998535, "lr": 3.363742215634416e-06, "epoch": 1.212372448979592, "percentage": 60.62, "elapsed_time": "1 day, 10:30:09", "remaining_time": "22:24:53", "throughput": 4645.4, "total_tokens": 577004104} {"current_steps": 9510, "total_steps": 15680, "loss": 0.2601757526397705, "lr": 3.3590099253218745e-06, "epoch": 1.2130102040816326, "percentage": 60.65, "elapsed_time": "1 day, 10:31:19", "remaining_time": "22:23:51", "throughput": 4645.26, "total_tokens": 577309832} {"current_steps": 9515, "total_steps": 15680, "loss": 0.26034154891967776, "lr": 3.3542792818574793e-06, "epoch": 1.2136479591836735, "percentage": 60.68, "elapsed_time": "1 day, 10:32:22", "remaining_time": "22:22:44", "throughput": 4645.44, "total_tokens": 577625664} {"current_steps": 9520, "total_steps": 15680, "loss": 0.24712867736816407, "lr": 3.3495502899887624e-06, "epoch": 1.2142857142857142, "percentage": 60.71, "elapsed_time": "1 day, 10:33:21", "remaining_time": "22:21:34", "throughput": 4645.67, "total_tokens": 577925920} {"current_steps": 9525, "total_steps": 15680, "loss": 0.2680546760559082, "lr": 3.344822954461595e-06, "epoch": 1.214923469387755, "percentage": 60.75, "elapsed_time": "1 day, 10:34:10", "remaining_time": "22:20:19", "throughput": 4646.36, "total_tokens": 578241024} {"current_steps": 9530, "total_steps": 15680, "loss": 0.26010828018188475, "lr": 3.34009728002019e-06, "epoch": 1.215561224489796, "percentage": 60.78, "elapsed_time": "1 day, 10:34:56", "remaining_time": "22:19:01", "throughput": 4647.17, "total_tokens": 578558576} {"current_steps": 9535, "total_steps": 15680, "loss": 0.26022019386291506, "lr": 3.3353732714070933e-06, "epoch": 1.2161989795918366, "percentage": 60.81, "elapsed_time": "1 day, 10:36:05", "remaining_time": "22:17:58", "throughput": 4647.03, "total_tokens": 578861152} {"current_steps": 9540, "total_steps": 15680, "loss": 0.26360206604003905, "lr": 3.3306509333631755e-06, "epoch": 1.2168367346938775, "percentage": 60.84, "elapsed_time": "1 day, 10:37:08", "remaining_time": "22:16:51", "throughput": 4647.18, "total_tokens": 579170880} {"current_steps": 9545, "total_steps": 15680, "loss": 0.24070911407470702, "lr": 3.325930270627632e-06, "epoch": 1.2174744897959184, "percentage": 60.87, "elapsed_time": "1 day, 10:38:21", "remaining_time": "22:15:51", "throughput": 4646.78, "total_tokens": 579462640} {"current_steps": 9550, "total_steps": 15680, "loss": 0.2483356475830078, "lr": 3.3212112879379806e-06, "epoch": 1.218112244897959, "percentage": 60.91, "elapsed_time": "1 day, 10:39:24", "remaining_time": "22:14:44", "throughput": 4646.77, "total_tokens": 579752112} {"current_steps": 9555, "total_steps": 15680, "loss": 0.2761533737182617, "lr": 3.3164939900300467e-06, "epoch": 1.21875, "percentage": 60.94, "elapsed_time": "1 day, 10:40:21", "remaining_time": "22:13:33", "throughput": 4647.13, "total_tokens": 580059640} {"current_steps": 9560, "total_steps": 15680, "loss": 0.26920223236083984, "lr": 3.31177838163797e-06, "epoch": 1.219387755102041, "percentage": 60.97, "elapsed_time": "1 day, 10:41:25", "remaining_time": "22:12:27", "throughput": 4647.2, "total_tokens": 580366720} {"current_steps": 9565, "total_steps": 15680, "loss": 0.23745627403259278, "lr": 3.3070644674941938e-06, "epoch": 1.2200255102040816, "percentage": 61.0, "elapsed_time": "1 day, 10:42:32", "remaining_time": "22:11:23", "throughput": 4647.13, "total_tokens": 580669264} {"current_steps": 9570, "total_steps": 15680, "loss": 0.26337151527404784, "lr": 3.302352252329456e-06, "epoch": 1.2206632653061225, "percentage": 61.03, "elapsed_time": "1 day, 10:43:47", "remaining_time": "22:10:24", "throughput": 4646.8, "total_tokens": 580976232} {"current_steps": 9575, "total_steps": 15680, "loss": 0.273178243637085, "lr": 3.2976417408727978e-06, "epoch": 1.2213010204081634, "percentage": 61.07, "elapsed_time": "1 day, 10:44:47", "remaining_time": "22:09:15", "throughput": 4647.1, "total_tokens": 581296456} {"current_steps": 9580, "total_steps": 15680, "loss": 0.261471152305603, "lr": 3.2929329378515466e-06, "epoch": 1.221938775510204, "percentage": 61.1, "elapsed_time": "1 day, 10:45:47", "remaining_time": "22:08:06", "throughput": 4647.43, "total_tokens": 581614240} {"current_steps": 9585, "total_steps": 15680, "loss": 0.26575982570648193, "lr": 3.288225847991312e-06, "epoch": 1.222576530612245, "percentage": 61.13, "elapsed_time": "1 day, 10:47:02", "remaining_time": "22:07:07", "throughput": 4647.01, "total_tokens": 581908472} {"current_steps": 9590, "total_steps": 15680, "loss": 0.24958672523498535, "lr": 3.2835204760159883e-06, "epoch": 1.2232142857142858, "percentage": 61.16, "elapsed_time": "1 day, 10:48:09", "remaining_time": "22:06:03", "throughput": 4646.83, "total_tokens": 582199800} {"current_steps": 9595, "total_steps": 15680, "loss": 0.24088971614837645, "lr": 3.278816826647747e-06, "epoch": 1.2238520408163265, "percentage": 61.19, "elapsed_time": "1 day, 10:49:06", "remaining_time": "22:04:52", "throughput": 4647.09, "total_tokens": 582494648} {"current_steps": 9600, "total_steps": 15680, "loss": 0.27124848365783694, "lr": 3.2741149046070274e-06, "epoch": 1.2244897959183674, "percentage": 61.22, "elapsed_time": "1 day, 10:49:55", "remaining_time": "22:03:37", "throughput": 4647.75, "total_tokens": 582806568} {"current_steps": 9605, "total_steps": 15680, "loss": 0.2765587329864502, "lr": 3.269414714612534e-06, "epoch": 1.225127551020408, "percentage": 61.26, "elapsed_time": "1 day, 10:51:04", "remaining_time": "22:02:34", "throughput": 4647.62, "total_tokens": 583109984} {"current_steps": 9610, "total_steps": 15680, "loss": 0.25553967952728274, "lr": 3.2647162613812435e-06, "epoch": 1.225765306122449, "percentage": 61.29, "elapsed_time": "1 day, 10:52:00", "remaining_time": "22:01:23", "throughput": 4648.0, "total_tokens": 583420288} {"current_steps": 9615, "total_steps": 15680, "loss": 0.2552331447601318, "lr": 3.2600195496283716e-06, "epoch": 1.2264030612244898, "percentage": 61.32, "elapsed_time": "1 day, 10:53:08", "remaining_time": "22:00:19", "throughput": 4647.95, "total_tokens": 583728232} {"current_steps": 9620, "total_steps": 15680, "loss": 0.2471709966659546, "lr": 3.2553245840674037e-06, "epoch": 1.2270408163265305, "percentage": 61.35, "elapsed_time": "1 day, 10:54:18", "remaining_time": "21:59:16", "throughput": 4647.7, "total_tokens": 584022528} {"current_steps": 9625, "total_steps": 15680, "loss": 0.26244239807128905, "lr": 3.2506313694100643e-06, "epoch": 1.2276785714285714, "percentage": 61.38, "elapsed_time": "1 day, 10:55:18", "remaining_time": "21:58:08", "throughput": 4647.89, "total_tokens": 584327616} {"current_steps": 9630, "total_steps": 15680, "loss": 0.2675912618637085, "lr": 3.245939910366319e-06, "epoch": 1.2283163265306123, "percentage": 61.42, "elapsed_time": "1 day, 10:56:12", "remaining_time": "21:56:56", "throughput": 4648.31, "total_tokens": 584631752} {"current_steps": 9635, "total_steps": 15680, "loss": 0.25380563735961914, "lr": 3.2412502116443783e-06, "epoch": 1.228954081632653, "percentage": 61.45, "elapsed_time": "1 day, 10:57:24", "remaining_time": "21:55:54", "throughput": 4648.13, "total_tokens": 584940920} {"current_steps": 9640, "total_steps": 15680, "loss": 0.2619779586791992, "lr": 3.236562277950682e-06, "epoch": 1.2295918367346939, "percentage": 61.48, "elapsed_time": "1 day, 10:58:30", "remaining_time": "21:54:49", "throughput": 4648.04, "total_tokens": 585235728} {"current_steps": 9645, "total_steps": 15680, "loss": 0.2630010604858398, "lr": 3.231876113989897e-06, "epoch": 1.2302295918367347, "percentage": 61.51, "elapsed_time": "1 day, 10:59:35", "remaining_time": "21:53:44", "throughput": 4648.08, "total_tokens": 585544368} {"current_steps": 9650, "total_steps": 15680, "loss": 0.24690713882446289, "lr": 3.227191724464918e-06, "epoch": 1.2308673469387754, "percentage": 61.54, "elapsed_time": "1 day, 11:00:37", "remaining_time": "21:52:37", "throughput": 4648.12, "total_tokens": 585837104} {"current_steps": 9655, "total_steps": 15680, "loss": 0.23948249816894532, "lr": 3.2225091140768537e-06, "epoch": 1.2315051020408163, "percentage": 61.58, "elapsed_time": "1 day, 11:01:44", "remaining_time": "21:51:32", "throughput": 4648.08, "total_tokens": 586144912} {"current_steps": 9660, "total_steps": 15680, "loss": 0.243941068649292, "lr": 3.2178282875250356e-06, "epoch": 1.2321428571428572, "percentage": 61.61, "elapsed_time": "1 day, 11:02:53", "remaining_time": "21:50:29", "throughput": 4648.02, "total_tokens": 586457568} {"current_steps": 9665, "total_steps": 15680, "loss": 0.26530961990356444, "lr": 3.213149249506997e-06, "epoch": 1.2327806122448979, "percentage": 61.64, "elapsed_time": "1 day, 11:04:09", "remaining_time": "21:49:31", "throughput": 4647.69, "total_tokens": 586767512} {"current_steps": 9670, "total_steps": 15680, "loss": 0.2521230697631836, "lr": 3.208472004718479e-06, "epoch": 1.2334183673469388, "percentage": 61.67, "elapsed_time": "1 day, 11:05:06", "remaining_time": "21:48:20", "throughput": 4647.97, "total_tokens": 587068624} {"current_steps": 9675, "total_steps": 15680, "loss": 0.27018778324127196, "lr": 3.2037965578534245e-06, "epoch": 1.2340561224489797, "percentage": 61.7, "elapsed_time": "1 day, 11:06:20", "remaining_time": "21:47:20", "throughput": 4647.73, "total_tokens": 587380544} {"current_steps": 9680, "total_steps": 15680, "loss": 0.24798645973205566, "lr": 3.199122913603972e-06, "epoch": 1.2346938775510203, "percentage": 61.73, "elapsed_time": "1 day, 11:07:29", "remaining_time": "21:46:17", "throughput": 4647.57, "total_tokens": 587682416} {"current_steps": 9685, "total_steps": 15680, "loss": 0.253771448135376, "lr": 3.1944510766604473e-06, "epoch": 1.2353316326530612, "percentage": 61.77, "elapsed_time": "1 day, 11:08:41", "remaining_time": "21:45:16", "throughput": 4647.39, "total_tokens": 587994000} {"current_steps": 9690, "total_steps": 15680, "loss": 0.2575406551361084, "lr": 3.1897810517113657e-06, "epoch": 1.2359693877551021, "percentage": 61.8, "elapsed_time": "1 day, 11:09:29", "remaining_time": "21:44:00", "throughput": 4648.07, "total_tokens": 588303784} {"current_steps": 9695, "total_steps": 15680, "loss": 0.2514672756195068, "lr": 3.1851128434434263e-06, "epoch": 1.2366071428571428, "percentage": 61.83, "elapsed_time": "1 day, 11:10:28", "remaining_time": "21:42:51", "throughput": 4648.29, "total_tokens": 588603984} {"current_steps": 9700, "total_steps": 15680, "loss": 0.26751532554626467, "lr": 3.1804464565414993e-06, "epoch": 1.2372448979591837, "percentage": 61.86, "elapsed_time": "1 day, 11:11:29", "remaining_time": "21:41:43", "throughput": 4648.42, "total_tokens": 588907392} {"current_steps": 9705, "total_steps": 15680, "loss": 0.2393946886062622, "lr": 3.17578189568863e-06, "epoch": 1.2378826530612246, "percentage": 61.89, "elapsed_time": "1 day, 11:12:24", "remaining_time": "21:40:31", "throughput": 4648.72, "total_tokens": 589200744} {"current_steps": 9710, "total_steps": 15680, "loss": 0.256895112991333, "lr": 3.1711191655660327e-06, "epoch": 1.2385204081632653, "percentage": 61.93, "elapsed_time": "1 day, 11:13:35", "remaining_time": "21:39:30", "throughput": 4648.59, "total_tokens": 589514904} {"current_steps": 9715, "total_steps": 15680, "loss": 0.2531773805618286, "lr": 3.1664582708530796e-06, "epoch": 1.2391581632653061, "percentage": 61.96, "elapsed_time": "1 day, 11:14:41", "remaining_time": "21:38:25", "throughput": 4648.46, "total_tokens": 589802968} {"current_steps": 9720, "total_steps": 15680, "loss": 0.2313767671585083, "lr": 3.161799216227307e-06, "epoch": 1.239795918367347, "percentage": 61.99, "elapsed_time": "1 day, 11:15:50", "remaining_time": "21:37:21", "throughput": 4648.28, "total_tokens": 590100256} {"current_steps": 9725, "total_steps": 15680, "loss": 0.256287145614624, "lr": 3.157142006364401e-06, "epoch": 1.2404336734693877, "percentage": 62.02, "elapsed_time": "1 day, 11:16:55", "remaining_time": "21:36:16", "throughput": 4648.24, "total_tokens": 590398160} {"current_steps": 9730, "total_steps": 15680, "loss": 0.25388460159301757, "lr": 3.1524866459381966e-06, "epoch": 1.2410714285714286, "percentage": 62.05, "elapsed_time": "1 day, 11:18:03", "remaining_time": "21:35:12", "throughput": 4648.08, "total_tokens": 590694312} {"current_steps": 9735, "total_steps": 15680, "loss": 0.25645253658294676, "lr": 3.147833139620671e-06, "epoch": 1.2417091836734695, "percentage": 62.09, "elapsed_time": "1 day, 11:19:00", "remaining_time": "21:34:02", "throughput": 4648.37, "total_tokens": 590994960} {"current_steps": 9740, "total_steps": 15680, "loss": 0.26023178100585936, "lr": 3.143181492081947e-06, "epoch": 1.2423469387755102, "percentage": 62.12, "elapsed_time": "1 day, 11:19:48", "remaining_time": "21:32:46", "throughput": 4649.04, "total_tokens": 591304168} {"current_steps": 9745, "total_steps": 15680, "loss": 0.26649203300476076, "lr": 3.1385317079902743e-06, "epoch": 1.242984693877551, "percentage": 62.15, "elapsed_time": "1 day, 11:20:45", "remaining_time": "21:31:36", "throughput": 4649.43, "total_tokens": 591618200} {"current_steps": 9750, "total_steps": 15680, "loss": 0.24660344123840333, "lr": 3.133883792012037e-06, "epoch": 1.243622448979592, "percentage": 62.18, "elapsed_time": "1 day, 11:21:47", "remaining_time": "21:30:29", "throughput": 4649.59, "total_tokens": 591928872} {"current_steps": 9755, "total_steps": 15680, "loss": 0.2687695026397705, "lr": 3.1292377488117466e-06, "epoch": 1.2442602040816326, "percentage": 62.21, "elapsed_time": "1 day, 11:22:44", "remaining_time": "21:29:18", "throughput": 4649.91, "total_tokens": 592234376} {"current_steps": 9760, "total_steps": 15680, "loss": 0.25377483367919923, "lr": 3.124593583052026e-06, "epoch": 1.2448979591836735, "percentage": 62.24, "elapsed_time": "1 day, 11:23:57", "remaining_time": "21:28:18", "throughput": 4649.59, "total_tokens": 592531608} {"current_steps": 9765, "total_steps": 15680, "loss": 0.2609021902084351, "lr": 3.119951299393625e-06, "epoch": 1.2455357142857142, "percentage": 62.28, "elapsed_time": "1 day, 11:24:57", "remaining_time": "21:27:09", "throughput": 4649.7, "total_tokens": 592827608} {"current_steps": 9770, "total_steps": 15680, "loss": 0.26243650913238525, "lr": 3.115310902495396e-06, "epoch": 1.246173469387755, "percentage": 62.31, "elapsed_time": "1 day, 11:26:11", "remaining_time": "21:26:09", "throughput": 4649.44, "total_tokens": 593137488} {"current_steps": 9775, "total_steps": 15680, "loss": 0.273140025138855, "lr": 3.1106723970143016e-06, "epoch": 1.246811224489796, "percentage": 62.34, "elapsed_time": "1 day, 11:27:22", "remaining_time": "21:25:07", "throughput": 4649.33, "total_tokens": 593451248} {"current_steps": 9780, "total_steps": 15680, "loss": 0.24771556854248047, "lr": 3.10603578760541e-06, "epoch": 1.2474489795918366, "percentage": 62.37, "elapsed_time": "1 day, 11:28:33", "remaining_time": "21:24:06", "throughput": 4648.96, "total_tokens": 593735344} {"current_steps": 9785, "total_steps": 15680, "loss": 0.2547657251358032, "lr": 3.101401078921878e-06, "epoch": 1.2480867346938775, "percentage": 62.4, "elapsed_time": "1 day, 11:29:37", "remaining_time": "21:22:59", "throughput": 4649.04, "total_tokens": 594041320} {"current_steps": 9790, "total_steps": 15680, "loss": 0.2581759452819824, "lr": 3.0967682756149607e-06, "epoch": 1.2487244897959184, "percentage": 62.44, "elapsed_time": "1 day, 11:30:49", "remaining_time": "21:21:58", "throughput": 4648.76, "total_tokens": 594341352} {"current_steps": 9795, "total_steps": 15680, "loss": 0.25716280937194824, "lr": 3.0921373823340028e-06, "epoch": 1.249362244897959, "percentage": 62.47, "elapsed_time": "1 day, 11:31:57", "remaining_time": "21:20:54", "throughput": 4648.67, "total_tokens": 594646352} {"current_steps": 9800, "total_steps": 15680, "loss": 0.25070748329162595, "lr": 3.0875084037264237e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "1 day, 11:32:59", "remaining_time": "21:19:47", "throughput": 4648.79, "total_tokens": 594951600} {"current_steps": 9805, "total_steps": 15680, "loss": 0.26685409545898436, "lr": 3.0828813444377304e-06, "epoch": 1.250637755102041, "percentage": 62.53, "elapsed_time": "1 day, 11:34:00", "remaining_time": "21:18:39", "throughput": 4649.03, "total_tokens": 595265464} {"current_steps": 9810, "total_steps": 15680, "loss": 0.24711506366729735, "lr": 3.0782562091114997e-06, "epoch": 1.2512755102040816, "percentage": 62.56, "elapsed_time": "1 day, 11:35:03", "remaining_time": "21:17:33", "throughput": 4649.08, "total_tokens": 595563768} {"current_steps": 9815, "total_steps": 15680, "loss": 0.27412877082824705, "lr": 3.0736330023893774e-06, "epoch": 1.2519132653061225, "percentage": 62.6, "elapsed_time": "1 day, 11:35:50", "remaining_time": "21:16:17", "throughput": 4649.78, "total_tokens": 595873808} {"current_steps": 9820, "total_steps": 15680, "loss": 0.2447650909423828, "lr": 3.0690117289110732e-06, "epoch": 1.2525510204081631, "percentage": 62.63, "elapsed_time": "1 day, 11:36:54", "remaining_time": "21:15:10", "throughput": 4649.77, "total_tokens": 596168104} {"current_steps": 9825, "total_steps": 15680, "loss": 0.27698750495910646, "lr": 3.0643923933143603e-06, "epoch": 1.253188775510204, "percentage": 62.66, "elapsed_time": "1 day, 11:37:54", "remaining_time": "21:14:02", "throughput": 4650.0, "total_tokens": 596477128} {"current_steps": 9830, "total_steps": 15680, "loss": 0.24812660217285157, "lr": 3.059775000235063e-06, "epoch": 1.253826530612245, "percentage": 62.69, "elapsed_time": "1 day, 11:38:54", "remaining_time": "21:12:53", "throughput": 4650.18, "total_tokens": 596775888} {"current_steps": 9835, "total_steps": 15680, "loss": 0.25735490322113036, "lr": 3.0551595543070567e-06, "epoch": 1.2544642857142856, "percentage": 62.72, "elapsed_time": "1 day, 11:39:54", "remaining_time": "21:11:45", "throughput": 4650.39, "total_tokens": 597083000} {"current_steps": 9840, "total_steps": 15680, "loss": 0.25598070621490476, "lr": 3.050546060162267e-06, "epoch": 1.2551020408163265, "percentage": 62.76, "elapsed_time": "1 day, 11:40:58", "remaining_time": "21:10:39", "throughput": 4650.42, "total_tokens": 597384416} {"current_steps": 9845, "total_steps": 15680, "loss": 0.2531641960144043, "lr": 3.045934522430655e-06, "epoch": 1.2557397959183674, "percentage": 62.79, "elapsed_time": "1 day, 11:41:59", "remaining_time": "21:09:31", "throughput": 4650.53, "total_tokens": 597683408} {"current_steps": 9850, "total_steps": 15680, "loss": 0.24352428913116456, "lr": 3.0413249457402206e-06, "epoch": 1.256377551020408, "percentage": 62.82, "elapsed_time": "1 day, 11:42:55", "remaining_time": "21:08:21", "throughput": 4650.79, "total_tokens": 597978680} {"current_steps": 9855, "total_steps": 15680, "loss": 0.2518972396850586, "lr": 3.0367173347169978e-06, "epoch": 1.257015306122449, "percentage": 62.85, "elapsed_time": "1 day, 11:44:04", "remaining_time": "21:07:17", "throughput": 4650.64, "total_tokens": 598278904} {"current_steps": 9860, "total_steps": 15680, "loss": 0.25064496994018554, "lr": 3.0321116939850435e-06, "epoch": 1.2576530612244898, "percentage": 62.88, "elapsed_time": "1 day, 11:45:15", "remaining_time": "21:06:16", "throughput": 4650.47, "total_tokens": 598588448} {"current_steps": 9865, "total_steps": 15680, "loss": 0.26858522891998293, "lr": 3.0275080281664417e-06, "epoch": 1.2582908163265305, "percentage": 62.91, "elapsed_time": "1 day, 11:46:16", "remaining_time": "21:05:08", "throughput": 4650.65, "total_tokens": 598894360} {"current_steps": 9870, "total_steps": 15680, "loss": 0.2568094253540039, "lr": 3.0229063418812932e-06, "epoch": 1.2589285714285714, "percentage": 62.95, "elapsed_time": "1 day, 11:47:29", "remaining_time": "21:04:07", "throughput": 4650.32, "total_tokens": 599191976} {"current_steps": 9875, "total_steps": 15680, "loss": 0.24946315288543702, "lr": 3.0183066397477103e-06, "epoch": 1.2595663265306123, "percentage": 62.98, "elapsed_time": "1 day, 11:48:27", "remaining_time": "21:02:58", "throughput": 4650.61, "total_tokens": 599499472} {"current_steps": 9880, "total_steps": 15680, "loss": 0.2662359237670898, "lr": 3.013708926381814e-06, "epoch": 1.260204081632653, "percentage": 63.01, "elapsed_time": "1 day, 11:49:37", "remaining_time": "21:01:55", "throughput": 4650.46, "total_tokens": 599806944} {"current_steps": 9885, "total_steps": 15680, "loss": 0.2581866502761841, "lr": 3.0091132063977344e-06, "epoch": 1.2608418367346939, "percentage": 63.04, "elapsed_time": "1 day, 11:50:42", "remaining_time": "21:00:50", "throughput": 4650.53, "total_tokens": 600115496} {"current_steps": 9890, "total_steps": 15680, "loss": 0.25688824653625486, "lr": 3.004519484407594e-06, "epoch": 1.2614795918367347, "percentage": 63.07, "elapsed_time": "1 day, 11:51:47", "remaining_time": "20:59:44", "throughput": 4650.61, "total_tokens": 600426616} {"current_steps": 9895, "total_steps": 15680, "loss": 0.25172607898712157, "lr": 2.9999277650215164e-06, "epoch": 1.2621173469387754, "percentage": 63.11, "elapsed_time": "1 day, 11:52:55", "remaining_time": "20:58:40", "throughput": 4650.42, "total_tokens": 600719552} {"current_steps": 9900, "total_steps": 15680, "loss": 0.25584452152252196, "lr": 2.9953380528476105e-06, "epoch": 1.2627551020408163, "percentage": 63.14, "elapsed_time": "1 day, 11:54:08", "remaining_time": "20:57:40", "throughput": 4650.16, "total_tokens": 601024464} {"current_steps": 9905, "total_steps": 15680, "loss": 0.26361684799194335, "lr": 2.9907503524919734e-06, "epoch": 1.2633928571428572, "percentage": 63.17, "elapsed_time": "1 day, 11:55:18", "remaining_time": "20:56:37", "throughput": 4649.97, "total_tokens": 601324424} {"current_steps": 9910, "total_steps": 15680, "loss": 0.26084651947021487, "lr": 2.9861646685586843e-06, "epoch": 1.2640306122448979, "percentage": 63.2, "elapsed_time": "1 day, 11:56:30", "remaining_time": "20:55:36", "throughput": 4649.76, "total_tokens": 601633216} {"current_steps": 9915, "total_steps": 15680, "loss": 0.25563340187072753, "lr": 2.981581005649795e-06, "epoch": 1.2646683673469388, "percentage": 63.23, "elapsed_time": "1 day, 11:57:30", "remaining_time": "20:54:27", "throughput": 4649.99, "total_tokens": 601941432} {"current_steps": 9920, "total_steps": 15680, "loss": 0.2499422550201416, "lr": 2.9769993683653324e-06, "epoch": 1.2653061224489797, "percentage": 63.27, "elapsed_time": "1 day, 11:58:38", "remaining_time": "20:53:24", "throughput": 4649.91, "total_tokens": 602250352} {"current_steps": 9925, "total_steps": 15680, "loss": 0.24319024085998536, "lr": 2.9724197613032917e-06, "epoch": 1.2659438775510203, "percentage": 63.3, "elapsed_time": "1 day, 11:59:39", "remaining_time": "20:52:16", "throughput": 4650.09, "total_tokens": 602558568} {"current_steps": 9930, "total_steps": 15680, "loss": 0.25522913932800295, "lr": 2.9678421890596254e-06, "epoch": 1.2665816326530612, "percentage": 63.33, "elapsed_time": "1 day, 12:00:47", "remaining_time": "20:51:12", "throughput": 4650.05, "total_tokens": 602868024} {"current_steps": 9935, "total_steps": 15680, "loss": 0.26373605728149413, "lr": 2.9632666562282477e-06, "epoch": 1.2672193877551021, "percentage": 63.36, "elapsed_time": "1 day, 12:01:48", "remaining_time": "20:50:05", "throughput": 4650.2, "total_tokens": 603170320} {"current_steps": 9940, "total_steps": 15680, "loss": 0.2531527757644653, "lr": 2.9586931674010265e-06, "epoch": 1.2678571428571428, "percentage": 63.39, "elapsed_time": "1 day, 12:02:54", "remaining_time": "20:49:00", "throughput": 4650.19, "total_tokens": 603477864} {"current_steps": 9945, "total_steps": 15680, "loss": 0.2425062894821167, "lr": 2.9541217271677747e-06, "epoch": 1.2684948979591837, "percentage": 63.42, "elapsed_time": "1 day, 12:03:59", "remaining_time": "20:47:54", "throughput": 4650.27, "total_tokens": 603787784} {"current_steps": 9950, "total_steps": 15680, "loss": 0.2609687089920044, "lr": 2.949552340116254e-06, "epoch": 1.2691326530612246, "percentage": 63.46, "elapsed_time": "1 day, 12:05:15", "remaining_time": "20:46:55", "throughput": 4649.92, "total_tokens": 604096976} {"current_steps": 9955, "total_steps": 15680, "loss": 0.242216157913208, "lr": 2.9449850108321644e-06, "epoch": 1.2697704081632653, "percentage": 63.49, "elapsed_time": "1 day, 12:06:22", "remaining_time": "20:45:51", "throughput": 4649.8, "total_tokens": 604392392} {"current_steps": 9960, "total_steps": 15680, "loss": 0.26979479789733884, "lr": 2.9404197438991377e-06, "epoch": 1.2704081632653061, "percentage": 63.52, "elapsed_time": "1 day, 12:07:28", "remaining_time": "20:44:46", "throughput": 4649.82, "total_tokens": 604699384} {"current_steps": 9965, "total_steps": 15680, "loss": 0.2459017515182495, "lr": 2.935856543898737e-06, "epoch": 1.271045918367347, "percentage": 63.55, "elapsed_time": "1 day, 12:08:31", "remaining_time": "20:43:39", "throughput": 4649.91, "total_tokens": 605005040} {"current_steps": 9970, "total_steps": 15680, "loss": 0.26631999015808105, "lr": 2.9312954154104563e-06, "epoch": 1.2716836734693877, "percentage": 63.58, "elapsed_time": "1 day, 12:09:37", "remaining_time": "20:42:35", "throughput": 4649.85, "total_tokens": 605306128} {"current_steps": 9975, "total_steps": 15680, "loss": 0.2491915225982666, "lr": 2.9267363630117028e-06, "epoch": 1.2723214285714286, "percentage": 63.62, "elapsed_time": "1 day, 12:10:45", "remaining_time": "20:41:31", "throughput": 4649.8, "total_tokens": 605616512} {"current_steps": 9980, "total_steps": 15680, "loss": 0.2490309476852417, "lr": 2.9221793912778053e-06, "epoch": 1.2729591836734695, "percentage": 63.65, "elapsed_time": "1 day, 12:11:44", "remaining_time": "20:40:22", "throughput": 4649.93, "total_tokens": 605908128} {"current_steps": 9985, "total_steps": 15680, "loss": 0.2644538640975952, "lr": 2.9176245047820064e-06, "epoch": 1.2735969387755102, "percentage": 63.68, "elapsed_time": "1 day, 12:12:40", "remaining_time": "20:39:11", "throughput": 4650.21, "total_tokens": 606204472} {"current_steps": 9990, "total_steps": 15680, "loss": 0.2759737730026245, "lr": 2.913071708095446e-06, "epoch": 1.274234693877551, "percentage": 63.71, "elapsed_time": "1 day, 12:13:40", "remaining_time": "20:38:03", "throughput": 4650.42, "total_tokens": 606511672} {"current_steps": 9995, "total_steps": 15680, "loss": 0.25093646049499513, "lr": 2.908521005787177e-06, "epoch": 1.274872448979592, "percentage": 63.74, "elapsed_time": "1 day, 12:14:48", "remaining_time": "20:37:00", "throughput": 4650.26, "total_tokens": 606807536} {"current_steps": 10000, "total_steps": 15680, "loss": 0.26477274894714353, "lr": 2.903972402424151e-06, "epoch": 1.2755102040816326, "percentage": 63.78, "elapsed_time": "1 day, 12:16:03", "remaining_time": "20:36:00", "throughput": 4649.89, "total_tokens": 607106096} {"current_steps": 10005, "total_steps": 15680, "loss": 0.28002426624298093, "lr": 2.899425902571203e-06, "epoch": 1.2761479591836735, "percentage": 63.81, "elapsed_time": "1 day, 12:16:58", "remaining_time": "20:34:48", "throughput": 4650.38, "total_tokens": 607424872} {"current_steps": 10010, "total_steps": 15680, "loss": 0.25679717063903806, "lr": 2.8948815107910653e-06, "epoch": 1.2767857142857144, "percentage": 63.84, "elapsed_time": "1 day, 12:18:04", "remaining_time": "20:33:43", "throughput": 4650.4, "total_tokens": 607733480} {"current_steps": 10015, "total_steps": 15680, "loss": 0.257327938079834, "lr": 2.8903392316443534e-06, "epoch": 1.277423469387755, "percentage": 63.87, "elapsed_time": "1 day, 12:19:16", "remaining_time": "20:32:42", "throughput": 4650.16, "total_tokens": 608038432} {"current_steps": 10020, "total_steps": 15680, "loss": 0.25208125114440916, "lr": 2.885799069689561e-06, "epoch": 1.278061224489796, "percentage": 63.9, "elapsed_time": "1 day, 12:20:13", "remaining_time": "20:31:32", "throughput": 4650.56, "total_tokens": 608354768} {"current_steps": 10025, "total_steps": 15680, "loss": 0.2639681100845337, "lr": 2.8812610294830568e-06, "epoch": 1.2786989795918369, "percentage": 63.93, "elapsed_time": "1 day, 12:21:22", "remaining_time": "20:30:29", "throughput": 4650.31, "total_tokens": 608646632} {"current_steps": 10030, "total_steps": 15680, "loss": 0.25915184020996096, "lr": 2.8767251155790826e-06, "epoch": 1.2793367346938775, "percentage": 63.97, "elapsed_time": "1 day, 12:22:30", "remaining_time": "20:29:25", "throughput": 4650.25, "total_tokens": 608954568} {"current_steps": 10035, "total_steps": 15680, "loss": 0.27418949604034426, "lr": 2.8721913325297434e-06, "epoch": 1.2799744897959184, "percentage": 64.0, "elapsed_time": "1 day, 12:23:29", "remaining_time": "20:28:17", "throughput": 4650.54, "total_tokens": 609265952} {"current_steps": 10040, "total_steps": 15680, "loss": 0.25756547451019285, "lr": 2.8676596848850084e-06, "epoch": 1.280612244897959, "percentage": 64.03, "elapsed_time": "1 day, 12:24:31", "remaining_time": "20:27:09", "throughput": 4650.76, "total_tokens": 609583120} {"current_steps": 10045, "total_steps": 15680, "loss": 0.219584321975708, "lr": 2.8631301771927024e-06, "epoch": 1.28125, "percentage": 64.06, "elapsed_time": "1 day, 12:25:37", "remaining_time": "20:26:05", "throughput": 4650.77, "total_tokens": 609891536} {"current_steps": 10050, "total_steps": 15680, "loss": 0.261248779296875, "lr": 2.858602813998501e-06, "epoch": 1.281887755102041, "percentage": 64.09, "elapsed_time": "1 day, 12:26:49", "remaining_time": "20:25:03", "throughput": 4650.52, "total_tokens": 610191608} {"current_steps": 10055, "total_steps": 15680, "loss": 0.2619506597518921, "lr": 2.8540775998459336e-06, "epoch": 1.2825255102040816, "percentage": 64.13, "elapsed_time": "1 day, 12:27:56", "remaining_time": "20:23:59", "throughput": 4650.44, "total_tokens": 610492744} {"current_steps": 10060, "total_steps": 15680, "loss": 0.2608958721160889, "lr": 2.849554539276361e-06, "epoch": 1.2831632653061225, "percentage": 64.16, "elapsed_time": "1 day, 12:29:10", "remaining_time": "20:22:58", "throughput": 4650.2, "total_tokens": 610807288} {"current_steps": 10065, "total_steps": 15680, "loss": 0.2728137016296387, "lr": 2.845033636828998e-06, "epoch": 1.2838010204081631, "percentage": 64.19, "elapsed_time": "1 day, 12:30:24", "remaining_time": "20:21:58", "throughput": 4649.91, "total_tokens": 611113336} {"current_steps": 10070, "total_steps": 15680, "loss": 0.25149002075195315, "lr": 2.840514897040884e-06, "epoch": 1.284438775510204, "percentage": 64.22, "elapsed_time": "1 day, 12:31:31", "remaining_time": "20:20:53", "throughput": 4649.92, "total_tokens": 611424664} {"current_steps": 10075, "total_steps": 15680, "loss": 0.24344327449798583, "lr": 2.835998324446887e-06, "epoch": 1.285076530612245, "percentage": 64.25, "elapsed_time": "1 day, 12:32:40", "remaining_time": "20:19:50", "throughput": 4649.73, "total_tokens": 611722296} {"current_steps": 10080, "total_steps": 15680, "loss": 0.21739587783813477, "lr": 2.831483923579703e-06, "epoch": 1.2857142857142856, "percentage": 64.29, "elapsed_time": "1 day, 12:33:50", "remaining_time": "20:18:47", "throughput": 4649.45, "total_tokens": 612008712} {"current_steps": 10085, "total_steps": 15680, "loss": 0.2605217456817627, "lr": 2.8269716989698547e-06, "epoch": 1.2863520408163265, "percentage": 64.32, "elapsed_time": "1 day, 12:34:59", "remaining_time": "20:17:45", "throughput": 4649.28, "total_tokens": 612309344} {"current_steps": 10090, "total_steps": 15680, "loss": 0.2618260383605957, "lr": 2.822461655145669e-06, "epoch": 1.2869897959183674, "percentage": 64.35, "elapsed_time": "1 day, 12:36:03", "remaining_time": "20:16:38", "throughput": 4649.31, "total_tokens": 612608216} {"current_steps": 10095, "total_steps": 15680, "loss": 0.24970576763153077, "lr": 2.817953796633289e-06, "epoch": 1.287627551020408, "percentage": 64.38, "elapsed_time": "1 day, 12:37:11", "remaining_time": "20:15:34", "throughput": 4649.19, "total_tokens": 612908504} {"current_steps": 10100, "total_steps": 15680, "loss": 0.2589538335800171, "lr": 2.813448127956672e-06, "epoch": 1.288265306122449, "percentage": 64.41, "elapsed_time": "1 day, 12:38:14", "remaining_time": "20:14:28", "throughput": 4649.2, "total_tokens": 613202592} {"current_steps": 10105, "total_steps": 15680, "loss": 0.2536892890930176, "lr": 2.8089446536375642e-06, "epoch": 1.2889030612244898, "percentage": 64.45, "elapsed_time": "1 day, 12:39:21", "remaining_time": "20:13:24", "throughput": 4649.16, "total_tokens": 613511544} {"current_steps": 10110, "total_steps": 15680, "loss": 0.2439013957977295, "lr": 2.8044433781955196e-06, "epoch": 1.2895408163265305, "percentage": 64.48, "elapsed_time": "1 day, 12:40:24", "remaining_time": "20:12:17", "throughput": 4649.23, "total_tokens": 613812360} {"current_steps": 10115, "total_steps": 15680, "loss": 0.2278393268585205, "lr": 2.7999443061478827e-06, "epoch": 1.2901785714285714, "percentage": 64.51, "elapsed_time": "1 day, 12:41:31", "remaining_time": "20:11:13", "throughput": 4649.1, "total_tokens": 614108216} {"current_steps": 10120, "total_steps": 15680, "loss": 0.2468031167984009, "lr": 2.795447442009786e-06, "epoch": 1.2908163265306123, "percentage": 64.54, "elapsed_time": "1 day, 12:42:36", "remaining_time": "20:10:07", "throughput": 4649.12, "total_tokens": 614409664} {"current_steps": 10125, "total_steps": 15680, "loss": 0.26167936325073243, "lr": 2.7909527902941467e-06, "epoch": 1.291454081632653, "percentage": 64.57, "elapsed_time": "1 day, 12:43:43", "remaining_time": "20:09:03", "throughput": 4649.07, "total_tokens": 614716896} {"current_steps": 10130, "total_steps": 15680, "loss": 0.2604956150054932, "lr": 2.786460355511662e-06, "epoch": 1.2920918367346939, "percentage": 64.6, "elapsed_time": "1 day, 12:44:42", "remaining_time": "20:07:54", "throughput": 4649.23, "total_tokens": 615013432} {"current_steps": 10135, "total_steps": 15680, "loss": 0.2588627338409424, "lr": 2.7819701421708047e-06, "epoch": 1.2927295918367347, "percentage": 64.64, "elapsed_time": "1 day, 12:45:44", "remaining_time": "20:06:47", "throughput": 4649.24, "total_tokens": 615303208} {"current_steps": 10140, "total_steps": 15680, "loss": 0.276265287399292, "lr": 2.7774821547778176e-06, "epoch": 1.2933673469387754, "percentage": 64.67, "elapsed_time": "1 day, 12:46:29", "remaining_time": "20:05:31", "throughput": 4650.13, "total_tokens": 615628832} {"current_steps": 10145, "total_steps": 15680, "loss": 0.25055019855499266, "lr": 2.772996397836704e-06, "epoch": 1.2940051020408163, "percentage": 64.7, "elapsed_time": "1 day, 12:47:28", "remaining_time": "20:04:22", "throughput": 4650.34, "total_tokens": 615931752} {"current_steps": 10150, "total_steps": 15680, "loss": 0.23627872467041017, "lr": 2.768512875849242e-06, "epoch": 1.2946428571428572, "percentage": 64.73, "elapsed_time": "1 day, 12:48:16", "remaining_time": "20:03:07", "throughput": 4651.03, "total_tokens": 616243688} {"current_steps": 10155, "total_steps": 15680, "loss": 0.26852166652679443, "lr": 2.7640315933149568e-06, "epoch": 1.2952806122448979, "percentage": 64.76, "elapsed_time": "1 day, 12:49:24", "remaining_time": "20:02:04", "throughput": 4650.92, "total_tokens": 616547944} {"current_steps": 10160, "total_steps": 15680, "loss": 0.24700803756713868, "lr": 2.7595525547311257e-06, "epoch": 1.2959183673469388, "percentage": 64.8, "elapsed_time": "1 day, 12:50:36", "remaining_time": "20:01:02", "throughput": 4650.63, "total_tokens": 616845272} {"current_steps": 10165, "total_steps": 15680, "loss": 0.26582865715026854, "lr": 2.755075764592777e-06, "epoch": 1.2965561224489797, "percentage": 64.83, "elapsed_time": "1 day, 12:51:41", "remaining_time": "19:59:57", "throughput": 4650.74, "total_tokens": 617160472} {"current_steps": 10170, "total_steps": 15680, "loss": 0.24859161376953126, "lr": 2.750601227392687e-06, "epoch": 1.2971938775510203, "percentage": 64.86, "elapsed_time": "1 day, 12:52:51", "remaining_time": "19:58:53", "throughput": 4650.53, "total_tokens": 617456352} {"current_steps": 10175, "total_steps": 15680, "loss": 0.2627084732055664, "lr": 2.7461289476213617e-06, "epoch": 1.2978316326530612, "percentage": 64.89, "elapsed_time": "1 day, 12:53:49", "remaining_time": "19:57:45", "throughput": 4650.8, "total_tokens": 617764112} {"current_steps": 10180, "total_steps": 15680, "loss": 0.24822802543640138, "lr": 2.741658929767045e-06, "epoch": 1.2984693877551021, "percentage": 64.92, "elapsed_time": "1 day, 12:54:47", "remaining_time": "19:56:35", "throughput": 4651.11, "total_tokens": 618072856} {"current_steps": 10185, "total_steps": 15680, "loss": 0.23618090152740479, "lr": 2.7371911783157178e-06, "epoch": 1.2991071428571428, "percentage": 64.96, "elapsed_time": "1 day, 12:55:47", "remaining_time": "19:55:27", "throughput": 4651.21, "total_tokens": 618365920} {"current_steps": 10190, "total_steps": 15680, "loss": 0.261117959022522, "lr": 2.7327256977510764e-06, "epoch": 1.2997448979591837, "percentage": 64.99, "elapsed_time": "1 day, 12:56:42", "remaining_time": "19:54:16", "throughput": 4651.65, "total_tokens": 618681128} {"current_steps": 10195, "total_steps": 15680, "loss": 0.2443925380706787, "lr": 2.7282624925545432e-06, "epoch": 1.3003826530612246, "percentage": 65.02, "elapsed_time": "1 day, 12:57:29", "remaining_time": "19:53:02", "throughput": 4652.3, "total_tokens": 618987336} {"current_steps": 10200, "total_steps": 15680, "loss": 0.2537305593490601, "lr": 2.723801567205256e-06, "epoch": 1.3010204081632653, "percentage": 65.05, "elapsed_time": "1 day, 12:58:41", "remaining_time": "19:52:00", "throughput": 4652.1, "total_tokens": 619294688} {"current_steps": 10205, "total_steps": 15680, "loss": 0.2404731035232544, "lr": 2.7193429261800657e-06, "epoch": 1.3016581632653061, "percentage": 65.08, "elapsed_time": "1 day, 12:59:45", "remaining_time": "19:50:54", "throughput": 4652.15, "total_tokens": 619599992} {"current_steps": 10210, "total_steps": 15680, "loss": 0.2664501667022705, "lr": 2.7148865739535303e-06, "epoch": 1.302295918367347, "percentage": 65.11, "elapsed_time": "1 day, 13:00:42", "remaining_time": "19:49:44", "throughput": 4652.46, "total_tokens": 619904240} {"current_steps": 10215, "total_steps": 15680, "loss": 0.27101132869720457, "lr": 2.710432514997909e-06, "epoch": 1.3029336734693877, "percentage": 65.15, "elapsed_time": "1 day, 13:01:45", "remaining_time": "19:48:37", "throughput": 4652.62, "total_tokens": 620218168} {"current_steps": 10220, "total_steps": 15680, "loss": 0.2491471290588379, "lr": 2.7059807537831624e-06, "epoch": 1.3035714285714286, "percentage": 65.18, "elapsed_time": "1 day, 13:02:48", "remaining_time": "19:47:31", "throughput": 4652.74, "total_tokens": 620530952} {"current_steps": 10225, "total_steps": 15680, "loss": 0.25763468742370604, "lr": 2.7015312947769436e-06, "epoch": 1.3042091836734695, "percentage": 65.21, "elapsed_time": "1 day, 13:03:58", "remaining_time": "19:46:28", "throughput": 4652.57, "total_tokens": 620831664} {"current_steps": 10230, "total_steps": 15680, "loss": 0.26262674331665037, "lr": 2.6970841424445947e-06, "epoch": 1.3048469387755102, "percentage": 65.24, "elapsed_time": "1 day, 13:05:05", "remaining_time": "19:45:24", "throughput": 4652.42, "total_tokens": 621126216} {"current_steps": 10235, "total_steps": 15680, "loss": 0.2711535692214966, "lr": 2.692639301249144e-06, "epoch": 1.305484693877551, "percentage": 65.27, "elapsed_time": "1 day, 13:06:12", "remaining_time": "19:44:20", "throughput": 4652.4, "total_tokens": 621431064} {"current_steps": 10240, "total_steps": 15680, "loss": 0.24485445022583008, "lr": 2.6881967756513004e-06, "epoch": 1.306122448979592, "percentage": 65.31, "elapsed_time": "1 day, 13:06:59", "remaining_time": "19:43:05", "throughput": 4653.14, "total_tokens": 621748664} {"current_steps": 10245, "total_steps": 15680, "loss": 0.26869773864746094, "lr": 2.6837565701094505e-06, "epoch": 1.3067602040816326, "percentage": 65.34, "elapsed_time": "1 day, 13:08:10", "remaining_time": "19:42:03", "throughput": 4652.9, "total_tokens": 622049712} {"current_steps": 10250, "total_steps": 15680, "loss": 0.2626228094100952, "lr": 2.679318689079645e-06, "epoch": 1.3073979591836735, "percentage": 65.37, "elapsed_time": "1 day, 13:09:22", "remaining_time": "19:41:01", "throughput": 4652.73, "total_tokens": 622359040} {"current_steps": 10255, "total_steps": 15680, "loss": 0.24830842018127441, "lr": 2.6748831370156148e-06, "epoch": 1.3080357142857144, "percentage": 65.4, "elapsed_time": "1 day, 13:10:27", "remaining_time": "19:39:56", "throughput": 4652.67, "total_tokens": 622654288} {"current_steps": 10260, "total_steps": 15680, "loss": 0.24921224117279053, "lr": 2.6704499183687404e-06, "epoch": 1.308673469387755, "percentage": 65.43, "elapsed_time": "1 day, 13:11:31", "remaining_time": "19:38:50", "throughput": 4652.73, "total_tokens": 622960992} {"current_steps": 10265, "total_steps": 15680, "loss": 0.24191765785217284, "lr": 2.6660190375880656e-06, "epoch": 1.309311224489796, "percentage": 65.47, "elapsed_time": "1 day, 13:12:43", "remaining_time": "19:37:48", "throughput": 4652.54, "total_tokens": 623271960} {"current_steps": 10270, "total_steps": 15680, "loss": 0.2493054151535034, "lr": 2.661590499120296e-06, "epoch": 1.3099489795918369, "percentage": 65.5, "elapsed_time": "1 day, 13:13:39", "remaining_time": "19:36:38", "throughput": 4652.9, "total_tokens": 623578472} {"current_steps": 10275, "total_steps": 15680, "loss": 0.2380746841430664, "lr": 2.657164307409773e-06, "epoch": 1.3105867346938775, "percentage": 65.53, "elapsed_time": "1 day, 13:14:38", "remaining_time": "19:35:30", "throughput": 