{"current_steps": 5, "total_steps": 40000, "loss": 0.3536, "lr": 4.999999876629946e-05, "epoch": 0.05555555555555555, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "7:12:04", "throughput": 429.5, "total_tokens": 1392} {"current_steps": 10, "total_steps": 40000, "loss": 0.1388, "lr": 4.999999375439123e-05, "epoch": 0.1111111111111111, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "5:47:10", "throughput": 537.53, "total_tokens": 2800} {"current_steps": 15, "total_steps": 40000, "loss": 0.247, "lr": 4.9999984887169785e-05, "epoch": 0.16666666666666666, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "5:17:27", "throughput": 591.15, "total_tokens": 4224} {"current_steps": 20, "total_steps": 40000, "loss": 0.2303, "lr": 4.9999972164636506e-05, "epoch": 0.2222222222222222, "percentage": 0.05, "elapsed_time": "0:00:09", "remaining_time": "5:02:43", "throughput": 621.6, "total_tokens": 5648} {"current_steps": 25, "total_steps": 40000, "loss": 0.0298, "lr": 4.999995558679334e-05, "epoch": 0.2777777777777778, "percentage": 0.06, "elapsed_time": "0:00:11", "remaining_time": "4:54:03", "throughput": 638.02, "total_tokens": 7040} {"current_steps": 30, "total_steps": 40000, "loss": 0.1076, "lr": 4.999993515364287e-05, "epoch": 0.3333333333333333, "percentage": 0.07, "elapsed_time": "0:00:12", "remaining_time": "4:48:00", "throughput": 650.11, "total_tokens": 8432} {"current_steps": 35, "total_steps": 40000, "loss": 0.1874, "lr": 4.999991086518822e-05, "epoch": 0.3888888888888889, "percentage": 0.09, "elapsed_time": "0:00:14", "remaining_time": "4:43:59", "throughput": 659.4, "total_tokens": 9840} {"current_steps": 40, "total_steps": 40000, "loss": 0.0114, "lr": 4.999988272143315e-05, "epoch": 0.4444444444444444, "percentage": 0.1, "elapsed_time": "0:00:16", "remaining_time": "4:41:08", "throughput": 663.29, "total_tokens": 11200} {"current_steps": 45, "total_steps": 40000, "loss": 0.4715, "lr": 4.999985072238199e-05, "epoch": 0.5, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:38:35", "throughput": 671.41, "total_tokens": 12640} {"current_steps": 50, "total_steps": 40000, "loss": 0.4279, "lr": 4.999981486803969e-05, "epoch": 0.5555555555555556, "percentage": 0.12, "elapsed_time": "0:00:20", "remaining_time": "4:36:38", "throughput": 676.99, "total_tokens": 14064} {"current_steps": 55, "total_steps": 40000, "loss": 0.0883, "lr": 4.999977515841176e-05, "epoch": 0.6111111111111112, "percentage": 0.14, "elapsed_time": "0:00:22", "remaining_time": "4:34:53", "throughput": 681.99, "total_tokens": 15488} {"current_steps": 60, "total_steps": 40000, "loss": 0.1077, "lr": 4.9999731593504344e-05, "epoch": 0.6666666666666666, "percentage": 0.15, "elapsed_time": "0:00:24", "remaining_time": "4:33:28", "throughput": 685.43, "total_tokens": 16896} {"current_steps": 65, "total_steps": 40000, "loss": 0.1558, "lr": 4.999968417332415e-05, "epoch": 0.7222222222222222, "percentage": 0.16, "elapsed_time": "0:00:26", "remaining_time": "4:32:19", "throughput": 689.46, "total_tokens": 18336} {"current_steps": 70, "total_steps": 40000, "loss": 0.0742, "lr": 4.999963289787848e-05, "epoch": 0.7777777777777778, "percentage": 0.18, "elapsed_time": "0:00:28", "remaining_time": "4:31:19", "throughput": 692.4, "total_tokens": 19760} {"current_steps": 75, "total_steps": 40000, "loss": 0.1122, "lr": 4.999957776717526e-05, "epoch": 0.8333333333333334, "percentage": 0.19, "elapsed_time": "0:00:30", "remaining_time": "4:30:32", "throughput": 693.16, "total_tokens": 21136} {"current_steps": 80, "total_steps": 40000, "loss": 0.2608, "lr": 4.9999518781222984e-05, "epoch": 0.8888888888888888, "percentage": 0.2, "elapsed_time": "0:00:32", "remaining_time": "4:29:41", "throughput": 695.71, "total_tokens": 22560} {"current_steps": 85, "total_steps": 40000, "loss": 0.0559, "lr": 4.9999455940030746e-05, "epoch": 0.9444444444444444, "percentage": 0.21, "elapsed_time": "0:00:34", "remaining_time": "4:28:55", "throughput": 696.59, "total_tokens": 23936} {"current_steps": 90, "total_steps": 40000, "loss": 0.2861, "lr": 4.999938924360824e-05, "epoch": 1.0, "percentage": 0.22, "elapsed_time": "0:00:36", "remaining_time": "4:29:10", "throughput": 694.56, "total_tokens": 25296} {"current_steps": 95, "total_steps": 40000, "loss": 0.0234, "lr": 4.999931869196575e-05, "epoch": 1.0555555555555556, "percentage": 0.24, "elapsed_time": "0:00:38", "remaining_time": "4:30:33", "throughput": 690.97, "total_tokens": 26704} {"current_steps": 100, "total_steps": 40000, "loss": 0.0059, "lr": 4.999924428511416e-05, "epoch": 1.1111111111111112, "percentage": 0.25, "elapsed_time": "0:00:40", "remaining_time": "4:29:56", "throughput": 691.76, "total_tokens": 28080} {"current_steps": 105, "total_steps": 40000, "loss": 0.0055, "lr": 4.999916602306494e-05, "epoch": 1.1666666666666667, "percentage": 0.26, "elapsed_time": "0:00:42", "remaining_time": "4:29:18", "throughput": 692.99, "total_tokens": 29472} {"current_steps": 110, "total_steps": 40000, "loss": 0.0002, "lr": 4.999908390583016e-05, "epoch": 1.2222222222222223, "percentage": 0.27, "elapsed_time": "0:00:44", "remaining_time": "4:28:44", "throughput": 694.49, "total_tokens": 30880} {"current_steps": 115, "total_steps": 40000, "loss": 0.0032, "lr": 4.999899793342247e-05, "epoch": 1.2777777777777777, "percentage": 0.29, "elapsed_time": "0:00:46", "remaining_time": "4:28:20", "throughput": 695.2, "total_tokens": 32272} {"current_steps": 120, "total_steps": 40000, "loss": 0.0001, "lr": 4.999890810585516e-05, "epoch": 1.3333333333333333, "percentage": 0.3, "elapsed_time": "0:00:48", "remaining_time": "4:27:56", "throughput": 695.24, "total_tokens": 33632} {"current_steps": 125, "total_steps": 40000, "loss": 0.0, "lr": 4.999881442314206e-05, "epoch": 1.3888888888888888, "percentage": 0.31, "elapsed_time": "0:00:50", "remaining_time": "4:27:30", "throughput": 697.05, "total_tokens": 35072} {"current_steps": 130, "total_steps": 40000, "loss": 0.049, "lr": 4.9998716885297617e-05, "epoch": 1.4444444444444444, "percentage": 0.33, "elapsed_time": "0:00:52", "remaining_time": "4:27:05", "throughput": 699.07, "total_tokens": 36528} {"current_steps": 135, "total_steps": 40000, "loss": 0.0001, "lr": 4.999861549233688e-05, "epoch": 1.5, "percentage": 0.34, "elapsed_time": "0:00:54", "remaining_time": "4:26:44", "throughput": 699.93, "total_tokens": 37936} {"current_steps": 140, "total_steps": 40000, "loss": 0.0001, "lr": 4.999851024427548e-05, "epoch": 1.5555555555555556, "percentage": 0.35, "elapsed_time": "0:00:56", "remaining_time": "4:26:25", "throughput": 700.48, "total_tokens": 39328} {"current_steps": 145, "total_steps": 40000, "loss": 0.1647, "lr": 4.999840114112965e-05, "epoch": 1.6111111111111112, "percentage": 0.36, "elapsed_time": "0:00:58", "remaining_time": "4:26:03", "throughput": 701.65, "total_tokens": 40752} {"current_steps": 150, "total_steps": 40000, "loss": 0.0839, "lr": 4.999828818291621e-05, "epoch": 1.6666666666666665, "percentage": 0.38, "elapsed_time": "0:01:00", "remaining_time": "4:25:47", "throughput": 701.54, "total_tokens": 42112} {"current_steps": 155, "total_steps": 40000, "loss": 0.0029, "lr": 4.999817136965259e-05, "epoch": 1.7222222222222223, "percentage": 0.39, "elapsed_time": "0:01:01", "remaining_time": "4:25:30", "throughput": 702.0, "total_tokens": 43504} {"current_steps": 160, "total_steps": 40000, "loss": 0.0006, "lr": 4.9998050701356794e-05, "epoch": 1.7777777777777777, "percentage": 0.4, "elapsed_time": "0:01:03", "remaining_time": "4:25:16", "throughput": 701.86, "total_tokens": 44864} {"current_steps": 165, "total_steps": 40000, "loss": 0.0036, "lr": 4.999792617804744e-05, "epoch": 1.8333333333333335, "percentage": 0.41, "elapsed_time": "0:01:05", "remaining_time": "4:25:00", "throughput": 701.86, "total_tokens": 46224} {"current_steps": 170, "total_steps": 40000, "loss": 0.0004, "lr": 4.9997797799743724e-05, "epoch": 1.8888888888888888, "percentage": 0.43, "elapsed_time": "0:01:07", "remaining_time": "4:24:44", "throughput": 701.86, "total_tokens": 47584} {"current_steps": 175, "total_steps": 40000, "loss": 0.0768, "lr": 4.999766556646545e-05, "epoch": 1.9444444444444444, "percentage": 0.44, "elapsed_time": "0:01:09", "remaining_time": "4:24:28", "throughput": 702.83, "total_tokens": 49008} {"current_steps": 180, "total_steps": 40000, "loss": 0.0416, "lr": 4.9997529478232996e-05, "epoch": 2.0, "percentage": 0.45, "elapsed_time": "0:01:11", "remaining_time": "4:24:49", "throughput": 701.9, "total_tokens": 50416} {"current_steps": 185, "total_steps": 40000, "loss": 0.0001, "lr": 4.9997389535067365e-05, "epoch": 2.0555555555555554, "percentage": 0.46, "elapsed_time": "0:01:14", "remaining_time": "4:25:32", "throughput": 700.25, "total_tokens": 51840} {"current_steps": 190, "total_steps": 40000, "loss": 0.045, "lr": 4.999724573699012e-05, "epoch": 2.111111111111111, "percentage": 0.47, "elapsed_time": "0:01:16", "remaining_time": "4:25:24", "throughput": 700.21, "total_tokens": 53216} {"current_steps": 195, "total_steps": 40000, "loss": 0.0001, "lr": 4.9997098084023457e-05, "epoch": 2.1666666666666665, "percentage": 0.49, "elapsed_time": "0:01:17", "remaining_time": "4:25:10", "throughput": 700.81, "total_tokens": 54624} {"current_steps": 200, "total_steps": 40000, "loss": 0.0001, "lr": 4.999694657619013e-05, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:01:19", "remaining_time": "4:24:55", "throughput": 701.88, "total_tokens": 56064} {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.11372174322605133, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:01:21", "remaining_time": "4:29:16", "throughput": 690.52, "total_tokens": 56064} {"current_steps": 205, "total_steps": 40000, "loss": 0.0012, "lr": 4.999679121351352e-05, "epoch": 2.2777777777777777, "percentage": 0.51, "elapsed_time": "0:01:24", "remaining_time": "4:32:46", "throughput": 681.66, "total_tokens": 57472} {"current_steps": 210, "total_steps": 40000, "loss": 0.0, "lr": 4.9996631996017565e-05, "epoch": 2.3333333333333335, "percentage": 0.53, "elapsed_time": "0:01:26", "remaining_time": "4:32:34", "throughput": 681.25, "total_tokens": 58800} {"current_steps": 215, "total_steps": 40000, "loss": 0.0001, "lr": 4.9996468923726835e-05, "epoch": 2.388888888888889, "percentage": 0.54, "elapsed_time": "0:01:28", "remaining_time": "4:32:20", "throughput": 681.3, "total_tokens": 60160} {"current_steps": 220, "total_steps": 40000, "loss": 0.0, "lr": 4.999630199666647e-05, "epoch": 2.4444444444444446, "percentage": 0.55, "elapsed_time": "0:01:30", "remaining_time": "4:32:04", "throughput": 681.42, "total_tokens": 61520} {"current_steps": 225, "total_steps": 40000, "loss": 0.0013, "lr": 4.999613121486222e-05, "epoch": 2.5, "percentage": 0.56, "elapsed_time": "0:01:32", "remaining_time": "4:31:43", "throughput": 682.52, "total_tokens": 62944} {"current_steps": 230, "total_steps": 40000, "loss": 0.0, "lr": 4.999595657834041e-05, "epoch": 2.5555555555555554, "percentage": 0.57, "elapsed_time": "0:01:34", "remaining_time": "4:31:22", "throughput": 683.24, "total_tokens": 64336} {"current_steps": 235, "total_steps": 40000, "loss": 0.0, "lr": 4.999577808712798e-05, "epoch": 2.611111111111111, "percentage": 0.59, "elapsed_time": "0:01:36", "remaining_time": "4:31:02", "throughput": 684.25, "total_tokens": 65760} {"current_steps": 240, "total_steps": 40000, "loss": 0.0, "lr": 4.999559574125244e-05, "epoch": 2.6666666666666665, "percentage": 0.6, "elapsed_time": "0:01:38", "remaining_time": "4:30:43", "throughput": 685.06, "total_tokens": 67168} {"current_steps": 245, "total_steps": 40000, "loss": 0.0, "lr": 4.9995409540741934e-05, "epoch": 2.7222222222222223, "percentage": 0.61, "elapsed_time": "0:01:39", "remaining_time": "4:30:23", "throughput": 686.05, "total_tokens": 68592} {"current_steps": 250, "total_steps": 40000, "loss": 0.0, "lr": 4.999521948562516e-05, "epoch": 2.7777777777777777, "percentage": 0.62, "elapsed_time": "0:01:41", "remaining_time": "4:30:08", "throughput": 686.66, "total_tokens": 70000} {"current_steps": 255, "total_steps": 40000, "loss": 0.0, "lr": 4.999502557593143e-05, "epoch": 2.8333333333333335, "percentage": 0.64, "elapsed_time": "0:01:43", "remaining_time": "4:29:54", "throughput": 687.56, "total_tokens": 71440} {"current_steps": 260, "total_steps": 40000, "loss": 0.0, "lr": 4.999482781169066e-05, "epoch": 2.888888888888889, "percentage": 0.65, "elapsed_time": "0:01:45", "remaining_time": "4:29:42", "throughput": 688.37, "total_tokens": 72880} {"current_steps": 265, "total_steps": 40000, "loss": 0.0, "lr": 4.9994626192933324e-05, "epoch": 2.9444444444444446, "percentage": 0.66, "elapsed_time": "0:01:47", "remaining_time": "4:29:25", "throughput": 689.35, "total_tokens": 74320} {"current_steps": 270, "total_steps": 40000, "loss": 0.0, "lr": 4.999442071969054e-05, "epoch": 3.0, "percentage": 0.68, "elapsed_time": "0:01:49", "remaining_time": "4:29:34", "throughput": 688.66, "total_tokens": 75696} {"current_steps": 275, "total_steps": 40000, "loss": 0.0, "lr": 4.999421139199397e-05, "epoch": 3.0555555555555554, "percentage": 0.69, "elapsed_time": "0:01:52", "remaining_time": "4:29:55", "throughput": 687.71, "total_tokens": 77104} {"current_steps": 280, "total_steps": 40000, "loss": 0.0, "lr": 4.999399820987592e-05, "epoch": 3.111111111111111, "percentage": 0.7, "elapsed_time": "0:01:54", "remaining_time": "4:29:41", "throughput": 688.84, "total_tokens": 78576} {"current_steps": 285, "total_steps": 40000, "loss": 0.0, "lr": 4.999378117336924e-05, "epoch": 3.1666666666666665, "percentage": 0.71, "elapsed_time": "0:01:56", "remaining_time": "4:29:27", "throughput": 689.4, "total_tokens": 79984} {"current_steps": 290, "total_steps": 40000, "loss": 0.0, "lr": 4.9993560282507415e-05, "epoch": 3.2222222222222223, "percentage": 0.73, "elapsed_time": "0:01:57", "remaining_time": "4:29:13", "throughput": 689.93, "total_tokens": 81392} {"current_steps": 295, "total_steps": 40000, "loss": 0.0, "lr": 4.9993335537324495e-05, "epoch": 3.2777777777777777, "percentage": 0.74, "elapsed_time": "0:01:59", "remaining_time": "4:29:01", "throughput": 690.01, "total_tokens": 82752} {"current_steps": 300, "total_steps": 40000, "loss": 0.0, "lr": 4.999310693785516e-05, "epoch": 3.3333333333333335, "percentage": 0.75, "elapsed_time": "0:02:01", "remaining_time": "4:28:48", "throughput": 690.65, "total_tokens": 84176} {"current_steps": 305, "total_steps": 40000, "loss": 0.0, "lr": 4.9992874484134653e-05, "epoch": 3.388888888888889, "percentage": 0.76, "elapsed_time": "0:02:03", "remaining_time": "4:28:36", "throughput": 691.12, "total_tokens": 85584} {"current_steps": 310, "total_steps": 40000, "loss": 0.0, "lr": 4.999263817619882e-05, "epoch": 3.4444444444444446, "percentage": 0.78, "elapsed_time": "0:02:05", "remaining_time": "4:28:24", "throughput": 691.48, "total_tokens": 86976} {"current_steps": 315, "total_steps": 40000, "loss": 0.0, "lr": 4.9992398014084105e-05, "epoch": 3.5, "percentage": 0.79, "elapsed_time": "0:02:07", "remaining_time": "4:28:12", "throughput": 691.56, "total_tokens": 88336} {"current_steps": 320, "total_steps": 40000, "loss": 0.0, "lr": 4.999215399782754e-05, "epoch": 3.5555555555555554, "percentage": 0.8, "elapsed_time": "0:02:09", "remaining_time": "4:28:00", "throughput": 692.02, "total_tokens": 89744} {"current_steps": 325, "total_steps": 40000, "loss": 0.0, "lr": 4.999190612746675e-05, "epoch": 3.611111111111111, "percentage": 0.81, "elapsed_time": "0:02:11", "remaining_time": "4:27:48", "throughput": 692.49, "total_tokens": 91152} {"current_steps": 330, "total_steps": 40000, "loss": 0.0, "lr": 4.999165440303998e-05, "epoch": 3.6666666666666665, "percentage": 0.83, "elapsed_time": "0:02:13", "remaining_time": "4:27:36", "throughput": 693.09, "total_tokens": 92576} {"current_steps": 335, "total_steps": 40000, "loss": 0.0, "lr": 4.999139882458603e-05, "epoch": 3.7222222222222223, "percentage": 0.84, "elapsed_time": "0:02:15", "remaining_time": "4:27:26", "throughput": 693.25, "total_tokens": 93952} {"current_steps": 340, "total_steps": 40000, "loss": 0.0, "lr": 4.9991139392144314e-05, "epoch": 3.7777777777777777, "percentage": 0.85, "elapsed_time": "0:02:17", "remaining_time": "4:27:14", "throughput": 693.84, "total_tokens": 95376} {"current_steps": 345, "total_steps": 40000, "loss": 0.0, "lr": 4.999087610575485e-05, "epoch": 3.8333333333333335, "percentage": 0.86, "elapsed_time": "0:02:19", "remaining_time": "4:27:02", "throughput": 694.42, "total_tokens": 96800} {"current_steps": 350, "total_steps": 40000, "loss": 0.0, "lr": 4.999060896545824e-05, "epoch": 3.888888888888889, "percentage": 0.88, "elapsed_time": "0:02:21", "remaining_time": "4:26:53", "throughput": 694.67, "total_tokens": 98192} {"current_steps": 355, "total_steps": 40000, "loss": 0.0, "lr": 4.999033797129568e-05, "epoch": 3.9444444444444446, "percentage": 0.89, "elapsed_time": "0:02:23", "remaining_time": "4:26:42", "throughput": 694.84, "total_tokens": 99568} {"current_steps": 360, "total_steps": 40000, "loss": 0.0, "lr": 4.999006312330894e-05, "epoch": 4.0, "percentage": 0.9, "elapsed_time": "0:02:25", "remaining_time": "4:26:50", "throughput": 694.11, "total_tokens": 100928} {"current_steps": 365, "total_steps": 40000, "loss": 0.0, "lr": 4.998978442154043e-05, "epoch": 4.055555555555555, "percentage": 0.91, "elapsed_time": "0:02:27", "remaining_time": "4:27:07", "throughput": 693.57, "total_tokens": 102368} {"current_steps": 370, "total_steps": 40000, "loss": 0.0, "lr": 4.9989501866033125e-05, "epoch": 4.111111111111111, "percentage": 0.92, "elapsed_time": "0:02:29", "remaining_time": "4:26:56", "throughput": 693.9, "total_tokens": 103760} {"current_steps": 375, "total_steps": 40000, "loss": 0.0, "lr": 4.998921545683059e-05, "epoch": 4.166666666666667, "percentage": 0.94, "elapsed_time": "0:02:31", "remaining_time": "4:26:48", "throughput": 693.87, "total_tokens": 105120} {"current_steps": 380, "total_steps": 40000, "loss": 0.0, "lr": 4.9988925193976996e-05, "epoch": 4.222222222222222, "percentage": 0.95, "elapsed_time": "0:02:33", "remaining_time": "4:26:38", "throughput": 694.13, "total_tokens": 106512} {"current_steps": 385, "total_steps": 40000, "loss": 0.0, "lr": 4.998863107751711e-05, "epoch": 4.277777777777778, "percentage": 0.96, "elapsed_time": "0:02:35", "remaining_time": "4:26:28", "throughput": 694.31, "total_tokens": 107888} {"current_steps": 390, "total_steps": 40000, "loss": 0.0, "lr": 4.998833310749629e-05, "epoch": 4.333333333333333, "percentage": 0.97, "elapsed_time": "0:02:37", "remaining_time": "4:26:18", "throughput": 694.81, "total_tokens": 109312} {"current_steps": 395, "total_steps": 40000, "loss": 0.0, "lr": 4.998803128396047e-05, "epoch": 4.388888888888889, "percentage": 0.99, "elapsed_time": "0:02:39", "remaining_time": "4:26:11", "throughput": 694.89, "total_tokens": 110688} {"current_steps": 400, "total_steps": 40000, "loss": 0.0, "lr": 4.9987725606956215e-05, "epoch": 4.444444444444445, "percentage": 1.0, "elapsed_time": "0:02:41", "remaining_time": "4:26:01", "throughput": 695.06, "total_tokens": 112064} {"current_steps": 400, "total_steps": 40000, "eval_loss": 0.15980732440948486, "epoch": 4.444444444444445, "percentage": 1.0, "elapsed_time": "0:02:42", "remaining_time": "4:28:11", "throughput": 689.46, "total_tokens": 112064} {"current_steps": 405, "total_steps": 40000, "loss": 0.0, "lr": 4.998741607653066e-05, "epoch": 4.5, "percentage": 1.01, "elapsed_time": "0:02:45", "remaining_time": "4:29:56", "throughput": 684.85, "total_tokens": 113456} {"current_steps": 410, "total_steps": 40000, "loss": 0.0, "lr": 4.9987102692731523e-05, "epoch": 4.555555555555555, "percentage": 1.03, "elapsed_time": "0:02:47", "remaining_time": "4:29:50", "throughput": 685.07, "total_tokens": 114864} {"current_steps": 415, "total_steps": 40000, "loss": 0.0, "lr": 4.9986785455607157e-05, "epoch": 4.611111111111111, "percentage": 1.04, "elapsed_time": "0:02:49", "remaining_time": "4:29:43", "throughput": 685.04, "total_tokens": 116224} {"current_steps": 420, "total_steps": 40000, "loss": 0.0, "lr": 4.9986464365206456e-05, "epoch": 4.666666666666667, "percentage": 1.05, "elapsed_time": "0:02:51", "remaining_time": "4:29:31", "throughput": 685.67, "total_tokens": 117664} {"current_steps": 425, "total_steps": 40000, "loss": 0.0, "lr": 4.9986139421578956e-05, "epoch": 4.722222222222222, "percentage": 1.06, "elapsed_time": "0:02:53", "remaining_time": "4:29:20", "throughput": 686.0, "total_tokens": 119056} {"current_steps": 430, "total_steps": 40000, "loss": 0.0, "lr": 4.998581062477477e-05, "epoch": 4.777777777777778, "percentage": 1.07, "elapsed_time": "0:02:55", "remaining_time": "4:29:10", "throughput": 686.47, "total_tokens": 120480} {"current_steps": 435, "total_steps": 40000, "loss": 0.0, "lr": 4.998547797484458e-05, "epoch": 4.833333333333333, "percentage": 1.09, "elapsed_time": "0:02:57", "remaining_time": "4:28:59", "throughput": 687.08, "total_tokens": 121920} {"current_steps": 440, "total_steps": 40000, "loss": 0.0, "lr": 4.9985141471839706e-05, "epoch": 4.888888888888889, "percentage": 1.1, "elapsed_time": "0:02:59", "remaining_time": "4:28:50", "throughput": 687.43, "total_tokens": 123328} {"current_steps": 445, "total_steps": 40000, "loss": 0.0, "lr": 4.998480111581203e-05, "epoch": 4.944444444444445, "percentage": 1.11, "elapsed_time": "0:03:01", "remaining_time": "4:28:40", "throughput": 687.59, "total_tokens": 124704} {"current_steps": 450, "total_steps": 40000, "loss": 0.0, "lr": 4.998445690681405e-05, "epoch": 5.0, "percentage": 1.12, "elapsed_time": "0:03:03", "remaining_time": "4:28:44", "throughput": 687.47, "total_tokens": 126128} {"current_steps": 455, "total_steps": 40000, "loss": 0.0, "lr": 4.9984108844898834e-05, "epoch": 5.055555555555555, "percentage": 1.14, "elapsed_time": "0:03:05", "remaining_time": "4:28:57", "throughput": 686.63, "total_tokens": 127488} {"current_steps": 460, "total_steps": 40000, "loss": 0.0, "lr": 4.9983756930120076e-05, "epoch": 5.111111111111111, "percentage": 1.15, "elapsed_time": "0:03:07", "remaining_time": "4:28:46", "throughput": 687.04, "total_tokens": 128896} {"current_steps": 465, "total_steps": 40000, "loss": 0.0, "lr": 4.9983401162532025e-05, "epoch": 5.166666666666667, "percentage": 1.16, "elapsed_time": "0:03:09", "remaining_time": "4:28:36", "throughput": 687.51, "total_tokens": 130320} {"current_steps": 470, "total_steps": 40000, "loss": 0.0, "lr": 4.998304154218955e-05, "epoch": 5.222222222222222, "percentage": 1.18, "elapsed_time": "0:03:11", "remaining_time": "4:28:26", "throughput": 687.6, "total_tokens": 131680} {"current_steps": 475, "total_steps": 40000, "loss": 0.0, "lr": 4.998267806914812e-05, "epoch": 5.277777777777778, "percentage": 1.19, "elapsed_time": "0:03:13", "remaining_time": "4:28:17", "throughput": 687.94, "total_tokens": 133088} {"current_steps": 480, "total_steps": 40000, "loss": 0.0, "lr": 4.998231074346378e-05, "epoch": 5.333333333333333, "percentage": 1.2, "elapsed_time": "0:03:15", "remaining_time": "4:28:09", "throughput": 688.09, "total_tokens": 134464} {"current_steps": 485, "total_steps": 40000, "loss": 0.0, "lr": 4.998193956519317e-05, "epoch": 5.388888888888889, "percentage": 1.21, "elapsed_time": "0:03:17", "remaining_time": "4:27:59", "throughput": 688.88, "total_tokens": 135952} {"current_steps": 490, "total_steps": 40000, "loss": 0.0, "lr": 4.9981564534393545e-05, "epoch": 5.444444444444445, "percentage": 1.23, "elapsed_time": "0:03:19", "remaining_time": "4:27:49", "throughput": 689.16, "total_tokens": 137344} {"current_steps": 495, "total_steps": 40000, "loss": 0.0, "lr": 4.998118565112272e-05, "epoch": 5.5, "percentage": 1.24, "elapsed_time": "0:03:21", "remaining_time": "4:27:40", "throughput": 689.35, "total_tokens": 138720} {"current_steps": 500, "total_steps": 40000, "loss": 0.0, "lr": 4.998080291543914e-05, "epoch": 5.555555555555555, "percentage": 1.25, "elapsed_time": "0:03:23", "remaining_time": "4:27:31", "throughput": 689.67, "total_tokens": 140128} {"current_steps": 505, "total_steps": 40000, "loss": 0.0, "lr": 4.9980416327401826e-05, "epoch": 5.611111111111111, "percentage": 1.26, "elapsed_time": "0:03:25", "remaining_time": "4:27:22", "throughput": 689.93, "total_tokens": 141520} {"current_steps": 510, "total_steps": 40000, "loss": 0.0, "lr": 4.998002588707038e-05, "epoch": 5.666666666666667, "percentage": 1.27, "elapsed_time": "0:03:27", "remaining_time": "4:27:13", "throughput": 690.35, "total_tokens": 142944} {"current_steps": 515, "total_steps": 40000, "loss": 0.0, "lr": 4.997963159450503e-05, "epoch": 5.722222222222222, "percentage": 1.29, "elapsed_time": "0:03:29", "remaining_time": "4:27:04", "throughput": 690.9, "total_tokens": 144400} {"current_steps": 520, "total_steps": 40000, "loss": 0.0, "lr": 4.9979233449766575e-05, "epoch": 5.777777777777778, "percentage": 1.3, "elapsed_time": "0:03:30", "remaining_time": "4:26:56", "throughput": 691.0, "total_tokens": 145776} {"current_steps": 525, "total_steps": 40000, "loss": 0.0, "lr": 4.997883145291641e-05, "epoch": 5.833333333333333, "percentage": 1.31, "elapsed_time": "0:03:32", "remaining_time": "4:26:48", "throughput": 691.14, "total_tokens": 147152} {"current_steps": 530, "total_steps": 40000, "loss": 0.0, "lr": 4.9978425604016536e-05, "epoch": 5.888888888888889, "percentage": 1.32, "elapsed_time": "0:03:34", "remaining_time": "4:26:41", "throughput": 691.33, "total_tokens": 148544} {"current_steps": 535, "total_steps": 40000, "loss": 0.0, "lr": 4.9978015903129536e-05, "epoch": 5.944444444444445, "percentage": 1.34, "elapsed_time": "0:03:36", "remaining_time": "4:26:33", "throughput": 691.4, "total_tokens": 149904} {"current_steps": 540, "total_steps": 40000, "loss": 0.0, "lr": 4.997760235031859e-05, "epoch": 6.0, "percentage": 1.35, "elapsed_time": "0:03:38", "remaining_time": "4:26:36", "throughput": 691.12, "total_tokens": 151296} {"current_steps": 545, "total_steps": 40000, "loss": 0.0, "lr": 4.9977184945647473e-05, "epoch": 6.055555555555555, "percentage": 1.36, "elapsed_time": "0:03:41", "remaining_time": "4:26:47", "throughput": 690.62, "total_tokens": 152704} {"current_steps": 550, "total_steps": 40000, "loss": 0.0, "lr": 4.997676368918055e-05, "epoch": 6.111111111111111, "percentage": 1.38, "elapsed_time": "0:03:43", "remaining_time": "4:26:38", "throughput": 690.92, "total_tokens": 154112} {"current_steps": 555, "total_steps": 40000, "loss": 0.0, "lr": 4.9976338580982794e-05, "epoch": 6.166666666666667, "percentage": 1.39, "elapsed_time": "0:03:45", "remaining_time": "4:26:31", "throughput": 691.12, "total_tokens": 155504} {"current_steps": 560, "total_steps": 40000, "loss": 0.0, "lr": 4.9975909621119755e-05, "epoch": 6.222222222222222, "percentage": 1.4, "elapsed_time": "0:03:46", "remaining_time": "4:26:23", "throughput": 691.46, "total_tokens": 156928} {"current_steps": 565, "total_steps": 40000, "loss": 0.0, "lr": 4.997547680965758e-05, "epoch": 6.277777777777778, "percentage": 1.41, "elapsed_time": "0:03:48", "remaining_time": "4:26:16", "throughput": 691.85, "total_tokens": 158368} {"current_steps": 570, "total_steps": 40000, "loss": 0.0, "lr": 4.997504014666302e-05, "epoch": 6.333333333333333, "percentage": 1.43, "elapsed_time": "0:03:50", "remaining_time": "4:26:08", "throughput": 692.13, "total_tokens": 159776} {"current_steps": 575, "total_steps": 40000, "loss": 0.0, "lr": 4.997459963220342e-05, "epoch": 6.388888888888889, "percentage": 1.44, "elapsed_time": "0:03:52", "remaining_time": "4:26:01", "throughput": 692.2, "total_tokens": 161136} {"current_steps": 580, "total_steps": 40000, "loss": 0.0, "lr": 4.997415526634671e-05, "epoch": 6.444444444444445, "percentage": 1.45, "elapsed_time": "0:03:54", "remaining_time": "4:25:53", "throughput": 692.42, "total_tokens": 162528} {"current_steps": 585, "total_steps": 40000, "loss": 0.0, "lr": 4.99737070491614e-05, "epoch": 6.5, "percentage": 1.46, "elapsed_time": "0:03:56", "remaining_time": "4:25:45", "throughput": 692.56, "total_tokens": 163904} {"current_steps": 590, "total_steps": 40000, "loss": 0.0, "lr": 4.997325498071663e-05, "epoch": 6.555555555555555, "percentage": 1.47, "elapsed_time": "0:03:58", "remaining_time": "4:25:37", "throughput": 692.84, "total_tokens": 165312} {"current_steps": 595, "total_steps": 40000, "loss": 0.0, "lr": 4.997279906108211e-05, "epoch": 6.611111111111111, "percentage": 1.49, "elapsed_time": "0:04:00", "remaining_time": "4:25:31", "throughput": 692.94, "total_tokens": 166688} {"current_steps": 600, "total_steps": 40000, "loss": 0.0, "lr": 4.9972339290328155e-05, "epoch": 6.666666666666667, "percentage": 1.5, "elapsed_time": "0:04:02", "remaining_time": "4:25:23", "throughput": 693.22, "total_tokens": 168096} {"current_steps": 600, "total_steps": 40000, "eval_loss": 0.16979970037937164, "epoch": 6.666666666666667, "percentage": 1.5, "elapsed_time": "0:04:03", "remaining_time": "4:26:49", "throughput": 689.47, "total_tokens": 168096} {"current_steps": 605, "total_steps": 40000, "loss": 0.0, "lr": 4.9971875668525646e-05, "epoch": 6.722222222222222, "percentage": 1.51, "elapsed_time": "0:04:06", "remaining_time": "4:28:00", "throughput": 686.33, "total_tokens": 169488} {"current_steps": 610, "total_steps": 40000, "loss": 0.0, "lr": 4.997140819574609e-05, "epoch": 6.777777777777778, "percentage": 1.52, "elapsed_time": "0:04:08", "remaining_time": "4:27:57", "throughput": 686.32, "total_tokens": 170880} {"current_steps": 615, "total_steps": 40000, "loss": 0.0, "lr": 4.997093687206159e-05, "epoch": 6.833333333333333, "percentage": 1.54, "elapsed_time": "0:04:10", "remaining_time": "4:27:49", "throughput": 686.48, "total_tokens": 172256} {"current_steps": 620, "total_steps": 40000, "loss": 0.0, "lr": 4.997046169754482e-05, "epoch": 6.888888888888889, "percentage": 1.55, "elapsed_time": "0:04:12", "remaining_time": "4:27:41", "throughput": 686.75, "total_tokens": 173664} {"current_steps": 625, "total_steps": 40000, "loss": 0.0, "lr": 4.996998267226905e-05, "epoch": 6.944444444444445, "percentage": 1.56, "elapsed_time": "0:04:14", "remaining_time": "4:27:34", "throughput": 686.89, "total_tokens": 175040} {"current_steps": 630, "total_steps": 40000, "loss": 0.0, "lr": 4.996949979630817e-05, "epoch": 7.0, "percentage": 1.57, "elapsed_time": "0:04:16", "remaining_time": "4:27:36", "throughput": 686.6, "total_tokens": 176416} {"current_steps": 635, "total_steps": 40000, "loss": 0.0, "lr": 4.996901306973663e-05, "epoch": 7.055555555555555, "percentage": 1.59, "elapsed_time": "0:04:19", "remaining_time": "4:27:44", "throughput": 686.28, "total_tokens": 177840} {"current_steps": 640, "total_steps": 40000, "loss": 0.0, "lr": 4.996852249262949e-05, "epoch": 7.111111111111111, "percentage": 1.6, "elapsed_time": "0:04:21", "remaining_time": "4:27:36", "throughput": 686.49, "total_tokens": 179232} {"current_steps": 645, "total_steps": 40000, "loss": 0.0, "lr": 4.996802806506241e-05, "epoch": 7.166666666666667, "percentage": 1.61, "elapsed_time": "0:04:23", "remaining_time": "4:27:28", "throughput": 686.65, "total_tokens": 180608} {"current_steps": 650, "total_steps": 40000, "loss": 0.0, "lr": 4.996752978711164e-05, "epoch": 7.222222222222222, "percentage": 1.62, "elapsed_time": "0:04:24", "remaining_time": "4:27:20", "throughput": 687.0, "total_tokens": 182032} {"current_steps": 655, "total_steps": 40000, "loss": 0.0, "lr": 4.996702765885401e-05, "epoch": 7.277777777777778, "percentage": 1.64, "elapsed_time": "0:04:26", "remaining_time": "4:27:12", "throughput": 687.21, "total_tokens": 183424} {"current_steps": 660, "total_steps": 40000, "loss": 0.0, "lr": 4.9966521680366964e-05, "epoch": 7.333333333333333, "percentage": 1.65, "elapsed_time": "0:04:28", "remaining_time": "4:27:05", "throughput": 687.4, "total_tokens": 184816} {"current_steps": 665, "total_steps": 40000, "loss": 0.0, "lr": 4.9966011851728524e-05, "epoch": 7.388888888888889, "percentage": 1.66, "elapsed_time": "0:04:30", "remaining_time": "4:26:59", "throughput": 687.6, "total_tokens": 186224} {"current_steps": 670, "total_steps": 40000, "loss": 0.0, "lr": 4.996549817301731e-05, "epoch": 7.444444444444445, "percentage": 1.68, "elapsed_time": "0:04:32", "remaining_time": "4:26:52", "throughput": 687.82, "total_tokens": 187616} {"current_steps": 675, "total_steps": 40000, "loss": 0.0, "lr": 4.9964980644312544e-05, "epoch": 7.5, "percentage": 1.69, "elapsed_time": "0:04:34", "remaining_time": "4:26:44", "throughput": 688.03, "total_tokens": 189008} {"current_steps": 680, "total_steps": 40000, "loss": 0.0, "lr": 4.996445926569403e-05, "epoch": 7.555555555555555, "percentage": 1.7, "elapsed_time": "0:04:36", "remaining_time": "4:26:36", "throughput": 688.29, "total_tokens": 190416} {"current_steps": 685, "total_steps": 40000, "loss": 0.0, "lr": 4.996393403724218e-05, "epoch": 7.611111111111111, "percentage": 1.71, "elapsed_time": "0:04:38", "remaining_time": "4:26:30", "throughput": 688.52, "total_tokens": 191824} {"current_steps": 690, "total_steps": 40000, "loss": 0.0, "lr": 4.9963404959037985e-05, "epoch": 7.666666666666667, "percentage": 1.73, "elapsed_time": "0:04:40", "remaining_time": "4:26:23", "throughput": 688.54, "total_tokens": 193168} {"current_steps": 695, "total_steps": 40000, "loss": 0.0, "lr": 4.996287203116303e-05, "epoch": 7.722222222222222, "percentage": 1.74, "elapsed_time": "0:04:42", "remaining_time": "4:26:15", "throughput": 688.85, "total_tokens": 194592} {"current_steps": 700, "total_steps": 40000, "loss": 0.0, "lr": 4.996233525369951e-05, "epoch": 7.777777777777778, "percentage": 1.75, "elapsed_time": "0:04:44", "remaining_time": "4:26:08", "throughput": 689.24, "total_tokens": 196032} {"current_steps": 705, "total_steps": 40000, "loss": 0.0, "lr": 4.99617946267302e-05, "epoch": 7.833333333333333, "percentage": 1.76, "elapsed_time": "0:04:46", "remaining_time": "4:26:01", "throughput": 689.58, "total_tokens": 197472} {"current_steps": 710, "total_steps": 40000, "loss": 0.0, "lr": 4.996125015033846e-05, "epoch": 7.888888888888889, "percentage": 1.77, "elapsed_time": "0:04:48", "remaining_time": "4:25:53", "throughput": 689.89, "total_tokens": 198896} {"current_steps": 715, "total_steps": 40000, "loss": 0.0, "lr": 4.996070182460827e-05, "epoch": 7.944444444444445, "percentage": 1.79, "elapsed_time": "0:04:50", "remaining_time": "4:25:46", "throughput": 690.03, "total_tokens": 200272} {"current_steps": 720, "total_steps": 40000, "loss": 0.0, "lr": 4.996014964962418e-05, "epoch": 8.0, "percentage": 1.8, "elapsed_time": "0:04:52", "remaining_time": "4:25:48", "throughput": 689.88, "total_tokens": 201680} {"current_steps": 725, "total_steps": 40000, "loss": 0.0, "lr": 4.9959593625471344e-05, "epoch": 8.055555555555555, "percentage": 1.81, "elapsed_time": "0:04:54", "remaining_time": "4:25:55", "throughput": 689.7, "total_tokens": 203136} {"current_steps": 730, "total_steps": 40000, "loss": 0.0, "lr": 4.995903375223552e-05, "epoch": 8.11111111111111, "percentage": 1.82, "elapsed_time": "0:04:56", "remaining_time": "4:25:49", "throughput": 689.74, "total_tokens": 204496} {"current_steps": 735, "total_steps": 40000, "loss": 0.0, "lr": 4.995847003000302e-05, "epoch": 8.166666666666666, "percentage": 1.84, "elapsed_time": "0:04:58", "remaining_time": "4:25:42", "throughput": 689.98, "total_tokens": 205904} {"current_steps": 740, "total_steps": 40000, "loss": 0.0, "lr": 4.9957902458860804e-05, "epoch": 8.222222222222221, "percentage": 1.85, "elapsed_time": "0:05:00", "remaining_time": "4:25:36", "throughput": 690.29, "total_tokens": 207344} {"current_steps": 745, "total_steps": 40000, "loss": 0.0, "lr": 4.995733103889639e-05, "epoch": 8.277777777777779, "percentage": 1.86, "elapsed_time": "0:05:02", "remaining_time": "4:25:29", "throughput": 690.23, "total_tokens": 208672} {"current_steps": 750, "total_steps": 40000, "loss": 0.0, "lr": 4.99567557701979e-05, "epoch": 8.333333333333334, "percentage": 1.88, "elapsed_time": "0:05:04", "remaining_time": "4:25:23", "throughput": 690.5, "total_tokens": 210096} {"current_steps": 755, "total_steps": 40000, "loss": 0.0, "lr": 4.995617665285403e-05, "epoch": 8.38888888888889, "percentage": 1.89, "elapsed_time": "0:05:06", "remaining_time": "4:25:16", "throughput": 690.67, "total_tokens": 211488} {"current_steps": 760, "total_steps": 40000, "loss": 0.0, "lr": 4.99555936869541e-05, "epoch": 8.444444444444445, "percentage": 1.9, "elapsed_time": "0:05:08", "remaining_time": "4:25:10", "throughput": 690.94, "total_tokens": 212912} {"current_steps": 765, "total_steps": 40000, "loss": 0.0, "lr": 4.995500687258803e-05, "epoch": 8.5, "percentage": 1.91, "elapsed_time": "0:05:10", "remaining_time": "4:25:03", "throughput": 691.12, "total_tokens": 214304} {"current_steps": 770, "total_steps": 40000, "loss": 0.0, "lr": 4.995441620984628e-05, "epoch": 8.555555555555555, "percentage": 1.93, "elapsed_time": "0:05:12", "remaining_time": "4:24:56", "throughput": 691.49, "total_tokens": 215760} {"current_steps": 775, "total_steps": 40000, "loss": 0.0, "lr": 4.995382169881996e-05, "epoch": 8.61111111111111, "percentage": 1.94, "elapsed_time": "0:05:13", "remaining_time": "4:24:50", "throughput": 691.61, "total_tokens": 217136} {"current_steps": 780, "total_steps": 40000, "loss": 0.0, "lr": 4.9953223339600755e-05, "epoch": 8.666666666666666, "percentage": 1.95, "elapsed_time": "0:05:15", "remaining_time": "4:24:45", "throughput": 691.65, "total_tokens": 218512} {"current_steps": 785, "total_steps": 40000, "loss": 0.0, "lr": 4.995262113228091e-05, "epoch": 8.722222222222221, "percentage": 1.96, "elapsed_time": "0:05:17", "remaining_time": "4:24:39", "throughput": 691.65, "total_tokens": 219856} {"current_steps": 790, "total_steps": 40000, "loss": 0.0, "lr": 4.995201507695332e-05, "epoch": 8.777777777777779, "percentage": 1.98, "elapsed_time": "0:05:19", "remaining_time": "4:24:32", "throughput": 691.92, "total_tokens": 221280} {"current_steps": 795, "total_steps": 40000, "loss": 0.0, "lr": 4.995140517371144e-05, "epoch": 8.833333333333334, "percentage": 1.99, "elapsed_time": "0:05:21", "remaining_time": "4:24:26", "throughput": 692.13, "total_tokens": 222688} {"current_steps": 800, "total_steps": 40000, "loss": 0.0, "lr": 4.995079142264932e-05, "epoch": 8.88888888888889, "percentage": 2.0, "elapsed_time": "0:05:23", "remaining_time": "4:24:21", "throughput": 692.15, "total_tokens": 224048} {"current_steps": 800, "total_steps": 40000, "eval_loss": 0.1828708052635193, "epoch": 8.88888888888889, "percentage": 2.0, "elapsed_time": "0:05:25", "remaining_time": "4:25:26", "throughput": 689.32, "total_tokens": 224048} {"current_steps": 805, "total_steps": 40000, "loss": 0.0, "lr": 4.995017382386162e-05, "epoch": 8.944444444444445, "percentage": 2.01, "elapsed_time": "0:05:28", "remaining_time": "4:26:20", "throughput": 686.91, "total_tokens": 225456} {"current_steps": 810, "total_steps": 40000, "loss": 0.0, "lr": 4.994955237744356e-05, "epoch": 9.0, "percentage": 2.02, "elapsed_time": "0:05:30", "remaining_time": "4:26:25", "throughput": 686.63, "total_tokens": 226864} {"current_steps": 815, "total_steps": 40000, "loss": 0.0, "lr": 4.994892708349101e-05, "epoch": 9.055555555555555, "percentage": 2.04, "elapsed_time": "0:05:32", "remaining_time": "4:26:32", "throughput": 686.24, "total_tokens": 228256} {"current_steps": 820, "total_steps": 40000, "loss": 0.0, "lr": 4.994829794210035e-05, "epoch": 9.11111111111111, "percentage": 2.05, "elapsed_time": "0:05:34", "remaining_time": "4:26:25", "throughput": 686.52, "total_tokens": 229680} {"current_steps": 825, "total_steps": 40000, "loss": 0.0, "lr": 4.994766495336864e-05, "epoch": 9.166666666666666, "percentage": 2.06, "elapsed_time": "0:05:36", "remaining_time": "4:26:18", "throughput": 686.55, "total_tokens": 231024} {"current_steps": 830, "total_steps": 40000, "loss": 0.0, "lr": 4.994702811739348e-05, "epoch": 9.222222222222221, "percentage": 2.08, "elapsed_time": "0:05:38", "remaining_time": "4:26:11", "throughput": 686.79, "total_tokens": 232432} {"current_steps": 835, "total_steps": 40000, "loss": 0.0, "lr": 4.994638743427308e-05, "epoch": 9.277777777777779, "percentage": 2.09, "elapsed_time": "0:05:40", "remaining_time": "4:26:04", "throughput": 687.01, "total_tokens": 233840} {"current_steps": 840, "total_steps": 40000, "loss": 0.0, "lr": 4.994574290410624e-05, "epoch": 9.333333333333334, "percentage": 2.1, "elapsed_time": "0:05:42", "remaining_time": "4:25:58", "throughput": 687.33, "total_tokens": 235280} {"current_steps": 845, "total_steps": 40000, "loss": 0.0, "lr": 4.9945094526992364e-05, "epoch": 9.38888888888889, "percentage": 2.11, "elapsed_time": "0:05:44", "remaining_time": "4:25:51", "throughput": 687.54, "total_tokens": 236688} {"current_steps": 850, "total_steps": 40000, "loss": 0.0, "lr": 4.994444230303142e-05, "epoch": 9.444444444444445, "percentage": 2.12, "elapsed_time": "0:05:46", "remaining_time": "4:25:46", "throughput": 687.67, "total_tokens": 238080} {"current_steps": 855, "total_steps": 40000, "loss": 0.0, "lr": 4.994378623232402e-05, "epoch": 9.5, "percentage": 2.14, "elapsed_time": "0:05:48", "remaining_time": "4:25:39", "throughput": 687.83, "total_tokens": 239472} {"current_steps": 860, "total_steps": 40000, "loss": 0.0, "lr": 4.99431263149713e-05, "epoch": 9.555555555555555, "percentage": 2.15, "elapsed_time": "0:05:50", "remaining_time": "4:25:33", "throughput": 688.07, "total_tokens": 240896} {"current_steps": 865, "total_steps": 40000, "loss": 0.0, "lr": 4.9942462551075056e-05, "epoch": 9.61111111111111, "percentage": 2.16, "elapsed_time": "0:05:52", "remaining_time": "4:25:27", "throughput": 688.18, "total_tokens": 242272} {"current_steps": 870, "total_steps": 40000, "loss": 0.0, "lr": 4.994179494073764e-05, "epoch": 9.666666666666666, "percentage": 2.17, "elapsed_time": "0:05:53", "remaining_time": "4:25:21", "throughput": 688.23, "total_tokens": 243632} {"current_steps": 875, "total_steps": 40000, "loss": 0.0, "lr": 4.9941123484062e-05, "epoch": 9.722222222222221, "percentage": 2.19, "elapsed_time": "0:05:55", "remaining_time": "4:25:15", "throughput": 688.35, "total_tokens": 245008} {"current_steps": 880, "total_steps": 40000, "loss": 0.0, "lr": 4.99404481811517e-05, "epoch": 9.777777777777779, "percentage": 2.2, "elapsed_time": "0:05:57", "remaining_time": "4:25:09", "throughput": 688.55, "total_tokens": 246416} {"current_steps": 885, "total_steps": 40000, "loss": 0.0, "lr": 4.9939769032110864e-05, "epoch": 9.833333333333334, "percentage": 2.21, "elapsed_time": "0:05:59", "remaining_time": "4:25:03", "throughput": 688.83, "total_tokens": 247856} {"current_steps": 890, "total_steps": 40000, "loss": 0.0, "lr": 4.993908603704423e-05, "epoch": 9.88888888888889, "percentage": 2.23, "elapsed_time": "0:06:01", "remaining_time": "4:24:58", "throughput": 688.86, "total_tokens": 249216} {"current_steps": 895, "total_steps": 40000, "loss": 0.0, "lr": 4.9938399196057126e-05, "epoch": 9.944444444444445, "percentage": 2.24, "elapsed_time": "0:06:03", "remaining_time": "4:24:52", "throughput": 689.09, "total_tokens": 250640} {"current_steps": 900, "total_steps": 40000, "loss": 0.0, "lr": 4.993770850925547e-05, "epoch": 10.0, "percentage": 2.25, "elapsed_time": "0:06:05", "remaining_time": "4:24:54", "throughput": 688.81, "total_tokens": 252000} {"current_steps": 905, "total_steps": 40000, "loss": 0.0, "lr": 4.993701397674577e-05, "epoch": 10.055555555555555, "percentage": 2.26, "elapsed_time": "0:06:08", "remaining_time": "4:24:59", "throughput": 688.6, "total_tokens": 253440} {"current_steps": 910, "total_steps": 40000, "loss": 0.0, "lr": 4.993631559863515e-05, "epoch": 10.11111111111111, "percentage": 2.27, "elapsed_time": "0:06:09", "remaining_time": "4:24:53", "throughput": 688.7, "total_tokens": 254816} {"current_steps": 915, "total_steps": 40000, "loss": 0.0, "lr": 4.9935613375031283e-05, "epoch": 10.166666666666666, "percentage": 2.29, "elapsed_time": "0:06:11", "remaining_time": "4:24:47", "throughput": 688.94, "total_tokens": 256240} {"current_steps": 920, "total_steps": 40000, "loss": 0.0, "lr": 4.993490730604248e-05, "epoch": 10.222222222222221, "percentage": 2.3, "elapsed_time": "0:06:13", "remaining_time": "4:24:41", "throughput": 689.17, "total_tokens": 257664} {"current_steps": 925, "total_steps": 40000, "loss": 0.0, "lr": 4.993419739177761e-05, "epoch": 10.277777777777779, "percentage": 2.31, "elapsed_time": "0:06:15", "remaining_time": "4:24:36", "throughput": 689.42, "total_tokens": 259104} {"current_steps": 930, "total_steps": 40000, "loss": 0.0, "lr": 4.9933483632346164e-05, "epoch": 10.333333333333334, "percentage": 2.33, "elapsed_time": "0:06:17", "remaining_time": "4:24:30", "throughput": 689.59, "total_tokens": 260512} {"current_steps": 935, "total_steps": 40000, "loss": 0.0, "lr": 4.993276602785821e-05, "epoch": 10.38888888888889, "percentage": 2.34, "elapsed_time": "0:06:19", "remaining_time": "4:24:24", "throughput": 689.9, "total_tokens": 261968} {"current_steps": 940, "total_steps": 40000, "loss": 0.0, "lr": 4.993204457842441e-05, "epoch": 10.444444444444445, "percentage": 2.35, "elapsed_time": "0:06:21", "remaining_time": "4:24:19", "throughput": 690.01, "total_tokens": 263360} {"current_steps": 945, "total_steps": 40000, "loss": 0.0, "lr": 4.993131928415602e-05, "epoch": 10.5, "percentage": 2.36, "elapsed_time": "0:06:23", "remaining_time": "4:24:14", "throughput": 690.26, "total_tokens": 264800} {"current_steps": 950, "total_steps": 40000, "loss": 0.0, "lr": 4.993059014516489e-05, "epoch": 10.555555555555555, "percentage": 2.38, "elapsed_time": "0:06:25", "remaining_time": "4:24:08", "throughput": 690.38, "total_tokens": 266192} {"current_steps": 955, "total_steps": 40000, "loss": 0.0, "lr": 4.9929857161563464e-05, "epoch": 10.61111111111111, "percentage": 2.39, "elapsed_time": "0:06:27", "remaining_time": "4:24:15", "throughput": 690.02, "total_tokens": 267600} {"current_steps": 960, "total_steps": 40000, "loss": 0.0, "lr": 4.992912033346477e-05, "epoch": 10.666666666666666, "percentage": 2.4, "elapsed_time": "0:06:29", "remaining_time": "4:24:10", "throughput": 690.05, "total_tokens": 268960} {"current_steps": 965, "total_steps": 40000, "loss": 0.0, "lr": 4.992837966098245e-05, "epoch": 10.722222222222221, "percentage": 2.41, "elapsed_time": "0:06:31", "remaining_time": "4:24:04", "throughput": 690.19, "total_tokens": 270352} {"current_steps": 970, "total_steps": 40000, "loss": 0.0, "lr": 4.992763514423071e-05, "epoch": 10.777777777777779, "percentage": 2.43, "elapsed_time": "0:06:33", "remaining_time": "4:23:59", "throughput": 690.29, "total_tokens": 271728} {"current_steps": 975, "total_steps": 40000, "loss": 0.0, "lr": 4.992688678332437e-05, "epoch": 10.833333333333334, "percentage": 2.44, "elapsed_time": "0:06:35", "remaining_time": "4:23:53", "throughput": 690.43, "total_tokens": 273120} {"current_steps": 980, "total_steps": 40000, "loss": 0.0, "lr": 4.992613457837884e-05, "epoch": 10.88888888888889, "percentage": 2.45, "elapsed_time": "0:06:37", "remaining_time": "4:23:47", "throughput": 690.51, "total_tokens": 274496} {"current_steps": 985, "total_steps": 40000, "loss": 0.0, "lr": 4.992537852951011e-05, "epoch": 10.944444444444445, "percentage": 2.46, "elapsed_time": "0:06:39", "remaining_time": "4:23:42", "throughput": 690.66, "total_tokens": 275888} {"current_steps": 990, "total_steps": 40000, "loss": 0.0, "lr": 4.9924618636834785e-05, "epoch": 11.0, "percentage": 2.48, "elapsed_time": "0:06:41", "remaining_time": "4:23:43", "throughput": 690.48, "total_tokens": 277280} {"current_steps": 995, "total_steps": 40000, "loss": 0.0, "lr": 4.9923854900470046e-05, "epoch": 11.055555555555555, "percentage": 2.49, "elapsed_time": "0:06:43", "remaining_time": "4:23:48", "throughput": 690.12, "total_tokens": 278656} {"current_steps": 1000, "total_steps": 40000, "loss": 0.0, "lr": 4.992308732053367e-05, "epoch": 11.11111111111111, "percentage": 2.5, "elapsed_time": "0:06:45", "remaining_time": "4:23:43", "throughput": 690.22, "total_tokens": 280048} {"current_steps": 1000, "total_steps": 40000, "eval_loss": 0.19405324757099152, "epoch": 11.11111111111111, "percentage": 2.5, "elapsed_time": "0:06:47", "remaining_time": "4:24:34", "throughput": 688.03, "total_tokens": 280048} {"current_steps": 1005, "total_steps": 40000, "loss": 0.0, "lr": 4.992231589714402e-05, "epoch": 11.166666666666666, "percentage": 2.51, "elapsed_time": "0:06:50", "remaining_time": "4:25:15", "throughput": 686.27, "total_tokens": 281488} {"current_steps": 1010, "total_steps": 40000, "loss": 0.0, "lr": 4.992154063042007e-05, "epoch": 11.222222222222221, "percentage": 2.53, "elapsed_time": "0:06:52", "remaining_time": "4:25:11", "throughput": 686.34, "total_tokens": 282880} {"current_steps": 1015, "total_steps": 40000, "loss": 0.0, "lr": 4.992076152048136e-05, "epoch": 11.277777777777779, "percentage": 2.54, "elapsed_time": "0:06:54", "remaining_time": "4:25:04", "throughput": 686.49, "total_tokens": 284272} {"current_steps": 1020, "total_steps": 40000, "loss": 0.0, "lr": 4.991997856744807e-05, "epoch": 11.333333333333334, "percentage": 2.55, "elapsed_time": "0:06:56", "remaining_time": "4:24:58", "throughput": 686.64, "total_tokens": 285664} {"current_steps": 1025, "total_steps": 40000, "loss": 0.0, "lr": 4.9919191771440905e-05, "epoch": 11.38888888888889, "percentage": 2.56, "elapsed_time": "0:06:57", "remaining_time": "4:24:53", "throughput": 686.73, "total_tokens": 287040} {"current_steps": 1030, "total_steps": 40000, "loss": 0.0, "lr": 4.991840113258122e-05, "epoch": 11.444444444444445, "percentage": 2.57, "elapsed_time": "0:06:59", "remaining_time": "4:24:47", "throughput": 686.78, "total_tokens": 288400} {"current_steps": 1035, "total_steps": 40000, "loss": 0.0, "lr": 4.9917606650990933e-05, "epoch": 11.5, "percentage": 2.59, "elapsed_time": "0:07:01", "remaining_time": "4:24:42", "throughput": 686.9, "total_tokens": 289792} {"current_steps": 1040, "total_steps": 40000, "loss": 0.0, "lr": 4.9916808326792566e-05, "epoch": 11.555555555555555, "percentage": 2.6, "elapsed_time": "0:07:03", "remaining_time": "4:24:37", "throughput": 687.0, "total_tokens": 291168} {"current_steps": 1045, "total_steps": 40000, "loss": 0.0, "lr": 4.9916006160109235e-05, "epoch": 11.61111111111111, "percentage": 2.61, "elapsed_time": "0:07:05", "remaining_time": "4:24:31", "throughput": 687.06, "total_tokens": 292528} {"current_steps": 1050, "total_steps": 40000, "loss": 0.0, "lr": 4.991520015106464e-05, "epoch": 11.666666666666666, "percentage": 2.62, "elapsed_time": "0:07:07", "remaining_time": "4:24:26", "throughput": 687.31, "total_tokens": 293968} {"current_steps": 1055, "total_steps": 40000, "loss": 0.0, "lr": 4.991439029978308e-05, "epoch": 11.722222222222221, "percentage": 2.64, "elapsed_time": "0:07:09", "remaining_time": "4:24:20", "throughput": 687.4, "total_tokens": 295344} {"current_steps": 1060, "total_steps": 40000, "loss": 0.0, "lr": 4.9913576606389434e-05, "epoch": 11.777777777777779, "percentage": 2.65, "elapsed_time": "0:07:11", "remaining_time": "4:24:14", "throughput": 687.54, "total_tokens": 296736} {"current_steps": 1065, "total_steps": 40000, "loss": 0.0, "lr": 4.991275907100919e-05, "epoch": 11.833333333333334, "percentage": 2.66, "elapsed_time": "0:07:13", "remaining_time": "4:24:09", "throughput": 687.68, "total_tokens": 298128} {"current_steps": 1070, "total_steps": 40000, "loss": 0.0, "lr": 4.9911937693768434e-05, "epoch": 11.88888888888889, "percentage": 2.67, "elapsed_time": "0:07:15", "remaining_time": "4:24:04", "throughput": 687.97, "total_tokens": 299600} {"current_steps": 1075, "total_steps": 40000, "loss": 0.0, "lr": 4.991111247479382e-05, "epoch": 11.944444444444445, "percentage": 2.69, "elapsed_time": "0:07:17", "remaining_time": "4:23:59", "throughput": 688.08, "total_tokens": 300992} {"current_steps": 1080, "total_steps": 40000, "loss": 0.0, "lr": 4.9910283414212605e-05, "epoch": 12.0, "percentage": 2.7, "elapsed_time": "0:07:19", "remaining_time": "4:23:59", "throughput": 687.89, "total_tokens": 302352} {"current_steps": 1085, "total_steps": 40000, "loss": 0.0, "lr": 4.990945051215265e-05, "epoch": 12.055555555555555, "percentage": 2.71, "elapsed_time": "0:07:21", "remaining_time": "4:24:03", "throughput": 687.66, "total_tokens": 303760} {"current_steps": 1090, "total_steps": 40000, "loss": 0.0, "lr": 4.99086137687424e-05, "epoch": 12.11111111111111, "percentage": 2.73, "elapsed_time": "0:07:23", "remaining_time": "4:23:57", "throughput": 687.72, "total_tokens": 305120} {"current_steps": 1095, "total_steps": 40000, "loss": 0.0, "lr": 4.9907773184110874e-05, "epoch": 12.166666666666666, "percentage": 2.74, "elapsed_time": "0:07:25", "remaining_time": "4:23:52", "throughput": 687.92, "total_tokens": 306544} {"current_steps": 1100, "total_steps": 40000, "loss": 0.0, "lr": 4.9906928758387715e-05, "epoch": 12.222222222222221, "percentage": 2.75, "elapsed_time": "0:07:27", "remaining_time": "4:23:46", "throughput": 688.13, "total_tokens": 307968} {"current_steps": 1105, "total_steps": 40000, "loss": 0.0, "lr": 4.9906080491703146e-05, "epoch": 12.277777777777779, "percentage": 2.76, "elapsed_time": "0:07:29", "remaining_time": "4:23:41", "throughput": 688.26, "total_tokens": 309360} {"current_steps": 1110, "total_steps": 40000, "loss": 0.0, "lr": 4.990522838418797e-05, "epoch": 12.333333333333334, "percentage": 2.77, "elapsed_time": "0:07:31", "remaining_time": "4:23:36", "throughput": 688.4, "total_tokens": 310768} {"current_steps": 1115, "total_steps": 40000, "loss": 0.0, "lr": 4.9904372435973604e-05, "epoch": 12.38888888888889, "percentage": 2.79, "elapsed_time": "0:07:33", "remaining_time": "4:23:31", "throughput": 688.51, "total_tokens": 312160} {"current_steps": 1120, "total_steps": 40000, "loss": 0.0, "lr": 4.990351264719203e-05, "epoch": 12.444444444444445, "percentage": 2.8, "elapsed_time": "0:07:35", "remaining_time": "4:23:26", "throughput": 688.74, "total_tokens": 313600} {"current_steps": 1125, "total_steps": 40000, "loss": 0.0, "lr": 4.990264901797586e-05, "epoch": 12.5, "percentage": 2.81, "elapsed_time": "0:07:37", "remaining_time": "4:23:20", "throughput": 688.83, "total_tokens": 314976} {"current_steps": 1130, "total_steps": 40000, "loss": 0.0, "lr": 4.990178154845826e-05, "epoch": 12.555555555555555, "percentage": 2.83, "elapsed_time": "0:07:39", "remaining_time": "4:23:15", "throughput": 688.99, "total_tokens": 316384} {"current_steps": 1135, "total_steps": 40000, "loss": 0.0, "lr": 4.9900910238773014e-05, "epoch": 12.61111111111111, "percentage": 2.84, "elapsed_time": "0:07:41", "remaining_time": "4:23:10", "throughput": 689.1, "total_tokens": 317776} {"current_steps": 1140, "total_steps": 40000, "loss": 0.0, "lr": 4.990003508905448e-05, "epoch": 12.666666666666666, "percentage": 2.85, "elapsed_time": "0:07:43", "remaining_time": "4:23:05", "throughput": 689.15, "total_tokens": 319136} {"current_steps": 1145, "total_steps": 40000, "loss": 0.0, "lr": 4.989915609943763e-05, "epoch": 12.722222222222221, "percentage": 2.86, "elapsed_time": "0:07:45", "remaining_time": "4:23:00", "throughput": 689.29, "total_tokens": 320544} {"current_steps": 1150, "total_steps": 40000, "loss": 0.0, "lr": 4.9898273270058e-05, "epoch": 12.777777777777779, "percentage": 2.88, "elapsed_time": "0:07:46", "remaining_time": "4:22:55", "throughput": 689.41, "total_tokens": 321936} {"current_steps": 1155, "total_steps": 40000, "loss": 0.0, "lr": 4.989738660105174e-05, "epoch": 12.833333333333334, "percentage": 2.89, "elapsed_time": "0:07:48", "remaining_time": "4:22:50", "throughput": 689.57, "total_tokens": 323344} {"current_steps": 1160, "total_steps": 40000, "loss": 0.0, "lr": 4.989649609255559e-05, "epoch": 12.88888888888889, "percentage": 2.9, "elapsed_time": "0:07:50", "remaining_time": "4:22:45", "throughput": 689.67, "total_tokens": 324736} {"current_steps": 1165, "total_steps": 40000, "loss": 0.0, "lr": 4.989560174470687e-05, "epoch": 12.944444444444445, "percentage": 2.91, "elapsed_time": "0:07:52", "remaining_time": "4:22:40", "throughput": 689.89, "total_tokens": 326176} {"current_steps": 1170, "total_steps": 40000, "loss": 0.0, "lr": 4.989470355764351e-05, "epoch": 13.0, "percentage": 2.93, "elapsed_time": "0:07:54", "remaining_time": "4:22:40", "throughput": 689.8, "total_tokens": 327584} {"current_steps": 1175, "total_steps": 40000, "loss": 0.0, "lr": 4.9893801531504e-05, "epoch": 13.055555555555555, "percentage": 2.94, "elapsed_time": "0:07:57", "remaining_time": "4:22:44", "throughput": 689.56, "total_tokens": 328992} {"current_steps": 1180, "total_steps": 40000, "loss": 0.0, "lr": 4.9892895666427475e-05, "epoch": 13.11111111111111, "percentage": 2.95, "elapsed_time": "0:07:59", "remaining_time": "4:22:39", "throughput": 689.68, "total_tokens": 330384} {"current_steps": 1185, "total_steps": 40000, "loss": 0.0, "lr": 4.9891985962553606e-05, "epoch": 13.166666666666666, "percentage": 2.96, "elapsed_time": "0:08:00", "remaining_time": "4:22:35", "throughput": 689.84, "total_tokens": 331808} {"current_steps": 1190, "total_steps": 40000, "loss": 0.0, "lr": 4.989107242002269e-05, "epoch": 13.222222222222221, "percentage": 2.97, "elapsed_time": "0:08:02", "remaining_time": "4:22:30", "throughput": 689.92, "total_tokens": 333184} {"current_steps": 1195, "total_steps": 40000, "loss": 0.0, "lr": 4.989015503897561e-05, "epoch": 13.277777777777779, "percentage": 2.99, "elapsed_time": "0:08:04", "remaining_time": "4:22:25", "throughput": 690.16, "total_tokens": 334640} {"current_steps": 1200, "total_steps": 40000, "loss": 0.0, "lr": 4.988923381955383e-05, "epoch": 13.333333333333334, "percentage": 3.0, "elapsed_time": "0:08:06", "remaining_time": "4:22:20", "throughput": 690.26, "total_tokens": 336032} {"current_steps": 1200, "total_steps": 40000, "eval_loss": 0.18756745755672455, "epoch": 13.333333333333334, "percentage": 3.0, "elapsed_time": "0:08:08", "remaining_time": "4:23:03", "throughput": 688.39, "total_tokens": 336032} {"current_steps": 1205, "total_steps": 40000, "loss": 0.0, "lr": 4.988830876189942e-05, "epoch": 13.38888888888889, "percentage": 3.01, "elapsed_time": "0:08:11", "remaining_time": "4:23:37", "throughput": 686.82, "total_tokens": 337440} {"current_steps": 1210, "total_steps": 40000, "loss": 0.0, "lr": 4.988737986615503e-05, "epoch": 13.444444444444445, "percentage": 3.02, "elapsed_time": "0:08:13", "remaining_time": "4:23:35", "throughput": 686.81, "total_tokens": 338832} {"current_steps": 1215, "total_steps": 40000, "loss": 0.0, "lr": 4.988644713246391e-05, "epoch": 13.5, "percentage": 3.04, "elapsed_time": "0:08:15", "remaining_time": "4:23:30", "throughput": 686.9, "total_tokens": 340224} {"current_steps": 1220, "total_steps": 40000, "loss": 0.0, "lr": 4.988551056096991e-05, "epoch": 13.555555555555555, "percentage": 3.05, "elapsed_time": "0:08:17", "remaining_time": "4:23:26", "throughput": 686.94, "total_tokens": 341584} {"current_steps": 1225, "total_steps": 40000, "loss": 0.0, "lr": 4.988457015181743e-05, "epoch": 13.61111111111111, "percentage": 3.06, "elapsed_time": "0:08:19", "remaining_time": "4:23:21", "throughput": 687.0, "total_tokens": 342960} {"current_steps": 1230, "total_steps": 40000, "loss": 0.0, "lr": 4.988362590515153e-05, "epoch": 13.666666666666666, "percentage": 3.08, "elapsed_time": "0:08:21", "remaining_time": "4:23:16", "throughput": 687.22, "total_tokens": 344400} {"current_steps": 1235, "total_steps": 40000, "loss": 0.0, "lr": 4.9882677821117805e-05, "epoch": 13.722222222222221, "percentage": 3.09, "elapsed_time": "0:08:23", "remaining_time": "4:23:11", "throughput": 687.41, "total_tokens": 345840} {"current_steps": 1240, "total_steps": 40000, "loss": 0.0, "lr": 4.988172589986246e-05, "epoch": 13.777777777777779, "percentage": 3.1, "elapsed_time": "0:08:25", "remaining_time": "4:23:07", "throughput": 687.57, "total_tokens": 347264} {"current_steps": 1245, "total_steps": 40000, "loss": 0.0, "lr": 4.9880770141532304e-05, "epoch": 13.833333333333334, "percentage": 3.11, "elapsed_time": "0:08:26", "remaining_time": "4:23:02", "throughput": 687.75, "total_tokens": 348688} {"current_steps": 1250, "total_steps": 40000, "loss": 0.0, "lr": 4.987981054627472e-05, "epoch": 13.88888888888889, "percentage": 3.12, "elapsed_time": "0:08:28", "remaining_time": "4:22:57", "throughput": 687.8, "total_tokens": 350048} {"current_steps": 1255, "total_steps": 40000, "loss": 0.0, "lr": 4.987884711423769e-05, "epoch": 13.944444444444445, "percentage": 3.14, "elapsed_time": "0:08:30", "remaining_time": "4:22:52", "throughput": 687.89, "total_tokens": 351440} {"current_steps": 1260, "total_steps": 40000, "loss": 0.0, "lr": 4.9877879845569784e-05, "epoch": 14.0, "percentage": 3.15, "elapsed_time": "0:08:33", "remaining_time": "4:22:52", "throughput": 687.81, "total_tokens": 352848} {"current_steps": 1265, "total_steps": 40000, "loss": 0.0, "lr": 4.9876908740420175e-05, "epoch": 14.055555555555555, "percentage": 3.16, "elapsed_time": "0:08:35", "remaining_time": "4:22:55", "throughput": 687.6, "total_tokens": 354256} {"current_steps": 1270, "total_steps": 40000, "loss": 0.0, "lr": 4.987593379893861e-05, "epoch": 14.11111111111111, "percentage": 3.17, "elapsed_time": "0:08:37", "remaining_time": "4:22:51", "throughput": 687.77, "total_tokens": 355680} {"current_steps": 1275, "total_steps": 40000, "loss": 0.0, "lr": 4.987495502127545e-05, "epoch": 14.166666666666666, "percentage": 3.19, "elapsed_time": "0:08:39", "remaining_time": "4:22:46", "throughput": 687.88, "total_tokens": 357072} {"current_steps": 1280, "total_steps": 40000, "loss": 0.0, "lr": 4.987397240758162e-05, "epoch": 14.222222222222221, "percentage": 3.2, "elapsed_time": "0:08:41", "remaining_time": "4:22:41", "throughput": 688.01, "total_tokens": 358480} {"current_steps": 1285, "total_steps": 40000, "loss": 0.0, "lr": 4.9872985958008664e-05, "epoch": 14.277777777777779, "percentage": 3.21, "elapsed_time": "0:08:42", "remaining_time": "4:22:36", "throughput": 688.21, "total_tokens": 359920} {"current_steps": 1290, "total_steps": 40000, "loss": 0.0, "lr": 4.987199567270871e-05, "epoch": 14.333333333333334, "percentage": 3.23, "elapsed_time": "0:08:44", "remaining_time": "4:22:31", "throughput": 688.4, "total_tokens": 361360} {"current_steps": 1295, "total_steps": 40000, "loss": 0.0, "lr": 4.9871001551834444e-05, "epoch": 14.38888888888889, "percentage": 3.24, "elapsed_time": "0:08:46", "remaining_time": "4:22:27", "throughput": 688.58, "total_tokens": 362800} {"current_steps": 1300, "total_steps": 40000, "loss": 0.0, "lr": 4.98700035955392e-05, "epoch": 14.444444444444445, "percentage": 3.25, "elapsed_time": "0:08:48", "remaining_time": "4:22:22", "throughput": 688.62, "total_tokens": 364160} {"current_steps": 1305, "total_steps": 40000, "loss": 0.0, "lr": 4.986900180397686e-05, "epoch": 14.5, "percentage": 3.26, "elapsed_time": "0:08:50", "remaining_time": "4:22:18", "throughput": 688.63, "total_tokens": 365504} {"current_steps": 1310, "total_steps": 40000, "loss": 0.0, "lr": 4.9867996177301926e-05, "epoch": 14.555555555555555, "percentage": 3.28, "elapsed_time": "0:08:52", "remaining_time": "4:22:13", "throughput": 688.67, "total_tokens": 366864} {"current_steps": 1315, "total_steps": 40000, "loss": 0.0, "lr": 4.9866986715669464e-05, "epoch": 14.61111111111111, "percentage": 3.29, "elapsed_time": "0:08:54", "remaining_time": "4:22:08", "throughput": 688.81, "total_tokens": 368272} {"current_steps": 1320, "total_steps": 40000, "loss": 0.0, "lr": 4.9865973419235155e-05, "epoch": 14.666666666666666, "percentage": 3.3, "elapsed_time": "0:08:56", "remaining_time": "4:22:03", "throughput": 688.93, "total_tokens": 369680} {"current_steps": 1325, "total_steps": 40000, "loss": 0.0, "lr": 4.986495628815526e-05, "epoch": 14.722222222222221, "percentage": 3.31, "elapsed_time": "0:08:58", "remaining_time": "4:21:59", "throughput": 688.99, "total_tokens": 371056} {"current_steps": 1330, "total_steps": 40000, "loss": 0.0, "lr": 4.986393532258663e-05, "epoch": 14.777777777777779, "percentage": 3.33, "elapsed_time": "0:09:00", "remaining_time": "4:21:55", "throughput": 689.07, "total_tokens": 372448} {"current_steps": 1335, "total_steps": 40000, "loss": 0.0, "lr": 4.986291052268671e-05, "epoch": 14.833333333333334, "percentage": 3.34, "elapsed_time": "0:09:02", "remaining_time": "4:21:50", "throughput": 689.14, "total_tokens": 373824} {"current_steps": 1340, "total_steps": 40000, "loss": 0.0, "lr": 4.986188188861355e-05, "epoch": 14.88888888888889, "percentage": 3.35, "elapsed_time": "0:09:04", "remaining_time": "4:21:45", "throughput": 689.28, "total_tokens": 375232} {"current_steps": 1345, "total_steps": 40000, "loss": 0.0, "lr": 4.9860849420525766e-05, "epoch": 14.944444444444445, "percentage": 3.36, "elapsed_time": "0:09:06", "remaining_time": "4:21:41", "throughput": 689.34, "total_tokens": 376608} {"current_steps": 1350, "total_steps": 40000, "loss": 0.0, "lr": 4.9859813118582575e-05, "epoch": 15.0, "percentage": 3.38, "elapsed_time": "0:09:08", "remaining_time": "4:21:41", "throughput": 689.25, "total_tokens": 378016} {"current_steps": 1355, "total_steps": 40000, "loss": 0.0, "lr": 4.98587729829438e-05, "epoch": 15.055555555555555, "percentage": 3.39, "elapsed_time": "0:09:10", "remaining_time": "4:21:44", "throughput": 689.09, "total_tokens": 379440} {"current_steps": 1360, "total_steps": 40000, "loss": 0.0, "lr": 4.985772901376983e-05, "epoch": 15.11111111111111, "percentage": 3.4, "elapsed_time": "0:09:12", "remaining_time": "4:21:39", "throughput": 689.25, "total_tokens": 380864} {"current_steps": 1365, "total_steps": 40000, "loss": 0.0, "lr": 4.9856681211221666e-05, "epoch": 15.166666666666666, "percentage": 3.41, "elapsed_time": "0:09:14", "remaining_time": "4:21:35", "throughput": 689.3, "total_tokens": 382240} {"current_steps": 1370, "total_steps": 40000, "loss": 0.0, "lr": 4.985562957546089e-05, "epoch": 15.222222222222221, "percentage": 3.43, "elapsed_time": "0:09:16", "remaining_time": "4:21:31", "throughput": 689.37, "total_tokens": 383632} {"current_steps": 1375, "total_steps": 40000, "loss": 0.0, "lr": 4.9854574106649686e-05, "epoch": 15.277777777777779, "percentage": 3.44, "elapsed_time": "0:09:18", "remaining_time": "4:21:27", "throughput": 689.38, "total_tokens": 384976} {"current_steps": 1380, "total_steps": 40000, "loss": 0.0, "lr": 4.985351480495081e-05, "epoch": 15.333333333333334, "percentage": 3.45, "elapsed_time": "0:09:20", "remaining_time": "4:21:22", "throughput": 689.5, "total_tokens": 386384} {"current_steps": 1385, "total_steps": 40000, "loss": 0.0, "lr": 4.985245167052762e-05, "epoch": 15.38888888888889, "percentage": 3.46, "elapsed_time": "0:09:22", "remaining_time": "4:21:18", "throughput": 689.65, "total_tokens": 387808} {"current_steps": 1390, "total_steps": 40000, "loss": 0.0, "lr": 4.9851384703544066e-05, "epoch": 15.444444444444445, "percentage": 3.48, "elapsed_time": "0:09:24", "remaining_time": "4:21:13", "throughput": 689.72, "total_tokens": 389184} {"current_steps": 1395, "total_steps": 40000, "loss": 0.0, "lr": 4.985031390416469e-05, "epoch": 15.5, "percentage": 3.49, "elapsed_time": "0:09:26", "remaining_time": "4:21:08", "throughput": 689.79, "total_tokens": 390560} {"current_steps": 1400, "total_steps": 40000, "loss": 0.0, "lr": 4.984923927255461e-05, "epoch": 15.555555555555555, "percentage": 3.5, "elapsed_time": "0:09:28", "remaining_time": "4:21:04", "throughput": 690.03, "total_tokens": 392032} {"current_steps": 1400, "total_steps": 40000, "eval_loss": 0.17438191175460815, "epoch": 15.555555555555555, "percentage": 3.5, "elapsed_time": "0:09:29", "remaining_time": "4:21:40", "throughput": 688.46, "total_tokens": 392032} {"current_steps": 1405, "total_steps": 40000, "loss": 0.0, "lr": 4.984816080887958e-05, "epoch": 15.61111111111111, "percentage": 3.51, "elapsed_time": "0:09:32", "remaining_time": "4:22:09", "throughput": 687.13, "total_tokens": 393456} {"current_steps": 1410, "total_steps": 40000, "loss": 0.0, "lr": 4.9847078513305875e-05, "epoch": 15.666666666666666, "percentage": 3.52, "elapsed_time": "0:09:34", "remaining_time": "4:22:07", "throughput": 687.18, "total_tokens": 394880} {"current_steps": 1415, "total_steps": 40000, "loss": 0.0, "lr": 4.984599238600043e-05, "epoch": 15.722222222222221, "percentage": 3.54, "elapsed_time": "0:09:36", "remaining_time": "4:22:02", "throughput": 687.27, "total_tokens": 396272} {"current_steps": 1420, "total_steps": 40000, "loss": 0.0, "lr": 4.9844902427130716e-05, "epoch": 15.777777777777779, "percentage": 3.55, "elapsed_time": "0:09:38", "remaining_time": "4:21:58", "throughput": 687.26, "total_tokens": 397616} {"current_steps": 1425, "total_steps": 40000, "loss": 0.0, "lr": 4.984380863686482e-05, "epoch": 15.833333333333334, "percentage": 3.56, "elapsed_time": "0:09:40", "remaining_time": "4:21:54", "throughput": 687.39, "total_tokens": 399024} {"current_steps": 1430, "total_steps": 40000, "loss": 0.0, "lr": 4.984271101537143e-05, "epoch": 15.88888888888889, "percentage": 3.57, "elapsed_time": "0:09:42", "remaining_time": "4:21:49", "throughput": 687.52, "total_tokens": 400432} {"current_steps": 1435, "total_steps": 40000, "loss": 0.0, "lr": 4.9841609562819816e-05, "epoch": 15.944444444444445, "percentage": 3.59, "elapsed_time": "0:09:44", "remaining_time": "4:21:44", "throughput": 687.56, "total_tokens": 401792} {"current_steps": 1440, "total_steps": 40000, "loss": 0.0, "lr": 4.984050427937983e-05, "epoch": 16.0, "percentage": 3.6, "elapsed_time": "0:09:46", "remaining_time": "4:21:45", "throughput": 687.47, "total_tokens": 403200} {"current_steps": 1445, "total_steps": 40000, "loss": 0.0, "lr": 4.983939516522191e-05, "epoch": 16.055555555555557, "percentage": 3.61, "elapsed_time": "0:09:48", "remaining_time": "4:21:47", "throughput": 687.32, "total_tokens": 404624} {"current_steps": 1450, "total_steps": 40000, "loss": 0.0, "lr": 4.983828222051711e-05, "epoch": 16.11111111111111, "percentage": 3.62, "elapsed_time": "0:09:50", "remaining_time": "4:21:43", "throughput": 687.35, "total_tokens": 405984} {"current_steps": 1455, "total_steps": 40000, "loss": 0.0, "lr": 4.983716544543705e-05, "epoch": 16.166666666666668, "percentage": 3.64, "elapsed_time": "0:09:52", "remaining_time": "4:21:38", "throughput": 687.4, "total_tokens": 407344} {"current_steps": 1460, "total_steps": 40000, "loss": 0.0, "lr": 4.983604484015395e-05, "epoch": 16.22222222222222, "percentage": 3.65, "elapsed_time": "0:09:54", "remaining_time": "4:21:33", "throughput": 687.55, "total_tokens": 408768} {"current_steps": 1465, "total_steps": 40000, "loss": 0.0, "lr": 4.983492040484064e-05, "epoch": 16.27777777777778, "percentage": 3.66, "elapsed_time": "0:09:56", "remaining_time": "4:21:29", "throughput": 687.64, "total_tokens": 410160} {"current_steps": 1470, "total_steps": 40000, "loss": 0.0, "lr": 4.98337921396705e-05, "epoch": 16.333333333333332, "percentage": 3.67, "elapsed_time": "0:09:58", "remaining_time": "4:21:24", "throughput": 687.85, "total_tokens": 411616} {"current_steps": 1475, "total_steps": 40000, "loss": 0.0, "lr": 4.983266004481753e-05, "epoch": 16.38888888888889, "percentage": 3.69, "elapsed_time": "0:10:00", "remaining_time": "4:21:20", "throughput": 687.92, "total_tokens": 413008} {"current_steps": 1480, "total_steps": 40000, "loss": 0.0, "lr": 4.9831524120456316e-05, "epoch": 16.444444444444443, "percentage": 3.7, "elapsed_time": "0:10:02", "remaining_time": "4:21:16", "throughput": 687.97, "total_tokens": 414384} {"current_steps": 1485, "total_steps": 40000, "loss": 0.0, "lr": 4.9830384366762026e-05, "epoch": 16.5, "percentage": 3.71, "elapsed_time": "0:10:04", "remaining_time": "4:21:12", "throughput": 688.1, "total_tokens": 415808} {"current_steps": 1490, "total_steps": 40000, "loss": 0.0, "lr": 4.9829240783910436e-05, "epoch": 16.555555555555557, "percentage": 3.72, "elapsed_time": "0:10:06", "remaining_time": "4:21:08", "throughput": 688.24, "total_tokens": 417232} {"current_steps": 1495, "total_steps": 40000, "loss": 0.0, "lr": 4.982809337207789e-05, "epoch": 16.61111111111111, "percentage": 3.74, "elapsed_time": "0:10:08", "remaining_time": "4:21:04", "throughput": 688.3, "total_tokens": 418608} {"current_steps": 1500, "total_steps": 40000, "loss": 0.0, "lr": 4.9826942131441337e-05, "epoch": 16.666666666666668, "percentage": 3.75, "elapsed_time": "0:10:10", "remaining_time": "4:20:59", "throughput": 688.42, "total_tokens": 420016} {"current_steps": 1505, "total_steps": 40000, "loss": 0.0, "lr": 4.9825787062178315e-05, "epoch": 16.72222222222222, "percentage": 3.76, "elapsed_time": "0:10:12", "remaining_time": "4:20:55", "throughput": 688.6, "total_tokens": 421456} {"current_steps": 1510, "total_steps": 40000, "loss": 0.0, "lr": 4.9824628164466945e-05, "epoch": 16.77777777777778, "percentage": 3.77, "elapsed_time": "0:10:14", "remaining_time": "4:20:50", "throughput": 688.62, "total_tokens": 422816} {"current_steps": 1515, "total_steps": 40000, "loss": 0.0, "lr": 4.982346543848595e-05, "epoch": 16.833333333333332, "percentage": 3.79, "elapsed_time": "0:10:15", "remaining_time": "4:20:46", "throughput": 688.77, "total_tokens": 424256} {"current_steps": 1520, "total_steps": 40000, "loss": 0.0, "lr": 4.9822298884414626e-05, "epoch": 16.88888888888889, "percentage": 3.8, "elapsed_time": "0:10:17", "remaining_time": "4:20:42", "throughput": 688.86, "total_tokens": 425648} {"current_steps": 1525, "total_steps": 40000, "loss": 0.0, "lr": 4.982112850243288e-05, "epoch": 16.944444444444443, "percentage": 3.81, "elapsed_time": "0:10:19", "remaining_time": "4:20:38", "throughput": 688.93, "total_tokens": 427024} {"current_steps": 1530, "total_steps": 40000, "loss": 0.0, "lr": 4.98199542927212e-05, "epoch": 17.0, "percentage": 3.82, "elapsed_time": "0:10:21", "remaining_time": "4:20:37", "throughput": 688.86, "total_tokens": 428432} {"current_steps": 1535, "total_steps": 40000, "loss": 0.0, "lr": 4.981877625546066e-05, "epoch": 17.055555555555557, "percentage": 3.84, "elapsed_time": "0:10:24", "remaining_time": "4:20:40", "throughput": 688.69, "total_tokens": 429840} {"current_steps": 1540, "total_steps": 40000, "loss": 0.0, "lr": 4.981759439083293e-05, "epoch": 17.11111111111111, "percentage": 3.85, "elapsed_time": "0:10:26", "remaining_time": "4:20:35", "throughput": 688.87, "total_tokens": 431296} {"current_steps": 1545, "total_steps": 40000, "loss": 0.0, "lr": 4.981640869902027e-05, "epoch": 17.166666666666668, "percentage": 3.86, "elapsed_time": "0:10:28", "remaining_time": "4:20:31", "throughput": 688.98, "total_tokens": 432704} {"current_steps": 1550, "total_steps": 40000, "loss": 0.0, "lr": 4.9815219180205517e-05, "epoch": 17.22222222222222, "percentage": 3.88, "elapsed_time": "0:10:29", "remaining_time": "4:20:27", "throughput": 689.05, "total_tokens": 434096} {"current_steps": 1555, "total_steps": 40000, "loss": 0.0, "lr": 4.9814025834572126e-05, "epoch": 17.27777777777778, "percentage": 3.89, "elapsed_time": "0:10:31", "remaining_time": "4:20:23", "throughput": 689.14, "total_tokens": 435488} {"current_steps": 1560, "total_steps": 40000, "loss": 0.0, "lr": 4.981282866230411e-05, "epoch": 17.333333333333332, "percentage": 3.9, "elapsed_time": "0:10:33", "remaining_time": "4:20:19", "throughput": 689.2, "total_tokens": 436864} {"current_steps": 1565, "total_steps": 40000, "loss": 0.0, "lr": 4.981162766358611e-05, "epoch": 17.38888888888889, "percentage": 3.91, "elapsed_time": "0:10:35", "remaining_time": "4:20:15", "throughput": 689.23, "total_tokens": 438224} {"current_steps": 1570, "total_steps": 40000, "loss": 0.0, "lr": 4.9810422838603316e-05, "epoch": 17.444444444444443, "percentage": 3.92, "elapsed_time": "0:10:37", "remaining_time": "4:20:10", "throughput": 689.37, "total_tokens": 439648} {"current_steps": 1575, "total_steps": 40000, "loss": 0.0, "lr": 4.9809214187541533e-05, "epoch": 17.5, "percentage": 3.94, "elapsed_time": "0:10:39", "remaining_time": "4:20:06", "throughput": 689.52, "total_tokens": 441088} {"current_steps": 1580, "total_steps": 40000, "loss": 0.0, "lr": 4.980800171058715e-05, "epoch": 17.555555555555557, "percentage": 3.95, "elapsed_time": "0:10:41", "remaining_time": "4:20:02", "throughput": 689.62, "total_tokens": 442496} {"current_steps": 1585, "total_steps": 40000, "loss": 0.0, "lr": 4.980678540792715e-05, "epoch": 17.61111111111111, "percentage": 3.96, "elapsed_time": "0:10:43", "remaining_time": "4:19:58", "throughput": 689.71, "total_tokens": 443888} {"current_steps": 1590, "total_steps": 40000, "loss": 0.0, "lr": 4.980556527974909e-05, "epoch": 17.666666666666668, "percentage": 3.98, "elapsed_time": "0:10:45", "remaining_time": "4:19:54", "throughput": 689.88, "total_tokens": 445344} {"current_steps": 1595, "total_steps": 40000, "loss": 0.0, "lr": 4.980434132624114e-05, "epoch": 17.72222222222222, "percentage": 3.99, "elapsed_time": "0:10:47", "remaining_time": "4:19:50", "throughput": 689.99, "total_tokens": 446752} {"current_steps": 1600, "total_steps": 40000, "loss": 0.0, "lr": 4.980311354759205e-05, "epoch": 17.77777777777778, "percentage": 4.0, "elapsed_time": "0:10:49", "remaining_time": "4:19:45", "throughput": 690.05, "total_tokens": 448128} {"current_steps": 1600, "total_steps": 40000, "eval_loss": 0.2256428301334381, "epoch": 17.77777777777778, "percentage": 4.0, "elapsed_time": "0:10:50", "remaining_time": "4:20:17", "throughput": 688.64, "total_tokens": 448128} {"current_steps": 1605, "total_steps": 40000, "loss": 0.0, "lr": 4.980188194399116e-05, "epoch": 17.833333333333332, "percentage": 4.01, "elapsed_time": "0:10:53", "remaining_time": "4:20:43", "throughput": 687.39, "total_tokens": 449520} {"current_steps": 1610, "total_steps": 40000, "loss": 0.0, "lr": 4.9800646515628384e-05, "epoch": 17.88888888888889, "percentage": 4.03, "elapsed_time": "0:10:55", "remaining_time": "4:20:40", "throughput": 687.4, "total_tokens": 450896} {"current_steps": 1615, "total_steps": 40000, "loss": 0.0, "lr": 4.979940726269426e-05, "epoch": 17.944444444444443, "percentage": 4.04, "elapsed_time": "0:10:57", "remaining_time": "4:20:36", "throughput": 687.39, "total_tokens": 452240} {"current_steps": 1620, "total_steps": 40000, "loss": 0.0, "lr": 4.979816418537988e-05, "epoch": 18.0, "percentage": 4.05, "elapsed_time": "0:11:00", "remaining_time": "4:20:37", "throughput": 687.28, "total_tokens": 453632} {"current_steps": 1625, "total_steps": 40000, "loss": 0.0, "lr": 4.979691728387696e-05, "epoch": 18.055555555555557, "percentage": 4.06, "elapsed_time": "0:11:02", "remaining_time": "4:20:39", "throughput": 687.12, "total_tokens": 455040} {"current_steps": 1630, "total_steps": 40000, "loss": 0.0, "lr": 4.979566655837776e-05, "epoch": 18.11111111111111, "percentage": 4.08, "elapsed_time": "0:11:04", "remaining_time": "4:20:35", "throughput": 687.14, "total_tokens": 456400} {"current_steps": 1635, "total_steps": 40000, "loss": 0.0, "lr": 4.9794412009075184e-05, "epoch": 18.166666666666668, "percentage": 4.09, "elapsed_time": "0:11:06", "remaining_time": "4:20:31", "throughput": 687.27, "total_tokens": 457824} {"current_steps": 1640, "total_steps": 40000, "loss": 0.0, "lr": 4.979315363616269e-05, "epoch": 18.22222222222222, "percentage": 4.1, "elapsed_time": "0:11:08", "remaining_time": "4:20:27", "throughput": 687.27, "total_tokens": 459168} {"current_steps": 1645, "total_steps": 40000, "loss": 0.0, "lr": 4.979189143983434e-05, "epoch": 18.27777777777778, "percentage": 4.11, "elapsed_time": "0:11:10", "remaining_time": "4:20:22", "throughput": 687.41, "total_tokens": 460592} {"current_steps": 1650, "total_steps": 40000, "loss": 0.0, "lr": 4.979062542028478e-05, "epoch": 18.333333333333332, "percentage": 4.12, "elapsed_time": "0:11:11", "remaining_time": "4:20:18", "throughput": 687.59, "total_tokens": 462048} {"current_steps": 1655, "total_steps": 40000, "loss": 0.0, "lr": 4.978935557770923e-05, "epoch": 18.38888888888889, "percentage": 4.14, "elapsed_time": "0:11:13", "remaining_time": "4:20:14", "throughput": 687.7, "total_tokens": 463456} {"current_steps": 1660, "total_steps": 40000, "loss": 0.0, "lr": 4.978808191230353e-05, "epoch": 18.444444444444443, "percentage": 4.15, "elapsed_time": "0:11:15", "remaining_time": "4:20:10", "throughput": 687.73, "total_tokens": 464832} {"current_steps": 1665, "total_steps": 40000, "loss": 0.0, "lr": 4.9786804424264085e-05, "epoch": 18.5, "percentage": 4.16, "elapsed_time": "0:11:17", "remaining_time": "4:20:06", "throughput": 687.78, "total_tokens": 466208} {"current_steps": 1670, "total_steps": 40000, "loss": 0.0, "lr": 4.978552311378792e-05, "epoch": 18.555555555555557, "percentage": 4.17, "elapsed_time": "0:11:19", "remaining_time": "4:20:02", "throughput": 687.79, "total_tokens": 467552} {"current_steps": 1675, "total_steps": 40000, "loss": 0.0, "lr": 4.978423798107261e-05, "epoch": 18.61111111111111, "percentage": 4.19, "elapsed_time": "0:11:21", "remaining_time": "4:19:58", "throughput": 687.9, "total_tokens": 468960} {"current_steps": 1680, "total_steps": 40000, "loss": 0.0, "lr": 4.978294902631635e-05, "epoch": 18.666666666666668, "percentage": 4.2, "elapsed_time": "0:11:23", "remaining_time": "4:19:54", "throughput": 687.98, "total_tokens": 470352} {"current_steps": 1685, "total_steps": 40000, "loss": 0.0, "lr": 4.9781656249717914e-05, "epoch": 18.72222222222222, "percentage": 4.21, "elapsed_time": "0:11:25", "remaining_time": "4:19:50", "throughput": 688.04, "total_tokens": 471728} {"current_steps": 1690, "total_steps": 40000, "loss": 0.0, "lr": 4.9780359651476645e-05, "epoch": 18.77777777777778, "percentage": 4.23, "elapsed_time": "0:11:27", "remaining_time": "4:19:45", "throughput": 688.1, "total_tokens": 473104} {"current_steps": 1695, "total_steps": 40000, "loss": 0.0, "lr": 4.977905923179251e-05, "epoch": 18.833333333333332, "percentage": 4.24, "elapsed_time": "0:11:29", "remaining_time": "4:19:41", "throughput": 688.24, "total_tokens": 474544} {"current_steps": 1700, "total_steps": 40000, "loss": 0.0, "lr": 4.977775499086606e-05, "epoch": 18.88888888888889, "percentage": 4.25, "elapsed_time": "0:11:31", "remaining_time": "4:19:38", "throughput": 688.36, "total_tokens": 475968} {"current_steps": 1705, "total_steps": 40000, "loss": 0.0, "lr": 4.97764469288984e-05, "epoch": 18.944444444444443, "percentage": 4.26, "elapsed_time": "0:11:33", "remaining_time": "4:19:34", "throughput": 688.48, "total_tokens": 477392} {"current_steps": 1710, "total_steps": 40000, "loss": 0.0, "lr": 4.977513504609127e-05, "epoch": 19.0, "percentage": 4.28, "elapsed_time": "0:11:35", "remaining_time": "4:19:33", "throughput": 688.42, "total_tokens": 478800} {"current_steps": 1715, "total_steps": 40000, "loss": 0.0, "lr": 4.9773819342646965e-05, "epoch": 19.055555555555557, "percentage": 4.29, "elapsed_time": "0:11:37", "remaining_time": "4:19:35", "throughput": 688.27, "total_tokens": 480208} {"current_steps": 1720, "total_steps": 40000, "loss": 0.0, "lr": 4.97724998187684e-05, "epoch": 19.11111111111111, "percentage": 4.3, "elapsed_time": "0:11:39", "remaining_time": "4:19:31", "throughput": 688.3, "total_tokens": 481568} {"current_steps": 1725, "total_steps": 40000, "loss": 0.0, "lr": 4.9771176474659045e-05, "epoch": 19.166666666666668, "percentage": 4.31, "elapsed_time": "0:11:41", "remaining_time": "4:19:27", "throughput": 688.38, "total_tokens": 482960} {"current_steps": 1730, "total_steps": 40000, "loss": 0.0, "lr": 4.976984931052299e-05, "epoch": 19.22222222222222, "percentage": 4.32, "elapsed_time": "0:11:43", "remaining_time": "4:19:23", "throughput": 688.5, "total_tokens": 484384} {"current_steps": 1735, "total_steps": 40000, "loss": 0.0, "lr": 4.976851832656489e-05, "epoch": 19.27777777777778, "percentage": 4.34, "elapsed_time": "0:11:45", "remaining_time": "4:19:19", "throughput": 688.56, "total_tokens": 485776} {"current_steps": 1740, "total_steps": 40000, "loss": 0.0, "lr": 4.9767183522990004e-05, "epoch": 19.333333333333332, "percentage": 4.35, "elapsed_time": "0:11:47", "remaining_time": "4:19:15", "throughput": 688.72, "total_tokens": 487216} {"current_steps": 1745, "total_steps": 40000, "loss": 0.0, "lr": 4.9765844900004176e-05, "epoch": 19.38888888888889, "percentage": 4.36, "elapsed_time": "0:11:49", "remaining_time": "4:19:11", "throughput": 688.7, "total_tokens": 488544} {"current_steps": 1750, "total_steps": 40000, "loss": 0.0, "lr": 4.9764502457813834e-05, "epoch": 19.444444444444443, "percentage": 4.38, "elapsed_time": "0:11:51", "remaining_time": "4:19:07", "throughput": 688.72, "total_tokens": 489904} {"current_steps": 1755, "total_steps": 40000, "loss": 0.0, "lr": 4.9763156196626005e-05, "epoch": 19.5, "percentage": 4.39, "elapsed_time": "0:11:53", "remaining_time": "4:19:03", "throughput": 688.86, "total_tokens": 491344} {"current_steps": 1760, "total_steps": 40000, "loss": 0.0, "lr": 4.97618061166483e-05, "epoch": 19.555555555555557, "percentage": 4.4, "elapsed_time": "0:11:55", "remaining_time": "4:18:59", "throughput": 688.9, "total_tokens": 492720} {"current_steps": 1765, "total_steps": 40000, "loss": 0.0, "lr": 4.9760452218088915e-05, "epoch": 19.61111111111111, "percentage": 4.41, "elapsed_time": "0:11:57", "remaining_time": "4:18:55", "throughput": 689.0, "total_tokens": 494128} {"current_steps": 1770, "total_steps": 40000, "loss": 0.0, "lr": 4.975909450115663e-05, "epoch": 19.666666666666668, "percentage": 4.42, "elapsed_time": "0:11:59", "remaining_time": "4:18:51", "throughput": 689.06, "total_tokens": 495504} {"current_steps": 1775, "total_steps": 40000, "loss": 0.0, "lr": 4.975773296606084e-05, "epoch": 19.72222222222222, "percentage": 4.44, "elapsed_time": "0:12:01", "remaining_time": "4:18:48", "throughput": 689.16, "total_tokens": 496928} {"current_steps": 1780, "total_steps": 40000, "loss": 0.0, "lr": 4.97563676130115e-05, "epoch": 19.77777777777778, "percentage": 4.45, "elapsed_time": "0:12:03", "remaining_time": "4:18:44", "throughput": 689.22, "total_tokens": 498304} {"current_steps": 1785, "total_steps": 40000, "loss": 0.0, "lr": 4.9754998442219166e-05, "epoch": 19.833333333333332, "percentage": 4.46, "elapsed_time": "0:12:04", "remaining_time": "4:18:40", "throughput": 689.32, "total_tokens": 499712} {"current_steps": 1790, "total_steps": 40000, "loss": 0.0, "lr": 4.9753625453894984e-05, "epoch": 19.88888888888889, "percentage": 4.47, "elapsed_time": "0:12:06", "remaining_time": "4:18:36", "throughput": 689.36, "total_tokens": 501088} {"current_steps": 1795, "total_steps": 40000, "loss": 0.0, "lr": 4.975224864825068e-05, "epoch": 19.944444444444443, "percentage": 4.49, "elapsed_time": "0:12:08", "remaining_time": "4:18:32", "throughput": 689.42, "total_tokens": 502480} {"current_steps": 1800, "total_steps": 40000, "loss": 0.0, "lr": 4.9750868025498576e-05, "epoch": 20.0, "percentage": 4.5, "elapsed_time": "0:12:10", "remaining_time": "4:18:32", "throughput": 689.39, "total_tokens": 503904} {"current_steps": 1800, "total_steps": 40000, "eval_loss": 0.22095215320587158, "epoch": 20.0, "percentage": 4.5, "elapsed_time": "0:12:12", "remaining_time": "4:18:59", "throughput": 688.18, "total_tokens": 503904} {"current_steps": 1805, "total_steps": 40000, "loss": 0.0, "lr": 4.974948358585158e-05, "epoch": 20.055555555555557, "percentage": 4.51, "elapsed_time": "0:12:15", "remaining_time": "4:19:28", "throughput": 686.79, "total_tokens": 505280} {"current_steps": 1810, "total_steps": 40000, "loss": 0.0, "lr": 4.9748095329523205e-05, "epoch": 20.11111111111111, "percentage": 4.52, "elapsed_time": "0:12:17", "remaining_time": "4:19:25", "throughput": 686.79, "total_tokens": 506656} {"current_steps": 1815, "total_steps": 40000, "loss": 0.0, "lr": 4.974670325672752e-05, "epoch": 20.166666666666668, "percentage": 4.54, "elapsed_time": "0:12:19", "remaining_time": "4:19:21", "throughput": 686.91, "total_tokens": 508080} {"current_steps": 1820, "total_steps": 40000, "loss": 0.0, "lr": 4.974530736767921e-05, "epoch": 20.22222222222222, "percentage": 4.55, "elapsed_time": "0:12:21", "remaining_time": "4:19:17", "throughput": 686.98, "total_tokens": 509472} {"current_steps": 1825, "total_steps": 40000, "loss": 0.0, "lr": 4.9743907662593524e-05, "epoch": 20.27777777777778, "percentage": 4.56, "elapsed_time": "0:12:23", "remaining_time": "4:19:13", "throughput": 687.1, "total_tokens": 510896} {"current_steps": 1830, "total_steps": 40000, "loss": 0.0, "lr": 4.974250414168633e-05, "epoch": 20.333333333333332, "percentage": 4.58, "elapsed_time": "0:12:25", "remaining_time": "4:19:09", "throughput": 687.18, "total_tokens": 512304} {"current_steps": 1835, "total_steps": 40000, "loss": 0.0, "lr": 4.974109680517407e-05, "epoch": 20.38888888888889, "percentage": 4.59, "elapsed_time": "0:12:27", "remaining_time": "4:19:05", "throughput": 687.3, "total_tokens": 513728} {"current_steps": 1840, "total_steps": 40000, "loss": 0.0, "lr": 4.973968565327376e-05, "epoch": 20.444444444444443, "percentage": 4.6, "elapsed_time": "0:12:29", "remaining_time": "4:19:01", "throughput": 687.42, "total_tokens": 515152} {"current_steps": 1845, "total_steps": 40000, "loss": 0.0, "lr": 4.973827068620303e-05, "epoch": 20.5, "percentage": 4.61, "elapsed_time": "0:12:31", "remaining_time": "4:18:58", "throughput": 687.52, "total_tokens": 516576} {"current_steps": 1850, "total_steps": 40000, "loss": 0.0, "lr": 4.973685190418008e-05, "epoch": 20.555555555555557, "percentage": 4.62, "elapsed_time": "0:12:33", "remaining_time": "4:18:54", "throughput": 687.56, "total_tokens": 517952} {"current_steps": 1855, "total_steps": 40000, "loss": 0.0, "lr": 4.97354293074237e-05, "epoch": 20.61111111111111, "percentage": 4.64, "elapsed_time": "0:12:35", "remaining_time": "4:18:50", "throughput": 687.61, "total_tokens": 519328} {"current_steps": 1860, "total_steps": 40000, "loss": 0.0, "lr": 4.9734002896153276e-05, "epoch": 20.666666666666668, "percentage": 4.65, "elapsed_time": "0:12:37", "remaining_time": "4:18:46", "throughput": 687.68, "total_tokens": 520720} {"current_steps": 1865, "total_steps": 40000, "loss": 0.0, "lr": 4.973257267058877e-05, "epoch": 20.72222222222222, "percentage": 4.66, "elapsed_time": "0:12:39", "remaining_time": "4:18:42", "throughput": 687.76, "total_tokens": 522112} {"current_steps": 1870, "total_steps": 40000, "loss": 0.0, "lr": 4.973113863095076e-05, "epoch": 20.77777777777778, "percentage": 4.67, "elapsed_time": "0:12:41", "remaining_time": "4:18:39", "throughput": 687.86, "total_tokens": 523536} {"current_steps": 1875, "total_steps": 40000, "loss": 0.0, "lr": 4.9729700777460384e-05, "epoch": 20.833333333333332, "percentage": 4.69, "elapsed_time": "0:12:43", "remaining_time": "4:18:35", "throughput": 687.88, "total_tokens": 524896} {"current_steps": 1880, "total_steps": 40000, "loss": 0.0, "lr": 4.972825911033937e-05, "epoch": 20.88888888888889, "percentage": 4.7, "elapsed_time": "0:12:45", "remaining_time": "4:18:32", "throughput": 687.92, "total_tokens": 526272} {"current_steps": 1885, "total_steps": 40000, "loss": 0.0, "lr": 4.9726813629810056e-05, "epoch": 20.944444444444443, "percentage": 4.71, "elapsed_time": "0:12:46", "remaining_time": "4:18:28", "throughput": 687.97, "total_tokens": 527664} {"current_steps": 1890, "total_steps": 40000, "loss": 0.0, "lr": 4.9725364336095326e-05, "epoch": 21.0, "percentage": 4.72, "elapsed_time": "0:12:49", "remaining_time": "4:18:28", "throughput": 687.92, "total_tokens": 529088} {"current_steps": 1895, "total_steps": 40000, "loss": 0.0, "lr": 4.972391122941871e-05, "epoch": 21.055555555555557, "percentage": 4.74, "elapsed_time": "0:12:51", "remaining_time": "4:18:30", "throughput": 687.74, "total_tokens": 530480} {"current_steps": 1900, "total_steps": 40000, "loss": 0.0, "lr": 4.972245431000428e-05, "epoch": 21.11111111111111, "percentage": 4.75, "elapsed_time": "0:12:53", "remaining_time": "4:18:26", "throughput": 687.83, "total_tokens": 531888} {"current_steps": 1905, "total_steps": 40000, "loss": 0.0, "lr": 4.972099357807671e-05, "epoch": 21.166666666666668, "percentage": 4.76, "elapsed_time": "0:12:55", "remaining_time": "4:18:22", "throughput": 687.88, "total_tokens": 533264} {"current_steps": 1910, "total_steps": 40000, "loss": 0.0, "lr": 4.971952903386127e-05, "epoch": 21.22222222222222, "percentage": 4.78, "elapsed_time": "0:12:57", "remaining_time": "4:18:18", "throughput": 687.95, "total_tokens": 534656} {"current_steps": 1915, "total_steps": 40000, "loss": 0.0, "lr": 4.971806067758381e-05, "epoch": 21.27777777777778, "percentage": 4.79, "elapsed_time": "0:12:59", "remaining_time": "4:18:15", "throughput": 688.03, "total_tokens": 536080} {"current_steps": 1920, "total_steps": 40000, "loss": 0.0, "lr": 4.971658850947076e-05, "epoch": 21.333333333333332, "percentage": 4.8, "elapsed_time": "0:13:01", "remaining_time": "4:18:11", "throughput": 688.11, "total_tokens": 537488} {"current_steps": 1925, "total_steps": 40000, "loss": 0.0, "lr": 4.9715112529749165e-05, "epoch": 21.38888888888889, "percentage": 4.81, "elapsed_time": "0:13:03", "remaining_time": "4:18:08", "throughput": 688.22, "total_tokens": 538912} {"current_steps": 1930, "total_steps": 40000, "loss": 0.0, "lr": 4.9713632738646624e-05, "epoch": 21.444444444444443, "percentage": 4.83, "elapsed_time": "0:13:04", "remaining_time": "4:18:04", "throughput": 688.34, "total_tokens": 540336} {"current_steps": 1935, "total_steps": 40000, "loss": 0.0, "lr": 4.971214913639134e-05, "epoch": 21.5, "percentage": 4.84, "elapsed_time": "0:13:06", "remaining_time": "4:18:00", "throughput": 688.43, "total_tokens": 541744} {"current_steps": 1940, "total_steps": 40000, "loss": 0.0, "lr": 4.9710661723212104e-05, "epoch": 21.555555555555557, "percentage": 4.85, "elapsed_time": "0:13:08", "remaining_time": "4:17:56", "throughput": 688.47, "total_tokens": 543120} {"current_steps": 1945, "total_steps": 40000, "loss": 0.0, "lr": 4.9709170499338295e-05, "epoch": 21.61111111111111, "percentage": 4.86, "elapsed_time": "0:13:10", "remaining_time": "4:17:52", "throughput": 688.6, "total_tokens": 544560} {"current_steps": 1950, "total_steps": 40000, "loss": 0.0, "lr": 4.9707675464999895e-05, "epoch": 21.666666666666668, "percentage": 4.88, "elapsed_time": "0:13:12", "remaining_time": "4:17:49", "throughput": 688.67, "total_tokens": 545952} {"current_steps": 1955, "total_steps": 40000, "loss": 0.0, "lr": 4.970617662042743e-05, "epoch": 21.72222222222222, "percentage": 4.89, "elapsed_time": "0:13:15", "remaining_time": "4:17:52", "throughput": 688.36, "total_tokens": 547312} {"current_steps": 1960, "total_steps": 40000, "loss": 0.0, "lr": 4.970467396585206e-05, "epoch": 21.77777777777778, "percentage": 4.9, "elapsed_time": "0:13:17", "remaining_time": "4:17:49", "throughput": 688.53, "total_tokens": 548784} {"current_steps": 1965, "total_steps": 40000, "loss": 0.0, "lr": 4.97031675015055e-05, "epoch": 21.833333333333332, "percentage": 4.91, "elapsed_time": "0:13:18", "remaining_time": "4:17:45", "throughput": 688.62, "total_tokens": 550192} {"current_steps": 1970, "total_steps": 40000, "loss": 0.0, "lr": 4.9701657227620075e-05, "epoch": 21.88888888888889, "percentage": 4.92, "elapsed_time": "0:13:20", "remaining_time": "4:17:41", "throughput": 688.66, "total_tokens": 551568} {"current_steps": 1975, "total_steps": 40000, "loss": 0.0, "lr": 4.9700143144428685e-05, "epoch": 21.944444444444443, "percentage": 4.94, "elapsed_time": "0:13:22", "remaining_time": "4:17:38", "throughput": 688.73, "total_tokens": 552976} {"current_steps": 1980, "total_steps": 40000, "loss": 0.0, "lr": 4.969862525216482e-05, "epoch": 22.0, "percentage": 4.95, "elapsed_time": "0:13:25", "remaining_time": "4:17:38", "throughput": 688.62, "total_tokens": 554352} {"current_steps": 1985, "total_steps": 40000, "loss": 0.0, "lr": 4.9697103551062556e-05, "epoch": 22.055555555555557, "percentage": 4.96, "elapsed_time": "0:13:27", "remaining_time": "4:17:39", "throughput": 688.5, "total_tokens": 555776} {"current_steps": 1990, "total_steps": 40000, "loss": 0.0, "lr": 4.9695578041356565e-05, "epoch": 22.11111111111111, "percentage": 4.98, "elapsed_time": "0:13:29", "remaining_time": "4:17:35", "throughput": 688.53, "total_tokens": 557136} {"current_steps": 1995, "total_steps": 40000, "loss": 0.0, "lr": 4.969404872328209e-05, "epoch": 22.166666666666668, "percentage": 4.99, "elapsed_time": "0:13:31", "remaining_time": "4:17:32", "throughput": 688.61, "total_tokens": 558544} {"current_steps": 2000, "total_steps": 40000, "loss": 0.0, "lr": 4.969251559707498e-05, "epoch": 22.22222222222222, "percentage": 5.0, "elapsed_time": "0:13:33", "remaining_time": "4:17:28", "throughput": 688.67, "total_tokens": 559936} {"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.22411350905895233, "epoch": 22.22222222222222, "percentage": 5.0, "elapsed_time": "0:13:34", "remaining_time": "4:17:53", "throughput": 687.55, "total_tokens": 559936} {"current_steps": 2005, "total_steps": 40000, "loss": 0.0, "lr": 4.9690978662971674e-05, "epoch": 22.27777777777778, "percentage": 5.01, "elapsed_time": "0:13:37", "remaining_time": "4:18:19", "throughput": 686.32, "total_tokens": 561344} {"current_steps": 2010, "total_steps": 40000, "loss": 0.0, "lr": 4.968943792120916e-05, "epoch": 22.333333333333332, "percentage": 5.03, "elapsed_time": "0:13:39", "remaining_time": "4:18:16", "throughput": 686.29, "total_tokens": 562704} {"current_steps": 2015, "total_steps": 40000, "loss": 0.0, "lr": 4.9687893372025046e-05, "epoch": 22.38888888888889, "percentage": 5.04, "elapsed_time": "0:13:41", "remaining_time": "4:18:13", "throughput": 686.42, "total_tokens": 564144} {"current_steps": 2020, "total_steps": 40000, "loss": 0.0, "lr": 4.9686345015657535e-05, "epoch": 22.444444444444443, "percentage": 5.05, "elapsed_time": "0:13:43", "remaining_time": "4:18:09", "throughput": 686.5, "total_tokens": 565552} {"current_steps": 2025, "total_steps": 40000, "loss": 0.0, "lr": 4.968479285234538e-05, "epoch": 22.5, "percentage": 5.06, "elapsed_time": "0:13:45", "remaining_time": "4:18:06", "throughput": 686.54, "total_tokens": 566944} {"current_steps": 2030, "total_steps": 40000, "loss": 0.0, "lr": 4.9683236882327974e-05, "epoch": 22.555555555555557, "percentage": 5.08, "elapsed_time": "0:13:47", "remaining_time": "4:18:02", "throughput": 686.59, "total_tokens": 568320} {"current_steps": 2035, "total_steps": 40000, "loss": 0.0, "lr": 4.968167710584526e-05, "epoch": 22.61111111111111, "percentage": 5.09, "elapsed_time": "0:13:49", "remaining_time": "4:17:58", "throughput": 686.64, "total_tokens": 569712} {"current_steps": 2040, "total_steps": 40000, "loss": 0.0, "lr": 4.968011352313775e-05, "epoch": 22.666666666666668, "percentage": 5.1, "elapsed_time": "0:13:51", "remaining_time": "4:17:55", "throughput": 686.77, "total_tokens": 571152} {"current_steps": 2045, "total_steps": 40000, "loss": 0.0, "lr": 4.967854613444659e-05, "epoch": 22.72222222222222, "percentage": 5.11, "elapsed_time": "0:13:53", "remaining_time": "4:17:51", "throughput": 686.85, "total_tokens": 572560} {"current_steps": 2050, "total_steps": 40000, "loss": 0.0, "lr": 4.967697494001349e-05, "epoch": 22.77777777777778, "percentage": 5.12, "elapsed_time": "0:13:55", "remaining_time": "4:17:47", "throughput": 686.86, "total_tokens": 573904} {"current_steps": 2055, "total_steps": 40000, "loss": 0.0, "lr": 4.9675399940080736e-05, "epoch": 22.833333333333332, "percentage": 5.14, "elapsed_time": "0:13:57", "remaining_time": "4:17:43", "throughput": 686.95, "total_tokens": 575312} {"current_steps": 2060, "total_steps": 40000, "loss": 0.0, "lr": 4.9673821134891226e-05, "epoch": 22.88888888888889, "percentage": 5.15, "elapsed_time": "0:13:59", "remaining_time": "4:17:40", "throughput": 687.0, "total_tokens": 576688} {"current_steps": 2065, "total_steps": 40000, "loss": 0.0, "lr": 4.967223852468842e-05, "epoch": 22.944444444444443, "percentage": 5.16, "elapsed_time": "0:14:01", "remaining_time": "4:17:36", "throughput": 687.13, "total_tokens": 578144} {"current_steps": 2070, "total_steps": 40000, "loss": 0.0, "lr": 4.967065210971639e-05, "epoch": 23.0, "percentage": 5.17, "elapsed_time": "0:14:03", "remaining_time": "4:17:36", "throughput": 687.05, "total_tokens": 579536} {"current_steps": 2075, "total_steps": 40000, "loss": 0.0, "lr": 4.966906189021977e-05, "epoch": 23.055555555555557, "percentage": 5.19, "elapsed_time": "0:14:05", "remaining_time": "4:17:37", "throughput": 686.97, "total_tokens": 580976} {"current_steps": 2080, "total_steps": 40000, "loss": 0.0, "lr": 4.966746786644379e-05, "epoch": 23.11111111111111, "percentage": 5.2, "elapsed_time": "0:14:07", "remaining_time": "4:17:33", "throughput": 687.03, "total_tokens": 582368} {"current_steps": 2085, "total_steps": 40000, "loss": 0.0, "lr": 4.966587003863429e-05, "epoch": 23.166666666666668, "percentage": 5.21, "elapsed_time": "0:14:09", "remaining_time": "4:17:29", "throughput": 687.06, "total_tokens": 583728} {"current_steps": 2090, "total_steps": 40000, "loss": 0.0, "lr": 4.966426840703765e-05, "epoch": 23.22222222222222, "percentage": 5.22, "elapsed_time": "0:14:11", "remaining_time": "4:17:25", "throughput": 687.21, "total_tokens": 585184} {"current_steps": 2095, "total_steps": 40000, "loss": 0.0, "lr": 4.9662662971900875e-05, "epoch": 23.27777777777778, "percentage": 5.24, "elapsed_time": "0:14:13", "remaining_time": "4:17:22", "throughput": 687.23, "total_tokens": 586544} {"current_steps": 2100, "total_steps": 40000, "loss": 0.0, "lr": 4.9661053733471534e-05, "epoch": 23.333333333333332, "percentage": 5.25, "elapsed_time": "0:14:15", "remaining_time": "4:17:18", "throughput": 687.29, "total_tokens": 587936} {"current_steps": 2105, "total_steps": 40000, "loss": 0.0, "lr": 4.965944069199781e-05, "epoch": 23.38888888888889, "percentage": 5.26, "elapsed_time": "0:14:17", "remaining_time": "4:17:14", "throughput": 687.36, "total_tokens": 589328} {"current_steps": 2110, "total_steps": 40000, "loss": 0.0, "lr": 4.965782384772842e-05, "epoch": 23.444444444444443, "percentage": 5.27, "elapsed_time": "0:14:19", "remaining_time": "4:17:11", "throughput": 687.52, "total_tokens": 590800} {"current_steps": 2115, "total_steps": 40000, "loss": 0.0, "lr": 4.9656203200912734e-05, "epoch": 23.5, "percentage": 5.29, "elapsed_time": "0:14:21", "remaining_time": "4:17:07", "throughput": 687.57, "total_tokens": 592176} {"current_steps": 2120, "total_steps": 40000, "loss": 0.0, "lr": 4.965457875180067e-05, "epoch": 23.555555555555557, "percentage": 5.3, "elapsed_time": "0:14:23", "remaining_time": "4:17:03", "throughput": 687.63, "total_tokens": 593568} {"current_steps": 2125, "total_steps": 40000, "loss": 0.0, "lr": 4.9652950500642724e-05, "epoch": 23.61111111111111, "percentage": 5.31, "elapsed_time": "0:14:25", "remaining_time": "4:17:00", "throughput": 687.65, "total_tokens": 594928} {"current_steps": 2130, "total_steps": 40000, "loss": 0.0, "lr": 4.965131844769001e-05, "epoch": 23.666666666666668, "percentage": 5.33, "elapsed_time": "0:14:27", "remaining_time": "4:16:56", "throughput": 687.72, "total_tokens": 596320} {"current_steps": 2135, "total_steps": 40000, "loss": 0.0, "lr": 4.96496825931942e-05, "epoch": 23.72222222222222, "percentage": 5.34, "elapsed_time": "0:14:29", "remaining_time": "4:16:52", "throughput": 687.82, "total_tokens": 597744} {"current_steps": 2140, "total_steps": 40000, "loss": 0.0, "lr": 4.9648042937407566e-05, "epoch": 23.77777777777778, "percentage": 5.35, "elapsed_time": "0:14:30", "remaining_time": "4:16:49", "throughput": 687.92, "total_tokens": 599168} {"current_steps": 2145, "total_steps": 40000, "loss": 0.0, "lr": 4.964639948058297e-05, "epoch": 23.833333333333332, "percentage": 5.36, "elapsed_time": "0:14:32", "remaining_time": "4:16:45", "throughput": 687.98, "total_tokens": 600560} {"current_steps": 2150, "total_steps": 40000, "loss": 0.0, "lr": 4.9644752222973846e-05, "epoch": 23.88888888888889, "percentage": 5.38, "elapsed_time": "0:14:34", "remaining_time": "4:16:41", "throughput": 688.05, "total_tokens": 601952} {"current_steps": 2155, "total_steps": 40000, "loss": 0.0, "lr": 4.964310116483422e-05, "epoch": 23.944444444444443, "percentage": 5.39, "elapsed_time": "0:14:36", "remaining_time": "4:16:38", "throughput": 688.07, "total_tokens": 603312} {"current_steps": 2160, "total_steps": 40000, "loss": 0.0, "lr": 4.964144630641872e-05, "epoch": 24.0, "percentage": 5.4, "elapsed_time": "0:14:38", "remaining_time": "4:16:37", "throughput": 688.03, "total_tokens": 604736} {"current_steps": 2165, "total_steps": 40000, "loss": 0.0, "lr": 4.9639787647982525e-05, "epoch": 24.055555555555557, "percentage": 5.41, "elapsed_time": "0:14:41", "remaining_time": "4:16:39", "throughput": 687.88, "total_tokens": 606144} {"current_steps": 2170, "total_steps": 40000, "loss": 0.0, "lr": 4.963812518978143e-05, "epoch": 24.11111111111111, "percentage": 5.42, "elapsed_time": "0:14:43", "remaining_time": "4:16:36", "throughput": 687.92, "total_tokens": 607536} {"current_steps": 2175, "total_steps": 40000, "loss": 0.0, "lr": 4.963645893207182e-05, "epoch": 24.166666666666668, "percentage": 5.44, "elapsed_time": "0:14:45", "remaining_time": "4:16:32", "throughput": 687.99, "total_tokens": 608944} {"current_steps": 2180, "total_steps": 40000, "loss": 0.0, "lr": 4.963478887511063e-05, "epoch": 24.22222222222222, "percentage": 5.45, "elapsed_time": "0:14:47", "remaining_time": "4:16:29", "throughput": 688.07, "total_tokens": 610352} {"current_steps": 2185, "total_steps": 40000, "loss": 0.0, "lr": 4.963311501915542e-05, "epoch": 24.27777777777778, "percentage": 5.46, "elapsed_time": "0:14:48", "remaining_time": "4:16:25", "throughput": 688.19, "total_tokens": 611792} {"current_steps": 2190, "total_steps": 40000, "loss": 0.0, "lr": 4.963143736446432e-05, "epoch": 24.333333333333332, "percentage": 5.47, "elapsed_time": "0:14:50", "remaining_time": "4:16:21", "throughput": 688.19, "total_tokens": 613136} {"current_steps": 2195, "total_steps": 40000, "loss": 0.0, "lr": 4.962975591129603e-05, "epoch": 24.38888888888889, "percentage": 5.49, "elapsed_time": "0:14:52", "remaining_time": "4:16:18", "throughput": 688.3, "total_tokens": 614576} {"current_steps": 2200, "total_steps": 40000, "loss": 0.0, "lr": 4.962807065990986e-05, "epoch": 24.444444444444443, "percentage": 5.5, "elapsed_time": "0:14:54", "remaining_time": "4:16:14", "throughput": 688.36, "total_tokens": 615968} {"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.23023538291454315, "epoch": 24.444444444444443, "percentage": 5.5, "elapsed_time": "0:14:56", "remaining_time": "4:16:37", "throughput": 687.35, "total_tokens": 615968} {"current_steps": 2205, "total_steps": 40000, "loss": 0.0, "lr": 4.9626381610565714e-05, "epoch": 24.5, "percentage": 5.51, "elapsed_time": "0:14:59", "remaining_time": "4:16:57", "throughput": 686.34, "total_tokens": 617360} {"current_steps": 2210, "total_steps": 40000, "loss": 0.0, "lr": 4.9624688763524043e-05, "epoch": 24.555555555555557, "percentage": 5.53, "elapsed_time": "0:15:01", "remaining_time": "4:16:55", "throughput": 686.35, "total_tokens": 618736} {"current_steps": 2215, "total_steps": 40000, "loss": 0.0, "lr": 4.962299211904591e-05, "epoch": 24.61111111111111, "percentage": 5.54, "elapsed_time": "0:15:03", "remaining_time": "4:16:53", "throughput": 686.36, "total_tokens": 620144} {"current_steps": 2220, "total_steps": 40000, "loss": 0.0, "lr": 4.962129167739296e-05, "epoch": 24.666666666666668, "percentage": 5.55, "elapsed_time": "0:15:05", "remaining_time": "4:16:49", "throughput": 686.36, "total_tokens": 621488} {"current_steps": 2225, "total_steps": 40000, "loss": 0.0, "lr": 4.961958743882742e-05, "epoch": 24.72222222222222, "percentage": 5.56, "elapsed_time": "0:15:07", "remaining_time": "4:16:45", "throughput": 686.41, "total_tokens": 622864} {"current_steps": 2230, "total_steps": 40000, "loss": 0.0, "lr": 4.961787940361211e-05, "epoch": 24.77777777777778, "percentage": 5.58, "elapsed_time": "0:15:09", "remaining_time": "4:16:42", "throughput": 686.53, "total_tokens": 624304} {"current_steps": 2235, "total_steps": 40000, "loss": 0.0, "lr": 4.961616757201043e-05, "epoch": 24.833333333333332, "percentage": 5.59, "elapsed_time": "0:15:11", "remaining_time": "4:16:38", "throughput": 686.61, "total_tokens": 625712} {"current_steps": 2240, "total_steps": 40000, "loss": 0.0, "lr": 4.961445194428637e-05, "epoch": 24.88888888888889, "percentage": 5.6, "elapsed_time": "0:15:13", "remaining_time": "4:16:34", "throughput": 686.71, "total_tokens": 627136} {"current_steps": 2245, "total_steps": 40000, "loss": 0.0, "lr": 4.9612732520704486e-05, "epoch": 24.944444444444443, "percentage": 5.61, "elapsed_time": "0:15:15", "remaining_time": "4:16:31", "throughput": 686.74, "total_tokens": 628512} {"current_steps": 2250, "total_steps": 40000, "loss": 0.0, "lr": 4.961100930152994e-05, "epoch": 25.0, "percentage": 5.62, "elapsed_time": "0:15:17", "remaining_time": "4:16:30", "throughput": 686.74, "total_tokens": 629968} {"current_steps": 2255, "total_steps": 40000, "loss": 0.0, "lr": 4.960928228702849e-05, "epoch": 25.055555555555557, "percentage": 5.64, "elapsed_time": "0:15:19", "remaining_time": "4:16:31", "throughput": 686.56, "total_tokens": 631328} {"current_steps": 2260, "total_steps": 40000, "loss": 0.0, "lr": 4.960755147746645e-05, "epoch": 25.11111111111111, "percentage": 5.65, "elapsed_time": "0:15:21", "remaining_time": "4:16:28", "throughput": 686.61, "total_tokens": 632720} {"current_steps": 2265, "total_steps": 40000, "loss": 0.0, "lr": 4.9605816873110736e-05, "epoch": 25.166666666666668, "percentage": 5.66, "elapsed_time": "0:15:23", "remaining_time": "4:16:24", "throughput": 686.76, "total_tokens": 634192} {"current_steps": 2270, "total_steps": 40000, "loss": 0.0, "lr": 4.960407847422883e-05, "epoch": 25.22222222222222, "percentage": 5.67, "elapsed_time": "0:15:25", "remaining_time": "4:16:21", "throughput": 686.82, "total_tokens": 635584} {"current_steps": 2275, "total_steps": 40000, "loss": 0.0, "lr": 4.960233628108885e-05, "epoch": 25.27777777777778, "percentage": 5.69, "elapsed_time": "0:15:27", "remaining_time": "4:16:17", "throughput": 686.91, "total_tokens": 637008} {"current_steps": 2280, "total_steps": 40000, "loss": 0.0, "lr": 4.960059029395942e-05, "epoch": 25.333333333333332, "percentage": 5.7, "elapsed_time": "0:15:29", "remaining_time": "4:16:14", "throughput": 686.97, "total_tokens": 638400} {"current_steps": 2285, "total_steps": 40000, "loss": 0.0, "lr": 4.959884051310983e-05, "epoch": 25.38888888888889, "percentage": 5.71, "elapsed_time": "0:15:31", "remaining_time": "4:16:10", "throughput": 687.06, "total_tokens": 639824} {"current_steps": 2290, "total_steps": 40000, "loss": 0.0, "lr": 4.959708693880991e-05, "epoch": 25.444444444444443, "percentage": 5.73, "elapsed_time": "0:15:33", "remaining_time": "4:16:07", "throughput": 687.15, "total_tokens": 641248} {"current_steps": 2295, "total_steps": 40000, "loss": 0.0, "lr": 4.9595329571330074e-05, "epoch": 25.5, "percentage": 5.74, "elapsed_time": "0:15:35", "remaining_time": "4:16:03", "throughput": 687.17, "total_tokens": 642608} {"current_steps": 2300, "total_steps": 40000, "loss": 0.0, "lr": 4.9593568410941326e-05, "epoch": 25.555555555555557, "percentage": 5.75, "elapsed_time": "0:15:37", "remaining_time": "4:16:00", "throughput": 687.22, "total_tokens": 644000} {"current_steps": 2305, "total_steps": 40000, "loss": 0.0, "lr": 4.959180345791528e-05, "epoch": 25.61111111111111, "percentage": 5.76, "elapsed_time": "0:15:39", "remaining_time": "4:15:56", "throughput": 687.28, "total_tokens": 645392} {"current_steps": 2310, "total_steps": 40000, "loss": 0.0, "lr": 4.9590034712524086e-05, "epoch": 25.666666666666668, "percentage": 5.78, "elapsed_time": "0:15:40", "remaining_time": "4:15:53", "throughput": 687.3, "total_tokens": 646752} {"current_steps": 2315, "total_steps": 40000, "loss": 0.0, "lr": 4.958826217504053e-05, "epoch": 25.72222222222222, "percentage": 5.79, "elapsed_time": "0:15:42", "remaining_time": "4:15:49", "throughput": 687.38, "total_tokens": 648160} {"current_steps": 2320, "total_steps": 40000, "loss": 0.0, "lr": 4.958648584573795e-05, "epoch": 25.77777777777778, "percentage": 5.8, "elapsed_time": "0:15:44", "remaining_time": "4:15:46", "throughput": 687.44, "total_tokens": 649552} {"current_steps": 2325, "total_steps": 40000, "loss": 0.0, "lr": 4.958470572489028e-05, "epoch": 25.833333333333332, "percentage": 5.81, "elapsed_time": "0:15:46", "remaining_time": "4:15:42", "throughput": 687.53, "total_tokens": 650976} {"current_steps": 2330, "total_steps": 40000, "loss": 0.0, "lr": 4.958292181277203e-05, "epoch": 25.88888888888889, "percentage": 5.83, "elapsed_time": "0:15:48", "remaining_time": "4:15:39", "throughput": 687.61, "total_tokens": 652384} {"current_steps": 2335, "total_steps": 40000, "loss": 0.0, "lr": 4.958113410965832e-05, "epoch": 25.944444444444443, "percentage": 5.84, "elapsed_time": "0:15:50", "remaining_time": "4:15:35", "throughput": 687.68, "total_tokens": 653792} {"current_steps": 2340, "total_steps": 40000, "loss": 0.0, "lr": 4.957934261582481e-05, "epoch": 26.0, "percentage": 5.85, "elapsed_time": "0:15:52", "remaining_time": "4:15:34", "throughput": 687.64, "total_tokens": 655200} {"current_steps": 2345, "total_steps": 40000, "loss": 0.0, "lr": 4.95775473315478e-05, "epoch": 26.055555555555557, "percentage": 5.86, "elapsed_time": "0:15:55", "remaining_time": "4:15:35", "throughput": 687.51, "total_tokens": 656592} {"current_steps": 2350, "total_steps": 40000, "loss": 0.0, "lr": 4.9575748257104124e-05, "epoch": 26.11111111111111, "percentage": 5.88, "elapsed_time": "0:15:56", "remaining_time": "4:15:32", "throughput": 687.58, "total_tokens": 658000} {"current_steps": 2355, "total_steps": 40000, "loss": 0.0, "lr": 4.9573945392771224e-05, "epoch": 26.166666666666668, "percentage": 5.89, "elapsed_time": "0:15:58", "remaining_time": "4:15:28", "throughput": 687.69, "total_tokens": 659440} {"current_steps": 2360, "total_steps": 40000, "loss": 0.0, "lr": 4.9572138738827134e-05, "epoch": 26.22222222222222, "percentage": 5.9, "elapsed_time": "0:16:00", "remaining_time": "4:15:25", "throughput": 687.75, "total_tokens": 660848} {"current_steps": 2365, "total_steps": 40000, "loss": 0.0, "lr": 4.957032829555046e-05, "epoch": 26.27777777777778, "percentage": 5.91, "elapsed_time": "0:16:02", "remaining_time": "4:15:21", "throughput": 687.81, "total_tokens": 662240} {"current_steps": 2370, "total_steps": 40000, "loss": 0.0, "lr": 4.956851406322039e-05, "epoch": 26.333333333333332, "percentage": 5.92, "elapsed_time": "0:16:04", "remaining_time": "4:15:18", "throughput": 687.89, "total_tokens": 663664} {"current_steps": 2375, "total_steps": 40000, "loss": 0.0, "lr": 4.9566696042116704e-05, "epoch": 26.38888888888889, "percentage": 5.94, "elapsed_time": "0:16:06", "remaining_time": "4:15:14", "throughput": 688.0, "total_tokens": 665104} {"current_steps": 2380, "total_steps": 40000, "loss": 0.0, "lr": 4.9564874232519766e-05, "epoch": 26.444444444444443, "percentage": 5.95, "elapsed_time": "0:16:08", "remaining_time": "4:15:11", "throughput": 688.07, "total_tokens": 666512} {"current_steps": 2385, "total_steps": 40000, "loss": 0.0, "lr": 4.9563048634710516e-05, "epoch": 26.5, "percentage": 5.96, "elapsed_time": "0:16:10", "remaining_time": "4:15:08", "throughput": 688.14, "total_tokens": 667920} {"current_steps": 2390, "total_steps": 40000, "loss": 0.0, "lr": 4.956121924897049e-05, "epoch": 26.555555555555557, "percentage": 5.97, "elapsed_time": "0:16:12", "remaining_time": "4:15:04", "throughput": 688.2, "total_tokens": 669312} {"current_steps": 2395, "total_steps": 40000, "loss": 0.0, "lr": 4.955938607558181e-05, "epoch": 26.61111111111111, "percentage": 5.99, "elapsed_time": "0:16:14", "remaining_time": "4:15:00", "throughput": 688.28, "total_tokens": 670720} {"current_steps": 2400, "total_steps": 40000, "loss": 0.0, "lr": 4.955754911482715e-05, "epoch": 26.666666666666668, "percentage": 6.0, "elapsed_time": "0:16:16", "remaining_time": "4:14:57", "throughput": 688.28, "total_tokens": 672064} {"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.22735659778118134, "epoch": 26.666666666666668, "percentage": 6.0, "elapsed_time": "0:16:17", "remaining_time": "4:15:18", "throughput": 687.36, "total_tokens": 672064} {"current_steps": 2405, "total_steps": 40000, "loss": 0.0, "lr": 4.9555708366989804e-05, "epoch": 26.72222222222222, "percentage": 6.01, "elapsed_time": "0:16:20", "remaining_time": "4:15:34", "throughput": 686.5, "total_tokens": 673440} {"current_steps": 2410, "total_steps": 40000, "loss": 0.0, "lr": 4.9553863832353655e-05, "epoch": 26.77777777777778, "percentage": 6.02, "elapsed_time": "0:16:22", "remaining_time": "4:15:31", "throughput": 686.47, "total_tokens": 674784} {"current_steps": 2415, "total_steps": 40000, "loss": 0.0, "lr": 4.955201551120313e-05, "epoch": 26.833333333333332, "percentage": 6.04, "elapsed_time": "0:16:24", "remaining_time": "4:15:28", "throughput": 686.53, "total_tokens": 676176} {"current_steps": 2420, "total_steps": 40000, "loss": 0.0, "lr": 4.955016340382328e-05, "epoch": 26.88888888888889, "percentage": 6.05, "elapsed_time": "0:16:26", "remaining_time": "4:15:24", "throughput": 686.59, "total_tokens": 677568} {"current_steps": 2425, "total_steps": 40000, "loss": 0.0, "lr": 4.954830751049972e-05, "epoch": 26.944444444444443, "percentage": 6.06, "elapsed_time": "0:16:28", "remaining_time": "4:15:21", "throughput": 686.68, "total_tokens": 678992} {"current_steps": 2430, "total_steps": 40000, "loss": 0.0, "lr": 4.954644783151864e-05, "epoch": 27.0, "percentage": 6.08, "elapsed_time": "0:16:30", "remaining_time": "4:15:20", "throughput": 686.71, "total_tokens": 680464} {"current_steps": 2435, "total_steps": 40000, "loss": 0.0, "lr": 4.954458436716684e-05, "epoch": 27.055555555555557, "percentage": 6.09, "elapsed_time": "0:16:33", "remaining_time": "4:15:21", "throughput": 686.56, "total_tokens": 681840} {"current_steps": 2440, "total_steps": 40000, "loss": 0.0, "lr": 4.954271711773168e-05, "epoch": 27.11111111111111, "percentage": 6.1, "elapsed_time": "0:16:35", "remaining_time": "4:15:17", "throughput": 686.61, "total_tokens": 683232} {"current_steps": 2445, "total_steps": 40000, "loss": 0.0, "lr": 4.9540846083501115e-05, "epoch": 27.166666666666668, "percentage": 6.11, "elapsed_time": "0:16:37", "remaining_time": "4:15:14", "throughput": 686.67, "total_tokens": 684624} {"current_steps": 2450, "total_steps": 40000, "loss": 0.0, "lr": 4.953897126476369e-05, "epoch": 27.22222222222222, "percentage": 6.12, "elapsed_time": "0:16:38", "remaining_time": "4:15:10", "throughput": 686.74, "total_tokens": 686032} {"current_steps": 2455, "total_steps": 40000, "loss": 0.0, "lr": 4.9537092661808514e-05, "epoch": 27.27777777777778, "percentage": 6.14, "elapsed_time": "0:16:40", "remaining_time": "4:15:07", "throughput": 686.84, "total_tokens": 687456} {"current_steps": 2460, "total_steps": 40000, "loss": 0.0, "lr": 4.9535210274925306e-05, "epoch": 27.333333333333332, "percentage": 6.15, "elapsed_time": "0:16:42", "remaining_time": "4:15:03", "throughput": 686.91, "total_tokens": 688864} {"current_steps": 2465, "total_steps": 40000, "loss": 0.0, "lr": 4.953332410440435e-05, "epoch": 27.38888888888889, "percentage": 6.16, "elapsed_time": "0:16:44", "remaining_time": "4:15:00", "throughput": 686.96, "total_tokens": 690256} {"current_steps": 2470, "total_steps": 40000, "loss": 0.0, "lr": 4.9531434150536496e-05, "epoch": 27.444444444444443, "percentage": 6.17, "elapsed_time": "0:16:46", "remaining_time": "4:14:56", "throughput": 687.03, "total_tokens": 691664} {"current_steps": 2475, "total_steps": 40000, "loss": 0.0, "lr": 4.952954041361322e-05, "epoch": 27.5, "percentage": 6.19, "elapsed_time": "0:16:48", "remaining_time": "4:14:53", "throughput": 687.09, "total_tokens": 693056} {"current_steps": 2480, "total_steps": 40000, "loss": 0.0, "lr": 4.952764289392655e-05, "epoch": 27.555555555555557, "percentage": 