4653.06, "total_tokens": 623877328} {"current_steps": 10280, "total_steps": 15680, "loss": 0.24416801929473878, "lr": 2.6527404668984907e-06, "epoch": 1.3112244897959184, "percentage": 65.56, "elapsed_time": "1 day, 13:15:46", "remaining_time": "19:34:25", "throughput": 4652.91, "total_tokens": 624169576} {"current_steps": 10285, "total_steps": 15680, "loss": 0.23076577186584474, "lr": 2.648318982026082e-06, "epoch": 1.311862244897959, "percentage": 65.59, "elapsed_time": "1 day, 13:16:38", "remaining_time": "19:33:14", "throughput": 4653.32, "total_tokens": 624471232} {"current_steps": 10290, "total_steps": 15680, "loss": 0.25791611671447756, "lr": 2.6438998572298157e-06, "epoch": 1.3125, "percentage": 65.62, "elapsed_time": "1 day, 13:17:48", "remaining_time": "19:32:11", "throughput": 4653.1, "total_tokens": 624766680} {"current_steps": 10295, "total_steps": 15680, "loss": 0.2841819763183594, "lr": 2.639483096944593e-06, "epoch": 1.313137755102041, "percentage": 65.66, "elapsed_time": "1 day, 13:18:45", "remaining_time": "19:31:01", "throughput": 4653.38, "total_tokens": 625069280} {"current_steps": 10300, "total_steps": 15680, "loss": 0.25959005355834963, "lr": 2.63506870560294e-06, "epoch": 1.3137755102040816, "percentage": 65.69, "elapsed_time": "1 day, 13:19:48", "remaining_time": "19:29:55", "throughput": 4653.55, "total_tokens": 625385304} {"current_steps": 10305, "total_steps": 15680, "loss": 0.28363423347473143, "lr": 2.6306566876350072e-06, "epoch": 1.3144132653061225, "percentage": 65.72, "elapsed_time": "1 day, 13:20:56", "remaining_time": "19:28:51", "throughput": 4653.52, "total_tokens": 625697000} {"current_steps": 10310, "total_steps": 15680, "loss": 0.2525624752044678, "lr": 2.626247047468563e-06, "epoch": 1.3150510204081631, "percentage": 65.75, "elapsed_time": "1 day, 13:21:58", "remaining_time": "19:27:44", "throughput": 4653.51, "total_tokens": 625983968} {"current_steps": 10315, "total_steps": 15680, "loss": 0.25787949562072754, "lr": 2.6218397895289893e-06, "epoch": 1.315688775510204, "percentage": 65.78, "elapsed_time": "1 day, 13:23:06", "remaining_time": "19:26:40", "throughput": 4653.35, "total_tokens": 626278856} {"current_steps": 10320, "total_steps": 15680, "loss": 0.2836592197418213, "lr": 2.617434918239278e-06, "epoch": 1.316326530612245, "percentage": 65.82, "elapsed_time": "1 day, 13:24:12", "remaining_time": "19:25:35", "throughput": 4653.44, "total_tokens": 626594600} {"current_steps": 10325, "total_steps": 15680, "loss": 0.27531752586364744, "lr": 2.6130324380200234e-06, "epoch": 1.3169642857142856, "percentage": 65.85, "elapsed_time": "1 day, 13:25:09", "remaining_time": "19:24:26", "throughput": 4653.77, "total_tokens": 626907120} {"current_steps": 10330, "total_steps": 15680, "loss": 0.2745412826538086, "lr": 2.6086323532894225e-06, "epoch": 1.3176020408163265, "percentage": 65.88, "elapsed_time": "1 day, 13:26:11", "remaining_time": "19:23:19", "throughput": 4653.9, "total_tokens": 627215384} {"current_steps": 10335, "total_steps": 15680, "loss": 0.2636935949325562, "lr": 2.604234668463268e-06, "epoch": 1.3182397959183674, "percentage": 65.91, "elapsed_time": "1 day, 13:27:28", "remaining_time": "19:22:20", "throughput": 4653.55, "total_tokens": 627522696} {"current_steps": 10340, "total_steps": 15680, "loss": 0.24675984382629396, "lr": 2.5998393879549444e-06, "epoch": 1.318877551020408, "percentage": 65.94, "elapsed_time": "1 day, 13:28:31", "remaining_time": "19:21:13", "throughput": 4653.6, "total_tokens": 627822656} {"current_steps": 10345, "total_steps": 15680, "loss": 0.2533129692077637, "lr": 2.5954465161754226e-06, "epoch": 1.319515306122449, "percentage": 65.98, "elapsed_time": "1 day, 13:29:34", "remaining_time": "19:20:07", "throughput": 4653.76, "total_tokens": 628140568} {"current_steps": 10350, "total_steps": 15680, "loss": 0.2645681381225586, "lr": 2.5910560575332524e-06, "epoch": 1.3201530612244898, "percentage": 66.01, "elapsed_time": "1 day, 13:30:37", "remaining_time": "19:19:01", "throughput": 4653.87, "total_tokens": 628449208} {"current_steps": 10355, "total_steps": 15680, "loss": 0.26526970863342286, "lr": 2.5866680164345704e-06, "epoch": 1.3207908163265305, "percentage": 66.04, "elapsed_time": "1 day, 13:31:34", "remaining_time": "19:17:51", "throughput": 4654.17, "total_tokens": 628754088} {"current_steps": 10360, "total_steps": 15680, "loss": 0.2514237403869629, "lr": 2.5822823972830825e-06, "epoch": 1.3214285714285714, "percentage": 66.07, "elapsed_time": "1 day, 13:32:35", "remaining_time": "19:16:43", "throughput": 4654.42, "total_tokens": 629068856} {"current_steps": 10365, "total_steps": 15680, "loss": 0.26770195960998533, "lr": 2.5778992044800597e-06, "epoch": 1.3220663265306123, "percentage": 66.1, "elapsed_time": "1 day, 13:33:32", "remaining_time": "19:15:34", "throughput": 4654.64, "total_tokens": 629366976} {"current_steps": 10370, "total_steps": 15680, "loss": 0.24228177070617676, "lr": 2.573518442424343e-06, "epoch": 1.322704081632653, "percentage": 66.14, "elapsed_time": "1 day, 13:34:36", "remaining_time": "19:14:28", "throughput": 4654.68, "total_tokens": 629667240} {"current_steps": 10375, "total_steps": 15680, "loss": 0.2634902000427246, "lr": 2.569140115512338e-06, "epoch": 1.3233418367346939, "percentage": 66.17, "elapsed_time": "1 day, 13:35:48", "remaining_time": "19:13:27", "throughput": 4654.39, "total_tokens": 629965416} {"current_steps": 10380, "total_steps": 15680, "loss": 0.24268980026245118, "lr": 2.564764228137996e-06, "epoch": 1.3239795918367347, "percentage": 66.2, "elapsed_time": "1 day, 13:36:58", "remaining_time": "19:12:24", "throughput": 4654.28, "total_tokens": 630276384} {"current_steps": 10385, "total_steps": 15680, "loss": 0.23833558559417725, "lr": 2.5603907846928277e-06, "epoch": 1.3246173469387754, "percentage": 66.23, "elapsed_time": "1 day, 13:38:06", "remaining_time": "19:11:20", "throughput": 4654.2, "total_tokens": 630580696} {"current_steps": 10390, "total_steps": 15680, "loss": 0.2554591655731201, "lr": 2.556019789565889e-06, "epoch": 1.3252551020408163, "percentage": 66.26, "elapsed_time": "1 day, 13:39:18", "remaining_time": "19:10:18", "throughput": 4653.95, "total_tokens": 630884048} {"current_steps": 10395, "total_steps": 15680, "loss": 0.2595228910446167, "lr": 2.5516512471437783e-06, "epoch": 1.3258928571428572, "percentage": 66.29, "elapsed_time": "1 day, 13:40:30", "remaining_time": "19:09:16", "throughput": 4653.72, "total_tokens": 631185680} {"current_steps": 10400, "total_steps": 15680, "loss": 0.24489250183105468, "lr": 2.547285161810634e-06, "epoch": 1.3265306122448979, "percentage": 66.33, "elapsed_time": "1 day, 13:41:33", "remaining_time": "19:08:10", "throughput": 4653.83, "total_tokens": 631496624} {"current_steps": 10405, "total_steps": 15680, "loss": 0.23495521545410156, "lr": 2.5429215379481267e-06, "epoch": 1.3271683673469388, "percentage": 66.36, "elapsed_time": "1 day, 13:42:31", "remaining_time": "19:07:01", "throughput": 4653.99, "total_tokens": 631786144} {"current_steps": 10410, "total_steps": 15680, "loss": 0.25196335315704343, "lr": 2.5385603799354574e-06, "epoch": 1.3278061224489797, "percentage": 66.39, "elapsed_time": "1 day, 13:43:46", "remaining_time": "19:06:01", "throughput": 4653.69, "total_tokens": 632093448} {"current_steps": 10415, "total_steps": 15680, "loss": 0.2630856275558472, "lr": 2.534201692149354e-06, "epoch": 1.3284438775510203, "percentage": 66.42, "elapsed_time": "1 day, 13:44:42", "remaining_time": "19:04:51", "throughput": 4654.01, "total_tokens": 632396136} {"current_steps": 10420, "total_steps": 15680, "loss": 0.2595140218734741, "lr": 2.5298454789640636e-06, "epoch": 1.3290816326530612, "percentage": 66.45, "elapsed_time": "1 day, 13:45:41", "remaining_time": "19:03:43", "throughput": 4654.2, "total_tokens": 632701096} {"current_steps": 10425, "total_steps": 15680, "loss": 0.24976706504821777, "lr": 2.5254917447513503e-06, "epoch": 1.3297193877551021, "percentage": 66.49, "elapsed_time": "1 day, 13:46:55", "remaining_time": "19:02:42", "throughput": 4653.89, "total_tokens": 632999184} {"current_steps": 10430, "total_steps": 15680, "loss": 0.25724124908447266, "lr": 2.5211404938804917e-06, "epoch": 1.3303571428571428, "percentage": 66.52, "elapsed_time": "1 day, 13:48:05", "remaining_time": "19:01:39", "throughput": 4653.64, "total_tokens": 633291624} {"current_steps": 10435, "total_steps": 15680, "loss": 0.24438064098358153, "lr": 2.5167917307182675e-06, "epoch": 1.3309948979591837, "percentage": 66.55, "elapsed_time": "1 day, 13:49:16", "remaining_time": "19:00:37", "throughput": 4653.49, "total_tokens": 633604200} {"current_steps": 10440, "total_steps": 15680, "loss": 0.2546777009963989, "lr": 2.5124454596289704e-06, "epoch": 1.3316326530612246, "percentage": 66.58, "elapsed_time": "1 day, 13:50:18", "remaining_time": "18:59:30", "throughput": 4653.6, "total_tokens": 633907848} {"current_steps": 10445, "total_steps": 15680, "loss": 0.2731082677841187, "lr": 2.508101684974387e-06, "epoch": 1.3322704081632653, "percentage": 66.61, "elapsed_time": "1 day, 13:51:17", "remaining_time": "18:58:21", "throughput": 4653.84, "total_tokens": 634214488} {"current_steps": 10450, "total_steps": 15680, "loss": 0.25175440311431885, "lr": 2.5037604111137935e-06, "epoch": 1.3329081632653061, "percentage": 66.65, "elapsed_time": "1 day, 13:52:14", "remaining_time": "18:57:12", "throughput": 4654.08, "total_tokens": 634512472} {"current_steps": 10455, "total_steps": 15680, "loss": 0.26717848777770997, "lr": 2.4994216424039637e-06, "epoch": 1.333545918367347, "percentage": 66.68, "elapsed_time": "1 day, 13:53:22", "remaining_time": "18:56:08", "throughput": 4653.95, "total_tokens": 634811112} {"current_steps": 10460, "total_steps": 15680, "loss": 0.24141874313354492, "lr": 2.495085383199159e-06, "epoch": 1.3341836734693877, "percentage": 66.71, "elapsed_time": "1 day, 13:54:30", "remaining_time": "18:55:04", "throughput": 4653.81, "total_tokens": 635107792} {"current_steps": 10465, "total_steps": 15680, "loss": 0.2344221591949463, "lr": 2.4907516378511137e-06, "epoch": 1.3348214285714286, "percentage": 66.74, "elapsed_time": "1 day, 13:55:36", "remaining_time": "18:54:00", "throughput": 4653.79, "total_tokens": 635413496} {"current_steps": 10470, "total_steps": 15680, "loss": 0.2744720935821533, "lr": 2.486420410709043e-06, "epoch": 1.3354591836734695, "percentage": 66.77, "elapsed_time": "1 day, 13:56:42", "remaining_time": "18:52:55", "throughput": 4653.77, "total_tokens": 635717640} {"current_steps": 10475, "total_steps": 15680, "loss": 0.2511033296585083, "lr": 2.482091706119642e-06, "epoch": 1.3360969387755102, "percentage": 66.8, "elapsed_time": "1 day, 13:57:42", "remaining_time": "18:51:47", "throughput": 4654.03, "total_tokens": 636030608} {"current_steps": 10480, "total_steps": 15680, "loss": 0.25283474922180177, "lr": 2.4777655284270623e-06, "epoch": 1.336734693877551, "percentage": 66.84, "elapsed_time": "1 day, 13:58:52", "remaining_time": "18:50:44", "throughput": 4653.88, "total_tokens": 636337536} {"current_steps": 10485, "total_steps": 15680, "loss": 0.2502155065536499, "lr": 2.473441881972927e-06, "epoch": 1.337372448979592, "percentage": 66.87, "elapsed_time": "1 day, 14:00:01", "remaining_time": "18:49:41", "throughput": 4653.68, "total_tokens": 636632528} {"current_steps": 10490, "total_steps": 15680, "loss": 0.27263717651367186, "lr": 2.4691207710963185e-06, "epoch": 1.3380102040816326, "percentage": 66.9, "elapsed_time": "1 day, 14:01:11", "remaining_time": "18:48:37", "throughput": 4653.58, "total_tokens": 636940976} {"current_steps": 10495, "total_steps": 15680, "loss": 0.25528175830841066, "lr": 2.464802200133772e-06, "epoch": 1.3386479591836735, "percentage": 66.93, "elapsed_time": "1 day, 14:02:17", "remaining_time": "18:47:33", "throughput": 4653.61, "total_tokens": 637252544} {"current_steps": 10500, "total_steps": 15680, "loss": 0.2494715690612793, "lr": 2.4604861734192755e-06, "epoch": 1.3392857142857144, "percentage": 66.96, "elapsed_time": "1 day, 14:03:29", "remaining_time": "18:46:31", "throughput": 4653.26, "total_tokens": 637538400} {"current_steps": 10505, "total_steps": 15680, "loss": 0.2574897289276123, "lr": 2.456172695284263e-06, "epoch": 1.339923469387755, "percentage": 67.0, "elapsed_time": "1 day, 14:04:34", "remaining_time": "18:45:25", "throughput": 4653.16, "total_tokens": 637829512} {"current_steps": 10510, "total_steps": 15680, "loss": 0.25566754341125486, "lr": 2.4518617700576116e-06, "epoch": 1.340561224489796, "percentage": 67.03, "elapsed_time": "1 day, 14:05:26", "remaining_time": "18:44:14", "throughput": 4653.68, "total_tokens": 638144032} {"current_steps": 10515, "total_steps": 15680, "loss": 0.23982324600219726, "lr": 2.447553402065637e-06, "epoch": 1.3411989795918369, "percentage": 67.06, "elapsed_time": "1 day, 14:06:35", "remaining_time": "18:43:10", "throughput": 4653.59, "total_tokens": 638449872} {"current_steps": 10520, "total_steps": 15680, "loss": 0.24281463623046876, "lr": 2.4432475956320824e-06, "epoch": 1.3418367346938775, "percentage": 67.09, "elapsed_time": "1 day, 14:07:41", "remaining_time": "18:42:05", "throughput": 4653.58, "total_tokens": 638754928} {"current_steps": 10525, "total_steps": 15680, "loss": 0.2543042182922363, "lr": 2.4389443550781304e-06, "epoch": 1.3424744897959184, "percentage": 67.12, "elapsed_time": "1 day, 14:08:41", "remaining_time": "18:40:58", "throughput": 4653.77, "total_tokens": 639060400} {"current_steps": 10530, "total_steps": 15680, "loss": 0.24138739109039306, "lr": 2.4346436847223836e-06, "epoch": 1.343112244897959, "percentage": 67.16, "elapsed_time": "1 day, 14:09:45", "remaining_time": "18:39:52", "throughput": 4653.71, "total_tokens": 639352320} {"current_steps": 10535, "total_steps": 15680, "loss": 0.253510856628418, "lr": 2.4303455888808618e-06, "epoch": 1.34375, "percentage": 67.19, "elapsed_time": "1 day, 14:10:53", "remaining_time": "18:38:48", "throughput": 4653.73, "total_tokens": 639673216} {"current_steps": 10540, "total_steps": 15680, "loss": 0.2616002559661865, "lr": 2.4260500718670036e-06, "epoch": 1.344387755102041, "percentage": 67.22, "elapsed_time": "1 day, 14:12:11", "remaining_time": "18:37:49", "throughput": 4653.35, "total_tokens": 639980632} {"current_steps": 10545, "total_steps": 15680, "loss": 0.2384871006011963, "lr": 2.4217571379916673e-06, "epoch": 1.3450255102040816, "percentage": 67.25, "elapsed_time": "1 day, 14:13:19", "remaining_time": "18:36:45", "throughput": 4653.32, "total_tokens": 640294192} {"current_steps": 10550, "total_steps": 15680, "loss": 0.27579896450042723, "lr": 2.4174667915631038e-06, "epoch": 1.3456632653061225, "percentage": 67.28, "elapsed_time": "1 day, 14:14:23", "remaining_time": "18:35:39", "throughput": 4653.29, "total_tokens": 640588232} {"current_steps": 10555, "total_steps": 15680, "loss": 0.2730722188949585, "lr": 2.413179036886978e-06, "epoch": 1.3463010204081631, "percentage": 67.32, "elapsed_time": "1 day, 14:15:16", "remaining_time": "18:34:28", "throughput": 4653.76, "total_tokens": 640899440} {"current_steps": 10560, "total_steps": 15680, "loss": 0.26175551414489745, "lr": 2.408893878266355e-06, "epoch": 1.346938775510204, "percentage": 67.35, "elapsed_time": "1 day, 14:16:16", "remaining_time": "18:33:20", "throughput": 4653.92, "total_tokens": 641202424} {"current_steps": 10565, "total_steps": 15680, "loss": 0.263177752494812, "lr": 2.404611320001686e-06, "epoch": 1.347576530612245, "percentage": 67.38, "elapsed_time": "1 day, 14:17:31", "remaining_time": "18:32:20", "throughput": 4653.54, "total_tokens": 641499128} {"current_steps": 10570, "total_steps": 15680, "loss": 0.2511106491088867, "lr": 2.4003313663908182e-06, "epoch": 1.3482142857142856, "percentage": 67.41, "elapsed_time": "1 day, 14:18:38", "remaining_time": "18:31:15", "throughput": 4653.56, "total_tokens": 641811424} {"current_steps": 10575, "total_steps": 15680, "loss": 0.2438887119293213, "lr": 2.3960540217289856e-06, "epoch": 1.3488520408163265, "percentage": 67.44, "elapsed_time": "1 day, 14:19:35", "remaining_time": "18:30:06", "throughput": 4653.82, "total_tokens": 642110896} {"current_steps": 10580, "total_steps": 15680, "loss": 0.2553779125213623, "lr": 2.3917792903088013e-06, "epoch": 1.3494897959183674, "percentage": 67.47, "elapsed_time": "1 day, 14:20:26", "remaining_time": "18:28:54", "throughput": 4654.29, "total_tokens": 642416424} {"current_steps": 10585, "total_steps": 15680, "loss": 0.2522465229034424, "lr": 2.387507176420256e-06, "epoch": 1.350127551020408, "percentage": 67.51, "elapsed_time": "1 day, 14:21:41", "remaining_time": "18:27:53", "throughput": 4653.91, "total_tokens": 642710552} {"current_steps": 10590, "total_steps": 15680, "loss": 0.24289708137512206, "lr": 2.383237684350716e-06, "epoch": 1.350765306122449, "percentage": 67.54, "elapsed_time": "1 day, 14:22:47", "remaining_time": "18:26:49", "throughput": 4653.79, "total_tokens": 643003000} {"current_steps": 10595, "total_steps": 15680, "loss": 0.2685849666595459, "lr": 2.378970818384914e-06, "epoch": 1.3514030612244898, "percentage": 67.57, "elapsed_time": "1 day, 14:23:57", "remaining_time": "18:25:45", "throughput": 4653.67, "total_tokens": 643309952} {"current_steps": 10600, "total_steps": 15680, "loss": 0.2731654167175293, "lr": 2.374706582804948e-06, "epoch": 1.3520408163265305, "percentage": 67.6, "elapsed_time": "1 day, 14:25:08", "remaining_time": "18:24:43", "throughput": 4653.53, "total_tokens": 643622504} {"current_steps": 10605, "total_steps": 15680, "loss": 0.23430299758911133, "lr": 2.3704449818902763e-06, "epoch": 1.3526785714285714, "percentage": 67.63, "elapsed_time": "1 day, 14:26:11", "remaining_time": "18:23:37", "throughput": 4653.58, "total_tokens": 643922296} {"current_steps": 10610, "total_steps": 15680, "loss": 0.26416237354278566, "lr": 2.366186019917713e-06, "epoch": 1.3533163265306123, "percentage": 67.67, "elapsed_time": "1 day, 14:27:27", "remaining_time": "18:22:37", "throughput": 4653.21, "total_tokens": 644226648} {"current_steps": 10615, "total_steps": 15680, "loss": 0.24305322170257568, "lr": 2.3619297011614236e-06, "epoch": 1.353954081632653, "percentage": 67.7, "elapsed_time": "1 day, 14:28:37", "remaining_time": "18:21:34", "throughput": 4653.05, "total_tokens": 644529424} {"current_steps": 10620, "total_steps": 15680, "loss": 0.27020907402038574, "lr": 2.3576760298929236e-06, "epoch": 1.3545918367346939, "percentage": 67.73, "elapsed_time": "1 day, 14:29:40", "remaining_time": "18:20:27", "throughput": 4653.07, "total_tokens": 644823984} {"current_steps": 10625, "total_steps": 15680, "loss": 0.2463529586791992, "lr": 2.353425010381063e-06, "epoch": 1.3552295918367347, "percentage": 67.76, "elapsed_time": "1 day, 14:30:48", "remaining_time": "18:19:23", "throughput": 4652.98, "total_tokens": 645127368} {"current_steps": 10630, "total_steps": 15680, "loss": 0.2500694990158081, "lr": 2.349176646892045e-06, "epoch": 1.3558673469387754, "percentage": 67.79, "elapsed_time": "1 day, 14:31:54", "remaining_time": "18:18:19", "throughput": 4652.94, "total_tokens": 645431280} {"current_steps": 10635, "total_steps": 15680, "loss": 0.25265026092529297, "lr": 2.344930943689393e-06, "epoch": 1.3565051020408163, "percentage": 67.83, "elapsed_time": "1 day, 14:32:47", "remaining_time": "18:17:08", "throughput": 4653.49, "total_tokens": 645752504} {"current_steps": 10640, "total_steps": 15680, "loss": 0.25464611053466796, "lr": 2.3406879050339664e-06, "epoch": 1.3571428571428572, "percentage": 67.86, "elapsed_time": "1 day, 14:33:56", "remaining_time": "18:16:04", "throughput": 4653.34, "total_tokens": 646053008} {"current_steps": 10645, "total_steps": 15680, "loss": 0.2856419086456299, "lr": 2.3364475351839573e-06, "epoch": 1.3577806122448979, "percentage": 67.89, "elapsed_time": "1 day, 14:35:02", "remaining_time": "18:14:59", "throughput": 4653.35, "total_tokens": 646363800} {"current_steps": 10650, "total_steps": 15680, "loss": 0.25574593544006347, "lr": 2.3322098383948666e-06, "epoch": 1.3584183673469388, "percentage": 67.92, "elapsed_time": "1 day, 14:36:21", "remaining_time": "18:14:00", "throughput": 4652.88, "total_tokens": 646662400} {"current_steps": 10655, "total_steps": 15680, "loss": 0.2599836826324463, "lr": 2.327974818919521e-06, "epoch": 1.3590561224489797, "percentage": 67.95, "elapsed_time": "1 day, 14:37:23", "remaining_time": "18:12:54", "throughput": 4652.93, "total_tokens": 646961552} {"current_steps": 10660, "total_steps": 15680, "loss": 0.26797871589660643, "lr": 2.323742481008059e-06, "epoch": 1.3596938775510203, "percentage": 67.98, "elapsed_time": "1 day, 14:38:18", "remaining_time": "18:11:44", "throughput": 4653.3, "total_tokens": 647269032} {"current_steps": 10665, "total_steps": 15680, "loss": 0.2578679323196411, "lr": 2.3195128289079265e-06, "epoch": 1.3603316326530612, "percentage": 68.02, "elapsed_time": "1 day, 14:39:19", "remaining_time": "18:10:37", "throughput": 4653.41, "total_tokens": 647568480} {"current_steps": 10670, "total_steps": 15680, "loss": 0.27208359241485597, "lr": 2.315285866863875e-06, "epoch": 1.3609693877551021, "percentage": 68.05, "elapsed_time": "1 day, 14:40:22", "remaining_time": "18:09:30", "throughput": 4653.53, "total_tokens": 647874144} {"current_steps": 10675, "total_steps": 15680, "loss": 0.24118657112121583, "lr": 2.3110615991179556e-06, "epoch": 1.3616071428571428, "percentage": 68.08, "elapsed_time": "1 day, 14:41:16", "remaining_time": "18:08:20", "throughput": 4653.87, "total_tokens": 648176336} {"current_steps": 10680, "total_steps": 15680, "loss": 0.2557355880737305, "lr": 2.3068400299095172e-06, "epoch": 1.3622448979591837, "percentage": 68.11, "elapsed_time": "1 day, 14:42:23", "remaining_time": "18:07:15", "throughput": 4653.92, "total_tokens": 648491096} {"current_steps": 10685, "total_steps": 15680, "loss": 0.24427404403686523, "lr": 2.302621163475198e-06, "epoch": 1.3628826530612246, "percentage": 68.14, "elapsed_time": "1 day, 14:43:33", "remaining_time": "18:06:12", "throughput": 4653.79, "total_tokens": 648799472} {"current_steps": 10690, "total_steps": 15680, "loss": 0.2685335636138916, "lr": 2.2984050040489266e-06, "epoch": 1.3635204081632653, "percentage": 68.18, "elapsed_time": "1 day, 14:44:39", "remaining_time": "18:05:07", "throughput": 4653.7, "total_tokens": 649093176} {"current_steps": 10695, "total_steps": 15680, "loss": 0.24063777923583984, "lr": 2.2941915558619123e-06, "epoch": 1.3641581632653061, "percentage": 68.21, "elapsed_time": "1 day, 14:45:42", "remaining_time": "18:04:01", "throughput": 4653.63, "total_tokens": 649381256} {"current_steps": 10700, "total_steps": 15680, "loss": 0.25992212295532224, "lr": 2.2899808231426447e-06, "epoch": 1.364795918367347, "percentage": 68.24, "elapsed_time": "1 day, 14:46:49", "remaining_time": "18:02:56", "throughput": 4653.59, "total_tokens": 649682888} {"current_steps": 10705, "total_steps": 15680, "loss": 0.26885318756103516, "lr": 2.28577281011689e-06, "epoch": 1.3654336734693877, "percentage": 68.27, "elapsed_time": "1 day, 14:47:40", "remaining_time": "18:01:45", "throughput": 4654.11, "total_tokens": 649995064} {"current_steps": 10710, "total_steps": 15680, "loss": 0.23794171810150147, "lr": 2.281567521007678e-06, "epoch": 1.3660714285714286, "percentage": 68.3, "elapsed_time": "1 day, 14:48:47", "remaining_time": "18:00:40", "throughput": 4654.06, "total_tokens": 650299792} {"current_steps": 10715, "total_steps": 15680, "loss": 0.24845671653747559, "lr": 2.277364960035316e-06, "epoch": 1.3667091836734695, "percentage": 68.34, "elapsed_time": "1 day, 14:49:55", "remaining_time": "17:59:36", "throughput": 4653.93, "total_tokens": 650599768} {"current_steps": 10720, "total_steps": 15680, "loss": 0.2722214937210083, "lr": 2.2731651314173665e-06, "epoch": 1.3673469387755102, "percentage": 68.37, "elapsed_time": "1 day, 14:51:01", "remaining_time": "17:58:32", "throughput": 4653.89, "total_tokens": 650901360} {"current_steps": 10725, "total_steps": 15680, "loss": 0.25092372894287107, "lr": 2.2689680393686457e-06, "epoch": 1.367984693877551, "percentage": 68.4, "elapsed_time": "1 day, 14:52:11", "remaining_time": "17:57:28", "throughput": 4653.78, "total_tokens": 651208024} {"current_steps": 10730, "total_steps": 15680, "loss": 0.26037437915802003, "lr": 2.2647736881012337e-06, "epoch": 1.368622448979592, "percentage": 68.43, "elapsed_time": "1 day, 14:53:14", "remaining_time": "17:56:22", "throughput": 4653.81, "total_tokens": 651509616} {"current_steps": 10735, "total_steps": 15680, "loss": 0.2595388650894165, "lr": 2.2605820818244563e-06, "epoch": 1.3692602040816326, "percentage": 68.46, "elapsed_time": "1 day, 14:54:22", "remaining_time": "17:55:18", "throughput": 4653.74, "total_tokens": 651812552} {"current_steps": 10740, "total_steps": 15680, "loss": 0.247703218460083, "lr": 2.256393224744878e-06, "epoch": 1.3698979591836735, "percentage": 68.49, "elapsed_time": "1 day, 14:55:15", "remaining_time": "17:54:07", "throughput": 4654.2, "total_tokens": 652123936} {"current_steps": 10745, "total_steps": 15680, "loss": 0.2506424903869629, "lr": 2.252207121066311e-06, "epoch": 1.3705357142857144, "percentage": 68.53, "elapsed_time": "1 day, 14:56:12", "remaining_time": "17:52:58", "throughput": 4654.53, "total_tokens": 652436208} {"current_steps": 10750, "total_steps": 15680, "loss": 0.2539947032928467, "lr": 2.248023774989804e-06, "epoch": 1.371173469387755, "percentage": 68.56, "elapsed_time": "1 day, 14:57:24", "remaining_time": "17:51:56", "throughput": 4654.22, "total_tokens": 652728840} {"current_steps": 10755, "total_steps": 15680, "loss": 0.25039238929748536, "lr": 2.2438431907136365e-06, "epoch": 1.371811224489796, "percentage": 68.59, "elapsed_time": "1 day, 14:58:37", "remaining_time": "17:50:55", "throughput": 4654.0, "total_tokens": 653037248} {"current_steps": 10760, "total_steps": 15680, "loss": 0.2588667392730713, "lr": 2.2396653724333167e-06, "epoch": 1.3724489795918369, "percentage": 68.62, "elapsed_time": "1 day, 14:59:42", "remaining_time": "17:49:49", "throughput": 4653.95, "total_tokens": 653331840} {"current_steps": 10765, "total_steps": 15680, "loss": 0.25351243019104003, "lr": 2.235490324341577e-06, "epoch": 1.3730867346938775, "percentage": 68.65, "elapsed_time": "1 day, 15:00:47", "remaining_time": "17:48:44", "throughput": 4653.84, "total_tokens": 653619864} {"current_steps": 10770, "total_steps": 15680, "loss": 0.24595603942871094, "lr": 2.2313180506283695e-06, "epoch": 1.3737244897959184, "percentage": 68.69, "elapsed_time": "1 day, 15:01:55", "remaining_time": "17:47:40", "throughput": 4653.7, "total_tokens": 653918392} {"current_steps": 10775, "total_steps": 15680, "loss": 0.25271408557891845, "lr": 2.227148555480863e-06, "epoch": 1.374362244897959, "percentage": 68.72, "elapsed_time": "1 day, 15:02:58", "remaining_time": "17:46:34", "throughput": 4653.85, "total_tokens": 654231808} {"current_steps": 10780, "total_steps": 15680, "loss": 0.2630213022232056, "lr": 2.222981843083436e-06, "epoch": 1.375, "percentage": 68.75, "elapsed_time": "1 day, 15:04:08", "remaining_time": "17:45:31", "throughput": 4653.71, "total_tokens": 654537768} {"current_steps": 10785, "total_steps": 15680, "loss": 0.24607279300689697, "lr": 2.2188179176176767e-06, "epoch": 1.375637755102041, "percentage": 68.78, "elapsed_time": "1 day, 15:05:06", "remaining_time": "17:44:22", "throughput": 4653.93, "total_tokens": 654839688} {"current_steps": 10790, "total_steps": 15680, "loss": 0.2657738924026489, "lr": 2.2146567832623737e-06, "epoch": 1.3762755102040816, "percentage": 68.81, "elapsed_time": "1 day, 15:06:11", "remaining_time": "17:43:17", "throughput": 4654.03, "total_tokens": 655155736} {"current_steps": 10795, "total_steps": 15680, "loss": 0.26737127304077146, "lr": 2.2104984441935167e-06, "epoch": 1.3769132653061225, "percentage": 68.85, "elapsed_time": "1 day, 15:07:18", "remaining_time": "17:42:12", "throughput": 4653.9, "total_tokens": 655448320} {"current_steps": 10800, "total_steps": 15680, "loss": 0.2794210910797119, "lr": 2.20634290458429e-06, "epoch": 1.3775510204081631, "percentage": 68.88, "elapsed_time": "1 day, 15:08:28", "remaining_time": "17:41:09", "throughput": 4653.74, "total_tokens": 655752952} {"current_steps": 10805, "total_steps": 15680, "loss": 0.2476513147354126, "lr": 2.2021901686050684e-06, "epoch": 1.378188775510204, "percentage": 68.91, "elapsed_time": "1 day, 15:09:30", "remaining_time": "17:40:03", "throughput": 4653.84, "total_tokens": 656054200} {"current_steps": 10810, "total_steps": 15680, "loss": 0.26006624698638914, "lr": 2.1980402404234074e-06, "epoch": 1.378826530612245, "percentage": 68.94, "elapsed_time": "1 day, 15:10:34", "remaining_time": "17:38:57", "throughput": 4653.76, "total_tokens": 656343272} {"current_steps": 10815, "total_steps": 15680, "loss": 0.23834261894226075, "lr": 2.1938931242040557e-06, "epoch": 1.3794642857142856, "percentage": 68.97, "elapsed_time": "1 day, 15:11:42", "remaining_time": "17:37:53", "throughput": 4653.73, "total_tokens": 656653912} {"current_steps": 10820, "total_steps": 15680, "loss": 0.24825513362884521, "lr": 2.1897488241089336e-06, "epoch": 1.3801020408163265, "percentage": 69.01, "elapsed_time": "1 day, 15:12:50", "remaining_time": "17:36:49", "throughput": 4653.52, "total_tokens": 656939456} {"current_steps": 10825, "total_steps": 15680, "loss": 0.23897290229797363, "lr": 2.1856073442971322e-06, "epoch": 1.3807397959183674, "percentage": 69.04, "elapsed_time": "1 day, 15:14:06", "remaining_time": "17:35:48", "throughput": 4653.19, "total_tokens": 657245400} {"current_steps": 10830, "total_steps": 15680, "loss": 0.25669231414794924, "lr": 2.181468688924916e-06, "epoch": 1.381377551020408, "percentage": 69.07, "elapsed_time": "1 day, 15:15:15", "remaining_time": "17:34:45", "throughput": 4653.0, "total_tokens": 657542320} {"current_steps": 10835, "total_steps": 15680, "loss": 0.266129207611084, "lr": 2.1773328621457196e-06, "epoch": 1.382015306122449, "percentage": 69.1, "elapsed_time": "1 day, 15:16:28", "remaining_time": "17:33:43", "throughput": 4652.76, "total_tokens": 657848208} {"current_steps": 10840, "total_steps": 15680, "loss": 0.2581286907196045, "lr": 2.1731998681101293e-06, "epoch": 1.3826530612244898, "percentage": 69.13, "elapsed_time": "1 day, 15:17:32", "remaining_time": "17:32:37", "throughput": 4652.73, "total_tokens": 658141328} {"current_steps": 10845, "total_steps": 15680, "loss": 0.2503084659576416, "lr": 2.169069710965892e-06, "epoch": 1.3832908163265305, "percentage": 69.16, "elapsed_time": "1 day, 15:18:38", "remaining_time": "17:31:32", "throughput": 4652.75, "total_tokens": 658449416} {"current_steps": 10850, "total_steps": 15680, "loss": 0.2516158580780029, "lr": 2.1649423948579157e-06, "epoch": 1.3839285714285714, "percentage": 69.2, "elapsed_time": "1 day, 15:19:44", "remaining_time": "17:30:27", "throughput": 4652.71, "total_tokens": 658752104} {"current_steps": 10855, "total_steps": 15680, "loss": 0.24149253368377685, "lr": 2.160817923928244e-06, "epoch": 1.3845663265306123, "percentage": 69.23, "elapsed_time": "1 day, 15:20:44", "remaining_time": "17:29:20", "throughput": 4652.96, "total_tokens": 659068832} {"current_steps": 10860, "total_steps": 15680, "loss": 0.24596431255340576, "lr": 2.156696302316074e-06, "epoch": 1.385204081632653, "percentage": 69.26, "elapsed_time": "1 day, 15:21:48", "remaining_time": "17:28:14", "throughput": 4653.0, "total_tokens": 659370344} {"current_steps": 10865, "total_steps": 15680, "loss": 0.2650430679321289, "lr": 2.1525775341577404e-06, "epoch": 1.3858418367346939, "percentage": 69.29, "elapsed_time": "1 day, 15:23:00", "remaining_time": "17:27:12", "throughput": 4652.81, "total_tokens": 659675272} {"current_steps": 10870, "total_steps": 15680, "loss": 0.2624351501464844, "lr": 2.1484616235867152e-06, "epoch": 1.3864795918367347, "percentage": 69.32, "elapsed_time": "1 day, 15:23:59", "remaining_time": "17:26:04", "throughput": 4653.04, "total_tokens": 659984064} {"current_steps": 10875, "total_steps": 15680, "loss": 0.2529263973236084, "lr": 2.1443485747336014e-06, "epoch": 1.3871173469387754, "percentage": 69.36, "elapsed_time": "1 day, 15:25:12", "remaining_time": "17:25:02", "throughput": 4652.76, "total_tokens": 660283112} {"current_steps": 10880, "total_steps": 15680, "loss": 0.23541016578674318, "lr": 2.140238391726131e-06, "epoch": 1.3877551020408163, "percentage": 69.39, "elapsed_time": "1 day, 15:26:15", "remaining_time": "17:23:56", "throughput": 4652.73, "total_tokens": 660575688} {"current_steps": 10885, "total_steps": 15680, "loss": 0.24966943264007568, "lr": 2.1361310786891596e-06, "epoch": 1.3883928571428572, "percentage": 69.42, "elapsed_time": "1 day, 15:27:06", "remaining_time": "17:22:44", "throughput": 4653.29, "total_tokens": 660891000} {"current_steps": 10890, "total_steps": 15680, "loss": 0.24406077861785888, "lr": 2.1320266397446655e-06, "epoch": 1.3890306122448979, "percentage": 69.45, "elapsed_time": "1 day, 15:28:20", "remaining_time": "17:21:43", "throughput": 4652.91, "total_tokens": 661181296} {"current_steps": 10895, "total_steps": 15680, "loss": 0.24395380020141602, "lr": 2.1279250790117327e-06, "epoch": 1.3896683673469388, "percentage": 69.48, "elapsed_time": "1 day, 15:29:32", "remaining_time": "17:20:41", "throughput": 4652.69, "total_tokens": 661486088} {"current_steps": 10900, "total_steps": 15680, "loss": 0.24505012035369872, "lr": 2.123826400606571e-06, "epoch": 1.3903061224489797, "percentage": 69.52, "elapsed_time": "1 day, 15:30:46", "remaining_time": "17:19:39", "throughput": 4652.34, "total_tokens": 661776696} {"current_steps": 10905, "total_steps": 15680, "loss": 0.2468052625656128, "lr": 2.119730608642489e-06, "epoch": 1.3909438775510203, "percentage": 69.55, "elapsed_time": "1 day, 15:31:52", "remaining_time": "17:18:34", "throughput": 4652.26, "total_tokens": 662075896} {"current_steps": 10910, "total_steps": 15680, "loss": 0.2510690450668335, "lr": 2.1156377072298972e-06, "epoch": 1.3915816326530612, "percentage": 69.58, "elapsed_time": "1 day, 15:33:04", "remaining_time": "17:17:32", "throughput": 4652.08, "total_tokens": 662382448} {"current_steps": 10915, "total_steps": 15680, "loss": 0.26249260902404786, "lr": 2.111547700476308e-06, "epoch": 1.3922193877551021, "percentage": 69.61, "elapsed_time": "1 day, 15:33:59", "remaining_time": "17:16:22", "throughput": 4652.44, "total_tokens": 662690784} {"current_steps": 10920, "total_steps": 15680, "loss": 0.268072772026062, "lr": 2.107460592486333e-06, "epoch": 1.3928571428571428, "percentage": 69.64, "elapsed_time": "1 day, 15:35:04", "remaining_time": "17:15:17", "throughput": 4652.36, "total_tokens": 662980848} {"current_steps": 10925, "total_steps": 15680, "loss": 0.24447717666625976, "lr": 2.1033763873616675e-06, "epoch": 1.3934948979591837, "percentage": 69.67, "elapsed_time": "1 day, 15:36:19", "remaining_time": "17:14:16", "throughput": 4652.04, "total_tokens": 663286584} {"current_steps": 10930, "total_steps": 15680, "loss": 0.2554739475250244, "lr": 2.0992950892010948e-06, "epoch": 1.3941326530612246, "percentage": 69.71, "elapsed_time": "1 day, 15:37:18", "remaining_time": "17:13:08", "throughput": 4652.28, "total_tokens": 663595984} {"current_steps": 10935, "total_steps": 15680, "loss": 0.2546344995498657, "lr": 2.0952167021004887e-06, "epoch": 1.3947704081632653, "percentage": 69.74, "elapsed_time": "1 day, 15:38:29", "remaining_time": "17:12:05", "throughput": 4652.2, "total_tokens": 663913360} {"current_steps": 10940, "total_steps": 15680, "loss": 0.248978590965271, "lr": 2.0911412301527895e-06, "epoch": 1.3954081632653061, "percentage": 69.77, "elapsed_time": "1 day, 15:39:38", "remaining_time": "17:11:01", "throughput": 4652.06, "total_tokens": 664212632} {"current_steps": 10945, "total_steps": 15680, "loss": 0.24985527992248535, "lr": 2.08706867744802e-06, "epoch": 1.396045918367347, "percentage": 69.8, "elapsed_time": "1 day, 15:40:42", "remaining_time": "17:09:56", "throughput": 4652.05, "total_tokens": 664511248} {"current_steps": 10950, "total_steps": 15680, "loss": 0.25580124855041503, "lr": 2.0829990480732715e-06, "epoch": 1.3966836734693877, "percentage": 69.83, "elapsed_time": "1 day, 15:41:48", "remaining_time": "17:08:51", "throughput": 4651.91, "total_tokens": 664799920} {"current_steps": 10955, "total_steps": 15680, "loss": 0.258500075340271, "lr": 2.0789323461127015e-06, "epoch": 1.3973214285714286, "percentage": 69.87, "elapsed_time": "1 day, 15:42:51", "remaining_time": "17:07:45", "throughput": 4652.0, "total_tokens": 665103792} {"current_steps": 10960, "total_steps": 15680, "loss": 0.2610204219818115, "lr": 2.0748685756475286e-06, "epoch": 1.3979591836734695, "percentage": 69.9, "elapsed_time": "1 day, 15:43:54", "remaining_time": "17:06:38", "throughput": 4652.01, "total_tokens": 665399664} {"current_steps": 10965, "total_steps": 15680, "loss": 0.24911460876464844, "lr": 2.0708077407560305e-06, "epoch": 1.3985969387755102, "percentage": 69.93, "elapsed_time": "1 day, 15:44:53", "remaining_time": "17:05:30", "throughput": 4652.17, "total_tokens": 665695688} {"current_steps": 10970, "total_steps": 15680, "loss": 0.2696921110153198, "lr": 2.06674984551354e-06, "epoch": 1.399234693877551, "percentage": 69.96, "elapsed_time": "1 day, 15:45:50", "remaining_time": "17:04:21", "throughput": 4652.46, "total_tokens": 666000336} {"current_steps": 10975, "total_steps": 15680, "loss": 0.24796009063720703, "lr": 2.062694893992436e-06, "epoch": 1.399872448979592, "percentage": 69.99, "elapsed_time": "1 day, 15:46:49", "remaining_time": "17:03:14", "throughput": 4652.65, "total_tokens": 666303304} {"current_steps": 10980, "total_steps": 15680, "loss": 0.24918723106384277, "lr": 2.0586428902621474e-06, "epoch": 1.4005102040816326, "percentage": 70.03, "elapsed_time": "1 day, 15:47:34", "remaining_time": "17:02:00", "throughput": 4653.41, "total_tokens": 666622728} {"current_steps": 10985, "total_steps": 15680, "loss": 0.2662821292877197, "lr": 2.0545938383891427e-06, "epoch": 1.4011479591836735, "percentage": 70.06, "elapsed_time": "1 day, 15:48:36", "remaining_time": "17:00:53", "throughput": 4653.47, "total_tokens": 666917368} {"current_steps": 10990, "total_steps": 15680, "loss": 0.23631629943847657, "lr": 2.050547742436929e-06, "epoch": 1.4017857142857144, "percentage": 70.09, "elapsed_time": "1 day, 15:49:48", "remaining_time": "16:59:51", "throughput": 4653.21, "total_tokens": 667217976} {"current_steps": 10995, "total_steps": 15680, "loss": 0.2509471416473389, "lr": 2.0465046064660437e-06, "epoch": 1.402423469387755, "percentage": 70.12, "elapsed_time": "1 day, 15:50:58", "remaining_time": "16:58:47", "throughput": 4653.03, "total_tokens": 667515672} {"current_steps": 11000, "total_steps": 15680, "loss": 0.24612851142883302, "lr": 2.0424644345340554e-06, "epoch": 1.403061224489796, "percentage": 70.15, "elapsed_time": "1 day, 15:52:03", "remaining_time": "16:57:42", "throughput": 4653.03, "total_tokens": 667817512} {"current_steps": 11005, "total_steps": 15680, "loss": 0.24648277759552, "lr": 2.038427230695565e-06, "epoch": 1.4036989795918369, "percentage": 70.18, "elapsed_time": "1 day, 15:53:12", "remaining_time": "16:56:39", "throughput": 4652.89, "total_tokens": 668120112} {"current_steps": 11010, "total_steps": 15680, "loss": 0.2571901321411133, "lr": 2.034392999002182e-06, "epoch": 1.4043367346938775, "percentage": 70.22, "elapsed_time": "1 day, 15:54:28", "remaining_time": "16:55:38", "throughput": 4652.58, "total_tokens": 668429272} {"current_steps": 11015, "total_steps": 15680, "loss": 0.24138829708099366, "lr": 2.0303617435025407e-06, "epoch": 1.4049744897959184, "percentage": 70.25, "elapsed_time": "1 day, 15:55:39", "remaining_time": "16:54:35", "throughput": 4652.45, "total_tokens": 668739184} {"current_steps": 11020, "total_steps": 15680, "loss": 0.2457888126373291, "lr": 2.0263334682422923e-06, "epoch": 1.405612244897959, "percentage": 70.28, "elapsed_time": "1 day, 15:56:55", "remaining_time": "16:53:34", "throughput": 4652.08, "total_tokens": 669040392} {"current_steps": 11025, "total_steps": 15680, "loss": 0.2669305086135864, "lr": 2.0223081772640867e-06, "epoch": 1.40625, "percentage": 70.31, "elapsed_time": "1 day, 15:57:53", "remaining_time": "16:52:26", "throughput": 4652.27, "total_tokens": 669337248} {"current_steps": 11030, "total_steps": 15680, "loss": 0.24875364303588868, "lr": 2.0182858746075873e-06, "epoch": 1.406887755102041, "percentage": 70.34, "elapsed_time": "1 day, 15:58:59", "remaining_time": "16:51:21", "throughput": 4652.27, "total_tokens": 669647448} {"current_steps": 11035, "total_steps": 15680, "loss": 0.2550758123397827, "lr": 2.014266564309455e-06, "epoch": 1.4075255102040816, "percentage": 70.38, "elapsed_time": "1 day, 16:00:02", "remaining_time": "16:50:15", "throughput": 4652.27, "total_tokens": 669939544} {"current_steps": 11040, "total_steps": 15680, "loss": 0.2659616947174072, "lr": 2.010250250403349e-06, "epoch": 1.4081632653061225, "percentage": 70.41, "elapsed_time": "1 day, 16:01:00", "remaining_time": "16:49:06", "throughput": 4652.48, "total_tokens": 670236248} {"current_steps": 11045, "total_steps": 15680, "loss": 0.2394233226776123, "lr": 2.00623693691992e-06, "epoch": 1.4088010204081631, "percentage": 70.44, "elapsed_time": "1 day, 16:02:06", "remaining_time": "16:48:02", "throughput": 4652.52, "total_tokens": 670550248} {"current_steps": 11050, "total_steps": 15680, "loss": 0.2595332145690918, "lr": 2.0022266278868086e-06, "epoch": 1.409438775510204, "percentage": 70.47, "elapsed_time": "1 day, 16:03:07", "remaining_time": "16:46:55", "throughput": 4652.65, "total_tokens": 670855080} {"current_steps": 11055, "total_steps": 15680, "loss": 0.2402665615081787, "lr": 1.9982193273286404e-06, "epoch": 1.410076530612245, "percentage": 70.5, "elapsed_time": "1 day, 16:03:57", "remaining_time": "16:45:43", "throughput": 4653.17, "total_tokens": 671159224} {"current_steps": 11060, "total_steps": 15680, "loss": 0.24990315437316896, "lr": 1.9942150392670207e-06, "epoch": 1.4107142857142856, "percentage": 70.54, "elapsed_time": "1 day, 16:05:07", "remaining_time": "16:44:40", "throughput": 4652.96, "total_tokens": 671456704} {"current_steps": 11065, "total_steps": 15680, "loss": 0.2636767148971558, "lr": 1.990213767720533e-06, "epoch": 1.4113520408163265, "percentage": 70.57, "elapsed_time": "1 day, 16:06:06", "remaining_time": "16:43:32", "throughput": 4653.24, "total_tokens": 671772664} {"current_steps": 11070, "total_steps": 15680, "loss": 0.26303236484527587, "lr": 1.9862155167047324e-06, "epoch": 1.4119897959183674, "percentage": 70.6, "elapsed_time": "1 day, 16:07:13", "remaining_time": "16:42:27", "throughput": 4653.2, "total_tokens": 672075568} {"current_steps": 11075, "total_steps": 15680, "loss": 0.2502783536911011, "lr": 1.982220290232143e-06, "epoch": 1.412627551020408, "percentage": 70.63, "elapsed_time": "1 day, 16:08:20", "remaining_time": "16:41:23", "throughput": 4653.11, "total_tokens": 672377576} {"current_steps": 11080, "total_steps": 15680, "loss": 0.2444309711456299, "lr": 1.9782280923122555e-06, "epoch": 1.413265306122449, "percentage": 70.66, "elapsed_time": "1 day, 16:09:26", "remaining_time": "16:40:18", "throughput": 4653.05, "total_tokens": 672674632} {"current_steps": 11085, "total_steps": 15680, "loss": 0.2458259105682373, "lr": 1.9742389269515137e-06, "epoch": 1.4139030612244898, "percentage": 70.7, "elapsed_time": "1 day, 16:10:36", "remaining_time": "16:39:15", "throughput": 4652.95, "total_tokens": 672988200} {"current_steps": 11090, "total_steps": 15680, "loss": 0.22437753677368164, "lr": 1.970252798153329e-06, "epoch": 1.4145408163265305, "percentage": 70.73, "elapsed_time": "1 day, 16:11:39", "remaining_time": "16:38:09", "throughput": 4653.03, "total_tokens": 673289928} {"current_steps": 11095, "total_steps": 15680, "loss": 0.2727480888366699, "lr": 1.9662697099180607e-06, "epoch": 1.4151785714285714, "percentage": 70.76, "elapsed_time": "1 day, 16:12:33", "remaining_time": "16:36:59", "throughput": 4653.5, "total_tokens": 673609528} {"current_steps": 11100, "total_steps": 15680, "loss": 0.24592394828796388, "lr": 1.9622896662430098e-06, "epoch": 1.4158163265306123, "percentage": 70.79, "elapsed_time": "1 day, 16:13:36", "remaining_time": "16:35:53", "throughput": 4653.55, "total_tokens": 673911976} {"current_steps": 11105, "total_steps": 15680, "loss": 0.25740480422973633, "lr": 1.9583126711224342e-06, "epoch": 1.416454081632653, "percentage": 70.82, "elapsed_time": "1 day, 16:14:39", "remaining_time": "16:34:46", "throughput": 4653.65, "total_tokens": 674217488} {"current_steps": 11110, "total_steps": 15680, "loss": 0.25806460380554197, "lr": 1.954338728547526e-06, "epoch": 1.4170918367346939, "percentage": 70.85, "elapsed_time": "1 day, 16:15:47", "remaining_time": "16:33:42", "throughput": 4653.6, "total_tokens": 674528768} {"current_steps": 11115, "total_steps": 15680, "loss": 0.26084744930267334, "lr": 1.9503678425064097e-06, "epoch": 1.4177295918367347, "percentage": 70.89, "elapsed_time": "1 day, 16:17:01", "remaining_time": "16:32:41", "throughput": 4653.34, "total_tokens": 674833976} {"current_steps": 11120, "total_steps": 15680, "loss": 0.2530702829360962, "lr": 1.9464000169841495e-06, "epoch": 1.4183673469387754, "percentage": 70.92, "elapsed_time": "1 day, 16:18:10", "remaining_time": "16:31:37", "throughput": 4653.28, "total_tokens": 675144408} {"current_steps": 11125, "total_steps": 15680, "loss": 0.2522618055343628, "lr": 1.942435255962736e-06, "epoch": 1.4190051020408163, "percentage": 70.95, "elapsed_time": "1 day, 16:19:18", "remaining_time": "16:30:33", "throughput": 4653.15, "total_tokens": 675444376} {"current_steps": 11130, "total_steps": 15680, "loss": 0.2615769624710083, "lr": 1.938473563421082e-06, "epoch": 1.4196428571428572, "percentage": 70.98, "elapsed_time": "1 day, 16:20:22", "remaining_time": "16:29:27", "throughput": 4653.23, "total_tokens": 675753496} {"current_steps": 11135, "total_steps": 15680, "loss": 0.25546267032623293, "lr": 1.934514943335024e-06, "epoch": 1.4202806122448979, "percentage": 71.01, "elapsed_time": "1 day, 16:21:35", "remaining_time": "16:28:25", "throughput": 4652.94, "total_tokens": 676051376} {"current_steps": 11140, "total_steps": 15680, "loss": 0.26701812744140624, "lr": 1.930559399677313e-06, "epoch": 1.4209183673469388, "percentage": 71.05, "elapsed_time": "1 day, 16:22:50", "remaining_time": "16:27:24", "throughput": 4652.58, "total_tokens": 676348080} {"current_steps": 11145, "total_steps": 15680, "loss": 0.26505365371704104, "lr": 1.9266069364176144e-06, "epoch": 1.4215561224489797, "percentage": 71.08, "elapsed_time": "1 day, 16:23:53", "remaining_time": "16:26:18", "throughput": 4652.63, "total_tokens": 676648304} {"current_steps": 11150, "total_steps": 15680, "loss": 0.26203341484069825, "lr": 1.9226575575225002e-06, "epoch": 1.4221938775510203, "percentage": 71.11, "elapsed_time": "1 day, 16:24:50", "remaining_time": "16:25:09", "throughput": 4652.88, "total_tokens": 676951648} {"current_steps": 11155, "total_steps": 15680, "loss": 0.26873183250427246, "lr": 1.918711266955448e-06, "epoch": 1.4228316326530612, "percentage": 71.14, "elapsed_time": "1 day, 16:25:57", "remaining_time": "16:24:05", "throughput": 4652.89, "total_tokens": 677263584} {"current_steps": 11160, "total_steps": 15680, "loss": 0.24950363636016845, "lr": 1.914768068676836e-06, "epoch": 1.4234693877551021, "percentage": 71.17, "elapsed_time": "1 day, 16:27:10", "remaining_time": "16:23:02", "throughput": 4652.69, "total_tokens": 677572232} {"current_steps": 11165, "total_steps": 15680, "loss": 0.2430121660232544, "lr": 1.9108279666439394e-06, "epoch": 1.4241071428571428, "percentage": 71.21, "elapsed_time": "1 day, 16:28:15", "remaining_time": "16:21:57", "throughput": 4652.73, "total_tokens": 677882176} {"current_steps": 11170, "total_steps": 15680, "loss": 0.270355224609375, "lr": 1.9068909648109258e-06, "epoch": 1.4247448979591837, "percentage": 71.24, "elapsed_time": "1 day, 16:29:20", "remaining_time": "16:20:52", "throughput": 4652.65, "total_tokens": 678173632} {"current_steps": 11175, "total_steps": 15680, "loss": 0.25338528156280515, "lr": 1.9029570671288511e-06, "epoch": 1.4253826530612246, "percentage": 71.27, "elapsed_time": "1 day, 16:30:18", "remaining_time": "16:19:44", "throughput": 4652.88, "total_tokens": 678474600} {"current_steps": 11180, "total_steps": 15680, "loss": 0.25733702182769774, "lr": 1.899026277545658e-06, "epoch": 1.4260204081632653, "percentage": 71.3, "elapsed_time": "1 day, 16:31:23", "remaining_time": "16:18:38", "throughput": 4652.89, "total_tokens": 678780864} {"current_steps": 11185, "total_steps": 15680, "loss": 0.25646467208862306, "lr": 1.895098600006164e-06, "epoch": 1.4266581632653061, "percentage": 71.33, "elapsed_time": "1 day, 16:32:41", "remaining_time": "16:17:38", "throughput": 4652.52, "total_tokens": 679088520} {"current_steps": 11190, "total_steps": 15680, "loss": 0.25247950553894044, "lr": 1.8911740384520717e-06, "epoch": 1.427295918367347, "percentage": 71.36, "elapsed_time": "1 day, 16:33:47", "remaining_time": "16:16:33", "throughput": 4652.58, "total_tokens": 679405536} {"current_steps": 11195, "total_steps": 15680, "loss": 0.2619307041168213, "lr": 1.8872525968219541e-06, "epoch": 1.4279336734693877, "percentage": 71.4, "elapsed_time": "1 day, 16:34:52", "remaining_time": "16:15:28", "throughput": 4652.58, "total_tokens": 679708992} {"current_steps": 11200, "total_steps": 15680, "loss": 0.2534599304199219, "lr": 1.8833342790512472e-06, "epoch": 1.4285714285714286, "percentage": 71.43, "elapsed_time": "1 day, 16:35:48", "remaining_time": "16:14:19", "throughput": 4652.91, "total_tokens": 680014824} {"current_steps": 11205, "total_steps": 15680, "loss": 0.25667262077331543, "lr": 1.8794190890722575e-06, "epoch": 1.4292091836734695, "percentage": 71.46, "elapsed_time": "1 day, 16:36:49", "remaining_time": "16:13:12", "throughput": 4653.02, "total_tokens": 680316552} {"current_steps": 11210, "total_steps": 15680, "loss": 0.24242887496948243, "lr": 1.875507030814156e-06, "epoch": 1.4298469387755102, "percentage": 71.49, "elapsed_time": "1 day, 16:37:53", "remaining_time": "16:12:06", "throughput": 4653.04, "total_tokens": 680617056} {"current_steps": 11215, "total_steps": 15680, "loss": 0.25613572597503664, "lr": 1.871598108202961e-06, "epoch": 1.430484693877551, "percentage": 71.52, "elapsed_time": "1 day, 16:38:53", "remaining_time": "16:10:59", "throughput": 4653.17, "total_tokens": 680913152} {"current_steps": 11220, "total_steps": 15680, "loss": 0.24273557662963868, "lr": 1.8676923251615503e-06, "epoch": 1.431122448979592, "percentage": 71.56, "elapsed_time": "1 day, 16:40:00", "remaining_time": "16:09:54", "throughput": 4653.07, "total_tokens": 681212248} {"current_steps": 11225, "total_steps": 15680, "loss": 0.25536012649536133, "lr": 1.863789685609655e-06, "epoch": 1.4317602040816326, "percentage": 71.59, "elapsed_time": "1 day, 16:41:06", "remaining_time": "16:08:49", "throughput": 4653.07, "total_tokens": 681517160} {"current_steps": 11230, "total_steps": 15680, "loss": 0.25140721797943116, "lr": 1.8598901934638402e-06, "epoch": 1.4323979591836735, "percentage": 71.62, "elapsed_time": "1 day, 16:41:59", "remaining_time": "16:07:39", "throughput": 4653.48, "total_tokens": 681824104} {"current_steps": 11235, "total_steps": 15680, "loss": 0.26719353199005125, "lr": 1.8559938526375215e-06, "epoch": 1.4330357142857144, "percentage": 71.65, "elapsed_time": "1 day, 16:43:03", "remaining_time": "16:06:34", "throughput": 4653.39, "total_tokens": 682111592} {"current_steps": 11240, "total_steps": 15680, "loss": 0.2607134819030762, "lr": 1.8521006670409481e-06, "epoch": 1.433673469387755, "percentage": 71.68, "elapsed_time": "1 day, 16:44:09", "remaining_time": "16:05:29", "throughput": 4653.41, "total_tokens": 682419768} {"current_steps": 11245, "total_steps": 15680, "loss": 0.2534268856048584, "lr": 1.8482106405812046e-06, "epoch": 1.434311224489796, "percentage": 71.72, "elapsed_time": "1 day, 16:45:15", "remaining_time": "16:04:24", "throughput": 4653.38, "total_tokens": 682722376} {"current_steps": 11250, "total_steps": 15680, "loss": 0.261114501953125, "lr": 1.8443237771622037e-06, "epoch": 1.4349489795918369, "percentage": 71.75, "elapsed_time": "1 day, 16:46:26", "remaining_time": "16:03:21", "throughput": 4653.22, "total_tokens": 683030000} {"current_steps": 11255, "total_steps": 15680, "loss": 0.2725719451904297, "lr": 1.840440080684684e-06, "epoch": 1.4355867346938775, "percentage": 71.78, "elapsed_time": "1 day, 16:47:21", "remaining_time": "16:02:11", "throughput": 4653.63, "total_tokens": 683344624} {"current_steps": 11260, "total_steps": 15680, "loss": 0.26194334030151367, "lr": 1.8365595550462068e-06, "epoch": 1.4362244897959184, "percentage": 71.81, "elapsed_time": "1 day, 16:48:30", "remaining_time": "16:01:08", "throughput": 4653.48, "total_tokens": 683647312} {"current_steps": 11265, "total_steps": 15680, "loss": 0.25354886054992676, "lr": 1.8326822041411524e-06, "epoch": 1.436862244897959, "percentage": 71.84, "elapsed_time": "1 day, 16:49:27", "remaining_time": "15:59:59", "throughput": 4653.79, "total_tokens": 683953976} {"current_steps": 11270, "total_steps": 15680, "loss": 0.2550026893615723, "lr": 1.828808031860707e-06, "epoch": 1.4375, "percentage": 71.88, "elapsed_time": "1 day, 16:50:37", "remaining_time": "15:58:56", "throughput": 4653.53, "total_tokens": 684245328} {"current_steps": 11275, "total_steps": 15680, "loss": 0.255743408203125, "lr": 1.824937042092879e-06, "epoch": 1.438137755102041, "percentage": 71.91, "elapsed_time": "1 day, 16:51:40", "remaining_time": "15:57:50", "throughput": 4653.51, "total_tokens": 684534456} {"current_steps": 11280, "total_steps": 15680, "loss": 0.2595668792724609, "lr": 1.8210692387224776e-06, "epoch": 1.4387755102040816, "percentage": 71.94, "elapsed_time": "1 day, 16:52:32", "remaining_time": "15:56:40", "throughput": 4653.91, "total_tokens": 684835696} {"current_steps": 11285, "total_steps": 15680, "loss": 0.262544584274292, "lr": 1.8172046256311087e-06, "epoch": 1.4394132653061225, "percentage": 71.97, "elapsed_time": "1 day, 16:53:40", "remaining_time": "15:55:35", "throughput": 4653.85, "total_tokens": 685141560} {"current_steps": 11290, "total_steps": 15680, "loss": 0.24910640716552734, "lr": 1.8133432066971823e-06, "epoch": 1.4400510204081631, "percentage": 72.0, "elapsed_time": "1 day, 16:54:53", "remaining_time": "15:54:33", "throughput": 4653.59, "total_tokens": 685444368} {"current_steps": 11295, "total_steps": 15680, "loss": 0.267687463760376, "lr": 1.8094849857959074e-06, "epoch": 1.440688775510204, "percentage": 72.03, "elapsed_time": "1 day, 16:56:03", "remaining_time": "15:53:30", "throughput": 4653.35, "total_tokens": 685735024} {"current_steps": 11300, "total_steps": 15680, "loss": 0.25908875465393066, "lr": 1.8056299667992721e-06, "epoch": 1.441326530612245, "percentage": 72.07, "elapsed_time": "1 day, 16:57:04", "remaining_time": "15:52:23", "throughput": 4653.42, "total_tokens": 686029680} {"current_steps": 11305, "total_steps": 15680, "loss": 0.2524980068206787, "lr": 1.8017781535760581e-06, "epoch": 1.4419642857142856, "percentage": 72.1, "elapsed_time": "1 day, 16:58:10", "remaining_time": "15:51:18", "throughput": 4653.33, "total_tokens": 686323368} {"current_steps": 11310, "total_steps": 15680, "loss": 0.25349082946777346, "lr": 1.7979295499918338e-06, "epoch": 1.4426020408163265, "percentage": 72.13, "elapsed_time": "1 day, 16:59:18", "remaining_time": "15:50:14", "throughput": 4653.21, "total_tokens": 686619760} {"current_steps": 11315, "total_steps": 15680, "loss": 0.26335620880126953, "lr": 1.7940841599089364e-06, "epoch": 1.4432397959183674, "percentage": 72.16, "elapsed_time": "1 day, 17:00:11", "remaining_time": "15:49:04", "throughput": 4653.68, "total_tokens": 686937152} {"current_steps": 11320, "total_steps": 15680, "loss": 0.2568617582321167, "lr": 1.790241987186485e-06, "epoch": 1.443877551020408, "percentage": 72.19, "elapsed_time": "1 day, 17:01:18", "remaining_time": "15:47:59", "throughput": 4653.58, "total_tokens": 687234768} {"current_steps": 11325, "total_steps": 15680, "loss": 0.2553276300430298, "lr": 1.7864030356803685e-06, "epoch": 1.444515306122449, "percentage": 72.23, "elapsed_time": "1 day, 17:02:17", "remaining_time": "15:46:52", "throughput": 4653.76, "total_tokens": 687535408} {"current_steps": 11330, "total_steps": 15680, "loss": 0.26634774208068845, "lr": 1.7825673092432433e-06, "epoch": 1.4451530612244898, "percentage": 72.26, "elapsed_time": "1 day, 17:03:15", "remaining_time": "15:45:44", "throughput": 4654.02, "total_tokens": 687842240} {"current_steps": 11335, "total_steps": 15680, "loss": 0.24077410697937013, "lr": 1.7787348117245278e-06, "epoch": 1.4457908163265305, "percentage": 72.29, "elapsed_time": "1 day, 17:04:11", "remaining_time": "15:44:35", "throughput": 4654.28, "total_tokens": 688143488} {"current_steps": 11340, "total_steps": 15680, "loss": 0.24639506340026857, "lr": 1.7749055469704013e-06, "epoch": 1.4464285714285714, "percentage": 72.32, "elapsed_time": "1 day, 17:05:25", "remaining_time": "15:43:33", "throughput": 4653.96, "total_tokens": 688438208} {"current_steps": 11345, "total_steps": 15680, "loss": 0.2675870418548584, "lr": 1.771079518823799e-06, "epoch": 1.4470663265306123, "percentage": 72.35, "elapsed_time": "1 day, 17:06:38", "remaining_time": "15:42:31", "throughput": 4653.78, "total_tokens": 688750184} {"current_steps": 11350, "total_steps": 15680, "loss": 0.24507179260253906, "lr": 1.7672567311244065e-06, "epoch": 1.447704081632653, "percentage": 72.39, "elapsed_time": "1 day, 17:07:47", "remaining_time": "15:41:27", "throughput": 4653.62, "total_tokens": 689051608} {"current_steps": 11355, "total_steps": 15680, "loss": 0.251706600189209, "lr": 1.7634371877086587e-06, "epoch": 1.4483418367346939, "percentage": 72.42, "elapsed_time": "1 day, 17:08:42", "remaining_time": "15:40:18", "throughput": 4653.84, "total_tokens": 689338368} {"current_steps": 11360, "total_steps": 15680, "loss": 0.2331090450286865, "lr": 1.7596208924097336e-06, "epoch": 1.4489795918367347, "percentage": 72.45, "elapsed_time": "1 day, 17:09:55", "remaining_time": "15:39:16", "throughput": 4653.61, "total_tokens": 689645832} {"current_steps": 11365, "total_steps": 15680, "loss": 0.2676694393157959, "lr": 1.7558078490575531e-06, "epoch": 1.4496173469387754, "percentage": 72.48, "elapsed_time": "1 day, 17:10:58", "remaining_time": "15:38:10", "throughput": 4653.71, "total_tokens": 689953024} {"current_steps": 11370, "total_steps": 15680, "loss": 0.26604576110839845, "lr": 1.7519980614787673e-06, "epoch": 1.4502551020408163, "percentage": 72.51, "elapsed_time": "1 day, 17:11:50", "remaining_time": "15:36:59", "throughput": 4654.2, "total_tokens": 690265872} {"current_steps": 11375, "total_steps": 15680, "loss": 0.2404193878173828, "lr": 1.748191533496766e-06, "epoch": 1.4508928571428572, "percentage": 72.54, "elapsed_time": "1 day, 17:13:01", "remaining_time": "15:35:56", "throughput": 4653.94, "total_tokens": 690559424} {"current_steps": 11380, "total_steps": 15680, "loss": 0.261887264251709, "lr": 1.7443882689316693e-06, "epoch": 1.4515306122448979, "percentage": 72.58, "elapsed_time": "1 day, 17:14:06", "remaining_time": "15:34:51", "throughput": 4653.97, "total_tokens": 690867440} {"current_steps": 11385, "total_steps": 15680, "loss": 0.2412036657333374, "lr": 1.7405882716003154e-06, "epoch": 1.4521683673469388, "percentage": 72.61, "elapsed_time": "1 day, 17:15:03", "remaining_time": "15:33:42", "throughput": 4654.32, "total_tokens": 691179896} {"current_steps": 11390, "total_steps": 15680, "loss": 0.2515883207321167, "lr": 1.7367915453162653e-06, "epoch": 1.4528061224489797, "percentage": 72.64, "elapsed_time": "1 day, 17:16:15", "remaining_time": "15:32:40", "throughput": 4654.08, "total_tokens": 691479832} {"current_steps": 11395, "total_steps": 15680, "loss": 0.25553102493286134, "lr": 1.732998093889805e-06, "epoch": 1.4534438775510203, "percentage": 72.67, "elapsed_time": "1 day, 17:17:23", "remaining_time": "15:31:36", "throughput": 4653.88, "total_tokens": 691770328} {"current_steps": 11400, "total_steps": 15680, "loss": 0.2637500286102295, "lr": 1.7292079211279229e-06, "epoch": 1.4540816326530612, "percentage": 72.7, "elapsed_time": "1 day, 17:18:27", "remaining_time": "15:30:30", "throughput": 4653.74, "total_tokens": 692047224} {"current_steps": 11405, "total_steps": 15680, "loss": 0.2611916303634644, "lr": 1.7254210308343233e-06, "epoch": 1.4547193877551021, "percentage": 72.74, "elapsed_time": "1 day, 17:19:32", "remaining_time": "15:29:25", "throughput": 4653.78, "total_tokens": 692351568} {"current_steps": 11410, "total_steps": 15680, "loss": 0.2512598991394043, "lr": 1.721637426809415e-06, "epoch": 1.4553571428571428, "percentage": 72.77, "elapsed_time": "1 day, 17:20:44", "remaining_time": "15:28:22", "throughput": 4653.5, "total_tokens": 692648960} {"current_steps": 11415, "total_steps": 15680, "loss": 0.2514254093170166, "lr": 1.7178571128503097e-06, "epoch": 1.4559948979591837, "percentage": 72.8, "elapsed_time": "1 day, 17:21:55", "remaining_time": "15:27:19", "throughput": 4653.28, "total_tokens": 692945064} {"current_steps": 11420, "total_steps": 15680, "loss": 0.26080052852630614, "lr": 1.7140800927508162e-06, "epoch": 1.4566326530612246, "percentage": 72.83, "elapsed_time": "1 day, 17:23:00", "remaining_time": "15:26:14", "throughput": 4653.3, "total_tokens": 693250712} {"current_steps": 11425, "total_steps": 15680, "loss": 0.25720174312591554, "lr": 1.7103063703014372e-06, "epoch": 1.4572704081632653, "percentage": 72.86, "elapsed_time": "1 day, 17:24:11", "remaining_time": "15:25:10", "throughput": 4653.15, "total_tokens": 693557616} {"current_steps": 11430, "total_steps": 15680, "loss": 0.27224562168121336, "lr": 1.706535949289368e-06, "epoch": 1.4579081632653061, "percentage": 72.9, "elapsed_time": "1 day, 17:25:24", "remaining_time": "15:24:08", "throughput": 4652.92, "total_tokens": 693865096} {"current_steps": 11435, "total_steps": 15680, "loss": 0.26955580711364746, "lr": 1.7027688334984881e-06, "epoch": 1.458545918367347, "percentage": 72.93, "elapsed_time": "1 day, 17:26:34", "remaining_time": "15:23:05", "throughput": 4652.76, "total_tokens": 694167488} {"current_steps": 11440, "total_steps": 15680, "loss": 0.24876112937927247, "lr": 1.6990050267093621e-06, "epoch": 1.4591836734693877, "percentage": 72.96, "elapsed_time": "1 day, 17:27:26", "remaining_time": "15:21:55", "throughput": 4653.18, "total_tokens": 694471352} {"current_steps": 11445, "total_steps": 15680, "loss": 0.23597230911254882, "lr": 1.6952445326992327e-06, "epoch": 1.4598214285714286, "percentage": 72.99, "elapsed_time": "1 day, 17:28:33", "remaining_time": "15:20:50", "throughput": 4653.02, "total_tokens": 694760392} {"current_steps": 11450, "total_steps": 15680, "loss": 0.26068577766418455, "lr": 1.6914873552420185e-06, "epoch": 1.4604591836734695, "percentage": 73.02, "elapsed_time": "1 day, 17:29:50", "remaining_time": "15:19:49", "throughput": 4652.6, "total_tokens": 695056072} {"current_steps": 11455, "total_steps": 15680, "loss": 0.26918802261352537, "lr": 1.687733498108311e-06, "epoch": 1.4610969387755102, "percentage": 73.05, "elapsed_time": "1 day, 17:30:48", "remaining_time": "15:18:41", "throughput": 4652.88, "total_tokens": 695365848} {"current_steps": 11460, "total_steps": 15680, "loss": 0.24681711196899414, "lr": 1.6839829650653632e-06, "epoch": 1.461734693877551, "percentage": 73.09, "elapsed_time": "1 day, 17:31:51", "remaining_time": "15:17:35", "throughput": 4652.9, "total_tokens": 695661496} {"current_steps": 11465, "total_steps": 15680, "loss": 0.2575855016708374, "lr": 1.6802357598771014e-06, "epoch": 1.462372448979592, "percentage": 73.12, "elapsed_time": "1 day, 17:32:57", "remaining_time": "15:16:30", "throughput": 4652.83, "total_tokens": 695960184} {"current_steps": 11470, "total_steps": 15680, "loss": 0.25083796977996825, "lr": 1.6764918863041079e-06, "epoch": 1.4630102040816326, "percentage": 73.15, "elapsed_time": "1 day, 17:34:00", "remaining_time": "15:15:24", "throughput": 4652.88, "total_tokens": 696258456} {"current_steps": 11475, "total_steps": 15680, "loss": 0.23392910957336427, "lr": 1.6727513481036167e-06, "epoch": 1.4636479591836735, "percentage": 73.18, "elapsed_time": "1 day, 17:35:09", "remaining_time": "15:14:20", "throughput": 4652.76, "total_tokens": 696562944} {"current_steps": 11480, "total_steps": 15680, "loss": 0.2381272792816162, "lr": 1.6690141490295259e-06, "epoch": 1.4642857142857144, "percentage": 73.21, "elapsed_time": "1 day, 17:36:21", "remaining_time": "15:13:17", "throughput": 4652.54, "total_tokens": 696861776} {"current_steps": 11485, "total_steps": 15680, "loss": 0.2412243127822876, "lr": 1.6652802928323698e-06, "epoch": 1.464923469387755, "percentage": 73.25, "elapsed_time": "1 day, 17:37:36", "remaining_time": "15:12:16", "throughput": 4652.28, "total_tokens": 697176216} {"current_steps": 11490, "total_steps": 15680, "loss": 0.25841598510742186, "lr": 1.6615497832593365e-06, "epoch": 1.465561224489796, "percentage": 73.28, "elapsed_time": "1 day, 17:38:43", "remaining_time": "15:11:11", "throughput": 4652.24, "total_tokens": 697478792} {"current_steps": 11495, "total_steps": 15680, "loss": 0.2742449760437012, "lr": 1.6578226240542528e-06, "epoch": 1.4661989795918369, "percentage": 73.31, "elapsed_time": "1 day, 17:39:48", "remaining_time": "15:10:06", "throughput": 4652.26, "total_tokens": 697785848} {"current_steps": 11500, "total_steps": 15680, "loss": 0.2669424533843994, "lr": 1.6540988189575823e-06, "epoch": 1.4668367346938775, "percentage": 73.34, "elapsed_time": "1 day, 17:40:56", "remaining_time": "15:09:02", "throughput": 4652.3, "total_tokens": 698107216} {"current_steps": 11505, "total_steps": 15680, "loss": 0.2652735710144043, "lr": 1.6503783717064247e-06, "epoch": 1.4674744897959184, "percentage": 73.37, "elapsed_time": "1 day, 17:42:13", "remaining_time": "15:08:01", "throughput": 4651.97, "total_tokens": 698415200} {"current_steps": 11510, "total_steps": 15680, "loss": 0.2547138690948486, "lr": 1.6466612860345083e-06, "epoch": 1.468112244897959, "percentage": 73.41, "elapsed_time": "1 day, 17:43:22", "remaining_time": "15:06:57", "throughput": 4651.85, "total_tokens": 698717160} {"current_steps": 11515, "total_steps": 15680, "loss": 0.2531946897506714, "lr": 1.6429475656721878e-06, "epoch": 1.46875, "percentage": 73.44, "elapsed_time": "1 day, 17:44:33", "remaining_time": "15:05:54", "throughput": 4651.64, "total_tokens": 699019328} {"current_steps": 11520, "total_steps": 15680, "loss": 0.24852967262268066, "lr": 1.6392372143464407e-06, "epoch": 1.469387755102041, "percentage": 73.47, "elapsed_time": "1 day, 17:45:26", "remaining_time": "15:04:44", "throughput": 4652.1, "total_tokens": 699332520} {"current_steps": 11525, "total_steps": 15680, "loss": 0.2493694543838501, "lr": 1.635530235780865e-06, "epoch": 1.4700255102040816, "percentage": 73.5, "elapsed_time": "1 day, 17:46:39", "remaining_time": "15:03:42", "throughput": 4651.79, "total_tokens": 699626568} {"current_steps": 11530, "total_steps": 15680, "loss": 0.239760160446167, "lr": 1.6318266336956713e-06, "epoch": 1.4706632653061225, "percentage": 73.53, "elapsed_time": "1 day, 17:47:53", "remaining_time": "15:02:39", "throughput": 4651.49, "total_tokens": 699925336} {"current_steps": 11535, "total_steps": 15680, "loss": 0.23812055587768555, "lr": 1.6281264118076833e-06, "epoch": 1.4713010204081631, "percentage": 73.57, "elapsed_time": "1 day, 17:49:00", "remaining_time": "15:01:35", "throughput": 4651.46, "total_tokens": 700232720} {"current_steps": 11540, "total_steps": 15680, "loss": 0.2438938856124878, "lr": 1.6244295738303323e-06, "epoch": 1.471938775510204, "percentage": 73.6, "elapsed_time": "1 day, 17:50:11", "remaining_time": "15:00:32", "throughput": 4651.21, "total_tokens": 700527648} {"current_steps": 11545, "total_steps": 15680, "loss": 0.2975417375564575, "lr": 1.6207361234736535e-06, "epoch": 1.472576530612245, "percentage": 73.63, "elapsed_time": "1 day, 17:51:03", "remaining_time": "14:59:22", "throughput": 4651.72, "total_tokens": 700843920} {"current_steps": 11550, "total_steps": 15680, "loss": 0.25352983474731444, "lr": 1.6170460644442814e-06, "epoch": 1.4732142857142856, "percentage": 73.66, "elapsed_time": "1 day, 17:52:10", "remaining_time": "14:58:17", "throughput": 4651.66, "total_tokens": 701144312} {"current_steps": 11555, "total_steps": 15680, "loss": 0.26451525688171384, "lr": 1.6133594004454512e-06, "epoch": 1.4738520408163265, "percentage": 73.69, "elapsed_time": "1 day, 17:53:19", "remaining_time": "14:57:13", "throughput": 4651.52, "total_tokens": 701449824} {"current_steps": 11560, "total_steps": 15680, "loss": 0.26746971607208253, "lr": 1.6096761351769813e-06, "epoch": 1.4744897959183674, "percentage": 73.72, "elapsed_time": "1 day, 17:54:27", "remaining_time": "14:56:09", "throughput": 4651.39, "total_tokens": 701742128} {"current_steps": 11565, "total_steps": 15680, "loss": 0.2517268657684326, "lr": 1.6059962723352912e-06, "epoch": 1.475127551020408, "percentage": 73.76, "elapsed_time": "1 day, 17:55:29", "remaining_time": "14:55:02", "throughput": 4651.55, "total_tokens": 702054784} {"current_steps": 11570, "total_steps": 15680, "loss": 0.2649550437927246, "lr": 1.6023198156133796e-06, "epoch": 1.475765306122449, "percentage": 73.79, "elapsed_time": "1 day, 17:56:34", "remaining_time": "14:53:57", "throughput": 4651.51, "total_tokens": 702354392} {"current_steps": 11575, "total_steps": 15680, "loss": 0.23227922916412352, "lr": 1.5986467687008256e-06, "epoch": 1.4764030612244898, "percentage": 73.82, "elapsed_time": "1 day, 17:57:34", "remaining_time": "14:52:50", "throughput": 4651.7, "total_tokens": 702659368} {"current_steps": 11580, "total_steps": 15680, "loss": 0.27329676151275634, "lr": 1.5949771352837873e-06, "epoch": 1.4770408163265305, "percentage": 73.85, "elapsed_time": "1 day, 17:58:43", "remaining_time": "14:51:46", "throughput": 4651.65, "total_tokens": 702974120} {"current_steps": 11585, "total_steps": 15680, "loss": 0.2482689619064331, "lr": 1.5913109190450033e-06, "epoch": 1.4776785714285714, "percentage": 73.88, "elapsed_time": "1 day, 17:59:59", "remaining_time": "14:50:44", "throughput": 4651.32, "total_tokens": 703274640} {"current_steps": 11590, "total_steps": 15680, "loss": 0.25067954063415526, "lr": 1.5876481236637725e-06, "epoch": 1.4783163265306123, "percentage": 73.92, "elapsed_time": "1 day, 18:01:07", "remaining_time": "14:49:40", "throughput": 4651.19, "total_tokens": 703571232} {"current_steps": 11595, "total_steps": 15680, "loss": 0.24625492095947266, "lr": 1.5839887528159664e-06, "epoch": 1.478954081632653, "percentage": 73.95, "elapsed_time": "1 day, 18:02:15", "remaining_time": "14:48:36", "throughput": 4651.16, "total_tokens": 703886312} {"current_steps": 11600, "total_steps": 15680, "loss": 0.27662837505340576, "lr": 1.580332810174024e-06, "epoch": 1.4795918367346939, "percentage": 73.98, "elapsed_time": "1 day, 18:03:31", "remaining_time": "14:47:34", "throughput": 4650.9, "total_tokens": 704198792} {"current_steps": 11605, "total_steps": 15680, "loss": 0.2493530035018921, "lr": 1.5766802994069336e-06, "epoch": 1.4802295918367347, "percentage": 74.01, "elapsed_time": "1 day, 18:04:31", "remaining_time": "14:46:27", "throughput": 4651.16, "total_tokens": 704515848} {"current_steps": 11610, "total_steps": 15680, "loss": 0.27558221817016604, "lr": 1.573031224180247e-06, "epoch": 1.4808673469387754, "percentage": 74.04, "elapsed_time": "1 day, 18:05:35", "remaining_time": "14:45:22", "throughput": 4651.19, "total_tokens": 704821864} {"current_steps": 11615, "total_steps": 15680, "loss": 0.23457353115081786, "lr": 1.5693855881560654e-06, "epoch": 1.4815051020408163, "percentage": 74.08, "elapsed_time": "1 day, 18:06:42", "remaining_time": "14:44:17", "throughput": 4651.21, "total_tokens": 705133552} {"current_steps": 11620, "total_steps": 15680, "loss": 0.25937981605529786, "lr": 1.5657433949930406e-06, "epoch": 1.4821428571428572, "percentage": 74.11, "elapsed_time": "1 day, 18:07:56", "remaining_time": "14:43:15", "throughput": 4650.96, "total_tokens": 705442408} {"current_steps": 11625, "total_steps": 15680, "loss": 0.2675338268280029, "lr": 1.5621046483463663e-06, "epoch": 1.4827806122448979, "percentage": 74.14, "elapsed_time": "1 day, 18:09:05", "remaining_time": "14:42:11", "throughput": 4650.94, "total_tokens": 705756872} {"current_steps": 11630, "total_steps": 15680, "loss": 0.2641123294830322, "lr": 1.5584693518677796e-06, "epoch": 1.4834183673469388, "percentage": 74.17, "elapsed_time": "1 day, 18:10:16", "remaining_time": "14:41:08", "throughput": 4650.79, "total_tokens": 706064448} {"current_steps": 11635, "total_steps": 15680, "loss": 0.24312682151794435, "lr": 1.554837509205554e-06, "epoch": 1.4840561224489797, "percentage": 74.2, "elapsed_time": "1 day, 18:11:22", "remaining_time": "14:40:03", "throughput": 4650.75, "total_tokens": 706367832} {"current_steps": 11640, "total_steps": 15680, "loss": 0.2624907732009888, "lr": 1.5512091240044996e-06, "epoch": 1.4846938775510203, "percentage": 74.23, "elapsed_time": "1 day, 18:12:22", "remaining_time": "14:38:55", "throughput": 4650.99, "total_tokens": 706681984} {"current_steps": 11645, "total_steps": 15680, "loss": 0.27055678367614744, "lr": 1.5475841999059487e-06, "epoch": 1.4853316326530612, "percentage": 74.27, "elapsed_time": "1 day, 18:13:25", "remaining_time": "14:37:50", "throughput": 4651.06, "total_tokens": 706987120} {"current_steps": 11650, "total_steps": 15680, "loss": 0.2421438217163086, "lr": 1.5439627405477714e-06, "epoch": 1.4859693877551021, "percentage": 74.3, "elapsed_time": "1 day, 18:14:25", "remaining_time": "14:36:42", "throughput": 4651.29, "total_tokens": 707300040} {"current_steps": 11655, "total_steps": 15680, "loss": 0.23953189849853515, "lr": 1.5403447495643542e-06, "epoch": 1.4866071428571428, "percentage": 74.33, "elapsed_time": "1 day, 18:15:39", "remaining_time": "14:35:40", "throughput": 4651.03, "total_tokens": 707605520} {"current_steps": 11660, "total_steps": 15680, "loss": 0.2567351579666138, "lr": 1.5367302305866017e-06, "epoch": 1.4872448979591837, "percentage": 74.36, "elapsed_time": "1 day, 18:16:48", "remaining_time": "14:34:36", "throughput": 4650.91, "total_tokens": 707906880} {"current_steps": 11665, "total_steps": 15680, "loss": 0.25123307704925535, "lr": 1.5331191872419349e-06, "epoch": 1.4878826530612246, "percentage": 74.39, "elapsed_time": "1 day, 18:17:57", "remaining_time": "14:33:32", "throughput": 4650.8, "total_tokens": 708213592} {"current_steps": 11670, "total_steps": 15680, "loss": 0.2430964231491089, "lr": 1.5295116231542935e-06, "epoch": 1.4885204081632653, "percentage": 74.43, "elapsed_time": "1 day, 18:19:04", "remaining_time": "14:32:28", "throughput": 4650.67, "total_tokens": 708503720} {"current_steps": 11675, "total_steps": 15680, "loss": 0.25212526321411133, "lr": 1.5259075419441144e-06, "epoch": 1.4891581632653061, "percentage": 74.46, "elapsed_time": "1 day, 18:20:11", "remaining_time": "14:31:23", "throughput": 4650.63, "total_tokens": 708809960} {"current_steps": 11680, "total_steps": 15680, "loss": 0.2657268762588501, "lr": 1.5223069472283464e-06, "epoch": 1.489795918367347, "percentage": 74.49, "elapsed_time": "1 day, 18:21:08", "remaining_time": "14:30:15", "throughput": 4650.91, "total_tokens": 709116352} {"current_steps": 11685, "total_steps": 15680, "loss": 0.22965846061706544, "lr": 1.5187098426204411e-06, "epoch": 1.4904336734693877, "percentage": 74.52, "elapsed_time": "1 day, 18:22:16", "remaining_time": "14:29:10", "throughput": 4650.68, "total_tokens": 709399184} {"current_steps": 11690, "total_steps": 15680, "loss": 0.23941805362701415, "lr": 1.5151162317303398e-06, "epoch": 1.4910714285714286, "percentage": 74.55, "elapsed_time": "1 day, 18:23:25", "remaining_time": "14:28:06", "throughput": 4650.5, "total_tokens": 709692272} {"current_steps": 11695, "total_steps": 15680, "loss": 0.26945855617523196, "lr": 1.5115261181644842e-06, "epoch": 1.4917091836734695, "percentage": 74.59, "elapsed_time": "1 day, 18:24:42", "remaining_time": "14:27:05", "throughput": 4650.22, "total_tokens": 710004984} {"current_steps": 11700, "total_steps": 15680, "loss": 0.23934993743896485, "lr": 1.5079395055258027e-06, "epoch": 1.4923469387755102, "percentage": 74.62, "elapsed_time": "1 day, 18:25:45", "remaining_time": "14:25:59", "throughput": 4650.31, "total_tokens": 710313688} {"current_steps": 11705, "total_steps": 15680, "loss": 0.22617621421813966, "lr": 1.5043563974137132e-06, "epoch": 1.492984693877551, "percentage": 74.65, "elapsed_time": "1 day, 18:26:47", "remaining_time": "14:24:53", "throughput": 4650.4, "total_tokens": 710618288} {"current_steps": 11710, "total_steps": 15680, "loss": 0.2418062686920166, "lr": 1.5007767974241133e-06, "epoch": 1.493622448979592, "percentage": 74.68, "elapsed_time": "1 day, 18:27:53", "remaining_time": "14:23:48", "throughput": 4650.44, "total_tokens": 710926392} {"current_steps": 11715, "total_steps": 15680, "loss": 0.2354290008544922, "lr": 1.497200709149383e-06, "epoch": 1.4942602040816326, "percentage": 74.71, "elapsed_time": "1 day, 18:28:53", "remaining_time": "14:22:41", "throughput": 4650.58, "total_tokens": 711230608} {"current_steps": 11720, "total_steps": 15680, "loss": 0.2707733154296875, "lr": 1.493628136178376e-06, "epoch": 1.4948979591836735, "percentage": 74.74, "elapsed_time": "1 day, 18:30:03", "remaining_time": "14:21:37", "throughput": 4650.39, "total_tokens": 711527456} {"current_steps": 11725, "total_steps": 15680, "loss": 0.2669675827026367, "lr": 1.49005908209642e-06, "epoch": 1.4955357142857144, "percentage": 74.78, "elapsed_time": "1 day, 18:31:07", "remaining_time": "14:20:31", "throughput": 4650.5, "total_tokens": 711838440} {"current_steps": 11730, "total_steps": 15680, "loss": 0.24235136508941652, "lr": 1.4864935504853062e-06, "epoch": 1.496173469387755, "percentage": 74.81, "elapsed_time": "1 day, 18:32:21", "remaining_time": "14:19:29", "throughput": 4650.27, "total_tokens": 712150208} {"current_steps": 11735, "total_steps": 15680, "loss": 0.2580772876739502, "lr": 1.4829315449232984e-06, "epoch": 1.496811224489796, "percentage": 74.84, "elapsed_time": "1 day, 18:33:24", "remaining_time": "14:18:23", "throughput": 4650.38, "total_tokens": 712457024} {"current_steps": 11740, "total_steps": 15680, "loss": 0.2615934133529663, "lr": 1.4793730689851187e-06, "epoch": 1.4974489795918369, "percentage": 74.87, "elapsed_time": "1 day, 18:34:29", "remaining_time": "14:17:17", "throughput": 4650.37, "total_tokens": 712757864} {"current_steps": 11745, "total_steps": 15680, "loss": 0.24282798767089844, "lr": 1.4758181262419425e-06, "epoch": 1.4980867346938775, "percentage": 74.9, "elapsed_time": "1 day, 18:35:34", "remaining_time": "14:16:12", "throughput": 4650.47, "total_tokens": 713075888} {"current_steps": 11750, "total_steps": 15680, "loss": 0.23960046768188475, "lr": 1.4722667202614037e-06, "epoch": 1.4987244897959184, "percentage": 74.94, "elapsed_time": "1 day, 18:36:28", "remaining_time": "14:15:03", "throughput": 4650.75, "total_tokens": 713371464} {"current_steps": 11755, "total_steps": 15680, "loss": 0.23960208892822266, "lr": 1.4687188546075903e-06, "epoch": 1.499362244897959, "percentage": 74.97, "elapsed_time": "1 day, 18:37:38", "remaining_time": "14:13:59", "throughput": 4650.48, "total_tokens": 713657632} {"current_steps": 11760, "total_steps": 15680, "loss": 0.258426833152771, "lr": 1.4651745328410289e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "1 day, 18:38:47", "remaining_time": "14:12:55", "throughput": 4650.34, "total_tokens": 713955144} {"current_steps": 11765, "total_steps": 15680, "loss": 0.24520792961120605, "lr": 1.4616337585186941e-06, "epoch": 1.5006377551020407, "percentage": 75.03, "elapsed_time": "1 day, 18:39:54", "remaining_time": "14:11:51", "throughput": 4650.27, "total_tokens": 714257392} {"current_steps": 11770, "total_steps": 15680, "loss": 0.26330649852752686, "lr": 1.4580965351940045e-06, "epoch": 1.5012755102040818, "percentage": 75.06, "elapsed_time": "1 day, 18:41:04", "remaining_time": "14:10:47", "throughput": 4650.19, "total_tokens": 714569056} {"current_steps": 11775, "total_steps": 15680, "loss": 0.23243155479431152, "lr": 1.454562866416806e-06, "epoch": 1.5019132653061225, "percentage": 75.1, "elapsed_time": "1 day, 18:41:58", "remaining_time": "14:09:38", "throughput": 4650.6, "total_tokens": 714881472} {"current_steps": 11780, "total_steps": 15680, "loss": 0.2522455930709839, "lr": 1.4510327557333843e-06, "epoch": 1.5025510204081631, "percentage": 75.13, "elapsed_time": "1 day, 18:43:13", "remaining_time": "14:08:36", "throughput": 4650.35, "total_tokens": 715192808} {"current_steps": 11785, "total_steps": 15680, "loss": 0.2767788410186768, "lr": 1.4475062066864516e-06, "epoch": 1.5031887755102042, "percentage": 75.16, "elapsed_time": "1 day, 18:44:13", "remaining_time": "14:07:29", "throughput": 4650.62, "total_tokens": 715515792} {"current_steps": 11790, "total_steps": 15680, "loss": 0.24577155113220214, "lr": 1.4439832228151457e-06, "epoch": 1.503826530612245, "percentage": 75.19, "elapsed_time": "1 day, 18:45:01", "remaining_time": "14:06:18", "throughput": 4651.23, "total_tokens": 715831936} {"current_steps": 11795, "total_steps": 15680, "loss": 0.2581317901611328, "lr": 1.4404638076550276e-06, "epoch": 1.5044642857142856, "percentage": 75.22, "elapsed_time": "1 day, 18:45:53", "remaining_time": "14:05:08", "throughput": 4651.63, "total_tokens": 716136120} {"current_steps": 11800, "total_steps": 15680, "loss": 0.2634751319885254, "lr": 1.4369479647380758e-06, "epoch": 1.5051020408163265, "percentage": 75.26, "elapsed_time": "1 day, 18:47:02", "remaining_time": "14:04:04", "throughput": 4651.55, "total_tokens": 716445392} {"current_steps": 11805, "total_steps": 15680, "loss": 0.2595194339752197, "lr": 1.4334356975926843e-06, "epoch": 1.5057397959183674, "percentage": 75.29, "elapsed_time": "1 day, 18:48:17", "remaining_time": "14:03:02", "throughput": 4651.24, "total_tokens": 716746224} {"current_steps": 11810, "total_steps": 15680, "loss": 0.2642998218536377, "lr": 1.429927009743659e-06, "epoch": 1.506377551020408, "percentage": 75.32, "elapsed_time": "1 day, 18:49:15", "remaining_time": "14:01:54", "throughput": 4651.56, "total_tokens": 717062648} {"current_steps": 11815, "total_steps": 15680, "loss": 0.26960577964782717, "lr": 1.4264219047122125e-06, "epoch": 1.507015306122449, "percentage": 75.35, "elapsed_time": "1 day, 18:50:13", "remaining_time": "14:00:47", "throughput": 4651.79, "total_tokens": 717368720} {"current_steps": 11820, "total_steps": 15680, "loss": 0.25219082832336426, "lr": 