6.2, "elapsed_time": "0:16:50", "remaining_time": "4:14:49", "throughput": 687.11, "total_tokens": 694416} {"current_steps": 2485, "total_steps": 40000, "loss": 0.0, "lr": 4.952574159176912e-05, "epoch": 27.61111111111111, "percentage": 6.21, "elapsed_time": "0:16:52", "remaining_time": "4:14:46", "throughput": 687.2, "total_tokens": 695840} {"current_steps": 2490, "total_steps": 40000, "loss": 0.0, "lr": 4.952383650743413e-05, "epoch": 27.666666666666668, "percentage": 6.22, "elapsed_time": "0:16:54", "remaining_time": "4:14:42", "throughput": 687.27, "total_tokens": 697248} {"current_steps": 2495, "total_steps": 40000, "loss": 0.0, "lr": 4.952192764121536e-05, "epoch": 27.72222222222222, "percentage": 6.24, "elapsed_time": "0:16:56", "remaining_time": "4:14:39", "throughput": 687.38, "total_tokens": 698688} {"current_steps": 2500, "total_steps": 40000, "loss": 0.0, "lr": 4.9520014993407185e-05, "epoch": 27.77777777777778, "percentage": 6.25, "elapsed_time": "0:16:58", "remaining_time": "4:14:35", "throughput": 687.45, "total_tokens": 700096} {"current_steps": 2505, "total_steps": 40000, "loss": 0.0, "lr": 4.951809856430456e-05, "epoch": 27.833333333333332, "percentage": 6.26, "elapsed_time": "0:17:00", "remaining_time": "4:14:32", "throughput": 687.53, "total_tokens": 701520} {"current_steps": 2510, "total_steps": 40000, "loss": 0.0, "lr": 4.951617835420303e-05, "epoch": 27.88888888888889, "percentage": 6.28, "elapsed_time": "0:17:02", "remaining_time": "4:14:29", "throughput": 687.57, "total_tokens": 702896} {"current_steps": 2515, "total_steps": 40000, "loss": 0.0, "lr": 4.951425436339869e-05, "epoch": 27.944444444444443, "percentage": 6.29, "elapsed_time": "0:17:04", "remaining_time": "4:14:25", "throughput": 687.63, "total_tokens": 704288} {"current_steps": 2520, "total_steps": 40000, "loss": 0.0, "lr": 4.9512326592188274e-05, "epoch": 28.0, "percentage": 6.3, "elapsed_time": "0:17:06", "remaining_time": "4:14:24", "throughput": 687.58, "total_tokens": 705680} {"current_steps": 2525, "total_steps": 40000, "loss": 0.0, "lr": 4.9510395040869054e-05, "epoch": 28.055555555555557, "percentage": 6.31, "elapsed_time": "0:17:08", "remaining_time": "4:14:25", "throughput": 687.44, "total_tokens": 707056} {"current_steps": 2530, "total_steps": 40000, "loss": 0.0, "lr": 4.9508459709738905e-05, "epoch": 28.11111111111111, "percentage": 6.33, "elapsed_time": "0:17:10", "remaining_time": "4:14:21", "throughput": 687.58, "total_tokens": 708528} {"current_steps": 2535, "total_steps": 40000, "loss": 0.0, "lr": 4.950652059909627e-05, "epoch": 28.166666666666668, "percentage": 6.34, "elapsed_time": "0:17:12", "remaining_time": "4:14:18", "throughput": 687.59, "total_tokens": 709888} {"current_steps": 2540, "total_steps": 40000, "loss": 0.0, "lr": 4.95045777092402e-05, "epoch": 28.22222222222222, "percentage": 6.35, "elapsed_time": "0:17:14", "remaining_time": "4:14:15", "throughput": 687.63, "total_tokens": 711264} {"current_steps": 2545, "total_steps": 40000, "loss": 0.0, "lr": 4.950263104047031e-05, "epoch": 28.27777777777778, "percentage": 6.36, "elapsed_time": "0:17:16", "remaining_time": "4:14:11", "throughput": 687.66, "total_tokens": 712640} {"current_steps": 2550, "total_steps": 40000, "loss": 0.0, "lr": 4.9500680593086775e-05, "epoch": 28.333333333333332, "percentage": 6.38, "elapsed_time": "0:17:18", "remaining_time": "4:14:08", "throughput": 687.72, "total_tokens": 714048} {"current_steps": 2555, "total_steps": 40000, "loss": 0.0, "lr": 4.94987263673904e-05, "epoch": 28.38888888888889, "percentage": 6.39, "elapsed_time": "0:17:20", "remaining_time": "4:14:05", "throughput": 687.78, "total_tokens": 715440} {"current_steps": 2560, "total_steps": 40000, "loss": 0.0, "lr": 4.949676836368256e-05, "epoch": 28.444444444444443, "percentage": 6.4, "elapsed_time": "0:17:22", "remaining_time": "4:14:01", "throughput": 687.84, "total_tokens": 716848} {"current_steps": 2565, "total_steps": 40000, "loss": 0.0, "lr": 4.949480658226518e-05, "epoch": 28.5, "percentage": 6.41, "elapsed_time": "0:17:24", "remaining_time": "4:13:58", "throughput": 687.92, "total_tokens": 718256} {"current_steps": 2570, "total_steps": 40000, "loss": 0.0, "lr": 4.949284102344082e-05, "epoch": 28.555555555555557, "percentage": 6.42, "elapsed_time": "0:17:26", "remaining_time": "4:13:54", "throughput": 687.99, "total_tokens": 719664} {"current_steps": 2575, "total_steps": 40000, "loss": 0.0, "lr": 4.9490871687512565e-05, "epoch": 28.61111111111111, "percentage": 6.44, "elapsed_time": "0:17:28", "remaining_time": "4:13:51", "throughput": 688.03, "total_tokens": 721056} {"current_steps": 2580, "total_steps": 40000, "loss": 0.0, "lr": 4.948889857478413e-05, "epoch": 28.666666666666668, "percentage": 6.45, "elapsed_time": "0:17:29", "remaining_time": "4:13:48", "throughput": 688.08, "total_tokens": 722448} {"current_steps": 2585, "total_steps": 40000, "loss": 0.0, "lr": 4.948692168555978e-05, "epoch": 28.72222222222222, "percentage": 6.46, "elapsed_time": "0:17:31", "remaining_time": "4:13:44", "throughput": 688.18, "total_tokens": 723888} {"current_steps": 2590, "total_steps": 40000, "loss": 0.0, "lr": 4.94849410201444e-05, "epoch": 28.77777777777778, "percentage": 6.48, "elapsed_time": "0:17:33", "remaining_time": "4:13:41", "throughput": 688.26, "total_tokens": 725312} {"current_steps": 2595, "total_steps": 40000, "loss": 0.0, "lr": 4.948295657884341e-05, "epoch": 28.833333333333332, "percentage": 6.49, "elapsed_time": "0:17:35", "remaining_time": "4:13:38", "throughput": 688.32, "total_tokens": 726720} {"current_steps": 2600, "total_steps": 40000, "loss": 0.0, "lr": 4.9480968361962835e-05, "epoch": 28.88888888888889, "percentage": 6.5, "elapsed_time": "0:17:37", "remaining_time": "4:13:34", "throughput": 688.4, "total_tokens": 728128} {"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.232314795255661, "epoch": 28.88888888888889, "percentage": 6.5, "elapsed_time": "0:17:39", "remaining_time": "4:13:53", "throughput": 687.54, "total_tokens": 728128} {"current_steps": 2605, "total_steps": 40000, "loss": 0.0, "lr": 4.9478976369809305e-05, "epoch": 28.944444444444443, "percentage": 6.51, "elapsed_time": "0:17:42", "remaining_time": "4:14:11", "throughput": 686.67, "total_tokens": 729536} {"current_steps": 2610, "total_steps": 40000, "loss": 0.0, "lr": 4.947698060268999e-05, "epoch": 29.0, "percentage": 6.53, "elapsed_time": "0:17:44", "remaining_time": "4:14:11", "throughput": 686.57, "total_tokens": 730928} {"current_steps": 2615, "total_steps": 40000, "loss": 0.0, "lr": 4.9474981060912665e-05, "epoch": 29.055555555555557, "percentage": 6.54, "elapsed_time": "0:17:46", "remaining_time": "4:14:11", "throughput": 686.47, "total_tokens": 732336} {"current_steps": 2620, "total_steps": 40000, "loss": 0.0, "lr": 4.94729777447857e-05, "epoch": 29.11111111111111, "percentage": 6.55, "elapsed_time": "0:17:48", "remaining_time": "4:14:08", "throughput": 686.54, "total_tokens": 733744} {"current_steps": 2625, "total_steps": 40000, "loss": 0.0, "lr": 4.947097065461801e-05, "epoch": 29.166666666666668, "percentage": 6.56, "elapsed_time": "0:17:50", "remaining_time": "4:14:04", "throughput": 686.6, "total_tokens": 735152} {"current_steps": 2630, "total_steps": 40000, "loss": 0.0, "lr": 4.9468959790719125e-05, "epoch": 29.22222222222222, "percentage": 6.58, "elapsed_time": "0:17:52", "remaining_time": "4:14:01", "throughput": 686.66, "total_tokens": 736560} {"current_steps": 2635, "total_steps": 40000, "loss": 0.0, "lr": 4.9466945153399146e-05, "epoch": 29.27777777777778, "percentage": 6.59, "elapsed_time": "0:17:54", "remaining_time": "4:13:58", "throughput": 686.7, "total_tokens": 737936} {"current_steps": 2640, "total_steps": 40000, "loss": 0.0, "lr": 4.9464926742968755e-05, "epoch": 29.333333333333332, "percentage": 6.6, "elapsed_time": "0:17:56", "remaining_time": "4:13:54", "throughput": 686.72, "total_tokens": 739296} {"current_steps": 2645, "total_steps": 40000, "loss": 0.0, "lr": 4.946290455973921e-05, "epoch": 29.38888888888889, "percentage": 6.61, "elapsed_time": "0:17:58", "remaining_time": "4:13:51", "throughput": 686.77, "total_tokens": 740688} {"current_steps": 2650, "total_steps": 40000, "loss": 0.0, "lr": 4.9460878604022365e-05, "epoch": 29.444444444444443, "percentage": 6.62, "elapsed_time": "0:18:00", "remaining_time": "4:13:48", "throughput": 686.79, "total_tokens": 742048} {"current_steps": 2655, "total_steps": 40000, "loss": 0.0, "lr": 4.945884887613065e-05, "epoch": 29.5, "percentage": 6.64, "elapsed_time": "0:18:02", "remaining_time": "4:13:44", "throughput": 686.81, "total_tokens": 743408} {"current_steps": 2660, "total_steps": 40000, "loss": 0.0, "lr": 4.9456815376377055e-05, "epoch": 29.555555555555557, "percentage": 6.65, "elapsed_time": "0:18:04", "remaining_time": "4:13:41", "throughput": 686.85, "total_tokens": 744784} {"current_steps": 2665, "total_steps": 40000, "loss": 0.0, "lr": 4.9454778105075195e-05, "epoch": 29.61111111111111, "percentage": 6.66, "elapsed_time": "0:18:06", "remaining_time": "4:13:38", "throughput": 686.89, "total_tokens": 746160} {"current_steps": 2670, "total_steps": 40000, "loss": 0.0, "lr": 4.945273706253924e-05, "epoch": 29.666666666666668, "percentage": 6.68, "elapsed_time": "0:18:08", "remaining_time": "4:13:34", "throughput": 686.98, "total_tokens": 747584} {"current_steps": 2675, "total_steps": 40000, "loss": 0.0, "lr": 4.9450692249083925e-05, "epoch": 29.72222222222222, "percentage": 6.69, "elapsed_time": "0:18:10", "remaining_time": "4:13:31", "throughput": 687.07, "total_tokens": 749024} {"current_steps": 2680, "total_steps": 40000, "loss": 0.0, "lr": 4.9448643665024605e-05, "epoch": 29.77777777777778, "percentage": 6.7, "elapsed_time": "0:18:12", "remaining_time": "4:13:27", "throughput": 687.17, "total_tokens": 750464} {"current_steps": 2685, "total_steps": 40000, "loss": 0.0, "lr": 4.944659131067719e-05, "epoch": 29.833333333333332, "percentage": 6.71, "elapsed_time": "0:18:14", "remaining_time": "4:13:24", "throughput": 687.26, "total_tokens": 751888} {"current_steps": 2690, "total_steps": 40000, "loss": 0.0, "lr": 4.944453518635818e-05, "epoch": 29.88888888888889, "percentage": 6.73, "elapsed_time": "0:18:15", "remaining_time": "4:13:21", "throughput": 687.31, "total_tokens": 753280} {"current_steps": 2695, "total_steps": 40000, "loss": 0.0, "lr": 4.944247529238465e-05, "epoch": 29.944444444444443, "percentage": 6.74, "elapsed_time": "0:18:17", "remaining_time": "4:13:17", "throughput": 687.35, "total_tokens": 754656} {"current_steps": 2700, "total_steps": 40000, "loss": 0.0, "lr": 4.944041162907427e-05, "epoch": 30.0, "percentage": 6.75, "elapsed_time": "0:18:20", "remaining_time": "4:13:16", "throughput": 687.33, "total_tokens": 756080} {"current_steps": 2705, "total_steps": 40000, "loss": 0.0, "lr": 4.943834419674529e-05, "epoch": 30.055555555555557, "percentage": 6.76, "elapsed_time": "0:18:22", "remaining_time": "4:13:17", "throughput": 687.27, "total_tokens": 757536} {"current_steps": 2710, "total_steps": 40000, "loss": 0.0, "lr": 4.9436272995716506e-05, "epoch": 30.11111111111111, "percentage": 6.78, "elapsed_time": "0:18:24", "remaining_time": "4:13:13", "throughput": 687.34, "total_tokens": 758960} {"current_steps": 2715, "total_steps": 40000, "loss": 0.0, "lr": 4.943419802630735e-05, "epoch": 30.166666666666668, "percentage": 6.79, "elapsed_time": "0:18:26", "remaining_time": "4:13:10", "throughput": 687.41, "total_tokens": 760384} {"current_steps": 2720, "total_steps": 40000, "loss": 0.0, "lr": 4.94321192888378e-05, "epoch": 30.22222222222222, "percentage": 6.8, "elapsed_time": "0:18:28", "remaining_time": "4:13:07", "throughput": 687.42, "total_tokens": 761728} {"current_steps": 2725, "total_steps": 40000, "loss": 0.0, "lr": 4.943003678362842e-05, "epoch": 30.27777777777778, "percentage": 6.81, "elapsed_time": "0:18:30", "remaining_time": "4:13:04", "throughput": 687.46, "total_tokens": 763120} {"current_steps": 2730, "total_steps": 40000, "loss": 0.0, "lr": 4.942795051100036e-05, "epoch": 30.333333333333332, "percentage": 6.83, "elapsed_time": "0:18:32", "remaining_time": "4:13:01", "throughput": 687.52, "total_tokens": 764528} {"current_steps": 2735, "total_steps": 40000, "loss": 0.0, "lr": 4.942586047127536e-05, "epoch": 30.38888888888889, "percentage": 6.84, "elapsed_time": "0:18:33", "remaining_time": "4:12:57", "throughput": 687.56, "total_tokens": 765904} {"current_steps": 2740, "total_steps": 40000, "loss": 0.0, "lr": 4.942376666477571e-05, "epoch": 30.444444444444443, "percentage": 6.85, "elapsed_time": "0:18:35", "remaining_time": "4:12:54", "throughput": 687.61, "total_tokens": 767296} {"current_steps": 2745, "total_steps": 40000, "loss": 0.0, "lr": 4.9421669091824304e-05, "epoch": 30.5, "percentage": 6.86, "elapsed_time": "0:18:37", "remaining_time": "4:12:51", "throughput": 687.64, "total_tokens": 768672} {"current_steps": 2750, "total_steps": 40000, "loss": 0.0, "lr": 4.9419567752744634e-05, "epoch": 30.555555555555557, "percentage": 6.88, "elapsed_time": "0:18:39", "remaining_time": "4:12:47", "throughput": 687.71, "total_tokens": 770080} {"current_steps": 2755, "total_steps": 40000, "loss": 0.0, "lr": 4.941746264786074e-05, "epoch": 30.61111111111111, "percentage": 6.89, "elapsed_time": "0:18:41", "remaining_time": "4:12:44", "throughput": 687.77, "total_tokens": 771488} {"current_steps": 2760, "total_steps": 40000, "loss": 0.0, "lr": 4.9415353777497254e-05, "epoch": 30.666666666666668, "percentage": 6.9, "elapsed_time": "0:18:43", "remaining_time": "4:12:41", "throughput": 687.89, "total_tokens": 772960} {"current_steps": 2765, "total_steps": 40000, "loss": 0.0, "lr": 4.9413241141979394e-05, "epoch": 30.72222222222222, "percentage": 6.91, "elapsed_time": "0:18:45", "remaining_time": "4:12:38", "throughput": 687.94, "total_tokens": 774352} {"current_steps": 2770, "total_steps": 40000, "loss": 0.0, "lr": 4.9411124741632956e-05, "epoch": 30.77777777777778, "percentage": 6.93, "elapsed_time": "0:18:47", "remaining_time": "4:12:34", "throughput": 687.97, "total_tokens": 775728} {"current_steps": 2775, "total_steps": 40000, "loss": 0.0, "lr": 4.940900457678431e-05, "epoch": 30.833333333333332, "percentage": 6.94, "elapsed_time": "0:18:49", "remaining_time": "4:12:31", "throughput": 688.02, "total_tokens": 777120} {"current_steps": 2780, "total_steps": 40000, "loss": 0.0, "lr": 4.9406880647760425e-05, "epoch": 30.88888888888889, "percentage": 6.95, "elapsed_time": "0:18:51", "remaining_time": "4:12:28", "throughput": 688.09, "total_tokens": 778544} {"current_steps": 2785, "total_steps": 40000, "loss": 0.0, "lr": 4.9404752954888824e-05, "epoch": 30.944444444444443, "percentage": 6.96, "elapsed_time": "0:18:53", "remaining_time": "4:12:25", "throughput": 688.12, "total_tokens": 779904} {"current_steps": 2790, "total_steps": 40000, "loss": 0.0, "lr": 4.940262149849762e-05, "epoch": 31.0, "percentage": 6.98, "elapsed_time": "0:18:55", "remaining_time": "4:12:23", "throughput": 688.02, "total_tokens": 781248} {"current_steps": 2795, "total_steps": 40000, "loss": 0.0, "lr": 4.9400486278915526e-05, "epoch": 31.055555555555557, "percentage": 6.99, "elapsed_time": "0:18:57", "remaining_time": "4:12:24", "throughput": 687.92, "total_tokens": 782640} {"current_steps": 2800, "total_steps": 40000, "loss": 0.0, "lr": 4.939834729647181e-05, "epoch": 31.11111111111111, "percentage": 7.0, "elapsed_time": "0:18:59", "remaining_time": "4:12:20", "throughput": 687.96, "total_tokens": 784032} {"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.23051214218139648, "epoch": 31.11111111111111, "percentage": 7.0, "elapsed_time": "0:19:00", "remaining_time": "4:12:38", "throughput": 687.17, "total_tokens": 784032} {"current_steps": 2805, "total_steps": 40000, "loss": 0.0, "lr": 4.9396204551496326e-05, "epoch": 31.166666666666668, "percentage": 7.01, "elapsed_time": "0:19:04", "remaining_time": "4:12:51", "throughput": 686.46, "total_tokens": 785408} {"current_steps": 2810, "total_steps": 40000, "loss": 0.0, "lr": 4.939405804431952e-05, "epoch": 31.22222222222222, "percentage": 7.03, "elapsed_time": "0:19:06", "remaining_time": "4:12:48", "throughput": 686.54, "total_tokens": 786864} {"current_steps": 2815, "total_steps": 40000, "loss": 0.0, "lr": 4.9391907775272414e-05, "epoch": 31.27777777777778, "percentage": 7.04, "elapsed_time": "0:19:08", "remaining_time": "4:12:45", "throughput": 686.58, "total_tokens": 788256} {"current_steps": 2820, "total_steps": 40000, "loss": 0.0, "lr": 4.9389753744686604e-05, "epoch": 31.333333333333332, "percentage": 7.05, "elapsed_time": "0:19:10", "remaining_time": "4:12:42", "throughput": 686.63, "total_tokens": 789648} {"current_steps": 2825, "total_steps": 40000, "loss": 0.0, "lr": 4.938759595289426e-05, "epoch": 31.38888888888889, "percentage": 7.06, "elapsed_time": "0:19:11", "remaining_time": "4:12:39", "throughput": 686.67, "total_tokens": 791040} {"current_steps": 2830, "total_steps": 40000, "loss": 0.0, "lr": 4.938543440022815e-05, "epoch": 31.444444444444443, "percentage": 7.07, "elapsed_time": "0:19:13", "remaining_time": "4:12:36", "throughput": 686.69, "total_tokens": 792400} {"current_steps": 2835, "total_steps": 40000, "loss": 0.0, "lr": 4.938326908702161e-05, "epoch": 31.5, "percentage": 7.09, "elapsed_time": "0:19:15", "remaining_time": "4:12:33", "throughput": 686.79, "total_tokens": 793856} {"current_steps": 2840, "total_steps": 40000, "loss": 0.0, "lr": 4.9381100013608554e-05, "epoch": 31.555555555555557, "percentage": 7.1, "elapsed_time": "0:19:17", "remaining_time": "4:12:29", "throughput": 686.84, "total_tokens": 795264} {"current_steps": 2845, "total_steps": 40000, "loss": 0.0, "lr": 4.9378927180323485e-05, "epoch": 31.61111111111111, "percentage": 7.11, "elapsed_time": "0:19:19", "remaining_time": "4:12:26", "throughput": 686.93, "total_tokens": 796704} {"current_steps": 2850, "total_steps": 40000, "loss": 0.0, "lr": 4.937675058750148e-05, "epoch": 31.666666666666668, "percentage": 7.12, "elapsed_time": "0:19:21", "remaining_time": "4:12:23", "throughput": 687.0, "total_tokens": 798128} {"current_steps": 2855, "total_steps": 40000, "loss": 0.0, "lr": 4.937457023547819e-05, "epoch": 31.72222222222222, "percentage": 7.14, "elapsed_time": "0:19:23", "remaining_time": "4:12:20", "throughput": 687.05, "total_tokens": 799520} {"current_steps": 2860, "total_steps": 40000, "loss": 0.0, "lr": 4.9372386124589876e-05, "epoch": 31.77777777777778, "percentage": 7.15, "elapsed_time": "0:19:25", "remaining_time": "4:12:16", "throughput": 687.12, "total_tokens": 800928} {"current_steps": 2865, "total_steps": 40000, "loss": 0.0, "lr": 4.937019825517333e-05, "epoch": 31.833333333333332, "percentage": 7.16, "elapsed_time": "0:19:27", "remaining_time": "4:12:13", "throughput": 687.17, "total_tokens": 802320} {"current_steps": 2870, "total_steps": 40000, "loss": 0.0, "lr": 4.9368006627565954e-05, "epoch": 31.88888888888889, "percentage": 7.17, "elapsed_time": "0:19:29", "remaining_time": "4:12:10", "throughput": 687.17, "total_tokens": 803664} {"current_steps": 2875, "total_steps": 40000, "loss": 0.0, "lr": 4.936581124210573e-05, "epoch": 31.944444444444443, "percentage": 7.19, "elapsed_time": "0:19:31", "remaining_time": "4:12:07", "throughput": 687.23, "total_tokens": 805072} {"current_steps": 2880, "total_steps": 40000, "loss": 0.0, "lr": 4.9363612099131216e-05, "epoch": 32.0, "percentage": 7.2, "elapsed_time": "0:19:33", "remaining_time": "4:12:06", "throughput": 687.21, "total_tokens": 806496} {"current_steps": 2885, "total_steps": 40000, "loss": 0.0, "lr": 4.936140919898155e-05, "epoch": 32.05555555555556, "percentage": 7.21, "elapsed_time": "0:19:35", "remaining_time": "4:12:06", "throughput": 687.1, "total_tokens": 807888} {"current_steps": 2890, "total_steps": 40000, "loss": 0.0, "lr": 4.9359202541996426e-05, "epoch": 32.111111111111114, "percentage": 7.22, "elapsed_time": "0:19:37", "remaining_time": "4:12:03", "throughput": 687.18, "total_tokens": 809312} {"current_steps": 2895, "total_steps": 40000, "loss": 0.0, "lr": 4.935699212851616e-05, "epoch": 32.166666666666664, "percentage": 7.24, "elapsed_time": "0:19:39", "remaining_time": "4:11:59", "throughput": 687.26, "total_tokens": 810736} {"current_steps": 2900, "total_steps": 40000, "loss": 0.0, "lr": 4.935477795888162e-05, "epoch": 32.22222222222222, "percentage": 7.25, "elapsed_time": "0:19:41", "remaining_time": "4:11:56", "throughput": 687.33, "total_tokens": 812160} {"current_steps": 2905, "total_steps": 40000, "loss": 0.0, "lr": 4.935256003343426e-05, "epoch": 32.27777777777778, "percentage": 7.26, "elapsed_time": "0:19:43", "remaining_time": "4:11:53", "throughput": 687.41, "total_tokens": 813584} {"current_steps": 2910, "total_steps": 40000, "loss": 0.0, "lr": 4.93503383525161e-05, "epoch": 32.333333333333336, "percentage": 7.27, "elapsed_time": "0:19:45", "remaining_time": "4:11:50", "throughput": 687.41, "total_tokens": 814928} {"current_steps": 2915, "total_steps": 40000, "loss": 0.0, "lr": 4.934811291646977e-05, "epoch": 32.388888888888886, "percentage": 7.29, "elapsed_time": "0:19:47", "remaining_time": "4:11:47", "throughput": 687.45, "total_tokens": 816320} {"current_steps": 2920, "total_steps": 40000, "loss": 0.0, "lr": 4.934588372563845e-05, "epoch": 32.44444444444444, "percentage": 7.3, "elapsed_time": "0:19:49", "remaining_time": "4:11:43", "throughput": 687.51, "total_tokens": 817728} {"current_steps": 2925, "total_steps": 40000, "loss": 0.0, "lr": 4.93436507803659e-05, "epoch": 32.5, "percentage": 7.31, "elapsed_time": "0:19:51", "remaining_time": "4:11:40", "throughput": 687.56, "total_tokens": 819120} {"current_steps": 2930, "total_steps": 40000, "loss": 0.0, "lr": 4.934141408099649e-05, "epoch": 32.55555555555556, "percentage": 7.32, "elapsed_time": "0:19:53", "remaining_time": "4:11:37", "throughput": 687.6, "total_tokens": 820512} {"current_steps": 2935, "total_steps": 40000, "loss": 0.0, "lr": 4.9339173627875135e-05, "epoch": 32.611111111111114, "percentage": 7.34, "elapsed_time": "0:19:55", "remaining_time": "4:11:34", "throughput": 687.66, "total_tokens": 821920} {"current_steps": 2940, "total_steps": 40000, "loss": 0.0, "lr": 4.9336929421347335e-05, "epoch": 32.666666666666664, "percentage": 7.35, "elapsed_time": "0:19:57", "remaining_time": "4:11:30", "throughput": 687.73, "total_tokens": 823328} {"current_steps": 2945, "total_steps": 40000, "loss": 0.0, "lr": 4.933468146175918e-05, "epoch": 32.72222222222222, "percentage": 7.36, "elapsed_time": "0:19:59", "remaining_time": "4:11:27", "throughput": 687.75, "total_tokens": 824688} {"current_steps": 2950, "total_steps": 40000, "loss": 0.0, "lr": 4.933242974945734e-05, "epoch": 32.77777777777778, "percentage": 7.38, "elapsed_time": "0:20:01", "remaining_time": "4:11:24", "throughput": 687.84, "total_tokens": 826144} {"current_steps": 2955, "total_steps": 40000, "loss": 0.0, "lr": 4.933017428478906e-05, "epoch": 32.833333333333336, "percentage": 7.39, "elapsed_time": "0:20:03", "remaining_time": "4:11:25", "throughput": 687.66, "total_tokens": 827504} {"current_steps": 2960, "total_steps": 40000, "loss": 0.0, "lr": 4.932791506810214e-05, "epoch": 32.888888888888886, "percentage": 7.4, "elapsed_time": "0:20:05", "remaining_time": "4:11:22", "throughput": 687.71, "total_tokens": 828896} {"current_steps": 2965, "total_steps": 40000, "loss": 0.0, "lr": 4.932565209974499e-05, "epoch": 32.94444444444444, "percentage": 7.41, "elapsed_time": "0:20:07", "remaining_time": "4:11:19", "throughput": 687.77, "total_tokens": 830304} {"current_steps": 2970, "total_steps": 40000, "loss": 0.0, "lr": 4.93233853800666e-05, "epoch": 33.0, "percentage": 7.42, "elapsed_time": "0:20:09", "remaining_time": "4:11:18", "throughput": 687.71, "total_tokens": 831696} {"current_steps": 2975, "total_steps": 40000, "loss": 0.0, "lr": 4.932111490941651e-05, "epoch": 33.05555555555556, "percentage": 7.44, "elapsed_time": "0:20:11", "remaining_time": "4:11:18", "throughput": 687.6, "total_tokens": 833072} {"current_steps": 2980, "total_steps": 40000, "loss": 0.0, "lr": 4.9318840688144876e-05, "epoch": 33.111111111111114, "percentage": 7.45, "elapsed_time": "0:20:13", "remaining_time": "4:11:15", "throughput": 687.61, "total_tokens": 834432} {"current_steps": 2985, "total_steps": 40000, "loss": 0.0, "lr": 4.9316562716602387e-05, "epoch": 33.166666666666664, "percentage": 7.46, "elapsed_time": "0:20:15", "remaining_time": "4:11:12", "throughput": 687.66, "total_tokens": 835840} {"current_steps": 2990, "total_steps": 40000, "loss": 0.0, "lr": 4.9314280995140346e-05, "epoch": 33.22222222222222, "percentage": 7.47, "elapsed_time": "0:20:17", "remaining_time": "4:11:09", "throughput": 687.71, "total_tokens": 837232} {"current_steps": 2995, "total_steps": 40000, "loss": 0.0, "lr": 4.931199552411063e-05, "epoch": 33.27777777777778, "percentage": 7.49, "elapsed_time": "0:20:19", "remaining_time": "4:11:05", "throughput": 687.76, "total_tokens": 838624} {"current_steps": 3000, "total_steps": 40000, "loss": 0.0, "lr": 4.930970630386568e-05, "epoch": 33.333333333333336, "percentage": 7.5, "elapsed_time": "0:20:21", "remaining_time": "4:11:02", "throughput": 687.78, "total_tokens": 839984} {"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.2234121561050415, "epoch": 33.333333333333336, "percentage": 7.5, "elapsed_time": "0:20:22", "remaining_time": "4:11:18", "throughput": 687.04, "total_tokens": 839984} {"current_steps": 3005, "total_steps": 40000, "loss": 0.0, "lr": 4.9307413334758524e-05, "epoch": 33.388888888888886, "percentage": 7.51, "elapsed_time": "0:20:25", "remaining_time": "4:11:31", "throughput": 686.37, "total_tokens": 841376} {"current_steps": 3010, "total_steps": 40000, "loss": 0.0, "lr": 4.930511661714276e-05, "epoch": 33.44444444444444, "percentage": 7.52, "elapsed_time": "0:20:27", "remaining_time": "4:11:29", "throughput": 686.4, "total_tokens": 842800} {"current_steps": 3015, "total_steps": 40000, "loss": 0.0, "lr": 4.9302816151372576e-05, "epoch": 33.5, "percentage": 7.54, "elapsed_time": "0:20:29", "remaining_time": "4:11:25", "throughput": 686.46, "total_tokens": 844208} {"current_steps": 3020, "total_steps": 40000, "loss": 0.0, "lr": 4.930051193780274e-05, "epoch": 33.55555555555556, "percentage": 7.55, "elapsed_time": "0:20:31", "remaining_time": "4:11:22", "throughput": 686.53, "total_tokens": 845632} {"current_steps": 3025, "total_steps": 40000, "loss": 0.0, "lr": 4.929820397678858e-05, "epoch": 33.611111111111114, "percentage": 7.56, "elapsed_time": "0:20:33", "remaining_time": "4:11:19", "throughput": 686.62, "total_tokens": 847072} {"current_steps": 3030, "total_steps": 40000, "loss": 0.0, "lr": 4.9295892268686015e-05, "epoch": 33.666666666666664, "percentage": 7.58, "elapsed_time": "0:20:35", "remaining_time": "4:11:16", "throughput": 686.68, "total_tokens": 848480} {"current_steps": 3035, "total_steps": 40000, "loss": 0.0, "lr": 4.9293576813851536e-05, "epoch": 33.72222222222222, "percentage": 7.59, "elapsed_time": "0:20:37", "remaining_time": "4:11:13", "throughput": 686.72, "total_tokens": 849872} {"current_steps": 3040, "total_steps": 40000, "loss": 0.0, "lr": 4.929125761264223e-05, "epoch": 33.77777777777778, "percentage": 7.6, "elapsed_time": "0:20:39", "remaining_time": "4:11:09", "throughput": 686.81, "total_tokens": 851312} {"current_steps": 3045, "total_steps": 40000, "loss": 0.0, "lr": 4.928893466541573e-05, "epoch": 33.833333333333336, "percentage": 7.61, "elapsed_time": "0:20:41", "remaining_time": "4:11:06", "throughput": 686.88, "total_tokens": 852720} {"current_steps": 3050, "total_steps": 40000, "loss": 0.0, "lr": 4.928660797253027e-05, "epoch": 33.888888888888886, "percentage": 7.62, "elapsed_time": "0:20:43", "remaining_time": "4:11:03", "throughput": 686.93, "total_tokens": 854128} {"current_steps": 3055, "total_steps": 40000, "loss": 0.0, "lr": 4.928427753434467e-05, "epoch": 33.94444444444444, "percentage": 7.64, "elapsed_time": "0:20:45", "remaining_time": "4:11:00", "throughput": 686.98, "total_tokens": 855536} {"current_steps": 3060, "total_steps": 40000, "loss": 0.0, "lr": 4.9281943351218286e-05, "epoch": 34.0, "percentage": 7.65, "elapsed_time": "0:20:47", "remaining_time": "4:10:59", "throughput": 686.95, "total_tokens": 856944} {"current_steps": 3065, "total_steps": 40000, "loss": 0.0, "lr": 4.9279605423511095e-05, "epoch": 34.05555555555556, "percentage": 7.66, "elapsed_time": "0:20:49", "remaining_time": "4:10:59", "throughput": 686.88, "total_tokens": 858368} {"current_steps": 3070, "total_steps": 40000, "loss": 0.0, "lr": 4.927726375158363e-05, "epoch": 34.111111111111114, "percentage": 7.67, "elapsed_time": "0:20:51", "remaining_time": "4:10:55", "throughput": 686.9, "total_tokens": 859728} {"current_steps": 3075, "total_steps": 40000, "loss": 0.0, "lr": 4.9274918335797004e-05, "epoch": 34.166666666666664, "percentage": 7.69, "elapsed_time": "0:20:53", "remaining_time": "4:10:52", "throughput": 686.94, "total_tokens": 861120} {"current_steps": 3080, "total_steps": 40000, "loss": 0.0, "lr": 4.927256917651292e-05, "epoch": 34.22222222222222, "percentage": 7.7, "elapsed_time": "0:20:55", "remaining_time": "4:10:49", "throughput": 686.98, "total_tokens": 862496} {"current_steps": 3085, "total_steps": 40000, "loss": 0.0, "lr": 4.927021627409364e-05, "epoch": 34.27777777777778, "percentage": 7.71, "elapsed_time": "0:20:57", "remaining_time": "4:10:46", "throughput": 687.04, "total_tokens": 863904} {"current_steps": 3090, "total_steps": 40000, "loss": 0.0, "lr": 4.9267859628902005e-05, "epoch": 34.333333333333336, "percentage": 7.72, "elapsed_time": "0:20:59", "remaining_time": "4:10:43", "throughput": 687.11, "total_tokens": 865328} {"current_steps": 3095, "total_steps": 40000, "loss": 0.0, "lr": 4.9265499241301454e-05, "epoch": 34.388888888888886, "percentage": 7.74, "elapsed_time": "0:21:01", "remaining_time": "4:10:40", "throughput": 687.13, "total_tokens": 866704} {"current_steps": 3100, "total_steps": 40000, "loss": 0.0, "lr": 4.926313511165598e-05, "epoch": 34.44444444444444, "percentage": 7.75, "elapsed_time": "0:21:03", "remaining_time": "4:10:37", "throughput": 687.17, "total_tokens": 868096} {"current_steps": 3105, "total_steps": 40000, "loss": 0.0, "lr": 4.926076724033016e-05, "epoch": 34.5, "percentage": 7.76, "elapsed_time": "0:21:05", "remaining_time": "4:10:34", "throughput": 687.18, "total_tokens": 869456} {"current_steps": 3110, "total_steps": 40000, "loss": 0.0, "lr": 4.9258395627689146e-05, "epoch": 34.55555555555556, "percentage": 7.78, "elapsed_time": "0:21:07", "remaining_time": "4:10:31", "throughput": 687.28, "total_tokens": 870912} {"current_steps": 3115, "total_steps": 40000, "loss": 0.0, "lr": 4.925602027409868e-05, "epoch": 34.611111111111114, "percentage": 7.79, "elapsed_time": "0:21:09", "remaining_time": "4:10:28", "throughput": 687.29, "total_tokens": 872272} {"current_steps": 3120, "total_steps": 40000, "loss": 0.0, "lr": 4.925364117992507e-05, "epoch": 34.666666666666664, "percentage": 7.8, "elapsed_time": "0:21:11", "remaining_time": "4:10:25", "throughput": 687.33, "total_tokens": 873664} {"current_steps": 3125, "total_steps": 40000, "loss": 0.0, "lr": 4.92512583455352e-05, "epoch": 34.72222222222222, "percentage": 7.81, "elapsed_time": "0:21:13", "remaining_time": "4:10:21", "throughput": 687.39, "total_tokens": 875072} {"current_steps": 3130, "total_steps": 40000, "loss": 0.0, "lr": 4.9248871771296536e-05, "epoch": 34.77777777777778, "percentage": 7.83, "elapsed_time": "0:21:14", "remaining_time": "4:10:18", "throughput": 687.44, "total_tokens": 876480} {"current_steps": 3135, "total_steps": 40000, "loss": 0.0, "lr": 4.924648145757711e-05, "epoch": 34.833333333333336, "percentage": 7.84, "elapsed_time": "0:21:16", "remaining_time": "4:10:15", "throughput": 687.53, "total_tokens": 877936} {"current_steps": 3140, "total_steps": 40000, "loss": 0.0, "lr": 4.924408740474554e-05, "epoch": 34.888888888888886, "percentage": 7.85, "elapsed_time": "0:21:18", "remaining_time": "4:10:12", "throughput": 687.6, "total_tokens": 879360} {"current_steps": 3145, "total_steps": 40000, "loss": 0.0, "lr": 4.924168961317103e-05, "epoch": 34.94444444444444, "percentage": 7.86, "elapsed_time": "0:21:20", "remaining_time": "4:10:09", "throughput": 687.64, "total_tokens": 880752} {"current_steps": 3150, "total_steps": 40000, "loss": 0.0, "lr": 4.9239288083223334e-05, "epoch": 35.0, "percentage": 7.88, "elapsed_time": "0:21:22", "remaining_time": "4:10:08", "throughput": 687.62, "total_tokens": 882176} {"current_steps": 3155, "total_steps": 40000, "loss": 0.0, "lr": 4.9236882815272803e-05, "epoch": 35.05555555555556, "percentage": 7.89, "elapsed_time": "0:21:25", "remaining_time": "4:10:08", "throughput": 687.57, "total_tokens": 883616} {"current_steps": 3160, "total_steps": 40000, "loss": 0.0, "lr": 4.9234473809690365e-05, "epoch": 35.111111111111114, "percentage": 7.9, "elapsed_time": "0:21:27", "remaining_time": "4:10:04", "throughput": 687.65, "total_tokens": 885056} {"current_steps": 3165, "total_steps": 40000, "loss": 0.0, "lr": 4.923206106684752e-05, "epoch": 35.166666666666664, "percentage": 7.91, "elapsed_time": "0:21:28", "remaining_time": "4:10:01", "throughput": 687.73, "total_tokens": 886480} {"current_steps": 3170, "total_steps": 40000, "loss": 0.0, "lr": 4.922964458711634e-05, "epoch": 35.22222222222222, "percentage": 7.92, "elapsed_time": "0:21:30", "remaining_time": "4:09:58", "throughput": 687.78, "total_tokens": 887888} {"current_steps": 3175, "total_steps": 40000, "loss": 0.0, "lr": 4.9227224370869474e-05, "epoch": 35.27777777777778, "percentage": 7.94, "elapsed_time": "0:21:32", "remaining_time": "4:09:55", "throughput": 687.81, "total_tokens": 889264} {"current_steps": 3180, "total_steps": 40000, "loss": 0.0, "lr": 4.9224800418480155e-05, "epoch": 35.333333333333336, "percentage": 7.95, "elapsed_time": "0:21:34", "remaining_time": "4:09:52", "throughput": 687.81, "total_tokens": 890608} {"current_steps": 3185, "total_steps": 40000, "loss": 0.0, "lr": 4.9222372730322176e-05, "epoch": 35.388888888888886, "percentage": 7.96, "elapsed_time": "0:21:36", "remaining_time": "4:09:49", "throughput": 687.87, "total_tokens": 892016} {"current_steps": 3190, "total_steps": 40000, "loss": 0.0, "lr": 4.921994130676993e-05, "epoch": 35.44444444444444, "percentage": 7.98, "elapsed_time": "0:21:38", "remaining_time": "4:09:46", "throughput": 687.95, "total_tokens": 893456} {"current_steps": 3195, "total_steps": 40000, "loss": 0.0, "lr": 4.9217506148198366e-05, "epoch": 35.5, "percentage": 7.99, "elapsed_time": "0:21:40", "remaining_time": "4:09:43", "throughput": 688.03, "total_tokens": 894896} {"current_steps": 3200, "total_steps": 40000, "loss": 0.0, "lr": 4.921506725498302e-05, "epoch": 35.55555555555556, "percentage": 8.0, "elapsed_time": "0:21:42", "remaining_time": "4:09:40", "throughput": 688.07, "total_tokens": 896288} {"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.23261216282844543, "epoch": 35.55555555555556, "percentage": 8.0, "elapsed_time": "0:21:43", "remaining_time": "4:09:54", "throughput": 687.38, "total_tokens": 896288} {"current_steps": 3205, "total_steps": 40000, "loss": 0.0, "lr": 4.9212624627499994e-05, "epoch": 35.611111111111114, "percentage": 8.01, "elapsed_time": "0:21:47", "remaining_time": "4:10:06", "throughput": 686.76, "total_tokens": 897680} {"current_steps": 3210, "total_steps": 40000, "loss": 0.0, "lr": 4.921017826612597e-05, "epoch": 35.666666666666664, "percentage": 8.03, "elapsed_time": "0:21:49", "remaining_time": "4:10:04", "throughput": 686.76, "total_tokens": 899056} {"current_steps": 3215, "total_steps": 40000, "loss": 0.0, "lr": 4.9207728171238223e-05, "epoch": 35.72222222222222, "percentage": 8.04, "elapsed_time": "0:21:51", "remaining_time": "4:10:00", "throughput": 686.79, "total_tokens": 900432} {"current_steps": 3220, "total_steps": 40000, "loss": 0.0, "lr": 4.920527434321458e-05, "epoch": 35.77777777777778, "percentage": 8.05, "elapsed_time": "0:21:53", "remaining_time": "4:09:57", "throughput": 686.82, "total_tokens": 901808} {"current_steps": 3225, "total_steps": 40000, "loss": 0.0, "lr": 4.920281678243345e-05, "epoch": 35.833333333333336, "percentage": 8.06, "elapsed_time": "0:21:54", "remaining_time": "4:09:54", "throughput": 686.89, "total_tokens": 903232} {"current_steps": 3230, "total_steps": 40000, "loss": 0.0, "lr": 4.920035548927381e-05, "epoch": 35.888888888888886, "percentage": 8.08, "elapsed_time": "0:21:56", "remaining_time": "4:09:51", "throughput": 686.95, "total_tokens": 904640} {"current_steps": 3235, "total_steps": 40000, "loss": 0.0, "lr": 4.919789046411525e-05, "epoch": 35.94444444444444, "percentage": 8.09, "elapsed_time": "0:21:58", "remaining_time": "4:09:48", "throughput": 686.98, "total_tokens": 906016} {"current_steps": 3240, "total_steps": 40000, "loss": 0.0, "lr": 4.919542170733787e-05, "epoch": 36.0, "percentage": 8.1, "elapsed_time": "0:22:00", "remaining_time": "4:09:47", "throughput": 686.93, "total_tokens": 907408} {"current_steps": 3245, "total_steps": 40000, "loss": 0.0, "lr": 4.919294921932242e-05, "epoch": 36.05555555555556, "percentage": 8.11, "elapsed_time": "0:22:03", "remaining_time": "4:09:47", "throughput": 686.83, "total_tokens": 908784} {"current_steps": 3250, "total_steps": 40000, "loss": 0.0, "lr": 4.919047300045016e-05, "epoch": 36.111111111111114, "percentage": 8.12, "elapsed_time": "0:22:05", "remaining_time": "4:09:44", "throughput": 686.87, "total_tokens": 910192} {"current_steps": 3255, "total_steps": 40000, "loss": 0.0, "lr": 4.918799305110299e-05, "epoch": 36.166666666666664, "percentage": 8.14, "elapsed_time": "0:22:07", "remaining_time": "4:09:40", "throughput": 686.89, "total_tokens": 911552} {"current_steps": 3260, "total_steps": 40000, "loss": 0.0, "lr": 4.918550937166331e-05, "epoch": 36.22222222222222, "percentage": 8.15, "elapsed_time": "0:22:09", "remaining_time": "4:09:37", "throughput": 686.93, "total_tokens": 912944} {"current_steps": 3265, "total_steps": 40000, "loss": 0.0, "lr": 4.918302196251415e-05, "epoch": 36.27777777777778, "percentage": 8.16, "elapsed_time": "0:22:10", "remaining_time": "4:09:34", "throughput": 687.0, "total_tokens": 914368} {"current_steps": 3270, "total_steps": 40000, "loss": 0.0, "lr": 4.91805308240391e-05, "epoch": 36.333333333333336, "percentage": 8.18, "elapsed_time": "0:22:12", "remaining_time": "4:09:31", "throughput": 687.03, "total_tokens": 915744} {"current_steps": 3275, "total_steps": 40000, "loss": 0.0, "lr": 4.9178035956622326e-05, "epoch": 36.388888888888886, "percentage": 8.19, "elapsed_time": "0:22:14", "remaining_time": "4:09:28", "throughput": 687.09, "total_tokens": 917152} {"current_steps": 3280, "total_steps": 40000, "loss": 0.0, "lr": 4.917553736064857e-05, "epoch": 36.44444444444444, "percentage": 8.2, "elapsed_time": "0:22:16", "remaining_time": "4:09:25", "throughput": 687.17, "total_tokens": 918592} {"current_steps": 3285, "total_steps": 40000, "loss": 0.0, "lr": 4.917303503650314e-05, "epoch": 36.5, "percentage": 8.21, "elapsed_time": "0:22:18", "remaining_time": "4:09:22", "throughput": 687.22, "total_tokens": 920000} {"current_steps": 3290, "total_steps": 40000, "loss": 0.0, "lr": 4.917052898457194e-05, "epoch": 36.55555555555556, "percentage": 8.22, "elapsed_time": "0:22:20", "remaining_time": "4:09:19", "throughput": 687.28, "total_tokens": 921424} {"current_steps": 3295, "total_steps": 40000, "loss": 0.0, "lr": 4.916801920524141e-05, "epoch": 36.611111111111114, "percentage": 8.24, "elapsed_time": "0:22:22", "remaining_time": "4:09:16", "throughput": 687.34, "total_tokens": 922832} {"current_steps": 3300, "total_steps": 40000, "loss": 0.0, "lr": 4.916550569889862e-05, "epoch": 36.666666666666664, "percentage": 8.25, "elapsed_time": "0:22:24", "remaining_time": "4:09:13", "throughput": 687.38, "total_tokens": 924224} {"current_steps": 3305, "total_steps": 40000, "loss": 0.0, "lr": 4.916298846593116e-05, "epoch": 36.72222222222222, "percentage": 8.26, "elapsed_time": "0:22:26", "remaining_time": "4:09:10", "throughput": 687.43, "total_tokens": 925632} {"current_steps": 3310, "total_steps": 40000, "loss": 0.0, "lr": 4.916046750672722e-05, "epoch": 36.77777777777778, "percentage": 8.28, "elapsed_time": "0:22:28", "remaining_time": "4:09:06", "throughput": 687.51, "total_tokens": 927072} {"current_steps": 3315, "total_steps": 40000, "loss": 0.0, "lr": 4.915794282167559e-05, "epoch": 36.833333333333336, "percentage": 8.29, "elapsed_time": "0:22:30", "remaining_time": "4:09:04", "throughput": 687.52, "total_tokens": 928432} {"current_steps": 3320, "total_steps": 40000, "loss": 0.0, "lr": 4.915541441116558e-05, "epoch": 36.888888888888886, "percentage": 8.3, "elapsed_time": "0:22:32", "remaining_time": "4:09:01", "throughput": 687.57, "total_tokens": 929840} {"current_steps": 3325, "total_steps": 40000, "loss": 0.0, "lr": 4.915288227558711e-05, "epoch": 36.94444444444444, "percentage": 8.31, "elapsed_time": "0:22:34", "remaining_time": "4:08:57", "throughput": 687.63, "total_tokens": 931248} {"current_steps": 3330, "total_steps": 40000, "loss": 0.0, "lr": 4.915034641533066e-05, "epoch": 37.0, "percentage": 8.33, "elapsed_time": "0:22:36", "remaining_time": "4:08:56", "throughput": 687.6, "total_tokens": 932656} {"current_steps": 3335, "total_steps": 40000, "loss": 0.0, "lr": 4.914780683078731e-05, "epoch": 37.05555555555556, "percentage": 8.34, "elapsed_time": "0:22:38", "remaining_time": "4:08:56", "throughput": 687.54, "total_tokens": 934080} {"current_steps": 3340, "total_steps": 40000, "loss": 0.0, "lr": 4.9145263522348695e-05, "epoch": 37.111111111111114, "percentage": 8.35, "elapsed_time": "0:22:40", "remaining_time": "4:08:53", "throughput": 687.58, "total_tokens": 935472} {"current_steps": 3345, "total_steps": 40000, "loss": 0.0, "lr": 4.9142716490407e-05, "epoch": 37.166666666666664, "percentage": 8.36, "elapsed_time": "0:22:42", "remaining_time": "4:08:50", "throughput": 687.62, "total_tokens": 936864} {"current_steps": 3350, "total_steps": 40000, "loss": 0.0, "lr": 4.914016573535504e-05, "epoch": 37.22222222222222, "percentage": 8.38, "elapsed_time": "0:22:44", "remaining_time": "4:08:47", "throughput": 687.71, "total_tokens": 938320} {"current_steps": 3355, "total_steps": 40000, "loss": 0.0, "lr": 4.9137611257586154e-05, "epoch": 37.27777777777778, "percentage": 8.39, "elapsed_time": "0:22:46", "remaining_time": "4:08:44", "throughput": 687.77, "total_tokens": 939744} {"current_steps": 3360, "total_steps": 40000, "loss": 0.0, "lr": 4.9135053057494274e-05, "epoch": 37.333333333333336, "percentage": 8.4, "elapsed_time": "0:22:48", "remaining_time": "4:08:41", "throughput": 687.76, "total_tokens": 941072} {"current_steps": 3365, "total_steps": 40000, "loss": 0.0, "lr": 4.913249113547392e-05, "epoch": 37.388888888888886, "percentage": 8.41, "elapsed_time": "0:22:50", "remaining_time": "4:08:38", "throughput": 687.79, "total_tokens": 942448} {"current_steps": 3370, "total_steps": 40000, "loss": 0.0, "lr": 4.912992549192016e-05, "epoch": 37.44444444444444, "percentage": 8.43, "elapsed_time": "0:22:52", "remaining_time": "4:08:34", "throughput": 687.82, "total_tokens": 943824} {"current_steps": 3375, "total_steps": 40000, "loss": 0.0, "lr": 4.9127356127228665e-05, "epoch": 37.5, "percentage": 8.44, "elapsed_time": "0:22:54", "remaining_time": "4:08:31", "throughput": 687.86, "total_tokens": 945216} {"current_steps": 3380, "total_steps": 40000, "loss": 0.0, "lr": 4.912478304179564e-05, "epoch": 37.55555555555556, "percentage": 8.45, "elapsed_time": "0:22:56", "remaining_time": "4:08:29", "throughput": 687.9, "total_tokens": 946608} {"current_steps": 3385, "total_steps": 40000, "loss": 0.0, "lr": 4.9122206236017896e-05, "epoch": 37.611111111111114, "percentage": 8.46, "elapsed_time": "0:22:58", "remaining_time": "4:08:26", "throughput": 687.9, "total_tokens": 947952} {"current_steps": 3390, "total_steps": 40000, "loss": 0.0, "lr": 4.911962571029282e-05, "epoch": 37.666666666666664, "percentage": 8.48, "elapsed_time": "0:23:00", "remaining_time": "4:08:23", "throughput": 687.93, "total_tokens": 949344} {"current_steps": 3395, "total_steps": 40000, "loss": 0.0, "lr": 4.9117041465018353e-05, "epoch": 37.72222222222222, "percentage": 8.49, "elapsed_time": "0:23:01", "remaining_time": "4:08:20", "throughput": 687.95, "total_tokens": 950720} {"current_steps": 3400, "total_steps": 40000, "loss": 0.0, "lr": 4.911445350059302e-05, "epoch": 37.77777777777778, "percentage": 8.5, "elapsed_time": "0:23:03", "remaining_time": "4:08:17", "throughput": 688.0, "total_tokens": 952128} {"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.22534139454364777, "epoch": 37.77777777777778, "percentage": 8.5, "elapsed_time": "0:23:05", "remaining_time": "4:08:31", "throughput": 687.36, "total_tokens": 952128} {"current_steps": 3405, "total_steps": 40000, "loss": 0.0, "lr": 4.9111861817415905e-05, "epoch": 37.833333333333336, "percentage": 8.51, "elapsed_time": "0:23:08", "remaining_time": "4:08:42", "throughput": 686.72, "total_tokens": 953520} {"current_steps": 3410, "total_steps": 40000, "loss": 0.0, "lr": 4.91092664158867e-05, "epoch": 37.888888888888886, "percentage": 8.53, "elapsed_time": "0:23:10", "remaining_time": "4:08:40", "throughput": 686.75, "total_tokens": 954928} {"current_steps": 3415, "total_steps": 40000, "loss": 0.0, "lr": 4.910666729640563e-05, "epoch": 37.94444444444444, "percentage": 8.54, "elapsed_time": "0:23:12", "remaining_time": "4:08:37", "throughput": 686.8, "total_tokens": 956320} {"current_steps": 3420, "total_steps": 40000, "loss": 0.0, "lr": 4.910406445937353e-05, "epoch": 38.0, "percentage": 8.55, "elapsed_time": "0:23:14", "remaining_time": "4:08:35", "throughput": 686.74, "total_tokens": 957696} {"current_steps": 3425, "total_steps": 40000, "loss": 0.0, "lr": 4.9101457905191774e-05, "epoch": 38.05555555555556, "percentage": 8.56, "elapsed_time": "0:23:16", "remaining_time": "4:08:35", "throughput": 686.62, "total_tokens": 959056} {"current_steps": 3430, "total_steps": 40000, "loss": 0.0, "lr": 4.909884763426233e-05, "epoch": 38.111111111111114, "percentage": 8.58, "elapsed_time": "0:23:18", "remaining_time": "4:08:32", "throughput": 686.67, "total_tokens": 960464} {"current_steps": 3435, "total_steps": 40000, "loss": 0.0, "lr": 4.9096233646987736e-05, "epoch": 38.166666666666664, "percentage": 8.59, "elapsed_time": "0:23:20", "remaining_time": "4:08:29", "throughput": 686.75, "total_tokens": 961904} {"current_steps": 3440, "total_steps": 40000, "loss": 0.0, "lr": 4.9093615943771104e-05, "epoch": 38.22222222222222, "percentage": 8.6, "elapsed_time": "0:23:22", "remaining_time": "4:08:26", "throughput": 686.8, "total_tokens": 963312} {"current_steps": 3445, "total_steps": 40000, "loss": 0.0, "lr": 4.909099452501611e-05, "epoch": 38.27777777777778, "percentage": 8.61, "elapsed_time": "0:23:24", "remaining_time": "4:08:23", "throughput": 686.81, "total_tokens": 964672} {"current_steps": 3450, "total_steps": 40000, "loss": 0.0, "lr": 4.908836939112702e-05, "epoch": 38.333333333333336, "percentage": 8.62, "elapsed_time": "0:23:26", "remaining_time": "4:08:20", "throughput": 686.87, "total_tokens": 966080} {"current_steps": 3455, "total_steps": 40000, "loss": 0.0, "lr": 4.908574054250865e-05, "epoch": 38.388888888888886, "percentage": 8.64, "elapsed_time": "0:23:28", "remaining_time": "4:08:17", "throughput": 686.89, "total_tokens": 967456} {"current_steps": 3460, "total_steps": 40000, "loss": 0.0, "lr": 4.9083107979566414e-05, "epoch": 38.44444444444444, "percentage": 8.65, "elapsed_time": "0:23:30", "remaining_time": "4:08:14", "throughput": 686.92, "total_tokens": 968832} {"current_steps": 3465, "total_steps": 40000, "loss": 0.0, "lr": 4.908047170270628e-05, "epoch": 38.5, "percentage": 8.66, "elapsed_time": "0:23:32", "remaining_time": "4:08:11", "throughput": 686.98, "total_tokens": 970256} {"current_steps": 3470, "total_steps": 40000, "loss": 0.0, "lr": 4.9077831712334784e-05, "epoch": 38.55555555555556, "percentage": 8.67, "elapsed_time": "0:23:34", "remaining_time": "4:08:08", "throughput": 687.03, "total_tokens": 971664} {"current_steps": 3475, "total_steps": 40000, "loss": 0.0, "lr": 4.907518800885907e-05, "epoch": 38.611111111111114, "percentage": 8.69, "elapsed_time": "0:23:36", "remaining_time": "4:08:05", "throughput": 687.1, "total_tokens": 973104} {"current_steps": 3480, "total_steps": 40000, "loss": 0.0, "lr": 4.907254059268681e-05, "epoch": 38.666666666666664, "percentage": 8.7, "elapsed_time": "0:23:38", "remaining_time": "4:08:02", "throughput": 687.14, "total_tokens": 974496} {"current_steps": 3485, "total_steps": 40000, "loss": 0.0, "lr": 4.906988946422628e-05, "epoch": 38.72222222222222, "percentage": 8.71, "elapsed_time": "0:23:40", "remaining_time": "4:07:59", "throughput": 687.2, "total_tokens": 975920} {"current_steps": 3490, "total_steps": 40000, "loss": 0.0, "lr": 4.9067234623886315e-05, "epoch": 38.77777777777778, "percentage": 8.72, "elapsed_time": "0:23:42", "remaining_time": "4:07:56", "throughput": 687.25, "total_tokens": 977328} {"current_steps": 3495, "total_steps": 40000, "loss": 0.0, "lr": 4.9064576072076316e-05, "epoch": 38.833333333333336, "percentage": 8.74, "elapsed_time": "0:23:44", "remaining_time": "4:07:53", "throughput": 687.31, "total_tokens": 978736} {"current_steps": 3500, "total_steps": 40000, "loss": 0.0, "lr": 4.906191380920628e-05, "epoch": 38.888888888888886, "percentage": 8.75, "elapsed_time": "0:23:45", "remaining_time": "4:07:50", "throughput": 687.32, "total_tokens": 980096} {"current_steps": 3505, "total_steps": 40000, "loss": 0.0, "lr": 4.905924783568675e-05, "epoch": 38.94444444444444, "percentage": 8.76, "elapsed_time": "0:23:47", "remaining_time": "4:07:47", "throughput": 687.38, "total_tokens": 981520} {"current_steps": 3510, "total_steps": 40000, "loss": 0.0, "lr": 4.905657815192886e-05, "epoch": 39.0, "percentage": 8.77, "elapsed_time": "0:23:50", "remaining_time": "4:07:46", "throughput": 687.35, "total_tokens": 982928} {"current_steps": 3515, "total_steps": 40000, "loss": 0.0, "lr": 4.90539047583443e-05, "epoch": 39.05555555555556, "percentage": 8.79, "elapsed_time": "0:23:52", "remaining_time": "4:07:46", "throughput": 687.3, "total_tokens": 984384} {"current_steps": 3520, "total_steps": 40000, "loss": 0.0, "lr": 4.905122765534534e-05, "epoch": 39.111111111111114, "percentage": 8.8, "elapsed_time": "0:23:54", "remaining_time": "4:07:43", "throughput": 687.38, "total_tokens": 985824} {"current_steps": 3525, "total_steps": 40000, "loss": 0.0, "lr": 4.9048546843344846e-05, "epoch": 39.166666666666664, "percentage": 8.81, "elapsed_time": "0:23:56", "remaining_time": "4:07:40", "throughput": 687.39, "total_tokens": 987184} {"current_steps": 3530, "total_steps": 40000, "loss": 0.0, "lr": 4.9045862322756206e-05, "epoch": 39.22222222222222, "percentage": 8.82, "elapsed_time": "0:23:58", "remaining_time": "4:07:37", "throughput": 687.47, "total_tokens": 988640} {"current_steps": 3535, "total_steps": 40000, "loss": 0.0, "lr": 4.904317409399342e-05, "epoch": 39.27777777777778, "percentage": 8.84, "elapsed_time": "0:24:00", "remaining_time": "4:07:34", "throughput": 687.48, "total_tokens": 990000} {"current_steps": 3540, "total_steps": 40000, "loss": 0.0, "lr": 4.904048215747104e-05, "epoch": 39.333333333333336, "percentage": 8.85, "elapsed_time": "0:24:01", "remaining_time": "4:07:31", "throughput": 687.56, "total_tokens": 991440} {"current_steps": 3545, "total_steps": 40000, "loss": 0.0, "lr": 4.90377865136042e-05, "epoch": 39.388888888888886, "percentage": 8.86, "elapsed_time": "0:24:03", "remaining_time": "4:07:28", "throughput": 687.6, "total_tokens": 992832} {"current_steps": 3550, "total_steps": 40000, "loss": 0.0, "lr": 4.90350871628086e-05, "epoch": 39.44444444444444, "percentage": 8.88, "elapsed_time": "0:24:05", "remaining_time": "4:07:25", "throughput": 687.64, "total_tokens": 994224} {"current_steps": 3555, "total_steps": 40000, "loss": 0.0, "lr": 4.903238410550052e-05, "epoch": 39.5, "percentage": 8.89, "elapsed_time": "0:24:07", "remaining_time": "4:07:22", "throughput": 687.68, "total_tokens": 995616} {"current_steps": 3560, "total_steps": 40000, "loss": 0.0, "lr": 4.90296773420968e-05, "epoch": 39.55555555555556, "percentage": 8.9, "elapsed_time": "0:24:09", "remaining_time": "4:07:19", "throughput": 687.67, "total_tokens": 996944} {"current_steps": 3565, "total_steps": 40000, "loss": 0.0, "lr": 4.902696687301486e-05, "epoch": 39.611111111111114, "percentage": 8.91, "elapsed_time": "0:24:11", "remaining_time": "4:07:16", "throughput": 687.73, "total_tokens": 998368} {"current_steps": 3570, "total_steps": 40000, "loss": 0.0, "lr": 4.902425269867268e-05, "epoch": 39.666666666666664, "percentage": 8.92, "elapsed_time": "0:24:13", "remaining_time": "4:07:13", "throughput": 687.79, "total_tokens": 999792} {"current_steps": 3575, "total_steps": 40000, "loss": 0.0, "lr": 4.902153481948883e-05, "epoch": 39.72222222222222, "percentage": 8.94, "elapsed_time": "0:24:15", "remaining_time": "4:07:10", "throughput": 687.81, "total_tokens": 1001168} {"current_steps": 3580, "total_steps": 40000, "loss": 0.0, "lr": 4.901881323588244e-05, "epoch": 39.77777777777778, "percentage": 8.95, "elapsed_time": "0:24:17", "remaining_time": "4:07:07", "throughput": 687.86, "total_tokens": 1002576} {"current_steps": 3585, "total_steps": 40000, "loss": 0.0, "lr": 4.90160879482732e-05, "epoch": 39.833333333333336, "percentage": 8.96, "elapsed_time": "0:24:19", "remaining_time": "4:07:04", "throughput": 687.89, "total_tokens": 1003952} {"current_steps": 3590, "total_steps": 40000, "loss": 0.0, "lr": 4.9013358957081405e-05, "epoch": 39.888888888888886, "percentage": 8.97, "elapsed_time": "0:24:21", "remaining_time": "4:07:01", "throughput": 687.91, "total_tokens": 1005312} {"current_steps": 3595, "total_steps": 40000, "loss": 0.0, "lr": 4.901062626272789e-05, "epoch": 39.94444444444444, "percentage": 8.99, "elapsed_time": "0:24:23", "remaining_time": "4:06:58", "throughput": 687.96, "total_tokens": 1006720} {"current_steps": 3600, "total_steps": 40000, "loss": 0.0, "lr": 4.900788986563406e-05, "epoch": 40.0, "percentage": 9.0, "elapsed_time": "0:24:25", "remaining_time": "4:06:57", "throughput": 687.91, "total_tokens": 1008096} {"current_steps": 3600, "total_steps": 40000, "eval_loss": 0.2456374615430832, "epoch": 40.0, "percentage": 9.0, "elapsed_time": "0:24:26", "remaining_time": "4:07:10", "throughput": 687.3, "total_tokens": 1008096} {"current_steps": 3605, "total_steps": 40000, "loss": 0.0, "lr": 4.9005149766221915e-05, "epoch": 40.05555555555556, "percentage": 9.01, "elapsed_time": "0:24:30", "remaining_time": "4:07:25", "throughput": 686.5, "total_tokens": 1009488} {"current_steps": 3610, "total_steps": 40000, "loss": 0.0, "lr": 4.9002405964914e-05, "epoch": 40.111111111111114, "percentage": 9.03, "elapsed_time": "0:24:32", "remaining_time": "4:07:23", "throughput": 686.52, "total_tokens": 1010880} {"current_steps": 3615, "total_steps": 40000, "loss": 0.0, "lr": 4.899965846213346e-05, "epoch": 40.166666666666664, "percentage": 9.04, "elapsed_time": "0:24:34", "remaining_time": "4:07:20", "throughput": 686.52, "total_tokens": 1012224} {"current_steps": 3620, "total_steps": 40000, "loss": 0.0, "lr": 4.899690725830399e-05, "epoch": 40.22222222222222, "percentage": 9.05, "elapsed_time": "0:24:36", "remaining_time": "4:07:17", "throughput": 686.58, "total_tokens": 1013648} {"current_steps": 3625, "total_steps": 40000, "loss": 0.0, "lr": 4.899415235384985e-05, "epoch": 40.27777777777778, "percentage": 9.06, "elapsed_time": "0:24:38", "remaining_time": "4:07:14", "throughput": 686.64, "total_tokens": 1015088} {"current_steps": 3630, "total_steps": 40000, "loss": 0.0, "lr": 4.899139374919589e-05, "epoch": 40.333333333333336, "percentage": 9.07, "elapsed_time": "0:24:40", "remaining_time": "4:07:11", "throughput": 686.71, "total_tokens": 1016528} {"current_steps": 3635, "total_steps": 40000, "loss": 0.0, "lr": 4.898863144476752e-05, "epoch": 40.388888888888886, "percentage": 9.09, "elapsed_time": "0:24:42", "remaining_time": "4:07:08", "throughput": 686.75, "total_tokens": 1017920} {"current_steps": 3640, "total_steps": 40000, "loss": 0.0, "lr": 4.898586544099072e-05, "epoch": 40.44444444444444, "percentage": 9.1, "elapsed_time": "0:24:44", "remaining_time": "4:07:05", "throughput": 686.78, "total_tokens": 1019312} {"current_steps": 3645, "total_steps": 40000, "loss": 0.0, "lr": 4.898309573829204e-05, "epoch": 40.5, "percentage": 9.11, "elapsed_time": "0:24:46", "remaining_time": "4:07:02", "throughput": 686.83, "total_tokens": 1020736} {"current_steps": 3650, "total_steps": 40000, "loss": 0.0, "lr": 4.898032233709862e-05, "epoch": 40.55555555555556, "percentage": 9.12, "elapsed_time": "0:24:48", "remaining_time": "4:06:59", "throughput": 686.85, "total_tokens": 1022096} {"current_steps": 3655, "total_steps": 40000, "loss": 0.0, "lr": 4.8977545237838123e-05, "epoch": 40.611111111111114, "percentage": 9.14, "elapsed_time": "0:24:50", "remaining_time": "4:06:56", "throughput": 686.85, "total_tokens": 1023440} {"current_steps": 3660, "total_steps": 40000, "loss": 0.0, "lr": 4.8974764440938836e-05, "epoch": 40.666666666666664, "percentage": 9.15, "elapsed_time": "0:24:52", "remaining_time": "4:06:54", "throughput": 686.85, "total_tokens": 1024800} {"current_steps": 3665, "total_steps": 40000, "loss": 0.0, "lr": 4.897197994682959e-05, "epoch": 40.72222222222222, "percentage": 9.16, "elapsed_time": "0:24:53", "remaining_time": "4:06:51", "throughput": 686.91, "total_tokens": 1026240} {"current_steps": 3670, "total_steps": 40000, "loss": 0.0, "lr": 4.8969191755939786e-05, "epoch": 40.77777777777778, "percentage": 9.18, "elapsed_time": "0:24:55", "remaining_time": "4:06:48", "throughput": 686.99, "total_tokens": 1027696} {"current_steps": 3675, "total_steps": 40000, "loss": 0.0, "lr": 4.8966399868699396e-05, "epoch": 40.833333333333336, "percentage": 9.19, "elapsed_time": "0:24:57", "remaining_time": "4:06:45", "throughput": 687.03, "total_tokens": 1029088} {"current_steps": 3680, "total_steps": 40000, "loss": 0.0, "lr": 4.8963604285538965e-05, "epoch": 40.888888888888886, "percentage": 9.2, "elapsed_time": "0:24:59", "remaining_time": "4:06:42", "throughput": 687.04, "total_tokens": 1030448} {"current_steps": 3685, "total_steps": 40000, "loss": 0.0, "lr": 4.8960805006889604e-05, "epoch": 40.94444444444444, "percentage": 9.21, "elapsed_time": "0:25:01", "remaining_time": "4:06:39", "throughput": 687.11, "total_tokens": 1031904} {"current_steps": 3690, "total_steps": 40000, "loss": 0.0, "lr": 4.8958002033183004e-05, "epoch": 41.0, "percentage": 9.22, "elapsed_time": "0:25:03", "remaining_time": "4:06:38", "throughput": 687.07, "total_tokens": 1033312} {"current_steps": 3695, "total_steps": 40000, "loss": 0.0, "lr": 4.8955195364851414e-05, "epoch": 41.05555555555556, "percentage": 9.24, "elapsed_time": "0:25:06", "remaining_time": "4:06:38", "throughput": 687.02, "total_tokens": 1034752} {"current_steps": 3700, "total_steps": 40000, "loss": 0.0, "lr": 4.895238500232766e-05, "epoch": 41.111111111111114, "percentage": 9.25, "elapsed_time": "0:25:08", "remaining_time": "4:06:35", "throughput": 687.06, "total_tokens": 1036144} {"current_steps": 3705, "total_steps": 40000, "loss": 0.0, "lr": 4.8949570946045143e-05, "epoch": 41.166666666666664, "percentage": 9.26, "elapsed_time": "0:25:10", "remaining_time": "4:06:32", "throughput": 687.1, "total_tokens": 1037536} {"current_steps": 3710, "total_steps": 40000, "loss": 0.0, "lr": 4.89467531964378e-05, "epoch": 41.22222222222222, "percentage": 9.28, "elapsed_time": "0:25:11", "remaining_time": "4:06:29", "throughput": 687.14, "total_tokens": 1038928} {"current_steps": 3715, "total_steps": 40000, "loss": 0.0, "lr": 4.894393175394019e-05, "epoch": 41.27777777777778, "percentage": 9.29, "elapsed_time": "0:25:13", "remaining_time": "4:06:26", "throughput": 687.16, "total_tokens": 1040288} {"current_steps": 3720, "total_steps": 40000, "loss": 0.0, "lr": 4.8941106618987406e-05, "epoch": 41.333333333333336, "percentage": 9.3, "elapsed_time": "0:25:15", "remaining_time": "4:06:23", "throughput": 687.18, "total_tokens": 1041664} {"current_steps": 3725, "total_steps": 40000, "loss": 0.0, "lr": 4.893827779201512e-05, "epoch": 41.388888888888886, "percentage": 9.31, "elapsed_time": "0:25:17", "remaining_time": "4:06:20", "throughput": 687.19, "total_tokens": 1043024} {"current_steps": 3730, "total_steps": 40000, "loss": 0.0, "lr": 4.893544527345957e-05, "epoch": 41.44444444444444, "percentage": 9.32, "elapsed_time": "0:25:19", "remaining_time": "4:06:17", "throughput": 687.23, "total_tokens": 1044416} {"current_steps": 3735, "total_steps": 40000, "loss": 0.0, "lr": 4.8932609063757563e-05, "epoch": 41.5, "percentage": 9.34, "elapsed_time": "0:25:21", "remaining_time": "4:06:14", "throughput": 687.29, "total_tokens": 1045840} {"current_steps": 3740, "total_steps": 40000, "loss": 0.0, "lr": 4.8929769163346484e-05, "epoch": 41.55555555555556, "percentage": 9.35, "elapsed_time": "0:25:23", "remaining_time": "4:06:11", "throughput": 687.34, "total_tokens": 1047248} {"current_steps": 3745, "total_steps": 40000, "loss": 0.0, "lr": 4.892692557266429e-05, "epoch": 41.611111111111114, "percentage": 9.36, "elapsed_time": "0:25:25", "remaining_time": "4:06:08", "throughput": 687.38, "total_tokens": 1048640} {"current_steps": 3750, "total_steps": 40000, "loss": 0.0, "lr": 4.8924078292149464e-05, "epoch": 41.666666666666664, "percentage": 9.38, "elapsed_time": "0:25:27", "remaining_time": "4:06:05", "throughput": 687.43, "total_tokens": 1050064} {"current_steps": 3755, "total_steps": 40000, "loss": 0.0, "lr": 4.892122732224114e-05, "epoch": 41.72222222222222, "percentage": 9.39, "elapsed_time": "0:25:29", "remaining_time": "4:06:03", "throughput": 687.46, "total_tokens": 1051440} {"current_steps": 3760, "total_steps": 40000, "loss": 0.0, "lr": 4.8918372663378944e-05, "epoch": 41.77777777777778, "percentage": 9.4, "elapsed_time": "0:25:31", "remaining_time": "4:06:00", "throughput": 687.46, "total_tokens": 1052800} {"current_steps": 3765, "total_steps": 40000, "loss": 0.0, "lr": 4.89155143160031e-05, "epoch": 41.833333333333336, "percentage": 9.41, "elapsed_time": "0:25:33", "remaining_time": "4:05:57", "throughput": 687.51, "total_tokens": 1054208} {"current_steps": 3770, "total_steps": 40000, "loss": 0.0, "lr": 4.891265228055441e-05, "epoch": 41.888888888888886, "percentage": 9.43, "elapsed_time": "0:25:35", "remaining_time": "4:05:54", "throughput": 687.55, "total_tokens": 1055600} {"current_steps": 3775, "total_steps": 40000, "loss": 0.0, "lr": 4.890978655747424e-05, "epoch": 41.94444444444444, "percentage": 9.44, "elapsed_time": "0:25:37", "remaining_time": "4:05:51", "throughput": 687.62, "total_tokens": 1057040} {"current_steps": 3780, "total_steps": 40000, "loss": 0.0, "lr": 4.89069171472045e-05, "epoch": 42.0, "percentage": 9.45, "elapsed_time": "0:25:39", "remaining_time": "4:05:50", "throughput": 687.59, "total_tokens": 1058448} {"current_steps": 3785, "total_steps": 40000, "loss": 0.0, "lr": 4.890404405018772e-05, "epoch": 42.05555555555556, "percentage": 9.46, "elapsed_time": "0:25:41", "remaining_time": "4:05:49", "throughput": 687.48, "total_tokens": 1059792} {"current_steps": 3790, "total_steps": 40000, "loss": 0.0, "lr": 4.8901167266866934e-05, "epoch": 42.111111111111114, "percentage": 9.47, "elapsed_time": "0:25:43", "remaining_time": "4:05:46", "throughput": 687.53, "total_tokens": 1061200} {"current_steps": 3795, "total_steps": 40000, "loss": 0.0, "lr": 4.88982867976858e-05, "epoch": 42.166666666666664, "percentage": 9.49, "elapsed_time": "0:25:45", "remaining_time": "4:05:43", "throughput": 687.54, "total_tokens": 1062560} {"current_steps": 3800, "total_steps": 40000, "loss": 0.0, "lr": 4.889540264308852e-05, "epoch": 42.22222222222222, "percentage": 9.5, "elapsed_time": "0:25:47", "remaining_time": "4:05:41", "throughput": 687.59, "total_tokens": 1063984} {"current_steps": 3800, "total_steps": 40000, "eval_loss": 0.26800304651260376, "epoch": 42.22222222222222, "percentage": 9.5, "elapsed_time": "0:25:48", "remaining_time": "4:05:53", "throughput": 687.0, "total_tokens": 1063984} {"current_steps": 3805, "total_steps": 40000, "loss": 0.0, "lr": 4.889251480351986e-05, "epoch": 42.27777777777778, "percentage": 9.51, "elapsed_time": "0:25:51", "remaining_time": "4:06:03", "throughput": 686.48, "total_tokens": 1065392} {"current_steps": 3810, "total_steps": 40000, "loss": 0.0, "lr": 4.888962327942517e-05, "epoch": 42.333333333333336, "percentage": 9.53, "elapsed_time": "0:25:53", "remaining_time": "4:06:00", "throughput": 686.48, "total_tokens": 1066784} {"current_steps": 3815, "total_steps": 40000, "loss": 0.0, "lr": 4.8886728071250356e-05, "epoch": 42.388888888888886, "percentage": 9.54, "elapsed_time": "0:25:55", "remaining_time": "4:05:57", "throughput": 686.54, "total_tokens": 1068208} {"current_steps": 3820, "total_steps": 40000, "loss": 0.0, "lr": 4.8883829179441884e-05, "epoch": 42.44444444444444, "percentage": 9.55, "elapsed_time": "0:25:57", "remaining_time": "4:05:55", "throughput": 686.58, "total_tokens": 1069616} {"current_steps": 3825, "total_steps": 40000, "loss": 0.0, "lr": 4.888092660444682e-05, "epoch": 42.5, "percentage": 9.56, "elapsed_time": "0:25:59", "remaining_time": "4:05:52", "throughput": 686.63, "total_tokens": 1071024} {"current_steps": 3830, "total_steps": 40000, "loss": 0.0, "lr": 4.887802034671276e-05, "epoch": 42.55555555555556, "percentage": 9.57, "elapsed_time": "0:26:01", "remaining_time": "4:05:49", "throughput": 686.68, "total_tokens": 1072448} {"current_steps": 3835, "total_steps": 40000, "loss": 0.0, "lr": 4.88751104066879e-05, "epoch": 42.611111111111114, "percentage": 9.59, "elapsed_time": "0:26:03", "remaining_time": "4:05:46", "throughput": 686.7, "total_tokens": 1073808} {"current_steps": 3840, "total_steps": 40000, "loss": 0.0, "lr": 4.887219678482098e-05, "epoch": 42.666666666666664, "percentage": 9.6, "elapsed_time": "0:26:05", "remaining_time": "4:05:43", "throughput": 686.76, "total_tokens": 1075232} {"current_steps": 3845, "total_steps": 40000, "loss": 0.0, "lr": 4.8869279481561316e-05, "epoch": 42.72222222222222, "percentage": 9.61, "elapsed_time": "0:26:07", "remaining_time": "4:05:40", "throughput": 686.79, "total_tokens": 1076624} {"current_steps": 3850, "total_steps": 40000, "loss": 0.0, "lr": 4.88663584973588e-05, "epoch": 42.77777777777778, "percentage": 9.62, "elapsed_time": "0:26:09", "remaining_time": "4:05:37", "throughput": 686.82, "total_tokens": 1078016} {"current_steps": 3855, "total_steps": 40000, "loss": 0.0, "lr": 4.8863433832663874e-05, "epoch": 42.833333333333336, "percentage": 9.64, "elapsed_time": "0:26:11", "remaining_time": "4:05:35", "throughput": 686.86, "total_tokens": 1079440} {"current_steps": 3860, "total_steps": 40000, "loss": 0.0, "lr": 4.886050548792757e-05, "epoch": 42.888888888888886, "percentage": 9.65, "elapsed_time": "0:26:13", "remaining_time": "4:05:32", "throughput": 686.87, "total_tokens": 1080800} {"current_steps": 3865, "total_steps": 40000, "loss": 0.0, "lr": 4.8857573463601465e-05, "epoch": 42.94444444444444, "percentage": 9.66, "elapsed_time": "0:26:15", "remaining_time": "4:05:29", "throughput": 686.94, "total_tokens": 1082240} {"current_steps": 3870, "total_steps": 40000, "loss": 0.0, "lr": 4.885463776013772e-05, "epoch": 43.0, "percentage": 9.68, "elapsed_time": "0:26:17", "remaining_time": "4:05:28", "throughput": 686.9, "total_tokens": 1083632} {"current_steps": 3875, "total_steps": 40000, "loss": 0.0, "lr": 4.8851698377989056e-05, "epoch": 43.05555555555556, "percentage": 9.69, "elapsed_time": "0:26:19", "remaining_time": "4:05:27", "throughput": 686.86, "total_tokens": 1085088} {"current_steps": 3880, "total_steps": 40000, "loss": 0.0, "lr": 4.884875531760876e-05, "epoch": 43.111111111111114, "percentage": 9.7, "elapsed_time": "0:26:21", "remaining_time": "4:05:24", "throughput": 686.9, "total_tokens": 1086496} {"current_steps": 3885, "total_steps": 40000, "loss": 0.0, "lr": 4.88458085794507e-05, "epoch": 43.166666666666664, "percentage": 9.71, "elapsed_time": "0:26:23", "remaining_time": "4:05:21", "throughput": 686.94, "total_tokens": 1087888} {"current_steps": 3890, "total_steps": 40000, "loss": 0.0, "lr": 4.884285816396929e-05, "epoch": 43.22222222222222, "percentage": 9.72, "elapsed_time": "0:26:25", "remaining_time": "4:05:18", "throughput": 686.97, "total_tokens": 1089280} {"current_steps": 3895, "total_steps": 40000, "loss": 0.0, "lr": 4.8839904071619526e-05, "epoch": 43.27777777777778, "percentage": 9.74, "elapsed_time": "0:26:27", "remaining_time": "4:05:16", "throughput": 687.02, "total_tokens": 1090688} {"current_steps": 3900, "total_steps": 40000, "loss": 0.0, "lr": 4.8836946302856955e-05, "epoch": 43.333333333333336, "percentage": 9.75, "elapsed_time": "0:26:29", "remaining_time": "4:05:13", "throughput": 687.06, "total_tokens": 1092096} {"current_steps": 3905, "total_steps": 40000, "loss": 0.0, "lr": 4.8833984858137715e-05, "epoch": 43.388888888888886, "percentage": 9.76, "elapsed_time": "0:26:31", "remaining_time": "4:05:10", "throughput": 687.07, "total_tokens": 1093456} {"current_steps": 3910, "total_steps": 40000, "loss": 0.0, "lr": 4.8831019737918494e-05, "epoch": 43.44444444444444, "percentage": 9.78, "elapsed_time": "0:26:33", "remaining_time": "4:05:07", "throughput": 687.12, "total_tokens": 1094880} {"current_steps": 3915, "total_steps": 40000, "loss": 0.0, "lr": 4.882805094265655e-05, "epoch": 43.5, "percentage": 9.79, "elapsed_time": "0:26:35", "remaining_time": "4:05:04", "throughput": 687.17, "total_tokens": 1096288} {"current_steps": 3920, "total_steps": 40000, "loss": 0.0, "lr": 4.8825078472809706e-05, "epoch": 43.55555555555556, "percentage": 9.8, "elapsed_time": "0:26:37", "remaining_time": "4:05:01", "throughput": 687.18, "total_tokens": 1097648} {"current_steps": 3925, "total_steps": 40000, "loss": 0.0, "lr": 4.882210232883635e-05, "epoch": 43.611111111111114, "percentage": 9.81, "elapsed_time": "0:26:39", "remaining_time": "4:04:58", "throughput": 687.21, "total_tokens": 1099024} {"current_steps": 3930, "total_steps": 40000, "loss": 0.0, "lr": 4.881912251119546e-05, "epoch": 43.666666666666664, "percentage": 9.83, "elapsed_time": "0:26:41", "remaining_time": "4:04:56", "throughput": 687.27, "total_tokens": 1100464} {"current_steps": 3935, "total_steps": 40000, "loss": 0.0, "lr": 4.881613902034654e-05, "epoch": 43.72222222222222, "percentage": 9.84, "elapsed_time": "0:26:43", "remaining_time": "4:04:53", "throughput": 687.33, "total_tokens": 1101904} {"current_steps": 3940, "total_steps": 40000, "loss": 0.0, "lr": 4.88131518567497e-05, "epoch": 43.77777777777778, "percentage": 9.85, "elapsed_time": "0:26:45", "remaining_time": "4:04:50", "throughput": 687.36, "total_tokens": 1103296} {"current_steps": 3945, "total_steps": 40000, "loss": 0.0, "lr": 4.881016102086558e-05, "epoch": 43.833333333333336, "percentage": 9.86, "elapsed_time": "0:26:47", "remaining_time": "4:04:47", "throughput": 687.4, "total_tokens": 1104704} {"current_steps": 3950, "total_steps": 40000, "loss": 0.0, "lr": 4.8807166513155425e-05, "epoch": 43.888888888888886, "percentage": 9.88, "elapsed_time": "0:26:49", "remaining_time": "4:04:44", "throughput": 687.44, "total_tokens": 1106112} {"current_steps": 3955, "total_steps": 40000, "loss": 0.0, "lr": 4.8804168334081004e-05, "epoch": 43.94444444444444, "percentage": 9.89, "elapsed_time": "0:26:50", "remaining_time": "4:04:41", "throughput": 687.48, "total_tokens": 1107504} {"current_steps": 3960, "total_steps": 40000, "loss": 0.0, "lr": 4.880116648410468e-05, "epoch": 44.0, "percentage": 9.9, "elapsed_time": "0:26:53", "remaining_time": "4:04:43", "throughput": 687.34, "total_tokens": 1108928} {"current_steps": 3965, "total_steps": 40000, "loss": 0.0, "lr": 4.879816096368939e-05, "epoch": 44.05555555555556, "percentage": 9.91, "elapsed_time": "0:26:55", "remaining_time": "4:04:42", "throughput": 687.27, "total_tokens": 1110352} {"current_steps": 3970, "total_steps": 40000, "loss": 0.0, "lr": 4.879515177329861e-05, "epoch": 44.111111111111114, "percentage": 9.93, "elapsed_time": "0:26:57", "remaining_time": "4:04:40", "throughput": 687.31, "total_tokens": 1111744} {"current_steps": 3975, "total_steps": 40000, "loss": 0.0, "lr": 4.8792138913396394e-05, "epoch": 44.166666666666664, "percentage": 9.94, "elapsed_time": "0:26:59", "remaining_time": "4:04:37", "throughput": 687.33, "total_tokens": 1113120} {"current_steps": 3980, "total_steps": 40000, "loss": 0.0, "lr": 4.8789122384447374e-05, "epoch": 44.22222222222222, "percentage": 9.95, "elapsed_time": "0:27:01", "remaining_time": "4:04:34", "throughput": 687.37, "total_tokens": 1114544} {"current_steps": 3985, "total_steps": 40000, "loss": 0.0, "lr": 4.878610218691673e-05, "epoch": 44.27777777777778, "percentage": 9.96, "elapsed_time": "0:27:03", "remaining_time": "4:04:31", "throughput": 687.4, "total_tokens": 1115920} {"current_steps": 3990, "total_steps": 40000, "loss": 0.0, "lr": 4.87830783212702e-05, "epoch": 44.333333333333336, "percentage": 9.98, "elapsed_time": "0:27:05", "remaining_time": "4:04:28", "throughput": 687.41, "total_tokens": 1117280} {"current_steps": 3995, "total_steps": 40000, "loss": 0.0, "lr": 4.878005078797413e-05, "epoch": 44.388888888888886, "percentage": 9.99, "elapsed_time": "0:27:07", "remaining_time": "4:04:26", "throughput": 687.44, "total_tokens": 1118672} {"current_steps": 4000, "total_steps": 40000, "loss": 0.0, "lr": 4.877701958749539e-05, "epoch": 44.44444444444444, "percentage": 10.0, "elapsed_time": "0:27:09", "remaining_time": "4:04:23", "throughput": 687.48, "total_tokens": 1120080} {"current_steps": 4000, "total_steps": 40000, "eval_loss": 0.2292131930589676, "epoch": 44.44444444444444, "percentage": 10.0, "elapsed_time": "0:27:10", "remaining_time": "4:04:35", "throughput": 686.92, "total_tokens": 1120080} {"current_steps": 4005, "total_steps": 40000, "loss": 0.0, "lr": 4.877398472030142e-05, "epoch": 44.5, "percentage": 10.01, "elapsed_time": "0:27:13", "remaining_time": "4:04:43", "throughput": 686.4, "total_tokens": 1121440} {"current_steps": 4010, "total_steps": 40000, "loss": 0.0, "lr": 4.877094618686024e-05, "epoch": 44.55555555555556, "percentage": 10.03, "elapsed_time": "0:27:15", "remaining_time": "4:04:40", "throughput": 686.44, "total_tokens": 1122848} {"current_steps": 4015, "total_steps": 40000, "loss": 0.0, "lr": 4.876790398764045e-05, "epoch": 44.611111111111114, "percentage": 10.04, "elapsed_time": "0:27:17", "remaining_time": "4:04:38", "throughput": 686.49, "total_tokens": 1124272} {"current_steps": 4020, "total_steps": 40000, "loss": 0.0, "lr": 4.8764858123111167e-05, "epoch": 44.666666666666664, "percentage": 10.05, "elapsed_time": "0:27:19", "remaining_time": "4:04:36", "throughput": 686.48, "total_tokens": 1125648} {"current_steps": 4025, "total_steps": 40000, "loss": 0.0, "lr": 4.876180859374212e-05, "epoch": 44.72222222222222, "percentage": 10.06, "elapsed_time": "0:27:21", "remaining_time": "4:04:33", "throughput": 686.53, "total_tokens": 1127072} {"current_steps": 4030, "total_steps": 40000, "loss": 0.0, "lr": 4.875875540000357e-05, "epoch": 44.77777777777778, "percentage": 10.08, "elapsed_time": "0:27:23", "remaining_time": "4:04:30", "throughput": 686.57, "total_tokens": 1128480} {"current_steps": 4035, "total_steps": 40000, "loss": 0.0, "lr": 4.8755698542366376e-05, "epoch": 44.833333333333336, "percentage": 10.09, "elapsed_time": "0:27:25", "remaining_time": "4:04:27", "throughput": 686.62, "total_tokens": 1129904} {"current_steps": 4040, "total_steps": 40000, "loss": 0.0, "lr": 4.875263802130193e-05, "epoch": 44.888888888888886, "percentage": 10.1, "elapsed_time": "0:27:27", "remaining_time": "4:04:24", "throughput": 686.67, "total_tokens": 1131328} {"current_steps": 4045, "total_steps": 40000, "loss": 0.0, "lr": 4.8749573837282207e-05, "epoch": 44.94444444444444, "percentage": 10.11, "elapsed_time": "0:27:29", "remaining_time": "4:04:21", "throughput": 686.71, "total_tokens": 1132720} {"current_steps": 4050, "total_steps": 40000, "loss": 0.0, "lr": 4.874650599077974e-05, "epoch": 45.0, "percentage": 10.12, "elapsed_time": "0:27:31", "remaining_time": "4:04:20", "throughput": 686.67, "total_tokens": 1134128} {"current_steps": 4055, "total_steps": 40000, "loss": 0.0, "lr": 4.874343448226764e-05, "epoch": 45.05555555555556, "percentage": 10.14, "elapsed_time": "0:27:33", "remaining_time": "4:04:20", "throughput": 686.62, "total_tokens": 1135552} {"current_steps": 4060, "total_steps": 40000, "loss": 0.0, "lr": 4.874035931221955e-05, "epoch": 45.111111111111114, "percentage": 10.15, "elapsed_time": "0:27:35", "remaining_time": "4:04:17", "throughput": 686.66, "total_tokens": 1136960} {"current_steps": 4065, "total_steps": 40000, "loss": 0.0, "lr": 4.8737280481109724e-05, "epoch": 45.166666666666664, "percentage": 10.16, "elapsed_time": "0:27:37", "remaining_time": "4:04:14", "throughput": 686.69, "total_tokens": 1138352} {"current_steps": 4070, "total_steps": 40000, "loss": 0.0, "lr": 4.873419798941294e-05, "epoch": 45.22222222222222, "percentage": 10.17, "elapsed_time": "0:27:39", "remaining_time": "4:04:11", "throughput": 686.73, "total_tokens": 1139760} {"current_steps": 4075, "total_steps": 40000, "loss": 0.0, "lr": 4.873111183760458e-05, "epoch": 45.27777777777778, "percentage": 10.19, "elapsed_time": "0:27:41", "remaining_time": "4:04:08", "throughput": 686.78, "total_tokens": 1141184} {"current_steps": 4080, "total_steps": 40000, "loss": 0.0, "lr": 4.8728022026160537e-05, "epoch": 45.333333333333336, "percentage": 10.2, "elapsed_time": "0:27:43", "remaining_time": "4:04:06", "throughput": 686.81, "total_tokens": 1142560} {"current_steps": 4085, "total_steps": 40000, "loss": 0.0, "lr": 4.872492855555732e-05, "epoch": 45.388888888888886, "percentage": 10.21, "elapsed_time": "0:27:45", "remaining_time": "4:04:03", "throughput": 686.82, "total_tokens": 1143920} {"current_steps": 4090, "total_steps": 40000, "loss": 0.0, "lr": 4.8721831426271956e-05, "epoch": 45.44444444444444, "percentage": 10.22, "elapsed_time": "0:27:47", "remaining_time": "4:04:00", "throughput": 686.85, "total_tokens": 1145312} {"current_steps": 4095, "total_steps": 40000, "loss": 0.0, "lr": 4.87187306387821e-05, "epoch": 45.5, "percentage": 10.24, "elapsed_time": "0:27:49", "remaining_time": "4:03:57", "throughput": 686.91, "total_tokens": 1146736} {"current_steps": 4100, "total_steps": 40000, "loss": 0.0, "lr": 4.87156261935659e-05, "epoch": 45.55555555555556, "percentage": 10.25, "elapsed_time": "0:27:51", "remaining_time": "4:03:54", "throughput": 686.96, "total_tokens": 1148160} {"current_steps": 4105, "total_steps": 40000, "loss": 0.0, "lr": 4.871251809110211e-05, "epoch": 45.611111111111114, "percentage": 10.26, "elapsed_time": "0:27:53", "remaining_time": "4:03:51", "throughput": 687.0, "total_tokens": 1149568} {"current_steps": 4110, "total_steps": 40000, "loss": 0.0, "lr": 4.8709406331870044e-05, "epoch": 45.666666666666664, "percentage": 10.27, "elapsed_time": "0:27:55", "remaining_time": "4:03:48", "throughput": 687.03, "total_tokens": 1150944} {"current_steps": 4115, "total_steps": 40000, "loss": 0.0, "lr": 4.8706290916349574e-05, "epoch": 45.72222222222222, "percentage": 10.29, "elapsed_time": "0:27:57", "remaining_time": "4:03:45", "throughput": 687.08, "total_tokens": 1152352} {"current_steps": 4120, "total_steps": 40000, "loss": 0.0, "lr": 4.8703171845021134e-05, "epoch": 45.77777777777778, "percentage": 10.3, "elapsed_time": "0:27:59", "remaining_time": "4:03:43", "throughput": 687.12, "total_tokens": 1153760} {"current_steps": 4125, "total_steps": 40000, "loss": 0.0, "lr": 4.870004911836572e-05, "epoch": 45.833333333333336, "percentage": 10.31, "elapsed_time": "0:28:01", "remaining_time": "4:03:40", "throughput": 687.15, "total_tokens": 1155168} {"current_steps": 4130, "total_steps": 40000, "loss": 0.0, "lr": 4.869692273686489e-05, "epoch": 45.888888888888886, "percentage": 10.32, "elapsed_time": "0:28:03", "remaining_time": "4:03:37", "throughput": 687.18, "total_tokens": 1156560} {"current_steps": 4135, "total_steps": 40000, "loss": 0.0, "lr": 4.869379270100079e-05, "epoch": 45.94444444444444, "percentage": 10.34, "elapsed_time": "0:28:04", "remaining_time": "4:03:34", "throughput": 687.22, "total_tokens": 1157952} {"current_steps": 4140, "total_steps": 40000, "loss": 0.0, "lr": 4.86906590112561e-05, "epoch": 46.0, "percentage": 10.35, "elapsed_time": "0:28:07", "remaining_time": "4:03:33", "throughput": 687.18, "total_tokens": 1159328} {"current_steps": 4145, "total_steps": 40000, "loss": 0.0, "lr": 4.8687521668114064e-05, "epoch": 46.05555555555556, "percentage": 10.36, "elapsed_time": "0:28:09", "remaining_time": "4:03:32", "throughput": 687.1, "total_tokens": 1160720} {"current_steps": 4150, "total_steps": 40000, "loss": 0.0, "lr": 4.868438067205853e-05, "epoch": 46.111111111111114, "percentage": 10.38, "elapsed_time": "0:28:11", "remaining_time": "4:03:29", "throughput": 687.13, "total_tokens": 1162112} {"current_steps": 4155, "total_steps": 40000, "loss": 0.0, "lr": 4.8681236023573844e-05, "epoch": 46.166666666666664, "percentage": 10.39, "elapsed_time": "0:28:13", "remaining_time": "4:03:27", "throughput": 687.19, "total_tokens": 1163536} {"current_steps": 4160, "total_steps": 40000, "loss": 0.0, "lr": 4.867808772314497e-05, "epoch": 46.22222222222222, "percentage": 10.4, "elapsed_time": "0:28:15", "remaining_time": "4:03:24", "throughput": 687.26, "total_tokens": 1164992} {"current_steps": 4165, "total_steps": 40000, "loss": 0.0, "lr": 4.867493577125741e-05, "epoch": 46.27777777777778, "percentage": 10.41, "elapsed_time": "0:28:17", "remaining_time": "4:03:21", "throughput": 687.32, "total_tokens": 1166432} {"current_steps": 4170, "total_steps": 40000, "loss": 0.0, "lr": 4.867178016839725e-05, "epoch": 46.333333333333336, "percentage": 10.42, "elapsed_time": "0:28:19", "remaining_time": "4:03:18", "throughput": 687.36, "total_tokens": 1167840} {"current_steps": 4175, "total_steps": 40000, "loss": 0.0, "lr": 4.8668620915051094e-05, "epoch": 46.388888888888886, "percentage": 10.44, "elapsed_time": "0:28:20", "remaining_time": "4:03:15", "throughput": 687.4, "total_tokens": 1169232} {"current_steps": 4180, "total_steps": 40000, "loss": 0.0, "lr": 4.866545801170616e-05, "epoch": 46.44444444444444, "percentage": 10.45, "elapsed_time": "0:28:22", "remaining_time": "4:03:12", "throughput": 687.42, "total_tokens": 1170624} {"current_steps": 4185, "total_steps": 40000, "loss": 0.0, "lr": 4.86622914588502e-05, "epoch": 46.5, "percentage": 10.46, "elapsed_time": "0:28:24", "remaining_time": "4:03:09", "throughput": 687.48, "total_tokens": 1172048} {"current_steps": 4190, "total_steps": 40000, "loss": 0.0, "lr": 4.865912125697154e-05, "epoch": 46.55555555555556, "percentage": 10.47, "elapsed_time": "0:28:26", "remaining_time": "4:03:07", "throughput": 687.52, "total_tokens": 1173456} {"current_steps": 4195, "total_steps": 40000, "loss": 0.0, "lr": 4.865594740655907e-05, "epoch": 46.611111111111114, "percentage": 10.49, "elapsed_time": "0:28:28", "remaining_time": "4:03:04", "throughput": 687.56, "total_tokens": 1174864} {"current_steps": 4200, "total_steps": 40000, "loss": 0.0, "lr": 4.865276990810222e-05, "epoch": 46.666666666666664, "percentage": 10.5, "elapsed_time": "0:28:30", "remaining_time": "4:03:01", "throughput": 687.58, "total_tokens": 1176240} {"current_steps": 4200, "total_steps": 40000, "eval_loss": 0.24723908305168152, "epoch": 46.666666666666664, "percentage": 10.5, "elapsed_time": "0:28:32", "remaining_time": "4:03:12", "throughput": 687.05, "total_tokens": 1176240} {"current_steps": 4205, "total_steps": 40000, "loss": 0.0, "lr": 4.8649588762091016e-05, "epoch": 46.72222222222222, "percentage": 10.51, "elapsed_time": "0:28:35", "remaining_time": "4:03:21", "throughput": 686.51, "total_tokens": 1177616} {"current_steps": 4210, "total_steps": 40000, "loss": 0.0, "lr": 4.8646403969016016e-05, "epoch": 46.77777777777778, "percentage": 10.53, "elapsed_time": "0:28:37", "remaining_time": "4:03:19", "throughput": 686.51, "total_tokens": 1178992} {"current_steps": 4215, "total_steps": 40000, "loss": 0.0, "lr": 4.864321552936838e-05, "epoch": 46.833333333333336, "percentage": 10.54, "elapsed_time": "0:28:39", "remaining_time": "4:03:16", "throughput": 686.54, "total_tokens": 1180384} {"current_steps": 4220, "total_steps": 40000, "loss": 0.0, "lr": 4.864002344363978e-05, "epoch": 46.888888888888886, "percentage": 10.55, "elapsed_time": "0:28:41", "remaining_time": "4:03:14", "throughput": 686.55, "total_tokens": 1181760} {"current_steps": 4225, "total_steps": 40000, "loss": 0.0, "lr": 4.863682771232248e-05, "epoch": 46.94444444444444, "percentage": 10.56, "elapsed_time": "0:28:43", "remaining_time": "4:03:11", "throughput": 686.6, "total_tokens": 1183184} {"current_steps": 4230, "total_steps": 40000, "loss": 0.0, "lr": 4.8633628335909324e-05, "epoch": 47.0, "percentage": 10.57, "elapsed_time": "0:28:45", "remaining_time": "4:03:10", "throughput": 686.56, "total_tokens": 1184576} {"current_steps": 4235, "total_steps": 40000, "loss": 0.0, "lr": 4.8630425314893676e-05, "epoch": 47.05555555555556, "percentage": 10.59, "elapsed_time": "0:28:47", "remaining_time": "4:03:09", "throughput": 686.48, "total_tokens": 1185952} {"current_steps": 4240, "total_steps": 40000, "loss": 0.0, "lr": 4.862721864976948e-05, "epoch": 47.111111111111114, "percentage": 10.6, "elapsed_time": "0:28:49", "remaining_time": "4:03:06", "throughput": 686.52, "total_tokens": 1187360} {"current_steps": 4245, "total_steps": 40000, "loss": 0.0, "lr": 4.862400834103125e-05, "epoch": 47.166666666666664, "percentage": 10.61, "elapsed_time": "0:28:51", "remaining_time": "4:03:04", "throughput": 686.57, "total_tokens": 1188784} {"current_steps": 4250, "total_steps": 40000, "loss": 0.0, "lr": 4.862079438917406e-05, "epoch": 47.22222222222222, "percentage": 10.62, "elapsed_time": "0:28:53", "remaining_time": "4:03:01", "throughput": 686.61, "total_tokens": 1190192} {"current_steps": 4255, "total_steps": 40000, "loss": 0.0, "lr": 4.8617576794693536e-05, "epoch": 47.27777777777778, "percentage": 10.64, "elapsed_time": "0:28:55", "remaining_time": "4:02:58", "throughput": 686.65, "total_tokens": 1191584} {"current_steps": 4260, "total_steps": 40000, "loss": 0.0, "lr": 4.8614355558085875e-05, "epoch": 47.333333333333336, "percentage": 10.65, "elapsed_time": "0:28:57", "remaining_time": "4:02:55", "throughput": 686.68, "total_tokens": 1192976} {"current_steps": 4265, "total_steps": 40000, "loss": 0.0, "lr": 4.861113067984783e-05, "epoch": 47.388888888888886, "percentage": 10.66, "elapsed_time": "0:28:59", "remaining_time": "4:02:52", "throughput": 686.7, "total_tokens": 1194336} {"current_steps": 4270, "total_steps": 40000, "loss": 0.0, "lr": 4.860790216047671e-05, "epoch": 47.44444444444444, "percentage": 10.67, "elapsed_time": "0:29:01", "remaining_time": "4:02:49", "throughput": 686.75, "total_tokens": 1195760} {"current_steps": 4275, "total_steps": 40000, "loss": 0.0, "lr": 4.860467000047041e-05, "epoch": 47.5, "percentage": 10.69, "elapsed_time": "0:29:03", "remaining_time": "4:02:46", "throughput": 686.75, "total_tokens": 1197104} {"current_steps": 4280, "total_steps": 40000, "loss": 0.0, "lr": 4.860143420032737e-05, "epoch": 47.55555555555556, "percentage": 10.7, "elapsed_time": "0:29:05", "remaining_time": "4:02:44", "throughput": 686.78, "total_tokens": 1198496} {"current_steps": 4285, "total_steps": 40000, "loss": 0.0, "lr": 4.859819476054657e-05, "epoch": 47.611111111111114, "percentage": 10.71, "elapsed_time": "0:29:07", "remaining_time": "4:02:41", "throughput": 686.82, "total_tokens": 1199888} {"current_steps": 4290, "total_steps": 40000, "loss": 0.0, "lr": 4.859495168162758e-05, "epoch": 47.666666666666664, "percentage": 10.72, "elapsed_time": "0:29:08", "remaining_time": "4:02:38", "throughput": 686.86, "total_tokens": 1201296} {"current_steps": 4295, "total_steps": 40000, "loss": 0.0, "lr": 4.859170496407054e-05, "epoch": 47.72222222222222, "percentage": 10.74, "elapsed_time": "0:29:10", "remaining_time": "4:02:35", "throughput": 686.89, "total_tokens": 1202672} {"current_steps": 4300, "total_steps": 40000, "loss": 0.0, "lr": 4.8588454608376114e-05, "epoch": 47.77777777777778, "percentage": 10.75, "elapsed_time": "0:29:12", "remaining_time": "4:02:32", "throughput": 686.93, "total_tokens": 1204080} {"current_steps": 4305, "total_steps": 40000, "loss": 0.0, "lr": 4.8585200615045555e-05, "epoch": 47.833333333333336, "percentage": 10.76, "elapsed_time": "0:29:14", "remaining_time": "4:02:29", "throughput": 686.96, "total_tokens": 1205472} {"current_steps": 4310, "total_steps": 40000, "loss": 0.0, "lr": 4.8581942984580674e-05, "epoch": 47.888888888888886, "percentage": 10.78, "elapsed_time": "0:29:16", "remaining_time": "4:02:27", "throughput": 687.04, "total_tokens": 1206944} {"current_steps": 4315, "total_steps": 40000, "loss": 0.0, "lr": 4.857868171748384e-05, "epoch": 47.94444444444444, "percentage": 10.79, "elapsed_time": "0:29:18", "remaining_time": "4:02:24", "throughput": 687.11, "total_tokens": 1208416} {"current_steps": 4320, "total_steps": 40000, "loss": 0.0, "lr": 4.8575416814257976e-05, "epoch": 48.0, "percentage": 10.8, "elapsed_time": "0:29:20", "remaining_time": "4:02:22", "throughput": 687.07, "total_tokens": 1209792} {"current_steps": 4325, "total_steps": 40000, "loss": 0.0, "lr": 4.857214827540657e-05, "epoch": 48.05555555555556, "percentage": 10.81, "elapsed_time": "0:29:23", "remaining_time": "4:02:22", "throughput": 687.02, "total_tokens": 1211232} {"current_steps": 4330, "total_steps": 40000, "loss": 0.0, "lr": 4.856887610143367e-05, "epoch": 48.111111111111114, "percentage": 10.82, "elapsed_time": "0:29:24", "remaining_time": "4:02:19", "throughput": 687.04, "total_tokens": 1212592} {"current_steps": 4335, "total_steps": 40000, "loss": 0.0, "lr": 4.8565600292843896e-05, "epoch": 48.166666666666664, "percentage": 10.84, "elapsed_time": "0:29:26", "remaining_time": "4:02:16", "throughput": 687.07, "total_tokens": 1213984} {"current_steps": 4340, "total_steps": 40000, "loss": 0.0, "lr": 4.856232085014241e-05, "epoch": 48.22222222222222, "percentage": 10.85, "elapsed_time": "0:29:28", "remaining_time": "4:02:13", "throughput": 687.14, "total_tokens": 1215456} {"current_steps": 4345, "total_steps": 40000, "loss": 0.0, "lr": 4.855903777383495e-05, "epoch": 48.27777777777778, "percentage": 10.86, "elapsed_time": "0:29:30", "remaining_time": "4:02:11", "throughput": 687.2, "total_tokens": 1216912} {"current_steps": 4350, "total_steps": 40000, "loss": 0.0, "lr": 4.85557510644278e-05, "epoch": 48.333333333333336, "percentage": 10.88, "elapsed_time": "0:29:32", "remaining_time": "4:02:08", "throughput": 687.26, "total_tokens": 1218352} {"current_steps": 4355, "total_steps": 40000, "loss": 0.0, "lr": 4.855246072242782e-05, "epoch": 48.388888888888886, "percentage": 10.89, "elapsed_time": "0:29:34", "remaining_time": "4:02:05", "throughput": 687.27, "total_tokens": 1219712} {"current_steps": 4360, "total_steps": 40000, "loss": 0.0, "lr": 4.8549166748342414e-05, "epoch": 48.44444444444444, "percentage": 10.9, "elapsed_time": "0:29:36", "remaining_time": "4:02:03", "throughput": 687.31, "total_tokens": 1221120} {"current_steps": 4365, "total_steps": 40000, "loss": 0.0, "lr": 4.8545869142679556e-05, "epoch": 48.5, "percentage": 10.91, "elapsed_time": "0:29:38", "remaining_time": "4:02:00", "throughput": 687.29, "total_tokens": 1222448} {"current_steps": 4370, "total_steps": 40000, "loss": 0.0, "lr": 4.8542567905947776e-05, "epoch": 48.55555555555556, "percentage": 10.93, "elapsed_time": "0:29:40", "remaining_time": "4:01:57", "throughput": 687.3, "total_tokens": 1223808} {"current_steps": 4375, "total_steps": 40000, "loss": 0.0, "lr": 4.853926303865618e-05, "epoch": 48.611111111111114, "percentage": 10.94, "elapsed_time": "0:29:42", "remaining_time": "4:01:54", "throughput": 687.33, "total_tokens": 1225200} {"current_steps": 4380, "total_steps": 40000, "loss": 0.0, "lr": 4.853595454131441e-05, "epoch": 48.666666666666664, "percentage": 10.95, "elapsed_time": "0:29:44", "remaining_time": "4:01:52", "throughput": 687.35, "total_tokens": 1226560} {"current_steps": 4385, "total_steps": 40000, "loss": 0.0, "lr": 4.8532642414432674e-05, "epoch": 48.72222222222222, "percentage": 10.96, "elapsed_time": "0:29:46", "remaining_time": "4:01:49", "throughput": 687.37, "total_tokens": 1227952} {"current_steps": 4390, "total_steps": 40000, "loss": 0.0, "lr": 4.8529326658521754e-05, "epoch": 48.77777777777778, "percentage": 10.97, "elapsed_time": "0:29:48", "remaining_time": "4:01:46", "throughput": 687.42, "total_tokens": 1229376} {"current_steps": 4395, "total_steps": 40000, "loss": 0.0, "lr": 4.8526007274092965e-05, "epoch": 48.833333333333336, "percentage": 10.99, "elapsed_time": "0:29:50", "remaining_time": "4:01:43", "throughput": 687.45, "total_tokens": 1230768} {"current_steps": 4400, "total_steps": 40000, "loss": 0.0, "lr": 4.852268426165822e-05, "epoch": 48.888888888888886, "percentage": 11.0, "elapsed_time": "0:29:52", "remaining_time": "4:01:41", "throughput": 687.49, "total_tokens": 1232160} {"current_steps": 4400, "total_steps": 40000, "eval_loss": 0.2371339350938797, "epoch": 48.888888888888886, "percentage": 11.0, "elapsed_time": "0:29:53", "remaining_time": "4:01:51", "throughput": 686.98, "total_tokens": 1232160} {"current_steps": 4405, "total_steps": 40000, "loss": 0.0, "lr": 4.851935762172995e-05, "epoch": 48.94444444444444, "percentage": 11.01, "elapsed_time": "0:29:56", "remaining_time": "4:01:59", "throughput": 686.53, "total_tokens": 1233584} {"current_steps": 4410, "total_steps": 40000, "loss": 0.0, "lr": 4.8516027354821175e-05, "epoch": 49.0, "percentage": 11.03, "elapsed_time": "0:29:59", "remaining_time": "4:01:58", "throughput": 686.47, "total_tokens": 1234976} {"current_steps": 4415, "total_steps": 40000, "loss": 0.0, "lr": 4.851269346144546e-05, "epoch": 49.05555555555556, "percentage": 11.04, "elapsed_time": "0:30:01", "remaining_time": "4:01:58", "throughput": 686.36, "total_tokens": 1236320} {"current_steps": 4420, "total_steps": 40000, "loss": 0.0, "lr": 4.850935594211693e-05, "epoch": 49.111111111111114, "percentage": 11.05, "elapsed_time": "0:30:03", "remaining_time": "4:01:55", "throughput": 686.41, "total_tokens": 1237760} {"current_steps": 4425, "total_steps": 40000, "loss": 0.0, "lr": 4.850601479735029e-05, "epoch": 49.166666666666664, "percentage": 11.06, "elapsed_time": "0:30:05", "remaining_time": "4:01:52", "throughput": 686.45, "total_tokens": 1239168} {"current_steps": 4430, "total_steps": 40000, "loss": 0.0, "lr": 4.850267002766076e-05, "epoch": 49.22222222222222, "percentage": 11.07, "elapsed_time": "0:30:07", "remaining_time": "4:01:50", "throughput": 686.5, "total_tokens": 1240592} {"current_steps": 4435, "total_steps": 40000, "loss": 0.0, "lr": 4.849932163356417e-05, "epoch": 49.27777777777778, "percentage": 11.09, "elapsed_time": "0:30:09", "remaining_time": "4:01:47", "throughput": 686.54, "total_tokens": 1242000} {"current_steps": 4440, "total_steps": 40000, "loss": 0.0, "lr": 4.8495969615576864e-05, "epoch": 49.333333333333336, "percentage": 11.1, "elapsed_time": "0:30:11", "remaining_time": "4:01:44", "throughput": 686.57, "total_tokens": 1243408} {"current_steps": 4445, "total_steps": 40000, "loss": 0.0, "lr": 4.849261397421577e-05, "epoch": 49.388888888888886, "percentage": 11.11, "elapsed_time": "0:30:12", "remaining_time": "4:01:41", "throughput": 686.61, "total_tokens": 1244816} {"current_steps": 4450, "total_steps": 40000, "loss": 0.0, "lr": 4.848925470999839e-05, "epoch": 49.44444444444444, "percentage": 11.12, "elapsed_time": "0:30:14", "remaining_time": "4:01:39", "throughput": 686.67, "total_tokens": 1246256} {"current_steps": 4455, "total_steps": 40000, "loss": 0.0, "lr": 4.848589182344273e-05, "epoch": 49.5, "percentage": 11.14, "elapsed_time": "0:30:16", "remaining_time": "4:01:36", "throughput": 686.7, "total_tokens": 1247664} {"current_steps": 4460, "total_steps": 40000, "loss": 0.0, "lr": 4.848252531506742e-05, "epoch": 49.55555555555556, "percentage": 11.15, "elapsed_time": "0:30:18", "remaining_time": "4:01:33", "throughput": 686.75, "total_tokens": 1249072} {"current_steps": 4465, "total_steps": 40000, "loss": 0.0, "lr": 4.847915518539161e-05, "epoch": 49.611111111111114, "percentage": 11.16, "elapsed_time": "0:30:20", "remaining_time": "4:01:30", "throughput": 686.78, "total_tokens": 1250464} {"current_steps": 4470, "total_steps": 40000, "loss": 0.0, "lr": 4.847578143493501e-05, "epoch": 49.666666666666664, "percentage": 11.18, "elapsed_time": "0:30:22", "remaining_time": "4:01:27", "throughput": 686.81, "total_tokens": 1251856} {"current_steps": 4475, "total_steps": 40000, "loss": 0.0, "lr": 4.847240406421789e-05, "epoch": 49.72222222222222, "percentage": 11.19, "elapsed_time": "0:30:24", "remaining_time": "4:01:25", "throughput": 686.83, "total_tokens": 1253248} {"current_steps": 4480, "total_steps": 40000, "loss": 0.0, "lr": 4.84690230737611e-05, "epoch": 49.77777777777778, "percentage": 11.2, "elapsed_time": "0:30:26", "remaining_time": "4:01:22", "throughput": 686.83, "total_tokens": 1254592} {"current_steps": 4485, "total_steps": 40000, "loss": 0.0, "lr": 4.846563846408602e-05, "epoch": 49.833333333333336, "percentage": 11.21, "elapsed_time": "0:30:28", "remaining_time": "4:01:20", "throughput": 686.85, "total_tokens": 1255984} {"current_steps": 4490, "total_steps": 40000, "loss": 0.0, "lr": 4.84622502357146e-05, "epoch": 49.888888888888886, "percentage": 11.22, "elapsed_time": "0:30:30", "remaining_time": "4:01:17", "throughput": 686.89, "total_tokens": 1257408} {"current_steps": 4495, "total_steps": 40000, "loss": 0.0, "lr": 4.8458858389169345e-05, "epoch": 49.94444444444444, "percentage": 11.24, "elapsed_time": "0:30:32", "remaining_time": "4:01:14", "throughput": 686.89, "total_tokens": 1258752} {"current_steps": 4500, "total_steps": 40000, "loss": 0.0, "lr": 4.8455462924973334e-05, "epoch": 50.0, "percentage": 11.25, "elapsed_time": "0:30:34", "remaining_time": "4:01:13", "throughput": 686.86, "total_tokens": 1260144} {"current_steps": 4505, "total_steps": 40000, "loss": 0.0, "lr": 4.845206384365018e-05, "epoch": 50.05555555555556, "percentage": 11.26, "elapsed_time": "0:30:36", "remaining_time": "4:01:12", "throughput": 686.79, "total_tokens": 1261552} {"current_steps": 4510, "total_steps": 40000, "loss": 0.0, "lr": 4.844866114572405e-05, "epoch": 50.111111111111114, "percentage": 11.28, "elapsed_time": "0:30:38", "remaining_time": "4:01:10", "throughput": 686.82, "total_tokens": 1262944} {"current_steps": 4515, "total_steps": 40000, "loss": 0.0, "lr": 4.8445254831719706e-05, "epoch": 50.166666666666664, "percentage": 11.29, "elapsed_time": "0:30:40", "remaining_time": "4:01:07", "throughput": 686.85, "total_tokens": 1264336} {"current_steps": 4520, "total_steps": 40000, "loss": 0.0, "lr": 4.8441844902162434e-05, "epoch": 50.22222222222222, "percentage": 11.3, "elapsed_time": "0:30:42", "remaining_time": "4:01:04", "throughput": 686.88, "total_tokens": 1265728} {"current_steps": 4525, "total_steps": 40000, "loss": 0.0, "lr": 4.843843135757809e-05, "epoch": 50.27777777777778, "percentage": 11.31, "elapsed_time": "0:30:44", "remaining_time": "4:01:01", "throughput": 686.94, "total_tokens": 1267184} {"current_steps": 4530, "total_steps": 40000, "loss": 0.0, "lr": 4.843501419849308e-05, "epoch": 50.333333333333336, "percentage": 11.33, "elapsed_time": "0:30:46", "remaining_time": "4:00:59", "throughput": 686.97, "total_tokens": 1268592} {"current_steps": 4535, "total_steps": 40000, "loss": 0.0, "lr": 4.8431593425434386e-05, "epoch": 50.388888888888886, "percentage": 11.34, "elapsed_time": "0:30:48", "remaining_time": "4:00:56", "throughput": 687.03, "total_tokens": 1270032} {"current_steps": 4540, "total_steps": 40000, "loss": 0.0, "lr": 4.8428169038929526e-05, "epoch": 50.44444444444444, "percentage": 11.35, "elapsed_time": "0:30:50", "remaining_time": "4:00:53", "throughput": 687.03, "total_tokens": 1271376} {"current_steps": 4545, "total_steps": 40000, "loss": 0.0, "lr": 4.8424741039506575e-05, "epoch": 50.5, "percentage": 11.36, "elapsed_time": "0:30:52", "remaining_time": "4:00:51", "throughput": 687.07, "total_tokens": 1272784} {"current_steps": 4550, "total_steps": 40000, "loss": 0.0, "lr": 4.842130942769419e-05, "epoch": 50.55555555555556, "percentage": 11.38, "elapsed_time": "0:30:54", "remaining_time": "4:00:48", "throughput": 687.1, "total_tokens": 1274192} {"current_steps": 4555, "total_steps": 40000, "loss": 0.0, "lr": 4.841787420402156e-05, "epoch": 50.611111111111114, "percentage": 11.39, "elapsed_time": "0:30:56", "remaining_time": "4:00:45", "throughput": 687.13, "total_tokens": 1275584} {"current_steps": 4560, "total_steps": 40000, "loss": 0.0, "lr": 4.841443536901844e-05, "epoch": 50.666666666666664, "percentage": 11.4, "elapsed_time": "0:30:58", "remaining_time": "4:00:42", "throughput": 687.18, "total_tokens": 1277008} {"current_steps": 4565, "total_steps": 40000, "loss": 0.0, "lr": 4.841099292321514e-05, "epoch": 50.72222222222222, "percentage": 11.41, "elapsed_time": "0:31:00", "remaining_time": "4:00:40", "throughput": 687.22, "total_tokens": 1278432} {"current_steps": 4570, "total_steps": 40000, "loss": 0.0, "lr": 4.8407546867142525e-05, "epoch": 50.77777777777778, "percentage": 11.43, "elapsed_time": "0:31:02", "remaining_time": "4:00:37", "throughput": 687.24, "total_tokens": 1279808} {"current_steps": 4575, "total_steps": 40000, "loss": 0.0, "lr": 4.840409720133203e-05, "epoch": 50.833333333333336, "percentage": 11.44, "elapsed_time": "0:31:04", "remaining_time": "4:00:34", "throughput": 687.24, "total_tokens": 1281152} {"current_steps": 4580, "total_steps": 40000, "loss": 0.0, "lr": 4.8400643926315634e-05, "epoch": 50.888888888888886, "percentage": 11.45, "elapsed_time": "0:31:06", "remaining_time": "4:00:32", "throughput": 687.3, "total_tokens": 1282592} {"current_steps": 4585, "total_steps": 40000, "loss": 0.0, "lr": 4.839718704262587e-05, "epoch": 50.94444444444444, "percentage": 11.46, "elapsed_time": "0:31:08", "remaining_time": "4:00:29", "throughput": 687.32, "total_tokens": 1283968} {"current_steps": 4590, "total_steps": 40000, "loss": 0.0, "lr": 4.839372655079585e-05, "epoch": 51.0, "percentage": 11.47, "elapsed_time": "0:31:10", "remaining_time": "4:00:27", "throughput": 687.28, "total_tokens": 1285344} {"current_steps": 4595, "total_steps": 40000, "loss": 0.0, "lr": 4.83902624513592e-05, "epoch": 51.05555555555556, "percentage": 11.49, "elapsed_time": "0:31:12", "remaining_time": "4:00:27", "throughput": 687.22, "total_tokens": 1286768} {"current_steps": 4600, "total_steps": 40000, "loss": 0.0, "lr": 4.838679474485014e-05, "epoch": 51.111111111111114, "percentage": 11.5, "elapsed_time": "0:31:14", "remaining_time": "4:00:24", "throughput": 687.24, "total_tokens": 1288160} {"current_steps": 4600, "total_steps": 40000, "eval_loss": 0.2620989680290222, "epoch": 51.111111111111114, "percentage": 11.5, "elapsed_time": "0:31:15", "remaining_time": "4:00:34", "throughput": 686.76, "total_tokens": 1288160} {"current_steps": 4605, "total_steps": 40000, "loss": 0.0, "lr": 4.838332343180343e-05, "epoch": 51.166666666666664, "percentage": 11.51, "elapsed_time": "0:31:18", "remaining_time": "4:00:41", "throughput": 686.31, "total_tokens": 1289536} {"current_steps": 4610, "total_steps": 40000, "loss": 0.0, "lr": 4.83798485127544e-05, "epoch": 51.22222222222222, "percentage": 11.53, "elapsed_time": "0:31:20", "remaining_time": "4:00:39", "throughput": 686.31, "total_tokens": 1290912} {"current_steps": 4615, "total_steps": 40000, "loss": 0.0, "lr": 4.837636998823892e-05, "epoch": 51.27777777777778, "percentage": 11.54, "elapsed_time": "0:31:22", "remaining_time": "4:00:37", "throughput": 686.33, "total_tokens": 1292304} {"current_steps": 4620, "total_steps": 40000, "loss": 0.0, "lr": 4.8372887858793414e-05, "epoch": 51.333333333333336, "percentage": 11.55, "elapsed_time": "0:31:24", "remaining_time": "4:00:34", "throughput": 686.35, "total_tokens": 1293664} {"current_steps": 4625, "total_steps": 40000, "loss": 0.0, "lr": 4.836940212495489e-05, "epoch": 51.388888888888886, "percentage": 11.56, "elapsed_time": "0:31:26", "remaining_time": "4:00:31", "throughput": 686.41, "total_tokens": 1295120} {"current_steps": 4630, "total_steps": 40000, "loss": 0.0, "lr": 4.836591278726087e-05, "epoch": 51.44444444444444, "percentage": 11.58, "elapsed_time": "0:31:28", "remaining_time": "4:00:28", "throughput": 686.47, "total_tokens": 1296560} {"current_steps": 4635, "total_steps": 40000, "loss": 0.0, "lr": 4.836241984624947e-05, "epoch": 51.5, "percentage": 11.59, "elapsed_time": "0:31:30", "remaining_time": "4:00:25", "throughput": 686.52, "total_tokens": 1298000} {"current_steps": 4640, "total_steps": 40000, "loss": 0.0, "lr": 4.8358923302459336e-05, "epoch": 51.55555555555556, "percentage": 11.6, "elapsed_time": "0:31:32", "remaining_time": "4:00:23", "throughput": 686.56, "total_tokens": 1299408} {"current_steps": 4645, "total_steps": 40000, "loss": 0.0, "lr": 4.835542315642968e-05, "epoch": 51.611111111111114, "percentage": 11.61, "elapsed_time": "0:31:34", "remaining_time": "4:00:20", "throughput": 686.59, "total_tokens": 1300800} {"current_steps": 4650, "total_steps": 40000, "loss": 0.0, "lr": 4.8351919408700274e-05, "epoch": 51.666666666666664, "percentage": 11.62, "elapsed_time": "0:31:36", "remaining_time": "4:00:17", "throughput": 686.61, "total_tokens": 1302176} {"current_steps": 4655, "total_steps": 40000, "loss": 0.0, "lr": 4.834841205981144e-05, "epoch": 51.72222222222222, "percentage": 11.64, "elapsed_time": "0:31:38", "remaining_time": "4:00:14", "throughput": 686.64, "total_tokens": 1303568} {"current_steps": 4660, "total_steps": 40000, "loss": 0.0, "lr": 4.8344901110304054e-05, "epoch": 51.77777777777778, "percentage": 11.65, "elapsed_time": "0:31:40", "remaining_time": "4:00:12", "throughput": 686.7, "total_tokens": 1305008} {"current_steps": 4665, "total_steps": 40000, "loss": 0.0, "lr": 4.8341386560719534e-05, "epoch": 51.833333333333336, "percentage": 11.66, "elapsed_time": "0:31:42", "remaining_time": "4:00:09", "throughput": 686.72, "total_tokens": 1306368} {"current_steps": 4670, "total_steps": 40000, "loss": 0.0, "lr": 4.833786841159989e-05, "epoch": 51.888888888888886, "percentage": 11.68, "elapsed_time": "0:31:44", "remaining_time": "4:00:06", "throughput": 686.74, "total_tokens": 1307760} {"current_steps": 4675, "total_steps": 40000, "loss": 0.0, "lr": 4.833434666348765e-05, "epoch": 51.94444444444444, "percentage": 11.69, "elapsed_time": "0:31:46", "remaining_time": "4:00:03", "throughput": 686.79, "total_tokens": 1309184} {"current_steps": 4680, "total_steps": 40000, "loss": 0.0, "lr": 4.833082131692592e-05, "epoch": 52.0, "percentage": 11.7, "elapsed_time": "0:31:48", "remaining_time": "4:00:02", "throughput": 686.75, "total_tokens": 1310560} {"current_steps": 4685, "total_steps": 40000, "loss": 0.0, "lr": 4.832729237245835e-05, "epoch": 52.05555555555556, "percentage": 11.71, "elapsed_time": "0:31:50", "remaining_time": "4:00:01", "throughput": 686.67, "total_tokens": 1311920} {"current_steps": 4690, "total_steps": 40000, "loss": 0.0, "lr": 4.8323759830629145e-05, "epoch": 52.111111111111114, "percentage": 11.72, "elapsed_time": "0:31:52", "remaining_time": "3:59:58", "throughput": 686.7, "total_tokens": 1313312} {"current_steps": 4695, "total_steps": 40000, "loss": 0.0, "lr": 4.8320223691983066e-05, "epoch": 52.166666666666664, "percentage": 11.74, "elapsed_time": "0:31:54", "remaining_time": "3:59:56", "throughput": 686.73, "total_tokens": 1314704} {"current_steps": 4700, "total_steps": 40000, "loss": 0.0, "lr": 4.831668395706544e-05, "epoch": 52.22222222222222, "percentage": 11.75, "elapsed_time": "0:31:56", "remaining_time": "3:59:53", "throughput": 686.78, "total_tokens": 1316144} {"current_steps": 4705, "total_steps": 40000, "loss": 0.0, "lr": 4.8313140626422125e-05, "epoch": 52.27777777777778, "percentage": 11.76, "elapsed_time": "0:31:58", "remaining_time": "3:59:50", "throughput": 686.81, "total_tokens": 1317536} {"current_steps": 4710, "total_steps": 40000, "loss": 0.0, "lr": 4.830959370059956e-05, "epoch": 52.333333333333336, "percentage": 11.77, "elapsed_time": "0:32:00", "remaining_time": "3:59:47", "throughput": 686.84, "total_tokens": 1318928} {"current_steps": 4715, "total_steps": 40000, "loss": 0.0, "lr": 4.830604318014472e-05, "epoch": 52.388888888888886, "percentage": 11.79, "elapsed_time": "0:32:02", "remaining_time": "3:59:45", "throughput": 686.87, "total_tokens": 1320320} {"current_steps": 4720, "total_steps": 40000, "loss": 0.0, "lr": 4.830248906560514e-05, "epoch": 52.44444444444444, "percentage": 11.8, "elapsed_time": "0:32:04", "remaining_time": "3:59:42", "throughput": 686.93, "total_tokens": 1321760} {"current_steps": 4725, "total_steps": 40000, "loss": 0.0, "lr": 4.829893135752891e-05, "epoch": 52.5, "percentage": 11.81, "elapsed_time": "0:32:06", "remaining_time": "3:59:39", "throughput": 687.0, "total_tokens": 1323232} {"current_steps": 4730, "total_steps": 40000, "loss": 0.0, "lr": 4.829537005646466e-05, "epoch": 52.55555555555556, "percentage": 11.82, "elapsed_time": "0:32:08", "remaining_time": "3:59:36", "throughput": 687.02, "total_tokens": 1324608} {"current_steps": 4735, "total_steps": 40000, "loss": 0.0, "lr": 4.8291805162961615e-05, "epoch": 52.611111111111114, "percentage": 11.84, "elapsed_time": "0:32:09", "remaining_time": "3:59:34", "throughput": 687.05, "total_tokens": 1326000} {"current_steps": 4740, "total_steps": 40000, "loss": 0.0, "lr": 4.82882366775695e-05, "epoch": 52.666666666666664, "percentage": 11.85, "elapsed_time": "0:32:11", "remaining_time": "3:59:31", "throughput": 687.07, "total_tokens": 1327376} {"current_steps": 4745, "total_steps": 40000, "loss": 0.0, "lr": 4.828466460083864e-05, "epoch": 52.72222222222222, "percentage": 11.86, "elapsed_time": "0:32:13", "remaining_time": "3:59:28", "throughput": 687.09, "total_tokens": 1328752} {"current_steps": 4750, "total_steps": 40000, "loss": 0.0, "lr": 4.8281088933319877e-05, "epoch": 52.77777777777778, "percentage": 11.88, "elapsed_time": "0:32:15", "remaining_time": "3:59:26", "throughput": 687.1, "total_tokens": 1330112} {"current_steps": 4755, "total_steps": 40000, "loss": 0.0, "lr": 4.827750967556464e-05, "epoch": 52.833333333333336, "percentage": 11.89, "elapsed_time": "0:32:17", "remaining_time": "3:59:23", "throughput": 687.13, "total_tokens": 1331520} {"current_steps": 4760, "total_steps": 40000, "loss": 0.0, "lr": 4.827392682812488e-05, "epoch": 52.888888888888886, "percentage": 11.9, "elapsed_time": "0:32:19", "remaining_time": "3:59:20", "throughput": 687.17, "total_tokens": 1332928} {"current_steps": 4765, "total_steps": 40000, "loss": 0.0, "lr": 4.827034039155312e-05, "epoch": 52.94444444444444, "percentage": 11.91, "elapsed_time": "0:32:21", "remaining_time": "3:59:17", "throughput": 687.21, "total_tokens": 1334336} {"current_steps": 4770, "total_steps": 40000, "loss": 0.0, "lr": 4.8266750366402445e-05, "epoch": 53.0, "percentage": 11.92, "elapsed_time": "0:32:23", "remaining_time": "3:59:16", "throughput": 687.2, "total_tokens": 1335760} {"current_steps": 4775, "total_steps": 40000, "loss": 0.0, "lr": 4.8263156753226476e-05, "epoch": 53.05555555555556, "percentage": 11.94, "elapsed_time": "0:32:25", "remaining_time": "3:59:15", "throughput": 687.13, "total_tokens": 1337136} {"current_steps": 4780, "total_steps": 40000, "loss": 0.0, "lr": 4.8259559552579394e-05, "epoch": 53.111111111111114, "percentage": 11.95, "elapsed_time": "0:32:27", "remaining_time": "3:59:12", "throughput": 687.13, "total_tokens": 1338496} {"current_steps": 4785, "total_steps": 40000, "loss": 0.0, "lr": 4.825595876501593e-05, "epoch": 53.166666666666664, "percentage": 11.96, "elapsed_time": "0:32:29", "remaining_time": "3:59:10", "throughput": 687.18, "total_tokens": 1339920} {"current_steps": 4790, "total_steps": 40000, "loss": 0.0, "lr": 4.825235439109137e-05, "epoch": 53.22222222222222, "percentage": 11.97, "elapsed_time": "0:32:31", "remaining_time": "3:59:07", "throughput": 687.22, "total_tokens": 1341344} {"current_steps": 4795, "total_steps": 40000, "loss": 0.0, "lr": 4.824874643136156e-05, "epoch": 53.27777777777778, "percentage": 11.99, "elapsed_time": "0:32:33", "remaining_time": "3:59:04", "throughput": 687.26, "total_tokens": 1342768} {"current_steps": 4800, "total_steps": 40000, "loss": 0.0, "lr": 4.824513488638288e-05, "epoch": 53.333333333333336, "percentage": 12.0, "elapsed_time": "0:32:35", "remaining_time": "3:59:02", "throughput": 687.29, "total_tokens": 1344160} {"current_steps": 4800, "total_steps": 40000, "eval_loss": 0.2626498341560364, "epoch": 53.333333333333336, "percentage": 12.0, "elapsed_time": "0:32:37", "remaining_time": "3:59:11", "throughput": 686.83, "total_tokens": 1344160} {"current_steps": 4805, "total_steps": 40000, "loss": 0.0, "lr": 4.8241519756712293e-05, "epoch": 53.388888888888886, "percentage": 12.01, "elapsed_time": "0:32:40", "remaining_time": "3:59:18", "throughput": 686.41, "total_tokens": 1345552} {"current_steps": 4810, "total_steps": 40000, "loss": 0.0, "lr": 4.8237901042907285e-05, "epoch": 53.44444444444444, "percentage": 12.03, "elapsed_time": "0:32:42", "remaining_time": "3:59:16", "throughput": 686.43, "total_tokens": 1346976} {"current_steps": 4815, "total_steps": 40000, "loss": 0.0, "lr": 4.823427874552591e-05, "epoch": 53.5, "percentage": 12.04, "elapsed_time": "0:32:44", "remaining_time": "3:59:13", "throughput": 686.48, "total_tokens": 1348400} {"current_steps": 4820, "total_steps": 40000, "loss": 0.0, "lr": 4.823065286512677e-05, "epoch": 53.55555555555556, "percentage": 12.05, "elapsed_time": "0:32:46", "remaining_time": "3:59:10", "throughput": 686.51, "total_tokens": 1349808} {"current_steps": 4825, "total_steps": 40000, "loss": 0.0, "lr": 4.8227023402269025e-05, "epoch": 53.611111111111114, "percentage": 12.06, "elapsed_time": "0:32:48", "remaining_time": "3:59:08", "throughput": 686.52, "total_tokens": 1351168} {"current_steps": 4830, "total_steps": 40000, "loss": 0.0, "lr": 4.822339035751239e-05, "epoch": 53.666666666666664, "percentage": 12.07, "elapsed_time": "0:32:50", "remaining_time": "3:59:05", "throughput": 686.54, "total_tokens": 1352560} {"current_steps": 4835, "total_steps": 40000, "loss": 0.0, "lr": 4.8219753731417104e-05, "epoch": 53.72222222222222, "percentage": 12.09, "elapsed_time": "0:32:52", "remaining_time": "3:59:02", "throughput": 686.57, "total_tokens": 1353936} {"current_steps": 4840, "total_steps": 40000, "loss": 0.0, "lr": 4.821611352454401e-05, "epoch": 53.77777777777778, "percentage": 12.1, "elapsed_time": "0:32:53", "remaining_time": "3:58:59", "throughput": 686.59, "total_tokens": 1355328} {"current_steps": 4845, "total_steps": 40000, "loss": 0.0, "lr": 4.8212469737454444e-05, "epoch": 53.833333333333336, "percentage": 12.11, "elapsed_time": "0:32:55", "remaining_time": "3:58:57", "throughput": 686.65, "total_tokens": 1356768} {"current_steps": 4850, "total_steps": 40000, "loss": 0.0, "lr": 4.820882237071035e-05, "epoch": 53.888888888888886, "percentage": 12.12, "elapsed_time": "0:32:57", "remaining_time": "3:58:54", "throughput": 686.7, "total_tokens": 1358208} {"current_steps": 4855, "total_steps": 40000, "loss": 0.0, "lr": 4.820517142487417e-05, "epoch": 53.94444444444444, "percentage": 12.14, "elapsed_time": "0:32:59", "remaining_time": "3:58:51", "throughput": 686.73, "total_tokens": 1359616} {"current_steps": 4860, "total_steps": 40000, "loss": 0.0, "lr": 4.8201516900508956e-05, "epoch": 54.0, "percentage": 12.15, "elapsed_time": "0:33:01", "remaining_time": "3:58:50", "throughput": 686.72, "total_tokens": 1361040} {"current_steps": 4865, "total_steps": 40000, "loss": 0.0, "lr": 4.819785879817827e-05, "epoch": 54.05555555555556, "percentage": 12.16, "elapsed_time": "0:33:04", "remaining_time": "3:58:49", "throughput": 686.65, "total_tokens": 1362416} {"current_steps": 4870, "total_steps": 40000, "loss": 0.0, "lr": 4.8194197118446226e-05, "epoch": 54.111111111111114, "percentage": 12.17, "elapsed_time": "0:33:06", "remaining_time": "3:58:46", "throughput": 686.68, "total_tokens": 1363824} {"current_steps": 4875, "total_steps": 40000, "loss": 0.0, "lr": 4.819053186187752e-05, "epoch": 54.166666666666664, "percentage": 12.19, "elapsed_time": "0:33:08", "remaining_time": "3:58:44", "throughput": 686.71, "total_tokens": 1365216} {"current_steps": 4880, "total_steps": 40000, "loss": 0.0, "lr": 4.818686302903736e-05, "epoch": 54.22222222222222, "percentage": 12.2, "elapsed_time": "0:33:09", "remaining_time": "3:58:41", "throughput": 686.75, "total_tokens": 1366624} {"current_steps": 4885, "total_steps": 40000, "loss": 0.0, "lr": 4.818319062049154e-05, "epoch": 54.27777777777778, "percentage": 12.21, "elapsed_time": "0:33:11", "remaining_time": "3:58:38", "throughput": 686.79, "total_tokens": 1368048} {"current_steps": 4890, "total_steps": 40000, "loss": 0.0, "lr": 4.817951463680639e-05, "epoch": 54.333333333333336, "percentage": 12.22, "elapsed_time": "0:33:13", "remaining_time": "3:58:36", "throughput": 686.81, "total_tokens": 1369424} {"current_steps": 4895, "total_steps": 40000, "loss": 0.0, "lr": 4.817583507854879e-05, "epoch": 54.388888888888886, "percentage": 12.24, "elapsed_time": "0:33:15", "remaining_time": "3:58:33", "throughput": 686.84, "total_tokens": 1370832} {"current_steps": 4900, "total_steps": 40000, "loss": 0.0, "lr": 4.817215194628617e-05, "epoch": 54.44444444444444, "percentage": 12.25, "elapsed_time": "0:33:17", "remaining_time": "3:58:30", "throughput": 686.89, "total_tokens": 1372272} {"current_steps": 4905, "total_steps": 40000, "loss": 0.0, "lr": 4.816846524058653e-05, "epoch": 54.5, "percentage": 12.26, "elapsed_time": "0:33:19", "remaining_time": "3:58:27", "throughput": 686.93, "total_tokens": 1373680} {"current_steps": 4910, "total_steps": 40000, "loss": 0.0, "lr": 4.816477496201839e-05, "epoch": 54.55555555555556, "percentage": 12.28, "elapsed_time": "0:33:21", "remaining_time": "3:58:25", "throughput": 686.96, "total_tokens": 1375072} {"current_steps": 4915, "total_steps": 40000, "loss": 0.0, "lr": 4.8161081111150845e-05, "epoch": 54.611111111111114, "percentage": 12.29, "elapsed_time": "0:33:23", "remaining_time": "3:58:22", "throughput": 686.98, "total_tokens": 1376448} {"current_steps": 4920, "total_steps": 40000, "loss": 0.0, "lr": 4.815738368855354e-05, "epoch": 54.666666666666664, "percentage": 12.3, "elapsed_time": "0:33:25", "remaining_time": "3:58:19", "throughput": 687.01, "total_tokens": 1377856} {"current_steps": 4925, "total_steps": 40000, "loss": 0.0, "lr": 4.815368269479664e-05, "epoch": 54.72222222222222, "percentage": 12.31, "elapsed_time": "0:33:27", "remaining_time": "3:58:17", "throughput": 687.03, "total_tokens": 1379216} {"current_steps": 4930, "total_steps": 40000, "loss": 0.0, "lr": 4.814997813045092e-05, "epoch": 54.77777777777778, "percentage": 12.32, "elapsed_time": "0:33:29", "remaining_time": "3:58:14", "throughput": 687.06, "total_tokens": 1380608} {"current_steps": 4935, "total_steps": 40000, "loss": 0.0, "lr": 4.814626999608764e-05, "epoch": 54.833333333333336, "percentage": 12.34, "elapsed_time": "0:33:31", "remaining_time": "3:58:11", "throughput": 687.09, "total_tokens": 1382016} {"current_steps": 4940, "total_steps": 40000, "loss": 0.0, "lr": 4.814255829227865e-05, "epoch": 54.888888888888886, "percentage": 12.35, "elapsed_time": "0:33:33", "remaining_time": "3:58:09", "throughput": 687.12, "total_tokens": 1383408} {"current_steps": 