1.422920386015963e-06, "epoch": 1.5076530612244898, "percentage": 75.38, "elapsed_time": "1 day, 18:51:06", "remaining_time": "13:59:38", "throughput": 4652.15, "total_tokens": 717673224} {"current_steps": 11825, "total_steps": 15680, "loss": 0.26119270324707033, "lr": 1.4194224571689286e-06, "epoch": 1.5082908163265305, "percentage": 75.41, "elapsed_time": "1 day, 18:52:15", "remaining_time": "13:58:33", "throughput": 4652.05, "total_tokens": 717975600} {"current_steps": 11830, "total_steps": 15680, "loss": 0.26681981086730955, "lr": 1.4159281216815269e-06, "epoch": 1.5089285714285714, "percentage": 75.45, "elapsed_time": "1 day, 18:53:32", "remaining_time": "13:57:32", "throughput": 4651.64, "total_tokens": 718269840} {"current_steps": 11835, "total_steps": 15680, "loss": 0.24793519973754882, "lr": 1.412437383060563e-06, "epoch": 1.5095663265306123, "percentage": 75.48, "elapsed_time": "1 day, 18:54:31", "remaining_time": "13:56:25", "throughput": 4651.87, "total_tokens": 718583704} {"current_steps": 11840, "total_steps": 15680, "loss": 0.25735931396484374, "lr": 1.4089502448092418e-06, "epoch": 1.510204081632653, "percentage": 75.51, "elapsed_time": "1 day, 18:55:37", "remaining_time": "13:55:20", "throughput": 4651.87, "total_tokens": 718886464} {"current_steps": 11845, "total_steps": 15680, "loss": 0.2530500411987305, "lr": 1.4054667104271497e-06, "epoch": 1.5108418367346939, "percentage": 75.54, "elapsed_time": "1 day, 18:56:42", "remaining_time": "13:54:14", "throughput": 4651.79, "total_tokens": 719178912} {"current_steps": 11850, "total_steps": 15680, "loss": 0.25861315727233886, "lr": 1.4019867834102525e-06, "epoch": 1.5114795918367347, "percentage": 75.57, "elapsed_time": "1 day, 18:57:46", "remaining_time": "13:53:09", "throughput": 4651.88, "total_tokens": 719488832} {"current_steps": 11855, "total_steps": 15680, "loss": 0.23546905517578126, "lr": 1.398510467250906e-06, "epoch": 1.5121173469387754, "percentage": 75.61, "elapsed_time": "1 day, 18:59:01", "remaining_time": "13:52:07", "throughput": 4651.55, "total_tokens": 719789416} {"current_steps": 11860, "total_steps": 15680, "loss": 0.2624575853347778, "lr": 1.3950377654378312e-06, "epoch": 1.5127551020408163, "percentage": 75.64, "elapsed_time": "1 day, 19:00:12", "remaining_time": "13:51:03", "throughput": 4651.44, "total_tokens": 720099464} {"current_steps": 11865, "total_steps": 15680, "loss": 0.2599982023239136, "lr": 1.3915686814561285e-06, "epoch": 1.5133928571428572, "percentage": 75.67, "elapsed_time": "1 day, 19:01:15", "remaining_time": "13:49:57", "throughput": 4651.47, "total_tokens": 720395896} {"current_steps": 11870, "total_steps": 15680, "loss": 0.2580726623535156, "lr": 1.3881032187872666e-06, "epoch": 1.5140306122448979, "percentage": 75.7, "elapsed_time": "1 day, 19:02:22", "remaining_time": "13:48:52", "throughput": 4651.42, "total_tokens": 720701088} {"current_steps": 11875, "total_steps": 15680, "loss": 0.24667282104492189, "lr": 1.3846413809090792e-06, "epoch": 1.5146683673469388, "percentage": 75.73, "elapsed_time": "1 day, 19:03:24", "remaining_time": "13:47:46", "throughput": 4651.37, "total_tokens": 720984848} {"current_steps": 11880, "total_steps": 15680, "loss": 0.2713295936584473, "lr": 1.381183171295762e-06, "epoch": 1.5153061224489797, "percentage": 75.77, "elapsed_time": "1 day, 19:04:37", "remaining_time": "13:46:43", "throughput": 4651.12, "total_tokens": 721284416} {"current_steps": 11885, "total_steps": 15680, "loss": 0.26169524192810056, "lr": 1.3777285934178697e-06, "epoch": 1.5159438775510203, "percentage": 75.8, "elapsed_time": "1 day, 19:05:40", "remaining_time": "13:45:37", "throughput": 4651.24, "total_tokens": 721595160} {"current_steps": 11890, "total_steps": 15680, "loss": 0.2720316171646118, "lr": 1.3742776507423127e-06, "epoch": 1.5165816326530612, "percentage": 75.83, "elapsed_time": "1 day, 19:06:43", "remaining_time": "13:44:31", "throughput": 4651.24, "total_tokens": 721886792} {"current_steps": 11895, "total_steps": 15680, "loss": 0.24444787502288817, "lr": 1.3708303467323536e-06, "epoch": 1.5172193877551021, "percentage": 75.86, "elapsed_time": "1 day, 19:07:40", "remaining_time": "13:43:23", "throughput": 4651.49, "total_tokens": 722191392} {"current_steps": 11900, "total_steps": 15680, "loss": 0.24946393966674804, "lr": 1.367386684847602e-06, "epoch": 1.5178571428571428, "percentage": 75.89, "elapsed_time": "1 day, 19:08:45", "remaining_time": "13:42:18", "throughput": 4651.49, "total_tokens": 722495968} {"current_steps": 11905, "total_steps": 15680, "loss": 0.2545601844787598, "lr": 1.3639466685440133e-06, "epoch": 1.5184948979591837, "percentage": 75.92, "elapsed_time": "1 day, 19:10:03", "remaining_time": "13:41:17", "throughput": 4651.03, "total_tokens": 722787536} {"current_steps": 11910, "total_steps": 15680, "loss": 0.24752330780029297, "lr": 1.360510301273884e-06, "epoch": 1.5191326530612246, "percentage": 75.96, "elapsed_time": "1 day, 19:11:15", "remaining_time": "13:40:14", "throughput": 4650.75, "total_tokens": 723079568} {"current_steps": 11915, "total_steps": 15680, "loss": 0.26047818660736083, "lr": 1.3570775864858487e-06, "epoch": 1.5197704081632653, "percentage": 75.99, "elapsed_time": "1 day, 19:12:25", "remaining_time": "13:39:10", "throughput": 4650.62, "total_tokens": 723382784} {"current_steps": 11920, "total_steps": 15680, "loss": 0.24889864921569824, "lr": 1.3536485276248768e-06, "epoch": 1.5204081632653061, "percentage": 76.02, "elapsed_time": "1 day, 19:13:27", "remaining_time": "13:38:04", "throughput": 4650.69, "total_tokens": 723681840} {"current_steps": 11925, "total_steps": 15680, "loss": 0.24691829681396485, "lr": 1.350223128132268e-06, "epoch": 1.521045918367347, "percentage": 76.05, "elapsed_time": "1 day, 19:14:43", "remaining_time": "13:37:02", "throughput": 4650.37, "total_tokens": 723983624} {"current_steps": 11930, "total_steps": 15680, "loss": 0.2515766143798828, "lr": 1.3468013914456518e-06, "epoch": 1.5216836734693877, "percentage": 76.08, "elapsed_time": "1 day, 19:15:46", "remaining_time": "13:35:56", "throughput": 4650.4, "total_tokens": 724282784} {"current_steps": 11935, "total_steps": 15680, "loss": 0.2518887996673584, "lr": 1.3433833209989743e-06, "epoch": 1.5223214285714286, "percentage": 76.12, "elapsed_time": "1 day, 19:16:46", "remaining_time": "13:34:49", "throughput": 4650.48, "total_tokens": 724577608} {"current_steps": 11940, "total_steps": 15680, "loss": 0.2504230737686157, "lr": 1.3399689202225136e-06, "epoch": 1.5229591836734695, "percentage": 76.15, "elapsed_time": "1 day, 19:17:54", "remaining_time": "13:33:44", "throughput": 4650.36, "total_tokens": 724872224} {"current_steps": 11945, "total_steps": 15680, "loss": 0.253280782699585, "lr": 1.3365581925428594e-06, "epoch": 1.5235969387755102, "percentage": 76.18, "elapsed_time": "1 day, 19:19:07", "remaining_time": "13:32:42", "throughput": 4650.17, "total_tokens": 725180384} {"current_steps": 11950, "total_steps": 15680, "loss": 0.2489948272705078, "lr": 1.3331511413829113e-06, "epoch": 1.524234693877551, "percentage": 76.21, "elapsed_time": "1 day, 19:20:20", "remaining_time": "13:31:39", "throughput": 4649.93, "total_tokens": 725483576} {"current_steps": 11955, "total_steps": 15680, "loss": 0.2944218635559082, "lr": 1.3297477701618833e-06, "epoch": 1.524872448979592, "percentage": 76.24, "elapsed_time": "1 day, 19:21:31", "remaining_time": "13:30:35", "throughput": 4649.77, "total_tokens": 725791648} {"current_steps": 11960, "total_steps": 15680, "loss": 0.24970026016235353, "lr": 1.3263480822953011e-06, "epoch": 1.5255102040816326, "percentage": 76.28, "elapsed_time": "1 day, 19:22:35", "remaining_time": "13:29:29", "throughput": 4649.87, "total_tokens": 726100440} {"current_steps": 11965, "total_steps": 15680, "loss": 0.2613847732543945, "lr": 1.3229520811949836e-06, "epoch": 1.5261479591836735, "percentage": 76.31, "elapsed_time": "1 day, 19:23:33", "remaining_time": "13:28:22", "throughput": 4650.16, "total_tokens": 726418864} {"current_steps": 11970, "total_steps": 15680, "loss": 0.2561951160430908, "lr": 1.3195597702690577e-06, "epoch": 1.5267857142857144, "percentage": 76.34, "elapsed_time": "1 day, 19:24:39", "remaining_time": "13:27:17", "throughput": 4650.1, "total_tokens": 726713968} {"current_steps": 11975, "total_steps": 15680, "loss": 0.24800543785095214, "lr": 1.3161711529219434e-06, "epoch": 1.527423469387755, "percentage": 76.37, "elapsed_time": "1 day, 19:25:44", "remaining_time": "13:26:12", "throughput": 4649.97, "total_tokens": 726998080} {"current_steps": 11980, "total_steps": 15680, "loss": 0.2613114356994629, "lr": 1.3127862325543555e-06, "epoch": 1.5280612244897958, "percentage": 76.4, "elapsed_time": "1 day, 19:26:48", "remaining_time": "13:25:06", "throughput": 4650.08, "total_tokens": 727314256} {"current_steps": 11985, "total_steps": 15680, "loss": 0.24103777408599852, "lr": 1.3094050125632973e-06, "epoch": 1.5286989795918369, "percentage": 76.43, "elapsed_time": "1 day, 19:28:02", "remaining_time": "13:24:03", "throughput": 4649.81, "total_tokens": 727614136} {"current_steps": 11990, "total_steps": 15680, "loss": 0.26449012756347656, "lr": 1.30602749634206e-06, "epoch": 1.5293367346938775, "percentage": 76.47, "elapsed_time": "1 day, 19:28:54", "remaining_time": "13:22:54", "throughput": 4650.26, "total_tokens": 727924752} {"current_steps": 11995, "total_steps": 15680, "loss": 0.25784077644348147, "lr": 1.302653687280216e-06, "epoch": 1.5299744897959182, "percentage": 76.5, "elapsed_time": "1 day, 19:30:01", "remaining_time": "13:21:49", "throughput": 4650.2, "total_tokens": 728228968} {"current_steps": 12000, "total_steps": 15680, "loss": 0.2542006492614746, "lr": 1.299283588763619e-06, "epoch": 1.5306122448979593, "percentage": 76.53, "elapsed_time": "1 day, 19:31:10", "remaining_time": "13:20:45", "throughput": 4650.06, "total_tokens": 728525984} {"current_steps": 12005, "total_steps": 15680, "loss": 0.2613798141479492, "lr": 1.2959172041743985e-06, "epoch": 1.53125, "percentage": 76.56, "elapsed_time": "1 day, 19:32:12", "remaining_time": "13:19:39", "throughput": 4650.18, "total_tokens": 728835224} {"current_steps": 12010, "total_steps": 15680, "loss": 0.2360307455062866, "lr": 1.2925545368909558e-06, "epoch": 1.5318877551020407, "percentage": 76.59, "elapsed_time": "1 day, 19:33:23", "remaining_time": "13:18:35", "throughput": 4649.89, "total_tokens": 729121784} {"current_steps": 12015, "total_steps": 15680, "loss": 0.25995163917541503, "lr": 1.289195590287965e-06, "epoch": 1.5325255102040818, "percentage": 76.63, "elapsed_time": "1 day, 19:34:24", "remaining_time": "13:17:29", "throughput": 4650.02, "total_tokens": 729424080} {"current_steps": 12020, "total_steps": 15680, "loss": 0.25633811950683594, "lr": 1.285840367736358e-06, "epoch": 1.5331632653061225, "percentage": 76.66, "elapsed_time": "1 day, 19:35:24", "remaining_time": "13:16:22", "throughput": 4650.19, "total_tokens": 729730768} {"current_steps": 12025, "total_steps": 15680, "loss": 0.2491147756576538, "lr": 1.2824888726033391e-06, "epoch": 1.5338010204081631, "percentage": 76.69, "elapsed_time": "1 day, 19:36:32", "remaining_time": "13:15:18", "throughput": 4650.11, "total_tokens": 730035304} {"current_steps": 12030, "total_steps": 15680, "loss": 0.2503811836242676, "lr": 1.2791411082523692e-06, "epoch": 1.5344387755102042, "percentage": 76.72, "elapsed_time": "1 day, 19:37:38", "remaining_time": "13:14:12", "throughput": 4650.01, "total_tokens": 730325824} {"current_steps": 12035, "total_steps": 15680, "loss": 0.27198493480682373, "lr": 1.2757970780431594e-06, "epoch": 1.535076530612245, "percentage": 76.75, "elapsed_time": "1 day, 19:38:54", "remaining_time": "13:13:10", "throughput": 4649.72, "total_tokens": 730630584} {"current_steps": 12040, "total_steps": 15680, "loss": 0.24685401916503907, "lr": 1.2724567853316788e-06, "epoch": 1.5357142857142856, "percentage": 76.79, "elapsed_time": "1 day, 19:40:12", "remaining_time": "13:12:09", "throughput": 4649.29, "total_tokens": 730926424} {"current_steps": 12045, "total_steps": 15680, "loss": 0.2603030204772949, "lr": 1.2691202334701474e-06, "epoch": 1.5363520408163265, "percentage": 76.82, "elapsed_time": "1 day, 19:41:22", "remaining_time": "13:11:05", "throughput": 4649.25, "total_tokens": 731245296} {"current_steps": 12050, "total_steps": 15680, "loss": 0.24165427684783936, "lr": 1.2657874258070247e-06, "epoch": 1.5369897959183674, "percentage": 76.85, "elapsed_time": "1 day, 19:42:32", "remaining_time": "13:10:01", "throughput": 4649.11, "total_tokens": 731549024} {"current_steps": 12055, "total_steps": 15680, "loss": 0.24589719772338867, "lr": 1.2624583656870153e-06, "epoch": 1.537627551020408, "percentage": 76.88, "elapsed_time": "1 day, 19:43:33", "remaining_time": "13:08:54", "throughput": 4649.25, "total_tokens": 731854376} {"current_steps": 12060, "total_steps": 15680, "loss": 0.24840226173400878, "lr": 1.2591330564510683e-06, "epoch": 1.538265306122449, "percentage": 76.91, "elapsed_time": "1 day, 19:44:41", "remaining_time": "13:07:50", "throughput": 4649.08, "total_tokens": 732146608} {"current_steps": 12065, "total_steps": 15680, "loss": 0.2419034481048584, "lr": 1.2558115014363592e-06, "epoch": 1.5389030612244898, "percentage": 76.95, "elapsed_time": "1 day, 19:45:58", "remaining_time": "13:06:48", "throughput": 4648.77, "total_tokens": 732451520} {"current_steps": 12070, "total_steps": 15680, "loss": 0.25946569442749023, "lr": 1.2524937039763025e-06, "epoch": 1.5395408163265305, "percentage": 76.98, "elapsed_time": "1 day, 19:46:57", "remaining_time": "13:05:41", "throughput": 4649.02, "total_tokens": 732764640} {"current_steps": 12075, "total_steps": 15680, "loss": 0.2480013370513916, "lr": 1.2491796674005385e-06, "epoch": 1.5401785714285714, "percentage": 77.01, "elapsed_time": "1 day, 19:48:08", "remaining_time": "13:04:38", "throughput": 4648.83, "total_tokens": 733067904} {"current_steps": 12080, "total_steps": 15680, "loss": 0.27153429985046384, "lr": 1.2458693950349349e-06, "epoch": 1.5408163265306123, "percentage": 77.04, "elapsed_time": "1 day, 19:49:17", "remaining_time": "13:03:33", "throughput": 4648.77, "total_tokens": 733376560} {"current_steps": 12085, "total_steps": 15680, "loss": 0.24982929229736328, "lr": 1.2425628902015818e-06, "epoch": 1.541454081632653, "percentage": 77.07, "elapsed_time": "1 day, 19:50:14", "remaining_time": "13:02:26", "throughput": 4648.93, "total_tokens": 733668536} {"current_steps": 12090, "total_steps": 15680, "loss": 0.25737121105194094, "lr": 1.2392601562187867e-06, "epoch": 1.5420918367346939, "percentage": 77.1, "elapsed_time": "1 day, 19:51:26", "remaining_time": "13:01:22", "throughput": 4648.71, "total_tokens": 733967608} {"current_steps": 12095, "total_steps": 15680, "loss": 0.26229133605957033, "lr": 1.2359611964010747e-06, "epoch": 1.5427295918367347, "percentage": 77.14, "elapsed_time": "1 day, 19:52:33", "remaining_time": "13:00:17", "throughput": 4648.64, "total_tokens": 734268424} {"current_steps": 12100, "total_steps": 15680, "loss": 0.24214916229248046, "lr": 1.2326660140591835e-06, "epoch": 1.5433673469387754, "percentage": 77.17, "elapsed_time": "1 day, 19:53:40", "remaining_time": "12:59:13", "throughput": 4648.58, "total_tokens": 734570048} {"current_steps": 12105, "total_steps": 15680, "loss": 0.2654332876205444, "lr": 1.2293746125000538e-06, "epoch": 1.5440051020408163, "percentage": 77.2, "elapsed_time": "1 day, 19:54:40", "remaining_time": "12:58:06", "throughput": 4648.77, "total_tokens": 734878848} {"current_steps": 12110, "total_steps": 15680, "loss": 0.25348896980285646, "lr": 1.2260869950268422e-06, "epoch": 1.5446428571428572, "percentage": 77.23, "elapsed_time": "1 day, 19:55:52", "remaining_time": "12:57:03", "throughput": 4648.47, "total_tokens": 735169440} {"current_steps": 12115, "total_steps": 15680, "loss": 0.23989582061767578, "lr": 1.2228031649389021e-06, "epoch": 1.5452806122448979, "percentage": 77.26, "elapsed_time": "1 day, 19:57:05", "remaining_time": "12:55:59", "throughput": 4648.25, "total_tokens": 735470464} {"current_steps": 12120, "total_steps": 15680, "loss": 0.2431865692138672, "lr": 1.2195231255317834e-06, "epoch": 1.5459183673469388, "percentage": 77.3, "elapsed_time": "1 day, 19:58:11", "remaining_time": "12:54:55", "throughput": 4648.23, "total_tokens": 735778104} {"current_steps": 12125, "total_steps": 15680, "loss": 0.2632904052734375, "lr": 1.2162468800972344e-06, "epoch": 1.5465561224489797, "percentage": 77.33, "elapsed_time": "1 day, 19:59:20", "remaining_time": "12:53:50", "throughput": 4648.18, "total_tokens": 736087024} {"current_steps": 12130, "total_steps": 15680, "loss": 0.2559070587158203, "lr": 1.2129744319232013e-06, "epoch": 1.5471938775510203, "percentage": 77.36, "elapsed_time": "1 day, 20:00:27", "remaining_time": "12:52:45", "throughput": 4648.18, "total_tokens": 736400016} {"current_steps": 12135, "total_steps": 15680, "loss": 0.23843395709991455, "lr": 1.2097057842938093e-06, "epoch": 1.5478316326530612, "percentage": 77.39, "elapsed_time": "1 day, 20:01:39", "remaining_time": "12:51:42", "throughput": 4648.06, "total_tokens": 736714392} {"current_steps": 12140, "total_steps": 15680, "loss": 0.2515080690383911, "lr": 1.206440940489375e-06, "epoch": 1.5484693877551021, "percentage": 77.42, "elapsed_time": "1 day, 20:02:37", "remaining_time": "12:50:35", "throughput": 4648.22, "total_tokens": 737012256} {"current_steps": 12145, "total_steps": 15680, "loss": 0.2598711967468262, "lr": 1.203179903786401e-06, "epoch": 1.5491071428571428, "percentage": 77.46, "elapsed_time": "1 day, 20:03:40", "remaining_time": "12:49:29", "throughput": 4648.35, "total_tokens": 737325784} {"current_steps": 12150, "total_steps": 15680, "loss": 0.24842023849487305, "lr": 1.1999226774575618e-06, "epoch": 1.5497448979591837, "percentage": 77.49, "elapsed_time": "1 day, 20:04:47", "remaining_time": "12:48:24", "throughput": 4648.18, "total_tokens": 737609096} {"current_steps": 12155, "total_steps": 15680, "loss": 0.2655647754669189, "lr": 1.1966692647717127e-06, "epoch": 1.5503826530612246, "percentage": 77.52, "elapsed_time": "1 day, 20:05:50", "remaining_time": "12:47:18", "throughput": 4648.3, "total_tokens": 737918056} {"current_steps": 12160, "total_steps": 15680, "loss": 0.24559359550476073, "lr": 1.1934196689938804e-06, "epoch": 1.5510204081632653, "percentage": 77.55, "elapsed_time": "1 day, 20:06:48", "remaining_time": "12:46:10", "throughput": 4648.53, "total_tokens": 738225024} {"current_steps": 12165, "total_steps": 15680, "loss": 0.27126526832580566, "lr": 1.1901738933852608e-06, "epoch": 1.5516581632653061, "percentage": 77.58, "elapsed_time": "1 day, 20:07:56", "remaining_time": "12:45:06", "throughput": 4648.41, "total_tokens": 738522432} {"current_steps": 12170, "total_steps": 15680, "loss": 0.23754267692565917, "lr": 1.1869319412032171e-06, "epoch": 1.552295918367347, "percentage": 77.61, "elapsed_time": "1 day, 20:09:01", "remaining_time": "12:44:00", "throughput": 4648.37, "total_tokens": 738817336} {"current_steps": 12175, "total_steps": 15680, "loss": 0.23989269733428956, "lr": 1.1836938157012746e-06, "epoch": 1.5529336734693877, "percentage": 77.65, "elapsed_time": "1 day, 20:09:50", "remaining_time": "12:42:51", "throughput": 4648.86, "total_tokens": 739126784} {"current_steps": 12180, "total_steps": 15680, "loss": 0.2581769943237305, "lr": 1.180459520129118e-06, "epoch": 1.5535714285714286, "percentage": 77.68, "elapsed_time": "1 day, 20:10:52", "remaining_time": "12:41:44", "throughput": 4649.02, "total_tokens": 739438768} {"current_steps": 12185, "total_steps": 15680, "loss": 0.26799817085266114, "lr": 1.1772290577325895e-06, "epoch": 1.5542091836734695, "percentage": 77.71, "elapsed_time": "1 day, 20:12:05", "remaining_time": "12:40:41", "throughput": 4648.76, "total_tokens": 739734376} {"current_steps": 12190, "total_steps": 15680, "loss": 0.25603523254394533, "lr": 1.174002431753683e-06, "epoch": 1.5548469387755102, "percentage": 77.74, "elapsed_time": "1 day, 20:13:08", "remaining_time": "12:39:35", "throughput": 4648.74, "total_tokens": 740027464} {"current_steps": 12195, "total_steps": 15680, "loss": 0.23553390502929689, "lr": 1.1707796454305437e-06, "epoch": 1.555484693877551, "percentage": 77.77, "elapsed_time": "1 day, 20:14:17", "remaining_time": "12:38:31", "throughput": 4648.67, "total_tokens": 740332856} {"current_steps": 12200, "total_steps": 15680, "loss": 0.23785796165466308, "lr": 1.167560701997462e-06, "epoch": 1.556122448979592, "percentage": 77.81, "elapsed_time": "1 day, 20:15:22", "remaining_time": "12:37:26", "throughput": 4648.63, "total_tokens": 740630472} {"current_steps": 12205, "total_steps": 15680, "loss": 0.2628336429595947, "lr": 1.1643456046848745e-06, "epoch": 1.5567602040816326, "percentage": 77.84, "elapsed_time": "1 day, 20:16:17", "remaining_time": "12:36:17", "throughput": 4648.94, "total_tokens": 740938432} {"current_steps": 12210, "total_steps": 15680, "loss": 0.24759845733642577, "lr": 1.161134356719351e-06, "epoch": 1.5573979591836735, "percentage": 77.87, "elapsed_time": "1 day, 20:17:26", "remaining_time": "12:35:13", "throughput": 4648.83, "total_tokens": 741239992} {"current_steps": 12215, "total_steps": 15680, "loss": 0.25596597194671633, "lr": 1.1579269613236094e-06, "epoch": 1.5580357142857144, "percentage": 77.9, "elapsed_time": "1 day, 20:18:26", "remaining_time": "12:34:06", "throughput": 4648.97, "total_tokens": 741543208} {"current_steps": 12220, "total_steps": 15680, "loss": 0.24630370140075683, "lr": 1.1547234217164904e-06, "epoch": 1.558673469387755, "percentage": 77.93, "elapsed_time": "1 day, 20:19:27", "remaining_time": "12:33:00", "throughput": 4649.14, "total_tokens": 741853032} {"current_steps": 12225, "total_steps": 15680, "loss": 0.2798213005065918, "lr": 1.1515237411129698e-06, "epoch": 1.5593112244897958, "percentage": 77.97, "elapsed_time": "1 day, 20:20:36", "remaining_time": "12:31:55", "throughput": 4648.99, "total_tokens": 742146616} {"current_steps": 12230, "total_steps": 15680, "loss": 0.2604410648345947, "lr": 1.148327922724155e-06, "epoch": 1.5599489795918369, "percentage": 78.0, "elapsed_time": "1 day, 20:21:40", "remaining_time": "12:30:50", "throughput": 4649.04, "total_tokens": 742453680} {"current_steps": 12235, "total_steps": 15680, "loss": 0.24161162376403808, "lr": 1.1451359697572684e-06, "epoch": 1.5605867346938775, "percentage": 78.03, "elapsed_time": "1 day, 20:22:52", "remaining_time": "12:29:47", "throughput": 4648.83, "total_tokens": 742755152} {"current_steps": 12240, "total_steps": 15680, "loss": 0.2437690258026123, "lr": 1.141947885415659e-06, "epoch": 1.5612244897959182, "percentage": 78.06, "elapsed_time": "1 day, 20:23:56", "remaining_time": "12:28:41", "throughput": 4648.84, "total_tokens": 743055552} {"current_steps": 12245, "total_steps": 15680, "loss": 0.26891021728515624, "lr": 1.1387636728987927e-06, "epoch": 1.5618622448979593, "percentage": 78.09, "elapsed_time": "1 day, 20:25:01", "remaining_time": "12:27:35", "throughput": 4648.79, "total_tokens": 743348152} {"current_steps": 12250, "total_steps": 15680, "loss": 0.2813580513000488, "lr": 1.135583335402249e-06, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "1 day, 20:26:15", "remaining_time": "12:26:33", "throughput": 4648.5, "total_tokens": 743649088} {"current_steps": 12255, "total_steps": 15680, "loss": 0.26078205108642577, "lr": 1.1324068761177176e-06, "epoch": 1.5631377551020407, "percentage": 78.16, "elapsed_time": "1 day, 20:27:13", "remaining_time": "12:25:25", "throughput": 4648.74, "total_tokens": 743956208} {"current_steps": 12260, "total_steps": 15680, "loss": 0.23866262435913085, "lr": 1.129234298232999e-06, "epoch": 1.5637755102040818, "percentage": 78.19, "elapsed_time": "1 day, 20:28:25", "remaining_time": "12:24:22", "throughput": 4648.51, "total_tokens": 744251880} {"current_steps": 12265, "total_steps": 15680, "loss": 0.25392653942108157, "lr": 1.1260656049319957e-06, "epoch": 1.5644132653061225, "percentage": 78.22, "elapsed_time": "1 day, 20:29:40", "remaining_time": "12:23:19", "throughput": 4648.26, "total_tokens": 744561384} {"current_steps": 12270, "total_steps": 15680, "loss": 0.22959496974945068, "lr": 1.1229007993947122e-06, "epoch": 1.5650510204081631, "percentage": 78.25, "elapsed_time": "1 day, 20:30:56", "remaining_time": "12:22:17", "throughput": 4647.94, "total_tokens": 744861632} {"current_steps": 12275, "total_steps": 15680, "loss": 0.2407773494720459, "lr": 1.119739884797253e-06, "epoch": 1.5656887755102042, "percentage": 78.28, "elapsed_time": "1 day, 20:32:08", "remaining_time": "12:21:13", "throughput": 4647.71, "total_tokens": 745159520} {"current_steps": 12280, "total_steps": 15680, "loss": 0.2587071418762207, "lr": 1.116582864311816e-06, "epoch": 1.566326530612245, "percentage": 78.32, "elapsed_time": "1 day, 20:33:18", "remaining_time": "12:20:09", "throughput": 4647.65, "total_tokens": 745473160} {"current_steps": 12285, "total_steps": 15680, "loss": 0.25202369689941406, "lr": 1.1134297411066925e-06, "epoch": 1.5669642857142856, "percentage": 78.35, "elapsed_time": "1 day, 20:34:18", "remaining_time": "12:19:03", "throughput": 4647.81, "total_tokens": 745782512} {"current_steps": 12290, "total_steps": 15680, "loss": 0.2682202816009521, "lr": 1.1102805183462605e-06, "epoch": 1.5676020408163265, "percentage": 78.38, "elapsed_time": "1 day, 20:35:31", "remaining_time": "12:18:00", "throughput": 4647.55, "total_tokens": 746079024} {"current_steps": 12295, "total_steps": 15680, "loss": 0.2658061504364014, "lr": 1.1071351991909863e-06, "epoch": 1.5682397959183674, "percentage": 78.41, "elapsed_time": "1 day, 20:36:26", "remaining_time": "12:16:51", "throughput": 4647.88, "total_tokens": 746387368} {"current_steps": 12300, "total_steps": 15680, "loss": 0.24722461700439452, "lr": 1.1039937867974166e-06, "epoch": 1.568877551020408, "percentage": 78.44, "elapsed_time": "1 day, 20:37:37", "remaining_time": "12:15:48", "throughput": 4647.76, "total_tokens": 746695480} {"current_steps": 12305, "total_steps": 15680, "loss": 0.24347903728485107, "lr": 1.1008562843181796e-06, "epoch": 1.569515306122449, "percentage": 78.48, "elapsed_time": "1 day, 20:38:27", "remaining_time": "12:14:38", "throughput": 4648.23, "total_tokens": 747007624} {"current_steps": 12310, "total_steps": 15680, "loss": 0.25902271270751953, "lr": 1.0977226949019743e-06, "epoch": 1.5701530612244898, "percentage": 78.51, "elapsed_time": "1 day, 20:39:34", "remaining_time": "12:13:33", "throughput": 4648.24, "total_tokens": 747317696} {"current_steps": 12315, "total_steps": 15680, "loss": 0.26403059959411623, "lr": 1.09459302169358e-06, "epoch": 1.5707908163265305, "percentage": 78.54, "elapsed_time": "1 day, 20:40:40", "remaining_time": "12:12:28", "throughput": 4648.13, "total_tokens": 747607568} {"current_steps": 12320, "total_steps": 15680, "loss": 0.24433636665344238, "lr": 1.0914672678338434e-06, "epoch": 1.5714285714285714, "percentage": 78.57, "elapsed_time": "1 day, 20:41:52", "remaining_time": "12:11:25", "throughput": 4648.02, "total_tokens": 747925216} {"current_steps": 12325, "total_steps": 15680, "loss": 0.253980016708374, "lr": 1.088345436459673e-06, "epoch": 1.5720663265306123, "percentage": 78.6, "elapsed_time": "1 day, 20:42:44", "remaining_time": "12:10:16", "throughput": 4648.44, "total_tokens": 748233008} {"current_steps": 12330, "total_steps": 15680, "loss": 0.2468017578125, "lr": 1.0852275307040454e-06, "epoch": 1.572704081632653, "percentage": 78.64, "elapsed_time": "1 day, 20:43:59", "remaining_time": "12:09:13", "throughput": 4648.13, "total_tokens": 748531304} {"current_steps": 12335, "total_steps": 15680, "loss": 0.2438680648803711, "lr": 1.082113553696001e-06, "epoch": 1.5733418367346939, "percentage": 78.67, "elapsed_time": "1 day, 20:45:06", "remaining_time": "12:08:08", "throughput": 4648.05, "total_tokens": 748829480} {"current_steps": 12340, "total_steps": 15680, "loss": 0.2425311803817749, "lr": 1.0790035085606282e-06, "epoch": 1.5739795918367347, "percentage": 78.7, "elapsed_time": "1 day, 20:46:17", "remaining_time": "12:07:05", "throughput": 4647.83, "total_tokens": 749126768} {"current_steps": 12345, "total_steps": 15680, "loss": 0.2524994373321533, "lr": 1.0758973984190764e-06, "epoch": 1.5746173469387754, "percentage": 78.73, "elapsed_time": "1 day, 20:47:24", "remaining_time": "12:06:00", "throughput": 4647.8, "total_tokens": 749431224} {"current_steps": 12350, "total_steps": 15680, "loss": 0.2606823444366455, "lr": 1.072795226388544e-06, "epoch": 1.5752551020408163, "percentage": 78.76, "elapsed_time": "1 day, 20:48:29", "remaining_time": "12:04:54", "throughput": 4647.84, "total_tokens": 749740744} {"current_steps": 12355, "total_steps": 15680, "loss": 0.26224217414855955, "lr": 1.0696969955822772e-06, "epoch": 1.5758928571428572, "percentage": 78.79, "elapsed_time": "1 day, 20:49:24", "remaining_time": "12:03:46", "throughput": 4648.18, "total_tokens": 750049528} {"current_steps": 12360, "total_steps": 15680, "loss": 0.26146037578582765, "lr": 1.0666027091095672e-06, "epoch": 1.5765306122448979, "percentage": 78.83, "elapsed_time": "1 day, 20:50:22", "remaining_time": "12:02:39", "throughput": 4648.39, "total_tokens": 750354768} {"current_steps": 12365, "total_steps": 15680, "loss": 0.26197237968444825, "lr": 1.063512370075746e-06, "epoch": 1.5771683673469388, "percentage": 78.86, "elapsed_time": "1 day, 20:51:36", "remaining_time": "12:01:36", "throughput": 4648.17, "total_tokens": 750665432} {"current_steps": 12370, "total_steps": 15680, "loss": 0.2529475688934326, "lr": 1.060425981582186e-06, "epoch": 1.5778061224489797, "percentage": 78.89, "elapsed_time": "1 day, 20:52:47", "remaining_time": "12:00:32", "throughput": 4648.01, "total_tokens": 750965168} {"current_steps": 12375, "total_steps": 15680, "loss": 0.2558449268341064, "lr": 1.0573435467262922e-06, "epoch": 1.5784438775510203, "percentage": 78.92, "elapsed_time": "1 day, 20:53:50", "remaining_time": "11:59:26", "throughput": 4648.08, "total_tokens": 751272352} {"current_steps": 12380, "total_steps": 15680, "loss": 0.25114145278930666, "lr": 1.0542650686015039e-06, "epoch": 1.5790816326530612, "percentage": 78.95, "elapsed_time": "1 day, 20:54:50", "remaining_time": "11:58:19", "throughput": 4648.21, "total_tokens": 751568720} {"current_steps": 12385, "total_steps": 15680, "loss": 0.2342022180557251, "lr": 1.0511905502972885e-06, "epoch": 1.5797193877551021, "percentage": 78.99, "elapsed_time": "1 day, 20:55:56", "remaining_time": "11:57:14", "throughput": 4648.06, "total_tokens": 751854528} {"current_steps": 12390, "total_steps": 15680, "loss": 0.2556438446044922, "lr": 1.0481199948991416e-06, "epoch": 1.5803571428571428, "percentage": 79.02, "elapsed_time": "1 day, 20:57:07", "remaining_time": "11:56:11", "throughput": 4647.87, "total_tokens": 752152672} {"current_steps": 12395, "total_steps": 15680, "loss": 0.24029622077941895, "lr": 1.0450534054885765e-06, "epoch": 1.5809948979591837, "percentage": 79.05, "elapsed_time": "1 day, 20:58:14", "remaining_time": "11:55:06", "throughput": 4647.8, "total_tokens": 752451632} {"current_steps": 12400, "total_steps": 15680, "loss": 0.24811995029449463, "lr": 1.0419907851431321e-06, "epoch": 1.5816326530612246, "percentage": 79.08, "elapsed_time": "1 day, 20:59:27", "remaining_time": "11:54:03", "throughput": 4647.52, "total_tokens": 752748848} {"current_steps": 12405, "total_steps": 15680, "loss": 0.252943229675293, "lr": 1.0389321369363636e-06, "epoch": 1.5822704081632653, "percentage": 79.11, "elapsed_time": "1 day, 21:00:44", "remaining_time": "11:53:00", "throughput": 4647.18, "total_tokens": 753048504} {"current_steps": 12410, "total_steps": 15680, "loss": 0.24510138034820556, "lr": 1.0358774639378344e-06, "epoch": 1.5829081632653061, "percentage": 79.15, "elapsed_time": "1 day, 21:01:46", "remaining_time": "11:51:54", "throughput": 4647.25, "total_tokens": 753350536} {"current_steps": 12415, "total_steps": 15680, "loss": 0.23749666213989257, "lr": 1.0328267692131227e-06, "epoch": 1.583545918367347, "percentage": 79.18, "elapsed_time": "1 day, 21:03:01", "remaining_time": "11:50:51", "throughput": 4646.99, "total_tokens": 753655064} {"current_steps": 12420, "total_steps": 15680, "loss": 0.2700827598571777, "lr": 1.0297800558238175e-06, "epoch": 1.5841836734693877, "percentage": 79.21, "elapsed_time": "1 day, 21:04:01", "remaining_time": "11:49:45", "throughput": 4647.17, "total_tokens": 753965960} {"current_steps": 12425, "total_steps": 15680, "loss": 0.2491556167602539, "lr": 1.026737326827505e-06, "epoch": 1.5848214285714286, "percentage": 79.24, "elapsed_time": "1 day, 21:05:14", "remaining_time": "11:48:41", "throughput": 4646.9, "total_tokens": 754261800} {"current_steps": 12430, "total_steps": 15680, "loss": 0.22559471130371095, "lr": 1.0236985852777748e-06, "epoch": 1.5854591836734695, "percentage": 79.27, "elapsed_time": "1 day, 21:06:26", "remaining_time": "11:47:38", "throughput": 4646.73, "total_tokens": 754566128} {"current_steps": 12435, "total_steps": 15680, "loss": 0.25476698875427245, "lr": 1.020663834224222e-06, "epoch": 1.5860969387755102, "percentage": 79.3, "elapsed_time": "1 day, 21:07:19", "remaining_time": "11:46:29", "throughput": 4647.11, "total_tokens": 754874792} {"current_steps": 12440, "total_steps": 15680, "loss": 0.2633042335510254, "lr": 1.017633076712426e-06, "epoch": 1.586734693877551, "percentage": 79.34, "elapsed_time": "1 day, 21:08:27", "remaining_time": "11:45:25", "throughput": 4647.08, "total_tokens": 755183832} {"current_steps": 12445, "total_steps": 15680, "loss": 0.24064431190490723, "lr": 1.0146063157839653e-06, "epoch": 1.587372448979592, "percentage": 79.37, "elapsed_time": "1 day, 21:09:22", "remaining_time": "11:44:17", "throughput": 4647.33, "total_tokens": 755483224} {"current_steps": 12450, "total_steps": 15680, "loss": 0.2448643207550049, "lr": 1.0115835544764063e-06, "epoch": 1.5880102040816326, "percentage": 79.4, "elapsed_time": "1 day, 21:10:42", "remaining_time": "11:43:15", "throughput": 4646.97, "total_tokens": 755793864} {"current_steps": 12455, "total_steps": 15680, "loss": 0.23660359382629395, "lr": 1.0085647958233008e-06, "epoch": 1.5886479591836735, "percentage": 79.43, "elapsed_time": "1 day, 21:11:43", "remaining_time": "11:42:09", "throughput": 4647.06, "total_tokens": 756095472} {"current_steps": 12460, "total_steps": 15680, "loss": 0.23841919898986816, "lr": 1.0055500428541836e-06, "epoch": 1.5892857142857144, "percentage": 79.46, "elapsed_time": "1 day, 21:12:49", "remaining_time": "11:41:04", "throughput": 4647.12, "total_tokens": 756410888} {"current_steps": 12465, "total_steps": 15680, "loss": 0.25959603786468505, "lr": 1.0025392985945703e-06, "epoch": 1.589923469387755, "percentage": 79.5, "elapsed_time": "1 day, 21:13:43", "remaining_time": "11:39:55", "throughput": 4647.46, "total_tokens": 756716856} {"current_steps": 12470, "total_steps": 15680, "loss": 0.25395450592041013, "lr": 9.995325660659533e-07, "epoch": 1.5905612244897958, "percentage": 79.53, "elapsed_time": "1 day, 21:15:02", "remaining_time": "11:38:54", "throughput": 4647.07, "total_tokens": 757020568} {"current_steps": 12475, "total_steps": 15680, "loss": 0.25415830612182616, "lr": 9.965298482857993e-07, "epoch": 1.5911989795918369, "percentage": 79.56, "elapsed_time": "1 day, 21:16:04", "remaining_time": "11:37:47", "throughput": 4647.16, "total_tokens": 757323152} {"current_steps": 12480, "total_steps": 15680, "loss": 0.2535807371139526, "lr": 9.935311482675413e-07, "epoch": 1.5918367346938775, "percentage": 79.59, "elapsed_time": "1 day, 21:17:08", "remaining_time": "11:36:42", "throughput": 4647.23, "total_tokens": 757630000} {"current_steps": 12485, "total_steps": 15680, "loss": 0.2578327417373657, "lr": 9.905364690205888e-07, "epoch": 1.5924744897959182, "percentage": 79.62, "elapsed_time": "1 day, 21:18:12", "remaining_time": "11:35:36", "throughput": 4647.31, "total_tokens": 757940600} {"current_steps": 12490, "total_steps": 15680, "loss": 0.26314606666564944, "lr": 9.875458135503113e-07, "epoch": 1.5931122448979593, "percentage": 79.66, "elapsed_time": "1 day, 21:19:17", "remaining_time": "11:34:31", "throughput": 4647.37, "total_tokens": 758251840} {"current_steps": 12495, "total_steps": 15680, "loss": 0.23812398910522461, "lr": 9.845591848580376e-07, "epoch": 1.59375, "percentage": 79.69, "elapsed_time": "1 day, 21:20:35", "remaining_time": "11:33:29", "throughput": 4647.0, "total_tokens": 758555896} {"current_steps": 12500, "total_steps": 15680, "loss": 0.269971227645874, "lr": 9.815765859410586e-07, "epoch": 1.5943877551020407, "percentage": 79.72, "elapsed_time": "1 day, 21:21:42", "remaining_time": "11:32:24", "throughput": 4646.91, "total_tokens": 758850688} {"current_steps": 12505, "total_steps": 15680, "loss": 0.24490811824798583, "lr": 9.785980197926242e-07, "epoch": 1.5950255102040818, "percentage": 79.75, "elapsed_time": "1 day, 21:22:49", "remaining_time": "11:31:19", "throughput": 4646.87, "total_tokens": 759157776} {"current_steps": 12510, "total_steps": 15680, "loss": 0.25566740036010743, "lr": 9.7562348940193e-07, "epoch": 1.5956632653061225, "percentage": 79.78, "elapsed_time": "1 day, 21:23:58", "remaining_time": "11:30:14", "throughput": 4646.82, "total_tokens": 759468720} {"current_steps": 12515, "total_steps": 15680, "loss": 0.24758310317993165, "lr": 9.726529977541243e-07, "epoch": 1.5963010204081631, "percentage": 79.82, "elapsed_time": "1 day, 21:24:56", "remaining_time": "11:29:07", "throughput": 4647.08, "total_tokens": 759783072} {"current_steps": 12520, "total_steps": 15680, "loss": 0.24775145053863526, "lr": 9.696865478303075e-07, "epoch": 1.5969387755102042, "percentage": 79.85, "elapsed_time": "1 day, 21:25:59", "remaining_time": "11:28:01", "throughput": 4647.18, "total_tokens": 760088384} {"current_steps": 12525, "total_steps": 15680, "loss": 0.26232051849365234, "lr": 9.667241426075152e-07, "epoch": 1.597576530612245, "percentage": 79.88, "elapsed_time": "1 day, 21:27:08", "remaining_time": "11:26:57", "throughput": 4647.11, "total_tokens": 760400232} {"current_steps": 12530, "total_steps": 15680, "loss": 0.25011744499206545, "lr": 9.637657850587289e-07, "epoch": 1.5982142857142856, "percentage": 79.91, "elapsed_time": "1 day, 21:28:15", "remaining_time": "11:25:52", "throughput": 4647.07, "total_tokens": 760702064} {"current_steps": 12535, "total_steps": 15680, "loss": 0.22640318870544435, "lr": 9.608114781528671e-07, "epoch": 1.5988520408163265, "percentage": 79.94, "elapsed_time": "1 day, 21:29:23", "remaining_time": "11:24:47", "throughput": 4646.89, "total_tokens": 760993656} {"current_steps": 12540, "total_steps": 15680, "loss": 0.25423121452331543, "lr": 9.578612248547836e-07, "epoch": 1.5994897959183674, "percentage": 79.97, "elapsed_time": "1 day, 21:30:31", "remaining_time": "11:23:43", "throughput": 4646.82, "total_tokens": 761293168} {"current_steps": 12545, "total_steps": 15680, "loss": 0.24723145961761475, "lr": 9.549150281252633e-07, "epoch": 1.600127551020408, "percentage": 80.01, "elapsed_time": "1 day, 21:31:34", "remaining_time": "11:22:37", "throughput": 4646.87, "total_tokens": 761597688} {"current_steps": 12550, "total_steps": 15680, "loss": 0.2562461614608765, "lr": 9.519728909210202e-07, "epoch": 1.600765306122449, "percentage": 80.04, "elapsed_time": "1 day, 21:32:46", "remaining_time": "11:21:33", "throughput": 4646.66, "total_tokens": 761898112} {"current_steps": 12555, "total_steps": 15680, "loss": 0.24855079650878906, "lr": 9.49034816194695e-07, "epoch": 1.6014030612244898, "percentage": 80.07, "elapsed_time": "1 day, 21:33:45", "remaining_time": "11:20:26", "throughput": 4646.84, "total_tokens": 762201840} {"current_steps": 12560, "total_steps": 15680, "loss": 0.25662262439727784, "lr": 9.461008068948502e-07, "epoch": 1.6020408163265305, "percentage": 80.1, "elapsed_time": "1 day, 21:34:52", "remaining_time": "11:19:21", "throughput": 4646.83, "total_tokens": 762511008} {"current_steps": 12565, "total_steps": 15680, "loss": 0.2622831344604492, "lr": 9.431708659659694e-07, "epoch": 1.6026785714285714, "percentage": 80.13, "elapsed_time": "1 day, 21:35:54", "remaining_time": "11:18:15", "throughput": 4646.96, "total_tokens": 762819600} {"current_steps": 12570, "total_steps": 15680, "loss": 0.2846518516540527, "lr": 9.402449963484528e-07, "epoch": 1.6033163265306123, "percentage": 80.17, "elapsed_time": "1 day, 21:36:58", "remaining_time": "11:17:10", "throughput": 4646.94, "total_tokens": 763114568} {"current_steps": 12575, "total_steps": 15680, "loss": 0.25565176010131835, "lr": 9.373232009786154e-07, "epoch": 1.603954081632653, "percentage": 80.2, "elapsed_time": "1 day, 21:38:10", "remaining_time": "11:16:06", "throughput": 4646.82, "total_tokens": 763426824} {"current_steps": 12580, "total_steps": 15680, "loss": 0.24167089462280272, "lr": 9.344054827886839e-07, "epoch": 1.6045918367346939, "percentage": 80.23, "elapsed_time": "1 day, 21:39:09", "remaining_time": "11:14:59", "throughput": 4647.02, "total_tokens": 763735968} {"current_steps": 12585, "total_steps": 15680, "loss": 0.25985682010650635, "lr": 9.314918447067877e-07, "epoch": 1.6052295918367347, "percentage": 80.26, "elapsed_time": "1 day, 21:40:15", "remaining_time": "11:13:54", "throughput": 4647.01, "total_tokens": 764041712} {"current_steps": 12590, "total_steps": 15680, "loss": 0.2366727590560913, "lr": 9.285822896569724e-07, "epoch": 1.6058673469387754, "percentage": 80.29, "elapsed_time": "1 day, 21:41:17", "remaining_time": "11:12:48", "throughput": 4647.22, "total_tokens": 764362000} {"current_steps": 12595, "total_steps": 15680, "loss": 0.2414870262145996, "lr": 9.256768205591754e-07, "epoch": 1.6065051020408163, "percentage": 80.33, "elapsed_time": "1 day, 21:42:26", "remaining_time": "11:11:43", "throughput": 4647.13, "total_tokens": 764667152} {"current_steps": 12600, "total_steps": 15680, "loss": 0.2509591579437256, "lr": 9.227754403292377e-07, "epoch": 1.6071428571428572, "percentage": 80.36, "elapsed_time": "1 day, 21:43:13", "remaining_time": "11:10:33", "throughput": 4647.62, "total_tokens": 764968712} {"current_steps": 12605, "total_steps": 15680, "loss": 0.25958638191223143, "lr": 9.198781518789007e-07, "epoch": 1.6077806122448979, "percentage": 80.39, "elapsed_time": "1 day, 21:44:10", "remaining_time": "11:09:26", "throughput": 4647.91, "total_tokens": 765281152} {"current_steps": 12610, "total_steps": 15680, "loss": 0.26078200340270996, "lr": 9.169849581157925e-07, "epoch": 1.6084183673469388, "percentage": 80.42, "elapsed_time": "1 day, 21:45:10", "remaining_time": "11:08:19", "throughput": 4648.1, "total_tokens": 765588280} {"current_steps": 12615, "total_steps": 15680, "loss": 0.24608101844787597, "lr": 9.140958619434353e-07, "epoch": 1.6090561224489797, "percentage": 80.45, "elapsed_time": "1 day, 21:46:09", "remaining_time": "11:07:13", "throughput": 4648.27, "total_tokens": 765895232} {"current_steps": 12620, "total_steps": 15680, "loss": 0.24444227218627929, "lr": 9.112108662612401e-07, "epoch": 1.6096938775510203, "percentage": 80.48, "elapsed_time": "1 day, 21:47:09", "remaining_time": "11:06:06", "throughput": 4648.49, "total_tokens": 766209152} {"current_steps": 12625, "total_steps": 15680, "loss": 0.25504388809204104, "lr": 9.083299739645007e-07, "epoch": 1.6103316326530612, "percentage": 80.52, "elapsed_time": "1 day, 21:48:10", "remaining_time": "11:05:00", "throughput": 4648.63, "total_tokens": 766515456} {"current_steps": 12630, "total_steps": 15680, "loss": 0.24010090827941893, "lr": 9.054531879443945e-07, "epoch": 1.6109693877551021, "percentage": 80.55, "elapsed_time": "1 day, 21:49:14", "remaining_time": "11:03:54", "throughput": 4648.63, "total_tokens": 766811560} {"current_steps": 12635, "total_steps": 15680, "loss": 0.23866443634033202, "lr": 9.025805110879765e-07, "epoch": 1.6116071428571428, "percentage": 80.58, "elapsed_time": "1 day, 21:50:26", "remaining_time": "11:02:51", "throughput": 4648.37, "total_tokens": 767105144} {"current_steps": 12640, "total_steps": 15680, "loss": 0.26564598083496094, "lr": 8.997119462781784e-07, "epoch": 1.6122448979591837, "percentage": 80.61, "elapsed_time": "1 day, 21:51:28", "remaining_time": "11:01:44", "throughput": 4648.46, "total_tokens": 767407136} {"current_steps": 12645, "total_steps": 15680, "loss": 0.2686514377593994, "lr": 8.968474963938062e-07, "epoch": 1.6128826530612246, "percentage": 80.64, "elapsed_time": "1 day, 21:52:27", "remaining_time": "11:00:37", "throughput": 4648.66, "total_tokens": 767714440} {"current_steps": 12650, "total_steps": 15680, "loss": 0.24472124576568605, "lr": 8.939871643095344e-07, "epoch": 1.6135204081632653, "percentage": 80.68, "elapsed_time": "1 day, 21:53:34", "remaining_time": "10:59:33", "throughput": 4648.69, "total_tokens": 768028176} {"current_steps": 12655, "total_steps": 15680, "loss": 0.23885109424591064, "lr": 8.911309528959072e-07, "epoch": 1.6141581632653061, "percentage": 80.71, "elapsed_time": "1 day, 21:54:38", "remaining_time": "10:58:27", "throughput": 4648.59, "total_tokens": 768310720} {"current_steps": 12660, "total_steps": 15680, "loss": 0.25642588138580324, "lr": 8.882788650193308e-07, "epoch": 1.614795918367347, "percentage": 80.74, "elapsed_time": "1 day, 21:55:50", "remaining_time": "10:57:23", "throughput": 4648.35, "total_tokens": 768609424} {"current_steps": 12665, "total_steps": 15680, "loss": 0.24589982032775878, "lr": 8.854309035420772e-07, "epoch": 1.6154336734693877, "percentage": 80.77, "elapsed_time": "1 day, 21:57:04", "remaining_time": "10:56:20", "throughput": 4648.1, "total_tokens": 768910864} {"current_steps": 12670, "total_steps": 15680, "loss": 0.24904451370239258, "lr": 8.8258707132227e-07, "epoch": 1.6160714285714286, "percentage": 80.8, "elapsed_time": "1 day, 21:58:09", "remaining_time": "10:55:15", "throughput": 4648.17, "total_tokens": 769224144} {"current_steps": 12675, "total_steps": 15680, "loss": 0.2533883571624756, "lr": 8.797473712138976e-07, "epoch": 1.6167091836734695, "percentage": 80.84, "elapsed_time": "1 day, 21:59:17", "remaining_time": "10:54:10", "throughput": 4648.15, "total_tokens": 769534752} {"current_steps": 12680, "total_steps": 15680, "loss": 0.26964540481567384, "lr": 8.769118060667969e-07, "epoch": 1.6173469387755102, "percentage": 80.87, "elapsed_time": "1 day, 22:00:23", "remaining_time": "10:53:05", "throughput": 4648.18, "total_tokens": 769849432} {"current_steps": 12685, "total_steps": 15680, "loss": 0.24618177413940429, "lr": 8.740803787266522e-07, "epoch": 1.617984693877551, "percentage": 80.9, "elapsed_time": "1 day, 22:01:29", "remaining_time": "10:52:00", "throughput": 4648.14, "total_tokens": 770147568} {"current_steps": 12690, "total_steps": 15680, "loss": 0.2687231540679932, "lr": 8.712530920350026e-07, "epoch": 1.618622448979592, "percentage": 80.93, "elapsed_time": "1 day, 22:02:36", "remaining_time": "10:50:55", "throughput": 4648.1, "total_tokens": 770452992} {"current_steps": 12695, "total_steps": 15680, "loss": 0.25114462375640867, "lr": 8.684299488292275e-07, "epoch": 1.6192602040816326, "percentage": 80.96, "elapsed_time": "1 day, 22:03:51", "remaining_time": "10:49:52", "throughput": 4647.78, "total_tokens": 770747832} {"current_steps": 12700, "total_steps": 15680, "loss": 0.24409866333007812, "lr": 8.656109519425454e-07, "epoch": 1.6198979591836735, "percentage": 80.99, "elapsed_time": "1 day, 22:04:53", "remaining_time": "10:48:46", "throughput": 4647.91, "total_tokens": 771058800} {"current_steps": 12705, "total_steps": 15680, "loss": 0.260186767578125, "lr": 8.627961042040183e-07, "epoch": 1.6205357142857144, "percentage": 81.03, "elapsed_time": "1 day, 22:05:57", "remaining_time": "10:47:40", "throughput": 4647.98, "total_tokens": 771367112} {"current_steps": 12710, "total_steps": 15680, "loss": 0.2518947601318359, "lr": 8.599854084385422e-07, "epoch": 1.621173469387755, "percentage": 81.06, "elapsed_time": "1 day, 22:07:02", "remaining_time": "10:46:35", "throughput": 4648.01, "total_tokens": 771673080} {"current_steps": 12715, "total_steps": 15680, "loss": 0.2479722499847412, "lr": 8.571788674668469e-07, "epoch": 1.6218112244897958, "percentage": 81.09, "elapsed_time": "1 day, 22:08:14", "remaining_time": "10:45:31", "throughput": 4647.71, "total_tokens": 771961968} {"current_steps": 12720, "total_steps": 15680, "loss": 0.2650299072265625, "lr": 8.543764841054919e-07, "epoch": 1.6224489795918369, "percentage": 81.12, "elapsed_time": "1 day, 22:09:17", "remaining_time": "10:44:25", "throughput": 4647.83, "total_tokens": 772271248} {"current_steps": 12725, "total_steps": 15680, "loss": 0.24235401153564454, "lr": 8.515782611668649e-07, "epoch": 1.6230867346938775, "percentage": 81.15, "elapsed_time": "1 day, 22:10:22", "remaining_time": "10:43:20", "throughput": 4647.86, "total_tokens": 772580152} {"current_steps": 12730, "total_steps": 15680, "loss": 0.2494971752166748, "lr": 8.487842014591779e-07, "epoch": 1.6237244897959182, "percentage": 81.19, "elapsed_time": "1 day, 22:11:38", "remaining_time": "10:42:17", "throughput": 4647.62, "total_tokens": 772893608} {"current_steps": 12735, "total_steps": 15680, "loss": 0.2487192392349243, "lr": 8.459943077864651e-07, "epoch": 1.6243622448979593, "percentage": 81.22, "elapsed_time": "1 day, 22:12:37", "remaining_time": "10:41:10", "throughput": 4647.87, "total_tokens": 773206664} {"current_steps": 12740, "total_steps": 15680, "loss": 0.23452670574188234, "lr": 8.432085829485792e-07, "epoch": 1.625, "percentage": 81.25, "elapsed_time": "1 day, 22:13:39", "remaining_time": "10:40:04", "throughput": 4647.96, "total_tokens": 773511840} {"current_steps": 12745, "total_steps": 15680, "loss": 0.23406319618225097, "lr": 8.404270297411904e-07, "epoch": 1.6256377551020407, "percentage": 81.28, "elapsed_time": "1 day, 22:14:49", "remaining_time": "10:39:00", "throughput": 4647.71, "total_tokens": 773795056} {"current_steps": 12750, "total_steps": 15680, "loss": 0.24109892845153807, "lr": 8.376496509557808e-07, "epoch": 1.6262755102040818, "percentage": 81.31, "elapsed_time": "1 day, 22:15:58", "remaining_time": "10:37:55", "throughput": 4647.55, "total_tokens": 774086496} {"current_steps": 12755, "total_steps": 15680, "loss": 0.2351205587387085, "lr": 8.348764493796447e-07, "epoch": 1.6269132653061225, "percentage": 81.35, "elapsed_time": "1 day, 22:16:52", "remaining_time": "10:36:47", "throughput": 4647.94, "total_tokens": 774407344} {"current_steps": 12760, "total_steps": 15680, "loss": 0.22835516929626465, "lr": 8.321074277958835e-07, "epoch": 1.6275510204081631, "percentage": 81.38, "elapsed_time": "1 day, 22:18:00", "remaining_time": "10:35:43", "throughput": 4647.89, "total_tokens": 774713704} {"current_steps": 12765, "total_steps": 15680, "loss": 0.24194543361663817, "lr": 8.293425889834045e-07, "epoch": 1.6281887755102042, "percentage": 81.41, "elapsed_time": "1 day, 22:19:08", "remaining_time": "10:34:38", "throughput": 4647.85, "total_tokens": 775024480} {"current_steps": 12770, "total_steps": 15680, "loss": 0.25502166748046873, "lr": 8.265819357169124e-07, "epoch": 1.628826530612245, "percentage": 81.44, "elapsed_time": "1 day, 22:20:19", "remaining_time": "10:33:34", "throughput": 4647.61, "total_tokens": 775311536} {"current_steps": 12775, "total_steps": 15680, "loss": 0.24874403476715087, "lr": 8.238254707669208e-07, "epoch": 1.6294642857142856, "percentage": 81.47, "elapsed_time": "1 day, 22:21:34", "remaining_time": "10:32:31", "throughput": 4647.4, "total_tokens": 775627888} {"current_steps": 12780, "total_steps": 15680, "loss": 0.2492523431777954, "lr": 8.210731968997331e-07, "epoch": 1.6301020408163265, "percentage": 81.51, "elapsed_time": "1 day, 22:22:39", "remaining_time": "10:31:25", "throughput": 4647.43, "total_tokens": 775932416} {"current_steps": 12785, "total_steps": 15680, "loss": 0.26210508346557615, "lr": 8.183251168774476e-07, "epoch": 1.6307397959183674, "percentage": 81.54, "elapsed_time": "1 day, 22:23:44", "remaining_time": "10:30:20", "throughput": 4647.53, "total_tokens": 776250104} {"current_steps": 12790, "total_steps": 15680, "loss": 0.26555054187774657, "lr": 8.155812334579532e-07, "epoch": 1.631377551020408, "percentage": 81.57, "elapsed_time": "1 day, 22:24:48", "remaining_time": "10:29:14", "throughput": 4647.58, "total_tokens": 776555176} {"current_steps": 12795, "total_steps": 15680, "loss": 0.24640944004058837, "lr": 8.128415493949326e-07, "epoch": 1.632015306122449, "percentage": 81.6, "elapsed_time": "1 day, 22:25:58", "remaining_time": "10:28:10", "throughput": 4647.45, "total_tokens": 776859304} {"current_steps": 12800, "total_steps": 15680, "loss": 0.25874876976013184, "lr": 8.101060674378463e-07, "epoch": 1.6326530612244898, "percentage": 81.63, "elapsed_time": "1 day, 22:27:07", "remaining_time": "10:27:06", "throughput": 4647.31, "total_tokens": 777159832} {"current_steps": 12805, "total_steps": 15680, "loss": 0.24507718086242675, "lr": 8.073747903319418e-07, "epoch": 1.6332908163265305, "percentage": 81.66, "elapsed_time": "1 day, 22:28:08", "remaining_time": "10:25:59", "throughput": 4647.34, "total_tokens": 777445384} {"current_steps": 12810, "total_steps": 15680, "loss": 0.268278980255127, "lr": 8.046477208182501e-07, "epoch": 1.6339285714285714, "percentage": 81.7, "elapsed_time": "1 day, 22:29:17", "remaining_time": "10:24:55", "throughput": 4647.17, "total_tokens": 777738600} {"current_steps": 12815, "total_steps": 15680, "loss": 0.26207268238067627, "lr": 8.019248616335717e-07, "epoch": 1.6345663265306123, "percentage": 81.73, "elapsed_time": "1 day, 22:30:23", "remaining_time": "10:23:50", "throughput": 4647.15, "total_tokens": 778042536} {"current_steps": 12820, "total_steps": 15680, "loss": 0.2402644395828247, "lr": 7.992062155104879e-07, "epoch": 1.635204081632653, "percentage": 81.76, "elapsed_time": "1 day, 22:31:25", "remaining_time": "10:22:44", "throughput": 4647.24, "total_tokens": 778347480} {"current_steps": 12825, "total_steps": 15680, "loss": 0.263356351852417, "lr": 7.964917851773496e-07, "epoch": 1.6358418367346939, "percentage": 81.79, "elapsed_time": "1 day, 22:32:34", "remaining_time": "10:21:39", "throughput": 4647.16, "total_tokens": 778652856} {"current_steps": 12830, "total_steps": 15680, "loss": 0.26779518127441404, "lr": 7.937815733582771e-07, "epoch": 1.6364795918367347, "percentage": 81.82, "elapsed_time": "1 day, 22:33:34", "remaining_time": "10:20:33", "throughput": 4647.34, "total_tokens": 778960296} {"current_steps": 12835, "total_steps": 15680, "loss": 0.23808066844940184, "lr": 7.910755827731576e-07, "epoch": 1.6371173469387754, "percentage": 81.86, "elapsed_time": "1 day, 22:34:47", "remaining_time": "10:19:29", "throughput": 4647.12, "total_tokens": 779262384} {"current_steps": 12840, "total_steps": 15680, "loss": 0.23737592697143556, "lr": 7.883738161376414e-07, "epoch": 1.6377551020408163, "percentage": 81.89, "elapsed_time": "1 day, 22:35:48", "remaining_time": "10:18:23", "throughput": 4647.21, "total_tokens": 779563184} {"current_steps": 12845, "total_steps": 15680, "loss": 0.24407224655151366, "lr": 7.856762761631398e-07, "epoch": 1.6383928571428572, "percentage": 81.92, "elapsed_time": "1 day, 22:36:58", "remaining_time": "10:17:18", "throughput": 4647.17, "total_tokens": 779881240} {"current_steps": 12850, "total_steps": 15680, "loss": 0.2409985065460205, "lr": 7.829829655568239e-07, "epoch": 1.6390306122448979, "percentage": 81.95, "elapsed_time": "1 day, 22:38:01", "remaining_time": "10:16:13", "throughput": 4647.16, "total_tokens": 780172920} {"current_steps": 12855, "total_steps": 15680, "loss": 0.255547308921814, "lr": 7.802938870216159e-07, "epoch": 1.6396683673469388, "percentage": 81.98, "elapsed_time": "1 day, 22:39:08", "remaining_time": "10:15:08", "throughput": 4647.14, "total_tokens": 780480104} {"current_steps": 12860, "total_steps": 15680, "loss": 0.229118275642395, "lr": 7.776090432561967e-07, "epoch": 1.6403061224489797, "percentage": 82.02, "elapsed_time": "1 day, 22:40:11", "remaining_time": "10:14:02", "throughput": 4647.2, "total_tokens": 780783224} {"current_steps": 12865, "total_steps": 15680, "loss": 0.27794227600097654, "lr": 7.749284369549954e-07, "epoch": 1.6409438775510203, "percentage": 82.05, "elapsed_time": "1 day, 22:41:16", "remaining_time": "10:12:57", "throughput": 4647.22, "total_tokens": 781090976} {"current_steps": 12870, "total_steps": 15680, "loss": 0.24514400959014893, "lr": 7.722520708081843e-07, "epoch": 1.6415816326530612, "percentage": 82.08, "elapsed_time": "1 day, 22:42:24", "remaining_time": "10:11:52", "throughput": 4647.18, "total_tokens": 781398792} {"current_steps": 12875, "total_steps": 15680, "loss": 0.2551210880279541, "lr": 7.695799475016846e-07, "epoch": 1.6422193877551021, "percentage": 82.11, "elapsed_time": "1 day, 22:43:15", "remaining_time": "10:10:43", "throughput": 4647.65, "total_tokens": 781715312} {"current_steps": 12880, "total_steps": 15680, "loss": 0.24247095584869385, "lr": 7.669120697171617e-07, "epoch": 1.6428571428571428, "percentage": 82.14, "elapsed_time": "1 day, 22:44:26", "remaining_time": "10:09:39", "throughput": 4647.49, "total_tokens": 782018872} {"current_steps": 12885, "total_steps": 15680, "loss": 0.2649207592010498, "lr": 7.642484401320138e-07, "epoch": 1.6434948979591837, "percentage": 82.17, "elapsed_time": "1 day, 22:45:38", "remaining_time": "10:08:35", "throughput": 4647.25, "total_tokens": 782310112} {"current_steps": 12890, "total_steps": 15680, "loss": 0.2558600902557373, "lr": 7.615890614193788e-07, "epoch": 1.6441326530612246, "percentage": 82.21, "elapsed_time": "1 day, 22:46:42", "remaining_time": "10:07:30", "throughput": 4647.3, "total_tokens": 782613848} {"current_steps": 12895, "total_steps": 15680, "loss": 0.26041407585144044, "lr": 7.589339362481334e-07, "epoch": 1.6447704081632653, "percentage": 82.24, "elapsed_time": "1 day, 22:47:59", "remaining_time": "10:06:27", "throughput": 4646.93, "total_tokens": 782912536} {"current_steps": 12900, "total_steps": 15680, "loss": 0.2617289304733276, "lr": 7.562830672828775e-07, "epoch": 1.6454081632653061, "percentage": 82.27, "elapsed_time": "1 day, 22:48:56", "remaining_time": "10:05:20", "throughput": 4647.18, "total_tokens": 783219264} {"current_steps": 12905, "total_steps": 15680, "loss": 0.26701955795288085, "lr": 7.536364571839439e-07, "epoch": 1.646045918367347, "percentage": 82.3, "elapsed_time": "1 day, 22:49:50", "remaining_time": "10:04:12", "throughput": 4647.55, "total_tokens": 783532200} {"current_steps": 12910, "total_steps": 15680, "loss": 0.26680240631103513, "lr": 7.509941086073907e-07, "epoch": 1.6466836734693877, "percentage": 82.33, "elapsed_time": "1 day, 22:50:58", "remaining_time": "10:03:07", "throughput": 4647.52, "total_tokens": 783844176} {"current_steps": 12915, "total_steps": 15680, "loss": 0.2463916301727295, "lr": 7.483560242049998e-07, "epoch": 1.6473214285714286, "percentage": 82.37, "elapsed_time": "1 day, 22:52:08", "remaining_time": "10:02:03", "throughput": 4647.29, "total_tokens": 784130784} {"current_steps": 12920, "total_steps": 15680, "loss": 0.24036722183227538, "lr": 7.457222066242725e-07, "epoch": 1.6479591836734695, "percentage": 82.4, "elapsed_time": "1 day, 22:53:23", "remaining_time": "10:01:00", "throughput": 4647.1, "total_tokens": 784447456} {"current_steps": 12925, "total_steps": 15680, "loss": 0.24784183502197266, "lr": 7.430926585084292e-07, "epoch": 1.6485969387755102, "percentage": 82.43, "elapsed_time": "1 day, 22:54:25", "remaining_time": "9:59:54", "throughput": 4647.3, "total_tokens": 784767912} {"current_steps": 12930, "total_steps": 15680, "loss": 0.25671067237854006, "lr": 7.404673824964048e-07, "epoch": 1.649234693877551, "percentage": 82.46, "elapsed_time": "1 day, 22:55:20", "remaining_time": "9:58:46", "throughput": 4647.61, "total_tokens": 785078864} {"current_steps": 12935, "total_steps": 15680, "loss": 0.2695626974105835, "lr": 7.37846381222847e-07, "epoch": 1.649872448979592, "percentage": 82.49, "elapsed_time": "1 day, 22:56:24", "remaining_time": "9:57:41", "throughput": 4647.72, "total_tokens": 785393048} {"current_steps": 12940, "total_steps": 15680, "loss": 0.23758177757263182, "lr": 7.352296573181139e-07, "epoch": 1.6505102040816326, "percentage": 82.53, "elapsed_time": "1 day, 22:57:37", "remaining_time": "9:56:37", "throughput": 4647.47, "total_tokens": 785691312} {"current_steps": 12945, "total_steps": 15680, "loss": 0.26804699897766116, "lr": 7.326172134082704e-07, "epoch": 1.6511479591836735, "percentage": 82.56, "elapsed_time": "1 day, 22:58:45", "remaining_time": "9:55:32", "throughput": 4647.39, "total_tokens": 785992592} {"current_steps": 12950, "total_steps": 15680, "loss": 0.26202845573425293, "lr": 7.300090521150882e-07, "epoch": 1.6517857142857144, "percentage": 82.59, "elapsed_time": "1 day, 22:59:50", "remaining_time": "9:54:27", "throughput": 4647.4, "total_tokens": 786295144} {"current_steps": 12955, "total_steps": 15680, "loss": 0.2594417095184326, "lr": 7.274051760560364e-07, "epoch": 1.652423469387755, "percentage": 82.62, "elapsed_time": "1 day, 23:00:51", "remaining_time": "9:53:20", "throughput": 4647.49, "total_tokens": 786595296} {"current_steps": 12960, "total_steps": 15680, "loss": 0.25502710342407225, "lr": 7.248055878442861e-07, "epoch": 1.6530612244897958, "percentage": 82.65, "elapsed_time": "1 day, 23:01:55", "remaining_time": "9:52:15", "throughput": 4647.46, "total_tokens": 786887408} {"current_steps": 12965, "total_steps": 15680, "loss": 0.28072850704193114, "lr": 7.222102900887102e-07, "epoch": 1.6536989795918369, "percentage": 82.68, "elapsed_time": "1 day, 23:02:58", "remaining_time": "9:51:09", "throughput": 4647.51, "total_tokens": 787190392} {"current_steps": 12970, "total_steps": 15680, "loss": 0.2597139835357666, "lr": 7.196192853938672e-07, "epoch": 1.6543367346938775, "percentage": 82.72, "elapsed_time": "1 day, 23:04:04", "remaining_time": "9:50:04", "throughput": 4647.48, "total_tokens": 787490568} {"current_steps": 12975, "total_steps": 15680, "loss": 0.24894609451293945, "lr": 7.170325763600106e-07, "epoch": 1.6549744897959182, "percentage": 82.75, "elapsed_time": "1 day, 23:04:59", "remaining_time": "9:48:56", "throughput": 4647.72, "total_tokens": 787785952} {"current_steps": 12980, "total_steps": 15680, "loss": 0.2468048334121704, "lr": 7.144501655830882e-07, "epoch": 1.6556122448979593, "percentage": 82.78, "elapsed_time": "1 day, 23:06:03", "remaining_time": "9:47:51", "throughput": 4647.68, "total_tokens": 788076952} {"current_steps": 12985, "total_steps": 15680, "loss": 0.2554357051849365, "lr": 7.118720556547259e-07, "epoch": 1.65625, "percentage": 82.81, "elapsed_time": "1 day, 23:07:00", "remaining_time": "9:46:44", "throughput": 4647.83, "total_tokens": 788368824} {"current_steps": 12990, "total_steps": 15680, "loss": 0.261881685256958, "lr": 7.092982491622374e-07, "epoch": 1.6568877551020407, "percentage": 82.84, "elapsed_time": "1 day, 23:07:58", "remaining_time": "9:45:37", "throughput": 4648.06, "total_tokens": 788675568} {"current_steps": 12995, "total_steps": 15680, "loss": 0.24860353469848634, "lr": 7.067287486886181e-07, "epoch": 1.6575255102040818, "percentage": 82.88, "elapsed_time": "1 day, 23:09:06", "remaining_time": "9:44:32", "throughput": 4647.99, "total_tokens": 788981344} {"current_steps": 13000, "total_steps": 15680, "loss": 0.2610947132110596, "lr": 7.04163556812541e-07, "epoch": 1.6581632653061225, "percentage": 82.91, "elapsed_time": "1 day, 23:10:10", "remaining_time": "9:43:27", "throughput": 4648.02, "total_tokens": 789282208} {"current_steps": 13005, "total_steps": 15680, "loss": 0.2498173713684082, "lr": 7.016026761083556e-07, "epoch": 1.6588010204081631, "percentage": 82.94, "elapsed_time": "1 day, 23:11:22", "remaining_time": "9:42:23", "throughput": 4647.81, "total_tokens": 789584376} {"current_steps": 13010, "total_steps": 15680, "loss": 0.25535106658935547, "lr": 6.990461091460832e-07, "epoch": 1.6594387755102042, "percentage": 82.97, "elapsed_time": "1 day, 23:12:26", "remaining_time": "9:41:17", "throughput": 4647.82, "total_tokens": 789879496} {"current_steps": 13015, "total_steps": 15680, "loss": 0.2566126585006714, "lr": 6.964938584914188e-07, "epoch": 1.660076530612245, "percentage": 83.0, "elapsed_time": "1 day, 23:13:38", "remaining_time": "9:40:13", "throughput": 4647.62, "total_tokens": 790183328} {"current_steps": 13020, "total_steps": 15680, "loss": 0.2553213119506836, "lr": 6.939459267057236e-07, "epoch": 1.6607142857142856, "percentage": 83.04, "elapsed_time": "1 day, 23:14:36", "remaining_time": "9:39:06", "throughput": 4647.88, "total_tokens": 790497336} {"current_steps": 13025, "total_steps": 15680, "loss": 0.2686570644378662, "lr": 6.914023163460248e-07, "epoch": 1.6613520408163265, "percentage": 83.07, "elapsed_time": "1 day, 23:15:45", "remaining_time": "9:38:02", "throughput": 4647.79, "total_tokens": 790798448} {"current_steps": 13030, "total_steps": 15680, "loss": 0.2502615213394165, "lr": 6.888630299650134e-07, "epoch": 1.6619897959183674, "percentage": 83.1, "elapsed_time": "1 day, 23:16:47", "remaining_time": "9:36:56", "throughput": 4647.88, "total_tokens": 791104728} {"current_steps": 13035, "total_steps": 15680, "loss": 0.23832058906555176, "lr": 6.863280701110409e-07, "epoch": 1.662627551020408, "percentage": 83.13, "elapsed_time": "1 day, 23:17:59", "remaining_time": "9:35:52", "throughput": 4647.67, "total_tokens": 791402312} {"current_steps": 13040, "total_steps": 15680, "loss": 0.24954562187194823, "lr": 6.837974393281171e-07, "epoch": 1.663265306122449, "percentage": 83.16, "elapsed_time": "1 day, 23:19:01", "remaining_time": "9:34:46", "throughput": 4647.75, "total_tokens": 791703896} {"current_steps": 13045, "total_steps": 15680, "loss": 0.23029787540435792, "lr": 6.812711401559036e-07, "epoch": 1.6639030612244898, "percentage": 83.2, "elapsed_time": "1 day, 23:20:04", "remaining_time": "9:33:40", "throughput": 4647.75, "total_tokens": 791997456} {"current_steps": 13050, "total_steps": 15680, "loss": 0.2461026668548584, "lr": 6.787491751297215e-07, "epoch": 1.6645408163265305, "percentage": 83.23, "elapsed_time": "1 day, 23:21:08", "remaining_time": "9:32:34", "throughput": 4647.8, "total_tokens": 792301680} {"current_steps": 13055, "total_steps": 15680, "loss": 0.28578948974609375, "lr": 6.762315467805391e-07, "epoch": 1.6651785714285714, "percentage": 83.26, "elapsed_time": "1 day, 23:22:12", "remaining_time": "9:31:29", "throughput": 4647.83, "total_tokens": 792607080} {"current_steps": 13060, "total_steps": 15680, "loss": 0.246743106842041, "lr": 6.737182576349682e-07, "epoch": 1.6658163265306123, "percentage": 83.29, "elapsed_time": "1 day, 23:23:26", "remaining_time": "9:30:25", "throughput": 4647.62, "total_tokens": 792914096} {"current_steps": 13065, "total_steps": 15680, "loss": 0.24052057266235352, "lr": 6.712093102152739e-07, "epoch": 1.666454081632653, "percentage": 83.32, "elapsed_time": "1 day, 23:24:38", "remaining_time": "9:29:21", "throughput": 4647.44, "total_tokens": 793216536} {"current_steps": 13070, "total_steps": 15680, "loss": 0.2614285469055176, "lr": 6.687047070393599e-07, "epoch": 1.6670918367346939, "percentage": 83.35, "elapsed_time": "1 day, 23:25:44", "remaining_time": "9:28:16", "throughput": 4647.42, "total_tokens": 793522384} {"current_steps": 13075, "total_steps": 15680, "loss": 0.2567417144775391, "lr": 6.662044506207682e-07, "epoch": 1.6677295918367347, "percentage": 83.39, "elapsed_time": "1 day, 23:26:42", "remaining_time": "9:27:09", "throughput": 4647.65, "total_tokens": 793828944} {"current_steps": 13080, "total_steps": 15680, "loss": 0.253106427192688, "lr": 6.637085434686818e-07, "epoch": 1.6683673469387754, "percentage": 83.42, "elapsed_time": "1 day, 23:27:37", "remaining_time": "9:26:02", "throughput": 4648.0, "total_tokens": 794146080} {"current_steps": 13085, "total_steps": 15680, "loss": 0.24351756572723388, "lr": 6.612169880879182e-07, "epoch": 1.6690051020408163, "percentage": 83.45, "elapsed_time": "1 day, 23:28:42", "remaining_time": "9:24:57", "throughput": 4648.03, "total_tokens": 794452296} {"current_steps": 13090, "total_steps": 15680, "loss": 0.25382318496704104, "lr": 6.587297869789267e-07, "epoch": 1.6696428571428572, "percentage": 83.48, "elapsed_time": "1 day, 23:29:41", "remaining_time": "9:23:50", "throughput": 4648.21, "total_tokens": 794756976} {"current_steps": 13095, "total_steps": 15680, "loss": 0.25609397888183594, "lr": 6.562469426377876e-07, "epoch": 1.6702806122448979, "percentage": 83.51, "elapsed_time": "1 day, 23:30:52", "remaining_time": "9:22:46", "throughput": 4648.11, "total_tokens": 795069352} {"current_steps": 13100, "total_steps": 15680, "loss": 0.2575140237808228, "lr": 6.537684575562092e-07, "epoch": 1.6709183673469388, "percentage": 83.55, "elapsed_time": "1 day, 23:32:03", "remaining_time": "9:21:42", "throughput": 4647.91, "total_tokens": 795365352} {"current_steps": 13105, "total_steps": 15680, "loss": 0.26410722732543945, "lr": 6.512943342215234e-07, "epoch": 1.6715561224489797, "percentage": 83.58, "elapsed_time": "1 day, 23:33:00", "remaining_time": "9:20:35", "throughput": 4648.19, "total_tokens": 795678608} {"current_steps": 13110, "total_steps": 15680, "loss": 0.2558436870574951, "lr": 6.48824575116686e-07, "epoch": 1.6721938775510203, "percentage": 83.61, "elapsed_time": "1 day, 23:34:08", "remaining_time": "9:19:30", "throughput": 4648.07, "total_tokens": 795975296} {"current_steps": 13115, "total_steps": 15680, "loss": 0.2514554262161255, "lr": 6.463591827202731e-07, "epoch": 1.6728316326530612, "percentage": 83.64, "elapsed_time": "1 day, 23:35:07", "remaining_time": "9:18:23", "throughput": 4648.27, "total_tokens": 796281592} {"current_steps": 13120, "total_steps": 15680, "loss": 0.2432316780090332, "lr": 6.43898159506478e-07, "epoch": 1.6734693877551021, "percentage": 83.67, "elapsed_time": "1 day, 23:36:16", "remaining_time": "9:17:19", "throughput": 4648.15, "total_tokens": 796582856} {"current_steps": 13125, "total_steps": 15680, "loss": 0.24376821517944336, "lr": 6.414415079451092e-07, "epoch": 1.6741071428571428, "percentage": 83.71, "elapsed_time": "1 day, 23:37:18", "remaining_time": "9:16:13", "throughput": 4648.15, "total_tokens": 796872776} {"current_steps": 13130, "total_steps": 15680, "loss": 0.2742983341217041, "lr": 6.389892305015882e-07, "epoch": 1.6747448979591837, "percentage": 83.74, "elapsed_time": "1 day, 23:38:26", "remaining_time": "9:15:08", "throughput": 4648.15, "total_tokens": 797187792} {"current_steps": 13135, "total_steps": 15680, "loss": 0.24300801753997803, "lr": 6.365413296369466e-07, "epoch": 1.6753826530612246, "percentage": 83.77, "elapsed_time": "1 day, 23:39:32", "remaining_time": "9:14:03", "throughput": 4648.1, "total_tokens": 797483784} {"current_steps": 13140, "total_steps": 15680, "loss": 0.24329781532287598, "lr": 6.340978078078253e-07, "epoch": 1.6760204081632653, "percentage": 83.8, "elapsed_time": "1 day, 23:40:38", "remaining_time": "9:12:58", "throughput": 4648.06, "total_tokens": 797783992} {"current_steps": 13145, "total_steps": 15680, "loss": 0.24906373023986816, "lr": 6.316586674664654e-07, "epoch": 1.6766581632653061, "percentage": 83.83, "elapsed_time": "1 day, 23:41:50", "remaining_time": "9:11:54", "throughput": 4647.92, "total_tokens": 798095032} {"current_steps": 13150, "total_steps": 15680, "loss": 0.2658334732055664, "lr": 6.292239110607185e-07, "epoch": 1.677295918367347, "percentage": 83.86, "elapsed_time": "1 day, 23:43:05", "remaining_time": "9:10:50", "throughput": 4647.63, "total_tokens": 798396536} {"current_steps": 13155, "total_steps": 15680, "loss": 0.23490290641784667, "lr": 6.26793541034032e-07, "epoch": 1.6779336734693877, "percentage": 83.9, "elapsed_time": "1 day, 23:44:11", "remaining_time": "9:09:45", "throughput": 4647.49, "total_tokens": 798675488} {"current_steps": 13160, "total_steps": 15680, "loss": 0.24631378650665284, "lr": 6.243675598254501e-07, "epoch": 1.6785714285714286, "percentage": 83.93, "elapsed_time": "1 day, 23:45:15", "remaining_time": "9:08:39", "throughput": 4647.51, "total_tokens": 798979112} {"current_steps": 13165, "total_steps": 15680, "loss": 0.24266324043273926, "lr": 6.21945969869614e-07, "epoch": 1.6792091836734695, "percentage": 83.96, "elapsed_time": "1 day, 23:46:28", "remaining_time": "9:07:36", "throughput": 4647.33, "total_tokens": 799286176} {"current_steps": 13170, "total_steps": 15680, "loss": 0.22390503883361818, "lr": 6.195287735967626e-07, "epoch": 1.6798469387755102, "percentage": 83.99, "elapsed_time": "1 day, 23:47:22", "remaining_time": "9:06:28", "throughput": 4647.69, "total_tokens": 799599776} {"current_steps": 13175, "total_steps": 15680, "loss": 0.2543494462966919, "lr": 6.171159734327164e-07, "epoch": 1.680484693877551, "percentage": 84.02, "elapsed_time": "1 day, 23:48:31", "remaining_time": "9:05:24", "throughput": 4647.59, "total_tokens": 799903368} {"current_steps": 13180, "total_steps": 15680, "loss": 0.24501893520355225, "lr": 6.147075717988904e-07, "epoch": 1.681122448979592, "percentage": 84.06, "elapsed_time": "1 day, 23:49:37", "remaining_time": "9:04:18", "throughput": 4647.58, "total_tokens": 800207056} {"current_steps": 13185, "total_steps": 15680, "loss": 0.2572981834411621, "lr": 6.12303571112286e-07, "epoch": 1.6817602040816326, "percentage": 84.09, "elapsed_time": "1 day, 23:50:42", "remaining_time": "9:03:13", "throughput": 4647.58, "total_tokens": 800511624} {"current_steps": 13190, "total_steps": 15680, "loss": 0.2360074996948242, "lr": 6.099039737854834e-07, "epoch": 1.6823979591836735, "percentage": 84.12, "elapsed_time": "1 day, 23:51:58", "remaining_time": "9:02:10", "throughput": 4647.28, "total_tokens": 800811064} {"current_steps": 13195, "total_steps": 15680, "loss": 0.22553706169128418, "lr": 6.075087822266462e-07, "epoch": 1.6830357142857144, "percentage": 84.15, "elapsed_time": "1 day, 23:52:56", "remaining_time": "9:01:03", "throughput": 4647.46, "total_tokens": 801112472} {"current_steps": 13200, "total_steps": 15680, "loss": 0.24001829624176024, "lr": 6.051179988395172e-07, "epoch": 1.683673469387755, "percentage": 84.18, "elapsed_time": "1 day, 23:54:06", "remaining_time": "8:59:59", "throughput": 4647.28, "total_tokens": 801409320} {"current_steps": 13205, "total_steps": 15680, "loss": 0.25508794784545896, "lr": 6.027316260234146e-07, "epoch": 1.6843112244897958, "percentage": 84.22, "elapsed_time": "1 day, 23:55:10", "remaining_time": "8:58:53", "throughput": 4647.24, "total_tokens": 801695944} {"current_steps": 13210, "total_steps": 15680, "loss": 0.23457629680633546, "lr": 6.003496661732294e-07, "epoch": 1.6849489795918369, "percentage": 84.25, "elapsed_time": "1 day, 23:56:12", "remaining_time": "8:57:47", "throughput": 4647.34, "total_tokens": 802004992} {"current_steps": 13215, "total_steps": 15680, "loss": 0.24449772834777833, "lr": 5.979721216794248e-07, "epoch": 1.6855867346938775, "percentage": 84.28, "elapsed_time": "1 day, 23:57:12", "remaining_time": "8:56:41", "throughput": 4647.53, "total_tokens": 802316736} {"current_steps": 13220, "total_steps": 15680, "loss": 0.2484027624130249, "lr": 5.955989949280339e-07, "epoch": 1.6862244897959182, "percentage": 84.31, "elapsed_time": "1 day, 23:58:23", "remaining_time": "8:55:36", "throughput": 4647.4, "total_tokens": 802621320} {"current_steps": 13225, "total_steps": 15680, "loss": 0.24606828689575194, "lr": 5.932302883006546e-07, "epoch": 1.6868622448979593, "percentage": 84.34, "elapsed_time": "1 day, 23:59:27", "remaining_time": "8:54:31", "throughput": 4647.41, "total_tokens": 802920632} {"current_steps": 13230, "total_steps": 15680, "loss": 0.25984389781951905, "lr": 5.908660041744473e-07, "epoch": 1.6875, "percentage": 84.38, "elapsed_time": "2 days, 0:00:31", "remaining_time": "8:53:25", "throughput": 4647.38, "total_tokens": 803215896} {"current_steps": 13235, "total_steps": 15680, "loss": 0.2351299285888672, "lr": 5.88506144922139e-07, "epoch": 1.6881377551020407, "percentage": 84.41, "elapsed_time": "2 days, 0:01:34", "remaining_time": "8:52:20", "throughput": 4647.44, "total_tokens": 803516888} {"current_steps": 13240, "total_steps": 15680, "loss": 0.26414904594421384, "lr": 5.861507129120136e-07, "epoch": 1.6887755102040818, "percentage": 84.44, "elapsed_time": "2 days, 0:02:44", "remaining_time": "8:51:15", "throughput": 4647.27, "total_tokens": 803810240} {"current_steps": 13245, "total_steps": 15680, "loss": 0.25545492172241213, "lr": 5.83799710507909e-07, "epoch": 1.6894132653061225, "percentage": 84.47, "elapsed_time": "2 days, 0:03:51", "remaining_time": "8:50:10", "throughput": 4647.1, "total_tokens": 804093920} {"current_steps": 13250, "total_steps": 15680, "loss": 0.26322863101959226, "lr": 5.814531400692208e-07, "epoch": 1.6900510204081631, "percentage": 84.5, "elapsed_time": "2 days, 0:05:00", "remaining_time": "8:49:06", "throughput": 4646.98, "total_tokens": 804396312} {"current_steps": 13255, "total_steps": 15680, "loss": 0.24986505508422852, "lr": 5.791110039508991e-07, "epoch": 1.6906887755102042, "percentage": 84.53, "elapsed_time": "2 days, 0:05:53", "remaining_time": "8:47:58", "throughput": 4647.41, "total_tokens": 804713896} {"current_steps": 13260, "total_steps": 15680, "loss": 0.2752215385437012, "lr": 5.767733045034384e-07, "epoch": 1.691326530612245, "percentage": 84.57, "elapsed_time": "2 days, 0:06:50", "remaining_time": "8:46:51", "throughput": 4647.7, "total_tokens": 805030240} {"current_steps": 13265, "total_steps": 15680, "loss": 0.25286269187927246, "lr": 5.744400440728826e-07, "epoch": 1.6919642857142856, "percentage": 84.6, "elapsed_time": "2 days, 0:08:07", "remaining_time": "8:45:48", "throughput": 4647.3, "total_tokens": 805319600} {"current_steps": 13270, "total_steps": 15680, "loss": 0.24343976974487305, "lr": 5.721112250008254e-07, "epoch": 1.6926020408163265, "percentage": 84.63, "elapsed_time": "2 days, 0:09:12", "remaining_time": "8:44:42", "throughput": 4647.19, "total_tokens": 805599816} {"current_steps": 13275, "total_steps": 15680, "loss": 0.24480876922607422, "lr": 5.697868496243958e-07, "epoch": 1.6932397959183674, "percentage": 84.66, "elapsed_time": "2 days, 0:10:19", "remaining_time": "8:43:37", "throughput": 4647.05, "total_tokens": 805887848} {"current_steps": 13280, "total_steps": 15680, "loss": 0.25247907638549805, "lr": 5.674669202762684e-07, "epoch": 1.693877551020408, "percentage": 84.69, "elapsed_time": "2 days, 0:11:32", "remaining_time": "8:42:34", "throughput": 4646.87, "total_tokens": 806196384} {"current_steps": 13285, "total_steps": 15680, "loss": 0.2437495231628418, "lr": 5.651514392846535e-07, "epoch": 1.694515306122449, "percentage": 84.73, "elapsed_time": "2 days, 0:12:41", "remaining_time": "8:41:29", "throughput": 4646.78, "total_tokens": 806500696} {"current_steps": 13290, "total_steps": 15680, "loss": 0.2544881343841553, "lr": 5.628404089732986e-07, "epoch": 1.6951530612244898, "percentage": 84.76, "elapsed_time": "2 days, 0:13:46", "remaining_time": "8:40:24", "throughput": 4646.82, "total_tokens": 806810160} {"current_steps": 13295, "total_steps": 15680, "loss": 0.25745701789855957, "lr": 5.605338316614839e-07, "epoch": 1.6957908163265305, "percentage": 84.79, "elapsed_time": "2 days, 0:14:54", "remaining_time": "8:39:19", "throughput": 4646.74, "total_tokens": 807112440} {"current_steps": 13300, "total_steps": 15680, "loss": 0.2437589645385742, "lr": 5.582317096640205e-07, "epoch": 1.6964285714285714, "percentage": 84.82, "elapsed_time": "2 days, 0:16:02", "remaining_time": "8:38:14", "throughput": 4646.65, "total_tokens": 807413184} {"current_steps": 13305, "total_steps": 15680, "loss": 0.24849872589111327, "lr": 5.559340452912488e-07, "epoch": 1.6970663265306123, "percentage": 84.85, "elapsed_time": "2 days, 0:16:54", "remaining_time": "8:37:06", "throughput": 4647.09, "total_tokens": 807731504} {"current_steps": 13310, "total_steps": 15680, "loss": 0.23475873470306396, "lr": 5.536408408490357e-07, "epoch": 1.697704081632653, "percentage": 84.89, "elapsed_time": "2 days, 0:17:58", "remaining_time": "8:36:01", "throughput": 4647.12, "total_tokens": 808032920} {"current_steps": 13315, "total_steps": 15680, "loss": 0.2626044511795044, "lr": 5.513520986387721e-07, "epoch": 1.6983418367346939, "percentage": 84.92, "elapsed_time": "2 days, 0:19:06", "remaining_time": "8:34:56", "throughput": 4647.06, "total_tokens": 808338432} {"current_steps": 13320, "total_steps": 15680, "loss": 0.2594637632369995, "lr": 5.490678209573702e-07, "epoch": 1.6989795918367347, "percentage": 84.95, "elapsed_time": "2 days, 0:20:06", "remaining_time": "8:33:49", "throughput": 4647.25, "total_tokens": 808650944} {"current_steps": 13325, "total_steps": 15680, "loss": 0.24765939712524415, "lr": 5.467880100972633e-07, "epoch": 1.6996173469387754, "percentage": 84.98, "elapsed_time": "2 days, 0:21:11", "remaining_time": "8:32:44", "throughput": 4647.29, "total_tokens": 808959368} {"current_steps": 13330, "total_steps": 15680, "loss": 0.24539852142333984, "lr": 5.445126683463991e-07, "epoch": 1.7002551020408163, "percentage": 85.01, "elapsed_time": "2 days, 0:22:25", "remaining_time": "8:31:40", "throughput": 4647.07, "total_tokens": 809263464} {"current_steps": 13335, "total_steps": 15680, "loss": 0.24530429840087892, "lr": 5.422417979882416e-07, "epoch": 1.7008928571428572, "percentage": 85.04, "elapsed_time": "2 days, 0:23:39", "remaining_time": "8:30:37", "throughput": 4646.76, "total_tokens": 809557232} {"current_steps": 13340, "total_steps": 15680, "loss": 0.26610822677612306, "lr": 5.399754013017711e-07, "epoch": 1.7015306122448979, "percentage": 85.08, "elapsed_time": "2 days, 0:24:46", "remaining_time": "8:29:32", "throughput": 4646.64, "total_tokens": 809849272} {"current_steps": 13345, "total_steps": 15680, "loss": 0.2476370096206665, "lr": 5.377134805614714e-07, "epoch": 1.7021683673469388, "percentage": 85.11, "elapsed_time": "2 days, 0:25:43", "remaining_time": "8:28:25", "throughput": 4646.87, "total_tokens": 810150448} {"current_steps": 13350, "total_steps": 15680, "loss": 0.23286876678466797, "lr": 5.354560380373391e-07, "epoch": 1.7028061224489797, "percentage": 85.14, "elapsed_time": "2 days, 0:26:46", "remaining_time": "8:27:19", "throughput": 4646.91, "total_tokens": 810450680} {"current_steps": 13355, "total_steps": 15680, "loss": 0.26010301113128664, "lr": 5.33203075994877e-07, "epoch": 1.7034438775510203, "percentage": 85.17, "elapsed_time": "2 days, 0:27:56", "remaining_time": "8:26:14", "throughput": 4646.76, "total_tokens": 810750576} {"current_steps": 13360, "total_steps": 15680, "loss": 0.2614151477813721, "lr": 5.30954596695088e-07, "epoch": 1.7040816326530612, "percentage": 85.2, "elapsed_time": "2 days, 0:28:54", "remaining_time": "8:25:08", "throughput": 4647.0, "total_tokens": 811061000} {"current_steps": 13365, "total_steps": 15680, "loss": 0.2446915864944458, "lr": 