4945, "total_steps": 40000, "loss": 0.0, "lr": 4.813884301959635e-05, "epoch": 54.94444444444444, "percentage": 12.36, "elapsed_time": "0:33:35", "remaining_time": "3:58:06", "throughput": 687.16, "total_tokens": 1384832} {"current_steps": 4950, "total_steps": 40000, "loss": 0.0, "lr": 4.813512417861368e-05, "epoch": 55.0, "percentage": 12.38, "elapsed_time": "0:33:37", "remaining_time": "3:58:07", "throughput": 687.0, "total_tokens": 1386208} {"current_steps": 4955, "total_steps": 40000, "loss": 0.0, "lr": 4.813140176990411e-05, "epoch": 55.05555555555556, "percentage": 12.39, "elapsed_time": "0:33:39", "remaining_time": "3:58:06", "throughput": 686.94, "total_tokens": 1387584} {"current_steps": 4960, "total_steps": 40000, "loss": 0.0, "lr": 4.8127675794041714e-05, "epoch": 55.111111111111114, "percentage": 12.4, "elapsed_time": "0:33:41", "remaining_time": "3:58:03", "throughput": 686.98, "total_tokens": 1389008} {"current_steps": 4965, "total_steps": 40000, "loss": 0.0, "lr": 4.812394625160107e-05, "epoch": 55.166666666666664, "percentage": 12.41, "elapsed_time": "0:33:43", "remaining_time": "3:58:01", "throughput": 687.02, "total_tokens": 1390432} {"current_steps": 4970, "total_steps": 40000, "loss": 0.0, "lr": 4.812021314315732e-05, "epoch": 55.22222222222222, "percentage": 12.43, "elapsed_time": "0:33:45", "remaining_time": "3:57:58", "throughput": 687.04, "total_tokens": 1391808} {"current_steps": 4975, "total_steps": 40000, "loss": 0.0, "lr": 4.811647646928616e-05, "epoch": 55.27777777777778, "percentage": 12.44, "elapsed_time": "0:33:47", "remaining_time": "3:57:55", "throughput": 687.08, "total_tokens": 1393232} {"current_steps": 4980, "total_steps": 40000, "loss": 0.0, "lr": 4.8112736230563814e-05, "epoch": 55.333333333333336, "percentage": 12.45, "elapsed_time": "0:33:49", "remaining_time": "3:57:53", "throughput": 687.08, "total_tokens": 1394592} {"current_steps": 4985, "total_steps": 40000, "loss": 0.0, "lr": 4.81089924275671e-05, "epoch": 55.388888888888886, "percentage": 12.46, "elapsed_time": "0:33:51", "remaining_time": "3:57:50", "throughput": 687.11, "total_tokens": 1395984} {"current_steps": 4990, "total_steps": 40000, "loss": 0.0, "lr": 4.810524506087335e-05, "epoch": 55.44444444444444, "percentage": 12.47, "elapsed_time": "0:33:53", "remaining_time": "3:57:47", "throughput": 687.17, "total_tokens": 1397440} {"current_steps": 4995, "total_steps": 40000, "loss": 0.0, "lr": 4.810149413106044e-05, "epoch": 55.5, "percentage": 12.49, "elapsed_time": "0:33:55", "remaining_time": "3:57:45", "throughput": 687.23, "total_tokens": 1398896} {"current_steps": 5000, "total_steps": 40000, "loss": 0.0, "lr": 4.809773963870684e-05, "epoch": 55.55555555555556, "percentage": 12.5, "elapsed_time": "0:33:57", "remaining_time": "3:57:42", "throughput": 687.3, "total_tokens": 1400368} {"current_steps": 5000, "total_steps": 40000, "eval_loss": 0.26760876178741455, "epoch": 55.55555555555556, "percentage": 12.5, "elapsed_time": "0:33:58", "remaining_time": "3:57:51", "throughput": 686.86, "total_tokens": 1400368} {"current_steps": 5005, "total_steps": 40000, "loss": 0.0, "lr": 4.809398158439151e-05, "epoch": 55.611111111111114, "percentage": 12.51, "elapsed_time": "0:34:02", "remaining_time": "3:57:57", "throughput": 686.46, "total_tokens": 1401776} {"current_steps": 5010, "total_steps": 40000, "loss": 0.0, "lr": 4.8090219968694005e-05, "epoch": 55.666666666666664, "percentage": 12.53, "elapsed_time": "0:34:04", "remaining_time": "3:57:55", "throughput": 686.46, "total_tokens": 1403152} {"current_steps": 5015, "total_steps": 40000, "loss": 0.0, "lr": 4.808645479219442e-05, "epoch": 55.72222222222222, "percentage": 12.54, "elapsed_time": "0:34:05", "remaining_time": "3:57:52", "throughput": 686.48, "total_tokens": 1404528} {"current_steps": 5020, "total_steps": 40000, "loss": 0.0, "lr": 4.8082686055473375e-05, "epoch": 55.77777777777778, "percentage": 12.55, "elapsed_time": "0:34:07", "remaining_time": "3:57:50", "throughput": 686.5, "total_tokens": 1405904} {"current_steps": 5025, "total_steps": 40000, "loss": 0.0, "lr": 4.8078913759112066e-05, "epoch": 55.833333333333336, "percentage": 12.56, "elapsed_time": "0:34:09", "remaining_time": "3:57:47", "throughput": 686.5, "total_tokens": 1407248} {"current_steps": 5030, "total_steps": 40000, "loss": 0.0, "lr": 4.807513790369223e-05, "epoch": 55.888888888888886, "percentage": 12.57, "elapsed_time": "0:34:11", "remaining_time": "3:57:44", "throughput": 686.54, "total_tokens": 1408656} {"current_steps": 5035, "total_steps": 40000, "loss": 0.0, "lr": 4.8071358489796145e-05, "epoch": 55.94444444444444, "percentage": 12.59, "elapsed_time": "0:34:13", "remaining_time": "3:57:42", "throughput": 686.55, "total_tokens": 1410016} {"current_steps": 5040, "total_steps": 40000, "loss": 0.0, "lr": 4.806757551800665e-05, "epoch": 56.0, "percentage": 12.6, "elapsed_time": "0:34:15", "remaining_time": "3:57:40", "throughput": 686.54, "total_tokens": 1411472} {"current_steps": 5045, "total_steps": 40000, "loss": 0.0, "lr": 4.806378898890713e-05, "epoch": 56.05555555555556, "percentage": 12.61, "elapsed_time": "0:34:18", "remaining_time": "3:57:39", "throughput": 686.5, "total_tokens": 1412896} {"current_steps": 5050, "total_steps": 40000, "loss": 0.0, "lr": 4.80599989030815e-05, "epoch": 56.111111111111114, "percentage": 12.62, "elapsed_time": "0:34:20", "remaining_time": "3:57:37", "throughput": 686.55, "total_tokens": 1414320} {"current_steps": 5055, "total_steps": 40000, "loss": 0.0, "lr": 4.805620526111426e-05, "epoch": 56.166666666666664, "percentage": 12.64, "elapsed_time": "0:34:21", "remaining_time": "3:57:34", "throughput": 686.59, "total_tokens": 1415744} {"current_steps": 5060, "total_steps": 40000, "loss": 0.0, "lr": 4.805240806359042e-05, "epoch": 56.22222222222222, "percentage": 12.65, "elapsed_time": "0:34:23", "remaining_time": "3:57:31", "throughput": 686.63, "total_tokens": 1417152} {"current_steps": 5065, "total_steps": 40000, "loss": 0.0, "lr": 4.804860731109557e-05, "epoch": 56.27777777777778, "percentage": 12.66, "elapsed_time": "0:34:25", "remaining_time": "3:57:28", "throughput": 686.68, "total_tokens": 1418576} {"current_steps": 5070, "total_steps": 40000, "loss": 0.0, "lr": 4.804480300421581e-05, "epoch": 56.333333333333336, "percentage": 12.68, "elapsed_time": "0:34:27", "remaining_time": "3:57:26", "throughput": 686.69, "total_tokens": 1419936} {"current_steps": 5075, "total_steps": 40000, "loss": 0.0, "lr": 4.804099514353784e-05, "epoch": 56.388888888888886, "percentage": 12.69, "elapsed_time": "0:34:29", "remaining_time": "3:57:23", "throughput": 686.71, "total_tokens": 1421312} {"current_steps": 5080, "total_steps": 40000, "loss": 0.0, "lr": 4.8037183729648867e-05, "epoch": 56.44444444444444, "percentage": 12.7, "elapsed_time": "0:34:31", "remaining_time": "3:57:20", "throughput": 686.72, "total_tokens": 1422688} {"current_steps": 5085, "total_steps": 40000, "loss": 0.0, "lr": 4.803336876313666e-05, "epoch": 56.5, "percentage": 12.71, "elapsed_time": "0:34:33", "remaining_time": "3:57:18", "throughput": 686.74, "total_tokens": 1424064} {"current_steps": 5090, "total_steps": 40000, "loss": 0.0, "lr": 4.802955024458953e-05, "epoch": 56.55555555555556, "percentage": 12.72, "elapsed_time": "0:34:35", "remaining_time": "3:57:15", "throughput": 686.79, "total_tokens": 1425488} {"current_steps": 5095, "total_steps": 40000, "loss": 0.0, "lr": 4.802572817459634e-05, "epoch": 56.611111111111114, "percentage": 12.74, "elapsed_time": "0:34:37", "remaining_time": "3:57:12", "throughput": 686.84, "total_tokens": 1426912} {"current_steps": 5100, "total_steps": 40000, "loss": 0.0, "lr": 4.802190255374651e-05, "epoch": 56.666666666666664, "percentage": 12.75, "elapsed_time": "0:34:39", "remaining_time": "3:57:09", "throughput": 686.87, "total_tokens": 1428320} {"current_steps": 5105, "total_steps": 40000, "loss": 0.0, "lr": 4.801807338263e-05, "epoch": 56.72222222222222, "percentage": 12.76, "elapsed_time": "0:34:41", "remaining_time": "3:57:07", "throughput": 686.89, "total_tokens": 1429696} {"current_steps": 5110, "total_steps": 40000, "loss": 0.0, "lr": 4.8014240661837306e-05, "epoch": 56.77777777777778, "percentage": 12.78, "elapsed_time": "0:34:43", "remaining_time": "3:57:04", "throughput": 686.94, "total_tokens": 1431120} {"current_steps": 5115, "total_steps": 40000, "loss": 0.0, "lr": 4.80104043919595e-05, "epoch": 56.833333333333336, "percentage": 12.79, "elapsed_time": "0:34:45", "remaining_time": "3:57:01", "throughput": 686.96, "total_tokens": 1432496} {"current_steps": 5120, "total_steps": 40000, "loss": 0.0, "lr": 4.800656457358815e-05, "epoch": 56.888888888888886, "percentage": 12.8, "elapsed_time": "0:34:47", "remaining_time": "3:56:59", "throughput": 686.97, "total_tokens": 1433872} {"current_steps": 5125, "total_steps": 40000, "loss": 0.0, "lr": 4.800272120731544e-05, "epoch": 56.94444444444444, "percentage": 12.81, "elapsed_time": "0:34:49", "remaining_time": "3:56:56", "throughput": 687.02, "total_tokens": 1435296} {"current_steps": 5130, "total_steps": 40000, "loss": 0.0, "lr": 4.799887429373404e-05, "epoch": 57.0, "percentage": 12.83, "elapsed_time": "0:34:51", "remaining_time": "3:56:54", "throughput": 686.99, "total_tokens": 1436688} {"current_steps": 5135, "total_steps": 40000, "loss": 0.0, "lr": 4.79950238334372e-05, "epoch": 57.05555555555556, "percentage": 12.84, "elapsed_time": "0:34:53", "remaining_time": "3:56:53", "throughput": 686.97, "total_tokens": 1438144} {"current_steps": 5140, "total_steps": 40000, "loss": 0.0, "lr": 4.799116982701872e-05, "epoch": 57.111111111111114, "percentage": 12.85, "elapsed_time": "0:34:55", "remaining_time": "3:56:51", "throughput": 687.0, "total_tokens": 1439552} {"current_steps": 5145, "total_steps": 40000, "loss": 0.0, "lr": 4.7987312275072926e-05, "epoch": 57.166666666666664, "percentage": 12.86, "elapsed_time": "0:34:57", "remaining_time": "3:56:48", "throughput": 687.04, "total_tokens": 1440960} {"current_steps": 5150, "total_steps": 40000, "loss": 0.0, "lr": 4.79834511781947e-05, "epoch": 57.22222222222222, "percentage": 12.88, "elapsed_time": "0:34:59", "remaining_time": "3:56:45", "throughput": 687.05, "total_tokens": 1442320} {"current_steps": 5155, "total_steps": 40000, "loss": 0.0, "lr": 4.797958653697947e-05, "epoch": 57.27777777777778, "percentage": 12.89, "elapsed_time": "0:35:01", "remaining_time": "3:56:43", "throughput": 687.08, "total_tokens": 1443712} {"current_steps": 5160, "total_steps": 40000, "loss": 0.0, "lr": 4.7975718352023225e-05, "epoch": 57.333333333333336, "percentage": 12.9, "elapsed_time": "0:35:03", "remaining_time": "3:56:40", "throughput": 687.11, "total_tokens": 1445136} {"current_steps": 5165, "total_steps": 40000, "loss": 0.0, "lr": 4.7971846623922476e-05, "epoch": 57.388888888888886, "percentage": 12.91, "elapsed_time": "0:35:05", "remaining_time": "3:56:38", "throughput": 687.14, "total_tokens": 1446544} {"current_steps": 5170, "total_steps": 40000, "loss": 0.0, "lr": 4.7967971353274294e-05, "epoch": 57.44444444444444, "percentage": 12.93, "elapsed_time": "0:35:07", "remaining_time": "3:56:35", "throughput": 687.17, "total_tokens": 1447936} {"current_steps": 5175, "total_steps": 40000, "loss": 0.0, "lr": 4.79640925406763e-05, "epoch": 57.5, "percentage": 12.94, "elapsed_time": "0:35:09", "remaining_time": "3:56:32", "throughput": 687.2, "total_tokens": 1449344} {"current_steps": 5180, "total_steps": 40000, "loss": 0.0, "lr": 4.796021018672664e-05, "epoch": 57.55555555555556, "percentage": 12.95, "elapsed_time": "0:35:10", "remaining_time": "3:56:30", "throughput": 687.23, "total_tokens": 1450736} {"current_steps": 5185, "total_steps": 40000, "loss": 0.0, "lr": 4.795632429202405e-05, "epoch": 57.611111111111114, "percentage": 12.96, "elapsed_time": "0:35:12", "remaining_time": "3:56:27", "throughput": 687.27, "total_tokens": 1452144} {"current_steps": 5190, "total_steps": 40000, "loss": 0.0, "lr": 4.795243485716775e-05, "epoch": 57.666666666666664, "percentage": 12.97, "elapsed_time": "0:35:14", "remaining_time": "3:56:24", "throughput": 687.3, "total_tokens": 1453552} {"current_steps": 5195, "total_steps": 40000, "loss": 0.0, "lr": 4.794854188275757e-05, "epoch": 57.72222222222222, "percentage": 12.99, "elapsed_time": "0:35:16", "remaining_time": "3:56:21", "throughput": 687.35, "total_tokens": 1454992} {"current_steps": 5200, "total_steps": 40000, "loss": 0.0, "lr": 4.794464536939384e-05, "epoch": 57.77777777777778, "percentage": 13.0, "elapsed_time": "0:35:18", "remaining_time": "3:56:19", "throughput": 687.37, "total_tokens": 1456368} {"current_steps": 5200, "total_steps": 40000, "eval_loss": 0.2591719925403595, "epoch": 57.77777777777778, "percentage": 13.0, "elapsed_time": "0:35:20", "remaining_time": "3:56:28", "throughput": 686.94, "total_tokens": 1456368} {"current_steps": 5205, "total_steps": 40000, "loss": 0.0, "lr": 4.794074531767745e-05, "epoch": 57.833333333333336, "percentage": 13.01, "elapsed_time": "0:35:23", "remaining_time": "3:56:34", "throughput": 686.55, "total_tokens": 1457760} {"current_steps": 5210, "total_steps": 40000, "loss": 0.0, "lr": 4.7936841728209834e-05, "epoch": 57.888888888888886, "percentage": 13.03, "elapsed_time": "0:35:25", "remaining_time": "3:56:31", "throughput": 686.55, "total_tokens": 1459136} {"current_steps": 5215, "total_steps": 40000, "loss": 0.0, "lr": 4.7932934601593e-05, "epoch": 57.94444444444444, "percentage": 13.04, "elapsed_time": "0:35:27", "remaining_time": "3:56:29", "throughput": 686.6, "total_tokens": 1460576} {"current_steps": 5220, "total_steps": 40000, "loss": 0.0, "lr": 4.792902393842943e-05, "epoch": 58.0, "percentage": 13.05, "elapsed_time": "0:35:29", "remaining_time": "3:56:27", "throughput": 686.59, "total_tokens": 1462000} {"current_steps": 5225, "total_steps": 40000, "loss": 0.0, "lr": 4.792510973932225e-05, "epoch": 58.05555555555556, "percentage": 13.06, "elapsed_time": "0:35:31", "remaining_time": "3:56:26", "throughput": 686.51, "total_tokens": 1463360} {"current_steps": 5230, "total_steps": 40000, "loss": 0.0, "lr": 4.7921192004875036e-05, "epoch": 58.111111111111114, "percentage": 13.08, "elapsed_time": "0:35:33", "remaining_time": "3:56:24", "throughput": 686.55, "total_tokens": 1464768} {"current_steps": 5235, "total_steps": 40000, "loss": 0.0, "lr": 4.791727073569198e-05, "epoch": 58.166666666666664, "percentage": 13.09, "elapsed_time": "0:35:35", "remaining_time": "3:56:21", "throughput": 686.57, "total_tokens": 1466160} {"current_steps": 5240, "total_steps": 40000, "loss": 0.0, "lr": 4.7913345932377775e-05, "epoch": 58.22222222222222, "percentage": 13.1, "elapsed_time": "0:35:37", "remaining_time": "3:56:18", "throughput": 686.61, "total_tokens": 1467568} {"current_steps": 5245, "total_steps": 40000, "loss": 0.0, "lr": 4.790941759553769e-05, "epoch": 58.27777777777778, "percentage": 13.11, "elapsed_time": "0:35:39", "remaining_time": "3:56:16", "throughput": 686.63, "total_tokens": 1468960} {"current_steps": 5250, "total_steps": 40000, "loss": 0.0, "lr": 4.79054857257775e-05, "epoch": 58.333333333333336, "percentage": 13.12, "elapsed_time": "0:35:41", "remaining_time": "3:56:13", "throughput": 686.64, "total_tokens": 1470320} {"current_steps": 5255, "total_steps": 40000, "loss": 0.0, "lr": 4.790155032370357e-05, "epoch": 58.388888888888886, "percentage": 13.14, "elapsed_time": "0:35:43", "remaining_time": "3:56:10", "throughput": 686.67, "total_tokens": 1471728} {"current_steps": 5260, "total_steps": 40000, "loss": 0.0, "lr": 4.789761138992278e-05, "epoch": 58.44444444444444, "percentage": 13.15, "elapsed_time": "0:35:45", "remaining_time": "3:56:08", "throughput": 686.73, "total_tokens": 1473184} {"current_steps": 5265, "total_steps": 40000, "loss": 0.0, "lr": 4.7893668925042565e-05, "epoch": 58.5, "percentage": 13.16, "elapsed_time": "0:35:47", "remaining_time": "3:56:05", "throughput": 686.74, "total_tokens": 1474544} {"current_steps": 5270, "total_steps": 40000, "loss": 0.0, "lr": 4.78897229296709e-05, "epoch": 58.55555555555556, "percentage": 13.18, "elapsed_time": "0:35:49", "remaining_time": "3:56:02", "throughput": 686.76, "total_tokens": 1475920} {"current_steps": 5275, "total_steps": 40000, "loss": 0.0, "lr": 4.7885773404416315e-05, "epoch": 58.611111111111114, "percentage": 13.19, "elapsed_time": "0:35:51", "remaining_time": "3:56:00", "throughput": 686.78, "total_tokens": 1477296} {"current_steps": 5280, "total_steps": 40000, "loss": 0.0, "lr": 4.788182034988786e-05, "epoch": 58.666666666666664, "percentage": 13.2, "elapsed_time": "0:35:53", "remaining_time": "3:55:57", "throughput": 686.81, "total_tokens": 1478704} {"current_steps": 5285, "total_steps": 40000, "loss": 0.0, "lr": 4.787786376669516e-05, "epoch": 58.72222222222222, "percentage": 13.21, "elapsed_time": "0:35:54", "remaining_time": "3:55:54", "throughput": 686.82, "total_tokens": 1480064} {"current_steps": 5290, "total_steps": 40000, "loss": 0.0, "lr": 4.787390365544837e-05, "epoch": 58.77777777777778, "percentage": 13.23, "elapsed_time": "0:35:56", "remaining_time": "3:55:52", "throughput": 686.85, "total_tokens": 1481472} {"current_steps": 5295, "total_steps": 40000, "loss": 0.0, "lr": 4.786994001675818e-05, "epoch": 58.833333333333336, "percentage": 13.24, "elapsed_time": "0:35:58", "remaining_time": "3:55:49", "throughput": 686.89, "total_tokens": 1482880} {"current_steps": 5300, "total_steps": 40000, "loss": 0.0, "lr": 4.786597285123584e-05, "epoch": 58.888888888888886, "percentage": 13.25, "elapsed_time": "0:36:00", "remaining_time": "3:55:47", "throughput": 686.91, "total_tokens": 1484272} {"current_steps": 5305, "total_steps": 40000, "loss": 0.0, "lr": 4.7862002159493135e-05, "epoch": 58.94444444444444, "percentage": 13.26, "elapsed_time": "0:36:02", "remaining_time": "3:55:44", "throughput": 686.95, "total_tokens": 1485696} {"current_steps": 5310, "total_steps": 40000, "loss": 0.0, "lr": 4.785802794214239e-05, "epoch": 59.0, "percentage": 13.28, "elapsed_time": "0:36:04", "remaining_time": "3:55:42", "throughput": 686.95, "total_tokens": 1487136} {"current_steps": 5315, "total_steps": 40000, "loss": 0.0, "lr": 4.7854050199796495e-05, "epoch": 59.05555555555556, "percentage": 13.29, "elapsed_time": "0:36:07", "remaining_time": "3:55:41", "throughput": 686.9, "total_tokens": 1488544} {"current_steps": 5320, "total_steps": 40000, "loss": 0.0, "lr": 4.7850068933068845e-05, "epoch": 59.111111111111114, "percentage": 13.3, "elapsed_time": "0:36:08", "remaining_time": "3:55:39", "throughput": 686.92, "total_tokens": 1489936} {"current_steps": 5325, "total_steps": 40000, "loss": 0.0, "lr": 4.7846084142573425e-05, "epoch": 59.166666666666664, "percentage": 13.31, "elapsed_time": "0:36:10", "remaining_time": "3:55:36", "throughput": 686.97, "total_tokens": 1491360} {"current_steps": 5330, "total_steps": 40000, "loss": 0.0, "lr": 4.7842095828924725e-05, "epoch": 59.22222222222222, "percentage": 13.33, "elapsed_time": "0:36:12", "remaining_time": "3:55:33", "throughput": 686.99, "total_tokens": 1492752} {"current_steps": 5335, "total_steps": 40000, "loss": 0.0, "lr": 4.783810399273779e-05, "epoch": 59.27777777777778, "percentage": 13.34, "elapsed_time": "0:36:14", "remaining_time": "3:55:31", "throughput": 687.0, "total_tokens": 1494128} {"current_steps": 5340, "total_steps": 40000, "loss": 0.0, "lr": 4.7834108634628226e-05, "epoch": 59.333333333333336, "percentage": 13.35, "elapsed_time": "0:36:16", "remaining_time": "3:55:28", "throughput": 687.02, "total_tokens": 1495520} {"current_steps": 5345, "total_steps": 40000, "loss": 0.0, "lr": 4.783010975521216e-05, "epoch": 59.388888888888886, "percentage": 13.36, "elapsed_time": "0:36:18", "remaining_time": "3:55:26", "throughput": 687.05, "total_tokens": 1496928} {"current_steps": 5350, "total_steps": 40000, "loss": 0.0, "lr": 4.782610735510626e-05, "epoch": 59.44444444444444, "percentage": 13.38, "elapsed_time": "0:36:20", "remaining_time": "3:55:23", "throughput": 687.05, "total_tokens": 1498272} {"current_steps": 5355, "total_steps": 40000, "loss": 0.0, "lr": 4.782210143492776e-05, "epoch": 59.5, "percentage": 13.39, "elapsed_time": "0:36:22", "remaining_time": "3:55:21", "throughput": 687.07, "total_tokens": 1499664} {"current_steps": 5360, "total_steps": 40000, "loss": 0.0, "lr": 4.781809199529442e-05, "epoch": 59.55555555555556, "percentage": 13.4, "elapsed_time": "0:36:24", "remaining_time": "3:55:18", "throughput": 687.11, "total_tokens": 1501072} {"current_steps": 5365, "total_steps": 40000, "loss": 0.0, "lr": 4.781407903682454e-05, "epoch": 59.611111111111114, "percentage": 13.41, "elapsed_time": "0:36:26", "remaining_time": "3:55:15", "throughput": 687.15, "total_tokens": 1502512} {"current_steps": 5370, "total_steps": 40000, "loss": 0.0, "lr": 4.781006256013698e-05, "epoch": 59.666666666666664, "percentage": 13.43, "elapsed_time": "0:36:28", "remaining_time": "3:55:13", "throughput": 687.2, "total_tokens": 1503936} {"current_steps": 5375, "total_steps": 40000, "loss": 0.0, "lr": 4.7806042565851115e-05, "epoch": 59.72222222222222, "percentage": 13.44, "elapsed_time": "0:36:30", "remaining_time": "3:55:10", "throughput": 687.22, "total_tokens": 1505344} {"current_steps": 5380, "total_steps": 40000, "loss": 0.0, "lr": 4.7802019054586895e-05, "epoch": 59.77777777777778, "percentage": 13.45, "elapsed_time": "0:36:32", "remaining_time": "3:55:08", "throughput": 687.25, "total_tokens": 1506736} {"current_steps": 5385, "total_steps": 40000, "loss": 0.0, "lr": 4.779799202696479e-05, "epoch": 59.833333333333336, "percentage": 13.46, "elapsed_time": "0:36:34", "remaining_time": "3:55:05", "throughput": 687.29, "total_tokens": 1508160} {"current_steps": 5390, "total_steps": 40000, "loss": 0.0, "lr": 4.779396148360581e-05, "epoch": 59.888888888888886, "percentage": 13.48, "elapsed_time": "0:36:36", "remaining_time": "3:55:02", "throughput": 687.33, "total_tokens": 1509584} {"current_steps": 5395, "total_steps": 40000, "loss": 0.0, "lr": 4.7789927425131517e-05, "epoch": 59.94444444444444, "percentage": 13.49, "elapsed_time": "0:36:38", "remaining_time": "3:55:00", "throughput": 687.35, "total_tokens": 1510960} {"current_steps": 5400, "total_steps": 40000, "loss": 0.0, "lr": 4.778588985216403e-05, "epoch": 60.0, "percentage": 13.5, "elapsed_time": "0:36:40", "remaining_time": "3:54:58", "throughput": 687.32, "total_tokens": 1512336} {"current_steps": 5400, "total_steps": 40000, "eval_loss": 0.2541940212249756, "epoch": 60.0, "percentage": 13.5, "elapsed_time": "0:36:41", "remaining_time": "3:55:06", "throughput": 686.92, "total_tokens": 1512336} {"current_steps": 5405, "total_steps": 40000, "loss": 0.0, "lr": 4.778184876532598e-05, "epoch": 60.05555555555556, "percentage": 13.51, "elapsed_time": "0:36:45", "remaining_time": "3:55:14", "throughput": 686.45, "total_tokens": 1513728} {"current_steps": 5410, "total_steps": 40000, "loss": 0.0, "lr": 4.7777804165240556e-05, "epoch": 60.111111111111114, "percentage": 13.53, "elapsed_time": "0:36:47", "remaining_time": "3:55:11", "throughput": 686.45, "total_tokens": 1515104} {"current_steps": 5415, "total_steps": 40000, "loss": 0.0, "lr": 4.7773756052531485e-05, "epoch": 60.166666666666664, "percentage": 13.54, "elapsed_time": "0:36:49", "remaining_time": "3:55:09", "throughput": 686.48, "total_tokens": 1516512} {"current_steps": 5420, "total_steps": 40000, "loss": 0.0, "lr": 4.7769704427823035e-05, "epoch": 60.22222222222222, "percentage": 13.55, "elapsed_time": "0:36:51", "remaining_time": "3:55:06", "throughput": 686.5, "total_tokens": 1517888} {"current_steps": 5425, "total_steps": 40000, "loss": 0.0, "lr": 4.776564929174003e-05, "epoch": 60.27777777777778, "percentage": 13.56, "elapsed_time": "0:36:53", "remaining_time": "3:55:04", "throughput": 686.54, "total_tokens": 1519312} {"current_steps": 5430, "total_steps": 40000, "loss": 0.0, "lr": 4.7761590644907806e-05, "epoch": 60.333333333333336, "percentage": 13.58, "elapsed_time": "0:36:54", "remaining_time": "3:55:01", "throughput": 686.56, "total_tokens": 1520720} {"current_steps": 5435, "total_steps": 40000, "loss": 0.0, "lr": 4.7757528487952263e-05, "epoch": 60.388888888888886, "percentage": 13.59, "elapsed_time": "0:36:56", "remaining_time": "3:54:59", "throughput": 686.57, "total_tokens": 1522080} {"current_steps": 5440, "total_steps": 40000, "loss": 0.0, "lr": 4.7753462821499836e-05, "epoch": 60.44444444444444, "percentage": 13.6, "elapsed_time": "0:36:58", "remaining_time": "3:54:56", "throughput": 686.6, "total_tokens": 1523488} {"current_steps": 5445, "total_steps": 40000, "loss": 0.0, "lr": 4.774939364617751e-05, "epoch": 60.5, "percentage": 13.61, "elapsed_time": "0:37:00", "remaining_time": "3:54:53", "throughput": 686.62, "total_tokens": 1524896} {"current_steps": 5450, "total_steps": 40000, "loss": 0.0, "lr": 4.7745320962612795e-05, "epoch": 60.55555555555556, "percentage": 13.63, "elapsed_time": "0:37:02", "remaining_time": "3:54:51", "throughput": 686.68, "total_tokens": 1526352} {"current_steps": 5455, "total_steps": 40000, "loss": 0.0, "lr": 4.7741244771433756e-05, "epoch": 60.611111111111114, "percentage": 13.64, "elapsed_time": "0:37:04", "remaining_time": "3:54:48", "throughput": 686.73, "total_tokens": 1527792} {"current_steps": 5460, "total_steps": 40000, "loss": 0.0, "lr": 4.7737165073268985e-05, "epoch": 60.666666666666664, "percentage": 13.65, "elapsed_time": "0:37:06", "remaining_time": "3:54:46", "throughput": 686.74, "total_tokens": 1529168} {"current_steps": 5465, "total_steps": 40000, "loss": 0.0, "lr": 4.7733081868747626e-05, "epoch": 60.72222222222222, "percentage": 13.66, "elapsed_time": "0:37:08", "remaining_time": "3:54:43", "throughput": 686.76, "total_tokens": 1530544} {"current_steps": 5470, "total_steps": 40000, "loss": 0.0, "lr": 4.772899515849936e-05, "epoch": 60.77777777777778, "percentage": 13.68, "elapsed_time": "0:37:10", "remaining_time": "3:54:40", "throughput": 686.78, "total_tokens": 1531936} {"current_steps": 5475, "total_steps": 40000, "loss": 0.0, "lr": 4.7724904943154414e-05, "epoch": 60.833333333333336, "percentage": 13.69, "elapsed_time": "0:37:12", "remaining_time": "3:54:38", "throughput": 686.81, "total_tokens": 1533328} {"current_steps": 5480, "total_steps": 40000, "loss": 0.0, "lr": 4.772081122334354e-05, "epoch": 60.888888888888886, "percentage": 13.7, "elapsed_time": "0:37:14", "remaining_time": "3:54:35", "throughput": 686.84, "total_tokens": 1534736} {"current_steps": 5485, "total_steps": 40000, "loss": 0.0, "lr": 4.771671399969806e-05, "epoch": 60.94444444444444, "percentage": 13.71, "elapsed_time": "0:37:16", "remaining_time": "3:54:33", "throughput": 686.86, "total_tokens": 1536128} {"current_steps": 5490, "total_steps": 40000, "loss": 0.0, "lr": 4.7712613272849794e-05, "epoch": 61.0, "percentage": 13.73, "elapsed_time": "0:37:18", "remaining_time": "3:54:31", "throughput": 686.82, "total_tokens": 1537504} {"current_steps": 5495, "total_steps": 40000, "loss": 0.0, "lr": 4.770850904343114e-05, "epoch": 61.05555555555556, "percentage": 13.74, "elapsed_time": "0:37:20", "remaining_time": "3:54:30", "throughput": 686.77, "total_tokens": 1538896} {"current_steps": 5500, "total_steps": 40000, "loss": 0.0, "lr": 4.770440131207502e-05, "epoch": 61.111111111111114, "percentage": 13.75, "elapsed_time": "0:37:22", "remaining_time": "3:54:28", "throughput": 686.81, "total_tokens": 1540336} {"current_steps": 5505, "total_steps": 40000, "loss": 0.0, "lr": 4.7700290079414896e-05, "epoch": 61.166666666666664, "percentage": 13.76, "elapsed_time": "0:37:24", "remaining_time": "3:54:25", "throughput": 686.84, "total_tokens": 1541728} {"current_steps": 5510, "total_steps": 40000, "loss": 0.0, "lr": 4.769617534608477e-05, "epoch": 61.22222222222222, "percentage": 13.78, "elapsed_time": "0:37:26", "remaining_time": "3:54:22", "throughput": 686.89, "total_tokens": 1543168} {"current_steps": 5515, "total_steps": 40000, "loss": 0.0, "lr": 4.7692057112719193e-05, "epoch": 61.27777777777778, "percentage": 13.79, "elapsed_time": "0:37:28", "remaining_time": "3:54:20", "throughput": 686.94, "total_tokens": 1544608} {"current_steps": 5520, "total_steps": 40000, "loss": 0.0, "lr": 4.7687935379953234e-05, "epoch": 61.333333333333336, "percentage": 13.8, "elapsed_time": "0:37:30", "remaining_time": "3:54:17", "throughput": 686.95, "total_tokens": 1545984} {"current_steps": 5525, "total_steps": 40000, "loss": 0.0, "lr": 4.7683810148422534e-05, "epoch": 61.388888888888886, "percentage": 13.81, "elapsed_time": "0:37:32", "remaining_time": "3:54:14", "throughput": 686.98, "total_tokens": 1547376} {"current_steps": 5530, "total_steps": 40000, "loss": 0.0, "lr": 4.767968141876324e-05, "epoch": 61.44444444444444, "percentage": 13.83, "elapsed_time": "0:37:34", "remaining_time": "3:54:12", "throughput": 687.0, "total_tokens": 1548768} {"current_steps": 5535, "total_steps": 40000, "loss": 0.0, "lr": 4.767554919161207e-05, "epoch": 61.5, "percentage": 13.84, "elapsed_time": "0:37:36", "remaining_time": "3:54:09", "throughput": 687.0, "total_tokens": 1550112} {"current_steps": 5540, "total_steps": 40000, "loss": 0.0, "lr": 4.767141346760624e-05, "epoch": 61.55555555555556, "percentage": 13.85, "elapsed_time": "0:37:38", "remaining_time": "3:54:07", "throughput": 687.03, "total_tokens": 1551520} {"current_steps": 5545, "total_steps": 40000, "loss": 0.0, "lr": 4.766727424738356e-05, "epoch": 61.611111111111114, "percentage": 13.86, "elapsed_time": "0:37:40", "remaining_time": "3:54:04", "throughput": 687.06, "total_tokens": 1552928} {"current_steps": 5550, "total_steps": 40000, "loss": 0.0, "lr": 4.7663131531582325e-05, "epoch": 61.666666666666664, "percentage": 13.88, "elapsed_time": "0:37:42", "remaining_time": "3:54:01", "throughput": 687.05, "total_tokens": 1554240} {"current_steps": 5555, "total_steps": 40000, "loss": 0.0, "lr": 4.765898532084142e-05, "epoch": 61.72222222222222, "percentage": 13.89, "elapsed_time": "0:37:44", "remaining_time": "3:53:59", "throughput": 687.11, "total_tokens": 1555712} {"current_steps": 5560, "total_steps": 40000, "loss": 0.0, "lr": 4.765483561580022e-05, "epoch": 61.77777777777778, "percentage": 13.9, "elapsed_time": "0:37:46", "remaining_time": "3:53:56", "throughput": 687.14, "total_tokens": 1557120} {"current_steps": 5565, "total_steps": 40000, "loss": 0.0, "lr": 4.7650682417098666e-05, "epoch": 61.833333333333336, "percentage": 13.91, "elapsed_time": "0:37:48", "remaining_time": "3:53:53", "throughput": 687.17, "total_tokens": 1558512} {"current_steps": 5570, "total_steps": 40000, "loss": 0.0, "lr": 4.7646525725377244e-05, "epoch": 61.888888888888886, "percentage": 13.93, "elapsed_time": "0:37:49", "remaining_time": "3:53:51", "throughput": 687.2, "total_tokens": 1559920} {"current_steps": 5575, "total_steps": 40000, "loss": 0.0, "lr": 4.764236554127696e-05, "epoch": 61.94444444444444, "percentage": 13.94, "elapsed_time": "0:37:51", "remaining_time": "3:53:48", "throughput": 687.24, "total_tokens": 1561344} {"current_steps": 5580, "total_steps": 40000, "loss": 0.0, "lr": 4.7638201865439356e-05, "epoch": 62.0, "percentage": 13.95, "elapsed_time": "0:37:54", "remaining_time": "3:53:47", "throughput": 687.21, "total_tokens": 1562720} {"current_steps": 5585, "total_steps": 40000, "loss": 0.0, "lr": 4.7634034698506545e-05, "epoch": 62.05555555555556, "percentage": 13.96, "elapsed_time": "0:37:56", "remaining_time": "3:53:46", "throughput": 687.16, "total_tokens": 1564128} {"current_steps": 5590, "total_steps": 40000, "loss": 0.0, "lr": 4.762986404112115e-05, "epoch": 62.111111111111114, "percentage": 13.98, "elapsed_time": "0:37:58", "remaining_time": "3:53:43", "throughput": 687.17, "total_tokens": 1565488} {"current_steps": 5595, "total_steps": 40000, "loss": 0.0, "lr": 4.762568989392633e-05, "epoch": 62.166666666666664, "percentage": 13.99, "elapsed_time": "0:38:00", "remaining_time": "3:53:41", "throughput": 687.17, "total_tokens": 1566848} {"current_steps": 5600, "total_steps": 40000, "loss": 0.0, "lr": 4.76215122575658e-05, "epoch": 62.22222222222222, "percentage": 14.0, "elapsed_time": "0:38:02", "remaining_time": "3:53:38", "throughput": 687.18, "total_tokens": 1568192} {"current_steps": 5600, "total_steps": 40000, "eval_loss": 0.24483796954154968, "epoch": 62.22222222222222, "percentage": 14.0, "elapsed_time": "0:38:03", "remaining_time": "3:53:46", "throughput": 686.78, "total_tokens": 1568192} {"current_steps": 5605, "total_steps": 40000, "loss": 0.0, "lr": 4.7617331132683795e-05, "epoch": 62.27777777777778, "percentage": 14.01, "elapsed_time": "0:38:06", "remaining_time": "3:53:52", "throughput": 686.37, "total_tokens": 1569600} {"current_steps": 5610, "total_steps": 40000, "loss": 0.0, "lr": 4.7613146519925105e-05, "epoch": 62.333333333333336, "percentage": 14.03, "elapsed_time": "0:38:08", "remaining_time": "3:53:50", "throughput": 686.38, "total_tokens": 1570992} {"current_steps": 5615, "total_steps": 40000, "loss": 0.0, "lr": 4.7608958419935045e-05, "epoch": 62.388888888888886, "percentage": 14.04, "elapsed_time": "0:38:10", "remaining_time": "3:53:48", "throughput": 686.42, "total_tokens": 1572416} {"current_steps": 5620, "total_steps": 40000, "loss": 0.0, "lr": 4.760476683335948e-05, "epoch": 62.44444444444444, "percentage": 14.05, "elapsed_time": "0:38:12", "remaining_time": "3:53:45", "throughput": 686.45, "total_tokens": 1573840} {"current_steps": 5625, "total_steps": 40000, "loss": 0.0, "lr": 4.760057176084479e-05, "epoch": 62.5, "percentage": 14.06, "elapsed_time": "0:38:14", "remaining_time": "3:53:42", "throughput": 686.51, "total_tokens": 1575296} {"current_steps": 5630, "total_steps": 40000, "loss": 0.0, "lr": 4.759637320303793e-05, "epoch": 62.55555555555556, "percentage": 14.07, "elapsed_time": "0:38:16", "remaining_time": "3:53:40", "throughput": 686.53, "total_tokens": 1576704} {"current_steps": 5635, "total_steps": 40000, "loss": 0.0, "lr": 4.759217116058635e-05, "epoch": 62.611111111111114, "percentage": 14.09, "elapsed_time": "0:38:18", "remaining_time": "3:53:37", "throughput": 686.54, "total_tokens": 1578064} {"current_steps": 5640, "total_steps": 40000, "loss": 0.0, "lr": 4.758796563413807e-05, "epoch": 62.666666666666664, "percentage": 14.1, "elapsed_time": "0:38:20", "remaining_time": "3:53:35", "throughput": 686.56, "total_tokens": 1579456} {"current_steps": 5645, "total_steps": 40000, "loss": 0.0, "lr": 4.758375662434163e-05, "epoch": 62.72222222222222, "percentage": 14.11, "elapsed_time": "0:38:22", "remaining_time": "3:53:32", "throughput": 686.59, "total_tokens": 1580848} {"current_steps": 5650, "total_steps": 40000, "loss": 0.0, "lr": 4.7579544131846114e-05, "epoch": 62.77777777777778, "percentage": 14.12, "elapsed_time": "0:38:24", "remaining_time": "3:53:30", "throughput": 686.64, "total_tokens": 1582304} {"current_steps": 5655, "total_steps": 40000, "loss": 0.0, "lr": 4.757532815730114e-05, "epoch": 62.833333333333336, "percentage": 14.14, "elapsed_time": "0:38:26", "remaining_time": "3:53:27", "throughput": 686.69, "total_tokens": 1583744} {"current_steps": 5660, "total_steps": 40000, "loss": 0.0, "lr": 4.7571108701356865e-05, "epoch": 62.888888888888886, "percentage": 14.15, "elapsed_time": "0:38:28", "remaining_time": "3:53:24", "throughput": 686.71, "total_tokens": 1585136} {"current_steps": 5665, "total_steps": 40000, "loss": 0.0, "lr": 4.756688576466398e-05, "epoch": 62.94444444444444, "percentage": 14.16, "elapsed_time": "0:38:30", "remaining_time": "3:53:22", "throughput": 686.75, "total_tokens": 1586560} {"current_steps": 5670, "total_steps": 40000, "loss": 0.0, "lr": 4.756265934787372e-05, "epoch": 63.0, "percentage": 14.17, "elapsed_time": "0:38:32", "remaining_time": "3:53:20", "throughput": 686.71, "total_tokens": 1587936} {"current_steps": 5675, "total_steps": 40000, "loss": 0.0, "lr": 4.755842945163785e-05, "epoch": 63.05555555555556, "percentage": 14.19, "elapsed_time": "0:38:34", "remaining_time": "3:53:19", "throughput": 686.68, "total_tokens": 1589376} {"current_steps": 5680, "total_steps": 40000, "loss": 0.0, "lr": 4.755419607660867e-05, "epoch": 63.111111111111114, "percentage": 14.2, "elapsed_time": "0:38:36", "remaining_time": "3:53:16", "throughput": 686.72, "total_tokens": 1590800} {"current_steps": 5685, "total_steps": 40000, "loss": 0.0, "lr": 4.7549959223439016e-05, "epoch": 63.166666666666664, "percentage": 14.21, "elapsed_time": "0:38:38", "remaining_time": "3:53:14", "throughput": 686.75, "total_tokens": 1592208} {"current_steps": 5690, "total_steps": 40000, "loss": 0.0, "lr": 4.754571889278228e-05, "epoch": 63.22222222222222, "percentage": 14.22, "elapsed_time": "0:38:40", "remaining_time": "3:53:11", "throughput": 686.75, "total_tokens": 1593536} {"current_steps": 5695, "total_steps": 40000, "loss": 0.0, "lr": 4.754147508529235e-05, "epoch": 63.27777777777778, "percentage": 14.24, "elapsed_time": "0:38:42", "remaining_time": "3:53:09", "throughput": 686.79, "total_tokens": 1594960} {"current_steps": 5700, "total_steps": 40000, "loss": 0.0, "lr": 4.75372278016237e-05, "epoch": 63.333333333333336, "percentage": 14.25, "elapsed_time": "0:38:44", "remaining_time": "3:53:06", "throughput": 686.82, "total_tokens": 1596352} {"current_steps": 5705, "total_steps": 40000, "loss": 0.0, "lr": 4.753297704243129e-05, "epoch": 63.388888888888886, "percentage": 14.26, "elapsed_time": "0:38:46", "remaining_time": "3:53:03", "throughput": 686.84, "total_tokens": 1597760} {"current_steps": 5710, "total_steps": 40000, "loss": 0.0, "lr": 4.752872280837066e-05, "epoch": 63.44444444444444, "percentage": 14.27, "elapsed_time": "0:38:48", "remaining_time": "3:53:01", "throughput": 686.86, "total_tokens": 1599152} {"current_steps": 5715, "total_steps": 40000, "loss": 0.0, "lr": 4.752446510009786e-05, "epoch": 63.5, "percentage": 14.29, "elapsed_time": "0:38:50", "remaining_time": "3:52:58", "throughput": 686.87, "total_tokens": 1600528} {"current_steps": 5720, "total_steps": 40000, "loss": 0.0, "lr": 4.7520203918269476e-05, "epoch": 63.55555555555556, "percentage": 14.3, "elapsed_time": "0:38:52", "remaining_time": "3:52:56", "throughput": 686.88, "total_tokens": 1601888} {"current_steps": 5725, "total_steps": 40000, "loss": 0.0, "lr": 4.751593926354265e-05, "epoch": 63.611111111111114, "percentage": 14.31, "elapsed_time": "0:38:54", "remaining_time": "3:52:53", "throughput": 686.9, "total_tokens": 1603264} {"current_steps": 5730, "total_steps": 40000, "loss": 0.0, "lr": 4.751167113657503e-05, "epoch": 63.666666666666664, "percentage": 14.32, "elapsed_time": "0:38:56", "remaining_time": "3:52:51", "throughput": 686.92, "total_tokens": 1604656} {"current_steps": 5735, "total_steps": 40000, "loss": 0.0, "lr": 4.7507399538024834e-05, "epoch": 63.72222222222222, "percentage": 14.34, "elapsed_time": "0:38:57", "remaining_time": "3:52:48", "throughput": 686.95, "total_tokens": 1606064} {"current_steps": 5740, "total_steps": 40000, "loss": 0.0, "lr": 4.750312446855077e-05, "epoch": 63.77777777777778, "percentage": 14.35, "elapsed_time": "0:38:59", "remaining_time": "3:52:46", "throughput": 686.98, "total_tokens": 1607472} {"current_steps": 5745, "total_steps": 40000, "loss": 0.0, "lr": 4.749884592881212e-05, "epoch": 63.833333333333336, "percentage": 14.36, "elapsed_time": "0:39:01", "remaining_time": "3:52:43", "throughput": 687.02, "total_tokens": 1608880} {"current_steps": 5750, "total_steps": 40000, "loss": 0.0, "lr": 4.74945639194687e-05, "epoch": 63.888888888888886, "percentage": 14.37, "elapsed_time": "0:39:03", "remaining_time": "3:52:40", "throughput": 687.06, "total_tokens": 1610304} {"current_steps": 5755, "total_steps": 40000, "loss": 0.0, "lr": 4.749027844118083e-05, "epoch": 63.94444444444444, "percentage": 14.39, "elapsed_time": "0:39:05", "remaining_time": "3:52:38", "throughput": 687.09, "total_tokens": 1611728} {"current_steps": 5760, "total_steps": 40000, "loss": 0.0, "lr": 4.7485989494609395e-05, "epoch": 64.0, "percentage": 14.4, "elapsed_time": "0:39:07", "remaining_time": "3:52:36", "throughput": 687.05, "total_tokens": 1613088} {"current_steps": 5765, "total_steps": 40000, "loss": 0.0, "lr": 4.748169708041581e-05, "epoch": 64.05555555555556, "percentage": 14.41, "elapsed_time": "0:39:10", "remaining_time": "3:52:35", "throughput": 687.01, "total_tokens": 1614496} {"current_steps": 5770, "total_steps": 40000, "loss": 0.0, "lr": 4.7477401199262004e-05, "epoch": 64.11111111111111, "percentage": 14.42, "elapsed_time": "0:39:11", "remaining_time": "3:52:32", "throughput": 687.02, "total_tokens": 1615856} {"current_steps": 5775, "total_steps": 40000, "loss": 0.0, "lr": 4.747310185181048e-05, "epoch": 64.16666666666667, "percentage": 14.44, "elapsed_time": "0:39:13", "remaining_time": "3:52:30", "throughput": 687.04, "total_tokens": 1617248} {"current_steps": 5780, "total_steps": 40000, "loss": 0.0, "lr": 4.746879903872422e-05, "epoch": 64.22222222222223, "percentage": 14.45, "elapsed_time": "0:39:15", "remaining_time": "3:52:27", "throughput": 687.06, "total_tokens": 1618640} {"current_steps": 5785, "total_steps": 40000, "loss": 0.0, "lr": 4.746449276066679e-05, "epoch": 64.27777777777777, "percentage": 14.46, "elapsed_time": "0:39:17", "remaining_time": "3:52:25", "throughput": 687.08, "total_tokens": 1620016} {"current_steps": 5790, "total_steps": 40000, "loss": 0.0, "lr": 4.746018301830227e-05, "epoch": 64.33333333333333, "percentage": 14.47, "elapsed_time": "0:39:19", "remaining_time": "3:52:22", "throughput": 687.1, "total_tokens": 1621408} {"current_steps": 5795, "total_steps": 40000, "loss": 0.0, "lr": 4.7455869812295275e-05, "epoch": 64.38888888888889, "percentage": 14.49, "elapsed_time": "0:39:21", "remaining_time": "3:52:20", "throughput": 687.16, "total_tokens": 1622880} {"current_steps": 5800, "total_steps": 40000, "loss": 0.0, "lr": 4.7451553143310964e-05, "epoch": 64.44444444444444, "percentage": 14.5, "elapsed_time": "0:39:23", "remaining_time": "3:52:17", "throughput": 687.19, "total_tokens": 1624288} {"current_steps": 5800, "total_steps": 40000, "eval_loss": 0.24876172840595245, "epoch": 64.44444444444444, "percentage": 14.5, "elapsed_time": "0:39:24", "remaining_time": "3:52:25", "throughput": 686.81, "total_tokens": 1624288} {"current_steps": 5805, "total_steps": 40000, "loss": 0.0, "lr": 4.744723301201501e-05, "epoch": 64.5, "percentage": 14.51, "elapsed_time": "0:39:28", "remaining_time": "3:52:30", "throughput": 686.45, "total_tokens": 1625696} {"current_steps": 5810, "total_steps": 40000, "loss": 0.0, "lr": 4.744290941907364e-05, "epoch": 64.55555555555556, "percentage": 14.52, "elapsed_time": "0:39:30", "remaining_time": "3:52:28", "throughput": 686.47, "total_tokens": 1627104} {"current_steps": 5815, "total_steps": 40000, "loss": 0.0, "lr": 4.7438582365153594e-05, "epoch": 64.61111111111111, "percentage": 14.54, "elapsed_time": "0:39:32", "remaining_time": "3:52:25", "throughput": 686.48, "total_tokens": 1628480} {"current_steps": 5820, "total_steps": 40000, "loss": 0.0, "lr": 4.743425185092217e-05, "epoch": 64.66666666666667, "percentage": 14.55, "elapsed_time": "0:39:34", "remaining_time": "3:52:23", "throughput": 686.53, "total_tokens": 1629936} {"current_steps": 5825, "total_steps": 40000, "loss": 0.0, "lr": 4.742991787704719e-05, "epoch": 64.72222222222223, "percentage": 14.56, "elapsed_time": "0:39:36", "remaining_time": "3:52:20", "throughput": 686.55, "total_tokens": 1631328} {"current_steps": 5830, "total_steps": 40000, "loss": 0.0, "lr": 4.7425580444196994e-05, "epoch": 64.77777777777777, "percentage": 14.57, "elapsed_time": "0:39:38", "remaining_time": "3:52:18", "throughput": 686.56, "total_tokens": 1632688} {"current_steps": 5835, "total_steps": 40000, "loss": 0.0, "lr": 4.742123955304048e-05, "epoch": 64.83333333333333, "percentage": 14.59, "elapsed_time": "0:39:40", "remaining_time": "3:52:15", "throughput": 686.6, "total_tokens": 1634128} {"current_steps": 5840, "total_steps": 40000, "loss": 0.0, "lr": 4.741689520424706e-05, "epoch": 64.88888888888889, "percentage": 14.6, "elapsed_time": "0:39:41", "remaining_time": "3:52:12", "throughput": 686.63, "total_tokens": 1635536} {"current_steps": 5845, "total_steps": 40000, "loss": 0.0, "lr": 4.741254739848669e-05, "epoch": 64.94444444444444, "percentage": 14.61, "elapsed_time": "0:39:43", "remaining_time": "3:52:10", "throughput": 686.63, "total_tokens": 1636896} {"current_steps": 5850, "total_steps": 40000, "loss": 0.0, "lr": 4.740819613642987e-05, "epoch": 65.0, "percentage": 14.62, "elapsed_time": "0:39:46", "remaining_time": "3:52:08", "throughput": 686.6, "total_tokens": 1638272} {"current_steps": 5855, "total_steps": 40000, "loss": 0.0, "lr": 4.74038414187476e-05, "epoch": 65.05555555555556, "percentage": 14.64, "elapsed_time": "0:39:48", "remaining_time": "3:52:07", "throughput": 686.53, "total_tokens": 1639632} {"current_steps": 5860, "total_steps": 40000, "loss": 0.0, "lr": 4.739948324611144e-05, "epoch": 65.11111111111111, "percentage": 14.65, "elapsed_time": "0:39:50", "remaining_time": "3:52:05", "throughput": 686.55, "total_tokens": 1641008} {"current_steps": 5865, "total_steps": 40000, "loss": 0.0, "lr": 4.7395121619193465e-05, "epoch": 65.16666666666667, "percentage": 14.66, "elapsed_time": "0:39:52", "remaining_time": "3:52:02", "throughput": 686.57, "total_tokens": 1642384} {"current_steps": 5870, "total_steps": 40000, "loss": 0.0, "lr": 4.7390756538666313e-05, "epoch": 65.22222222222223, "percentage": 14.67, "elapsed_time": "0:39:54", "remaining_time": "3:52:00", "throughput": 686.58, "total_tokens": 1643760} {"current_steps": 5875, "total_steps": 40000, "loss": 0.0, "lr": 4.738638800520311e-05, "epoch": 65.27777777777777, "percentage": 14.69, "elapsed_time": "0:39:56", "remaining_time": "3:51:57", "throughput": 686.63, "total_tokens": 1645216} {"current_steps": 5880, "total_steps": 40000, "loss": 0.0, "lr": 4.738201601947757e-05, "epoch": 65.33333333333333, "percentage": 14.7, "elapsed_time": "0:39:58", "remaining_time": "3:51:54", "throughput": 686.64, "total_tokens": 1646576} {"current_steps": 5885, "total_steps": 40000, "loss": 0.0, "lr": 4.7377640582163876e-05, "epoch": 65.38888888888889, "percentage": 14.71, "elapsed_time": "0:39:59", "remaining_time": "3:51:52", "throughput": 686.67, "total_tokens": 1647984} {"current_steps": 5890, "total_steps": 40000, "loss": 0.0, "lr": 4.7373261693936786e-05, "epoch": 65.44444444444444, "percentage": 14.72, "elapsed_time": "0:40:01", "remaining_time": "3:51:49", "throughput": 686.69, "total_tokens": 1649376} {"current_steps": 5895, "total_steps": 40000, "loss": 0.0, "lr": 4.7368879355471595e-05, "epoch": 65.5, "percentage": 14.74, "elapsed_time": "0:40:03", "remaining_time": "3:51:47", "throughput": 686.72, "total_tokens": 1650784} {"current_steps": 5900, "total_steps": 40000, "loss": 0.0, "lr": 4.736449356744409e-05, "epoch": 65.55555555555556, "percentage": 14.75, "elapsed_time": "0:40:05", "remaining_time": "3:51:44", "throughput": 686.74, "total_tokens": 1652160} {"current_steps": 5905, "total_steps": 40000, "loss": 0.0, "lr": 4.736010433053064e-05, "epoch": 65.61111111111111, "percentage": 14.76, "elapsed_time": "0:40:07", "remaining_time": "3:51:42", "throughput": 686.77, "total_tokens": 1653568} {"current_steps": 5910, "total_steps": 40000, "loss": 0.0, "lr": 4.73557116454081e-05, "epoch": 65.66666666666667, "percentage": 14.77, "elapsed_time": "0:40:09", "remaining_time": "3:51:39", "throughput": 686.81, "total_tokens": 1655008} {"current_steps": 5915, "total_steps": 40000, "loss": 0.0, "lr": 4.735131551275389e-05, "epoch": 65.72222222222223, "percentage": 14.79, "elapsed_time": "0:40:11", "remaining_time": "3:51:37", "throughput": 686.85, "total_tokens": 1656448} {"current_steps": 5920, "total_steps": 40000, "loss": 0.0, "lr": 4.734691593324594e-05, "epoch": 65.77777777777777, "percentage": 14.8, "elapsed_time": "0:40:13", "remaining_time": "3:51:34", "throughput": 686.88, "total_tokens": 1657840} {"current_steps": 5925, "total_steps": 40000, "loss": 0.0, "lr": 4.734251290756272e-05, "epoch": 65.83333333333333, "percentage": 14.81, "elapsed_time": "0:40:15", "remaining_time": "3:51:31", "throughput": 686.9, "total_tokens": 1659248} {"current_steps": 5930, "total_steps": 40000, "loss": 0.0, "lr": 4.7338106436383246e-05, "epoch": 65.88888888888889, "percentage": 14.82, "elapsed_time": "0:40:17", "remaining_time": "3:51:29", "throughput": 686.93, "total_tokens": 1660656} {"current_steps": 5935, "total_steps": 40000, "loss": 0.0, "lr": 4.733369652038703e-05, "epoch": 65.94444444444444, "percentage": 14.84, "elapsed_time": "0:40:19", "remaining_time": "3:51:26", "throughput": 686.96, "total_tokens": 1662064} {"current_steps": 5940, "total_steps": 40000, "loss": 0.0, "lr": 4.7329283160254156e-05, "epoch": 66.0, "percentage": 14.85, "elapsed_time": "0:40:21", "remaining_time": "3:51:25", "throughput": 686.97, "total_tokens": 1663520} {"current_steps": 5945, "total_steps": 40000, "loss": 0.0, "lr": 4.732486635666521e-05, "epoch": 66.05555555555556, "percentage": 14.86, "elapsed_time": "0:40:23", "remaining_time": "3:51:24", "throughput": 686.9, "total_tokens": 1664864} {"current_steps": 5950, "total_steps": 40000, "loss": 0.0, "lr": 4.732044611030132e-05, "epoch": 66.11111111111111, "percentage": 14.88, "elapsed_time": "0:40:26", "remaining_time": "3:51:23", "throughput": 686.81, "total_tokens": 1666240} {"current_steps": 5955, "total_steps": 40000, "loss": 0.0, "lr": 4.731602242184414e-05, "epoch": 66.16666666666667, "percentage": 14.89, "elapsed_time": "0:40:28", "remaining_time": "3:51:20", "throughput": 686.84, "total_tokens": 1667648} {"current_steps": 5960, "total_steps": 40000, "loss": 0.0, "lr": 4.7311595291975864e-05, "epoch": 66.22222222222223, "percentage": 14.9, "elapsed_time": "0:40:29", "remaining_time": "3:51:18", "throughput": 686.86, "total_tokens": 1669040} {"current_steps": 5965, "total_steps": 40000, "loss": 0.0, "lr": 4.7307164721379216e-05, "epoch": 66.27777777777777, "percentage": 14.91, "elapsed_time": "0:40:31", "remaining_time": "3:51:15", "throughput": 686.87, "total_tokens": 1670400} {"current_steps": 5970, "total_steps": 40000, "loss": 0.0, "lr": 4.730273071073743e-05, "epoch": 66.33333333333333, "percentage": 14.92, "elapsed_time": "0:40:33", "remaining_time": "3:51:13", "throughput": 686.92, "total_tokens": 1671856} {"current_steps": 5975, "total_steps": 40000, "loss": 0.0, "lr": 4.729829326073429e-05, "epoch": 66.38888888888889, "percentage": 14.94, "elapsed_time": "0:40:35", "remaining_time": "3:51:10", "throughput": 686.95, "total_tokens": 1673248} {"current_steps": 5980, "total_steps": 40000, "loss": 0.0, "lr": 4.7293852372054126e-05, "epoch": 66.44444444444444, "percentage": 14.95, "elapsed_time": "0:40:37", "remaining_time": "3:51:08", "throughput": 686.98, "total_tokens": 1674672} {"current_steps": 5985, "total_steps": 40000, "loss": 0.0, "lr": 4.728940804538176e-05, "epoch": 66.5, "percentage": 14.96, "elapsed_time": "0:40:39", "remaining_time": "3:51:05", "throughput": 687.01, "total_tokens": 1676080} {"current_steps": 5990, "total_steps": 40000, "loss": 0.0, "lr": 4.7284960281402556e-05, "epoch": 66.55555555555556, "percentage": 14.97, "elapsed_time": "0:40:41", "remaining_time": "3:51:02", "throughput": 687.05, "total_tokens": 1677504} {"current_steps": 5995, "total_steps": 40000, "loss": 0.0, "lr": 4.728050908080244e-05, "epoch": 66.61111111111111, "percentage": 14.99, "elapsed_time": "0:40:43", "remaining_time": "3:51:00", "throughput": 687.08, "total_tokens": 1678912} {"current_steps": 6000, "total_steps": 40000, "loss": 0.0, "lr": 4.727605444426782e-05, "epoch": 66.66666666666667, "percentage": 15.0, "elapsed_time": "0:40:45", "remaining_time": "3:50:57", "throughput": 687.12, "total_tokens": 1680352} {"current_steps": 6000, "total_steps": 40000, "eval_loss": 0.24982008337974548, "epoch": 66.66666666666667, "percentage": 15.0, "elapsed_time": "0:40:46", "remaining_time": "3:51:05", "throughput": 686.75, "total_tokens": 1680352} {"current_steps": 6005, "total_steps": 40000, "loss": 0.0, "lr": 4.727159637248567e-05, "epoch": 66.72222222222223, "percentage": 15.01, "elapsed_time": "0:40:49", "remaining_time": "3:51:09", "throughput": 686.43, "total_tokens": 1681744} {"current_steps": 6010, "total_steps": 40000, "loss": 0.0, "lr": 4.7267134866143474e-05, "epoch": 66.77777777777777, "percentage": 15.02, "elapsed_time": "0:40:51", "remaining_time": "3:51:07", "throughput": 686.47, "total_tokens": 1683168} {"current_steps": 6015, "total_steps": 40000, "loss": 0.0, "lr": 4.726266992592926e-05, "epoch": 66.83333333333333, "percentage": 15.04, "elapsed_time": "0:40:53", "remaining_time": "3:51:04", "throughput": 686.46, "total_tokens": 1684528} {"current_steps": 6020, "total_steps": 40000, "loss": 0.0, "lr": 4.725820155253157e-05, "epoch": 66.88888888888889, "percentage": 15.05, "elapsed_time": "0:40:55", "remaining_time": "3:51:02", "throughput": 686.46, "total_tokens": 1685904} {"current_steps": 6025, "total_steps": 40000, "loss": 0.0, "lr": 4.725372974663948e-05, "epoch": 66.94444444444444, "percentage": 15.06, "elapsed_time": "0:40:57", "remaining_time": "3:50:59", "throughput": 686.48, "total_tokens": 1687280} {"current_steps": 6030, "total_steps": 40000, "loss": 0.0, "lr": 4.724925450894262e-05, "epoch": 67.0, "percentage": 15.07, "elapsed_time": "0:41:00", "remaining_time": "3:50:58", "throughput": 686.46, "total_tokens": 1688688} {"current_steps": 6035, "total_steps": 40000, "loss": 0.0, "lr": 4.72447758401311e-05, "epoch": 67.05555555555556, "percentage": 15.09, "elapsed_time": "0:41:02", "remaining_time": "3:50:57", "throughput": 686.42, "total_tokens": 1690112} {"current_steps": 6040, "total_steps": 40000, "loss": 0.0, "lr": 4.7240293740895616e-05, "epoch": 67.11111111111111, "percentage": 15.1, "elapsed_time": "0:41:04", "remaining_time": "3:50:54", "throughput": 686.47, "total_tokens": 1691568} {"current_steps": 6045, "total_steps": 40000, "loss": 0.0, "lr": 4.723580821192733e-05, "epoch": 67.16666666666667, "percentage": 15.11, "elapsed_time": "0:41:06", "remaining_time": "3:50:52", "throughput": 686.49, "total_tokens": 1692960} {"current_steps": 6050, "total_steps": 40000, "loss": 0.0, "lr": 4.7231319253917996e-05, "epoch": 67.22222222222223, "percentage": 15.12, "elapsed_time": "0:41:08", "remaining_time": "3:50:49", "throughput": 686.52, "total_tokens": 1694352} {"current_steps": 6055, "total_steps": 40000, "loss": 0.0, "lr": 4.722682686755986e-05, "epoch": 67.27777777777777, "percentage": 15.14, "elapsed_time": "0:41:09", "remaining_time": "3:50:46", "throughput": 686.54, "total_tokens": 1695744} {"current_steps": 6060, "total_steps": 40000, "loss": 0.0, "lr": 4.722233105354569e-05, "epoch": 67.33333333333333, "percentage": 15.15, "elapsed_time": "0:41:11", "remaining_time": "3:50:44", "throughput": 686.56, "total_tokens": 1697120} {"current_steps": 6065, "total_steps": 40000, "loss": 0.0, "lr": 4.7217831812568815e-05, "epoch": 67.38888888888889, "percentage": 15.16, "elapsed_time": "0:41:13", "remaining_time": "3:50:41", "throughput": 686.59, "total_tokens": 1698528} {"current_steps": 6070, "total_steps": 40000, "loss": 0.0, "lr": 4.721332914532307e-05, "epoch": 67.44444444444444, "percentage": 15.17, "elapsed_time": "0:41:15", "remaining_time": "3:50:39", "throughput": 686.61, "total_tokens": 1699920} {"current_steps": 6075, "total_steps": 40000, "loss": 0.0, "lr": 4.720882305250281e-05, "epoch": 67.5, "percentage": 15.19, "elapsed_time": "0:41:17", "remaining_time": "3:50:36", "throughput": 686.64, "total_tokens": 1701312} {"current_steps": 6080, "total_steps": 40000, "loss": 0.0, "lr": 4.720431353480295e-05, "epoch": 67.55555555555556, "percentage": 15.2, "elapsed_time": "0:41:19", "remaining_time": "3:50:34", "throughput": 686.65, "total_tokens": 1702688} {"current_steps": 6085, "total_steps": 40000, "loss": 0.0, "lr": 4.719980059291891e-05, "epoch": 67.61111111111111, "percentage": 15.21, "elapsed_time": "0:41:21", "remaining_time": "3:50:31", "throughput": 686.68, "total_tokens": 1704096} {"current_steps": 6090, "total_steps": 40000, "loss": 0.0, "lr": 4.7195284227546634e-05, "epoch": 67.66666666666667, "percentage": 15.22, "elapsed_time": "0:41:23", "remaining_time": "3:50:29", "throughput": 686.71, "total_tokens": 1705520} {"current_steps": 6095, "total_steps": 40000, "loss": 0.0, "lr": 4.7190764439382604e-05, "epoch": 67.72222222222223, "percentage": 15.24, "elapsed_time": "0:41:25", "remaining_time": "3:50:26", "throughput": 686.76, "total_tokens": 1706976} {"current_steps": 6100, "total_steps": 40000, "loss": 0.0, "lr": 4.7186241229123826e-05, "epoch": 67.77777777777777, "percentage": 15.25, "elapsed_time": "0:41:27", "remaining_time": "3:50:23", "throughput": 686.8, "total_tokens": 1708400} {"current_steps": 6105, "total_steps": 40000, "loss": 0.0, "lr": 4.718171459746785e-05, "epoch": 67.83333333333333, "percentage": 15.26, "elapsed_time": "0:41:29", "remaining_time": "3:50:21", "throughput": 686.81, "total_tokens": 1709776} {"current_steps": 6110, "total_steps": 40000, "loss": 0.0, "lr": 4.717718454511273e-05, "epoch": 67.88888888888889, "percentage": 15.28, "elapsed_time": "0:41:31", "remaining_time": "3:50:18", "throughput": 686.83, "total_tokens": 1711168} {"current_steps": 6115, "total_steps": 40000, "loss": 0.0, "lr": 4.7172651072757056e-05, "epoch": 67.94444444444444, "percentage": 15.29, "elapsed_time": "0:41:33", "remaining_time": "3:50:16", "throughput": 686.84, "total_tokens": 1712528} {"current_steps": 6120, "total_steps": 40000, "loss": 0.0, "lr": 4.7168114181099945e-05, "epoch": 68.0, "percentage": 15.3, "elapsed_time": "0:41:35", "remaining_time": "3:50:14", "throughput": 686.81, "total_tokens": 1713920} {"current_steps": 6125, "total_steps": 40000, "loss": 0.0, "lr": 4.716357387084105e-05, "epoch": 68.05555555555556, "percentage": 15.31, "elapsed_time": "0:41:37", "remaining_time": "3:50:13", "throughput": 686.76, "total_tokens": 1715296} {"current_steps": 6130, "total_steps": 40000, "loss": 0.0, "lr": 4.715903014268054e-05, "epoch": 68.11111111111111, "percentage": 15.32, "elapsed_time": "0:41:39", "remaining_time": "3:50:11", "throughput": 686.78, "total_tokens": 1716672} {"current_steps": 6135, "total_steps": 40000, "loss": 0.0, "lr": 4.715448299731911e-05, "epoch": 68.16666666666667, "percentage": 15.34, "elapsed_time": "0:41:41", "remaining_time": "3:50:08", "throughput": 686.79, "total_tokens": 1718048} {"current_steps": 6140, "total_steps": 40000, "loss": 0.0, "lr": 4.7149932435457986e-05, "epoch": 68.22222222222223, "percentage": 15.35, "elapsed_time": "0:41:43", "remaining_time": "3:50:05", "throughput": 686.82, "total_tokens": 1719456} {"current_steps": 6145, "total_steps": 40000, "loss": 0.0, "lr": 4.714537845779894e-05, "epoch": 68.27777777777777, "percentage": 15.36, "elapsed_time": "0:41:45", "remaining_time": "3:50:03", "throughput": 686.85, "total_tokens": 1720880} {"current_steps": 6150, "total_steps": 40000, "loss": 0.0, "lr": 4.714082106504423e-05, "epoch": 68.33333333333333, "percentage": 15.38, "elapsed_time": "0:41:47", "remaining_time": "3:50:00", "throughput": 686.88, "total_tokens": 1722288} {"current_steps": 6155, "total_steps": 40000, "loss": 0.0, "lr": 4.713626025789667e-05, "epoch": 68.38888888888889, "percentage": 15.39, "elapsed_time": "0:41:49", "remaining_time": "3:49:58", "throughput": 686.92, "total_tokens": 1723712} {"current_steps": 6160, "total_steps": 40000, "loss": 0.0, "lr": 4.7131696037059606e-05, "epoch": 68.44444444444444, "percentage": 15.4, "elapsed_time": "0:41:51", "remaining_time": "3:49:55", "throughput": 686.94, "total_tokens": 1725088} {"current_steps": 6165, "total_steps": 40000, "loss": 0.0, "lr": 4.712712840323689e-05, "epoch": 68.5, "percentage": 15.41, "elapsed_time": "0:41:53", "remaining_time": "3:49:53", "throughput": 686.96, "total_tokens": 1726464} {"current_steps": 6170, "total_steps": 40000, "loss": 0.0, "lr": 4.71225573571329e-05, "epoch": 68.55555555555556, "percentage": 15.43, "elapsed_time": "0:41:55", "remaining_time": "3:49:50", "throughput": 687.02, "total_tokens": 1727952} {"current_steps": 6175, "total_steps": 40000, "loss": 0.0, "lr": 4.711798289945256e-05, "epoch": 68.61111111111111, "percentage": 15.44, "elapsed_time": "0:41:57", "remaining_time": "3:49:47", "throughput": 687.05, "total_tokens": 1729360} {"current_steps": 6180, "total_steps": 40000, "loss": 0.0, "lr": 4.71134050309013e-05, "epoch": 68.66666666666667, "percentage": 15.45, "elapsed_time": "0:41:59", "remaining_time": "3:49:45", "throughput": 687.1, "total_tokens": 1730816} {"current_steps": 6185, "total_steps": 40000, "loss": 0.0, "lr": 4.710882375218509e-05, "epoch": 68.72222222222223, "percentage": 15.46, "elapsed_time": "0:42:00", "remaining_time": "3:49:42", "throughput": 687.14, "total_tokens": 1732256} {"current_steps": 6190, "total_steps": 40000, "loss": 0.0, "lr": 4.7104239064010424e-05, "epoch": 68.77777777777777, "percentage": 15.47, "elapsed_time": "0:42:02", "remaining_time": "3:49:40", "throughput": 687.16, "total_tokens": 1733648} {"current_steps": 6195, "total_steps": 40000, "loss": 0.0, "lr": 4.709965096708432e-05, "epoch": 68.83333333333333, "percentage": 15.49, "elapsed_time": "0:42:04", "remaining_time": "3:49:37", "throughput": 687.17, "total_tokens": 1735008} {"current_steps": 6200, "total_steps": 40000, "loss": 0.0, "lr": 4.709505946211431e-05, "epoch": 68.88888888888889, "percentage": 15.5, "elapsed_time": "0:42:06", "remaining_time": "3:49:35", "throughput": 687.19, "total_tokens": 1736384} {"current_steps": 6200, "total_steps": 40000, "eval_loss": 0.232396200299263, "epoch": 68.88888888888889, "percentage": 15.5, "elapsed_time": "0:42:08", "remaining_time": "3:49:42", "throughput": 686.83, "total_tokens": 1736384} {"current_steps": 6205, "total_steps": 40000, "loss": 0.0, "lr": 4.709046454980846e-05, "epoch": 68.94444444444444, "percentage": 15.51, "elapsed_time": "0:42:11", "remaining_time": "3:49:46", "throughput": 686.5, "total_tokens": 1737776} {"current_steps": 6210, "total_steps": 40000, "loss": 0.0, "lr": 4.708586623087538e-05, "epoch": 69.0, "percentage": 15.53, "elapsed_time": "0:42:13", "remaining_time": "3:49:45", "throughput": 686.47, "total_tokens": 1739184} {"current_steps": 6215, "total_steps": 40000, "loss": 0.0, "lr": 4.708126450602418e-05, "epoch": 69.05555555555556, "percentage": 15.54, "elapsed_time": "0:42:15", "remaining_time": "3:49:44", "throughput": 686.43, "total_tokens": 1740592} {"current_steps": 6220, "total_steps": 40000, "loss": 0.0, "lr": 4.7076659375964495e-05, "epoch": 69.11111111111111, "percentage": 15.55, "elapsed_time": "0:42:17", "remaining_time": "3:49:41", "throughput": 686.45, "total_tokens": 1741984} {"current_steps": 6225, "total_steps": 40000, "loss": 0.0, "lr": 4.707205084140651e-05, "epoch": 69.16666666666667, "percentage": 15.56, "elapsed_time": "0:42:19", "remaining_time": "3:49:39", "throughput": 686.48, "total_tokens": 1743408} {"current_steps": 6230, "total_steps": 40000, "loss": 0.0, "lr": 4.7067438903060904e-05, "epoch": 69.22222222222223, "percentage": 15.57, "elapsed_time": "0:42:21", "remaining_time": "3:49:36", "throughput": 686.53, "total_tokens": 1744848} {"current_steps": 6235, "total_steps": 40000, "loss": 0.0, "lr": 4.70628235616389e-05, "epoch": 69.27777777777777, "percentage": 15.59, "elapsed_time": "0:42:23", "remaining_time": "3:49:34", "throughput": 686.55, "total_tokens": 1746240} {"current_steps": 6240, "total_steps": 40000, "loss": 0.0, "lr": 4.7058204817852256e-05, "epoch": 69.33333333333333, "percentage": 15.6, "elapsed_time": "0:42:25", "remaining_time": "3:49:31", "throughput": 686.56, "total_tokens": 1747600} {"current_steps": 6245, "total_steps": 40000, "loss": 0.0, "lr": 4.705358267241322e-05, "epoch": 69.38888888888889, "percentage": 15.61, "elapsed_time": "0:42:27", "remaining_time": "3:49:28", "throughput": 686.59, "total_tokens": 1749008} {"current_steps": 6250, "total_steps": 40000, "loss": 0.0, "lr": 4.704895712603459e-05, "epoch": 69.44444444444444, "percentage": 15.62, "elapsed_time": "0:42:29", "remaining_time": "3:49:26", "throughput": 686.61, "total_tokens": 1750400} {"current_steps": 6255, "total_steps": 40000, "loss": 0.0, "lr": 4.704432817942969e-05, "epoch": 69.5, "percentage": 15.64, "elapsed_time": "0:42:31", "remaining_time": "3:49:23", "throughput": 686.65, "total_tokens": 1751856} {"current_steps": 6260, "total_steps": 40000, "loss": 0.0, "lr": 4.703969583331236e-05, "epoch": 69.55555555555556, "percentage": 15.65, "elapsed_time": "0:42:33", "remaining_time": "3:49:21", "throughput": 686.66, "total_tokens": 1753200} {"current_steps": 6265, "total_steps": 40000, "loss": 0.0, "lr": 4.7035060088396965e-05, "epoch": 69.61111111111111, "percentage": 15.66, "elapsed_time": "0:42:35", "remaining_time": "3:49:18", "throughput": 686.67, "total_tokens": 1754560} {"current_steps": 6270, "total_steps": 40000, "loss": 0.0, "lr": 4.703042094539839e-05, "epoch": 69.66666666666667, "percentage": 15.68, "elapsed_time": "0:42:37", "remaining_time": "3:49:16", "throughput": 686.69, "total_tokens": 1755968} {"current_steps": 6275, "total_steps": 40000, "loss": 0.0, "lr": 4.702577840503206e-05, "epoch": 69.72222222222223, "percentage": 15.69, "elapsed_time": "0:42:39", "remaining_time": "3:49:13", "throughput": 686.72, "total_tokens": 1757376} {"current_steps": 6280, "total_steps": 40000, "loss": 0.0, "lr": 4.70211324680139e-05, "epoch": 69.77777777777777, "percentage": 15.7, "elapsed_time": "0:42:41", "remaining_time": "3:49:11", "throughput": 686.75, "total_tokens": 1758768} {"current_steps": 6285, "total_steps": 40000, "loss": 0.0, "lr": 4.7016483135060386e-05, "epoch": 69.83333333333333, "percentage": 15.71, "elapsed_time": "0:42:42", "remaining_time": "3:49:08", "throughput": 686.79, "total_tokens": 1760208} {"current_steps": 6290, "total_steps": 40000, "loss": 0.0, "lr": 4.701183040688849e-05, "epoch": 69.88888888888889, "percentage": 15.72, "elapsed_time": "0:42:44", "remaining_time": "3:49:06", "throughput": 686.8, "total_tokens": 1761584} {"current_steps": 6295, "total_steps": 40000, "loss": 0.0, "lr": 4.700717428421573e-05, "epoch": 69.94444444444444, "percentage": 15.74, "elapsed_time": "0:42:46", "remaining_time": "3:49:03", "throughput": 686.85, "total_tokens": 1763040} {"current_steps": 6300, "total_steps": 40000, "loss": 0.0, "lr": 4.700251476776014e-05, "epoch": 70.0, "percentage": 15.75, "elapsed_time": "0:42:48", "remaining_time": "3:49:01", "throughput": 686.82, "total_tokens": 1764432} {"current_steps": 6305, "total_steps": 40000, "loss": 0.0, "lr": 4.699785185824026e-05, "epoch": 70.05555555555556, "percentage": 15.76, "elapsed_time": "0:42:51", "remaining_time": "3:49:00", "throughput": 686.77, "total_tokens": 1765808} {"current_steps": 6310, "total_steps": 40000, "loss": 0.0, "lr": 4.699318555637519e-05, "epoch": 70.11111111111111, "percentage": 15.78, "elapsed_time": "0:42:53", "remaining_time": "3:48:58", "throughput": 686.78, "total_tokens": 1767168} {"current_steps": 6315, "total_steps": 40000, "loss": 0.0, "lr": 4.6988515862884525e-05, "epoch": 70.16666666666667, "percentage": 15.79, "elapsed_time": "0:42:55", "remaining_time": "3:48:55", "throughput": 686.81, "total_tokens": 1768576} {"current_steps": 6320, "total_steps": 40000, "loss": 0.0, "lr": 4.698384277848838e-05, "epoch": 70.22222222222223, "percentage": 15.8, "elapsed_time": "0:42:57", "remaining_time": "3:48:53", "throughput": 686.86, "total_tokens": 1770032} {"current_steps": 6325, "total_steps": 40000, "loss": 0.0, "lr": 4.6979166303907425e-05, "epoch": 70.27777777777777, "percentage": 15.81, "elapsed_time": "0:42:58", "remaining_time": "3:48:50", "throughput": 686.87, "total_tokens": 1771392} {"current_steps": 6330, "total_steps": 40000, "loss": 0.0, "lr": 4.697448643986281e-05, "epoch": 70.33333333333333, "percentage": 15.82, "elapsed_time": "0:43:00", "remaining_time": "3:48:48", "throughput": 686.88, "total_tokens": 1772784} {"current_steps": 6335, "total_steps": 40000, "loss": 0.0, "lr": 4.696980318707624e-05, "epoch": 70.38888888888889, "percentage": 15.84, "elapsed_time": "0:43:02", "remaining_time": "3:48:45", "throughput": 686.93, "total_tokens": 1774224} {"current_steps": 6340, "total_steps": 40000, "loss": 0.0, "lr": 4.6965116546269924e-05, "epoch": 70.44444444444444, "percentage": 15.85, "elapsed_time": "0:43:04", "remaining_time": "3:48:42", "throughput": 686.96, "total_tokens": 1775648} {"current_steps": 6345, "total_steps": 40000, "loss": 0.0, "lr": 4.6960426518166615e-05, "epoch": 70.5, "percentage": 15.86, "elapsed_time": "0:43:06", "remaining_time": "3:48:40", "throughput": 686.98, "total_tokens": 1777024} {"current_steps": 6350, "total_steps": 40000, "loss": 0.0, "lr": 4.6955733103489556e-05, "epoch": 70.55555555555556, "percentage": 15.88, "elapsed_time": "0:43:08", "remaining_time": "3:48:37", "throughput": 687.01, "total_tokens": 1778448} {"current_steps": 6355, "total_steps": 40000, "loss": 0.0, "lr": 4.695103630296255e-05, "epoch": 70.61111111111111, "percentage": 15.89, "elapsed_time": "0:43:10", "remaining_time": "3:48:35", "throughput": 687.04, "total_tokens": 1779840} {"current_steps": 6360, "total_steps": 40000, "loss": 0.0, "lr": 4.694633611730988e-05, "epoch": 70.66666666666667, "percentage": 15.9, "elapsed_time": "0:43:12", "remaining_time": "3:48:32", "throughput": 687.07, "total_tokens": 1781264} {"current_steps": 6365, "total_steps": 40000, "loss": 0.0, "lr": 4.694163254725639e-05, "epoch": 70.72222222222223, "percentage": 15.91, "elapsed_time": "0:43:14", "remaining_time": "3:48:30", "throughput": 687.1, "total_tokens": 1782672} {"current_steps": 6370, "total_steps": 40000, "loss": 0.0, "lr": 4.693692559352743e-05, "epoch": 70.77777777777777, "percentage": 15.93, "elapsed_time": "0:43:16", "remaining_time": "3:48:27", "throughput": 687.13, "total_tokens": 1784080} {"current_steps": 6375, "total_steps": 40000, "loss": 0.0, "lr": 4.693221525684886e-05, "epoch": 70.83333333333333, "percentage": 15.94, "elapsed_time": "0:43:18", "remaining_time": "3:48:25", "throughput": 687.15, "total_tokens": 1785472} {"current_steps": 6380, "total_steps": 40000, "loss": 0.0, "lr": 4.6927501537947084e-05, "epoch": 70.88888888888889, "percentage": 15.95, "elapsed_time": "0:43:20", "remaining_time": "3:48:22", "throughput": 687.18, "total_tokens": 1786880} {"current_steps": 6385, "total_steps": 40000, "loss": 0.0, "lr": 4.692278443754901e-05, "epoch": 70.94444444444444, "percentage": 15.96, "elapsed_time": "0:43:22", "remaining_time": "3:48:19", "throughput": 687.2, "total_tokens": 1788256} {"current_steps": 6390, "total_steps": 40000, "loss": 0.0, "lr": 4.691806395638208e-05, "epoch": 71.0, "percentage": 15.97, "elapsed_time": "0:43:24", "remaining_time": "3:48:18", "throughput": 687.17, "total_tokens": 1789632} {"current_steps": 6395, "total_steps": 40000, "loss": 0.0, "lr": 4.6913340095174255e-05, "epoch": 71.05555555555556, "percentage": 15.99, "elapsed_time": "0:43:26", "remaining_time": "3:48:17", "throughput": 687.13, "total_tokens": 1791056} {"current_steps": 6400, "total_steps": 40000, "loss": 0.0, "lr": 4.690861285465399e-05, "epoch": 71.11111111111111, "percentage": 16.0, "elapsed_time": "0:43:28", "remaining_time": "3:48:14", "throughput": 687.16, "total_tokens": 1792480} {"current_steps": 6400, "total_steps": 40000, "eval_loss": 0.2660376727581024, "epoch": 71.11111111111111, "percentage": 16.0, "elapsed_time": "0:43:29", "remaining_time": "3:48:21", "throughput": 686.81, "total_tokens": 1792480} {"current_steps": 6405, "total_steps": 40000, "loss": 0.0, "lr": 4.690388223555031e-05, "epoch": 71.16666666666667, "percentage": 16.01, "elapsed_time": "0:43:33", "remaining_time": "3:48:27", "throughput": 686.45, "total_tokens": 1793888} {"current_steps": 6410, "total_steps": 40000, "loss": 0.0, "lr": 4.689914823859273e-05, "epoch": 71.22222222222223, "percentage": 16.02, "elapsed_time": "0:43:35", "remaining_time": "3:48:24", "throughput": 686.46, "total_tokens": 1795280} {"current_steps": 6415, "total_steps": 40000, "loss": 0.0, "lr": 4.689441086451129e-05, "epoch": 71.27777777777777, "percentage": 16.04, "elapsed_time": "0:43:37", "remaining_time": "3:48:22", "throughput": 686.5, "total_tokens": 1796720} {"current_steps": 6420, "total_steps": 40000, "loss": 0.0, "lr": 4.688967011403655e-05, "epoch": 71.33333333333333, "percentage": 16.05, "elapsed_time": "0:43:39", "remaining_time": "3:48:19", "throughput": 686.53, "total_tokens": 1798144} {"current_steps": 6425, "total_steps": 40000, "loss": 0.0, "lr": 4.68849259878996e-05, "epoch": 71.38888888888889, "percentage": 16.06, "elapsed_time": "0:43:41", "remaining_time": "3:48:17", "throughput": 686.54, "total_tokens": 1799504} {"current_steps": 6430, "total_steps": 40000, "loss": 0.0, "lr": 4.6880178486832036e-05, "epoch": 71.44444444444444, "percentage": 16.07, "elapsed_time": "0:43:43", "remaining_time": "3:48:14", "throughput": 686.57, "total_tokens": 1800928} {"current_steps": 6435, "total_steps": 40000, "loss": 0.0, "lr": 4.687542761156598e-05, "epoch": 71.5, "percentage": 16.09, "elapsed_time": "0:43:45", "remaining_time": "3:48:12", "throughput": 686.59, "total_tokens": 1802304} {"current_steps": 6440, "total_steps": 40000, "loss": 0.0, "lr": 4.6870673362834096e-05, "epoch": 71.55555555555556, "percentage": 16.1, "elapsed_time": "0:43:46", "remaining_time": "3:48:09", "throughput": 686.61, "total_tokens": 1803712} {"current_steps": 6445, "total_steps": 40000, "loss": 0.0, "lr": 4.6865915741369526e-05, "epoch": 71.61111111111111, "percentage": 16.11, "elapsed_time": "0:43:48", "remaining_time": "3:48:07", "throughput": 686.64, "total_tokens": 1805104} {"current_steps": 6450, "total_steps": 40000, "loss": 0.0, "lr": 4.686115474790597e-05, "epoch": 71.66666666666667, "percentage": 16.12, "elapsed_time": "0:43:50", "remaining_time": "3:48:04", "throughput": 686.67, "total_tokens": 1806528} {"current_steps": 6455, "total_steps": 40000, "loss": 0.0, "lr": 4.685639038317762e-05, "epoch": 71.72222222222223, "percentage": 16.14, "elapsed_time": "0:43:52", "remaining_time": "3:48:02", "throughput": 686.68, "total_tokens": 1807904} {"current_steps": 6460, "total_steps": 40000, "loss": 0.0, "lr": 4.685162264791921e-05, "epoch": 71.77777777777777, "percentage": 16.15, "elapsed_time": "0:43:54", "remaining_time": "3:47:59", "throughput": 686.7, "total_tokens": 1809280} {"current_steps": 6465, "total_steps": 40000, "loss": 0.0, "lr": 4.684685154286599e-05, "epoch": 71.83333333333333, "percentage": 16.16, "elapsed_time": "0:43:56", "remaining_time": "3:47:57", "throughput": 686.71, "total_tokens": 1810640} {"current_steps": 6470, "total_steps": 40000, "loss": 0.0, "lr": 4.684207706875371e-05, "epoch": 71.88888888888889, "percentage": 16.18, "elapsed_time": "0:43:58", "remaining_time": "3:47:54", "throughput": 686.74, "total_tokens": 1812064} {"current_steps": 6475, "total_steps": 40000, "loss": 0.0, "lr": 4.683729922631866e-05, "epoch": 71.94444444444444, "percentage": 16.19, "elapsed_time": "0:44:00", "remaining_time": "3:47:52", "throughput": 686.76, "total_tokens": 1813472} {"current_steps": 6480, "total_steps": 40000, "loss": 0.0, "lr": 4.683251801629765e-05, "epoch": 72.0, "percentage": 16.2, "elapsed_time": "0:44:02", "remaining_time": "3:47:50", "throughput": 686.73, "total_tokens": 1814864} {"current_steps": 6485, "total_steps": 40000, "loss": 0.0, "lr": 4.6827733439428e-05, "epoch": 72.05555555555556, "percentage": 16.21, "elapsed_time": "0:44:04", "remaining_time": "3:47:49", "throughput": 686.7, "total_tokens": 1816304} {"current_steps": 6490, "total_steps": 40000, "loss": 0.0, "lr": 4.682294549644754e-05, "epoch": 72.11111111111111, "percentage": 16.23, "elapsed_time": "0:44:06", "remaining_time": "3:47:46", "throughput": 686.72, "total_tokens": 1817680} {"current_steps": 6495, "total_steps": 40000, "loss": 0.0, "lr": 4.681815418809464e-05, "epoch": 72.16666666666667, "percentage": 16.24, "elapsed_time": "0:44:08", "remaining_time": "3:47:44", "throughput": 686.76, "total_tokens": 1819104} {"current_steps": 6500, "total_steps": 40000, "loss": 0.0, "lr": 4.681335951510819e-05, "epoch": 72.22222222222223, "percentage": 16.25, "elapsed_time": "0:44:10", "remaining_time": "3:47:41", "throughput": 686.78, "total_tokens": 1820512} {"current_steps": 6505, "total_steps": 40000, "loss": 0.0, "lr": 4.6808561478227576e-05, "epoch": 72.27777777777777, "percentage": 16.26, "elapsed_time": "0:44:12", "remaining_time": "3:47:39", "throughput": 686.81, "total_tokens": 1821920} {"current_steps": 6510, "total_steps": 40000, "loss": 0.0, "lr": 4.680376007819271e-05, "epoch": 72.33333333333333, "percentage": 16.28, "elapsed_time": "0:44:14", "remaining_time": "3:47:36", "throughput": 686.84, "total_tokens": 1823328} {"current_steps": 6515, "total_steps": 40000, "loss": 0.0, "lr": 4.679895531574405e-05, "epoch": 72.38888888888889, "percentage": 16.29, "elapsed_time": "0:44:16", "remaining_time": "3:47:34", "throughput": 686.84, "total_tokens": 1824672} {"current_steps": 6520, "total_steps": 40000, "loss": 0.0, "lr": 4.679414719162253e-05, "epoch": 72.44444444444444, "percentage": 16.3, "elapsed_time": "0:44:18", "remaining_time": "3:47:31", "throughput": 686.85, "total_tokens": 1826048} {"current_steps": 6525, "total_steps": 40000, "loss": 0.0, "lr": 4.6789335706569635e-05, "epoch": 72.5, "percentage": 16.31, "elapsed_time": "0:44:20", "remaining_time": "3:47:29", "throughput": 686.87, "total_tokens": 1827424} {"current_steps": 6530, "total_steps": 40000, "loss": 0.0, "lr": 4.678452086132734e-05, "epoch": 72.55555555555556, "percentage": 16.32, "elapsed_time": "0:44:22", "remaining_time": "3:47:26", "throughput": 686.89, "total_tokens": 1828832} {"current_steps": 6535, "total_steps": 40000, "loss": 0.0, "lr": 4.677970265663818e-05, "epoch": 72.61111111111111, "percentage": 16.34, "elapsed_time": "0:44:24", "remaining_time": "3:47:24", "throughput": 686.92, "total_tokens": 1830240} {"current_steps": 6540, "total_steps": 40000, "loss": 0.0, "lr": 4.677488109324517e-05, "epoch": 72.66666666666667, "percentage": 16.35, "elapsed_time": "0:44:26", "remaining_time": "3:47:21", "throughput": 686.94, "total_tokens": 1831616} {"current_steps": 6545, "total_steps": 40000, "loss": 0.0, "lr": 4.6770056171891846e-05, "epoch": 72.72222222222223, "percentage": 16.36, "elapsed_time": "0:44:28", "remaining_time": "3:47:19", "throughput": 686.96, "total_tokens": 1833024} {"current_steps": 6550, "total_steps": 40000, "loss": 0.0, "lr": 4.6765227893322286e-05, "epoch": 72.77777777777777, "percentage": 16.38, "elapsed_time": "0:44:30", "remaining_time": "3:47:16", "throughput": 686.99, "total_tokens": 1834416} {"current_steps": 6555, "total_steps": 40000, "loss": 0.0, "lr": 4.676039625828107e-05, "epoch": 72.83333333333333, "percentage": 16.39, "elapsed_time": "0:44:32", "remaining_time": "3:47:14", "throughput": 687.02, "total_tokens": 1835856} {"current_steps": 6560, "total_steps": 40000, "loss": 0.0, "lr": 4.675556126751328e-05, "epoch": 72.88888888888889, "percentage": 16.4, "elapsed_time": "0:44:34", "remaining_time": "3:47:11", "throughput": 687.05, "total_tokens": 1837264} {"current_steps": 6565, "total_steps": 40000, "loss": 0.0, "lr": 4.6750722921764556e-05, "epoch": 72.94444444444444, "percentage": 16.41, "elapsed_time": "0:44:36", "remaining_time": "3:47:08", "throughput": 687.08, "total_tokens": 1838672} {"current_steps": 6570, "total_steps": 40000, "loss": 0.0, "lr": 4.674588122178102e-05, "epoch": 73.0, "percentage": 16.43, "elapsed_time": "0:44:38", "remaining_time": "3:47:07", "throughput": 687.07, "total_tokens": 1840096} {"current_steps": 6575, "total_steps": 40000, "loss": 0.0, "lr": 4.674103616830931e-05, "epoch": 73.05555555555556, "percentage": 16.44, "elapsed_time": "0:44:40", "remaining_time": "3:47:06", "throughput": 687.01, "total_tokens": 1841488} {"current_steps": 6580, "total_steps": 40000, "loss": 0.0, "lr": 4.673618776209663e-05, "epoch": 73.11111111111111, "percentage": 16.45, "elapsed_time": "0:44:42", "remaining_time": "3:47:03", "throughput": 687.03, "total_tokens": 1842880} {"current_steps": 6585, "total_steps": 40000, "loss": 0.0, "lr": 4.673133600389063e-05, "epoch": 73.16666666666667, "percentage": 16.46, "elapsed_time": "0:44:44", "remaining_time": "3:47:01", "throughput": 687.06, "total_tokens": 1844288} {"current_steps": 6590, "total_steps": 40000, "loss": 0.0, "lr": 4.672648089443953e-05, "epoch": 73.22222222222223, "percentage": 16.48, "elapsed_time": "0:44:46", "remaining_time": "3:46:58", "throughput": 687.08, "total_tokens": 1845696} {"current_steps": 6595, "total_steps": 40000, "loss": 0.0, "lr": 4.672162243449204e-05, "epoch": 73.27777777777777, "percentage": 16.49, "elapsed_time": "0:44:48", "remaining_time": "3:46:56", "throughput": 687.09, "total_tokens": 1847040} {"current_steps": 6600, "total_steps": 40000, "loss": 0.0, "lr": 4.67167606247974e-05, "epoch": 73.33333333333333, "percentage": 16.5, "elapsed_time": "0:44:50", "remaining_time": "3:46:53", "throughput": 687.1, "total_tokens": 1848416} {"current_steps": 6600, "total_steps": 40000, "eval_loss": 0.2606924772262573, "epoch": 73.33333333333333, "percentage": 16.5, "elapsed_time": "0:44:51", "remaining_time": "3:47:00", "throughput": 686.76, "total_tokens": 1848416} {"current_steps": 6605, "total_steps": 40000, "loss": 0.0, "lr": 4.671189546610536e-05, "epoch": 73.38888888888889, "percentage": 16.51, "elapsed_time": "0:44:54", "remaining_time": "3:47:04", "throughput": 686.45, "total_tokens": 1849792} {"current_steps": 6610, "total_steps": 40000, "loss": 0.0, "lr": 4.67070269591662e-05, "epoch": 73.44444444444444, "percentage": 16.53, "elapsed_time": "0:44:56", "remaining_time": "3:47:02", "throughput": 686.45, "total_tokens": 1851168} {"current_steps": 6615, "total_steps": 40000, "loss": 0.0, "lr": 4.670215510473068e-05, "epoch": 73.5, "percentage": 16.54, "elapsed_time": "0:44:58", "remaining_time": "3:46:59", "throughput": 686.48, "total_tokens": 1852592} {"current_steps": 6620, "total_steps": 40000, "loss": 0.0, "lr": 4.669727990355013e-05, "epoch": 73.55555555555556, "percentage": 16.55, "elapsed_time": "0:45:00", "remaining_time": "3:46:57", "throughput": 686.5, "total_tokens": 1854000} {"current_steps": 6625, "total_steps": 40000, "loss": 0.0, "lr": 4.669240135637635e-05, "epoch": 73.61111111111111, "percentage": 16.56, "elapsed_time": "0:45:02", "remaining_time": "3:46:54", "throughput": 686.52, "total_tokens": 1855376} {"current_steps": 6630, "total_steps": 40000, "loss": 0.0, "lr": 4.6687519463961675e-05, "epoch": 73.66666666666667, "percentage": 16.57, "elapsed_time": "0:45:04", "remaining_time": "3:46:52", "throughput": 686.53, "total_tokens": 1856752} {"current_steps": 6635, "total_steps": 40000, "loss": 0.0, "lr": 4.668263422705896e-05, "epoch": 73.72222222222223, "percentage": 16.59, "elapsed_time": "0:45:06", "remaining_time": "3:46:49", "throughput": 686.56, "total_tokens": 1858176} {"current_steps": 6640, "total_steps": 40000, "loss": 0.0, "lr": 4.667774564642156e-05, "epoch": 73.77777777777777, "percentage": 16.6, "elapsed_time": "0:45:08", "remaining_time": "3:46:47", "throughput": 686.59, "total_tokens": 1859584} {"current_steps": 6645, "total_steps": 40000, "loss": 0.0, "lr": 4.6672853722803365e-05, "epoch": 73.83333333333333, "percentage": 16.61, "elapsed_time": "0:45:10", "remaining_time": "3:46:44", "throughput": 686.62, "total_tokens": 1860992} {"current_steps": 6650, "total_steps": 40000, "loss": 0.0, "lr": 4.666795845695877e-05, "epoch": 73.88888888888889, "percentage": 16.62, "elapsed_time": "0:45:12", "remaining_time": "3:46:42", "throughput": 686.65, "total_tokens": 1862416} {"current_steps": 6655, "total_steps": 40000, "loss": 0.0, "lr": 4.666305984964269e-05, "epoch": 73.94444444444444, "percentage": 16.64, "elapsed_time": "0:45:14", "remaining_time": "3:46:39", "throughput": 686.69, "total_tokens": 1863856} {"current_steps": 6660, "total_steps": 40000, "loss": 0.0, "lr": 4.6658157901610535e-05, "epoch": 74.0, "percentage": 16.65, "elapsed_time": "0:45:16", "remaining_time": "3:46:38", "throughput": 686.66, "total_tokens": 1865232} {"current_steps": 6665, "total_steps": 40000, "loss": 0.0, "lr": 4.665325261361826e-05, "epoch": 74.05555555555556, "percentage": 16.66, "elapsed_time": "0:45:18", "remaining_time": "3:46:37", "throughput": 686.62, "total_tokens": 1866672} {"current_steps": 6670, "total_steps": 40000, "loss": 0.0, "lr": 4.664834398642232e-05, "epoch": 74.11111111111111, "percentage": 16.68, "elapsed_time": "0:45:20", "remaining_time": "3:46:34", "throughput": 686.64, "total_tokens": 1868064} {"current_steps": 6675, "total_steps": 40000, "loss": 0.0, "lr": 4.6643432020779686e-05, "epoch": 74.16666666666667, "percentage": 16.69, "elapsed_time": "0:45:22", "remaining_time": "3:46:32", "throughput": 686.66, "total_tokens": 1869456} {"current_steps": 6680, "total_steps": 40000, "loss": 0.0, "lr": 4.663851671744786e-05, "epoch": 74.22222222222223, "percentage": 16.7, "elapsed_time": "0:45:24", "remaining_time": "3:46:29", "throughput": 686.68, "total_tokens": 1870848} {"current_steps": 6685, "total_steps": 40000, "loss": 0.0, "lr": 4.6633598077184815e-05, "epoch": 74.27777777777777, "percentage": 16.71, "elapsed_time": "0:45:26", "remaining_time": "3:46:27", "throughput": 686.71, "total_tokens": 1872272} {"current_steps": 6690, "total_steps": 40000, "loss": 0.0, "lr": 4.662867610074908e-05, "epoch": 74.33333333333333, "percentage": 16.73, "elapsed_time": "0:45:28", "remaining_time": "3:46:24", "throughput": 686.72, "total_tokens": 1873648} {"current_steps": 6695, "total_steps": 40000, "loss": 0.0, "lr": 4.6623750788899696e-05, "epoch": 74.38888888888889, "percentage": 16.74, "elapsed_time": "0:45:30", "remaining_time": "3:46:22", "throughput": 686.74, "total_tokens": 1875040} {"current_steps": 6700, "total_steps": 40000, "loss": 0.0, "lr": 4.6618822142396195e-05, "epoch": 74.44444444444444, "percentage": 16.75, "elapsed_time": "0:45:32", "remaining_time": "3:46:19", "throughput": 686.73, "total_tokens": 1876368} {"current_steps": 6705, "total_steps": 40000, "loss": 0.0, "lr": 4.661389016199864e-05, "epoch": 74.5, "percentage": 16.76, "elapsed_time": "0:45:34", "remaining_time": "3:46:17", "throughput": 686.77, "total_tokens": 1877792} {"current_steps": 6710, "total_steps": 40000, "loss": 0.0, "lr": 4.660895484846761e-05, "epoch": 74.55555555555556, "percentage": 16.78, "elapsed_time": "0:45:36", "remaining_time": "3:46:14", "throughput": 686.79, "total_tokens": 1879200} {"current_steps": 6715, "total_steps": 40000, "loss": 0.0, "lr": 4.660401620256418e-05, "epoch": 74.61111111111111, "percentage": 16.79, "elapsed_time": "0:45:38", "remaining_time": "3:46:12", "throughput": 686.83, "total_tokens": 1880640} {"current_steps": 6720, "total_steps": 40000, "loss": 0.0, "lr": 4.659907422504997e-05, "epoch": 74.66666666666667, "percentage": 16.8, "elapsed_time": "0:45:40", "remaining_time": "3:46:09", "throughput": 686.86, "total_tokens": 1882032} {"current_steps": 6725, "total_steps": 40000, "loss": 0.0, "lr": 4.6594128916687074e-05, "epoch": 74.72222222222223, "percentage": 16.81, "elapsed_time": "0:45:42", "remaining_time": "3:46:07", "throughput": 686.89, "total_tokens": 1883472} {"current_steps": 6730, "total_steps": 40000, "loss": 0.0, "lr": 4.658918027823813e-05, "epoch": 74.77777777777777, "percentage": 16.83, "elapsed_time": "0:45:43", "remaining_time": "3:46:04", "throughput": 686.91, "total_tokens": 1884864} {"current_steps": 6735, "total_steps": 40000, "loss": 0.0, "lr": 4.658422831046628e-05, "epoch": 74.83333333333333, "percentage": 16.84, "elapsed_time": "0:45:45", "remaining_time": "3:46:02", "throughput": 686.93, "total_tokens": 1886256} {"current_steps": 6740, "total_steps": 40000, "loss": 0.0, "lr": 4.657927301413518e-05, "epoch": 74.88888888888889, "percentage": 16.85, "elapsed_time": "0:45:47", "remaining_time": "3:45:59", "throughput": 686.95, "total_tokens": 1887648} {"current_steps": 6745, "total_steps": 40000, "loss": 0.0, "lr": 4.657431439000901e-05, "epoch": 74.94444444444444, "percentage": 16.86, "elapsed_time": "0:45:49", "remaining_time": "3:45:57", "throughput": 686.97, "total_tokens": 1889040} {"current_steps": 6750, "total_steps": 40000, "loss": 0.0, "lr": 4.656935243885243e-05, "epoch": 75.0, "percentage": 16.88, "elapsed_time": "0:45:51", "remaining_time": "3:45:55", "throughput": 686.95, "total_tokens": 1890432} {"current_steps": 6755, "total_steps": 40000, "loss": 0.0, "lr": 4.656438716143066e-05, "epoch": 75.05555555555556, "percentage": 16.89, "elapsed_time": "0:45:54", "remaining_time": "3:45:54", "throughput": 686.9, "total_tokens": 1891824} {"current_steps": 6760, "total_steps": 40000, "loss": 0.0, "lr": 4.6559418558509384e-05, "epoch": 75.11111111111111, "percentage": 16.9, "elapsed_time": "0:45:56", "remaining_time": "3:45:52", "throughput": 686.92, "total_tokens": 1893232} {"current_steps": 6765, "total_steps": 40000, "loss": 0.0, "lr": 4.6554446630854833e-05, "epoch": 75.16666666666667, "percentage": 16.91, "elapsed_time": "0:45:58", "remaining_time": "3:45:49", "throughput": 686.95, "total_tokens": 1894640} {"current_steps": 6770, "total_steps": 40000, "loss": 0.0, "lr": 4.654947137923374e-05, "epoch": 75.22222222222223, "percentage": 16.93, "elapsed_time": "0:46:00", "remaining_time": "3:45:47", "throughput": 686.98, "total_tokens": 1896080} {"current_steps": 6775, "total_steps": 40000, "loss": 0.0, "lr": 4.654449280441335e-05, "epoch": 75.27777777777777, "percentage": 16.94, "elapsed_time": "0:46:01", "remaining_time": "3:45:44", "throughput": 687.0, "total_tokens": 1897472} {"current_steps": 6780, "total_steps": 40000, "loss": 0.0, "lr": 4.653951090716143e-05, "epoch": 75.33333333333333, "percentage": 16.95, "elapsed_time": "0:46:03", "remaining_time": "3:45:42", "throughput": 687.02, "total_tokens": 1898864} {"current_steps": 6785, "total_steps": 40000, "loss": 0.0, "lr": 4.653452568824625e-05, "epoch": 75.38888888888889, "percentage": 16.96, "elapsed_time": "0:46:05", "remaining_time": "3:45:39", "throughput": 687.05, "total_tokens": 1900272} {"current_steps": 6790, "total_steps": 40000, "loss": 0.0, "lr": 4.6529537148436585e-05, "epoch": 75.44444444444444, "percentage": 16.98, "elapsed_time": "0:46:07", "remaining_time": "3:45:37", "throughput": 687.06, "total_tokens": 1901648} {"current_steps": 6795, "total_steps": 40000, "loss": 0.0, "lr": 4.6524545288501734e-05, "epoch": 75.5, "percentage": 16.99, "elapsed_time": "0:46:09", "remaining_time": "3:45:34", "throughput": 687.1, "total_tokens": 1903088} {"current_steps": 6800, "total_steps": 40000, "loss": 0.0, "lr": 4.6519550109211506e-05, "epoch": 75.55555555555556, "percentage": 17.0, "elapsed_time": "0:46:11", "remaining_time": "3:45:32", "throughput": 687.12, "total_tokens": 1904480} {"current_steps": 6800, "total_steps": 40000, "eval_loss": 0.27321183681488037, "epoch": 75.55555555555556, "percentage": 17.0, "elapsed_time": "0:46:13", "remaining_time": "3:45:38", "throughput": 686.79, "total_tokens": 1904480} {"current_steps": 6805, "total_steps": 40000, "loss": 0.0, "lr": 4.651455161133622e-05, "epoch": 75.61111111111111, "percentage": 17.01, "elapsed_time": "0:46:16", "remaining_time": "3:45:44", "throughput": 686.4, "total_tokens": 1905856} {"current_steps": 6810, "total_steps": 40000, "loss": 0.0, "lr": 4.6509549795646704e-05, "epoch": 75.66666666666667, "percentage": 17.03, "elapsed_time": "0:46:18", "remaining_time": "3:45:42", "throughput": 686.4, "total_tokens": 1907232} {"current_steps": 6815, "total_steps": 40000, "loss": 0.0, "lr": 4.6504544662914306e-05, "epoch": 75.72222222222223, "percentage": 17.04, "elapsed_time": "0:46:20", "remaining_time": "3:45:39", "throughput": 686.43, "total_tokens": 1908672} {"current_steps": 6820, "total_steps": 40000, "loss": 0.0, "lr": 4.6499536213910876e-05, "epoch": 75.77777777777777, "percentage": 17.05, "elapsed_time": "0:46:22", "remaining_time": "3:45:37", "throughput": 686.44, "total_tokens": 1910064} {"current_steps": 6825, "total_steps": 40000, "loss": 0.0, "lr": 4.6494524449408786e-05, "epoch": 75.83333333333333, "percentage": 17.06, "elapsed_time": "0:46:24", "remaining_time": "3:45:34", "throughput": 686.47, "total_tokens": 1911488} {"current_steps": 6830, "total_steps": 40000, "loss": 0.0, "lr": 4.6489509370180903e-05, "epoch": 75.88888888888889, "percentage": 17.08, "elapsed_time": "0:46:26", "remaining_time": "3:45:32", "throughput": 686.49, "total_tokens": 1912864} {"current_steps": 6835, "total_steps": 40000, "loss": 0.0, "lr": 4.648449097700063e-05, "epoch": 75.94444444444444, "percentage": 17.09, "elapsed_time": "0:46:28", "remaining_time": "3:45:29", "throughput": 686.51, "total_tokens": 1914272} {"current_steps": 6840, "total_steps": 40000, "loss": 0.0, "lr": 4.647946927064185e-05, "epoch": 76.0, "percentage": 17.1, "elapsed_time": "0:46:30", "remaining_time": "3:45:28", "throughput": 686.46, "total_tokens": 1915600} {"current_steps": 6845, "total_steps": 40000, "loss": 0.0, "lr": 4.647444425187898e-05, "epoch": 76.05555555555556, "percentage": 17.11, "elapsed_time": "0:46:32", "remaining_time": "3:45:27", "throughput": 686.42, "total_tokens": 1916992} {"current_steps": 6850, "total_steps": 40000, "loss": 0.0, "lr": 4.646941592148695e-05, "epoch": 76.11111111111111, "percentage": 17.12, "elapsed_time": "0:46:34", "remaining_time": "3:45:24", "throughput": 686.43, "total_tokens": 1918368} {"current_steps": 6855, "total_steps": 40000, "loss": 0.0, "lr": 4.646438428024117e-05, "epoch": 76.16666666666667, "percentage": 17.14, "elapsed_time": "0:46:36", "remaining_time": "3:45:22", "throughput": 686.43, "total_tokens": 1919696} {"current_steps": 6860, "total_steps": 40000, "loss": 0.0, "lr": 4.64593493289176e-05, "epoch": 76.22222222222223, "percentage": 17.15, "elapsed_time": "0:46:38", "remaining_time": "3:45:19", "throughput": 686.46, "total_tokens": 1921104} {"current_steps": 6865, "total_steps": 40000, "loss": 0.0, "lr": 4.64543110682927e-05, "epoch": 76.27777777777777, "percentage": 17.16, "elapsed_time": "0:46:40", "remaining_time": "3:45:17", "throughput": 686.48, "total_tokens": 1922496} {"current_steps": 6870, "total_steps": 40000, "loss": 0.0, "lr": 4.644926949914341e-05, "epoch": 76.33333333333333, "percentage": 17.18, "elapsed_time": "0:46:42", "remaining_time": "3:45:14", "throughput": 686.53, "total_tokens": 1923968} {"current_steps": 6875, "total_steps": 40000, "loss": 0.0, "lr": 4.644422462224722e-05, "epoch": 76.38888888888889, "percentage": 17.19, "elapsed_time": "0:46:44", "remaining_time": "3:45:12", "throughput": 686.56, "total_tokens": 1925376} {"current_steps": 6880, "total_steps": 40000, "loss": 0.0, "lr": 4.643917643838211e-05, "epoch": 76.44444444444444, "percentage": 17.2, "elapsed_time": "0:46:46", "remaining_time": "3:45:09", "throughput": 686.58, "total_tokens": 1926800} {"current_steps": 6885, "total_steps": 40000, "loss": 0.0, "lr": 4.6434124948326564e-05, "epoch": 76.5, "percentage": 17.21, "elapsed_time": "0:46:48", "remaining_time": "3:45:07", "throughput": 686.59, "total_tokens": 1928160} {"current_steps": 6890, "total_steps": 40000, "loss": 0.0, "lr": 4.6429070152859594e-05, "epoch": 76.55555555555556, "percentage": 17.22, "elapsed_time": "0:46:50", "remaining_time": "3:45:04", "throughput": 686.63, "total_tokens": 1929600} {"current_steps": 6895, "total_steps": 40000, "loss": 0.0, "lr": 4.6424012052760714e-05, "epoch": 76.61111111111111, "percentage": 17.24, "elapsed_time": "0:46:52", "remaining_time": "3:45:02", "throughput": 686.63, "total_tokens": 1930944} {"current_steps": 6900, "total_steps": 40000, "loss": 0.0, "lr": 4.6418950648809945e-05, "epoch": 76.66666666666667, "percentage": 17.25, "elapsed_time": "0:46:54", "remaining_time": "3:44:59", "throughput": 686.66, "total_tokens": 1932368} {"current_steps": 6905, "total_steps": 40000, "loss": 0.0, "lr": 4.641388594178782e-05, "epoch": 76.72222222222223, "percentage": 17.26, "elapsed_time": "0:46:56", "remaining_time": "3:44:57", "throughput": 686.68, "total_tokens": 1933744} {"current_steps": 6910, "total_steps": 40000, "loss": 0.0, "lr": 4.640881793247538e-05, "epoch": 76.77777777777777, "percentage": 17.27, "elapsed_time": "0:46:58", "remaining_time": "3:44:54", "throughput": 686.72, "total_tokens": 1935184} {"current_steps": 6915, "total_steps": 40000, "loss": 0.0, "lr": 4.6403746621654173e-05, "epoch": 76.83333333333333, "percentage": 17.29, "elapsed_time": "0:46:59", "remaining_time": "3:44:52", "throughput": 686.73, "total_tokens": 1936544} {"current_steps": 6920, "total_steps": 40000, "loss": 0.0, "lr": 4.639867201010626e-05, "epoch": 76.88888888888889, "percentage": 17.3, "elapsed_time": "0:47:01", "remaining_time": "3:44:49", "throughput": 686.75, "total_tokens": 1937936} {"current_steps": 6925, "total_steps": 40000, "loss": 0.0, "lr": 4.6393594098614204e-05, "epoch": 76.94444444444444, "percentage": 17.31, "elapsed_time": "0:47:03", "remaining_time": "3:44:47", "throughput": 686.78, "total_tokens": 1939360} {"current_steps": 6930, "total_steps": 40000, "loss": 0.0, "lr": 4.63885128879611e-05, "epoch": 77.0, "percentage": 17.32, "elapsed_time": "0:47:05", "remaining_time": "3:44:45", "throughput": 686.78, "total_tokens": 1940800} {"current_steps": 6935, "total_steps": 40000, "loss": 0.0, "lr": 4.638342837893052e-05, "epoch": 77.05555555555556, "percentage": 17.34, "elapsed_time": "0:47:08", "remaining_time": "3:44:46", "throughput": 686.66, "total_tokens": 1942240} {"current_steps": 6940, "total_steps": 40000, "loss": 0.0, "lr": 4.6378340572306565e-05, "epoch": 77.11111111111111, "percentage": 17.35, "elapsed_time": "0:47:10", "remaining_time": "3:44:43", "throughput": 686.69, "total_tokens": 1943664} {"current_steps": 6945, "total_steps": 40000, "loss": 0.0, "lr": 4.6373249468873833e-05, "epoch": 77.16666666666667, "percentage": 17.36, "elapsed_time": "0:47:12", "remaining_time": "3:44:41", "throughput": 686.7, "total_tokens": 1945040} {"current_steps": 6950, "total_steps": 40000, "loss": 0.0, "lr": 4.636815506941744e-05, "epoch": 77.22222222222223, "percentage": 17.38, "elapsed_time": "0:47:14", "remaining_time": "3:44:38", "throughput": 686.71, "total_tokens": 1946432} {"current_steps": 6955, "total_steps": 40000, "loss": 0.0, "lr": 4.6363057374723004e-05, "epoch": 77.27777777777777, "percentage": 17.39, "elapsed_time": "0:47:16", "remaining_time": "3:44:36", "throughput": 686.73, "total_tokens": 1947824} {"current_steps": 6960, "total_steps": 40000, "loss": 0.0, "lr": 4.635795638557666e-05, "epoch": 77.33333333333333, "percentage": 17.4, "elapsed_time": "0:47:18", "remaining_time": "3:44:33", "throughput": 686.76, "total_tokens": 1949232} {"current_steps": 6965, "total_steps": 40000, "loss": 0.0, "lr": 4.635285210276504e-05, "epoch": 77.38888888888889, "percentage": 17.41, "elapsed_time": "0:47:20", "remaining_time": "3:44:31", "throughput": 686.79, "total_tokens": 1950656} {"current_steps": 6970, "total_steps": 40000, "loss": 0.0, "lr": 4.6347744527075295e-05, "epoch": 77.44444444444444, "percentage": 17.42, "elapsed_time": "0:47:22", "remaining_time": "3:44:28", "throughput": 686.83, "total_tokens": 1952112} {"current_steps": 6975, "total_steps": 40000, "loss": 0.0, "lr": 4.634263365929506e-05, "epoch": 77.5, "percentage": 17.44, "elapsed_time": "0:47:24", "remaining_time": "3:44:26", "throughput": 686.87, "total_tokens": 1953552} {"current_steps": 6980, "total_steps": 40000, "loss": 0.0, "lr": 4.6337519500212515e-05, "epoch": 77.55555555555556, "percentage": 17.45, "elapsed_time": "0:47:26", "remaining_time": "3:44:23", "throughput": 686.88, "total_tokens": 1954912} {"current_steps": 6985, "total_steps": 40000, "loss": 0.0, "lr": 4.633240205061632e-05, "epoch": 77.61111111111111, "percentage": 17.46, "elapsed_time": "0:47:28", "remaining_time": "3:44:21", "throughput": 686.9, "total_tokens": 1956320} {"current_steps": 6990, "total_steps": 40000, "loss": 0.0, "lr": 4.632728131129565e-05, "epoch": 77.66666666666667, "percentage": 17.47, "elapsed_time": "0:47:29", "remaining_time": "3:44:18", "throughput": 686.91, "total_tokens": 1957696} {"current_steps": 6995, "total_steps": 40000, "loss": 0.0, "lr": 4.632215728304018e-05, "epoch": 77.72222222222223, "percentage": 17.49, "elapsed_time": "0:47:31", "remaining_time": "3:44:16", "throughput": 686.94, "total_tokens": 1959104} {"current_steps": 7000, "total_steps": 40000, "loss": 0.0, "lr": 4.63170299666401e-05, "epoch": 77.77777777777777, "percentage": 17.5, "elapsed_time": "0:47:33", "remaining_time": "3:44:14", "throughput": 686.96, "total_tokens": 1960496} {"current_steps": 7000, "total_steps": 40000, "eval_loss": 0.268013060092926, "epoch": 77.77777777777777, "percentage": 17.5, "elapsed_time": "0:47:35", "remaining_time": "3:44:20", "throughput": 686.64, "total_tokens": 1960496} {"current_steps": 7005, "total_steps": 40000, "loss": 0.0, "lr": 4.631189936288612e-05, "epoch": 77.83333333333333, "percentage": 17.51, "elapsed_time": "0:47:38", "remaining_time": "3:44:24", "throughput": 686.35, "total_tokens": 1961936} {"current_steps": 7010, "total_steps": 40000, "loss": 0.0, "lr": 4.630676547256944e-05, "epoch": 77.88888888888889, "percentage": 17.52, "elapsed_time": "0:47:40", "remaining_time": "3:44:21", "throughput": 686.35, "total_tokens": 1963296} {"current_steps": 7015, "total_steps": 40000, "loss": 0.0, "lr": 4.630162829648176e-05, "epoch": 77.94444444444444, "percentage": 17.54, "elapsed_time": "0:47:42", "remaining_time": "3:44:19", "throughput": 686.34, "total_tokens": 1964656} {"current_steps": 7020, "total_steps": 40000, "loss": 0.0, "lr": 4.629648783541531e-05, "epoch": 78.0, "percentage": 17.55, "elapsed_time": "0:47:44", "remaining_time": "3:44:18", "throughput": 686.34, "total_tokens": 1966096} {"current_steps": 7025, "total_steps": 40000, "loss": 0.0, "lr": 4.6291344090162804e-05, "epoch": 78.05555555555556, "percentage": 17.56, "elapsed_time": "0:47:46", "remaining_time": "3:44:16", "throughput": 686.32, "total_tokens": 1967552} {"current_steps": 7030, "total_steps": 40000, "loss": 0.0, "lr": 4.628619706151748e-05, "epoch": 78.11111111111111, "percentage": 17.57, "elapsed_time": "0:47:48", "remaining_time": "3:44:14", "throughput": 686.33, "total_tokens": 1968928} {"current_steps": 7035, "total_steps": 40000, "loss": 0.0, "lr": 4.628104675027306e-05, "epoch": 78.16666666666667, "percentage": 17.59, "elapsed_time": "0:47:50", "remaining_time": "3:44:11", "throughput": 686.35, "total_tokens": 1970336} {"current_steps": 7040, "total_steps": 40000, "loss": 0.0, "lr": 4.6275893157223805e-05, "epoch": 78.22222222222223, "percentage": 17.6, "elapsed_time": "0:47:52", "remaining_time": "3:44:09", "throughput": 686.38, "total_tokens": 1971744} {"current_steps": 7045, "total_steps": 40000, "loss": 0.0, "lr": 4.627073628316445e-05, "epoch": 78.27777777777777, "percentage": 17.61, "elapsed_time": "0:47:54", "remaining_time": "3:44:06", "throughput": 686.39, "total_tokens": 1973120} {"current_steps": 7050, "total_steps": 40000, "loss": 0.0, "lr": 4.626557612889026e-05, "epoch": 78.33333333333333, "percentage": 17.62, "elapsed_time": "0:47:56", "remaining_time": "3:44:04", "throughput": 686.42, "total_tokens": 1974512} {"current_steps": 7055, "total_steps": 40000, "loss": 0.0, "lr": 4.626041269519699e-05, "epoch": 78.38888888888889, "percentage": 17.64, "elapsed_time": "0:47:58", "remaining_time": "3:44:01", "throughput": 686.43, "total_tokens": 1975888} {"current_steps": 7060, "total_steps": 40000, "loss": 0.0, "lr": 4.6255245982880905e-05, "epoch": 78.44444444444444, "percentage": 17.65, "elapsed_time": "0:48:00", "remaining_time": "3:43:59", "throughput": 686.44, "total_tokens": 1977264} {"current_steps": 7065, "total_steps": 40000, "loss": 0.0, "lr": 4.625007599273879e-05, "epoch": 78.5, "percentage": 17.66, "elapsed_time": "0:48:02", "remaining_time": "3:43:56", "throughput": 686.45, "total_tokens": 1978640} {"current_steps": 7070, "total_steps": 40000, "loss": 0.0, "lr": 4.6244902725567895e-05, "epoch": 78.55555555555556, "percentage": 17.68, "elapsed_time": "0:48:04", "remaining_time": "3:43:54", "throughput": 686.47, "total_tokens": 1980016} {"current_steps": 7075, "total_steps": 40000, "loss": 0.0, "lr": 4.6239726182166024e-05, "epoch": 78.61111111111111, "percentage": 17.69, "elapsed_time": "0:48:06", "remaining_time": "3:43:52", "throughput": 686.48, "total_tokens": 1981392} {"current_steps": 7080, "total_steps": 40000, "loss": 0.0, "lr": 4.623454636333147e-05, "epoch": 78.66666666666667, "percentage": 17.7, "elapsed_time": "0:48:08", "remaining_time": "3:43:49", "throughput": 686.51, "total_tokens": 1982800} {"current_steps": 7085, "total_steps": 40000, "loss": 0.0, "lr": 4.622936326986301e-05, "epoch": 78.72222222222223, "percentage": 17.71, "elapsed_time": "0:48:10", "remaining_time": "3:43:46", "throughput": 686.54, "total_tokens": 1984224} {"current_steps": 7090, "total_steps": 40000, "loss": 0.0, "lr": 4.6224176902559946e-05, "epoch": 78.77777777777777, "percentage": 17.72, "elapsed_time": "0:48:12", "remaining_time": "3:43:44", "throughput": 686.57, "total_tokens": 1985632} {"current_steps": 7095, "total_steps": 40000, "loss": 0.0, "lr": 4.621898726222209e-05, "epoch": 78.83333333333333, "percentage": 17.74, "elapsed_time": "0:48:14", "remaining_time": "3:43:41", "throughput": 686.59, "total_tokens": 1987040} {"current_steps": 7100, "total_steps": 40000, "loss": 0.0, "lr": 4.6213794349649744e-05, "epoch": 78.88888888888889, "percentage": 17.75, "elapsed_time": "0:48:16", "remaining_time": "3:43:39", "throughput": 686.61, "total_tokens": 1988432} {"current_steps": 7105, "total_steps": 40000, "loss": 0.0, "lr": 4.6208598165643715e-05, "epoch": 78.94444444444444, "percentage": 17.76, "elapsed_time": "0:48:17", "remaining_time": "3:43:37", "throughput": 686.64, "total_tokens": 1989856} {"current_steps": 7110, "total_steps": 40000, "loss": 0.0, "lr": 4.620339871100533e-05, "epoch": 79.0, "percentage": 17.77, "elapsed_time": "0:48:20", "remaining_time": "3:43:35", "throughput": 686.62, "total_tokens": 1991248} {"current_steps": 7115, "total_steps": 40000, "loss": 0.0, "lr": 4.6198195986536394e-05, "epoch": 79.05555555555556, "percentage": 17.79, "elapsed_time": "0:48:22", "remaining_time": "3:43:34", "throughput": 686.59, "total_tokens": 1992656} {"current_steps": 7120, "total_steps": 40000, "loss": 0.0, "lr": 4.619298999303926e-05, "epoch": 79.11111111111111, "percentage": 17.8, "elapsed_time": "0:48:24", "remaining_time": "3:43:31", "throughput": 686.59, "total_tokens": 1994000} {"current_steps": 7125, "total_steps": 40000, "loss": 0.0, "lr": 4.618778073131673e-05, "epoch": 79.16666666666667, "percentage": 17.81, "elapsed_time": "0:48:26", "remaining_time": "3:43:29", "throughput": 686.6, "total_tokens": 1995376} {"current_steps": 7130, "total_steps": 40000, "loss": 0.0, "lr": 4.618256820217215e-05, "epoch": 79.22222222222223, "percentage": 17.82, "elapsed_time": "0:48:28", "remaining_time": "3:43:26", "throughput": 686.62, "total_tokens": 1996768} {"current_steps": 7135, "total_steps": 40000, "loss": 0.0, "lr": 4.617735240640936e-05, "epoch": 79.27777777777777, "percentage": 17.84, "elapsed_time": "0:48:30", "remaining_time": "3:43:24", "throughput": 686.63, "total_tokens": 1998144} {"current_steps": 7140, "total_steps": 40000, "loss": 0.0, "lr": 4.6172133344832705e-05, "epoch": 79.33333333333333, "percentage": 17.85, "elapsed_time": "0:48:32", "remaining_time": "3:43:21", "throughput": 686.64, "total_tokens": 1999520} {"current_steps": 7145, "total_steps": 40000, "loss": 0.0, "lr": 4.6166911018247004e-05, "epoch": 79.38888888888889, "percentage": 17.86, "elapsed_time": "0:48:33", "remaining_time": "3:43:19", "throughput": 686.65, "total_tokens": 2000880} {"current_steps": 7150, "total_steps": 40000, "loss": 0.0, "lr": 4.616168542745764e-05, "epoch": 79.44444444444444, "percentage": 17.88, "elapsed_time": "0:48:35", "remaining_time": "3:43:16", "throughput": 686.69, "total_tokens": 2002320} {"current_steps": 7155, "total_steps": 40000, "loss": 0.0, "lr": 4.6156456573270446e-05, "epoch": 79.5, "percentage": 17.89, "elapsed_time": "0:48:37", "remaining_time": "3:43:14", "throughput": 686.7, "total_tokens": 2003696} {"current_steps": 7160, "total_steps": 40000, "loss": 0.0, "lr": 4.615122445649177e-05, "epoch": 79.55555555555556, "percentage": 17.9, "elapsed_time": "0:48:39", "remaining_time": "3:43:11", "throughput": 686.73, "total_tokens": 2005104} {"current_steps": 7165, "total_steps": 40000, "loss": 0.0, "lr": 4.6145989077928486e-05, "epoch": 79.61111111111111, "percentage": 17.91, "elapsed_time": "0:48:41", "remaining_time": "3:43:09", "throughput": 686.74, "total_tokens": 2006480} {"current_steps": 7170, "total_steps": 40000, "loss": 0.0, "lr": 4.6140750438387953e-05, "epoch": 79.66666666666667, "percentage": 17.93, "elapsed_time": "0:48:43", "remaining_time": "3:43:06", "throughput": 686.77, "total_tokens": 2007888} {"current_steps": 7175, "total_steps": 40000, "loss": 0.0, "lr": 4.613550853867803e-05, "epoch": 79.72222222222223, "percentage": 17.94, "elapsed_time": "0:48:45", "remaining_time": "3:43:04", "throughput": 686.82, "total_tokens": 2009360} {"current_steps": 7180, "total_steps": 40000, "loss": 0.0, "lr": 4.613026337960708e-05, "epoch": 79.77777777777777, "percentage": 17.95, "elapsed_time": "0:48:47", "remaining_time": "3:43:01", "throughput": 686.84, "total_tokens": 2010768} {"current_steps": 7185, "total_steps": 40000, "loss": 0.0, "lr": 4.612501496198398e-05, "epoch": 79.83333333333333, "percentage": 17.96, "elapsed_time": "0:48:49", "remaining_time": "3:42:59", "throughput": 686.85, "total_tokens": 2012112} {"current_steps": 7190, "total_steps": 40000, "loss": 0.0, "lr": 4.61197632866181e-05, "epoch": 79.88888888888889, "percentage": 17.97, "elapsed_time": "0:48:51", "remaining_time": "3:42:57", "throughput": 686.87, "total_tokens": 2013520} {"current_steps": 7195, "total_steps": 40000, "loss": 0.0, "lr": 4.611450835431931e-05, "epoch": 79.94444444444444, "percentage": 17.99, "elapsed_time": "0:48:53", "remaining_time": "3:42:54", "throughput": 686.9, "total_tokens": 2014944} {"current_steps": 7200, "total_steps": 40000, "loss": 0.0, "lr": 4.6109250165898e-05, "epoch": 80.0, "percentage": 18.0, "elapsed_time": "0:48:55", "remaining_time": "3:42:52", "throughput": 686.89, "total_tokens": 2016368} {"current_steps": 7200, "total_steps": 40000, "eval_loss": 0.28183484077453613, "epoch": 80.0, "percentage": 18.0, "elapsed_time": "0:48:56", "remaining_time": "3:42:58", "throughput": 686.59, "total_tokens": 2016368} {"current_steps": 7205, "total_steps": 40000, "loss": 0.0, "lr": 4.610398872216503e-05, "epoch": 80.05555555555556, "percentage": 18.01, "elapsed_time": "0:49:00", "remaining_time": "3:43:03", "throughput": 686.24, "total_tokens": 2017760} {"current_steps": 7210, "total_steps": 40000, "loss": 0.0, "lr": 4.6098724023931796e-05, "epoch": 80.11111111111111, "percentage": 18.02, "elapsed_time": "0:49:02", "remaining_time": "3:43:01", "throughput": 686.24, "total_tokens": 2019152} {"current_steps": 7215, "total_steps": 40000, "loss": 0.0, "lr": 4.609345607201017e-05, "epoch": 80.16666666666667, "percentage": 18.04, "elapsed_time": "0:49:04", "remaining_time": "3:42:58", "throughput": 686.28, "total_tokens": 2020592} {"current_steps": 7220, "total_steps": 40000, "loss": 0.0, "lr": 4.608818486721254e-05, "epoch": 80.22222222222223, "percentage": 18.05, "elapsed_time": "0:49:06", "remaining_time": "3:42:56", "throughput": 686.3, "total_tokens": 2022000} {"current_steps": 7225, "total_steps": 40000, "loss": 0.0, "lr": 4.608291041035179e-05, "epoch": 80.27777777777777, "percentage": 18.06, "elapsed_time": "0:49:08", "remaining_time": "3:42:53", "throughput": 686.31, "total_tokens": 2023376} {"current_steps": 7230, "total_steps": 40000, "loss": 0.0, "lr": 4.607763270224132e-05, "epoch": 80.33333333333333, "percentage": 18.07, "elapsed_time": "0:49:10", "remaining_time": "3:42:51", "throughput": 686.33, "total_tokens": 2024768} {"current_steps": 7235, "total_steps": 40000, "loss": 0.0, "lr": 4.6072351743695e-05, "epoch": 80.38888888888889, "percentage": 18.09, "elapsed_time": "0:49:12", "remaining_time": "3:42:49", "throughput": 686.34, "total_tokens": 2026144} {"current_steps": 7240, "total_steps": 40000, "loss": 0.0, "lr": 4.606706753552723e-05, "epoch": 80.44444444444444, "percentage": 18.1, "elapsed_time": "0:49:14", "remaining_time": "3:42:46", "throughput": 686.36, "total_tokens": 2027536} {"current_steps": 7245, "total_steps": 40000, "loss": 0.0, "lr": 4.6061780078552906e-05, "epoch": 80.5, "percentage": 18.11, "elapsed_time": "0:49:15", "remaining_time": "3:42:44", "throughput": 686.39, "total_tokens": 2028944} {"current_steps": 7250, "total_steps": 40000, "loss": 0.0, "lr": 4.605648937358742e-05, "epoch": 80.55555555555556, "percentage": 18.12, "elapsed_time": "0:49:17", "remaining_time": "3:42:41", "throughput": 686.4, "total_tokens": 2030336} {"current_steps": 7255, "total_steps": 40000, "loss": 0.0, "lr": 4.605119542144665e-05, "epoch": 80.61111111111111, "percentage": 18.14, "elapsed_time": "0:49:19", "remaining_time": "3:42:39", "throughput": 686.42, "total_tokens": 2031728} {"current_steps": 7260, "total_steps": 40000, "loss": 0.0, "lr": 4.604589822294701e-05, "epoch": 80.66666666666667, "percentage": 18.15, "elapsed_time": "0:49:21", "remaining_time": "3:42:36", "throughput": 686.46, "total_tokens": 2033168} {"current_steps": 7265, "total_steps": 40000, "loss": 0.0, "lr": 4.604059777890537e-05, "epoch": 80.72222222222223, "percentage": 18.16, "elapsed_time": "0:49:23", "remaining_time": "3:42:34", "throughput": 686.47, "total_tokens": 2034544} {"current_steps": 7270, "total_steps": 40000, "loss": 0.0, "lr": 4.6035294090139145e-05, "epoch": 80.77777777777777, "percentage": 18.18, "elapsed_time": "0:49:25", "remaining_time": "3:42:31", "throughput": 686.49, "total_tokens": 2035936} {"current_steps": 7275, "total_steps": 40000, "loss": 0.0, "lr": 4.6029987157466226e-05, "epoch": 80.83333333333333, "percentage": 18.19, "elapsed_time": "0:49:27", "remaining_time": "3:42:29", "throughput": 686.51, "total_tokens": 2037344} {"current_steps": 7280, "total_steps": 40000, "loss": 0.0, "lr": 4.602467698170502e-05, "epoch": 80.88888888888889, "percentage": 18.2, "elapsed_time": "0:49:29", "remaining_time": "3:42:27", "throughput": 686.52, "total_tokens": 2038720} {"current_steps": 7285, "total_steps": 40000, "loss": 0.0, "lr": 4.601936356367439e-05, "epoch": 80.94444444444444, "percentage": 18.21, "elapsed_time": "0:49:31", "remaining_time": "3:42:24", "throughput": 686.54, "total_tokens": 2040128} {"current_steps": 7290, "total_steps": 40000, "loss": 0.0, "lr": 4.601404690419377e-05, "epoch": 81.0, "percentage": 18.22, "elapsed_time": "0:49:33", "remaining_time": "3:42:22", "throughput": 686.53, "total_tokens": 2041536} {"current_steps": 7295, "total_steps": 40000, "loss": 0.0, "lr": 4.600872700408303e-05, "epoch": 81.05555555555556, "percentage": 18.24, "elapsed_time": "0:49:35", "remaining_time": "3:42:21", "throughput": 686.48, "total_tokens": 2042912} {"current_steps": 7300, "total_steps": 40000, "loss": 0.0, "lr": 4.600340386416258e-05, "epoch": 81.11111111111111, "percentage": 18.25, "elapsed_time": "0:49:37", "remaining_time": "3:42:19", "throughput": 686.51, "total_tokens": 2044336} {"current_steps": 7305, "total_steps": 40000, "loss": 0.0, "lr": 4.5998077485253296e-05, "epoch": 81.16666666666667, "percentage": 18.26, "elapsed_time": "0:49:39", "remaining_time": "3:42:16", "throughput": 686.53, "total_tokens": 2045728} {"current_steps": 7310, "total_steps": 40000, "loss": 0.0, "lr": 4.59927478681766e-05, "epoch": 81.22222222222223, "percentage": 18.27, "elapsed_time": "0:49:41", "remaining_time": "3:42:14", "throughput": 686.56, "total_tokens": 2047152} {"current_steps": 7315, "total_steps": 40000, "loss": 0.0, "lr": 4.5987415013754366e-05, "epoch": 81.27777777777777, "percentage": 18.29, "elapsed_time": "0:49:43", "remaining_time": "3:42:11", "throughput": 686.57, "total_tokens": 2048544} {"current_steps": 7320, "total_steps": 40000, "loss": 0.0, "lr": 4.598207892280899e-05, "epoch": 81.33333333333333, "percentage": 18.3, "elapsed_time": "0:49:45", "remaining_time": "3:42:09", "throughput": 686.6, "total_tokens": 2049968} {"current_steps": 7325, "total_steps": 40000, "loss": 0.0, "lr": 4.597673959616337e-05, "epoch": 81.38888888888889, "percentage": 18.31, "elapsed_time": "0:49:47", "remaining_time": "3:42:07", "throughput": 686.6, "total_tokens": 2051312} {"current_steps": 7330, "total_steps": 40000, "loss": 0.0, "lr": 4.597139703464089e-05, "epoch": 81.44444444444444, "percentage": 18.32, "elapsed_time": "0:49:49", "remaining_time": "3:42:04", "throughput": 686.63, "total_tokens": 2052736} {"current_steps": 7335, "total_steps": 40000, "loss": 0.0, "lr": 4.596605123906545e-05, "epoch": 81.5, "percentage": 18.34, "elapsed_time": "0:49:51", "remaining_time": "3:42:02", "throughput": 686.65, "total_tokens": 2054128} {"current_steps": 7340, "total_steps": 40000, "loss": 0.0, "lr": 4.596070221026143e-05, "epoch": 81.55555555555556, "percentage": 18.35, "elapsed_time": "0:49:53", "remaining_time": "3:41:59", "throughput": 686.67, "total_tokens": 2055520} {"current_steps": 7345, "total_steps": 40000, "loss": 0.0, "lr": 4.595534994905372e-05, "epoch": 81.61111111111111, "percentage": 18.36, "elapsed_time": "0:49:55", "remaining_time": "3:41:57", "throughput": 686.69, "total_tokens": 2056928} {"current_steps": 7350, "total_steps": 40000, "loss": 0.0, "lr": 4.594999445626771e-05, "epoch": 81.66666666666667, "percentage": 18.38, "elapsed_time": "0:49:57", "remaining_time": "3:41:54", "throughput": 686.72, "total_tokens": 2058368} {"current_steps": 7355, "total_steps": 40000, "loss": 0.0, "lr": 4.5944635732729276e-05, "epoch": 81.72222222222223, "percentage": 18.39, "elapsed_time": "0:49:59", "remaining_time": "3:41:52", "throughput": 686.74, "total_tokens": 2059760} {"current_steps": 7360, "total_steps": 40000, "loss": 0.0, "lr": 4.5939273779264804e-05, "epoch": 81.77777777777777, "percentage": 18.4, "elapsed_time": "0:50:01", "remaining_time": "3:41:50", "throughput": 686.76, "total_tokens": 2061168} {"current_steps": 7365, "total_steps": 40000, "loss": 0.0, "lr": 4.593390859670118e-05, "epoch": 81.83333333333333, "percentage": 18.41, "elapsed_time": "0:50:03", "remaining_time": "3:41:47", "throughput": 686.77, "total_tokens": 2062528} {"current_steps": 7370, "total_steps": 40000, "loss": 0.0, "lr": 4.5928540185865776e-05, "epoch": 81.88888888888889, "percentage": 18.43, "elapsed_time": "0:50:05", "remaining_time": "3:41:45", "throughput": 686.8, "total_tokens": 2063952} {"current_steps": 7375, "total_steps": 40000, "loss": 0.0, "lr": 4.592316854758648e-05, "epoch": 81.94444444444444, "percentage": 18.44, "elapsed_time": "0:50:07", "remaining_time": "3:41:42", "throughput": 686.82, "total_tokens": 2065376} {"current_steps": 7380, "total_steps": 40000, "loss": 0.0, "lr": 4.5917793682691646e-05, "epoch": 82.0, "percentage": 18.45, "elapsed_time": "0:50:09", "remaining_time": "3:41:41", "throughput": 686.81, "total_tokens": 2066784} {"current_steps": 7385, "total_steps": 40000, "loss": 0.0, "lr": 4.5912415592010164e-05, "epoch": 82.05555555555556, "percentage": 18.46, "elapsed_time": "0:50:11", "remaining_time": "3:41:39", "throughput": 686.79, "total_tokens": 2068224} {"current_steps": 7390, "total_steps": 40000, "loss": 0.0, "lr": 4.5907034276371386e-05, "epoch": 82.11111111111111, "percentage": 18.48, "elapsed_time": "0:50:13", "remaining_time": "3:41:37", "throughput": 686.8, "total_tokens": 2069600} {"current_steps": 7395, "total_steps": 40000, "loss": 0.0, "lr": 4.5901649736605196e-05, "epoch": 82.16666666666667, "percentage": 18.49, "elapsed_time": "0:50:15", "remaining_time": "3:41:34", "throughput": 686.82, "total_tokens": 