5.287106023944782e-07, "epoch": 1.7047193877551021, "percentage": 85.24, "elapsed_time": "2 days, 0:30:01", "remaining_time": "8:24:03", "throughput": 4646.95, "total_tokens": 811364840} {"current_steps": 13370, "total_steps": 15680, "loss": 0.2663325309753418, "lr": 5.264710953450536e-07, "epoch": 1.7053571428571428, "percentage": 85.27, "elapsed_time": "2 days, 0:31:10", "remaining_time": "8:22:58", "throughput": 4646.85, "total_tokens": 811669248} {"current_steps": 13375, "total_steps": 15680, "loss": 0.26160728931427, "lr": 5.242360777943151e-07, "epoch": 1.7059948979591837, "percentage": 85.3, "elapsed_time": "2 days, 0:32:20", "remaining_time": "8:21:54", "throughput": 4646.75, "total_tokens": 811973912} {"current_steps": 13380, "total_steps": 15680, "loss": 0.2614679574966431, "lr": 5.220055519852596e-07, "epoch": 1.7066326530612246, "percentage": 85.33, "elapsed_time": "2 days, 0:33:32", "remaining_time": "8:20:49", "throughput": 4646.52, "total_tokens": 812269376} {"current_steps": 13385, "total_steps": 15680, "loss": 0.26145367622375487, "lr": 5.197795201563744e-07, "epoch": 1.7072704081632653, "percentage": 85.36, "elapsed_time": "2 days, 0:34:25", "remaining_time": "8:19:42", "throughput": 4646.86, "total_tokens": 812574120} {"current_steps": 13390, "total_steps": 15680, "loss": 0.2672783851623535, "lr": 5.17557984541639e-07, "epoch": 1.7079081632653061, "percentage": 85.4, "elapsed_time": "2 days, 0:35:21", "remaining_time": "8:18:35", "throughput": 4647.08, "total_tokens": 812875616} {"current_steps": 13395, "total_steps": 15680, "loss": 0.24822840690612794, "lr": 5.153409473705196e-07, "epoch": 1.708545918367347, "percentage": 85.43, "elapsed_time": "2 days, 0:36:27", "remaining_time": "8:17:30", "throughput": 4647.06, "total_tokens": 813175688} {"current_steps": 13400, "total_steps": 15680, "loss": 0.25509934425354003, "lr": 5.131284108679669e-07, "epoch": 1.7091836734693877, "percentage": 85.46, "elapsed_time": "2 days, 0:37:31", "remaining_time": "8:16:24", "throughput": 4647.06, "total_tokens": 813475616} {"current_steps": 13405, "total_steps": 15680, "loss": 0.25195741653442383, "lr": 5.109203772544164e-07, "epoch": 1.7098214285714286, "percentage": 85.49, "elapsed_time": "2 days, 0:38:31", "remaining_time": "8:15:18", "throughput": 4647.18, "total_tokens": 813776688} {"current_steps": 13410, "total_steps": 15680, "loss": 0.2547295570373535, "lr": 5.087168487457838e-07, "epoch": 1.7104591836734695, "percentage": 85.52, "elapsed_time": "2 days, 0:39:40", "remaining_time": "8:14:13", "throughput": 4647.14, "total_tokens": 814086584} {"current_steps": 13415, "total_steps": 15680, "loss": 0.24732956886291504, "lr": 5.065178275534649e-07, "epoch": 1.7110969387755102, "percentage": 85.55, "elapsed_time": "2 days, 0:40:51", "remaining_time": "8:13:09", "throughput": 4647.03, "total_tokens": 814396000} {"current_steps": 13420, "total_steps": 15680, "loss": 0.2538780212402344, "lr": 5.043233158843286e-07, "epoch": 1.711734693877551, "percentage": 85.59, "elapsed_time": "2 days, 0:42:01", "remaining_time": "8:12:05", "throughput": 4646.94, "total_tokens": 814709408} {"current_steps": 13425, "total_steps": 15680, "loss": 0.258031439781189, "lr": 5.021333159407232e-07, "epoch": 1.712372448979592, "percentage": 85.62, "elapsed_time": "2 days, 0:43:08", "remaining_time": "8:11:00", "throughput": 4646.89, "total_tokens": 815013680} {"current_steps": 13430, "total_steps": 15680, "loss": 0.23726649284362794, "lr": 4.999478299204663e-07, "epoch": 1.7130102040816326, "percentage": 85.65, "elapsed_time": "2 days, 0:44:02", "remaining_time": "8:09:52", "throughput": 4647.25, "total_tokens": 815325336} {"current_steps": 13435, "total_steps": 15680, "loss": 0.23950729370117188, "lr": 4.977668600168428e-07, "epoch": 1.7136479591836735, "percentage": 85.68, "elapsed_time": "2 days, 0:45:18", "remaining_time": "8:08:49", "throughput": 4646.88, "total_tokens": 815613392} {"current_steps": 13440, "total_steps": 15680, "loss": 0.2627774953842163, "lr": 4.95590408418613e-07, "epoch": 1.7142857142857144, "percentage": 85.71, "elapsed_time": "2 days, 0:46:24", "remaining_time": "8:07:44", "throughput": 4646.89, "total_tokens": 815921320} {"current_steps": 13445, "total_steps": 15680, "loss": 0.27510771751403806, "lr": 4.934184773099943e-07, "epoch": 1.714923469387755, "percentage": 85.75, "elapsed_time": "2 days, 0:47:38", "remaining_time": "8:06:40", "throughput": 4646.75, "total_tokens": 816239416} {"current_steps": 13450, "total_steps": 15680, "loss": 0.2529017448425293, "lr": 4.912510688706729e-07, "epoch": 1.7155612244897958, "percentage": 85.78, "elapsed_time": "2 days, 0:48:43", "remaining_time": "8:05:34", "throughput": 4646.75, "total_tokens": 816543240} {"current_steps": 13455, "total_steps": 15680, "loss": 0.2732319116592407, "lr": 4.89088185275794e-07, "epoch": 1.7161989795918369, "percentage": 85.81, "elapsed_time": "2 days, 0:49:45", "remaining_time": "8:04:28", "throughput": 4646.87, "total_tokens": 816852968} {"current_steps": 13460, "total_steps": 15680, "loss": 0.2589241981506348, "lr": 4.869298286959629e-07, "epoch": 1.7168367346938775, "percentage": 85.84, "elapsed_time": "2 days, 0:50:54", "remaining_time": "8:03:24", "throughput": 4646.8, "total_tokens": 817160528} {"current_steps": 13465, "total_steps": 15680, "loss": 0.24462056159973145, "lr": 4.847760012972402e-07, "epoch": 1.7174744897959182, "percentage": 85.87, "elapsed_time": "2 days, 0:52:00", "remaining_time": "8:02:19", "throughput": 4646.82, "total_tokens": 817470512} {"current_steps": 13470, "total_steps": 15680, "loss": 0.2470067024230957, "lr": 4.826267052411432e-07, "epoch": 1.7181122448979593, "percentage": 85.91, "elapsed_time": "2 days, 0:53:04", "remaining_time": "8:01:13", "throughput": 4646.81, "total_tokens": 817764792} {"current_steps": 13475, "total_steps": 15680, "loss": 0.2478943109512329, "lr": 4.804819426846402e-07, "epoch": 1.71875, "percentage": 85.94, "elapsed_time": "2 days, 0:54:12", "remaining_time": "8:00:08", "throughput": 4646.73, "total_tokens": 818067224} {"current_steps": 13480, "total_steps": 15680, "loss": 0.2814014911651611, "lr": 4.783417157801496e-07, "epoch": 1.7193877551020407, "percentage": 85.97, "elapsed_time": "2 days, 0:55:16", "remaining_time": "7:59:02", "throughput": 4646.77, "total_tokens": 818371368} {"current_steps": 13485, "total_steps": 15680, "loss": 0.24475960731506347, "lr": 4.7620602667553973e-07, "epoch": 1.7200255102040818, "percentage": 86.0, "elapsed_time": "2 days, 0:56:22", "remaining_time": "7:57:57", "throughput": 4646.76, "total_tokens": 818675136} {"current_steps": 13490, "total_steps": 15680, "loss": 0.2473832368850708, "lr": 4.7407487751412297e-07, "epoch": 1.7206632653061225, "percentage": 86.03, "elapsed_time": "2 days, 0:57:25", "remaining_time": "7:56:52", "throughput": 4646.75, "total_tokens": 818969848} {"current_steps": 13495, "total_steps": 15680, "loss": 0.25057687759399416, "lr": 4.719482704346567e-07, "epoch": 1.7213010204081631, "percentage": 86.07, "elapsed_time": "2 days, 0:58:35", "remaining_time": "7:55:47", "throughput": 4646.63, "total_tokens": 819271288} {"current_steps": 13500, "total_steps": 15680, "loss": 0.2580732345581055, "lr": 4.6982620757133947e-07, "epoch": 1.7219387755102042, "percentage": 86.1, "elapsed_time": "2 days, 0:59:38", "remaining_time": "7:54:41", "throughput": 4646.69, "total_tokens": 819576904} {"current_steps": 13505, "total_steps": 15680, "loss": 0.250787091255188, "lr": 4.677086910538092e-07, "epoch": 1.722576530612245, "percentage": 86.13, "elapsed_time": "2 days, 1:00:44", "remaining_time": "7:53:36", "throughput": 4646.72, "total_tokens": 819888528} {"current_steps": 13510, "total_steps": 15680, "loss": 0.24778370857238768, "lr": 4.6559572300714227e-07, "epoch": 1.7232142857142856, "percentage": 86.16, "elapsed_time": "2 days, 1:01:49", "remaining_time": "7:52:31", "throughput": 4646.72, "total_tokens": 820188984} {"current_steps": 13515, "total_steps": 15680, "loss": 0.26547608375549314, "lr": 4.6348730555185017e-07, "epoch": 1.7238520408163265, "percentage": 86.19, "elapsed_time": "2 days, 1:02:48", "remaining_time": "7:51:24", "throughput": 4646.84, "total_tokens": 820484616} {"current_steps": 13520, "total_steps": 15680, "loss": 0.24309449195861815, "lr": 4.6138344080387477e-07, "epoch": 1.7244897959183674, "percentage": 86.22, "elapsed_time": "2 days, 1:03:54", "remaining_time": "7:50:19", "throughput": 4646.85, "total_tokens": 820793416} {"current_steps": 13525, "total_steps": 15680, "loss": 0.2588818073272705, "lr": 4.5928413087459325e-07, "epoch": 1.725127551020408, "percentage": 86.26, "elapsed_time": "2 days, 1:05:07", "remaining_time": "7:49:15", "throughput": 4646.64, "total_tokens": 821094712} {"current_steps": 13530, "total_steps": 15680, "loss": 0.23107919692993165, "lr": 4.571893778708103e-07, "epoch": 1.725765306122449, "percentage": 86.29, "elapsed_time": "2 days, 1:06:11", "remaining_time": "7:48:10", "throughput": 4646.69, "total_tokens": 821399712} {"current_steps": 13535, "total_steps": 15680, "loss": 0.265388560295105, "lr": 4.550991838947555e-07, "epoch": 1.7264030612244898, "percentage": 86.32, "elapsed_time": "2 days, 1:07:13", "remaining_time": "7:47:04", "throughput": 4646.79, "total_tokens": 821707328} {"current_steps": 13540, "total_steps": 15680, "loss": 0.2338574171066284, "lr": 4.5301355104408364e-07, "epoch": 1.7270408163265305, "percentage": 86.35, "elapsed_time": "2 days, 1:08:29", "remaining_time": "7:46:00", "throughput": 4646.5, "total_tokens": 822009192} {"current_steps": 13545, "total_steps": 15680, "loss": 0.25485005378723147, "lr": 4.509324814118754e-07, "epoch": 1.7276785714285714, "percentage": 86.38, "elapsed_time": "2 days, 1:09:24", "remaining_time": "7:44:53", "throughput": 4646.72, "total_tokens": 822306680} {"current_steps": 13550, "total_steps": 15680, "loss": 0.25541257858276367, "lr": 4.48855977086628e-07, "epoch": 1.7283163265306123, "percentage": 86.42, "elapsed_time": "2 days, 1:10:25", "remaining_time": "7:43:47", "throughput": 4646.83, "total_tokens": 822605176} {"current_steps": 13555, "total_steps": 15680, "loss": 0.24527978897094727, "lr": 4.4678404015225774e-07, "epoch": 1.728954081632653, "percentage": 86.45, "elapsed_time": "2 days, 1:11:39", "remaining_time": "7:42:43", "throughput": 4646.59, "total_tokens": 822907840} {"current_steps": 13560, "total_steps": 15680, "loss": 0.26441819667816163, "lr": 4.447166726881008e-07, "epoch": 1.7295918367346939, "percentage": 86.48, "elapsed_time": "2 days, 1:12:55", "remaining_time": "7:41:39", "throughput": 4646.35, "total_tokens": 823217208} {"current_steps": 13565, "total_steps": 15680, "loss": 0.24485955238342286, "lr": 4.4265387676890203e-07, "epoch": 1.7302295918367347, "percentage": 86.51, "elapsed_time": "2 days, 1:13:57", "remaining_time": "7:40:34", "throughput": 4646.43, "total_tokens": 823522816} {"current_steps": 13570, "total_steps": 15680, "loss": 0.23918466567993163, "lr": 4.4059565446482264e-07, "epoch": 1.7308673469387754, "percentage": 86.54, "elapsed_time": "2 days, 1:15:02", "remaining_time": "7:39:28", "throughput": 4646.43, "total_tokens": 823824144} {"current_steps": 13575, "total_steps": 15680, "loss": 0.2566037893295288, "lr": 4.385420078414321e-07, "epoch": 1.7315051020408163, "percentage": 86.58, "elapsed_time": "2 days, 1:16:05", "remaining_time": "7:38:23", "throughput": 4646.43, "total_tokens": 824116440} {"current_steps": 13580, "total_steps": 15680, "loss": 0.23905861377716064, "lr": 4.364929389597078e-07, "epoch": 1.7321428571428572, "percentage": 86.61, "elapsed_time": "2 days, 1:17:09", "remaining_time": "7:37:17", "throughput": 4646.48, "total_tokens": 824420288} {"current_steps": 13585, "total_steps": 15680, "loss": 0.25505044460296633, "lr": 4.344484498760343e-07, "epoch": 1.7327806122448979, "percentage": 86.64, "elapsed_time": "2 days, 1:18:09", "remaining_time": "7:36:11", "throughput": 4646.65, "total_tokens": 824731064} {"current_steps": 13590, "total_steps": 15680, "loss": 0.27058048248291017, "lr": 4.324085426421981e-07, "epoch": 1.7334183673469388, "percentage": 86.67, "elapsed_time": "2 days, 1:19:16", "remaining_time": "7:35:06", "throughput": 4646.65, "total_tokens": 825043776} {"current_steps": 13595, "total_steps": 15680, "loss": 0.24852211475372316, "lr": 4.3037321930539e-07, "epoch": 1.7340561224489797, "percentage": 86.7, "elapsed_time": "2 days, 1:20:25", "remaining_time": "7:34:01", "throughput": 4646.54, "total_tokens": 825343224} {"current_steps": 13600, "total_steps": 15680, "loss": 0.24766051769256592, "lr": 4.283424819081988e-07, "epoch": 1.7346938775510203, "percentage": 86.73, "elapsed_time": "2 days, 1:21:34", "remaining_time": "7:32:56", "throughput": 4646.41, "total_tokens": 825642352} {"current_steps": 13605, "total_steps": 15680, "loss": 0.24031505584716797, "lr": 4.2631633248860937e-07, "epoch": 1.7353316326530612, "percentage": 86.77, "elapsed_time": "2 days, 1:22:40", "remaining_time": "7:31:51", "throughput": 4646.41, "total_tokens": 825946616} {"current_steps": 13610, "total_steps": 15680, "loss": 0.24826493263244628, "lr": 4.2429477308000676e-07, "epoch": 1.7359693877551021, "percentage": 86.8, "elapsed_time": "2 days, 1:23:47", "remaining_time": "7:30:46", "throughput": 4646.31, "total_tokens": 826243296} {"current_steps": 13615, "total_steps": 15680, "loss": 0.26136996746063235, "lr": 4.222778057111665e-07, "epoch": 1.7366071428571428, "percentage": 86.83, "elapsed_time": "2 days, 1:24:52", "remaining_time": "7:29:41", "throughput": 4646.27, "total_tokens": 826537744} {"current_steps": 13620, "total_steps": 15680, "loss": 0.2185586452484131, "lr": 4.202654324062544e-07, "epoch": 1.7372448979591837, "percentage": 86.86, "elapsed_time": "2 days, 1:25:47", "remaining_time": "7:28:34", "throughput": 4646.49, "total_tokens": 826831632} {"current_steps": 13625, "total_steps": 15680, "loss": 0.24439539909362792, "lr": 4.182576551848283e-07, "epoch": 1.7378826530612246, "percentage": 86.89, "elapsed_time": "2 days, 1:26:49", "remaining_time": "7:27:28", "throughput": 4646.57, "total_tokens": 827132840} {"current_steps": 13630, "total_steps": 15680, "loss": 0.23791561126708985, "lr": 4.1625447606183533e-07, "epoch": 1.7385204081632653, "percentage": 86.93, "elapsed_time": "2 days, 1:27:59", "remaining_time": "7:26:23", "throughput": 4646.47, "total_tokens": 827439840} {"current_steps": 13635, "total_steps": 15680, "loss": 0.2288142204284668, "lr": 4.142558970476024e-07, "epoch": 1.7391581632653061, "percentage": 86.96, "elapsed_time": "2 days, 1:28:59", "remaining_time": "7:25:17", "throughput": 4646.65, "total_tokens": 827753720} {"current_steps": 13640, "total_steps": 15680, "loss": 0.2142507553100586, "lr": 4.1226192014784393e-07, "epoch": 1.739795918367347, "percentage": 86.99, "elapsed_time": "2 days, 1:29:59", "remaining_time": "7:24:11", "throughput": 4646.79, "total_tokens": 828054520} {"current_steps": 13645, "total_steps": 15680, "loss": 0.24937853813171387, "lr": 4.102725473636571e-07, "epoch": 1.7404336734693877, "percentage": 87.02, "elapsed_time": "2 days, 1:31:00", "remaining_time": "7:23:05", "throughput": 4646.93, "total_tokens": 828362584} {"current_steps": 13650, "total_steps": 15680, "loss": 0.27016596794128417, "lr": 4.0828778069151363e-07, "epoch": 1.7410714285714286, "percentage": 87.05, "elapsed_time": "2 days, 1:32:18", "remaining_time": "7:22:02", "throughput": 4646.6, "total_tokens": 828668024} {"current_steps": 13655, "total_steps": 15680, "loss": 0.24024586677551268, "lr": 4.063076221232676e-07, "epoch": 1.7417091836734695, "percentage": 87.09, "elapsed_time": "2 days, 1:33:24", "remaining_time": "7:20:56", "throughput": 4646.58, "total_tokens": 828968552} {"current_steps": 13660, "total_steps": 15680, "loss": 0.27800915241241453, "lr": 4.043320736461448e-07, "epoch": 1.7423469387755102, "percentage": 87.12, "elapsed_time": "2 days, 1:34:24", "remaining_time": "7:19:50", "throughput": 4646.76, "total_tokens": 829280800} {"current_steps": 13665, "total_steps": 15680, "loss": 0.2446291923522949, "lr": 4.0236113724274716e-07, "epoch": 1.742984693877551, "percentage": 87.15, "elapsed_time": "2 days, 1:35:28", "remaining_time": "7:18:45", "throughput": 4646.81, "total_tokens": 829588144} {"current_steps": 13670, "total_steps": 15680, "loss": 0.2662153959274292, "lr": 4.0039481489104636e-07, "epoch": 1.743622448979592, "percentage": 87.18, "elapsed_time": "2 days, 1:36:30", "remaining_time": "7:17:39", "throughput": 4646.94, "total_tokens": 829898896} {"current_steps": 13675, "total_steps": 15680, "loss": 0.24277727603912352, "lr": 3.98433108564385e-07, "epoch": 1.7442602040816326, "percentage": 87.21, "elapsed_time": "2 days, 1:37:33", "remaining_time": "7:16:33", "throughput": 4646.98, "total_tokens": 830197328} {"current_steps": 13680, "total_steps": 15680, "loss": 0.24192190170288086, "lr": 3.964760202314716e-07, "epoch": 1.7448979591836735, "percentage": 87.24, "elapsed_time": "2 days, 1:38:28", "remaining_time": "7:15:26", "throughput": 4647.31, "total_tokens": 830513592} {"current_steps": 13685, "total_steps": 15680, "loss": 0.25597119331359863, "lr": 3.9452355185638226e-07, "epoch": 1.7455357142857144, "percentage": 87.28, "elapsed_time": "2 days, 1:39:41", "remaining_time": "7:14:22", "throughput": 4647.11, "total_tokens": 830815680} {"current_steps": 13690, "total_steps": 15680, "loss": 0.2551027774810791, "lr": 3.9257570539855237e-07, "epoch": 1.746173469387755, "percentage": 87.31, "elapsed_time": "2 days, 1:40:33", "remaining_time": "7:13:15", "throughput": 4647.43, "total_tokens": 831116968} {"current_steps": 13695, "total_steps": 15680, "loss": 0.24135251045227052, "lr": 3.9063248281278555e-07, "epoch": 1.7468112244897958, "percentage": 87.34, "elapsed_time": "2 days, 1:41:45", "remaining_time": "7:12:11", "throughput": 4647.21, "total_tokens": 831412080} {"current_steps": 13700, "total_steps": 15680, "loss": 0.2383573532104492, "lr": 3.8869388604924007e-07, "epoch": 1.7474489795918369, "percentage": 87.37, "elapsed_time": "2 days, 1:42:52", "remaining_time": "7:11:06", "throughput": 4647.14, "total_tokens": 831711544} {"current_steps": 13705, "total_steps": 15680, "loss": 0.2385228157043457, "lr": 3.8675991705343197e-07, "epoch": 1.7480867346938775, "percentage": 87.4, "elapsed_time": "2 days, 1:43:56", "remaining_time": "7:10:00", "throughput": 4647.15, "total_tokens": 832007984} {"current_steps": 13710, "total_steps": 15680, "loss": 0.2456441879272461, "lr": 3.848305777662342e-07, "epoch": 1.7487244897959182, "percentage": 87.44, "elapsed_time": "2 days, 1:45:02", "remaining_time": "7:08:55", "throughput": 4647.07, "total_tokens": 832303496} {"current_steps": 13715, "total_steps": 15680, "loss": 0.2562390327453613, "lr": 3.829058701238764e-07, "epoch": 1.7493622448979593, "percentage": 87.47, "elapsed_time": "2 days, 1:46:05", "remaining_time": "7:07:49", "throughput": 4647.12, "total_tokens": 832603704} {"current_steps": 13720, "total_steps": 15680, "loss": 0.25684871673583987, "lr": 3.8098579605793385e-07, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "2 days, 1:47:02", "remaining_time": "7:06:43", "throughput": 4647.36, "total_tokens": 832912352} {"current_steps": 13725, "total_steps": 15680, "loss": 0.25089006423950194, "lr": 3.790703574953353e-07, "epoch": 1.7506377551020407, "percentage": 87.53, "elapsed_time": "2 days, 1:48:08", "remaining_time": "7:05:38", "throughput": 4647.42, "total_tokens": 833230920} {"current_steps": 13730, "total_steps": 15680, "loss": 0.22961339950561524, "lr": 3.771595563583602e-07, "epoch": 1.7512755102040818, "percentage": 87.56, "elapsed_time": "2 days, 1:49:27", "remaining_time": "7:04:34", "throughput": 4647.09, "total_tokens": 833535792} {"current_steps": 13735, "total_steps": 15680, "loss": 0.27449326515197753, "lr": 3.752533945646275e-07, "epoch": 1.7519132653061225, "percentage": 87.6, "elapsed_time": "2 days, 1:50:26", "remaining_time": "7:03:28", "throughput": 4647.26, "total_tokens": 833842504} {"current_steps": 13740, "total_steps": 15680, "loss": 0.24901988506317138, "lr": 3.733518740271047e-07, "epoch": 1.7525510204081631, "percentage": 87.63, "elapsed_time": "2 days, 1:51:30", "remaining_time": "7:02:22", "throughput": 4647.26, "total_tokens": 834138640} {"current_steps": 13745, "total_steps": 15680, "loss": 0.24527840614318847, "lr": 3.7145499665410147e-07, "epoch": 1.7531887755102042, "percentage": 87.66, "elapsed_time": "2 days, 1:52:38", "remaining_time": "7:01:18", "throughput": 4647.09, "total_tokens": 834425800} {"current_steps": 13750, "total_steps": 15680, "loss": 0.2338253974914551, "lr": 3.695627643492655e-07, "epoch": 1.753826530612245, "percentage": 87.69, "elapsed_time": "2 days, 1:53:43", "remaining_time": "7:00:12", "throughput": 4647.09, "total_tokens": 834725488} {"current_steps": 13755, "total_steps": 15680, "loss": 0.236647891998291, "lr": 3.6767517901158455e-07, "epoch": 1.7544642857142856, "percentage": 87.72, "elapsed_time": "2 days, 1:54:42", "remaining_time": "6:59:06", "throughput": 4647.24, "total_tokens": 835027360} {"current_steps": 13760, "total_steps": 15680, "loss": 0.2543475866317749, "lr": 3.6579224253538213e-07, "epoch": 1.7551020408163265, "percentage": 87.76, "elapsed_time": "2 days, 1:55:44", "remaining_time": "6:58:00", "throughput": 4647.29, "total_tokens": 835324880} {"current_steps": 13765, "total_steps": 15680, "loss": 0.2533092021942139, "lr": 3.639139568103173e-07, "epoch": 1.7557397959183674, "percentage": 87.79, "elapsed_time": "2 days, 1:56:47", "remaining_time": "6:56:54", "throughput": 4647.41, "total_tokens": 835637264} {"current_steps": 13770, "total_steps": 15680, "loss": 0.25517432689666747, "lr": 3.620403237213799e-07, "epoch": 1.756377551020408, "percentage": 87.82, "elapsed_time": "2 days, 1:57:48", "remaining_time": "6:55:49", "throughput": 4647.51, "total_tokens": 835941560} {"current_steps": 13775, "total_steps": 15680, "loss": 0.26593616008758547, "lr": 3.6017134514889196e-07, "epoch": 1.757015306122449, "percentage": 87.85, "elapsed_time": "2 days, 1:58:43", "remaining_time": "6:54:42", "throughput": 4647.86, "total_tokens": 836258672} {"current_steps": 13780, "total_steps": 15680, "loss": 0.2549485206604004, "lr": 3.583070229685043e-07, "epoch": 1.7576530612244898, "percentage": 87.88, "elapsed_time": "2 days, 1:59:43", "remaining_time": "6:53:36", "throughput": 4648.0, "total_tokens": 836561840} {"current_steps": 13785, "total_steps": 15680, "loss": 0.24862639904022216, "lr": 3.564473590511941e-07, "epoch": 1.7582908163265305, "percentage": 87.91, "elapsed_time": "2 days, 2:00:51", "remaining_time": "6:52:31", "throughput": 4647.93, "total_tokens": 836865200} {"current_steps": 13790, "total_steps": 15680, "loss": 0.240686297416687, "lr": 3.5459235526326464e-07, "epoch": 1.7589285714285714, "percentage": 87.95, "elapsed_time": "2 days, 2:01:55", "remaining_time": "6:51:25", "throughput": 4647.96, "total_tokens": 837168000} {"current_steps": 13795, "total_steps": 15680, "loss": 0.2507588863372803, "lr": 3.527420134663401e-07, "epoch": 1.7595663265306123, "percentage": 87.98, "elapsed_time": "2 days, 2:02:51", "remaining_time": "6:50:19", "throughput": 4648.14, "total_tokens": 837463912} {"current_steps": 13800, "total_steps": 15680, "loss": 0.246191143989563, "lr": 3.5089633551736946e-07, "epoch": 1.760204081632653, "percentage": 88.01, "elapsed_time": "2 days, 2:03:54", "remaining_time": "6:49:13", "throughput": 4648.2, "total_tokens": 837767624} {"current_steps": 13805, "total_steps": 15680, "loss": 0.23849906921386718, "lr": 3.4905532326861946e-07, "epoch": 1.7608418367346939, "percentage": 88.04, "elapsed_time": "2 days, 2:05:00", "remaining_time": "6:48:08", "throughput": 4648.22, "total_tokens": 838076624} {"current_steps": 13810, "total_steps": 15680, "loss": 0.2654818773269653, "lr": 3.4721897856767275e-07, "epoch": 1.7614795918367347, "percentage": 88.07, "elapsed_time": "2 days, 2:06:12", "remaining_time": "6:47:04", "throughput": 4648.08, "total_tokens": 838387688} {"current_steps": 13815, "total_steps": 15680, "loss": 0.24663257598876953, "lr": 3.4538730325743174e-07, "epoch": 1.7621173469387754, "percentage": 88.11, "elapsed_time": "2 days, 2:07:26", "remaining_time": "6:45:59", "throughput": 4647.86, "total_tokens": 838688192} {"current_steps": 13820, "total_steps": 15680, "loss": 0.24232873916625977, "lr": 3.4356029917610833e-07, "epoch": 1.7627551020408163, "percentage": 88.14, "elapsed_time": "2 days, 2:08:31", "remaining_time": "6:44:54", "throughput": 4647.9, "total_tokens": 838997520} {"current_steps": 13825, "total_steps": 15680, "loss": 0.24702844619750977, "lr": 3.417379681572297e-07, "epoch": 1.7633928571428572, "percentage": 88.17, "elapsed_time": "2 days, 2:09:47", "remaining_time": "6:43:50", "throughput": 4647.59, "total_tokens": 839296400} {"current_steps": 13830, "total_steps": 15680, "loss": 0.25472800731658934, "lr": 3.3992031202963293e-07, "epoch": 1.7640306122448979, "percentage": 88.2, "elapsed_time": "2 days, 2:10:39", "remaining_time": "6:42:43", "throughput": 4647.97, "total_tokens": 839608360} {"current_steps": 13835, "total_steps": 15680, "loss": 0.24146430492401122, "lr": 3.3810733261746167e-07, "epoch": 1.7646683673469388, "percentage": 88.23, "elapsed_time": "2 days, 2:11:53", "remaining_time": "6:41:39", "throughput": 4647.82, "total_tokens": 839922696} {"current_steps": 13840, "total_steps": 15680, "loss": 0.2496337413787842, "lr": 3.362990317401688e-07, "epoch": 1.7653061224489797, "percentage": 88.27, "elapsed_time": "2 days, 2:13:00", "remaining_time": "6:40:34", "throughput": 4647.71, "total_tokens": 840213632} {"current_steps": 13845, "total_steps": 15680, "loss": 0.23286681175231932, "lr": 3.344954112125087e-07, "epoch": 1.7659438775510203, "percentage": 88.3, "elapsed_time": "2 days, 2:14:18", "remaining_time": "6:39:30", "throughput": 4647.36, "total_tokens": 840513384} {"current_steps": 13850, "total_steps": 15680, "loss": 0.24792745113372802, "lr": 3.3269647284454253e-07, "epoch": 1.7665816326530612, "percentage": 88.33, "elapsed_time": "2 days, 2:15:28", "remaining_time": "6:38:26", "throughput": 4647.11, "total_tokens": 840793696} {"current_steps": 13855, "total_steps": 15680, "loss": 0.2583718776702881, "lr": 3.309022184416288e-07, "epoch": 1.7672193877551021, "percentage": 88.36, "elapsed_time": "2 days, 2:16:37", "remaining_time": "6:37:21", "throughput": 4647.05, "total_tokens": 841104192} {"current_steps": 13860, "total_steps": 15680, "loss": 0.25423059463500974, "lr": 3.2911264980442834e-07, "epoch": 1.7678571428571428, "percentage": 88.39, "elapsed_time": "2 days, 2:17:45", "remaining_time": "6:36:16", "throughput": 4647.03, "total_tokens": 841415992} {"current_steps": 13865, "total_steps": 15680, "loss": 0.2673047542572021, "lr": 3.273277687288978e-07, "epoch": 1.7684948979591837, "percentage": 88.42, "elapsed_time": "2 days, 2:18:51", "remaining_time": "6:35:11", "throughput": 4647.04, "total_tokens": 841723464} {"current_steps": 13870, "total_steps": 15680, "loss": 0.25228047370910645, "lr": 3.255475770062899e-07, "epoch": 1.7691326530612246, "percentage": 88.46, "elapsed_time": "2 days, 2:19:56", "remaining_time": "6:34:05", "throughput": 4646.99, "total_tokens": 842018680} {"current_steps": 13875, "total_steps": 15680, "loss": 0.27175297737121584, "lr": 3.237720764231517e-07, "epoch": 1.7697704081632653, "percentage": 88.49, "elapsed_time": "2 days, 2:21:00", "remaining_time": "6:33:00", "throughput": 4647.04, "total_tokens": 842324096} {"current_steps": 13880, "total_steps": 15680, "loss": 0.2552263975143433, "lr": 3.220012687613222e-07, "epoch": 1.7704081632653061, "percentage": 88.52, "elapsed_time": "2 days, 2:22:13", "remaining_time": "6:31:55", "throughput": 4646.83, "total_tokens": 842624944} {"current_steps": 13885, "total_steps": 15680, "loss": 0.26123366355895994, "lr": 3.2023515579793e-07, "epoch": 1.771045918367347, "percentage": 88.55, "elapsed_time": "2 days, 2:23:18", "remaining_time": "6:30:50", "throughput": 4646.89, "total_tokens": 842936928} {"current_steps": 13890, "total_steps": 15680, "loss": 0.24546425342559813, "lr": 3.1847373930539326e-07, "epoch": 1.7716836734693877, "percentage": 88.58, "elapsed_time": "2 days, 2:24:14", "remaining_time": "6:29:43", "throughput": 4647.15, "total_tokens": 843244832} {"current_steps": 13895, "total_steps": 15680, "loss": 0.2333463191986084, "lr": 3.167170210514153e-07, "epoch": 1.7723214285714286, "percentage": 88.62, "elapsed_time": "2 days, 2:25:19", "remaining_time": "6:28:38", "throughput": 4647.08, "total_tokens": 843537008} {"current_steps": 13900, "total_steps": 15680, "loss": 0.2539116621017456, "lr": 3.14965002798987e-07, "epoch": 1.7729591836734695, "percentage": 88.65, "elapsed_time": "2 days, 2:26:29", "remaining_time": "6:27:33", "throughput": 4647.01, "total_tokens": 843848648} {"current_steps": 13905, "total_steps": 15680, "loss": 0.23679733276367188, "lr": 3.1321768630638073e-07, "epoch": 1.7735969387755102, "percentage": 88.68, "elapsed_time": "2 days, 2:27:27", "remaining_time": "6:26:27", "throughput": 4647.19, "total_tokens": 844152576} {"current_steps": 13910, "total_steps": 15680, "loss": 0.24175968170166015, "lr": 3.1147507332715044e-07, "epoch": 1.774234693877551, "percentage": 88.71, "elapsed_time": "2 days, 2:28:33", "remaining_time": "6:25:22", "throughput": 4647.14, "total_tokens": 844450232} {"current_steps": 13915, "total_steps": 15680, "loss": 0.25646772384643557, "lr": 3.097371656101289e-07, "epoch": 1.774872448979592, "percentage": 88.74, "elapsed_time": "2 days, 2:29:39", "remaining_time": "6:24:17", "throughput": 4647.12, "total_tokens": 844753504} {"current_steps": 13920, "total_steps": 15680, "loss": 0.2563156604766846, "lr": 3.080039648994304e-07, "epoch": 1.7755102040816326, "percentage": 88.78, "elapsed_time": "2 days, 2:30:42", "remaining_time": "6:23:11", "throughput": 4647.16, "total_tokens": 845053312} {"current_steps": 13925, "total_steps": 15680, "loss": 0.2489215612411499, "lr": 3.062754729344408e-07, "epoch": 1.7761479591836735, "percentage": 88.81, "elapsed_time": "2 days, 2:31:47", "remaining_time": "6:22:06", "throughput": 4647.15, "total_tokens": 845353704} {"current_steps": 13930, "total_steps": 15680, "loss": 0.24673690795898437, "lr": 3.0455169144982257e-07, "epoch": 1.7767857142857144, "percentage": 88.84, "elapsed_time": "2 days, 2:32:57", "remaining_time": "6:21:01", "throughput": 4647.11, "total_tokens": 845669088} {"current_steps": 13935, "total_steps": 15680, "loss": 0.2515824317932129, "lr": 3.028326221755118e-07, "epoch": 1.777423469387755, "percentage": 88.87, "elapsed_time": "2 days, 2:33:59", "remaining_time": "6:19:55", "throughput": 4647.14, "total_tokens": 845963736} {"current_steps": 13940, "total_steps": 15680, "loss": 0.29273903369903564, "lr": 3.0111826683671407e-07, "epoch": 1.7780612244897958, "percentage": 88.9, "elapsed_time": "2 days, 2:35:01", "remaining_time": "6:18:49", "throughput": 4647.21, "total_tokens": 846263064} {"current_steps": 13945, "total_steps": 15680, "loss": 0.2593369483947754, "lr": 2.9940862715390483e-07, "epoch": 1.7786989795918369, "percentage": 88.93, "elapsed_time": "2 days, 2:36:16", "remaining_time": "6:17:45", "throughput": 4646.98, "total_tokens": 846571384} {"current_steps": 13950, "total_steps": 15680, "loss": 0.24895977973937988, "lr": 2.9770370484282665e-07, "epoch": 1.7793367346938775, "percentage": 88.97, "elapsed_time": "2 days, 2:37:31", "remaining_time": "6:16:41", "throughput": 4646.71, "total_tokens": 846871040} {"current_steps": 13955, "total_steps": 15680, "loss": 0.2705617666244507, "lr": 2.960035016144885e-07, "epoch": 1.7799744897959182, "percentage": 89.0, "elapsed_time": "2 days, 2:38:43", "remaining_time": "6:15:37", "throughput": 4646.52, "total_tokens": 847170952} {"current_steps": 13960, "total_steps": 15680, "loss": 0.26220757961273194, "lr": 2.943080191751629e-07, "epoch": 1.7806122448979593, "percentage": 89.03, "elapsed_time": "2 days, 2:39:40", "remaining_time": "6:14:30", "throughput": 4646.77, "total_tokens": 847480888} {"current_steps": 13965, "total_steps": 15680, "loss": 0.24409053325653077, "lr": 2.9261725922638485e-07, "epoch": 1.78125, "percentage": 89.06, "elapsed_time": "2 days, 2:40:47", "remaining_time": "6:13:25", "throughput": 4646.72, "total_tokens": 847780648} {"current_steps": 13970, "total_steps": 15680, "loss": 0.23370254039764404, "lr": 2.9093122346494974e-07, "epoch": 1.7818877551020407, "percentage": 89.09, "elapsed_time": "2 days, 2:41:43", "remaining_time": "6:12:19", "throughput": 4646.84, "total_tokens": 848066224} {"current_steps": 13975, "total_steps": 15680, "loss": 0.2403944969177246, "lr": 2.8924991358291354e-07, "epoch": 1.7825255102040818, "percentage": 89.13, "elapsed_time": "2 days, 2:42:37", "remaining_time": "6:11:12", "throughput": 4647.11, "total_tokens": 848364288} {"current_steps": 13980, "total_steps": 15680, "loss": 0.2287726640701294, "lr": 2.875733312675855e-07, "epoch": 1.7831632653061225, "percentage": 89.16, "elapsed_time": "2 days, 2:43:38", "remaining_time": "6:10:06", "throughput": 4647.12, "total_tokens": 848652288} {"current_steps": 13985, "total_steps": 15680, "loss": 0.2606127977371216, "lr": 2.8590147820153513e-07, "epoch": 1.7838010204081631, "percentage": 89.19, "elapsed_time": "2 days, 2:44:43", "remaining_time": "6:09:01", "throughput": 4647.14, "total_tokens": 848956280} {"current_steps": 13990, "total_steps": 15680, "loss": 0.25071115493774415, "lr": 2.8423435606258485e-07, "epoch": 1.7844387755102042, "percentage": 89.22, "elapsed_time": "2 days, 2:45:40", "remaining_time": "6:07:55", "throughput": 4647.38, "total_tokens": 849265056} {"current_steps": 13995, "total_steps": 15680, "loss": 0.27875847816467286, "lr": 2.8257196652380523e-07, "epoch": 1.785076530612245, "percentage": 89.25, "elapsed_time": "2 days, 2:46:52", "remaining_time": "6:06:50", "throughput": 4647.19, "total_tokens": 849562600} {"current_steps": 14000, "total_steps": 15680, "loss": 0.25108349323272705, "lr": 2.809143112535212e-07, "epoch": 1.7857142857142856, "percentage": 89.29, "elapsed_time": "2 days, 2:47:53", "remaining_time": "6:05:44", "throughput": 4647.24, "total_tokens": 849859784} {"current_steps": 14005, "total_steps": 15680, "loss": 0.24347131252288817, "lr": 2.7926139191530697e-07, "epoch": 1.7863520408163265, "percentage": 89.32, "elapsed_time": "2 days, 2:49:02", "remaining_time": "6:04:39", "throughput": 4647.09, "total_tokens": 850149912} {"current_steps": 14010, "total_steps": 15680, "loss": 0.25662524700164796, "lr": 2.7761321016798183e-07, "epoch": 1.7869897959183674, "percentage": 89.35, "elapsed_time": "2 days, 2:50:07", "remaining_time": "6:03:34", "throughput": 4647.08, "total_tokens": 850451656} {"current_steps": 14015, "total_steps": 15680, "loss": 0.25433058738708497, "lr": 2.7596976766560977e-07, "epoch": 1.787627551020408, "percentage": 89.38, "elapsed_time": "2 days, 2:51:20", "remaining_time": "6:02:30", "throughput": 4646.97, "total_tokens": 850768992} {"current_steps": 14020, "total_steps": 15680, "loss": 0.22808046340942384, "lr": 2.743310660575027e-07, "epoch": 1.788265306122449, "percentage": 89.41, "elapsed_time": "2 days, 2:52:32", "remaining_time": "6:01:25", "throughput": 4646.77, "total_tokens": 851067016} {"current_steps": 14025, "total_steps": 15680, "loss": 0.2544532060623169, "lr": 2.726971069882101e-07, "epoch": 1.7889030612244898, "percentage": 89.45, "elapsed_time": "2 days, 2:53:49", "remaining_time": "6:00:21", "throughput": 4646.51, "total_tokens": 851376720} {"current_steps": 14030, "total_steps": 15680, "loss": 0.23698220252990723, "lr": 2.7106789209752513e-07, "epoch": 1.7895408163265305, "percentage": 89.48, "elapsed_time": "2 days, 2:54:56", "remaining_time": "5:59:16", "throughput": 4646.41, "total_tokens": 851672720} {"current_steps": 14035, "total_steps": 15680, "loss": 0.2619039297103882, "lr": 2.6944342302047785e-07, "epoch": 1.7901785714285714, "percentage": 89.51, "elapsed_time": "2 days, 2:56:08", "remaining_time": "5:58:12", "throughput": 4646.26, "total_tokens": 851976424} {"current_steps": 14040, "total_steps": 15680, "loss": 0.26267783641815184, "lr": 2.678237013873375e-07, "epoch": 1.7908163265306123, "percentage": 89.54, "elapsed_time": "2 days, 2:57:03", "remaining_time": "5:57:05", "throughput": 4646.53, "total_tokens": 852281432} {"current_steps": 14045, "total_steps": 15680, "loss": 0.2652120113372803, "lr": 2.66208728823607e-07, "epoch": 1.791454081632653, "percentage": 89.57, "elapsed_time": "2 days, 2:58:18", "remaining_time": "5:56:01", "throughput": 4646.34, "total_tokens": 852594760} {"current_steps": 14050, "total_steps": 15680, "loss": 0.24768829345703125, "lr": 2.6459850695002454e-07, "epoch": 1.7920918367346939, "percentage": 89.6, "elapsed_time": "2 days, 2:59:08", "remaining_time": "5:54:54", "throughput": 4646.81, "total_tokens": 852914064} {"current_steps": 14055, "total_steps": 15680, "loss": 0.24914608001708985, "lr": 2.629930373825595e-07, "epoch": 1.7927295918367347, "percentage": 89.64, "elapsed_time": "2 days, 3:00:09", "remaining_time": "5:53:48", "throughput": 4646.96, "total_tokens": 853226440} {"current_steps": 14060, "total_steps": 15680, "loss": 0.2694690227508545, "lr": 2.6139232173241434e-07, "epoch": 1.7933673469387754, "percentage": 89.67, "elapsed_time": "2 days, 3:01:19", "remaining_time": "5:52:43", "throughput": 4646.88, "total_tokens": 853536736} {"current_steps": 14065, "total_steps": 15680, "loss": 0.24811267852783203, "lr": 2.5979636160601673e-07, "epoch": 1.7940051020408163, "percentage": 89.7, "elapsed_time": "2 days, 3:02:27", "remaining_time": "5:51:38", "throughput": 4646.75, "total_tokens": 853826704} {"current_steps": 14070, "total_steps": 15680, "loss": 0.27320079803466796, "lr": 2.5820515860502604e-07, "epoch": 1.7946428571428572, "percentage": 89.73, "elapsed_time": "2 days, 3:03:26", "remaining_time": "5:50:32", "throughput": 4646.97, "total_tokens": 854143904} {"current_steps": 14075, "total_steps": 15680, "loss": 0.2347564935684204, "lr": 2.5661871432632545e-07, "epoch": 1.7952806122448979, "percentage": 89.76, "elapsed_time": "2 days, 3:04:30", "remaining_time": "5:49:27", "throughput": 4647.02, "total_tokens": 854451200} {"current_steps": 14080, "total_steps": 15680, "loss": 0.20640251636505128, "lr": 2.550370303620214e-07, "epoch": 1.7959183673469388, "percentage": 89.8, "elapsed_time": "2 days, 3:05:38", "remaining_time": "5:48:22", "throughput": 4646.95, "total_tokens": 854750472} {"current_steps": 14085, "total_steps": 15680, "loss": 0.2538137912750244, "lr": 2.534601082994437e-07, "epoch": 1.7965561224489797, "percentage": 89.83, "elapsed_time": "2 days, 3:06:45", "remaining_time": "5:47:17", "throughput": 4646.85, "total_tokens": 855047024} {"current_steps": 14090, "total_steps": 15680, "loss": 0.2629712104797363, "lr": 2.5188794972114684e-07, "epoch": 1.7971938775510203, "percentage": 89.86, "elapsed_time": "2 days, 3:07:54", "remaining_time": "5:46:12", "throughput": 4646.64, "total_tokens": 855326880} {"current_steps": 14095, "total_steps": 15680, "loss": 0.23544673919677733, "lr": 2.503205562048994e-07, "epoch": 1.7978316326530612, "percentage": 89.89, "elapsed_time": "2 days, 3:09:10", "remaining_time": "5:45:07", "throughput": 4646.34, "total_tokens": 855626608} {"current_steps": 14100, "total_steps": 15680, "loss": 0.2749136447906494, "lr": 2.487579293236897e-07, "epoch": 1.7984693877551021, "percentage": 89.92, "elapsed_time": "2 days, 3:10:17", "remaining_time": "5:44:02", "throughput": 4646.32, "total_tokens": 855935280} {"current_steps": 14105, "total_steps": 15680, "loss": 0.25101404190063475, "lr": 2.4720007064572506e-07, "epoch": 1.7991071428571428, "percentage": 89.96, "elapsed_time": "2 days, 3:11:24", "remaining_time": "5:42:57", "throughput": 4646.28, "total_tokens": 856237432} {"current_steps": 14110, "total_steps": 15680, "loss": 0.24380555152893066, "lr": 2.456469817344237e-07, "epoch": 1.7997448979591837, "percentage": 89.99, "elapsed_time": "2 days, 3:12:28", "remaining_time": "5:41:52", "throughput": 4646.25, "total_tokens": 856528816} {"current_steps": 14115, "total_steps": 15680, "loss": 0.25036029815673827, "lr": 2.4409866414841996e-07, "epoch": 1.8003826530612246, "percentage": 90.02, "elapsed_time": "2 days, 3:13:18", "remaining_time": "5:40:45", "throughput": 4646.67, "total_tokens": 856837488} {"current_steps": 14120, "total_steps": 15680, "loss": 0.2392751932144165, "lr": 2.4255511944155764e-07, "epoch": 1.8010204081632653, "percentage": 90.05, "elapsed_time": "2 days, 3:14:26", "remaining_time": "5:39:40", "throughput": 4646.58, "total_tokens": 857138856} {"current_steps": 14125, "total_steps": 15680, "loss": 0.2524121761322021, "lr": 2.410163491628925e-07, "epoch": 1.8016581632653061, "percentage": 90.08, "elapsed_time": "2 days, 3:15:23", "remaining_time": "5:38:33", "throughput": 4646.89, "total_tokens": 857460528} {"current_steps": 14130, "total_steps": 15680, "loss": 0.24928345680236816, "lr": 2.394823548566877e-07, "epoch": 1.802295918367347, "percentage": 90.11, "elapsed_time": "2 days, 3:16:43", "remaining_time": "5:37:30", "throughput": 4646.53, "total_tokens": 857764176} {"current_steps": 14135, "total_steps": 15680, "loss": 0.23600704669952394, "lr": 2.3795313806241337e-07, "epoch": 1.8029336734693877, "percentage": 90.15, "elapsed_time": "2 days, 3:17:46", "remaining_time": "5:36:24", "throughput": 4646.56, "total_tokens": 858062936} {"current_steps": 14140, "total_steps": 15680, "loss": 0.24544596672058105, "lr": 2.364287003147453e-07, "epoch": 1.8035714285714286, "percentage": 90.18, "elapsed_time": "2 days, 3:18:52", "remaining_time": "5:35:19", "throughput": 4646.46, "total_tokens": 858351512} {"current_steps": 14145, "total_steps": 15680, "loss": 0.2638862133026123, "lr": 2.3490904314356412e-07, "epoch": 1.8042091836734695, "percentage": 90.21, "elapsed_time": "2 days, 3:20:07", "remaining_time": "5:34:15", "throughput": 4646.27, "total_tokens": 858666680} {"current_steps": 14150, "total_steps": 15680, "loss": 0.25586857795715334, "lr": 2.3339416807395154e-07, "epoch": 1.8048469387755102, "percentage": 90.24, "elapsed_time": "2 days, 3:21:13", "remaining_time": "5:33:09", "throughput": 4646.26, "total_tokens": 858970664} {"current_steps": 14155, "total_steps": 15680, "loss": 0.24245853424072267, "lr": 2.3188407662618983e-07, "epoch": 1.805484693877551, "percentage": 90.27, "elapsed_time": "2 days, 3:22:21", "remaining_time": "5:32:04", "throughput": 4646.13, "total_tokens": 859261112} {"current_steps": 14160, "total_steps": 15680, "loss": 0.2581301212310791, "lr": 2.3037877031576172e-07, "epoch": 1.806122448979592, "percentage": 90.31, "elapsed_time": "2 days, 3:23:20", "remaining_time": "5:30:58", "throughput": 4646.34, "total_tokens": 859577136} {"current_steps": 14165, "total_steps": 15680, "loss": 0.2506843566894531, "lr": 2.2887825065334822e-07, "epoch": 1.8067602040816326, "percentage": 90.34, "elapsed_time": "2 days, 3:24:25", "remaining_time": "5:29:53", "throughput": 4646.37, "total_tokens": 859880464} {"current_steps": 14170, "total_steps": 15680, "loss": 0.24305098056793212, "lr": 2.2738251914482312e-07, "epoch": 1.8073979591836735, "percentage": 90.37, "elapsed_time": "2 days, 3:25:42", "remaining_time": "5:28:49", "throughput": 4646.04, "total_tokens": 860178936} {"current_steps": 14175, "total_steps": 15680, "loss": 0.23382172584533692, "lr": 2.258915772912601e-07, "epoch": 1.8080357142857144, "percentage": 90.4, "elapsed_time": "2 days, 3:26:50", "remaining_time": "5:27:44", "throughput": 4645.92, "total_tokens": 860472656} {"current_steps": 14180, "total_steps": 15680, "loss": 0.26403107643127444, "lr": 2.2440542658892172e-07, "epoch": 1.808673469387755, "percentage": 90.43, "elapsed_time": "2 days, 3:27:57", "remaining_time": "5:26:39", "throughput": 4645.89, "total_tokens": 860776504} {"current_steps": 14185, "total_steps": 15680, "loss": 0.25989222526550293, "lr": 2.2292406852926385e-07, "epoch": 1.8093112244897958, "percentage": 90.47, "elapsed_time": "2 days, 3:29:02", "remaining_time": "5:25:33", "throughput": 4645.89, "total_tokens": 861080704} {"current_steps": 14190, "total_steps": 15680, "loss": 0.2608367919921875, "lr": 2.214475045989345e-07, "epoch": 1.8099489795918369, "percentage": 90.5, "elapsed_time": "2 days, 3:29:59", "remaining_time": "5:24:27", "throughput": 4646.14, "total_tokens": 861392760} {"current_steps": 14195, "total_steps": 15680, "loss": 0.24211552143096923, "lr": 2.199757362797672e-07, "epoch": 1.8105867346938775, "percentage": 90.53, "elapsed_time": "2 days, 3:31:09", "remaining_time": "5:23:22", "throughput": 4646.07, "total_tokens": 861703280} {"current_steps": 14200, "total_steps": 15680, "loss": 0.26641933917999266, "lr": 2.1850876504878492e-07, "epoch": 1.8112244897959182, "percentage": 90.56, "elapsed_time": "2 days, 3:32:02", "remaining_time": "5:22:16", "throughput": 4646.37, "total_tokens": 862005704} {"current_steps": 14205, "total_steps": 15680, "loss": 0.2593922853469849, "lr": 2.1704659237819558e-07, "epoch": 1.8118622448979593, "percentage": 90.59, "elapsed_time": "2 days, 3:33:14", "remaining_time": "5:21:11", "throughput": 4646.23, "total_tokens": 862313352} {"current_steps": 14210, "total_steps": 15680, "loss": 0.22741270065307617, "lr": 2.1558921973539092e-07, "epoch": 1.8125, "percentage": 90.62, "elapsed_time": "2 days, 3:34:16", "remaining_time": "5:20:05", "throughput": 4646.28, "total_tokens": 862611096} {"current_steps": 14215, "total_steps": 15680, "loss": 0.2631678104400635, "lr": 2.1413664858294713e-07, "epoch": 1.8131377551020407, "percentage": 90.66, "elapsed_time": "2 days, 3:35:07", "remaining_time": "5:18:59", "throughput": 4646.6, "total_tokens": 862909136} {"current_steps": 14220, "total_steps": 15680, "loss": 0.23754780292510985, "lr": 2.126888803786209e-07, "epoch": 1.8137755102040818, "percentage": 90.69, "elapsed_time": "2 days, 3:36:03", "remaining_time": "5:17:52", "throughput": 4646.8, "total_tokens": 863205776} {"current_steps": 14225, "total_steps": 15680, "loss": 0.2515824556350708, "lr": 2.1124591657534776e-07, "epoch": 1.8144132653061225, "percentage": 90.72, "elapsed_time": "2 days, 3:37:03", "remaining_time": "5:16:46", "throughput": 4646.94, "total_tokens": 863513144} {"current_steps": 14230, "total_steps": 15680, "loss": 0.26154017448425293, "lr": 2.0980775862124326e-07, "epoch": 1.8150510204081631, "percentage": 90.75, "elapsed_time": "2 days, 3:38:06", "remaining_time": "5:15:41", "throughput": 4647.03, "total_tokens": 863819928} {"current_steps": 14235, "total_steps": 15680, "loss": 0.24450421333312988, "lr": 2.083744079595995e-07, "epoch": 1.8156887755102042, "percentage": 90.78, "elapsed_time": "2 days, 3:38:59", "remaining_time": "5:14:34", "throughput": 4647.35, "total_tokens": 864123928} {"current_steps": 14240, "total_steps": 15680, "loss": 0.25495457649230957, "lr": 2.069458660288831e-07, "epoch": 1.816326530612245, "percentage": 90.82, "elapsed_time": "2 days, 3:39:56", "remaining_time": "5:13:28", "throughput": 4647.58, "total_tokens": 864431064} {"current_steps": 14245, "total_steps": 15680, "loss": 0.26381802558898926, "lr": 2.0552213426273725e-07, "epoch": 1.8169642857142856, "percentage": 90.85, "elapsed_time": "2 days, 3:40:59", "remaining_time": "5:12:23", "throughput": 4647.61, "total_tokens": 864729568} {"current_steps": 14250, "total_steps": 15680, "loss": 0.25765416622161863, "lr": 2.0410321408997459e-07, "epoch": 1.8176020408163265, "percentage": 90.88, "elapsed_time": "2 days, 3:42:17", "remaining_time": "5:11:19", "throughput": 4647.33, "total_tokens": 865040992} {"current_steps": 14255, "total_steps": 15680, "loss": 0.25167059898376465, "lr": 2.0268910693458154e-07, "epoch": 1.8182397959183674, "percentage": 90.91, "elapsed_time": "2 days, 3:43:21", "remaining_time": "5:10:13", "throughput": 4647.27, "total_tokens": 865330088} {"current_steps": 14260, "total_steps": 15680, "loss": 0.23990678787231445, "lr": 2.0127981421571295e-07, "epoch": 1.818877551020408, "percentage": 90.94, "elapsed_time": "2 days, 3:44:28", "remaining_time": "5:09:08", "throughput": 4647.23, "total_tokens": 865633168} {"current_steps": 14265, "total_steps": 15680, "loss": 0.25752208232879636, "lr": 1.998753373476936e-07, "epoch": 1.819515306122449, "percentage": 90.98, "elapsed_time": "2 days, 3:45:30", "remaining_time": "5:08:02", "throughput": 4647.29, "total_tokens": 865932040} {"current_steps": 14270, "total_steps": 15680, "loss": 0.2669686794281006, "lr": 1.9847567774001153e-07, "epoch": 1.8201530612244898, "percentage": 91.01, "elapsed_time": "2 days, 3:46:34", "remaining_time": "5:06:57", "throughput": 4647.31, "total_tokens": 866232520} {"current_steps": 14275, "total_steps": 15680, "loss": 0.2516944885253906, "lr": 1.9708083679732538e-07, "epoch": 1.8207908163265305, "percentage": 91.04, "elapsed_time": "2 days, 3:47:38", "remaining_time": "5:05:51", "throughput": 4647.35, "total_tokens": 866539944} {"current_steps": 14280, "total_steps": 15680, "loss": 0.2641996622085571, "lr": 1.9569081591945537e-07, "epoch": 1.8214285714285714, "percentage": 91.07, "elapsed_time": "2 days, 3:48:41", "remaining_time": "5:04:46", "throughput": 4647.37, "total_tokens": 866835376} {"current_steps": 14285, "total_steps": 15680, "loss": 0.2752277374267578, "lr": 1.9430561650138292e-07, "epoch": 1.8220663265306123, "percentage": 91.1, "elapsed_time": "2 days, 3:49:48", "remaining_time": "5:03:41", "throughput": 4647.4, "total_tokens": 867149688} {"current_steps": 14290, "total_steps": 15680, "loss": 0.2481313943862915, "lr": 1.9292523993325318e-07, "epoch": 1.822704081632653, "percentage": 91.14, "elapsed_time": "2 days, 3:51:02", "remaining_time": "5:02:36", "throughput": 4647.17, "total_tokens": 867451672} {"current_steps": 14295, "total_steps": 15680, "loss": 0.24785711765289306, "lr": 1.9154968760037142e-07, "epoch": 1.8233418367346939, "percentage": 91.17, "elapsed_time": "2 days, 3:52:07", "remaining_time": "5:01:31", "throughput": 4647.12, "total_tokens": 867746048} {"current_steps": 14300, "total_steps": 15680, "loss": 0.26390371322631834, "lr": 1.9017896088319888e-07, "epoch": 1.8239795918367347, "percentage": 91.2, "elapsed_time": "2 days, 3:53:06", "remaining_time": "5:00:25", "throughput": 4647.29, "total_tokens": 868050248} {"current_steps": 14305, "total_steps": 15680, "loss": 0.23825533390045167, "lr": 1.8881306115735632e-07, "epoch": 1.8246173469387754, "percentage": 91.23, "elapsed_time": "2 days, 3:54:11", "remaining_time": "4:59:20", "throughput": 4647.3, "total_tokens": 868353320} {"current_steps": 14310, "total_steps": 15680, "loss": 0.25106494426727294, "lr": 1.8745198979361944e-07, "epoch": 1.8252551020408163, "percentage": 91.26, "elapsed_time": "2 days, 3:55:06", "remaining_time": "4:58:13", "throughput": 4647.61, "total_tokens": 868666888} {"current_steps": 14315, "total_steps": 15680, "loss": 0.25816683769226073, "lr": 1.8609574815791843e-07, "epoch": 1.8258928571428572, "percentage": 91.29, "elapsed_time": "2 days, 3:56:15", "remaining_time": "4:57:08", "throughput": 4647.45, "total_tokens": 868959528} {"current_steps": 14320, "total_steps": 15680, "loss": 0.2542288780212402, "lr": 1.8474433761133614e-07, "epoch": 1.8265306122448979, "percentage": 91.33, "elapsed_time": "2 days, 3:57:26", "remaining_time": "4:56:04", "throughput": 4647.33, "total_tokens": 869269160} {"current_steps": 14325, "total_steps": 15680, "loss": 0.26385793685913084, "lr": 1.833977595101083e-07, "epoch": 1.8271683673469388, "percentage": 91.36, "elapsed_time": "2 days, 3:58:34", "remaining_time": "4:54:59", "throughput": 4647.31, "total_tokens": 869579752} {"current_steps": 14330, "total_steps": 15680, "loss": 0.24700777530670165, "lr": 1.8205601520561945e-07, "epoch": 1.8278061224489797, "percentage": 91.39, "elapsed_time": "2 days, 3:59:42", "remaining_time": "4:53:54", "throughput": 4647.19, "total_tokens": 869872912} {"current_steps": 14335, "total_steps": 15680, "loss": 0.2464057445526123, "lr": 1.8071910604440356e-07, "epoch": 1.8284438775510203, "percentage": 91.42, "elapsed_time": "2 days, 4:00:46", "remaining_time": "4:52:48", "throughput": 4647.24, "total_tokens": 870179712} {"current_steps": 14340, "total_steps": 15680, "loss": 0.23783507347106933, "lr": 1.79387033368143e-07, "epoch": 1.8290816326530612, "percentage": 91.45, "elapsed_time": "2 days, 4:01:46", "remaining_time": "4:51:42", "throughput": 4647.33, "total_tokens": 870472648} {"current_steps": 14345, "total_steps": 15680, "loss": 0.25328662395477297, "lr": 1.7805979851366505e-07, "epoch": 1.8297193877551021, "percentage": 91.49, "elapsed_time": "2 days, 4:02:49", "remaining_time": "4:50:37", "throughput": 4647.34, "total_tokens": 870770136} {"current_steps": 14350, "total_steps": 15680, "loss": 0.25124058723449705, "lr": 1.7673740281294316e-07, "epoch": 1.8303571428571428, "percentage": 91.52, "elapsed_time": "2 days, 4:04:04", "remaining_time": "4:49:32", "throughput": 4647.14, "total_tokens": 871079520} {"current_steps": 14355, "total_steps": 15680, "loss": 0.2524874687194824, "lr": 1.7541984759309294e-07, "epoch": 1.8309948979591837, "percentage": 91.55, "elapsed_time": "2 days, 4:05:12", "remaining_time": "4:48:27", "throughput": 4647.03, "total_tokens": 871377240} {"current_steps": 14360, "total_steps": 15680, "loss": 0.2508760929107666, "lr": 1.7410713417637338e-07, "epoch": 1.8316326530612246, "percentage": 91.58, "elapsed_time": "2 days, 4:06:17", "remaining_time": "4:47:22", "throughput": 4647.03, "total_tokens": 871676128} {"current_steps": 14365, "total_steps": 15680, "loss": 0.24621005058288575, "lr": 1.7279926388018564e-07, "epoch": 1.8322704081632653, "percentage": 91.61, "elapsed_time": "2 days, 4:07:21", "remaining_time": "4:46:17", "throughput": 4647.07, "total_tokens": 871980776} {"current_steps": 14370, "total_steps": 15680, "loss": 0.23934614658355713, "lr": 1.714962380170665e-07, "epoch": 1.8329081632653061, "percentage": 91.65, "elapsed_time": "2 days, 4:08:30", "remaining_time": "4:45:12", "throughput": 4646.95, "total_tokens": 872279784} {"current_steps": 14375, "total_steps": 15680, "loss": 0.22678751945495607, "lr": 1.701980578946938e-07, "epoch": 1.833545918367347, "percentage": 91.68, "elapsed_time": "2 days, 4:09:34", "remaining_time": "4:44:06", "throughput": 4647.03, "total_tokens": 872592464} {"current_steps": 14380, "total_steps": 15680, "loss": 0.2569415092468262, "lr": 1.6890472481588426e-07, "epoch": 1.8341836734693877, "percentage": 91.71, "elapsed_time": "2 days, 4:10:48", "remaining_time": "4:43:02", "throughput": 4646.74, "total_tokens": 872884192} {"current_steps": 14385, "total_steps": 15680, "loss": 0.24323534965515137, "lr": 1.6761624007858524e-07, "epoch": 1.8348214285714286, "percentage": 91.74, "elapsed_time": "2 days, 4:11:39", "remaining_time": "4:41:55", "throughput": 4647.15, "total_tokens": 873200056} {"current_steps": 14390, "total_steps": 15680, "loss": 0.25774874687194826, "lr": 1.6633260497588233e-07, "epoch": 1.8354591836734695, "percentage": 91.77, "elapsed_time": "2 days, 4:12:54", "remaining_time": "4:40:51", "throughput": 4646.89, "total_tokens": 873496664} {"current_steps": 14395, "total_steps": 15680, "loss": 0.26739423274993895, "lr": 1.6505382079599341e-07, "epoch": 1.8360969387755102, "percentage": 91.8, "elapsed_time": "2 days, 4:13:59", "remaining_time": "4:39:45", "throughput": 4646.97, "total_tokens": 873815000} {"current_steps": 14400, "total_steps": 15680, "loss": 0.2510525226593018, "lr": 1.6377988882226691e-07, "epoch": 1.836734693877551, "percentage": 91.84, "elapsed_time": "2 days, 4:15:16", "remaining_time": "4:38:41", "throughput": 4646.66, "total_tokens": 874111704} {"current_steps": 14405, "total_steps": 15680, "loss": 0.2626865148544312, "lr": 1.6251081033318294e-07, "epoch": 1.837372448979592, "percentage": 91.87, "elapsed_time": "2 days, 4:16:23", "remaining_time": "4:37:36", "throughput": 4646.61, "total_tokens": 874416736} {"current_steps": 14410, "total_steps": 15680, "loss": 0.25091991424560545, "lr": 1.6124658660234993e-07, "epoch": 1.8380102040816326, "percentage": 91.9, "elapsed_time": "2 days, 4:17:36", "remaining_time": "4:36:31", "throughput": 4646.37, "total_tokens": 874708496} {"current_steps": 14415, "total_steps": 15680, "loss": 0.2551647901535034, "lr": 1.5998721889850577e-07, "epoch": 1.8386479591836735, "percentage": 91.93, "elapsed_time": "2 days, 4:18:26", "remaining_time": "4:35:24", "throughput": 4646.8, "total_tokens": 875023056} {"current_steps": 14420, "total_steps": 15680, "loss": 0.2508412837982178, "lr": 1.5873270848551227e-07, "epoch": 1.8392857142857144, "percentage": 91.96, "elapsed_time": "2 days, 4:19:33", "remaining_time": "4:34:19", "throughput": 4646.67, "total_tokens": 875310232} {"current_steps": 14425, "total_steps": 15680, "loss": 0.2600100994110107, "lr": 1.5748305662236008e-07, "epoch": 1.839923469387755, "percentage": 92.0, "elapsed_time": "2 days, 4:20:42", "remaining_time": "4:33:14", "throughput": 4646.61, "total_tokens": 875617936} {"current_steps": 14430, "total_steps": 15680, "loss": 0.24649903774261475, "lr": 1.562382645631605e-07, "epoch": 1.8405612244897958, "percentage": 92.03, "elapsed_time": "2 days, 4:21:55", "remaining_time": "4:32:10", "throughput": 4646.37, "total_tokens": 875913640} {"current_steps": 14435, "total_steps": 15680, "loss": 0.24332361221313475, "lr": 1.549983335571509e-07, "epoch": 1.8411989795918369, "percentage": 92.06, "elapsed_time": "2 days, 4:22:52", "remaining_time": "4:31:04", "throughput": 4646.6, "total_tokens": 876218840} {"current_steps": 14440, "total_steps": 15680, "loss": 0.2727149248123169, "lr": 1.537632648486864e-07, "epoch": 1.8418367346938775, "percentage": 92.09, "elapsed_time": "2 days, 4:23:55", "remaining_time": "4:29:58", "throughput": 4646.67, "total_tokens": 876527088} {"current_steps": 14445, "total_steps": 15680, "loss": 0.24445388317108155, "lr": 1.5253305967724674e-07, "epoch": 1.8424744897959182, "percentage": 92.12, "elapsed_time": "2 days, 4:24:53", "remaining_time": "4:28:52", "throughput": 4646.82, "total_tokens": 876825528} {"current_steps": 14450, "total_steps": 15680, "loss": 0.2287886619567871, "lr": 1.513077192774287e-07, "epoch": 1.8431122448979593, "percentage": 92.16, "elapsed_time": "2 days, 4:26:00", "remaining_time": "4:27:47", "throughput": 4646.79, "total_tokens": 877131672} {"current_steps": 14455, "total_steps": 15680, "loss": 0.2465895652770996, "lr": 1.500872448789459e-07, "epoch": 1.84375, "percentage": 92.19, "elapsed_time": "2 days, 4:26:56", "remaining_time": "4:26:41", "throughput": 4647.04, "total_tokens": 877437424} {"current_steps": 14460, "total_steps": 15680, "loss": 0.2551894664764404, "lr": 1.4887163770662905e-07, "epoch": 1.8443877551020407, "percentage": 92.22, "elapsed_time": "2 days, 4:27:53", "remaining_time": "4:25:35", "throughput": 4647.16, "total_tokens": 877726048} {"current_steps": 14465, "total_steps": 15680, "loss": 0.2440091848373413, "lr": 1.4766089898042678e-07, "epoch": 1.8450255102040818, "percentage": 92.25, "elapsed_time": "2 days, 4:28:50", "remaining_time": "4:24:29", "throughput": 4647.39, "total_tokens": 878032896} {"current_steps": 14470, "total_steps": 15680, "loss": 0.24983086585998535, "lr": 1.4645502991539883e-07, "epoch": 1.8456632653061225, "percentage": 92.28, "elapsed_time": "2 days, 4:30:01", "remaining_time": "4:23:24", "throughput": 4647.25, "total_tokens": 878336096} {"current_steps": 14475, "total_steps": 15680, "loss": 0.2324315309524536, "lr": 1.452540317217188e-07, "epoch": 1.8463010204081631, "percentage": 92.32, "elapsed_time": "2 days, 4:31:14", "remaining_time": "4:22:19", "throughput": 4647.1, "total_tokens": 878647240} {"current_steps": 14480, "total_steps": 15680, "loss": 0.2568353176116943, "lr": 1.440579056046737e-07, "epoch": 1.8469387755102042, "percentage": 92.35, "elapsed_time": "2 days, 4:32:19", "remaining_time": "4:21:14", "throughput": 4647.12, "total_tokens": 878950824} {"current_steps": 14485, "total_steps": 15680, "loss": 0.2626702308654785, "lr": 1.428666527646577e-07, "epoch": 1.847576530612245, "percentage": 92.38, "elapsed_time": "2 days, 4:33:18", "remaining_time": "4:20:08", "throughput": 4647.33, "total_tokens": 879270336} {"current_steps": 14490, "total_steps": 15680, "loss": 0.25818753242492676, "lr": 1.4168027439717735e-07, "epoch": 1.8482142857142856, "percentage": 92.41, "elapsed_time": "2 days, 4:34:22", "remaining_time": "4:19:03", "throughput": 4647.37, "total_tokens": 879571280} {"current_steps": 14495, "total_steps": 15680, "loss": 0.2519019842147827, "lr": 1.4049877169284575e-07, "epoch": 1.8488520408163265, "percentage": 92.44, "elapsed_time": "2 days, 4:35:21", "remaining_time": "4:17:57", "throughput": 4647.5, "total_tokens": 879869408} {"current_steps": 14500, "total_steps": 15680, "loss": 0.273012113571167, "lr": 1.3932214583738334e-07, "epoch": 1.8494897959183674, "percentage": 92.47, "elapsed_time": "2 days, 4:36:26", "remaining_time": "4:16:52", "throughput": 4647.57, "total_tokens": 880185176} {"current_steps": 14505, "total_steps": 15680, "loss": 0.23094744682312013, "lr": 1.3815039801161723e-07, "epoch": 1.850127551020408, "percentage": 92.51, "elapsed_time": "2 days, 4:37:35", "remaining_time": "4:15:47", "throughput": 4647.46, "total_tokens": 880486032} {"current_steps": 14510, "total_steps": 15680, "loss": 0.25781404972076416, "lr": 1.369835293914773e-07, "epoch": 1.850765306122449, "percentage": 92.54, "elapsed_time": "2 days, 4:38:31", "remaining_time": "4:14:41", "throughput": 4647.67, "total_tokens": 880787096} {"current_steps": 14515, "total_steps": 15680, "loss": 0.2545320510864258, "lr": 1.358215411479974e-07, "epoch": 1.8514030612244898, "percentage": 92.57, "elapsed_time": "2 days, 4:39:47", "remaining_time": "4:13:36", "throughput": 4647.44, "total_tokens": 881095592} {"current_steps": 14520, "total_steps": 15680, "loss": 0.2468923568725586, "lr": 1.3466443444731525e-07, "epoch": 1.8520408163265305, "percentage": 92.6, "elapsed_time": "2 days, 4:40:55", "remaining_time": "4:12:31", "throughput": 4647.32, "total_tokens": 881389136} {"current_steps": 14525, "total_steps": 15680, "loss": 0.25362067222595214, "lr": 1.3351221045066698e-07, "epoch": 1.8526785714285714, "percentage": 92.63, "elapsed_time": "2 days, 4:42:01", "remaining_time": "4:11:26", "throughput": 4647.31, "total_tokens": 881695144} {"current_steps": 14530, "total_steps": 15680, "loss": 0.2443603277206421, "lr": 1.3236487031439037e-07, "epoch": 1.8533163265306123, "percentage": 92.67, "elapsed_time": "2 days, 4:43:07", "remaining_time": "4:10:21", "throughput": 4647.35, "total_tokens": 882008248} {"current_steps": 14535, "total_steps": 15680, "loss": 0.23978824615478517, "lr": 1.3122241518992107e-07, "epoch": 1.853954081632653, "percentage": 92.7, "elapsed_time": "2 days, 4:44:12", "remaining_time": "4:09:15", "throughput": 4647.37, "total_tokens": 882314240} {"current_steps": 14540, "total_steps": 15680, "loss": 0.2655137300491333, "lr": 1.3008484622379358e-07, "epoch": 1.8545918367346939, "percentage": 92.73, "elapsed_time": "2 days, 4:45:20", "remaining_time": "4:08:10", "throughput": 4647.28, "total_tokens": 882616304} {"current_steps": 14545, "total_steps": 15680, "loss": 0.2473900079727173, "lr": 1.2895216455763582e-07, "epoch": 1.8552295918367347, "percentage": 92.76, "elapsed_time": "2 days, 4:46:18", "remaining_time": "4:07:04", "throughput": 4647.48, "total_tokens": 882923560} {"current_steps": 14550, "total_steps": 15680, "loss": 0.2586209774017334, "lr": 1.278243713281757e-07, "epoch": 1.8558673469387754, "percentage": 92.79, "elapsed_time": "2 days, 4:47:36", "remaining_time": "4:06:00", "throughput": 4647.14, "total_tokens": 883219664} {"current_steps": 14555, "total_steps": 15680, "loss": 0.234542179107666, "lr": 1.2670146766723013e-07, "epoch": 1.8565051020408163, "percentage": 92.83, "elapsed_time": "2 days, 4:48:36", "remaining_time": "4:04:54", "throughput": 4647.3, "total_tokens": 883530760} {"current_steps": 14560, "total_steps": 15680, "loss": 0.2434833526611328, "lr": 1.2558345470171153e-07, "epoch": 1.8571428571428572, "percentage": 92.86, "elapsed_time": "2 days, 4:49:44", "remaining_time": "4:03:49", "throughput": 4647.25, "total_tokens": 883836120} {"current_steps": 14565, "total_steps": 15680, "loss": 0.2338038921356201, "lr": 1.244703335536257e-07, "epoch": 1.8577806122448979, "percentage": 92.89, "elapsed_time": "2 days, 4:50:46", "remaining_time": "4:02:43", "throughput": 4647.3, "total_tokens": 884131064} {"current_steps": 14570, "total_steps": 15680, "loss": 0.254522705078125, "lr": 1.2336210534006576e-07, "epoch": 1.8584183673469388, "percentage": 92.92, "elapsed_time": "2 days, 4:51:47", "remaining_time": "4:01:38", "throughput": 4647.37, "total_tokens": 884427608} {"current_steps": 14575, "total_steps": 15680, "loss": 0.23550329208374024, "lr": 1.2225877117321705e-07, "epoch": 1.8590561224489797, "percentage": 92.95, "elapsed_time": "2 days, 4:53:05", "remaining_time": "4:00:34", "throughput": 4647.09, "total_tokens": 884738240} {"current_steps": 14580, "total_steps": 15680, "loss": 0.26369943618774416, "lr": 1.2116033216035162e-07, "epoch": 1.8596938775510203, "percentage": 92.98, "elapsed_time": "2 days, 4:54:19", "remaining_time": "3:59:29", "throughput": 4646.9, "total_tokens": 885046808} {"current_steps": 14585, "total_steps": 15680, "loss": 0.26955347061157225, "lr": 1.20066789403831e-07, "epoch": 1.8603316326530612, "percentage": 93.02, "elapsed_time": "2 days, 4:55:17", "remaining_time": "3:58:23", "throughput": 4647.1, "total_tokens": 885351872} {"current_steps": 14590, "total_steps": 15680, "loss": 0.24823312759399413, "lr": 1.1897814400110064e-07, "epoch": 1.8609693877551021, "percentage": 93.05, "elapsed_time": "2 days, 4:56:15", "remaining_time": "3:57:17", "throughput": 4647.32, "total_tokens": 885663712} {"current_steps": 14595, "total_steps": 15680, "loss": 0.2636047124862671, "lr": 1.1789439704469219e-07, "epoch": 1.8616071428571428, "percentage": 93.08, "elapsed_time": "2 days, 4:57:19", "remaining_time": "3:56:12", "throughput": 4647.31, "total_tokens": 885960504} {"current_steps": 14600, "total_steps": 15680, "loss": 0.2618051290512085, "lr": 1.168155496222223e-07, "epoch": 1.8622448979591837, "percentage": 93.11, "elapsed_time": "2 days, 4:58:27", "remaining_time": "3:55:07", "throughput": 4647.26, "total_tokens": 886267272} {"current_steps": 14605, "total_steps": 15680, "loss": 0.2571128845214844, "lr": 1.1574160281638935e-07, "epoch": 1.8628826530612246, "percentage": 93.14, "elapsed_time": "2 days, 4:59:22", "remaining_time": "3:54:01", "throughput": 4647.48, "total_tokens": 886563408} {"current_steps": 14610, "total_steps": 15680, "loss": 0.24137578010559083, "lr": 1.1467255770497343e-07, "epoch": 1.8635204081632653, "percentage": 93.18, "elapsed_time": "2 days, 5:00:31", "remaining_time": "3:52:55", "throughput": 4647.4, "total_tokens": 886868720} {"current_steps": 14615, "total_steps": 15680, "loss": 0.23988428115844726, "lr": 1.1360841536083633e-07, "epoch": 1.8641581632653061, "percentage": 93.21, "elapsed_time": "2 days, 5:01:28", "remaining_time": "3:51:50", "throughput": 4647.64, "total_tokens": 887181184} {"current_steps": 14620, "total_steps": 15680, "loss": 0.2605908393859863, "lr": 1.125491768519199e-07, "epoch": 1.864795918367347, "percentage": 93.24, "elapsed_time": "2 days, 5:02:46", "remaining_time": "3:50:45", "throughput": 4647.3, "total_tokens": 887479224} {"current_steps": 14625, "total_steps": 15680, "loss": 0.25436906814575194, "lr": 1.1149484324124326e-07, "epoch": 1.8654336734693877, "percentage": 93.27, "elapsed_time": "2 days, 5:03:55", "remaining_time": "3:49:40", "throughput": 4647.31, "total_tokens": 887799912} {"current_steps": 14630, "total_steps": 15680, "loss": 0.25912206172943114, "lr": 1.1044541558690281e-07, "epoch": 1.8660714285714286, "percentage": 93.3, "elapsed_time": "2 days, 5:04:52", "remaining_time": "3:48:34", "throughput": 4647.43, "total_tokens": 888088832} {"current_steps": 14635, "total_steps": 15680, "loss": 0.22946701049804688, "lr": 1.094008949420744e-07, "epoch": 1.8667091836734695, "percentage": 93.34, "elapsed_time": "2 days, 5:05:57", "remaining_time": "3:47:29", "throughput": 4647.49, "total_tokens": 888399576} {"current_steps": 14640, "total_steps": 15680, "loss": 0.23314986228942872, "lr": 1.0836128235500676e-07, "epoch": 1.8673469387755102, "percentage": 93.37, "elapsed_time": "2 days, 5:06:56", "remaining_time": "3:46:23", "throughput": 4647.65, "total_tokens": 888707984} {"current_steps": 14645, "total_steps": 15680, "loss": 0.2371466875076294, "lr": 1.0732657886902308e-07, "epoch": 1.867984693877551, "percentage": 93.4, "elapsed_time": "2 days, 5:08:01", "remaining_time": "3:45:18", "throughput": 4647.72, "total_tokens": 889023480} {"current_steps": 14650, "total_steps": 15680, "loss": 0.25177536010742185, "lr": 1.0629678552252109e-07, "epoch": 1.868622448979592, "percentage": 93.43, "elapsed_time": "2 days, 5:09:10", "remaining_time": "3:44:13", "throughput": 4647.56, "total_tokens": 889315784} {"current_steps": 14655, "total_steps": 15680, "loss": 0.26426329612731936, "lr": 1.0527190334897076e-07, "epoch": 1.8692602040816326, "percentage": 93.46, "elapsed_time": "2 days, 5:10:16", "remaining_time": "3:43:08", "throughput": 4647.55, "total_tokens": 889620424} {"current_steps": 14660, "total_steps": 15680, "loss": 0.2512818813323975, "lr": 1.0425193337691208e-07, "epoch": 1.8698979591836735, "percentage": 93.49, "elapsed_time": "2 days, 5:11:21", "remaining_time": "3:42:02", "throughput": 4647.54, "total_tokens": 889919392} {"current_steps": 14665, "total_steps": 15680, "loss": 0.271722412109375, "lr": 1.0323687662995685e-07, "epoch": 1.8705357142857144, "percentage": 93.53, "elapsed_time": "2 days, 5:12:28", "remaining_time": "3:40:57", "throughput": 4647.55, "total_tokens": 890229504} {"current_steps": 14670, "total_steps": 15680, "loss": 0.23242733478546143, "lr": 1.0222673412678518e-07, "epoch": 1.871173469387755, "percentage": 93.56, "elapsed_time": "2 days, 5:13:36", "remaining_time": "3:39:52", "throughput": 4647.49, "total_tokens": 890534280} {"current_steps": 14675, "total_steps": 15680, "loss": 0.25556354522705077, "lr": 1.0122150688114507e-07, "epoch": 1.8718112244897958, "percentage": 93.59, "elapsed_time": "2 days, 5:14:38", "remaining_time": "3:38:46", "throughput": 4647.57, "total_tokens": 890838848} {"current_steps": 14680, "total_steps": 15680, "loss": 0.25017662048339845, "lr": 1.0022119590185287e-07, "epoch": 1.8724489795918369, "percentage": 93.62, "elapsed_time": "2 days, 5:15:46", "remaining_time": "3:37:41", "throughput": 4647.54, "total_tokens": 891149616} {"current_steps": 14685, "total_steps": 15680, "loss": 0.25757060050964353, "lr": 9.922580219279055e-08, "epoch": 1.8730867346938775, "percentage": 93.65, "elapsed_time": "2 days, 5:17:03", "remaining_time": "3:36:37", "throughput": 4647.23, "total_tokens": 891449720} {"current_steps": 14690, "total_steps": 15680, "loss": 0.2548252582550049, "lr": 9.82353267529046e-08, "epoch": 1.8737244897959182, "percentage": 93.69, "elapsed_time": "2 days, 5:18:04", "remaining_time": "3:35:31", "throughput": 4647.32, "total_tokens": 891747784} {"current_steps": 14695, "total_steps": 15680, "loss": 0.2520712375640869, "lr": 9.72497705762071e-08, "epoch": 1.8743622448979593, "percentage": 93.72, "elapsed_time": "2 days, 5:19:07", "remaining_time": "3:34:26", "throughput": 4647.4, "total_tokens": 892058120} {"current_steps": 14700, "total_steps": 15680, "loss": 0.26645793914794924, "lr": 9.626913465177246e-08, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "2 days, 5:20:09", "remaining_time": "3:33:20", "throughput": 4647.49, "total_tokens": 892363192} {"current_steps": 14705, "total_steps": 15680, "loss": 0.2566962718963623, "lr": 9.529341996373675e-08, "epoch": 1.8756377551020407, "percentage": 93.78, "elapsed_time": "2 days, 5:21:22", "remaining_time": "3:32:15", "throughput": 4647.33, "total_tokens": 892669392} {"current_steps": 14710, "total_steps": 15680, "loss": 0.24963088035583497, "lr": 9.432262749129784e-08, "epoch": 1.8762755102040818, "percentage": 93.81, "elapsed_time": "2 days, 5:22:36", "remaining_time": "3:31:11", "throughput": 4647.1, "total_tokens": 892968720} {"current_steps": 14715, "total_steps": 15680, "loss": 0.24836084842681885, "lr": 9.335675820871415e-08, "epoch": 1.8769132653061225, "percentage": 93.85, "elapsed_time": "2 days, 5:23:36", "remaining_time": "3:30:05", "throughput": 4647.27, "total_tokens": 893280344} {"current_steps": 14720, "total_steps": 15680, "loss": 0.27693932056427, "lr": 9.239581308530254e-08, "epoch": 1.8775510204081631, "percentage": 93.88, "elapsed_time": "2 days, 5:24:40", "remaining_time": "3:29:00", "throughput": 4647.32, "total_tokens": 893587816} {"current_steps": 14725, "total_steps": 15680, "loss": 0.2538874626159668, "lr": 9.143979308543993e-08, "epoch": 1.8781887755102042, "percentage": 93.91, "elapsed_time": "2 days, 5:25:44", "remaining_time": "3:27:54", "throughput": 4647.38, "total_tokens": 893900112} {"current_steps": 14730, "total_steps": 15680, "loss": 0.2388587236404419, "lr": 9.048869916855662e-08, "epoch": 1.878826530612245, "percentage": 93.94, "elapsed_time": "2 days, 5:26:50", "remaining_time": "3:26:49", "throughput": 4647.36, "total_tokens": 894202528} {"current_steps": 14735, "total_steps": 15680, "loss": 0.24752345085144042, "lr": 8.954253228914356e-08, "epoch": 1.8794642857142856, "percentage": 93.97, "elapsed_time": "2 days, 5:28:05", "remaining_time": "3:25:44", "throughput": 4647.19, "total_tokens": 894517032} {"current_steps": 14740, "total_steps": 15680, "loss": 0.2614644289016724, "lr": 8.860129339674562e-08, "epoch": 1.8801020408163265, "percentage": 94.01, "elapsed_time": "2 days, 5:29:05", "remaining_time": "3:24:39", "throughput": 4647.27, "total_tokens": 894810904} {"current_steps": 14745, "total_steps": 15680, "loss": 0.23589935302734374, "lr": 8.766498343596053e-08, "epoch": 1.8807397959183674, "percentage": 94.04, "elapsed_time": "2 days, 5:30:13", "remaining_time": "3:23:33", "throughput": 4647.14, "total_tokens": 895101344} {"current_steps": 14750, "total_steps": 15680, "loss": 0.2402803421020508, "lr": 8.67336033464411e-08, "epoch": 1.881377551020408, "percentage": 94.07, "elapsed_time": "2 days, 5:31:26", "remaining_time": "3:22:29", "throughput": 4646.92, "total_tokens": 895400528} {"current_steps": 14755, "total_steps": 15680, "loss": 0.23293819427490234, "lr": 8.580715406289353e-08, "epoch": 1.882015306122449, "percentage": 94.1, "elapsed_time": "2 days, 5:32:43", "remaining_time": "3:21:24", "throughput": 4646.65, "total_tokens": 895706304} {"current_steps": 14760, "total_steps": 15680, "loss": 0.2630185127258301, "lr": 8.488563651507242e-08, "epoch": 1.8826530612244898, "percentage": 94.13, "elapsed_time": "2 days, 5:33:49", "remaining_time": "3:20:19", "throughput": 4646.63, "total_tokens": 896006184} {"current_steps": 14765, "total_steps": 15680, "loss": 0.26844196319580077, "lr": 8.396905162778523e-08, "epoch": 1.8832908163265305, "percentage": 94.16, "elapsed_time": "2 days, 5:34:51", "remaining_time": "3:19:13", "throughput": 4646.73, "total_tokens": 896313528} {"current_steps": 14770, "total_steps": 15680, "loss": 0.2632472991943359, "lr": 8.305740032089116e-08, "epoch": 1.8839285714285714, "percentage": 94.2, "elapsed_time": "2 days, 5:36:00", "remaining_time": "3:18:08", "throughput": 4646.64, "total_tokens": 896619432} {"current_steps": 14775, "total_steps": 15680, "loss": 0.25128650665283203, "lr": 8.215068350929334e-08, "epoch": 1.8845663265306123, "percentage": 94.23, "elapsed_time": "2 days, 5:37:17", "remaining_time": "3:17:03", "throughput": 4646.34, "total_tokens": 896916752} {"current_steps": 14780, "total_steps": 15680, "loss": 0.24625537395477295, "lr": 8.124890210294667e-08, "epoch": 1.885204081632653, "percentage": 94.26, "elapsed_time": "2 days, 5:38:21", "remaining_time": "3:15:58", "throughput": 4646.38, "total_tokens": 897221008} {"current_steps": 14785, "total_steps": 15680, "loss": 0.2617891788482666, "lr": 8.035205700685167e-08, "epoch": 1.8858418367346939, "percentage": 94.29, "elapsed_time": "2 days, 5:39:27", "remaining_time": "3:14:53", "throughput": 4646.29, "total_tokens": 897511264} {"current_steps": 14790, "total_steps": 15680, "loss": 0.26091532707214354, "lr": 7.946014912105505e-08, "epoch": 1.8864795918367347, "percentage": 94.32, "elapsed_time": "2 days, 5:40:48", "remaining_time": "3:13:48", "throughput": 4645.88, "total_tokens": 897807720} {"current_steps": 14795, "total_steps": 15680, "loss": 0.2553201198577881, "lr": 7.857317934064857e-08, "epoch": 1.8871173469387754, "percentage": 94.36, "elapsed_time": "2 days, 5:41:57", "remaining_time": "3:12:43", "throughput": 4645.82, "total_tokens": 898117528} {"current_steps": 14800, "total_steps": 15680, "loss": 0.26304941177368163, "lr": 7.769114855576799e-08, "epoch": 1.8877551020408163, "percentage": 94.39, "elapsed_time": "2 days, 5:43:07", "remaining_time": "3:11:38", "throughput": 4645.68, "total_tokens": 898417680} {"current_steps": 14805, "total_steps": 15680, "loss": 0.25156078338623045, "lr": 7.6814057651593e-08, "epoch": 1.8883928571428572, "percentage": 94.42, "elapsed_time": "2 days, 5:44:24", "remaining_time": "3:10:34", "throughput": 4645.37, "total_tokens": 898714720} {"current_steps": 14810, "total_steps": 15680, "loss": 0.24910693168640136, "lr": 7.594190750834617e-08, "epoch": 1.8890306122448979, "percentage": 94.45, "elapsed_time": "2 days, 5:45:38", "remaining_time": "3:09:29", "throughput": 4645.13, "total_tokens": 899011592} {"current_steps": 14815, "total_steps": 15680, "loss": 0.25336446762084963, "lr": 7.507469900129016e-08, "epoch": 1.8896683673469388, "percentage": 94.48, "elapsed_time": "2 days, 5:46:33", "remaining_time": "3:08:23", "throughput": 4645.38, "total_tokens": 899318184} {"current_steps": 14820, "total_steps": 15680, "loss": 0.23741183280944825, "lr": 7.421243300072989e-08, "epoch": 1.8903061224489797, "percentage": 94.52, "elapsed_time": "2 days, 5:47:30", "remaining_time": "3:07:17", "throughput": 4645.58, "total_tokens": 899618656} {"current_steps": 14825, "total_steps": 15680, "loss": 0.2510697841644287, "lr": 7.335511037200982e-08, "epoch": 1.8909438775510203, "percentage": 94.55, "elapsed_time": "2 days, 5:48:23", "remaining_time": "3:06:11", "throughput": 4645.9, "total_tokens": 899924056} {"current_steps": 14830, "total_steps": 15680, "loss": 0.23379080295562743, "lr": 7.250273197551227e-08, "epoch": 1.8915816326530612, "percentage": 94.58, "elapsed_time": "2 days, 5:49:37", "remaining_time": "3:05:06", "throughput": 4645.67, "total_tokens": 900226328} {"current_steps": 14835, "total_steps": 15680, "loss": 0.23528714179992677, "lr": 7.165529866665855e-08, "epoch": 1.8922193877551021, "percentage": 94.61, "elapsed_time": "2 days, 5:50:37", "remaining_time": "3:04:00", "throughput": 4645.72, "total_tokens": 900513536} {"current_steps": 14840, "total_steps": 15680, "loss": 0.2547890663146973, "lr": 7.081281129590777e-08, "epoch": 1.8928571428571428, "percentage": 94.64, "elapsed_time": "2 days, 5:51:49", "remaining_time": "3:02:56", "throughput": 4645.57, "total_tokens": 900821760} {"current_steps": 14845, "total_steps": 15680, "loss": 0.26011736392974855, "lr": 6.99752707087542e-08, "epoch": 1.8934948979591837, "percentage": 94.67, "elapsed_time": "2 days, 5:52:52", "remaining_time": "3:01:50", "throughput": 4645.64, "total_tokens": 901126832} {"current_steps": 14850, "total_steps": 15680, "loss": 0.25217404365539553, "lr": 6.91426777457288e-08, "epoch": 1.8941326530612246, "percentage": 94.71, "elapsed_time": "2 days, 5:54:04", "remaining_time": "3:00:45", "throughput": 4645.45, "total_tokens": 901424120} {"current_steps": 14855, "total_steps": 15680, "loss": 0.24703493118286132, "lr": 6.831503324239707e-08, "epoch": 1.8947704081632653, "percentage": 94.74, "elapsed_time": "2 days, 5:55:09", "remaining_time": "2:59:40", "throughput": 4645.43, "total_tokens": 901724328} {"current_steps": 14860, "total_steps": 15680, "loss": 0.2439436674118042, "lr": 6.749233802935684e-08, "epoch": 1.8954081632653061, "percentage": 94.77, "elapsed_time": "2 days, 5:56:09", "remaining_time": "2:58:34", "throughput": 4645.55, "total_tokens": 902025920} {"current_steps": 14865, "total_steps": 15680, "loss": 0.2603579044342041, "lr": 6.667459293224155e-08, "epoch": 1.896045918367347, "percentage": 94.8, "elapsed_time": "2 days, 5:56:58", "remaining_time": "2:57:28", "throughput": 4646.03, "total_tokens": 902344136} {"current_steps": 14870, "total_steps": 15680, "loss": 0.24415109157562256, "lr": 6.586179877171473e-08, "epoch": 1.8966836734693877, "percentage": 94.83, "elapsed_time": "2 days, 5:57:54", "remaining_time": "2:56:22", "throughput": 4646.28, "total_tokens": 902653128} {"current_steps": 14875, "total_steps": 15680, "loss": 0.24298529624938964, "lr": 6.505395636347222e-08, "epoch": 1.8973214285714286, "percentage": 94.87, "elapsed_time": "2 days, 5:58:59", "remaining_time": "2:55:17", "throughput": 4646.35, "total_tokens": 902969696} {"current_steps": 14880, "total_steps": 15680, "loss": 0.24060254096984862, "lr": 6.425106651824054e-08, "epoch": 1.8979591836734695, "percentage": 94.9, "elapsed_time": "2 days, 6:00:00", "remaining_time": "2:54:11", "throughput": 4646.46, "total_tokens": 903275896} {"current_steps": 14885, "total_steps": 15680, "loss": 0.23076014518737792, "lr": 6.345313004177511e-08, "epoch": 1.8985969387755102, "percentage": 94.93, "elapsed_time": "2 days, 6:01:07", "remaining_time": "2:53:06", "throughput": 4646.48, "total_tokens": 903589936} {"current_steps": 14890, "total_steps": 15680, "loss": 0.23166513442993164, "lr": 6.266014773486207e-08, "epoch": 1.899234693877551, "percentage": 94.96, "elapsed_time": "2 days, 6:02:12", "remaining_time": "2:52:01", "throughput": 4646.51, "total_tokens": 903899464} {"current_steps": 14895, "total_steps": 15680, "loss": 0.24292712211608886, "lr": 6.187212039331314e-08, "epoch": 1.899872448979592, "percentage": 94.99, "elapsed_time": "2 days, 6:03:17", "remaining_time": "2:50:55", "throughput": 4646.51, "total_tokens": 904199632} {"current_steps": 14900, "total_steps": 15680, "loss": 0.24226779937744142, "lr": 6.108904880797017e-08, "epoch": 1.9005102040816326, "percentage": 95.03, "elapsed_time": "2 days, 6:04:27", "remaining_time": "2:49:50", "throughput": 4646.38, "total_tokens": 904499744} {"current_steps": 14905, "total_steps": 15680, "loss": 0.2677560091018677, "lr": 6.031093376469899e-08, "epoch": 1.9011479591836735, "percentage": 95.06, "elapsed_time": "2 days, 6:05:34", "remaining_time": "2:48:45", "throughput": 4646.37, "total_tokens": 904810904} {"current_steps": 14910, "total_steps": 15680, "loss": 0.2479987621307373, "lr": 5.9537776044393256e-08, "epoch": 1.9017857142857144, "percentage": 95.09, "elapsed_time": "2 days, 6:06:43", "remaining_time": "2:47:40", "throughput": 