2070992} {"current_steps": 7400, "total_steps": 40000, "loss": 0.0, "lr": 4.589626197354195e-05, "epoch": 82.22222222222223, "percentage": 18.5, "elapsed_time": "0:50:17", "remaining_time": "3:41:32", "throughput": 686.84, "total_tokens": 2072400} {"current_steps": 7400, "total_steps": 40000, "eval_loss": 0.25661951303482056, "epoch": 82.22222222222223, "percentage": 18.5, "elapsed_time": "0:50:18", "remaining_time": "3:41:38", "throughput": 686.54, "total_tokens": 2072400} {"current_steps": 7405, "total_steps": 40000, "loss": 0.0, "lr": 4.5890870988012504e-05, "epoch": 82.27777777777777, "percentage": 18.51, "elapsed_time": "0:50:21", "remaining_time": "3:41:41", "throughput": 686.26, "total_tokens": 2073824} {"current_steps": 7410, "total_steps": 40000, "loss": 0.0, "lr": 4.5885476780848226e-05, "epoch": 82.33333333333333, "percentage": 18.52, "elapsed_time": "0:50:23", "remaining_time": "3:41:39", "throughput": 686.26, "total_tokens": 2075200} {"current_steps": 7415, "total_steps": 40000, "loss": 0.0, "lr": 4.5880079352880964e-05, "epoch": 82.38888888888889, "percentage": 18.54, "elapsed_time": "0:50:25", "remaining_time": "3:41:37", "throughput": 686.27, "total_tokens": 2076592} {"current_steps": 7420, "total_steps": 40000, "loss": 0.0, "lr": 4.5874678704943065e-05, "epoch": 82.44444444444444, "percentage": 18.55, "elapsed_time": "0:50:27", "remaining_time": "3:41:34", "throughput": 686.3, "total_tokens": 2078000} {"current_steps": 7425, "total_steps": 40000, "loss": 0.0, "lr": 4.5869274837867394e-05, "epoch": 82.5, "percentage": 18.56, "elapsed_time": "0:50:29", "remaining_time": "3:41:32", "throughput": 686.32, "total_tokens": 2079408} {"current_steps": 7430, "total_steps": 40000, "loss": 0.0, "lr": 4.5863867752487275e-05, "epoch": 82.55555555555556, "percentage": 18.57, "elapsed_time": "0:50:31", "remaining_time": "3:41:29", "throughput": 686.33, "total_tokens": 2080800} {"current_steps": 7435, "total_steps": 40000, "loss": 0.0, "lr": 4.5858457449636554e-05, "epoch": 82.61111111111111, "percentage": 18.59, "elapsed_time": "0:50:33", "remaining_time": "3:41:27", "throughput": 686.35, "total_tokens": 2082176} {"current_steps": 7440, "total_steps": 40000, "loss": 0.0, "lr": 4.5853043930149574e-05, "epoch": 82.66666666666667, "percentage": 18.6, "elapsed_time": "0:50:35", "remaining_time": "3:41:25", "throughput": 686.38, "total_tokens": 2083600} {"current_steps": 7445, "total_steps": 40000, "loss": 0.0, "lr": 4.584762719486117e-05, "epoch": 82.72222222222223, "percentage": 18.61, "elapsed_time": "0:50:37", "remaining_time": "3:41:22", "throughput": 686.39, "total_tokens": 2084976} {"current_steps": 7450, "total_steps": 40000, "loss": 0.0, "lr": 4.584220724460665e-05, "epoch": 82.77777777777777, "percentage": 18.62, "elapsed_time": "0:50:39", "remaining_time": "3:41:20", "throughput": 686.41, "total_tokens": 2086384} {"current_steps": 7455, "total_steps": 40000, "loss": 0.0, "lr": 4.5836784080221865e-05, "epoch": 82.83333333333333, "percentage": 18.64, "elapsed_time": "0:50:41", "remaining_time": "3:41:17", "throughput": 686.43, "total_tokens": 2087776} {"current_steps": 7460, "total_steps": 40000, "loss": 0.0, "lr": 4.583135770254312e-05, "epoch": 82.88888888888889, "percentage": 18.65, "elapsed_time": "0:50:43", "remaining_time": "3:41:15", "throughput": 686.45, "total_tokens": 2089152} {"current_steps": 7465, "total_steps": 40000, "loss": 0.0, "lr": 4.5825928112407236e-05, "epoch": 82.94444444444444, "percentage": 18.66, "elapsed_time": "0:50:45", "remaining_time": "3:41:12", "throughput": 686.46, "total_tokens": 2090544} {"current_steps": 7470, "total_steps": 40000, "loss": 0.0, "lr": 4.582049531065152e-05, "epoch": 83.0, "percentage": 18.68, "elapsed_time": "0:50:47", "remaining_time": "3:41:11", "throughput": 686.46, "total_tokens": 2092000} {"current_steps": 7475, "total_steps": 40000, "loss": 0.0, "lr": 4.5815059298113783e-05, "epoch": 83.05555555555556, "percentage": 18.69, "elapsed_time": "0:50:49", "remaining_time": "3:41:09", "throughput": 686.42, "total_tokens": 2093392} {"current_steps": 7480, "total_steps": 40000, "loss": 0.0, "lr": 4.580962007563232e-05, "epoch": 83.11111111111111, "percentage": 18.7, "elapsed_time": "0:50:51", "remaining_time": "3:41:07", "throughput": 686.45, "total_tokens": 2094816} {"current_steps": 7485, "total_steps": 40000, "loss": 0.0, "lr": 4.5804177644045935e-05, "epoch": 83.16666666666667, "percentage": 18.71, "elapsed_time": "0:50:53", "remaining_time": "3:41:05", "throughput": 686.46, "total_tokens": 2096208} {"current_steps": 7490, "total_steps": 40000, "loss": 0.0, "lr": 4.579873200419391e-05, "epoch": 83.22222222222223, "percentage": 18.73, "elapsed_time": "0:50:55", "remaining_time": "3:41:02", "throughput": 686.49, "total_tokens": 2097616} {"current_steps": 7495, "total_steps": 40000, "loss": 0.0, "lr": 4.5793283156916046e-05, "epoch": 83.27777777777777, "percentage": 18.74, "elapsed_time": "0:50:57", "remaining_time": "3:41:00", "throughput": 686.5, "total_tokens": 2098992} {"current_steps": 7500, "total_steps": 40000, "loss": 0.0, "lr": 4.578783110305261e-05, "epoch": 83.33333333333333, "percentage": 18.75, "elapsed_time": "0:50:59", "remaining_time": "3:40:57", "throughput": 686.53, "total_tokens": 2100400} {"current_steps": 7505, "total_steps": 40000, "loss": 0.0, "lr": 4.578237584344438e-05, "epoch": 83.38888888888889, "percentage": 18.76, "elapsed_time": "0:51:01", "remaining_time": "3:40:55", "throughput": 686.55, "total_tokens": 2101808} {"current_steps": 7510, "total_steps": 40000, "loss": 0.0, "lr": 4.577691737893263e-05, "epoch": 83.44444444444444, "percentage": 18.77, "elapsed_time": "0:51:03", "remaining_time": "3:40:52", "throughput": 686.57, "total_tokens": 2103216} {"current_steps": 7515, "total_steps": 40000, "loss": 0.0, "lr": 4.577145571035912e-05, "epoch": 83.5, "percentage": 18.79, "elapsed_time": "0:51:05", "remaining_time": "3:40:50", "throughput": 686.59, "total_tokens": 2104624} {"current_steps": 7520, "total_steps": 40000, "loss": 0.0, "lr": 4.576599083856611e-05, "epoch": 83.55555555555556, "percentage": 18.8, "elapsed_time": "0:51:07", "remaining_time": "3:40:47", "throughput": 686.62, "total_tokens": 2106048} {"current_steps": 7525, "total_steps": 40000, "loss": 0.0, "lr": 4.576052276439635e-05, "epoch": 83.61111111111111, "percentage": 18.81, "elapsed_time": "0:51:09", "remaining_time": "3:40:45", "throughput": 686.65, "total_tokens": 2107472} {"current_steps": 7530, "total_steps": 40000, "loss": 0.0, "lr": 4.575505148869308e-05, "epoch": 83.66666666666667, "percentage": 18.82, "elapsed_time": "0:51:11", "remaining_time": "3:40:43", "throughput": 686.66, "total_tokens": 2108832} {"current_steps": 7535, "total_steps": 40000, "loss": 0.0, "lr": 4.574957701230006e-05, "epoch": 83.72222222222223, "percentage": 18.84, "elapsed_time": "0:51:13", "remaining_time": "3:40:40", "throughput": 686.67, "total_tokens": 2110208} {"current_steps": 7540, "total_steps": 40000, "loss": 0.0, "lr": 4.57440993360615e-05, "epoch": 83.77777777777777, "percentage": 18.85, "elapsed_time": "0:51:15", "remaining_time": "3:40:38", "throughput": 686.69, "total_tokens": 2111584} {"current_steps": 7545, "total_steps": 40000, "loss": 0.0, "lr": 4.5738618460822134e-05, "epoch": 83.83333333333333, "percentage": 18.86, "elapsed_time": "0:51:16", "remaining_time": "3:40:35", "throughput": 686.72, "total_tokens": 2113008} {"current_steps": 7550, "total_steps": 40000, "loss": 0.0, "lr": 4.573313438742719e-05, "epoch": 83.88888888888889, "percentage": 18.88, "elapsed_time": "0:51:18", "remaining_time": "3:40:33", "throughput": 686.74, "total_tokens": 2114416} {"current_steps": 7555, "total_steps": 40000, "loss": 0.0, "lr": 4.5727647116722374e-05, "epoch": 83.94444444444444, "percentage": 18.89, "elapsed_time": "0:51:20", "remaining_time": "3:40:30", "throughput": 686.75, "total_tokens": 2115776} {"current_steps": 7560, "total_steps": 40000, "loss": 0.0, "lr": 4.5722156649553884e-05, "epoch": 84.0, "percentage": 18.9, "elapsed_time": "0:51:22", "remaining_time": "3:40:29", "throughput": 686.74, "total_tokens": 2117200} {"current_steps": 7565, "total_steps": 40000, "loss": 0.0, "lr": 4.571666298676843e-05, "epoch": 84.05555555555556, "percentage": 18.91, "elapsed_time": "0:51:25", "remaining_time": "3:40:27", "throughput": 686.7, "total_tokens": 2118592} {"current_steps": 7570, "total_steps": 40000, "loss": 0.0, "lr": 4.571116612921321e-05, "epoch": 84.11111111111111, "percentage": 18.93, "elapsed_time": "0:51:27", "remaining_time": "3:40:25", "throughput": 686.72, "total_tokens": 2120000} {"current_steps": 7575, "total_steps": 40000, "loss": 0.0, "lr": 4.57056660777359e-05, "epoch": 84.16666666666667, "percentage": 18.94, "elapsed_time": "0:51:29", "remaining_time": "3:40:22", "throughput": 686.75, "total_tokens": 2121408} {"current_steps": 7580, "total_steps": 40000, "loss": 0.0, "lr": 4.5700162833184666e-05, "epoch": 84.22222222222223, "percentage": 18.95, "elapsed_time": "0:51:31", "remaining_time": "3:40:20", "throughput": 686.76, "total_tokens": 2122784} {"current_steps": 7585, "total_steps": 40000, "loss": 0.0, "lr": 4.5694656396408195e-05, "epoch": 84.27777777777777, "percentage": 18.96, "elapsed_time": "0:51:32", "remaining_time": "3:40:18", "throughput": 686.77, "total_tokens": 2124160} {"current_steps": 7590, "total_steps": 40000, "loss": 0.0, "lr": 4.5689146768255646e-05, "epoch": 84.33333333333333, "percentage": 18.98, "elapsed_time": "0:51:34", "remaining_time": "3:40:15", "throughput": 686.82, "total_tokens": 2125632} {"current_steps": 7595, "total_steps": 40000, "loss": 0.0, "lr": 4.568363394957667e-05, "epoch": 84.38888888888889, "percentage": 18.99, "elapsed_time": "0:51:36", "remaining_time": "3:40:13", "throughput": 686.84, "total_tokens": 2127024} {"current_steps": 7600, "total_steps": 40000, "loss": 0.0, "lr": 4.567811794122141e-05, "epoch": 84.44444444444444, "percentage": 19.0, "elapsed_time": "0:51:38", "remaining_time": "3:40:10", "throughput": 686.84, "total_tokens": 2128384} {"current_steps": 7600, "total_steps": 40000, "eval_loss": 0.28496068716049194, "epoch": 84.44444444444444, "percentage": 19.0, "elapsed_time": "0:51:40", "remaining_time": "3:40:16", "throughput": 686.55, "total_tokens": 2128384} {"current_steps": 7605, "total_steps": 40000, "loss": 0.0, "lr": 4.56725987440405e-05, "epoch": 84.5, "percentage": 19.01, "elapsed_time": "0:51:43", "remaining_time": "3:40:19", "throughput": 686.25, "total_tokens": 2129776} {"current_steps": 7610, "total_steps": 40000, "loss": 0.0, "lr": 4.566707635888508e-05, "epoch": 84.55555555555556, "percentage": 19.02, "elapsed_time": "0:51:45", "remaining_time": "3:40:17", "throughput": 686.26, "total_tokens": 2131200} {"current_steps": 7615, "total_steps": 40000, "loss": 0.0, "lr": 4.566155078660677e-05, "epoch": 84.61111111111111, "percentage": 19.04, "elapsed_time": "0:51:47", "remaining_time": "3:40:15", "throughput": 686.27, "total_tokens": 2132608} {"current_steps": 7620, "total_steps": 40000, "loss": 0.0, "lr": 4.565602202805768e-05, "epoch": 84.66666666666667, "percentage": 19.05, "elapsed_time": "0:51:49", "remaining_time": "3:40:13", "throughput": 686.28, "total_tokens": 2133968} {"current_steps": 7625, "total_steps": 40000, "loss": 0.0, "lr": 4.56504900840904e-05, "epoch": 84.72222222222223, "percentage": 19.06, "elapsed_time": "0:51:51", "remaining_time": "3:40:10", "throughput": 686.29, "total_tokens": 2135360} {"current_steps": 7630, "total_steps": 40000, "loss": 0.0, "lr": 4.564495495555805e-05, "epoch": 84.77777777777777, "percentage": 19.07, "elapsed_time": "0:51:53", "remaining_time": "3:40:08", "throughput": 686.33, "total_tokens": 2136800} {"current_steps": 7635, "total_steps": 40000, "loss": 0.0, "lr": 4.5639416643314204e-05, "epoch": 84.83333333333333, "percentage": 19.09, "elapsed_time": "0:51:55", "remaining_time": "3:40:05", "throughput": 686.35, "total_tokens": 2138192} {"current_steps": 7640, "total_steps": 40000, "loss": 0.0, "lr": 4.5633875148212946e-05, "epoch": 84.88888888888889, "percentage": 19.1, "elapsed_time": "0:51:57", "remaining_time": "3:40:03", "throughput": 686.38, "total_tokens": 2139632} {"current_steps": 7645, "total_steps": 40000, "loss": 0.0, "lr": 4.562833047110883e-05, "epoch": 84.94444444444444, "percentage": 19.11, "elapsed_time": "0:51:59", "remaining_time": "3:40:01", "throughput": 686.4, "total_tokens": 2141008} {"current_steps": 7650, "total_steps": 40000, "loss": 0.0, "lr": 4.5622782612856923e-05, "epoch": 85.0, "percentage": 19.12, "elapsed_time": "0:52:01", "remaining_time": "3:39:59", "throughput": 686.37, "total_tokens": 2142400} {"current_steps": 7655, "total_steps": 40000, "loss": 0.0, "lr": 4.561723157431278e-05, "epoch": 85.05555555555556, "percentage": 19.14, "elapsed_time": "0:52:03", "remaining_time": "3:39:58", "throughput": 686.34, "total_tokens": 2143808} {"current_steps": 7660, "total_steps": 40000, "loss": 0.0, "lr": 4.5611677356332435e-05, "epoch": 85.11111111111111, "percentage": 19.15, "elapsed_time": "0:52:05", "remaining_time": "3:39:55", "throughput": 686.36, "total_tokens": 2145200} {"current_steps": 7665, "total_steps": 40000, "loss": 0.0, "lr": 4.560611995977242e-05, "epoch": 85.16666666666667, "percentage": 19.16, "elapsed_time": "0:52:07", "remaining_time": "3:39:53", "throughput": 686.37, "total_tokens": 2146592} {"current_steps": 7670, "total_steps": 40000, "loss": 0.0, "lr": 4.560055938548975e-05, "epoch": 85.22222222222223, "percentage": 19.18, "elapsed_time": "0:52:09", "remaining_time": "3:39:50", "throughput": 686.41, "total_tokens": 2148032} {"current_steps": 7675, "total_steps": 40000, "loss": 0.0, "lr": 4.5594995634341944e-05, "epoch": 85.27777777777777, "percentage": 19.19, "elapsed_time": "0:52:11", "remaining_time": "3:39:48", "throughput": 686.43, "total_tokens": 2149424} {"current_steps": 7680, "total_steps": 40000, "loss": 0.0, "lr": 4.5589428707187e-05, "epoch": 85.33333333333333, "percentage": 19.2, "elapsed_time": "0:52:13", "remaining_time": "3:39:45", "throughput": 686.45, "total_tokens": 2150832} {"current_steps": 7685, "total_steps": 40000, "loss": 0.0, "lr": 4.55838586048834e-05, "epoch": 85.38888888888889, "percentage": 19.21, "elapsed_time": "0:52:15", "remaining_time": "3:39:43", "throughput": 686.48, "total_tokens": 2152256} {"current_steps": 7690, "total_steps": 40000, "loss": 0.0, "lr": 4.557828532829013e-05, "epoch": 85.44444444444444, "percentage": 19.23, "elapsed_time": "0:52:17", "remaining_time": "3:39:41", "throughput": 686.49, "total_tokens": 2153648} {"current_steps": 7695, "total_steps": 40000, "loss": 0.0, "lr": 4.557270887826667e-05, "epoch": 85.5, "percentage": 19.24, "elapsed_time": "0:52:19", "remaining_time": "3:39:38", "throughput": 686.51, "total_tokens": 2155056} {"current_steps": 7700, "total_steps": 40000, "loss": 0.0, "lr": 4.556712925567296e-05, "epoch": 85.55555555555556, "percentage": 19.25, "elapsed_time": "0:52:21", "remaining_time": "3:39:36", "throughput": 686.53, "total_tokens": 2156432} {"current_steps": 7705, "total_steps": 40000, "loss": 0.0, "lr": 4.5561546461369454e-05, "epoch": 85.61111111111111, "percentage": 19.26, "elapsed_time": "0:52:23", "remaining_time": "3:39:33", "throughput": 686.54, "total_tokens": 2157808} {"current_steps": 7710, "total_steps": 40000, "loss": 0.0, "lr": 4.55559604962171e-05, "epoch": 85.66666666666667, "percentage": 19.28, "elapsed_time": "0:52:24", "remaining_time": "3:39:31", "throughput": 686.57, "total_tokens": 2159232} {"current_steps": 7715, "total_steps": 40000, "loss": 0.0, "lr": 4.55503713610773e-05, "epoch": 85.72222222222223, "percentage": 19.29, "elapsed_time": "0:52:26", "remaining_time": "3:39:28", "throughput": 686.59, "total_tokens": 2160640} {"current_steps": 7720, "total_steps": 40000, "loss": 0.0, "lr": 4.5544779056812e-05, "epoch": 85.77777777777777, "percentage": 19.3, "elapsed_time": "0:52:28", "remaining_time": "3:39:26", "throughput": 686.62, "total_tokens": 2162064} {"current_steps": 7725, "total_steps": 40000, "loss": 0.0, "lr": 4.553918358428358e-05, "epoch": 85.83333333333333, "percentage": 19.31, "elapsed_time": "0:52:30", "remaining_time": "3:39:24", "throughput": 686.64, "total_tokens": 2163456} {"current_steps": 7730, "total_steps": 40000, "loss": 0.0, "lr": 4.553358494435494e-05, "epoch": 85.88888888888889, "percentage": 19.32, "elapsed_time": "0:52:32", "remaining_time": "3:39:21", "throughput": 686.66, "total_tokens": 2164848} {"current_steps": 7735, "total_steps": 40000, "loss": 0.0, "lr": 4.5527983137889464e-05, "epoch": 85.94444444444444, "percentage": 19.34, "elapsed_time": "0:52:34", "remaining_time": "3:39:19", "throughput": 686.69, "total_tokens": 2166272} {"current_steps": 7740, "total_steps": 40000, "loss": 0.0, "lr": 4.5522378165751015e-05, "epoch": 86.0, "percentage": 19.35, "elapsed_time": "0:52:36", "remaining_time": "3:39:17", "throughput": 686.67, "total_tokens": 2167664} {"current_steps": 7745, "total_steps": 40000, "loss": 0.0, "lr": 4.5516770028803954e-05, "epoch": 86.05555555555556, "percentage": 19.36, "elapsed_time": "0:52:38", "remaining_time": "3:39:16", "throughput": 686.63, "total_tokens": 2169072} {"current_steps": 7750, "total_steps": 40000, "loss": 0.0, "lr": 4.5511158727913116e-05, "epoch": 86.11111111111111, "percentage": 19.38, "elapsed_time": "0:52:40", "remaining_time": "3:39:13", "throughput": 686.66, "total_tokens": 2170480} {"current_steps": 7755, "total_steps": 40000, "loss": 0.0, "lr": 4.5505544263943856e-05, "epoch": 86.16666666666667, "percentage": 19.39, "elapsed_time": "0:52:42", "remaining_time": "3:39:11", "throughput": 686.68, "total_tokens": 2171888} {"current_steps": 7760, "total_steps": 40000, "loss": 0.0, "lr": 4.549992663776197e-05, "epoch": 86.22222222222223, "percentage": 19.4, "elapsed_time": "0:52:44", "remaining_time": "3:39:08", "throughput": 686.69, "total_tokens": 2173248} {"current_steps": 7765, "total_steps": 40000, "loss": 0.0, "lr": 4.5494305850233786e-05, "epoch": 86.27777777777777, "percentage": 19.41, "elapsed_time": "0:52:46", "remaining_time": "3:39:06", "throughput": 686.71, "total_tokens": 2174656} {"current_steps": 7770, "total_steps": 40000, "loss": 0.0, "lr": 4.5488681902226094e-05, "epoch": 86.33333333333333, "percentage": 19.43, "elapsed_time": "0:52:48", "remaining_time": "3:39:03", "throughput": 686.73, "total_tokens": 2176064} {"current_steps": 7775, "total_steps": 40000, "loss": 0.0, "lr": 4.5483054794606174e-05, "epoch": 86.38888888888889, "percentage": 19.44, "elapsed_time": "0:52:50", "remaining_time": "3:39:01", "throughput": 686.75, "total_tokens": 2177456} {"current_steps": 7780, "total_steps": 40000, "loss": 0.0, "lr": 4.547742452824179e-05, "epoch": 86.44444444444444, "percentage": 19.45, "elapsed_time": "0:52:52", "remaining_time": "3:38:59", "throughput": 686.77, "total_tokens": 2178864} {"current_steps": 7785, "total_steps": 40000, "loss": 0.0, "lr": 4.5471791104001215e-05, "epoch": 86.5, "percentage": 19.46, "elapsed_time": "0:52:54", "remaining_time": "3:38:56", "throughput": 686.79, "total_tokens": 2180240} {"current_steps": 7790, "total_steps": 40000, "loss": 0.0, "lr": 4.546615452275319e-05, "epoch": 86.55555555555556, "percentage": 19.48, "elapsed_time": "0:52:56", "remaining_time": "3:38:54", "throughput": 686.79, "total_tokens": 2181584} {"current_steps": 7795, "total_steps": 40000, "loss": 0.0, "lr": 4.5460514785366944e-05, "epoch": 86.61111111111111, "percentage": 19.49, "elapsed_time": "0:52:58", "remaining_time": "3:38:51", "throughput": 686.81, "total_tokens": 2182992} {"current_steps": 7800, "total_steps": 40000, "loss": 0.0, "lr": 4.545487189271219e-05, "epoch": 86.66666666666667, "percentage": 19.5, "elapsed_time": "0:53:00", "remaining_time": "3:38:49", "throughput": 686.84, "total_tokens": 2184416} {"current_steps": 7800, "total_steps": 40000, "eval_loss": 0.25023534893989563, "epoch": 86.66666666666667, "percentage": 19.5, "elapsed_time": "0:53:01", "remaining_time": "3:38:54", "throughput": 686.55, "total_tokens": 2184416} {"current_steps": 7805, "total_steps": 40000, "loss": 0.0, "lr": 4.544922584565914e-05, "epoch": 86.72222222222223, "percentage": 19.51, "elapsed_time": "0:53:04", "remaining_time": "3:38:57", "throughput": 686.29, "total_tokens": 2185808} {"current_steps": 7810, "total_steps": 40000, "loss": 0.0, "lr": 4.544357664507848e-05, "epoch": 86.77777777777777, "percentage": 19.53, "elapsed_time": "0:53:06", "remaining_time": "3:38:55", "throughput": 686.29, "total_tokens": 2187184} {"current_steps": 7815, "total_steps": 40000, "loss": 0.0, "lr": 4.54379242918414e-05, "epoch": 86.83333333333333, "percentage": 19.54, "elapsed_time": "0:53:08", "remaining_time": "3:38:53", "throughput": 686.33, "total_tokens": 2188640} {"current_steps": 7820, "total_steps": 40000, "loss": 0.0, "lr": 4.543226878681955e-05, "epoch": 86.88888888888889, "percentage": 19.55, "elapsed_time": "0:53:10", "remaining_time": "3:38:50", "throughput": 686.35, "total_tokens": 2190048} {"current_steps": 7825, "total_steps": 40000, "loss": 0.0, "lr": 4.5426610130885087e-05, "epoch": 86.94444444444444, "percentage": 19.56, "elapsed_time": "0:53:12", "remaining_time": "3:38:48", "throughput": 686.37, "total_tokens": 2191440} {"current_steps": 7830, "total_steps": 40000, "loss": 0.0, "lr": 4.542094832491064e-05, "epoch": 87.0, "percentage": 19.57, "elapsed_time": "0:53:14", "remaining_time": "3:38:46", "throughput": 686.37, "total_tokens": 2192864} {"current_steps": 7835, "total_steps": 40000, "loss": 0.0, "lr": 4.541528336976934e-05, "epoch": 87.05555555555556, "percentage": 19.59, "elapsed_time": "0:53:17", "remaining_time": "3:38:45", "throughput": 686.34, "total_tokens": 2194288} {"current_steps": 7840, "total_steps": 40000, "loss": 0.0, "lr": 4.540961526633479e-05, "epoch": 87.11111111111111, "percentage": 19.6, "elapsed_time": "0:53:19", "remaining_time": "3:38:42", "throughput": 686.37, "total_tokens": 2195728} {"current_steps": 7845, "total_steps": 40000, "loss": 0.0, "lr": 4.540394401548108e-05, "epoch": 87.16666666666667, "percentage": 19.61, "elapsed_time": "0:53:20", "remaining_time": "3:38:40", "throughput": 686.39, "total_tokens": 2197120} {"current_steps": 7850, "total_steps": 40000, "loss": 0.0, "lr": 4.539826961808279e-05, "epoch": 87.22222222222223, "percentage": 19.62, "elapsed_time": "0:53:22", "remaining_time": "3:38:37", "throughput": 686.41, "total_tokens": 2198512} {"current_steps": 7855, "total_steps": 40000, "loss": 0.0, "lr": 4.5392592075014994e-05, "epoch": 87.27777777777777, "percentage": 19.64, "elapsed_time": "0:53:24", "remaining_time": "3:38:35", "throughput": 686.43, "total_tokens": 2199920} {"current_steps": 7860, "total_steps": 40000, "loss": 0.0, "lr": 4.538691138715322e-05, "epoch": 87.33333333333333, "percentage": 19.65, "elapsed_time": "0:53:26", "remaining_time": "3:38:32", "throughput": 686.44, "total_tokens": 2201296} {"current_steps": 7865, "total_steps": 40000, "loss": 0.0, "lr": 4.5381227555373516e-05, "epoch": 87.38888888888889, "percentage": 19.66, "elapsed_time": "0:53:28", "remaining_time": "3:38:30", "throughput": 686.46, "total_tokens": 2202688} {"current_steps": 7870, "total_steps": 40000, "loss": 0.0, "lr": 4.537554058055239e-05, "epoch": 87.44444444444444, "percentage": 19.68, "elapsed_time": "0:53:30", "remaining_time": "3:38:28", "throughput": 686.49, "total_tokens": 2204112} {"current_steps": 7875, "total_steps": 40000, "loss": 0.0, "lr": 4.5369850463566865e-05, "epoch": 87.5, "percentage": 19.69, "elapsed_time": "0:53:32", "remaining_time": "3:38:25", "throughput": 686.49, "total_tokens": 2205472} {"current_steps": 7880, "total_steps": 40000, "loss": 0.0, "lr": 4.5364157205294404e-05, "epoch": 87.55555555555556, "percentage": 19.7, "elapsed_time": "0:53:34", "remaining_time": "3:38:23", "throughput": 686.51, "total_tokens": 2206864} {"current_steps": 7885, "total_steps": 40000, "loss": 0.0, "lr": 4.5358460806612996e-05, "epoch": 87.61111111111111, "percentage": 19.71, "elapsed_time": "0:53:36", "remaining_time": "3:38:20", "throughput": 686.55, "total_tokens": 2208336} {"current_steps": 7890, "total_steps": 40000, "loss": 0.0, "lr": 4.535276126840109e-05, "epoch": 87.66666666666667, "percentage": 19.73, "elapsed_time": "0:53:38", "remaining_time": "3:38:18", "throughput": 686.57, "total_tokens": 2209744} {"current_steps": 7895, "total_steps": 40000, "loss": 0.0, "lr": 4.5347058591537626e-05, "epoch": 87.72222222222223, "percentage": 19.74, "elapsed_time": "0:53:40", "remaining_time": "3:38:15", "throughput": 686.59, "total_tokens": 2211120} {"current_steps": 7900, "total_steps": 40000, "loss": 0.0, "lr": 4.534135277690203e-05, "epoch": 87.77777777777777, "percentage": 19.75, "elapsed_time": "0:53:42", "remaining_time": "3:38:13", "throughput": 686.6, "total_tokens": 2212496} {"current_steps": 7905, "total_steps": 40000, "loss": 0.0, "lr": 4.533564382537421e-05, "epoch": 87.83333333333333, "percentage": 19.76, "elapsed_time": "0:53:44", "remaining_time": "3:38:12", "throughput": 686.53, "total_tokens": 2213856} {"current_steps": 7910, "total_steps": 40000, "loss": 0.0, "lr": 4.532993173783456e-05, "epoch": 87.88888888888889, "percentage": 19.78, "elapsed_time": "0:53:46", "remaining_time": "3:38:10", "throughput": 686.56, "total_tokens": 2215296} {"current_steps": 7915, "total_steps": 40000, "loss": 0.0, "lr": 4.5324216515163954e-05, "epoch": 87.94444444444444, "percentage": 19.79, "elapsed_time": "0:53:48", "remaining_time": "3:38:07", "throughput": 686.58, "total_tokens": 2216704} {"current_steps": 7920, "total_steps": 40000, "loss": 0.0, "lr": 4.531849815824375e-05, "epoch": 88.0, "percentage": 19.8, "elapsed_time": "0:53:50", "remaining_time": "3:38:06", "throughput": 686.57, "total_tokens": 2218128} {"current_steps": 7925, "total_steps": 40000, "loss": 0.0, "lr": 4.5312776667955795e-05, "epoch": 88.05555555555556, "percentage": 19.81, "elapsed_time": "0:53:52", "remaining_time": "3:38:04", "throughput": 686.51, "total_tokens": 2219472} {"current_steps": 7930, "total_steps": 40000, "loss": 0.0, "lr": 4.5307052045182405e-05, "epoch": 88.11111111111111, "percentage": 19.82, "elapsed_time": "0:53:54", "remaining_time": "3:38:02", "throughput": 686.52, "total_tokens": 2220832} {"current_steps": 7935, "total_steps": 40000, "loss": 0.0, "lr": 4.53013242908064e-05, "epoch": 88.16666666666667, "percentage": 19.84, "elapsed_time": "0:53:56", "remaining_time": "3:38:00", "throughput": 686.54, "total_tokens": 2222224} {"current_steps": 7940, "total_steps": 40000, "loss": 0.0, "lr": 4.529559340571107e-05, "epoch": 88.22222222222223, "percentage": 19.85, "elapsed_time": "0:53:58", "remaining_time": "3:37:57", "throughput": 686.54, "total_tokens": 2223584} {"current_steps": 7945, "total_steps": 40000, "loss": 0.0, "lr": 4.528985939078018e-05, "epoch": 88.27777777777777, "percentage": 19.86, "elapsed_time": "0:54:00", "remaining_time": "3:37:55", "throughput": 686.55, "total_tokens": 2224944} {"current_steps": 7950, "total_steps": 40000, "loss": 0.0, "lr": 4.5284122246898e-05, "epoch": 88.33333333333333, "percentage": 19.88, "elapsed_time": "0:54:02", "remaining_time": "3:37:52", "throughput": 686.57, "total_tokens": 2226336} {"current_steps": 7955, "total_steps": 40000, "loss": 0.0, "lr": 4.527838197494926e-05, "epoch": 88.38888888888889, "percentage": 19.89, "elapsed_time": "0:54:04", "remaining_time": "3:37:50", "throughput": 686.58, "total_tokens": 2227728} {"current_steps": 7960, "total_steps": 40000, "loss": 0.0, "lr": 4.527263857581918e-05, "epoch": 88.44444444444444, "percentage": 19.9, "elapsed_time": "0:54:06", "remaining_time": "3:37:47", "throughput": 686.62, "total_tokens": 2229168} {"current_steps": 7965, "total_steps": 40000, "loss": 0.0, "lr": 4.526689205039347e-05, "epoch": 88.5, "percentage": 19.91, "elapsed_time": "0:54:08", "remaining_time": "3:37:45", "throughput": 686.65, "total_tokens": 2230592} {"current_steps": 7970, "total_steps": 40000, "loss": 0.0, "lr": 4.5261142399558324e-05, "epoch": 88.55555555555556, "percentage": 19.93, "elapsed_time": "0:54:10", "remaining_time": "3:37:43", "throughput": 686.66, "total_tokens": 2231984} {"current_steps": 7975, "total_steps": 40000, "loss": 0.0, "lr": 4.525538962420041e-05, "epoch": 88.61111111111111, "percentage": 19.94, "elapsed_time": "0:54:12", "remaining_time": "3:37:40", "throughput": 686.7, "total_tokens": 2233424} {"current_steps": 7980, "total_steps": 40000, "loss": 0.0, "lr": 4.524963372520685e-05, "epoch": 88.66666666666667, "percentage": 19.95, "elapsed_time": "0:54:14", "remaining_time": "3:37:38", "throughput": 686.72, "total_tokens": 2234848} {"current_steps": 7985, "total_steps": 40000, "loss": 0.0, "lr": 4.524387470346531e-05, "epoch": 88.72222222222223, "percentage": 19.96, "elapsed_time": "0:54:16", "remaining_time": "3:37:35", "throughput": 686.76, "total_tokens": 2236304} {"current_steps": 7990, "total_steps": 40000, "loss": 0.0, "lr": 4.5238112559863885e-05, "epoch": 88.77777777777777, "percentage": 19.98, "elapsed_time": "0:54:18", "remaining_time": "3:37:33", "throughput": 686.77, "total_tokens": 2237680} {"current_steps": 7995, "total_steps": 40000, "loss": 0.0, "lr": 4.5232347295291175e-05, "epoch": 88.83333333333333, "percentage": 19.99, "elapsed_time": "0:54:20", "remaining_time": "3:37:31", "throughput": 686.79, "total_tokens": 2239104} {"current_steps": 8000, "total_steps": 40000, "loss": 0.0, "lr": 4.522657891063626e-05, "epoch": 88.88888888888889, "percentage": 20.0, "elapsed_time": "0:54:22", "remaining_time": "3:37:28", "throughput": 686.82, "total_tokens": 2240512} {"current_steps": 8000, "total_steps": 40000, "eval_loss": 0.2656751573085785, "epoch": 88.88888888888889, "percentage": 20.0, "elapsed_time": "0:54:23", "remaining_time": "3:37:33", "throughput": 686.54, "total_tokens": 2240512} {"current_steps": 8005, "total_steps": 40000, "loss": 0.0, "lr": 4.52208074067887e-05, "epoch": 88.94444444444444, "percentage": 20.01, "elapsed_time": "0:54:26", "remaining_time": "3:37:36", "throughput": 686.28, "total_tokens": 2241904} {"current_steps": 8010, "total_steps": 40000, "loss": 0.0, "lr": 4.5215032784638516e-05, "epoch": 89.0, "percentage": 20.03, "elapsed_time": "0:54:28", "remaining_time": "3:37:35", "throughput": 686.26, "total_tokens": 2243328} {"current_steps": 8015, "total_steps": 40000, "loss": 0.0, "lr": 4.5209255045076245e-05, "epoch": 89.05555555555556, "percentage": 20.04, "elapsed_time": "0:54:31", "remaining_time": "3:37:33", "throughput": 686.24, "total_tokens": 2244752} {"current_steps": 8020, "total_steps": 40000, "loss": 0.0, "lr": 4.5203474188992875e-05, "epoch": 89.11111111111111, "percentage": 20.05, "elapsed_time": "0:54:33", "remaining_time": "3:37:31", "throughput": 686.26, "total_tokens": 2246160} {"current_steps": 8025, "total_steps": 40000, "loss": 0.0, "lr": 4.51976902172799e-05, "epoch": 89.16666666666667, "percentage": 20.06, "elapsed_time": "0:54:35", "remaining_time": "3:37:29", "throughput": 686.28, "total_tokens": 2247568} {"current_steps": 8030, "total_steps": 40000, "loss": 0.0, "lr": 4.519190313082927e-05, "epoch": 89.22222222222223, "percentage": 20.08, "elapsed_time": "0:54:36", "remaining_time": "3:37:26", "throughput": 686.28, "total_tokens": 2248912} {"current_steps": 8035, "total_steps": 40000, "loss": 0.0, "lr": 4.518611293053343e-05, "epoch": 89.27777777777777, "percentage": 20.09, "elapsed_time": "0:54:38", "remaining_time": "3:37:24", "throughput": 686.3, "total_tokens": 2250304} {"current_steps": 8040, "total_steps": 40000, "loss": 0.0, "lr": 4.51803196172853e-05, "epoch": 89.33333333333333, "percentage": 20.1, "elapsed_time": "0:54:40", "remaining_time": "3:37:21", "throughput": 686.31, "total_tokens": 2251680} {"current_steps": 8045, "total_steps": 40000, "loss": 0.0, "lr": 4.517452319197828e-05, "epoch": 89.38888888888889, "percentage": 20.11, "elapsed_time": "0:54:42", "remaining_time": "3:37:19", "throughput": 686.32, "total_tokens": 2253056} {"current_steps": 8050, "total_steps": 40000, "loss": 0.0, "lr": 4.5168723655506265e-05, "epoch": 89.44444444444444, "percentage": 20.12, "elapsed_time": "0:54:44", "remaining_time": "3:37:16", "throughput": 686.34, "total_tokens": 2254448} {"current_steps": 8055, "total_steps": 40000, "loss": 0.0, "lr": 4.51629210087636e-05, "epoch": 89.5, "percentage": 20.14, "elapsed_time": "0:54:46", "remaining_time": "3:37:14", "throughput": 686.35, "total_tokens": 2255824} {"current_steps": 8060, "total_steps": 40000, "loss": 0.0, "lr": 4.515711525264513e-05, "epoch": 89.55555555555556, "percentage": 20.15, "elapsed_time": "0:54:48", "remaining_time": "3:37:12", "throughput": 686.38, "total_tokens": 2257248} {"current_steps": 8065, "total_steps": 40000, "loss": 0.0, "lr": 4.5151306388046175e-05, "epoch": 89.61111111111111, "percentage": 20.16, "elapsed_time": "0:54:50", "remaining_time": "3:37:09", "throughput": 686.39, "total_tokens": 2258624} {"current_steps": 8070, "total_steps": 40000, "loss": 0.0, "lr": 4.514549441586255e-05, "epoch": 89.66666666666667, "percentage": 20.18, "elapsed_time": "0:54:52", "remaining_time": "3:37:07", "throughput": 686.43, "total_tokens": 2260096} {"current_steps": 8075, "total_steps": 40000, "loss": 0.0, "lr": 4.513967933699051e-05, "epoch": 89.72222222222223, "percentage": 20.19, "elapsed_time": "0:54:54", "remaining_time": "3:37:04", "throughput": 686.46, "total_tokens": 2261520} {"current_steps": 8080, "total_steps": 40000, "loss": 0.0, "lr": 4.513386115232684e-05, "epoch": 89.77777777777777, "percentage": 20.2, "elapsed_time": "0:54:56", "remaining_time": "3:37:02", "throughput": 686.48, "total_tokens": 2262928} {"current_steps": 8085, "total_steps": 40000, "loss": 0.0, "lr": 4.5128039862768745e-05, "epoch": 89.83333333333333, "percentage": 20.21, "elapsed_time": "0:54:58", "remaining_time": "3:37:00", "throughput": 686.5, "total_tokens": 2264304} {"current_steps": 8090, "total_steps": 40000, "loss": 0.0, "lr": 4.512221546921397e-05, "epoch": 89.88888888888889, "percentage": 20.23, "elapsed_time": "0:55:00", "remaining_time": "3:36:57", "throughput": 686.5, "total_tokens": 2265648} {"current_steps": 8095, "total_steps": 40000, "loss": 0.0, "lr": 4.5116387972560694e-05, "epoch": 89.94444444444444, "percentage": 20.24, "elapsed_time": "0:55:02", "remaining_time": "3:36:55", "throughput": 686.52, "total_tokens": 2267056} {"current_steps": 8100, "total_steps": 40000, "loss": 0.0, "lr": 4.511055737370759e-05, "epoch": 90.0, "percentage": 20.25, "elapsed_time": "0:55:04", "remaining_time": "3:36:53", "throughput": 686.51, "total_tokens": 2268464} {"current_steps": 8105, "total_steps": 40000, "loss": 0.0, "lr": 4.510472367355383e-05, "epoch": 90.05555555555556, "percentage": 20.26, "elapsed_time": "0:55:06", "remaining_time": "3:36:51", "throughput": 686.48, "total_tokens": 2269872} {"current_steps": 8110, "total_steps": 40000, "loss": 0.0, "lr": 4.509888687299901e-05, "epoch": 90.11111111111111, "percentage": 20.28, "elapsed_time": "0:55:08", "remaining_time": "3:36:49", "throughput": 686.5, "total_tokens": 2271280} {"current_steps": 8115, "total_steps": 40000, "loss": 0.0, "lr": 4.5093046972943266e-05, "epoch": 90.16666666666667, "percentage": 20.29, "elapsed_time": "0:55:10", "remaining_time": "3:36:47", "throughput": 686.53, "total_tokens": 2272720} {"current_steps": 8120, "total_steps": 40000, "loss": 0.0, "lr": 4.508720397428717e-05, "epoch": 90.22222222222223, "percentage": 20.3, "elapsed_time": "0:55:12", "remaining_time": "3:36:44", "throughput": 686.55, "total_tokens": 2274112} {"current_steps": 8125, "total_steps": 40000, "loss": 0.0, "lr": 4.508135787793178e-05, "epoch": 90.27777777777777, "percentage": 20.31, "elapsed_time": "0:55:14", "remaining_time": "3:36:42", "throughput": 686.57, "total_tokens": 2275520} {"current_steps": 8130, "total_steps": 40000, "loss": 0.0, "lr": 4.5075508684778664e-05, "epoch": 90.33333333333333, "percentage": 20.32, "elapsed_time": "0:55:16", "remaining_time": "3:36:39", "throughput": 686.58, "total_tokens": 2276896} {"current_steps": 8135, "total_steps": 40000, "loss": 0.0, "lr": 4.506965639572982e-05, "epoch": 90.38888888888889, "percentage": 20.34, "elapsed_time": "0:55:18", "remaining_time": "3:36:37", "throughput": 686.61, "total_tokens": 2278304} {"current_steps": 8140, "total_steps": 40000, "loss": 0.0, "lr": 4.506380101168774e-05, "epoch": 90.44444444444444, "percentage": 20.35, "elapsed_time": "0:55:20", "remaining_time": "3:36:35", "throughput": 686.63, "total_tokens": 2279696} {"current_steps": 8145, "total_steps": 40000, "loss": 0.0, "lr": 4.505794253355542e-05, "epoch": 90.5, "percentage": 20.36, "elapsed_time": "0:55:22", "remaining_time": "3:36:32", "throughput": 686.64, "total_tokens": 2281072} {"current_steps": 8150, "total_steps": 40000, "loss": 0.0, "lr": 4.5052080962236286e-05, "epoch": 90.55555555555556, "percentage": 20.38, "elapsed_time": "0:55:24", "remaining_time": "3:36:30", "throughput": 686.65, "total_tokens": 2282448} {"current_steps": 8155, "total_steps": 40000, "loss": 0.0, "lr": 4.504621629863428e-05, "epoch": 90.61111111111111, "percentage": 20.39, "elapsed_time": "0:55:25", "remaining_time": "3:36:27", "throughput": 686.69, "total_tokens": 2283888} {"current_steps": 8160, "total_steps": 40000, "loss": 0.0, "lr": 4.504034854365381e-05, "epoch": 90.66666666666667, "percentage": 20.4, "elapsed_time": "0:55:27", "remaining_time": "3:36:25", "throughput": 686.71, "total_tokens": 2285312} {"current_steps": 8165, "total_steps": 40000, "loss": 0.0, "lr": 4.503447769819974e-05, "epoch": 90.72222222222223, "percentage": 20.41, "elapsed_time": "0:55:29", "remaining_time": "3:36:23", "throughput": 686.73, "total_tokens": 2286704} {"current_steps": 8170, "total_steps": 40000, "loss": 0.0, "lr": 4.502860376317745e-05, "epoch": 90.77777777777777, "percentage": 20.42, "elapsed_time": "0:55:31", "remaining_time": "3:36:20", "throughput": 686.74, "total_tokens": 2288080} {"current_steps": 8175, "total_steps": 40000, "loss": 0.0, "lr": 4.502272673949276e-05, "epoch": 90.83333333333333, "percentage": 20.44, "elapsed_time": "0:55:33", "remaining_time": "3:36:18", "throughput": 686.76, "total_tokens": 2289488} {"current_steps": 8180, "total_steps": 40000, "loss": 0.0, "lr": 4.501684662805199e-05, "epoch": 90.88888888888889, "percentage": 20.45, "elapsed_time": "0:55:35", "remaining_time": "3:36:15", "throughput": 686.78, "total_tokens": 2290896} {"current_steps": 8185, "total_steps": 40000, "loss": 0.0, "lr": 4.5010963429761924e-05, "epoch": 90.94444444444444, "percentage": 20.46, "elapsed_time": "0:55:37", "remaining_time": "3:36:13", "throughput": 686.78, "total_tokens": 2292240} {"current_steps": 8190, "total_steps": 40000, "loss": 0.0, "lr": 4.500507714552982e-05, "epoch": 91.0, "percentage": 20.47, "elapsed_time": "0:55:39", "remaining_time": "3:36:11", "throughput": 686.78, "total_tokens": 2293664} {"current_steps": 8195, "total_steps": 40000, "loss": 0.0, "lr": 4.499918777626342e-05, "epoch": 91.05555555555556, "percentage": 20.49, "elapsed_time": "0:55:41", "remaining_time": "3:36:10", "throughput": 686.77, "total_tokens": 2295120} {"current_steps": 8200, "total_steps": 40000, "loss": 0.0, "lr": 4.499329532287093e-05, "epoch": 91.11111111111111, "percentage": 20.5, "elapsed_time": "0:55:43", "remaining_time": "3:36:07", "throughput": 686.78, "total_tokens": 2296496} {"current_steps": 8200, "total_steps": 40000, "eval_loss": 0.27814704179763794, "epoch": 91.11111111111111, "percentage": 20.5, "elapsed_time": "0:55:45", "remaining_time": "3:36:12", "throughput": 686.51, "total_tokens": 2296496} {"current_steps": 8205, "total_steps": 40000, "loss": 0.0, "lr": 4.4987399786261064e-05, "epoch": 91.16666666666667, "percentage": 20.51, "elapsed_time": "0:55:48", "remaining_time": "3:36:15", "throughput": 686.25, "total_tokens": 2297856} {"current_steps": 8210, "total_steps": 40000, "loss": 0.0, "lr": 4.498150116734297e-05, "epoch": 91.22222222222223, "percentage": 20.52, "elapsed_time": "0:55:50", "remaining_time": "3:36:13", "throughput": 686.25, "total_tokens": 2299216} {"current_steps": 8215, "total_steps": 40000, "loss": 0.0, "lr": 4.4975599467026294e-05, "epoch": 91.27777777777777, "percentage": 20.54, "elapsed_time": "0:55:52", "remaining_time": "3:36:10", "throughput": 686.26, "total_tokens": 2300592} {"current_steps": 8220, "total_steps": 40000, "loss": 0.0, "lr": 4.496969468622114e-05, "epoch": 91.33333333333333, "percentage": 20.55, "elapsed_time": "0:55:54", "remaining_time": "3:36:08", "throughput": 686.27, "total_tokens": 2301952} {"current_steps": 8225, "total_steps": 40000, "loss": 0.0, "lr": 4.496378682583813e-05, "epoch": 91.38888888888889, "percentage": 20.56, "elapsed_time": "0:55:56", "remaining_time": "3:36:05", "throughput": 686.28, "total_tokens": 2303328} {"current_steps": 8230, "total_steps": 40000, "loss": 0.0, "lr": 4.495787588678829e-05, "epoch": 91.44444444444444, "percentage": 20.57, "elapsed_time": "0:55:58", "remaining_time": "3:36:03", "throughput": 686.31, "total_tokens": 2304768} {"current_steps": 8235, "total_steps": 40000, "loss": 0.0, "lr": 4.4951961869983196e-05, "epoch": 91.5, "percentage": 20.59, "elapsed_time": "0:56:00", "remaining_time": "3:36:01", "throughput": 686.33, "total_tokens": 2306192} {"current_steps": 8240, "total_steps": 40000, "loss": 0.0, "lr": 4.494604477633485e-05, "epoch": 91.55555555555556, "percentage": 20.6, "elapsed_time": "0:56:02", "remaining_time": "3:35:58", "throughput": 686.34, "total_tokens": 2307568} {"current_steps": 8245, "total_steps": 40000, "loss": 0.0, "lr": 4.4940124606755734e-05, "epoch": 91.61111111111111, "percentage": 20.61, "elapsed_time": "0:56:04", "remaining_time": "3:35:56", "throughput": 686.36, "total_tokens": 2308944} {"current_steps": 8250, "total_steps": 40000, "loss": 0.0, "lr": 4.493420136215882e-05, "epoch": 91.66666666666667, "percentage": 20.62, "elapsed_time": "0:56:06", "remaining_time": "3:35:54", "throughput": 686.38, "total_tokens": 2310368} {"current_steps": 8255, "total_steps": 40000, "loss": 0.0, "lr": 4.492827504345756e-05, "epoch": 91.72222222222223, "percentage": 20.64, "elapsed_time": "0:56:07", "remaining_time": "3:35:51", "throughput": 686.41, "total_tokens": 2311808} {"current_steps": 8260, "total_steps": 40000, "loss": 0.0, "lr": 4.492234565156584e-05, "epoch": 91.77777777777777, "percentage": 20.65, "elapsed_time": "0:56:09", "remaining_time": "3:35:49", "throughput": 686.43, "total_tokens": 2313216} {"current_steps": 8265, "total_steps": 40000, "loss": 0.0, "lr": 4.491641318739807e-05, "epoch": 91.83333333333333, "percentage": 20.66, "elapsed_time": "0:56:11", "remaining_time": "3:35:46", "throughput": 686.44, "total_tokens": 2314576} {"current_steps": 8270, "total_steps": 40000, "loss": 0.0, "lr": 4.4910477651869096e-05, "epoch": 91.88888888888889, "percentage": 20.67, "elapsed_time": "0:56:13", "remaining_time": "3:35:44", "throughput": 686.47, "total_tokens": 2316016} {"current_steps": 8275, "total_steps": 40000, "loss": 0.0, "lr": 4.4904539045894254e-05, "epoch": 91.94444444444444, "percentage": 20.69, "elapsed_time": "0:56:15", "remaining_time": "3:35:42", "throughput": 686.51, "total_tokens": 2317472} {"current_steps": 8280, "total_steps": 40000, "loss": 0.0, "lr": 4.4898597370389364e-05, "epoch": 92.0, "percentage": 20.7, "elapsed_time": "0:56:17", "remaining_time": "3:35:40", "throughput": 686.49, "total_tokens": 2318864} {"current_steps": 8285, "total_steps": 40000, "loss": 0.0, "lr": 4.489265262627069e-05, "epoch": 92.05555555555556, "percentage": 20.71, "elapsed_time": "0:56:20", "remaining_time": "3:35:38", "throughput": 686.45, "total_tokens": 2320240} {"current_steps": 8290, "total_steps": 40000, "loss": 0.0, "lr": 4.488670481445499e-05, "epoch": 92.11111111111111, "percentage": 20.72, "elapsed_time": "0:56:22", "remaining_time": "3:35:36", "throughput": 686.47, "total_tokens": 2321664} {"current_steps": 8295, "total_steps": 40000, "loss": 0.0, "lr": 4.488075393585951e-05, "epoch": 92.16666666666667, "percentage": 20.74, "elapsed_time": "0:56:23", "remaining_time": "3:35:34", "throughput": 686.48, "total_tokens": 2323040} {"current_steps": 8300, "total_steps": 40000, "loss": 0.0, "lr": 4.487479999140193e-05, "epoch": 92.22222222222223, "percentage": 20.75, "elapsed_time": "0:56:25", "remaining_time": "3:35:31", "throughput": 686.51, "total_tokens": 2324448} {"current_steps": 8305, "total_steps": 40000, "loss": 0.0, "lr": 4.4868842982000425e-05, "epoch": 92.27777777777777, "percentage": 20.76, "elapsed_time": "0:56:27", "remaining_time": "3:35:29", "throughput": 686.52, "total_tokens": 2325840} {"current_steps": 8310, "total_steps": 40000, "loss": 0.0, "lr": 4.486288290857365e-05, "epoch": 92.33333333333333, "percentage": 20.77, "elapsed_time": "0:56:29", "remaining_time": "3:35:26", "throughput": 686.53, "total_tokens": 2327216} {"current_steps": 8315, "total_steps": 40000, "loss": 0.0, "lr": 4.4856919772040715e-05, "epoch": 92.38888888888889, "percentage": 20.79, "elapsed_time": "0:56:31", "remaining_time": "3:35:24", "throughput": 686.56, "total_tokens": 2328640} {"current_steps": 8320, "total_steps": 40000, "loss": 0.0, "lr": 4.485095357332122e-05, "epoch": 92.44444444444444, "percentage": 20.8, "elapsed_time": "0:56:33", "remaining_time": "3:35:22", "throughput": 686.59, "total_tokens": 2330064} {"current_steps": 8325, "total_steps": 40000, "loss": 0.0, "lr": 4.484498431333521e-05, "epoch": 92.5, "percentage": 20.81, "elapsed_time": "0:56:35", "remaining_time": "3:35:19", "throughput": 686.61, "total_tokens": 2331472} {"current_steps": 8330, "total_steps": 40000, "loss": 0.0, "lr": 4.4839011993003245e-05, "epoch": 92.55555555555556, "percentage": 20.82, "elapsed_time": "0:56:37", "remaining_time": "3:35:17", "throughput": 686.63, "total_tokens": 2332864} {"current_steps": 8335, "total_steps": 40000, "loss": 0.0, "lr": 4.4833036613246305e-05, "epoch": 92.61111111111111, "percentage": 20.84, "elapsed_time": "0:56:39", "remaining_time": "3:35:14", "throughput": 686.63, "total_tokens": 2334224} {"current_steps": 8340, "total_steps": 40000, "loss": 0.0, "lr": 4.482705817498589e-05, "epoch": 92.66666666666667, "percentage": 20.85, "elapsed_time": "0:56:41", "remaining_time": "3:35:12", "throughput": 686.65, "total_tokens": 2335600} {"current_steps": 8345, "total_steps": 40000, "loss": 0.0, "lr": 4.4821076679143934e-05, "epoch": 92.72222222222223, "percentage": 20.86, "elapsed_time": "0:56:43", "remaining_time": "3:35:10", "throughput": 686.66, "total_tokens": 2336992} {"current_steps": 8350, "total_steps": 40000, "loss": 0.0, "lr": 4.481509212664288e-05, "epoch": 92.77777777777777, "percentage": 20.88, "elapsed_time": "0:56:45", "remaining_time": "3:35:07", "throughput": 686.69, "total_tokens": 2338432} {"current_steps": 8355, "total_steps": 40000, "loss": 0.0, "lr": 4.480910451840559e-05, "epoch": 92.83333333333333, "percentage": 20.89, "elapsed_time": "0:56:47", "remaining_time": "3:35:05", "throughput": 686.73, "total_tokens": 2339904} {"current_steps": 8360, "total_steps": 40000, "loss": 0.0, "lr": 4.480311385535546e-05, "epoch": 92.88888888888889, "percentage": 20.9, "elapsed_time": "0:56:49", "remaining_time": "3:35:02", "throughput": 686.75, "total_tokens": 2341312} {"current_steps": 8365, "total_steps": 40000, "loss": 0.0, "lr": 4.47971201384163e-05, "epoch": 92.94444444444444, "percentage": 20.91, "elapsed_time": "0:56:51", "remaining_time": "3:35:00", "throughput": 686.77, "total_tokens": 2342704} {"current_steps": 8370, "total_steps": 40000, "loss": 0.0, "lr": 4.4791123368512446e-05, "epoch": 93.0, "percentage": 20.93, "elapsed_time": "0:56:53", "remaining_time": "3:34:58", "throughput": 686.75, "total_tokens": 2344096} {"current_steps": 8375, "total_steps": 40000, "loss": 0.0, "lr": 4.478512354656864e-05, "epoch": 93.05555555555556, "percentage": 20.94, "elapsed_time": "0:56:55", "remaining_time": "3:34:57", "throughput": 686.73, "total_tokens": 2345520} {"current_steps": 8380, "total_steps": 40000, "loss": 0.0, "lr": 4.477912067351016e-05, "epoch": 93.11111111111111, "percentage": 20.95, "elapsed_time": "0:56:57", "remaining_time": "3:34:54", "throughput": 686.76, "total_tokens": 2346960} {"current_steps": 8385, "total_steps": 40000, "loss": 0.0, "lr": 4.477311475026271e-05, "epoch": 93.16666666666667, "percentage": 20.96, "elapsed_time": "0:56:59", "remaining_time": "3:34:52", "throughput": 686.79, "total_tokens": 2348384} {"current_steps": 8390, "total_steps": 40000, "loss": 0.0, "lr": 4.476710577775248e-05, "epoch": 93.22222222222223, "percentage": 20.97, "elapsed_time": "0:57:01", "remaining_time": "3:34:50", "throughput": 686.79, "total_tokens": 2349744} {"current_steps": 8395, "total_steps": 40000, "loss": 0.0, "lr": 4.476109375690612e-05, "epoch": 93.27777777777777, "percentage": 20.99, "elapsed_time": "0:57:03", "remaining_time": "3:34:47", "throughput": 686.81, "total_tokens": 2351136} {"current_steps": 8400, "total_steps": 40000, "loss": 0.0, "lr": 4.4755078688650784e-05, "epoch": 93.33333333333333, "percentage": 21.0, "elapsed_time": "0:57:05", "remaining_time": "3:34:45", "throughput": 686.84, "total_tokens": 2352560} {"current_steps": 8400, "total_steps": 40000, "eval_loss": 0.29218530654907227, "epoch": 93.33333333333333, "percentage": 21.0, "elapsed_time": "0:57:06", "remaining_time": "3:34:50", "throughput": 686.57, "total_tokens": 2352560} {"current_steps": 8405, "total_steps": 40000, "loss": 0.0, "lr": 4.474906057391406e-05, "epoch": 93.38888888888889, "percentage": 21.01, "elapsed_time": "0:57:09", "remaining_time": "3:34:52", "throughput": 686.33, "total_tokens": 2353952} {"current_steps": 8410, "total_steps": 40000, "loss": 0.0, "lr": 4.4743039413624e-05, "epoch": 93.44444444444444, "percentage": 21.02, "elapsed_time": "0:57:11", "remaining_time": "3:34:50", "throughput": 686.34, "total_tokens": 2355360} {"current_steps": 8415, "total_steps": 40000, "loss": 0.0, "lr": 4.473701520870916e-05, "epoch": 93.5, "percentage": 21.04, "elapsed_time": "0:57:13", "remaining_time": "3:34:48", "throughput": 686.35, "total_tokens": 2356752} {"current_steps": 8420, "total_steps": 40000, "loss": 0.0, "lr": 4.4730987960098544e-05, "epoch": 93.55555555555556, "percentage": 21.05, "elapsed_time": "0:57:15", "remaining_time": "3:34:45", "throughput": 686.36, "total_tokens": 2358128} {"current_steps": 8425, "total_steps": 40000, "loss": 0.0, "lr": 4.4724957668721635e-05, "epoch": 93.61111111111111, "percentage": 21.06, "elapsed_time": "0:57:17", "remaining_time": "3:34:43", "throughput": 686.37, "total_tokens": 2359488} {"current_steps": 8430, "total_steps": 40000, "loss": 0.0, "lr": 4.471892433550836e-05, "epoch": 93.66666666666667, "percentage": 21.07, "elapsed_time": "0:57:19", "remaining_time": "3:34:41", "throughput": 686.39, "total_tokens": 2360912} {"current_steps": 8435, "total_steps": 40000, "loss": 0.0, "lr": 4.471288796138916e-05, "epoch": 93.72222222222223, "percentage": 21.09, "elapsed_time": "0:57:21", "remaining_time": "3:34:38", "throughput": 686.4, "total_tokens": 2362288} {"current_steps": 8440, "total_steps": 40000, "loss": 0.0, "lr": 4.470684854729491e-05, "epoch": 93.77777777777777, "percentage": 21.1, "elapsed_time": "0:57:23", "remaining_time": "3:34:36", "throughput": 686.42, "total_tokens": 2363712} {"current_steps": 8445, "total_steps": 40000, "loss": 0.0, "lr": 4.4700806094156955e-05, "epoch": 93.83333333333333, "percentage": 21.11, "elapsed_time": "0:57:25", "remaining_time": "3:34:34", "throughput": 686.44, "total_tokens": 2365104} {"current_steps": 8450, "total_steps": 40000, "loss": 0.0, "lr": 4.469476060290713e-05, "epoch": 93.88888888888889, "percentage": 21.12, "elapsed_time": "0:57:27", "remaining_time": "3:34:31", "throughput": 686.45, "total_tokens": 2366496} {"current_steps": 8455, "total_steps": 40000, "loss": 0.0, "lr": 4.468871207447772e-05, "epoch": 93.94444444444444, "percentage": 21.14, "elapsed_time": "0:57:29", "remaining_time": "3:34:29", "throughput": 686.47, "total_tokens": 2367888} {"current_steps": 8460, "total_steps": 40000, "loss": 0.0, "lr": 4.4682660509801486e-05, "epoch": 94.0, "percentage": 21.15, "elapsed_time": "0:57:31", "remaining_time": "3:34:27", "throughput": 686.46, "total_tokens": 2369312} {"current_steps": 8465, "total_steps": 40000, "loss": 0.0, "lr": 4.467660590981165e-05, "epoch": 94.05555555555556, "percentage": 21.16, "elapsed_time": "0:57:33", "remaining_time": "3:34:26", "throughput": 686.43, "total_tokens": 2370720} {"current_steps": 8470, "total_steps": 40000, "loss": 0.0, "lr": 4.467054827544191e-05, "epoch": 94.11111111111111, "percentage": 21.18, "elapsed_time": "0:57:35", "remaining_time": "3:34:23", "throughput": 686.45, "total_tokens": 2372128} {"current_steps": 8475, "total_steps": 40000, "loss": 0.0, "lr": 4.4664487607626434e-05, "epoch": 94.16666666666667, "percentage": 21.19, "elapsed_time": "0:57:37", "remaining_time": "3:34:21", "throughput": 686.47, "total_tokens": 2373536} {"current_steps": 8480, "total_steps": 40000, "loss": 0.0, "lr": 4.4658423907299845e-05, "epoch": 94.22222222222223, "percentage": 21.2, "elapsed_time": "0:57:39", "remaining_time": "3:34:19", "throughput": 686.48, "total_tokens": 2374896} {"current_steps": 8485, "total_steps": 40000, "loss": 0.0, "lr": 4.465235717539725e-05, "epoch": 94.27777777777777, "percentage": 21.21, "elapsed_time": "0:57:41", "remaining_time": "3:34:16", "throughput": 686.48, "total_tokens": 2376256} {"current_steps": 8490, "total_steps": 40000, "loss": 0.0, "lr": 4.464628741285421e-05, "epoch": 94.33333333333333, "percentage": 21.22, "elapsed_time": "0:57:43", "remaining_time": "3:34:14", "throughput": 686.51, "total_tokens": 2377680} {"current_steps": 8495, "total_steps": 40000, "loss": 0.0, "lr": 4.4640214620606754e-05, "epoch": 94.38888888888889, "percentage": 21.24, "elapsed_time": "0:57:45", "remaining_time": "3:34:11", "throughput": 686.53, "total_tokens": 2379104} {"current_steps": 8500, "total_steps": 40000, "loss": 0.0, "lr": 4.46341387995914e-05, "epoch": 94.44444444444444, "percentage": 21.25, "elapsed_time": "0:57:47", "remaining_time": "3:34:09", "throughput": 686.55, "total_tokens": 2380512} {"current_steps": 8505, "total_steps": 40000, "loss": 0.0, "lr": 4.4628059950745106e-05, "epoch": 94.5, "percentage": 21.26, "elapsed_time": "0:57:49", "remaining_time": "3:34:07", "throughput": 686.58, "total_tokens": 2381936} {"current_steps": 8510, "total_steps": 40000, "loss": 0.0, "lr": 4.4621978075005297e-05, "epoch": 94.55555555555556, "percentage": 21.27, "elapsed_time": "0:57:51", "remaining_time": "3:34:04", "throughput": 686.59, "total_tokens": 2383296} {"current_steps": 8515, "total_steps": 40000, "loss": 0.0, "lr": 4.461589317330989e-05, "epoch": 94.61111111111111, "percentage": 21.29, "elapsed_time": "0:57:53", "remaining_time": "3:34:02", "throughput": 686.62, "total_tokens": 2384736} {"current_steps": 8520, "total_steps": 40000, "loss": 0.0, "lr": 4.460980524659724e-05, "epoch": 94.66666666666667, "percentage": 21.3, "elapsed_time": "0:57:55", "remaining_time": "3:33:59", "throughput": 686.65, "total_tokens": 2386192} {"current_steps": 8525, "total_steps": 40000, "loss": 0.0, "lr": 4.46037142958062e-05, "epoch": 94.72222222222223, "percentage": 21.31, "elapsed_time": "0:57:57", "remaining_time": "3:33:57", "throughput": 686.67, "total_tokens": 2387584} {"current_steps": 8530, "total_steps": 40000, "loss": 0.0, "lr": 4.4597620321876046e-05, "epoch": 94.77777777777777, "percentage": 21.32, "elapsed_time": "0:57:58", "remaining_time": "3:33:55", "throughput": 686.69, "total_tokens": 2388976} {"current_steps": 8535, "total_steps": 40000, "loss": 0.0, "lr": 4.459152332574656e-05, "epoch": 94.83333333333333, "percentage": 21.34, "elapsed_time": "0:58:00", "remaining_time": "3:33:52", "throughput": 686.7, "total_tokens": 2390368} {"current_steps": 8540, "total_steps": 40000, "loss": 0.0, "lr": 4.4585423308357985e-05, "epoch": 94.88888888888889, "percentage": 21.35, "elapsed_time": "0:58:02", "remaining_time": "3:33:50", "throughput": 686.73, "total_tokens": 2391792} {"current_steps": 8545, "total_steps": 40000, "loss": 0.0, "lr": 4.457932027065102e-05, "epoch": 94.94444444444444, "percentage": 21.36, "elapsed_time": "0:58:04", "remaining_time": "3:33:47", "throughput": 686.75, "total_tokens": 2393200} {"current_steps": 8550, "total_steps": 40000, "loss": 0.0, "lr": 4.45732142135668e-05, "epoch": 95.0, "percentage": 21.38, "elapsed_time": "0:58:06", "remaining_time": "3:33:46", "throughput": 686.74, "total_tokens": 2394624} {"current_steps": 8555, "total_steps": 40000, "loss": 0.0, "lr": 4.4567105138046986e-05, "epoch": 95.05555555555556, "percentage": 21.39, "elapsed_time": "0:58:09", "remaining_time": "3:33:44", "throughput": 686.72, "total_tokens": 2396048} {"current_steps": 8560, "total_steps": 40000, "loss": 0.0, "lr": 4.456099304503365e-05, "epoch": 95.11111111111111, "percentage": 21.4, "elapsed_time": "0:58:11", "remaining_time": "3:33:42", "throughput": 686.74, "total_tokens": 2397456} {"current_steps": 8565, "total_steps": 40000, "loss": 0.0, "lr": 4.455487793546939e-05, "epoch": 95.16666666666667, "percentage": 21.41, "elapsed_time": "0:58:13", "remaining_time": "3:33:39", "throughput": 686.76, "total_tokens": 2398864} {"current_steps": 8570, "total_steps": 40000, "loss": 0.0, "lr": 4.454875981029719e-05, "epoch": 95.22222222222223, "percentage": 21.43, "elapsed_time": "0:58:14", "remaining_time": "3:33:37", "throughput": 686.77, "total_tokens": 2400240} {"current_steps": 8575, "total_steps": 40000, "loss": 0.0, "lr": 4.454263867046057e-05, "epoch": 95.27777777777777, "percentage": 21.44, "elapsed_time": "0:58:16", "remaining_time": "3:33:35", "throughput": 686.79, "total_tokens": 2401648} {"current_steps": 8580, "total_steps": 40000, "loss": 0.0, "lr": 4.4536514516903484e-05, "epoch": 95.33333333333333, "percentage": 21.45, "elapsed_time": "0:58:18", "remaining_time": "3:33:32", "throughput": 686.81, "total_tokens": 2403056} {"current_steps": 8585, "total_steps": 40000, "loss": 0.0, "lr": 4.453038735057034e-05, "epoch": 95.38888888888889, "percentage": 21.46, "elapsed_time": "0:58:20", "remaining_time": "3:33:30", "throughput": 686.81, "total_tokens": 2404400} {"current_steps": 8590, "total_steps": 40000, "loss": 0.0, "lr": 4.4524257172406034e-05, "epoch": 95.44444444444444, "percentage": 21.48, "elapsed_time": "0:58:22", "remaining_time": "3:33:28", "throughput": 686.83, "total_tokens": 2405824} {"current_steps": 8595, "total_steps": 40000, "loss": 0.0, "lr": 4.451812398335592e-05, "epoch": 95.5, "percentage": 21.49, "elapsed_time": "0:58:24", "remaining_time": "3:33:25", "throughput": 686.86, "total_tokens": 2407232} {"current_steps": 8600, "total_steps": 40000, "loss": 0.0, "lr": 4.4511987784365805e-05, "epoch": 95.55555555555556, "percentage": 21.5, "elapsed_time": "0:58:26", "remaining_time": "3:33:23", "throughput": 686.88, "total_tokens": 2408640} {"current_steps": 8600, "total_steps": 40000, "eval_loss": 0.2896016240119934, "epoch": 95.55555555555556, "percentage": 21.5, "elapsed_time": "0:58:27", "remaining_time": "3:33:28", "throughput": 686.62, "total_tokens": 2408640} {"current_steps": 8605, "total_steps": 40000, "loss": 0.0, "lr": 4.450584857638197e-05, "epoch": 95.61111111111111, "percentage": 21.51, "elapsed_time": "0:58:31", "remaining_time": "3:33:30", "throughput": 686.37, "total_tokens": 2410048} {"current_steps": 8610, "total_steps": 40000, "loss": 0.0, "lr": 4.449970636035116e-05, "epoch": 95.66666666666667, "percentage": 21.52, "elapsed_time": "0:58:33", "remaining_time": "3:33:28", "throughput": 686.37, "total_tokens": 2411440} {"current_steps": 8615, "total_steps": 40000, "loss": 0.0, "lr": 4.4493561137220574e-05, "epoch": 95.72222222222223, "percentage": 21.54, "elapsed_time": "0:58:35", "remaining_time": "3:33:26", "throughput": 686.39, "total_tokens": 2412848} {"current_steps": 8620, "total_steps": 40000, "loss": 0.0, "lr": 4.44874129079379e-05, "epoch": 95.77777777777777, "percentage": 21.55, "elapsed_time": "0:58:37", "remaining_time": "3:33:23", "throughput": 686.42, "total_tokens": 2414272} {"current_steps": 8625, "total_steps": 40000, "loss": 0.0, "lr": 4.4481261673451255e-05, "epoch": 95.83333333333333, "percentage": 21.56, "elapsed_time": "0:58:39", "remaining_time": "3:33:21", "throughput": 686.44, "total_tokens": 2415680} {"current_steps": 8630, "total_steps": 40000, "loss": 0.0, "lr": 4.4475107434709245e-05, "epoch": 95.88888888888889, "percentage": 21.57, "elapsed_time": "0:58:41", "remaining_time": "3:33:19", "throughput": 686.47, "total_tokens": 2417104} {"current_steps": 8635, "total_steps": 40000, "loss": 0.0, "lr": 4.446895019266093e-05, "epoch": 95.94444444444444, "percentage": 21.59, "elapsed_time": "0:58:43", "remaining_time": "3:33:16", "throughput": 686.5, "total_tokens": 2418544} {"current_steps": 8640, "total_steps": 40000, "loss": 0.0, "lr": 4.446278994825583e-05, "epoch": 96.0, "percentage": 21.6, "elapsed_time": "0:58:45", "remaining_time": "3:33:15", "throughput": 686.47, "total_tokens": 2419920} {"current_steps": 8645, "total_steps": 40000, "loss": 0.0, "lr": 4.445662670244394e-05, "epoch": 96.05555555555556, "percentage": 21.61, "elapsed_time": "0:58:47", "remaining_time": "3:33:13", "throughput": 686.44, "total_tokens": 2421312} {"current_steps": 8650, "total_steps": 40000, "loss": 0.0, "lr": 4.44504604561757e-05, "epoch": 96.11111111111111, "percentage": 21.62, "elapsed_time": "0:58:49", "remaining_time": "3:33:11", "throughput": 686.44, "total_tokens": 2422656} {"current_steps": 8655, "total_steps": 40000, "loss": 0.0, "lr": 4.4444291210402035e-05, "epoch": 96.16666666666667, "percentage": 21.64, "elapsed_time": "0:58:51", "remaining_time": "3:33:08", "throughput": 686.46, "total_tokens": 2424064} {"current_steps": 8660, "total_steps": 40000, "loss": 0.0, "lr": 4.443811896607431e-05, "epoch": 96.22222222222223, "percentage": 21.65, "elapsed_time": "0:58:53", "remaining_time": "3:33:06", "throughput": 686.46, "total_tokens": 2425424} {"current_steps": 8665, "total_steps": 40000, "loss": 0.0, "lr": 4.443194372414436e-05, "epoch": 96.27777777777777, "percentage": 21.66, "elapsed_time": "0:58:55", "remaining_time": "3:33:04", "throughput": 686.5, "total_tokens": 2426880} {"current_steps": 8670, "total_steps": 40000, "loss": 0.0, "lr": 4.442576548556449e-05, "epoch": 96.33333333333333, "percentage": 21.68, "elapsed_time": "0:58:57", "remaining_time": "3:33:01", "throughput": 686.51, "total_tokens": 2428272} {"current_steps": 8675, "total_steps": 40000, "loss": 0.0, "lr": 4.441958425128747e-05, "epoch": 96.38888888888889, "percentage": 21.69, "elapsed_time": "0:58:59", "remaining_time": "3:32:59", "throughput": 686.53, "total_tokens": 2429648} {"current_steps": 8680, "total_steps": 40000, "loss": 0.0, "lr": 4.4413400022266515e-05, "epoch": 96.44444444444444, "percentage": 21.7, "elapsed_time": "0:59:00", "remaining_time": "3:32:56", "throughput": 686.54, "total_tokens": 2431040} {"current_steps": 8685, "total_steps": 40000, "loss": 0.0, "lr": 4.4407212799455313e-05, "epoch": 96.5, "percentage": 21.71, "elapsed_time": "0:59:02", "remaining_time": "3:32:54", "throughput": 686.55, "total_tokens": 2432416} {"current_steps": 8690, "total_steps": 40000, "loss": 0.0, "lr": 4.4401022583808003e-05, "epoch": 96.55555555555556, "percentage": 21.73, "elapsed_time": "0:59:04", "remaining_time": "3:32:52", "throughput": 686.58, "total_tokens": 2433824} {"current_steps": 8695, "total_steps": 40000, "loss": 0.0, "lr": 4.439482937627921e-05, "epoch": 96.61111111111111, "percentage": 21.74, "elapsed_time": "0:59:06", "remaining_time": "3:32:49", "throughput": 686.6, "total_tokens": 2435248} {"current_steps": 8700, "total_steps": 40000, "loss": 0.0, "lr": 4.4388633177824004e-05, "epoch": 96.66666666666667, "percentage": 21.75, "elapsed_time": "0:59:08", "remaining_time": "3:32:47", "throughput": 686.64, "total_tokens": 2436704} {"current_steps": 8705, "total_steps": 40000, "loss": 0.0, "lr": 4.4382433989397895e-05, "epoch": 96.72222222222223, "percentage": 21.76, "elapsed_time": "0:59:10", "remaining_time": "3:32:44", "throughput": 686.66, "total_tokens": 2438112} {"current_steps": 8710, "total_steps": 40000, "loss": 0.0, "lr": 4.4376231811956895e-05, "epoch": 96.77777777777777, "percentage": 21.77, "elapsed_time": "0:59:12", "remaining_time": "3:32:42", "throughput": 686.68, "total_tokens": 2439520} {"current_steps": 8715, "total_steps": 40000, "loss": 0.0, "lr": 4.437002664645745e-05, "epoch": 96.83333333333333, "percentage": 21.79, "elapsed_time": "0:59:14", "remaining_time": "3:32:40", "throughput": 686.69, "total_tokens": 2440880} {"current_steps": 8720, "total_steps": 40000, "loss": 0.0, "lr": 4.436381849385649e-05, "epoch": 96.88888888888889, "percentage": 21.8, "elapsed_time": "0:59:16", "remaining_time": "3:32:37", "throughput": 686.7, "total_tokens": 2442272} {"current_steps": 8725, "total_steps": 40000, "loss": 0.0, "lr": 4.435760735511136e-05, "epoch": 96.94444444444444, "percentage": 21.81, "elapsed_time": "0:59:18", "remaining_time": "3:32:35", "throughput": 686.71, "total_tokens": 2443648} {"current_steps": 8730, "total_steps": 40000, "loss": 0.0, "lr": 4.435139323117992e-05, "epoch": 97.0, "percentage": 21.82, "elapsed_time": "0:59:20", "remaining_time": "3:32:33", "throughput": 686.7, "total_tokens": 2445072} {"current_steps": 8735, "total_steps": 40000, "loss": 0.0, "lr": 4.434517612302046e-05, "epoch": 97.05555555555556, "percentage": 21.84, "elapsed_time": "0:59:22", "remaining_time": "3:32:32", "throughput": 686.68, "total_tokens": 2446512} {"current_steps": 8740, "total_steps": 40000, "loss": 0.0, "lr": 4.433895603159174e-05, "epoch": 97.11111111111111, "percentage": 21.85, "elapsed_time": "0:59:24", "remaining_time": "3:32:29", "throughput": 686.7, "total_tokens": 2447920} {"current_steps": 8745, "total_steps": 40000, "loss": 0.0, "lr": 4.433273295785296e-05, "epoch": 97.16666666666667, "percentage": 21.86, "elapsed_time": "0:59:26", "remaining_time": "3:32:27", "throughput": 686.72, "total_tokens": 2449328} {"current_steps": 8750, "total_steps": 40000, "loss": 0.0, "lr": 4.432650690276382e-05, "epoch": 97.22222222222223, "percentage": 21.88, "elapsed_time": "0:59:28", "remaining_time": "3:32:25", "throughput": 686.75, "total_tokens": 2450752} {"current_steps": 8755, "total_steps": 40000, "loss": 0.0, "lr": 4.4320277867284435e-05, "epoch": 97.27777777777777, "percentage": 21.89, "elapsed_time": "0:59:30", "remaining_time": "3:32:22", "throughput": 686.77, "total_tokens": 2452176} {"current_steps": 8760, "total_steps": 40000, "loss": 0.0, "lr": 4.431404585237541e-05, "epoch": 97.33333333333333, "percentage": 21.9, "elapsed_time": "0:59:32", "remaining_time": "3:32:20", "throughput": 686.78, "total_tokens": 2453552} {"current_steps": 8765, "total_steps": 40000, "loss": 0.0, "lr": 4.43078108589978e-05, "epoch": 97.38888888888889, "percentage": 21.91, "elapsed_time": "0:59:34", "remaining_time": "3:32:17", "throughput": 686.8, "total_tokens": 2454928} {"current_steps": 8770, "total_steps": 40000, "loss": 0.0, "lr": 4.4301572888113116e-05, "epoch": 97.44444444444444, "percentage": 21.93, "elapsed_time": "0:59:36", "remaining_time": "3:32:15", "throughput": 686.83, "total_tokens": 2456368} {"current_steps": 8775, "total_steps": 40000, "loss": 0.0, "lr": 4.4295331940683337e-05, "epoch": 97.5, "percentage": 21.94, "elapsed_time": "0:59:38", "remaining_time": "3:32:13", "throughput": 686.84, "total_tokens": 2457744} {"current_steps": 8780, "total_steps": 40000, "loss": 0.0, "lr": 4.428908801767089e-05, "epoch": 97.55555555555556, "percentage": 21.95, "elapsed_time": "0:59:40", "remaining_time": "3:32:10", "throughput": 686.86, "total_tokens": 2459152} {"current_steps": 8785, "total_steps": 40000, "loss": 0.0, "lr": 4.428284112003868e-05, "epoch": 97.61111111111111, "percentage": 21.96, "elapsed_time": "0:59:42", "remaining_time": "3:32:08", "throughput": 686.87, "total_tokens": 2460496} {"current_steps": 8790, "total_steps": 40000, "loss": 0.0, "lr": 4.4276591248750033e-05, "epoch": 97.66666666666667, "percentage": 21.98, "elapsed_time": "0:59:44", "remaining_time": "3:32:05", "throughput": 686.89, "total_tokens": 2461920} {"current_steps": 8795, "total_steps": 40000, "loss": 0.0, "lr": 4.4270338404768774e-05, "epoch": 97.72222222222223, "percentage": 21.99, "elapsed_time": "0:59:46", "remaining_time": "3:32:03", "throughput": 686.9, "total_tokens": 2463312} {"current_steps": 8800, "total_steps": 40000, "loss": 0.0, "lr": 4.426408258905917e-05, "epoch": 97.77777777777777, "percentage": 22.0, "elapsed_time": "0:59:48", "remaining_time": "3:32:01", "throughput": 686.91, "total_tokens": 2464672} {"current_steps": 8800, "total_steps": 40000, "eval_loss": 0.3003152906894684, "epoch": 97.77777777777777, "percentage": 22.0, "elapsed_time": "0:59:49", "remaining_time": "3:32:05", "throughput": 686.66, "total_tokens": 2464672} {"current_steps": 8805, "total_steps": 40000, "loss": 0.0, "lr": 4.425782380258594e-05, "epoch": 97.83333333333333, "percentage": 22.01, "elapsed_time": "0:59:52", "remaining_time": "3:32:08", "throughput": 686.42, "total_tokens": 2466080} {"current_steps": 8810, "total_steps": 40000, "loss": 0.0, "lr": 4.425156204631427e-05, "epoch": 97.88888888888889, "percentage": 22.02, "elapsed_time": "0:59:54", "remaining_time": "3:32:06", "throughput": 686.43, "total_tokens": 2467488} {"current_steps": 8815, "total_steps": 40000, "loss": 0.0, "lr": 4.424529732120981e-05, "epoch": 97.94444444444444, "percentage": 22.04, "elapsed_time": "0:59:56", "remaining_time": "3:32:03", "throughput": 686.45, "total_tokens": 2468896} {"current_steps": 8820, "total_steps": 40000, "loss": 0.0, "lr": 4.423902962823864e-05, "epoch": 98.0, "percentage": 22.05, "elapsed_time": "0:59:58", "remaining_time": "3:32:01", "throughput": 686.44, "total_tokens": 2470304} {"current_steps": 8825, "total_steps": 40000, "loss": 0.0, "lr": 4.423275896836733e-05, "epoch": 98.05555555555556, "percentage": 22.06, "elapsed_time": "1:00:00", "remaining_time": "3:32:00", "throughput": 686.4, "total_tokens": 2471696} {"current_steps": 8830, "total_steps": 40000, "loss": 0.0, "lr": 4.42264853425629e-05, "epoch": 98.11111111111111, "percentage": 22.07, "elapsed_time": "1:00:02", "remaining_time": "3:31:58", "throughput": 686.42, "total_tokens": 2473088} {"current_steps": 8835, "total_steps": 40000, "loss": 0.0, "lr": 4.4220208751792816e-05, "epoch": 98.16666666666667, "percentage": 22.09, "elapsed_time": "1:00:04", "remaining_time": "3:31:55", "throughput": 686.44, "total_tokens": 2474496} {"current_steps": 8840, "total_steps": 40000, "loss": 0.0, "lr": 4.421392919702499e-05, "epoch": 98.22222222222223, "percentage": 22.1, "elapsed_time": "1:00:06", "remaining_time": "3:31:53", "throughput": 686.45, "total_tokens": 2475888} {"current_steps": 8845, "total_steps": 40000, "loss": 0.0, "lr": 4.4207646679227846e-05, "epoch": 98.27777777777777, "percentage": 22.11, "elapsed_time": "1:00:08", "remaining_time": "3:31:51", "throughput": 686.47, "total_tokens": 2477296} {"current_steps": 8850, "total_steps": 40000, "loss": 0.0, "lr": 4.42013611993702e-05, "epoch": 98.33333333333333, "percentage": 22.12, "elapsed_time": "1:00:10", "remaining_time": "3:31:48", "throughput": 686.5, "total_tokens": 2478736} {"current_steps": 8855, "total_steps": 40000, "loss": 0.0, "lr": 4.419507275842135e-05, "epoch": 98.38888888888889, "percentage": 22.14, "elapsed_time": "1:00:12", "remaining_time": "3:31:46", "throughput": 686.51, "total_tokens": 2480112} {"current_steps": 8860, "total_steps": 40000, "loss": 0.0, "lr": 4.418878135735106e-05, "epoch": 98.44444444444444, "percentage": 22.15, "elapsed_time": "1:00:14", "remaining_time": "3:31:44", "throughput": 686.55, "total_tokens": 2481584} {"current_steps": 8865, "total_steps": 40000, "loss": 0.0, "lr": 4.418248699712955e-05, "epoch": 98.5, "percentage": 22.16, "elapsed_time": "1:00:16", "remaining_time": "3:31:41", "throughput": 686.56, "total_tokens": 2482960} {"current_steps": 8870, "total_steps": 40000, "loss": 0.0, "lr": 4.417618967872748e-05, "epoch": 98.55555555555556, "percentage": 22.18, "elapsed_time": "1:00:18", "remaining_time": "3:31:39", "throughput": 686.57, "total_tokens": 2484352} {"current_steps": 8875, "total_steps": 40000, "loss": 0.0, "lr": 4.4169889403115985e-05, "epoch": 98.61111111111111, "percentage": 22.19, "elapsed_time": "1:00:20", "remaining_time": "3:31:36", "throughput": 686.6, "total_tokens": 2485776} {"current_steps": 8880, "total_steps": 40000, "loss": 0.0, "lr": 4.4163586171266627e-05, "epoch": 98.66666666666667, "percentage": 22.2, "elapsed_time": "1:00:22", "remaining_time": "3:31:34", "throughput": 686.6, "total_tokens": 2487136} {"current_steps": 8885, "total_steps": 40000, "loss": 0.0, "lr": 4.415727998415147e-05, "epoch": 98.72222222222223, "percentage": 22.21, "elapsed_time": "1:00:24", "remaining_time": "3:31:32", "throughput": 686.63, "total_tokens": 2488560} {"current_steps": 8890, "total_steps": 40000, "loss": 0.0, "lr": 4.4150970842742985e-05, "epoch": 98.77777777777777, "percentage": 22.23, "elapsed_time": "1:00:26", "remaining_time": "3:31:31", "throughput": 686.58, "total_tokens": 2489984} {"current_steps": 8895, "total_steps": 40000, "loss": 0.0, "lr": 4.4144658748014134e-05, "epoch": 98.83333333333333, "percentage": 22.24, "elapsed_time": "1:00:28", "remaining_time": "3:31:28", "throughput": 686.6, "total_tokens": 2491376} {"current_steps": 8900, "total_steps": 40000, "loss": 0.0, "lr": 4.413834370093831e-05, "epoch": 98.88888888888889, "percentage": 22.25, "elapsed_time": "1:00:30", "remaining_time": "3:31:26", "throughput": 686.62, "total_tokens": 2492816} {"current_steps": 8905, "total_steps": 40000, "loss": 0.0, "lr": 4.413202570248939e-05, "epoch": 98.94444444444444, "percentage": 22.26, "elapsed_time": "1:00:32", "remaining_time": "3:31:24", "throughput": 686.63, "total_tokens": 2494176} {"current_steps": 8910, "total_steps": 40000, "loss": 0.0, "lr": 4.412570475364167e-05, "epoch": 99.0, "percentage": 22.27, "elapsed_time": "1:00:34", "remaining_time": "3:31:22", "throughput": 686.59, "total_tokens": 2495488} {"current_steps": 8915, "total_steps": 40000, "loss": 0.0, "lr": 4.411938085536994e-05, "epoch": 99.05555555555556, "percentage": 22.29, "elapsed_time": "1:00:36", "remaining_time": "3:31:21", "throughput": 686.55, "total_tokens": 2496880} {"current_steps": 8920, "total_steps": 40000, "loss": 0.0, "lr": 4.41130540086494e-05, "epoch": 99.11111111111111, "percentage": 22.3, "elapsed_time": "1:00:38", "remaining_time": "3:31:18", "throughput": 686.57, "total_tokens": 2498288} {"current_steps": 8925, "total_steps": 40000, "loss": 0.0, "lr": 4.4106724214455754e-05, "epoch": 99.16666666666667, "percentage": 22.31, "elapsed_time": "1:00:40", "remaining_time": "3:31:16", "throughput": 686.57, "total_tokens": 2499648} {"current_steps": 8930, "total_steps": 40000, "loss": 0.0, "lr": 4.4100391473765115e-05, "epoch": 99.22222222222223, "percentage": 22.32, "elapsed_time": "1:00:42", "remaining_time": "3:31:13", "throughput": 686.58, "total_tokens": 2501008} {"current_steps": 8935, "total_steps": 40000, "loss": 0.0, "lr": 4.409405578755408e-05, "epoch": 99.27777777777777, "percentage": 22.34, "elapsed_time": "1:00:44", "remaining_time": "3:31:11", "throughput": 686.6, "total_tokens": 2502416} {"current_steps": 8940, "total_steps": 40000, "loss": 0.0, "lr": 4.4087717156799705e-05, "epoch": 99.33333333333333, "percentage": 22.35, "elapsed_time": "1:00:46", "remaining_time": "3:31:09", "throughput": 686.61, "total_tokens": 2503808} {"current_steps": 8945, "total_steps": 40000, "loss": 0.0, "lr": 4.408137558247946e-05, "epoch": 99.38888888888889, "percentage": 22.36, "elapsed_time": "1:00:48", "remaining_time": "3:31:06", "throughput": 686.63, "total_tokens": 2505200} {"current_steps": 8950, "total_steps": 40000, "loss": 0.0, "lr": 4.4075031065571306e-05, "epoch": 99.44444444444444, "percentage": 22.38, "elapsed_time": "1:00:50", "remaining_time": "3:31:04", "throughput": 686.65, "total_tokens": 2506608} {"current_steps": 8955, "total_steps": 40000, "loss": 0.0, "lr": 4.406868360705366e-05, "epoch": 99.5, "percentage": 22.39, "elapsed_time": "1:00:52", "remaining_time": "3:31:02", "throughput": 686.67, "total_tokens": 2508000} {"current_steps": 8960, "total_steps": 40000, "loss": 0.0, "lr": 4.406233320790536e-05, "epoch": 99.55555555555556, "percentage": 22.4, "elapsed_time": "1:00:54", "remaining_time": "3:30:59", "throughput": 686.7, "total_tokens": 2509440} {"current_steps": 8965, "total_steps": 40000, "loss": 0.0, "lr": 4.4055979869105734e-05, "epoch": 99.61111111111111, "percentage": 22.41, "elapsed_time": "1:00:56", "remaining_time": "3:30:57", "throughput": 686.72, "total_tokens": 2510864} {"current_steps": 8970, "total_steps": 40000, "loss": 0.0, "lr": 4.404962359163454e-05, "epoch": 99.66666666666667, "percentage": 22.43, "elapsed_time": "1:00:58", "remaining_time": "3:30:55", "throughput": 686.74, "total_tokens": 2512272} {"current_steps": 8975, "total_steps": 40000, "loss": 0.0, "lr": 4.404326437647199e-05, "epoch": 99.72222222222223, "percentage": 22.44, "elapsed_time": "1:01:00", "remaining_time": "3:30:52", "throughput": 686.76, "total_tokens": 2513680} {"current_steps": 8980, "total_steps": 40000, "loss": 0.0, "lr": 4.403690222459877e-05, "epoch": 99.77777777777777, "percentage": 22.45, "elapsed_time": "1:01:02", "remaining_time": "3:30:50", "throughput": 686.77, "total_tokens": 2515056} {"current_steps": 8985, "total_steps": 40000, "loss": 0.0, "lr": 4.4030537136995984e-05, "epoch": 99.83333333333333, "percentage": 22.46, "elapsed_time": "1:01:04", "remaining_time": "3:30:47", "throughput": 686.79, "total_tokens": 2516464} {"current_steps": 8990, "total_steps": 40000, "loss": 0.0, "lr": 4.402416911464523e-05, "epoch": 99.88888888888889, "percentage": 22.48, "elapsed_time": "1:01:06", "remaining_time": "3:30:45", "throughput": 686.82, "total_tokens": 2517888} {"current_steps": 8995, "total_steps": 40000, "loss": 0.0, "lr": 4.4017798158528516e-05, "epoch": 99.94444444444444, "percentage": 22.49, "elapsed_time": "1:01:07", "remaining_time": "3:30:43", "throughput": 686.84, "total_tokens": 2519312} {"current_steps": 9000, "total_steps": 40000, "loss": 0.0, "lr": 4.401142426962834e-05, "epoch": 100.0, "percentage": 22.5, "elapsed_time": "1:01:10", "remaining_time": "3:30:41", "throughput": 686.82, "total_tokens": 2520688} {"current_steps": 9000, "total_steps": 40000, "eval_loss": 0.2869197726249695, "epoch": 100.0, "percentage": 22.5, "elapsed_time": "1:01:11", "remaining_time": "3:30:45", "throughput": 686.58, "total_tokens": 2520688} {"current_steps": 9005, "total_steps": 40000, "loss": 0.0, "lr": 4.400504744892763e-05, "epoch": 100.05555555555556, "percentage": 22.51, "elapsed_time": "1:01:14", "remaining_time": "3:30:48", "throughput": 686.31, "total_tokens": 2522112} {"current_steps": 9010, "total_steps": 40000, "loss": 0.0, "lr": 4.399866769740975e-05, "epoch": 100.11111111111111, "percentage": 22.53, "elapsed_time": "1:01:16", "remaining_time": "3:30:46", "throughput": 686.32, "total_tokens": 2523552} {"current_steps": 9015, "total_steps": 40000, "loss": 0.0, "lr": 4.399228501605859e-05, "epoch": 100.16666666666667, "percentage": 22.54, "elapsed_time": "1:01:18", "remaining_time": "3:30:44", "throughput": 686.34, "total_tokens": 2524960} {"current_steps": 9020, "total_steps": 40000, "loss": 0.0, "lr": 4.398589940585839e-05, "epoch": 100.22222222222223, "percentage": 22.55, "elapsed_time": "1:01:20", "remaining_time": "3:30:42", "throughput": 686.35, "total_tokens": 2526336} {"current_steps": 9025, "total_steps": 40000, "loss": 0.0, "lr": 4.3979510867793917e-05, "epoch": 100.27777777777777, "percentage": 22.56, "elapsed_time": "1:01:22", "remaining_time": "3:30:39", "throughput": 686.38, "total_tokens": 2527760} {"current_steps": 9030, "total_steps": 40000, "loss": 0.0, "lr": 4.3973119402850346e-05, "epoch": 100.33333333333333, "percentage": 22.57, "elapsed_time": "1:01:24", "remaining_time": "3:30:37", "throughput": 686.38, "total_tokens": 2529152} {"current_steps": 9035, "total_steps": 40000, "loss": 0.0, "lr": 4.396672501201334e-05, "epoch": 100.38888888888889, "percentage": 22.59, "elapsed_time": "1:01:26", "remaining_time": "3:30:35", "throughput": 686.4, "total_tokens": 2530560} {"current_steps": 9040, "total_steps": 40000, "loss": 0.0, "lr": 4.396032769626899e-05, "epoch": 100.44444444444444, "percentage": 22.6, "elapsed_time": "1:01:28", "remaining_time": "3:30:32", "throughput": 686.41, "total_tokens": 2531936} {"current_steps": 9045, "total_steps": 40000, "loss": 0.0, "lr": 4.395392745660384e-05, "epoch": 100.5, "percentage": 22.61, "elapsed_time": "1:01:30", "remaining_time": "3:30:30", "throughput": 686.42, "total_tokens": 2533328} {"current_steps": 9050, "total_steps": 40000, "loss": 0.0, "lr": 4.394752429400488e-05, "epoch": 100.55555555555556, "percentage": 22.62, "elapsed_time": "1:01:32", "remaining_time": "3:30:28", "throughput": 686.42, "total_tokens": 2534672} {"current_steps": 9055, "total_steps": 40000, "loss": 0.0, "lr": 4.394111820945957e-05, "epoch": 100.61111111111111, "percentage": 22.64, "elapsed_time": "1:01:34", "remaining_time": "3:30:25", "throughput": 686.43, "total_tokens": 2536032} {"current_steps": 9060, "total_steps": 40000, "loss": 0.0, "lr": 4.393470920395579e-05, "epoch": 100.66666666666667, "percentage": 22.65, "elapsed_time": "1:01:36", "remaining_time": "3:30:23", "throughput": 686.44, "total_tokens": 2537408} {"current_steps": 9065, "total_steps": 40000, "loss": 0.0, "lr": 4.392829727848192e-05, "epoch": 100.72222222222223, "percentage": 22.66, "elapsed_time": "1:01:38", "remaining_time": "3:30:21", "throughput": 686.45, "total_tokens": 2538800} {"current_steps": 9070, "total_steps": 40000, "loss": 0.0, "lr": 4.392188243402673e-05, "epoch": 100.77777777777777, "percentage": 22.68, "elapsed_time": "1:01:40", "remaining_time": "3:30:18", "throughput": 686.48, "total_tokens": 2540224} {"current_steps": 9075, "total_steps": 40000, "loss": 0.0, "lr": 4.391546467157949e-05, "epoch": 100.83333333333333, "percentage": 22.69, "elapsed_time": "1:01:42", "remaining_time": "3:30:16", "throughput": 686.5, "total_tokens": 2541632} {"current_steps": 9080, "total_steps": 40000, "loss": 0.0, "lr": 4.390904399212988e-05, "epoch": 100.88888888888889, "percentage": 22.7, "elapsed_time": "1:01:44", "remaining_time": "3:30:14", "throughput": 686.51, "total_tokens": 2543008} {"current_steps": 9085, "total_steps": 40000, "loss": 0.0, "lr": 4.390262039666807e-05, "epoch": 100.94444444444444, "percentage": 22.71, "elapsed_time": "1:01:46", "remaining_time": "3:30:11", "throughput": 686.53, "total_tokens": 2544416} {"current_steps": 9090, "total_steps": 40000, "loss": 0.0, "lr": 4.389619388618464e-05, "epoch": 101.0, "percentage": 22.73, "elapsed_time": "1:01:48", "remaining_time": "3:30:10", "throughput": 686.51, "total_tokens": 2545824} {"current_steps": 9095, "total_steps": 40000, "loss": 0.0, "lr": 4.3889764461670655e-05, "epoch": 101.05555555555556, "percentage": 22.74, "elapsed_time": "1:01:50", "remaining_time": "3:30:08", "throughput": 686.48, "total_tokens": 2547216} {"current_steps": 9100, "total_steps": 40000, "loss": 0.0, "lr": 4.38833321241176e-05, "epoch": 101.11111111111111, "percentage": 22.75, "elapsed_time": "1:01:52", "remaining_time": "3:30:06", "throughput": 686.49, "total_tokens": 2548608} {"current_steps": 9105, "total_steps": 40000, "loss": 0.0, "lr": 4.3876896874517434e-05, "epoch": 101.16666666666667, "percentage": 22.76, "elapsed_time": "1:01:54", "remaining_time": "3:30:03", "throughput": 686.52, "total_tokens": 2550032} {"current_steps": 9110, "total_steps": 40000, "loss": 0.0, "lr": 4.3870458713862554e-05, "epoch": 101.22222222222223, "percentage": 22.78, "elapsed_time": "1:01:56", "remaining_time": "3:30:01", "throughput": 686.54, "total_tokens": 2551440} {"current_steps": 9115, "total_steps": 40000, "loss": 0.0, "lr": 4.386401764314579e-05, "epoch": 101.27777777777777, "percentage": 22.79, "elapsed_time": "1:01:58", "remaining_time": "3:29:59", "throughput": 686.54, "total_tokens": 2552800} {"current_steps": 9120, "total_steps": 40000, "loss": 0.0, "lr": 4.385757366336045e-05, "epoch": 101.33333333333333, "percentage": 22.8, "elapsed_time": "1:02:00", "remaining_time": "3:29:56", "throughput": 686.57, "total_tokens": 2554240} {"current_steps": 9125, "total_steps": 40000, "loss": 0.0, "lr": 4.385112677550027e-05, "epoch": 101.38888888888889, "percentage": 22.81, "elapsed_time": "1:02:02", "remaining_time": "3:29:54", "throughput": 686.59, "total_tokens": 2555664} {"current_steps": 9130, "total_steps": 40000, "loss": 0.0, "lr": 4.384467698055945e-05, "epoch": 101.44444444444444, "percentage": 22.82, "elapsed_time": "1:02:04", "remaining_time": "3:29:52", "throughput": 686.61, "total_tokens": 2557056} {"current_steps": 9135, "total_steps": 40000, "loss": 0.0, "lr": 4.383822427953261e-05, "epoch": 101.5, "percentage": 22.84, "elapsed_time": "1:02:06", "remaining_time": "3:29:49", "throughput": 686.63, "total_tokens": 2558464} {"current_steps": 9140, "total_steps": 40000, "loss": 0.0, "lr": 4.3831768673414864e-05, "epoch": 101.55555555555556, "percentage": 22.85, "elapsed_time": "1:02:08", "remaining_time": "3:29:47", "throughput": 686.64, "total_tokens": 2559856} {"current_steps": 9145, "total_steps": 40000, "loss": 0.0, "lr": 4.382531016320173e-05, "epoch": 101.61111111111111, "percentage": 22.86, "elapsed_time": "1:02:10", "remaining_time": "3:29:45", "throughput": 686.65, "total_tokens": 2561232} {"current_steps": 9150, "total_steps": 40000, "loss": 0.0, "lr": 4.3818848749889184e-05, "epoch": 101.66666666666667, "percentage": 22.88, "elapsed_time": "1:02:11", "remaining_time": "3:29:42", "throughput": 686.68, "total_tokens": 2562672} {"current_steps": 9155, "total_steps": 40000, "loss": 0.0, "lr": 4.381238443447368e-05, "epoch": 101.72222222222223, "percentage": 22.89, "elapsed_time": "1:02:13", "remaining_time": "3:29:40", "throughput": 686.69, "total_tokens": 2564048} {"current_steps": 9160, "total_steps": 40000, "loss": 0.0, "lr": 4.380591721795208e-05, "epoch": 101.77777777777777, "percentage": 22.9, "elapsed_time": "1:02:15", "remaining_time": "3:29:37", "throughput": 686.7, "total_tokens": 2565424} {"current_steps": 9165, "total_steps": 40000, "loss": 0.0, "lr": 4.3799447101321723e-05, "epoch": 101.83333333333333, "percentage": 22.91, "elapsed_time": "1:02:17", "remaining_time": "3:29:35", "throughput": 686.74, "total_tokens": 2566896} {"current_steps": 9170, "total_steps": 40000, "loss": 0.0, "lr": 4.379297408558036e-05, "epoch": 101.88888888888889, "percentage": 22.93, "elapsed_time": "1:02:19", "remaining_time": "3:29:33", "throughput": 686.76, "total_tokens": 2568288} {"current_steps": 9175, "total_steps": 40000, "loss": 0.0, "lr": 4.378649817172624e-05, "epoch": 101.94444444444444, "percentage": 22.94, "elapsed_time": "1:02:21", "remaining_time": "3:29:30", "throughput": 686.76, "total_tokens": 2569664} {"current_steps": 9180, "total_steps": 40000, "loss": 0.0, "lr": 4.378001936075801e-05, "epoch": 102.0, "percentage": 22.95, "elapsed_time": "1:02:23", "remaining_time": "3:29:29", "throughput": 686.75, "total_tokens": 2571056} {"current_steps": 9185, "total_steps": 40000, "loss": 0.0, "lr": 4.377353765367479e-05, "epoch": 102.05555555555556, "percentage": 22.96, "elapsed_time": "1:02:25", "remaining_time": "3:29:27", "throughput": 686.73, "total_tokens": 2572496} {"current_steps": 9190, "total_steps": 40000, "loss": 0.0, "lr": 4.376705305147614e-05, "epoch": 102.11111111111111, "percentage": 22.98, "elapsed_time": "1:02:27", "remaining_time": "3:29:25", "throughput": 686.74, "total_tokens": 2573872} {"current_steps": 9195, "total_steps": 40000, "loss": 0.0, "lr": 4.376056555516206e-05, "epoch": 102.16666666666667, "percentage": 22.99, "elapsed_time": "1:02:29", "remaining_time": "3:29:22", "throughput": 686.76, "total_tokens": 2575280} {"current_steps": 9200, "total_steps": 40000, "loss": 0.0, "lr": 4.375407516573302e-05, "epoch": 102.22222222222223, "percentage": 23.0, "elapsed_time": "1:02:31", "remaining_time": "3:29:20", "throughput": 686.77, "total_tokens": 2576656} {"current_steps": 9200, "total_steps": 40000, "eval_loss": 0.30222058296203613, "epoch": 102.22222222222223, "percentage": 23.0, "elapsed_time": "1:02:33", "remaining_time": "3:29:24", "throughput": 686.53, "total_tokens": 2576656} {"current_steps": 9205, "total_steps": 40000, "loss": 0.0, "lr": 4.3747581884189913e-05, "epoch": 102.27777777777777, "percentage": 23.01, "elapsed_time": "1:02:36", "remaining_time": "3:29:26", "throughput": 686.31, "total_tokens": 2578032} {"current_steps": 9210, "total_steps": 40000, "loss": 0.0, "lr": 4.374108571153408e-05, "epoch": 102.33333333333333, "percentage": 23.03, "elapsed_time": "1:02:38", "remaining_time": "3:29:24", "throughput": 686.32, "total_tokens": 2579456} {"current_steps": 9215, "total_steps": 40000, "loss": 0.0, "lr": 4.3734586648767316e-05, "epoch": 102.38888888888889, "percentage": 23.04, "elapsed_time": "1:02:40", "remaining_time": "3:29:22", "throughput": 686.33, "total_tokens": 2580880} {"current_steps": 9220, "total_steps": 40000, "loss": 0.0, "lr": 4.372808469689186e-05, "epoch": 102.44444444444444, "percentage": 23.05, "elapsed_time": "1:02:42", "remaining_time": "3:29:20", "throughput": 686.35, "total_tokens": 2582304} {"current_steps": 9225, "total_steps": 40000, "loss": 0.0, "lr": 4.372157985691039e-05, "epoch": 102.5, "percentage": 23.06, "elapsed_time": "1:02:44", "remaining_time": "3:29:17", "throughput": 686.36, "total_tokens": 2583664} {"current_steps": 9230, "total_steps": 40000, "loss": 0.0, "lr": 4.371507212982603e-05, "epoch": 102.55555555555556, "percentage": 23.08, "elapsed_time": "1:02:46", "remaining_time": "3:29:15", "throughput": 686.39, "total_tokens": 2585136} {"current_steps": 9235, "total_steps": 40000, "loss": 0.0, "lr": 4.370856151664236e-05, "epoch": 102.61111111111111, "percentage": 23.09, "elapsed_time": "1:02:48", "remaining_time": "3:29:13", "throughput": 686.41, "total_tokens": 2586544} {"current_steps": 9240, "total_steps": 40000, "loss": 0.0, "lr": 4.3702048018363404e-05, "epoch": 102.66666666666667, "percentage": 23.1, "elapsed_time": "1:02:50", "remaining_time": "3:29:10", "throughput": 686.45, "total_tokens": 2588000} {"current_steps": 9245, "total_steps": 40000, "loss": 0.0, "lr": 4.369553163599362e-05, "epoch": 102.72222222222223, "percentage": 23.11, "elapsed_time": "1:02:52", "remaining_time": "3:29:08", "throughput": 686.45, "total_tokens": 2589344} {"current_steps": 9250, "total_steps": 40000, "loss": 0.0, "lr": 4.3689012370537904e-05, "epoch": 102.77777777777777, "percentage": 23.12, "elapsed_time": "1:02:54", "remaining_time": "3:29:06", "throughput": 686.47, "total_tokens": 2590736} {"current_steps": 9255, "total_steps": 40000, "loss": 0.0, "lr": 4.368249022300164e-05, "epoch": 102.83333333333333, "percentage": 23.14, "elapsed_time": "1:02:55", "remaining_time": "3:29:03", "throughput": 686.48, "total_tokens": 2592112} {"current_steps": 9260, "total_steps": 40000, "loss": 0.0, "lr": 4.367596519439059e-05, "epoch": 102.88888888888889, "percentage": 23.15, "elapsed_time": "1:02:57", "remaining_time": "3:29:01", "throughput": 686.49, "total_tokens": 2593520} {"current_steps": 9265, "total_steps": 40000, "loss": 0.0, "lr": 4.366943728571101e-05, "epoch": 102.94444444444444, "percentage": 23.16, "elapsed_time": "1:02:59", "remaining_time": "3:28:59", "throughput": 686.5, "total_tokens": 2594880} {"current_steps": 9270, "total_steps": 40000, "loss": 0.0, "lr": 4.366290649796959e-05, "epoch": 103.0, "percentage": 23.18, "elapsed_time": "1:03:01", "remaining_time": "3:28:57", "throughput": 686.48, "total_tokens": 2596256} {"current_steps": 9275, "total_steps": 40000, "loss": 0.0, "lr": 4.3656372832173456e-05, "epoch": 103.05555555555556, "percentage": 23.19, "elapsed_time": "1:03:04", "remaining_time": "3:28:55", "throughput": 686.45, "total_tokens": 2597648} {"current_steps": 9280, "total_steps": 40000, "loss": 0.0, "lr": 4.364983628933017e-05, "epoch": 103.11111111111111, "percentage": 23.2, "elapsed_time": "1:03:06", "remaining_time": "3:28:53", "throughput": 686.46, "total_tokens": 2599040} {"current_steps": 9285, "total_steps": 40000, "loss": 0.0, "lr": 4.364329687044777e-05, "epoch": 103.16666666666667, "percentage": 23.21, "elapsed_time": "1:03:08", "remaining_time": "3:28:51", "throughput": 686.49, "total_tokens": 2600464} {"current_steps": 9290, "total_steps": 40000, "loss": 0.0, "lr": 4.36367545765347e-05, "epoch": 103.22222222222223, "percentage": 23.23, "elapsed_time": "1:03:10", "remaining_time": "3:28:48", "throughput": 686.52, "total_tokens": 2601904} {"current_steps": 9295, "total_steps": 40000, "loss": 0.0, "lr": 4.363020940859988e-05, "epoch": 103.27777777777777, "percentage": 23.24, "elapsed_time": "1:03:11", "remaining_time": "3:28:46", "throughput": 686.54, "total_tokens": 2603328} {"current_steps": 9300, "total_steps": 40000, "loss": 0.0, "lr": 4.362366136765263e-05, "epoch": 103.33333333333333, "percentage": 23.25, "elapsed_time": "1:03:13", "remaining_time": "3:28:43", "throughput": 686.57, "total_tokens": 2604768} {"current_steps": 9305, "total_steps": 40000, "loss": 0.0, "lr": 4.361711045470278e-05, "epoch": 103.38888888888889, "percentage": 23.26, "elapsed_time": "1:03:15", "remaining_time": "3:28:41", "throughput": 686.57, "total_tokens": 2606112} {"current_steps": 9310, "total_steps": 40000, "loss": 0.0, "lr": 4.3610556670760524e-05, "epoch": 103.44444444444444, "percentage": 23.28, "elapsed_time": "1:03:17", "remaining_time": "3:28:39", "throughput": 686.59, "total_tokens": 2607520} {"current_steps": 9315, "total_steps": 40000, "loss": 0.0, "lr": 4.360400001683657e-05, "epoch": 103.5, "percentage": 23.29, "elapsed_time": "1:03:19", "remaining_time": "3:28:36", "throughput": 686.6, "total_tokens": 2608912} {"current_steps": 9320, "total_steps": 40000, "loss": 0.0, "lr": 4.3597440493942e-05, "epoch": 103.55555555555556, "percentage": 23.3, "elapsed_time": "1:03:21", "remaining_time": "3:28:34", "throughput": 686.64, "total_tokens": 2610368} {"current_steps": 9325, "total_steps": 40000, "loss": 0.0, "lr": 4.3590878103088405e-05, "epoch": 103.61111111111111, "percentage": 23.31, "elapsed_time": "1:03:23", "remaining_time": "3:28:32", "throughput": 686.66, "total_tokens": 2611792} {"current_steps": 9330, "total_steps": 40000, "loss": 0.0, "lr": 4.358431284528779e-05, "epoch": 103.66666666666667, "percentage": 23.33, "elapsed_time": "1:03:25", "remaining_time": "3:28:29", "throughput": 686.67, "total_tokens": 2613168} {"current_steps": 9335, "total_steps": 40000, "loss": 0.0, "lr": 4.357774472155257e-05, "epoch": 103.72222222222223, "percentage": 23.34, "elapsed_time": "1:03:27", "remaining_time": "3:28:27", "throughput": 686.68, "total_tokens": 2614528} {"current_steps": 9340, "total_steps": 40000, "loss": 0.0, "lr": 4.3571173732895664e-05, "epoch": 103.77777777777777, "percentage": 23.35, "elapsed_time": "1:03:29", "remaining_time": "3:28:25", "throughput": 686.69, "total_tokens": 2615920} {"current_steps": 9345, "total_steps": 40000, "loss": 0.0, "lr": 4.356459988033039e-05, "epoch": 103.83333333333333, "percentage": 23.36, "elapsed_time": "1:03:31", "remaining_time": "3:28:22", "throughput": 686.68, "total_tokens": 2617232} {"current_steps": 9350, "total_steps": 40000, "loss": 0.0, "lr": 4.355802316487051e-05, "epoch": 103.88888888888889, "percentage": 23.38, "elapsed_time": "1:03:33", "remaining_time": "3:28:20", "throughput": 686.69, "total_tokens": 2618608} {"current_steps": 9355, "total_steps": 40000, "loss": 0.0, "lr": 4.355144358753025e-05, "epoch": 103.94444444444444, "percentage": 23.39, "elapsed_time": "1:03:35", "remaining_time": "3:28:18", "throughput": 686.72, "total_tokens": 2620032} {"current_steps": 9360, "total_steps": 40000, "loss": 0.0, "lr": 4.354486114932425e-05, "epoch": 104.0, "percentage": 23.4, "elapsed_time": "1:03:37", "remaining_time": "3:28:16", "throughput": 686.71, "total_tokens": 2621424} {"current_steps": 9365, "total_steps": 40000, "loss": 0.0, "lr": 4.353827585126762e-05, "epoch": 104.05555555555556, "percentage": 23.41, "elapsed_time": "1:03:39", "remaining_time": "3:28:14", "throughput": 686.68, "total_tokens": 2622832} {"current_steps": 9370, "total_steps": 40000, "loss": 0.0, "lr": 4.353168769437588e-05, "epoch": 104.11111111111111, "percentage": 23.43, "elapsed_time": "1:03:41", "remaining_time": "3:28:12", "throughput": 686.72, "total_tokens": 2624320} {"current_steps": 9375, "total_steps": 40000, "loss": 0.0, "lr": 4.3525096679665014e-05, "epoch": 104.16666666666667, "percentage": 23.44, "elapsed_time": "1:03:43", "remaining_time": "3:28:10", "throughput": 686.73, "total_tokens": 2625680} {"current_steps": 9380, "total_steps": 40000, "loss": 0.0, "lr": 4.351850280815144e-05, "epoch": 104.22222222222223, "percentage": 23.45, "elapsed_time": "1:03:45", "remaining_time": "3:28:07", "throughput": 686.75, "total_tokens": 2627104} {"current_steps": 9385, "total_steps": 40000, "loss": 0.0, "lr": 4.3511906080852014e-05, "epoch": 104.27777777777777, "percentage": 23.46, "elapsed_time": "1:03:47", "remaining_time": "3:28:05", "throughput": 686.77, "total_tokens": 2628528} {"current_steps": 9390, "total_steps": 40000, "loss": 0.0, "lr": 4.350530649878404e-05, "epoch": 104.33333333333333, "percentage": 23.47, "elapsed_time": "1:03:49", "remaining_time": "3:28:03", "throughput": 686.78, "total_tokens": 2629920} {"current_steps": 9395, "total_steps": 40000, "loss": 0.0, "lr": 4.3498704062965246e-05, "epoch": 104.38888888888889, "percentage": 23.49, "elapsed_time": "1:03:51", "remaining_time": "3:28:00", "throughput": 686.8, "total_tokens": 2631328} {"current_steps": 9400, "total_steps": 40000, "loss": 0.0, "lr": 4.3492098774413815e-05, "epoch": 104.44444444444444, "percentage": 23.5, "elapsed_time": "1:03:53", "remaining_time": "3:27:58", "throughput": 686.81, "total_tokens": 2632720} {"current_steps": 9400, "total_steps": 40000, "eval_loss": 0.2932952344417572, "epoch": 104.44444444444444, "percentage": 23.5, "elapsed_time": "1:03:54", "remaining_time": "3:28:02", "throughput": 686.58, "total_tokens": 2632720} {"current_steps": 9405, "total_steps": 40000, "loss": 0.0, "lr": 4.3485490634148375e-05, "epoch": 104.5, "percentage": 23.51, "elapsed_time": "1:03:58", "remaining_time": "3:28:05", "throughput": 686.3, "total_tokens": 2634144} {"current_steps": 9410, "total_steps": 40000, "loss": 0.0, "lr": 4.347887964318797e-05, "epoch": 104.55555555555556, "percentage": 23.52, "elapsed_time": "1:04:00", "remaining_time": "3:28:03", "throughput": 686.31, "total_tokens": 2635568} {"current_steps": 9415, "total_steps": 40000, "loss": 0.0, "lr": 4.34722658025521e-05, "epoch": 104.61111111111111, "percentage": 23.54, "elapsed_time": "1:04:02", "remaining_time": "3:28:01", "throughput": 686.31, "total_tokens": 2636896} {"current_steps": 9420, "total_steps": 40000, "loss": 0.0, "lr": 4.346564911326071e-05, "epoch": 104.66666666666667, "percentage": 23.55, "elapsed_time": "1:04:04", "remaining_time": "3:27:58", "throughput": 686.33, "total_tokens": 2638320} {"current_steps": 9425, "total_steps": 40000, "loss": 0.0, "lr": 4.345902957633418e-05, "epoch": 104.72222222222223, "percentage": 23.56, "elapsed_time": "1:04:06", "remaining_time": "3:27:56", "throughput": 686.35, "total_tokens": 2639712} {"current_steps": 9430, "total_steps": 40000, "loss": 0.0, "lr": 4.345240719279331e-05, "epoch": 104.77777777777777, "percentage": 23.57, "elapsed_time": "1:04:07", "remaining_time": "3:27:54", "throughput": 686.37, "total_tokens": 2641136} {"current_steps": 9435, "total_steps": 40000, "loss": 0.0, "lr": 4.3445781963659374e-05, "epoch": 104.83333333333333, "percentage": 23.59, "elapsed_time": "1:04:09", "remaining_time": "3:27:51", "throughput": 686.39, "total_tokens": 2642544} {"current_steps": 9440, "total_steps": 40000, "loss": 0.0, "lr": 4.3439153889954045e-05, "epoch": 104.88888888888889, "percentage": 23.6, "elapsed_time": "1:04:11", "remaining_time": "3:27:49", "throughput": 686.4, "total_tokens": 2643904} {"current_steps": 9445, "total_steps": 40000, "loss": 0.0, "lr": 4.343252297269946e-05, "epoch": 104.94444444444444, "percentage": 23.61, "elapsed_time": "1:04:13", "remaining_time": "3:27:47", "throughput": 686.41, "total_tokens": 2645296} {"current_steps": 9450, "total_steps": 40000, "loss": 0.0, "lr": 4.342588921291821e-05, "epoch": 105.0, "percentage": 23.62, "elapsed_time": "1:04:15", "remaining_time": "3:27:45", "throughput": 686.39, "total_tokens": 2646672} {"current_steps": 9455, "total_steps": 40000, "loss": 0.0, "lr": 4.341925261163328e-05, "epoch": 105.05555555555556, "percentage": 23.64, "elapsed_time": "1:04:18", "remaining_time": "3:27:43", "throughput": 686.37, "total_tokens": 2648112} {"current_steps": 9460, "total_steps": 40000, "loss": 0.0, "lr": 4.341261316986813e-05, "epoch": 105.11111111111111, "percentage": 23.65, "elapsed_time": "1:04:20", "remaining_time": "3:27:41", "throughput": 686.37, "total_tokens": 2649456} {"current_steps": 9465, "total_steps": 40000, "loss": 0.0, "lr": 4.340597088864664e-05, "epoch": 105.16666666666667, "percentage": 23.66, "elapsed_time": "1:04:22", "remaining_time": "3:27:39", "throughput": 686.39, "total_tokens": 2650880} {"current_steps": 9470, "total_steps": 40000, "loss": 0.0, "lr": 4.339932576899313e-05, "epoch": 105.22222222222223, "percentage": 23.67, "elapsed_time": "1:04:23", "remaining_time": "3:27:36", "throughput": 686.42, "total_tokens": 2652320} {"current_steps": 9475, "total_steps": 40000, "loss": 0.0, "lr": 4.3392677811932375e-05, "epoch": 105.27777777777777, "percentage": 23.69, "elapsed_time": "1:04:25", "remaining_time": "3:27:34", "throughput": 686.43, "total_tokens": 2653680} {"current_steps": 9480, "total_steps": 40000, "loss": 0.0, "lr": 4.338602701848956e-05, "epoch": 105.33333333333333, "percentage": 23.7, "elapsed_time": "1:04:27", "remaining_time": "3:27:32", "throughput": 686.44, "total_tokens": 2655072} {"current_steps": 9485, "total_steps": 40000, "loss": 0.0, "lr": 4.337937338969033e-05, "epoch": 105.38888888888889, "percentage": 23.71, "elapsed_time": "1:04:29", "remaining_time": "3:27:29", "throughput": 686.46, "total_tokens": 2656496} {"current_steps": 9490, "total_steps": 40000, "loss": 0.0, "lr": 4.337271692656075e-05, "epoch": 105.44444444444444, "percentage": 23.72, "elapsed_time": "1:04:31", "remaining_time": "3:27:27", "throughput": 686.49, "total_tokens": 2657920} {"current_steps": 9495, "total_steps": 40000, "loss": 0.0, "lr": 4.336605763012733e-05, "epoch": 105.5, "percentage": 23.74, "elapsed_time": "1:04:33", "remaining_time": "3:27:25", "throughput": 686.5, "total_tokens": 2659296} {"current_steps": 9500, "total_steps": 40000, "loss": 0.0, "lr": 4.3359395501417026e-05, "epoch": 105.55555555555556, "percentage": 23.75, "elapsed_time": "1:04:35", "remaining_time": "3:27:22", "throughput": 686.5, "total_tokens": 2660656} {"current_steps": 9505, "total_steps": 40000, "loss": 0.0, "lr": 4.335273054145722e-05, "epoch": 105.61111111111111, "percentage": 23.76, "elapsed_time": "1:04:37", "remaining_time": "3:27:20", "throughput": 686.51, "total_tokens": 2662016} {"current_steps": 9510, "total_steps": 40000, "loss": 0.0, "lr": 4.334606275127572e-05, "epoch": 105.66666666666667, "percentage": 23.77, "elapsed_time": "1:04:39", "remaining_time": "3:27:18", "throughput": 686.53, "total_tokens": 2663424} {"current_steps": 9515, "total_steps": 40000, "loss": 0.0, "lr": 4.33393921319008e-05, "epoch": 105.72222222222223, "percentage": 23.79, "elapsed_time": "1:04:41", "remaining_time": "3:27:15", "throughput": 686.55, "total_tokens": 2664832} {"current_steps": 9520, "total_steps": 40000, "loss": 0.0, "lr": 4.3332718684361146e-05, "epoch": 105.77777777777777, "percentage": 23.8, "elapsed_time": "1:04:43", "remaining_time": "3:27:13", "throughput": 686.57, "total_tokens": 2666240} {"current_steps": 9525, "total_steps": 40000, "loss": 0.0, "lr": 4.332604240968588e-05, "epoch": 105.83333333333333, "percentage": 23.81, "elapsed_time": "1:04:45", "remaining_time": "3:27:11", "throughput": 686.59, "total_tokens": 2667664} {"current_steps": 9530, "total_steps": 40000, "loss": 0.0, "lr": 4.331936330890459e-05, "epoch": 105.88888888888889, "percentage": 23.82, "elapsed_time": "1:04:47", "remaining_time": "3:27:08", "throughput": 686.61, "total_tokens": 2669104} {"current_steps": 9535, "total_steps": 40000, "loss": 0.0, "lr": 4.331268138304725e-05, "epoch": 105.94444444444444, "percentage": 23.84, "elapsed_time": "1:04:49", "remaining_time": "3:27:06", "throughput": 686.63, "total_tokens": 2670512} {"current_steps": 9540, "total_steps": 40000, "loss": 0.0, "lr": 4.330599663314431e-05, "epoch": 106.0, "percentage": 23.85, "elapsed_time": "1:04:51", "remaining_time": "3:27:04", "throughput": 686.62, "total_tokens": 2671904} {"current_steps": 9545, "total_steps": 40000, "loss": 0.0, "lr": 4.329930906022665e-05, "epoch": 106.05555555555556, "percentage": 23.86, "elapsed_time": "1:04:53", "remaining_time": "3:27:03", "throughput": 686.6, "total_tokens": 2673344} {"current_steps": 9550, "total_steps": 40000, "loss": 0.0, "lr": 4.3292618665325564e-05, "epoch": 106.11111111111111, "percentage": 23.88, "elapsed_time": "1:04:55", "remaining_time": "3:27:00", "throughput": 686.63, "total_tokens": 2674800} {"current_steps": 9555, "total_steps": 40000, "loss": 0.0, "lr": 4.3285925449472796e-05, "epoch": 106.16666666666667, "percentage": 23.89, "elapsed_time": "1:04:57", "remaining_time": "3:26:58", "throughput": 686.64, "total_tokens": 2676176} {"current_steps": 9560, "total_steps": 40000, "loss": 0.0, "lr": 4.327922941370054e-05, "epoch": 106.22222222222223, "percentage": 23.9, "elapsed_time": "1:04:59", "remaining_time": "3:26:56", "throughput": 686.65, "total_tokens": 2677520} {"current_steps": 9565, "total_steps": 40000, "loss": 0.0, "lr": 4.3272530559041384e-05, "epoch": 106.27777777777777, "percentage": 23.91, "elapsed_time": "1:05:01", "remaining_time": "3:26:53", "throughput": 686.67, "total_tokens": 2678944} {"current_steps": 9570, "total_steps": 40000, "loss": 0.0, "lr": 4.32658288865284e-05, "epoch": 106.33333333333333, "percentage": 23.93, "elapsed_time": "1:05:03", "remaining_time": "3:26:51", "throughput": 686.68, "total_tokens": 2680336} {"current_steps": 9575, "total_steps": 40000, "loss": 0.0, "lr": 4.325912439719505e-05, "epoch": 106.38888888888889, "percentage": 23.94, "elapsed_time": "1:05:05", "remaining_time": "3:26:49", "throughput": 686.69, "total_tokens": 2681696} {"current_steps": 9580, "total_steps": 40000, "loss": 0.0, "lr": 4.3252417092075266e-05, "epoch": 106.44444444444444, "percentage": 23.95, "elapsed_time": "1:05:07", "remaining_time": "3:26:46", "throughput": 686.71, "total_tokens": 2683104} {"current_steps": 9585, "total_steps": 40000, "loss": 0.0, "lr": 4.3245706972203385e-05, "epoch": 106.5, "percentage": 23.96, "elapsed_time": "1:05:09", "remaining_time": "3:26:44", "throughput": 686.73, "total_tokens": 2684544} {"current_steps": 9590, "total_steps": 40000, "loss": 0.0, "lr": 4.323899403861421e-05, "epoch": 106.55555555555556, "percentage": 23.97, "elapsed_time": "1:05:11", "remaining_time": "3:26:42", "throughput": 686.74, "total_tokens": 2685920} {"current_steps": 9595, "total_steps": 40000, "loss": 0.0, "lr": 4.3232278292342935e-05, "epoch": 106.61111111111111, "percentage": 23.99, "elapsed_time": "1:05:13", "remaining_time": "3:26:39", "throughput": 686.75, "total_tokens": 2687264} {"current_steps": 9600, "total_steps": 40000, "loss": 0.0, "lr": 4.322555973442524e-05, "epoch": 106.66666666666667, "percentage": 24.0, "elapsed_time": "1:05:14", "remaining_time": "3:26:37", "throughput": 686.77, "total_tokens": 2688704} {"current_steps": 9600, "total_steps": 40000, "eval_loss": 0.3191697597503662, "epoch": 106.66666666666667, "percentage": 24.0, "elapsed_time": "1:05:16", "remaining_time": "3:26:41", "throughput": 686.54, "total_tokens": 2688704} {"current_steps": 9605, "total_steps": 40000, "loss": 0.0, "lr": 4.3218838365897184e-05, "epoch": 106.72222222222223, "percentage": 24.01, "elapsed_time": "1:05:19", "remaining_time": "3:26:43", "throughput": 686.34, "total_tokens": 2690128} {"current_steps": 9610, "total_steps": 40000, "loss": 0.0, "lr": 4.3212114187795306e-05, "epoch": 106.77777777777777, "percentage": 24.02, "elapsed_time": "1:05:21", "remaining_time": "3:26:41", "throughput": 686.36, "total_tokens": 2691568} {"current_steps": 9615, "total_steps": 40000, "loss": 0.0, "lr": 4.320538720115656e-05, "epoch": 106.83333333333333, "percentage": 24.04, "elapsed_time": "1:05:23", "remaining_time": "3:26:38", "throughput": 686.37, "total_tokens": 2692960} {"current_steps": 9620, "total_steps": 40000, "loss": 0.0, "lr": 4.319865740701831e-05, "epoch": 106.88888888888889, "percentage": 24.05, "elapsed_time": "1:05:25", "remaining_time": "3:26:36", "throughput": 686.38, "total_tokens": 2694336} {"current_steps": 9625, "total_steps": 40000, "loss": 0.0, "lr": 4.3191924806418396e-05, "epoch": 106.94444444444444, "percentage": 24.06, "elapsed_time": "1:05:27", "remaining_time": "3:26:34", "throughput": 686.4, "total_tokens": 2695744} {"current_steps": 9630, "total_steps": 40000, "loss": 0.0, "lr": 4.318518940039507e-05, "epoch": 107.0, "percentage": 24.07, "elapsed_time": "1:05:29", "remaining_time": "3:26:32", "throughput": 686.39, "total_tokens": 2697136} {"current_steps": 9635, "total_steps": 40000, "loss": 0.0, "lr": 4.3178451189987e-05, "epoch": 107.05555555555556, "percentage": 24.09, "elapsed_time": "1:05:31", "remaining_time": "3:26:30", "throughput": 686.36, "total_tokens": 2698560} {"current_steps": 9640, "total_steps": 40000, "loss": 0.0, "lr": 4.3171710176233315e-05, "epoch": 107.11111111111111, "percentage": 24.1, "elapsed_time": "1:05:33", "remaining_time": "3:26:28", "throughput": 686.38, "total_tokens": 2700000} {"current_steps": 9645, "total_steps": 40000, "loss": 0.0, "lr": 4.316496636017355e-05, "epoch": 107.16666666666667, "percentage": 24.11, "elapsed_time": "1:05:35", "remaining_time": "3:26:26", "throughput": 686.41, "total_tokens": 2701424} {"current_steps": 9650, "total_steps": 40000, "loss": 0.0, "lr": 4.315821974284771e-05, "epoch": 107.22222222222223, "percentage": 24.12, "elapsed_time": "1:05:37", "remaining_time": "3:26:23", "throughput": 686.43, "total_tokens": 2702832} {"current_steps": 9655, "total_steps": 40000, "loss": 0.0, "lr": 4.315147032529619e-05, "epoch": 107.27777777777777, "percentage": 24.14, "elapsed_time": "1:05:39", "remaining_time": "3:26:21", "throughput": 686.44, "total_tokens": 2704224} {"current_steps": 9660, "total_steps": 40000, "loss": 0.0, "lr": 4.3144718108559845e-05, "epoch": 107.33333333333333, "percentage": 24.15, "elapsed_time": "1:05:41", "remaining_time": "3:26:19", "throughput": 686.46, "total_tokens": 2705648} {"current_steps": 9665, "total_steps": 40000, "loss": 0.0, "lr": 4.3137963093679945e-05, "epoch": 107.38888888888889, "percentage": 24.16, "elapsed_time": "1:05:43", "remaining_time": "3:26:16", "throughput": 686.47, "total_tokens": 2707024} {"current_steps": 9670, "total_steps": 40000, "loss": 0.0, "lr": 4.31312052816982e-05, "epoch": 107.44444444444444, "percentage": 24.18, "elapsed_time": "1:05:45", "remaining_time": "3:26:14", "throughput": 686.48, "total_tokens": 2708400} {"current_steps": 9675, "total_steps": 40000, "loss": 0.0, "lr": 4.312444467365675e-05, "epoch": 107.5, "percentage": 24.19, "elapsed_time": "1:05:47", "remaining_time": "3:26:12", "throughput": 686.49, "total_tokens": 2709792} {"current_steps": 9680, "total_steps": 40000, "loss": 0.0, "lr": 4.311768127059816e-05, "epoch": 107.55555555555556, "percentage": 24.2, "elapsed_time": "1:05:49", "remaining_time": "3:26:09", "throughput": 686.51, "total_tokens": 2711184} {"current_steps": 9685, "total_steps": 40000, "loss": 0.0, "lr": 4.3110915073565444e-05, "epoch": 107.61111111111111, "percentage": 24.21, "elapsed_time": "1:05:51", "remaining_time": "3:26:07", "throughput": 686.53, "total_tokens": 2712592} {"current_steps": 9690, "total_steps": 40000, "loss": 0.0, "lr": 4.310414608360203e-05, "epoch": 107.66666666666667, "percentage": 24.22, "elapsed_time": "1:05:53", "remaining_time": "3:26:05", "throughput": 686.54, "total_tokens": 2713968} {"current_steps": 9695, "total_steps": 40000, "loss": 0.0, "lr": 4.309737430175177e-05, "epoch": 107.72222222222223, "percentage": 24.24, "elapsed_time": "1:05:55", "remaining_time": "3:26:02", "throughput": 686.55, "total_tokens": 2715344} {"current_steps": 9700, "total_steps": 40000, "loss": 0.0, "lr": 4.309059972905897e-05, "epoch": 107.77777777777777, "percentage": 24.25, "elapsed_time": "1:05:57", "remaining_time": "3:26:00", "throughput": 686.57, "total_tokens": 2716752} {"current_steps": 9705, "total_steps": 40000, "loss": 0.0, "lr": 4.308382236656836e-05, "epoch": 107.83333333333333, "percentage": 24.26, "elapsed_time": "1:05:58", "remaining_time": "3:25:58", "throughput": 686.58, "total_tokens": 2718144} {"current_steps": 9710, "total_steps": 40000, "loss": 0.0, "lr": 4.307704221532507e-05, "epoch": 107.88888888888889, "percentage": 24.27, "elapsed_time": "1:06:00", "remaining_time": "3:25:55", "throughput": 686.6, "total_tokens": 2719552} {"current_steps": 9715, "total_steps": 40000, "loss": 0.0, "lr": 4.307025927637471e-05, "epoch": 107.94444444444444, "percentage": 24.29, "elapsed_time": "1:06:02", "remaining_time": "3:25:53", "throughput": 686.62, "total_tokens": 2720960} {"current_steps": 9720, "total_steps": 40000, "loss": 0.0, "lr": 4.306347355076328e-05, "epoch": 108.0, "percentage": 24.3, "elapsed_time": "1:06:04", "remaining_time": "3:25:51", "throughput": 686.6, "total_tokens": 2722336} {"current_steps": 9725, "total_steps": 40000, "loss": 0.0, "lr": 4.305668503953724e-05, "epoch": 108.05555555555556, "percentage": 24.31, "elapsed_time": "1:06:07", "remaining_time": "3:25:50", "throughput": 686.58, "total_tokens": 2723760} {"current_steps": 9730, "total_steps": 40000, "loss": 0.0, "lr": 4.3049893743743436e-05, "epoch": 108.11111111111111, "percentage": 24.32, "elapsed_time": "1:06:09", "remaining_time": "3:25:47", "throughput": 686.6, "total_tokens": 2725184} {"current_steps": 9735, "total_steps": 40000, "loss": 0.0, "lr": 4.304309966442919e-05, "epoch": 108.16666666666667, "percentage": 24.34, "elapsed_time": "1:06:11", "remaining_time": "3:25:45", "throughput": 686.63, "total_tokens": 2726640} {"current_steps": 9740, "total_steps": 40000, "loss": 0.0, "lr": 4.303630280264224e-05, "epoch": 108.22222222222223, "percentage": 24.35, "elapsed_time": "1:06:12", "remaining_time": "3:25:43", "throughput": 686.63, "total_tokens": 2727984} {"current_steps": 9745, "total_steps": 40000, "loss": 0.0, "lr": 4.302950315943074e-05, "epoch": 108.27777777777777, "percentage": 24.36, "elapsed_time": "1:06:14", "remaining_time": "3:25:40", "throughput": 686.65, "total_tokens": 2729408} {"current_steps": 9750, "total_steps": 40000, "loss": 0.0, "lr": 4.3022700735843275e-05, "epoch": 108.33333333333333, "percentage": 24.38, "elapsed_time": "1:06:16", "remaining_time": "3:25:38", "throughput": 686.66, "total_tokens": 2730784} {"current_steps": 9755, "total_steps": 40000, "loss": 0.0, "lr": 4.301589553292887e-05, "epoch": 108.38888888888889, "percentage": 24.39, "elapsed_time": "1:06:18", "remaining_time": "3:25:36", "throughput": 686.68, "total_tokens": 2732176} {"current_steps": 9760, "total_steps": 40000, "loss": 0.0, "lr": 4.300908755173697e-05, "epoch": 108.44444444444444, "percentage": 24.4, "elapsed_time": "1:06:20", "remaining_time": "3:25:33", "throughput": 686.7, "total_tokens": 2733600} {"current_steps": 9765, "total_steps": 40000, "loss": 0.0, "lr": 4.300227679331745e-05, "epoch": 108.5, "percentage": 24.41, "elapsed_time": "1:06:22", "remaining_time": "3:25:31", "throughput": 686.71, "total_tokens": 2734992} {"current_steps": 9770, "total_steps": 40000, "loss": 0.0, "lr": 4.299546325872063e-05, "epoch": 108.55555555555556, "percentage": 24.43, "elapsed_time": "1:06:24", "remaining_time": "3:25:29", "throughput": 686.72, "total_tokens": 2736352} {"current_steps": 9775, "total_steps": 40000, "loss": 0.0, "lr": 4.2988646948997225e-05, "epoch": 108.61111111111111, "percentage": 24.44, "elapsed_time": "1:06:26", "remaining_time": "3:25:26", "throughput": 686.74, "total_tokens": 2737760} {"current_steps": 9780, "total_steps": 40000, "loss": 0.0, "lr": 4.29818278651984e-05, "epoch": 108.66666666666667, "percentage": 24.45, "elapsed_time": "1:06:28", "remaining_time": "3:25:24", "throughput": 686.74, "total_tokens": 2739136} {"current_steps": 9785, "total_steps": 40000, "loss": 0.0, "lr": 4.297500600837574e-05, "epoch": 108.72222222222223, "percentage": 24.46, "elapsed_time": "1:06:30", "remaining_time": "3:25:22", "throughput": 686.75, "total_tokens": 2740496} {"current_steps": 9790, "total_steps": 40000, "loss": 0.0, "lr": 4.2968181379581276e-05, "epoch": 108.77777777777777, "percentage": 24.47, "elapsed_time": "1:06:32", "remaining_time": "3:25:20", "throughput": 686.77, "total_tokens": 2741936} {"current_steps": 9795, "total_steps": 40000, "loss": 0.0, "lr": 4.296135397986743e-05, "epoch": 108.83333333333333, "percentage": 24.49, "elapsed_time": "1:06:34", "remaining_time": "3:25:17", "throughput": 686.79, "total_tokens": 2743344} {"current_steps": 9800, "total_steps": 40000, "loss": 0.0, "lr": 4.295452381028709e-05, "epoch": 108.88888888888889, "percentage": 24.5, "elapsed_time": "1:06:36", "remaining_time": "3:25:15", "throughput": 686.82, "total_tokens": 2744768} {"current_steps": 9800, "total_steps": 40000, "eval_loss": 0.29875534772872925, "epoch": 108.88888888888889, "percentage": 24.5, "elapsed_time": "1:06:37", "remaining_time": "3:25:19", "throughput": 686.59, "total_tokens": 2744768} {"current_steps": 9805, "total_steps": 40000, "loss": 0.0, "lr": 4.294769087189354e-05, "epoch": 108.94444444444444, "percentage": 24.51, "elapsed_time": "1:06:40", "remaining_time": "3:25:21", "throughput": 686.37, "total_tokens": 2746144} {"current_steps": 9810, "total_steps": 40000, "loss": 0.0, "lr": 4.294085516574052e-05, "epoch": 109.0, "percentage": 24.52, "elapsed_time": "1:06:43", "remaining_time": "3:25:19", "throughput": 686.35, "total_tokens": 2747552} {"current_steps": 9815, "total_steps": 40000, "loss": 0.0, "lr": 4.2934016692882176e-05, "epoch": 109.05555555555556, "percentage": 24.54, "elapsed_time": "1:06:45", "remaining_time": "3:25:18", "throughput": 686.32, "total_tokens": 2748960} {"current_steps": 9820, "total_steps": 40000, "loss": 0.0, "lr": 4.292717545437308e-05, "epoch": 109.11111111111111, "percentage": 24.55, "elapsed_time": "1:06:47", "remaining_time": "3:25:15", "throughput": 686.33, "total_tokens": 2750336} {"current_steps": 9825, "total_steps": 40000, "loss": 0.0, "lr": 4.292033145126825e-05, "epoch": 109.16666666666667, "percentage": 24.56, "elapsed_time": "1:06:49", "remaining_time": "3:25:13", "throughput": 686.34, "total_tokens": 2751728} {"current_steps": 9830, "total_steps": 40000, "loss": 0.0, "lr": 4.29134846846231e-05, "epoch": 109.22222222222223, "percentage": 24.57, "elapsed_time": "1:06:51", "remaining_time": "3:25:11", "throughput": 686.35, "total_tokens": 2753104} {"current_steps": 9835, "total_steps": 40000, "loss": 0.0, "lr": 4.29066351554935e-05, "epoch": 109.27777777777777, "percentage": 24.59, "elapsed_time": "1:06:53", "remaining_time": "3:25:08", "throughput": 686.37, "total_tokens": 2754496} {"current_steps": 9840, "total_steps": 40000, "loss": 0.0, "lr": 4.289978286493574e-05, "epoch": 109.33333333333333, "percentage": 24.6, "elapsed_time": "1:06:55", "remaining_time": "3:25:06", "throughput": 686.38, "total_tokens": 2755872} {"current_steps": 9845, "total_steps": 40000, "loss": 0.0, "lr": 4.28929278140065e-05, "epoch": 109.38888888888889, "percentage": 24.61, "elapsed_time": "1:06:57", "remaining_time": "3:25:04", "throughput": 686.4, "total_tokens": 2757312} {"current_steps": 9850, "total_steps": 40000, "loss": 0.0, "lr": 4.288607000376295e-05, "epoch": 109.44444444444444, "percentage": 24.62, "elapsed_time": "1:06:59", "remaining_time": "3:25:01", "throughput": 686.41, "total_tokens": 2758672} {"current_steps": 9855, "total_steps": 40000, "loss": 0.0, "lr": 4.2879209435262624e-05, "epoch": 109.5, "percentage": 24.64, "elapsed_time": "1:07:00", "remaining_time": "3:24:59", "throughput": 686.42, "total_tokens": 2760080} {"current_steps": 9860, "total_steps": 40000, "loss": 0.0, "lr": 4.287234610956353e-05, "epoch": 109.55555555555556, "percentage": 24.65, "elapsed_time": "1:07:02", "remaining_time": "3:24:57", "throughput": 686.43, "total_tokens": 2761440} {"current_steps": 9865, "total_steps": 40000, "loss": 0.0, "lr": 4.2865480027724056e-05, "epoch": 109.61111111111111, "percentage": 24.66, "elapsed_time": "1:07:04", "remaining_time": "3:24:54", "throughput": 686.44, "total_tokens": 2762832} {"current_steps": 9870, "total_steps": 40000, "loss": 0.0, "lr": 4.285861119080306e-05, "epoch": 109.66666666666667, "percentage": 24.68, "elapsed_time": "1:07:06", "remaining_time": "3:24:52", "throughput": 686.46, "total_tokens": 2764256} {"current_steps": 9875, "total_steps": 40000, "loss": 0.0, "lr": 4.2851739599859784e-05, "epoch": 109.72222222222223, "percentage": 24.69, "elapsed_time": "1:07:08", "remaining_time": "3:24:50", "throughput": 686.48, "total_tokens": 2765648} {"current_steps": 9880, "total_steps": 40000, "loss": 0.0, "lr": 4.2844865255953934e-05, "epoch": 109.77777777777777, "percentage": 24.7, "elapsed_time": "1:07:10", "remaining_time": "3:24:47", "throughput": 686.51, "total_tokens": 2767104} {"current_steps": 9885, "total_steps": 40000, "loss": 0.0, "lr": 4.2837988160145605e-05, "epoch": 109.83333333333333, "percentage": 24.71, "elapsed_time": "1:07:12", "remaining_time": "3:24:45", "throughput": 686.53, "total_tokens": 2768512} {"current_steps": 9890, "total_steps": 40000, "loss": 0.0, "lr": 4.2831108313495336e-05, "epoch": 109.88888888888889, "percentage": 24.73, "elapsed_time": "1:07:14", "remaining_time": "3:24:44", "throughput": 686.48, "total_tokens": 2769904} {"current_steps": 9895, "total_steps": 40000, "loss": 0.0, "lr": 4.282422571706408e-05, "epoch": 109.94444444444444, "percentage": 24.74, "elapsed_time": "1:07:16", "remaining_time": "3:24:42", "throughput": 686.5, "total_tokens": 2771312} {"current_steps": 9900, "total_steps": 40000, "loss": 0.0, "lr": 4.281734037191323e-05, "epoch": 110.0, "percentage": 24.75, "elapsed_time": "1:07:19", "remaining_time": "3:24:40", "throughput": 686.49, "total_tokens": 2772736} {"current_steps": 9905, "total_steps": 40000, "loss": 0.0, "lr": 4.281045227910459e-05, "epoch": 110.05555555555556, "percentage": 24.76, "elapsed_time": "1:07:21", "remaining_time": "3:24:38", "throughput": 686.46, "total_tokens": 2774128} {"current_steps": 9910, "total_steps": 40000, "loss": 0.0, "lr": 4.280356143970038e-05, "epoch": 110.11111111111111, "percentage": 24.77, "elapsed_time": "1:07:23", "remaining_time": "3:24:36", "throughput": 686.47, "total_tokens": 2775520} {"current_steps": 9915, "total_steps": 40000, "loss": 0.0, "lr": 4.279666785476327e-05, "epoch": 110.16666666666667, "percentage": 24.79, "elapsed_time": "1:07:25", "remaining_time": "3:24:34", "throughput": 686.49, "total_tokens": 2776944} {"current_steps": 9920, "total_steps": 40000, "loss": 0.0, "lr": 4.2789771525356325e-05, "epoch": 110.22222222222223, "percentage": 24.8, "elapsed_time": "1:07:27", "remaining_time": "3:24:31", "throughput": 686.51, "total_tokens": 2778336} {"current_steps": 9925, "total_steps": 40000, "loss": 0.0, "lr": 4.2782872452543056e-05, "epoch": 110.27777777777777, "percentage": 24.81, "elapsed_time": "1:07:28", "remaining_time": "3:24:29", "throughput": 686.53, "total_tokens": 2779760} {"current_steps": 9930, "total_steps": 40000, "loss": 0.0, "lr": 4.2775970637387376e-05, "epoch": 110.33333333333333, "percentage": 24.82, "elapsed_time": "1:07:30", "remaining_time": "3:24:27", "throughput": 686.54, "total_tokens": 2781152} {"current_steps": 9935, "total_steps": 40000, "loss": 0.0, "lr": 4.276906608095363e-05, "epoch": 110.38888888888889, "percentage": 24.84, "elapsed_time": "1:07:32", "remaining_time": "3:24:24", "throughput": 686.56, "total_tokens": 2782544} {"current_steps": 9940, "total_steps": 40000, "loss": 0.0, "lr": 4.276215878430661e-05, "epoch": 110.44444444444444, "percentage": 24.85, "elapsed_time": "1:07:34", "remaining_time": "3:24:22", "throughput": 686.57, "total_tokens": 2783936} {"current_steps": 9945, "total_steps": 40000, "loss": 0.0, "lr": 4.275524874851149e-05, "epoch": 110.5, "percentage": 24.86, "elapsed_time": "1:07:36", "remaining_time": "3:24:20", "throughput": 686.58, "total_tokens": 2785328} {"current_steps": 9950, "total_steps": 40000, "loss": 0.0, "lr": 4.274833597463388e-05, "epoch": 110.55555555555556, "percentage": 24.88, "elapsed_time": "1:07:38", "remaining_time": "3:24:17", "throughput": 686.6, "total_tokens": 2786736} {"current_steps": 9955, "total_steps": 40000, "loss": 0.0, "lr": 4.2741420463739824e-05, "epoch": 110.61111111111111, "percentage": 24.89, "elapsed_time": "1:07:40", "remaining_time": "3:24:15", "throughput": 686.62, "total_tokens": 2788144} {"current_steps": 9960, "total_steps": 40000, "loss": 0.0, "lr": 4.273450221689578e-05, "epoch": 110.66666666666667, "percentage": 24.9, "elapsed_time": "1:07:42", "remaining_time": "3:24:13", "throughput": 686.64, "total_tokens": 2789552} {"current_steps": 9965, "total_steps": 40000, "loss": 0.0, "lr": 4.272758123516863e-05, "epoch": 110.72222222222223, "percentage": 24.91, "elapsed_time": "1:07:44", "remaining_time": "3:24:10", "throughput": 686.67, "total_tokens": 2791008} {"current_steps": 9970, "total_steps": 40000, "loss": 0.0, "lr": 4.272065751962567e-05, "epoch": 110.77777777777777, "percentage": 24.93, "elapsed_time": "1:07:46", "remaining_time": "3:24:08", "throughput": 686.68, "total_tokens": 2792384} {"current_steps": 9975, "total_steps": 40000, "loss": 0.0, "lr": 4.271373107133464e-05, "epoch": 110.83333333333333, "percentage": 24.94, "elapsed_time": "1:07:48", "remaining_time": "3:24:06", "throughput": 686.69, "total_tokens": 2793760} {"current_steps": 9980, "total_steps": 40000, "loss": 0.0, "lr": 4.270680189136366e-05, "epoch": 110.88888888888889, "percentage": 24.95, "elapsed_time": "1:07:50", "remaining_time": "3:24:03", "throughput": 686.71, "total_tokens": 2795184} {"current_steps": 9985, "total_steps": 40000, "loss": 0.0, "lr": 4.269986998078132e-05, "epoch": 110.94444444444444, "percentage": 24.96, "elapsed_time": "1:07:52", "remaining_time": "3:24:01", "throughput": 686.72, "total_tokens": 2796560} {"current_steps": 9990, "total_steps": 40000, "loss": 0.0, "lr": 4.2692935340656595e-05, "epoch": 111.0, "percentage": 24.98, "elapsed_time": "1:07:54", "remaining_time": "3:23:59", "throughput": 686.7, "total_tokens": 2797952} {"current_steps": 9995, "total_steps": 40000, "loss": 0.0, "lr": 4.26859979720589e-05, "epoch": 111.05555555555556, "percentage": 24.99, "elapsed_time": "1:07:56", "remaining_time": "3:23:58", "throughput": 686.68, "total_tokens": 2799344} {"current_steps": 10000, "total_steps": 40000, "loss": 0.0, "lr": 4.267905787605806e-05, "epoch": 111.11111111111111, "percentage": 25.0, "elapsed_time": "1:07:58", "remaining_time": "3:23:55", "throughput": 686.7, "total_tokens": 2800768} {"current_steps": 10000, "total_steps": 40000, "eval_loss": 0.34467577934265137, "epoch": 111.11111111111111, "percentage": 25.0, "elapsed_time": "1:07:59", "remaining_time": "3:23:59", "throughput": 686.48, "total_tokens": 2800768} {"current_steps": 10005, "total_steps": 40000, "loss": 0.0, "lr": 4.267211505372433e-05, "epoch": 111.16666666666667, "percentage": 25.01, "elapsed_time": "1:08:03", "remaining_time": "3:24:01", "throughput": 686.26, "total_tokens": 2802160} {"current_steps": 10010, "total_steps": 40000, "loss": 0.0, "lr": 4.266516950612837e-05, "epoch": 111.22222222222223, "percentage": 25.02, "elapsed_time": "1:08:05", "remaining_time": "3:23:59", "throughput": 686.26, "total_tokens": 2803536} {"current_steps": 10015, "total_steps": 40000, "loss": 0.0, "lr": 4.265822123434128e-05, "epoch": 111.27777777777777, "percentage": 25.04, "elapsed_time": "1:08:07", "remaining_time": "3:23:57", "throughput": 686.27, "total_tokens": 2804928} {"current_steps": 10020, "total_steps": 40000, "loss": 0.0, "lr": 4.265127023943457e-05, "epoch": 111.33333333333333, "percentage": 25.05, "elapsed_time": "1:08:09", "remaining_time": "3:23:54", "throughput": 686.29, "total_tokens": 2806336} {"current_steps": 10025, "total_steps": 40000, "loss": 0.0, "lr": 4.2644316522480176e-05, "epoch": 111.38888888888889, "percentage": 25.06, "elapsed_time": "1:08:11", "remaining_time": "3:23:52", "throughput": 686.31, "total_tokens": 2807744} {"current_steps": 10030, "total_steps": 40000, "loss": 0.0, "lr": 4.263736008455044e-05, "epoch": 111.44444444444444, "percentage": 25.07, "elapsed_time": "1:08:13", "remaining_time": "3:23:50", "throughput": 686.32, "total_tokens": 2809120} {"current_steps": 10035, "total_steps": 40000, "loss": 0.0, "lr": 4.2630400926718125e-05, "epoch": 111.5, "percentage": 25.09, "elapsed_time": "1:08:14", "remaining_time": "3:23:47", "throughput": 686.33, "total_tokens": 2810512} {"current_steps": 10040, "total_steps": 40000, "loss": 0.0, "lr": 4.262343905005644e-05, "epoch": 111.55555555555556, "percentage": 25.1, "elapsed_time": "1:08:16", "remaining_time": "3:23:45", "throughput": 686.35, "total_tokens": 2811920} {"current_steps": 10045, "total_steps": 40000, "loss": 0.0, "lr": 4.261647445563897e-05, "epoch": 111.61111111111111, "percentage": 25.11, "elapsed_time": "1:08:18", "remaining_time": "3:23:43", "throughput": 686.38, "total_tokens": 2813376} {"current_steps": 10050, "total_steps": 40000, "loss": 0.0, "lr": 4.260950714453976e-05, "epoch": 111.66666666666667, "percentage": 25.12, "elapsed_time": "1:08:20", "remaining_time": "3:23:40", "throughput": 686.4, "total_tokens": 2814784} {"current_steps": 10055, "total_steps": 40000, "loss": 0.0, "lr": 4.2602537117833266e-05, "epoch": 111.72222222222223, "percentage": 25.14, "elapsed_time": "1:08:22", "remaining_time": "3:23:38", "throughput": 686.42, "total_tokens": 2816208} {"current_steps": 10060, "total_steps": 40000, "loss": 0.0, "lr": 4.259556437659433e-05, "epoch": 111.77777777777777, "percentage": 25.15, "elapsed_time": "1:08:24", "remaining_time": "3:23:36", "throughput": 686.43, "total_tokens": 2817584} {"current_steps": 10065, "total_steps": 40000, "loss": 0.0, "lr": 4.258858892189825e-05, "epoch": 111.83333333333333, "percentage": 25.16, "elapsed_time": "1:08:26", "remaining_time": "3:23:33", "throughput": 686.45, "total_tokens": 2819008} {"current_steps": 10070, "total_steps": 40000, "loss": 0.0, "lr": 4.2581610754820725e-05, "epoch": 111.88888888888889, "percentage": 25.17, "elapsed_time": "1:08:28", "remaining_time": "3:23:31", "throughput": 686.45, "total_tokens": 2820368} {"current_steps": 10075, "total_steps": 40000, "loss": 0.0, "lr": 4.2574629876437876e-05, "epoch": 111.94444444444444, "percentage": 25.19, "elapsed_time": "1:08:30", "remaining_time": "3:23:29", "throughput": 686.47, "total_tokens": 2821776} {"current_steps": 10080, "total_steps": 40000, "loss": 0.0, "lr": 4.256764628782625e-05, "epoch": 112.0, "percentage": 25.2, "elapsed_time": "1:08:32", "remaining_time": "3:23:27", "throughput": 686.46, "total_tokens": 2823184} {"current_steps": 10085, "total_steps": 40000, "loss": 0.0, "lr": 4.256065999006279e-05, "epoch": 112.05555555555556, "percentage": 25.21, "elapsed_time": "1:08:34", "remaining_time": "3:23:25", "throughput": 686.42, "total_tokens": 2824528} {"current_steps": 10090, "total_steps": 40000, "loss": 0.0, "lr": 4.2553670984224885e-05, "epoch": 112.11111111111111, "percentage": 25.22, "elapsed_time": "1:08:36", "remaining_time": "3:23:23", "throughput": 686.44, "total_tokens": 2825952} {"current_steps": 10095, "total_steps": 40000, "loss": 0.0, "lr": 4.254667927139032e-05, "epoch": 112.16666666666667, "percentage": 25.24, "elapsed_time": "1:08:38", "remaining_time": "3:23:21", "throughput": 686.46, "total_tokens": 2827376} {"current_steps": 10100, "total_steps": 40000, "loss": 0.0, "lr": 4.2539684852637295e-05, "epoch": 112.22222222222223, "percentage": 25.25, "elapsed_time": "1:08:40", "remaining_time": "3:23:18", "throughput": 686.47, "total_tokens": 2828752} {"current_steps": 10105, "total_steps": 40000, "loss": 0.0, "lr": 4.253268772904446e-05, "epoch": 112.27777777777777, "percentage": 25.26, "elapsed_time": "1:08:42", "remaining_time": "3:23:16", "throughput": 686.49, "total_tokens": 2830176} {"current_steps": 10110, "total_steps": 40000, "loss": 0.0, "lr": 4.252568790169085e-05, "epoch": 112.33333333333333, "percentage": 25.27, "elapsed_time": "1:08:44", "remaining_time": "3:23:14", "throughput": 686.51, "total_tokens": 2831584} {"current_steps": 10115, "total_steps": 40000, "loss": 0.0, "lr": 4.251868537165592e-05, "epoch": 112.38888888888889, "percentage": 25.29, "elapsed_time": "1:08:46", "remaining_time": "3:23:11", "throughput": 686.53, "total_tokens": 2832992} {"current_steps": 10120, "total_steps": 40000, "loss": 0.0, "lr": 4.251168014001955e-05, "epoch": 112.44444444444444, "percentage": 25.3, "elapsed_time": "1:08:48", "remaining_time": "3:23:09", "throughput": 686.55, "total_tokens": 2834400} {"current_steps": 10125, "total_steps": 40000, "loss": 0.0, "lr": 4.250467220786204e-05, "epoch": 112.5, "percentage": 25.31, "elapsed_time": "1:08:50", "remaining_time": "3:23:07", "throughput": 686.55, "total_tokens": 2835744} {"current_steps": 10130, "total_steps": 40000, "loss": 0.0, "lr": 4.249766157626409e-05, "epoch": 112.55555555555556, "percentage": 25.32, "elapsed_time": "1:08:52", "remaining_time": "3:23:04", "throughput": 686.57, "total_tokens": 2837168} {"current_steps": 10135, "total_steps": 40000, "loss": 0.0, "lr": 4.249064824630684e-05, "epoch": 112.61111111111111, "percentage": 25.34, "elapsed_time": "1:08:54", "remaining_time": "3:23:02", "throughput": 686.58, "total_tokens": 2838528} {"current_steps": 10140, "total_steps": 40000, "loss": 0.0, "lr": 4.248363221907183e-05, "epoch": 112.66666666666667, "percentage": 25.35, "elapsed_time": "1:08:56", "remaining_time": "3:23:00", "throughput": 686.58, "total_tokens": 2839888} {"current_steps": 10145, "total_steps": 40000, "loss": 0.0, "lr": 4.2476613495641026e-05, "epoch": 112.72222222222223, "percentage": 25.36, "elapsed_time": "1:08:58", "remaining_time": "3:22:58", "throughput": 686.59, "total_tokens": 2841248} {"current_steps": 10150, "total_steps": 40000, "loss": 0.0, "lr": 4.246959207709679e-05, "epoch": 112.77777777777777, "percentage": 25.37, "elapsed_time": "1:09:00", "remaining_time": "3:22:55", "throughput": 686.61, "total_tokens": 2842688} {"current_steps": 10155, "total_steps": 40000, "loss": 0.0, "lr": 4.246256796452192e-05, "epoch": 112.83333333333333, "percentage": 25.39, "elapsed_time": "1:09:02", "remaining_time": "3:22:53", "throughput": 686.62, "total_tokens": 2844064} {"current_steps": 10160, "total_steps": 40000, "loss": 0.0, "lr": 4.245554115899962e-05, "epoch": 112.88888888888889, "percentage": 25.4, "elapsed_time": "1:09:04", "remaining_time": "3:22:51", "throughput": 686.63, "total_tokens": 2845440} {"current_steps": 10165, "total_steps": 40000, "loss": 0.0, "lr": 4.2448511661613514e-05, "epoch": 112.94444444444444, "percentage": 25.41, "elapsed_time": "1:09:06", "remaining_time": "3:22:48", "throughput": 686.64, "total_tokens": 2846800} {"current_steps": 10170, "total_steps": 40000, "loss": 0.0, "lr": 4.2441479473447635e-05, "epoch": 113.0, "percentage": 25.42, "elapsed_time": "1:09:08", "remaining_time": "3:22:47", "throughput": 686.64, "total_tokens": 2848256} {"current_steps": 10175, "total_steps": 40000, "loss": 0.0, "lr": 4.243444459558644e-05, "epoch": 113.05555555555556, "percentage": 25.44, "elapsed_time": "1:09:10", "remaining_time": "3:22:45", "throughput": 686.59, "total_tokens": 2849584} {"current_steps": 10180, "total_steps": 40000, "loss": 0.0, "lr": 4.24274070291148e-05, "epoch": 113.11111111111111, "percentage": 25.45, "elapsed_time": "1:09:12", "remaining_time": "3:22:43", "throughput": 686.61, "total_tokens": 2850992} {"current_steps": 10185, "total_steps": 40000, "loss": 0.0, "lr": 4.242036677511798e-05, "epoch": 113.16666666666667, "percentage": 25.46, "elapsed_time": "1:09:14", "remaining_time": "3:22:40", "throughput": 686.65, "total_tokens": 2852464} {"current_steps": 10190, "total_steps": 40000, "loss": 0.0, "lr": 4.241332383468169e-05, "epoch": 113.22222222222223, "percentage": 25.47, "elapsed_time": "1:09:16", "remaining_time": "3:22:38", "throughput": 686.67, "total_tokens": 2853904} {"current_steps": 10195, "total_steps": 40000, "loss": 0.0, "lr": 4.2406278208892034e-05, "epoch": 113.27777777777777, "percentage": 25.49, "elapsed_time": "1:09:18", "remaining_time": "3:22:36", "throughput": 686.69, "total_tokens": 2855344} {"current_steps": 10200, "total_steps": 40000, "loss": 0.0, "lr": 4.2399229898835536e-05, "epoch": 113.33333333333333, "percentage": 25.5, "elapsed_time": "1:09:20", "remaining_time": "3:22:33", "throughput": 686.72, "total_tokens": 2856768} {"current_steps": 10200, "total_steps": 40000, "eval_loss": 0.32345396280288696, "epoch": 113.33333333333333, "percentage": 25.5, "elapsed_time": "1:09:21", "remaining_time": "3:22:37", "throughput": 686.5, "total_tokens": 2856768} {"current_steps": 10205, "total_steps": 40000, "loss": 0.0, "lr": 4.239217890559914e-05, "epoch": 113.38888888888889, "percentage": 25.51, "elapsed_time": "1:09:24", "remaining_time": "3:22:39", "throughput": 686.29, "total_tokens": 2858144} {"current_steps": 10210, "total_steps": 40000, "loss": 0.0, "lr": 4.238512523027019e-05, "epoch": 113.44444444444444, "percentage": 25.52, "elapsed_time": "1:09:26", "remaining_time": "3:22:37", "throughput": 686.28, "total_tokens": 2859504} {"current_steps": 10215, "total_steps": 40000, "loss": 0.0, "lr": 4.237806887393645e-05, "epoch": 113.5, "percentage": 25.54, "elapsed_time": "1:09:28", "remaining_time": "3:22:34", "throughput": 686.3, "total_tokens": 2860896} {"current_steps": 10220, "total_steps": 40000, "loss": 0.0, "lr": 4.237100983768611e-05, "epoch": 113.55555555555556, "percentage": 25.55, "elapsed_time": "1:09:30", "remaining_time": "3:22:32", "throughput": 686.31, "total_tokens": 2862304} {"current_steps": 10225, "total_steps": 40000, "loss": 0.0, "lr": 4.2363948122607756e-05, "epoch": 113.61111111111111, "percentage": 25.56, "elapsed_time": "1:09:32", "remaining_time": "3:22:30", "throughput": 686.33, "total_tokens": 2863712} {"current_steps": 10230, "total_steps": 40000, "loss": 0.0, "lr": 4.235688372979039e-05, "epoch": 113.66666666666667, "percentage": 25.57, "elapsed_time": "1:09:34", "remaining_time": "3:22:27", "throughput": 686.33, "total_tokens": 2865072} {"current_steps": 10235, "total_steps": 40000, "loss": 0.0, "lr": 4.234981666032343e-05, "epoch": 113.72222222222223, "percentage": 25.59, "elapsed_time": "1:09:36", "remaining_time": "3:22:25", "throughput": 686.35, "total_tokens": 2866464} {"current_steps": 10240, "total_steps": 40000, "loss": 0.0, "lr": 4.2342746915296704e-05, "epoch": 113.77777777777777, "percentage": 25.6, "elapsed_time": "1:09:38", "remaining_time": "3:22:23", "throughput": 686.35, "total_tokens": 2867824} {"current_steps": 10245, "total_steps": 40000, "loss": 0.0, "lr": 4.233567449580047e-05, "epoch": 113.83333333333333, "percentage": 25.61, "elapsed_time": "1:09:40", "remaining_time": "3:22:20", "throughput": 686.37, "total_tokens": 2869200} {"current_steps": 10250, "total_steps": 40000, "loss": 0.0, "lr": 4.232859940292537e-05, "epoch": 113.88888888888889, "percentage": 25.62, "elapsed_time": "1:09:42", "remaining_time": "3:22:18", "throughput": 686.38, "total_tokens": 2870592} {"current_steps": 10255, "total_steps": 40000, "loss": 0.0, "lr": 4.232152163776248e-05, "epoch": 113.94444444444444, "percentage": 25.64, "elapsed_time": "1:09:44", "remaining_time": "3:22:16", "throughput": 686.41, "total_tokens": 2872032} {"current_steps": 10260, "total_steps": 40000, "loss": 0.0, "lr": 4.231444120140328e-05, "epoch": 114.0, "percentage": 25.65, "elapsed_time": "1:09:46", "remaining_time": "3:22:14", "throughput": 686.39, "total_tokens": 2873424} {"current_steps": 10265, "total_steps": 40000, "loss": 0.0, "lr": 4.230735809493967e-05, "epoch": 114.05555555555556, "percentage": 25.66, "elapsed_time": "1:09:48", "remaining_time": "3:22:12", "throughput": 686.35, "total_tokens": 2874784} {"current_steps": 10270, "total_steps": 40000, "loss": 0.0, "lr": 4.2300272319463926e-05, "epoch": 114.11111111111111, "percentage": 25.67, "elapsed_time": "1:09:50", "remaining_time": "3:22:10", "throughput": 686.36, "total_tokens": 2876160} {"current_steps": 10275, "total_steps": 40000, "loss": 0.0, "lr": 4.2293183876068786e-05, "epoch": 114.16666666666667, "percentage": 25.69, "elapsed_time": "1:09:52", "remaining_time": "3:22:08", "throughput": 686.39, "total_tokens": 2877600} {"current_steps": 10280, "total_steps": 40000, "loss": 0.0, "lr": 4.228609276584737e-05, "epoch": 114.22222222222223, "percentage": 25.7, "elapsed_time": "1:09:54", "remaining_time": "3:22:06", "throughput": 686.4, "total_tokens": 2878976} {"current_steps": 10285, "total_steps": 40000, "loss": 0.0, "lr": 4.227899898989323e-05, "epoch": 114.27777777777777, "percentage": 25.71, "elapsed_time": "1:09:56", "remaining_time": "3:22:03", "throughput": 686.4, "total_tokens": 2880320} {"current_steps": 10290, "total_steps": 40000, "loss": 0.0, "lr": 4.2271902549300293e-05, "epoch": 114.33333333333333, "percentage": 25.72, "elapsed_time": "1:09:58", "remaining_time": "3:22:01", "throughput": 686.41, "total_tokens": 2881712} {"current_steps": 10295, "total_steps": 40000, "loss": 0.0, "lr": 4.226480344516294e-05, "epoch": 114.38888888888889, "percentage": 25.74, "elapsed_time": "1:10:00", "remaining_time": "3:21:59", "throughput": 686.43, "total_tokens": 2883104} {"current_steps": 10300, "total_steps": 40000, "loss": 0.0, "lr": 4.2257701678575925e-05, "epoch": 114.44444444444444, "percentage": 25.75, "elapsed_time": "1:10:02", "remaining_time": "3:21:56", "throughput": 686.45, "total_tokens": 2884544} {"current_steps": 10305, "total_steps": 40000, "loss": 0.0, "lr": 4.225059725063444e-05, "epoch": 114.5, "percentage": 25.76, "elapsed_time": "1:10:04", "remaining_time": "3:21:54", "throughput": 686.47, "total_tokens": 2885952} {"current_steps": 10310, "total_steps": 40000, "loss": 0.0, "lr": 4.2243490162434074e-05, "epoch": 114.55555555555556, "percentage": 25.77, "elapsed_time": "1:10:05", "remaining_time": "3:21:52", "throughput": 686.49, "total_tokens": 2887360} {"current_steps": 10315, "total_steps": 40000, "loss": 0.0, "lr": 4.223638041507083e-05, "epoch": 114.61111111111111, "percentage": 25.79, "elapsed_time": "1:10:07", "remaining_time": "3:21:49", "throughput": 686.5, "total_tokens": 2888736} {"current_steps": 10320, "total_steps": 40000, "loss": 0.0, "lr": 4.2229268009641124e-05, "epoch": 114.66666666666667, "percentage": 25.8, "elapsed_time": "1:10:09", "remaining_time": "3:21:47", "throughput": 686.52, "total_tokens": 2890176} {"current_steps": 10325, "total_steps": 40000, "loss": 0.0, "lr": 4.222215294724177e-05, "epoch": 114.72222222222223, "percentage": 25.81, "elapsed_time": "1:10:11", "remaining_time": "3:21:45", "throughput": 686.54, "total_tokens": 2891584} {"current_steps": 10330, "total_steps": 40000, "loss": 0.0, "lr": 4.2215035228970005e-05, "epoch": 114.77777777777777, "percentage": 25.82, "elapsed_time": "1:10:13", "remaining_time": "3:21:42", "throughput": 686.56, "total_tokens": 2892992} {"current_steps": 10335, "total_steps": 40000, "loss": 0.0, "lr": 4.2207914855923464e-05, "epoch": 114.83333333333333, "percentage": 25.84, "elapsed_time": "1:10:15", "remaining_time": "3:21:40", "throughput": 686.57, "total_tokens": 2894400} {"current_steps": 10340, "total_steps": 40000, "loss": 0.0, "lr": 4.220079182920021e-05, "epoch": 114.88888888888889, "percentage": 25.85, "elapsed_time": "1:10:17", "remaining_time": "3:21:38", "throughput": 686.6, "total_tokens": 2895840} {"current_steps": 10345, "total_steps": 40000, "loss": 0.0, "lr": 4.2193666149898705e-05, "epoch": 114.94444444444444, "percentage": 25.86, "elapsed_time": "1:10:19", "remaining_time": "3:21:35", "throughput": 686.62, "total_tokens": 2897264} {"current_steps": 10350, "total_steps": 40000, "loss": 0.0, "lr": 4.21865378191178e-05, "epoch": 115.0, "percentage": 25.87, "elapsed_time": "1:10:21", "remaining_time": "3:21:34", "throughput": 686.6, "total_tokens": 2898624} {"current_steps": 10355, "total_steps": 40000, "loss": 0.0, "lr": 4.217940683795678e-05, "epoch": 115.05555555555556, "percentage": 25.89, "elapsed_time": "1:10:23", "remaining_time": "3:21:32", "throughput": 686.57, "total_tokens": 2900032} {"current_steps": 10360, "total_steps": 40000, "loss": 0.0, "lr": 4.217227320751534e-05, "epoch": 115.11111111111111, "percentage": 25.9, "elapsed_time": "1:10:25", "remaining_time": "3:21:30", "throughput": 686.58, "total_tokens": 2901376} {"current_steps": 10365, "total_steps": 40000, "loss": 0.0, "lr": 4.216513692889358e-05, "epoch": 115.16666666666667, "percentage": 25.91, "elapsed_time": "1:10:27", "remaining_time": "3:21:27", "throughput": 686.59, "total_tokens": 2902784} {"current_steps": 10370, "total_steps": 40000, "loss": 0.0, "lr": 4.215799800319199e-05, "epoch": 115.22222222222223, "percentage": 25.92, "elapsed_time": "1:10:29", "remaining_time": "3:21:25", "throughput": 686.6, "total_tokens": 2904160} {"current_steps": 10375, "total_steps": 40000, "loss": 0.0, "lr": 4.2150856431511485e-05, "epoch": 115.27777777777777, "percentage": 25.94, "elapsed_time": "1:10:31", "remaining_time": "3:21:23", "throughput": 686.61, "total_tokens": 2905552} {"current_steps": 10380, "total_steps": 40000, "loss": 0.0, "lr": 4.214371221495339e-05, "epoch": 115.33333333333333, "percentage": 25.95, "elapsed_time": "1:10:33", "remaining_time": "3:21:20", "throughput": 686.63, "total_tokens": 2906960} {"current_steps": 10385, "total_steps": 40000, "loss": 0.0, "lr": 4.213656535461942e-05, "epoch": 115.38888888888889, "percentage": 25.96, "elapsed_time": "1:10:35", "remaining_time": "3:21:18", "throughput": 686.66, "total_tokens": 2908400} {"current_steps": 10390, "total_steps": 40000, "loss": 0.0, "lr": 4.2129415851611734e-05, "epoch": 115.44444444444444, "percentage": 25.97, "elapsed_time": "1:10:37", "remaining_time": "3:21:16", "throughput": 686.68, "total_tokens": 2909840} {"current_steps": 10395, "total_steps": 40000, "loss": 0.0, "lr": 4.2122263707032855e-05, "epoch": 115.5, "percentage": 25.99, "elapsed_time": "1:10:39", "remaining_time": "3:21:14", "throughput": 686.7, "total_tokens": 2911232} {"current_steps": 10400, "total_steps": 40000, "loss": 0.0, "lr": 4.211510892198574e-05, "epoch": 115.55555555555556, "percentage": 26.0, "elapsed_time": "1:10:41", "remaining_time": "3:21:11", "throughput": 686.71, "total_tokens": 2912640} {"current_steps": 10400, "total_steps": 40000, "eval_loss": 0.3244749903678894, "epoch": 115.55555555555556, "percentage": 26.0, "elapsed_time": "1:10:42", "remaining_time": "3:21:15", "throughput": 686.5, "total_tokens": 2912640} {"current_steps": 10405, "total_steps": 40000, "loss": 0.0, "lr": 4.210795149757375e-05, "epoch": 115.61111111111111, "percentage": 26.01, "elapsed_time": "1:10:46", "remaining_time": "3:21:16", "throughput": 686.31, "total_tokens": 2914080} {"current_steps": 10410, "total_steps": 40000, "loss": 0.0, "lr": 4.210079143490065e-05, "epoch": 115.66666666666667, "percentage": 26.02, "elapsed_time": "1:10:48", "remaining_time": "3:21:14", "throughput": 686.32, "total_tokens": 2915472} {"current_steps": 10415, "total_steps": 40000, "loss": 0.0, "lr": 4.2093628735070604e-05, "epoch": 115.72222222222223, "percentage": 26.04, "elapsed_time": "1:10:49", "remaining_time": "3:21:12", "throughput": 686.33, "total_tokens": 2916864} {"current_steps": 10420, "total_steps": 40000, "loss": 0.0, "lr": 4.208646339918819e-05, "epoch": 115.77777777777777, "percentage": 26.05, "elapsed_time": "1:10:51", "remaining_time": "3:21:10", "throughput": 686.34, "total_tokens": 2918256} {"current_steps": 10425, "total_steps": 40000, "loss": 0.0, "lr": 4.2079295428358414e-05, "epoch": 115.83333333333333, "percentage": 26.06, "elapsed_time": "1:10:53", "remaining_time": "3:21:07", "throughput": 686.36, "total_tokens": 2919664} {"current_steps": 10430, "total_steps": 40000, "loss": 0.0, "lr": 4.207212482368664e-05, "epoch": 115.88888888888889, "percentage": 26.07, "elapsed_time": "1:10:55", "remaining_time": "3:21:05", "throughput": 686.37, "total_tokens": 2921056} {"current_steps": 10435, "total_steps": 40000, "loss": 0.0, "lr": 4.206495158627867e-05, "epoch": 115.94444444444444, "percentage": 26.09, "elapsed_time": "1:10:57", "remaining_time": "3:21:03", "throughput": 686.39, "total_tokens": 2922480} {"current_steps": 10440, "total_steps": 40000, "loss": 0.0, "lr": 4.205777571724073e-05, "epoch": 116.0, "percentage": 26.1, "elapsed_time": "1:10:59", "remaining_time": "3:21:01", "throughput": 686.37, "total_tokens": 2923856} {"current_steps": 10445, "total_steps": 40000, "loss": 0.0, "lr": 4.20505972176794e-05, "epoch": 116.05555555555556, "percentage": 26.11, "elapsed_time": "1:11:02", "remaining_time": "3:20:59", "throughput": 686.35, "total_tokens": 2925296} {"current_steps": 10450, "total_steps": 40000, "loss": 0.0, "lr": 4.204341608870171e-05, "epoch": 116.11111111111111, "percentage": 26.12, "elapsed_time": "1:11:04", "remaining_time": "3:20:57", "throughput": 686.37, "total_tokens": 2926704} {"current_steps": 10455, "total_steps": 40000, "loss": 0.0, "lr": 4.203623233141508e-05, "epoch": 116.16666666666667, "percentage": 26.14, "elapsed_time": "1:11:05", "remaining_time": "3:20:55", "throughput": 686.4, "total_tokens": 2928160} {"current_steps": 10460, "total_steps": 40000, "loss": 0.0, "lr": 4.2029045946927334e-05, "epoch": 116.22222222222223, "percentage": 26.15, "elapsed_time": "1:11:07", "remaining_time": "3:20:52", "throughput": 686.42, "total_tokens": 2929600} {"current_steps": 10465, "total_steps": 40000, "loss": 0.0, "lr": 4.20218569363467e-05, "epoch": 116.27777777777777, "percentage": 26.16, "elapsed_time": "1:11:09", "remaining_time": "3:20:50", "throughput": 686.45, "total_tokens": 2931024} {"current_steps": 10470, "total_steps": 40000, "loss": 0.0, "lr": 4.2014665300781834e-05, "epoch": 116.33333333333333, "percentage": 26.17, "elapsed_time": "1:11:11", "remaining_time": "3:20:48", "throughput": 686.45, "total_tokens": 2932368} {"current_steps": 10475, "total_steps": 40000, "loss": 0.0, "lr": 4.200747104134174e-05, "epoch": 116.38888888888889, "percentage": 26.19, "elapsed_time": "1:11:13", "remaining_time": "3:20:46", "throughput": 686.46, "total_tokens": 2933728} {"current_steps": 10480, "total_steps": 40000, "loss": 0.0, "lr": 4.200027415913588e-05, "epoch": 116.44444444444444, "percentage": 26.2, "elapsed_time": "1:11:15", "remaining_time": "3:20:43", "throughput": 686.46, "total_tokens": 2935104} {"current_steps": 10485, "total_steps": 40000, "loss": 0.0, "lr": 4.1993074655274126e-05, "epoch": 116.5, "percentage": 26.21, "elapsed_time": "1:11:17", "remaining_time": "3:20:41", "throughput": 686.48, "total_tokens": 2936528} {"current_steps": 10490, "total_steps": 40000, "loss": 0.0, "lr": 4.198587253086669e-05, "epoch": 116.55555555555556, "percentage": 26.22, "elapsed_time": "1:11:19", "remaining_time": "3:20:39", "throughput": 686.49, "total_tokens": 2937888} {"current_steps": 10495, "total_steps": 40000, "loss": 0.0, "lr": 4.197866778702426e-05, "epoch": 116.61111111111111, "percentage": 26.24, "elapsed_time": "1:11:21", "remaining_time": "3:20:36", "throughput": 686.5, "total_tokens": 2939264} {"current_steps": 10500, "total_steps": 40000, "loss": 0.0, "lr": 4.197146042485789e-05, "epoch": 116.66666666666667, "percentage": 26.25, "elapsed_time": "1:11:23", "remaining_time": "3:20:34", "throughput": 686.51, "total_tokens": 2940640} {"current_steps": 10505, "total_steps": 40000, "loss": 0.0, "lr": 4.1964250445479046e-05, "epoch": 116.72222222222223, "percentage": 26.26, "elapsed_time": "1:11:25", "remaining_time": "3:20:32", "throughput": 686.52, "total_tokens": 2942048} {"current_steps": 10510, "total_steps": 40000, "loss": 0.0, "lr": 4.19570378499996e-05, "epoch": 116.77777777777777, "percentage": 26.27, "elapsed_time": "1:11:27", "remaining_time": "3:20:29", "throughput": 686.54, "total_tokens": 2943456} {"current_steps": 10515, "total_steps": 40000, "loss": 0.0, "lr": 4.194982263953182e-05, "epoch": 116.83333333333333, "percentage": 26.29, "elapsed_time": "1:11:29", "remaining_time": "3:20:27", "throughput": 686.56, "total_tokens": 2944896} {"current_steps": 10520, "total_steps": 40000, "loss": 0.0, "lr": 4.194260481518838e-05, "epoch": 116.88888888888889, "percentage": 26.3, "elapsed_time": "1:11:31", "remaining_time": "3:20:25", "throughput": 686.58, "total_tokens": 2946288} {"current_steps": 10525, "total_steps": 40000, "loss": 0.0, "lr": 4.1935384378082366e-05, "epoch": 116.94444444444444, "percentage": 26.31, "elapsed_time": "1:11:33", "remaining_time": "3:20:23", "throughput": 686.59, "total_tokens": 2947680} {"current_steps": 10530, "total_steps": 40000, "loss": 0.0, "lr": 4.1928161329327267e-05, "epoch": 117.0, "percentage": 26.32, "elapsed_time": "1:11:35", "remaining_time": "3:20:21", "throughput": 686.59, "total_tokens": 2949120} {"current_steps": 10535, "total_steps": 40000, "loss": 0.0, "lr": 4.1920935670036945e-05, "epoch": 117.05555555555556, "percentage": 26.34, "elapsed_time": "1:11:37", "remaining_time": "3:20:19", "throughput": 686.56, "total_tokens": 2950512} {"current_steps": 10540, "total_steps": 40000, "loss": 0.0, "lr": 4.1913707401325705e-05, "epoch": 117.11111111111111, "percentage": 26.35, "elapsed_time": "1:11:39", "remaining_time": "3:20:17", "throughput": 686.58, "total_tokens": 2951952} {"current_steps": 10545, "total_steps": 40000, "loss": 0.0, "lr": 4.1906476524308235e-05, "epoch": 117.16666666666667, "percentage": 26.36, "elapsed_time": "1:11:41", "remaining_time": "3:20:15", "throughput": 686.6, "total_tokens": 2953344} {"current_steps": 10550, "total_steps": 40000, "loss": 0.0, "lr": 4.189924304009962e-05, "epoch": 117.22222222222223, "percentage": 26.38, "elapsed_time": "1:11:43", "remaining_time": "3:20:12", "throughput": 686.61, "total_tokens": 2954720} {"current_steps": 10555, "total_steps": 40000, "loss": 0.0, "lr": 4.189200694981537e-05, "epoch": 117.27777777777777, "percentage": 26.39, "elapsed_time": "1:11:45", "remaining_time": "3:20:10", "throughput": 686.62, "total_tokens": 2956128} {"current_steps": 10560, "total_steps": 40000, "loss": 0.0, "lr": 4.188476825457136e-05, "epoch": 117.33333333333333, "percentage": 26.4, "elapsed_time": "1:11:47", "remaining_time": "3:20:08", "throughput": 686.62, "total_tokens": 2957488} {"current_steps": 10565, "total_steps": 40000, "loss": 0.0, "lr": 4.18775269554839e-05, "epoch": 117.38888888888889, "percentage": 26.41, "elapsed_time": "1:11:49", "remaining_time": "3:20:05", "throughput": 686.65, "total_tokens": 2958944} {"current_steps": 10570, "total_steps": 40000, "loss": 0.0, "lr": 4.187028305366969e-05, "epoch": 117.44444444444444, "percentage": 26.42, "elapsed_time": "1:11:51", "remaining_time": "3:20:03", "throughput": 686.67, "total_tokens": 2960352} {"current_steps": 10575, "total_steps": 40000, "loss": 0.0, "lr": 4.1863036550245824e-05, "epoch": 117.5, "percentage": 26.44, "elapsed_time": "1:11:53", "remaining_time": "3:20:01", "throughput": 686.69, "total_tokens": 2961792} {"current_steps": 10580, "total_steps": 40000, "loss": 0.0, "lr": 4.1855787446329806e-05, "epoch": 117.55555555555556, "percentage": 26.45, "elapsed_time": "1:11:55", "remaining_time": "3:19:58", "throughput": 686.71, "total_tokens": 2963200} {"current_steps": 10585, "total_steps": 40000, "loss": 0.0, "lr": 4.184853574303955e-05, "epoch": 117.61111111111111, "percentage": 26.46, "elapsed_time": "1:11:57", "remaining_time": "3:19:56", "throughput": 686.73, "total_tokens": 2964624} {"current_steps": 10590, "total_steps": 40000, "loss": 0.0, "lr": 4.184128144149334e-05, "epoch": 117.66666666666667, "percentage": 26.47, "elapsed_time": "1:11:58", "remaining_time": "3:19:54", "throughput": 686.75, "total_tokens": 2966048} {"current_steps": 10595, "total_steps": 40000, "loss": 0.0, "lr": 4.1834024542809896e-05, "epoch": 117.72222222222223, "percentage": 26.49, "elapsed_time": "1:12:00", "remaining_time": "3:19:52", "throughput": 686.77, "total_tokens": 2967456} {"current_steps": 10600, "total_steps": 40000, "loss": 0.0, "lr": 4.1826765048108315e-05, "epoch": 117.77777777777777, "percentage": 26.5, "elapsed_time": "1:12:02", "remaining_time": "3:19:49", "throughput": 686.78, "total_tokens": 2968832} {"current_steps": 10600, "total_steps": 40000, "eval_loss": 0.3207324147224426, "epoch": 117.77777777777777, "percentage": 26.5, "elapsed_time": "1:12:04", "remaining_time": "3:19:53", "throughput": 686.57, "total_tokens": 2968832} {"current_steps": 10605, "total_steps": 40000, "loss": 0.0, "lr": 4.181950295850811e-05, "epoch": 117.83333333333333, "percentage": 26.51, "elapsed_time": "1:12:07", "remaining_time": "3:19:54", "throughput": 686.39, "total_tokens": 2970240} {"current_steps": 10610, "total_steps": 40000, "loss": 0.0, "lr": 4.181223827512918e-05, "epoch": 117.88888888888889, "percentage": 26.52, "elapsed_time": "1:12:09", "remaining_time": "3:19:52", "throughput": 686.39, "total_tokens": 2971616} {"current_steps": 10615, "total_steps": 40000, "loss": 0.0, "lr": 4.180497099909183e-05, "epoch": 117.94444444444444, "percentage": 26.54, "elapsed_time": "1:12:11", "remaining_time": "3:19:50", "throughput": 686.4, "total_tokens": 2973040} {"current_steps": 10620, "total_steps": 40000, "loss": 0.0, "lr": 4.179770113151677e-05, "epoch": 118.0, "percentage": 26.55, "elapsed_time": "1:12:13", "remaining_time": "3:19:48", "throughput": 686.38, "total_tokens": 2974416} {"current_steps": 10625, "total_steps": 40000, "loss": 0.0, "lr": 4.179042867352511e-05, "epoch": 118.05555555555556, "percentage": 26.56, "elapsed_time": "1:12:15", "remaining_time": "3:19:46", "throughput": 686.36, "total_tokens": 2975872} {"current_steps": 10630, "total_steps": 40000, "loss": 0.0, "lr": 4.1783153626238334e-05, "epoch": 118.11111111111111, "percentage": 26.57, "elapsed_time": "1:12:17", "remaining_time": "3:19:44", "throughput": 686.37, "total_tokens": 2977232} {"current_steps": 10635, "total_steps": 40000, "loss": 0.0, "lr": 4.177587599077836e-05, "epoch": 118.16666666666667, "percentage": 26.59, "elapsed_time": "1:12:19", "remaining_time": "3:19:42", "throughput": 686.38, "total_tokens": 2978624} {"current_steps": 10640, "total_steps": 40000, "loss": 0.0, "lr": 4.1768595768267494e-05, "epoch": 118.22222222222223, "percentage": 26.6, "elapsed_time": "1:12:21", "remaining_time": "3:19:40", "throughput": 686.4, "total_tokens": 2980048} {"current_steps": 10645, "total_steps": 40000, "loss": 0.0, "lr": 4.176131295982843e-05, "epoch": 118.27777777777777, "percentage": 26.61, "elapsed_time": "1:12:23", "remaining_time": "3:19:37", "throughput": 686.42, "total_tokens": 2981456} {"current_steps": 10650, "total_steps": 40000, "loss": 0.0, "lr": 4.1754027566584276e-05, "epoch": 118.33333333333333, "percentage": 26.62, "elapsed_time": "1:12:25", "remaining_time": "3:19:35", "throughput": 686.42, "total_tokens": 2982816} {"current_steps": 10655, "total_steps": 40000, "loss": 0.0, "lr": 4.174673958965852e-05, "epoch": 118.38888888888889, "percentage": 26.64, "elapsed_time": "1:12:27", "remaining_time": "3:19:33", "throughput": 686.45, "total_tokens": 2984240} {"current_steps": 10660, "total_steps": 40000, "loss": 0.0, "lr": 4.173944903017507e-05, "epoch": 118.44444444444444, "percentage": 26.65, "elapsed_time": "1:12:29", "remaining_time": "3:19:30", "throughput": 686.47, "total_tokens": 2985664} {"current_steps": 10665, "total_steps": 40000, "loss": 0.0, "lr": 4.173215588925822e-05, "epoch": 118.5, "percentage": 26.66, "elapsed_time": "1:12:31", "remaining_time": "3:19:28", "throughput": 686.48, "total_tokens": 2987072} {"current_steps": 10670, "total_steps": 40000, "loss": 0.0, "lr": 4.172486016803266e-05, "epoch": 118.55555555555556, "percentage": 26.67, "elapsed_time": "1:12:33", "remaining_time": "3:19:26", "throughput": 686.5, "total_tokens": 2988480} {"current_steps": 10675, "total_steps": 40000, "loss": 0.0, "lr": 4.171756186762349e-05, "epoch": 118.61111111111111, "percentage": 26.69, "elapsed_time": "1:12:35", "remaining_time": "3:19:23", "throughput": 686.53, "total_tokens": 2989952} {"current_steps": 10680, "total_steps": 40000, "loss": 0.0, "lr": 4.171026098915619e-05, "epoch": 118.66666666666667, "percentage": 26.7, "elapsed_time": "1:12:37", "remaining_time": "3:19:21", "throughput": 686.54, "total_tokens": 2991344} {"current_steps": 10685, "total_steps": 40000, "loss": 0.0, "lr": 4.170295753375665e-05, "epoch": 118.72222222222223, "percentage": 26.71, "elapsed_time": "1:12:39", "remaining_time": "3:19:19", "throughput": 686.56, "total_tokens": 2992736} {"current_steps": 10690, "total_steps": 40000, "loss": 0.0, "lr": 4.169565150255117e-05, "epoch": 118.77777777777777, "percentage": 26.72, "elapsed_time": "1:12:40", "remaining_time": "3:19:17", "throughput": 686.57, "total_tokens": 2994144} {"current_steps": 10695, "total_steps": 40000, "loss": 0.0, "lr": 4.16883428966664e-05, "epoch": 118.83333333333333, "percentage": 26.74, "elapsed_time": "1:12:42", "remaining_time": "3:19:14", "throughput": 686.58, "total_tokens": 2995504} {"current_steps": 10700, "total_steps": 40000, "loss": 0.0, "lr": 4.168103171722944e-05, "epoch": 118.88888888888889, "percentage": 26.75, "elapsed_time": "1:12:44", "remaining_time": "3:19:12", "throughput": 686.59, "total_tokens": 2996896} {"current_steps": 10705, "total_steps": 40000, "loss": 0.0, "lr": 4.167371796536777e-05, "epoch": 118.94444444444444, "percentage": 26.76, "elapsed_time": "1:12:46", "remaining_time": "3:19:10", "throughput": 686.6, "total_tokens": 2998288} {"current_steps": 10710, "total_steps": 40000, "loss": 0.0, "lr": 4.166640164220924e-05, "epoch": 119.0, "percentage": 26.77, "elapsed_time": "1:12:48", "remaining_time": "3:19:08", "throughput": 686.58, "total_tokens": 2999664} {"current_steps": 10715, "total_steps": 40000, "loss": 0.0, "lr": 4.1659082748882144e-05, "epoch": 119.05555555555556, "percentage": 26.79, "elapsed_time": "1:12:51", "remaining_time": "3:19:06", "throughput": 686.55, "total_tokens": 3001056} {"current_steps": 10720, "total_steps": 40000, "loss": 0.0, "lr": 4.1651761286515135e-05, "epoch": 119.11111111111111, "percentage": 26.8, "elapsed_time": "1:12:53", "remaining_time": "3:19:04", "throughput": 686.57, "total_tokens": 3002464} {"current_steps": 10725, "total_steps": 40000, "loss": 0.0, "lr": 4.164443725623728e-05, "epoch": 119.16666666666667, "percentage": 26.81, "elapsed_time": "1:12:55", "remaining_time": "3:19:02", "throughput": 686.58, "total_tokens": 3003856} {"current_steps": 10730, "total_steps": 40000, "loss": 0.0, "lr": 4.163711065917802e-05, "epoch": 119.22222222222223, "percentage": 26.82, "elapsed_time": "1:12:57", "remaining_time": "3:18:59", "throughput": 686.61, "total_tokens": 3005280} {"current_steps": 10735, "total_steps": 40000, "loss": 0.0, "lr": 4.1629781496467234e-05, "epoch": 119.27777777777777, "percentage": 26.84, "elapsed_time": "1:12:58", "remaining_time": "3:18:57", "throughput": 686.62, "total_tokens": 3006672} {"current_steps": 10740, "total_steps": 40000, "loss": 0.0, "lr": 4.1622449769235164e-05, "epoch": 119.33333333333333, "percentage": 26.85, "elapsed_time": "1:13:00", "remaining_time": "3:18:55", "throughput": 686.64, "total_tokens": 3008096} {"current_steps": 10745, "total_steps": 40000, "loss": 0.0, "lr": 4.161511547861243e-05, "epoch": 119.38888888888889, "percentage": 26.86, "elapsed_time": "1:13:02", "remaining_time": "3:18:53", "throughput": 686.66, "total_tokens": 3009536} {"current_steps": 10750, "total_steps": 40000, "loss": 0.0, "lr": 4.1607778625730104e-05, "epoch": 119.44444444444444, "percentage": 26.88, "elapsed_time": "1:13:04", "remaining_time": "3:18:50", "throughput": 686.67, "total_tokens": 3010896} {"current_steps": 10755, "total_steps": 40000, "loss": 0.0, "lr": 4.160043921171961e-05, "epoch": 119.5, "percentage": 26.89, "elapsed_time": "1:13:06", "remaining_time": "3:18:48", "throughput": 686.67, "total_tokens": 3012256} {"current_steps": 10760, "total_steps": 40000, "loss": 0.0, "lr": 4.159309723771276e-05, "epoch": 119.55555555555556, "percentage": 26.9, "elapsed_time": "1:13:08", "remaining_time": "3:18:46", "throughput": 686.68, "total_tokens": 3013632} {"current_steps": 10765, "total_steps": 40000, "loss": 0.0, "lr": 4.158575270484181e-05, "epoch": 119.61111111111111, "percentage": 26.91, "elapsed_time": "1:13:10", "remaining_time": "3:18:43", "throughput": 686.7, "total_tokens": 3015056} {"current_steps": 10770, "total_steps": 40000, "loss": 0.0, "lr": 4.157840561423936e-05, "epoch": 119.66666666666667, "percentage": 26.92, "elapsed_time": "1:13:12", "remaining_time": "3:18:41", "throughput": 686.72, "total_tokens": 3016496} {"current_steps": 10775, "total_steps": 40000, "loss": 0.0, "lr": 4.1571055967038416e-05, "epoch": 119.72222222222223, "percentage": 26.94, "elapsed_time": "1:13:14", "remaining_time": "3:18:39", "throughput": 686.74, "total_tokens": 3017904} {"current_steps": 10780, "total_steps": 40000, "loss": 0.0, "lr": 4.156370376437241e-05, "epoch": 119.77777777777777, "percentage": 26.95, "elapsed_time": "1:13:16", "remaining_time": "3:18:37", "throughput": 686.75, "total_tokens": 3019280} {"current_steps": 10785, "total_steps": 40000, "loss": 0.0, "lr": 4.155634900737513e-05, "epoch": 119.83333333333333, "percentage": 26.96, "elapsed_time": "1:13:18", "remaining_time": "3:18:34", "throughput": 686.77, "total_tokens": 3020720} {"current_steps": 10790, "total_steps": 40000, "loss": 0.0, "lr": 4.1548991697180764e-05, "epoch": 119.88888888888889, "percentage": 26.97, "elapsed_time": "1:13:20", "remaining_time": "3:18:32", "throughput": 686.77, "total_tokens": 3022064} {"current_steps": 10795, "total_steps": 40000, "loss": 0.0, "lr": 4.1541631834923914e-05, "epoch": 119.94444444444444, "percentage": 26.99, "elapsed_time": "1:13:22", "remaining_time": "3:18:30", "throughput": 686.79, "total_tokens": 3023488} {"current_steps": 10800, "total_steps": 40000, "loss": 0.0, "lr": 4.153426942173956e-05, "epoch": 120.0, "percentage": 27.0, "elapsed_time": "1:13:24", "remaining_time": "3:18:28", "throughput": 686.78, "total_tokens": 3024896} {"current_steps": 10800, "total_steps": 40000, "eval_loss": 0.28891822695732117, "epoch": 120.0, "percentage": 27.0, "elapsed_time": "1:13:25", "remaining_time": "3:18:31", "throughput": 686.58, "total_tokens": 3024896} {"current_steps": 10805, "total_steps": 40000, "loss": 0.0, "lr": 4.152690445876308e-05, "epoch": 120.05555555555556, "percentage": 27.01, "elapsed_time": "1:13:30", "remaining_time": "3:18:38", "throughput": 686.09, "total_tokens": 3026320} {"current_steps": 10810, "total_steps": 40000, "loss": 0.0, "lr": 4.1519536947130245e-05, "epoch": 120.11111111111111, "percentage": 27.02, "elapsed_time": "1:13:33", "remaining_time": "3:18:36", "throughput": 686.08, "total_tokens": 3027696} {"current_steps": 10815, "total_steps": 40000, "loss": 0.0, "lr": 4.151216688797722e-05, "epoch": 120.16666666666667, "percentage": 27.04, "elapsed_time": "1:13:34", "remaining_time": "3:18:34", "throughput": 686.1, "total_tokens": 3029136} {"current_steps": 10820, "total_steps": 40000, "loss": 0.0, "lr": 4.150479428244054e-05, "epoch": 120.22222222222223, "percentage": 27.05, "elapsed_time": "1:13:36", "remaining_time": "3:18:31", "throughput": 686.14, "total_tokens": 3030608} {"current_steps": 10825, "total_steps": 40000, "loss": 0.0, "lr": 4.1497419131657176e-05, "epoch": 120.27777777777777, "percentage": 27.06, "elapsed_time": "1:13:38", "remaining_time": "3:18:29", "throughput": 686.15, "total_tokens": 3032016} {"current_steps": 10830, "total_steps": 40000, "loss": 0.0, "lr": 4.149004143676447e-05, "epoch": 120.33333333333333, "percentage": 27.07, "elapsed_time": "1:13:40", "remaining_time": "3:18:27", "throughput": 686.18, "total_tokens": 3033456} {"current_steps": 10835, "total_steps": 40000, "loss": 0.0, "lr": 4.148266119890015e-05, "epoch": 120.38888888888889, "percentage": 27.09, "elapsed_time": "1:13:42", "remaining_time": "3:18:24", "throughput": 686.2, "total_tokens": 3034912} {"current_steps": 10840, "total_steps": 40000, "loss": 0.0, "lr": 4.1475278419202324e-05, "epoch": 120.44444444444444, "percentage": 27.1, "elapsed_time": "1:13:44", "remaining_time": "3:18:22", "throughput": 686.23, "total_tokens": 3036352} {"current_steps": 10845, "total_steps": 40000, "loss": 0.0, "lr": 4.146789309880953e-05, "epoch": 120.5, "percentage": 27.11, "elapsed_time": "1:13:46", "remaining_time": "3:18:20", "throughput": 686.23, "total_tokens": 3037712} {"current_steps": 10850, "total_steps": 40000, "loss": 0.0, "lr": 4.146050523886068e-05, "epoch": 120.55555555555556, "percentage": 27.12, "elapsed_time": "1:13:48", "remaining_time": "3:18:18", "throughput": 686.25, "total_tokens": 3039120} {"current_steps": 10855, "total_steps": 40000, "loss": 0.0, "lr": 4.1453114840495055e-05, "epoch": 120.61111111111111, "percentage": 27.14, "elapsed_time": "1:13:50", "remaining_time": "3:18:15", "throughput": 686.26, "total_tokens": 3040512} {"current_steps": 10860, "total_steps": 40000, "loss": 0.0, "lr": 4.1445721904852364e-05, "epoch": 120.66666666666667, "percentage": 27.15, "elapsed_time": "1:13:52", "remaining_time": "3:18:13", "throughput": 686.29, "total_tokens": 3041984} {"current_steps": 10865, "total_steps": 40000, "loss": 0.0, "lr": 4.143832643307269e-05, "epoch": 120.72222222222223, "percentage": 27.16, "elapsed_time": "1:13:54", "remaining_time": "3:18:11", "throughput": 686.3, "total_tokens": 3043392} {"current_steps": 10870, "total_steps": 40000, "loss": 0.0, "lr": 4.1430928426296503e-05, "epoch": 120.77777777777777, "percentage": 27.18, "elapsed_time": "1:13:56", "remaining_time": "3:18:08", "throughput": 686.31, "total_tokens": 3044752} {"current_steps": 10875, "total_steps": 40000, "loss": 0.0, "lr": 4.142352788566466e-05, "epoch": 120.83333333333333, "percentage": 27.19, "elapsed_time": "1:13:58", "remaining_time": "3:18:06", "throughput": 686.31, "total_tokens": 3046096} {"current_steps": 10880, "total_steps": 40000, "loss": 0.0, "lr": 4.1416124812318424e-05, "epoch": 120.88888888888889, "percentage": 27.2, "elapsed_time": "1:14:00", "remaining_time": "3:18:04", "throughput": 686.31, "total_tokens": 3047440} {"current_steps": 10885, "total_steps": 40000, "loss": 0.0, "lr": 4.1408719207399453e-05, "epoch": 120.94444444444444, "percentage": 27.21, "elapsed_time": "1:14:02", "remaining_time": "3:18:03", "throughput": 686.26, "total_tokens": 3048848} {"current_steps": 10890, "total_steps": 40000, "loss": 0.0, "lr": 4.140131107204978e-05, "epoch": 121.0, "percentage": 27.22, "elapsed_time": "1:14:04", "remaining_time": "3:18:01", "throughput": 686.24, "total_tokens": 3050240} {"current_steps": 10895, "total_steps": 40000, "loss": 0.0, "lr": 4.139390040741182e-05, "epoch": 121.05555555555556, "percentage": 27.24, "elapsed_time": "1:14:07", "remaining_time": "3:17:59", "throughput": 686.21, "total_tokens": 3051616} {"current_steps": 10900, "total_steps": 40000, "loss": 0.0, "lr": 4.1386487214628396e-05, "epoch": 121.11111111111111, "percentage": 27.25, "elapsed_time": "1:14:08", "remaining_time": "3:17:57", "throughput": 686.23, "total_tokens": 3053008} {"current_steps": 10905, "total_steps": 40000, "loss": 0.0, "lr": 4.137907149484272e-05, "epoch": 121.16666666666667, "percentage": 27.26, "elapsed_time": "1:14:10", "remaining_time": "3:17:55", "throughput": 686.23, "total_tokens": 3054384} {"current_steps": 10910, "total_steps": 40000, "loss": 0.0, "lr": 4.137165324919839e-05, "epoch": 121.22222222222223, "percentage": 27.27, "elapsed_time": "1:14:12", "remaining_time": "3:17:52", "throughput": 686.25, "total_tokens": 3055776} {"current_steps": 10915, "total_steps": 40000, "loss": 0.0, "lr": 4.136423247883939e-05, "epoch": 121.27777777777777, "percentage": 27.29, "elapsed_time": "1:14:14", "remaining_time": "3:17:50", "throughput": 686.26, "total_tokens": 3057168} {"current_steps": 10920, "total_steps": 40000, "loss": 0.0, "lr": 4.135680918491009e-05, "epoch": 121.33333333333333, "percentage": 27.3, "elapsed_time": "1:14:16", "remaining_time": "3:17:48", "throughput": 686.28, "total_tokens": 3058608} {"current_steps": 10925, "total_steps": 40000, "loss": 0.0, "lr": 4.1349383368555265e-05, "epoch": 121.38888888888889, "percentage": 27.31, "elapsed_time": "1:14:18", "remaining_time": "3:17:46", "throughput": 686.3, "total_tokens": 3060000} {"current_steps": 10930, "total_steps": 40000, "loss": 0.0, "lr": 4.1341955030920065e-05, "epoch": 121.44444444444444, "percentage": 27.32, "elapsed_time": "1:14:20", "remaining_time": "3:17:43", "throughput": 686.31, "total_tokens": 3061408} {"current_steps": 10935, "total_steps": 40000, "loss": 0.0, "lr": 4.1334524173150036e-05, "epoch": 121.5, "percentage": 27.34, "elapsed_time": "1:14:22", "remaining_time": "3:17:41", "throughput": 686.32, "total_tokens": 3062768} {"current_steps": 10940, "total_steps": 40000, "loss": 0.0, "lr": 4.13270907963911e-05, "epoch": 121.55555555555556, "percentage": 27.35, "elapsed_time": "1:14:24", "remaining_time": "3:17:39", "throughput": 686.33, "total_tokens": 3064176} {"current_steps": 10945, "total_steps": 40000, "loss": 0.0, "lr": 4.131965490178959e-05, "epoch": 121.61111111111111, "percentage": 27.36, "elapsed_time": "1:14:26", "remaining_time": "3:17:36", "throughput": 686.34, "total_tokens": 3065552} {"current_steps": 10950, "total_steps": 40000, "loss": 0.0, "lr": 4.131221649049222e-05, "epoch": 121.66666666666667, "percentage": 27.38, "elapsed_time": "1:14:28", "remaining_time": "3:17:34", "throughput": 686.36, "total_tokens": 3066960} {"current_steps": 10955, "total_steps": 40000, "loss": 0.0, "lr": 4.130477556364606e-05, "epoch": 121.72222222222223, "percentage": 27.39, "elapsed_time": "1:14:30", "remaining_time": "3:17:32", "throughput": 686.37, "total_tokens": 3068368} {"current_steps": 10960, "total_steps": 40000, "loss": 0.0, "lr": 4.129733212239861e-05, "epoch": 121.77777777777777, "percentage": 27.4, "elapsed_time": "1:14:32", "remaining_time": "3:17:30", "throughput": 686.38, "total_tokens": 3069744} {"current_steps": 10965, "total_steps": 40000, "loss": 0.0, "lr": 4.128988616789774e-05, "epoch": 121.83333333333333, "percentage": 27.41, "elapsed_time": "1:14:34", "remaining_time": "3:17:27", "throughput": 686.4, "total_tokens": 3071168} {"current_steps": 10970, "total_steps": 40000, "loss": 0.0, "lr": 4.1282437701291724e-05, "epoch": 121.88888888888889, "percentage": 27.43, "elapsed_time": "1:14:36", "remaining_time": "3:17:25", "throughput": 686.42, "total_tokens": 3072576} {"current_steps": 10975, "total_steps": 40000, "loss": 0.0, "lr": 4.1274986723729184e-05, "epoch": 121.94444444444444, "percentage": 27.44, "elapsed_time": "1:14:38", "remaining_time": "3:17:23", "throughput": 686.43, "total_tokens": 3073968} {"current_steps": 10980, "total_steps": 40000, "loss": 0.0, "lr": 4.126753323635917e-05, "epoch": 122.0, "percentage": 27.45, "elapsed_time": "1:14:40", "remaining_time": "3:17:21", "throughput": 686.43, "total_tokens": 3075392} {"current_steps": 10985, "total_steps": 40000, "loss": 0.0, "lr": 4.12600772403311e-05, "epoch": 122.05555555555556, "percentage": 27.46, "elapsed_time": "1:14:42", "remaining_time": "3:17:19", "throughput": 686.4, "total_tokens": 3076800} {"current_steps": 10990, "total_steps": 40000, "loss": 0.0, "lr": 4.125261873679479e-05, "epoch": 122.11111111111111, "percentage": 27.47, "elapsed_time": "1:14:44", "remaining_time": "3:17:17", "throughput": 686.43, "total_tokens": 3078256} {"current_steps": 10995, "total_steps": 40000, "loss": 0.0, "lr": 4.124515772690042e-05, "epoch": 122.16666666666667, "percentage": 27.49, "elapsed_time": "1:14:46", "remaining_time": "3:17:15", "throughput": 686.45, "total_tokens": 3079680} {"current_steps": 11000, "total_steps": 40000, "loss": 0.0, "lr": 4.123769421179858e-05, "epoch": 122.22222222222223, "percentage": 27.5, "elapsed_time": "1:14:48", "remaining_time": "3:17:12", "throughput": 686.46, "total_tokens": 3081056} {"current_steps": 11000, "total_steps": 40000, "eval_loss": 0.3320853114128113, "epoch": 122.22222222222223, "percentage": 27.5, "elapsed_time": "1:14:49", "remaining_time": "3:17:16", "throughput": 686.25, "total_tokens": 3081056} {"current_steps": 11005, "total_steps": 40000, "loss": 0.0, "lr": 4.1230228192640236e-05, "epoch": 122.27777777777777, "percentage": 27.51, "elapsed_time": "1:14:52", "remaining_time": "3:17:17", "throughput": 686.07, "total_tokens": 3082464} {"current_steps": 11010, "total_steps": 40000, "loss": 0.0, "lr": 4.122275967057675e-05, "epoch": 122.33333333333333, "percentage": 27.52, "elapsed_time": "1:14:54", "remaining_time": "3:17:15", "throughput": 686.08, "total_tokens": 3083904} {"current_steps": 11015, "total_steps": 40000, "loss": 0.0, "lr": 4.1215288646759846e-05, "epoch": 122.38888888888889, "percentage": 27.54, "elapsed_time": "1:14:56", "remaining_time": "3:17:13", "throughput": 686.09, "total_tokens": 3085296} {"current_steps": 11020, "total_steps": 40000, "loss": 0.0, "lr": 4.120781512234166e-05, "epoch": 122.44444444444444, "percentage": 27.55, "elapsed_time": "1:14:58", "remaining_time": "3:17:10", "throughput": 686.1, "total_tokens": 3086688} {"current_steps": 11025, "total_steps": 40000, "loss": 0.0, "lr": 4.120033909847471e-05, "epoch": 122.5, "percentage": 27.56, "elapsed_time": "1:15:00", "remaining_time": "3:17:08", "throughput": 686.11, "total_tokens": 3088096} {"current_steps": 11030, "total_steps": 40000, "loss": 0.0, "lr": 4.119286057631187e-05, "epoch": 122.55555555555556, "percentage": 27.57, "elapsed_time": "1:15:02", "remaining_time": "3:17:06", "throughput": 686.13, "total_tokens": 3089504} {"current_steps": 11035, "total_steps": 40000, "loss": 0.0, "lr": 4.118537955700646e-05, "epoch": 122.61111111111111, "percentage": 27.59, "elapsed_time": "1:15:04", "remaining_time": "3:17:04", "throughput": 686.13, "total_tokens": 3090864} {"current_steps": 11040, "total_steps": 40000, "loss": 0.0, "lr": 4.11778960417121e-05, "epoch": 122.66666666666667, "percentage": 27.6, "elapsed_time": "1:15:06", "remaining_time": "3:17:01", "throughput": 686.15, "total_tokens": 3092272} {"current_steps": 11045, "total_steps": 40000, "loss": 0.0, "lr": 4.117041003158288e-05, "epoch": 122.72222222222223, "percentage": 27.61, "elapsed_time": "1:15:08", "remaining_time": "3:16:59", "throughput": 686.17, "total_tokens": 3093696} {"current_steps": 11050, "total_steps": 40000, "loss": 0.0, "lr": 4.1162921527773215e-05, "epoch": 122.77777777777777, "percentage": 27.62, "elapsed_time": "1:15:10", "remaining_time": "3:16:57", "throughput": 686.18, "total_tokens": 3095072} {"current_steps": 11055, "total_steps": 40000, "loss": 0.0, "lr": 4.115543053143794e-05, "epoch": 122.83333333333333, "percentage": 27.64, "elapsed_time": "1:15:12", "remaining_time": "3:16:55", "throughput": 686.19, "total_tokens": 3096464} {"current_steps": 11060, "total_steps": 40000, "loss": 0.0, "lr": 4.114793704373226e-05, "epoch": 122.88888888888889, "percentage": 27.65, "elapsed_time": "1:15:14", "remaining_time": "3:16:52", "throughput": 686.2, "total_tokens": 3097856} {"current_steps": 11065, "total_steps": 40000, "loss": 0.0, "lr": 4.114044106581175e-05, "epoch": 122.94444444444444, "percentage": 27.66, "elapsed_time": "1:15:16", "remaining_time": "3:16:50", "throughput": 686.21, "total_tokens": 3099232} {"current_steps": 11070, "total_steps": 40000, "loss": 0.0, "lr": 4.11329425988324e-05, "epoch": 123.0, "percentage": 27.68, "elapsed_time": "1:15:18", "remaining_time": "3:16:48", "throughput": 686.2, "total_tokens": 3100640} {"current_steps": 11075, "total_steps": 40000, "loss": 0.0, "lr": 4.112544164395056e-05, "epoch": 123.05555555555556, "percentage": 27.69, "elapsed_time": "1:15:20", "remaining_time": "3:16:47", "throughput": 686.17, "total_tokens": 3102048} {"current_steps": 11080, "total_steps": 40000, "loss": 0.0, "lr": 4.111793820232297e-05, "epoch": 123.11111111111111, "percentage": 27.7, "elapsed_time": "1:15:22", "remaining_time": "3:16:44", "throughput": 686.18, "total_tokens": 3103408} {"current_steps": 11085, "total_steps": 40000, "loss": 0.0, "lr": 4.1110432275106767e-05, "epoch": 123.16666666666667, "percentage": 27.71, "elapsed_time": "1:15:24", "remaining_time": "3:16:42", "throughput": 686.19, "total_tokens": 3104784} {"current_steps": 11090, "total_steps": 40000, "loss": 0.0, "lr": 4.110292386345944e-05, "epoch": 123.22222222222223, "percentage": 27.73, "elapsed_time": "1:15:26", "remaining_time": "3:16:40", "throughput": 686.2, "total_tokens": 3106176} {"current_steps": 11095, "total_steps": 40000, "loss": 0.0, "lr": 4.109541296853891e-05, "epoch": 123.27777777777777, "percentage": 27.74, "elapsed_time": "1:15:28", "remaining_time": "3:16:37", "throughput": 686.22, "total_tokens": 3107584} {"current_steps": 11100, "total_steps": 40000, "loss": 0.0, "lr": 4.108789959150341e-05, "epoch": 123.33333333333333, "percentage": 27.75, "elapsed_time": "1:15:30", "remaining_time": "3:16:35", "throughput": 686.23, "total_tokens": 3108976} {"current_steps": 11105, "total_steps": 40000, "loss": 0.0, "lr": 4.108038373351163e-05, "epoch": 123.38888888888889, "percentage": 27.76, "elapsed_time": "1:15:32", "remaining_time": "3:16:33", "throughput": 686.25, "total_tokens": 3110416} {"current_steps": 11110, "total_steps": 40000, "loss": 0.0, "lr": 4.10728653957226e-05, "epoch": 123.44444444444444, "percentage": 27.77, "elapsed_time": "1:15:34", "remaining_time": "3:16:31", "throughput": 686.27, "total_tokens": 3111808} {"current_steps": 11115, "total_steps": 40000, "loss": 0.0, "lr": 4.106534457929575e-05, "epoch": 123.5, "percentage": 27.79, "elapsed_time": "1:15:36", "remaining_time": "3:16:28", "throughput": 686.29, "total_tokens": 3113248} {"current_steps": 11120, "total_steps": 40000, "loss": 0.0, "lr": 4.105782128539086e-05, "epoch": 123.55555555555556, "percentage": 27.8, "elapsed_time": "1:15:38", "remaining_time": "3:16:26", "throughput": 686.31, "total_tokens": 3114688} {"current_steps": 11125, "total_steps": 40000, "loss": 0.0, "lr": 4.1050295515168144e-05, "epoch": 123.61111111111111, "percentage": 27.81, "elapsed_time": "1:15:40", "remaining_time": "3:16:24", "throughput": 686.32, "total_tokens": 3116048} {"current_steps": 11130, "total_steps": 40000, "loss": 0.0, "lr": 4.1042767269788155e-05, "epoch": 123.66666666666667, "percentage": 27.82, "elapsed_time": "1:15:42", "remaining_time": "3:16:21", "throughput": 686.33, "total_tokens": 3117424} {"current_steps": 11135, "total_steps": 40000, "loss": 0.0, "lr": 4.103523655041185e-05, "epoch": 123.72222222222223, "percentage": 27.84, "elapsed_time": "1:15:44", "remaining_time": "3:16:19", "throughput": 686.34, "total_tokens": 3118832} {"current_steps": 11140, "total_steps": 40000, "loss": 0.0, "lr": 4.102770335820055e-05, "epoch": 123.77777777777777, "percentage": 27.85, "elapsed_time": "1:15:46", "remaining_time": "3:16:17", "throughput": 686.36, "total_tokens": 3120256} {"current_steps": 11145, "total_steps": 40000, "loss": 0.0, "lr": 4.1020167694315984e-05, "epoch": 123.83333333333333, "percentage": 27.86, "elapsed_time": "1:15:48", "remaining_time": "3:16:15", "throughput": 686.38, "total_tokens": 3121648} {"current_steps": 11150, "total_steps": 40000, "loss": 0.0, "lr": 4.101262955992023e-05, "epoch": 123.88888888888889, "percentage": 27.88, "elapsed_time": "1:15:49", "remaining_time": "3:16:12", "throughput": 686.39, "total_tokens": 3123056} {"current_steps": 11155, "total_steps": 40000, "loss": 0.0, "lr": 4.100508895617578e-05, "epoch": 123.94444444444444, "percentage": 27.89, "elapsed_time": "1:15:51", "remaining_time": "3:16:10", "throughput": 686.4, "total_tokens": 3124432} {"current_steps": 11160, "total_steps": 40000, "loss": 0.0, "lr": 4.099754588424547e-05, "epoch": 124.0, "percentage": 27.9, "elapsed_time": "1:15:54", "remaining_time": "3:16:08", "throughput": 686.38, "total_tokens": 3125808} {"current_steps": 11165, "total_steps": 40000, "loss": 0.0, "lr": 4.0990000345292546e-05, "epoch": 124.05555555555556, "percentage": 27.91, "elapsed_time": "1:15:56", "remaining_time": "3:16:07", "throughput": 686.35, "total_tokens": 3127184} {"current_steps": 11170, "total_steps": 40000, "loss": 0.0, "lr": 4.098245234048064e-05, "epoch": 124.11111111111111, "percentage": 27.93, "elapsed_time": "1:15:58", "remaining_time": "3:16:04", "throughput": 686.37, "total_tokens": 3128624} {"current_steps": 11175, "total_steps": 40000, "loss": 0.0, "lr": 4.0974901870973726e-05, "epoch": 124.16666666666667, "percentage": 27.94, "elapsed_time": "1:16:00", "remaining_time": "3:16:02", "throughput": 686.38, "total_tokens": 3130016} {"current_steps": 11180, "total_steps": 40000, "loss": 0.0, "lr": 4.096734893793619e-05, "epoch": 124.22222222222223, "percentage": 27.95, "elapsed_time": "1:16:02", "remaining_time": "3:16:00", "throughput": 686.4, "total_tokens": 3131424} {"current_steps": 11185, "total_steps": 40000, "loss": 0.0, "lr": 4.095979354253279e-05, "epoch": 124.27777777777777, "percentage": 27.96, "elapsed_time": "1:16:04", "remaining_time": "3:15:58", "throughput": 686.4, "total_tokens": 3132784} {"current_steps": 11190, "total_steps": 40000, "loss": 0.0, "lr": 4.0952235685928656e-05, "epoch": 124.33333333333333, "percentage": 27.98, "elapsed_time": "1:16:05", "remaining_time": "3:15:55", "throughput": 686.42, "total_tokens": 3134176} {"current_steps": 11195, "total_steps": 40000, "loss": 0.0, "lr": 4.094467536928932e-05, "epoch": 124.38888888888889, "percentage": 27.99, "elapsed_time": "1:16:07", "remaining_time": "3:15:53", "throughput": 686.43, "total_tokens": 3135568} {"current_steps": 11200, "total_steps": 40000, "loss": 0.0, "lr": 4.093711259378067e-05, "epoch": 124.44444444444444, "percentage": 28.0, "elapsed_time": "1:16:09", "remaining_time": "3:15:51", "throughput": 686.44, "total_tokens": 3136944} {"current_steps": 11200, "total_steps": 40000, "eval_loss": 0.3126493990421295, "epoch": 124.44444444444444, "percentage": 28.0, "elapsed_time": "1:16:11", "remaining_time": "3:15:54", "throughput": 686.24, "total_tokens": 3136944} {"current_steps": 11205, "total_steps": 40000, "loss": 0.0, "lr": 4.092954736056897e-05, "epoch": 124.5, "percentage": 28.01, "elapsed_time": "1:16:14", "remaining_time": "3:15:55", "throughput": 686.07, "total_tokens": 3138368} {"current_steps": 11210, "total_steps": 40000, "loss": 0.0, "lr": 4.09219796708209e-05, "epoch": 124.55555555555556, "percentage": 28.02, "elapsed_time": "1:16:16", "remaining_time": "3:15:53", "throughput": 686.07, "total_tokens": 3139776} {"current_steps": 11215, "total_steps": 40000, "loss": 0.0, "lr": 4.0914409525703464e-05, "epoch": 124.61111111111111, "percentage": 28.04, "elapsed_time": "1:16:18", "remaining_time": "3:15:51", "throughput": 686.09, "total_tokens": 3141184} {"current_steps": 11220, "total_steps": 40000, "loss": 0.0, "lr": 4.090683692638408e-05, "epoch": 124.66666666666667, "percentage": 28.05, "elapsed_time": "1:16:20", "remaining_time": "3:15:48", "throughput": 686.1, "total_tokens": 3142592} {"current_steps": 11225, "total_steps": 40000, "loss": 0.0, "lr": 4.089926187403056e-05, "epoch": 124.72222222222223, "percentage": 28.06, "elapsed_time": "1:16:22", "remaining_time": "3:15:46", "throughput": 686.13, "total_tokens": 3144032} {"current_steps": 11230, "total_steps": 40000, "loss": 0.0, "lr": 4.0891684369811044e-05, "epoch": 124.77777777777777, "percentage": 28.07, "elapsed_time": "1:16:24", "remaining_time": "3:15:44", "throughput": 686.14, "total_tokens": 3145440} {"current_steps": 11235, "total_steps": 40000, "loss": 0.0, "lr": 4.0884104414894107e-05, "epoch": 124.83333333333333, "percentage": 28.09, "elapsed_time": "1:16:26", "remaining_time": "3:15:42", "throughput": 686.15, "total_tokens": 3146816} {"current_steps": 11240, "total_steps": 40000, "loss": 0.0, "lr": 4.087652201044864e-05, "epoch": 124.88888888888889, "percentage": 28.1, "elapsed_time": "1:16:28", "remaining_time": "3:15:39", "throughput": 686.16, "total_tokens": 3148208} {"current_steps": 11245, "total_steps": 40000, "loss": 0.0, "lr": 4.086893715764397e-05, "epoch": 124.94444444444444, "percentage": 28.11, "elapsed_time": "1:16:30", "remaining_time": "3:15:37", "throughput": 686.17, "total_tokens": 3149600} {"current_steps": 11250, "total_steps": 40000, "loss": 0.0, "lr": 4.086134985764977e-05, "epoch": 125.0, "percentage": 28.12, "elapsed_time": "1:16:32", "remaining_time": "3:15:35", "throughput": 686.16, "total_tokens": 3151008} {"current_steps": 11255, "total_steps": 40000, "loss": 0.0, "lr": 4.0853760111636085e-05, "epoch": 125.05555555555556, "percentage": 28.14, "elapsed_time": "1:16:34", "remaining_time": "3:15:34", "throughput": 686.13, "total_tokens": 3152400} {"current_steps": 11260, "total_steps": 40000, "loss": 0.0, "lr": 4.084616792077337e-05, "epoch": 125.11111111111111, "percentage": 28.15, "elapsed_time": "1:16:36", "remaining_time": "3:15:31", "throughput": 686.15, "total_tokens": 3153792} {"current_steps": 11265, "total_steps": 40000, "loss": 0.0, "lr": 4.083857328623243e-05, "epoch": 125.16666666666667, "percentage": 28.16, "elapsed_time": "1:16:38", "remaining_time": "3:15:29", "throughput": 686.16, "total_tokens": 3155200} {"current_steps": 11270, "total_steps": 40000, "loss": 0.0, "lr": 4.083097620918444e-05, "epoch": 125.22222222222223, "percentage": 28.18, "elapsed_time": "1:16:40", "remaining_time": "3:15:27", "throughput": 686.17, "total_tokens": 3156576} {"current_steps": 11275, "total_steps": 40000, "loss": 0.0, "lr": 4.082337669080097e-05, "epoch": 125.27777777777777, "percentage": 28.19, "elapsed_time": "1:16:42", "remaining_time": "3:15:24", "throughput": 686.17, "total_tokens": 3157920} {"current_steps": 11280, "total_steps": 40000, "loss": 0.0, "lr": 4.081577473225398e-05, "epoch": 125.33333333333333, "percentage": 28.2, "elapsed_time": "1:16:44", "remaining_time": "3:15:22", "throughput": 686.19, "total_tokens": 3159328} {"current_steps": 11285, "total_steps": 40000, "loss": 0.0, "lr": 4.080817033471577e-05, "epoch": 125.38888888888889, "percentage": 28.21, "elapsed_time": "1:16:46", "remaining_time": "3:15:20", "throughput": 686.21, "total_tokens": 3160768} {"current_steps": 11290, "total_steps": 40000, "loss": 0.0, "lr": 4.080056349935903e-05, "epoch": 125.44444444444444, "percentage": 28.23, "elapsed_time": "1:16:48", "remaining_time": "3:15:18", "throughput": 686.22, "total_tokens": 3162144} {"current_steps": 11295, "total_steps": 40000, "loss": 0.0, "lr": 4.079295422735684e-05, "epoch": 125.5, "percentage": 28.24, "elapsed_time": "1:16:50", "remaining_time": "3:15:15", "throughput": 686.23, "total_tokens": 3163536} {"current_steps": 11300, "total_steps": 40000, "loss": 0.0, "lr": 4.078534251988264e-05, "epoch": 125.55555555555556, "percentage": 28.25, "elapsed_time": "1:16:51", "remaining_time": "3:15:13", "throughput": 686.25, "total_tokens": 3164960} {"current_steps": 11305, "total_steps": 40000, "loss": 0.0, "lr": 4.077772837811025e-05, "epoch": 125.61111111111111, "percentage": 28.26, "elapsed_time": "1:16:53", "remaining_time": "3:15:11", "throughput": 686.27, "total_tokens": 3166384} {"current_steps": 11310, "total_steps": 40000, "loss": 0.0, "lr": 4.0770111803213874e-05, "epoch": 125.66666666666667, "percentage": 28.27, "elapsed_time": "1:16:55", "remaining_time": "3:15:08", "throughput": 686.29, "total_tokens": 3167824} {"current_steps": 11315, "total_steps": 40000, "loss": 0.0, "lr": 4.076249279636807e-05, "epoch": 125.72222222222223, "percentage": 28.29, "elapsed_time": "1:16:57", "remaining_time": "3:15:06", "throughput": 686.3, "total_tokens": 3169200} {"current_steps": 11320, "total_steps": 40000, "loss": 0.0, "lr": 4.075487135874781e-05, "epoch": 125.77777777777777, "percentage": 28.3, "elapsed_time": "1:16:59", "remaining_time": "3:15:04", "throughput": 686.31, "total_tokens": 3170576} {"current_steps": 11325, "total_steps": 40000, "loss": 0.0, "lr": 4.074724749152837e-05, "epoch": 125.83333333333333, "percentage": 28.31, "elapsed_time": "1:17:01", "remaining_time": "3:15:02", "throughput": 686.33, "total_tokens": 3172016} {"current_steps": 11330, "total_steps": 40000, "loss": 0.0, "lr": 4.07396211958855e-05, "epoch": 125.88888888888889, "percentage": 28.32, "elapsed_time": "1:17:03", "remaining_time": "3:14:59", "throughput": 686.34, "total_tokens": 3173392} {"current_steps": 11335, "total_steps": 40000, "loss": 0.0, "lr": 4.073199247299523e-05, "epoch": 125.94444444444444, "percentage": 28.34, "elapsed_time": "1:17:05", "remaining_time": "3:14:57", "throughput": 686.37, "total_tokens": 3174832} {"current_steps": 11340, "total_steps": 40000, "loss": 0.0, "lr": 4.072436132403403e-05, "epoch": 126.0, "percentage": 28.35, "elapsed_time": "1:17:07", "remaining_time": "3:14:55", "throughput": 686.35, "total_tokens": 3176192} {"current_steps": 11345, "total_steps": 40000, "loss": 0.0, "lr": 4.0716727750178704e-05, "epoch": 126.05555555555556, "percentage": 28.36, "elapsed_time": "1:17:09", "remaining_time": "3:14:54", "throughput": 686.31, "total_tokens": 3177552} {"current_steps": 11350, "total_steps": 40000, "loss": 0.0, "lr": 4.0709091752606455e-05, "epoch": 126.11111111111111, "percentage": 28.38, "elapsed_time": "1:17:11", "remaining_time": "3:14:51", "throughput": 686.34, "total_tokens": 3178992} {"current_steps": 11355, "total_steps": 40000, "loss": 0.0, "lr": 4.070145333249484e-05, "epoch": 126.16666666666667, "percentage": 28.39, "elapsed_time": "1:17:13", "remaining_time": "3:14:49", "throughput": 686.35, "total_tokens": 3180400} {"current_steps": 11360, "total_steps": 40000, "loss": 0.0, "lr": 4.069381249102181e-05, "epoch": 126.22222222222223, "percentage": 28.4, "elapsed_time": "1:17:15", "remaining_time": "3:14:47", "throughput": 686.37, "total_tokens": 3181824} {"current_steps": 11365, "total_steps": 40000, "loss": 0.0, "lr": 4.0686169229365665e-05, "epoch": 126.27777777777777, "percentage": 28.41, "elapsed_time": "1:17:17", "remaining_time": "3:14:44", "throughput": 686.39, "total_tokens": 3183232} {"current_steps": 11370, "total_steps": 40000, "loss": 0.0, "lr": 4.067852354870511e-05, "epoch": 126.33333333333333, "percentage": 28.43, "elapsed_time": "1:17:19", "remaining_time": "3:14:42", "throughput": 686.4, "total_tokens": 3184624} {"current_steps": 11375, "total_steps": 40000, "loss": 0.0, "lr": 4.067087545021919e-05, "epoch": 126.38888888888889, "percentage": 28.44, "elapsed_time": "1:17:21", "remaining_time": "3:14:40", "throughput": 686.42, "total_tokens": 3186048} {"current_steps": 11380, "total_steps": 40000, "loss": 0.0, "lr": 4.066322493508734e-05, "epoch": 126.44444444444444, "percentage": 28.45, "elapsed_time": "1:17:23", "remaining_time": "3:14:38", "throughput": 686.43, "total_tokens": 3187424} {"current_steps": 11385, "total_steps": 40000, "loss": 0.0, "lr": 4.065557200448937e-05, "epoch": 126.5, "percentage": 28.46, "elapsed_time": "1:17:25", "remaining_time": "3:14:35", "throughput": 686.44, "total_tokens": 3188816} {"current_steps": 11390, "total_steps": 40000, "loss": 0.0, "lr": 4.064791665960546e-05, "epoch": 126.55555555555556, "percentage": 28.48, "elapsed_time": "1:17:27", "remaining_time": "3:14:33", "throughput": 686.46, "total_tokens": 3190224} {"current_steps": 11395, "total_steps": 40000, "loss": 0.0, "lr": 4.064025890161615e-05, "epoch": 126.61111111111111, "percentage": 28.49, "elapsed_time": "1:17:29", "remaining_time": "3:14:31", "throughput": 686.46, "total_tokens": 3191584} {"current_steps": 11400, "total_steps": 40000, "loss": 0.0, "lr": 4.0632598731702373e-05, "epoch": 126.66666666666667, "percentage": 28.5, "elapsed_time": "1:17:31", "remaining_time": "3:14:28", "throughput": 686.47, "total_tokens": 3192960} {"current_steps": 11400, "total_steps": 40000, "eval_loss": 0.3366057872772217, "epoch": 126.66666666666667, "percentage": 28.5, "elapsed_time": "1:17:32", "remaining_time": "3:14:32", "throughput": 686.28, "total_tokens": 3192960} {"current_steps": 11405, "total_steps": 40000, "loss": 0.0, "lr": 4.0624936151045426e-05, "epoch": 126.72222222222223, "percentage": 28.51, "elapsed_time": "1:17:35", "remaining_time": "3:14:33", "throughput": 686.1, "total_tokens": 3194352} {"current_steps": 11410, "total_steps": 40000, "loss": 0.0, "lr": 4.061727116082696e-05, "epoch": 126.77777777777777, "percentage": 28.52, "elapsed_time": "1:17:37", "remaining_time": "3:14:31", "throughput": 686.1, "total_tokens": 3195760} {"current_steps": 11415, "total_steps": 40000, "loss": 0.0, "lr": 4.060960376222903e-05, "epoch": 126.83333333333333, "percentage": 28.54, "elapsed_time": "1:17:39", "remaining_time": "3:14:28", "throughput": 686.12, "total_tokens": 3197184} {"current_steps": 11420, "total_steps": 40000, "loss": 0.0, "lr": 4.0601933956434034e-05, "epoch": 126.88888888888889, "percentage": 28.55, "elapsed_time": "1:17:41", "remaining_time": "3:14:26", "throughput": 686.13, "total_tokens": 3198560} {"current_steps": 11425, "total_steps": 40000, "loss": 0.0, "lr": 4.059426174462476e-05, "epoch": 126.94444444444444, "percentage": 28.56, "elapsed_time": "1:17:43", "remaining_time": "3:14:24", "throughput": 686.14, "total_tokens": 3199952} {"current_steps": 11430, "total_steps": 40000, "loss": 0.0, "lr": 4.058658712798435e-05, "epoch": 127.0, "percentage": 28.57, "elapsed_time": "1:17:45", "remaining_time": "3:14:22", "throughput": 686.13, "total_tokens": 3201328} {"current_steps": 11435, "total_steps": 40000, "loss": 0.0, "lr": 4.0578910107696336e-05, "epoch": 127.05555555555556, "percentage": 28.59, "elapsed_time": "1:17:48", "remaining_time": "3:14:20", "throughput": 686.1, "total_tokens": 3202736} {"current_steps": 11440, "total_steps": 40000, "loss": 0.0, "lr": 4.05712306849446e-05, "epoch": 127.11111111111111, "percentage": 28.6, "elapsed_time": "1:17:49", "remaining_time": "3:14:18", "throughput": 686.11, "total_tokens": 3204144} {"current_steps": 11445, "total_steps": 40000, "loss": 0.0, "lr": 4.0563548860913415e-05, "epoch": 127.16666666666667, "percentage": 28.61, "elapsed_time": "1:17:51", "remaining_time": "3:14:16", "throughput": 686.12, "total_tokens": 3205536} {"current_steps": 11450, "total_steps": 40000, "loss": 0.0, "lr": 4.0555864636787414e-05, "epoch": 127.22222222222223, "percentage": 28.62, "elapsed_time": "1:17:53", "remaining_time": "3:14:14", "throughput": 686.13, "total_tokens": 3206928} {"current_steps": 11455, "total_steps": 40000, "loss": 0.0, "lr": 4.054817801375159e-05, "epoch": 127.27777777777777, "percentage": 28.64, "elapsed_time": "1:17:55", "remaining_time": "3:14:11", "throughput": 686.15, "total_tokens": 3208336} {"current_steps": 11460, "total_steps": 40000, "loss": 0.0, "lr": 4.054048899299134e-05, "epoch": 127.33333333333333, "percentage": 28.65, "elapsed_time": "1:17:57", "remaining_time": "3:14:09", "throughput": 686.15, "total_tokens": 3209696} {"current_steps": 11465, "total_steps": 40000, "loss": 0.0, "lr": 4.0532797575692385e-05, "epoch": 127.38888888888889, "percentage": 28.66, "elapsed_time": "1:17:59", "remaining_time": "3:14:07", "throughput": 686.16, "total_tokens": 3211088} {"current_steps": 11470, "total_steps": 40000, "loss": 0.0, "lr": 4.052510376304085e-05, "epoch": 127.44444444444444, "percentage": 28.68, "elapsed_time": "1:18:01", "remaining_time": "3:14:05", "throughput": 686.18, "total_tokens": 3212496} {"current_steps": 11475, "total_steps": 40000, "loss": 0.0, "lr": 4.051740755622321e-05, "epoch": 127.5, "percentage": 28.69, "elapsed_time": "1:18:03", "remaining_time": "3:14:02", "throughput": 686.19, "total_tokens": 3213888} {"current_steps": 11480, "total_steps": 40000, "loss": 0.0, "lr": 4.050970895642632e-05, "epoch": 127.55555555555556, "percentage": 28.7, "elapsed_time": "1:18:05", "remaining_time": "3:14:00", "throughput": 686.19, "total_tokens": 3215232} {"current_steps": 11485, "total_steps": 40000, "loss": 0.0, "lr": 4.050200796483741e-05, "epoch": 127.61111111111111, "percentage": 28.71, "elapsed_time": "1:18:07", "remaining_time": "3:13:58", "throughput": 686.19, "total_tokens": 3216592} {"current_steps": 11490, "total_steps": 40000, "loss": 0.0, "lr": 4.049430458264405e-05, "epoch": 127.66666666666667, "percentage": 28.73, "elapsed_time": "1:18:09", "remaining_time": "3:13:56", "throughput": 686.21, "total_tokens": 3218000} {"current_steps": 11495, "total_steps": 40000, "loss": 0.0, "lr": 4.048659881103422e-05, "epoch": 127.72222222222223, "percentage": 28.74, "elapsed_time": "1:18:11", "remaining_time": "3:13:53", "throughput": 686.22, "total_tokens": 3219392} {"current_steps": 11500, "total_steps": 40000, "loss": 0.0, "lr": 4.0478890651196235e-05, "epoch": 127.77777777777777, "percentage": 28.75, "elapsed_time": "1:18:13", "remaining_time": "3:13:51", "throughput": 686.24, "total_tokens": 3220832} {"current_steps": 11505, "total_steps": 40000, "loss": 0.0, "lr": 4.047118010431879e-05, "epoch": 127.83333333333333, "percentage": 28.76, "elapsed_time": "1:18:15", "remaining_time": "3:13:49", "throughput": 686.26, "total_tokens": 3222272} {"current_steps": 11510, "total_steps": 40000, "loss": 0.0, "lr": 4.046346717159094e-05, "epoch": 127.88888888888889, "percentage": 28.78, "elapsed_time": "1:18:17", "remaining_time": "3:13:47", "throughput": 686.28, "total_tokens": 3223680} {"current_steps": 11515, "total_steps": 40000, "loss": 0.0, "lr": 4.045575185420214e-05, "epoch": 127.94444444444444, "percentage": 28.79, "elapsed_time": "1:18:19", "remaining_time": "3:13:44", "throughput": 686.29, "total_tokens": 3225088} {"current_steps": 11520, "total_steps": 40000, "loss": 0.0, "lr": 4.0448034153342165e-05, "epoch": 128.0, "percentage": 28.8, "elapsed_time": "1:18:21", "remaining_time": "3:13:42", "throughput": 686.29, "total_tokens": 3226512} {"current_steps": 11525, "total_steps": 40000, "loss": 0.0, "lr": 4.0440314070201194e-05, "epoch": 128.05555555555554, "percentage": 28.81, "elapsed_time": "1:18:23", "remaining_time": "3:13:41", "throughput": 686.26, "total_tokens": 3227888} {"current_steps": 11530, "total_steps": 40000, "loss": 0.0, "lr": 4.043259160596976e-05, "epoch": 128.11111111111111, "percentage": 28.82, "elapsed_time": "1:18:25", "remaining_time": "3:13:39", "throughput": 686.27, "total_tokens": 3229296} {"current_steps": 11535, "total_steps": 40000, "loss": 0.0, "lr": 4.0424866761838767e-05, "epoch": 128.16666666666666, "percentage": 28.84, "elapsed_time": "1:18:27", "remaining_time": "3:13:36", "throughput": 686.29, "total_tokens": 3230720} {"current_steps": 11540, "total_steps": 40000, "loss": 0.0, "lr": 4.041713953899948e-05, "epoch": 128.22222222222223, "percentage": 28.85, "elapsed_time": "1:18:29", "remaining_time": "3:13:34", "throughput": 686.31, "total_tokens": 3232160} {"current_steps": 11545, "total_steps": 40000, "loss": 0.0, "lr": 4.0409409938643515e-05, "epoch": 128.27777777777777, "percentage": 28.86, "elapsed_time": "1:18:31", "remaining_time": "3:13:32", "throughput": 686.33, "total_tokens": 3233616} {"current_steps": 11550, "total_steps": 40000, "loss": 0.0, "lr": 4.0401677961962904e-05, "epoch": 128.33333333333334, "percentage": 28.88, "elapsed_time": "1:18:33", "remaining_time": "3:13:30", "throughput": 686.35, "total_tokens": 3235008} {"current_steps": 11555, "total_steps": 40000, "loss": 0.0, "lr": 4.039394361015001e-05, "epoch": 128.38888888888889, "percentage": 28.89, "elapsed_time": "1:18:35", "remaining_time": "3:13:27", "throughput": 686.36, "total_tokens": 3236416} {"current_steps": 11560, "total_steps": 40000, "loss": 0.0, "lr": 4.038620688439755e-05, "epoch": 128.44444444444446, "percentage": 28.9, "elapsed_time": "1:18:37", "remaining_time": "3:13:25", "throughput": 686.38, "total_tokens": 3237808} {"current_steps": 11565, "total_steps": 40000, "loss": 0.0, "lr": 4.037846778589862e-05, "epoch": 128.5, "percentage": 28.91, "elapsed_time": "1:18:39", "remaining_time": "3:13:23", "throughput": 686.39, "total_tokens": 3239200} {"current_steps": 11570, "total_steps": 40000, "loss": 0.0, "lr": 4.0370726315846715e-05, "epoch": 128.55555555555554, "percentage": 28.93, "elapsed_time": "1:18:41", "remaining_time": "3:13:20", "throughput": 686.4, "total_tokens": 3240592} {"current_steps": 11575, "total_steps": 40000, "loss": 0.0, "lr": 4.036298247543565e-05, "epoch": 128.61111111111111, "percentage": 28.94, "elapsed_time": "1:18:43", "remaining_time": "3:13:18", "throughput": 686.42, "total_tokens": 3242016} {"current_steps": 11580, "total_steps": 40000, "loss": 0.0, "lr": 4.035523626585962e-05, "epoch": 128.66666666666666, "percentage": 28.95, "elapsed_time": "1:18:45", "remaining_time": "3:13:16", "throughput": 686.43, "total_tokens": 3243392} {"current_steps": 11585, "total_steps": 40000, "loss": 0.0, "lr": 4.0347487688313194e-05, "epoch": 128.72222222222223, "percentage": 28.96, "elapsed_time": "1:18:47", "remaining_time": "3:13:14", "throughput": 686.44, "total_tokens": 3244800} {"current_steps": 11590, "total_steps": 40000, "loss": 0.0, "lr": 4.0339736743991296e-05, "epoch": 128.77777777777777, "percentage": 28.98, "elapsed_time": "1:18:48", "remaining_time": "3:13:11", "throughput": 686.45, "total_tokens": 3246176} {"current_steps": 11595, "total_steps": 40000, "loss": 0.0, "lr": 4.0331983434089227e-05, "epoch": 128.83333333333334, "percentage": 28.99, "elapsed_time": "1:18:50", "remaining_time": "3:13:09", "throughput": 686.46, "total_tokens": 3247568} {"current_steps": 11600, "total_steps": 40000, "loss": 0.0, "lr": 4.032422775980264e-05, "epoch": 128.88888888888889, "percentage": 29.0, "elapsed_time": "1:18:52", "remaining_time": "3:13:07", "throughput": 686.48, "total_tokens": 3248976} {"current_steps": 11600, "total_steps": 40000, "eval_loss": 0.34557223320007324, "epoch": 128.88888888888889, "percentage": 29.0, "elapsed_time": "1:18:54", "remaining_time": "3:13:10", "throughput": 686.29, "total_tokens": 3248976} {"current_steps": 11605, "total_steps": 40000, "loss": 0.0, "lr": 4.031646972232754e-05, "epoch": 128.94444444444446, "percentage": 29.01, "elapsed_time": "1:18:57", "remaining_time": "3:13:11", "throughput": 686.1, "total_tokens": 3250352} {"current_steps": 11610, "total_steps": 40000, "loss": 0.0, "lr": 4.0308709322860344e-05, "epoch": 129.0, "percentage": 29.03, "elapsed_time": "1:18:59", "remaining_time": "3:13:09", "throughput": 686.09, "total_tokens": 3251776} {"current_steps": 11615, "total_steps": 40000, "loss": 0.0, "lr": 4.0300946562597784e-05, "epoch": 129.05555555555554, "percentage": 29.04, "elapsed_time": "1:19:01", "remaining_time": "3:13:08", "throughput": 686.06, "total_tokens": 3253200} {"current_steps": 11620, "total_steps": 40000, "loss": 0.0, "lr": 4.029318144273698e-05, "epoch": 129.11111111111111, "percentage": 29.05, "elapsed_time": "1:19:03", "remaining_time": "3:13:05", "throughput": 686.07, "total_tokens": 3254560} {"current_steps": 11625, "total_steps": 40000, "loss": 0.0, "lr": 4.0285413964475415e-05, "epoch": 129.16666666666666, "percentage": 29.06, "elapsed_time": "1:19:05", "remaining_time": "3:13:03", "throughput": 686.09, "total_tokens": 3255968} {"current_steps": 11630, "total_steps": 40000, "loss": 0.0, "lr": 4.0277644129010927e-05, "epoch": 129.22222222222223, "percentage": 29.07, "elapsed_time": "1:19:07", "remaining_time": "3:13:01", "throughput": 686.1, "total_tokens": 3257392} {"current_steps": 11635, "total_steps": 40000, "loss": 0.0, "lr": 4.0269871937541724e-05, "epoch": 129.27777777777777, "percentage": 29.09, "elapsed_time": "1:19:09", "remaining_time": "3:12:59", "throughput": 686.11, "total_tokens": 3258768} {"current_steps": 11640, "total_steps": 40000, "loss": 0.0, "lr": 4.026209739126637e-05, "epoch": 129.33333333333334, "percentage": 29.1, "elapsed_time": "1:19:11", "remaining_time": "3:12:56", "throughput": 686.13, "total_tokens": 3260192} {"current_steps": 11645, "total_steps": 40000, "loss": 0.0, "lr": 4.025432049138381e-05, "epoch": 129.38888888888889, "percentage": 29.11, "elapsed_time": "1:19:13", "remaining_time": "3:12:54", "throughput": 686.15, "total_tokens": 3261600} {"current_steps": 11650, "total_steps": 40000, "loss": 0.0, "lr": 4.0246541239093325e-05, "epoch": 129.44444444444446, "percentage": 29.12, "elapsed_time": "1:19:15", "remaining_time": "3:12:52", "throughput": 686.16, "total_tokens": 3263008} {"current_steps": 11655, "total_steps": 40000, "loss": 0.0, "lr": 4.023875963559459e-05, "epoch": 129.5, "percentage": 29.14, "elapsed_time": "1:19:17", "remaining_time": "3:12:50", "throughput": 686.18, "total_tokens": 3264432} {"current_steps": 11660, "total_steps": 40000, "loss": 0.0, "lr": 4.023097568208761e-05, "epoch": 129.55555555555554, "percentage": 29.15, "elapsed_time": "1:19:19", "remaining_time": "3:12:47", "throughput": 686.2, "total_tokens": 3265840} {"current_steps": 11665, "total_steps": 40000, "loss": 0.0, "lr": 4.022318937977277e-05, "epoch": 129.61111111111111, "percentage": 29.16, "elapsed_time": "1:19:21", "remaining_time": "3:12:45", "throughput": 686.21, "total_tokens": 3267264} {"current_steps": 11670, "total_steps": 40000, "loss": 0.0, "lr": 4.021540072985084e-05, "epoch": 129.66666666666666, "percentage": 29.18, "elapsed_time": "1:19:23", "remaining_time": "3:12:43", "throughput": 686.23, "total_tokens": 3268688} {"current_steps": 11675, "total_steps": 40000, "loss": 0.0, "lr": 4.020760973352289e-05, "epoch": 129.72222222222223, "percentage": 29.19, "elapsed_time": "1:19:25", "remaining_time": "3:12:40", "throughput": 686.24, "total_tokens": 3270080} {"current_steps": 11680, "total_steps": 40000, "loss": 0.0, "lr": 4.019981639199042e-05, "epoch": 129.77777777777777, "percentage": 29.2, "elapsed_time": "1:19:27", "remaining_time": "3:12:38", "throughput": 686.25, "total_tokens": 3271440} {"current_steps": 11685, "total_steps": 40000, "loss": 0.0, "lr": 4.0192020706455245e-05, "epoch": 129.83333333333334, "percentage": 29.21, "elapsed_time": "1:19:29", "remaining_time": "3:12:36", "throughput": 686.26, "total_tokens": 3272816} {"current_steps": 11690, "total_steps": 40000, "loss": 0.0, "lr": 4.018422267811956e-05, "epoch": 129.88888888888889, "percentage": 29.23, "elapsed_time": "1:19:31", "remaining_time": "3:12:34", "throughput": 686.27, "total_tokens": 3274224} {"current_steps": 11695, "total_steps": 40000, "loss": 0.0, "lr": 4.017642230818592e-05, "epoch": 129.94444444444446, "percentage": 29.24, "elapsed_time": "1:19:32", "remaining_time": "3:12:31", "throughput": 686.28, "total_tokens": 3275584} {"current_steps": 11700, "total_steps": 40000, "loss": 0.0, "lr": 4.0168619597857246e-05, "epoch": 130.0, "percentage": 29.25, "elapsed_time": "1:19:35", "remaining_time": "3:12:29", "throughput": 686.27, "total_tokens": 3276976} {"current_steps": 11705, "total_steps": 40000, "loss": 0.0, "lr": 4.016081454833681e-05, "epoch": 130.05555555555554, "percentage": 29.26, "elapsed_time": "1:19:37", "remaining_time": "3:12:28", "throughput": 686.25, "total_tokens": 3278400} {"current_steps": 11710, "total_steps": 40000, "loss": 0.0, "lr": 4.0153007160828245e-05, "epoch": 130.11111111111111, "percentage": 29.28, "elapsed_time": "1:19:39", "remaining_time": "3:12:26", "throughput": 686.26, "total_tokens": 3279808} {"current_steps": 11715, "total_steps": 40000, "loss": 0.0, "lr": 4.0145197436535555e-05, "epoch": 130.16666666666666, "percentage": 29.29, "elapsed_time": "1:19:41", "remaining_time": "3:12:23", "throughput": 686.28, "total_tokens": 3281232} {"current_steps": 11720, "total_steps": 40000, "loss": 0.0, "lr": 4.0137385376663095e-05, "epoch": 130.22222222222223, "percentage": 29.3, "elapsed_time": "1:19:43", "remaining_time": "3:12:21", "throughput": 686.28, "total_tokens": 3282576} {"current_steps": 11725, "total_steps": 40000, "loss": 0.0, "lr": 4.012957098241558e-05, "epoch": 130.27777777777777, "percentage": 29.31, "elapsed_time": "1:19:45", "remaining_time": "3:12:19", "throughput": 686.3, "total_tokens": 3284016} {"current_steps": 11730, "total_steps": 40000, "loss": 0.0, "lr": 4.0121754254998076e-05, "epoch": 130.33333333333334, "percentage": 29.33, "elapsed_time": "1:19:47", "remaining_time": "3:12:17", "throughput": 686.32, "total_tokens": 3285440} {"current_steps": 11735, "total_steps": 40000, "loss": 0.0, "lr": 4.011393519561606e-05, "epoch": 130.38888888888889, "percentage": 29.34, "elapsed_time": "1:19:48", "remaining_time": "3:12:14", "throughput": 686.33, "total_tokens": 3286816} {"current_steps": 11740, "total_steps": 40000, "loss": 0.0, "lr": 4.010611380547529e-05, "epoch": 130.44444444444446, "percentage": 29.35, "elapsed_time": "1:19:50", "remaining_time": "3:12:12", "throughput": 686.34, "total_tokens": 3288208} {"current_steps": 11745, "total_steps": 40000, "loss": 0.0, "lr": 4.009829008578192e-05, "epoch": 130.5, "percentage": 29.36, "elapsed_time": "1:19:52", "remaining_time": "3:12:10", "throughput": 686.35, "total_tokens": 3289600} {"current_steps": 11750, "total_steps": 40000, "loss": 0.0, "lr": 4.00904640377425e-05, "epoch": 130.55555555555554, "percentage": 29.38, "elapsed_time": "1:19:54", "remaining_time": "3:12:07", "throughput": 686.37, "total_tokens": 3291024} {"current_steps": 11755, "total_steps": 40000, "loss": 0.0, "lr": 4.0082635662563886e-05, "epoch": 130.61111111111111, "percentage": 29.39, "elapsed_time": "1:19:56", "remaining_time": "3:12:05", "throughput": 686.39, "total_tokens": 3292448} {"current_steps": 11760, "total_steps": 40000, "loss": 0.0, "lr": 4.007480496145331e-05, "epoch": 130.66666666666666, "percentage": 29.4, "elapsed_time": "1:19:58", "remaining_time": "3:12:03", "throughput": 686.4, "total_tokens": 3293840} {"current_steps": 11765, "total_steps": 40000, "loss": 0.0, "lr": 4.006697193561837e-05, "epoch": 130.72222222222223, "percentage": 29.41, "elapsed_time": "1:20:00", "remaining_time": "3:12:01", "throughput": 686.42, "total_tokens": 3295264} {"current_steps": 11770, "total_steps": 40000, "loss": 0.0, "lr": 4.005913658626701e-05, "epoch": 130.77777777777777, "percentage": 29.43, "elapsed_time": "1:20:02", "remaining_time": "3:11:58", "throughput": 686.44, "total_tokens": 3296672} {"current_steps": 11775, "total_steps": 40000, "loss": 0.0, "lr": 4.005129891460754e-05, "epoch": 130.83333333333334, "percentage": 29.44, "elapsed_time": "1:20:04", "remaining_time": "3:11:56", "throughput": 686.45, "total_tokens": 3298064} {"current_steps": 11780, "total_steps": 40000, "loss": 0.0, "lr": 4.004345892184864e-05, "epoch": 130.88888888888889, "percentage": 29.45, "elapsed_time": "1:20:06", "remaining_time": "3:11:54", "throughput": 686.46, "total_tokens": 3299440} {"current_steps": 11785, "total_steps": 40000, "loss": 0.0, "lr": 4.003561660919932e-05, "epoch": 130.94444444444446, "percentage": 29.46, "elapsed_time": "1:20:08", "remaining_time": "3:11:52", "throughput": 686.47, "total_tokens": 3300816} {"current_steps": 11790, "total_steps": 40000, "loss": 0.0, "lr": 4.002777197786897e-05, "epoch": 131.0, "percentage": 29.48, "elapsed_time": "1:20:10", "remaining_time": "3:11:50", "throughput": 686.45, "total_tokens": 3302176} {"current_steps": 11795, "total_steps": 40000, "loss": 0.0, "lr": 4.0019925029067326e-05, "epoch": 131.05555555555554, "percentage": 29.49, "elapsed_time": "1:20:12", "remaining_time": "3:11:48", "throughput": 686.42, "total_tokens": 3303552} {"current_steps": 11800, "total_steps": 40000, "loss": 0.0, "lr": 4.0012075764004495e-05, "epoch": 131.11111111111111, "percentage": 29.5, "elapsed_time": "1:20:14", "remaining_time": "3:11:46", "throughput": 686.45, "total_tokens": 3305024} {"current_steps": 11800, "total_steps": 40000, "eval_loss": 0.3281330466270447, "epoch": 131.11111111111111, "percentage": 29.5, "elapsed_time": "1:20:16", "remaining_time": "3:11:49", "throughput": 686.26, "total_tokens": 3305024} {"current_steps": 11805, "total_steps": 40000, "loss": 0.0, "lr": 4.000422418389094e-05, "epoch": 131.16666666666666, "percentage": 29.51, "elapsed_time": "1:20:19", "remaining_time": "3:11:50", "throughput": 686.1, "total_tokens": 3306464} {"current_steps": 11810, "total_steps": 40000, "loss": 0.0, "lr": 3.999637028993744e-05, "epoch": 131.22222222222223, "percentage": 29.53, "elapsed_time": "1:20:21", "remaining_time": "3:11:48", "throughput": 686.11, "total_tokens": 3307888} {"current_steps": 11815, "total_steps": 40000, "loss": 0.0, "lr": 3.99885140833552e-05, "epoch": 131.27777777777777, "percentage": 29.54, "elapsed_time": "1:20:23", "remaining_time": "3:11:45", "throughput": 686.13, "total_tokens": 3309328} {"current_steps": 11820, "total_steps": 40000, "loss": 0.0, "lr": 3.998065556535572e-05, "epoch": 131.33333333333334, "percentage": 29.55, "elapsed_time": "1:20:25", "remaining_time": "3:11:43", "throughput": 686.13, "total_tokens": 3310688} {"current_steps": 11825, "total_steps": 40000, "loss": 0.0, "lr": 3.9972794737150895e-05, "epoch": 131.38888888888889, "percentage": 29.56, "elapsed_time": "1:20:27", "remaining_time": "3:11:41", "throughput": 686.14, "total_tokens": 3312064} {"current_steps": 11830, "total_steps": 40000, "loss": 0.0, "lr": 3.996493159995297e-05, "epoch": 131.44444444444446, "percentage": 29.58, "elapsed_time": "1:20:29", "remaining_time": "3:11:39", "throughput": 686.14, "total_tokens": 3313392} {"current_steps": 11835, "total_steps": 40000, "loss": 0.0, "lr": 3.995706615497453e-05, "epoch": 131.5, "percentage": 29.59, "elapsed_time": "1:20:31", "remaining_time": "3:11:36", "throughput": 686.16, "total_tokens": 3314832} {"current_steps": 11840, "total_steps": 40000, "loss": 0.0, "lr": 3.994919840342852e-05, "epoch": 131.55555555555554, "percentage": 29.6, "elapsed_time": "1:20:32", "remaining_time": "3:11:34", "throughput": 686.17, "total_tokens": 3316224} {"current_steps": 11845, "total_steps": 40000, "loss": 0.0, "lr": 3.994132834652825e-05, "epoch": 131.61111111111111, "percentage": 29.61, "elapsed_time": "1:20:34", "remaining_time": "3:11:32", "throughput": 686.18, "total_tokens": 3317616} {"current_steps": 11850, "total_steps": 40000, "loss": 0.0, "lr": 3.99334559854874e-05, "epoch": 131.66666666666666, "percentage": 29.62, "elapsed_time": "1:20:36", "remaining_time": "3:11:30", "throughput": 686.19, "total_tokens": 3319008} {"current_steps": 11855, "total_steps": 40000, "loss": 0.0, "lr": 3.9925581321519955e-05, "epoch": 131.72222222222223, "percentage": 29.64, "elapsed_time": "1:20:38", "remaining_time": "3:11:27", "throughput": 686.2, "total_tokens": 3320400} {"current_steps": 11860, "total_steps": 40000, "loss": 0.0, "lr": 3.991770435584031e-05, "epoch": 131.77777777777777, "percentage": 29.65, "elapsed_time": "1:20:40", "remaining_time": "3:11:25", "throughput": 686.22, "total_tokens": 3321808} {"current_steps": 11865, "total_steps": 40000, "loss": 0.0, "lr": 3.990982508966319e-05, "epoch": 131.83333333333334, "percentage": 29.66, "elapsed_time": "1:20:42", "remaining_time": "3:11:23", "throughput": 686.22, "total_tokens": 3323168} {"current_steps": 11870, "total_steps": 40000, "loss": 0.0, "lr": 3.990194352420367e-05, "epoch": 131.88888888888889, "percentage": 29.68, "elapsed_time": "1:20:44", "remaining_time": "3:11:21", "throughput": 686.23, "total_tokens": 3324544} {"current_steps": 11875, "total_steps": 40000, "loss": 0.0, "lr": 3.9894059660677184e-05, "epoch": 131.94444444444446, "percentage": 29.69, "elapsed_time": "1:20:46", "remaining_time": "3:11:18", "throughput": 686.25, "total_tokens": 3326000} {"current_steps": 11880, "total_steps": 40000, "loss": 0.0, "lr": 3.9886173500299526e-05, "epoch": 132.0, "percentage": 29.7, "elapsed_time": "1:20:49", "remaining_time": "3:11:17", "throughput": 686.21, "total_tokens": 3327424} {"current_steps": 11885, "total_steps": 40000, "loss": 0.0, "lr": 3.987828504428685e-05, "epoch": 132.05555555555554, "percentage": 29.71, "elapsed_time": "1:20:51", "remaining_time": "3:11:16", "throughput": 686.17, "total_tokens": 3328784} {"current_steps": 11890, "total_steps": 40000, "loss": 0.0, "lr": 3.987039429385565e-05, "epoch": 132.11111111111111, "percentage": 29.73, "elapsed_time": "1:20:53", "remaining_time": "3:11:13", "throughput": 686.2, "total_tokens": 3330256} {"current_steps": 11895, "total_steps": 40000, "loss": 0.0, "lr": 3.986250125022277e-05, "epoch": 132.16666666666666, "percentage": 29.74, "elapsed_time": "1:20:55", "remaining_time": "3:11:11", "throughput": 686.21, "total_tokens": 3331664} {"current_steps": 11900, "total_steps": 40000, "loss": 0.0, "lr": 3.985460591460544e-05, "epoch": 132.22222222222223, "percentage": 29.75, "elapsed_time": "1:20:57", "remaining_time": "3:11:09", "throughput": 686.23, "total_tokens": 3333056} {"current_steps": 11905, "total_steps": 40000, "loss": 0.0, "lr": 3.984670828822118e-05, "epoch": 132.27777777777777, "percentage": 29.76, "elapsed_time": "1:20:59", "remaining_time": "3:11:06", "throughput": 686.23, "total_tokens": 3334432} {"current_steps": 11910, "total_steps": 40000, "loss": 0.0, "lr": 3.983880837228794e-05, "epoch": 132.33333333333334, "percentage": 29.78, "elapsed_time": "1:21:00", "remaining_time": "3:11:04", "throughput": 686.25, "total_tokens": 3335872} {"current_steps": 11915, "total_steps": 40000, "loss": 0.0, "lr": 3.983090616802396e-05, "epoch": 132.38888888888889, "percentage": 29.79, "elapsed_time": "1:21:02", "remaining_time": "3:11:02", "throughput": 686.26, "total_tokens": 3337264} {"current_steps": 11920, "total_steps": 40000, "loss": 0.0, "lr": 3.982300167664788e-05, "epoch": 132.44444444444446, "percentage": 29.8, "elapsed_time": "1:21:04", "remaining_time": "3:11:00", "throughput": 686.27, "total_tokens": 3338656} {"current_steps": 11925, "total_steps": 40000, "loss": 0.0, "lr": 3.981509489937868e-05, "epoch": 132.5, "percentage": 29.81, "elapsed_time": "1:21:06", "remaining_time": "3:10:58", "throughput": 686.28, "total_tokens": 3340048} {"current_steps": 11930, "total_steps": 40000, "loss": 0.0, "lr": 3.9807185837435643e-05, "epoch": 132.55555555555554, "percentage": 29.83, "elapsed_time": "1:21:08", "remaining_time": "3:10:55", "throughput": 686.3, "total_tokens": 3341488} {"current_steps": 11935, "total_steps": 40000, "loss": 0.0, "lr": 3.9799274492038484e-05, "epoch": 132.61111111111111, "percentage": 29.84, "elapsed_time": "1:21:10", "remaining_time": "3:10:53", "throughput": 686.32, "total_tokens": 3342896} {"current_steps": 11940, "total_steps": 40000, "loss": 0.0, "lr": 3.979136086440722e-05, "epoch": 132.66666666666666, "percentage": 29.85, "elapsed_time": "1:21:12", "remaining_time": "3:10:51", "throughput": 686.32, "total_tokens": 3344240} {"current_steps": 11945, "total_steps": 40000, "loss": 0.0, "lr": 3.9783444955762226e-05, "epoch": 132.72222222222223, "percentage": 29.86, "elapsed_time": "1:21:14", "remaining_time": "3:10:49", "throughput": 686.32, "total_tokens": 3345600} {"current_steps": 11950, "total_steps": 40000, "loss": 0.0, "lr": 3.977552676732424e-05, "epoch": 132.77777777777777, "percentage": 29.88, "elapsed_time": "1:21:16", "remaining_time": "3:10:46", "throughput": 686.33, "total_tokens": 3346992} {"current_steps": 11955, "total_steps": 40000, "loss": 0.0, "lr": 3.976760630031435e-05, "epoch": 132.83333333333334, "percentage": 29.89, "elapsed_time": "1:21:18", "remaining_time": "3:10:44", "throughput": 686.34, "total_tokens": 3348384} {"current_steps": 11960, "total_steps": 40000, "loss": 0.0, "lr": 3.975968355595398e-05, "epoch": 132.88888888888889, "percentage": 29.9, "elapsed_time": "1:21:20", "remaining_time": "3:10:42", "throughput": 686.37, "total_tokens": 3349840} {"current_steps": 11965, "total_steps": 40000, "loss": 0.0, "lr": 3.9751758535464935e-05, "epoch": 132.94444444444446, "percentage": 29.91, "elapsed_time": "1:21:22", "remaining_time": "3:10:40", "throughput": 686.39, "total_tokens": 3351264} {"current_steps": 11970, "total_steps": 40000, "loss": 0.0, "lr": 3.9743831240069326e-05, "epoch": 133.0, "percentage": 29.93, "elapsed_time": "1:21:24", "remaining_time": "3:10:38", "throughput": 686.37, "total_tokens": 3352624} {"current_steps": 11975, "total_steps": 40000, "loss": 0.0, "lr": 3.9735901670989675e-05, "epoch": 133.05555555555554, "percentage": 29.94, "elapsed_time": "1:21:26", "remaining_time": "3:10:36", "throughput": 686.33, "total_tokens": 3353984} {"current_steps": 11980, "total_steps": 40000, "loss": 0.0, "lr": 3.97279698294488e-05, "epoch": 133.11111111111111, "percentage": 29.95, "elapsed_time": "1:21:28", "remaining_time": "3:10:34", "throughput": 686.35, "total_tokens": 3355392} {"current_steps": 11985, "total_steps": 40000, "loss": 0.0, "lr": 3.9720035716669876e-05, "epoch": 133.16666666666666, "percentage": 29.96, "elapsed_time": "1:21:30", "remaining_time": "3:10:32", "throughput": 686.35, "total_tokens": 3356784} {"current_steps": 11990, "total_steps": 40000, "loss": 0.0, "lr": 3.9712099333876474e-05, "epoch": 133.22222222222223, "percentage": 29.98, "elapsed_time": "1:21:32", "remaining_time": "3:10:29", "throughput": 686.37, "total_tokens": 3358208} {"current_steps": 11995, "total_steps": 40000, "loss": 0.0, "lr": 3.9704160682292475e-05, "epoch": 133.27777777777777, "percentage": 29.99, "elapsed_time": "1:21:34", "remaining_time": "3:10:27", "throughput": 686.39, "total_tokens": 3359632} {"current_steps": 12000, "total_steps": 40000, "loss": 0.0, "lr": 3.9696219763142106e-05, "epoch": 133.33333333333334, "percentage": 30.0, "elapsed_time": "1:21:36", "remaining_time": "3:10:25", "throughput": 686.4, "total_tokens": 3361008} {"current_steps": 12000, "total_steps": 40000, "eval_loss": 0.34895405173301697, "epoch": 133.33333333333334, "percentage": 30.0, "elapsed_time": "1:21:37", "remaining_time": "3:10:28", "throughput": 686.22, "total_tokens": 3361008} {"current_steps": 12005, "total_steps": 40000, "loss": 0.0, "lr": 3.968827657764997e-05, "epoch": 133.38888888888889, "percentage": 30.01, "elapsed_time": "1:21:41", "remaining_time": "3:10:29", "throughput": 686.06, "total_tokens": 3362432} {"current_steps": 12010, "total_steps": 40000, "loss": 0.0, "lr": 3.9680331127041e-05, "epoch": 133.44444444444446, "percentage": 30.03, "elapsed_time": "1:21:43", "remaining_time": "3:10:27", "throughput": 686.07, "total_tokens": 3363872} {"current_steps": 12015, "total_steps": 40000, "loss": 0.0, "lr": 3.9672383412540495e-05, "epoch": 133.5, "percentage": 30.04, "elapsed_time": "1:21:45", "remaining_time": "3:10:24", "throughput": 686.08, "total_tokens": 3365264} {"current_steps": 12020, "total_steps": 40000, "loss": 0.0, "lr": 3.966443343537407e-05, "epoch": 133.55555555555554, "percentage": 30.05, "elapsed_time": "1:21:47", "remaining_time": "3:10:22", "throughput": 686.08, "total_tokens": 3366640} {"current_steps": 12025, "total_steps": 40000, "loss": 0.0, "lr": 3.965648119676772e-05, "epoch": 133.61111111111111, "percentage": 30.06, "elapsed_time": "1:21:48", "remaining_time": "3:10:20", "throughput": 686.1, "total_tokens": 3368032} {"current_steps": 12030, "total_steps": 40000, "loss": 0.0, "lr": 3.96485266979478e-05, "epoch": 133.66666666666666, "percentage": 30.08, "elapsed_time": "1:21:50", "remaining_time": "3:10:17", "throughput": 686.11, "total_tokens": 3369456} {"current_steps": 12035, "total_steps": 40000, "loss": 0.0, "lr": 3.9640569940140974e-05, "epoch": 133.72222222222223, "percentage": 30.09, "elapsed_time": "1:21:52", "remaining_time": "3:10:15", "throughput": 686.12, "total_tokens": 3370848} {"current_steps": 12040, "total_steps": 40000, "loss": 0.0, "lr": 3.963261092457428e-05, "epoch": 133.77777777777777, "percentage": 30.1, "elapsed_time": "1:21:54", "remaining_time": "3:10:13", "throughput": 686.14, "total_tokens": 3372256} {"current_steps": 12045, "total_steps": 40000, "loss": 0.0, "lr": 3.962464965247509e-05, "epoch": 133.83333333333334, "percentage": 30.11, "elapsed_time": "1:21:56", "remaining_time": "3:10:11", "throughput": 686.15, "total_tokens": 3373664} {"current_steps": 12050, "total_steps": 40000, "loss": 0.0, "lr": 3.9616686125071135e-05, "epoch": 133.88888888888889, "percentage": 30.12, "elapsed_time": "1:21:58", "remaining_time": "3:10:08", "throughput": 686.17, "total_tokens": 3375072} {"current_steps": 12055, "total_steps": 40000, "loss": 0.0, "lr": 3.9608720343590506e-05, "epoch": 133.94444444444446, "percentage": 30.14, "elapsed_time": "1:22:00", "remaining_time": "3:10:06", "throughput": 686.18, "total_tokens": 3376480} {"current_steps": 12060, "total_steps": 40000, "loss": 0.0, "lr": 3.960075230926161e-05, "epoch": 134.0, "percentage": 30.15, "elapsed_time": "1:22:02", "remaining_time": "3:10:04", "throughput": 686.16, "total_tokens": 3377840} {"current_steps": 12065, "total_steps": 40000, "loss": 0.0, "lr": 3.959278202331322e-05, "epoch": 134.05555555555554, "percentage": 30.16, "elapsed_time": "1:22:04", "remaining_time": "3:10:03", "throughput": 686.15, "total_tokens": 3379264} {"current_steps": 12070, "total_steps": 40000, "loss": 0.0, "lr": 3.958480948697446e-05, "epoch": 134.11111111111111, "percentage": 30.18, "elapsed_time": "1:22:06", "remaining_time": "3:10:00", "throughput": 686.15, "total_tokens": 3380608} {"current_steps": 12075, "total_steps": 40000, "loss": 0.0, "lr": 3.95768347014748e-05, "epoch": 134.16666666666666, "percentage": 30.19, "elapsed_time": "1:22:08", "remaining_time": "3:09:58", "throughput": 686.16, "total_tokens": 3382000} {"current_steps": 12080, "total_steps": 40000, "loss": 0.0, "lr": 3.956885766804404e-05, "epoch": 134.22222222222223, "percentage": 30.2, "elapsed_time": "1:22:10", "remaining_time": "3:09:56", "throughput": 686.17, "total_tokens": 3383392} {"current_steps": 12085, "total_steps": 40000, "loss": 0.0, "lr": 3.956087838791235e-05, "epoch": 134.27777777777777, "percentage": 30.21, "elapsed_time": "1:22:12", "remaining_time": "3:09:54", "throughput": 686.19, "total_tokens": 3384784} {"current_steps": 12090, "total_steps": 40000, "loss": 0.0, "lr": 3.955289686231022e-05, "epoch": 134.33333333333334, "percentage": 30.23, "elapsed_time": "1:22:14", "remaining_time": "3:09:51", "throughput": 686.21, "total_tokens": 3386240} {"current_steps": 12095, "total_steps": 40000, "loss": 0.0, "lr": 3.9544913092468504e-05, "epoch": 134.38888888888889, "percentage": 30.24, "elapsed_time": "1:22:16", "remaining_time": "3:09:49", "throughput": 686.22, "total_tokens": 3387616} {"current_steps": 12100, "total_steps": 40000, "loss": 0.0, "lr": 3.9536927079618425e-05, "epoch": 134.44444444444446, "percentage": 30.25, "elapsed_time": "1:22:18", "remaining_time": "3:09:47", "throughput": 686.23, "total_tokens": 3389008} {"current_steps": 12105, "total_steps": 40000, "loss": 0.0, "lr": 3.9528938824991494e-05, "epoch": 134.5, "percentage": 30.26, "elapsed_time": "1:22:20", "remaining_time": "3:09:45", "throughput": 686.24, "total_tokens": 3390416} {"current_steps": 12110, "total_steps": 40000, "loss": 0.0, "lr": 3.952094832981962e-05, "epoch": 134.55555555555554, "percentage": 30.28, "elapsed_time": "1:22:22", "remaining_time": "3:09:42", "throughput": 686.26, "total_tokens": 3391856} {"current_steps": 12115, "total_steps": 40000, "loss": 0.0, "lr": 3.951295559533503e-05, "epoch": 134.61111111111111, "percentage": 30.29, "elapsed_time": "1:22:24", "remaining_time": "3:09:40", "throughput": 686.27, "total_tokens": 3393216} {"current_steps": 12120, "total_steps": 40000, "loss": 0.0, "lr": 3.95049606227703e-05, "epoch": 134.66666666666666, "percentage": 30.3, "elapsed_time": "1:22:26", "remaining_time": "3:09:38", "throughput": 686.28, "total_tokens": 3394592} {"current_steps": 12125, "total_steps": 40000, "loss": 0.0, "lr": 3.949696341335838e-05, "epoch": 134.72222222222223, "percentage": 30.31, "elapsed_time": "1:22:28", "remaining_time": "3:09:36", "throughput": 686.29, "total_tokens": 3396016} {"current_steps": 12130, "total_steps": 40000, "loss": 0.0, "lr": 3.9488963968332503e-05, "epoch": 134.77777777777777, "percentage": 30.33, "elapsed_time": "1:22:30", "remaining_time": "3:09:33", "throughput": 686.31, "total_tokens": 3397424} {"current_steps": 12135, "total_steps": 40000, "loss": 0.0, "lr": 3.948096228892631e-05, "epoch": 134.83333333333334, "percentage": 30.34, "elapsed_time": "1:22:32", "remaining_time": "3:09:31", "throughput": 686.33, "total_tokens": 3398848} {"current_steps": 12140, "total_steps": 40000, "loss": 0.0, "lr": 3.947295837637375e-05, "epoch": 134.88888888888889, "percentage": 30.35, "elapsed_time": "1:22:34", "remaining_time": "3:09:29", "throughput": 686.34, "total_tokens": 3400272} {"current_steps": 12145, "total_steps": 40000, "loss": 0.0, "lr": 3.9464952231909135e-05, "epoch": 134.94444444444446, "percentage": 30.36, "elapsed_time": "1:22:36", "remaining_time": "3:09:27", "throughput": 686.35, "total_tokens": 3401648} {"current_steps": 12150, "total_steps": 40000, "loss": 0.0, "lr": 3.945694385676711e-05, "epoch": 135.0, "percentage": 30.38, "elapsed_time": "1:22:38", "remaining_time": "3:09:25", "throughput": 686.35, "total_tokens": 3403056} {"current_steps": 12155, "total_steps": 40000, "loss": 0.0, "lr": 3.944893325218265e-05, "epoch": 135.05555555555554, "percentage": 30.39, "elapsed_time": "1:22:40", "remaining_time": "3:09:23", "throughput": 686.33, "total_tokens": 3404464} {"current_steps": 12160, "total_steps": 40000, "loss": 0.0, "lr": 3.944092041939112e-05, "epoch": 135.11111111111111, "percentage": 30.4, "elapsed_time": "1:22:42", "remaining_time": "3:09:21", "throughput": 686.34, "total_tokens": 3405872} {"current_steps": 12165, "total_steps": 40000, "loss": 0.0, "lr": 3.943290535962818e-05, "epoch": 135.16666666666666, "percentage": 30.41, "elapsed_time": "1:22:44", "remaining_time": "3:09:18", "throughput": 686.36, "total_tokens": 3407312} {"current_steps": 12170, "total_steps": 40000, "loss": 0.0, "lr": 3.942488807412985e-05, "epoch": 135.22222222222223, "percentage": 30.43, "elapsed_time": "1:22:46", "remaining_time": "3:09:16", "throughput": 686.38, "total_tokens": 3408736} {"current_steps": 12175, "total_steps": 40000, "loss": 0.0, "lr": 3.941686856413251e-05, "epoch": 135.27777777777777, "percentage": 30.44, "elapsed_time": "1:22:48", "remaining_time": "3:09:14", "throughput": 686.39, "total_tokens": 3410144} {"current_steps": 12180, "total_steps": 40000, "loss": 0.0, "lr": 3.9408846830872874e-05, "epoch": 135.33333333333334, "percentage": 30.45, "elapsed_time": "1:22:50", "remaining_time": "3:09:12", "throughput": 686.42, "total_tokens": 3411600} {"current_steps": 12185, "total_steps": 40000, "loss": 0.0, "lr": 3.940082287558798e-05, "epoch": 135.38888888888889, "percentage": 30.46, "elapsed_time": "1:22:52", "remaining_time": "3:09:09", "throughput": 686.42, "total_tokens": 3412976} {"current_steps": 12190, "total_steps": 40000, "loss": 0.0, "lr": 3.939279669951522e-05, "epoch": 135.44444444444446, "percentage": 30.48, "elapsed_time": "1:22:54", "remaining_time": "3:09:07", "throughput": 686.44, "total_tokens": 3414384} {"current_steps": 12195, "total_steps": 40000, "loss": 0.0, "lr": 3.938476830389234e-05, "epoch": 135.5, "percentage": 30.49, "elapsed_time": "1:22:55", "remaining_time": "3:09:05", "throughput": 686.45, "total_tokens": 3415792} {"current_steps": 12200, "total_steps": 40000, "loss": 0.0, "lr": 3.937673768995742e-05, "epoch": 135.55555555555554, "percentage": 30.5, "elapsed_time": "1:22:57", "remaining_time": "3:09:03", "throughput": 686.46, "total_tokens": 3417152} {"current_steps": 12200, "total_steps": 40000, "eval_loss": 0.3237461447715759, "epoch": 135.55555555555554, "percentage": 30.5, "elapsed_time": "1:22:59", "remaining_time": "3:09:06", "throughput": 686.28, "total_tokens": 3417152} {"current_steps": 12205, "total_steps": 40000, "loss": 0.0, "lr": 3.936870485894888e-05, "epoch": 135.61111111111111, "percentage": 30.51, "elapsed_time": "1:23:03", "remaining_time": "3:09:08", "throughput": 686.01, "total_tokens": 3418480} {"current_steps": 12210, "total_steps": 40000, "loss": 0.0, "lr": 3.9360669812105475e-05, "epoch": 135.66666666666666, "percentage": 30.53, "elapsed_time": "1:23:05", "remaining_time": "3:09:06", "throughput": 686.01, "total_tokens": 3419888} {"current_steps": 12215, "total_steps": 40000, "loss": 0.0, "lr": 3.9352632550666325e-05, "epoch": 135.72222222222223, "percentage": 30.54, "elapsed_time": "1:23:07", "remaining_time": "3:09:04", "throughput": 686.03, "total_tokens": 3421296} {"current_steps": 12220, "total_steps": 40000, "loss": 0.0, "lr": 3.9344593075870866e-05, "epoch": 135.77777777777777, "percentage": 30.55, "elapsed_time": "1:23:09", "remaining_time": "3:09:01", "throughput": 686.04, "total_tokens": 3422688} {"current_steps": 12225, "total_steps": 40000, "loss": 0.0, "lr": 3.933655138895889e-05, "epoch": 135.83333333333334, "percentage": 30.56, "elapsed_time": "1:23:11", "remaining_time": "3:08:59", "throughput": 686.04, "total_tokens": 3424048} {"current_steps": 12230, "total_steps": 40000, "loss": 0.0, "lr": 3.932850749117053e-05, "epoch": 135.88888888888889, "percentage": 30.58, "elapsed_time": "1:23:12", "remaining_time": "3:08:57", "throughput": 686.05, "total_tokens": 3425440} {"current_steps": 12235, "total_steps": 40000, "loss": 0.0, "lr": 3.932046138374624e-05, "epoch": 135.94444444444446, "percentage": 30.59, "elapsed_time": "1:23:14", "remaining_time": "3:08:55", "throughput": 686.05, "total_tokens": 3426784} {"current_steps": 12240, "total_steps": 40000, "loss": 0.0, "lr": 3.9312413067926854e-05, "epoch": 136.0, "percentage": 30.6, "elapsed_time": "1:23:17", "remaining_time": "3:08:53", "throughput": 686.05, "total_tokens": 3428192} {"current_steps": 12245, "total_steps": 40000, "loss": 0.0, "lr": 3.9304362544953506e-05, "epoch": 136.05555555555554, "percentage": 30.61, "elapsed_time": "1:23:19", "remaining_time": "3:08:51", "throughput": 686.02, "total_tokens": 3429600} {"current_steps": 12250, "total_steps": 40000, "loss": 0.0, "lr": 3.929630981606769e-05, "epoch": 136.11111111111111, "percentage": 30.63, "elapsed_time": "1:23:21", "remaining_time": "3:08:49", "throughput": 686.04, "total_tokens": 3431008} {"current_steps": 12255, "total_steps": 40000, "loss": 0.0, "lr": 3.928825488251124e-05, "epoch": 136.16666666666666, "percentage": 30.64, "elapsed_time": "1:23:23", "remaining_time": "3:08:47", "throughput": 686.05, "total_tokens": 3432416} {"current_steps": 12260, "total_steps": 40000, "loss": 0.0, "lr": 3.9280197745526344e-05, "epoch": 136.22222222222223, "percentage": 30.65, "elapsed_time": "1:23:25", "remaining_time": "3:08:44", "throughput": 686.05, "total_tokens": 3433760} {"current_steps": 12265, "total_steps": 40000, "loss": 0.0, "lr": 3.9272138406355495e-05, "epoch": 136.27777777777777, "percentage": 30.66, "elapsed_time": "1:23:27", "remaining_time": "3:08:42", "throughput": 686.06, "total_tokens": 3435136} {"current_steps": 12270, "total_steps": 40000, "loss": 0.0, "lr": 3.926407686624154e-05, "epoch": 136.33333333333334, "percentage": 30.68, "elapsed_time": "1:23:28", "remaining_time": "3:08:40", "throughput": 686.07, "total_tokens": 3436512} {"current_steps": 12275, "total_steps": 40000, "loss": 0.0, "lr": 3.9256013126427684e-05, "epoch": 136.38888888888889, "percentage": 30.69, "elapsed_time": "1:23:30", "remaining_time": "3:08:38", "throughput": 686.07, "total_tokens": 3437888} {"current_steps": 12280, "total_steps": 40000, "loss": 0.0, "lr": 