4646.32, "total_tokens": 905119168} {"current_steps": 14915, "total_steps": 15680, "loss": 0.23430242538452148, "lr": 5.87695764229701e-08, "epoch": 1.902423469387755, "percentage": 95.12, "elapsed_time": "2 days, 6:07:52", "remaining_time": "2:46:35", "throughput": 4646.25, "total_tokens": 905425624} {"current_steps": 14920, "total_steps": 15680, "loss": 0.26269304752349854, "lr": 5.80063356713717e-08, "epoch": 1.9030612244897958, "percentage": 95.15, "elapsed_time": "2 days, 6:08:50", "remaining_time": "2:45:29", "throughput": 4646.4, "total_tokens": 905726560} {"current_steps": 14925, "total_steps": 15680, "loss": 0.2633235931396484, "lr": 5.7248054555563704e-08, "epoch": 1.9036989795918369, "percentage": 95.18, "elapsed_time": "2 days, 6:09:46", "remaining_time": "2:44:23", "throughput": 4646.67, "total_tokens": 906035824} {"current_steps": 14930, "total_steps": 15680, "loss": 0.24860916137695313, "lr": 5.6494733836534035e-08, "epoch": 1.9043367346938775, "percentage": 95.22, "elapsed_time": "2 days, 6:10:49", "remaining_time": "2:43:18", "throughput": 4646.75, "total_tokens": 906346096} {"current_steps": 14935, "total_steps": 15680, "loss": 0.24390010833740233, "lr": 5.574637427029239e-08, "epoch": 1.9049744897959182, "percentage": 95.25, "elapsed_time": "2 days, 6:11:52", "remaining_time": "2:42:12", "throughput": 4646.8, "total_tokens": 906648504} {"current_steps": 14940, "total_steps": 15680, "loss": 0.26183409690856935, "lr": 5.50029766078708e-08, "epoch": 1.9056122448979593, "percentage": 95.28, "elapsed_time": "2 days, 6:13:01", "remaining_time": "2:41:07", "throughput": 4646.71, "total_tokens": 906951760} {"current_steps": 14945, "total_steps": 15680, "loss": 0.25227718353271483, "lr": 5.426454159531913e-08, "epoch": 1.90625, "percentage": 95.31, "elapsed_time": "2 days, 6:14:11", "remaining_time": "2:40:02", "throughput": 4646.63, "total_tokens": 907262016} {"current_steps": 14950, "total_steps": 15680, "loss": 0.2548694610595703, "lr": 5.3531069973709607e-08, "epoch": 1.9068877551020407, "percentage": 95.34, "elapsed_time": "2 days, 6:15:20", "remaining_time": "2:38:57", "throughput": 4646.51, "total_tokens": 907561240} {"current_steps": 14955, "total_steps": 15680, "loss": 0.26091346740722654, "lr": 5.280256247913229e-08, "epoch": 1.9075255102040818, "percentage": 95.38, "elapsed_time": "2 days, 6:16:32", "remaining_time": "2:37:52", "throughput": 4646.33, "total_tokens": 907859912} {"current_steps": 14960, "total_steps": 15680, "loss": 0.24626507759094238, "lr": 5.207901984269459e-08, "epoch": 1.9081632653061225, "percentage": 95.41, "elapsed_time": "2 days, 6:17:35", "remaining_time": "2:36:46", "throughput": 4646.35, "total_tokens": 908156416} {"current_steps": 14965, "total_steps": 15680, "loss": 0.260360860824585, "lr": 5.136044279052288e-08, "epoch": 1.9088010204081631, "percentage": 95.44, "elapsed_time": "2 days, 6:18:46", "remaining_time": "2:35:41", "throughput": 4646.23, "total_tokens": 908460312} {"current_steps": 14970, "total_steps": 15680, "loss": 0.23393001556396484, "lr": 5.0646832043758645e-08, "epoch": 1.9094387755102042, "percentage": 95.47, "elapsed_time": "2 days, 6:19:41", "remaining_time": "2:34:36", "throughput": 4646.44, "total_tokens": 908759856} {"current_steps": 14975, "total_steps": 15680, "loss": 0.25123028755187987, "lr": 4.993818831856123e-08, "epoch": 1.910076530612245, "percentage": 95.5, "elapsed_time": "2 days, 6:20:51", "remaining_time": "2:33:30", "throughput": 4646.31, "total_tokens": 909059128} {"current_steps": 14980, "total_steps": 15680, "loss": 0.2689199686050415, "lr": 4.923451232610288e-08, "epoch": 1.9107142857142856, "percentage": 95.54, "elapsed_time": "2 days, 6:21:49", "remaining_time": "2:32:25", "throughput": 4646.53, "total_tokens": 909368704} {"current_steps": 14985, "total_steps": 15680, "loss": 0.24207632541656493, "lr": 4.8535804772572024e-08, "epoch": 1.9113520408163265, "percentage": 95.57, "elapsed_time": "2 days, 6:22:51", "remaining_time": "2:31:19", "throughput": 4646.58, "total_tokens": 909668768} {"current_steps": 14990, "total_steps": 15680, "loss": 0.26170997619628905, "lr": 4.7842066359170544e-08, "epoch": 1.9119897959183674, "percentage": 95.6, "elapsed_time": "2 days, 6:23:51", "remaining_time": "2:30:14", "throughput": 4646.76, "total_tokens": 909982280} {"current_steps": 14995, "total_steps": 15680, "loss": 0.24396302700042724, "lr": 4.715329778211375e-08, "epoch": 1.912627551020408, "percentage": 95.63, "elapsed_time": "2 days, 6:24:52", "remaining_time": "2:29:08", "throughput": 4646.9, "total_tokens": 910291280} {"current_steps": 15000, "total_steps": 15680, "loss": 0.241226863861084, "lr": 4.646949973262871e-08, "epoch": 1.913265306122449, "percentage": 95.66, "elapsed_time": "2 days, 6:25:54", "remaining_time": "2:28:03", "throughput": 4646.98, "total_tokens": 910597016} {"current_steps": 15005, "total_steps": 15680, "loss": 0.25010688304901124, "lr": 4.579067289695427e-08, "epoch": 1.9139030612244898, "percentage": 95.7, "elapsed_time": "2 days, 6:27:00", "remaining_time": "2:26:57", "throughput": 4646.92, "total_tokens": 910889416} {"current_steps": 15010, "total_steps": 15680, "loss": 0.24684762954711914, "lr": 4.511681795634049e-08, "epoch": 1.9145408163265305, "percentage": 95.73, "elapsed_time": "2 days, 6:28:10", "remaining_time": "2:25:52", "throughput": 4646.79, "total_tokens": 911194392} {"current_steps": 15015, "total_steps": 15680, "loss": 0.24867401123046876, "lr": 4.4447935587049185e-08, "epoch": 1.9151785714285714, "percentage": 95.76, "elapsed_time": "2 days, 6:29:19", "remaining_time": "2:24:47", "throughput": 4646.77, "total_tokens": 911506240} {"current_steps": 15020, "total_steps": 15680, "loss": 0.24369287490844727, "lr": 4.37840264603484e-08, "epoch": 1.9158163265306123, "percentage": 95.79, "elapsed_time": "2 days, 6:30:20", "remaining_time": "2:23:42", "throughput": 4646.88, "total_tokens": 911812040} {"current_steps": 15025, "total_steps": 15680, "loss": 0.26245894432067873, "lr": 4.312509124251907e-08, "epoch": 1.916454081632653, "percentage": 95.82, "elapsed_time": "2 days, 6:31:25", "remaining_time": "2:22:36", "throughput": 4646.91, "total_tokens": 912118696} {"current_steps": 15030, "total_steps": 15680, "loss": 0.24296834468841552, "lr": 4.247113059484775e-08, "epoch": 1.9170918367346939, "percentage": 95.85, "elapsed_time": "2 days, 6:32:39", "remaining_time": "2:21:31", "throughput": 4646.63, "total_tokens": 912411904} {"current_steps": 15035, "total_steps": 15680, "loss": 0.23697316646575928, "lr": 4.1822145173630033e-08, "epoch": 1.9177295918367347, "percentage": 95.89, "elapsed_time": "2 days, 6:33:45", "remaining_time": "2:20:26", "throughput": 4646.64, "total_tokens": 912720144} {"current_steps": 15040, "total_steps": 15680, "loss": 0.24823360443115233, "lr": 4.117813563016826e-08, "epoch": 1.9183673469387754, "percentage": 95.92, "elapsed_time": "2 days, 6:34:41", "remaining_time": "2:19:20", "throughput": 4646.93, "total_tokens": 913034744} {"current_steps": 15045, "total_steps": 15680, "loss": 0.2661388397216797, "lr": 4.0539102610770434e-08, "epoch": 1.9190051020408163, "percentage": 95.95, "elapsed_time": "2 days, 6:35:37", "remaining_time": "2:18:15", "throughput": 4647.16, "total_tokens": 913344128} {"current_steps": 15050, "total_steps": 15680, "loss": 0.24283137321472167, "lr": 3.990504675675133e-08, "epoch": 1.9196428571428572, "percentage": 95.98, "elapsed_time": "2 days, 6:36:39", "remaining_time": "2:17:09", "throughput": 4647.3, "total_tokens": 913656280} {"current_steps": 15055, "total_steps": 15680, "loss": 0.2644121885299683, "lr": 3.927596870442973e-08, "epoch": 1.9202806122448979, "percentage": 96.01, "elapsed_time": "2 days, 6:37:35", "remaining_time": "2:16:04", "throughput": 4647.5, "total_tokens": 913958416} {"current_steps": 15060, "total_steps": 15680, "loss": 0.24419598579406737, "lr": 3.8651869085130076e-08, "epoch": 1.9209183673469388, "percentage": 96.05, "elapsed_time": "2 days, 6:38:49", "remaining_time": "2:14:59", "throughput": 4647.29, "total_tokens": 914260256} {"current_steps": 15065, "total_steps": 15680, "loss": 0.23569097518920898, "lr": 3.8032748525179684e-08, "epoch": 1.9215561224489797, "percentage": 96.08, "elapsed_time": "2 days, 6:40:06", "remaining_time": "2:13:54", "throughput": 4646.98, "total_tokens": 914553184} {"current_steps": 15070, "total_steps": 15680, "loss": 0.24265587329864502, "lr": 3.741860764590877e-08, "epoch": 1.9221938775510203, "percentage": 96.11, "elapsed_time": "2 days, 6:41:20", "remaining_time": "2:12:49", "throughput": 4646.76, "total_tokens": 914855288} {"current_steps": 15075, "total_steps": 15680, "loss": 0.25319323539733884, "lr": 3.680944706365097e-08, "epoch": 1.9228316326530612, "percentage": 96.14, "elapsed_time": "2 days, 6:42:31", "remaining_time": "2:11:44", "throughput": 4646.62, "total_tokens": 915159176} {"current_steps": 15080, "total_steps": 15680, "loss": 0.23566744327545167, "lr": 3.6205267389741724e-08, "epoch": 1.9234693877551021, "percentage": 96.17, "elapsed_time": "2 days, 6:43:33", "remaining_time": "2:10:38", "throughput": 4646.76, "total_tokens": 915473424} {"current_steps": 15085, "total_steps": 15680, "loss": 0.23976473808288573, "lr": 3.560606923051768e-08, "epoch": 1.9241071428571428, "percentage": 96.21, "elapsed_time": "2 days, 6:44:43", "remaining_time": "2:09:33", "throughput": 4646.57, "total_tokens": 915764344} {"current_steps": 15090, "total_steps": 15680, "loss": 0.23405833244323732, "lr": 3.5011853187315035e-08, "epoch": 1.9247448979591837, "percentage": 96.24, "elapsed_time": "2 days, 6:45:48", "remaining_time": "2:08:28", "throughput": 4646.56, "total_tokens": 916061512} {"current_steps": 15095, "total_steps": 15680, "loss": 0.25694937705993653, "lr": 3.442261985647177e-08, "epoch": 1.9253826530612246, "percentage": 96.27, "elapsed_time": "2 days, 6:47:05", "remaining_time": "2:07:23", "throughput": 4646.35, "total_tokens": 916381160} {"current_steps": 15100, "total_steps": 15680, "loss": 0.2462223768234253, "lr": 3.383836982932542e-08, "epoch": 1.9260204081632653, "percentage": 96.3, "elapsed_time": "2 days, 6:48:11", "remaining_time": "2:06:18", "throughput": 4646.32, "total_tokens": 916678328} {"current_steps": 15105, "total_steps": 15680, "loss": 0.25452375411987305, "lr": 3.325910369220975e-08, "epoch": 1.9266581632653061, "percentage": 96.33, "elapsed_time": "2 days, 6:49:06", "remaining_time": "2:05:12", "throughput": 4646.6, "total_tokens": 916992400} {"current_steps": 15110, "total_steps": 15680, "loss": 0.2523342609405518, "lr": 3.268482202646084e-08, "epoch": 1.927295918367347, "percentage": 96.36, "elapsed_time": "2 days, 6:50:11", "remaining_time": "2:04:07", "throughput": 4646.59, "total_tokens": 917292000} {"current_steps": 15115, "total_steps": 15680, "loss": 0.26769270896911623, "lr": 3.211552540840934e-08, "epoch": 1.9279336734693877, "percentage": 96.4, "elapsed_time": "2 days, 6:51:22", "remaining_time": "2:03:01", "throughput": 4646.48, "total_tokens": 917597016} {"current_steps": 15120, "total_steps": 15680, "loss": 0.23019323348999024, "lr": 3.1551214409384355e-08, "epoch": 1.9285714285714286, "percentage": 96.43, "elapsed_time": "2 days, 6:52:38", "remaining_time": "2:01:56", "throughput": 4646.25, "total_tokens": 917908152} {"current_steps": 15125, "total_steps": 15680, "loss": 0.2444523811340332, "lr": 3.09918895957112e-08, "epoch": 1.9292091836734695, "percentage": 96.46, "elapsed_time": "2 days, 6:53:46", "remaining_time": "2:00:51", "throughput": 4646.22, "total_tokens": 918217408} {"current_steps": 15130, "total_steps": 15680, "loss": 0.2376544237136841, "lr": 3.0437551528711974e-08, "epoch": 1.9298469387755102, "percentage": 96.49, "elapsed_time": "2 days, 6:54:53", "remaining_time": "1:59:46", "throughput": 4646.12, "total_tokens": 918506528} {"current_steps": 15135, "total_steps": 15680, "loss": 0.25788092613220215, "lr": 2.988820076470278e-08, "epoch": 1.930484693877551, "percentage": 96.52, "elapsed_time": "2 days, 6:56:05", "remaining_time": "1:58:41", "throughput": 4645.94, "total_tokens": 918805920} {"current_steps": 15140, "total_steps": 15680, "loss": 0.23025188446044922, "lr": 2.934383785499595e-08, "epoch": 1.931122448979592, "percentage": 96.56, "elapsed_time": "2 days, 6:56:58", "remaining_time": "1:57:35", "throughput": 4646.25, "total_tokens": 919113720} {"current_steps": 15145, "total_steps": 15680, "loss": 0.2734971046447754, "lr": 2.880446334589837e-08, "epoch": 1.9317602040816326, "percentage": 96.59, "elapsed_time": "2 days, 6:58:02", "remaining_time": "1:56:30", "throughput": 4646.3, "total_tokens": 919419376} {"current_steps": 15150, "total_steps": 15680, "loss": 0.25088844299316404, "lr": 2.8270077778708714e-08, "epoch": 1.9323979591836735, "percentage": 96.62, "elapsed_time": "2 days, 6:59:01", "remaining_time": "1:55:24", "throughput": 4646.48, "total_tokens": 919729912} {"current_steps": 15155, "total_steps": 15680, "loss": 0.2477257490158081, "lr": 2.7740681689721327e-08, "epoch": 1.9330357142857144, "percentage": 96.65, "elapsed_time": "2 days, 7:00:07", "remaining_time": "1:54:19", "throughput": 4646.42, "total_tokens": 920027720} {"current_steps": 15160, "total_steps": 15680, "loss": 0.25936317443847656, "lr": 2.721627561022122e-08, "epoch": 1.933673469387755, "percentage": 96.68, "elapsed_time": "2 days, 7:01:11", "remaining_time": "1:53:14", "throughput": 4646.41, "total_tokens": 920323064} {"current_steps": 15165, "total_steps": 15680, "loss": 0.2339953899383545, "lr": 2.6696860066487417e-08, "epoch": 1.9343112244897958, "percentage": 96.72, "elapsed_time": "2 days, 7:02:24", "remaining_time": "1:52:08", "throughput": 4646.25, "total_tokens": 920627616} {"current_steps": 15170, "total_steps": 15680, "loss": 0.2542128562927246, "lr": 2.6182435579789055e-08, "epoch": 1.9349489795918369, "percentage": 96.75, "elapsed_time": "2 days, 7:03:28", "remaining_time": "1:51:03", "throughput": 4646.23, "total_tokens": 920923736} {"current_steps": 15175, "total_steps": 15680, "loss": 0.27027325630187987, "lr": 2.567300266638706e-08, "epoch": 1.9355867346938775, "percentage": 96.78, "elapsed_time": "2 days, 7:04:40", "remaining_time": "1:49:58", "throughput": 4646.02, "total_tokens": 921217520} {"current_steps": 15180, "total_steps": 15680, "loss": 0.2549232006072998, "lr": 2.516856183753358e-08, "epoch": 1.9362244897959182, "percentage": 96.81, "elapsed_time": "2 days, 7:05:41", "remaining_time": "1:48:52", "throughput": 4646.07, "total_tokens": 921505632} {"current_steps": 15185, "total_steps": 15680, "loss": 0.24539024829864503, "lr": 2.4669113599469774e-08, "epoch": 1.9368622448979593, "percentage": 96.84, "elapsed_time": "2 days, 7:06:47", "remaining_time": "1:47:47", "throughput": 4646.08, "total_tokens": 921818320} {"current_steps": 15190, "total_steps": 15680, "loss": 0.24641995429992675, "lr": 2.4174658453426368e-08, "epoch": 1.9375, "percentage": 96.88, "elapsed_time": "2 days, 7:07:55", "remaining_time": "1:46:42", "throughput": 4646.01, "total_tokens": 922118720} {"current_steps": 15195, "total_steps": 15680, "loss": 0.2644636631011963, "lr": 2.3685196895624206e-08, "epoch": 1.9381377551020407, "percentage": 96.91, "elapsed_time": "2 days, 7:08:55", "remaining_time": "1:45:36", "throughput": 4646.12, "total_tokens": 922420232} {"current_steps": 15200, "total_steps": 15680, "loss": 0.2815537452697754, "lr": 2.3200729417272028e-08, "epoch": 1.9387755102040818, "percentage": 96.94, "elapsed_time": "2 days, 7:09:58", "remaining_time": "1:44:31", "throughput": 4646.23, "total_tokens": 922733976} {"current_steps": 15205, "total_steps": 15680, "loss": 0.24536752700805664, "lr": 2.2721256504567026e-08, "epoch": 1.9394132653061225, "percentage": 96.97, "elapsed_time": "2 days, 7:11:16", "remaining_time": "1:43:26", "throughput": 4645.91, "total_tokens": 923030704} {"current_steps": 15210, "total_steps": 15680, "loss": 0.241164493560791, "lr": 2.2246778638692623e-08, "epoch": 1.9400510204081631, "percentage": 97.0, "elapsed_time": "2 days, 7:12:32", "remaining_time": "1:42:21", "throughput": 4645.67, "total_tokens": 923335856} {"current_steps": 15215, "total_steps": 15680, "loss": 0.26407551765441895, "lr": 2.177729629582237e-08, "epoch": 1.9406887755102042, "percentage": 97.03, "elapsed_time": "2 days, 7:13:31", "remaining_time": "1:41:16", "throughput": 4645.8, "total_tokens": 923639016} {"current_steps": 15220, "total_steps": 15680, "loss": 0.22718312740325927, "lr": 2.1312809947113267e-08, "epoch": 1.941326530612245, "percentage": 97.07, "elapsed_time": "2 days, 7:14:38", "remaining_time": "1:40:10", "throughput": 4645.74, "total_tokens": 923939616} {"current_steps": 15225, "total_steps": 15680, "loss": 0.23678016662597656, "lr": 2.0853320058710214e-08, "epoch": 1.9419642857142856, "percentage": 97.1, "elapsed_time": "2 days, 7:15:43", "remaining_time": "1:39:05", "throughput": 4645.72, "total_tokens": 924234088} {"current_steps": 15230, "total_steps": 15680, "loss": 0.27280292510986326, "lr": 2.0398827091743234e-08, "epoch": 1.9426020408163265, "percentage": 97.13, "elapsed_time": "2 days, 7:16:56", "remaining_time": "1:38:00", "throughput": 4645.56, "total_tokens": 924543768} {"current_steps": 15235, "total_steps": 15680, "loss": 0.23533403873443604, "lr": 1.9949331502327475e-08, "epoch": 1.9432397959183674, "percentage": 97.16, "elapsed_time": "2 days, 7:18:07", "remaining_time": "1:36:55", "throughput": 4645.37, "total_tokens": 924832536} {"current_steps": 15240, "total_steps": 15680, "loss": 0.26111152172088625, "lr": 1.950483374156431e-08, "epoch": 1.943877551020408, "percentage": 97.19, "elapsed_time": "2 days, 7:19:13", "remaining_time": "1:35:49", "throughput": 4645.34, "total_tokens": 925138328} {"current_steps": 15245, "total_steps": 15680, "loss": 0.25782184600830077, "lr": 1.9065334255536916e-08, "epoch": 1.944515306122449, "percentage": 97.23, "elapsed_time": "2 days, 7:20:25", "remaining_time": "1:34:44", "throughput": 4645.22, "total_tokens": 925447200} {"current_steps": 15250, "total_steps": 15680, "loss": 0.24272508621215821, "lr": 1.8630833485314693e-08, "epoch": 1.9451530612244898, "percentage": 97.26, "elapsed_time": "2 days, 7:21:42", "remaining_time": "1:33:39", "throughput": 4644.96, "total_tokens": 925753016} {"current_steps": 15255, "total_steps": 15680, "loss": 0.25693254470825194, "lr": 1.8201331866948834e-08, "epoch": 1.9457908163265305, "percentage": 97.29, "elapsed_time": "2 days, 7:22:53", "remaining_time": "1:32:34", "throughput": 4644.83, "total_tokens": 926056384} {"current_steps": 15260, "total_steps": 15680, "loss": 0.2646693229675293, "lr": 1.7776829831474553e-08, "epoch": 1.9464285714285714, "percentage": 97.32, "elapsed_time": "2 days, 7:24:00", "remaining_time": "1:31:29", "throughput": 4644.82, "total_tokens": 926363824} {"current_steps": 15265, "total_steps": 15680, "loss": 0.27986161708831786, "lr": 1.735732780490884e-08, "epoch": 1.9470663265306123, "percentage": 97.35, "elapsed_time": "2 days, 7:24:55", "remaining_time": "1:30:23", "throughput": 4645.08, "total_tokens": 926674400} {"current_steps": 15270, "total_steps": 15680, "loss": 0.2596017122268677, "lr": 1.694282620825216e-08, "epoch": 1.947704081632653, "percentage": 97.39, "elapsed_time": "2 days, 7:26:04", "remaining_time": "1:29:18", "throughput": 4644.98, "total_tokens": 926972904} {"current_steps": 15275, "total_steps": 15680, "loss": 0.25693569183349607, "lr": 1.6533325457485093e-08, "epoch": 1.9483418367346939, "percentage": 97.42, "elapsed_time": "2 days, 7:27:09", "remaining_time": "1:28:12", "throughput": 4645.02, "total_tokens": 927282680} {"current_steps": 15280, "total_steps": 15680, "loss": 0.2503585577011108, "lr": 1.612882596357057e-08, "epoch": 1.9489795918367347, "percentage": 97.45, "elapsed_time": "2 days, 7:28:20", "remaining_time": "1:27:07", "throughput": 4644.91, "total_tokens": 927592416} {"current_steps": 15285, "total_steps": 15680, "loss": 0.24806904792785645, "lr": 1.5729328132452203e-08, "epoch": 1.9496173469387754, "percentage": 97.48, "elapsed_time": "2 days, 7:29:24", "remaining_time": "1:26:02", "throughput": 4645.0, "total_tokens": 927904256} {"current_steps": 15290, "total_steps": 15680, "loss": 0.24865076541900635, "lr": 1.533483236505373e-08, "epoch": 1.9502551020408163, "percentage": 97.51, "elapsed_time": "2 days, 7:30:30", "remaining_time": "1:24:57", "throughput": 4645.03, "total_tokens": 928217856} {"current_steps": 15295, "total_steps": 15680, "loss": 0.26568968296051027, "lr": 1.494533905727902e-08, "epoch": 1.9508928571428572, "percentage": 97.54, "elapsed_time": "2 days, 7:31:38", "remaining_time": "1:23:51", "throughput": 4644.95, "total_tokens": 928520184} {"current_steps": 15300, "total_steps": 15680, "loss": 0.24280576705932616, "lr": 1.4560848600012056e-08, "epoch": 1.9515306122448979, "percentage": 97.58, "elapsed_time": "2 days, 7:32:40", "remaining_time": "1:22:46", "throughput": 4645.05, "total_tokens": 928828280} {"current_steps": 15305, "total_steps": 15680, "loss": 0.25272064208984374, "lr": 1.4181361379115854e-08, "epoch": 1.9521683673469388, "percentage": 97.61, "elapsed_time": "2 days, 7:33:50", "remaining_time": "1:21:41", "throughput": 4645.01, "total_tokens": 929145448} {"current_steps": 15310, "total_steps": 15680, "loss": 0.24609718322753907, "lr": 1.3806877775432436e-08, "epoch": 1.9528061224489797, "percentage": 97.64, "elapsed_time": "2 days, 7:34:44", "remaining_time": "1:20:35", "throughput": 4645.3, "total_tokens": 929452648} {"current_steps": 15315, "total_steps": 15680, "loss": 0.24976670742034912, "lr": 1.3437398164781734e-08, "epoch": 1.9534438775510203, "percentage": 97.67, "elapsed_time": "2 days, 7:35:49", "remaining_time": "1:19:30", "throughput": 4645.27, "total_tokens": 929748480} {"current_steps": 15320, "total_steps": 15680, "loss": 0.24251127243041992, "lr": 1.3072922917963249e-08, "epoch": 1.9540816326530612, "percentage": 97.7, "elapsed_time": "2 days, 7:36:53", "remaining_time": "1:18:24", "throughput": 4645.31, "total_tokens": 930053288} {"current_steps": 15325, "total_steps": 15680, "loss": 0.2625253677368164, "lr": 1.2713452400752724e-08, "epoch": 1.9547193877551021, "percentage": 97.74, "elapsed_time": "2 days, 7:38:00", "remaining_time": "1:17:19", "throughput": 4645.33, "total_tokens": 930369984} {"current_steps": 15330, "total_steps": 15680, "loss": 0.2642559051513672, "lr": 1.2358986973903807e-08, "epoch": 1.9553571428571428, "percentage": 97.77, "elapsed_time": "2 days, 7:39:05", "remaining_time": "1:16:14", "throughput": 4645.4, "total_tokens": 930684352} {"current_steps": 15335, "total_steps": 15680, "loss": 0.2565456390380859, "lr": 1.2009526993147503e-08, "epoch": 1.9559948979591837, "percentage": 97.8, "elapsed_time": "2 days, 7:40:06", "remaining_time": "1:15:08", "throughput": 4645.54, "total_tokens": 930994304} {"current_steps": 15340, "total_steps": 15680, "loss": 0.24982020854949952, "lr": 1.1665072809191602e-08, "epoch": 1.9566326530612246, "percentage": 97.83, "elapsed_time": "2 days, 7:41:07", "remaining_time": "1:14:03", "throughput": 4645.68, "total_tokens": 931306504} {"current_steps": 15345, "total_steps": 15680, "loss": 0.25244736671447754, "lr": 1.132562476771959e-08, "epoch": 1.9572704081632653, "percentage": 97.86, "elapsed_time": "2 days, 7:42:01", "remaining_time": "1:12:57", "throughput": 4645.94, "total_tokens": 931609672} {"current_steps": 15350, "total_steps": 15680, "loss": 0.24548232555389404, "lr": 1.0991183209391188e-08, "epoch": 1.9579081632653061, "percentage": 97.9, "elapsed_time": "2 days, 7:43:10", "remaining_time": "1:11:52", "throughput": 4645.85, "total_tokens": 931914232} {"current_steps": 15355, "total_steps": 15680, "loss": 0.2334390640258789, "lr": 1.0661748469842359e-08, "epoch": 1.958545918367347, "percentage": 97.93, "elapsed_time": "2 days, 7:44:15", "remaining_time": "1:10:47", "throughput": 4645.87, "total_tokens": 932218120} {"current_steps": 15360, "total_steps": 15680, "loss": 0.23780970573425292, "lr": 1.0337320879683087e-08, "epoch": 1.9591836734693877, "percentage": 97.96, "elapsed_time": "2 days, 7:45:28", "remaining_time": "1:09:41", "throughput": 4645.73, "total_tokens": 932530040} {"current_steps": 15365, "total_steps": 15680, "loss": 0.255706787109375, "lr": 1.0017900764500155e-08, "epoch": 1.9598214285714286, "percentage": 97.99, "elapsed_time": "2 days, 7:46:23", "remaining_time": "1:08:36", "throughput": 4646.01, "total_tokens": 932840976} {"current_steps": 15370, "total_steps": 15680, "loss": 0.2541600942611694, "lr": 9.703488444853248e-09, "epoch": 1.9604591836734695, "percentage": 98.02, "elapsed_time": "2 days, 7:47:34", "remaining_time": "1:07:31", "throughput": 4645.89, "total_tokens": 933147184} {"current_steps": 15375, "total_steps": 15680, "loss": 0.24727683067321776, "lr": 9.39408423627719e-09, "epoch": 1.9610969387755102, "percentage": 98.05, "elapsed_time": "2 days, 7:48:32", "remaining_time": "1:06:25", "throughput": 4646.06, "total_tokens": 933449616} {"current_steps": 15380, "total_steps": 15680, "loss": 0.2606107950210571, "lr": 9.089688449280265e-09, "epoch": 1.961734693877551, "percentage": 98.09, "elapsed_time": "2 days, 7:49:46", "remaining_time": "1:05:20", "throughput": 4645.82, "total_tokens": 933748368} {"current_steps": 15385, "total_steps": 15680, "loss": 0.25869710445404054, "lr": 8.79030138934589e-09, "epoch": 1.962372448979592, "percentage": 98.12, "elapsed_time": "2 days, 7:50:32", "remaining_time": "1:04:14", "throughput": 4646.35, "total_tokens": 934066280} {"current_steps": 15390, "total_steps": 15680, "loss": 0.23783254623413086, "lr": 8.49592335692928e-09, "epoch": 1.9630102040816326, "percentage": 98.15, "elapsed_time": "2 days, 7:51:32", "remaining_time": "1:03:09", "throughput": 4646.42, "total_tokens": 934360528} {"current_steps": 15395, "total_steps": 15680, "loss": 0.22529397010803223, "lr": 8.206554647459675e-09, "epoch": 1.9636479591836735, "percentage": 98.18, "elapsed_time": "2 days, 7:52:47", "remaining_time": "1:02:04", "throughput": 4646.2, "total_tokens": 934662128} {"current_steps": 15400, "total_steps": 15680, "loss": 0.2720287084579468, "lr": 7.922195551338107e-09, "epoch": 1.9642857142857144, "percentage": 98.21, "elapsed_time": "2 days, 7:53:45", "remaining_time": "1:00:58", "throughput": 4646.3, "total_tokens": 934954856} {"current_steps": 15405, "total_steps": 15680, "loss": 0.2662359237670898, "lr": 7.642846353939637e-09, "epoch": 1.964923469387755, "percentage": 98.25, "elapsed_time": "2 days, 7:55:04", "remaining_time": "0:59:53", "throughput": 4646.02, "total_tokens": 935263264} {"current_steps": 15410, "total_steps": 15680, "loss": 0.2379246711730957, "lr": 7.368507335610009e-09, "epoch": 1.9655612244897958, "percentage": 98.28, "elapsed_time": "2 days, 7:56:05", "remaining_time": "0:58:48", "throughput": 4646.05, "total_tokens": 935557064} {"current_steps": 15415, "total_steps": 15680, "loss": 0.24412119388580322, "lr": 7.099178771668436e-09, "epoch": 1.9661989795918369, "percentage": 98.31, "elapsed_time": "2 days, 7:57:09", "remaining_time": "0:57:42", "throughput": 4646.12, "total_tokens": 935867560} {"current_steps": 15420, "total_steps": 15680, "loss": 0.25436787605285643, "lr": 6.834860932403709e-09, "epoch": 1.9668367346938775, "percentage": 98.34, "elapsed_time": "2 days, 7:58:30", "remaining_time": "0:56:37", "throughput": 4645.74, "total_tokens": 936164024} {"current_steps": 15425, "total_steps": 15680, "loss": 0.2626820087432861, "lr": 6.575554083078084e-09, "epoch": 1.9674744897959182, "percentage": 98.37, "elapsed_time": "2 days, 7:59:42", "remaining_time": "0:55:32", "throughput": 4645.58, "total_tokens": 936466568} {"current_steps": 15430, "total_steps": 15680, "loss": 0.2702171802520752, "lr": 6.321258483924508e-09, "epoch": 1.9681122448979593, "percentage": 98.41, "elapsed_time": "2 days, 8:00:45", "remaining_time": "0:54:27", "throughput": 4645.63, "total_tokens": 936768752} {"current_steps": 15435, "total_steps": 15680, "loss": 0.23894684314727782, "lr": 6.071974390144953e-09, "epoch": 1.96875, "percentage": 98.44, "elapsed_time": "2 days, 8:01:46", "remaining_time": "0:53:21", "throughput": 4645.71, "total_tokens": 937071272} {"current_steps": 15440, "total_steps": 15680, "loss": 0.25569274425506594, "lr": 5.827702051914852e-09, "epoch": 1.9693877551020407, "percentage": 98.47, "elapsed_time": "2 days, 8:03:02", "remaining_time": "0:52:16", "throughput": 4645.48, "total_tokens": 937374224} {"current_steps": 15445, "total_steps": 15680, "loss": 0.2737967252731323, "lr": 5.5884417143775574e-09, "epoch": 1.9700255102040818, "percentage": 98.5, "elapsed_time": "2 days, 8:03:57", "remaining_time": "0:51:11", "throughput": 4645.72, "total_tokens": 937680296} {"current_steps": 15450, "total_steps": 15680, "loss": 0.25485644340515134, "lr": 5.354193617648218e-09, "epoch": 1.9706632653061225, "percentage": 98.53, "elapsed_time": "2 days, 8:05:06", "remaining_time": "0:50:05", "throughput": 4645.55, "total_tokens": 937965664} {"current_steps": 15455, "total_steps": 15680, "loss": 0.2593040466308594, "lr": 5.124957996811009e-09, "epoch": 1.9713010204081631, "percentage": 98.57, "elapsed_time": "2 days, 8:06:10", "remaining_time": "0:49:00", "throughput": 4645.55, "total_tokens": 938265008} {"current_steps": 15460, "total_steps": 15680, "loss": 0.23735318183898926, "lr": 4.900735081919128e-09, "epoch": 1.9719387755102042, "percentage": 98.6, "elapsed_time": "2 days, 8:07:13", "remaining_time": "0:47:54", "throughput": 4645.62, "total_tokens": 938569376} {"current_steps": 15465, "total_steps": 15680, "loss": 0.25776076316833496, "lr": 4.6815250979970195e-09, "epoch": 1.972576530612245, "percentage": 98.63, "elapsed_time": "2 days, 8:08:14", "remaining_time": "0:46:49", "throughput": 4645.74, "total_tokens": 938878464} {"current_steps": 15470, "total_steps": 15680, "loss": 0.25017719268798827, "lr": 4.467328265037041e-09, "epoch": 1.9732142857142856, "percentage": 98.66, "elapsed_time": "2 days, 8:09:18", "remaining_time": "0:45:44", "throughput": 4645.71, "total_tokens": 939168384} {"current_steps": 15475, "total_steps": 15680, "loss": 0.2674983501434326, "lr": 4.258144798000019e-09, "epoch": 1.9738520408163265, "percentage": 98.69, "elapsed_time": "2 days, 8:10:28", "remaining_time": "0:44:38", "throughput": 4645.63, "total_tokens": 939479720} {"current_steps": 15480, "total_steps": 15680, "loss": 0.2481661319732666, "lr": 4.05397490681636e-09, "epoch": 1.9744897959183674, "percentage": 98.72, "elapsed_time": "2 days, 8:11:38", "remaining_time": "0:43:33", "throughput": 4645.49, "total_tokens": 939776816} {"current_steps": 15485, "total_steps": 15680, "loss": 0.26866137981414795, "lr": 3.854818796385495e-09, "epoch": 1.975127551020408, "percentage": 98.76, "elapsed_time": "2 days, 8:12:40", "remaining_time": "0:42:28", "throughput": 4645.54, "total_tokens": 940072480} {"current_steps": 15490, "total_steps": 15680, "loss": 0.24293665885925292, "lr": 3.660676666573659e-09, "epoch": 1.975765306122449, "percentage": 98.79, "elapsed_time": "2 days, 8:13:44", "remaining_time": "0:41:22", "throughput": 4645.54, "total_tokens": 940372488} {"current_steps": 15495, "total_steps": 15680, "loss": 0.2463254451751709, "lr": 3.4715487122161107e-09, "epoch": 1.9764030612244898, "percentage": 98.82, "elapsed_time": "2 days, 8:14:50", "remaining_time": "0:40:17", "throughput": 4645.54, "total_tokens": 940678120} {"current_steps": 15500, "total_steps": 15680, "loss": 0.258991003036499, "lr": 3.287435123116578e-09, "epoch": 1.9770408163265305, "percentage": 98.85, "elapsed_time": "2 days, 8:15:54", "remaining_time": "0:39:12", "throughput": 4645.63, "total_tokens": 940991336} {"current_steps": 15505, "total_steps": 15680, "loss": 0.24148159027099608, "lr": 3.1083360840455935e-09, "epoch": 1.9776785714285714, "percentage": 98.88, "elapsed_time": "2 days, 8:16:57", "remaining_time": "0:38:06", "throughput": 4645.63, "total_tokens": 941285288} {"current_steps": 15510, "total_steps": 15680, "loss": 0.25423603057861327, "lr": 2.9342517747410482e-09, "epoch": 1.9783163265306123, "percentage": 98.92, "elapsed_time": "2 days, 8:17:48", "remaining_time": "0:37:01", "throughput": 4646.03, "total_tokens": 941603816} {"current_steps": 15515, "total_steps": 15680, "loss": 0.24060502052307128, "lr": 2.7651823699093027e-09, "epoch": 1.978954081632653, "percentage": 98.95, "elapsed_time": "2 days, 8:18:41", "remaining_time": "0:35:55", "throughput": 4646.4, "total_tokens": 941927344} {"current_steps": 15520, "total_steps": 15680, "loss": 0.25852391719818113, "lr": 2.6011280392235215e-09, "epoch": 1.9795918367346939, "percentage": 98.98, "elapsed_time": "2 days, 8:19:49", "remaining_time": "0:34:50", "throughput": 4646.35, "total_tokens": 942228704} {"current_steps": 15525, "total_steps": 15680, "loss": 0.2551721572875977, "lr": 2.442088947323118e-09, "epoch": 1.9802295918367347, "percentage": 99.01, "elapsed_time": "2 days, 8:21:01", "remaining_time": "0:33:45", "throughput": 4646.19, "total_tokens": 942534256} {"current_steps": 15530, "total_steps": 15680, "loss": 0.2408912420272827, "lr": 2.288065253814864e-09, "epoch": 1.9808673469387754, "percentage": 99.04, "elapsed_time": "2 days, 8:22:05", "remaining_time": "0:32:39", "throughput": 4646.16, "total_tokens": 942822104} {"current_steps": 15535, "total_steps": 15680, "loss": 0.249487042427063, "lr": 2.139057113272891e-09, "epoch": 1.9815051020408163, "percentage": 99.08, "elapsed_time": "2 days, 8:23:06", "remaining_time": "0:31:34", "throughput": 4646.24, "total_tokens": 943125064} {"current_steps": 15540, "total_steps": 15680, "loss": 0.24320669174194337, "lr": 1.995064675237024e-09, "epoch": 1.9821428571428572, "percentage": 99.11, "elapsed_time": "2 days, 8:24:12", "remaining_time": "0:30:29", "throughput": 4646.15, "total_tokens": 943414656} {"current_steps": 15545, "total_steps": 15680, "loss": 0.2668965578079224, "lr": 1.8560880842133366e-09, "epoch": 1.9827806122448979, "percentage": 99.14, "elapsed_time": "2 days, 8:25:09", "remaining_time": "0:29:23", "throughput": 4646.34, "total_tokens": 943715632} {"current_steps": 15550, "total_steps": 15680, "loss": 0.2613052845001221, "lr": 1.7221274796752618e-09, "epoch": 1.9834183673469388, "percentage": 99.17, "elapsed_time": "2 days, 8:26:20", "remaining_time": "0:28:18", "throughput": 4646.22, "total_tokens": 944022192} {"current_steps": 15555, "total_steps": 15680, "loss": 0.266310453414917, "lr": 1.5931829960608158e-09, "epoch": 1.9840561224489797, "percentage": 99.2, "elapsed_time": "2 days, 8:27:31", "remaining_time": "0:27:13", "throughput": 4646.12, "total_tokens": 944328320} {"current_steps": 15560, "total_steps": 15680, "loss": 0.2567771911621094, "lr": 1.469254762775374e-09, "epoch": 1.9846938775510203, "percentage": 99.23, "elapsed_time": "2 days, 8:28:28", "remaining_time": "0:26:07", "throughput": 4646.25, "total_tokens": 944620232} {"current_steps": 15565, "total_steps": 15680, "loss": 0.25018773078918455, "lr": 1.350342904188895e-09, "epoch": 1.9853316326530612, "percentage": 99.27, "elapsed_time": "2 days, 8:29:11", "remaining_time": "0:25:02", "throughput": 4646.76, "total_tokens": 944927232} {"current_steps": 15570, "total_steps": 15680, "loss": 0.25844545364379884, "lr": 1.2364475396386966e-09, "epoch": 1.9859693877551021, "percentage": 99.3, "elapsed_time": "2 days, 8:30:19", "remaining_time": "0:23:57", "throughput": 4646.73, "total_tokens": 945234328} {"current_steps": 15575, "total_steps": 15680, "loss": 0.24469830989837646, "lr": 1.1275687834266803e-09, "epoch": 1.9866071428571428, "percentage": 99.33, "elapsed_time": "2 days, 8:31:28", "remaining_time": "0:22:51", "throughput": 4646.61, "total_tokens": 945532880} {"current_steps": 15580, "total_steps": 15680, "loss": 0.24163453578948973, "lr": 1.0237067448193306e-09, "epoch": 1.9872448979591837, "percentage": 99.36, "elapsed_time": "2 days, 8:32:41", "remaining_time": "0:21:46", "throughput": 4646.49, "total_tokens": 945847360} {"current_steps": 15585, "total_steps": 15680, "loss": 0.24226274490356445, "lr": 9.248615280499362e-10, "epoch": 1.9878826530612246, "percentage": 99.39, "elapsed_time": "2 days, 8:33:37", "remaining_time": "0:20:41", "throughput": 4646.65, "total_tokens": 946141912} {"current_steps": 15590, "total_steps": 15680, "loss": 0.2418217182159424, "lr": 8.310332323169246e-10, "epoch": 1.9885204081632653, "percentage": 99.43, "elapsed_time": "2 days, 8:34:50", "remaining_time": "0:19:35", "throughput": 4646.48, "total_tokens": 946445056} {"current_steps": 15595, "total_steps": 15680, "loss": 0.25137481689453123, "lr": 7.422219517833062e-10, "epoch": 1.9891581632653061, "percentage": 99.46, "elapsed_time": "2 days, 8:36:01", "remaining_time": "0:18:30", "throughput": 4646.36, "total_tokens": 946746768} {"current_steps": 15600, "total_steps": 15680, "loss": 0.24022195339202881, "lr": 6.584277755772306e-10, "epoch": 1.989795918367347, "percentage": 99.49, "elapsed_time": "2 days, 8:37:01", "remaining_time": "0:17:25", "throughput": 4646.38, "total_tokens": 947033408} {"current_steps": 15605, "total_steps": 15680, "loss": 0.24291386604309081, "lr": 5.796507877919855e-10, "epoch": 1.9904336734693877, "percentage": 99.52, "elapsed_time": "2 days, 8:38:01", "remaining_time": "0:16:19", "throughput": 4646.49, "total_tokens": 947333432} {"current_steps": 15610, "total_steps": 15680, "loss": 0.25441684722900393, "lr": 5.058910674859973e-10, "epoch": 1.9910714285714286, "percentage": 99.55, "elapsed_time": "2 days, 8:39:07", "remaining_time": "0:15:14", "throughput": 4646.46, "total_tokens": 947631536} {"current_steps": 15615, "total_steps": 15680, "loss": 0.2432384490966797, "lr": 4.371486886822762e-10, "epoch": 1.9917091836734695, "percentage": 99.59, "elapsed_time": "2 days, 8:40:03", "remaining_time": "0:14:09", "throughput": 4646.71, "total_tokens": 947946016} {"current_steps": 15620, "total_steps": 15680, "loss": 0.2673120737075806, "lr": 3.7342372036841546e-10, "epoch": 1.9923469387755102, "percentage": 99.62, "elapsed_time": "2 days, 8:41:08", "remaining_time": "0:13:03", "throughput": 4646.74, "total_tokens": 948251504} {"current_steps": 15625, "total_steps": 15680, "loss": 0.26491403579711914, "lr": 3.147162264971471e-10, "epoch": 1.992984693877551, "percentage": 99.65, "elapsed_time": "2 days, 8:42:10", "remaining_time": "0:11:58", "throughput": 4646.82, "total_tokens": 948559176} {"current_steps": 15630, "total_steps": 15680, "loss": 0.23858168125152587, "lr": 2.610262659852314e-10, "epoch": 1.993622448979592, "percentage": 99.68, "elapsed_time": "2 days, 8:43:11", "remaining_time": "0:10:53", "throughput": 4646.98, "total_tokens": 948871280} {"current_steps": 15635, "total_steps": 15680, "loss": 0.25632877349853517, "lr": 2.123538927145674e-10, "epoch": 1.9942602040816326, "percentage": 99.71, "elapsed_time": "2 days, 8:44:20", "remaining_time": "0:09:47", "throughput": 4646.82, "total_tokens": 949161856} {"current_steps": 15640, "total_steps": 15680, "loss": 0.2401134490966797, "lr": 1.686991555310824e-10, "epoch": 1.9948979591836735, "percentage": 99.74, "elapsed_time": "2 days, 8:45:29", "remaining_time": "0:08:42", "throughput": 4646.69, "total_tokens": 949457536} {"current_steps": 15645, "total_steps": 15680, "loss": 0.24632782936096193, "lr": 1.3006209824584226e-10, "epoch": 1.9955357142857144, "percentage": 99.78, "elapsed_time": "2 days, 8:46:27", "remaining_time": "0:07:37", "throughput": 4646.87, "total_tokens": 949760728} {"current_steps": 15650, "total_steps": 15680, "loss": 0.24630413055419922, "lr": 9.6442759632831e-11, "epoch": 1.996173469387755, "percentage": 99.81, "elapsed_time": "2 days, 8:47:38", "remaining_time": "0:06:31", "throughput": 4646.78, "total_tokens": 950074048} {"current_steps": 15655, "total_steps": 15680, "loss": 0.22919554710388185, "lr": 6.784117343228147e-11, "epoch": 1.9968112244897958, "percentage": 99.84, "elapsed_time": "2 days, 8:48:31", "remaining_time": "0:05:26", "throughput": 4647.07, "total_tokens": 950380584} {"current_steps": 15660, "total_steps": 15680, "loss": 0.2392258644104004, "lr": 4.425736834789973e-11, "epoch": 1.9974489795918369, "percentage": 99.87, "elapsed_time": "2 days, 8:49:42", "remaining_time": "0:04:21", "throughput": 4646.88, "total_tokens": 950672704} {"current_steps": 15665, "total_steps": 15680, "loss": 0.2364060640335083, "lr": 2.5691368046865118e-11, "epoch": 1.9980867346938775, "percentage": 99.9, "elapsed_time": "2 days, 8:50:55", "remaining_time": "0:03:15", "throughput": 4646.73, "total_tokens": 950979656} {"current_steps": 15670, "total_steps": 15680, "loss": 0.24228816032409667, "lr": 1.214319116260576e-11, "epoch": 1.9987244897959182, "percentage": 99.94, "elapsed_time": "2 days, 8:51:58", "remaining_time": "0:02:10", "throughput": 4646.84, "total_tokens": 951292560} {"current_steps": 15675, "total_steps": 15680, "loss": 0.25652594566345216, "lr": 3.6128512903577105e-12, "epoch": 1.9993622448979593, "percentage": 99.97, "elapsed_time": "2 days, 8:53:06", "remaining_time": "0:01:05", "throughput": 4646.81, "total_tokens": 951600896} {"current_steps": 15680, "total_steps": 15680, "loss": 0.23354415893554686, "lr": 1.0035699216093265e-13, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2 days, 8:54:09", "remaining_time": "0:00:00", "throughput": 4646.76, "total_tokens": 951884320} {"current_steps": 15680, "total_steps": 15680, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2 days, 8:54:49", "remaining_time": "0:00:00", "throughput": 4645.83, "total_tokens": 951884320}