3.9247947188157455e-05, "epoch": 136.44444444444446, "percentage": 30.7, "elapsed_time": "1:23:32", "remaining_time": "3:08:35", "throughput": 686.09, "total_tokens": 3439296} {"current_steps": 12285, "total_steps": 40000, "loss": 0.0, "lr": 3.9239879052674715e-05, "epoch": 136.5, "percentage": 30.71, "elapsed_time": "1:23:34", "remaining_time": "3:08:33", "throughput": 686.1, "total_tokens": 3440704} {"current_steps": 12290, "total_steps": 40000, "loss": 0.0, "lr": 3.9231808721223673e-05, "epoch": 136.55555555555554, "percentage": 30.73, "elapsed_time": "1:23:36", "remaining_time": "3:08:31", "throughput": 686.12, "total_tokens": 3442144} {"current_steps": 12295, "total_steps": 40000, "loss": 0.0, "lr": 3.9223736195048886e-05, "epoch": 136.61111111111111, "percentage": 30.74, "elapsed_time": "1:23:38", "remaining_time": "3:08:29", "throughput": 686.13, "total_tokens": 3443504} {"current_steps": 12300, "total_steps": 40000, "loss": 0.0, "lr": 3.921566147539523e-05, "epoch": 136.66666666666666, "percentage": 30.75, "elapsed_time": "1:23:40", "remaining_time": "3:08:26", "throughput": 686.14, "total_tokens": 3444928} {"current_steps": 12305, "total_steps": 40000, "loss": 0.0, "lr": 3.920758456350792e-05, "epoch": 136.72222222222223, "percentage": 30.76, "elapsed_time": "1:23:42", "remaining_time": "3:08:24", "throughput": 686.16, "total_tokens": 3446368} {"current_steps": 12310, "total_steps": 40000, "loss": 0.0, "lr": 3.919950546063253e-05, "epoch": 136.77777777777777, "percentage": 30.78, "elapsed_time": "1:23:44", "remaining_time": "3:08:22", "throughput": 686.17, "total_tokens": 3447712} {"current_steps": 12315, "total_steps": 40000, "loss": 0.0, "lr": 3.919142416801496e-05, "epoch": 136.83333333333334, "percentage": 30.79, "elapsed_time": "1:23:46", "remaining_time": "3:08:20", "throughput": 686.19, "total_tokens": 3449168} {"current_steps": 12320, "total_steps": 40000, "loss": 0.0, "lr": 3.918334068690144e-05, "epoch": 136.88888888888889, "percentage": 30.8, "elapsed_time": "1:23:48", "remaining_time": "3:08:17", "throughput": 686.19, "total_tokens": 3450528} {"current_steps": 12325, "total_steps": 40000, "loss": 0.0, "lr": 3.917525501853855e-05, "epoch": 136.94444444444446, "percentage": 30.81, "elapsed_time": "1:23:50", "remaining_time": "3:08:15", "throughput": 686.21, "total_tokens": 3451952} {"current_steps": 12330, "total_steps": 40000, "loss": 0.0, "lr": 3.916716716417319e-05, "epoch": 137.0, "percentage": 30.83, "elapsed_time": "1:23:52", "remaining_time": "3:08:13", "throughput": 686.2, "total_tokens": 3453328} {"current_steps": 12335, "total_steps": 40000, "loss": 0.0, "lr": 3.915907712505263e-05, "epoch": 137.05555555555554, "percentage": 30.84, "elapsed_time": "1:23:54", "remaining_time": "3:08:11", "throughput": 686.16, "total_tokens": 3454672} {"current_steps": 12340, "total_steps": 40000, "loss": 0.0, "lr": 3.915098490242444e-05, "epoch": 137.11111111111111, "percentage": 30.85, "elapsed_time": "1:23:56", "remaining_time": "3:08:09", "throughput": 686.18, "total_tokens": 3456096} {"current_steps": 12345, "total_steps": 40000, "loss": 0.0, "lr": 3.914289049753654e-05, "epoch": 137.16666666666666, "percentage": 30.86, "elapsed_time": "1:23:58", "remaining_time": "3:08:07", "throughput": 686.2, "total_tokens": 3457536} {"current_steps": 12350, "total_steps": 40000, "loss": 0.0, "lr": 3.913479391163719e-05, "epoch": 137.22222222222223, "percentage": 30.88, "elapsed_time": "1:24:00", "remaining_time": "3:08:05", "throughput": 686.21, "total_tokens": 3458928} {"current_steps": 12355, "total_steps": 40000, "loss": 0.0, "lr": 3.9126695145975e-05, "epoch": 137.27777777777777, "percentage": 30.89, "elapsed_time": "1:24:02", "remaining_time": "3:08:03", "throughput": 686.23, "total_tokens": 3460368} {"current_steps": 12360, "total_steps": 40000, "loss": 0.0, "lr": 3.911859420179889e-05, "epoch": 137.33333333333334, "percentage": 30.9, "elapsed_time": "1:24:04", "remaining_time": "3:08:00", "throughput": 686.24, "total_tokens": 3461760} {"current_steps": 12365, "total_steps": 40000, "loss": 0.0, "lr": 3.911049108035813e-05, "epoch": 137.38888888888889, "percentage": 30.91, "elapsed_time": "1:24:06", "remaining_time": "3:07:58", "throughput": 686.26, "total_tokens": 3463184} {"current_steps": 12370, "total_steps": 40000, "loss": 0.0, "lr": 3.910238578290232e-05, "epoch": 137.44444444444446, "percentage": 30.93, "elapsed_time": "1:24:08", "remaining_time": "3:07:56", "throughput": 686.28, "total_tokens": 3464624} {"current_steps": 12375, "total_steps": 40000, "loss": 0.0, "lr": 3.90942783106814e-05, "epoch": 137.5, "percentage": 30.94, "elapsed_time": "1:24:10", "remaining_time": "3:07:53", "throughput": 686.29, "total_tokens": 3466000} {"current_steps": 12380, "total_steps": 40000, "loss": 0.0, "lr": 3.908616866494564e-05, "epoch": 137.55555555555554, "percentage": 30.95, "elapsed_time": "1:24:12", "remaining_time": "3:07:51", "throughput": 686.29, "total_tokens": 3467344} {"current_steps": 12385, "total_steps": 40000, "loss": 0.0, "lr": 3.907805684694566e-05, "epoch": 137.61111111111111, "percentage": 30.96, "elapsed_time": "1:24:14", "remaining_time": "3:07:49", "throughput": 686.3, "total_tokens": 3468720} {"current_steps": 12390, "total_steps": 40000, "loss": 0.0, "lr": 3.90699428579324e-05, "epoch": 137.66666666666666, "percentage": 30.98, "elapsed_time": "1:24:16", "remaining_time": "3:07:47", "throughput": 686.3, "total_tokens": 3470064} {"current_steps": 12395, "total_steps": 40000, "loss": 0.0, "lr": 3.906182669915713e-05, "epoch": 137.72222222222223, "percentage": 30.99, "elapsed_time": "1:24:18", "remaining_time": "3:07:45", "throughput": 686.31, "total_tokens": 3471456} {"current_steps": 12400, "total_steps": 40000, "loss": 0.0, "lr": 3.9053708371871476e-05, "epoch": 137.77777777777777, "percentage": 31.0, "elapsed_time": "1:24:20", "remaining_time": "3:07:42", "throughput": 686.31, "total_tokens": 3472832} {"current_steps": 12400, "total_steps": 40000, "eval_loss": 0.3754573464393616, "epoch": 137.77777777777777, "percentage": 31.0, "elapsed_time": "1:24:21", "remaining_time": "3:07:45", "throughput": 686.13, "total_tokens": 3472832} {"current_steps": 12405, "total_steps": 40000, "loss": 0.0, "lr": 3.904558787732738e-05, "epoch": 137.83333333333334, "percentage": 31.01, "elapsed_time": "1:24:24", "remaining_time": "3:07:46", "throughput": 685.95, "total_tokens": 3474272} {"current_steps": 12410, "total_steps": 40000, "loss": 0.0, "lr": 3.9037465216777135e-05, "epoch": 137.88888888888889, "percentage": 31.03, "elapsed_time": "1:24:26", "remaining_time": "3:07:44", "throughput": 685.95, "total_tokens": 3475680} {"current_steps": 12415, "total_steps": 40000, "loss": 0.0, "lr": 3.902934039147334e-05, "epoch": 137.94444444444446, "percentage": 31.04, "elapsed_time": "1:24:28", "remaining_time": "3:07:42", "throughput": 685.97, "total_tokens": 3477088} {"current_steps": 12420, "total_steps": 40000, "loss": 0.0, "lr": 3.902121340266894e-05, "epoch": 138.0, "percentage": 31.05, "elapsed_time": "1:24:31", "remaining_time": "3:07:40", "throughput": 685.95, "total_tokens": 3478464} {"current_steps": 12425, "total_steps": 40000, "loss": 0.0, "lr": 3.9013084251617246e-05, "epoch": 138.05555555555554, "percentage": 31.06, "elapsed_time": "1:24:33", "remaining_time": "3:07:39", "throughput": 685.93, "total_tokens": 3479888} {"current_steps": 12430, "total_steps": 40000, "loss": 0.0, "lr": 3.9004952939571865e-05, "epoch": 138.11111111111111, "percentage": 31.08, "elapsed_time": "1:24:35", "remaining_time": "3:07:36", "throughput": 685.94, "total_tokens": 3481248} {"current_steps": 12435, "total_steps": 40000, "loss": 0.0, "lr": 3.899681946778673e-05, "epoch": 138.16666666666666, "percentage": 31.09, "elapsed_time": "1:24:37", "remaining_time": "3:07:34", "throughput": 685.95, "total_tokens": 3482624} {"current_steps": 12440, "total_steps": 40000, "loss": 0.0, "lr": 3.898868383751615e-05, "epoch": 138.22222222222223, "percentage": 31.1, "elapsed_time": "1:24:39", "remaining_time": "3:07:32", "throughput": 685.96, "total_tokens": 3484032} {"current_steps": 12445, "total_steps": 40000, "loss": 0.0, "lr": 3.8980546050014724e-05, "epoch": 138.27777777777777, "percentage": 31.11, "elapsed_time": "1:24:40", "remaining_time": "3:07:30", "throughput": 685.97, "total_tokens": 3485424} {"current_steps": 12450, "total_steps": 40000, "loss": 0.0, "lr": 3.897240610653741e-05, "epoch": 138.33333333333334, "percentage": 31.13, "elapsed_time": "1:24:42", "remaining_time": "3:07:27", "throughput": 685.99, "total_tokens": 3486832} {"current_steps": 12455, "total_steps": 40000, "loss": 0.0, "lr": 3.896426400833948e-05, "epoch": 138.38888888888889, "percentage": 31.14, "elapsed_time": "1:24:44", "remaining_time": "3:07:25", "throughput": 686.01, "total_tokens": 3488256} {"current_steps": 12460, "total_steps": 40000, "loss": 0.0, "lr": 3.895611975667656e-05, "epoch": 138.44444444444446, "percentage": 31.15, "elapsed_time": "1:24:46", "remaining_time": "3:07:23", "throughput": 686.01, "total_tokens": 3489632} {"current_steps": 12465, "total_steps": 40000, "loss": 0.0, "lr": 3.8947973352804584e-05, "epoch": 138.5, "percentage": 31.16, "elapsed_time": "1:24:48", "remaining_time": "3:07:21", "throughput": 686.02, "total_tokens": 3491024} {"current_steps": 12470, "total_steps": 40000, "loss": 0.0, "lr": 3.893982479797984e-05, "epoch": 138.55555555555554, "percentage": 31.18, "elapsed_time": "1:24:50", "remaining_time": "3:07:18", "throughput": 686.04, "total_tokens": 3492432} {"current_steps": 12475, "total_steps": 40000, "loss": 0.0, "lr": 3.8931674093458926e-05, "epoch": 138.61111111111111, "percentage": 31.19, "elapsed_time": "1:24:52", "remaining_time": "3:07:16", "throughput": 686.06, "total_tokens": 3493872} {"current_steps": 12480, "total_steps": 40000, "loss": 0.0, "lr": 3.89235212404988e-05, "epoch": 138.66666666666666, "percentage": 31.2, "elapsed_time": "1:24:54", "remaining_time": "3:07:14", "throughput": 686.07, "total_tokens": 3495280} {"current_steps": 12485, "total_steps": 40000, "loss": 0.0, "lr": 3.891536624035672e-05, "epoch": 138.72222222222223, "percentage": 31.21, "elapsed_time": "1:24:56", "remaining_time": "3:07:12", "throughput": 686.09, "total_tokens": 3496688} {"current_steps": 12490, "total_steps": 40000, "loss": 0.0, "lr": 3.8907209094290295e-05, "epoch": 138.77777777777777, "percentage": 31.23, "elapsed_time": "1:24:58", "remaining_time": "3:07:09", "throughput": 686.1, "total_tokens": 3498096} {"current_steps": 12495, "total_steps": 40000, "loss": 0.0, "lr": 3.8899049803557466e-05, "epoch": 138.83333333333334, "percentage": 31.24, "elapsed_time": "1:25:00", "remaining_time": "3:07:07", "throughput": 686.11, "total_tokens": 3499488} {"current_steps": 12500, "total_steps": 40000, "loss": 0.0, "lr": 3.889088836941648e-05, "epoch": 138.88888888888889, "percentage": 31.25, "elapsed_time": "1:25:02", "remaining_time": "3:07:05", "throughput": 686.13, "total_tokens": 3500896} {"current_steps": 12505, "total_steps": 40000, "loss": 0.0, "lr": 3.8882724793125946e-05, "epoch": 138.94444444444446, "percentage": 31.26, "elapsed_time": "1:25:04", "remaining_time": "3:07:03", "throughput": 686.14, "total_tokens": 3502304} {"current_steps": 12510, "total_steps": 40000, "loss": 0.0, "lr": 3.8874559075944794e-05, "epoch": 139.0, "percentage": 31.27, "elapsed_time": "1:25:06", "remaining_time": "3:07:01", "throughput": 686.14, "total_tokens": 3503728} {"current_steps": 12515, "total_steps": 40000, "loss": 0.0, "lr": 3.886639121913227e-05, "epoch": 139.05555555555554, "percentage": 31.29, "elapsed_time": "1:25:08", "remaining_time": "3:06:59", "throughput": 686.11, "total_tokens": 3505120} {"current_steps": 12520, "total_steps": 40000, "loss": 0.0, "lr": 3.885822122394797e-05, "epoch": 139.11111111111111, "percentage": 31.3, "elapsed_time": "1:25:10", "remaining_time": "3:06:57", "throughput": 686.12, "total_tokens": 3506512} {"current_steps": 12525, "total_steps": 40000, "loss": 0.0, "lr": 3.8850049091651794e-05, "epoch": 139.16666666666666, "percentage": 31.31, "elapsed_time": "1:25:12", "remaining_time": "3:06:54", "throughput": 686.13, "total_tokens": 3507872} {"current_steps": 12530, "total_steps": 40000, "loss": 0.0, "lr": 3.8841874823504e-05, "epoch": 139.22222222222223, "percentage": 31.32, "elapsed_time": "1:25:14", "remaining_time": "3:06:52", "throughput": 686.13, "total_tokens": 3509248} {"current_steps": 12535, "total_steps": 40000, "loss": 0.0, "lr": 3.8833698420765157e-05, "epoch": 139.27777777777777, "percentage": 31.34, "elapsed_time": "1:25:16", "remaining_time": "3:06:50", "throughput": 686.14, "total_tokens": 3510640} {"current_steps": 12540, "total_steps": 40000, "loss": 0.0, "lr": 3.882551988469618e-05, "epoch": 139.33333333333334, "percentage": 31.35, "elapsed_time": "1:25:18", "remaining_time": "3:06:48", "throughput": 686.16, "total_tokens": 3512064} {"current_steps": 12545, "total_steps": 40000, "loss": 0.0, "lr": 3.881733921655829e-05, "epoch": 139.38888888888889, "percentage": 31.36, "elapsed_time": "1:25:20", "remaining_time": "3:06:46", "throughput": 686.17, "total_tokens": 3513472} {"current_steps": 12550, "total_steps": 40000, "loss": 0.0, "lr": 3.8809156417613054e-05, "epoch": 139.44444444444446, "percentage": 31.37, "elapsed_time": "1:25:22", "remaining_time": "3:06:43", "throughput": 686.2, "total_tokens": 3514928} {"current_steps": 12555, "total_steps": 40000, "loss": 0.0, "lr": 3.8800971489122364e-05, "epoch": 139.5, "percentage": 31.39, "elapsed_time": "1:25:24", "remaining_time": "3:06:41", "throughput": 686.21, "total_tokens": 3516336} {"current_steps": 12560, "total_steps": 40000, "loss": 0.0, "lr": 3.8792784432348434e-05, "epoch": 139.55555555555554, "percentage": 31.4, "elapsed_time": "1:25:26", "remaining_time": "3:06:39", "throughput": 686.22, "total_tokens": 3517728} {"current_steps": 12565, "total_steps": 40000, "loss": 0.0, "lr": 3.878459524855381e-05, "epoch": 139.61111111111111, "percentage": 31.41, "elapsed_time": "1:25:28", "remaining_time": "3:06:37", "throughput": 686.23, "total_tokens": 3519120} {"current_steps": 12570, "total_steps": 40000, "loss": 0.0, "lr": 3.8776403939001384e-05, "epoch": 139.66666666666666, "percentage": 31.42, "elapsed_time": "1:25:30", "remaining_time": "3:06:34", "throughput": 686.24, "total_tokens": 3520512} {"current_steps": 12575, "total_steps": 40000, "loss": 0.0, "lr": 3.876821050495433e-05, "epoch": 139.72222222222223, "percentage": 31.44, "elapsed_time": "1:25:32", "remaining_time": "3:06:32", "throughput": 686.25, "total_tokens": 3521920} {"current_steps": 12580, "total_steps": 40000, "loss": 0.0, "lr": 3.87600149476762e-05, "epoch": 139.77777777777777, "percentage": 31.45, "elapsed_time": "1:25:34", "remaining_time": "3:06:30", "throughput": 686.28, "total_tokens": 3523360} {"current_steps": 12585, "total_steps": 40000, "loss": 0.0, "lr": 3.8751817268430843e-05, "epoch": 139.83333333333334, "percentage": 31.46, "elapsed_time": "1:25:35", "remaining_time": "3:06:28", "throughput": 686.29, "total_tokens": 3524768} {"current_steps": 12590, "total_steps": 40000, "loss": 0.0, "lr": 3.8743617468482464e-05, "epoch": 139.88888888888889, "percentage": 31.47, "elapsed_time": "1:25:37", "remaining_time": "3:06:25", "throughput": 686.3, "total_tokens": 3526176} {"current_steps": 12595, "total_steps": 40000, "loss": 0.0, "lr": 3.8735415549095535e-05, "epoch": 139.94444444444446, "percentage": 31.49, "elapsed_time": "1:25:39", "remaining_time": "3:06:23", "throughput": 686.32, "total_tokens": 3527600} {"current_steps": 12600, "total_steps": 40000, "loss": 0.0, "lr": 3.8727211511534934e-05, "epoch": 140.0, "percentage": 31.5, "elapsed_time": "1:25:41", "remaining_time": "3:06:21", "throughput": 686.31, "total_tokens": 3529008} {"current_steps": 12600, "total_steps": 40000, "eval_loss": 0.3278871774673462, "epoch": 140.0, "percentage": 31.5, "elapsed_time": "1:25:43", "remaining_time": "3:06:24", "throughput": 686.14, "total_tokens": 3529008} {"current_steps": 12605, "total_steps": 40000, "loss": 0.0, "lr": 3.8719005357065804e-05, "epoch": 140.05555555555554, "percentage": 31.51, "elapsed_time": "1:25:46", "remaining_time": "3:06:25", "throughput": 685.94, "total_tokens": 3530384} {"current_steps": 12610, "total_steps": 40000, "loss": 0.0, "lr": 3.8710797086953645e-05, "epoch": 140.11111111111111, "percentage": 31.52, "elapsed_time": "1:25:48", "remaining_time": "3:06:23", "throughput": 685.94, "total_tokens": 3531760} {"current_steps": 12615, "total_steps": 40000, "loss": 0.0, "lr": 3.870258670246427e-05, "epoch": 140.16666666666666, "percentage": 31.54, "elapsed_time": "1:25:50", "remaining_time": "3:06:21", "throughput": 685.95, "total_tokens": 3533152} {"current_steps": 12620, "total_steps": 40000, "loss": 0.0, "lr": 3.869437420486384e-05, "epoch": 140.22222222222223, "percentage": 31.55, "elapsed_time": "1:25:52", "remaining_time": "3:06:19", "throughput": 685.97, "total_tokens": 3534608} {"current_steps": 12625, "total_steps": 40000, "loss": 0.0, "lr": 3.8686159595418805e-05, "epoch": 140.27777777777777, "percentage": 31.56, "elapsed_time": "1:25:54", "remaining_time": "3:06:16", "throughput": 685.99, "total_tokens": 3536016} {"current_steps": 12630, "total_steps": 40000, "loss": 0.0, "lr": 3.867794287539597e-05, "epoch": 140.33333333333334, "percentage": 31.57, "elapsed_time": "1:25:56", "remaining_time": "3:06:14", "throughput": 686.0, "total_tokens": 3537408} {"current_steps": 12635, "total_steps": 40000, "loss": 0.0, "lr": 3.866972404606245e-05, "epoch": 140.38888888888889, "percentage": 31.59, "elapsed_time": "1:25:58", "remaining_time": "3:06:12", "throughput": 686.0, "total_tokens": 3538784} {"current_steps": 12640, "total_steps": 40000, "loss": 0.0, "lr": 3.866150310868571e-05, "epoch": 140.44444444444446, "percentage": 31.6, "elapsed_time": "1:26:00", "remaining_time": "3:06:10", "throughput": 686.02, "total_tokens": 3540192} {"current_steps": 12645, "total_steps": 40000, "loss": 0.0, "lr": 3.8653280064533506e-05, "epoch": 140.5, "percentage": 31.61, "elapsed_time": "1:26:02", "remaining_time": "3:06:07", "throughput": 686.04, "total_tokens": 3541648} {"current_steps": 12650, "total_steps": 40000, "loss": 0.0, "lr": 3.864505491487394e-05, "epoch": 140.55555555555554, "percentage": 31.62, "elapsed_time": "1:26:04", "remaining_time": "3:06:05", "throughput": 686.04, "total_tokens": 3543008} {"current_steps": 12655, "total_steps": 40000, "loss": 0.0, "lr": 3.8636827660975414e-05, "epoch": 140.61111111111111, "percentage": 31.64, "elapsed_time": "1:26:06", "remaining_time": "3:06:03", "throughput": 686.07, "total_tokens": 3544496} {"current_steps": 12660, "total_steps": 40000, "loss": 0.0, "lr": 3.862859830410671e-05, "epoch": 140.66666666666666, "percentage": 31.65, "elapsed_time": "1:26:08", "remaining_time": "3:06:01", "throughput": 686.09, "total_tokens": 3545936} {"current_steps": 12665, "total_steps": 40000, "loss": 0.0, "lr": 3.862036684553688e-05, "epoch": 140.72222222222223, "percentage": 31.66, "elapsed_time": "1:26:10", "remaining_time": "3:05:59", "throughput": 686.1, "total_tokens": 3547312} {"current_steps": 12670, "total_steps": 40000, "loss": 0.0, "lr": 3.8612133286535314e-05, "epoch": 140.77777777777777, "percentage": 31.67, "elapsed_time": "1:26:12", "remaining_time": "3:05:56", "throughput": 686.11, "total_tokens": 3548736} {"current_steps": 12675, "total_steps": 40000, "loss": 0.0, "lr": 3.860389762837173e-05, "epoch": 140.83333333333334, "percentage": 31.69, "elapsed_time": "1:26:14", "remaining_time": "3:05:54", "throughput": 686.12, "total_tokens": 3550112} {"current_steps": 12680, "total_steps": 40000, "loss": 0.0, "lr": 3.859565987231618e-05, "epoch": 140.88888888888889, "percentage": 31.7, "elapsed_time": "1:26:16", "remaining_time": "3:05:52", "throughput": 686.11, "total_tokens": 3551456} {"current_steps": 12685, "total_steps": 40000, "loss": 0.0, "lr": 3.858742001963902e-05, "epoch": 140.94444444444446, "percentage": 31.71, "elapsed_time": "1:26:18", "remaining_time": "3:05:50", "throughput": 686.14, "total_tokens": 3552912} {"current_steps": 12690, "total_steps": 40000, "loss": 0.0, "lr": 3.857917807161094e-05, "epoch": 141.0, "percentage": 31.72, "elapsed_time": "1:26:20", "remaining_time": "3:05:48", "throughput": 686.13, "total_tokens": 3554304} {"current_steps": 12695, "total_steps": 40000, "loss": 0.0, "lr": 3.857093402950296e-05, "epoch": 141.05555555555554, "percentage": 31.74, "elapsed_time": "1:26:22", "remaining_time": "3:05:46", "throughput": 686.11, "total_tokens": 3555744} {"current_steps": 12700, "total_steps": 40000, "loss": 0.0, "lr": 3.8562687894586414e-05, "epoch": 141.11111111111111, "percentage": 31.75, "elapsed_time": "1:26:24", "remaining_time": "3:05:44", "throughput": 686.13, "total_tokens": 3557184} {"current_steps": 12705, "total_steps": 40000, "loss": 0.0, "lr": 3.8554439668132946e-05, "epoch": 141.16666666666666, "percentage": 31.76, "elapsed_time": "1:26:26", "remaining_time": "3:05:42", "throughput": 686.14, "total_tokens": 3558592} {"current_steps": 12710, "total_steps": 40000, "loss": 0.0, "lr": 3.854618935141455e-05, "epoch": 141.22222222222223, "percentage": 31.77, "elapsed_time": "1:26:28", "remaining_time": "3:05:40", "throughput": 686.15, "total_tokens": 3559984} {"current_steps": 12715, "total_steps": 40000, "loss": 0.0, "lr": 3.8537936945703525e-05, "epoch": 141.27777777777777, "percentage": 31.79, "elapsed_time": "1:26:30", "remaining_time": "3:05:37", "throughput": 686.15, "total_tokens": 3561360} {"current_steps": 12720, "total_steps": 40000, "loss": 0.0, "lr": 3.852968245227249e-05, "epoch": 141.33333333333334, "percentage": 31.8, "elapsed_time": "1:26:32", "remaining_time": "3:05:35", "throughput": 686.16, "total_tokens": 3562768} {"current_steps": 12725, "total_steps": 40000, "loss": 0.0, "lr": 3.85214258723944e-05, "epoch": 141.38888888888889, "percentage": 31.81, "elapsed_time": "1:26:34", "remaining_time": "3:05:33", "throughput": 686.18, "total_tokens": 3564176} {"current_steps": 12730, "total_steps": 40000, "loss": 0.0, "lr": 3.8513167207342524e-05, "epoch": 141.44444444444446, "percentage": 31.82, "elapsed_time": "1:26:36", "remaining_time": "3:05:31", "throughput": 686.18, "total_tokens": 3565552} {"current_steps": 12735, "total_steps": 40000, "loss": 0.0, "lr": 3.850490645839044e-05, "epoch": 141.5, "percentage": 31.84, "elapsed_time": "1:26:38", "remaining_time": "3:05:28", "throughput": 686.19, "total_tokens": 3566928} {"current_steps": 12740, "total_steps": 40000, "loss": 0.0, "lr": 3.849664362681207e-05, "epoch": 141.55555555555554, "percentage": 31.85, "elapsed_time": "1:26:40", "remaining_time": "3:05:26", "throughput": 686.21, "total_tokens": 3568352} {"current_steps": 12745, "total_steps": 40000, "loss": 0.0, "lr": 3.848837871388165e-05, "epoch": 141.61111111111111, "percentage": 31.86, "elapsed_time": "1:26:42", "remaining_time": "3:05:24", "throughput": 686.22, "total_tokens": 3569744} {"current_steps": 12750, "total_steps": 40000, "loss": 0.0, "lr": 3.848011172087371e-05, "epoch": 141.66666666666666, "percentage": 31.87, "elapsed_time": "1:26:43", "remaining_time": "3:05:22", "throughput": 686.22, "total_tokens": 3571088} {"current_steps": 12755, "total_steps": 40000, "loss": 0.0, "lr": 3.847184264906315e-05, "epoch": 141.72222222222223, "percentage": 31.89, "elapsed_time": "1:26:45", "remaining_time": "3:05:20", "throughput": 686.23, "total_tokens": 3572496} {"current_steps": 12760, "total_steps": 40000, "loss": 0.0, "lr": 3.846357149972516e-05, "epoch": 141.77777777777777, "percentage": 31.9, "elapsed_time": "1:26:47", "remaining_time": "3:05:17", "throughput": 686.25, "total_tokens": 3573920} {"current_steps": 12765, "total_steps": 40000, "loss": 0.0, "lr": 3.8455298274135246e-05, "epoch": 141.83333333333334, "percentage": 31.91, "elapsed_time": "1:26:49", "remaining_time": "3:05:15", "throughput": 686.25, "total_tokens": 3575264} {"current_steps": 12770, "total_steps": 40000, "loss": 0.0, "lr": 3.8447022973569254e-05, "epoch": 141.88888888888889, "percentage": 31.92, "elapsed_time": "1:26:51", "remaining_time": "3:05:13", "throughput": 686.26, "total_tokens": 3576672} {"current_steps": 12775, "total_steps": 40000, "loss": 0.0, "lr": 3.843874559930332e-05, "epoch": 141.94444444444446, "percentage": 31.94, "elapsed_time": "1:26:53", "remaining_time": "3:05:11", "throughput": 686.28, "total_tokens": 3578112} {"current_steps": 12780, "total_steps": 40000, "loss": 0.0, "lr": 3.843046615261394e-05, "epoch": 142.0, "percentage": 31.95, "elapsed_time": "1:26:55", "remaining_time": "3:05:09", "throughput": 686.28, "total_tokens": 3579568} {"current_steps": 12785, "total_steps": 40000, "loss": 0.0, "lr": 3.842218463477791e-05, "epoch": 142.05555555555554, "percentage": 31.96, "elapsed_time": "1:26:58", "remaining_time": "3:05:07", "throughput": 686.27, "total_tokens": 3581008} {"current_steps": 12790, "total_steps": 40000, "loss": 0.0, "lr": 3.841390104707233e-05, "epoch": 142.11111111111111, "percentage": 31.97, "elapsed_time": "1:27:00", "remaining_time": "3:05:05", "throughput": 686.28, "total_tokens": 3582416} {"current_steps": 12795, "total_steps": 40000, "loss": 0.0, "lr": 3.8405615390774643e-05, "epoch": 142.16666666666666, "percentage": 31.99, "elapsed_time": "1:27:02", "remaining_time": "3:05:03", "throughput": 686.3, "total_tokens": 3583840} {"current_steps": 12800, "total_steps": 40000, "loss": 0.0, "lr": 3.839732766716259e-05, "epoch": 142.22222222222223, "percentage": 32.0, "elapsed_time": "1:27:03", "remaining_time": "3:05:00", "throughput": 686.3, "total_tokens": 3585200} {"current_steps": 12800, "total_steps": 40000, "eval_loss": 0.30285048484802246, "epoch": 142.22222222222223, "percentage": 32.0, "elapsed_time": "1:27:05", "remaining_time": "3:05:03", "throughput": 686.12, "total_tokens": 3585200} {"current_steps": 12805, "total_steps": 40000, "loss": 0.0, "lr": 3.838903787751425e-05, "epoch": 142.27777777777777, "percentage": 32.01, "elapsed_time": "1:27:08", "remaining_time": "3:05:04", "throughput": 685.96, "total_tokens": 3586640} {"current_steps": 12810, "total_steps": 40000, "loss": 0.0, "lr": 3.838074602310802e-05, "epoch": 142.33333333333334, "percentage": 32.02, "elapsed_time": "1:27:10", "remaining_time": "3:05:02", "throughput": 685.96, "total_tokens": 3588032} {"current_steps": 12815, "total_steps": 40000, "loss": 0.0, "lr": 3.837245210522258e-05, "epoch": 142.38888888888889, "percentage": 32.04, "elapsed_time": "1:27:12", "remaining_time": "3:05:00", "throughput": 685.97, "total_tokens": 3589424} {"current_steps": 12820, "total_steps": 40000, "loss": 0.0, "lr": 3.8364156125136996e-05, "epoch": 142.44444444444446, "percentage": 32.05, "elapsed_time": "1:27:14", "remaining_time": "3:04:57", "throughput": 685.98, "total_tokens": 3590832} {"current_steps": 12825, "total_steps": 40000, "loss": 0.0, "lr": 3.835585808413059e-05, "epoch": 142.5, "percentage": 32.06, "elapsed_time": "1:27:16", "remaining_time": "3:04:55", "throughput": 686.0, "total_tokens": 3592256} {"current_steps": 12830, "total_steps": 40000, "loss": 0.0, "lr": 3.8347557983483024e-05, "epoch": 142.55555555555554, "percentage": 32.07, "elapsed_time": "1:27:18", "remaining_time": "3:04:53", "throughput": 686.01, "total_tokens": 3593632} {"current_steps": 12835, "total_steps": 40000, "loss": 0.0, "lr": 3.833925582447428e-05, "epoch": 142.61111111111111, "percentage": 32.09, "elapsed_time": "1:27:20", "remaining_time": "3:04:51", "throughput": 686.01, "total_tokens": 3594976} {"current_steps": 12840, "total_steps": 40000, "loss": 0.0, "lr": 3.8330951608384656e-05, "epoch": 142.66666666666666, "percentage": 32.1, "elapsed_time": "1:27:22", "remaining_time": "3:04:49", "throughput": 686.02, "total_tokens": 3596400} {"current_steps": 12845, "total_steps": 40000, "loss": 0.0, "lr": 3.832264533649477e-05, "epoch": 142.72222222222223, "percentage": 32.11, "elapsed_time": "1:27:24", "remaining_time": "3:04:46", "throughput": 686.04, "total_tokens": 3597824} {"current_steps": 12850, "total_steps": 40000, "loss": 0.0, "lr": 3.8314337010085555e-05, "epoch": 142.77777777777777, "percentage": 32.12, "elapsed_time": "1:27:26", "remaining_time": "3:04:44", "throughput": 686.04, "total_tokens": 3599200} {"current_steps": 12855, "total_steps": 40000, "loss": 0.0, "lr": 3.830602663043824e-05, "epoch": 142.83333333333334, "percentage": 32.14, "elapsed_time": "1:27:28", "remaining_time": "3:04:42", "throughput": 686.06, "total_tokens": 3600624} {"current_steps": 12860, "total_steps": 40000, "loss": 0.0, "lr": 3.8297714198834414e-05, "epoch": 142.88888888888889, "percentage": 32.15, "elapsed_time": "1:27:30", "remaining_time": "3:04:40", "throughput": 686.07, "total_tokens": 3602032} {"current_steps": 12865, "total_steps": 40000, "loss": 0.0, "lr": 3.828939971655595e-05, "epoch": 142.94444444444446, "percentage": 32.16, "elapsed_time": "1:27:32", "remaining_time": "3:04:37", "throughput": 686.08, "total_tokens": 3603408} {"current_steps": 12870, "total_steps": 40000, "loss": 0.0, "lr": 3.828108318488505e-05, "epoch": 143.0, "percentage": 32.17, "elapsed_time": "1:27:34", "remaining_time": "3:04:36", "throughput": 686.08, "total_tokens": 3604848} {"current_steps": 12875, "total_steps": 40000, "loss": 0.0, "lr": 3.8272764605104216e-05, "epoch": 143.05555555555554, "percentage": 32.19, "elapsed_time": "1:27:36", "remaining_time": "3:04:35", "throughput": 686.01, "total_tokens": 3606256} {"current_steps": 12880, "total_steps": 40000, "loss": 0.0, "lr": 3.826444397849628e-05, "epoch": 143.11111111111111, "percentage": 32.2, "elapsed_time": "1:27:38", "remaining_time": "3:04:32", "throughput": 686.02, "total_tokens": 3607632} {"current_steps": 12885, "total_steps": 40000, "loss": 0.0, "lr": 3.825612130634439e-05, "epoch": 143.16666666666666, "percentage": 32.21, "elapsed_time": "1:27:40", "remaining_time": "3:04:30", "throughput": 686.02, "total_tokens": 3608992} {"current_steps": 12890, "total_steps": 40000, "loss": 0.0, "lr": 3.824779658993202e-05, "epoch": 143.22222222222223, "percentage": 32.23, "elapsed_time": "1:27:42", "remaining_time": "3:04:28", "throughput": 686.03, "total_tokens": 3610400} {"current_steps": 12895, "total_steps": 40000, "loss": 0.0, "lr": 3.823946983054292e-05, "epoch": 143.27777777777777, "percentage": 32.24, "elapsed_time": "1:27:44", "remaining_time": "3:04:26", "throughput": 686.05, "total_tokens": 3611840} {"current_steps": 12900, "total_steps": 40000, "loss": 0.0, "lr": 3.82311410294612e-05, "epoch": 143.33333333333334, "percentage": 32.25, "elapsed_time": "1:27:46", "remaining_time": "3:04:24", "throughput": 686.06, "total_tokens": 3613216} {"current_steps": 12905, "total_steps": 40000, "loss": 0.0, "lr": 3.822281018797127e-05, "epoch": 143.38888888888889, "percentage": 32.26, "elapsed_time": "1:27:48", "remaining_time": "3:04:21", "throughput": 686.07, "total_tokens": 3614608} {"current_steps": 12910, "total_steps": 40000, "loss": 0.0, "lr": 3.821447730735783e-05, "epoch": 143.44444444444446, "percentage": 32.27, "elapsed_time": "1:27:50", "remaining_time": "3:04:19", "throughput": 686.09, "total_tokens": 3616048} {"current_steps": 12915, "total_steps": 40000, "loss": 0.0, "lr": 3.820614238890592e-05, "epoch": 143.5, "percentage": 32.29, "elapsed_time": "1:27:52", "remaining_time": "3:04:17", "throughput": 686.1, "total_tokens": 3617440} {"current_steps": 12920, "total_steps": 40000, "loss": 0.0, "lr": 3.819780543390091e-05, "epoch": 143.55555555555554, "percentage": 32.3, "elapsed_time": "1:27:54", "remaining_time": "3:04:15", "throughput": 686.11, "total_tokens": 3618832} {"current_steps": 12925, "total_steps": 40000, "loss": 0.0, "lr": 3.818946644362844e-05, "epoch": 143.61111111111111, "percentage": 32.31, "elapsed_time": "1:27:56", "remaining_time": "3:04:12", "throughput": 686.12, "total_tokens": 3620240} {"current_steps": 12930, "total_steps": 40000, "loss": 0.0, "lr": 3.81811254193745e-05, "epoch": 143.66666666666666, "percentage": 32.32, "elapsed_time": "1:27:58", "remaining_time": "3:04:10", "throughput": 686.14, "total_tokens": 3621664} {"current_steps": 12935, "total_steps": 40000, "loss": 0.0, "lr": 3.8172782362425366e-05, "epoch": 143.72222222222223, "percentage": 32.34, "elapsed_time": "1:28:00", "remaining_time": "3:04:08", "throughput": 686.15, "total_tokens": 3623056} {"current_steps": 12940, "total_steps": 40000, "loss": 0.0, "lr": 3.816443727406765e-05, "epoch": 143.77777777777777, "percentage": 32.35, "elapsed_time": "1:28:02", "remaining_time": "3:04:06", "throughput": 686.17, "total_tokens": 3624496} {"current_steps": 12945, "total_steps": 40000, "loss": 0.0, "lr": 3.815609015558829e-05, "epoch": 143.83333333333334, "percentage": 32.36, "elapsed_time": "1:28:04", "remaining_time": "3:04:03", "throughput": 686.18, "total_tokens": 3625888} {"current_steps": 12950, "total_steps": 40000, "loss": 0.0, "lr": 3.814774100827448e-05, "epoch": 143.88888888888889, "percentage": 32.38, "elapsed_time": "1:28:06", "remaining_time": "3:04:01", "throughput": 686.18, "total_tokens": 3627264} {"current_steps": 12955, "total_steps": 40000, "loss": 0.0, "lr": 3.813938983341379e-05, "epoch": 143.94444444444446, "percentage": 32.39, "elapsed_time": "1:28:08", "remaining_time": "3:03:59", "throughput": 686.19, "total_tokens": 3628640} {"current_steps": 12960, "total_steps": 40000, "loss": 0.0, "lr": 3.813103663229407e-05, "epoch": 144.0, "percentage": 32.4, "elapsed_time": "1:28:10", "remaining_time": "3:03:57", "throughput": 686.17, "total_tokens": 3630016} {"current_steps": 12965, "total_steps": 40000, "loss": 0.0, "lr": 3.812268140620349e-05, "epoch": 144.05555555555554, "percentage": 32.41, "elapsed_time": "1:28:12", "remaining_time": "3:03:55", "throughput": 686.15, "total_tokens": 3631424} {"current_steps": 12970, "total_steps": 40000, "loss": 0.0, "lr": 3.811432415643051e-05, "epoch": 144.11111111111111, "percentage": 32.42, "elapsed_time": "1:28:14", "remaining_time": "3:03:53", "throughput": 686.16, "total_tokens": 3632800} {"current_steps": 12975, "total_steps": 40000, "loss": 0.0, "lr": 3.8105964884263954e-05, "epoch": 144.16666666666666, "percentage": 32.44, "elapsed_time": "1:28:16", "remaining_time": "3:03:51", "throughput": 686.17, "total_tokens": 3634192} {"current_steps": 12980, "total_steps": 40000, "loss": 0.0, "lr": 3.809760359099291e-05, "epoch": 144.22222222222223, "percentage": 32.45, "elapsed_time": "1:28:18", "remaining_time": "3:03:49", "throughput": 686.19, "total_tokens": 3635632} {"current_steps": 12985, "total_steps": 40000, "loss": 0.0, "lr": 3.8089240277906804e-05, "epoch": 144.27777777777777, "percentage": 32.46, "elapsed_time": "1:28:20", "remaining_time": "3:03:47", "throughput": 686.19, "total_tokens": 3636976} {"current_steps": 12990, "total_steps": 40000, "loss": 0.0, "lr": 3.808087494629535e-05, "epoch": 144.33333333333334, "percentage": 32.48, "elapsed_time": "1:28:22", "remaining_time": "3:03:44", "throughput": 686.2, "total_tokens": 3638368} {"current_steps": 12995, "total_steps": 40000, "loss": 0.0, "lr": 3.8072507597448595e-05, "epoch": 144.38888888888889, "percentage": 32.49, "elapsed_time": "1:28:24", "remaining_time": "3:03:42", "throughput": 686.21, "total_tokens": 3639744} {"current_steps": 13000, "total_steps": 40000, "loss": 0.0, "lr": 3.806413823265689e-05, "epoch": 144.44444444444446, "percentage": 32.5, "elapsed_time": "1:28:26", "remaining_time": "3:03:40", "throughput": 686.23, "total_tokens": 3641200} {"current_steps": 13000, "total_steps": 40000, "eval_loss": 0.3639534115791321, "epoch": 144.44444444444446, "percentage": 32.5, "elapsed_time": "1:28:27", "remaining_time": "3:03:43", "throughput": 686.06, "total_tokens": 3641200} {"current_steps": 13005, "total_steps": 40000, "loss": 0.0, "lr": 3.805576685321089e-05, "epoch": 144.5, "percentage": 32.51, "elapsed_time": "1:28:30", "remaining_time": "3:03:43", "throughput": 685.9, "total_tokens": 3642592} {"current_steps": 13010, "total_steps": 40000, "loss": 0.0, "lr": 3.804739346040158e-05, "epoch": 144.55555555555554, "percentage": 32.52, "elapsed_time": "1:28:32", "remaining_time": "3:03:41", "throughput": 685.91, "total_tokens": 3643984} {"current_steps": 13015, "total_steps": 40000, "loss": 0.0, "lr": 3.8039018055520234e-05, "epoch": 144.61111111111111, "percentage": 32.54, "elapsed_time": "1:28:34", "remaining_time": "3:03:39", "throughput": 685.91, "total_tokens": 3645360} {"current_steps": 13020, "total_steps": 40000, "loss": 0.0, "lr": 3.803064063985844e-05, "epoch": 144.66666666666666, "percentage": 32.55, "elapsed_time": "1:28:36", "remaining_time": "3:03:37", "throughput": 685.92, "total_tokens": 3646784} {"current_steps": 13025, "total_steps": 40000, "loss": 0.0, "lr": 3.802226121470811e-05, "epoch": 144.72222222222223, "percentage": 32.56, "elapsed_time": "1:28:38", "remaining_time": "3:03:34", "throughput": 685.94, "total_tokens": 3648192} {"current_steps": 13030, "total_steps": 40000, "loss": 0.0, "lr": 3.801387978136145e-05, "epoch": 144.77777777777777, "percentage": 32.57, "elapsed_time": "1:28:40", "remaining_time": "3:03:32", "throughput": 685.95, "total_tokens": 3649584} {"current_steps": 13035, "total_steps": 40000, "loss": 0.0, "lr": 3.800549634111099e-05, "epoch": 144.83333333333334, "percentage": 32.59, "elapsed_time": "1:28:42", "remaining_time": "3:03:30", "throughput": 685.96, "total_tokens": 3650976} {"current_steps": 13040, "total_steps": 40000, "loss": 0.0, "lr": 3.799711089524955e-05, "epoch": 144.88888888888889, "percentage": 32.6, "elapsed_time": "1:28:44", "remaining_time": "3:03:28", "throughput": 685.97, "total_tokens": 3652384} {"current_steps": 13045, "total_steps": 40000, "loss": 0.0, "lr": 3.7988723445070285e-05, "epoch": 144.94444444444446, "percentage": 32.61, "elapsed_time": "1:28:46", "remaining_time": "3:03:25", "throughput": 685.98, "total_tokens": 3653792} {"current_steps": 13050, "total_steps": 40000, "loss": 0.0, "lr": 3.798033399186663e-05, "epoch": 145.0, "percentage": 32.62, "elapsed_time": "1:28:48", "remaining_time": "3:03:24", "throughput": 685.98, "total_tokens": 3655216} {"current_steps": 13055, "total_steps": 40000, "loss": 0.0, "lr": 3.797194253693237e-05, "epoch": 145.05555555555554, "percentage": 32.64, "elapsed_time": "1:28:50", "remaining_time": "3:03:22", "throughput": 685.96, "total_tokens": 3656640} {"current_steps": 13060, "total_steps": 40000, "loss": 0.0, "lr": 3.796354908156153e-05, "epoch": 145.11111111111111, "percentage": 32.65, "elapsed_time": "1:28:52", "remaining_time": "3:03:20", "throughput": 685.97, "total_tokens": 3658032} {"current_steps": 13065, "total_steps": 40000, "loss": 0.0, "lr": 3.795515362704853e-05, "epoch": 145.16666666666666, "percentage": 32.66, "elapsed_time": "1:28:54", "remaining_time": "3:03:17", "throughput": 685.98, "total_tokens": 3659392} {"current_steps": 13070, "total_steps": 40000, "loss": 0.0, "lr": 3.794675617468803e-05, "epoch": 145.22222222222223, "percentage": 32.67, "elapsed_time": "1:28:56", "remaining_time": "3:03:15", "throughput": 685.98, "total_tokens": 3660768} {"current_steps": 13075, "total_steps": 40000, "loss": 0.0, "lr": 3.793835672577503e-05, "epoch": 145.27777777777777, "percentage": 32.69, "elapsed_time": "1:28:58", "remaining_time": "3:03:13", "throughput": 686.0, "total_tokens": 3662192} {"current_steps": 13080, "total_steps": 40000, "loss": 0.0, "lr": 3.7929955281604826e-05, "epoch": 145.33333333333334, "percentage": 32.7, "elapsed_time": "1:29:00", "remaining_time": "3:03:11", "throughput": 686.01, "total_tokens": 3663600} {"current_steps": 13085, "total_steps": 40000, "loss": 0.0, "lr": 3.7921551843473036e-05, "epoch": 145.38888888888889, "percentage": 32.71, "elapsed_time": "1:29:02", "remaining_time": "3:03:08", "throughput": 686.02, "total_tokens": 3664992} {"current_steps": 13090, "total_steps": 40000, "loss": 0.0, "lr": 3.791314641267557e-05, "epoch": 145.44444444444446, "percentage": 32.73, "elapsed_time": "1:29:04", "remaining_time": "3:03:06", "throughput": 686.03, "total_tokens": 3666384} {"current_steps": 13095, "total_steps": 40000, "loss": 0.0, "lr": 3.790473899050864e-05, "epoch": 145.5, "percentage": 32.74, "elapsed_time": "1:29:06", "remaining_time": "3:03:04", "throughput": 686.04, "total_tokens": 3667792} {"current_steps": 13100, "total_steps": 40000, "loss": 0.0, "lr": 3.7896329578268794e-05, "epoch": 145.55555555555554, "percentage": 32.75, "elapsed_time": "1:29:08", "remaining_time": "3:03:02", "throughput": 686.06, "total_tokens": 3669200} {"current_steps": 13105, "total_steps": 40000, "loss": 0.0, "lr": 3.7887918177252855e-05, "epoch": 145.61111111111111, "percentage": 32.76, "elapsed_time": "1:29:10", "remaining_time": "3:02:59", "throughput": 686.06, "total_tokens": 3670560} {"current_steps": 13110, "total_steps": 40000, "loss": 0.0, "lr": 3.787950478875798e-05, "epoch": 145.66666666666666, "percentage": 32.77, "elapsed_time": "1:29:12", "remaining_time": "3:02:57", "throughput": 686.08, "total_tokens": 3671952} {"current_steps": 13115, "total_steps": 40000, "loss": 0.0, "lr": 3.787108941408162e-05, "epoch": 145.72222222222223, "percentage": 32.79, "elapsed_time": "1:29:14", "remaining_time": "3:02:55", "throughput": 686.09, "total_tokens": 3673360} {"current_steps": 13120, "total_steps": 40000, "loss": 0.0, "lr": 3.786267205452151e-05, "epoch": 145.77777777777777, "percentage": 32.8, "elapsed_time": "1:29:15", "remaining_time": "3:02:53", "throughput": 686.1, "total_tokens": 3674736} {"current_steps": 13125, "total_steps": 40000, "loss": 0.0, "lr": 3.785425271137573e-05, "epoch": 145.83333333333334, "percentage": 32.81, "elapsed_time": "1:29:17", "remaining_time": "3:02:50", "throughput": 686.11, "total_tokens": 3676144} {"current_steps": 13130, "total_steps": 40000, "loss": 0.0, "lr": 3.7845831385942655e-05, "epoch": 145.88888888888889, "percentage": 32.82, "elapsed_time": "1:29:19", "remaining_time": "3:02:48", "throughput": 686.13, "total_tokens": 3677584} {"current_steps": 13135, "total_steps": 40000, "loss": 0.0, "lr": 3.7837408079520944e-05, "epoch": 145.94444444444446, "percentage": 32.84, "elapsed_time": "1:29:21", "remaining_time": "3:02:46", "throughput": 686.15, "total_tokens": 3679008} {"current_steps": 13140, "total_steps": 40000, "loss": 0.0, "lr": 3.782898279340957e-05, "epoch": 146.0, "percentage": 32.85, "elapsed_time": "1:29:23", "remaining_time": "3:02:44", "throughput": 686.14, "total_tokens": 3680432} {"current_steps": 13145, "total_steps": 40000, "loss": 0.0, "lr": 3.782055552890784e-05, "epoch": 146.05555555555554, "percentage": 32.86, "elapsed_time": "1:29:26", "remaining_time": "3:02:42", "throughput": 686.12, "total_tokens": 3681808} {"current_steps": 13150, "total_steps": 40000, "loss": 0.0, "lr": 3.781212628731534e-05, "epoch": 146.11111111111111, "percentage": 32.88, "elapsed_time": "1:29:28", "remaining_time": "3:02:40", "throughput": 686.13, "total_tokens": 3683200} {"current_steps": 13155, "total_steps": 40000, "loss": 0.0, "lr": 3.7803695069931946e-05, "epoch": 146.16666666666666, "percentage": 32.89, "elapsed_time": "1:29:30", "remaining_time": "3:02:38", "throughput": 686.14, "total_tokens": 3684608} {"current_steps": 13160, "total_steps": 40000, "loss": 0.0, "lr": 3.779526187805789e-05, "epoch": 146.22222222222223, "percentage": 32.9, "elapsed_time": "1:29:31", "remaining_time": "3:02:36", "throughput": 686.16, "total_tokens": 3686064} {"current_steps": 13165, "total_steps": 40000, "loss": 0.0, "lr": 3.778682671299364e-05, "epoch": 146.27777777777777, "percentage": 32.91, "elapsed_time": "1:29:33", "remaining_time": "3:02:33", "throughput": 686.18, "total_tokens": 3687456} {"current_steps": 13170, "total_steps": 40000, "loss": 0.0, "lr": 3.777838957604003e-05, "epoch": 146.33333333333334, "percentage": 32.92, "elapsed_time": "1:29:35", "remaining_time": "3:02:31", "throughput": 686.18, "total_tokens": 3688800} {"current_steps": 13175, "total_steps": 40000, "loss": 0.0, "lr": 3.776995046849816e-05, "epoch": 146.38888888888889, "percentage": 32.94, "elapsed_time": "1:29:37", "remaining_time": "3:02:29", "throughput": 686.19, "total_tokens": 3690208} {"current_steps": 13180, "total_steps": 40000, "loss": 0.0, "lr": 3.776150939166945e-05, "epoch": 146.44444444444446, "percentage": 32.95, "elapsed_time": "1:29:39", "remaining_time": "3:02:27", "throughput": 686.21, "total_tokens": 3691616} {"current_steps": 13185, "total_steps": 40000, "loss": 0.0, "lr": 3.775306634685562e-05, "epoch": 146.5, "percentage": 32.96, "elapsed_time": "1:29:41", "remaining_time": "3:02:25", "throughput": 686.22, "total_tokens": 3693008} {"current_steps": 13190, "total_steps": 40000, "loss": 0.0, "lr": 3.7744621335358696e-05, "epoch": 146.55555555555554, "percentage": 32.98, "elapsed_time": "1:29:43", "remaining_time": "3:02:22", "throughput": 686.24, "total_tokens": 3694448} {"current_steps": 13195, "total_steps": 40000, "loss": 0.0, "lr": 3.7736174358481e-05, "epoch": 146.61111111111111, "percentage": 32.99, "elapsed_time": "1:29:45", "remaining_time": "3:02:20", "throughput": 686.25, "total_tokens": 3695840} {"current_steps": 13200, "total_steps": 40000, "loss": 0.0, "lr": 3.7727725417525175e-05, "epoch": 146.66666666666666, "percentage": 33.0, "elapsed_time": "1:29:47", "remaining_time": "3:02:18", "throughput": 686.26, "total_tokens": 3697232} {"current_steps": 13200, "total_steps": 40000, "eval_loss": 0.3433644771575928, "epoch": 146.66666666666666, "percentage": 33.0, "elapsed_time": "1:29:48", "remaining_time": "3:02:21", "throughput": 686.09, "total_tokens": 3697232} {"current_steps": 13205, "total_steps": 40000, "loss": 0.0, "lr": 3.771927451379414e-05, "epoch": 146.72222222222223, "percentage": 33.01, "elapsed_time": "1:29:52", "remaining_time": "3:02:21", "throughput": 685.91, "total_tokens": 3698624} {"current_steps": 13210, "total_steps": 40000, "loss": 0.0, "lr": 3.7710821648591135e-05, "epoch": 146.77777777777777, "percentage": 33.02, "elapsed_time": "1:29:54", "remaining_time": "3:02:19", "throughput": 685.92, "total_tokens": 3700064} {"current_steps": 13215, "total_steps": 40000, "loss": 0.0, "lr": 3.7702366823219694e-05, "epoch": 146.83333333333334, "percentage": 33.04, "elapsed_time": "1:29:56", "remaining_time": "3:02:17", "throughput": 685.92, "total_tokens": 3701440} {"current_steps": 13220, "total_steps": 40000, "loss": 0.0, "lr": 3.769391003898366e-05, "epoch": 146.88888888888889, "percentage": 33.05, "elapsed_time": "1:29:58", "remaining_time": "3:02:15", "throughput": 685.93, "total_tokens": 3702832} {"current_steps": 13225, "total_steps": 40000, "loss": 0.0, "lr": 3.768545129718718e-05, "epoch": 146.94444444444446, "percentage": 33.06, "elapsed_time": "1:30:00", "remaining_time": "3:02:13", "throughput": 685.93, "total_tokens": 3704192} {"current_steps": 13230, "total_steps": 40000, "loss": 0.0, "lr": 3.7676990599134686e-05, "epoch": 147.0, "percentage": 33.07, "elapsed_time": "1:30:02", "remaining_time": "3:02:11", "throughput": 685.92, "total_tokens": 3705584} {"current_steps": 13235, "total_steps": 40000, "loss": 0.0, "lr": 3.766852794613095e-05, "epoch": 147.05555555555554, "percentage": 33.09, "elapsed_time": "1:30:04", "remaining_time": "3:02:09", "throughput": 685.89, "total_tokens": 3706960} {"current_steps": 13240, "total_steps": 40000, "loss": 0.0, "lr": 3.766006333948099e-05, "epoch": 147.11111111111111, "percentage": 33.1, "elapsed_time": "1:30:06", "remaining_time": "3:02:07", "throughput": 685.9, "total_tokens": 3708336} {"current_steps": 13245, "total_steps": 40000, "loss": 0.0, "lr": 3.765159678049017e-05, "epoch": 147.16666666666666, "percentage": 33.11, "elapsed_time": "1:30:08", "remaining_time": "3:02:05", "throughput": 685.91, "total_tokens": 3709712} {"current_steps": 13250, "total_steps": 40000, "loss": 0.0, "lr": 3.7643128270464134e-05, "epoch": 147.22222222222223, "percentage": 33.12, "elapsed_time": "1:30:10", "remaining_time": "3:02:02", "throughput": 685.93, "total_tokens": 3711152} {"current_steps": 13255, "total_steps": 40000, "loss": 0.0, "lr": 3.763465781070884e-05, "epoch": 147.27777777777777, "percentage": 33.14, "elapsed_time": "1:30:12", "remaining_time": "3:02:00", "throughput": 685.94, "total_tokens": 3712544} {"current_steps": 13260, "total_steps": 40000, "loss": 0.0, "lr": 3.762618540253052e-05, "epoch": 147.33333333333334, "percentage": 33.15, "elapsed_time": "1:30:14", "remaining_time": "3:01:58", "throughput": 685.96, "total_tokens": 3713968} {"current_steps": 13265, "total_steps": 40000, "loss": 0.0, "lr": 3.761771104723576e-05, "epoch": 147.38888888888889, "percentage": 33.16, "elapsed_time": "1:30:16", "remaining_time": "3:01:56", "throughput": 685.97, "total_tokens": 3715376} {"current_steps": 13270, "total_steps": 40000, "loss": 0.0, "lr": 3.7609234746131386e-05, "epoch": 147.44444444444446, "percentage": 33.17, "elapsed_time": "1:30:18", "remaining_time": "3:01:53", "throughput": 685.99, "total_tokens": 3716816} {"current_steps": 13275, "total_steps": 40000, "loss": 0.0, "lr": 3.7600756500524556e-05, "epoch": 147.5, "percentage": 33.19, "elapsed_time": "1:30:20", "remaining_time": "3:01:51", "throughput": 685.99, "total_tokens": 3718160} {"current_steps": 13280, "total_steps": 40000, "loss": 0.0, "lr": 3.759227631172271e-05, "epoch": 147.55555555555554, "percentage": 33.2, "elapsed_time": "1:30:22", "remaining_time": "3:01:49", "throughput": 686.0, "total_tokens": 3719552} {"current_steps": 13285, "total_steps": 40000, "loss": 0.0, "lr": 3.758379418103363e-05, "epoch": 147.61111111111111, "percentage": 33.21, "elapsed_time": "1:30:24", "remaining_time": "3:01:47", "throughput": 686.01, "total_tokens": 3720944} {"current_steps": 13290, "total_steps": 40000, "loss": 0.0, "lr": 3.757531010976534e-05, "epoch": 147.66666666666666, "percentage": 33.23, "elapsed_time": "1:30:25", "remaining_time": "3:01:44", "throughput": 686.03, "total_tokens": 3722352} {"current_steps": 13295, "total_steps": 40000, "loss": 0.0, "lr": 3.75668240992262e-05, "epoch": 147.72222222222223, "percentage": 33.24, "elapsed_time": "1:30:27", "remaining_time": "3:01:42", "throughput": 686.04, "total_tokens": 3723728} {"current_steps": 13300, "total_steps": 40000, "loss": 0.0, "lr": 3.7558336150724865e-05, "epoch": 147.77777777777777, "percentage": 33.25, "elapsed_time": "1:30:29", "remaining_time": "3:01:40", "throughput": 686.05, "total_tokens": 3725152} {"current_steps": 13305, "total_steps": 40000, "loss": 0.0, "lr": 3.754984626557028e-05, "epoch": 147.83333333333334, "percentage": 33.26, "elapsed_time": "1:30:31", "remaining_time": "3:01:38", "throughput": 686.06, "total_tokens": 3726528} {"current_steps": 13310, "total_steps": 40000, "loss": 0.0, "lr": 3.754135444507168e-05, "epoch": 147.88888888888889, "percentage": 33.27, "elapsed_time": "1:30:33", "remaining_time": "3:01:36", "throughput": 686.07, "total_tokens": 3727920} {"current_steps": 13315, "total_steps": 40000, "loss": 0.0, "lr": 3.753286069053863e-05, "epoch": 147.94444444444446, "percentage": 33.29, "elapsed_time": "1:30:35", "remaining_time": "3:01:33", "throughput": 686.09, "total_tokens": 3729360} {"current_steps": 13320, "total_steps": 40000, "loss": 0.0, "lr": 3.7524365003280945e-05, "epoch": 148.0, "percentage": 33.3, "elapsed_time": "1:30:37", "remaining_time": "3:01:31", "throughput": 686.09, "total_tokens": 3730784} {"current_steps": 13325, "total_steps": 40000, "loss": 0.0, "lr": 3.75158673846088e-05, "epoch": 148.05555555555554, "percentage": 33.31, "elapsed_time": "1:30:39", "remaining_time": "3:01:30", "throughput": 686.06, "total_tokens": 3732144} {"current_steps": 13330, "total_steps": 40000, "loss": 0.0, "lr": 3.750736783583262e-05, "epoch": 148.11111111111111, "percentage": 33.32, "elapsed_time": "1:30:41", "remaining_time": "3:01:27", "throughput": 686.08, "total_tokens": 3733584} {"current_steps": 13335, "total_steps": 40000, "loss": 0.0, "lr": 3.7498866358263144e-05, "epoch": 148.16666666666666, "percentage": 33.34, "elapsed_time": "1:30:43", "remaining_time": "3:01:25", "throughput": 686.09, "total_tokens": 3735008} {"current_steps": 13340, "total_steps": 40000, "loss": 0.0, "lr": 3.74903629532114e-05, "epoch": 148.22222222222223, "percentage": 33.35, "elapsed_time": "1:30:45", "remaining_time": "3:01:23", "throughput": 686.11, "total_tokens": 3736416} {"current_steps": 13345, "total_steps": 40000, "loss": 0.0, "lr": 3.748185762198873e-05, "epoch": 148.27777777777777, "percentage": 33.36, "elapsed_time": "1:30:47", "remaining_time": "3:01:21", "throughput": 686.13, "total_tokens": 3737888} {"current_steps": 13350, "total_steps": 40000, "loss": 0.0, "lr": 3.747335036590676e-05, "epoch": 148.33333333333334, "percentage": 33.38, "elapsed_time": "1:30:49", "remaining_time": "3:01:19", "throughput": 686.14, "total_tokens": 3739296} {"current_steps": 13355, "total_steps": 40000, "loss": 0.0, "lr": 3.7464841186277405e-05, "epoch": 148.38888888888889, "percentage": 33.39, "elapsed_time": "1:30:51", "remaining_time": "3:01:16", "throughput": 686.15, "total_tokens": 3740672} {"current_steps": 13360, "total_steps": 40000, "loss": 0.0, "lr": 3.7456330084412896e-05, "epoch": 148.44444444444446, "percentage": 33.4, "elapsed_time": "1:30:53", "remaining_time": "3:01:14", "throughput": 686.17, "total_tokens": 3742128} {"current_steps": 13365, "total_steps": 40000, "loss": 0.0, "lr": 3.744781706162576e-05, "epoch": 148.5, "percentage": 33.41, "elapsed_time": "1:30:55", "remaining_time": "3:01:12", "throughput": 686.17, "total_tokens": 3743472} {"current_steps": 13370, "total_steps": 40000, "loss": 0.0, "lr": 3.743930211922879e-05, "epoch": 148.55555555555554, "percentage": 33.42, "elapsed_time": "1:30:57", "remaining_time": "3:01:10", "throughput": 686.18, "total_tokens": 3744816} {"current_steps": 13375, "total_steps": 40000, "loss": 0.0, "lr": 3.743078525853513e-05, "epoch": 148.61111111111111, "percentage": 33.44, "elapsed_time": "1:30:59", "remaining_time": "3:01:07", "throughput": 686.18, "total_tokens": 3746192} {"current_steps": 13380, "total_steps": 40000, "loss": 0.0, "lr": 3.7422266480858154e-05, "epoch": 148.66666666666666, "percentage": 33.45, "elapsed_time": "1:31:01", "remaining_time": "3:01:05", "throughput": 686.19, "total_tokens": 3747584} {"current_steps": 13385, "total_steps": 40000, "loss": 0.0, "lr": 3.741374578751158e-05, "epoch": 148.72222222222223, "percentage": 33.46, "elapsed_time": "1:31:03", "remaining_time": "3:01:03", "throughput": 686.2, "total_tokens": 3748960} {"current_steps": 13390, "total_steps": 40000, "loss": 0.0, "lr": 3.740522317980941e-05, "epoch": 148.77777777777777, "percentage": 33.48, "elapsed_time": "1:31:05", "remaining_time": "3:01:01", "throughput": 686.22, "total_tokens": 3750384} {"current_steps": 13395, "total_steps": 40000, "loss": 0.0, "lr": 3.739669865906593e-05, "epoch": 148.83333333333334, "percentage": 33.49, "elapsed_time": "1:31:07", "remaining_time": "3:00:58", "throughput": 686.22, "total_tokens": 3751728} {"current_steps": 13400, "total_steps": 40000, "loss": 0.0, "lr": 3.738817222659573e-05, "epoch": 148.88888888888889, "percentage": 33.5, "elapsed_time": "1:31:09", "remaining_time": "3:00:56", "throughput": 686.24, "total_tokens": 3753168} {"current_steps": 13400, "total_steps": 40000, "eval_loss": 0.37274837493896484, "epoch": 148.88888888888889, "percentage": 33.5, "elapsed_time": "1:31:10", "remaining_time": "3:00:59", "throughput": 686.07, "total_tokens": 3753168} {"current_steps": 13405, "total_steps": 40000, "loss": 0.0, "lr": 3.73796438837137e-05, "epoch": 148.94444444444446, "percentage": 33.51, "elapsed_time": "1:31:13", "remaining_time": "3:00:59", "throughput": 685.93, "total_tokens": 3754576} {"current_steps": 13410, "total_steps": 40000, "loss": 0.0, "lr": 3.7371113631735e-05, "epoch": 149.0, "percentage": 33.52, "elapsed_time": "1:31:15", "remaining_time": "3:00:57", "throughput": 685.91, "total_tokens": 3755984} {"current_steps": 13415, "total_steps": 40000, "loss": 0.0, "lr": 3.736258147197512e-05, "epoch": 149.05555555555554, "percentage": 33.54, "elapsed_time": "1:31:18", "remaining_time": "3:00:56", "throughput": 685.88, "total_tokens": 3757344} {"current_steps": 13420, "total_steps": 40000, "loss": 0.0, "lr": 3.735404740574981e-05, "epoch": 149.11111111111111, "percentage": 33.55, "elapsed_time": "1:31:20", "remaining_time": "3:00:53", "throughput": 685.89, "total_tokens": 3758704} {"current_steps": 13425, "total_steps": 40000, "loss": 0.0, "lr": 3.7345511434375145e-05, "epoch": 149.16666666666666, "percentage": 33.56, "elapsed_time": "1:31:22", "remaining_time": "3:00:51", "throughput": 685.9, "total_tokens": 3760112} {"current_steps": 13430, "total_steps": 40000, "loss": 0.0, "lr": 3.733697355916748e-05, "epoch": 149.22222222222223, "percentage": 33.58, "elapsed_time": "1:31:23", "remaining_time": "3:00:49", "throughput": 685.91, "total_tokens": 3761520} {"current_steps": 13435, "total_steps": 40000, "loss": 0.0, "lr": 3.732843378144345e-05, "epoch": 149.27777777777777, "percentage": 33.59, "elapsed_time": "1:31:25", "remaining_time": "3:00:47", "throughput": 685.92, "total_tokens": 3762896} {"current_steps": 13440, "total_steps": 40000, "loss": 0.0, "lr": 3.7319892102519995e-05, "epoch": 149.33333333333334, "percentage": 33.6, "elapsed_time": "1:31:27", "remaining_time": "3:00:45", "throughput": 685.93, "total_tokens": 3764320} {"current_steps": 13445, "total_steps": 40000, "loss": 0.0, "lr": 3.731134852371436e-05, "epoch": 149.38888888888889, "percentage": 33.61, "elapsed_time": "1:31:29", "remaining_time": "3:00:42", "throughput": 685.95, "total_tokens": 3765744} {"current_steps": 13450, "total_steps": 40000, "loss": 0.0, "lr": 3.730280304634408e-05, "epoch": 149.44444444444446, "percentage": 33.62, "elapsed_time": "1:31:31", "remaining_time": "3:00:40", "throughput": 685.96, "total_tokens": 3767152} {"current_steps": 13455, "total_steps": 40000, "loss": 0.0, "lr": 3.729425567172696e-05, "epoch": 149.5, "percentage": 33.64, "elapsed_time": "1:31:33", "remaining_time": "3:00:38", "throughput": 685.97, "total_tokens": 3768544} {"current_steps": 13460, "total_steps": 40000, "loss": 0.0, "lr": 3.728570640118111e-05, "epoch": 149.55555555555554, "percentage": 33.65, "elapsed_time": "1:31:35", "remaining_time": "3:00:36", "throughput": 685.98, "total_tokens": 3769952} {"current_steps": 13465, "total_steps": 40000, "loss": 0.0, "lr": 3.727715523602494e-05, "epoch": 149.61111111111111, "percentage": 33.66, "elapsed_time": "1:31:37", "remaining_time": "3:00:33", "throughput": 686.0, "total_tokens": 3771360} {"current_steps": 13470, "total_steps": 40000, "loss": 0.0, "lr": 3.726860217757715e-05, "epoch": 149.66666666666666, "percentage": 33.67, "elapsed_time": "1:31:39", "remaining_time": "3:00:31", "throughput": 686.01, "total_tokens": 3772768} {"current_steps": 13475, "total_steps": 40000, "loss": 0.0, "lr": 3.726004722715673e-05, "epoch": 149.72222222222223, "percentage": 33.69, "elapsed_time": "1:31:41", "remaining_time": "3:00:29", "throughput": 686.02, "total_tokens": 3774176} {"current_steps": 13480, "total_steps": 40000, "loss": 0.0, "lr": 3.725149038608296e-05, "epoch": 149.77777777777777, "percentage": 33.7, "elapsed_time": "1:31:43", "remaining_time": "3:00:27", "throughput": 686.04, "total_tokens": 3775600} {"current_steps": 13485, "total_steps": 40000, "loss": 0.0, "lr": 3.7242931655675404e-05, "epoch": 149.83333333333334, "percentage": 33.71, "elapsed_time": "1:31:45", "remaining_time": "3:00:25", "throughput": 686.05, "total_tokens": 3776976} {"current_steps": 13490, "total_steps": 40000, "loss": 0.0, "lr": 3.7234371037253937e-05, "epoch": 149.88888888888889, "percentage": 33.73, "elapsed_time": "1:31:47", "remaining_time": "3:00:22", "throughput": 686.05, "total_tokens": 3778336} {"current_steps": 13495, "total_steps": 40000, "loss": 0.0, "lr": 3.7225808532138705e-05, "epoch": 149.94444444444446, "percentage": 33.74, "elapsed_time": "1:31:49", "remaining_time": "3:00:20", "throughput": 686.07, "total_tokens": 3779744} {"current_steps": 13500, "total_steps": 40000, "loss": 0.0, "lr": 3.721724414165016e-05, "epoch": 150.0, "percentage": 33.75, "elapsed_time": "1:31:51", "remaining_time": "3:00:18", "throughput": 686.05, "total_tokens": 3781120} {"current_steps": 13505, "total_steps": 40000, "loss": 0.0, "lr": 3.720867786710904e-05, "epoch": 150.05555555555554, "percentage": 33.76, "elapsed_time": "1:31:53", "remaining_time": "3:00:17", "throughput": 686.02, "total_tokens": 3782480} {"current_steps": 13510, "total_steps": 40000, "loss": 0.0, "lr": 3.7200109709836366e-05, "epoch": 150.11111111111111, "percentage": 33.77, "elapsed_time": "1:31:55", "remaining_time": "3:00:14", "throughput": 686.03, "total_tokens": 3783888} {"current_steps": 13515, "total_steps": 40000, "loss": 0.0, "lr": 3.7191539671153465e-05, "epoch": 150.16666666666666, "percentage": 33.79, "elapsed_time": "1:31:57", "remaining_time": "3:00:12", "throughput": 686.05, "total_tokens": 3785296} {"current_steps": 13520, "total_steps": 40000, "loss": 0.0, "lr": 3.718296775238193e-05, "epoch": 150.22222222222223, "percentage": 33.8, "elapsed_time": "1:31:59", "remaining_time": "3:00:10", "throughput": 686.05, "total_tokens": 3786656} {"current_steps": 13525, "total_steps": 40000, "loss": 0.0, "lr": 3.7174393954843675e-05, "epoch": 150.27777777777777, "percentage": 33.81, "elapsed_time": "1:32:01", "remaining_time": "3:00:08", "throughput": 686.07, "total_tokens": 3788096} {"current_steps": 13530, "total_steps": 40000, "loss": 0.0, "lr": 3.716581827986087e-05, "epoch": 150.33333333333334, "percentage": 33.83, "elapsed_time": "1:32:03", "remaining_time": "3:00:05", "throughput": 686.08, "total_tokens": 3789472} {"current_steps": 13535, "total_steps": 40000, "loss": 0.0, "lr": 3.7157240728756004e-05, "epoch": 150.38888888888889, "percentage": 33.84, "elapsed_time": "1:32:05", "remaining_time": "3:00:03", "throughput": 686.09, "total_tokens": 3790896} {"current_steps": 13540, "total_steps": 40000, "loss": 0.0, "lr": 3.714866130285184e-05, "epoch": 150.44444444444446, "percentage": 33.85, "elapsed_time": "1:32:07", "remaining_time": "3:00:01", "throughput": 686.1, "total_tokens": 3792272} {"current_steps": 13545, "total_steps": 40000, "loss": 0.0, "lr": 3.714008000347143e-05, "epoch": 150.5, "percentage": 33.86, "elapsed_time": "1:32:09", "remaining_time": "2:59:59", "throughput": 686.11, "total_tokens": 3793664} {"current_steps": 13550, "total_steps": 40000, "loss": 0.0, "lr": 3.7131496831938126e-05, "epoch": 150.55555555555554, "percentage": 33.88, "elapsed_time": "1:32:11", "remaining_time": "2:59:56", "throughput": 686.13, "total_tokens": 3795104} {"current_steps": 13555, "total_steps": 40000, "loss": 0.0, "lr": 3.7122911789575565e-05, "epoch": 150.61111111111111, "percentage": 33.89, "elapsed_time": "1:32:13", "remaining_time": "2:59:54", "throughput": 686.15, "total_tokens": 3796528} {"current_steps": 13560, "total_steps": 40000, "loss": 0.0, "lr": 3.711432487770765e-05, "epoch": 150.66666666666666, "percentage": 33.9, "elapsed_time": "1:32:15", "remaining_time": "2:59:52", "throughput": 686.15, "total_tokens": 3797888} {"current_steps": 13565, "total_steps": 40000, "loss": 0.0, "lr": 3.710573609765861e-05, "epoch": 150.72222222222223, "percentage": 33.91, "elapsed_time": "1:32:16", "remaining_time": "2:59:50", "throughput": 686.17, "total_tokens": 3799328} {"current_steps": 13570, "total_steps": 40000, "loss": 0.0, "lr": 3.709714545075292e-05, "epoch": 150.77777777777777, "percentage": 33.92, "elapsed_time": "1:32:18", "remaining_time": "2:59:48", "throughput": 686.19, "total_tokens": 3800736} {"current_steps": 13575, "total_steps": 40000, "loss": 0.0, "lr": 3.708855293831538e-05, "epoch": 150.83333333333334, "percentage": 33.94, "elapsed_time": "1:32:20", "remaining_time": "2:59:45", "throughput": 686.19, "total_tokens": 3802096} {"current_steps": 13580, "total_steps": 40000, "loss": 0.0, "lr": 3.707995856167107e-05, "epoch": 150.88888888888889, "percentage": 33.95, "elapsed_time": "1:32:22", "remaining_time": "2:59:43", "throughput": 686.21, "total_tokens": 3803520} {"current_steps": 13585, "total_steps": 40000, "loss": 0.0, "lr": 3.707136232214534e-05, "epoch": 150.94444444444446, "percentage": 33.96, "elapsed_time": "1:32:24", "remaining_time": "2:59:41", "throughput": 686.21, "total_tokens": 3804880} {"current_steps": 13590, "total_steps": 40000, "loss": 0.0, "lr": 3.7062764221063844e-05, "epoch": 151.0, "percentage": 33.98, "elapsed_time": "1:32:26", "remaining_time": "2:59:39", "throughput": 686.21, "total_tokens": 3806304} {"current_steps": 13595, "total_steps": 40000, "loss": 0.0, "lr": 3.705416425975252e-05, "epoch": 151.05555555555554, "percentage": 33.99, "elapsed_time": "1:32:29", "remaining_time": "2:59:37", "throughput": 686.19, "total_tokens": 3807712} {"current_steps": 13600, "total_steps": 40000, "loss": 0.0, "lr": 3.704556243953758e-05, "epoch": 151.11111111111111, "percentage": 34.0, "elapsed_time": "1:32:31", "remaining_time": "2:59:35", "throughput": 686.21, "total_tokens": 3809136} {"current_steps": 13600, "total_steps": 40000, "eval_loss": 0.35036537051200867, "epoch": 151.11111111111111, "percentage": 34.0, "elapsed_time": "1:32:32", "remaining_time": "2:59:38", "throughput": 686.04, "total_tokens": 3809136} {"current_steps": 13605, "total_steps": 40000, "loss": 0.0, "lr": 3.7036958761745535e-05, "epoch": 151.16666666666666, "percentage": 34.01, "elapsed_time": "1:32:35", "remaining_time": "2:59:38", "throughput": 685.88, "total_tokens": 3810512} {"current_steps": 13610, "total_steps": 40000, "loss": 0.0, "lr": 3.702835322770318e-05, "epoch": 151.22222222222223, "percentage": 34.02, "elapsed_time": "1:32:37", "remaining_time": "2:59:36", "throughput": 685.89, "total_tokens": 3811936} {"current_steps": 13615, "total_steps": 40000, "loss": 0.0, "lr": 3.701974583873761e-05, "epoch": 151.27777777777777, "percentage": 34.04, "elapsed_time": "1:32:39", "remaining_time": "2:59:34", "throughput": 685.92, "total_tokens": 3813392} {"current_steps": 13620, "total_steps": 40000, "loss": 0.0, "lr": 3.701113659617618e-05, "epoch": 151.33333333333334, "percentage": 34.05, "elapsed_time": "1:32:41", "remaining_time": "2:59:31", "throughput": 685.92, "total_tokens": 3814784} {"current_steps": 13625, "total_steps": 40000, "loss": 0.0, "lr": 3.7002525501346535e-05, "epoch": 151.38888888888889, "percentage": 34.06, "elapsed_time": "1:32:43", "remaining_time": "2:59:29", "throughput": 685.94, "total_tokens": 3816208} {"current_steps": 13630, "total_steps": 40000, "loss": 0.0, "lr": 3.699391255557664e-05, "epoch": 151.44444444444446, "percentage": 34.08, "elapsed_time": "1:32:45", "remaining_time": "2:59:27", "throughput": 685.94, "total_tokens": 3817568} {"current_steps": 13635, "total_steps": 40000, "loss": 0.0, "lr": 3.69852977601947e-05, "epoch": 151.5, "percentage": 34.09, "elapsed_time": "1:32:47", "remaining_time": "2:59:25", "throughput": 685.94, "total_tokens": 3818896} {"current_steps": 13640, "total_steps": 40000, "loss": 0.0, "lr": 3.697668111652922e-05, "epoch": 151.55555555555554, "percentage": 34.1, "elapsed_time": "1:32:49", "remaining_time": "2:59:23", "throughput": 685.95, "total_tokens": 3820288} {"current_steps": 13645, "total_steps": 40000, "loss": 0.0, "lr": 3.6968062625909005e-05, "epoch": 151.61111111111111, "percentage": 34.11, "elapsed_time": "1:32:51", "remaining_time": "2:59:20", "throughput": 685.96, "total_tokens": 3821696} {"current_steps": 13650, "total_steps": 40000, "loss": 0.0, "lr": 3.6959442289663135e-05, "epoch": 151.66666666666666, "percentage": 34.12, "elapsed_time": "1:32:53", "remaining_time": "2:59:18", "throughput": 685.98, "total_tokens": 3823104} {"current_steps": 13655, "total_steps": 40000, "loss": 0.0, "lr": 3.695082010912098e-05, "epoch": 151.72222222222223, "percentage": 34.14, "elapsed_time": "1:32:55", "remaining_time": "2:59:16", "throughput": 685.99, "total_tokens": 3824496} {"current_steps": 13660, "total_steps": 40000, "loss": 0.0, "lr": 3.694219608561217e-05, "epoch": 151.77777777777777, "percentage": 34.15, "elapsed_time": "1:32:57", "remaining_time": "2:59:14", "throughput": 686.0, "total_tokens": 3825888} {"current_steps": 13665, "total_steps": 40000, "loss": 0.0, "lr": 3.693357022046665e-05, "epoch": 151.83333333333334, "percentage": 34.16, "elapsed_time": "1:32:59", "remaining_time": "2:59:11", "throughput": 686.01, "total_tokens": 3827296} {"current_steps": 13670, "total_steps": 40000, "loss": 0.0, "lr": 3.6924942515014644e-05, "epoch": 151.88888888888889, "percentage": 34.17, "elapsed_time": "1:33:01", "remaining_time": "2:59:09", "throughput": 686.02, "total_tokens": 3828688} {"current_steps": 13675, "total_steps": 40000, "loss": 0.0, "lr": 3.691631297058664e-05, "epoch": 151.94444444444446, "percentage": 34.19, "elapsed_time": "1:33:02", "remaining_time": "2:59:07", "throughput": 686.05, "total_tokens": 3830176} {"current_steps": 13680, "total_steps": 40000, "loss": 0.0, "lr": 3.6907681588513424e-05, "epoch": 152.0, "percentage": 34.2, "elapsed_time": "1:33:05", "remaining_time": "2:59:05", "throughput": 686.04, "total_tokens": 3831584} {"current_steps": 13685, "total_steps": 40000, "loss": 0.0, "lr": 3.689904837012606e-05, "epoch": 152.05555555555554, "percentage": 34.21, "elapsed_time": "1:33:07", "remaining_time": "2:59:03", "throughput": 686.02, "total_tokens": 3832960} {"current_steps": 13690, "total_steps": 40000, "loss": 0.0, "lr": 3.689041331675591e-05, "epoch": 152.11111111111111, "percentage": 34.23, "elapsed_time": "1:33:09", "remaining_time": "2:59:01", "throughput": 686.02, "total_tokens": 3834304} {"current_steps": 13695, "total_steps": 40000, "loss": 0.0, "lr": 3.688177642973461e-05, "epoch": 152.16666666666666, "percentage": 34.24, "elapsed_time": "1:33:11", "remaining_time": "2:58:59", "throughput": 686.03, "total_tokens": 3835680} {"current_steps": 13700, "total_steps": 40000, "loss": 0.0, "lr": 3.687313771039406e-05, "epoch": 152.22222222222223, "percentage": 34.25, "elapsed_time": "1:33:13", "remaining_time": "2:58:57", "throughput": 686.04, "total_tokens": 3837120} {"current_steps": 13705, "total_steps": 40000, "loss": 0.0, "lr": 3.686449716006647e-05, "epoch": 152.27777777777777, "percentage": 34.26, "elapsed_time": "1:33:15", "remaining_time": "2:58:54", "throughput": 686.06, "total_tokens": 3838528} {"current_steps": 13710, "total_steps": 40000, "loss": 0.0, "lr": 3.685585478008432e-05, "epoch": 152.33333333333334, "percentage": 34.27, "elapsed_time": "1:33:17", "remaining_time": "2:58:52", "throughput": 686.07, "total_tokens": 3839936} {"current_steps": 13715, "total_steps": 40000, "loss": 0.0, "lr": 3.6847210571780364e-05, "epoch": 152.38888888888889, "percentage": 34.29, "elapsed_time": "1:33:18", "remaining_time": "2:58:50", "throughput": 686.08, "total_tokens": 3841312} {"current_steps": 13720, "total_steps": 40000, "loss": 0.0, "lr": 3.683856453648767e-05, "epoch": 152.44444444444446, "percentage": 34.3, "elapsed_time": "1:33:20", "remaining_time": "2:58:48", "throughput": 686.09, "total_tokens": 3842688} {"current_steps": 13725, "total_steps": 40000, "loss": 0.0, "lr": 3.682991667553954e-05, "epoch": 152.5, "percentage": 34.31, "elapsed_time": "1:33:22", "remaining_time": "2:58:45", "throughput": 686.09, "total_tokens": 3844064} {"current_steps": 13730, "total_steps": 40000, "loss": 0.0, "lr": 3.6821266990269606e-05, "epoch": 152.55555555555554, "percentage": 34.33, "elapsed_time": "1:33:24", "remaining_time": "2:58:43", "throughput": 686.1, "total_tokens": 3845456} {"current_steps": 13735, "total_steps": 40000, "loss": 0.0, "lr": 3.681261548201174e-05, "epoch": 152.61111111111111, "percentage": 34.34, "elapsed_time": "1:33:26", "remaining_time": "2:58:41", "throughput": 686.12, "total_tokens": 3846880} {"current_steps": 13740, "total_steps": 40000, "loss": 0.0, "lr": 3.6803962152100125e-05, "epoch": 152.66666666666666, "percentage": 34.35, "elapsed_time": "1:33:28", "remaining_time": "2:58:39", "throughput": 686.14, "total_tokens": 3848336} {"current_steps": 13745, "total_steps": 40000, "loss": 0.0, "lr": 3.67953070018692e-05, "epoch": 152.72222222222223, "percentage": 34.36, "elapsed_time": "1:33:30", "remaining_time": "2:58:37", "throughput": 686.15, "total_tokens": 3849728} {"current_steps": 13750, "total_steps": 40000, "loss": 0.0, "lr": 3.678665003265371e-05, "epoch": 152.77777777777777, "percentage": 34.38, "elapsed_time": "1:33:32", "remaining_time": "2:58:34", "throughput": 686.16, "total_tokens": 3851120} {"current_steps": 13755, "total_steps": 40000, "loss": 0.0, "lr": 3.677799124578867e-05, "epoch": 152.83333333333334, "percentage": 34.39, "elapsed_time": "1:33:34", "remaining_time": "2:58:32", "throughput": 686.19, "total_tokens": 3852576} {"current_steps": 13760, "total_steps": 40000, "loss": 0.0, "lr": 3.676933064260937e-05, "epoch": 152.88888888888889, "percentage": 34.4, "elapsed_time": "1:33:36", "remaining_time": "2:58:30", "throughput": 686.2, "total_tokens": 3853968} {"current_steps": 13765, "total_steps": 40000, "loss": 0.0, "lr": 3.6760668224451365e-05, "epoch": 152.94444444444446, "percentage": 34.41, "elapsed_time": "1:33:38", "remaining_time": "2:58:28", "throughput": 686.22, "total_tokens": 3855424} {"current_steps": 13770, "total_steps": 40000, "loss": 0.0, "lr": 3.675200399265054e-05, "epoch": 153.0, "percentage": 34.42, "elapsed_time": "1:33:40", "remaining_time": "2:58:26", "throughput": 686.21, "total_tokens": 3856816} {"current_steps": 13775, "total_steps": 40000, "loss": 0.0, "lr": 3.6743337948543014e-05, "epoch": 153.05555555555554, "percentage": 34.44, "elapsed_time": "1:33:42", "remaining_time": "2:58:24", "throughput": 686.18, "total_tokens": 3858192} {"current_steps": 13780, "total_steps": 40000, "loss": 0.0, "lr": 3.6734670093465204e-05, "epoch": 153.11111111111111, "percentage": 34.45, "elapsed_time": "1:33:44", "remaining_time": "2:58:22", "throughput": 686.2, "total_tokens": 3859600} {"current_steps": 13785, "total_steps": 40000, "loss": 0.0, "lr": 3.672600042875379e-05, "epoch": 153.16666666666666, "percentage": 34.46, "elapsed_time": "1:33:46", "remaining_time": "2:58:20", "throughput": 686.21, "total_tokens": 3861008} {"current_steps": 13790, "total_steps": 40000, "loss": 0.0, "lr": 3.671732895574575e-05, "epoch": 153.22222222222223, "percentage": 34.48, "elapsed_time": "1:33:48", "remaining_time": "2:58:17", "throughput": 686.22, "total_tokens": 3862400} {"current_steps": 13795, "total_steps": 40000, "loss": 0.0, "lr": 3.670865567577834e-05, "epoch": 153.27777777777777, "percentage": 34.49, "elapsed_time": "1:33:50", "remaining_time": "2:58:15", "throughput": 686.23, "total_tokens": 3863824} {"current_steps": 13800, "total_steps": 40000, "loss": 0.0, "lr": 3.669998059018909e-05, "epoch": 153.33333333333334, "percentage": 34.5, "elapsed_time": "1:33:52", "remaining_time": "2:58:13", "throughput": 686.24, "total_tokens": 3865216} {"current_steps": 13800, "total_steps": 40000, "eval_loss": 0.3873576521873474, "epoch": 153.33333333333334, "percentage": 34.5, "elapsed_time": "1:33:53", "remaining_time": "2:58:15", "throughput": 686.08, "total_tokens": 3865216} {"current_steps": 13805, "total_steps": 40000, "loss": 0.0, "lr": 3.6691303700315796e-05, "epoch": 153.38888888888889, "percentage": 34.51, "elapsed_time": "1:33:57", "remaining_time": "2:58:16", "throughput": 685.92, "total_tokens": 3866576} {"current_steps": 13810, "total_steps": 40000, "loss": 0.0, "lr": 3.668262500749655e-05, "epoch": 153.44444444444446, "percentage": 34.52, "elapsed_time": "1:33:59", "remaining_time": "2:58:14", "throughput": 685.93, "total_tokens": 3868000} {"current_steps": 13815, "total_steps": 40000, "loss": 0.0, "lr": 3.667394451306971e-05, "epoch": 153.5, "percentage": 34.54, "elapsed_time": "1:34:01", "remaining_time": "2:58:12", "throughput": 685.94, "total_tokens": 3869440} {"current_steps": 13820, "total_steps": 40000, "loss": 0.0, "lr": 3.666526221837393e-05, "epoch": 153.55555555555554, "percentage": 34.55, "elapsed_time": "1:34:03", "remaining_time": "2:58:09", "throughput": 685.95, "total_tokens": 3870800} {"current_steps": 13825, "total_steps": 40000, "loss": 0.0, "lr": 3.665657812474812e-05, "epoch": 153.61111111111111, "percentage": 34.56, "elapsed_time": "1:34:04", "remaining_time": "2:58:07", "throughput": 685.96, "total_tokens": 3872208} {"current_steps": 13830, "total_steps": 40000, "loss": 0.0, "lr": 3.664789223353147e-05, "epoch": 153.66666666666666, "percentage": 34.58, "elapsed_time": "1:34:06", "remaining_time": "2:58:05", "throughput": 685.97, "total_tokens": 3873584} {"current_steps": 13835, "total_steps": 40000, "loss": 0.0, "lr": 3.663920454606347e-05, "epoch": 153.72222222222223, "percentage": 34.59, "elapsed_time": "1:34:08", "remaining_time": "2:58:03", "throughput": 685.98, "total_tokens": 3874992} {"current_steps": 13840, "total_steps": 40000, "loss": 0.0, "lr": 3.6630515063683856e-05, "epoch": 153.77777777777777, "percentage": 34.6, "elapsed_time": "1:34:10", "remaining_time": "2:58:00", "throughput": 685.99, "total_tokens": 3876400} {"current_steps": 13845, "total_steps": 40000, "loss": 0.0, "lr": 3.662182378773267e-05, "epoch": 153.83333333333334, "percentage": 34.61, "elapsed_time": "1:34:12", "remaining_time": "2:57:58", "throughput": 686.0, "total_tokens": 3877776} {"current_steps": 13850, "total_steps": 40000, "loss": 0.0, "lr": 3.66131307195502e-05, "epoch": 153.88888888888889, "percentage": 34.62, "elapsed_time": "1:34:14", "remaining_time": "2:57:56", "throughput": 686.01, "total_tokens": 3879168} {"current_steps": 13855, "total_steps": 40000, "loss": 0.0, "lr": 3.6604435860477034e-05, "epoch": 153.94444444444446, "percentage": 34.64, "elapsed_time": "1:34:16", "remaining_time": "2:57:54", "throughput": 686.01, "total_tokens": 3880528} {"current_steps": 13860, "total_steps": 40000, "loss": 0.0, "lr": 3.6595739211854025e-05, "epoch": 154.0, "percentage": 34.65, "elapsed_time": "1:34:18", "remaining_time": "2:57:52", "throughput": 686.01, "total_tokens": 3881968} {"current_steps": 13865, "total_steps": 40000, "loss": 0.0, "lr": 3.658704077502231e-05, "epoch": 154.05555555555554, "percentage": 34.66, "elapsed_time": "1:34:20", "remaining_time": "2:57:50", "throughput": 685.99, "total_tokens": 3883392} {"current_steps": 13870, "total_steps": 40000, "loss": 0.0, "lr": 3.65783405513233e-05, "epoch": 154.11111111111111, "percentage": 34.67, "elapsed_time": "1:34:23", "remaining_time": "2:57:49", "throughput": 685.97, "total_tokens": 3884832} {"current_steps": 13875, "total_steps": 40000, "loss": 0.0, "lr": 3.656963854209867e-05, "epoch": 154.16666666666666, "percentage": 34.69, "elapsed_time": "1:34:25", "remaining_time": "2:57:46", "throughput": 685.97, "total_tokens": 3886208} {"current_steps": 13880, "total_steps": 40000, "loss": 0.0, "lr": 3.656093474869038e-05, "epoch": 154.22222222222223, "percentage": 34.7, "elapsed_time": "1:34:27", "remaining_time": "2:57:44", "throughput": 685.98, "total_tokens": 3887568} {"current_steps": 13885, "total_steps": 40000, "loss": 0.0, "lr": 3.655222917244068e-05, "epoch": 154.27777777777777, "percentage": 34.71, "elapsed_time": "1:34:29", "remaining_time": "2:57:42", "throughput": 685.99, "total_tokens": 3888976} {"current_steps": 13890, "total_steps": 40000, "loss": 0.0, "lr": 3.6543521814692054e-05, "epoch": 154.33333333333334, "percentage": 34.73, "elapsed_time": "1:34:31", "remaining_time": "2:57:40", "throughput": 686.0, "total_tokens": 3890368} {"current_steps": 13895, "total_steps": 40000, "loss": 0.0, "lr": 3.653481267678731e-05, "epoch": 154.38888888888889, "percentage": 34.74, "elapsed_time": "1:34:33", "remaining_time": "2:57:38", "throughput": 686.01, "total_tokens": 3891792} {"current_steps": 13900, "total_steps": 40000, "loss": 0.0, "lr": 3.652610176006949e-05, "epoch": 154.44444444444446, "percentage": 34.75, "elapsed_time": "1:34:34", "remaining_time": "2:57:35", "throughput": 686.02, "total_tokens": 3893168} {"current_steps": 13905, "total_steps": 40000, "loss": 0.0, "lr": 3.6517389065881925e-05, "epoch": 154.5, "percentage": 34.76, "elapsed_time": "1:34:36", "remaining_time": "2:57:33", "throughput": 686.03, "total_tokens": 3894560} {"current_steps": 13910, "total_steps": 40000, "loss": 0.0, "lr": 3.650867459556824e-05, "epoch": 154.55555555555554, "percentage": 34.77, "elapsed_time": "1:34:38", "remaining_time": "2:57:31", "throughput": 686.05, "total_tokens": 3895968} {"current_steps": 13915, "total_steps": 40000, "loss": 0.0, "lr": 3.64999583504723e-05, "epoch": 154.61111111111111, "percentage": 34.79, "elapsed_time": "1:34:40", "remaining_time": "2:57:29", "throughput": 686.06, "total_tokens": 3897360} {"current_steps": 13920, "total_steps": 40000, "loss": 0.0, "lr": 3.649124033193827e-05, "epoch": 154.66666666666666, "percentage": 34.8, "elapsed_time": "1:34:42", "remaining_time": "2:57:26", "throughput": 686.07, "total_tokens": 3898768} {"current_steps": 13925, "total_steps": 40000, "loss": 0.0, "lr": 3.648252054131057e-05, "epoch": 154.72222222222223, "percentage": 34.81, "elapsed_time": "1:34:44", "remaining_time": "2:57:24", "throughput": 686.09, "total_tokens": 3900192} {"current_steps": 13930, "total_steps": 40000, "loss": 0.0, "lr": 3.647379897993391e-05, "epoch": 154.77777777777777, "percentage": 34.83, "elapsed_time": "1:34:46", "remaining_time": "2:57:22", "throughput": 686.1, "total_tokens": 3901584} {"current_steps": 13935, "total_steps": 40000, "loss": 0.0, "lr": 3.646507564915325e-05, "epoch": 154.83333333333334, "percentage": 34.84, "elapsed_time": "1:34:48", "remaining_time": "2:57:20", "throughput": 686.11, "total_tokens": 3902992} {"current_steps": 13940, "total_steps": 40000, "loss": 0.0, "lr": 3.645635055031385e-05, "epoch": 154.88888888888889, "percentage": 34.85, "elapsed_time": "1:34:50", "remaining_time": "2:57:18", "throughput": 686.13, "total_tokens": 3904432} {"current_steps": 13945, "total_steps": 40000, "loss": 0.0, "lr": 3.6447623684761224e-05, "epoch": 154.94444444444446, "percentage": 34.86, "elapsed_time": "1:34:52", "remaining_time": "2:57:15", "throughput": 686.14, "total_tokens": 3905824} {"current_steps": 13950, "total_steps": 40000, "loss": 0.0, "lr": 3.643889505384117e-05, "epoch": 155.0, "percentage": 34.88, "elapsed_time": "1:34:54", "remaining_time": "2:57:13", "throughput": 686.14, "total_tokens": 3907280} {"current_steps": 13955, "total_steps": 40000, "loss": 0.0, "lr": 3.6430164658899744e-05, "epoch": 155.05555555555554, "percentage": 34.89, "elapsed_time": "1:34:56", "remaining_time": "2:57:12", "throughput": 686.12, "total_tokens": 3908656} {"current_steps": 13960, "total_steps": 40000, "loss": 0.0, "lr": 3.642143250128329e-05, "epoch": 155.11111111111111, "percentage": 34.9, "elapsed_time": "1:34:58", "remaining_time": "2:57:10", "throughput": 686.11, "total_tokens": 3909968} {"current_steps": 13965, "total_steps": 40000, "loss": 0.0, "lr": 3.641269858233841e-05, "epoch": 155.16666666666666, "percentage": 34.91, "elapsed_time": "1:35:00", "remaining_time": "2:57:07", "throughput": 686.12, "total_tokens": 3911344} {"current_steps": 13970, "total_steps": 40000, "loss": 0.0, "lr": 3.640396290341199e-05, "epoch": 155.22222222222223, "percentage": 34.92, "elapsed_time": "1:35:02", "remaining_time": "2:57:05", "throughput": 686.13, "total_tokens": 3912752} {"current_steps": 13975, "total_steps": 40000, "loss": 0.0, "lr": 3.639522546585118e-05, "epoch": 155.27777777777777, "percentage": 34.94, "elapsed_time": "1:35:04", "remaining_time": "2:57:03", "throughput": 686.15, "total_tokens": 3914176} {"current_steps": 13980, "total_steps": 40000, "loss": 0.0, "lr": 3.6386486271003404e-05, "epoch": 155.33333333333334, "percentage": 34.95, "elapsed_time": "1:35:06", "remaining_time": "2:57:01", "throughput": 686.16, "total_tokens": 3915584} {"current_steps": 13985, "total_steps": 40000, "loss": 0.0, "lr": 3.6377745320216346e-05, "epoch": 155.38888888888889, "percentage": 34.96, "elapsed_time": "1:35:08", "remaining_time": "2:56:58", "throughput": 686.18, "total_tokens": 3917040} {"current_steps": 13990, "total_steps": 40000, "loss": 0.0, "lr": 3.636900261483798e-05, "epoch": 155.44444444444446, "percentage": 34.98, "elapsed_time": "1:35:10", "remaining_time": "2:56:56", "throughput": 686.19, "total_tokens": 3918432} {"current_steps": 13995, "total_steps": 40000, "loss": 0.0, "lr": 3.636025815621654e-05, "epoch": 155.5, "percentage": 34.99, "elapsed_time": "1:35:12", "remaining_time": "2:56:54", "throughput": 686.2, "total_tokens": 3919808} {"current_steps": 14000, "total_steps": 40000, "loss": 0.0, "lr": 3.635151194570054e-05, "epoch": 155.55555555555554, "percentage": 35.0, "elapsed_time": "1:35:14", "remaining_time": "2:56:52", "throughput": 686.21, "total_tokens": 3921216} {"current_steps": 14000, "total_steps": 40000, "eval_loss": 0.3806132376194, "epoch": 155.55555555555554, "percentage": 35.0, "elapsed_time": "1:35:15", "remaining_time": "2:56:54", "throughput": 686.05, "total_tokens": 3921216} {"current_steps": 14005, "total_steps": 40000, "loss": 0.0, "lr": 3.634276398463873e-05, "epoch": 155.61111111111111, "percentage": 35.01, "elapsed_time": "1:35:18", "remaining_time": "2:56:54", "throughput": 685.92, "total_tokens": 3922640} {"current_steps": 14010, "total_steps": 40000, "loss": 0.0, "lr": 3.633401427438018e-05, "epoch": 155.66666666666666, "percentage": 35.02, "elapsed_time": "1:35:20", "remaining_time": "2:56:52", "throughput": 685.92, "total_tokens": 3924032} {"current_steps": 14015, "total_steps": 40000, "loss": 0.0, "lr": 3.63252628162742e-05, "epoch": 155.72222222222223, "percentage": 35.04, "elapsed_time": "1:35:22", "remaining_time": "2:56:50", "throughput": 685.92, "total_tokens": 3925424} {"current_steps": 14020, "total_steps": 40000, "loss": 0.0, "lr": 3.6316509611670364e-05, "epoch": 155.77777777777777, "percentage": 35.05, "elapsed_time": "1:35:24", "remaining_time": "2:56:48", "throughput": 685.93, "total_tokens": 3926816} {"current_steps": 14025, "total_steps": 40000, "loss": 0.0, "lr": 3.630775466191854e-05, "epoch": 155.83333333333334, "percentage": 35.06, "elapsed_time": "1:35:26", "remaining_time": "2:56:46", "throughput": 685.95, "total_tokens": 3928224} {"current_steps": 14030, "total_steps": 40000, "loss": 0.0, "lr": 3.629899796836884e-05, "epoch": 155.88888888888889, "percentage": 35.08, "elapsed_time": "1:35:28", "remaining_time": "2:56:44", "throughput": 685.95, "total_tokens": 3929584} {"current_steps": 14035, "total_steps": 40000, "loss": 0.0, "lr": 3.6290239532371666e-05, "epoch": 155.94444444444446, "percentage": 35.09, "elapsed_time": "1:35:30", "remaining_time": "2:56:41", "throughput": 685.96, "total_tokens": 3931024} {"current_steps": 14040, "total_steps": 40000, "loss": 0.0, "lr": 3.628147935527767e-05, "epoch": 156.0, "percentage": 35.1, "elapsed_time": "1:35:32", "remaining_time": "2:56:39", "throughput": 685.96, "total_tokens": 3932464} {"current_steps": 14045, "total_steps": 40000, "loss": 0.0, "lr": 3.627271743843779e-05, "epoch": 156.05555555555554, "percentage": 35.11, "elapsed_time": "1:35:34", "remaining_time": "2:56:38", "throughput": 685.95, "total_tokens": 3933920} {"current_steps": 14050, "total_steps": 40000, "loss": 0.0, "lr": 3.626395378320321e-05, "epoch": 156.11111111111111, "percentage": 35.12, "elapsed_time": "1:35:36", "remaining_time": "2:56:35", "throughput": 685.96, "total_tokens": 3935312} {"current_steps": 14055, "total_steps": 40000, "loss": 0.0, "lr": 3.625518839092541e-05, "epoch": 156.16666666666666, "percentage": 35.14, "elapsed_time": "1:35:38", "remaining_time": "2:56:33", "throughput": 685.97, "total_tokens": 3936688} {"current_steps": 14060, "total_steps": 40000, "loss": 0.0, "lr": 3.624642126295612e-05, "epoch": 156.22222222222223, "percentage": 35.15, "elapsed_time": "1:35:40", "remaining_time": "2:56:31", "throughput": 685.98, "total_tokens": 3938080} {"current_steps": 14065, "total_steps": 40000, "loss": 0.0, "lr": 3.6237652400647345e-05, "epoch": 156.27777777777777, "percentage": 35.16, "elapsed_time": "1:35:42", "remaining_time": "2:56:29", "throughput": 686.0, "total_tokens": 3939504} {"current_steps": 14070, "total_steps": 40000, "loss": 0.0, "lr": 3.622888180535134e-05, "epoch": 156.33333333333334, "percentage": 35.17, "elapsed_time": "1:35:44", "remaining_time": "2:56:27", "throughput": 686.01, "total_tokens": 3940928} {"current_steps": 14075, "total_steps": 40000, "loss": 0.0, "lr": 3.6220109478420655e-05, "epoch": 156.38888888888889, "percentage": 35.19, "elapsed_time": "1:35:46", "remaining_time": "2:56:24", "throughput": 686.01, "total_tokens": 3942288} {"current_steps": 14080, "total_steps": 40000, "loss": 0.0, "lr": 3.6211335421208084e-05, "epoch": 156.44444444444446, "percentage": 35.2, "elapsed_time": "1:35:48", "remaining_time": "2:56:22", "throughput": 686.03, "total_tokens": 3943696} {"current_steps": 14085, "total_steps": 40000, "loss": 0.0, "lr": 3.62025596350667e-05, "epoch": 156.5, "percentage": 35.21, "elapsed_time": "1:35:50", "remaining_time": "2:56:20", "throughput": 686.04, "total_tokens": 3945088} {"current_steps": 14090, "total_steps": 40000, "loss": 0.0, "lr": 3.619378212134984e-05, "epoch": 156.55555555555554, "percentage": 35.23, "elapsed_time": "1:35:52", "remaining_time": "2:56:18", "throughput": 686.04, "total_tokens": 3946464} {"current_steps": 14095, "total_steps": 40000, "loss": 0.0, "lr": 3.618500288141111e-05, "epoch": 156.61111111111111, "percentage": 35.24, "elapsed_time": "1:35:54", "remaining_time": "2:56:15", "throughput": 686.06, "total_tokens": 3947856} {"current_steps": 14100, "total_steps": 40000, "loss": 0.0, "lr": 3.617622191660438e-05, "epoch": 156.66666666666666, "percentage": 35.25, "elapsed_time": "1:35:56", "remaining_time": "2:56:13", "throughput": 686.07, "total_tokens": 3949248} {"current_steps": 14105, "total_steps": 40000, "loss": 0.0, "lr": 3.616743922828377e-05, "epoch": 156.72222222222223, "percentage": 35.26, "elapsed_time": "1:35:58", "remaining_time": "2:56:11", "throughput": 686.09, "total_tokens": 3950704} {"current_steps": 14110, "total_steps": 40000, "loss": 0.0, "lr": 3.615865481780371e-05, "epoch": 156.77777777777777, "percentage": 35.27, "elapsed_time": "1:36:00", "remaining_time": "2:56:09", "throughput": 686.1, "total_tokens": 3952080} {"current_steps": 14115, "total_steps": 40000, "loss": 0.0, "lr": 3.614986868651883e-05, "epoch": 156.83333333333334, "percentage": 35.29, "elapsed_time": "1:36:02", "remaining_time": "2:56:07", "throughput": 686.12, "total_tokens": 3953536} {"current_steps": 14120, "total_steps": 40000, "loss": 0.0, "lr": 3.614108083578409e-05, "epoch": 156.88888888888889, "percentage": 35.3, "elapsed_time": "1:36:04", "remaining_time": "2:56:04", "throughput": 686.12, "total_tokens": 3954880} {"current_steps": 14125, "total_steps": 40000, "loss": 0.0, "lr": 3.613229126695467e-05, "epoch": 156.94444444444446, "percentage": 35.31, "elapsed_time": "1:36:06", "remaining_time": "2:56:02", "throughput": 686.13, "total_tokens": 3956288} {"current_steps": 14130, "total_steps": 40000, "loss": 0.0, "lr": 3.612349998138605e-05, "epoch": 157.0, "percentage": 35.33, "elapsed_time": "1:36:08", "remaining_time": "2:56:01", "throughput": 686.1, "total_tokens": 3957712} {"current_steps": 14135, "total_steps": 40000, "loss": 0.0, "lr": 3.6114706980433946e-05, "epoch": 157.05555555555554, "percentage": 35.34, "elapsed_time": "1:36:10", "remaining_time": "2:55:59", "throughput": 686.08, "total_tokens": 3959136} {"current_steps": 14140, "total_steps": 40000, "loss": 0.0, "lr": 3.610591226545435e-05, "epoch": 157.11111111111111, "percentage": 35.35, "elapsed_time": "1:36:12", "remaining_time": "2:55:57", "throughput": 686.09, "total_tokens": 3960528} {"current_steps": 14145, "total_steps": 40000, "loss": 0.0, "lr": 3.6097115837803505e-05, "epoch": 157.16666666666666, "percentage": 35.36, "elapsed_time": "1:36:14", "remaining_time": "2:55:54", "throughput": 686.11, "total_tokens": 3961936} {"current_steps": 14150, "total_steps": 40000, "loss": 0.0, "lr": 3.608831769883795e-05, "epoch": 157.22222222222223, "percentage": 35.38, "elapsed_time": "1:36:16", "remaining_time": "2:55:52", "throughput": 686.12, "total_tokens": 3963360} {"current_steps": 14155, "total_steps": 40000, "loss": 0.0, "lr": 3.607951784991446e-05, "epoch": 157.27777777777777, "percentage": 35.39, "elapsed_time": "1:36:18", "remaining_time": "2:55:50", "throughput": 686.13, "total_tokens": 3964736} {"current_steps": 14160, "total_steps": 40000, "loss": 0.0, "lr": 3.6070716292390085e-05, "epoch": 157.33333333333334, "percentage": 35.4, "elapsed_time": "1:36:20", "remaining_time": "2:55:48", "throughput": 686.14, "total_tokens": 3966144} {"current_steps": 14165, "total_steps": 40000, "loss": 0.0, "lr": 3.606191302762213e-05, "epoch": 157.38888888888889, "percentage": 35.41, "elapsed_time": "1:36:22", "remaining_time": "2:55:46", "throughput": 686.14, "total_tokens": 3967504} {"current_steps": 14170, "total_steps": 40000, "loss": 0.0, "lr": 3.605310805696818e-05, "epoch": 157.44444444444446, "percentage": 35.43, "elapsed_time": "1:36:24", "remaining_time": "2:55:43", "throughput": 686.16, "total_tokens": 3968944} {"current_steps": 14175, "total_steps": 40000, "loss": 0.0, "lr": 3.6044301381786067e-05, "epoch": 157.5, "percentage": 35.44, "elapsed_time": "1:36:26", "remaining_time": "2:55:41", "throughput": 686.15, "total_tokens": 3970256} {"current_steps": 14180, "total_steps": 40000, "loss": 0.0, "lr": 3.6035493003433883e-05, "epoch": 157.55555555555554, "percentage": 35.45, "elapsed_time": "1:36:28", "remaining_time": "2:55:39", "throughput": 686.17, "total_tokens": 3971696} {"current_steps": 14185, "total_steps": 40000, "loss": 0.0, "lr": 3.6026682923269994e-05, "epoch": 157.61111111111111, "percentage": 35.46, "elapsed_time": "1:36:30", "remaining_time": "2:55:37", "throughput": 686.18, "total_tokens": 3973056} {"current_steps": 14190, "total_steps": 40000, "loss": 0.0, "lr": 3.6017871142653034e-05, "epoch": 157.66666666666666, "percentage": 35.48, "elapsed_time": "1:36:32", "remaining_time": "2:55:35", "throughput": 686.19, "total_tokens": 3974448} {"current_steps": 14195, "total_steps": 40000, "loss": 0.0, "lr": 3.600905766294189e-05, "epoch": 157.72222222222223, "percentage": 35.49, "elapsed_time": "1:36:34", "remaining_time": "2:55:32", "throughput": 686.2, "total_tokens": 3975872} {"current_steps": 14200, "total_steps": 40000, "loss": 0.0, "lr": 3.60002424854957e-05, "epoch": 157.77777777777777, "percentage": 35.5, "elapsed_time": "1:36:35", "remaining_time": "2:55:30", "throughput": 686.22, "total_tokens": 3977312} {"current_steps": 14200, "total_steps": 40000, "eval_loss": 0.3885982632637024, "epoch": 157.77777777777777, "percentage": 35.5, "elapsed_time": "1:36:37", "remaining_time": "2:55:33", "throughput": 686.06, "total_tokens": 3977312} {"current_steps": 14205, "total_steps": 40000, "loss": 0.0, "lr": 3.5991425611673876e-05, "epoch": 157.83333333333334, "percentage": 35.51, "elapsed_time": "1:36:40", "remaining_time": "2:55:33", "throughput": 685.9, "total_tokens": 3978752} {"current_steps": 14210, "total_steps": 40000, "loss": 0.0, "lr": 3.5982607042836105e-05, "epoch": 157.88888888888889, "percentage": 35.52, "elapsed_time": "1:36:42", "remaining_time": "2:55:31", "throughput": 685.91, "total_tokens": 3980160} {"current_steps": 14215, "total_steps": 40000, "loss": 0.0, "lr": 3.597378678034231e-05, "epoch": 157.94444444444446, "percentage": 35.54, "elapsed_time": "1:36:44", "remaining_time": "2:55:29", "throughput": 685.92, "total_tokens": 3981568} {"current_steps": 14220, "total_steps": 40000, "loss": 0.0, "lr": 3.596496482555269e-05, "epoch": 158.0, "percentage": 35.55, "elapsed_time": "1:36:46", "remaining_time": "2:55:27", "throughput": 685.91, "total_tokens": 3982960} {"current_steps": 14225, "total_steps": 40000, "loss": 0.0, "lr": 3.595614117982769e-05, "epoch": 158.05555555555554, "percentage": 35.56, "elapsed_time": "1:36:49", "remaining_time": "2:55:25", "throughput": 685.9, "total_tokens": 3984400} {"current_steps": 14230, "total_steps": 40000, "loss": 0.0, "lr": 3.594731584452805e-05, "epoch": 158.11111111111111, "percentage": 35.58, "elapsed_time": "1:36:50", "remaining_time": "2:55:23", "throughput": 685.9, "total_tokens": 3985776} {"current_steps": 14235, "total_steps": 40000, "loss": 0.0, "lr": 3.593848882101472e-05, "epoch": 158.16666666666666, "percentage": 35.59, "elapsed_time": "1:36:52", "remaining_time": "2:55:21", "throughput": 685.91, "total_tokens": 3987136} {"current_steps": 14240, "total_steps": 40000, "loss": 0.0, "lr": 3.592966011064896e-05, "epoch": 158.22222222222223, "percentage": 35.6, "elapsed_time": "1:36:54", "remaining_time": "2:55:19", "throughput": 685.92, "total_tokens": 3988544} {"current_steps": 14245, "total_steps": 40000, "loss": 0.0, "lr": 3.592082971479226e-05, "epoch": 158.27777777777777, "percentage": 35.61, "elapsed_time": "1:36:56", "remaining_time": "2:55:16", "throughput": 685.94, "total_tokens": 3989968} {"current_steps": 14250, "total_steps": 40000, "loss": 0.0, "lr": 3.5911997634806385e-05, "epoch": 158.33333333333334, "percentage": 35.62, "elapsed_time": "1:36:58", "remaining_time": "2:55:14", "throughput": 685.95, "total_tokens": 3991376} {"current_steps": 14255, "total_steps": 40000, "loss": 0.0, "lr": 3.5903163872053336e-05, "epoch": 158.38888888888889, "percentage": 35.64, "elapsed_time": "1:37:00", "remaining_time": "2:55:12", "throughput": 685.96, "total_tokens": 3992800} {"current_steps": 14260, "total_steps": 40000, "loss": 0.0, "lr": 3.58943284278954e-05, "epoch": 158.44444444444446, "percentage": 35.65, "elapsed_time": "1:37:02", "remaining_time": "2:55:10", "throughput": 685.98, "total_tokens": 3994240} {"current_steps": 14265, "total_steps": 40000, "loss": 0.0, "lr": 3.588549130369512e-05, "epoch": 158.5, "percentage": 35.66, "elapsed_time": "1:37:04", "remaining_time": "2:55:08", "throughput": 685.99, "total_tokens": 3995616} {"current_steps": 14270, "total_steps": 40000, "loss": 0.0, "lr": 3.5876652500815274e-05, "epoch": 158.55555555555554, "percentage": 35.68, "elapsed_time": "1:37:06", "remaining_time": "2:55:05", "throughput": 685.99, "total_tokens": 3996976} {"current_steps": 14275, "total_steps": 40000, "loss": 0.0, "lr": 3.586781202061894e-05, "epoch": 158.61111111111111, "percentage": 35.69, "elapsed_time": "1:37:08", "remaining_time": "2:55:03", "throughput": 686.01, "total_tokens": 3998384} {"current_steps": 14280, "total_steps": 40000, "loss": 0.0, "lr": 3.585896986446942e-05, "epoch": 158.66666666666666, "percentage": 35.7, "elapsed_time": "1:37:10", "remaining_time": "2:55:01", "throughput": 686.02, "total_tokens": 3999808} {"current_steps": 14285, "total_steps": 40000, "loss": 0.0, "lr": 3.585012603373028e-05, "epoch": 158.72222222222223, "percentage": 35.71, "elapsed_time": "1:37:12", "remaining_time": "2:54:59", "throughput": 686.03, "total_tokens": 4001184} {"current_steps": 14290, "total_steps": 40000, "loss": 0.0, "lr": 3.584128052976535e-05, "epoch": 158.77777777777777, "percentage": 35.73, "elapsed_time": "1:37:14", "remaining_time": "2:54:56", "throughput": 686.05, "total_tokens": 4002624} {"current_steps": 14295, "total_steps": 40000, "loss": 0.0, "lr": 3.5832433353938724e-05, "epoch": 158.83333333333334, "percentage": 35.74, "elapsed_time": "1:37:16", "remaining_time": "2:54:54", "throughput": 686.06, "total_tokens": 4004016} {"current_steps": 14300, "total_steps": 40000, "loss": 0.0, "lr": 3.5823584507614746e-05, "epoch": 158.88888888888889, "percentage": 35.75, "elapsed_time": "1:37:18", "remaining_time": "2:54:52", "throughput": 686.07, "total_tokens": 4005440} {"current_steps": 14305, "total_steps": 40000, "loss": 0.0, "lr": 3.581473399215802e-05, "epoch": 158.94444444444446, "percentage": 35.76, "elapsed_time": "1:37:20", "remaining_time": "2:54:50", "throughput": 686.08, "total_tokens": 4006848} {"current_steps": 14310, "total_steps": 40000, "loss": 0.0, "lr": 3.580588180893341e-05, "epoch": 159.0, "percentage": 35.77, "elapsed_time": "1:37:22", "remaining_time": "2:54:48", "throughput": 686.08, "total_tokens": 4008256} {"current_steps": 14315, "total_steps": 40000, "loss": 0.0, "lr": 3.579702795930602e-05, "epoch": 159.05555555555554, "percentage": 35.79, "elapsed_time": "1:37:24", "remaining_time": "2:54:46", "throughput": 686.06, "total_tokens": 4009648} {"current_steps": 14320, "total_steps": 40000, "loss": 0.0, "lr": 3.578817244464125e-05, "epoch": 159.11111111111111, "percentage": 35.8, "elapsed_time": "1:37:26", "remaining_time": "2:54:44", "throughput": 686.07, "total_tokens": 4011040} {"current_steps": 14325, "total_steps": 40000, "loss": 0.0, "lr": 3.577931526630471e-05, "epoch": 159.16666666666666, "percentage": 35.81, "elapsed_time": "1:37:28", "remaining_time": "2:54:42", "throughput": 686.08, "total_tokens": 4012448} {"current_steps": 14330, "total_steps": 40000, "loss": 0.0, "lr": 3.577045642566229e-05, "epoch": 159.22222222222223, "percentage": 35.83, "elapsed_time": "1:37:30", "remaining_time": "2:54:39", "throughput": 686.09, "total_tokens": 4013856} {"current_steps": 14335, "total_steps": 40000, "loss": 0.0, "lr": 3.576159592408014e-05, "epoch": 159.27777777777777, "percentage": 35.84, "elapsed_time": "1:37:32", "remaining_time": "2:54:37", "throughput": 686.11, "total_tokens": 4015280} {"current_steps": 14340, "total_steps": 40000, "loss": 0.0, "lr": 3.575273376292466e-05, "epoch": 159.33333333333334, "percentage": 35.85, "elapsed_time": "1:37:34", "remaining_time": "2:54:35", "throughput": 686.11, "total_tokens": 4016640} {"current_steps": 14345, "total_steps": 40000, "loss": 0.0, "lr": 3.574386994356251e-05, "epoch": 159.38888888888889, "percentage": 35.86, "elapsed_time": "1:37:36", "remaining_time": "2:54:33", "throughput": 686.13, "total_tokens": 4018064} {"current_steps": 14350, "total_steps": 40000, "loss": 0.0, "lr": 3.573500446736059e-05, "epoch": 159.44444444444446, "percentage": 35.88, "elapsed_time": "1:37:38", "remaining_time": "2:54:31", "throughput": 686.14, "total_tokens": 4019472} {"current_steps": 14355, "total_steps": 40000, "loss": 0.0, "lr": 3.5726137335686094e-05, "epoch": 159.5, "percentage": 35.89, "elapsed_time": "1:37:40", "remaining_time": "2:54:28", "throughput": 686.15, "total_tokens": 4020848} {"current_steps": 14360, "total_steps": 40000, "loss": 0.0, "lr": 3.571726854990642e-05, "epoch": 159.55555555555554, "percentage": 35.9, "elapsed_time": "1:37:41", "remaining_time": "2:54:26", "throughput": 686.16, "total_tokens": 4022240} {"current_steps": 14365, "total_steps": 40000, "loss": 0.0, "lr": 3.570839811138925e-05, "epoch": 159.61111111111111, "percentage": 35.91, "elapsed_time": "1:37:43", "remaining_time": "2:54:24", "throughput": 686.16, "total_tokens": 4023616} {"current_steps": 14370, "total_steps": 40000, "loss": 0.0, "lr": 3.569952602150252e-05, "epoch": 159.66666666666666, "percentage": 35.93, "elapsed_time": "1:37:45", "remaining_time": "2:54:22", "throughput": 686.17, "total_tokens": 4024992} {"current_steps": 14375, "total_steps": 40000, "loss": 0.0, "lr": 3.569065228161442e-05, "epoch": 159.72222222222223, "percentage": 35.94, "elapsed_time": "1:37:47", "remaining_time": "2:54:20", "throughput": 686.18, "total_tokens": 4026400} {"current_steps": 14380, "total_steps": 40000, "loss": 0.0, "lr": 3.5681776893093395e-05, "epoch": 159.77777777777777, "percentage": 35.95, "elapsed_time": "1:37:49", "remaining_time": "2:54:17", "throughput": 686.2, "total_tokens": 4027824} {"current_steps": 14385, "total_steps": 40000, "loss": 0.0, "lr": 3.5672899857308134e-05, "epoch": 159.83333333333334, "percentage": 35.96, "elapsed_time": "1:37:51", "remaining_time": "2:54:15", "throughput": 686.21, "total_tokens": 4029216} {"current_steps": 14390, "total_steps": 40000, "loss": 0.0, "lr": 3.566402117562759e-05, "epoch": 159.88888888888889, "percentage": 35.98, "elapsed_time": "1:37:53", "remaining_time": "2:54:13", "throughput": 686.22, "total_tokens": 4030640} {"current_steps": 14395, "total_steps": 40000, "loss": 0.0, "lr": 3.565514084942097e-05, "epoch": 159.94444444444446, "percentage": 35.99, "elapsed_time": "1:37:55", "remaining_time": "2:54:11", "throughput": 686.24, "total_tokens": 4032048} {"current_steps": 14400, "total_steps": 40000, "loss": 0.0, "lr": 3.564625888005773e-05, "epoch": 160.0, "percentage": 36.0, "elapsed_time": "1:37:57", "remaining_time": "2:54:09", "throughput": 686.24, "total_tokens": 4033488} {"current_steps": 14400, "total_steps": 40000, "eval_loss": 0.36411207914352417, "epoch": 160.0, "percentage": 36.0, "elapsed_time": "1:37:58", "remaining_time": "2:54:11", "throughput": 686.08, "total_tokens": 4033488} {"current_steps": 14405, "total_steps": 40000, "loss": 0.0, "lr": 3.563737526890759e-05, "epoch": 160.05555555555554, "percentage": 36.01, "elapsed_time": "1:38:02", "remaining_time": "2:54:12", "throughput": 685.88, "total_tokens": 4034848} {"current_steps": 14410, "total_steps": 40000, "loss": 0.0, "lr": 3.562849001734049e-05, "epoch": 160.11111111111111, "percentage": 36.02, "elapsed_time": "1:38:04", "remaining_time": "2:54:10", "throughput": 685.89, "total_tokens": 4036272} {"current_steps": 14415, "total_steps": 40000, "loss": 0.0, "lr": 3.561960312672667e-05, "epoch": 160.16666666666666, "percentage": 36.04, "elapsed_time": "1:38:06", "remaining_time": "2:54:08", "throughput": 685.9, "total_tokens": 4037696} {"current_steps": 14420, "total_steps": 40000, "loss": 0.0, "lr": 3.5610714598436596e-05, "epoch": 160.22222222222223, "percentage": 36.05, "elapsed_time": "1:38:08", "remaining_time": "2:54:06", "throughput": 685.9, "total_tokens": 4039056} {"current_steps": 14425, "total_steps": 40000, "loss": 0.0, "lr": 3.5601824433840986e-05, "epoch": 160.27777777777777, "percentage": 36.06, "elapsed_time": "1:38:10", "remaining_time": "2:54:03", "throughput": 685.92, "total_tokens": 4040496} {"current_steps": 14430, "total_steps": 40000, "loss": 0.0, "lr": 3.559293263431082e-05, "epoch": 160.33333333333334, "percentage": 36.08, "elapsed_time": "1:38:12", "remaining_time": "2:54:01", "throughput": 685.94, "total_tokens": 4041904} {"current_steps": 14435, "total_steps": 40000, "loss": 0.0, "lr": 3.558403920121732e-05, "epoch": 160.38888888888889, "percentage": 36.09, "elapsed_time": "1:38:14", "remaining_time": "2:53:59", "throughput": 685.95, "total_tokens": 4043296} {"current_steps": 14440, "total_steps": 40000, "loss": 0.0, "lr": 3.557514413593197e-05, "epoch": 160.44444444444446, "percentage": 36.1, "elapsed_time": "1:38:16", "remaining_time": "2:53:57", "throughput": 685.95, "total_tokens": 4044672} {"current_steps": 14445, "total_steps": 40000, "loss": 0.0, "lr": 3.55662474398265e-05, "epoch": 160.5, "percentage": 36.11, "elapsed_time": "1:38:18", "remaining_time": "2:53:55", "throughput": 685.95, "total_tokens": 4046032} {"current_steps": 14450, "total_steps": 40000, "loss": 0.0, "lr": 3.555734911427288e-05, "epoch": 160.55555555555554, "percentage": 36.12, "elapsed_time": "1:38:20", "remaining_time": "2:53:52", "throughput": 685.96, "total_tokens": 4047408} {"current_steps": 14455, "total_steps": 40000, "loss": 0.0, "lr": 3.5548449160643363e-05, "epoch": 160.61111111111111, "percentage": 36.14, "elapsed_time": "1:38:22", "remaining_time": "2:53:50", "throughput": 685.97, "total_tokens": 4048848} {"current_steps": 14460, "total_steps": 40000, "loss": 0.0, "lr": 3.553954758031043e-05, "epoch": 160.66666666666666, "percentage": 36.15, "elapsed_time": "1:38:24", "remaining_time": "2:53:48", "throughput": 685.98, "total_tokens": 4050208} {"current_steps": 14465, "total_steps": 40000, "loss": 0.0, "lr": 3.5530644374646815e-05, "epoch": 160.72222222222223, "percentage": 36.16, "elapsed_time": "1:38:26", "remaining_time": "2:53:46", "throughput": 686.0, "total_tokens": 4051632} {"current_steps": 14470, "total_steps": 40000, "loss": 0.0, "lr": 3.552173954502549e-05, "epoch": 160.77777777777777, "percentage": 36.18, "elapsed_time": "1:38:28", "remaining_time": "2:53:43", "throughput": 686.01, "total_tokens": 4053024} {"current_steps": 14475, "total_steps": 40000, "loss": 0.0, "lr": 3.55128330928197e-05, "epoch": 160.83333333333334, "percentage": 36.19, "elapsed_time": "1:38:30", "remaining_time": "2:53:41", "throughput": 686.02, "total_tokens": 4054432} {"current_steps": 14480, "total_steps": 40000, "loss": 0.0, "lr": 3.550392501940294e-05, "epoch": 160.88888888888889, "percentage": 36.2, "elapsed_time": "1:38:32", "remaining_time": "2:53:39", "throughput": 686.04, "total_tokens": 4055888} {"current_steps": 14485, "total_steps": 40000, "loss": 0.0, "lr": 3.5495015326148945e-05, "epoch": 160.94444444444446, "percentage": 36.21, "elapsed_time": "1:38:33", "remaining_time": "2:53:37", "throughput": 686.06, "total_tokens": 4057344} {"current_steps": 14490, "total_steps": 40000, "loss": 0.0, "lr": 3.548610401443169e-05, "epoch": 161.0, "percentage": 36.23, "elapsed_time": "1:38:36", "remaining_time": "2:53:35", "throughput": 686.04, "total_tokens": 4058704} {"current_steps": 14495, "total_steps": 40000, "loss": 0.0, "lr": 3.547719108562543e-05, "epoch": 161.05555555555554, "percentage": 36.24, "elapsed_time": "1:38:38", "remaining_time": "2:53:33", "throughput": 686.02, "total_tokens": 4060112} {"current_steps": 14500, "total_steps": 40000, "loss": 0.0, "lr": 3.546827654110464e-05, "epoch": 161.11111111111111, "percentage": 36.25, "elapsed_time": "1:38:40", "remaining_time": "2:53:31", "throughput": 686.03, "total_tokens": 4061504} {"current_steps": 14505, "total_steps": 40000, "loss": 0.0, "lr": 3.545936038224405e-05, "epoch": 161.16666666666666, "percentage": 36.26, "elapsed_time": "1:38:42", "remaining_time": "2:53:29", "throughput": 686.05, "total_tokens": 4062928} {"current_steps": 14510, "total_steps": 40000, "loss": 0.0, "lr": 3.545044261041864e-05, "epoch": 161.22222222222223, "percentage": 36.27, "elapsed_time": "1:38:44", "remaining_time": "2:53:27", "throughput": 686.07, "total_tokens": 4064400} {"current_steps": 14515, "total_steps": 40000, "loss": 0.0, "lr": 3.5441523227003657e-05, "epoch": 161.27777777777777, "percentage": 36.29, "elapsed_time": "1:38:46", "remaining_time": "2:53:24", "throughput": 686.08, "total_tokens": 4065808} {"current_steps": 14520, "total_steps": 40000, "loss": 0.0, "lr": 3.543260223337459e-05, "epoch": 161.33333333333334, "percentage": 36.3, "elapsed_time": "1:38:48", "remaining_time": "2:53:22", "throughput": 686.1, "total_tokens": 4067248} {"current_steps": 14525, "total_steps": 40000, "loss": 0.0, "lr": 3.542367963090714e-05, "epoch": 161.38888888888889, "percentage": 36.31, "elapsed_time": "1:38:49", "remaining_time": "2:53:20", "throughput": 686.11, "total_tokens": 4068624} {"current_steps": 14530, "total_steps": 40000, "loss": 0.0, "lr": 3.5414755420977295e-05, "epoch": 161.44444444444446, "percentage": 36.33, "elapsed_time": "1:38:51", "remaining_time": "2:53:18", "throughput": 686.12, "total_tokens": 4070016} {"current_steps": 14535, "total_steps": 40000, "loss": 0.0, "lr": 3.54058296049613e-05, "epoch": 161.5, "percentage": 36.34, "elapsed_time": "1:38:53", "remaining_time": "2:53:16", "throughput": 686.13, "total_tokens": 4071440} {"current_steps": 14540, "total_steps": 40000, "loss": 0.0, "lr": 3.53969021842356e-05, "epoch": 161.55555555555554, "percentage": 36.35, "elapsed_time": "1:38:55", "remaining_time": "2:53:13", "throughput": 686.14, "total_tokens": 4072800} {"current_steps": 14545, "total_steps": 40000, "loss": 0.0, "lr": 3.5387973160176926e-05, "epoch": 161.61111111111111, "percentage": 36.36, "elapsed_time": "1:38:57", "remaining_time": "2:53:11", "throughput": 686.15, "total_tokens": 4074192} {"current_steps": 14550, "total_steps": 40000, "loss": 0.0, "lr": 3.537904253416224e-05, "epoch": 161.66666666666666, "percentage": 36.38, "elapsed_time": "1:38:59", "remaining_time": "2:53:09", "throughput": 686.15, "total_tokens": 4075584} {"current_steps": 14555, "total_steps": 40000, "loss": 0.0, "lr": 3.537011030756878e-05, "epoch": 161.72222222222223, "percentage": 36.39, "elapsed_time": "1:39:01", "remaining_time": "2:53:07", "throughput": 686.16, "total_tokens": 4076960} {"current_steps": 14560, "total_steps": 40000, "loss": 0.0, "lr": 3.536117648177399e-05, "epoch": 161.77777777777777, "percentage": 36.4, "elapsed_time": "1:39:03", "remaining_time": "2:53:05", "throughput": 686.17, "total_tokens": 4078336} {"current_steps": 14565, "total_steps": 40000, "loss": 0.0, "lr": 3.535224105815558e-05, "epoch": 161.83333333333334, "percentage": 36.41, "elapsed_time": "1:39:05", "remaining_time": "2:53:02", "throughput": 686.19, "total_tokens": 4079792} {"current_steps": 14570, "total_steps": 40000, "loss": 0.0, "lr": 3.5343304038091494e-05, "epoch": 161.88888888888889, "percentage": 36.43, "elapsed_time": "1:39:07", "remaining_time": "2:53:00", "throughput": 686.2, "total_tokens": 4081168} {"current_steps": 14575, "total_steps": 40000, "loss": 0.0, "lr": 3.5334365422959955e-05, "epoch": 161.94444444444446, "percentage": 36.44, "elapsed_time": "1:39:09", "remaining_time": "2:52:58", "throughput": 686.21, "total_tokens": 4082560} {"current_steps": 14580, "total_steps": 40000, "loss": 0.0, "lr": 3.5325425214139396e-05, "epoch": 162.0, "percentage": 36.45, "elapsed_time": "1:39:11", "remaining_time": "2:52:56", "throughput": 686.19, "total_tokens": 4083904} {"current_steps": 14585, "total_steps": 40000, "loss": 0.0, "lr": 3.531648341300851e-05, "epoch": 162.05555555555554, "percentage": 36.46, "elapsed_time": "1:39:13", "remaining_time": "2:52:54", "throughput": 686.16, "total_tokens": 4085280} {"current_steps": 14590, "total_steps": 40000, "loss": 0.0, "lr": 3.530754002094623e-05, "epoch": 162.11111111111111, "percentage": 36.48, "elapsed_time": "1:39:15", "remaining_time": "2:52:52", "throughput": 686.17, "total_tokens": 4086688} {"current_steps": 14595, "total_steps": 40000, "loss": 0.0, "lr": 3.529859503933175e-05, "epoch": 162.16666666666666, "percentage": 36.49, "elapsed_time": "1:39:17", "remaining_time": "2:52:50", "throughput": 686.18, "total_tokens": 4088064} {"current_steps": 14600, "total_steps": 40000, "loss": 0.0, "lr": 3.52896484695445e-05, "epoch": 162.22222222222223, "percentage": 36.5, "elapsed_time": "1:39:19", "remaining_time": "2:52:48", "throughput": 686.2, "total_tokens": 4089504} {"current_steps": 14600, "total_steps": 40000, "eval_loss": 0.39667797088623047, "epoch": 162.22222222222223, "percentage": 36.5, "elapsed_time": "1:39:21", "remaining_time": "2:52:50", "throughput": 686.04, "total_tokens": 4089504} {"current_steps": 14605, "total_steps": 40000, "loss": 0.0, "lr": 3.528070031296414e-05, "epoch": 162.27777777777777, "percentage": 36.51, "elapsed_time": "1:39:24", "remaining_time": "2:52:50", "throughput": 685.9, "total_tokens": 4090896} {"current_steps": 14610, "total_steps": 40000, "loss": 0.0, "lr": 3.5271750570970605e-05, "epoch": 162.33333333333334, "percentage": 36.52, "elapsed_time": "1:39:26", "remaining_time": "2:52:48", "throughput": 685.9, "total_tokens": 4092288} {"current_steps": 14615, "total_steps": 40000, "loss": 0.0, "lr": 3.526279924494405e-05, "epoch": 162.38888888888889, "percentage": 36.54, "elapsed_time": "1:39:28", "remaining_time": "2:52:46", "throughput": 685.91, "total_tokens": 4093712} {"current_steps": 14620, "total_steps": 40000, "loss": 0.0, "lr": 3.5253846336264874e-05, "epoch": 162.44444444444446, "percentage": 36.55, "elapsed_time": "1:39:30", "remaining_time": "2:52:44", "throughput": 685.92, "total_tokens": 4095104} {"current_steps": 14625, "total_steps": 40000, "loss": 0.0, "lr": 3.5244891846313736e-05, "epoch": 162.5, "percentage": 36.56, "elapsed_time": "1:39:32", "remaining_time": "2:52:41", "throughput": 685.94, "total_tokens": 4096528} {"current_steps": 14630, "total_steps": 40000, "loss": 0.0, "lr": 3.5235935776471527e-05, "epoch": 162.55555555555554, "percentage": 36.58, "elapsed_time": "1:39:34", "remaining_time": "2:52:39", "throughput": 685.95, "total_tokens": 4097952} {"current_steps": 14635, "total_steps": 40000, "loss": 0.0, "lr": 3.522697812811939e-05, "epoch": 162.61111111111111, "percentage": 36.59, "elapsed_time": "1:39:36", "remaining_time": "2:52:37", "throughput": 685.96, "total_tokens": 4099328} {"current_steps": 14640, "total_steps": 40000, "loss": 0.0, "lr": 3.521801890263871e-05, "epoch": 162.66666666666666, "percentage": 36.6, "elapsed_time": "1:39:38", "remaining_time": "2:52:35", "throughput": 685.97, "total_tokens": 4100752} {"current_steps": 14645, "total_steps": 40000, "loss": 0.0, "lr": 3.5209058101411114e-05, "epoch": 162.72222222222223, "percentage": 36.61, "elapsed_time": "1:39:39", "remaining_time": "2:52:33", "throughput": 685.99, "total_tokens": 4102176} {"current_steps": 14650, "total_steps": 40000, "loss": 0.0, "lr": 3.520009572581845e-05, "epoch": 162.77777777777777, "percentage": 36.62, "elapsed_time": "1:39:41", "remaining_time": "2:52:30", "throughput": 686.0, "total_tokens": 4103584} {"current_steps": 14655, "total_steps": 40000, "loss": 0.0, "lr": 3.519113177724285e-05, "epoch": 162.83333333333334, "percentage": 36.64, "elapsed_time": "1:39:43", "remaining_time": "2:52:28", "throughput": 686.01, "total_tokens": 4105008} {"current_steps": 14660, "total_steps": 40000, "loss": 0.0, "lr": 3.5182166257066656e-05, "epoch": 162.88888888888889, "percentage": 36.65, "elapsed_time": "1:39:45", "remaining_time": "2:52:26", "throughput": 686.02, "total_tokens": 4106384} {"current_steps": 14665, "total_steps": 40000, "loss": 0.0, "lr": 3.517319916667247e-05, "epoch": 162.94444444444446, "percentage": 36.66, "elapsed_time": "1:39:47", "remaining_time": "2:52:24", "throughput": 686.03, "total_tokens": 4107808} {"current_steps": 14670, "total_steps": 40000, "loss": 0.0, "lr": 3.516423050744313e-05, "epoch": 163.0, "percentage": 36.68, "elapsed_time": "1:39:49", "remaining_time": "2:52:22", "throughput": 686.02, "total_tokens": 4109200} {"current_steps": 14675, "total_steps": 40000, "loss": 0.0, "lr": 3.5155260280761704e-05, "epoch": 163.05555555555554, "percentage": 36.69, "elapsed_time": "1:39:52", "remaining_time": "2:52:20", "throughput": 686.0, "total_tokens": 4110608} {"current_steps": 14680, "total_steps": 40000, "loss": 0.0, "lr": 3.514628848801154e-05, "epoch": 163.11111111111111, "percentage": 36.7, "elapsed_time": "1:39:54", "remaining_time": "2:52:18", "throughput": 686.01, "total_tokens": 4112000} {"current_steps": 14685, "total_steps": 40000, "loss": 0.0, "lr": 3.5137315130576174e-05, "epoch": 163.16666666666666, "percentage": 36.71, "elapsed_time": "1:39:55", "remaining_time": "2:52:16", "throughput": 686.02, "total_tokens": 4113392} {"current_steps": 14690, "total_steps": 40000, "loss": 0.0, "lr": 3.512834020983942e-05, "epoch": 163.22222222222223, "percentage": 36.73, "elapsed_time": "1:39:57", "remaining_time": "2:52:14", "throughput": 686.04, "total_tokens": 4114832} {"current_steps": 14695, "total_steps": 40000, "loss": 0.0, "lr": 3.5119363727185334e-05, "epoch": 163.27777777777777, "percentage": 36.74, "elapsed_time": "1:39:59", "remaining_time": "2:52:11", "throughput": 686.06, "total_tokens": 4116256} {"current_steps": 14700, "total_steps": 40000, "loss": 0.0, "lr": 3.511038568399819e-05, "epoch": 163.33333333333334, "percentage": 36.75, "elapsed_time": "1:40:01", "remaining_time": "2:52:09", "throughput": 686.07, "total_tokens": 4117664} {"current_steps": 14705, "total_steps": 40000, "loss": 0.0, "lr": 3.510140608166251e-05, "epoch": 163.38888888888889, "percentage": 36.76, "elapsed_time": "1:40:03", "remaining_time": "2:52:07", "throughput": 686.08, "total_tokens": 4119040} {"current_steps": 14710, "total_steps": 40000, "loss": 0.0, "lr": 3.509242492156308e-05, "epoch": 163.44444444444446, "percentage": 36.78, "elapsed_time": "1:40:05", "remaining_time": "2:52:05", "throughput": 686.09, "total_tokens": 4120464} {"current_steps": 14715, "total_steps": 40000, "loss": 0.0, "lr": 3.5083442205084896e-05, "epoch": 163.5, "percentage": 36.79, "elapsed_time": "1:40:07", "remaining_time": "2:52:03", "throughput": 686.1, "total_tokens": 4121872} {"current_steps": 14720, "total_steps": 40000, "loss": 0.0, "lr": 3.507445793361321e-05, "epoch": 163.55555555555554, "percentage": 36.8, "elapsed_time": "1:40:09", "remaining_time": "2:52:00", "throughput": 686.1, "total_tokens": 4123216} {"current_steps": 14725, "total_steps": 40000, "loss": 0.0, "lr": 3.5065472108533505e-05, "epoch": 163.61111111111111, "percentage": 36.81, "elapsed_time": "1:40:11", "remaining_time": "2:51:58", "throughput": 686.11, "total_tokens": 4124592} {"current_steps": 14730, "total_steps": 40000, "loss": 0.0, "lr": 3.5056484731231504e-05, "epoch": 163.66666666666666, "percentage": 36.83, "elapsed_time": "1:40:13", "remaining_time": "2:51:56", "throughput": 686.12, "total_tokens": 4125952} {"current_steps": 14735, "total_steps": 40000, "loss": 0.0, "lr": 3.504749580309319e-05, "epoch": 163.72222222222223, "percentage": 36.84, "elapsed_time": "1:40:15", "remaining_time": "2:51:54", "throughput": 686.12, "total_tokens": 4127344} {"current_steps": 14740, "total_steps": 40000, "loss": 0.0, "lr": 3.5038505325504753e-05, "epoch": 163.77777777777777, "percentage": 36.85, "elapsed_time": "1:40:17", "remaining_time": "2:51:52", "throughput": 686.14, "total_tokens": 4128784} {"current_steps": 14745, "total_steps": 40000, "loss": 0.0, "lr": 3.502951329985264e-05, "epoch": 163.83333333333334, "percentage": 36.86, "elapsed_time": "1:40:19", "remaining_time": "2:51:49", "throughput": 686.15, "total_tokens": 4130176} {"current_steps": 14750, "total_steps": 40000, "loss": 0.0, "lr": 3.502051972752354e-05, "epoch": 163.88888888888889, "percentage": 36.88, "elapsed_time": "1:40:21", "remaining_time": "2:51:47", "throughput": 686.16, "total_tokens": 4131568} {"current_steps": 14755, "total_steps": 40000, "loss": 0.0, "lr": 3.5011524609904374e-05, "epoch": 163.94444444444446, "percentage": 36.89, "elapsed_time": "1:40:23", "remaining_time": "2:51:45", "throughput": 686.17, "total_tokens": 4132960} {"current_steps": 14760, "total_steps": 40000, "loss": 0.0, "lr": 3.50025279483823e-05, "epoch": 164.0, "percentage": 36.9, "elapsed_time": "1:40:25", "remaining_time": "2:51:43", "throughput": 686.16, "total_tokens": 4134368} {"current_steps": 14765, "total_steps": 40000, "loss": 0.0, "lr": 3.499352974434472e-05, "epoch": 164.05555555555554, "percentage": 36.91, "elapsed_time": "1:40:27", "remaining_time": "2:51:41", "throughput": 686.13, "total_tokens": 4135712} {"current_steps": 14770, "total_steps": 40000, "loss": 0.0, "lr": 3.498452999917926e-05, "epoch": 164.11111111111111, "percentage": 36.93, "elapsed_time": "1:40:29", "remaining_time": "2:51:39", "throughput": 686.15, "total_tokens": 4137104} {"current_steps": 14775, "total_steps": 40000, "loss": 0.0, "lr": 3.4975528714273795e-05, "epoch": 164.16666666666666, "percentage": 36.94, "elapsed_time": "1:40:31", "remaining_time": "2:51:37", "throughput": 686.15, "total_tokens": 4138480} {"current_steps": 14780, "total_steps": 40000, "loss": 0.0, "lr": 3.4966525891016454e-05, "epoch": 164.22222222222223, "percentage": 36.95, "elapsed_time": "1:40:33", "remaining_time": "2:51:35", "throughput": 686.17, "total_tokens": 4139936} {"current_steps": 14785, "total_steps": 40000, "loss": 0.0, "lr": 3.495752153079557e-05, "epoch": 164.27777777777777, "percentage": 36.96, "elapsed_time": "1:40:35", "remaining_time": "2:51:32", "throughput": 686.18, "total_tokens": 4141328} {"current_steps": 14790, "total_steps": 40000, "loss": 0.0, "lr": 3.494851563499974e-05, "epoch": 164.33333333333334, "percentage": 36.98, "elapsed_time": "1:40:37", "remaining_time": "2:51:30", "throughput": 686.19, "total_tokens": 4142720} {"current_steps": 14795, "total_steps": 40000, "loss": 0.0, "lr": 3.493950820501777e-05, "epoch": 164.38888888888889, "percentage": 36.99, "elapsed_time": "1:40:39", "remaining_time": "2:51:28", "throughput": 686.21, "total_tokens": 4144144} {"current_steps": 14800, "total_steps": 40000, "loss": 0.0, "lr": 3.493049924223872e-05, "epoch": 164.44444444444446, "percentage": 37.0, "elapsed_time": "1:40:41", "remaining_time": "2:51:26", "throughput": 686.21, "total_tokens": 4145504} {"current_steps": 14800, "total_steps": 40000, "eval_loss": 0.4044431746006012, "epoch": 164.44444444444446, "percentage": 37.0, "elapsed_time": "1:40:42", "remaining_time": "2:51:28", "throughput": 686.06, "total_tokens": 4145504} {"current_steps": 14805, "total_steps": 40000, "loss": 0.0, "lr": 3.49214887480519e-05, "epoch": 164.5, "percentage": 37.01, "elapsed_time": "1:40:45", "remaining_time": "2:51:28", "throughput": 685.9, "total_tokens": 4146816} {"current_steps": 14810, "total_steps": 40000, "loss": 0.0, "lr": 3.4912476723846834e-05, "epoch": 164.55555555555554, "percentage": 37.03, "elapsed_time": "1:40:47", "remaining_time": "2:51:26", "throughput": 685.9, "total_tokens": 4148192} {"current_steps": 14815, "total_steps": 40000, "loss": 0.0, "lr": 3.490346317101328e-05, "epoch": 164.61111111111111, "percentage": 37.04, "elapsed_time": "1:40:49", "remaining_time": "2:51:24", "throughput": 685.93, "total_tokens": 4149648} {"current_steps": 14820, "total_steps": 40000, "loss": 0.0, "lr": 3.4894448090941266e-05, "epoch": 164.66666666666666, "percentage": 37.05, "elapsed_time": "1:40:51", "remaining_time": "2:51:22", "throughput": 685.93, "total_tokens": 4150992} {"current_steps": 14825, "total_steps": 40000, "loss": 0.0, "lr": 3.488543148502101e-05, "epoch": 164.72222222222223, "percentage": 37.06, "elapsed_time": "1:40:53", "remaining_time": "2:51:19", "throughput": 685.94, "total_tokens": 4152416} {"current_steps": 14830, "total_steps": 40000, "loss": 0.0, "lr": 3.487641335464299e-05, "epoch": 164.77777777777777, "percentage": 37.08, "elapsed_time": "1:40:55", "remaining_time": "2:51:17", "throughput": 685.95, "total_tokens": 4153840} {"current_steps": 14835, "total_steps": 40000, "loss": 0.0, "lr": 3.4867393701197914e-05, "epoch": 164.83333333333334, "percentage": 37.09, "elapsed_time": "1:40:57", "remaining_time": "2:51:15", "throughput": 685.96, "total_tokens": 4155232} {"current_steps": 14840, "total_steps": 40000, "loss": 0.0, "lr": 3.485837252607673e-05, "epoch": 164.88888888888889, "percentage": 37.1, "elapsed_time": "1:40:59", "remaining_time": "2:51:13", "throughput": 685.98, "total_tokens": 4156672} {"current_steps": 14845, "total_steps": 40000, "loss": 0.0, "lr": 3.4849349830670615e-05, "epoch": 164.94444444444446, "percentage": 37.11, "elapsed_time": "1:41:01", "remaining_time": "2:51:11", "throughput": 685.99, "total_tokens": 4158064} {"current_steps": 14850, "total_steps": 40000, "loss": 0.0, "lr": 3.4840325616370976e-05, "epoch": 165.0, "percentage": 37.12, "elapsed_time": "1:41:03", "remaining_time": "2:51:09", "throughput": 685.98, "total_tokens": 4159472} {"current_steps": 14855, "total_steps": 40000, "loss": 0.0, "lr": 3.483129988456947e-05, "epoch": 165.05555555555554, "percentage": 37.14, "elapsed_time": "1:41:05", "remaining_time": "2:51:07", "throughput": 685.96, "total_tokens": 4160848} {"current_steps": 14860, "total_steps": 40000, "loss": 0.0, "lr": 3.482227263665797e-05, "epoch": 165.11111111111111, "percentage": 37.15, "elapsed_time": "1:41:08", "remaining_time": "2:51:05", "throughput": 685.93, "total_tokens": 4162256} {"current_steps": 14865, "total_steps": 40000, "loss": 0.0, "lr": 3.48132438740286e-05, "epoch": 165.16666666666666, "percentage": 37.16, "elapsed_time": "1:41:09", "remaining_time": "2:51:03", "throughput": 685.94, "total_tokens": 4163680} {"current_steps": 14870, "total_steps": 40000, "loss": 0.0, "lr": 3.48042135980737e-05, "epoch": 165.22222222222223, "percentage": 37.18, "elapsed_time": "1:41:11", "remaining_time": "2:51:01", "throughput": 685.95, "total_tokens": 4165056} {"current_steps": 14875, "total_steps": 40000, "loss": 0.0, "lr": 3.479518181018586e-05, "epoch": 165.27777777777777, "percentage": 37.19, "elapsed_time": "1:41:13", "remaining_time": "2:50:59", "throughput": 685.96, "total_tokens": 4166448} {"current_steps": 14880, "total_steps": 40000, "loss": 0.0, "lr": 3.4786148511757886e-05, "epoch": 165.33333333333334, "percentage": 37.2, "elapsed_time": "1:41:15", "remaining_time": "2:50:57", "throughput": 685.96, "total_tokens": 4167808} {"current_steps": 14885, "total_steps": 40000, "loss": 0.0, "lr": 3.477711370418284e-05, "epoch": 165.38888888888889, "percentage": 37.21, "elapsed_time": "1:41:17", "remaining_time": "2:50:54", "throughput": 685.98, "total_tokens": 4169248} {"current_steps": 14890, "total_steps": 40000, "loss": 0.0, "lr": 3.476807738885399e-05, "epoch": 165.44444444444446, "percentage": 37.23, "elapsed_time": "1:41:19", "remaining_time": "2:50:52", "throughput": 685.99, "total_tokens": 4170640} {"current_steps": 14895, "total_steps": 40000, "loss": 0.0, "lr": 3.475903956716485e-05, "epoch": 165.5, "percentage": 37.24, "elapsed_time": "1:41:21", "remaining_time": "2:50:50", "throughput": 686.01, "total_tokens": 4172064} {"current_steps": 14900, "total_steps": 40000, "loss": 0.0, "lr": 3.475000024050917e-05, "epoch": 165.55555555555554, "percentage": 37.25, "elapsed_time": "1:41:23", "remaining_time": "2:50:48", "throughput": 686.02, "total_tokens": 4173472} {"current_steps": 14905, "total_steps": 40000, "loss": 0.0, "lr": 3.4740959410280926e-05, "epoch": 165.61111111111111, "percentage": 37.26, "elapsed_time": "1:41:25", "remaining_time": "2:50:46", "throughput": 686.02, "total_tokens": 4174848} {"current_steps": 14910, "total_steps": 40000, "loss": 0.0, "lr": 3.4731917077874324e-05, "epoch": 165.66666666666666, "percentage": 37.28, "elapsed_time": "1:41:27", "remaining_time": "2:50:43", "throughput": 686.04, "total_tokens": 4176256} {"current_steps": 14915, "total_steps": 40000, "loss": 0.0, "lr": 3.4722873244683816e-05, "epoch": 165.72222222222223, "percentage": 37.29, "elapsed_time": "1:41:29", "remaining_time": "2:50:41", "throughput": 686.05, "total_tokens": 4177664} {"current_steps": 14920, "total_steps": 40000, "loss": 0.0, "lr": 3.4713827912104065e-05, "epoch": 165.77777777777777, "percentage": 37.3, "elapsed_time": "1:41:31", "remaining_time": "2:50:39", "throughput": 686.06, "total_tokens": 4179056} {"current_steps": 14925, "total_steps": 40000, "loss": 0.0, "lr": 3.470478108152998e-05, "epoch": 165.83333333333334, "percentage": 37.31, "elapsed_time": "1:41:33", "remaining_time": "2:50:37", "throughput": 686.06, "total_tokens": 4180416} {"current_steps": 14930, "total_steps": 40000, "loss": 0.0, "lr": 3.4695732754356695e-05, "epoch": 165.88888888888889, "percentage": 37.33, "elapsed_time": "1:41:35", "remaining_time": "2:50:35", "throughput": 686.08, "total_tokens": 4181856} {"current_steps": 14935, "total_steps": 40000, "loss": 0.0, "lr": 3.4686682931979576e-05, "epoch": 165.94444444444446, "percentage": 37.34, "elapsed_time": "1:41:37", "remaining_time": "2:50:32", "throughput": 686.08, "total_tokens": 4183232} {"current_steps": 14940, "total_steps": 40000, "loss": 0.0, "lr": 3.467763161579422e-05, "epoch": 166.0, "percentage": 37.35, "elapsed_time": "1:41:39", "remaining_time": "2:50:30", "throughput": 686.08, "total_tokens": 4184672} {"current_steps": 14945, "total_steps": 40000, "loss": 0.0, "lr": 3.466857880719645e-05, "epoch": 166.05555555555554, "percentage": 37.36, "elapsed_time": "1:41:41", "remaining_time": "2:50:29", "throughput": 686.07, "total_tokens": 4186096} {"current_steps": 14950, "total_steps": 40000, "loss": 0.0, "lr": 3.465952450758233e-05, "epoch": 166.11111111111111, "percentage": 37.38, "elapsed_time": "1:41:43", "remaining_time": "2:50:26", "throughput": 686.08, "total_tokens": 4187472} {"current_steps": 14955, "total_steps": 40000, "loss": 0.0, "lr": 3.4650468718348126e-05, "epoch": 166.16666666666666, "percentage": 37.39, "elapsed_time": "1:41:45", "remaining_time": "2:50:24", "throughput": 686.09, "total_tokens": 4188880} {"current_steps": 14960, "total_steps": 40000, "loss": 0.0, "lr": 3.464141144089038e-05, "epoch": 166.22222222222223, "percentage": 37.4, "elapsed_time": "1:41:47", "remaining_time": "2:50:22", "throughput": 686.1, "total_tokens": 4190288} {"current_steps": 14965, "total_steps": 40000, "loss": 0.0, "lr": 3.463235267660583e-05, "epoch": 166.27777777777777, "percentage": 37.41, "elapsed_time": "1:41:49", "remaining_time": "2:50:20", "throughput": 686.1, "total_tokens": 4191632} {"current_steps": 14970, "total_steps": 40000, "loss": 0.0, "lr": 3.462329242689145e-05, "epoch": 166.33333333333334, "percentage": 37.43, "elapsed_time": "1:41:51", "remaining_time": "2:50:18", "throughput": 686.1, "total_tokens": 4192976} {"current_steps": 14975, "total_steps": 40000, "loss": 0.0, "lr": 3.461423069314444e-05, "epoch": 166.38888888888889, "percentage": 37.44, "elapsed_time": "1:41:53", "remaining_time": "2:50:15", "throughput": 686.12, "total_tokens": 4194416} {"current_steps": 14980, "total_steps": 40000, "loss": 0.0, "lr": 3.460516747676224e-05, "epoch": 166.44444444444446, "percentage": 37.45, "elapsed_time": "1:41:55", "remaining_time": "2:50:13", "throughput": 686.13, "total_tokens": 4195824} {"current_steps": 14985, "total_steps": 40000, "loss": 0.0, "lr": 3.459610277914251e-05, "epoch": 166.5, "percentage": 37.46, "elapsed_time": "1:41:57", "remaining_time": "2:50:11", "throughput": 686.14, "total_tokens": 4197232} {"current_steps": 14990, "total_steps": 40000, "loss": 0.0, "lr": 3.458703660168314e-05, "epoch": 166.55555555555554, "percentage": 37.48, "elapsed_time": "1:41:59", "remaining_time": "2:50:09", "throughput": 686.16, "total_tokens": 4198640} {"current_steps": 14995, "total_steps": 40000, "loss": 0.0, "lr": 3.457796894578224e-05, "epoch": 166.61111111111111, "percentage": 37.49, "elapsed_time": "1:42:01", "remaining_time": "2:50:07", "throughput": 686.17, "total_tokens": 4200048} {"current_steps": 15000, "total_steps": 40000, "loss": 0.0, "lr": 3.456889981283817e-05, "epoch": 166.66666666666666, "percentage": 37.5, "elapsed_time": "1:42:02", "remaining_time": "2:50:04", "throughput": 686.17, "total_tokens": 4201440} {"current_steps": 15000, "total_steps": 40000, "eval_loss": 0.4140651226043701, "epoch": 166.66666666666666, "percentage": 37.5, "elapsed_time": "1:42:04", "remaining_time": "2:50:07", "throughput": 686.02, "total_tokens": 4201440} {"current_steps": 15005, "total_steps": 40000, "loss": 0.0, "lr": 3.45598292042495e-05, "epoch": 166.72222222222223, "percentage": 37.51, "elapsed_time": "1:42:07", "remaining_time": "2:50:07", "throughput": 685.89, "total_tokens": 4202864} {"current_steps": 15010, "total_steps": 40000, "loss": 0.0, "lr": 3.4550757121415035e-05, "epoch": 166.77777777777777, "percentage": 37.52, "elapsed_time": "1:42:09", "remaining_time": "2:50:05", "throughput": 685.9, "total_tokens": 4204304} {"current_steps": 15015, "total_steps": 40000, "loss": 0.0, "lr": 3.454168356573378e-05, "epoch": 166.83333333333334, "percentage": 37.54, "elapsed_time": "1:42:11", "remaining_time": "2:50:02", "throughput": 685.9, "total_tokens": 4205664} {"current_steps": 15020, "total_steps": 40000, "loss": 0.0, "lr": 3.453260853860503e-05, "epoch": 166.88888888888889, "percentage": 37.55, "elapsed_time": "1:42:13", "remaining_time": "2:50:00", "throughput": 685.91, "total_tokens": 4207056} {"current_steps": 15025, "total_steps": 40000, "loss": 0.0, "lr": 3.452353204142824e-05, "epoch": 166.94444444444446, "percentage": 37.56, "elapsed_time": "1:42:15", "remaining_time": "2:49:58", "throughput": 685.92, "total_tokens": 4208432} {"current_steps": 15030, "total_steps": 40000, "loss": 0.0, "lr": 3.4514454075603136e-05, "epoch": 167.0, "percentage": 37.57, "elapsed_time": "1:42:17", "remaining_time": "2:49:56", "throughput": 685.91, "total_tokens": 4209840} {"current_steps": 15035, "total_steps": 40000, "loss": 0.0, "lr": 3.450537464252964e-05, "epoch": 167.05555555555554, "percentage": 37.59, "elapsed_time": "1:42:19", "remaining_time": "2:49:54", "throughput": 685.89, "total_tokens": 4211216} {"current_steps": 15040, "total_steps": 40000, "loss": 0.0, "lr": 3.4496293743607925e-05, "epoch": 167.11111111111111, "percentage": 37.6, "elapsed_time": "1:42:21", "remaining_time": "2:49:52", "throughput": 685.9, "total_tokens": 4212656} {"current_steps": 15045, "total_steps": 40000, "loss": 0.0, "lr": 3.448721138023838e-05, "epoch": 167.16666666666666, "percentage": 37.61, "elapsed_time": "1:42:23", "remaining_time": "2:49:50", "throughput": 685.91, "total_tokens": 4214032} {"current_steps": 15050, "total_steps": 40000, "loss": 0.0, "lr": 3.447812755382162e-05, "epoch": 167.22222222222223, "percentage": 37.62, "elapsed_time": "1:42:25", "remaining_time": "2:49:48", "throughput": 685.92, "total_tokens": 4215440} {"current_steps": 15055, "total_steps": 40000, "loss": 0.0, "lr": 3.446904226575847e-05, "epoch": 167.27777777777777, "percentage": 37.64, "elapsed_time": "1:42:27", "remaining_time": "2:49:46", "throughput": 685.94, "total_tokens": 4216848} {"current_steps": 15060, "total_steps": 40000, "loss": 0.0, "lr": 3.445995551745002e-05, "epoch": 167.33333333333334, "percentage": 37.65, "elapsed_time": "1:42:29", "remaining_time": "2:49:43", "throughput": 685.95, "total_tokens": 4218256} {"current_steps": 15065, "total_steps": 40000, "loss": 0.0, "lr": 3.445086731029753e-05, "epoch": 167.38888888888889, "percentage": 37.66, "elapsed_time": "1:42:31", "remaining_time": "2:49:41", "throughput": 685.96, "total_tokens": 4219648} {"current_steps": 15070, "total_steps": 40000, "loss": 0.0, "lr": 3.444177764570255e-05, "epoch": 167.44444444444446, "percentage": 37.67, "elapsed_time": "1:42:33", "remaining_time": "2:49:39", "throughput": 685.96, "total_tokens": 4221024} {"current_steps": 15075, "total_steps": 40000, "loss": 0.0, "lr": 3.44326865250668e-05, "epoch": 167.5, "percentage": 37.69, "elapsed_time": "1:42:35", "remaining_time": "2:49:37", "throughput": 685.99, "total_tokens": 4222480} {"current_steps": 15080, "total_steps": 40000, "loss": 0.0, "lr": 3.442359394979225e-05, "epoch": 167.55555555555554, "percentage": 37.7, "elapsed_time": "1:42:37", "remaining_time": "2:49:35", "throughput": 685.99, "total_tokens": 4223840} {"current_steps": 15085, "total_steps": 40000, "loss": 0.0, "lr": 3.441449992128108e-05, "epoch": 167.61111111111111, "percentage": 37.71, "elapsed_time": "1:42:39", "remaining_time": "2:49:32", "throughput": 686.0, "total_tokens": 4225248} {"current_steps": 15090, "total_steps": 40000, "loss": 0.0, "lr": 3.440540444093573e-05, "epoch": 167.66666666666666, "percentage": 37.72, "elapsed_time": "1:42:41", "remaining_time": "2:49:30", "throughput": 686.01, "total_tokens": 4226656} {"current_steps": 15095, "total_steps": 40000, "loss": 0.0, "lr": 3.43963075101588e-05, "epoch": 167.72222222222223, "percentage": 37.74, "elapsed_time": "1:42:43", "remaining_time": "2:49:28", "throughput": 686.02, "total_tokens": 4228032} {"current_steps": 15100, "total_steps": 40000, "loss": 0.0, "lr": 3.438720913035318e-05, "epoch": 167.77777777777777, "percentage": 37.75, "elapsed_time": "1:42:45", "remaining_time": "2:49:26", "throughput": 686.04, "total_tokens": 4229456} {"current_steps": 15105, "total_steps": 40000, "loss": 0.0, "lr": 3.437810930292195e-05, "epoch": 167.83333333333334, "percentage": 37.76, "elapsed_time": "1:42:47", "remaining_time": "2:49:24", "throughput": 686.04, "total_tokens": 4230848} {"current_steps": 15110, "total_steps": 40000, "loss": 0.0, "lr": 3.43690080292684e-05, "epoch": 167.88888888888889, "percentage": 37.77, "elapsed_time": "1:42:48", "remaining_time": "2:49:21", "throughput": 686.06, "total_tokens": 4232256} {"current_steps": 15115, "total_steps": 40000, "loss": 0.0, "lr": 3.435990531079608e-05, "epoch": 167.94444444444446, "percentage": 37.79, "elapsed_time": "1:42:50", "remaining_time": "2:49:19", "throughput": 686.07, "total_tokens": 4233648} {"current_steps": 15120, "total_steps": 40000, "loss": 0.0, "lr": 3.435080114890874e-05, "epoch": 168.0, "percentage": 37.8, "elapsed_time": "1:42:53", "remaining_time": "2:49:17", "throughput": 686.06, "total_tokens": 4235040} {"current_steps": 15125, "total_steps": 40000, "loss": 0.0, "lr": 3.434169554501035e-05, "epoch": 168.05555555555554, "percentage": 37.81, "elapsed_time": "1:42:55", "remaining_time": "2:49:16", "throughput": 686.04, "total_tokens": 4236464} {"current_steps": 15130, "total_steps": 40000, "loss": 0.0, "lr": 3.433258850050511e-05, "epoch": 168.11111111111111, "percentage": 37.82, "elapsed_time": "1:42:57", "remaining_time": "2:49:13", "throughput": 686.04, "total_tokens": 4237824} {"current_steps": 15135, "total_steps": 40000, "loss": 0.0, "lr": 3.4323480016797446e-05, "epoch": 168.16666666666666, "percentage": 37.84, "elapsed_time": "1:42:59", "remaining_time": "2:49:11", "throughput": 686.05, "total_tokens": 4239216} {"current_steps": 15140, "total_steps": 40000, "loss": 0.0, "lr": 3.4314370095291995e-05, "epoch": 168.22222222222223, "percentage": 37.85, "elapsed_time": "1:43:01", "remaining_time": "2:49:09", "throughput": 686.06, "total_tokens": 4240624} {"current_steps": 15145, "total_steps": 40000, "loss": 0.0, "lr": 3.430525873739363e-05, "epoch": 168.27777777777777, "percentage": 37.86, "elapsed_time": "1:43:03", "remaining_time": "2:49:07", "throughput": 686.07, "total_tokens": 4242032} {"current_steps": 15150, "total_steps": 40000, "loss": 0.0, "lr": 3.429614594450743e-05, "epoch": 168.33333333333334, "percentage": 37.88, "elapsed_time": "1:43:05", "remaining_time": "2:49:05", "throughput": 686.09, "total_tokens": 4243440} {"current_steps": 15155, "total_steps": 40000, "loss": 0.0, "lr": 3.428703171803869e-05, "epoch": 168.38888888888889, "percentage": 37.89, "elapsed_time": "1:43:06", "remaining_time": "2:49:02", "throughput": 686.1, "total_tokens": 4244864} {"current_steps": 15160, "total_steps": 40000, "loss": 0.0, "lr": 3.4277916059392964e-05, "epoch": 168.44444444444446, "percentage": 37.9, "elapsed_time": "1:43:08", "remaining_time": "2:49:00", "throughput": 686.12, "total_tokens": 4246320} {"current_steps": 15165, "total_steps": 40000, "loss": 0.0, "lr": 3.426879896997598e-05, "epoch": 168.5, "percentage": 37.91, "elapsed_time": "1:43:10", "remaining_time": "2:48:58", "throughput": 686.13, "total_tokens": 4247680} {"current_steps": 15170, "total_steps": 40000, "loss": 0.0, "lr": 3.425968045119372e-05, "epoch": 168.55555555555554, "percentage": 37.92, "elapsed_time": "1:43:12", "remaining_time": "2:48:56", "throughput": 686.14, "total_tokens": 4249104} {"current_steps": 15175, "total_steps": 40000, "loss": 0.0, "lr": 3.425056050445237e-05, "epoch": 168.61111111111111, "percentage": 37.94, "elapsed_time": "1:43:14", "remaining_time": "2:48:54", "throughput": 686.14, "total_tokens": 4250480} {"current_steps": 15180, "total_steps": 40000, "loss": 0.0, "lr": 3.4241439131158336e-05, "epoch": 168.66666666666666, "percentage": 37.95, "elapsed_time": "1:43:16", "remaining_time": "2:48:51", "throughput": 686.15, "total_tokens": 4251872} {"current_steps": 15185, "total_steps": 40000, "loss": 0.0, "lr": 3.423231633271825e-05, "epoch": 168.72222222222223, "percentage": 37.96, "elapsed_time": "1:43:18", "remaining_time": "2:48:49", "throughput": 686.17, "total_tokens": 4253312} {"current_steps": 15190, "total_steps": 40000, "loss": 0.0, "lr": 3.4223192110538985e-05, "epoch": 168.77777777777777, "percentage": 37.97, "elapsed_time": "1:43:20", "remaining_time": "2:48:47", "throughput": 686.17, "total_tokens": 4254656} {"current_steps": 15195, "total_steps": 40000, "loss": 0.0, "lr": 3.4214066466027575e-05, "epoch": 168.83333333333334, "percentage": 37.99, "elapsed_time": "1:43:22", "remaining_time": "2:48:45", "throughput": 686.18, "total_tokens": 4256064} {"current_steps": 15200, "total_steps": 40000, "loss": 0.0, "lr": 3.4204939400591325e-05, "epoch": 168.88888888888889, "percentage": 38.0, "elapsed_time": "1:43:24", "remaining_time": "2:48:43", "throughput": 686.2, "total_tokens": 4257504} {"current_steps": 15200, "total_steps": 40000, "eval_loss": 0.35443609952926636, "epoch": 168.88888888888889, "percentage": 38.0, "elapsed_time": "1:43:25", "remaining_time": "2:48:45", "throughput": 686.05, "total_tokens": 4257504} {"current_steps": 15205, "total_steps": 40000, "loss": 0.0, "lr": 3.419581091563775e-05, "epoch": 168.94444444444446, "percentage": 38.01, "elapsed_time": "1:43:29", "remaining_time": "2:48:45", "throughput": 685.92, "total_tokens": 4258928} {"current_steps": 15210, "total_steps": 40000, "loss": 0.0, "lr": 3.418668101257456e-05, "epoch": 169.0, "percentage": 38.02, "elapsed_time": "1:43:31", "remaining_time": "2:48:43", "throughput": 685.89, "total_tokens": 4260272} {"current_steps": 15215, "total_steps": 40000, "loss": 0.0, "lr": 3.417754969280971e-05, "epoch": 169.05555555555554, "percentage": 38.04, "elapsed_time": "1:43:33", "remaining_time": "2:48:41", "throughput": 685.88, "total_tokens": 4261680} {"current_steps": 15220, "total_steps": 40000, "loss": 0.0, "lr": 3.416841695775137e-05, "epoch": 169.11111111111111, "percentage": 38.05, "elapsed_time": "1:43:35", "remaining_time": "2:48:39", "throughput": 685.89, "total_tokens": 4263120} {"current_steps": 15225, "total_steps": 40000, "loss": 0.0, "lr": 3.415928280880792e-05, "epoch": 169.16666666666666, "percentage": 38.06, "elapsed_time": "1:43:37", "remaining_time": "2:48:37", "throughput": 685.9, "total_tokens": 4264512} {"current_steps": 15230, "total_steps": 40000, "loss": 0.0, "lr": 3.4150147247387965e-05, "epoch": 169.22222222222223, "percentage": 38.07, "elapsed_time": "1:43:39", "remaining_time": "2:48:35", "throughput": 685.92, "total_tokens": 4265952} {"current_steps": 15235, "total_steps": 40000, "loss": 0.0, "lr": 3.4141010274900306e-05, "epoch": 169.27777777777777, "percentage": 38.09, "elapsed_time": "1:43:41", "remaining_time": "2:48:32", "throughput": 685.93, "total_tokens": 4267344} {"current_steps": 15240, "total_steps": 40000, "loss": 0.0, "lr": 3.413187189275399e-05, "epoch": 169.33333333333334, "percentage": 38.1, "elapsed_time": "1:43:43", "remaining_time": "2:48:30", "throughput": 685.94, "total_tokens": 4268752} {"current_steps": 15245, "total_steps": 40000, "loss": 0.0, "lr": 3.4122732102358265e-05, "epoch": 169.38888888888889, "percentage": 38.11, "elapsed_time": "1:43:45", "remaining_time": "2:48:28", "throughput": 685.94, "total_tokens": 4270080} {"current_steps": 15250, "total_steps": 40000, "loss": 0.0, "lr": 3.411359090512261e-05, "epoch": 169.44444444444446, "percentage": 38.12, "elapsed_time": "1:43:47", "remaining_time": "2:48:26", "throughput": 685.94, "total_tokens": 4271440} {"current_steps": 15255, "total_steps": 40000, "loss": 0.0, "lr": 3.410444830245672e-05, "epoch": 169.5, "percentage": 38.14, "elapsed_time": "1:43:49", "remaining_time": "2:48:24", "throughput": 685.95, "total_tokens": 4272832} {"current_steps": 15260, "total_steps": 40000, "loss": 0.0, "lr": 3.409530429577048e-05, "epoch": 169.55555555555554, "percentage": 38.15, "elapsed_time": "1:43:51", "remaining_time": "2:48:21", "throughput": 685.96, "total_tokens": 4274240} {"current_steps": 15265, "total_steps": 40000, "loss": 0.0, "lr": 3.408615888647402e-05, "epoch": 169.61111111111111, "percentage": 38.16, "elapsed_time": "1:43:52", "remaining_time": "2:48:19", "throughput": 685.98, "total_tokens": 4275664} {"current_steps": 15270, "total_steps": 40000, "loss": 0.0, "lr": 3.4077012075977675e-05, "epoch": 169.66666666666666, "percentage": 38.17, "elapsed_time": "1:43:54", "remaining_time": "2:48:17", "throughput": 685.98, "total_tokens": 4277056} {"current_steps": 15275, "total_steps": 40000, "loss": 0.0, "lr": 3.4067863865692e-05, "epoch": 169.72222222222223, "percentage": 38.19, "elapsed_time": "1:43:56", "remaining_time": "2:48:15", "throughput": 685.99, "total_tokens": 4278432} {"current_steps": 15280, "total_steps": 40000, "loss": 0.0, "lr": 3.4058714257027755e-05, "epoch": 169.77777777777777, "percentage": 38.2, "elapsed_time": "1:43:58", "remaining_time": "2:48:13", "throughput": 686.0, "total_tokens": 4279792} {"current_steps": 15285, "total_steps": 40000, "loss": 0.0, "lr": 3.404956325139594e-05, "epoch": 169.83333333333334, "percentage": 38.21, "elapsed_time": "1:44:00", "remaining_time": "2:48:10", "throughput": 686.01, "total_tokens": 4281232} {"current_steps": 15290, "total_steps": 40000, "loss": 0.0, "lr": 3.404041085020775e-05, "epoch": 169.88888888888889, "percentage": 38.22, "elapsed_time": "1:44:02", "remaining_time": "2:48:08", "throughput": 686.02, "total_tokens": 4282624} {"current_steps": 15295, "total_steps": 40000, "loss": 0.0, "lr": 3.403125705487459e-05, "epoch": 169.94444444444446, "percentage": 38.24, "elapsed_time": "1:44:04", "remaining_time": "2:48:06", "throughput": 686.04, "total_tokens": 4284064} {"current_steps": 15300, "total_steps": 40000, "loss": 0.0, "lr": 3.402210186680811e-05, "epoch": 170.0, "percentage": 38.25, "elapsed_time": "1:44:06", "remaining_time": "2:48:04", "throughput": 686.03, "total_tokens": 4285504} {"current_steps": 15305, "total_steps": 40000, "loss": 0.0, "lr": 3.4012945287420137e-05, "epoch": 170.05555555555554, "percentage": 38.26, "elapsed_time": "1:44:08", "remaining_time": "2:48:02", "throughput": 686.01, "total_tokens": 4286848} {"current_steps": 15310, "total_steps": 40000, "loss": 0.0, "lr": 3.400378731812274e-05, "epoch": 170.11111111111111, "percentage": 38.27, "elapsed_time": "1:44:10", "remaining_time": "2:48:00", "throughput": 686.01, "total_tokens": 4288208} {"current_steps": 15315, "total_steps": 40000, "loss": 0.0, "lr": 3.399462796032817e-05, "epoch": 170.16666666666666, "percentage": 38.29, "elapsed_time": "1:44:12", "remaining_time": "2:47:58", "throughput": 686.02, "total_tokens": 4289600} {"current_steps": 15320, "total_steps": 40000, "loss": 0.0, "lr": 3.3985467215448954e-05, "epoch": 170.22222222222223, "percentage": 38.3, "elapsed_time": "1:44:14", "remaining_time": "2:47:56", "throughput": 686.03, "total_tokens": 4290992} {"current_steps": 15325, "total_steps": 40000, "loss": 0.0, "lr": 3.3976305084897776e-05, "epoch": 170.27777777777777, "percentage": 38.31, "elapsed_time": "1:44:16", "remaining_time": "2:47:54", "throughput": 686.04, "total_tokens": 4292384} {"current_steps": 15330, "total_steps": 40000, "loss": 0.0, "lr": 3.3967141570087544e-05, "epoch": 170.33333333333334, "percentage": 38.32, "elapsed_time": "1:44:18", "remaining_time": "2:47:51", "throughput": 686.04, "total_tokens": 4293760} {"current_steps": 15335, "total_steps": 40000, "loss": 0.0, "lr": 3.39579766724314e-05, "epoch": 170.38888888888889, "percentage": 38.34, "elapsed_time": "1:44:20", "remaining_time": "2:47:49", "throughput": 686.05, "total_tokens": 4295152} {"current_steps": 15340, "total_steps": 40000, "loss": 0.0, "lr": 3.3948810393342677e-05, "epoch": 170.44444444444446, "percentage": 38.35, "elapsed_time": "1:44:22", "remaining_time": "2:47:47", "throughput": 686.06, "total_tokens": 4296560} {"current_steps": 15345, "total_steps": 40000, "loss": 0.0, "lr": 3.3939642734234936e-05, "epoch": 170.5, "percentage": 38.36, "elapsed_time": "1:44:24", "remaining_time": "2:47:45", "throughput": 686.08, "total_tokens": 4297968} {"current_steps": 15350, "total_steps": 40000, "loss": 0.0, "lr": 3.393047369652194e-05, "epoch": 170.55555555555554, "percentage": 38.38, "elapsed_time": "1:44:26", "remaining_time": "2:47:43", "throughput": 686.09, "total_tokens": 4299376} {"current_steps": 15355, "total_steps": 40000, "loss": 0.0, "lr": 3.3921303281617664e-05, "epoch": 170.61111111111111, "percentage": 38.39, "elapsed_time": "1:44:28", "remaining_time": "2:47:40", "throughput": 686.11, "total_tokens": 4300832} {"current_steps": 15360, "total_steps": 40000, "loss": 0.0, "lr": 3.391213149093632e-05, "epoch": 170.66666666666666, "percentage": 38.4, "elapsed_time": "1:44:30", "remaining_time": "2:47:38", "throughput": 686.12, "total_tokens": 4302240} {"current_steps": 15365, "total_steps": 40000, "loss": 0.0, "lr": 3.3902958325892303e-05, "epoch": 170.72222222222223, "percentage": 38.41, "elapsed_time": "1:44:32", "remaining_time": "2:47:36", "throughput": 686.12, "total_tokens": 4303600} {"current_steps": 15370, "total_steps": 40000, "loss": 0.0, "lr": 3.389378378790023e-05, "epoch": 170.77777777777777, "percentage": 38.42, "elapsed_time": "1:44:34", "remaining_time": "2:47:34", "throughput": 686.14, "total_tokens": 4305040} {"current_steps": 15375, "total_steps": 40000, "loss": 0.0, "lr": 3.388460787837493e-05, "epoch": 170.83333333333334, "percentage": 38.44, "elapsed_time": "1:44:36", "remaining_time": "2:47:32", "throughput": 686.15, "total_tokens": 4306432} {"current_steps": 15380, "total_steps": 40000, "loss": 0.0, "lr": 3.387543059873145e-05, "epoch": 170.88888888888889, "percentage": 38.45, "elapsed_time": "1:44:38", "remaining_time": "2:47:30", "throughput": 686.16, "total_tokens": 4307840} {"current_steps": 15385, "total_steps": 40000, "loss": 0.0, "lr": 3.386625195038503e-05, "epoch": 170.94444444444446, "percentage": 38.46, "elapsed_time": "1:44:40", "remaining_time": "2:47:27", "throughput": 686.17, "total_tokens": 4309248} {"current_steps": 15390, "total_steps": 40000, "loss": 0.0, "lr": 3.3857071934751136e-05, "epoch": 171.0, "percentage": 38.48, "elapsed_time": "1:44:42", "remaining_time": "2:47:25", "throughput": 686.17, "total_tokens": 4310656} {"current_steps": 15395, "total_steps": 40000, "loss": 0.0, "lr": 3.384789055324544e-05, "epoch": 171.05555555555554, "percentage": 38.49, "elapsed_time": "1:44:44", "remaining_time": "2:47:24", "throughput": 686.15, "total_tokens": 4312048} {"current_steps": 15400, "total_steps": 40000, "loss": 0.0, "lr": 3.3838707807283843e-05, "epoch": 171.11111111111111, "percentage": 38.5, "elapsed_time": "1:44:46", "remaining_time": "2:47:21", "throughput": 686.15, "total_tokens": 4313408} {"current_steps": 15400, "total_steps": 40000, "eval_loss": 0.36459964513778687, "epoch": 171.11111111111111, "percentage": 38.5, "elapsed_time": "1:44:47", "remaining_time": "2:47:24", "throughput": 686.0, "total_tokens": 4313408} {"current_steps": 15405, "total_steps": 40000, "loss": 0.0, "lr": 3.382952369828243e-05, "epoch": 171.16666666666666, "percentage": 38.51, "elapsed_time": "1:44:51", "remaining_time": "2:47:24", "throughput": 685.87, "total_tokens": 4314832} {"current_steps": 15410, "total_steps": 40000, "loss": 0.0, "lr": 3.38203382276575e-05, "epoch": 171.22222222222223, "percentage": 38.52, "elapsed_time": "1:44:53", "remaining_time": "2:47:21", "throughput": 685.87, "total_tokens": 4316208} {"current_steps": 15415, "total_steps": 40000, "loss": 0.0, "lr": 3.381115139682557e-05, "epoch": 171.27777777777777, "percentage": 38.54, "elapsed_time": "1:44:54", "remaining_time": "2:47:19", "throughput": 685.88, "total_tokens": 4317584} {"current_steps": 15420, "total_steps": 40000, "loss": 0.0, "lr": 3.3801963207203366e-05, "epoch": 171.33333333333334, "percentage": 38.55, "elapsed_time": "1:44:56", "remaining_time": "2:47:17", "throughput": 685.88, "total_tokens": 4318944} {"current_steps": 15425, "total_steps": 40000, "loss": 0.0, "lr": 3.379277366020782e-05, "epoch": 171.38888888888889, "percentage": 38.56, "elapsed_time": "1:44:58", "remaining_time": "2:47:15", "throughput": 685.9, "total_tokens": 4320384} {"current_steps": 15430, "total_steps": 40000, "loss": 0.0, "lr": 3.3783582757256085e-05, "epoch": 171.44444444444446, "percentage": 38.57, "elapsed_time": "1:45:00", "remaining_time": "2:47:13", "throughput": 685.91, "total_tokens": 4321808} {"current_steps": 15435, "total_steps": 40000, "loss": 0.0, "lr": 3.3774390499765504e-05, "epoch": 171.5, "percentage": 38.59, "elapsed_time": "1:45:02", "remaining_time": "2:47:10", "throughput": 685.92, "total_tokens": 4323232} {"current_steps": 15440, "total_steps": 40000, "loss": 0.0, "lr": 3.376519688915364e-05, "epoch": 171.55555555555554, "percentage": 38.6, "elapsed_time": "1:45:04", "remaining_time": "2:47:08", "throughput": 685.94, "total_tokens": 4324656} {"current_steps": 15445, "total_steps": 40000, "loss": 0.0, "lr": 3.3756001926838273e-05, "epoch": 171.61111111111111, "percentage": 38.61, "elapsed_time": "1:45:06", "remaining_time": "2:47:06", "throughput": 685.95, "total_tokens": 4326064} {"current_steps": 15450, "total_steps": 40000, "loss": 0.0, "lr": 3.374680561423737e-05, "epoch": 171.66666666666666, "percentage": 38.62, "elapsed_time": "1:45:08", "remaining_time": "2:47:04", "throughput": 685.96, "total_tokens": 4327424} {"current_steps": 15455, "total_steps": 40000, "loss": 0.0, "lr": 3.373760795276912e-05, "epoch": 171.72222222222223, "percentage": 38.64, "elapsed_time": "1:45:10", "remaining_time": "2:47:02", "throughput": 685.97, "total_tokens": 4328832} {"current_steps": 15460, "total_steps": 40000, "loss": 0.0, "lr": 3.372840894385192e-05, "epoch": 171.77777777777777, "percentage": 38.65, "elapsed_time": "1:45:12", "remaining_time": "2:46:59", "throughput": 685.98, "total_tokens": 4330240} {"current_steps": 15465, "total_steps": 40000, "loss": 0.0, "lr": 3.3719208588904375e-05, "epoch": 171.83333333333334, "percentage": 38.66, "elapsed_time": "1:45:14", "remaining_time": "2:46:57", "throughput": 685.99, "total_tokens": 4331632} {"current_steps": 15470, "total_steps": 40000, "loss": 0.0, "lr": 3.371000688934529e-05, "epoch": 171.88888888888889, "percentage": 38.67, "elapsed_time": "1:45:16", "remaining_time": "2:46:55", "throughput": 685.99, "total_tokens": 4333024} {"current_steps": 15475, "total_steps": 40000, "loss": 0.0, "lr": 3.370080384659369e-05, "epoch": 171.94444444444446, "percentage": 38.69, "elapsed_time": "1:45:18", "remaining_time": "2:46:53", "throughput": 686.0, "total_tokens": 4334416} {"current_steps": 15480, "total_steps": 40000, "loss": 0.0, "lr": 3.36915994620688e-05, "epoch": 172.0, "percentage": 38.7, "elapsed_time": "1:45:20", "remaining_time": "2:46:51", "throughput": 685.99, "total_tokens": 4335808} {"current_steps": 15485, "total_steps": 40000, "loss": 0.0, "lr": 3.3682393737190035e-05, "epoch": 172.05555555555554, "percentage": 38.71, "elapsed_time": "1:45:22", "remaining_time": "2:46:49", "throughput": 685.98, "total_tokens": 4337264} {"current_steps": 15490, "total_steps": 40000, "loss": 0.0, "lr": 3.3673186673377054e-05, "epoch": 172.11111111111111, "percentage": 38.73, "elapsed_time": "1:45:24", "remaining_time": "2:46:47", "throughput": 686.0, "total_tokens": 4338688} {"current_steps": 15495, "total_steps": 40000, "loss": 0.0, "lr": 3.366397827204969e-05, "epoch": 172.16666666666666, "percentage": 38.74, "elapsed_time": "1:45:26", "remaining_time": "2:46:45", "throughput": 686.0, "total_tokens": 4340048} {"current_steps": 15500, "total_steps": 40000, "loss": 0.0, "lr": 3.3654768534628e-05, "epoch": 172.22222222222223, "percentage": 38.75, "elapsed_time": "1:45:28", "remaining_time": "2:46:43", "throughput": 686.02, "total_tokens": 4341472} {"current_steps": 15505, "total_steps": 40000, "loss": 0.0, "lr": 3.3645557462532245e-05, "epoch": 172.27777777777777, "percentage": 38.76, "elapsed_time": "1:45:30", "remaining_time": "2:46:40", "throughput": 686.04, "total_tokens": 4342944} {"current_steps": 15510, "total_steps": 40000, "loss": 0.0, "lr": 3.363634505718288e-05, "epoch": 172.33333333333334, "percentage": 38.77, "elapsed_time": "1:45:32", "remaining_time": "2:46:38", "throughput": 686.05, "total_tokens": 4344336} {"current_steps": 15515, "total_steps": 40000, "loss": 0.0, "lr": 3.362713132000057e-05, "epoch": 172.38888888888889, "percentage": 38.79, "elapsed_time": "1:45:34", "remaining_time": "2:46:36", "throughput": 686.06, "total_tokens": 4345744} {"current_steps": 15520, "total_steps": 40000, "loss": 0.0, "lr": 3.36179162524062e-05, "epoch": 172.44444444444446, "percentage": 38.8, "elapsed_time": "1:45:36", "remaining_time": "2:46:34", "throughput": 686.07, "total_tokens": 4347136} {"current_steps": 15525, "total_steps": 40000, "loss": 0.0, "lr": 3.3608699855820846e-05, "epoch": 172.5, "percentage": 38.81, "elapsed_time": "1:45:38", "remaining_time": "2:46:32", "throughput": 686.08, "total_tokens": 4348544} {"current_steps": 15530, "total_steps": 40000, "loss": 0.0, "lr": 3.359948213166578e-05, "epoch": 172.55555555555554, "percentage": 38.82, "elapsed_time": "1:45:40", "remaining_time": "2:46:29", "throughput": 686.09, "total_tokens": 4349920} {"current_steps": 15535, "total_steps": 40000, "loss": 0.0, "lr": 3.359026308136252e-05, "epoch": 172.61111111111111, "percentage": 38.84, "elapsed_time": "1:45:42", "remaining_time": "2:46:27", "throughput": 686.09, "total_tokens": 4351312} {"current_steps": 15540, "total_steps": 40000, "loss": 0.0, "lr": 3.358104270633272e-05, "epoch": 172.66666666666666, "percentage": 38.85, "elapsed_time": "1:45:44", "remaining_time": "2:46:25", "throughput": 686.1, "total_tokens": 4352704} {"current_steps": 15545, "total_steps": 40000, "loss": 0.0, "lr": 3.357182100799831e-05, "epoch": 172.72222222222223, "percentage": 38.86, "elapsed_time": "1:45:46", "remaining_time": "2:46:23", "throughput": 686.11, "total_tokens": 4354096} {"current_steps": 15550, "total_steps": 40000, "loss": 0.0, "lr": 3.3562597987781384e-05, "epoch": 172.77777777777777, "percentage": 38.88, "elapsed_time": "1:45:48", "remaining_time": "2:46:21", "throughput": 686.12, "total_tokens": 4355504} {"current_steps": 15555, "total_steps": 40000, "loss": 0.0, "lr": 3.355337364710424e-05, "epoch": 172.83333333333334, "percentage": 38.89, "elapsed_time": "1:45:49", "remaining_time": "2:46:19", "throughput": 686.12, "total_tokens": 4356816} {"current_steps": 15560, "total_steps": 40000, "loss": 0.0, "lr": 3.354414798738939e-05, "epoch": 172.88888888888889, "percentage": 38.9, "elapsed_time": "1:45:51", "remaining_time": "2:46:16", "throughput": 686.12, "total_tokens": 4358192} {"current_steps": 15565, "total_steps": 40000, "loss": 0.0, "lr": 3.353492101005955e-05, "epoch": 172.94444444444446, "percentage": 38.91, "elapsed_time": "1:45:53", "remaining_time": "2:46:14", "throughput": 686.14, "total_tokens": 4359648} {"current_steps": 15570, "total_steps": 40000, "loss": 0.0, "lr": 3.352569271653763e-05, "epoch": 173.0, "percentage": 38.92, "elapsed_time": "1:45:55", "remaining_time": "2:46:12", "throughput": 686.13, "total_tokens": 4361024} {"current_steps": 15575, "total_steps": 40000, "loss": 0.0, "lr": 3.351646310824675e-05, "epoch": 173.05555555555554, "percentage": 38.94, "elapsed_time": "1:45:58", "remaining_time": "2:46:10", "throughput": 686.12, "total_tokens": 4362464} {"current_steps": 15580, "total_steps": 40000, "loss": 0.0, "lr": 3.350723218661023e-05, "epoch": 173.11111111111111, "percentage": 38.95, "elapsed_time": "1:46:00", "remaining_time": "2:46:08", "throughput": 686.13, "total_tokens": 4363872} {"current_steps": 15585, "total_steps": 40000, "loss": 0.0, "lr": 3.349799995305162e-05, "epoch": 173.16666666666666, "percentage": 38.96, "elapsed_time": "1:46:02", "remaining_time": "2:46:06", "throughput": 686.14, "total_tokens": 4365264} {"current_steps": 15590, "total_steps": 40000, "loss": 0.0, "lr": 3.348876640899461e-05, "epoch": 173.22222222222223, "percentage": 38.98, "elapsed_time": "1:46:04", "remaining_time": "2:46:04", "throughput": 686.15, "total_tokens": 4366640} {"current_steps": 15595, "total_steps": 40000, "loss": 0.0, "lr": 3.3479531555863144e-05, "epoch": 173.27777777777777, "percentage": 38.99, "elapsed_time": "1:46:05", "remaining_time": "2:46:02", "throughput": 686.16, "total_tokens": 4368080} {"current_steps": 15600, "total_steps": 40000, "loss": 0.0, "lr": 3.3470295395081344e-05, "epoch": 173.33333333333334, "percentage": 39.0, "elapsed_time": "1:46:07", "remaining_time": "2:46:00", "throughput": 686.17, "total_tokens": 4369488} {"current_steps": 15600, "total_steps": 40000, "eval_loss": 0.3906360864639282, "epoch": 173.33333333333334, "percentage": 39.0, "elapsed_time": "1:46:09", "remaining_time": "2:46:02", "throughput": 686.03, "total_tokens": 4369488} {"current_steps": 15605, "total_steps": 40000, "loss": 0.0, "lr": 3.3461057928073556e-05, "epoch": 173.38888888888889, "percentage": 39.01, "elapsed_time": "1:46:12", "remaining_time": "2:46:02", "throughput": 685.88, "total_tokens": 4370896} {"current_steps": 15610, "total_steps": 40000, "loss": 0.0, "lr": 3.345181915626431e-05, "epoch": 173.44444444444446, "percentage": 39.02, "elapsed_time": "1:46:14", "remaining_time": "2:46:00", "throughput": 685.88, "total_tokens": 4372272} {"current_steps": 15615, "total_steps": 40000, "loss": 0.0, "lr": 3.344257908107834e-05, "epoch": 173.5, "percentage": 39.04, "elapsed_time": "1:46:16", "remaining_time": "2:45:58", "throughput": 685.89, "total_tokens": 4373696} {"current_steps": 15620, "total_steps": 40000, "loss": 0.0, "lr": 3.343333770394058e-05, "epoch": 173.55555555555554, "percentage": 39.05, "elapsed_time": "1:46:18", "remaining_time": "2:45:55", "throughput": 685.9, "total_tokens": 4375088} {"current_steps": 15625, "total_steps": 40000, "loss": 0.0, "lr": 3.342409502627616e-05, "epoch": 173.61111111111111, "percentage": 39.06, "elapsed_time": "1:46:20", "remaining_time": "2:45:53", "throughput": 685.92, "total_tokens": 4376512} {"current_steps": 15630, "total_steps": 40000, "loss": 0.0, "lr": 3.341485104951043e-05, "epoch": 173.66666666666666, "percentage": 39.07, "elapsed_time": "1:46:22", "remaining_time": "2:45:51", "throughput": 685.92, "total_tokens": 4377920} {"current_steps": 15635, "total_steps": 40000, "loss": 0.0, "lr": 3.340560577506892e-05, "epoch": 173.72222222222223, "percentage": 39.09, "elapsed_time": "1:46:24", "remaining_time": "2:45:49", "throughput": 685.93, "total_tokens": 4379296} {"current_steps": 15640, "total_steps": 40000, "loss": 0.0, "lr": 3.339635920437735e-05, "epoch": 173.77777777777777, "percentage": 39.1, "elapsed_time": "1:46:26", "remaining_time": "2:45:47", "throughput": 685.94, "total_tokens": 4380672} {"current_steps": 15645, "total_steps": 40000, "loss": 0.0, "lr": 3.338711133886169e-05, "epoch": 173.83333333333334, "percentage": 39.11, "elapsed_time": "1:46:28", "remaining_time": "2:45:44", "throughput": 685.94, "total_tokens": 4382048} {"current_steps": 15650, "total_steps": 40000, "loss": 0.0, "lr": 3.3377862179948064e-05, "epoch": 173.88888888888889, "percentage": 39.12, "elapsed_time": "1:46:30", "remaining_time": "2:45:42", "throughput": 685.95, "total_tokens": 4383440} {"current_steps": 15655, "total_steps": 40000, "loss": 0.0, "lr": 3.336861172906281e-05, "epoch": 173.94444444444446, "percentage": 39.14, "elapsed_time": "1:46:32", "remaining_time": "2:45:40", "throughput": 685.96, "total_tokens": 4384848} {"current_steps": 15660, "total_steps": 40000, "loss": 0.0, "lr": 3.335935998763245e-05, "epoch": 174.0, "percentage": 39.15, "elapsed_time": "1:46:34", "remaining_time": "2:45:38", "throughput": 685.95, "total_tokens": 4386256} {"current_steps": 15665, "total_steps": 40000, "loss": 0.0, "lr": 3.3350106957083744e-05, "epoch": 174.05555555555554, "percentage": 39.16, "elapsed_time": "1:46:36", "remaining_time": "2:45:36", "throughput": 685.93, "total_tokens": 4387600} {"current_steps": 15670, "total_steps": 40000, "loss": 0.0, "lr": 3.33408526388436e-05, "epoch": 174.11111111111111, "percentage": 39.17, "elapsed_time": "1:46:38", "remaining_time": "2:45:34", "throughput": 685.93, "total_tokens": 4388992} {"current_steps": 15675, "total_steps": 40000, "loss": 0.0, "lr": 3.3331597034339166e-05, "epoch": 174.16666666666666, "percentage": 39.19, "elapsed_time": "1:46:40", "remaining_time": "2:45:32", "throughput": 685.95, "total_tokens": 4390416} {"current_steps": 15680, "total_steps": 40000, "loss": 0.0, "lr": 3.3322340144997764e-05, "epoch": 174.22222222222223, "percentage": 39.2, "elapsed_time": "1:46:42", "remaining_time": "2:45:30", "throughput": 685.95, "total_tokens": 4391808} {"current_steps": 15685, "total_steps": 40000, "loss": 0.0, "lr": 3.331308197224693e-05, "epoch": 174.27777777777777, "percentage": 39.21, "elapsed_time": "1:46:44", "remaining_time": "2:45:28", "throughput": 685.96, "total_tokens": 4393200} {"current_steps": 15690, "total_steps": 40000, "loss": 0.0, "lr": 3.330382251751438e-05, "epoch": 174.33333333333334, "percentage": 39.23, "elapsed_time": "1:46:46", "remaining_time": "2:45:26", "throughput": 685.97, "total_tokens": 4394608} {"current_steps": 15695, "total_steps": 40000, "loss": 0.0, "lr": 3.3294561782228054e-05, "epoch": 174.38888888888889, "percentage": 39.24, "elapsed_time": "1:46:48", "remaining_time": "2:45:23", "throughput": 685.98, "total_tokens": 4395952} {"current_steps": 15700, "total_steps": 40000, "loss": 0.0, "lr": 3.328529976781607e-05, "epoch": 174.44444444444446, "percentage": 39.25, "elapsed_time": "1:46:50", "remaining_time": "2:45:21", "throughput": 685.99, "total_tokens": 4397360} {"current_steps": 15705, "total_steps": 40000, "loss": 0.0, "lr": 3.327603647570673e-05, "epoch": 174.5, "percentage": 39.26, "elapsed_time": "1:46:52", "remaining_time": "2:45:19", "throughput": 686.01, "total_tokens": 4398816} {"current_steps": 15710, "total_steps": 40000, "loss": 0.0, "lr": 3.326677190732857e-05, "epoch": 174.55555555555554, "percentage": 39.27, "elapsed_time": "1:46:54", "remaining_time": "2:45:17", "throughput": 686.01, "total_tokens": 4400208} {"current_steps": 15715, "total_steps": 40000, "loss": 0.0, "lr": 3.325750606411029e-05, "epoch": 174.61111111111111, "percentage": 39.29, "elapsed_time": "1:46:56", "remaining_time": "2:45:15", "throughput": 686.03, "total_tokens": 4401616} {"current_steps": 15720, "total_steps": 40000, "loss": 0.0, "lr": 3.3248238947480804e-05, "epoch": 174.66666666666666, "percentage": 39.3, "elapsed_time": "1:46:58", "remaining_time": "2:45:12", "throughput": 686.04, "total_tokens": 4403008} {"current_steps": 15725, "total_steps": 40000, "loss": 0.0, "lr": 3.323897055886922e-05, "epoch": 174.72222222222223, "percentage": 39.31, "elapsed_time": "1:47:00", "remaining_time": "2:45:10", "throughput": 686.05, "total_tokens": 4404432} {"current_steps": 15730, "total_steps": 40000, "loss": 0.0, "lr": 3.322970089970484e-05, "epoch": 174.77777777777777, "percentage": 39.32, "elapsed_time": "1:47:01", "remaining_time": "2:45:08", "throughput": 686.06, "total_tokens": 4405840} {"current_steps": 15735, "total_steps": 40000, "loss": 0.0, "lr": 3.3220429971417165e-05, "epoch": 174.83333333333334, "percentage": 39.34, "elapsed_time": "1:47:03", "remaining_time": "2:45:06", "throughput": 686.08, "total_tokens": 4407280} {"current_steps": 15740, "total_steps": 40000, "loss": 0.0, "lr": 3.321115777543588e-05, "epoch": 174.88888888888889, "percentage": 39.35, "elapsed_time": "1:47:05", "remaining_time": "2:45:04", "throughput": 686.08, "total_tokens": 4408672} {"current_steps": 15745, "total_steps": 40000, "loss": 0.0, "lr": 3.320188431319088e-05, "epoch": 174.94444444444446, "percentage": 39.36, "elapsed_time": "1:47:07", "remaining_time": "2:45:01", "throughput": 686.11, "total_tokens": 4410144} {"current_steps": 15750, "total_steps": 40000, "loss": 0.0, "lr": 3.319260958611224e-05, "epoch": 175.0, "percentage": 39.38, "elapsed_time": "1:47:09", "remaining_time": "2:44:59", "throughput": 686.09, "total_tokens": 4411504} {"current_steps": 15755, "total_steps": 40000, "loss": 0.0, "lr": 3.3183333595630256e-05, "epoch": 175.05555555555554, "percentage": 39.39, "elapsed_time": "1:47:12", "remaining_time": "2:44:58", "throughput": 686.08, "total_tokens": 4412928} {"current_steps": 15760, "total_steps": 40000, "loss": 0.0, "lr": 3.317405634317538e-05, "epoch": 175.11111111111111, "percentage": 39.4, "elapsed_time": "1:47:14", "remaining_time": "2:44:56", "throughput": 686.09, "total_tokens": 4414352} {"current_steps": 15765, "total_steps": 40000, "loss": 0.0, "lr": 3.3164777830178315e-05, "epoch": 175.16666666666666, "percentage": 39.41, "elapsed_time": "1:47:16", "remaining_time": "2:44:53", "throughput": 686.09, "total_tokens": 4415712} {"current_steps": 15770, "total_steps": 40000, "loss": 0.0, "lr": 3.315549805806989e-05, "epoch": 175.22222222222223, "percentage": 39.42, "elapsed_time": "1:47:17", "remaining_time": "2:44:51", "throughput": 686.1, "total_tokens": 4417072} {"current_steps": 15775, "total_steps": 40000, "loss": 0.0, "lr": 3.314621702828118e-05, "epoch": 175.27777777777777, "percentage": 39.44, "elapsed_time": "1:47:19", "remaining_time": "2:44:49", "throughput": 686.11, "total_tokens": 4418512} {"current_steps": 15780, "total_steps": 40000, "loss": 0.0, "lr": 3.313693474224342e-05, "epoch": 175.33333333333334, "percentage": 39.45, "elapsed_time": "1:47:21", "remaining_time": "2:44:47", "throughput": 686.12, "total_tokens": 4419888} {"current_steps": 15785, "total_steps": 40000, "loss": 0.0, "lr": 3.312765120138809e-05, "epoch": 175.38888888888889, "percentage": 39.46, "elapsed_time": "1:47:23", "remaining_time": "2:44:45", "throughput": 686.13, "total_tokens": 4421296} {"current_steps": 15790, "total_steps": 40000, "loss": 0.0, "lr": 3.311836640714679e-05, "epoch": 175.44444444444446, "percentage": 39.48, "elapsed_time": "1:47:25", "remaining_time": "2:44:42", "throughput": 686.15, "total_tokens": 4422736} {"current_steps": 15795, "total_steps": 40000, "loss": 0.0, "lr": 3.310908036095137e-05, "epoch": 175.5, "percentage": 39.49, "elapsed_time": "1:47:27", "remaining_time": "2:44:40", "throughput": 686.16, "total_tokens": 4424144} {"current_steps": 15800, "total_steps": 40000, "loss": 0.0, "lr": 3.309979306423386e-05, "epoch": 175.55555555555554, "percentage": 39.5, "elapsed_time": "1:47:29", "remaining_time": "2:44:38", "throughput": 686.17, "total_tokens": 4425536} {"current_steps": 15800, "total_steps": 40000, "eval_loss": 0.36695390939712524, "epoch": 175.55555555555554, "percentage": 39.5, "elapsed_time": "1:47:30", "remaining_time": "2:44:40", "throughput": 686.03, "total_tokens": 4425536} {"current_steps": 15805, "total_steps": 40000, "loss": 0.0, "lr": 3.309050451842647e-05, "epoch": 175.61111111111111, "percentage": 39.51, "elapsed_time": "1:47:34", "remaining_time": "2:44:40", "throughput": 685.91, "total_tokens": 4426992} {"current_steps": 15810, "total_steps": 40000, "loss": 0.0, "lr": 3.3081214724961604e-05, "epoch": 175.66666666666666, "percentage": 39.52, "elapsed_time": "1:47:36", "remaining_time": "2:44:38", "throughput": 685.91, "total_tokens": 4428384} {"current_steps": 15815, "total_steps": 40000, "loss": 0.0, "lr": 3.307192368527188e-05, "epoch": 175.72222222222223, "percentage": 39.54, "elapsed_time": "1:47:38", "remaining_time": "2:44:36", "throughput": 685.92, "total_tokens": 4429760} {"current_steps": 15820, "total_steps": 40000, "loss": 0.0, "lr": 3.306263140079008e-05, "epoch": 175.77777777777777, "percentage": 39.55, "elapsed_time": "1:47:40", "remaining_time": "2:44:33", "throughput": 685.93, "total_tokens": 4431152} {"current_steps": 15825, "total_steps": 40000, "loss": 0.0, "lr": 3.30533378729492e-05, "epoch": 175.83333333333334, "percentage": 39.56, "elapsed_time": "1:47:42", "remaining_time": "2:44:31", "throughput": 685.94, "total_tokens": 4432544} {"current_steps": 15830, "total_steps": 40000, "loss": 0.0, "lr": 3.304404310318242e-05, "epoch": 175.88888888888889, "percentage": 39.57, "elapsed_time": "1:47:43", "remaining_time": "2:44:29", "throughput": 685.95, "total_tokens": 4433968} {"current_steps": 15835, "total_steps": 40000, "loss": 0.0, "lr": 3.3034747092923105e-05, "epoch": 175.94444444444446, "percentage": 39.59, "elapsed_time": "1:47:45", "remaining_time": "2:44:27", "throughput": 685.96, "total_tokens": 4435344} {"current_steps": 15840, "total_steps": 40000, "loss": 0.0, "lr": 3.3025449843604806e-05, "epoch": 176.0, "percentage": 39.6, "elapsed_time": "1:47:48", "remaining_time": "2:44:25", "throughput": 685.95, "total_tokens": 4436752} {"current_steps": 15845, "total_steps": 40000, "loss": 0.0, "lr": 3.30161513566613e-05, "epoch": 176.05555555555554, "percentage": 39.61, "elapsed_time": "1:47:50", "remaining_time": "2:44:23", "throughput": 685.94, "total_tokens": 4438176} {"current_steps": 15850, "total_steps": 40000, "loss": 0.0, "lr": 3.3006851633526506e-05, "epoch": 176.11111111111111, "percentage": 39.62, "elapsed_time": "1:47:52", "remaining_time": "2:44:21", "throughput": 685.94, "total_tokens": 4439552} {"current_steps": 15855, "total_steps": 40000, "loss": 0.0, "lr": 3.2997550675634584e-05, "epoch": 176.16666666666666, "percentage": 39.64, "elapsed_time": "1:47:54", "remaining_time": "2:44:19", "throughput": 685.95, "total_tokens": 4440944} {"current_steps": 15860, "total_steps": 40000, "loss": 0.0, "lr": 3.2988248484419825e-05, "epoch": 176.22222222222223, "percentage": 39.65, "elapsed_time": "1:47:56", "remaining_time": "2:44:17", "throughput": 685.96, "total_tokens": 4442352} {"current_steps": 15865, "total_steps": 40000, "loss": 0.0, "lr": 3.2978945061316776e-05, "epoch": 176.27777777777777, "percentage": 39.66, "elapsed_time": "1:47:58", "remaining_time": "2:44:14", "throughput": 685.97, "total_tokens": 4443744} {"current_steps": 15870, "total_steps": 40000, "loss": 0.0, "lr": 3.296964040776013e-05, "epoch": 176.33333333333334, "percentage": 39.67, "elapsed_time": "1:48:00", "remaining_time": "2:44:13", "throughput": 685.95, "total_tokens": 4445200} {"current_steps": 15875, "total_steps": 40000, "loss": 0.0, "lr": 3.296033452518478e-05, "epoch": 176.38888888888889, "percentage": 39.69, "elapsed_time": "1:48:02", "remaining_time": "2:44:11", "throughput": 685.96, "total_tokens": 4446608} {"current_steps": 15880, "total_steps": 40000, "loss": 0.0, "lr": 3.2951027415025806e-05, "epoch": 176.44444444444446, "percentage": 39.7, "elapsed_time": "1:48:04", "remaining_time": "2:44:08", "throughput": 685.98, "total_tokens": 4448032} {"current_steps": 15885, "total_steps": 40000, "loss": 0.0, "lr": 3.294171907871849e-05, "epoch": 176.5, "percentage": 39.71, "elapsed_time": "1:48:06", "remaining_time": "2:44:06", "throughput": 686.0, "total_tokens": 4449472} {"current_steps": 15890, "total_steps": 40000, "loss": 0.0, "lr": 3.293240951769828e-05, "epoch": 176.55555555555554, "percentage": 39.73, "elapsed_time": "1:48:08", "remaining_time": "2:44:04", "throughput": 686.0, "total_tokens": 4450864} {"current_steps": 15895, "total_steps": 40000, "loss": 0.0, "lr": 3.2923098733400846e-05, "epoch": 176.61111111111111, "percentage": 39.74, "elapsed_time": "1:48:10", "remaining_time": "2:44:02", "throughput": 686.02, "total_tokens": 4452272} {"current_steps": 15900, "total_steps": 40000, "loss": 0.0, "lr": 3.291378672726202e-05, "epoch": 176.66666666666666, "percentage": 39.75, "elapsed_time": "1:48:11", "remaining_time": "2:44:00", "throughput": 686.04, "total_tokens": 4453728} {"current_steps": 15905, "total_steps": 40000, "loss": 0.0, "lr": 3.2904473500717824e-05, "epoch": 176.72222222222223, "percentage": 39.76, "elapsed_time": "1:48:13", "remaining_time": "2:43:57", "throughput": 686.05, "total_tokens": 4455120} {"current_steps": 15910, "total_steps": 40000, "loss": 0.0, "lr": 3.289515905520449e-05, "epoch": 176.77777777777777, "percentage": 39.77, "elapsed_time": "1:48:15", "remaining_time": "2:43:55", "throughput": 686.05, "total_tokens": 4456512} {"current_steps": 15915, "total_steps": 40000, "loss": 0.0, "lr": 3.288584339215841e-05, "epoch": 176.83333333333334, "percentage": 39.79, "elapsed_time": "1:48:17", "remaining_time": "2:43:53", "throughput": 686.05, "total_tokens": 4457840} {"current_steps": 15920, "total_steps": 40000, "loss": 0.0, "lr": 3.287652651301617e-05, "epoch": 176.88888888888889, "percentage": 39.8, "elapsed_time": "1:48:19", "remaining_time": "2:43:51", "throughput": 686.06, "total_tokens": 4459216} {"current_steps": 15925, "total_steps": 40000, "loss": 0.0, "lr": 3.286720841921457e-05, "epoch": 176.94444444444446, "percentage": 39.81, "elapsed_time": "1:48:21", "remaining_time": "2:43:49", "throughput": 686.06, "total_tokens": 4460576} {"current_steps": 15930, "total_steps": 40000, "loss": 0.0, "lr": 3.285788911219056e-05, "epoch": 177.0, "percentage": 39.83, "elapsed_time": "1:48:23", "remaining_time": "2:43:47", "throughput": 686.06, "total_tokens": 4462000} {"current_steps": 15935, "total_steps": 40000, "loss": 0.0, "lr": 3.284856859338131e-05, "epoch": 177.05555555555554, "percentage": 39.84, "elapsed_time": "1:48:26", "remaining_time": "2:43:45", "throughput": 686.04, "total_tokens": 4463392} {"current_steps": 15940, "total_steps": 40000, "loss": 0.0, "lr": 3.283924686422414e-05, "epoch": 177.11111111111111, "percentage": 39.85, "elapsed_time": "1:48:27", "remaining_time": "2:43:43", "throughput": 686.05, "total_tokens": 4464784} {"current_steps": 15945, "total_steps": 40000, "loss": 0.0, "lr": 3.282992392615659e-05, "epoch": 177.16666666666666, "percentage": 39.86, "elapsed_time": "1:48:29", "remaining_time": "2:43:41", "throughput": 686.06, "total_tokens": 4466160} {"current_steps": 15950, "total_steps": 40000, "loss": 0.0, "lr": 3.282059978061638e-05, "epoch": 177.22222222222223, "percentage": 39.88, "elapsed_time": "1:48:31", "remaining_time": "2:43:38", "throughput": 686.06, "total_tokens": 4467568} {"current_steps": 15955, "total_steps": 40000, "loss": 0.0, "lr": 3.28112744290414e-05, "epoch": 177.27777777777777, "percentage": 39.89, "elapsed_time": "1:48:33", "remaining_time": "2:43:36", "throughput": 686.07, "total_tokens": 4468944} {"current_steps": 15960, "total_steps": 40000, "loss": 0.0, "lr": 3.280194787286974e-05, "epoch": 177.33333333333334, "percentage": 39.9, "elapsed_time": "1:48:35", "remaining_time": "2:43:34", "throughput": 686.09, "total_tokens": 4470400} {"current_steps": 15965, "total_steps": 40000, "loss": 0.0, "lr": 3.2792620113539674e-05, "epoch": 177.38888888888889, "percentage": 39.91, "elapsed_time": "1:48:37", "remaining_time": "2:43:32", "throughput": 686.1, "total_tokens": 4471824} {"current_steps": 15970, "total_steps": 40000, "loss": 0.0, "lr": 3.278329115248966e-05, "epoch": 177.44444444444446, "percentage": 39.92, "elapsed_time": "1:48:39", "remaining_time": "2:43:30", "throughput": 686.11, "total_tokens": 4473216} {"current_steps": 15975, "total_steps": 40000, "loss": 0.0, "lr": 3.277396099115834e-05, "epoch": 177.5, "percentage": 39.94, "elapsed_time": "1:48:41", "remaining_time": "2:43:27", "throughput": 686.12, "total_tokens": 4474592} {"current_steps": 15980, "total_steps": 40000, "loss": 0.0, "lr": 3.276462963098454e-05, "epoch": 177.55555555555554, "percentage": 39.95, "elapsed_time": "1:48:43", "remaining_time": "2:43:25", "throughput": 686.13, "total_tokens": 4476016} {"current_steps": 15985, "total_steps": 40000, "loss": 0.0, "lr": 3.275529707340728e-05, "epoch": 177.61111111111111, "percentage": 39.96, "elapsed_time": "1:48:45", "remaining_time": "2:43:23", "throughput": 686.14, "total_tokens": 4477408} {"current_steps": 15990, "total_steps": 40000, "loss": 0.0, "lr": 3.274596331986574e-05, "epoch": 177.66666666666666, "percentage": 39.98, "elapsed_time": "1:48:47", "remaining_time": "2:43:21", "throughput": 686.14, "total_tokens": 4478752} {"current_steps": 15995, "total_steps": 40000, "loss": 0.0, "lr": 3.273662837179932e-05, "epoch": 177.72222222222223, "percentage": 39.99, "elapsed_time": "1:48:49", "remaining_time": "2:43:19", "throughput": 686.16, "total_tokens": 4480160} {"current_steps": 16000, "total_steps": 40000, "loss": 0.0, "lr": 3.272729223064758e-05, "epoch": 177.77777777777777, "percentage": 40.0, "elapsed_time": "1:48:51", "remaining_time": "2:43:16", "throughput": 686.17, "total_tokens": 4481568} {"current_steps": 16000, "total_steps": 40000, "eval_loss": 0.34323424100875854, "epoch": 177.77777777777777, "percentage": 40.0, "elapsed_time": "1:48:52", "remaining_time": "2:43:18", "throughput": 686.03, "total_tokens": 4481568} {"current_steps": 16005, "total_steps": 40000, "loss": 0.0, "lr": 3.2717954897850264e-05, "epoch": 177.83333333333334, "percentage": 40.01, "elapsed_time": "1:48:55", "remaining_time": "2:43:18", "throughput": 685.89, "total_tokens": 4482960} {"current_steps": 16010, "total_steps": 40000, "loss": 0.0, "lr": 3.270861637484733e-05, "epoch": 177.88888888888889, "percentage": 40.02, "elapsed_time": "1:48:57", "remaining_time": "2:43:16", "throughput": 685.89, "total_tokens": 4484352} {"current_steps": 16015, "total_steps": 40000, "loss": 0.0, "lr": 3.2699276663078867e-05, "epoch": 177.94444444444446, "percentage": 40.04, "elapsed_time": "1:48:59", "remaining_time": "2:43:14", "throughput": 685.91, "total_tokens": 4485776} {"current_steps": 16020, "total_steps": 40000, "loss": 0.0, "lr": 3.268993576398519e-05, "epoch": 178.0, "percentage": 40.05, "elapsed_time": "1:49:02", "remaining_time": "2:43:12", "throughput": 685.9, "total_tokens": 4487184} {"current_steps": 16025, "total_steps": 40000, "loss": 0.0, "lr": 3.268059367900678e-05, "epoch": 178.05555555555554, "percentage": 40.06, "elapsed_time": "1:49:04", "remaining_time": "2:43:10", "throughput": 685.89, "total_tokens": 4488608} {"current_steps": 16030, "total_steps": 40000, "loss": 0.0, "lr": 3.26712504095843e-05, "epoch": 178.11111111111111, "percentage": 40.08, "elapsed_time": "1:49:06", "remaining_time": "2:43:08", "throughput": 685.9, "total_tokens": 4490032} {"current_steps": 16035, "total_steps": 40000, "loss": 0.0, "lr": 3.2661905957158615e-05, "epoch": 178.16666666666666, "percentage": 40.09, "elapsed_time": "1:49:08", "remaining_time": "2:43:06", "throughput": 685.92, "total_tokens": 4491472} {"current_steps": 16040, "total_steps": 40000, "loss": 0.0, "lr": 3.2652560323170734e-05, "epoch": 178.22222222222223, "percentage": 40.1, "elapsed_time": "1:49:10", "remaining_time": "2:43:04", "throughput": 685.93, "total_tokens": 4492880} {"current_steps": 16045, "total_steps": 40000, "loss": 0.0, "lr": 3.264321350906189e-05, "epoch": 178.27777777777777, "percentage": 40.11, "elapsed_time": "1:49:12", "remaining_time": "2:43:02", "throughput": 685.94, "total_tokens": 4494272} {"current_steps": 16050, "total_steps": 40000, "loss": 0.0, "lr": 3.263386551627346e-05, "epoch": 178.33333333333334, "percentage": 40.12, "elapsed_time": "1:49:13", "remaining_time": "2:42:59", "throughput": 685.94, "total_tokens": 4495632} {"current_steps": 16055, "total_steps": 40000, "loss": 0.0, "lr": 3.2624516346247055e-05, "epoch": 178.38888888888889, "percentage": 40.14, "elapsed_time": "1:49:15", "remaining_time": "2:42:57", "throughput": 685.95, "total_tokens": 4497040} {"current_steps": 16060, "total_steps": 40000, "loss": 0.0, "lr": 3.2615166000424404e-05, "epoch": 178.44444444444446, "percentage": 40.15, "elapsed_time": "1:49:17", "remaining_time": "2:42:55", "throughput": 685.96, "total_tokens": 4498448} {"current_steps": 16065, "total_steps": 40000, "loss": 0.0, "lr": 3.260581448024745e-05, "epoch": 178.5, "percentage": 40.16, "elapsed_time": "1:49:19", "remaining_time": "2:42:53", "throughput": 685.97, "total_tokens": 4499888} {"current_steps": 16070, "total_steps": 40000, "loss": 0.0, "lr": 3.2596461787158335e-05, "epoch": 178.55555555555554, "percentage": 40.17, "elapsed_time": "1:49:21", "remaining_time": "2:42:51", "throughput": 685.99, "total_tokens": 4501296} {"current_steps": 16075, "total_steps": 40000, "loss": 0.0, "lr": 3.258710792259934e-05, "epoch": 178.61111111111111, "percentage": 40.19, "elapsed_time": "1:49:23", "remaining_time": "2:42:49", "throughput": 685.99, "total_tokens": 4502672} {"current_steps": 16080, "total_steps": 40000, "loss": 0.0, "lr": 3.257775288801296e-05, "epoch": 178.66666666666666, "percentage": 40.2, "elapsed_time": "1:49:25", "remaining_time": "2:42:46", "throughput": 686.0, "total_tokens": 4504032} {"current_steps": 16085, "total_steps": 40000, "loss": 0.0, "lr": 3.256839668484186e-05, "epoch": 178.72222222222223, "percentage": 40.21, "elapsed_time": "1:49:27", "remaining_time": "2:42:44", "throughput": 686.01, "total_tokens": 4505424} {"current_steps": 16090, "total_steps": 40000, "loss": 0.0, "lr": 3.255903931452888e-05, "epoch": 178.77777777777777, "percentage": 40.23, "elapsed_time": "1:49:29", "remaining_time": "2:42:42", "throughput": 686.01, "total_tokens": 4506800} {"current_steps": 16095, "total_steps": 40000, "loss": 0.0, "lr": 3.2549680778517045e-05, "epoch": 178.83333333333334, "percentage": 40.24, "elapsed_time": "1:49:31", "remaining_time": "2:42:40", "throughput": 686.01, "total_tokens": 4508144} {"current_steps": 16100, "total_steps": 40000, "loss": 0.0, "lr": 3.2540321078249556e-05, "epoch": 178.88888888888889, "percentage": 40.25, "elapsed_time": "1:49:33", "remaining_time": "2:42:38", "throughput": 686.03, "total_tokens": 4509584} {"current_steps": 16105, "total_steps": 40000, "loss": 0.0, "lr": 3.2530960215169795e-05, "epoch": 178.94444444444446, "percentage": 40.26, "elapsed_time": "1:49:35", "remaining_time": "2:42:35", "throughput": 686.04, "total_tokens": 4510976} {"current_steps": 16110, "total_steps": 40000, "loss": 0.0, "lr": 3.2521598190721345e-05, "epoch": 179.0, "percentage": 40.27, "elapsed_time": "1:49:37", "remaining_time": "2:42:34", "throughput": 686.03, "total_tokens": 4512384} {"current_steps": 16115, "total_steps": 40000, "loss": 0.0, "lr": 3.251223500634792e-05, "epoch": 179.05555555555554, "percentage": 40.29, "elapsed_time": "1:49:39", "remaining_time": "2:42:32", "throughput": 686.01, "total_tokens": 4513744} {"current_steps": 16120, "total_steps": 40000, "loss": 0.0, "lr": 3.2502870663493445e-05, "epoch": 179.11111111111111, "percentage": 40.3, "elapsed_time": "1:49:41", "remaining_time": "2:42:30", "throughput": 686.02, "total_tokens": 4515152} {"current_steps": 16125, "total_steps": 40000, "loss": 0.0, "lr": 3.249350516360203e-05, "epoch": 179.16666666666666, "percentage": 40.31, "elapsed_time": "1:49:43", "remaining_time": "2:42:27", "throughput": 686.03, "total_tokens": 4516544} {"current_steps": 16130, "total_steps": 40000, "loss": 0.0, "lr": 3.248413850811797e-05, "epoch": 179.22222222222223, "percentage": 40.33, "elapsed_time": "1:49:45", "remaining_time": "2:42:25", "throughput": 686.04, "total_tokens": 4517968} {"current_steps": 16135, "total_steps": 40000, "loss": 0.0, "lr": 3.2474770698485677e-05, "epoch": 179.27777777777777, "percentage": 40.34, "elapsed_time": "1:49:47", "remaining_time": "2:42:23", "throughput": 686.05, "total_tokens": 4519344} {"current_steps": 16140, "total_steps": 40000, "loss": 0.0, "lr": 3.246540173614983e-05, "epoch": 179.33333333333334, "percentage": 40.35, "elapsed_time": "1:49:49", "remaining_time": "2:42:21", "throughput": 686.06, "total_tokens": 4520736} {"current_steps": 16145, "total_steps": 40000, "loss": 0.0, "lr": 3.2456031622555197e-05, "epoch": 179.38888888888889, "percentage": 40.36, "elapsed_time": "1:49:51", "remaining_time": "2:42:19", "throughput": 686.07, "total_tokens": 4522128} {"current_steps": 16150, "total_steps": 40000, "loss": 0.0, "lr": 3.2446660359146794e-05, "epoch": 179.44444444444446, "percentage": 40.38, "elapsed_time": "1:49:53", "remaining_time": "2:42:16", "throughput": 686.08, "total_tokens": 4523552} {"current_steps": 16155, "total_steps": 40000, "loss": 0.0, "lr": 3.2437287947369786e-05, "epoch": 179.5, "percentage": 40.39, "elapsed_time": "1:49:55", "remaining_time": "2:42:14", "throughput": 686.09, "total_tokens": 4524944} {"current_steps": 16160, "total_steps": 40000, "loss": 0.0, "lr": 3.2427914388669525e-05, "epoch": 179.55555555555554, "percentage": 40.4, "elapsed_time": "1:49:57", "remaining_time": "2:42:12", "throughput": 686.11, "total_tokens": 4526384} {"current_steps": 16165, "total_steps": 40000, "loss": 0.0, "lr": 3.241853968449151e-05, "epoch": 179.61111111111111, "percentage": 40.41, "elapsed_time": "1:49:59", "remaining_time": "2:42:10", "throughput": 686.12, "total_tokens": 4527808} {"current_steps": 16170, "total_steps": 40000, "loss": 0.0, "lr": 3.240916383628144e-05, "epoch": 179.66666666666666, "percentage": 40.42, "elapsed_time": "1:50:01", "remaining_time": "2:42:08", "throughput": 686.13, "total_tokens": 4529200} {"current_steps": 16175, "total_steps": 40000, "loss": 0.0, "lr": 3.239978684548521e-05, "epoch": 179.72222222222223, "percentage": 40.44, "elapsed_time": "1:50:03", "remaining_time": "2:42:05", "throughput": 686.14, "total_tokens": 4530624} {"current_steps": 16180, "total_steps": 40000, "loss": 0.0, "lr": 3.239040871354885e-05, "epoch": 179.77777777777777, "percentage": 40.45, "elapsed_time": "1:50:04", "remaining_time": "2:42:03", "throughput": 686.15, "total_tokens": 4532016} {"current_steps": 16185, "total_steps": 40000, "loss": 0.0, "lr": 3.2381029441918596e-05, "epoch": 179.83333333333334, "percentage": 40.46, "elapsed_time": "1:50:06", "remaining_time": "2:42:01", "throughput": 686.16, "total_tokens": 4533392} {"current_steps": 16190, "total_steps": 40000, "loss": 0.0, "lr": 3.2371649032040845e-05, "epoch": 179.88888888888889, "percentage": 40.48, "elapsed_time": "1:50:08", "remaining_time": "2:41:59", "throughput": 686.18, "total_tokens": 4534832} {"current_steps": 16195, "total_steps": 40000, "loss": 0.0, "lr": 3.2362267485362174e-05, "epoch": 179.94444444444446, "percentage": 40.49, "elapsed_time": "1:50:10", "remaining_time": "2:41:57", "throughput": 686.19, "total_tokens": 4536240} {"current_steps": 16200, "total_steps": 40000, "loss": 0.0, "lr": 3.235288480332934e-05, "epoch": 180.0, "percentage": 40.5, "elapsed_time": "1:50:12", "remaining_time": "2:41:55", "throughput": 686.18, "total_tokens": 4537616} {"current_steps": 16200, "total_steps": 40000, "eval_loss": 0.3773461580276489, "epoch": 180.0, "percentage": 40.5, "elapsed_time": "1:50:14", "remaining_time": "2:41:57", "throughput": 686.05, "total_tokens": 4537616} {"current_steps": 16205, "total_steps": 40000, "loss": 0.0, "lr": 3.234350098738927e-05, "epoch": 180.05555555555554, "percentage": 40.51, "elapsed_time": "1:50:17", "remaining_time": "2:41:57", "throughput": 685.89, "total_tokens": 4539008} {"current_steps": 16210, "total_steps": 40000, "loss": 0.0, "lr": 3.233411603898906e-05, "epoch": 180.11111111111111, "percentage": 40.52, "elapsed_time": "1:50:19", "remaining_time": "2:41:55", "throughput": 685.9, "total_tokens": 4540384} {"current_steps": 16215, "total_steps": 40000, "loss": 0.0, "lr": 3.232472995957599e-05, "epoch": 180.16666666666666, "percentage": 40.54, "elapsed_time": "1:50:21", "remaining_time": "2:41:52", "throughput": 685.91, "total_tokens": 4541776} {"current_steps": 16220, "total_steps": 40000, "loss": 0.0, "lr": 3.231534275059751e-05, "epoch": 180.22222222222223, "percentage": 40.55, "elapsed_time": "1:50:23", "remaining_time": "2:41:50", "throughput": 685.91, "total_tokens": 4543152} {"current_steps": 16225, "total_steps": 40000, "loss": 0.0, "lr": 3.230595441350125e-05, "epoch": 180.27777777777777, "percentage": 40.56, "elapsed_time": "1:50:25", "remaining_time": "2:41:48", "throughput": 685.92, "total_tokens": 4544576} {"current_steps": 16230, "total_steps": 40000, "loss": 0.0, "lr": 3.2296564949735e-05, "epoch": 180.33333333333334, "percentage": 40.58, "elapsed_time": "1:50:27", "remaining_time": "2:41:46", "throughput": 685.94, "total_tokens": 4545984} {"current_steps": 16235, "total_steps": 40000, "loss": 0.0, "lr": 3.228717436074675e-05, "epoch": 180.38888888888889, "percentage": 40.59, "elapsed_time": "1:50:29", "remaining_time": "2:41:44", "throughput": 685.95, "total_tokens": 4547424} {"current_steps": 16240, "total_steps": 40000, "loss": 0.0, "lr": 3.227778264798463e-05, "epoch": 180.44444444444446, "percentage": 40.6, "elapsed_time": "1:50:31", "remaining_time": "2:41:41", "throughput": 685.96, "total_tokens": 4548800} {"current_steps": 16245, "total_steps": 40000, "loss": 0.0, "lr": 3.226838981289698e-05, "epoch": 180.5, "percentage": 40.61, "elapsed_time": "1:50:33", "remaining_time": "2:41:39", "throughput": 685.96, "total_tokens": 4550176} {"current_steps": 16250, "total_steps": 40000, "loss": 0.0, "lr": 3.225899585693227e-05, "epoch": 180.55555555555554, "percentage": 40.62, "elapsed_time": "1:50:35", "remaining_time": "2:41:37", "throughput": 685.98, "total_tokens": 4551584} {"current_steps": 16255, "total_steps": 40000, "loss": 0.0, "lr": 3.224960078153918e-05, "epoch": 180.61111111111111, "percentage": 40.64, "elapsed_time": "1:50:37", "remaining_time": "2:41:35", "throughput": 685.99, "total_tokens": 4552992} {"current_steps": 16260, "total_steps": 40000, "loss": 0.0, "lr": 3.224020458816655e-05, "epoch": 180.66666666666666, "percentage": 40.65, "elapsed_time": "1:50:39", "remaining_time": "2:41:33", "throughput": 686.0, "total_tokens": 4554416} {"current_steps": 16265, "total_steps": 40000, "loss": 0.0, "lr": 3.223080727826337e-05, "epoch": 180.72222222222223, "percentage": 40.66, "elapsed_time": "1:50:40", "remaining_time": "2:41:30", "throughput": 686.02, "total_tokens": 4555840} {"current_steps": 16270, "total_steps": 40000, "loss": 0.0, "lr": 3.222140885327885e-05, "epoch": 180.77777777777777, "percentage": 40.67, "elapsed_time": "1:50:42", "remaining_time": "2:41:28", "throughput": 686.03, "total_tokens": 4557248} {"current_steps": 16275, "total_steps": 40000, "loss": 0.0, "lr": 3.221200931466234e-05, "epoch": 180.83333333333334, "percentage": 40.69, "elapsed_time": "1:50:44", "remaining_time": "2:41:26", "throughput": 686.04, "total_tokens": 4558624} {"current_steps": 16280, "total_steps": 40000, "loss": 0.0, "lr": 3.220260866386336e-05, "epoch": 180.88888888888889, "percentage": 40.7, "elapsed_time": "1:50:46", "remaining_time": "2:41:24", "throughput": 686.05, "total_tokens": 4560032} {"current_steps": 16285, "total_steps": 40000, "loss": 0.0, "lr": 3.21932069023316e-05, "epoch": 180.94444444444446, "percentage": 40.71, "elapsed_time": "1:50:48", "remaining_time": "2:41:22", "throughput": 686.06, "total_tokens": 4561440} {"current_steps": 16290, "total_steps": 40000, "loss": 0.0, "lr": 3.218380403151695e-05, "epoch": 181.0, "percentage": 40.73, "elapsed_time": "1:50:50", "remaining_time": "2:41:20", "throughput": 686.06, "total_tokens": 4562880} {"current_steps": 16295, "total_steps": 40000, "loss": 0.0, "lr": 3.217440005286943e-05, "epoch": 181.05555555555554, "percentage": 40.74, "elapsed_time": "1:50:53", "remaining_time": "2:41:18", "throughput": 686.03, "total_tokens": 4564208} {"current_steps": 16300, "total_steps": 40000, "loss": 0.0, "lr": 3.216499496783928e-05, "epoch": 181.11111111111111, "percentage": 40.75, "elapsed_time": "1:50:54", "remaining_time": "2:41:16", "throughput": 686.05, "total_tokens": 4565632} {"current_steps": 16305, "total_steps": 40000, "loss": 0.0, "lr": 3.2155588777876856e-05, "epoch": 181.16666666666666, "percentage": 40.76, "elapsed_time": "1:50:56", "remaining_time": "2:41:14", "throughput": 686.06, "total_tokens": 4567056} {"current_steps": 16310, "total_steps": 40000, "loss": 0.0, "lr": 3.214618148443273e-05, "epoch": 181.22222222222223, "percentage": 40.77, "elapsed_time": "1:50:58", "remaining_time": "2:41:11", "throughput": 686.08, "total_tokens": 4568480} {"current_steps": 16315, "total_steps": 40000, "loss": 0.0, "lr": 3.2136773088957595e-05, "epoch": 181.27777777777777, "percentage": 40.79, "elapsed_time": "1:51:00", "remaining_time": "2:41:09", "throughput": 686.08, "total_tokens": 4569856} {"current_steps": 16320, "total_steps": 40000, "loss": 0.0, "lr": 3.2127363592902374e-05, "epoch": 181.33333333333334, "percentage": 40.8, "elapsed_time": "1:51:02", "remaining_time": "2:41:07", "throughput": 686.09, "total_tokens": 4571216} {"current_steps": 16325, "total_steps": 40000, "loss": 0.0, "lr": 3.211795299771812e-05, "epoch": 181.38888888888889, "percentage": 40.81, "elapsed_time": "1:51:04", "remaining_time": "2:41:05", "throughput": 686.1, "total_tokens": 4572640} {"current_steps": 16330, "total_steps": 40000, "loss": 0.0, "lr": 3.210854130485605e-05, "epoch": 181.44444444444446, "percentage": 40.83, "elapsed_time": "1:51:06", "remaining_time": "2:41:03", "throughput": 686.11, "total_tokens": 4574032} {"current_steps": 16335, "total_steps": 40000, "loss": 0.0, "lr": 3.209912851576759e-05, "epoch": 181.5, "percentage": 40.84, "elapsed_time": "1:51:08", "remaining_time": "2:41:00", "throughput": 686.12, "total_tokens": 4575408} {"current_steps": 16340, "total_steps": 40000, "loss": 0.0, "lr": 3.208971463190431e-05, "epoch": 181.55555555555554, "percentage": 40.85, "elapsed_time": "1:51:10", "remaining_time": "2:40:58", "throughput": 686.12, "total_tokens": 4576784} {"current_steps": 16345, "total_steps": 40000, "loss": 0.0, "lr": 3.208029965471793e-05, "epoch": 181.61111111111111, "percentage": 40.86, "elapsed_time": "1:51:12", "remaining_time": "2:40:56", "throughput": 686.13, "total_tokens": 4578176} {"current_steps": 16350, "total_steps": 40000, "loss": 0.0, "lr": 3.2070883585660364e-05, "epoch": 181.66666666666666, "percentage": 40.88, "elapsed_time": "1:51:14", "remaining_time": "2:40:54", "throughput": 686.14, "total_tokens": 4579568} {"current_steps": 16355, "total_steps": 40000, "loss": 0.0, "lr": 3.20614664261837e-05, "epoch": 181.72222222222223, "percentage": 40.89, "elapsed_time": "1:51:16", "remaining_time": "2:40:52", "throughput": 686.16, "total_tokens": 4581008} {"current_steps": 16360, "total_steps": 40000, "loss": 0.0, "lr": 3.205204817774016e-05, "epoch": 181.77777777777777, "percentage": 40.9, "elapsed_time": "1:51:18", "remaining_time": "2:40:50", "throughput": 686.17, "total_tokens": 4582416} {"current_steps": 16365, "total_steps": 40000, "loss": 0.0, "lr": 3.204262884178218e-05, "epoch": 181.83333333333334, "percentage": 40.91, "elapsed_time": "1:51:20", "remaining_time": "2:40:47", "throughput": 686.17, "total_tokens": 4583808} {"current_steps": 16370, "total_steps": 40000, "loss": 0.0, "lr": 3.2033208419762314e-05, "epoch": 181.88888888888889, "percentage": 40.92, "elapsed_time": "1:51:22", "remaining_time": "2:40:45", "throughput": 686.18, "total_tokens": 4585200} {"current_steps": 16375, "total_steps": 40000, "loss": 0.0, "lr": 3.2023786913133344e-05, "epoch": 181.94444444444446, "percentage": 40.94, "elapsed_time": "1:51:24", "remaining_time": "2:40:43", "throughput": 686.2, "total_tokens": 4586608} {"current_steps": 16380, "total_steps": 40000, "loss": 0.0, "lr": 3.201436432334816e-05, "epoch": 182.0, "percentage": 40.95, "elapsed_time": "1:51:26", "remaining_time": "2:40:41", "throughput": 686.19, "total_tokens": 4588032} {"current_steps": 16385, "total_steps": 40000, "loss": 0.0, "lr": 3.2004940651859844e-05, "epoch": 182.05555555555554, "percentage": 40.96, "elapsed_time": "1:51:28", "remaining_time": "2:40:39", "throughput": 686.18, "total_tokens": 4589408} {"current_steps": 16390, "total_steps": 40000, "loss": 0.0, "lr": 3.1995515900121655e-05, "epoch": 182.11111111111111, "percentage": 40.98, "elapsed_time": "1:51:30", "remaining_time": "2:40:37", "throughput": 686.19, "total_tokens": 4590816} {"current_steps": 16395, "total_steps": 40000, "loss": 0.0, "lr": 3.1986090069587e-05, "epoch": 182.16666666666666, "percentage": 40.99, "elapsed_time": "1:51:32", "remaining_time": "2:40:35", "throughput": 686.19, "total_tokens": 4592192} {"current_steps": 16400, "total_steps": 40000, "loss": 0.0, "lr": 3.1976663161709466e-05, "epoch": 182.22222222222223, "percentage": 41.0, "elapsed_time": "1:51:34", "remaining_time": "2:40:33", "throughput": 686.2, "total_tokens": 4593600} {"current_steps": 16400, "total_steps": 40000, "eval_loss": 0.39895930886268616, "epoch": 182.22222222222223, "percentage": 41.0, "elapsed_time": "1:51:35", "remaining_time": "2:40:35", "throughput": 686.07, "total_tokens": 4593600} {"current_steps": 16405, "total_steps": 40000, "loss": 0.0, "lr": 3.196723517794279e-05, "epoch": 182.27777777777777, "percentage": 41.01, "elapsed_time": "1:51:39", "remaining_time": "2:40:35", "throughput": 685.91, "total_tokens": 4594992} {"current_steps": 16410, "total_steps": 40000, "loss": 0.0, "lr": 3.19578061197409e-05, "epoch": 182.33333333333334, "percentage": 41.02, "elapsed_time": "1:51:41", "remaining_time": "2:40:33", "throughput": 685.91, "total_tokens": 4596384} {"current_steps": 16415, "total_steps": 40000, "loss": 0.0, "lr": 3.194837598855787e-05, "epoch": 182.38888888888889, "percentage": 41.04, "elapsed_time": "1:51:43", "remaining_time": "2:40:30", "throughput": 685.93, "total_tokens": 4597840} {"current_steps": 16420, "total_steps": 40000, "loss": 0.0, "lr": 3.193894478584794e-05, "epoch": 182.44444444444446, "percentage": 41.05, "elapsed_time": "1:51:45", "remaining_time": "2:40:28", "throughput": 685.94, "total_tokens": 4599248} {"current_steps": 16425, "total_steps": 40000, "loss": 0.0, "lr": 3.192951251306553e-05, "epoch": 182.5, "percentage": 41.06, "elapsed_time": "1:51:46", "remaining_time": "2:40:26", "throughput": 685.95, "total_tokens": 4600640} {"current_steps": 16430, "total_steps": 40000, "loss": 0.0, "lr": 3.192007917166521e-05, "epoch": 182.55555555555554, "percentage": 41.08, "elapsed_time": "1:51:48", "remaining_time": "2:40:24", "throughput": 685.96, "total_tokens": 4602048} {"current_steps": 16435, "total_steps": 40000, "loss": 0.0, "lr": 3.191064476310171e-05, "epoch": 182.61111111111111, "percentage": 41.09, "elapsed_time": "1:51:50", "remaining_time": "2:40:22", "throughput": 685.97, "total_tokens": 4603424} {"current_steps": 16440, "total_steps": 40000, "loss": 0.0, "lr": 3.1901209288829944e-05, "epoch": 182.66666666666666, "percentage": 41.1, "elapsed_time": "1:51:52", "remaining_time": "2:40:20", "throughput": 685.97, "total_tokens": 4604784} {"current_steps": 16445, "total_steps": 40000, "loss": 0.0, "lr": 3.1891772750304985e-05, "epoch": 182.72222222222223, "percentage": 41.11, "elapsed_time": "1:51:54", "remaining_time": "2:40:17", "throughput": 685.98, "total_tokens": 4606160} {"current_steps": 16450, "total_steps": 40000, "loss": 0.0, "lr": 3.188233514898206e-05, "epoch": 182.77777777777777, "percentage": 41.12, "elapsed_time": "1:51:56", "remaining_time": "2:40:15", "throughput": 685.98, "total_tokens": 4607520} {"current_steps": 16455, "total_steps": 40000, "loss": 0.0, "lr": 3.187289648631657e-05, "epoch": 182.83333333333334, "percentage": 41.14, "elapsed_time": "1:51:58", "remaining_time": "2:40:13", "throughput": 686.0, "total_tokens": 4608944} {"current_steps": 16460, "total_steps": 40000, "loss": 0.0, "lr": 3.186345676376406e-05, "epoch": 182.88888888888889, "percentage": 41.15, "elapsed_time": "1:52:00", "remaining_time": "2:40:11", "throughput": 686.0, "total_tokens": 4610304} {"current_steps": 16465, "total_steps": 40000, "loss": 0.0, "lr": 3.1854015982780275e-05, "epoch": 182.94444444444446, "percentage": 41.16, "elapsed_time": "1:52:02", "remaining_time": "2:40:09", "throughput": 686.01, "total_tokens": 4611696} {"current_steps": 16470, "total_steps": 40000, "loss": 0.0, "lr": 3.1844574144821084e-05, "epoch": 183.0, "percentage": 41.17, "elapsed_time": "1:52:04", "remaining_time": "2:40:07", "throughput": 686.01, "total_tokens": 4613136} {"current_steps": 16475, "total_steps": 40000, "loss": 0.0, "lr": 3.1835131251342554e-05, "epoch": 183.05555555555554, "percentage": 41.19, "elapsed_time": "1:52:06", "remaining_time": "2:40:05", "throughput": 686.0, "total_tokens": 4614592} {"current_steps": 16480, "total_steps": 40000, "loss": 0.0, "lr": 3.182568730380089e-05, "epoch": 183.11111111111111, "percentage": 41.2, "elapsed_time": "1:52:08", "remaining_time": "2:40:03", "throughput": 686.02, "total_tokens": 4616016} {"current_steps": 16485, "total_steps": 40000, "loss": 0.0, "lr": 3.181624230365245e-05, "epoch": 183.16666666666666, "percentage": 41.21, "elapsed_time": "1:52:10", "remaining_time": "2:40:00", "throughput": 686.03, "total_tokens": 4617456} {"current_steps": 16490, "total_steps": 40000, "loss": 0.0, "lr": 3.180679625235381e-05, "epoch": 183.22222222222223, "percentage": 41.23, "elapsed_time": "1:52:12", "remaining_time": "2:39:58", "throughput": 686.04, "total_tokens": 4618848} {"current_steps": 16495, "total_steps": 40000, "loss": 0.0, "lr": 3.1797349151361646e-05, "epoch": 183.27777777777777, "percentage": 41.24, "elapsed_time": "1:52:14", "remaining_time": "2:39:56", "throughput": 686.06, "total_tokens": 4620272} {"current_steps": 16500, "total_steps": 40000, "loss": 0.0, "lr": 3.178790100213281e-05, "epoch": 183.33333333333334, "percentage": 41.25, "elapsed_time": "1:52:16", "remaining_time": "2:39:54", "throughput": 686.06, "total_tokens": 4621680} {"current_steps": 16505, "total_steps": 40000, "loss": 0.0, "lr": 3.1778451806124346e-05, "epoch": 183.38888888888889, "percentage": 41.26, "elapsed_time": "1:52:18", "remaining_time": "2:39:52", "throughput": 686.07, "total_tokens": 4623056} {"current_steps": 16510, "total_steps": 40000, "loss": 0.0, "lr": 3.176900156479342e-05, "epoch": 183.44444444444446, "percentage": 41.27, "elapsed_time": "1:52:20", "remaining_time": "2:39:50", "throughput": 686.08, "total_tokens": 4624432} {"current_steps": 16515, "total_steps": 40000, "loss": 0.0, "lr": 3.17595502795974e-05, "epoch": 183.5, "percentage": 41.29, "elapsed_time": "1:52:22", "remaining_time": "2:39:47", "throughput": 686.09, "total_tokens": 4625840} {"current_steps": 16520, "total_steps": 40000, "loss": 0.0, "lr": 3.175009795199377e-05, "epoch": 183.55555555555554, "percentage": 41.3, "elapsed_time": "1:52:24", "remaining_time": "2:39:45", "throughput": 686.1, "total_tokens": 4627280} {"current_steps": 16525, "total_steps": 40000, "loss": 0.0, "lr": 3.1740644583440224e-05, "epoch": 183.61111111111111, "percentage": 41.31, "elapsed_time": "1:52:26", "remaining_time": "2:39:43", "throughput": 686.11, "total_tokens": 4628656} {"current_steps": 16530, "total_steps": 40000, "loss": 0.0, "lr": 3.173119017539457e-05, "epoch": 183.66666666666666, "percentage": 41.33, "elapsed_time": "1:52:28", "remaining_time": "2:39:41", "throughput": 686.13, "total_tokens": 4630096} {"current_steps": 16535, "total_steps": 40000, "loss": 0.0, "lr": 3.172173472931479e-05, "epoch": 183.72222222222223, "percentage": 41.34, "elapsed_time": "1:52:30", "remaining_time": "2:39:39", "throughput": 686.14, "total_tokens": 4631520} {"current_steps": 16540, "total_steps": 40000, "loss": 0.0, "lr": 3.1712278246659055e-05, "epoch": 183.77777777777777, "percentage": 41.35, "elapsed_time": "1:52:32", "remaining_time": "2:39:37", "throughput": 686.14, "total_tokens": 4632848} {"current_steps": 16545, "total_steps": 40000, "loss": 0.0, "lr": 3.170282072888566e-05, "epoch": 183.83333333333334, "percentage": 41.36, "elapsed_time": "1:52:34", "remaining_time": "2:39:34", "throughput": 686.15, "total_tokens": 4634256} {"current_steps": 16550, "total_steps": 40000, "loss": 0.0, "lr": 3.169336217745307e-05, "epoch": 183.88888888888889, "percentage": 41.38, "elapsed_time": "1:52:35", "remaining_time": "2:39:32", "throughput": 686.16, "total_tokens": 4635664} {"current_steps": 16555, "total_steps": 40000, "loss": 0.0, "lr": 3.1683902593819924e-05, "epoch": 183.94444444444446, "percentage": 41.39, "elapsed_time": "1:52:37", "remaining_time": "2:39:30", "throughput": 686.17, "total_tokens": 4637072} {"current_steps": 16560, "total_steps": 40000, "loss": 0.0, "lr": 3.1674441979445e-05, "epoch": 184.0, "percentage": 41.4, "elapsed_time": "1:52:39", "remaining_time": "2:39:28", "throughput": 686.16, "total_tokens": 4638448} {"current_steps": 16565, "total_steps": 40000, "loss": 0.0, "lr": 3.166498033578725e-05, "epoch": 184.05555555555554, "percentage": 41.41, "elapsed_time": "1:52:42", "remaining_time": "2:39:26", "throughput": 686.15, "total_tokens": 4639856} {"current_steps": 16570, "total_steps": 40000, "loss": 0.0, "lr": 3.165551766430578e-05, "epoch": 184.11111111111111, "percentage": 41.42, "elapsed_time": "1:52:44", "remaining_time": "2:39:24", "throughput": 686.15, "total_tokens": 4641232} {"current_steps": 16575, "total_steps": 40000, "loss": 0.0, "lr": 3.164605396645984e-05, "epoch": 184.16666666666666, "percentage": 41.44, "elapsed_time": "1:52:46", "remaining_time": "2:39:22", "throughput": 686.16, "total_tokens": 4642640} {"current_steps": 16580, "total_steps": 40000, "loss": 0.0, "lr": 3.163658924370886e-05, "epoch": 184.22222222222223, "percentage": 41.45, "elapsed_time": "1:52:48", "remaining_time": "2:39:20", "throughput": 686.17, "total_tokens": 4644016} {"current_steps": 16585, "total_steps": 40000, "loss": 0.0, "lr": 3.1627123497512415e-05, "epoch": 184.27777777777777, "percentage": 41.46, "elapsed_time": "1:52:49", "remaining_time": "2:39:17", "throughput": 686.18, "total_tokens": 4645424} {"current_steps": 16590, "total_steps": 40000, "loss": 0.0, "lr": 3.1617656729330245e-05, "epoch": 184.33333333333334, "percentage": 41.48, "elapsed_time": "1:52:51", "remaining_time": "2:39:15", "throughput": 686.19, "total_tokens": 4646800} {"current_steps": 16595, "total_steps": 40000, "loss": 0.0, "lr": 3.1608188940622255e-05, "epoch": 184.38888888888889, "percentage": 41.49, "elapsed_time": "1:52:53", "remaining_time": "2:39:13", "throughput": 686.2, "total_tokens": 4648224} {"current_steps": 16600, "total_steps": 40000, "loss": 0.0, "lr": 3.159872013284847e-05, "epoch": 184.44444444444446, "percentage": 41.5, "elapsed_time": "1:52:55", "remaining_time": "2:39:11", "throughput": 686.22, "total_tokens": 4649664} {"current_steps": 16600, "total_steps": 40000, "eval_loss": 0.3898445963859558, "epoch": 184.44444444444446, "percentage": 41.5, "elapsed_time": "1:52:57", "remaining_time": "2:39:13", "throughput": 686.09, "total_tokens": 4649664} {"current_steps": 16605, "total_steps": 40000, "loss": 0.0, "lr": 3.1589250307469134e-05, "epoch": 184.5, "percentage": 41.51, "elapsed_time": "1:53:00", "remaining_time": "2:39:12", "throughput": 685.97, "total_tokens": 4651088} {"current_steps": 16610, "total_steps": 40000, "loss": 0.0, "lr": 3.1579779465944586e-05, "epoch": 184.55555555555554, "percentage": 41.52, "elapsed_time": "1:53:02", "remaining_time": "2:39:10", "throughput": 685.97, "total_tokens": 4652464} {"current_steps": 16615, "total_steps": 40000, "loss": 0.0, "lr": 3.1570307609735363e-05, "epoch": 184.61111111111111, "percentage": 41.54, "elapsed_time": "1:53:04", "remaining_time": "2:39:08", "throughput": 685.98, "total_tokens": 4653872} {"current_steps": 16620, "total_steps": 40000, "loss": 0.0, "lr": 3.156083474030213e-05, "epoch": 184.66666666666666, "percentage": 41.55, "elapsed_time": "1:53:06", "remaining_time": "2:39:06", "throughput": 686.0, "total_tokens": 4655328} {"current_steps": 16625, "total_steps": 40000, "loss": 0.0, "lr": 3.155136085910573e-05, "epoch": 184.72222222222223, "percentage": 41.56, "elapsed_time": "1:53:08", "remaining_time": "2:39:04", "throughput": 686.01, "total_tokens": 4656720} {"current_steps": 16630, "total_steps": 40000, "loss": 0.0, "lr": 3.154188596760717e-05, "epoch": 184.77777777777777, "percentage": 41.58, "elapsed_time": "1:53:10", "remaining_time": "2:39:02", "throughput": 686.02, "total_tokens": 4658112} {"current_steps": 16635, "total_steps": 40000, "loss": 0.0, "lr": 3.153241006726757e-05, "epoch": 184.83333333333334, "percentage": 41.59, "elapsed_time": "1:53:12", "remaining_time": "2:38:59", "throughput": 686.03, "total_tokens": 4659536} {"current_steps": 16640, "total_steps": 40000, "loss": 0.0, "lr": 3.152293315954825e-05, "epoch": 184.88888888888889, "percentage": 41.6, "elapsed_time": "1:53:13", "remaining_time": "2:38:57", "throughput": 686.04, "total_tokens": 4660896} {"current_steps": 16645, "total_steps": 40000, "loss": 0.0, "lr": 3.1513455245910666e-05, "epoch": 184.94444444444446, "percentage": 41.61, "elapsed_time": "1:53:15", "remaining_time": "2:38:55", "throughput": 686.04, "total_tokens": 4662288} {"current_steps": 16650, "total_steps": 40000, "loss": 0.0, "lr": 3.150397632781643e-05, "epoch": 185.0, "percentage": 41.62, "elapsed_time": "1:53:18", "remaining_time": "2:38:53", "throughput": 686.03, "total_tokens": 4663648} {"current_steps": 16655, "total_steps": 40000, "loss": 0.0, "lr": 3.149449640672731e-05, "epoch": 185.05555555555554, "percentage": 41.64, "elapsed_time": "1:53:20", "remaining_time": "2:38:51", "throughput": 686.01, "total_tokens": 4665040} {"current_steps": 16660, "total_steps": 40000, "loss": 0.0, "lr": 3.148501548410523e-05, "epoch": 185.11111111111111, "percentage": 41.65, "elapsed_time": "1:53:22", "remaining_time": "2:38:49", "throughput": 686.02, "total_tokens": 4666432} {"current_steps": 16665, "total_steps": 40000, "loss": 0.0, "lr": 3.1475533561412256e-05, "epoch": 185.16666666666666, "percentage": 41.66, "elapsed_time": "1:53:24", "remaining_time": "2:38:47", "throughput": 686.04, "total_tokens": 4667872} {"current_steps": 16670, "total_steps": 40000, "loss": 0.0, "lr": 3.146605064011065e-05, "epoch": 185.22222222222223, "percentage": 41.68, "elapsed_time": "1:53:26", "remaining_time": "2:38:45", "throughput": 686.05, "total_tokens": 4669248} {"current_steps": 16675, "total_steps": 40000, "loss": 0.0, "lr": 3.145656672166277e-05, "epoch": 185.27777777777777, "percentage": 41.69, "elapsed_time": "1:53:27", "remaining_time": "2:38:42", "throughput": 686.06, "total_tokens": 4670656} {"current_steps": 16680, "total_steps": 40000, "loss": 0.0, "lr": 3.144708180753116e-05, "epoch": 185.33333333333334, "percentage": 41.7, "elapsed_time": "1:53:29", "remaining_time": "2:38:40", "throughput": 686.07, "total_tokens": 4672064} {"current_steps": 16685, "total_steps": 40000, "loss": 0.0, "lr": 3.143759589917851e-05, "epoch": 185.38888888888889, "percentage": 41.71, "elapsed_time": "1:53:31", "remaining_time": "2:38:38", "throughput": 686.08, "total_tokens": 4673472} {"current_steps": 16690, "total_steps": 40000, "loss": 0.0, "lr": 3.142810899806768e-05, "epoch": 185.44444444444446, "percentage": 41.73, "elapsed_time": "1:53:33", "remaining_time": "2:38:36", "throughput": 686.09, "total_tokens": 4674848} {"current_steps": 16695, "total_steps": 40000, "loss": 0.0, "lr": 3.141862110566166e-05, "epoch": 185.5, "percentage": 41.74, "elapsed_time": "1:53:35", "remaining_time": "2:38:34", "throughput": 686.1, "total_tokens": 4676256} {"current_steps": 16700, "total_steps": 40000, "loss": 0.0, "lr": 3.1409132223423606e-05, "epoch": 185.55555555555554, "percentage": 41.75, "elapsed_time": "1:53:37", "remaining_time": "2:38:32", "throughput": 686.11, "total_tokens": 4677664} {"current_steps": 16705, "total_steps": 40000, "loss": 0.0, "lr": 3.139964235281682e-05, "epoch": 185.61111111111111, "percentage": 41.76, "elapsed_time": "1:53:39", "remaining_time": "2:38:29", "throughput": 686.11, "total_tokens": 4679024} {"current_steps": 16710, "total_steps": 40000, "loss": 0.0, "lr": 3.139015149530476e-05, "epoch": 185.66666666666666, "percentage": 41.77, "elapsed_time": "1:53:41", "remaining_time": "2:38:27", "throughput": 686.12, "total_tokens": 4680416} {"current_steps": 16715, "total_steps": 40000, "loss": 0.0, "lr": 3.1380659652351034e-05, "epoch": 185.72222222222223, "percentage": 41.79, "elapsed_time": "1:53:43", "remaining_time": "2:38:25", "throughput": 686.14, "total_tokens": 4681840} {"current_steps": 16720, "total_steps": 40000, "loss": 0.0, "lr": 3.137116682541941e-05, "epoch": 185.77777777777777, "percentage": 41.8, "elapsed_time": "1:53:45", "remaining_time": "2:38:23", "throughput": 686.15, "total_tokens": 4683280} {"current_steps": 16725, "total_steps": 40000, "loss": 0.0, "lr": 3.136167301597379e-05, "epoch": 185.83333333333334, "percentage": 41.81, "elapsed_time": "1:53:47", "remaining_time": "2:38:21", "throughput": 686.16, "total_tokens": 4684704} {"current_steps": 16730, "total_steps": 40000, "loss": 0.0, "lr": 3.1352178225478254e-05, "epoch": 185.88888888888889, "percentage": 41.83, "elapsed_time": "1:53:49", "remaining_time": "2:38:19", "throughput": 686.17, "total_tokens": 4686080} {"current_steps": 16735, "total_steps": 40000, "loss": 0.0, "lr": 3.1342682455396996e-05, "epoch": 185.94444444444446, "percentage": 41.84, "elapsed_time": "1:53:51", "remaining_time": "2:38:16", "throughput": 686.17, "total_tokens": 4687440} {"current_steps": 16740, "total_steps": 40000, "loss": 0.0, "lr": 3.133318570719441e-05, "epoch": 186.0, "percentage": 41.85, "elapsed_time": "1:53:53", "remaining_time": "2:38:14", "throughput": 686.17, "total_tokens": 4688864} {"current_steps": 16745, "total_steps": 40000, "loss": 0.0, "lr": 3.132368798233499e-05, "epoch": 186.05555555555554, "percentage": 41.86, "elapsed_time": "1:53:55", "remaining_time": "2:38:13", "throughput": 686.15, "total_tokens": 4690208} {"current_steps": 16750, "total_steps": 40000, "loss": 0.0, "lr": 3.131418928228342e-05, "epoch": 186.11111111111111, "percentage": 41.88, "elapsed_time": "1:53:57", "remaining_time": "2:38:10", "throughput": 686.15, "total_tokens": 4691584} {"current_steps": 16755, "total_steps": 40000, "loss": 0.0, "lr": 3.1304689608504514e-05, "epoch": 186.16666666666666, "percentage": 41.89, "elapsed_time": "1:53:59", "remaining_time": "2:38:08", "throughput": 686.17, "total_tokens": 4693024} {"current_steps": 16760, "total_steps": 40000, "loss": 0.0, "lr": 3.129518896246324e-05, "epoch": 186.22222222222223, "percentage": 41.9, "elapsed_time": "1:54:01", "remaining_time": "2:38:06", "throughput": 686.18, "total_tokens": 4694416} {"current_steps": 16765, "total_steps": 40000, "loss": 0.0, "lr": 3.128568734562472e-05, "epoch": 186.27777777777777, "percentage": 41.91, "elapsed_time": "1:54:03", "remaining_time": "2:38:04", "throughput": 686.19, "total_tokens": 4695808} {"current_steps": 16770, "total_steps": 40000, "loss": 0.0, "lr": 3.127618475945421e-05, "epoch": 186.33333333333334, "percentage": 41.93, "elapsed_time": "1:54:05", "remaining_time": "2:38:02", "throughput": 686.2, "total_tokens": 4697232} {"current_steps": 16775, "total_steps": 40000, "loss": 0.0, "lr": 3.126668120541715e-05, "epoch": 186.38888888888889, "percentage": 41.94, "elapsed_time": "1:54:07", "remaining_time": "2:37:59", "throughput": 686.21, "total_tokens": 4698624} {"current_steps": 16780, "total_steps": 40000, "loss": 0.0, "lr": 3.1257176684979096e-05, "epoch": 186.44444444444446, "percentage": 41.95, "elapsed_time": "1:54:09", "remaining_time": "2:37:57", "throughput": 686.21, "total_tokens": 4700000} {"current_steps": 16785, "total_steps": 40000, "loss": 0.0, "lr": 3.124767119960576e-05, "epoch": 186.5, "percentage": 41.96, "elapsed_time": "1:54:11", "remaining_time": "2:37:55", "throughput": 686.22, "total_tokens": 4701376} {"current_steps": 16790, "total_steps": 40000, "loss": 0.0, "lr": 3.123816475076301e-05, "epoch": 186.55555555555554, "percentage": 41.98, "elapsed_time": "1:54:13", "remaining_time": "2:37:53", "throughput": 686.23, "total_tokens": 4702752} {"current_steps": 16795, "total_steps": 40000, "loss": 0.0, "lr": 3.122865733991687e-05, "epoch": 186.61111111111111, "percentage": 41.99, "elapsed_time": "1:54:15", "remaining_time": "2:37:51", "throughput": 686.24, "total_tokens": 4704208} {"current_steps": 16800, "total_steps": 40000, "loss": 0.0, "lr": 3.1219148968533486e-05, "epoch": 186.66666666666666, "percentage": 42.0, "elapsed_time": "1:54:16", "remaining_time": "2:37:49", "throughput": 686.25, "total_tokens": 4705600} {"current_steps": 16800, "total_steps": 40000, "eval_loss": 0.40677133202552795, "epoch": 186.66666666666666, "percentage": 42.0, "elapsed_time": "1:54:18", "remaining_time": "2:37:50", "throughput": 686.12, "total_tokens": 4705600} {"current_steps": 16805, "total_steps": 40000, "loss": 0.0, "lr": 3.120963963807918e-05, "epoch": 186.72222222222223, "percentage": 42.01, "elapsed_time": "1:54:21", "remaining_time": "2:37:50", "throughput": 686.0, "total_tokens": 4707072} {"current_steps": 16810, "total_steps": 40000, "loss": 0.0, "lr": 3.12001293500204e-05, "epoch": 186.77777777777777, "percentage": 42.02, "elapsed_time": "1:54:23", "remaining_time": "2:37:48", "throughput": 686.0, "total_tokens": 4708464} {"current_steps": 16815, "total_steps": 40000, "loss": 0.0, "lr": 3.1190618105823765e-05, "epoch": 186.83333333333334, "percentage": 42.04, "elapsed_time": "1:54:25", "remaining_time": "2:37:46", "throughput": 686.01, "total_tokens": 4709888} {"current_steps": 16820, "total_steps": 40000, "loss": 0.0, "lr": 3.118110590695603e-05, "epoch": 186.88888888888889, "percentage": 42.05, "elapsed_time": "1:54:27", "remaining_time": "2:37:44", "throughput": 686.03, "total_tokens": 4711344} {"current_steps": 16825, "total_steps": 40000, "loss": 0.0, "lr": 3.117159275488407e-05, "epoch": 186.94444444444446, "percentage": 42.06, "elapsed_time": "1:54:29", "remaining_time": "2:37:42", "throughput": 686.04, "total_tokens": 4712736} {"current_steps": 16830, "total_steps": 40000, "loss": 0.0, "lr": 3.1162078651074956e-05, "epoch": 187.0, "percentage": 42.08, "elapsed_time": "1:54:31", "remaining_time": "2:37:40", "throughput": 686.02, "total_tokens": 4714096} {"current_steps": 16835, "total_steps": 40000, "loss": 0.0, "lr": 3.1152563596995885e-05, "epoch": 187.05555555555554, "percentage": 42.09, "elapsed_time": "1:54:33", "remaining_time": "2:37:38", "throughput": 686.0, "total_tokens": 4715456} {"current_steps": 16840, "total_steps": 40000, "loss": 0.0, "lr": 3.1143047594114186e-05, "epoch": 187.11111111111111, "percentage": 42.1, "elapsed_time": "1:54:35", "remaining_time": "2:37:36", "throughput": 686.01, "total_tokens": 4716864} {"current_steps": 16845, "total_steps": 40000, "loss": 0.0, "lr": 3.113353064389734e-05, "epoch": 187.16666666666666, "percentage": 42.11, "elapsed_time": "1:54:37", "remaining_time": "2:37:34", "throughput": 686.02, "total_tokens": 4718240} {"current_steps": 16850, "total_steps": 40000, "loss": 0.0, "lr": 3.1124012747812993e-05, "epoch": 187.22222222222223, "percentage": 42.12, "elapsed_time": "1:54:39", "remaining_time": "2:37:31", "throughput": 686.02, "total_tokens": 4719600} {"current_steps": 16855, "total_steps": 40000, "loss": 0.0, "lr": 3.1114493907328936e-05, "epoch": 187.27777777777777, "percentage": 42.14, "elapsed_time": "1:54:41", "remaining_time": "2:37:29", "throughput": 686.03, "total_tokens": 4720992} {"current_steps": 16860, "total_steps": 40000, "loss": 0.0, "lr": 3.110497412391306e-05, "epoch": 187.33333333333334, "percentage": 42.15, "elapsed_time": "1:54:43", "remaining_time": "2:37:27", "throughput": 686.05, "total_tokens": 4722432} {"current_steps": 16865, "total_steps": 40000, "loss": 0.0, "lr": 3.1095453399033466e-05, "epoch": 187.38888888888889, "percentage": 42.16, "elapsed_time": "1:54:45", "remaining_time": "2:37:25", "throughput": 686.07, "total_tokens": 4723888} {"current_steps": 16870, "total_steps": 40000, "loss": 0.0, "lr": 3.108593173415835e-05, "epoch": 187.44444444444446, "percentage": 42.18, "elapsed_time": "1:54:47", "remaining_time": "2:37:23", "throughput": 686.08, "total_tokens": 4725296} {"current_steps": 16875, "total_steps": 40000, "loss": 0.0, "lr": 3.107640913075609e-05, "epoch": 187.5, "percentage": 42.19, "elapsed_time": "1:54:49", "remaining_time": "2:37:21", "throughput": 686.06, "total_tokens": 4726736} {"current_steps": 16880, "total_steps": 40000, "loss": 0.0, "lr": 3.106688559029517e-05, "epoch": 187.55555555555554, "percentage": 42.2, "elapsed_time": "1:54:51", "remaining_time": "2:37:19", "throughput": 686.08, "total_tokens": 4728176} {"current_steps": 16885, "total_steps": 40000, "loss": 0.0, "lr": 3.105736111424425e-05, "epoch": 187.61111111111111, "percentage": 42.21, "elapsed_time": "1:54:53", "remaining_time": "2:37:17", "throughput": 686.08, "total_tokens": 4729568} {"current_steps": 16890, "total_steps": 40000, "loss": 0.0, "lr": 3.1047835704072136e-05, "epoch": 187.66666666666666, "percentage": 42.23, "elapsed_time": "1:54:55", "remaining_time": "2:37:14", "throughput": 686.09, "total_tokens": 4730976} {"current_steps": 16895, "total_steps": 40000, "loss": 0.0, "lr": 3.103830936124775e-05, "epoch": 187.72222222222223, "percentage": 42.24, "elapsed_time": "1:54:57", "remaining_time": "2:37:12", "throughput": 686.11, "total_tokens": 4732384} {"current_steps": 16900, "total_steps": 40000, "loss": 0.0, "lr": 3.102878208724018e-05, "epoch": 187.77777777777777, "percentage": 42.25, "elapsed_time": "1:54:59", "remaining_time": "2:37:10", "throughput": 686.11, "total_tokens": 4733744} {"current_steps": 16905, "total_steps": 40000, "loss": 0.0, "lr": 3.101925388351865e-05, "epoch": 187.83333333333334, "percentage": 42.26, "elapsed_time": "1:55:01", "remaining_time": "2:37:08", "throughput": 686.12, "total_tokens": 4735168} {"current_steps": 16910, "total_steps": 40000, "loss": 0.0, "lr": 3.1009724751552515e-05, "epoch": 187.88888888888889, "percentage": 42.27, "elapsed_time": "1:55:03", "remaining_time": "2:37:06", "throughput": 686.13, "total_tokens": 4736576} {"current_steps": 16915, "total_steps": 40000, "loss": 0.0, "lr": 3.100019469281131e-05, "epoch": 187.94444444444446, "percentage": 42.29, "elapsed_time": "1:55:05", "remaining_time": "2:37:04", "throughput": 686.14, "total_tokens": 4737952} {"current_steps": 16920, "total_steps": 40000, "loss": 0.0, "lr": 3.0990663708764685e-05, "epoch": 188.0, "percentage": 42.3, "elapsed_time": "1:55:07", "remaining_time": "2:37:02", "throughput": 686.13, "total_tokens": 4739328} {"current_steps": 16925, "total_steps": 40000, "loss": 0.0, "lr": 3.098113180088243e-05, "epoch": 188.05555555555554, "percentage": 42.31, "elapsed_time": "1:55:09", "remaining_time": "2:37:00", "throughput": 686.11, "total_tokens": 4740736} {"current_steps": 16930, "total_steps": 40000, "loss": 0.0, "lr": 3.097159897063448e-05, "epoch": 188.11111111111111, "percentage": 42.33, "elapsed_time": "1:55:11", "remaining_time": "2:36:58", "throughput": 686.13, "total_tokens": 4742176} {"current_steps": 16935, "total_steps": 40000, "loss": 0.0, "lr": 3.096206521949094e-05, "epoch": 188.16666666666666, "percentage": 42.34, "elapsed_time": "1:55:13", "remaining_time": "2:36:55", "throughput": 686.14, "total_tokens": 4743568} {"current_steps": 16940, "total_steps": 40000, "loss": 0.0, "lr": 3.0952530548922006e-05, "epoch": 188.22222222222223, "percentage": 42.35, "elapsed_time": "1:55:15", "remaining_time": "2:36:53", "throughput": 686.15, "total_tokens": 4744992} {"current_steps": 16945, "total_steps": 40000, "loss": 0.0, "lr": 3.0942994960398064e-05, "epoch": 188.27777777777777, "percentage": 42.36, "elapsed_time": "1:55:17", "remaining_time": "2:36:51", "throughput": 686.16, "total_tokens": 4746384} {"current_steps": 16950, "total_steps": 40000, "loss": 0.0, "lr": 3.093345845538961e-05, "epoch": 188.33333333333334, "percentage": 42.38, "elapsed_time": "1:55:19", "remaining_time": "2:36:49", "throughput": 686.18, "total_tokens": 4747856} {"current_steps": 16955, "total_steps": 40000, "loss": 0.0, "lr": 3.09239210353673e-05, "epoch": 188.38888888888889, "percentage": 42.39, "elapsed_time": "1:55:21", "remaining_time": "2:36:47", "throughput": 686.19, "total_tokens": 4749216} {"current_steps": 16960, "total_steps": 40000, "loss": 0.0, "lr": 3.0914382701801926e-05, "epoch": 188.44444444444446, "percentage": 42.4, "elapsed_time": "1:55:23", "remaining_time": "2:36:44", "throughput": 686.19, "total_tokens": 4750608} {"current_steps": 16965, "total_steps": 40000, "loss": 0.0, "lr": 3.090484345616441e-05, "epoch": 188.5, "percentage": 42.41, "elapsed_time": "1:55:25", "remaining_time": "2:36:42", "throughput": 686.2, "total_tokens": 4751984} {"current_steps": 16970, "total_steps": 40000, "loss": 0.0, "lr": 3.0895303299925825e-05, "epoch": 188.55555555555554, "percentage": 42.43, "elapsed_time": "1:55:26", "remaining_time": "2:36:40", "throughput": 686.21, "total_tokens": 4753376} {"current_steps": 16975, "total_steps": 40000, "loss": 0.0, "lr": 3.0885762234557393e-05, "epoch": 188.61111111111111, "percentage": 42.44, "elapsed_time": "1:55:28", "remaining_time": "2:36:38", "throughput": 686.22, "total_tokens": 4754784} {"current_steps": 16980, "total_steps": 40000, "loss": 0.0, "lr": 3.087622026153045e-05, "epoch": 188.66666666666666, "percentage": 42.45, "elapsed_time": "1:55:30", "remaining_time": "2:36:36", "throughput": 686.23, "total_tokens": 4756208} {"current_steps": 16985, "total_steps": 40000, "loss": 0.0, "lr": 3.086667738231651e-05, "epoch": 188.72222222222223, "percentage": 42.46, "elapsed_time": "1:55:32", "remaining_time": "2:36:34", "throughput": 686.24, "total_tokens": 4757584} {"current_steps": 16990, "total_steps": 40000, "loss": 0.0, "lr": 3.085713359838718e-05, "epoch": 188.77777777777777, "percentage": 42.48, "elapsed_time": "1:55:34", "remaining_time": "2:36:31", "throughput": 686.25, "total_tokens": 4758992} {"current_steps": 16995, "total_steps": 40000, "loss": 0.0, "lr": 3.084758891121425e-05, "epoch": 188.83333333333334, "percentage": 42.49, "elapsed_time": "1:55:36", "remaining_time": "2:36:29", "throughput": 686.26, "total_tokens": 4760368} {"current_steps": 17000, "total_steps": 40000, "loss": 0.0, "lr": 3.083804332226963e-05, "epoch": 188.88888888888889, "percentage": 42.5, "elapsed_time": "1:55:38", "remaining_time": "2:36:27", "throughput": 686.27, "total_tokens": 4761760} {"current_steps": 17000, "total_steps": 40000, "eval_loss": 0.3945319652557373, "epoch": 188.88888888888889, "percentage": 42.5, "elapsed_time": "1:55:39", "remaining_time": "2:36:29", "throughput": 686.14, "total_tokens": 4761760} {"current_steps": 17005, "total_steps": 40000, "loss": 0.0, "lr": 3.082849683302536e-05, "epoch": 188.94444444444446, "percentage": 42.51, "elapsed_time": "1:55:43", "remaining_time": "2:36:29", "throughput": 686.0, "total_tokens": 4763104} {"current_steps": 17010, "total_steps": 40000, "loss": 0.0, "lr": 3.081894944495363e-05, "epoch": 189.0, "percentage": 42.52, "elapsed_time": "1:55:45", "remaining_time": "2:36:27", "throughput": 685.99, "total_tokens": 4764544} {"current_steps": 17015, "total_steps": 40000, "loss": 0.0, "lr": 3.080940115952677e-05, "epoch": 189.05555555555554, "percentage": 42.54, "elapsed_time": "1:55:47", "remaining_time": "2:36:25", "throughput": 685.98, "total_tokens": 4765968} {"current_steps": 17020, "total_steps": 40000, "loss": 0.0, "lr": 3.0799851978217245e-05, "epoch": 189.11111111111111, "percentage": 42.55, "elapsed_time": "1:55:49", "remaining_time": "2:36:23", "throughput": 686.0, "total_tokens": 4767440} {"current_steps": 17025, "total_steps": 40000, "loss": 0.0, "lr": 3.0790301902497666e-05, "epoch": 189.16666666666666, "percentage": 42.56, "elapsed_time": "1:55:51", "remaining_time": "2:36:20", "throughput": 686.01, "total_tokens": 4768848} {"current_steps": 17030, "total_steps": 40000, "loss": 0.0, "lr": 3.078075093384076e-05, "epoch": 189.22222222222223, "percentage": 42.58, "elapsed_time": "1:55:53", "remaining_time": "2:36:18", "throughput": 686.02, "total_tokens": 4770224} {"current_steps": 17035, "total_steps": 40000, "loss": 0.0, "lr": 3.077119907371942e-05, "epoch": 189.27777777777777, "percentage": 42.59, "elapsed_time": "1:55:55", "remaining_time": "2:36:16", "throughput": 686.03, "total_tokens": 4771648} {"current_steps": 17040, "total_steps": 40000, "loss": 0.0, "lr": 3.076164632360666e-05, "epoch": 189.33333333333334, "percentage": 42.6, "elapsed_time": "1:55:57", "remaining_time": "2:36:14", "throughput": 686.04, "total_tokens": 4773024} {"current_steps": 17045, "total_steps": 40000, "loss": 0.0, "lr": 3.075209268497563e-05, "epoch": 189.38888888888889, "percentage": 42.61, "elapsed_time": "1:55:59", "remaining_time": "2:36:12", "throughput": 686.05, "total_tokens": 4774432} {"current_steps": 17050, "total_steps": 40000, "loss": 0.0, "lr": 3.074253815929961e-05, "epoch": 189.44444444444446, "percentage": 42.62, "elapsed_time": "1:56:01", "remaining_time": "2:36:10", "throughput": 686.05, "total_tokens": 4775776} {"current_steps": 17055, "total_steps": 40000, "loss": 0.0, "lr": 3.0732982748052054e-05, "epoch": 189.5, "percentage": 42.64, "elapsed_time": "1:56:03", "remaining_time": "2:36:07", "throughput": 686.06, "total_tokens": 4777184} {"current_steps": 17060, "total_steps": 40000, "loss": 0.0, "lr": 3.072342645270651e-05, "epoch": 189.55555555555554, "percentage": 42.65, "elapsed_time": "1:56:05", "remaining_time": "2:36:05", "throughput": 686.08, "total_tokens": 4778640} {"current_steps": 17065, "total_steps": 40000, "loss": 0.0, "lr": 3.071386927473668e-05, "epoch": 189.61111111111111, "percentage": 42.66, "elapsed_time": "1:56:07", "remaining_time": "2:36:03", "throughput": 686.1, "total_tokens": 4780080} {"current_steps": 17070, "total_steps": 40000, "loss": 0.0, "lr": 3.0704311215616404e-05, "epoch": 189.66666666666666, "percentage": 42.68, "elapsed_time": "1:56:08", "remaining_time": "2:36:01", "throughput": 686.11, "total_tokens": 4781488} {"current_steps": 17075, "total_steps": 40000, "loss": 0.0, "lr": 3.0694752276819656e-05, "epoch": 189.72222222222223, "percentage": 42.69, "elapsed_time": "1:56:10", "remaining_time": "2:35:59", "throughput": 686.12, "total_tokens": 4782912} {"current_steps": 17080, "total_steps": 40000, "loss": 0.0, "lr": 3.068519245982054e-05, "epoch": 189.77777777777777, "percentage": 42.7, "elapsed_time": "1:56:12", "remaining_time": "2:35:57", "throughput": 686.13, "total_tokens": 4784272} {"current_steps": 17085, "total_steps": 40000, "loss": 0.0, "lr": 3.0675631766093304e-05, "epoch": 189.83333333333334, "percentage": 42.71, "elapsed_time": "1:56:14", "remaining_time": "2:35:54", "throughput": 686.12, "total_tokens": 4785600} {"current_steps": 17090, "total_steps": 40000, "loss": 0.0, "lr": 3.066607019711232e-05, "epoch": 189.88888888888889, "percentage": 42.73, "elapsed_time": "1:56:16", "remaining_time": "2:35:52", "throughput": 686.14, "total_tokens": 4787008} {"current_steps": 17095, "total_steps": 40000, "loss": 0.0, "lr": 3.065650775435211e-05, "epoch": 189.94444444444446, "percentage": 42.74, "elapsed_time": "1:56:18", "remaining_time": "2:35:50", "throughput": 686.15, "total_tokens": 4788432} {"current_steps": 17100, "total_steps": 40000, "loss": 0.0, "lr": 3.0646944439287326e-05, "epoch": 190.0, "percentage": 42.75, "elapsed_time": "1:56:20", "remaining_time": "2:35:48", "throughput": 686.15, "total_tokens": 4789856} {"current_steps": 17105, "total_steps": 40000, "loss": 0.0, "lr": 3.0637380253392736e-05, "epoch": 190.05555555555554, "percentage": 42.76, "elapsed_time": "1:56:23", "remaining_time": "2:35:46", "throughput": 686.12, "total_tokens": 4791216} {"current_steps": 17110, "total_steps": 40000, "loss": 0.0, "lr": 3.062781519814327e-05, "epoch": 190.11111111111111, "percentage": 42.77, "elapsed_time": "1:56:24", "remaining_time": "2:35:44", "throughput": 686.14, "total_tokens": 4792640} {"current_steps": 17115, "total_steps": 40000, "loss": 0.0, "lr": 3.0618249275013985e-05, "epoch": 190.16666666666666, "percentage": 42.79, "elapsed_time": "1:56:26", "remaining_time": "2:35:42", "throughput": 686.14, "total_tokens": 4794016} {"current_steps": 17120, "total_steps": 40000, "loss": 0.0, "lr": 3.060868248548005e-05, "epoch": 190.22222222222223, "percentage": 42.8, "elapsed_time": "1:56:28", "remaining_time": "2:35:40", "throughput": 686.15, "total_tokens": 4795408} {"current_steps": 17125, "total_steps": 40000, "loss": 0.0, "lr": 3.0599114831016796e-05, "epoch": 190.27777777777777, "percentage": 42.81, "elapsed_time": "1:56:30", "remaining_time": "2:35:38", "throughput": 686.17, "total_tokens": 4796848} {"current_steps": 17130, "total_steps": 40000, "loss": 0.0, "lr": 3.0589546313099666e-05, "epoch": 190.33333333333334, "percentage": 42.83, "elapsed_time": "1:56:32", "remaining_time": "2:35:35", "throughput": 686.18, "total_tokens": 4798256} {"current_steps": 17135, "total_steps": 40000, "loss": 0.0, "lr": 3.0579976933204255e-05, "epoch": 190.38888888888889, "percentage": 42.84, "elapsed_time": "1:56:34", "remaining_time": "2:35:33", "throughput": 686.19, "total_tokens": 4799648} {"current_steps": 17140, "total_steps": 40000, "loss": 0.0, "lr": 3.0570406692806284e-05, "epoch": 190.44444444444446, "percentage": 42.85, "elapsed_time": "1:56:36", "remaining_time": "2:35:31", "throughput": 686.2, "total_tokens": 4801040} {"current_steps": 17145, "total_steps": 40000, "loss": 0.0, "lr": 3.05608355933816e-05, "epoch": 190.5, "percentage": 42.86, "elapsed_time": "1:56:38", "remaining_time": "2:35:29", "throughput": 686.21, "total_tokens": 4802448} {"current_steps": 17150, "total_steps": 40000, "loss": 0.0, "lr": 3.055126363640618e-05, "epoch": 190.55555555555554, "percentage": 42.88, "elapsed_time": "1:56:40", "remaining_time": "2:35:27", "throughput": 686.21, "total_tokens": 4803808} {"current_steps": 17155, "total_steps": 40000, "loss": 0.0, "lr": 3.0541690823356146e-05, "epoch": 190.61111111111111, "percentage": 42.89, "elapsed_time": "1:56:42", "remaining_time": "2:35:24", "throughput": 686.23, "total_tokens": 4805248} {"current_steps": 17160, "total_steps": 40000, "loss": 0.0, "lr": 3.053211715570775e-05, "epoch": 190.66666666666666, "percentage": 42.9, "elapsed_time": "1:56:44", "remaining_time": "2:35:22", "throughput": 686.24, "total_tokens": 4806656} {"current_steps": 17165, "total_steps": 40000, "loss": 0.0, "lr": 3.052254263493736e-05, "epoch": 190.72222222222223, "percentage": 42.91, "elapsed_time": "1:56:46", "remaining_time": "2:35:20", "throughput": 686.25, "total_tokens": 4808080} {"current_steps": 17170, "total_steps": 40000, "loss": 0.0, "lr": 3.0512967262521498e-05, "epoch": 190.77777777777777, "percentage": 42.93, "elapsed_time": "1:56:48", "remaining_time": "2:35:18", "throughput": 686.26, "total_tokens": 4809472} {"current_steps": 17175, "total_steps": 40000, "loss": 0.0, "lr": 3.0503391039936803e-05, "epoch": 190.83333333333334, "percentage": 42.94, "elapsed_time": "1:56:50", "remaining_time": "2:35:16", "throughput": 686.26, "total_tokens": 4810832} {"current_steps": 17180, "total_steps": 40000, "loss": 0.0, "lr": 3.0493813968660056e-05, "epoch": 190.88888888888889, "percentage": 42.95, "elapsed_time": "1:56:52", "remaining_time": "2:35:14", "throughput": 686.27, "total_tokens": 4812208} {"current_steps": 17185, "total_steps": 40000, "loss": 0.0, "lr": 3.0484236050168153e-05, "epoch": 190.94444444444446, "percentage": 42.96, "elapsed_time": "1:56:54", "remaining_time": "2:35:11", "throughput": 686.28, "total_tokens": 4813632} {"current_steps": 17190, "total_steps": 40000, "loss": 0.0, "lr": 3.0474657285938123e-05, "epoch": 191.0, "percentage": 42.98, "elapsed_time": "1:56:56", "remaining_time": "2:35:09", "throughput": 686.27, "total_tokens": 4815008} {"current_steps": 17195, "total_steps": 40000, "loss": 0.0, "lr": 3.046507767744715e-05, "epoch": 191.05555555555554, "percentage": 42.99, "elapsed_time": "1:56:58", "remaining_time": "2:35:08", "throughput": 686.26, "total_tokens": 4816384} {"current_steps": 17200, "total_steps": 40000, "loss": 0.0, "lr": 3.045549722617252e-05, "epoch": 191.11111111111111, "percentage": 43.0, "elapsed_time": "1:57:00", "remaining_time": "2:35:06", "throughput": 686.25, "total_tokens": 4817728} {"current_steps": 17200, "total_steps": 40000, "eval_loss": 0.3966147005558014, "epoch": 191.11111111111111, "percentage": 43.0, "elapsed_time": "1:57:01", "remaining_time": "2:35:07", "throughput": 686.13, "total_tokens": 4817728} {"current_steps": 17205, "total_steps": 40000, "loss": 0.0, "lr": 3.0445915933591658e-05, "epoch": 191.16666666666666, "percentage": 43.01, "elapsed_time": "1:57:05", "remaining_time": "2:35:08", "throughput": 685.93, "total_tokens": 4819104} {"current_steps": 17210, "total_steps": 40000, "loss": 0.0, "lr": 3.0436333801182114e-05, "epoch": 191.22222222222223, "percentage": 43.03, "elapsed_time": "1:57:07", "remaining_time": "2:35:06", "throughput": 685.94, "total_tokens": 4820512} {"current_steps": 17215, "total_steps": 40000, "loss": 0.0, "lr": 3.0426750830421596e-05, "epoch": 191.27777777777777, "percentage": 43.04, "elapsed_time": "1:57:09", "remaining_time": "2:35:04", "throughput": 685.95, "total_tokens": 4821936} {"current_steps": 17220, "total_steps": 40000, "loss": 0.0, "lr": 3.0417167022787897e-05, "epoch": 191.33333333333334, "percentage": 43.05, "elapsed_time": "1:57:11", "remaining_time": "2:35:01", "throughput": 685.96, "total_tokens": 4823344} {"current_steps": 17225, "total_steps": 40000, "loss": 0.0, "lr": 3.0407582379758966e-05, "epoch": 191.38888888888889, "percentage": 43.06, "elapsed_time": "1:57:13", "remaining_time": "2:34:59", "throughput": 685.97, "total_tokens": 4824736} {"current_steps": 17230, "total_steps": 40000, "loss": 0.0, "lr": 3.039799690281287e-05, "epoch": 191.44444444444446, "percentage": 43.08, "elapsed_time": "1:57:15", "remaining_time": "2:34:57", "throughput": 685.98, "total_tokens": 4826128} {"current_steps": 17235, "total_steps": 40000, "loss": 0.0, "lr": 3.0388410593427823e-05, "epoch": 191.5, "percentage": 43.09, "elapsed_time": "1:57:17", "remaining_time": "2:34:55", "throughput": 685.99, "total_tokens": 4827536} {"current_steps": 17240, "total_steps": 40000, "loss": 0.0, "lr": 3.0378823453082146e-05, "epoch": 191.55555555555554, "percentage": 43.1, "elapsed_time": "1:57:19", "remaining_time": "2:34:53", "throughput": 686.0, "total_tokens": 4828944} {"current_steps": 17245, "total_steps": 40000, "loss": 0.0, "lr": 3.03692354832543e-05, "epoch": 191.61111111111111, "percentage": 43.11, "elapsed_time": "1:57:21", "remaining_time": "2:34:50", "throughput": 686.0, "total_tokens": 4830288} {"current_steps": 17250, "total_steps": 40000, "loss": 0.0, "lr": 3.0359646685422865e-05, "epoch": 191.66666666666666, "percentage": 43.12, "elapsed_time": "1:57:23", "remaining_time": "2:34:48", "throughput": 686.02, "total_tokens": 4831712} {"current_steps": 17255, "total_steps": 40000, "loss": 0.0, "lr": 3.035005706106656e-05, "epoch": 191.72222222222223, "percentage": 43.14, "elapsed_time": "1:57:25", "remaining_time": "2:34:46", "throughput": 686.03, "total_tokens": 4833088} {"current_steps": 17260, "total_steps": 40000, "loss": 0.0, "lr": 3.034046661166422e-05, "epoch": 191.77777777777777, "percentage": 43.15, "elapsed_time": "1:57:26", "remaining_time": "2:34:44", "throughput": 686.04, "total_tokens": 4834496} {"current_steps": 17265, "total_steps": 40000, "loss": 0.0, "lr": 3.033087533869482e-05, "epoch": 191.83333333333334, "percentage": 43.16, "elapsed_time": "1:57:28", "remaining_time": "2:34:42", "throughput": 686.05, "total_tokens": 4835920} {"current_steps": 17270, "total_steps": 40000, "loss": 0.0, "lr": 3.0321283243637444e-05, "epoch": 191.88888888888889, "percentage": 43.18, "elapsed_time": "1:57:30", "remaining_time": "2:34:40", "throughput": 686.07, "total_tokens": 4837392} {"current_steps": 17275, "total_steps": 40000, "loss": 0.0, "lr": 3.0311690327971326e-05, "epoch": 191.94444444444446, "percentage": 43.19, "elapsed_time": "1:57:32", "remaining_time": "2:34:37", "throughput": 686.08, "total_tokens": 4838784} {"current_steps": 17280, "total_steps": 40000, "loss": 0.0, "lr": 3.030209659317581e-05, "epoch": 192.0, "percentage": 43.2, "elapsed_time": "1:57:34", "remaining_time": "2:34:35", "throughput": 686.08, "total_tokens": 4840208} {"current_steps": 17285, "total_steps": 40000, "loss": 0.0, "lr": 3.0292502040730362e-05, "epoch": 192.05555555555554, "percentage": 43.21, "elapsed_time": "1:57:37", "remaining_time": "2:34:34", "throughput": 686.06, "total_tokens": 4841600} {"current_steps": 17290, "total_steps": 40000, "loss": 0.0, "lr": 3.0282906672114597e-05, "epoch": 192.11111111111111, "percentage": 43.23, "elapsed_time": "1:57:39", "remaining_time": "2:34:31", "throughput": 686.06, "total_tokens": 4842944} {"current_steps": 17295, "total_steps": 40000, "loss": 0.0, "lr": 3.027331048880823e-05, "epoch": 192.16666666666666, "percentage": 43.24, "elapsed_time": "1:57:40", "remaining_time": "2:34:29", "throughput": 686.07, "total_tokens": 4844320} {"current_steps": 17300, "total_steps": 40000, "loss": 0.0, "lr": 3.0263713492291123e-05, "epoch": 192.22222222222223, "percentage": 43.25, "elapsed_time": "1:57:42", "remaining_time": "2:34:27", "throughput": 686.08, "total_tokens": 4845744} {"current_steps": 17305, "total_steps": 40000, "loss": 0.0, "lr": 3.0254115684043242e-05, "epoch": 192.27777777777777, "percentage": 43.26, "elapsed_time": "1:57:44", "remaining_time": "2:34:25", "throughput": 686.1, "total_tokens": 4847152} {"current_steps": 17310, "total_steps": 40000, "loss": 0.0, "lr": 3.024451706554469e-05, "epoch": 192.33333333333334, "percentage": 43.28, "elapsed_time": "1:57:46", "remaining_time": "2:34:23", "throughput": 686.11, "total_tokens": 4848560} {"current_steps": 17315, "total_steps": 40000, "loss": 0.0, "lr": 3.0234917638275705e-05, "epoch": 192.38888888888889, "percentage": 43.29, "elapsed_time": "1:57:48", "remaining_time": "2:34:20", "throughput": 686.12, "total_tokens": 4849952} {"current_steps": 17320, "total_steps": 40000, "loss": 0.0, "lr": 3.0225317403716635e-05, "epoch": 192.44444444444446, "percentage": 43.3, "elapsed_time": "1:57:50", "remaining_time": "2:34:18", "throughput": 686.12, "total_tokens": 4851328} {"current_steps": 17325, "total_steps": 40000, "loss": 0.0, "lr": 3.0215716363347956e-05, "epoch": 192.5, "percentage": 43.31, "elapsed_time": "1:57:52", "remaining_time": "2:34:16", "throughput": 686.14, "total_tokens": 4852752} {"current_steps": 17330, "total_steps": 40000, "loss": 0.0, "lr": 3.0206114518650275e-05, "epoch": 192.55555555555554, "percentage": 43.33, "elapsed_time": "1:57:54", "remaining_time": "2:34:14", "throughput": 686.14, "total_tokens": 4854128} {"current_steps": 17335, "total_steps": 40000, "loss": 0.0, "lr": 3.0196511871104304e-05, "epoch": 192.61111111111111, "percentage": 43.34, "elapsed_time": "1:57:56", "remaining_time": "2:34:12", "throughput": 686.16, "total_tokens": 4855568} {"current_steps": 17340, "total_steps": 40000, "loss": 0.0, "lr": 3.01869084221909e-05, "epoch": 192.66666666666666, "percentage": 43.35, "elapsed_time": "1:57:58", "remaining_time": "2:34:10", "throughput": 686.17, "total_tokens": 4856992} {"current_steps": 17345, "total_steps": 40000, "loss": 0.0, "lr": 3.0177304173391037e-05, "epoch": 192.72222222222223, "percentage": 43.36, "elapsed_time": "1:58:00", "remaining_time": "2:34:07", "throughput": 686.18, "total_tokens": 4858384} {"current_steps": 17350, "total_steps": 40000, "loss": 0.0, "lr": 3.01676991261858e-05, "epoch": 192.77777777777777, "percentage": 43.38, "elapsed_time": "1:58:02", "remaining_time": "2:34:05", "throughput": 686.19, "total_tokens": 4859760} {"current_steps": 17355, "total_steps": 40000, "loss": 0.0, "lr": 3.015809328205642e-05, "epoch": 192.83333333333334, "percentage": 43.39, "elapsed_time": "1:58:04", "remaining_time": "2:34:03", "throughput": 686.2, "total_tokens": 4861200} {"current_steps": 17360, "total_steps": 40000, "loss": 0.0, "lr": 3.0148486642484248e-05, "epoch": 192.88888888888889, "percentage": 43.4, "elapsed_time": "1:58:06", "remaining_time": "2:34:01", "throughput": 686.21, "total_tokens": 4862608} {"current_steps": 17365, "total_steps": 40000, "loss": 0.0, "lr": 3.0138879208950722e-05, "epoch": 192.94444444444446, "percentage": 43.41, "elapsed_time": "1:58:08", "remaining_time": "2:33:59", "throughput": 686.22, "total_tokens": 4863984} {"current_steps": 17370, "total_steps": 40000, "loss": 0.0, "lr": 3.012927098293744e-05, "epoch": 193.0, "percentage": 43.43, "elapsed_time": "1:58:10", "remaining_time": "2:33:57", "throughput": 686.21, "total_tokens": 4865376} {"current_steps": 17375, "total_steps": 40000, "loss": 0.0, "lr": 3.0119661965926123e-05, "epoch": 193.05555555555554, "percentage": 43.44, "elapsed_time": "1:58:12", "remaining_time": "2:33:55", "throughput": 686.2, "total_tokens": 4866768} {"current_steps": 17380, "total_steps": 40000, "loss": 0.0, "lr": 3.0110052159398587e-05, "epoch": 193.11111111111111, "percentage": 43.45, "elapsed_time": "1:58:14", "remaining_time": "2:33:53", "throughput": 686.21, "total_tokens": 4868160} {"current_steps": 17385, "total_steps": 40000, "loss": 0.0, "lr": 3.0100441564836802e-05, "epoch": 193.16666666666666, "percentage": 43.46, "elapsed_time": "1:58:16", "remaining_time": "2:33:51", "throughput": 686.22, "total_tokens": 4869600} {"current_steps": 17390, "total_steps": 40000, "loss": 0.0, "lr": 3.0090830183722817e-05, "epoch": 193.22222222222223, "percentage": 43.48, "elapsed_time": "1:58:18", "remaining_time": "2:33:48", "throughput": 686.24, "total_tokens": 4871024} {"current_steps": 17395, "total_steps": 40000, "loss": 0.0, "lr": 3.0081218017538852e-05, "epoch": 193.27777777777777, "percentage": 43.49, "elapsed_time": "1:58:20", "remaining_time": "2:33:46", "throughput": 686.25, "total_tokens": 4872448} {"current_steps": 17400, "total_steps": 40000, "loss": 0.0, "lr": 3.0071605067767212e-05, "epoch": 193.33333333333334, "percentage": 43.5, "elapsed_time": "1:58:22", "remaining_time": "2:33:44", "throughput": 686.26, "total_tokens": 4873856} {"current_steps": 17400, "total_steps": 40000, "eval_loss": 0.39010462164878845, "epoch": 193.33333333333334, "percentage": 43.5, "elapsed_time": "1:58:23", "remaining_time": "2:33:46", "throughput": 686.14, "total_tokens": 4873856} {"current_steps": 17405, "total_steps": 40000, "loss": 0.0, "lr": 3.006199133589034e-05, "epoch": 193.38888888888889, "percentage": 43.51, "elapsed_time": "1:58:26", "remaining_time": "2:33:45", "throughput": 686.03, "total_tokens": 4875264} {"current_steps": 17410, "total_steps": 40000, "loss": 0.0, "lr": 3.005237682339079e-05, "epoch": 193.44444444444446, "percentage": 43.53, "elapsed_time": "1:58:28", "remaining_time": "2:33:43", "throughput": 686.03, "total_tokens": 4876640} {"current_steps": 17415, "total_steps": 40000, "loss": 0.0, "lr": 3.0042761531751228e-05, "epoch": 193.5, "percentage": 43.54, "elapsed_time": "1:58:30", "remaining_time": "2:33:41", "throughput": 686.04, "total_tokens": 4878016} {"current_steps": 17420, "total_steps": 40000, "loss": 0.0, "lr": 3.0033145462454482e-05, "epoch": 193.55555555555554, "percentage": 43.55, "elapsed_time": "1:58:32", "remaining_time": "2:33:39", "throughput": 686.04, "total_tokens": 4879408} {"current_steps": 17425, "total_steps": 40000, "loss": 0.0, "lr": 3.002352861698345e-05, "epoch": 193.61111111111111, "percentage": 43.56, "elapsed_time": "1:58:34", "remaining_time": "2:33:36", "throughput": 686.06, "total_tokens": 4880832} {"current_steps": 17430, "total_steps": 40000, "loss": 0.0, "lr": 3.0013910996821178e-05, "epoch": 193.66666666666666, "percentage": 43.58, "elapsed_time": "1:58:36", "remaining_time": "2:33:34", "throughput": 686.07, "total_tokens": 4882240} {"current_steps": 17435, "total_steps": 40000, "loss": 0.0, "lr": 3.0004292603450817e-05, "epoch": 193.72222222222223, "percentage": 43.59, "elapsed_time": "1:58:38", "remaining_time": "2:33:32", "throughput": 686.08, "total_tokens": 4883600} {"current_steps": 17440, "total_steps": 40000, "loss": 0.0, "lr": 2.9994673438355653e-05, "epoch": 193.77777777777777, "percentage": 43.6, "elapsed_time": "1:58:40", "remaining_time": "2:33:30", "throughput": 686.09, "total_tokens": 4885024} {"current_steps": 17445, "total_steps": 40000, "loss": 0.0, "lr": 2.9985053503019078e-05, "epoch": 193.83333333333334, "percentage": 43.61, "elapsed_time": "1:58:42", "remaining_time": "2:33:28", "throughput": 686.1, "total_tokens": 4886432} {"current_steps": 17450, "total_steps": 40000, "loss": 0.0, "lr": 2.99754327989246e-05, "epoch": 193.88888888888889, "percentage": 43.62, "elapsed_time": "1:58:43", "remaining_time": "2:33:26", "throughput": 686.12, "total_tokens": 4887856} {"current_steps": 17455, "total_steps": 40000, "loss": 0.0, "lr": 2.9965811327555864e-05, "epoch": 193.94444444444446, "percentage": 43.64, "elapsed_time": "1:58:45", "remaining_time": "2:33:23", "throughput": 686.12, "total_tokens": 4889232} {"current_steps": 17460, "total_steps": 40000, "loss": 0.0, "lr": 2.995618909039662e-05, "epoch": 194.0, "percentage": 43.65, "elapsed_time": "1:58:47", "remaining_time": "2:33:21", "throughput": 686.12, "total_tokens": 4890624} {"current_steps": 17465, "total_steps": 40000, "loss": 0.0, "lr": 2.9946566088930727e-05, "epoch": 194.05555555555554, "percentage": 43.66, "elapsed_time": "1:58:50", "remaining_time": "2:33:20", "throughput": 686.1, "total_tokens": 4892048} {"current_steps": 17470, "total_steps": 40000, "loss": 0.0, "lr": 2.9936942324642192e-05, "epoch": 194.11111111111111, "percentage": 43.68, "elapsed_time": "1:58:52", "remaining_time": "2:33:17", "throughput": 686.11, "total_tokens": 4893424} {"current_steps": 17475, "total_steps": 40000, "loss": 0.0, "lr": 2.9927317799015097e-05, "epoch": 194.16666666666666, "percentage": 43.69, "elapsed_time": "1:58:54", "remaining_time": "2:33:15", "throughput": 686.12, "total_tokens": 4894848} {"current_steps": 17480, "total_steps": 40000, "loss": 0.0, "lr": 2.9917692513533685e-05, "epoch": 194.22222222222223, "percentage": 43.7, "elapsed_time": "1:58:56", "remaining_time": "2:33:13", "throughput": 686.13, "total_tokens": 4896256} {"current_steps": 17485, "total_steps": 40000, "loss": 0.0, "lr": 2.990806646968229e-05, "epoch": 194.27777777777777, "percentage": 43.71, "elapsed_time": "1:58:57", "remaining_time": "2:33:11", "throughput": 686.15, "total_tokens": 4897680} {"current_steps": 17490, "total_steps": 40000, "loss": 0.0, "lr": 2.989843966894536e-05, "epoch": 194.33333333333334, "percentage": 43.73, "elapsed_time": "1:58:59", "remaining_time": "2:33:09", "throughput": 686.16, "total_tokens": 4899088} {"current_steps": 17495, "total_steps": 40000, "loss": 0.0, "lr": 2.9888812112807472e-05, "epoch": 194.38888888888889, "percentage": 43.74, "elapsed_time": "1:59:01", "remaining_time": "2:33:07", "throughput": 686.16, "total_tokens": 4900464} {"current_steps": 17500, "total_steps": 40000, "loss": 0.0, "lr": 2.987918380275333e-05, "epoch": 194.44444444444446, "percentage": 43.75, "elapsed_time": "1:59:03", "remaining_time": "2:33:04", "throughput": 686.18, "total_tokens": 4901904} {"current_steps": 17505, "total_steps": 40000, "loss": 0.0, "lr": 2.9869554740267724e-05, "epoch": 194.5, "percentage": 43.76, "elapsed_time": "1:59:05", "remaining_time": "2:33:02", "throughput": 686.19, "total_tokens": 4903280} {"current_steps": 17510, "total_steps": 40000, "loss": 0.0, "lr": 2.9859924926835585e-05, "epoch": 194.55555555555554, "percentage": 43.77, "elapsed_time": "1:59:07", "remaining_time": "2:33:00", "throughput": 686.2, "total_tokens": 4904704} {"current_steps": 17515, "total_steps": 40000, "loss": 0.0, "lr": 2.9850294363941944e-05, "epoch": 194.61111111111111, "percentage": 43.79, "elapsed_time": "1:59:09", "remaining_time": "2:32:58", "throughput": 686.22, "total_tokens": 4906144} {"current_steps": 17520, "total_steps": 40000, "loss": 0.0, "lr": 2.9840663053071967e-05, "epoch": 194.66666666666666, "percentage": 43.8, "elapsed_time": "1:59:11", "remaining_time": "2:32:56", "throughput": 686.22, "total_tokens": 4907504} {"current_steps": 17525, "total_steps": 40000, "loss": 0.0, "lr": 2.983103099571091e-05, "epoch": 194.72222222222223, "percentage": 43.81, "elapsed_time": "1:59:13", "remaining_time": "2:32:53", "throughput": 686.23, "total_tokens": 4908928} {"current_steps": 17530, "total_steps": 40000, "loss": 0.0, "lr": 2.9821398193344164e-05, "epoch": 194.77777777777777, "percentage": 43.82, "elapsed_time": "1:59:15", "remaining_time": "2:32:51", "throughput": 686.25, "total_tokens": 4910352} {"current_steps": 17535, "total_steps": 40000, "loss": 0.0, "lr": 2.9811764647457226e-05, "epoch": 194.83333333333334, "percentage": 43.84, "elapsed_time": "1:59:17", "remaining_time": "2:32:49", "throughput": 686.25, "total_tokens": 4911728} {"current_steps": 17540, "total_steps": 40000, "loss": 0.0, "lr": 2.9802130359535714e-05, "epoch": 194.88888888888889, "percentage": 43.85, "elapsed_time": "1:59:19", "remaining_time": "2:32:47", "throughput": 686.26, "total_tokens": 4913120} {"current_steps": 17545, "total_steps": 40000, "loss": 0.0, "lr": 2.979249533106535e-05, "epoch": 194.94444444444446, "percentage": 43.86, "elapsed_time": "1:59:21", "remaining_time": "2:32:45", "throughput": 686.27, "total_tokens": 4914496} {"current_steps": 17550, "total_steps": 40000, "loss": 0.0, "lr": 2.9782859563531986e-05, "epoch": 195.0, "percentage": 43.88, "elapsed_time": "1:59:23", "remaining_time": "2:32:43", "throughput": 686.26, "total_tokens": 4915904} {"current_steps": 17555, "total_steps": 40000, "loss": 0.0, "lr": 2.977322305842156e-05, "epoch": 195.05555555555554, "percentage": 43.89, "elapsed_time": "1:59:25", "remaining_time": "2:32:41", "throughput": 686.26, "total_tokens": 4917344} {"current_steps": 17560, "total_steps": 40000, "loss": 0.0, "lr": 2.9763585817220162e-05, "epoch": 195.11111111111111, "percentage": 43.9, "elapsed_time": "1:59:27", "remaining_time": "2:32:39", "throughput": 686.27, "total_tokens": 4918800} {"current_steps": 17565, "total_steps": 40000, "loss": 0.0, "lr": 2.975394784141397e-05, "epoch": 195.16666666666666, "percentage": 43.91, "elapsed_time": "1:59:29", "remaining_time": "2:32:37", "throughput": 686.28, "total_tokens": 4920192} {"current_steps": 17570, "total_steps": 40000, "loss": 0.0, "lr": 2.974430913248928e-05, "epoch": 195.22222222222223, "percentage": 43.92, "elapsed_time": "1:59:31", "remaining_time": "2:32:34", "throughput": 686.3, "total_tokens": 4921632} {"current_steps": 17575, "total_steps": 40000, "loss": 0.0, "lr": 2.9734669691932497e-05, "epoch": 195.27777777777777, "percentage": 43.94, "elapsed_time": "1:59:33", "remaining_time": "2:32:32", "throughput": 686.3, "total_tokens": 4922976} {"current_steps": 17580, "total_steps": 40000, "loss": 0.0, "lr": 2.9725029521230147e-05, "epoch": 195.33333333333334, "percentage": 43.95, "elapsed_time": "1:59:35", "remaining_time": "2:32:30", "throughput": 686.31, "total_tokens": 4924400} {"current_steps": 17585, "total_steps": 40000, "loss": 0.0, "lr": 2.9715388621868873e-05, "epoch": 195.38888888888889, "percentage": 43.96, "elapsed_time": "1:59:37", "remaining_time": "2:32:28", "throughput": 686.32, "total_tokens": 4925792} {"current_steps": 17590, "total_steps": 40000, "loss": 0.0, "lr": 2.970574699533541e-05, "epoch": 195.44444444444446, "percentage": 43.97, "elapsed_time": "1:59:39", "remaining_time": "2:32:26", "throughput": 686.33, "total_tokens": 4927200} {"current_steps": 17595, "total_steps": 40000, "loss": 0.0, "lr": 2.969610464311662e-05, "epoch": 195.5, "percentage": 43.99, "elapsed_time": "1:59:40", "remaining_time": "2:32:24", "throughput": 686.34, "total_tokens": 4928544} {"current_steps": 17600, "total_steps": 40000, "loss": 0.0, "lr": 2.9686461566699487e-05, "epoch": 195.55555555555554, "percentage": 44.0, "elapsed_time": "1:59:42", "remaining_time": "2:32:21", "throughput": 686.34, "total_tokens": 4929936} {"current_steps": 17600, "total_steps": 40000, "eval_loss": 0.40182334184646606, "epoch": 195.55555555555554, "percentage": 44.0, "elapsed_time": "1:59:44", "remaining_time": "2:32:23", "throughput": 686.22, "total_tokens": 4929936} {"current_steps": 17605, "total_steps": 40000, "loss": 0.0, "lr": 2.9676817767571086e-05, "epoch": 195.61111111111111, "percentage": 44.01, "elapsed_time": "1:59:47", "remaining_time": "2:32:23", "throughput": 686.09, "total_tokens": 4931296} {"current_steps": 17610, "total_steps": 40000, "loss": 0.0, "lr": 2.966717324721861e-05, "epoch": 195.66666666666666, "percentage": 44.02, "elapsed_time": "1:59:49", "remaining_time": "2:32:20", "throughput": 686.1, "total_tokens": 4932720} {"current_steps": 17615, "total_steps": 40000, "loss": 0.0, "lr": 2.9657528007129366e-05, "epoch": 195.72222222222223, "percentage": 44.04, "elapsed_time": "1:59:51", "remaining_time": "2:32:18", "throughput": 686.11, "total_tokens": 4934144} {"current_steps": 17620, "total_steps": 40000, "loss": 0.0, "lr": 2.9647882048790777e-05, "epoch": 195.77777777777777, "percentage": 44.05, "elapsed_time": "1:59:53", "remaining_time": "2:32:16", "throughput": 686.13, "total_tokens": 4935552} {"current_steps": 17625, "total_steps": 40000, "loss": 0.0, "lr": 2.963823537369037e-05, "epoch": 195.83333333333334, "percentage": 44.06, "elapsed_time": "1:59:55", "remaining_time": "2:32:14", "throughput": 686.13, "total_tokens": 4936912} {"current_steps": 17630, "total_steps": 40000, "loss": 0.0, "lr": 2.9628587983315775e-05, "epoch": 195.88888888888889, "percentage": 44.07, "elapsed_time": "1:59:57", "remaining_time": "2:32:12", "throughput": 686.15, "total_tokens": 4938352} {"current_steps": 17635, "total_steps": 40000, "loss": 0.0, "lr": 2.9618939879154746e-05, "epoch": 195.94444444444446, "percentage": 44.09, "elapsed_time": "1:59:59", "remaining_time": "2:32:10", "throughput": 686.16, "total_tokens": 4939760} {"current_steps": 17640, "total_steps": 40000, "loss": 0.0, "lr": 2.9609291062695143e-05, "epoch": 196.0, "percentage": 44.1, "elapsed_time": "2:00:01", "remaining_time": "2:32:08", "throughput": 686.15, "total_tokens": 4941168} {"current_steps": 17645, "total_steps": 40000, "loss": 0.0, "lr": 2.9599641535424938e-05, "epoch": 196.05555555555554, "percentage": 44.11, "elapsed_time": "2:00:03", "remaining_time": "2:32:06", "throughput": 686.13, "total_tokens": 4942544} {"current_steps": 17650, "total_steps": 40000, "loss": 0.0, "lr": 2.9589991298832202e-05, "epoch": 196.11111111111111, "percentage": 44.12, "elapsed_time": "2:00:05", "remaining_time": "2:32:04", "throughput": 686.14, "total_tokens": 4943920} {"current_steps": 17655, "total_steps": 40000, "loss": 0.0, "lr": 2.958034035440513e-05, "epoch": 196.16666666666666, "percentage": 44.14, "elapsed_time": "2:00:07", "remaining_time": "2:32:01", "throughput": 686.15, "total_tokens": 4945296} {"current_steps": 17660, "total_steps": 40000, "loss": 0.0, "lr": 2.957068870363201e-05, "epoch": 196.22222222222223, "percentage": 44.15, "elapsed_time": "2:00:09", "remaining_time": "2:31:59", "throughput": 686.17, "total_tokens": 4946768} {"current_steps": 17665, "total_steps": 40000, "loss": 0.0, "lr": 2.956103634800126e-05, "epoch": 196.27777777777777, "percentage": 44.16, "elapsed_time": "2:00:11", "remaining_time": "2:31:57", "throughput": 686.18, "total_tokens": 4948176} {"current_steps": 17670, "total_steps": 40000, "loss": 0.0, "lr": 2.9551383289001384e-05, "epoch": 196.33333333333334, "percentage": 44.17, "elapsed_time": "2:00:13", "remaining_time": "2:31:55", "throughput": 686.19, "total_tokens": 4949584} {"current_steps": 17675, "total_steps": 40000, "loss": 0.0, "lr": 2.9541729528121005e-05, "epoch": 196.38888888888889, "percentage": 44.19, "elapsed_time": "2:00:15", "remaining_time": "2:31:53", "throughput": 686.2, "total_tokens": 4950992} {"current_steps": 17680, "total_steps": 40000, "loss": 0.0, "lr": 2.9532075066848856e-05, "epoch": 196.44444444444446, "percentage": 44.2, "elapsed_time": "2:00:17", "remaining_time": "2:31:51", "throughput": 686.2, "total_tokens": 4952352} {"current_steps": 17685, "total_steps": 40000, "loss": 0.0, "lr": 2.9522419906673786e-05, "epoch": 196.5, "percentage": 44.21, "elapsed_time": "2:00:18", "remaining_time": "2:31:48", "throughput": 686.21, "total_tokens": 4953712} {"current_steps": 17690, "total_steps": 40000, "loss": 0.0, "lr": 2.951276404908474e-05, "epoch": 196.55555555555554, "percentage": 44.22, "elapsed_time": "2:00:20", "remaining_time": "2:31:46", "throughput": 686.22, "total_tokens": 4955120} {"current_steps": 17695, "total_steps": 40000, "loss": 0.0, "lr": 2.9503107495570752e-05, "epoch": 196.61111111111111, "percentage": 44.24, "elapsed_time": "2:00:22", "remaining_time": "2:31:44", "throughput": 686.24, "total_tokens": 4956576} {"current_steps": 17700, "total_steps": 40000, "loss": 0.0, "lr": 2.9493450247621003e-05, "epoch": 196.66666666666666, "percentage": 44.25, "elapsed_time": "2:00:24", "remaining_time": "2:31:42", "throughput": 686.25, "total_tokens": 4957984} {"current_steps": 17705, "total_steps": 40000, "loss": 0.0, "lr": 2.948379230672476e-05, "epoch": 196.72222222222223, "percentage": 44.26, "elapsed_time": "2:00:26", "remaining_time": "2:31:40", "throughput": 686.26, "total_tokens": 4959360} {"current_steps": 17710, "total_steps": 40000, "loss": 0.0, "lr": 2.9474133674371396e-05, "epoch": 196.77777777777777, "percentage": 44.27, "elapsed_time": "2:00:28", "remaining_time": "2:31:38", "throughput": 686.26, "total_tokens": 4960720} {"current_steps": 17715, "total_steps": 40000, "loss": 0.0, "lr": 2.9464474352050387e-05, "epoch": 196.83333333333334, "percentage": 44.29, "elapsed_time": "2:00:30", "remaining_time": "2:31:35", "throughput": 686.26, "total_tokens": 4962048} {"current_steps": 17720, "total_steps": 40000, "loss": 0.0, "lr": 2.9454814341251336e-05, "epoch": 196.88888888888889, "percentage": 44.3, "elapsed_time": "2:00:32", "remaining_time": "2:31:33", "throughput": 686.27, "total_tokens": 4963440} {"current_steps": 17725, "total_steps": 40000, "loss": 0.0, "lr": 2.9445153643463942e-05, "epoch": 196.94444444444446, "percentage": 44.31, "elapsed_time": "2:00:34", "remaining_time": "2:31:31", "throughput": 686.28, "total_tokens": 4964848} {"current_steps": 17730, "total_steps": 40000, "loss": 0.0, "lr": 2.943549226017798e-05, "epoch": 197.0, "percentage": 44.32, "elapsed_time": "2:00:36", "remaining_time": "2:31:29", "throughput": 686.28, "total_tokens": 4966272} {"current_steps": 17735, "total_steps": 40000, "loss": 0.0, "lr": 2.942583019288337e-05, "epoch": 197.05555555555554, "percentage": 44.34, "elapsed_time": "2:00:38", "remaining_time": "2:31:27", "throughput": 686.26, "total_tokens": 4967648} {"current_steps": 17740, "total_steps": 40000, "loss": 0.0, "lr": 2.9416167443070132e-05, "epoch": 197.11111111111111, "percentage": 44.35, "elapsed_time": "2:00:40", "remaining_time": "2:31:25", "throughput": 686.27, "total_tokens": 4969040} {"current_steps": 17745, "total_steps": 40000, "loss": 0.0, "lr": 2.9406504012228375e-05, "epoch": 197.16666666666666, "percentage": 44.36, "elapsed_time": "2:00:42", "remaining_time": "2:31:23", "throughput": 686.27, "total_tokens": 4970432} {"current_steps": 17750, "total_steps": 40000, "loss": 0.0, "lr": 2.939683990184832e-05, "epoch": 197.22222222222223, "percentage": 44.38, "elapsed_time": "2:00:44", "remaining_time": "2:31:21", "throughput": 686.28, "total_tokens": 4971792} {"current_steps": 17755, "total_steps": 40000, "loss": 0.0, "lr": 2.93871751134203e-05, "epoch": 197.27777777777777, "percentage": 44.39, "elapsed_time": "2:00:46", "remaining_time": "2:31:19", "throughput": 686.29, "total_tokens": 4973200} {"current_steps": 17760, "total_steps": 40000, "loss": 0.0, "lr": 2.9377509648434752e-05, "epoch": 197.33333333333334, "percentage": 44.4, "elapsed_time": "2:00:48", "remaining_time": "2:31:16", "throughput": 686.3, "total_tokens": 4974592} {"current_steps": 17765, "total_steps": 40000, "loss": 0.0, "lr": 2.9367843508382203e-05, "epoch": 197.38888888888889, "percentage": 44.41, "elapsed_time": "2:00:50", "remaining_time": "2:31:14", "throughput": 686.31, "total_tokens": 4976016} {"current_steps": 17770, "total_steps": 40000, "loss": 0.0, "lr": 2.9358176694753293e-05, "epoch": 197.44444444444446, "percentage": 44.42, "elapsed_time": "2:00:52", "remaining_time": "2:31:12", "throughput": 686.32, "total_tokens": 4977424} {"current_steps": 17775, "total_steps": 40000, "loss": 0.0, "lr": 2.9348509209038766e-05, "epoch": 197.5, "percentage": 44.44, "elapsed_time": "2:00:54", "remaining_time": "2:31:10", "throughput": 686.33, "total_tokens": 4978800} {"current_steps": 17780, "total_steps": 40000, "loss": 0.0, "lr": 2.933884105272947e-05, "epoch": 197.55555555555554, "percentage": 44.45, "elapsed_time": "2:00:56", "remaining_time": "2:31:08", "throughput": 686.34, "total_tokens": 4980240} {"current_steps": 17785, "total_steps": 40000, "loss": 0.0, "lr": 2.9329172227316366e-05, "epoch": 197.61111111111111, "percentage": 44.46, "elapsed_time": "2:00:58", "remaining_time": "2:31:06", "throughput": 686.35, "total_tokens": 4981648} {"current_steps": 17790, "total_steps": 40000, "loss": 0.0, "lr": 2.93195027342905e-05, "epoch": 197.66666666666666, "percentage": 44.47, "elapsed_time": "2:01:00", "remaining_time": "2:31:03", "throughput": 686.36, "total_tokens": 4983040} {"current_steps": 17795, "total_steps": 40000, "loss": 0.0, "lr": 2.9309832575143024e-05, "epoch": 197.72222222222223, "percentage": 44.49, "elapsed_time": "2:01:02", "remaining_time": "2:31:01", "throughput": 686.37, "total_tokens": 4984448} {"current_steps": 17800, "total_steps": 40000, "loss": 0.0, "lr": 2.930016175136521e-05, "epoch": 197.77777777777777, "percentage": 44.5, "elapsed_time": "2:01:03", "remaining_time": "2:30:59", "throughput": 686.38, "total_tokens": 4985840} {"current_steps": 17800, "total_steps": 40000, "eval_loss": 0.366407573223114, "epoch": 197.77777777777777, "percentage": 44.5, "elapsed_time": "2:01:05", "remaining_time": "2:31:01", "throughput": 686.26, "total_tokens": 4985840} {"current_steps": 17805, "total_steps": 40000, "loss": 0.0, "lr": 2.9290490264448412e-05, "epoch": 197.83333333333334, "percentage": 44.51, "elapsed_time": "2:01:08", "remaining_time": "2:31:00", "throughput": 686.15, "total_tokens": 4987280} {"current_steps": 17810, "total_steps": 40000, "loss": 0.0, "lr": 2.9280818115884094e-05, "epoch": 197.88888888888889, "percentage": 44.52, "elapsed_time": "2:01:10", "remaining_time": "2:30:58", "throughput": 686.17, "total_tokens": 4988704} {"current_steps": 17815, "total_steps": 40000, "loss": 0.0, "lr": 2.9271145307163828e-05, "epoch": 197.94444444444446, "percentage": 44.54, "elapsed_time": "2:01:12", "remaining_time": "2:30:56", "throughput": 686.18, "total_tokens": 4990112} {"current_steps": 17820, "total_steps": 40000, "loss": 0.0, "lr": 2.9261471839779287e-05, "epoch": 198.0, "percentage": 44.55, "elapsed_time": "2:01:14", "remaining_time": "2:30:54", "throughput": 686.17, "total_tokens": 4991520} {"current_steps": 17825, "total_steps": 40000, "loss": 0.0, "lr": 2.925179771522223e-05, "epoch": 198.05555555555554, "percentage": 44.56, "elapsed_time": "2:01:16", "remaining_time": "2:30:52", "throughput": 686.15, "total_tokens": 4992928} {"current_steps": 17830, "total_steps": 40000, "loss": 0.0, "lr": 2.9242122934984535e-05, "epoch": 198.11111111111111, "percentage": 44.57, "elapsed_time": "2:01:18", "remaining_time": "2:30:50", "throughput": 686.17, "total_tokens": 4994336} {"current_steps": 17835, "total_steps": 40000, "loss": 0.0, "lr": 2.9232447500558176e-05, "epoch": 198.16666666666666, "percentage": 44.59, "elapsed_time": "2:01:20", "remaining_time": "2:30:48", "throughput": 686.18, "total_tokens": 4995744} {"current_steps": 17840, "total_steps": 40000, "loss": 0.0, "lr": 2.9222771413435225e-05, "epoch": 198.22222222222223, "percentage": 44.6, "elapsed_time": "2:01:22", "remaining_time": "2:30:45", "throughput": 686.18, "total_tokens": 4997136} {"current_steps": 17845, "total_steps": 40000, "loss": 0.0, "lr": 2.9213094675107848e-05, "epoch": 198.27777777777777, "percentage": 44.61, "elapsed_time": "2:01:24", "remaining_time": "2:30:43", "throughput": 686.2, "total_tokens": 4998592} {"current_steps": 17850, "total_steps": 40000, "loss": 0.0, "lr": 2.9203417287068335e-05, "epoch": 198.33333333333334, "percentage": 44.62, "elapsed_time": "2:01:26", "remaining_time": "2:30:41", "throughput": 686.22, "total_tokens": 5000016} {"current_steps": 17855, "total_steps": 40000, "loss": 0.0, "lr": 2.9193739250809042e-05, "epoch": 198.38888888888889, "percentage": 44.64, "elapsed_time": "2:01:28", "remaining_time": "2:30:39", "throughput": 686.23, "total_tokens": 5001424} {"current_steps": 17860, "total_steps": 40000, "loss": 0.0, "lr": 2.9184060567822463e-05, "epoch": 198.44444444444446, "percentage": 44.65, "elapsed_time": "2:01:30", "remaining_time": "2:30:37", "throughput": 686.23, "total_tokens": 5002768} {"current_steps": 17865, "total_steps": 40000, "loss": 0.0, "lr": 2.9174381239601166e-05, "epoch": 198.5, "percentage": 44.66, "elapsed_time": "2:01:32", "remaining_time": "2:30:35", "throughput": 686.24, "total_tokens": 5004192} {"current_steps": 17870, "total_steps": 40000, "loss": 0.0, "lr": 2.916470126763783e-05, "epoch": 198.55555555555554, "percentage": 44.67, "elapsed_time": "2:01:34", "remaining_time": "2:30:32", "throughput": 686.25, "total_tokens": 5005584} {"current_steps": 17875, "total_steps": 40000, "loss": 0.0, "lr": 2.9155020653425203e-05, "epoch": 198.61111111111111, "percentage": 44.69, "elapsed_time": "2:01:36", "remaining_time": "2:30:31", "throughput": 686.23, "total_tokens": 5006976} {"current_steps": 17880, "total_steps": 40000, "loss": 0.0, "lr": 2.9145339398456184e-05, "epoch": 198.66666666666666, "percentage": 44.7, "elapsed_time": "2:01:38", "remaining_time": "2:30:28", "throughput": 686.24, "total_tokens": 5008400} {"current_steps": 17885, "total_steps": 40000, "loss": 0.0, "lr": 2.913565750422374e-05, "epoch": 198.72222222222223, "percentage": 44.71, "elapsed_time": "2:01:40", "remaining_time": "2:30:26", "throughput": 686.26, "total_tokens": 5009824} {"current_steps": 17890, "total_steps": 40000, "loss": 0.0, "lr": 2.9125974972220938e-05, "epoch": 198.77777777777777, "percentage": 44.73, "elapsed_time": "2:01:42", "remaining_time": "2:30:24", "throughput": 686.26, "total_tokens": 5011200} {"current_steps": 17895, "total_steps": 40000, "loss": 0.0, "lr": 2.9116291803940932e-05, "epoch": 198.83333333333334, "percentage": 44.74, "elapsed_time": "2:01:44", "remaining_time": "2:30:22", "throughput": 686.27, "total_tokens": 5012592} {"current_steps": 17900, "total_steps": 40000, "loss": 0.0, "lr": 2.910660800087701e-05, "epoch": 198.88888888888889, "percentage": 44.75, "elapsed_time": "2:01:46", "remaining_time": "2:30:20", "throughput": 686.28, "total_tokens": 5013968} {"current_steps": 17905, "total_steps": 40000, "loss": 0.0, "lr": 2.909692356452254e-05, "epoch": 198.94444444444446, "percentage": 44.76, "elapsed_time": "2:01:47", "remaining_time": "2:30:18", "throughput": 686.29, "total_tokens": 5015408} {"current_steps": 17910, "total_steps": 40000, "loss": 0.0, "lr": 2.9087238496370962e-05, "epoch": 199.0, "percentage": 44.77, "elapsed_time": "2:01:50", "remaining_time": "2:30:16", "throughput": 686.28, "total_tokens": 5016768} {"current_steps": 17915, "total_steps": 40000, "loss": 0.0, "lr": 2.907755279791583e-05, "epoch": 199.05555555555554, "percentage": 44.79, "elapsed_time": "2:01:52", "remaining_time": "2:30:14", "throughput": 686.27, "total_tokens": 5018160} {"current_steps": 17920, "total_steps": 40000, "loss": 0.0, "lr": 2.906786647065083e-05, "epoch": 199.11111111111111, "percentage": 44.8, "elapsed_time": "2:01:54", "remaining_time": "2:30:12", "throughput": 686.29, "total_tokens": 5019632} {"current_steps": 17925, "total_steps": 40000, "loss": 0.0, "lr": 2.9058179516069695e-05, "epoch": 199.16666666666666, "percentage": 44.81, "elapsed_time": "2:01:56", "remaining_time": "2:30:09", "throughput": 686.3, "total_tokens": 5021056} {"current_steps": 17930, "total_steps": 40000, "loss": 0.0, "lr": 2.9048491935666282e-05, "epoch": 199.22222222222223, "percentage": 44.82, "elapsed_time": "2:01:58", "remaining_time": "2:30:07", "throughput": 686.31, "total_tokens": 5022448} {"current_steps": 17935, "total_steps": 40000, "loss": 0.0, "lr": 2.9038803730934534e-05, "epoch": 199.27777777777777, "percentage": 44.84, "elapsed_time": "2:01:59", "remaining_time": "2:30:05", "throughput": 686.32, "total_tokens": 5023840} {"current_steps": 17940, "total_steps": 40000, "loss": 0.0, "lr": 2.9029114903368503e-05, "epoch": 199.33333333333334, "percentage": 44.85, "elapsed_time": "2:02:01", "remaining_time": "2:30:03", "throughput": 686.32, "total_tokens": 5025200} {"current_steps": 17945, "total_steps": 40000, "loss": 0.0, "lr": 2.9019425454462318e-05, "epoch": 199.38888888888889, "percentage": 44.86, "elapsed_time": "2:02:03", "remaining_time": "2:30:01", "throughput": 686.33, "total_tokens": 5026576} {"current_steps": 17950, "total_steps": 40000, "loss": 0.0, "lr": 2.9009735385710212e-05, "epoch": 199.44444444444446, "percentage": 44.88, "elapsed_time": "2:02:05", "remaining_time": "2:29:59", "throughput": 686.33, "total_tokens": 5027936} {"current_steps": 17955, "total_steps": 40000, "loss": 0.0, "lr": 2.900004469860652e-05, "epoch": 199.5, "percentage": 44.89, "elapsed_time": "2:02:07", "remaining_time": "2:29:56", "throughput": 686.34, "total_tokens": 5029344} {"current_steps": 17960, "total_steps": 40000, "loss": 0.0, "lr": 2.8990353394645668e-05, "epoch": 199.55555555555554, "percentage": 44.9, "elapsed_time": "2:02:09", "remaining_time": "2:29:54", "throughput": 686.36, "total_tokens": 5030800} {"current_steps": 17965, "total_steps": 40000, "loss": 0.0, "lr": 2.8980661475322186e-05, "epoch": 199.61111111111111, "percentage": 44.91, "elapsed_time": "2:02:11", "remaining_time": "2:29:52", "throughput": 686.38, "total_tokens": 5032224} {"current_steps": 17970, "total_steps": 40000, "loss": 0.0, "lr": 2.897096894213067e-05, "epoch": 199.66666666666666, "percentage": 44.92, "elapsed_time": "2:02:13", "remaining_time": "2:29:50", "throughput": 686.38, "total_tokens": 5033600} {"current_steps": 17975, "total_steps": 40000, "loss": 0.0, "lr": 2.8961275796565845e-05, "epoch": 199.72222222222223, "percentage": 44.94, "elapsed_time": "2:02:15", "remaining_time": "2:29:48", "throughput": 686.39, "total_tokens": 5034976} {"current_steps": 17980, "total_steps": 40000, "loss": 0.0, "lr": 2.8951582040122517e-05, "epoch": 199.77777777777777, "percentage": 44.95, "elapsed_time": "2:02:17", "remaining_time": "2:29:46", "throughput": 686.39, "total_tokens": 5036336} {"current_steps": 17985, "total_steps": 40000, "loss": 0.0, "lr": 2.894188767429557e-05, "epoch": 199.83333333333334, "percentage": 44.96, "elapsed_time": "2:02:19", "remaining_time": "2:29:43", "throughput": 686.4, "total_tokens": 5037712} {"current_steps": 17990, "total_steps": 40000, "loss": 0.0, "lr": 2.8932192700580014e-05, "epoch": 199.88888888888889, "percentage": 44.98, "elapsed_time": "2:02:21", "remaining_time": "2:29:41", "throughput": 686.41, "total_tokens": 5039104} {"current_steps": 17995, "total_steps": 40000, "loss": 0.0, "lr": 2.8922497120470916e-05, "epoch": 199.94444444444446, "percentage": 44.99, "elapsed_time": "2:02:23", "remaining_time": "2:29:39", "throughput": 686.41, "total_tokens": 5040480} {"current_steps": 18000, "total_steps": 40000, "loss": 0.0, "lr": 2.891280093546348e-05, "epoch": 200.0, "percentage": 45.0, "elapsed_time": "2:02:25", "remaining_time": "2:29:37", "throughput": 686.41, "total_tokens": 5041920} {"current_steps": 18000, "total_steps": 40000, "eval_loss": 0.3877609968185425, "epoch": 200.0, "percentage": 45.0, "elapsed_time": "2:02:26", "remaining_time": "2:29:39", "throughput": 686.29, "total_tokens": 5041920} {"current_steps": 18005, "total_steps": 40000, "loss": 0.0, "lr": 2.890310414705297e-05, "epoch": 200.05555555555554, "percentage": 45.01, "elapsed_time": "2:02:30", "remaining_time": "2:29:38", "throughput": 686.17, "total_tokens": 5043344} {"current_steps": 18010, "total_steps": 40000, "loss": 0.0, "lr": 2.8893406756734742e-05, "epoch": 200.11111111111111, "percentage": 45.02, "elapsed_time": "2:02:32", "remaining_time": "2:29:36", "throughput": 686.17, "total_tokens": 5044704} {"current_steps": 18015, "total_steps": 40000, "loss": 0.0, "lr": 2.888370876600427e-05, "epoch": 200.16666666666666, "percentage": 45.04, "elapsed_time": "2:02:33", "remaining_time": "2:29:34", "throughput": 686.17, "total_tokens": 5046112} {"current_steps": 18020, "total_steps": 40000, "loss": 0.0, "lr": 2.8874010176357104e-05, "epoch": 200.22222222222223, "percentage": 45.05, "elapsed_time": "2:02:35", "remaining_time": "2:29:32", "throughput": 686.19, "total_tokens": 5047520} {"current_steps": 18025, "total_steps": 40000, "loss": 0.0, "lr": 2.886431098928888e-05, "epoch": 200.27777777777777, "percentage": 45.06, "elapsed_time": "2:02:37", "remaining_time": "2:29:30", "throughput": 686.2, "total_tokens": 5048928} {"current_steps": 18030, "total_steps": 40000, "loss": 0.0, "lr": 2.885461120629534e-05, "epoch": 200.33333333333334, "percentage": 45.07, "elapsed_time": "2:02:39", "remaining_time": "2:29:28", "throughput": 686.21, "total_tokens": 5050352} {"current_steps": 18035, "total_steps": 40000, "loss": 0.0, "lr": 2.8844910828872317e-05, "epoch": 200.38888888888889, "percentage": 45.09, "elapsed_time": "2:02:41", "remaining_time": "2:29:25", "throughput": 686.22, "total_tokens": 5051760} {"current_steps": 18040, "total_steps": 40000, "loss": 0.0, "lr": 2.8835209858515715e-05, "epoch": 200.44444444444446, "percentage": 45.1, "elapsed_time": "2:02:43", "remaining_time": "2:29:23", "throughput": 686.23, "total_tokens": 5053152} {"current_steps": 18045, "total_steps": 40000, "loss": 0.0, "lr": 2.8825508296721566e-05, "epoch": 200.5, "percentage": 45.11, "elapsed_time": "2:02:45", "remaining_time": "2:29:21", "throughput": 686.23, "total_tokens": 5054528} {"current_steps": 18050, "total_steps": 40000, "loss": 0.0, "lr": 2.881580614498596e-05, "epoch": 200.55555555555554, "percentage": 45.12, "elapsed_time": "2:02:47", "remaining_time": "2:29:19", "throughput": 686.25, "total_tokens": 5055952} {"current_steps": 18055, "total_steps": 40000, "loss": 0.0, "lr": 2.8806103404805103e-05, "epoch": 200.61111111111111, "percentage": 45.14, "elapsed_time": "2:02:49", "remaining_time": "2:29:17", "throughput": 686.25, "total_tokens": 5057312} {"current_steps": 18060, "total_steps": 40000, "loss": 0.0, "lr": 2.8796400077675257e-05, "epoch": 200.66666666666666, "percentage": 45.15, "elapsed_time": "2:02:51", "remaining_time": "2:29:15", "throughput": 686.26, "total_tokens": 5058672} {"current_steps": 18065, "total_steps": 40000, "loss": 0.0, "lr": 2.8786696165092812e-05, "epoch": 200.72222222222223, "percentage": 45.16, "elapsed_time": "2:02:53", "remaining_time": "2:29:12", "throughput": 686.26, "total_tokens": 5060032} {"current_steps": 18070, "total_steps": 40000, "loss": 0.0, "lr": 2.8776991668554236e-05, "epoch": 200.77777777777777, "percentage": 45.17, "elapsed_time": "2:02:55", "remaining_time": "2:29:10", "throughput": 686.27, "total_tokens": 5061440} {"current_steps": 18075, "total_steps": 40000, "loss": 0.0, "lr": 2.876728658955608e-05, "epoch": 200.83333333333334, "percentage": 45.19, "elapsed_time": "2:02:57", "remaining_time": "2:29:08", "throughput": 686.28, "total_tokens": 5062832} {"current_steps": 18080, "total_steps": 40000, "loss": 0.0, "lr": 2.8757580929594986e-05, "epoch": 200.88888888888889, "percentage": 45.2, "elapsed_time": "2:02:59", "remaining_time": "2:29:06", "throughput": 686.3, "total_tokens": 5064272} {"current_steps": 18085, "total_steps": 40000, "loss": 0.0, "lr": 2.87478746901677e-05, "epoch": 200.94444444444446, "percentage": 45.21, "elapsed_time": "2:03:01", "remaining_time": "2:29:04", "throughput": 686.31, "total_tokens": 5065680} {"current_steps": 18090, "total_steps": 40000, "loss": 0.0, "lr": 2.873816787277103e-05, "epoch": 201.0, "percentage": 45.23, "elapsed_time": "2:03:03", "remaining_time": "2:29:02", "throughput": 686.3, "total_tokens": 5067088} {"current_steps": 18095, "total_steps": 40000, "loss": 0.0, "lr": 2.8728460478901903e-05, "epoch": 201.05555555555554, "percentage": 45.24, "elapsed_time": "2:03:05", "remaining_time": "2:29:00", "throughput": 686.29, "total_tokens": 5068496} {"current_steps": 18100, "total_steps": 40000, "loss": 0.0, "lr": 2.8718752510057307e-05, "epoch": 201.11111111111111, "percentage": 45.25, "elapsed_time": "2:03:07", "remaining_time": "2:28:58", "throughput": 686.3, "total_tokens": 5069872} {"current_steps": 18105, "total_steps": 40000, "loss": 0.0, "lr": 2.870904396773435e-05, "epoch": 201.16666666666666, "percentage": 45.26, "elapsed_time": "2:03:09", "remaining_time": "2:28:56", "throughput": 686.31, "total_tokens": 5071312} {"current_steps": 18110, "total_steps": 40000, "loss": 0.0, "lr": 2.86993348534302e-05, "epoch": 201.22222222222223, "percentage": 45.27, "elapsed_time": "2:03:11", "remaining_time": "2:28:53", "throughput": 686.32, "total_tokens": 5072688} {"current_steps": 18115, "total_steps": 40000, "loss": 0.0, "lr": 2.868962516864212e-05, "epoch": 201.27777777777777, "percentage": 45.29, "elapsed_time": "2:03:13", "remaining_time": "2:28:51", "throughput": 686.33, "total_tokens": 5074112} {"current_steps": 18120, "total_steps": 40000, "loss": 0.0, "lr": 2.8679914914867477e-05, "epoch": 201.33333333333334, "percentage": 45.3, "elapsed_time": "2:03:15", "remaining_time": "2:28:49", "throughput": 686.34, "total_tokens": 5075504} {"current_steps": 18125, "total_steps": 40000, "loss": 0.0, "lr": 2.8670204093603713e-05, "epoch": 201.38888888888889, "percentage": 45.31, "elapsed_time": "2:03:16", "remaining_time": "2:28:47", "throughput": 686.35, "total_tokens": 5076912} {"current_steps": 18130, "total_steps": 40000, "loss": 0.0, "lr": 2.8660492706348357e-05, "epoch": 201.44444444444446, "percentage": 45.32, "elapsed_time": "2:03:18", "remaining_time": "2:28:45", "throughput": 686.36, "total_tokens": 5078304} {"current_steps": 18135, "total_steps": 40000, "loss": 0.0, "lr": 2.8650780754599022e-05, "epoch": 201.5, "percentage": 45.34, "elapsed_time": "2:03:20", "remaining_time": "2:28:43", "throughput": 686.38, "total_tokens": 5079760} {"current_steps": 18140, "total_steps": 40000, "loss": 0.0, "lr": 2.8641068239853407e-05, "epoch": 201.55555555555554, "percentage": 45.35, "elapsed_time": "2:03:22", "remaining_time": "2:28:40", "throughput": 686.38, "total_tokens": 5081136} {"current_steps": 18145, "total_steps": 40000, "loss": 0.0, "lr": 2.863135516360932e-05, "epoch": 201.61111111111111, "percentage": 45.36, "elapsed_time": "2:03:24", "remaining_time": "2:28:38", "throughput": 686.4, "total_tokens": 5082544} {"current_steps": 18150, "total_steps": 40000, "loss": 0.0, "lr": 2.8621641527364633e-05, "epoch": 201.66666666666666, "percentage": 45.38, "elapsed_time": "2:03:26", "remaining_time": "2:28:36", "throughput": 686.41, "total_tokens": 5083984} {"current_steps": 18155, "total_steps": 40000, "loss": 0.0, "lr": 2.8611927332617313e-05, "epoch": 201.72222222222223, "percentage": 45.39, "elapsed_time": "2:03:28", "remaining_time": "2:28:34", "throughput": 686.42, "total_tokens": 5085376} {"current_steps": 18160, "total_steps": 40000, "loss": 0.0, "lr": 2.8602212580865405e-05, "epoch": 201.77777777777777, "percentage": 45.4, "elapsed_time": "2:03:30", "remaining_time": "2:28:32", "throughput": 686.43, "total_tokens": 5086784} {"current_steps": 18165, "total_steps": 40000, "loss": 0.0, "lr": 2.859249727360705e-05, "epoch": 201.83333333333334, "percentage": 45.41, "elapsed_time": "2:03:32", "remaining_time": "2:28:30", "throughput": 686.43, "total_tokens": 5088144} {"current_steps": 18170, "total_steps": 40000, "loss": 0.0, "lr": 2.8582781412340465e-05, "epoch": 201.88888888888889, "percentage": 45.42, "elapsed_time": "2:03:34", "remaining_time": "2:28:27", "throughput": 686.44, "total_tokens": 5089536} {"current_steps": 18175, "total_steps": 40000, "loss": 0.0, "lr": 2.857306499856397e-05, "epoch": 201.94444444444446, "percentage": 45.44, "elapsed_time": "2:03:36", "remaining_time": "2:28:25", "throughput": 686.45, "total_tokens": 5090960} {"current_steps": 18180, "total_steps": 40000, "loss": 0.0, "lr": 2.856334803377594e-05, "epoch": 202.0, "percentage": 45.45, "elapsed_time": "2:03:38", "remaining_time": "2:28:23", "throughput": 686.44, "total_tokens": 5092304} {"current_steps": 18185, "total_steps": 40000, "loss": 0.0, "lr": 2.8553630519474867e-05, "epoch": 202.05555555555554, "percentage": 45.46, "elapsed_time": "2:03:40", "remaining_time": "2:28:21", "throughput": 686.42, "total_tokens": 5093664} {"current_steps": 18190, "total_steps": 40000, "loss": 0.0, "lr": 2.8543912457159317e-05, "epoch": 202.11111111111111, "percentage": 45.48, "elapsed_time": "2:03:42", "remaining_time": "2:28:19", "throughput": 686.43, "total_tokens": 5095056} {"current_steps": 18195, "total_steps": 40000, "loss": 0.0, "lr": 2.853419384832792e-05, "epoch": 202.16666666666666, "percentage": 45.49, "elapsed_time": "2:03:44", "remaining_time": "2:28:17", "throughput": 686.44, "total_tokens": 5096464} {"current_steps": 18200, "total_steps": 40000, "loss": 0.0, "lr": 2.8524474694479423e-05, "epoch": 202.22222222222223, "percentage": 45.5, "elapsed_time": "2:03:46", "remaining_time": "2:28:15", "throughput": 686.45, "total_tokens": 5097872} {"current_steps": 18200, "total_steps": 40000, "eval_loss": 0.3578169345855713, "epoch": 202.22222222222223, "percentage": 45.5, "elapsed_time": "2:03:47", "remaining_time": "2:28:16", "throughput": 686.33, "total_tokens": 5097872} {"current_steps": 18205, "total_steps": 40000, "loss": 0.0, "lr": 2.851475499711264e-05, "epoch": 202.27777777777777, "percentage": 45.51, "elapsed_time": "2:03:50", "remaining_time": "2:28:16", "throughput": 686.22, "total_tokens": 5099280} {"current_steps": 18210, "total_steps": 40000, "loss": 0.0, "lr": 2.8505034757726468e-05, "epoch": 202.33333333333334, "percentage": 45.52, "elapsed_time": "2:03:52", "remaining_time": "2:28:14", "throughput": 686.22, "total_tokens": 5100672} {"current_steps": 18215, "total_steps": 40000, "loss": 0.0, "lr": 2.8495313977819886e-05, "epoch": 202.38888888888889, "percentage": 45.54, "elapsed_time": "2:03:54", "remaining_time": "2:28:12", "throughput": 686.23, "total_tokens": 5102096} {"current_steps": 18220, "total_steps": 40000, "loss": 0.0, "lr": 2.8485592658891956e-05, "epoch": 202.44444444444446, "percentage": 45.55, "elapsed_time": "2:03:56", "remaining_time": "2:28:09", "throughput": 686.25, "total_tokens": 5103520} {"current_steps": 18225, "total_steps": 40000, "loss": 0.0, "lr": 2.8475870802441844e-05, "epoch": 202.5, "percentage": 45.56, "elapsed_time": "2:03:58", "remaining_time": "2:28:07", "throughput": 686.27, "total_tokens": 5104992} {"current_steps": 18230, "total_steps": 40000, "loss": 0.0, "lr": 2.8466148409968774e-05, "epoch": 202.55555555555554, "percentage": 45.57, "elapsed_time": "2:04:00", "remaining_time": "2:28:05", "throughput": 686.28, "total_tokens": 5106416} {"current_steps": 18235, "total_steps": 40000, "loss": 0.0, "lr": 2.8456425482972067e-05, "epoch": 202.61111111111111, "percentage": 45.59, "elapsed_time": "2:04:02", "remaining_time": "2:28:03", "throughput": 686.29, "total_tokens": 5107824} {"current_steps": 18240, "total_steps": 40000, "loss": 0.0, "lr": 2.84467020229511e-05, "epoch": 202.66666666666666, "percentage": 45.6, "elapsed_time": "2:04:04", "remaining_time": "2:28:01", "throughput": 686.29, "total_tokens": 5109168} {"current_steps": 18245, "total_steps": 40000, "loss": 0.0, "lr": 2.8436978031405375e-05, "epoch": 202.72222222222223, "percentage": 45.61, "elapsed_time": "2:04:06", "remaining_time": "2:27:59", "throughput": 686.3, "total_tokens": 5110528} {"current_steps": 18250, "total_steps": 40000, "loss": 0.0, "lr": 2.842725350983445e-05, "epoch": 202.77777777777777, "percentage": 45.62, "elapsed_time": "2:04:08", "remaining_time": "2:27:56", "throughput": 686.31, "total_tokens": 5111936} {"current_steps": 18255, "total_steps": 40000, "loss": 0.0, "lr": 2.8417528459737957e-05, "epoch": 202.83333333333334, "percentage": 45.64, "elapsed_time": "2:04:10", "remaining_time": "2:27:54", "throughput": 686.32, "total_tokens": 5113360} {"current_steps": 18260, "total_steps": 40000, "loss": 0.0, "lr": 2.8407802882615624e-05, "epoch": 202.88888888888889, "percentage": 45.65, "elapsed_time": "2:04:12", "remaining_time": "2:27:52", "throughput": 686.32, "total_tokens": 5114704} {"current_steps": 18265, "total_steps": 40000, "loss": 0.0, "lr": 2.8398076779967277e-05, "epoch": 202.94444444444446, "percentage": 45.66, "elapsed_time": "2:04:14", "remaining_time": "2:27:50", "throughput": 686.33, "total_tokens": 5116080} {"current_steps": 18270, "total_steps": 40000, "loss": 0.0, "lr": 2.8388350153292774e-05, "epoch": 203.0, "percentage": 45.67, "elapsed_time": "2:04:16", "remaining_time": "2:27:48", "throughput": 686.33, "total_tokens": 5117488} {"current_steps": 18275, "total_steps": 40000, "loss": 0.0, "lr": 2.8378623004092103e-05, "epoch": 203.05555555555554, "percentage": 45.69, "elapsed_time": "2:04:18", "remaining_time": "2:27:46", "throughput": 686.31, "total_tokens": 5118848} {"current_steps": 18280, "total_steps": 40000, "loss": 0.0, "lr": 2.8368895333865302e-05, "epoch": 203.11111111111111, "percentage": 45.7, "elapsed_time": "2:04:20", "remaining_time": "2:27:44", "throughput": 686.32, "total_tokens": 5120288} {"current_steps": 18285, "total_steps": 40000, "loss": 0.0, "lr": 2.835916714411251e-05, "epoch": 203.16666666666666, "percentage": 45.71, "elapsed_time": "2:04:22", "remaining_time": "2:27:42", "throughput": 686.34, "total_tokens": 5121776} {"current_steps": 18290, "total_steps": 40000, "loss": 0.0, "lr": 2.8349438436333926e-05, "epoch": 203.22222222222223, "percentage": 45.73, "elapsed_time": "2:04:24", "remaining_time": "2:27:40", "throughput": 686.35, "total_tokens": 5123200} {"current_steps": 18295, "total_steps": 40000, "loss": 0.0, "lr": 2.833970921202984e-05, "epoch": 203.27777777777777, "percentage": 45.74, "elapsed_time": "2:04:26", "remaining_time": "2:27:37", "throughput": 686.36, "total_tokens": 5124608} {"current_steps": 18300, "total_steps": 40000, "loss": 0.0, "lr": 2.8329979472700628e-05, "epoch": 203.33333333333334, "percentage": 45.75, "elapsed_time": "2:04:28", "remaining_time": "2:27:35", "throughput": 686.37, "total_tokens": 5126016} {"current_steps": 18305, "total_steps": 40000, "loss": 0.0, "lr": 2.832024921984674e-05, "epoch": 203.38888888888889, "percentage": 45.76, "elapsed_time": "2:04:30", "remaining_time": "2:27:33", "throughput": 686.39, "total_tokens": 5127440} {"current_steps": 18310, "total_steps": 40000, "loss": 0.0, "lr": 2.8310518454968693e-05, "epoch": 203.44444444444446, "percentage": 45.77, "elapsed_time": "2:04:32", "remaining_time": "2:27:31", "throughput": 686.4, "total_tokens": 5128864} {"current_steps": 18315, "total_steps": 40000, "loss": 0.0, "lr": 2.8300787179567095e-05, "epoch": 203.5, "percentage": 45.79, "elapsed_time": "2:04:34", "remaining_time": "2:27:29", "throughput": 686.41, "total_tokens": 5130272} {"current_steps": 18320, "total_steps": 40000, "loss": 0.0, "lr": 2.8291055395142636e-05, "epoch": 203.55555555555554, "percentage": 45.8, "elapsed_time": "2:04:35", "remaining_time": "2:27:27", "throughput": 686.42, "total_tokens": 5131680} {"current_steps": 18325, "total_steps": 40000, "loss": 0.0, "lr": 2.8281323103196073e-05, "epoch": 203.61111111111111, "percentage": 45.81, "elapsed_time": "2:04:37", "remaining_time": "2:27:24", "throughput": 686.43, "total_tokens": 5133072} {"current_steps": 18330, "total_steps": 40000, "loss": 0.0, "lr": 2.8271590305228256e-05, "epoch": 203.66666666666666, "percentage": 45.82, "elapsed_time": "2:04:39", "remaining_time": "2:27:22", "throughput": 686.44, "total_tokens": 5134496} {"current_steps": 18335, "total_steps": 40000, "loss": 0.0, "lr": 2.82618570027401e-05, "epoch": 203.72222222222223, "percentage": 45.84, "elapsed_time": "2:04:41", "remaining_time": "2:27:20", "throughput": 686.45, "total_tokens": 5135872} {"current_steps": 18340, "total_steps": 40000, "loss": 0.0, "lr": 2.8252123197232604e-05, "epoch": 203.77777777777777, "percentage": 45.85, "elapsed_time": "2:04:43", "remaining_time": "2:27:18", "throughput": 686.46, "total_tokens": 5137264} {"current_steps": 18345, "total_steps": 40000, "loss": 0.0, "lr": 2.8242388890206843e-05, "epoch": 203.83333333333334, "percentage": 45.86, "elapsed_time": "2:04:45", "remaining_time": "2:27:16", "throughput": 686.47, "total_tokens": 5138672} {"current_steps": 18350, "total_steps": 40000, "loss": 0.0, "lr": 2.8232654083163967e-05, "epoch": 203.88888888888889, "percentage": 45.88, "elapsed_time": "2:04:47", "remaining_time": "2:27:14", "throughput": 686.47, "total_tokens": 5140048} {"current_steps": 18355, "total_steps": 40000, "loss": 0.0, "lr": 2.822291877760521e-05, "epoch": 203.94444444444446, "percentage": 45.89, "elapsed_time": "2:04:49", "remaining_time": "2:27:11", "throughput": 686.48, "total_tokens": 5141424} {"current_steps": 18360, "total_steps": 40000, "loss": 0.0, "lr": 2.8213182975031864e-05, "epoch": 204.0, "percentage": 45.9, "elapsed_time": "2:04:51", "remaining_time": "2:27:10", "throughput": 686.47, "total_tokens": 5142816} {"current_steps": 18365, "total_steps": 40000, "loss": 0.0, "lr": 2.8203446676945337e-05, "epoch": 204.05555555555554, "percentage": 45.91, "elapsed_time": "2:04:53", "remaining_time": "2:27:08", "throughput": 686.46, "total_tokens": 5144192} {"current_steps": 18370, "total_steps": 40000, "loss": 0.0, "lr": 2.8193709884847075e-05, "epoch": 204.11111111111111, "percentage": 45.92, "elapsed_time": "2:04:55", "remaining_time": "2:27:05", "throughput": 686.47, "total_tokens": 5145600} {"current_steps": 18375, "total_steps": 40000, "loss": 0.0, "lr": 2.8183972600238605e-05, "epoch": 204.16666666666666, "percentage": 45.94, "elapsed_time": "2:04:57", "remaining_time": "2:27:03", "throughput": 686.48, "total_tokens": 5146992} {"current_steps": 18380, "total_steps": 40000, "loss": 0.0, "lr": 2.817423482462156e-05, "epoch": 204.22222222222223, "percentage": 45.95, "elapsed_time": "2:04:59", "remaining_time": "2:27:01", "throughput": 686.49, "total_tokens": 5148416} {"current_steps": 18385, "total_steps": 40000, "loss": 0.0, "lr": 2.8164496559497605e-05, "epoch": 204.27777777777777, "percentage": 45.96, "elapsed_time": "2:05:01", "remaining_time": "2:26:59", "throughput": 686.5, "total_tokens": 5149808} {"current_steps": 18390, "total_steps": 40000, "loss": 0.0, "lr": 2.815475780636852e-05, "epoch": 204.33333333333334, "percentage": 45.98, "elapsed_time": "2:05:03", "remaining_time": "2:26:57", "throughput": 686.51, "total_tokens": 5151232} {"current_steps": 18395, "total_steps": 40000, "loss": 0.0, "lr": 2.814501856673613e-05, "epoch": 204.38888888888889, "percentage": 45.99, "elapsed_time": "2:05:05", "remaining_time": "2:26:55", "throughput": 686.52, "total_tokens": 5152656} {"current_steps": 18400, "total_steps": 40000, "loss": 0.0, "lr": 2.8135278842102353e-05, "epoch": 204.44444444444446, "percentage": 46.0, "elapsed_time": "2:05:07", "remaining_time": "2:26:53", "throughput": 686.53, "total_tokens": 5154064} {"current_steps": 18400, "total_steps": 40000, "eval_loss": 0.38750022649765015, "epoch": 204.44444444444446, "percentage": 46.0, "elapsed_time": "2:05:08", "remaining_time": "2:26:54", "throughput": 686.42, "total_tokens": 5154064} {"current_steps": 18405, "total_steps": 40000, "loss": 0.0, "lr": 2.8125538633969183e-05, "epoch": 204.5, "percentage": 46.01, "elapsed_time": "2:05:12", "remaining_time": "2:26:54", "throughput": 686.25, "total_tokens": 5155488} {"current_steps": 18410, "total_steps": 40000, "loss": 0.0, "lr": 2.8115797943838677e-05, "epoch": 204.55555555555554, "percentage": 46.02, "elapsed_time": "2:05:14", "remaining_time": "2:26:52", "throughput": 686.25, "total_tokens": 5156880} {"current_steps": 18415, "total_steps": 40000, "loss": 0.0, "lr": 2.810605677321298e-05, "epoch": 204.61111111111111, "percentage": 46.04, "elapsed_time": "2:05:16", "remaining_time": "2:26:50", "throughput": 686.26, "total_tokens": 5158272} {"current_steps": 18420, "total_steps": 40000, "loss": 0.0, "lr": 2.809631512359428e-05, "epoch": 204.66666666666666, "percentage": 46.05, "elapsed_time": "2:05:18", "remaining_time": "2:26:48", "throughput": 686.27, "total_tokens": 5159664} {"current_steps": 18425, "total_steps": 40000, "loss": 0.0, "lr": 2.8086572996484884e-05, "epoch": 204.72222222222223, "percentage": 46.06, "elapsed_time": "2:05:20", "remaining_time": "2:26:46", "throughput": 686.28, "total_tokens": 5161072} {"current_steps": 18430, "total_steps": 40000, "loss": 0.0, "lr": 2.8076830393387143e-05, "epoch": 204.77777777777777, "percentage": 46.08, "elapsed_time": "2:05:22", "remaining_time": "2:26:43", "throughput": 686.29, "total_tokens": 5162480} {"current_steps": 18435, "total_steps": 40000, "loss": 0.0, "lr": 2.8067087315803497e-05, "epoch": 204.83333333333334, "percentage": 46.09, "elapsed_time": "2:05:24", "remaining_time": "2:26:41", "throughput": 686.3, "total_tokens": 5163888} {"current_steps": 18440, "total_steps": 40000, "loss": 0.0, "lr": 2.8057343765236433e-05, "epoch": 204.88888888888889, "percentage": 46.1, "elapsed_time": "2:05:26", "remaining_time": "2:26:39", "throughput": 686.31, "total_tokens": 5165280} {"current_steps": 18445, "total_steps": 40000, "loss": 0.0, "lr": 2.804759974318854e-05, "epoch": 204.94444444444446, "percentage": 46.11, "elapsed_time": "2:05:28", "remaining_time": "2:26:37", "throughput": 686.32, "total_tokens": 5166704} {"current_steps": 18450, "total_steps": 40000, "loss": 0.0, "lr": 2.8037855251162482e-05, "epoch": 205.0, "percentage": 46.12, "elapsed_time": "2:05:30", "remaining_time": "2:26:35", "throughput": 686.28, "total_tokens": 5168096} {"current_steps": 18455, "total_steps": 40000, "loss": 0.0, "lr": 2.802811029066096e-05, "epoch": 205.05555555555554, "percentage": 46.14, "elapsed_time": "2:05:32", "remaining_time": "2:26:34", "throughput": 686.27, "total_tokens": 5169520} {"current_steps": 18460, "total_steps": 40000, "loss": 0.0, "lr": 2.8018364863186764e-05, "epoch": 205.11111111111111, "percentage": 46.15, "elapsed_time": "2:05:34", "remaining_time": "2:26:31", "throughput": 686.27, "total_tokens": 5170896} {"current_steps": 18465, "total_steps": 40000, "loss": 0.0, "lr": 2.800861897024279e-05, "epoch": 205.16666666666666, "percentage": 46.16, "elapsed_time": "2:05:36", "remaining_time": "2:26:29", "throughput": 686.29, "total_tokens": 5172320} {"current_steps": 18470, "total_steps": 40000, "loss": 0.0, "lr": 2.799887261333196e-05, "epoch": 205.22222222222223, "percentage": 46.17, "elapsed_time": "2:05:38", "remaining_time": "2:26:27", "throughput": 686.31, "total_tokens": 5173792} {"current_steps": 18475, "total_steps": 40000, "loss": 0.0, "lr": 2.798912579395728e-05, "epoch": 205.27777777777777, "percentage": 46.19, "elapsed_time": "2:05:40", "remaining_time": "2:26:25", "throughput": 686.32, "total_tokens": 5175184} {"current_steps": 18480, "total_steps": 40000, "loss": 0.0, "lr": 2.797937851362185e-05, "epoch": 205.33333333333334, "percentage": 46.2, "elapsed_time": "2:05:42", "remaining_time": "2:26:23", "throughput": 686.32, "total_tokens": 5176560} {"current_steps": 18485, "total_steps": 40000, "loss": 0.0, "lr": 2.7969630773828802e-05, "epoch": 205.38888888888889, "percentage": 46.21, "elapsed_time": "2:05:44", "remaining_time": "2:26:21", "throughput": 686.33, "total_tokens": 5177984} {"current_steps": 18490, "total_steps": 40000, "loss": 0.0, "lr": 2.7959882576081382e-05, "epoch": 205.44444444444446, "percentage": 46.23, "elapsed_time": "2:05:46", "remaining_time": "2:26:18", "throughput": 686.35, "total_tokens": 5179424} {"current_steps": 18495, "total_steps": 40000, "loss": 0.0, "lr": 2.795013392188286e-05, "epoch": 205.5, "percentage": 46.24, "elapsed_time": "2:05:48", "remaining_time": "2:26:16", "throughput": 686.35, "total_tokens": 5180784} {"current_steps": 18500, "total_steps": 40000, "loss": 0.0, "lr": 2.7940384812736614e-05, "epoch": 205.55555555555554, "percentage": 46.25, "elapsed_time": "2:05:50", "remaining_time": "2:26:14", "throughput": 686.36, "total_tokens": 5182160} {"current_steps": 18505, "total_steps": 40000, "loss": 0.0, "lr": 2.7930635250146087e-05, "epoch": 205.61111111111111, "percentage": 46.26, "elapsed_time": "2:05:52", "remaining_time": "2:26:12", "throughput": 686.37, "total_tokens": 5183552} {"current_steps": 18510, "total_steps": 40000, "loss": 0.0, "lr": 2.792088523561477e-05, "epoch": 205.66666666666666, "percentage": 46.27, "elapsed_time": "2:05:54", "remaining_time": "2:26:10", "throughput": 686.38, "total_tokens": 5184944} {"current_steps": 18515, "total_steps": 40000, "loss": 0.0, "lr": 2.7911134770646246e-05, "epoch": 205.72222222222223, "percentage": 46.29, "elapsed_time": "2:05:56", "remaining_time": "2:26:08", "throughput": 686.39, "total_tokens": 5186368} {"current_steps": 18520, "total_steps": 40000, "loss": 0.0, "lr": 2.7901383856744157e-05, "epoch": 205.77777777777777, "percentage": 46.3, "elapsed_time": "2:05:57", "remaining_time": "2:26:05", "throughput": 686.4, "total_tokens": 5187760} {"current_steps": 18525, "total_steps": 40000, "loss": 0.0, "lr": 2.7891632495412217e-05, "epoch": 205.83333333333334, "percentage": 46.31, "elapsed_time": "2:05:59", "remaining_time": "2:26:03", "throughput": 686.4, "total_tokens": 5189120} {"current_steps": 18530, "total_steps": 40000, "loss": 0.0, "lr": 2.7881880688154205e-05, "epoch": 205.88888888888889, "percentage": 46.33, "elapsed_time": "2:06:01", "remaining_time": "2:26:01", "throughput": 686.41, "total_tokens": 5190528} {"current_steps": 18535, "total_steps": 40000, "loss": 0.0, "lr": 2.7872128436473977e-05, "epoch": 205.94444444444446, "percentage": 46.34, "elapsed_time": "2:06:03", "remaining_time": "2:25:59", "throughput": 686.42, "total_tokens": 5191936} {"current_steps": 18540, "total_steps": 40000, "loss": 0.0, "lr": 2.7862375741875448e-05, "epoch": 206.0, "percentage": 46.35, "elapsed_time": "2:06:05", "remaining_time": "2:25:57", "throughput": 686.41, "total_tokens": 5193328} {"current_steps": 18545, "total_steps": 40000, "loss": 0.0, "lr": 2.785262260586261e-05, "epoch": 206.05555555555554, "percentage": 46.36, "elapsed_time": "2:06:08", "remaining_time": "2:25:55", "throughput": 686.39, "total_tokens": 5194672} {"current_steps": 18550, "total_steps": 40000, "loss": 0.0, "lr": 2.7842869029939517e-05, "epoch": 206.11111111111111, "percentage": 46.38, "elapsed_time": "2:06:10", "remaining_time": "2:25:53", "throughput": 686.4, "total_tokens": 5196064} {"current_steps": 18555, "total_steps": 40000, "loss": 0.0, "lr": 2.7833115015610296e-05, "epoch": 206.16666666666666, "percentage": 46.39, "elapsed_time": "2:06:11", "remaining_time": "2:25:51", "throughput": 686.41, "total_tokens": 5197440} {"current_steps": 18560, "total_steps": 40000, "loss": 0.0, "lr": 2.7823360564379136e-05, "epoch": 206.22222222222223, "percentage": 46.4, "elapsed_time": "2:06:13", "remaining_time": "2:25:49", "throughput": 686.41, "total_tokens": 5198816} {"current_steps": 18565, "total_steps": 40000, "loss": 0.0, "lr": 2.7813605677750297e-05, "epoch": 206.27777777777777, "percentage": 46.41, "elapsed_time": "2:06:15", "remaining_time": "2:25:46", "throughput": 686.42, "total_tokens": 5200224} {"current_steps": 18570, "total_steps": 40000, "loss": 0.0, "lr": 2.7803850357228102e-05, "epoch": 206.33333333333334, "percentage": 46.42, "elapsed_time": "2:06:17", "remaining_time": "2:25:44", "throughput": 686.43, "total_tokens": 5201600} {"current_steps": 18575, "total_steps": 40000, "loss": 0.0, "lr": 2.779409460431695e-05, "epoch": 206.38888888888889, "percentage": 46.44, "elapsed_time": "2:06:19", "remaining_time": "2:25:42", "throughput": 686.44, "total_tokens": 5203008} {"current_steps": 18580, "total_steps": 40000, "loss": 0.0, "lr": 2.778433842052129e-05, "epoch": 206.44444444444446, "percentage": 46.45, "elapsed_time": "2:06:21", "remaining_time": "2:25:40", "throughput": 686.45, "total_tokens": 5204432} {"current_steps": 18585, "total_steps": 40000, "loss": 0.0, "lr": 2.7774581807345664e-05, "epoch": 206.5, "percentage": 46.46, "elapsed_time": "2:06:23", "remaining_time": "2:25:38", "throughput": 686.46, "total_tokens": 5205824} {"current_steps": 18590, "total_steps": 40000, "loss": 0.0, "lr": 2.776482476629465e-05, "epoch": 206.55555555555554, "percentage": 46.48, "elapsed_time": "2:06:25", "remaining_time": "2:25:36", "throughput": 686.47, "total_tokens": 5207248} {"current_steps": 18595, "total_steps": 40000, "loss": 0.0, "lr": 2.7755067298872924e-05, "epoch": 206.61111111111111, "percentage": 46.49, "elapsed_time": "2:06:27", "remaining_time": "2:25:34", "throughput": 686.48, "total_tokens": 5208656} {"current_steps": 18600, "total_steps": 40000, "loss": 0.0, "lr": 2.774530940658518e-05, "epoch": 206.66666666666666, "percentage": 46.5, "elapsed_time": "2:06:29", "remaining_time": "2:25:31", "throughput": 686.5, "total_tokens": 5210112} {"current_steps": 18600, "total_steps": 40000, "eval_loss": 0.3622409701347351, "epoch": 206.66666666666666, "percentage": 46.5, "elapsed_time": "2:06:30", "remaining_time": "2:25:33", "throughput": 686.38, "total_tokens": 5210112} {"current_steps": 18605, "total_steps": 40000, "loss": 0.0, "lr": 2.7735551090936236e-05, "epoch": 206.72222222222223, "percentage": 46.51, "elapsed_time": "2:06:33", "remaining_time": "2:25:32", "throughput": 686.26, "total_tokens": 5211456} {"current_steps": 18610, "total_steps": 40000, "loss": 0.0, "lr": 2.7725792353430934e-05, "epoch": 206.77777777777777, "percentage": 46.52, "elapsed_time": "2:06:35", "remaining_time": "2:25:30", "throughput": 686.27, "total_tokens": 5212896} {"current_steps": 18615, "total_steps": 40000, "loss": 0.0, "lr": 2.77160331955742e-05, "epoch": 206.83333333333334, "percentage": 46.54, "elapsed_time": "2:06:37", "remaining_time": "2:25:28", "throughput": 686.28, "total_tokens": 5214304} {"current_steps": 18620, "total_steps": 40000, "loss": 0.0, "lr": 2.7706273618871008e-05, "epoch": 206.88888888888889, "percentage": 46.55, "elapsed_time": "2:06:39", "remaining_time": "2:25:26", "throughput": 686.29, "total_tokens": 5215696} {"current_steps": 18625, "total_steps": 40000, "loss": 0.0, "lr": 2.769651362482642e-05, "epoch": 206.94444444444446, "percentage": 46.56, "elapsed_time": "2:06:41", "remaining_time": "2:25:24", "throughput": 686.3, "total_tokens": 5217056} {"current_steps": 18630, "total_steps": 40000, "loss": 0.0, "lr": 2.768675321494555e-05, "epoch": 207.0, "percentage": 46.58, "elapsed_time": "2:06:43", "remaining_time": "2:25:22", "throughput": 686.29, "total_tokens": 5218448} {"current_steps": 18635, "total_steps": 40000, "loss": 0.0, "lr": 2.7676992390733565e-05, "epoch": 207.05555555555554, "percentage": 46.59, "elapsed_time": "2:06:46", "remaining_time": "2:25:20", "throughput": 686.27, "total_tokens": 5219840} {"current_steps": 18640, "total_steps": 40000, "loss": 0.0, "lr": 2.766723115369571e-05, "epoch": 207.11111111111111, "percentage": 46.6, "elapsed_time": "2:06:48", "remaining_time": "2:25:18", "throughput": 686.29, "total_tokens": 5221264} {"current_steps": 18645, "total_steps": 40000, "loss": 0.0, "lr": 2.765746950533729e-05, "epoch": 207.16666666666666, "percentage": 46.61, "elapsed_time": "2:06:49", "remaining_time": "2:25:16", "throughput": 686.29, "total_tokens": 5222640} {"current_steps": 18650, "total_steps": 40000, "loss": 0.0, "lr": 2.7647707447163684e-05, "epoch": 207.22222222222223, "percentage": 46.62, "elapsed_time": "2:06:51", "remaining_time": "2:25:13", "throughput": 686.29, "total_tokens": 5224000} {"current_steps": 18655, "total_steps": 40000, "loss": 0.0, "lr": 2.7637944980680315e-05, "epoch": 207.27777777777777, "percentage": 46.64, "elapsed_time": "2:06:53", "remaining_time": "2:25:11", "throughput": 686.31, "total_tokens": 5225472} {"current_steps": 18660, "total_steps": 40000, "loss": 0.0, "lr": 2.762818210739268e-05, "epoch": 207.33333333333334, "percentage": 46.65, "elapsed_time": "2:06:55", "remaining_time": "2:25:09", "throughput": 686.32, "total_tokens": 5226880} {"current_steps": 18665, "total_steps": 40000, "loss": 0.0, "lr": 2.7618418828806332e-05, "epoch": 207.38888888888889, "percentage": 46.66, "elapsed_time": "2:06:57", "remaining_time": "2:25:07", "throughput": 686.34, "total_tokens": 5228288} {"current_steps": 18670, "total_steps": 40000, "loss": 0.0, "lr": 2.76086551464269e-05, "epoch": 207.44444444444446, "percentage": 46.67, "elapsed_time": "2:06:59", "remaining_time": "2:25:05", "throughput": 686.34, "total_tokens": 5229680} {"current_steps": 18675, "total_steps": 40000, "loss": 0.0, "lr": 2.759889106176006e-05, "epoch": 207.5, "percentage": 46.69, "elapsed_time": "2:07:01", "remaining_time": "2:25:03", "throughput": 686.36, "total_tokens": 5231104} {"current_steps": 18680, "total_steps": 40000, "loss": 0.0, "lr": 2.758912657631156e-05, "epoch": 207.55555555555554, "percentage": 46.7, "elapsed_time": "2:07:03", "remaining_time": "2:25:00", "throughput": 686.36, "total_tokens": 5232480} {"current_steps": 18685, "total_steps": 40000, "loss": 0.0, "lr": 2.7579361691587198e-05, "epoch": 207.61111111111111, "percentage": 46.71, "elapsed_time": "2:07:05", "remaining_time": "2:24:58", "throughput": 686.38, "total_tokens": 5233904} {"current_steps": 18690, "total_steps": 40000, "loss": 0.0, "lr": 2.756959640909285e-05, "epoch": 207.66666666666666, "percentage": 46.73, "elapsed_time": "2:07:07", "remaining_time": "2:24:56", "throughput": 686.38, "total_tokens": 5235280} {"current_steps": 18695, "total_steps": 40000, "loss": 0.0, "lr": 2.7559830730334452e-05, "epoch": 207.72222222222223, "percentage": 46.74, "elapsed_time": "2:07:09", "remaining_time": "2:24:54", "throughput": 686.39, "total_tokens": 5236672} {"current_steps": 18700, "total_steps": 40000, "loss": 0.0, "lr": 2.7550064656817988e-05, "epoch": 207.77777777777777, "percentage": 46.75, "elapsed_time": "2:07:11", "remaining_time": "2:24:52", "throughput": 686.4, "total_tokens": 5238096} {"current_steps": 18705, "total_steps": 40000, "loss": 0.0, "lr": 2.7540298190049503e-05, "epoch": 207.83333333333334, "percentage": 46.76, "elapsed_time": "2:07:13", "remaining_time": "2:24:50", "throughput": 686.41, "total_tokens": 5239488} {"current_steps": 18710, "total_steps": 40000, "loss": 0.0, "lr": 2.7530531331535107e-05, "epoch": 207.88888888888889, "percentage": 46.77, "elapsed_time": "2:07:15", "remaining_time": "2:24:47", "throughput": 686.41, "total_tokens": 5240848} {"current_steps": 18715, "total_steps": 40000, "loss": 0.0, "lr": 2.752076408278099e-05, "epoch": 207.94444444444446, "percentage": 46.79, "elapsed_time": "2:07:17", "remaining_time": "2:24:45", "throughput": 686.42, "total_tokens": 5242256} {"current_steps": 18720, "total_steps": 40000, "loss": 0.0, "lr": 2.751099644529337e-05, "epoch": 208.0, "percentage": 46.8, "elapsed_time": "2:07:19", "remaining_time": "2:24:43", "throughput": 686.42, "total_tokens": 5243696} {"current_steps": 18725, "total_steps": 40000, "loss": 0.0, "lr": 2.7501228420578533e-05, "epoch": 208.05555555555554, "percentage": 46.81, "elapsed_time": "2:07:21", "remaining_time": "2:24:41", "throughput": 686.41, "total_tokens": 5245072} {"current_steps": 18730, "total_steps": 40000, "loss": 0.0, "lr": 2.7491460010142857e-05, "epoch": 208.11111111111111, "percentage": 46.83, "elapsed_time": "2:07:23", "remaining_time": "2:24:39", "throughput": 686.41, "total_tokens": 5246448} {"current_steps": 18735, "total_steps": 40000, "loss": 0.0, "lr": 2.7481691215492727e-05, "epoch": 208.16666666666666, "percentage": 46.84, "elapsed_time": "2:07:25", "remaining_time": "2:24:37", "throughput": 686.42, "total_tokens": 5247824} {"current_steps": 18740, "total_steps": 40000, "loss": 0.0, "lr": 2.747192203813463e-05, "epoch": 208.22222222222223, "percentage": 46.85, "elapsed_time": "2:07:27", "remaining_time": "2:24:35", "throughput": 686.42, "total_tokens": 5249200} {"current_steps": 18745, "total_steps": 40000, "loss": 0.0, "lr": 2.7462152479575087e-05, "epoch": 208.27777777777777, "percentage": 46.86, "elapsed_time": "2:07:29", "remaining_time": "2:24:33", "throughput": 686.44, "total_tokens": 5250624} {"current_steps": 18750, "total_steps": 40000, "loss": 0.0, "lr": 2.7452382541320697e-05, "epoch": 208.33333333333334, "percentage": 46.88, "elapsed_time": "2:07:31", "remaining_time": "2:24:31", "throughput": 686.44, "total_tokens": 5252000} {"current_steps": 18755, "total_steps": 40000, "loss": 0.0, "lr": 2.7442612224878096e-05, "epoch": 208.38888888888889, "percentage": 46.89, "elapsed_time": "2:07:32", "remaining_time": "2:24:29", "throughput": 686.46, "total_tokens": 5253456} {"current_steps": 18760, "total_steps": 40000, "loss": 0.0, "lr": 2.7432841531753994e-05, "epoch": 208.44444444444446, "percentage": 46.9, "elapsed_time": "2:07:34", "remaining_time": "2:24:26", "throughput": 686.47, "total_tokens": 5254896} {"current_steps": 18765, "total_steps": 40000, "loss": 0.0, "lr": 2.7423070463455147e-05, "epoch": 208.5, "percentage": 46.91, "elapsed_time": "2:07:36", "remaining_time": "2:24:24", "throughput": 686.48, "total_tokens": 5256288} {"current_steps": 18770, "total_steps": 40000, "loss": 0.0, "lr": 2.7413299021488397e-05, "epoch": 208.55555555555554, "percentage": 46.92, "elapsed_time": "2:07:38", "remaining_time": "2:24:22", "throughput": 686.49, "total_tokens": 5257680} {"current_steps": 18775, "total_steps": 40000, "loss": 0.0, "lr": 2.7403527207360615e-05, "epoch": 208.61111111111111, "percentage": 46.94, "elapsed_time": "2:07:40", "remaining_time": "2:24:20", "throughput": 686.5, "total_tokens": 5259056} {"current_steps": 18780, "total_steps": 40000, "loss": 0.0, "lr": 2.7393755022578722e-05, "epoch": 208.66666666666666, "percentage": 46.95, "elapsed_time": "2:07:42", "remaining_time": "2:24:18", "throughput": 686.51, "total_tokens": 5260480} {"current_steps": 18785, "total_steps": 40000, "loss": 0.0, "lr": 2.7383982468649714e-05, "epoch": 208.72222222222223, "percentage": 46.96, "elapsed_time": "2:07:44", "remaining_time": "2:24:16", "throughput": 686.52, "total_tokens": 5261872} {"current_steps": 18790, "total_steps": 40000, "loss": 0.0, "lr": 2.7374209547080665e-05, "epoch": 208.77777777777777, "percentage": 46.98, "elapsed_time": "2:07:46", "remaining_time": "2:24:13", "throughput": 686.52, "total_tokens": 5263248} {"current_steps": 18795, "total_steps": 40000, "loss": 0.0, "lr": 2.7364436259378663e-05, "epoch": 208.83333333333334, "percentage": 46.99, "elapsed_time": "2:07:48", "remaining_time": "2:24:11", "throughput": 686.53, "total_tokens": 5264624} {"current_steps": 18800, "total_steps": 40000, "loss": 0.0, "lr": 2.735466260705088e-05, "epoch": 208.88888888888889, "percentage": 47.0, "elapsed_time": "2:07:50", "remaining_time": "2:24:09", "throughput": 686.55, "total_tokens": 5266064} {"current_steps": 18800, "total_steps": 40000, "eval_loss": 0.36705824732780457, "epoch": 208.88888888888889, "percentage": 47.0, "elapsed_time": "2:07:51", "remaining_time": "2:24:11", "throughput": 686.43, "total_tokens": 5266064} {"current_steps": 18805, "total_steps": 40000, "loss": 0.0, "lr": 2.7344888591604524e-05, "epoch": 208.94444444444446, "percentage": 47.01, "elapsed_time": "2:07:54", "remaining_time": "2:24:10", "throughput": 686.33, "total_tokens": 5267504} {"current_steps": 18810, "total_steps": 40000, "loss": 0.0, "lr": 2.7335114214546893e-05, "epoch": 209.0, "percentage": 47.02, "elapsed_time": "2:07:57", "remaining_time": "2:24:08", "throughput": 686.32, "total_tokens": 5268928} {"current_steps": 18815, "total_steps": 40000, "loss": 0.0, "lr": 2.7325339477385293e-05, "epoch": 209.05555555555554, "percentage": 47.04, "elapsed_time": "2:07:59", "remaining_time": "2:24:06", "throughput": 686.32, "total_tokens": 5270368} {"current_steps": 18820, "total_steps": 40000, "loss": 0.0, "lr": 2.7315564381627128e-05, "epoch": 209.11111111111111, "percentage": 47.05, "elapsed_time": "2:08:01", "remaining_time": "2:24:04", "throughput": 686.33, "total_tokens": 5271792} {"current_steps": 18825, "total_steps": 40000, "loss": 0.0, "lr": 2.7305788928779835e-05, "epoch": 209.16666666666666, "percentage": 47.06, "elapsed_time": "2:08:03", "remaining_time": "2:24:02", "throughput": 686.33, "total_tokens": 5273184} {"current_steps": 18830, "total_steps": 40000, "loss": 0.0, "lr": 2.729601312035091e-05, "epoch": 209.22222222222223, "percentage": 47.08, "elapsed_time": "2:08:05", "remaining_time": "2:24:00", "throughput": 686.34, "total_tokens": 5274560} {"current_steps": 18835, "total_steps": 40000, "loss": 0.0, "lr": 2.7286236957847915e-05, "epoch": 209.27777777777777, "percentage": 47.09, "elapsed_time": "2:08:06", "remaining_time": "2:23:57", "throughput": 686.35, "total_tokens": 5275984} {"current_steps": 18840, "total_steps": 40000, "loss": 0.0, "lr": 2.7276460442778446e-05, "epoch": 209.33333333333334, "percentage": 47.1, "elapsed_time": "2:08:08", "remaining_time": "2:23:55", "throughput": 686.36, "total_tokens": 5277344} {"current_steps": 18845, "total_steps": 40000, "loss": 0.0, "lr": 2.726668357665017e-05, "epoch": 209.38888888888889, "percentage": 47.11, "elapsed_time": "2:08:11", "remaining_time": "2:23:53", "throughput": 686.34, "total_tokens": 5278720} {"current_steps": 18850, "total_steps": 40000, "loss": 0.0, "lr": 2.7256906360970808e-05, "epoch": 209.44444444444446, "percentage": 47.12, "elapsed_time": "2:08:13", "remaining_time": "2:23:51", "throughput": 686.35, "total_tokens": 5280160} {"current_steps": 18855, "total_steps": 40000, "loss": 0.0, "lr": 2.7247128797248117e-05, "epoch": 209.5, "percentage": 47.14, "elapsed_time": "2:08:15", "remaining_time": "2:23:49", "throughput": 686.36, "total_tokens": 5281600} {"current_steps": 18860, "total_steps": 40000, "loss": 0.0, "lr": 2.7237350886989925e-05, "epoch": 209.55555555555554, "percentage": 47.15, "elapsed_time": "2:08:16", "remaining_time": "2:23:47", "throughput": 686.37, "total_tokens": 5282960} {"current_steps": 18865, "total_steps": 40000, "loss": 0.0, "lr": 2.7227572631704107e-05, "epoch": 209.61111111111111, "percentage": 47.16, "elapsed_time": "2:08:18", "remaining_time": "2:23:45", "throughput": 686.38, "total_tokens": 5284368} {"current_steps": 18870, "total_steps": 40000, "loss": 0.0, "lr": 2.7217794032898596e-05, "epoch": 209.66666666666666, "percentage": 47.17, "elapsed_time": "2:08:20", "remaining_time": "2:23:43", "throughput": 686.39, "total_tokens": 5285792} {"current_steps": 18875, "total_steps": 40000, "loss": 0.0, "lr": 2.7208015092081384e-05, "epoch": 209.72222222222223, "percentage": 47.19, "elapsed_time": "2:08:22", "remaining_time": "2:23:40", "throughput": 686.4, "total_tokens": 5287200} {"current_steps": 18880, "total_steps": 40000, "loss": 0.0, "lr": 2.719823581076049e-05, "epoch": 209.77777777777777, "percentage": 47.2, "elapsed_time": "2:08:24", "remaining_time": "2:23:38", "throughput": 686.41, "total_tokens": 5288560} {"current_steps": 18885, "total_steps": 40000, "loss": 0.0, "lr": 2.718845619044401e-05, "epoch": 209.83333333333334, "percentage": 47.21, "elapsed_time": "2:08:26", "remaining_time": "2:23:36", "throughput": 686.42, "total_tokens": 5289968} {"current_steps": 18890, "total_steps": 40000, "loss": 0.0, "lr": 2.7178676232640088e-05, "epoch": 209.88888888888889, "percentage": 47.23, "elapsed_time": "2:08:28", "remaining_time": "2:23:34", "throughput": 686.42, "total_tokens": 5291312} {"current_steps": 18895, "total_steps": 40000, "loss": 0.0, "lr": 2.716889593885691e-05, "epoch": 209.94444444444446, "percentage": 47.24, "elapsed_time": "2:08:30", "remaining_time": "2:23:32", "throughput": 686.43, "total_tokens": 5292720} {"current_steps": 18900, "total_steps": 40000, "loss": 0.0, "lr": 2.7159115310602716e-05, "epoch": 210.0, "percentage": 47.25, "elapsed_time": "2:08:32", "remaining_time": "2:23:30", "throughput": 686.42, "total_tokens": 5294128} {"current_steps": 18905, "total_steps": 40000, "loss": 0.0, "lr": 2.7149334349385814e-05, "epoch": 210.05555555555554, "percentage": 47.26, "elapsed_time": "2:08:34", "remaining_time": "2:23:28", "throughput": 686.41, "total_tokens": 5295536} {"current_steps": 18910, "total_steps": 40000, "loss": 0.0, "lr": 2.713955305671454e-05, "epoch": 210.11111111111111, "percentage": 47.27, "elapsed_time": "2:08:36", "remaining_time": "2:23:26", "throughput": 686.42, "total_tokens": 5296944} {"current_steps": 18915, "total_steps": 40000, "loss": 0.0, "lr": 2.71297714340973e-05, "epoch": 210.16666666666666, "percentage": 47.29, "elapsed_time": "2:08:38", "remaining_time": "2:23:24", "throughput": 686.43, "total_tokens": 5298352} {"current_steps": 18920, "total_steps": 40000, "loss": 0.0, "lr": 2.7119989483042545e-05, "epoch": 210.22222222222223, "percentage": 47.3, "elapsed_time": "2:08:40", "remaining_time": "2:23:22", "throughput": 686.46, "total_tokens": 5299856} {"current_steps": 18925, "total_steps": 40000, "loss": 0.0, "lr": 2.7110207205058768e-05, "epoch": 210.27777777777777, "percentage": 47.31, "elapsed_time": "2:08:42", "remaining_time": "2:23:19", "throughput": 686.46, "total_tokens": 5301248} {"current_steps": 18930, "total_steps": 40000, "loss": 0.0, "lr": 2.7100424601654517e-05, "epoch": 210.33333333333334, "percentage": 47.33, "elapsed_time": "2:08:44", "remaining_time": "2:23:17", "throughput": 686.47, "total_tokens": 5302624} {"current_steps": 18935, "total_steps": 40000, "loss": 0.0, "lr": 2.7090641674338403e-05, "epoch": 210.38888888888889, "percentage": 47.34, "elapsed_time": "2:08:46", "remaining_time": "2:23:15", "throughput": 686.48, "total_tokens": 5304016} {"current_steps": 18940, "total_steps": 40000, "loss": 0.0, "lr": 2.7080858424619072e-05, "epoch": 210.44444444444446, "percentage": 47.35, "elapsed_time": "2:08:48", "remaining_time": "2:23:13", "throughput": 686.48, "total_tokens": 5305376} {"current_steps": 18945, "total_steps": 40000, "loss": 0.0, "lr": 2.707107485400521e-05, "epoch": 210.5, "percentage": 47.36, "elapsed_time": "2:08:50", "remaining_time": "2:23:11", "throughput": 686.49, "total_tokens": 5306736} {"current_steps": 18950, "total_steps": 40000, "loss": 0.0, "lr": 2.7061290964005586e-05, "epoch": 210.55555555555554, "percentage": 47.38, "elapsed_time": "2:08:52", "remaining_time": "2:23:09", "throughput": 686.5, "total_tokens": 5308176} {"current_steps": 18955, "total_steps": 40000, "loss": 0.0, "lr": 2.7051506756129e-05, "epoch": 210.61111111111111, "percentage": 47.39, "elapsed_time": "2:08:54", "remaining_time": "2:23:06", "throughput": 686.5, "total_tokens": 5309536} {"current_steps": 18960, "total_steps": 40000, "loss": 0.0, "lr": 2.704172223188428e-05, "epoch": 210.66666666666666, "percentage": 47.4, "elapsed_time": "2:08:56", "remaining_time": "2:23:04", "throughput": 686.51, "total_tokens": 5310928} {"current_steps": 18965, "total_steps": 40000, "loss": 0.0, "lr": 2.7031937392780334e-05, "epoch": 210.72222222222223, "percentage": 47.41, "elapsed_time": "2:08:58", "remaining_time": "2:23:02", "throughput": 686.52, "total_tokens": 5312320} {"current_steps": 18970, "total_steps": 40000, "loss": 0.0, "lr": 2.702215224032611e-05, "epoch": 210.77777777777777, "percentage": 47.42, "elapsed_time": "2:08:59", "remaining_time": "2:23:00", "throughput": 686.53, "total_tokens": 5313712} {"current_steps": 18975, "total_steps": 40000, "loss": 0.0, "lr": 2.70123667760306e-05, "epoch": 210.83333333333334, "percentage": 47.44, "elapsed_time": "2:09:01", "remaining_time": "2:22:58", "throughput": 686.55, "total_tokens": 5315168} {"current_steps": 18980, "total_steps": 40000, "loss": 0.0, "lr": 2.7002581001402845e-05, "epoch": 210.88888888888889, "percentage": 47.45, "elapsed_time": "2:09:03", "remaining_time": "2:22:56", "throughput": 686.56, "total_tokens": 5316592} {"current_steps": 18985, "total_steps": 40000, "loss": 0.0, "lr": 2.6992794917951923e-05, "epoch": 210.94444444444446, "percentage": 47.46, "elapsed_time": "2:09:05", "remaining_time": "2:22:53", "throughput": 686.56, "total_tokens": 5317952} {"current_steps": 18990, "total_steps": 40000, "loss": 0.0, "lr": 2.6983008527187e-05, "epoch": 211.0, "percentage": 47.48, "elapsed_time": "2:09:07", "remaining_time": "2:22:52", "throughput": 686.56, "total_tokens": 5319376} {"current_steps": 18995, "total_steps": 40000, "loss": 0.0, "lr": 2.697322183061723e-05, "epoch": 211.05555555555554, "percentage": 47.49, "elapsed_time": "2:09:10", "remaining_time": "2:22:50", "throughput": 686.55, "total_tokens": 5320784} {"current_steps": 19000, "total_steps": 40000, "loss": 0.0, "lr": 2.696343482975186e-05, "epoch": 211.11111111111111, "percentage": 47.5, "elapsed_time": "2:09:11", "remaining_time": "2:22:47", "throughput": 686.56, "total_tokens": 5322160} {"current_steps": 19000, "total_steps": 40000, "eval_loss": 0.3800784647464752, "epoch": 211.11111111111111, "percentage": 47.5, "elapsed_time": "2:09:13", "remaining_time": "2:22:49", "throughput": 686.44, "total_tokens": 5322160} {"current_steps": 19005, "total_steps": 40000, "loss": 0.0, "lr": 2.695364752610016e-05, "epoch": 211.16666666666666, "percentage": 47.51, "elapsed_time": "2:09:16", "remaining_time": "2:22:48", "throughput": 686.33, "total_tokens": 5323552} {"current_steps": 19010, "total_steps": 40000, "loss": 0.0, "lr": 2.6943859921171467e-05, "epoch": 211.22222222222223, "percentage": 47.52, "elapsed_time": "2:09:18", "remaining_time": "2:22:46", "throughput": 686.33, "total_tokens": 5324976} {"current_steps": 19015, "total_steps": 40000, "loss": 0.0, "lr": 2.6934072016475143e-05, "epoch": 211.27777777777777, "percentage": 47.54, "elapsed_time": "2:09:20", "remaining_time": "2:22:44", "throughput": 686.34, "total_tokens": 5326368} {"current_steps": 19020, "total_steps": 40000, "loss": 0.0, "lr": 2.6924283813520606e-05, "epoch": 211.33333333333334, "percentage": 47.55, "elapsed_time": "2:09:22", "remaining_time": "2:22:42", "throughput": 686.36, "total_tokens": 5327824} {"current_steps": 19025, "total_steps": 40000, "loss": 0.0, "lr": 2.691449531381733e-05, "epoch": 211.38888888888889, "percentage": 47.56, "elapsed_time": "2:09:24", "remaining_time": "2:22:40", "throughput": 686.37, "total_tokens": 5329248} {"current_steps": 19030, "total_steps": 40000, "loss": 0.0, "lr": 2.6904706518874816e-05, "epoch": 211.44444444444446, "percentage": 47.58, "elapsed_time": "2:09:26", "remaining_time": "2:22:38", "throughput": 686.37, "total_tokens": 5330608} {"current_steps": 19035, "total_steps": 40000, "loss": 0.0, "lr": 2.6894917430202615e-05, "epoch": 211.5, "percentage": 47.59, "elapsed_time": "2:09:28", "remaining_time": "2:22:35", "throughput": 686.38, "total_tokens": 5332016} {"current_steps": 19040, "total_steps": 40000, "loss": 0.0, "lr": 2.6885128049310343e-05, "epoch": 211.55555555555554, "percentage": 47.6, "elapsed_time": "2:09:30", "remaining_time": "2:22:33", "throughput": 686.39, "total_tokens": 5333424} {"current_steps": 19045, "total_steps": 40000, "loss": 0.0, "lr": 2.687533837770762e-05, "epoch": 211.61111111111111, "percentage": 47.61, "elapsed_time": "2:09:32", "remaining_time": "2:22:31", "throughput": 686.4, "total_tokens": 5334832} {"current_steps": 19050, "total_steps": 40000, "loss": 0.0, "lr": 2.6865548416904162e-05, "epoch": 211.66666666666666, "percentage": 47.62, "elapsed_time": "2:09:34", "remaining_time": "2:22:29", "throughput": 686.42, "total_tokens": 5336272} {"current_steps": 19055, "total_steps": 40000, "loss": 0.0, "lr": 2.68557581684097e-05, "epoch": 211.72222222222223, "percentage": 47.64, "elapsed_time": "2:09:36", "remaining_time": "2:22:27", "throughput": 686.43, "total_tokens": 5337680} {"current_steps": 19060, "total_steps": 40000, "loss": 0.0, "lr": 2.6845967633733998e-05, "epoch": 211.77777777777777, "percentage": 47.65, "elapsed_time": "2:09:37", "remaining_time": "2:22:25", "throughput": 686.44, "total_tokens": 5339056} {"current_steps": 19065, "total_steps": 40000, "loss": 0.0, "lr": 2.683617681438689e-05, "epoch": 211.83333333333334, "percentage": 47.66, "elapsed_time": "2:09:39", "remaining_time": "2:22:22", "throughput": 686.44, "total_tokens": 5340416} {"current_steps": 19070, "total_steps": 40000, "loss": 0.0, "lr": 2.682638571187825e-05, "epoch": 211.88888888888889, "percentage": 47.67, "elapsed_time": "2:09:41", "remaining_time": "2:22:20", "throughput": 686.44, "total_tokens": 5341760} {"current_steps": 19075, "total_steps": 40000, "loss": 0.0, "lr": 2.6816594327717976e-05, "epoch": 211.94444444444446, "percentage": 47.69, "elapsed_time": "2:09:43", "remaining_time": "2:22:18", "throughput": 686.46, "total_tokens": 5343184} {"current_steps": 19080, "total_steps": 40000, "loss": 0.0, "lr": 2.680680266341603e-05, "epoch": 212.0, "percentage": 47.7, "elapsed_time": "2:09:45", "remaining_time": "2:22:16", "throughput": 686.45, "total_tokens": 5344608} {"current_steps": 19085, "total_steps": 40000, "loss": 0.0, "lr": 2.67970107204824e-05, "epoch": 212.05555555555554, "percentage": 47.71, "elapsed_time": "2:09:48", "remaining_time": "2:22:14", "throughput": 686.43, "total_tokens": 5345952} {"current_steps": 19090, "total_steps": 40000, "loss": 0.0, "lr": 2.6787218500427142e-05, "epoch": 212.11111111111111, "percentage": 47.73, "elapsed_time": "2:09:49", "remaining_time": "2:22:12", "throughput": 686.44, "total_tokens": 5347328} {"current_steps": 19095, "total_steps": 40000, "loss": 0.0, "lr": 2.6777426004760332e-05, "epoch": 212.16666666666666, "percentage": 47.74, "elapsed_time": "2:09:51", "remaining_time": "2:22:10", "throughput": 686.45, "total_tokens": 5348720} {"current_steps": 19100, "total_steps": 40000, "loss": 0.0, "lr": 2.6767633234992094e-05, "epoch": 212.22222222222223, "percentage": 47.75, "elapsed_time": "2:09:53", "remaining_time": "2:22:08", "throughput": 686.45, "total_tokens": 5350112} {"current_steps": 19105, "total_steps": 40000, "loss": 0.0, "lr": 2.6757840192632598e-05, "epoch": 212.27777777777777, "percentage": 47.76, "elapsed_time": "2:09:55", "remaining_time": "2:22:06", "throughput": 686.47, "total_tokens": 5351568} {"current_steps": 19110, "total_steps": 40000, "loss": 0.0, "lr": 2.6748046879192052e-05, "epoch": 212.33333333333334, "percentage": 47.77, "elapsed_time": "2:09:57", "remaining_time": "2:22:04", "throughput": 686.48, "total_tokens": 5352960} {"current_steps": 19115, "total_steps": 40000, "loss": 0.0, "lr": 2.673825329618071e-05, "epoch": 212.38888888888889, "percentage": 47.79, "elapsed_time": "2:09:59", "remaining_time": "2:22:01", "throughput": 686.49, "total_tokens": 5354352} {"current_steps": 19120, "total_steps": 40000, "loss": 0.0, "lr": 2.6728459445108866e-05, "epoch": 212.44444444444446, "percentage": 47.8, "elapsed_time": "2:10:01", "remaining_time": "2:21:59", "throughput": 686.5, "total_tokens": 5355776} {"current_steps": 19125, "total_steps": 40000, "loss": 0.0, "lr": 2.6718665327486854e-05, "epoch": 212.5, "percentage": 47.81, "elapsed_time": "2:10:03", "remaining_time": "2:21:57", "throughput": 686.51, "total_tokens": 5357168} {"current_steps": 19130, "total_steps": 40000, "loss": 0.0, "lr": 2.6708870944825048e-05, "epoch": 212.55555555555554, "percentage": 47.83, "elapsed_time": "2:10:05", "remaining_time": "2:21:55", "throughput": 686.51, "total_tokens": 5358544} {"current_steps": 19135, "total_steps": 40000, "loss": 0.0, "lr": 2.6699076298633874e-05, "epoch": 212.61111111111111, "percentage": 47.84, "elapsed_time": "2:10:07", "remaining_time": "2:21:53", "throughput": 686.53, "total_tokens": 5360000} {"current_steps": 19140, "total_steps": 40000, "loss": 0.0, "lr": 2.6689281390423788e-05, "epoch": 212.66666666666666, "percentage": 47.85, "elapsed_time": "2:10:09", "remaining_time": "2:21:51", "throughput": 686.54, "total_tokens": 5361424} {"current_steps": 19145, "total_steps": 40000, "loss": 0.0, "lr": 2.667948622170527e-05, "epoch": 212.72222222222223, "percentage": 47.86, "elapsed_time": "2:10:11", "remaining_time": "2:21:48", "throughput": 686.55, "total_tokens": 5362816} {"current_steps": 19150, "total_steps": 40000, "loss": 0.0, "lr": 2.6669690793988873e-05, "epoch": 212.77777777777777, "percentage": 47.88, "elapsed_time": "2:10:13", "remaining_time": "2:21:46", "throughput": 686.56, "total_tokens": 5364208} {"current_steps": 19155, "total_steps": 40000, "loss": 0.0, "lr": 2.665989510878518e-05, "epoch": 212.83333333333334, "percentage": 47.89, "elapsed_time": "2:10:15", "remaining_time": "2:21:44", "throughput": 686.57, "total_tokens": 5365632} {"current_steps": 19160, "total_steps": 40000, "loss": 0.0, "lr": 2.6650099167604793e-05, "epoch": 212.88888888888889, "percentage": 47.9, "elapsed_time": "2:10:17", "remaining_time": "2:21:42", "throughput": 686.58, "total_tokens": 5367024} {"current_steps": 19165, "total_steps": 40000, "loss": 0.0, "lr": 2.6640302971958376e-05, "epoch": 212.94444444444446, "percentage": 47.91, "elapsed_time": "2:10:18", "remaining_time": "2:21:40", "throughput": 686.59, "total_tokens": 5368416} {"current_steps": 19170, "total_steps": 40000, "loss": 0.0, "lr": 2.6630506523356635e-05, "epoch": 213.0, "percentage": 47.93, "elapsed_time": "2:10:21", "remaining_time": "2:21:38", "throughput": 686.58, "total_tokens": 5369792} {"current_steps": 19175, "total_steps": 40000, "loss": 0.0, "lr": 2.6620709823310297e-05, "epoch": 213.05555555555554, "percentage": 47.94, "elapsed_time": "2:10:23", "remaining_time": "2:21:36", "throughput": 686.56, "total_tokens": 5371152} {"current_steps": 19180, "total_steps": 40000, "loss": 0.0, "lr": 2.661091287333014e-05, "epoch": 213.11111111111111, "percentage": 47.95, "elapsed_time": "2:10:25", "remaining_time": "2:21:34", "throughput": 686.57, "total_tokens": 5372560} {"current_steps": 19185, "total_steps": 40000, "loss": 0.0, "lr": 2.660111567492696e-05, "epoch": 213.16666666666666, "percentage": 47.96, "elapsed_time": "2:10:27", "remaining_time": "2:21:32", "throughput": 686.58, "total_tokens": 5373968} {"current_steps": 19190, "total_steps": 40000, "loss": 0.0, "lr": 2.6591318229611635e-05, "epoch": 213.22222222222223, "percentage": 47.98, "elapsed_time": "2:10:29", "remaining_time": "2:21:29", "throughput": 686.6, "total_tokens": 5375408} {"current_steps": 19195, "total_steps": 40000, "loss": 0.0, "lr": 2.6581520538895037e-05, "epoch": 213.27777777777777, "percentage": 47.99, "elapsed_time": "2:10:31", "remaining_time": "2:21:27", "throughput": 686.6, "total_tokens": 5376784} {"current_steps": 19200, "total_steps": 40000, "loss": 0.0, "lr": 2.6571722604288102e-05, "epoch": 213.33333333333334, "percentage": 48.0, "elapsed_time": "2:10:32", "remaining_time": "2:21:25", "throughput": 686.62, "total_tokens": 5378224} {"current_steps": 19200, "total_steps": 40000, "eval_loss": 0.35208946466445923, "epoch": 213.33333333333334, "percentage": 48.0, "elapsed_time": "2:10:34", "remaining_time": "2:21:27", "throughput": 686.5, "total_tokens": 5378224} {"current_steps": 19205, "total_steps": 40000, "loss": 0.0, "lr": 2.656192442730179e-05, "epoch": 213.38888888888889, "percentage": 48.01, "elapsed_time": "2:10:37", "remaining_time": "2:21:26", "throughput": 686.41, "total_tokens": 5379648} {"current_steps": 19210, "total_steps": 40000, "loss": 0.0, "lr": 2.6552126009447098e-05, "epoch": 213.44444444444446, "percentage": 48.02, "elapsed_time": "2:10:39", "remaining_time": "2:21:24", "throughput": 686.41, "total_tokens": 5381056} {"current_steps": 19215, "total_steps": 40000, "loss": 0.0, "lr": 2.654232735223507e-05, "epoch": 213.5, "percentage": 48.04, "elapsed_time": "2:10:41", "remaining_time": "2:21:22", "throughput": 686.42, "total_tokens": 5382480} {"current_steps": 19220, "total_steps": 40000, "loss": 0.0, "lr": 2.6532528457176787e-05, "epoch": 213.55555555555554, "percentage": 48.05, "elapsed_time": "2:10:43", "remaining_time": "2:21:19", "throughput": 686.43, "total_tokens": 5383840} {"current_steps": 19225, "total_steps": 40000, "loss": 0.0, "lr": 2.6522729325783348e-05, "epoch": 213.61111111111111, "percentage": 48.06, "elapsed_time": "2:10:45", "remaining_time": "2:21:17", "throughput": 686.44, "total_tokens": 5385248} {"current_steps": 19230, "total_steps": 40000, "loss": 0.0, "lr": 2.6512929959565914e-05, "epoch": 213.66666666666666, "percentage": 48.08, "elapsed_time": "2:10:47", "remaining_time": "2:21:15", "throughput": 686.44, "total_tokens": 5386608} {"current_steps": 19235, "total_steps": 40000, "loss": 0.0, "lr": 2.6503130360035673e-05, "epoch": 213.72222222222223, "percentage": 48.09, "elapsed_time": "2:10:49", "remaining_time": "2:21:13", "throughput": 686.45, "total_tokens": 5388032} {"current_steps": 19240, "total_steps": 40000, "loss": 0.0, "lr": 2.6493330528703835e-05, "epoch": 213.77777777777777, "percentage": 48.1, "elapsed_time": "2:10:51", "remaining_time": "2:21:11", "throughput": 686.46, "total_tokens": 5389456} {"current_steps": 19245, "total_steps": 40000, "loss": 0.0, "lr": 2.648353046708167e-05, "epoch": 213.83333333333334, "percentage": 48.11, "elapsed_time": "2:10:52", "remaining_time": "2:21:09", "throughput": 686.48, "total_tokens": 5390896} {"current_steps": 19250, "total_steps": 40000, "loss": 0.0, "lr": 2.647373017668046e-05, "epoch": 213.88888888888889, "percentage": 48.12, "elapsed_time": "2:10:54", "remaining_time": "2:21:06", "throughput": 686.49, "total_tokens": 5392304} {"current_steps": 19255, "total_steps": 40000, "loss": 0.0, "lr": 2.6463929659011537e-05, "epoch": 213.94444444444446, "percentage": 48.14, "elapsed_time": "2:10:56", "remaining_time": "2:21:04", "throughput": 686.5, "total_tokens": 5393728} {"current_steps": 19260, "total_steps": 40000, "loss": 0.0, "lr": 2.6454128915586262e-05, "epoch": 214.0, "percentage": 48.15, "elapsed_time": "2:10:58", "remaining_time": "2:21:02", "throughput": 686.49, "total_tokens": 5395104} {"current_steps": 19265, "total_steps": 40000, "loss": 0.0, "lr": 2.6444327947916036e-05, "epoch": 214.05555555555554, "percentage": 48.16, "elapsed_time": "2:11:01", "remaining_time": "2:21:00", "throughput": 686.48, "total_tokens": 5396496} {"current_steps": 19270, "total_steps": 40000, "loss": 0.0, "lr": 2.6434526757512292e-05, "epoch": 214.11111111111111, "percentage": 48.18, "elapsed_time": "2:11:03", "remaining_time": "2:20:58", "throughput": 686.49, "total_tokens": 5397952} {"current_steps": 19275, "total_steps": 40000, "loss": 0.0, "lr": 2.6424725345886486e-05, "epoch": 214.16666666666666, "percentage": 48.19, "elapsed_time": "2:11:05", "remaining_time": "2:20:56", "throughput": 686.5, "total_tokens": 5399296} {"current_steps": 19280, "total_steps": 40000, "loss": 0.0, "lr": 2.641492371455014e-05, "epoch": 214.22222222222223, "percentage": 48.2, "elapsed_time": "2:11:06", "remaining_time": "2:20:54", "throughput": 686.5, "total_tokens": 5400672} {"current_steps": 19285, "total_steps": 40000, "loss": 0.0, "lr": 2.640512186501477e-05, "epoch": 214.27777777777777, "percentage": 48.21, "elapsed_time": "2:11:08", "remaining_time": "2:20:52", "throughput": 686.52, "total_tokens": 5402112} {"current_steps": 19290, "total_steps": 40000, "loss": 0.0, "lr": 2.639531979879195e-05, "epoch": 214.33333333333334, "percentage": 48.23, "elapsed_time": "2:11:10", "remaining_time": "2:20:50", "throughput": 686.53, "total_tokens": 5403520} {"current_steps": 19295, "total_steps": 40000, "loss": 0.0, "lr": 2.638551751739328e-05, "epoch": 214.38888888888889, "percentage": 48.24, "elapsed_time": "2:11:12", "remaining_time": "2:20:48", "throughput": 686.54, "total_tokens": 5404928} {"current_steps": 19300, "total_steps": 40000, "loss": 0.0, "lr": 2.6375715022330404e-05, "epoch": 214.44444444444446, "percentage": 48.25, "elapsed_time": "2:11:14", "remaining_time": "2:20:45", "throughput": 686.55, "total_tokens": 5406336} {"current_steps": 19305, "total_steps": 40000, "loss": 0.0, "lr": 2.6365912315114976e-05, "epoch": 214.5, "percentage": 48.26, "elapsed_time": "2:11:16", "remaining_time": "2:20:43", "throughput": 686.56, "total_tokens": 5407744} {"current_steps": 19310, "total_steps": 40000, "loss": 0.0, "lr": 2.6356109397258704e-05, "epoch": 214.55555555555554, "percentage": 48.27, "elapsed_time": "2:11:18", "remaining_time": "2:20:41", "throughput": 686.57, "total_tokens": 5409136} {"current_steps": 19315, "total_steps": 40000, "loss": 0.0, "lr": 2.6346306270273325e-05, "epoch": 214.61111111111111, "percentage": 48.29, "elapsed_time": "2:11:20", "remaining_time": "2:20:39", "throughput": 686.57, "total_tokens": 5410512} {"current_steps": 19320, "total_steps": 40000, "loss": 0.0, "lr": 2.6336502935670608e-05, "epoch": 214.66666666666666, "percentage": 48.3, "elapsed_time": "2:11:22", "remaining_time": "2:20:37", "throughput": 686.58, "total_tokens": 5411936} {"current_steps": 19325, "total_steps": 40000, "loss": 0.0, "lr": 2.6326699394962333e-05, "epoch": 214.72222222222223, "percentage": 48.31, "elapsed_time": "2:11:24", "remaining_time": "2:20:35", "throughput": 686.59, "total_tokens": 5413328} {"current_steps": 19330, "total_steps": 40000, "loss": 0.0, "lr": 2.6316895649660334e-05, "epoch": 214.77777777777777, "percentage": 48.33, "elapsed_time": "2:11:26", "remaining_time": "2:20:32", "throughput": 686.6, "total_tokens": 5414704} {"current_steps": 19335, "total_steps": 40000, "loss": 0.0, "lr": 2.6307091701276486e-05, "epoch": 214.83333333333334, "percentage": 48.34, "elapsed_time": "2:11:28", "remaining_time": "2:20:30", "throughput": 686.61, "total_tokens": 5416112} {"current_steps": 19340, "total_steps": 40000, "loss": 0.0, "lr": 2.629728755132267e-05, "epoch": 214.88888888888889, "percentage": 48.35, "elapsed_time": "2:11:30", "remaining_time": "2:20:28", "throughput": 686.62, "total_tokens": 5417520} {"current_steps": 19345, "total_steps": 40000, "loss": 0.0, "lr": 2.628748320131081e-05, "epoch": 214.94444444444446, "percentage": 48.36, "elapsed_time": "2:11:32", "remaining_time": "2:20:26", "throughput": 686.63, "total_tokens": 5418960} {"current_steps": 19350, "total_steps": 40000, "loss": 0.0, "lr": 2.6277678652752856e-05, "epoch": 215.0, "percentage": 48.38, "elapsed_time": "2:11:34", "remaining_time": "2:20:24", "throughput": 686.63, "total_tokens": 5420384} {"current_steps": 19355, "total_steps": 40000, "loss": 0.0, "lr": 2.6267873907160807e-05, "epoch": 215.05555555555554, "percentage": 48.39, "elapsed_time": "2:11:36", "remaining_time": "2:20:22", "throughput": 686.62, "total_tokens": 5421792} {"current_steps": 19360, "total_steps": 40000, "loss": 0.0, "lr": 2.6258068966046668e-05, "epoch": 215.11111111111111, "percentage": 48.4, "elapsed_time": "2:11:38", "remaining_time": "2:20:20", "throughput": 686.62, "total_tokens": 5423152} {"current_steps": 19365, "total_steps": 40000, "loss": 0.0, "lr": 2.6248263830922475e-05, "epoch": 215.16666666666666, "percentage": 48.41, "elapsed_time": "2:11:40", "remaining_time": "2:20:18", "throughput": 686.63, "total_tokens": 5424528} {"current_steps": 19370, "total_steps": 40000, "loss": 0.0, "lr": 2.6238458503300318e-05, "epoch": 215.22222222222223, "percentage": 48.43, "elapsed_time": "2:11:42", "remaining_time": "2:20:16", "throughput": 686.64, "total_tokens": 5425952} {"current_steps": 19375, "total_steps": 40000, "loss": 0.0, "lr": 2.6228652984692292e-05, "epoch": 215.27777777777777, "percentage": 48.44, "elapsed_time": "2:11:44", "remaining_time": "2:20:14", "throughput": 686.65, "total_tokens": 5427376} {"current_steps": 19380, "total_steps": 40000, "loss": 0.0, "lr": 2.621884727661054e-05, "epoch": 215.33333333333334, "percentage": 48.45, "elapsed_time": "2:11:46", "remaining_time": "2:20:11", "throughput": 686.66, "total_tokens": 5428800} {"current_steps": 19385, "total_steps": 40000, "loss": 0.0, "lr": 2.6209041380567222e-05, "epoch": 215.38888888888889, "percentage": 48.46, "elapsed_time": "2:11:47", "remaining_time": "2:20:09", "throughput": 686.67, "total_tokens": 5430208} {"current_steps": 19390, "total_steps": 40000, "loss": 0.0, "lr": 2.6199235298074527e-05, "epoch": 215.44444444444446, "percentage": 48.48, "elapsed_time": "2:11:49", "remaining_time": "2:20:07", "throughput": 686.69, "total_tokens": 5431616} {"current_steps": 19395, "total_steps": 40000, "loss": 0.0, "lr": 2.618942903064468e-05, "epoch": 215.5, "percentage": 48.49, "elapsed_time": "2:11:51", "remaining_time": "2:20:05", "throughput": 686.69, "total_tokens": 5433024} {"current_steps": 19400, "total_steps": 40000, "loss": 0.0, "lr": 2.6179622579789932e-05, "epoch": 215.55555555555554, "percentage": 48.5, "elapsed_time": "2:11:53", "remaining_time": "2:20:03", "throughput": 686.7, "total_tokens": 5434432} {"current_steps": 19400, "total_steps": 40000, "eval_loss": 0.3748704493045807, "epoch": 215.55555555555554, "percentage": 48.5, "elapsed_time": "2:11:55", "remaining_time": "2:20:04", "throughput": 686.59, "total_tokens": 5434432} {"current_steps": 19405, "total_steps": 40000, "loss": 0.0, "lr": 2.6169815947022553e-05, "epoch": 215.61111111111111, "percentage": 48.51, "elapsed_time": "2:11:58", "remaining_time": "2:20:03", "throughput": 686.49, "total_tokens": 5435824} {"current_steps": 19410, "total_steps": 40000, "loss": 0.0, "lr": 2.6160009133854853e-05, "epoch": 215.66666666666666, "percentage": 48.52, "elapsed_time": "2:12:00", "remaining_time": "2:20:01", "throughput": 686.49, "total_tokens": 5437216} {"current_steps": 19415, "total_steps": 40000, "loss": 0.0, "lr": 2.6150202141799168e-05, "epoch": 215.72222222222223, "percentage": 48.54, "elapsed_time": "2:12:02", "remaining_time": "2:19:59", "throughput": 686.5, "total_tokens": 5438640} {"current_steps": 19420, "total_steps": 40000, "loss": 0.0, "lr": 2.614039497236786e-05, "epoch": 215.77777777777777, "percentage": 48.55, "elapsed_time": "2:12:04", "remaining_time": "2:19:57", "throughput": 686.51, "total_tokens": 5440048} {"current_steps": 19425, "total_steps": 40000, "loss": 0.0, "lr": 2.6130587627073315e-05, "epoch": 215.83333333333334, "percentage": 48.56, "elapsed_time": "2:12:06", "remaining_time": "2:19:55", "throughput": 686.52, "total_tokens": 5441440} {"current_steps": 19430, "total_steps": 40000, "loss": 0.0, "lr": 2.6120780107427956e-05, "epoch": 215.88888888888889, "percentage": 48.58, "elapsed_time": "2:12:08", "remaining_time": "2:19:53", "throughput": 686.53, "total_tokens": 5442816} {"current_steps": 19435, "total_steps": 40000, "loss": 0.0, "lr": 2.6110972414944214e-05, "epoch": 215.94444444444446, "percentage": 48.59, "elapsed_time": "2:12:09", "remaining_time": "2:19:51", "throughput": 686.54, "total_tokens": 5444272} {"current_steps": 19440, "total_steps": 40000, "loss": 0.0, "lr": 2.6101164551134565e-05, "epoch": 216.0, "percentage": 48.6, "elapsed_time": "2:12:12", "remaining_time": "2:19:49", "throughput": 686.54, "total_tokens": 5445680} {"current_steps": 19445, "total_steps": 40000, "loss": 0.0, "lr": 2.6091356517511505e-05, "epoch": 216.05555555555554, "percentage": 48.61, "elapsed_time": "2:12:14", "remaining_time": "2:19:47", "throughput": 686.53, "total_tokens": 5447136} {"current_steps": 19450, "total_steps": 40000, "loss": 0.0, "lr": 2.608154831558755e-05, "epoch": 216.11111111111111, "percentage": 48.62, "elapsed_time": "2:12:16", "remaining_time": "2:19:45", "throughput": 686.54, "total_tokens": 5448512} {"current_steps": 19455, "total_steps": 40000, "loss": 0.0, "lr": 2.607173994687526e-05, "epoch": 216.16666666666666, "percentage": 48.64, "elapsed_time": "2:12:18", "remaining_time": "2:19:42", "throughput": 686.54, "total_tokens": 5449872} {"current_steps": 19460, "total_steps": 40000, "loss": 0.0, "lr": 2.6061931412887196e-05, "epoch": 216.22222222222223, "percentage": 48.65, "elapsed_time": "2:12:20", "remaining_time": "2:19:40", "throughput": 686.55, "total_tokens": 5451280} {"current_steps": 19465, "total_steps": 40000, "loss": 0.0, "lr": 2.6052122715135973e-05, "epoch": 216.27777777777777, "percentage": 48.66, "elapsed_time": "2:12:22", "remaining_time": "2:19:38", "throughput": 686.56, "total_tokens": 5452688} {"current_steps": 19470, "total_steps": 40000, "loss": 0.0, "lr": 2.60423138551342e-05, "epoch": 216.33333333333334, "percentage": 48.68, "elapsed_time": "2:12:23", "remaining_time": "2:19:36", "throughput": 686.57, "total_tokens": 5454112} {"current_steps": 19475, "total_steps": 40000, "loss": 0.0, "lr": 2.6032504834394527e-05, "epoch": 216.38888888888889, "percentage": 48.69, "elapsed_time": "2:12:25", "remaining_time": "2:19:34", "throughput": 686.58, "total_tokens": 5455488} {"current_steps": 19480, "total_steps": 40000, "loss": 0.0, "lr": 2.602269565442964e-05, "epoch": 216.44444444444446, "percentage": 48.7, "elapsed_time": "2:12:27", "remaining_time": "2:19:32", "throughput": 686.59, "total_tokens": 5456896} {"current_steps": 19485, "total_steps": 40000, "loss": 0.0, "lr": 2.6012886316752227e-05, "epoch": 216.5, "percentage": 48.71, "elapsed_time": "2:12:29", "remaining_time": "2:19:29", "throughput": 686.6, "total_tokens": 5458304} {"current_steps": 19490, "total_steps": 40000, "loss": 0.0, "lr": 2.6003076822875018e-05, "epoch": 216.55555555555554, "percentage": 48.73, "elapsed_time": "2:12:31", "remaining_time": "2:19:27", "throughput": 686.61, "total_tokens": 5459712} {"current_steps": 19495, "total_steps": 40000, "loss": 0.0, "lr": 2.5993267174310755e-05, "epoch": 216.61111111111111, "percentage": 48.74, "elapsed_time": "2:12:33", "remaining_time": "2:19:25", "throughput": 686.62, "total_tokens": 5461104} {"current_steps": 19500, "total_steps": 40000, "loss": 0.0, "lr": 2.5983457372572218e-05, "epoch": 216.66666666666666, "percentage": 48.75, "elapsed_time": "2:12:35", "remaining_time": "2:19:23", "throughput": 686.62, "total_tokens": 5462448} {"current_steps": 19505, "total_steps": 40000, "loss": 0.0, "lr": 2.597364741917219e-05, "epoch": 216.72222222222223, "percentage": 48.76, "elapsed_time": "2:12:37", "remaining_time": "2:19:21", "throughput": 686.63, "total_tokens": 5463856} {"current_steps": 19510, "total_steps": 40000, "loss": 0.0, "lr": 2.5963837315623492e-05, "epoch": 216.77777777777777, "percentage": 48.77, "elapsed_time": "2:12:39", "remaining_time": "2:19:19", "throughput": 686.64, "total_tokens": 5465232} {"current_steps": 19515, "total_steps": 40000, "loss": 0.0, "lr": 2.595402706343897e-05, "epoch": 216.83333333333334, "percentage": 48.79, "elapsed_time": "2:12:41", "remaining_time": "2:19:17", "throughput": 686.65, "total_tokens": 5466672} {"current_steps": 19520, "total_steps": 40000, "loss": 0.0, "lr": 2.594421666413148e-05, "epoch": 216.88888888888889, "percentage": 48.8, "elapsed_time": "2:12:43", "remaining_time": "2:19:14", "throughput": 686.67, "total_tokens": 5468112} {"current_steps": 19525, "total_steps": 40000, "loss": 0.0, "lr": 2.5934406119213928e-05, "epoch": 216.94444444444446, "percentage": 48.81, "elapsed_time": "2:12:45", "remaining_time": "2:19:12", "throughput": 686.67, "total_tokens": 5469504} {"current_steps": 19530, "total_steps": 40000, "loss": 0.0, "lr": 2.5924595430199193e-05, "epoch": 217.0, "percentage": 48.83, "elapsed_time": "2:12:47", "remaining_time": "2:19:10", "throughput": 686.66, "total_tokens": 5470848} {"current_steps": 19535, "total_steps": 40000, "loss": 0.0, "lr": 2.5914784598600238e-05, "epoch": 217.05555555555554, "percentage": 48.84, "elapsed_time": "2:12:49", "remaining_time": "2:19:08", "throughput": 686.65, "total_tokens": 5472240} {"current_steps": 19540, "total_steps": 40000, "loss": 0.0, "lr": 2.5904973625930002e-05, "epoch": 217.11111111111111, "percentage": 48.85, "elapsed_time": "2:12:51", "remaining_time": "2:19:06", "throughput": 686.65, "total_tokens": 5473616} {"current_steps": 19545, "total_steps": 40000, "loss": 0.0, "lr": 2.5895162513701456e-05, "epoch": 217.16666666666666, "percentage": 48.86, "elapsed_time": "2:12:53", "remaining_time": "2:19:04", "throughput": 686.66, "total_tokens": 5475008} {"current_steps": 19550, "total_steps": 40000, "loss": 0.0, "lr": 2.5885351263427593e-05, "epoch": 217.22222222222223, "percentage": 48.88, "elapsed_time": "2:12:55", "remaining_time": "2:19:02", "throughput": 686.66, "total_tokens": 5476384} {"current_steps": 19555, "total_steps": 40000, "loss": 0.0, "lr": 2.5875539876621448e-05, "epoch": 217.27777777777777, "percentage": 48.89, "elapsed_time": "2:12:57", "remaining_time": "2:19:00", "throughput": 686.67, "total_tokens": 5477776} {"current_steps": 19560, "total_steps": 40000, "loss": 0.0, "lr": 2.586572835479605e-05, "epoch": 217.33333333333334, "percentage": 48.9, "elapsed_time": "2:12:59", "remaining_time": "2:18:58", "throughput": 686.68, "total_tokens": 5479168} {"current_steps": 19565, "total_steps": 40000, "loss": 0.0, "lr": 2.585591669946446e-05, "epoch": 217.38888888888889, "percentage": 48.91, "elapsed_time": "2:13:01", "remaining_time": "2:18:56", "throughput": 686.68, "total_tokens": 5480528} {"current_steps": 19570, "total_steps": 40000, "loss": 0.0, "lr": 2.5846104912139756e-05, "epoch": 217.44444444444446, "percentage": 48.93, "elapsed_time": "2:13:03", "remaining_time": "2:18:53", "throughput": 686.69, "total_tokens": 5481936} {"current_steps": 19575, "total_steps": 40000, "loss": 0.0, "lr": 2.583629299433505e-05, "epoch": 217.5, "percentage": 48.94, "elapsed_time": "2:13:05", "remaining_time": "2:18:51", "throughput": 686.7, "total_tokens": 5483328} {"current_steps": 19580, "total_steps": 40000, "loss": 0.0, "lr": 2.582648094756345e-05, "epoch": 217.55555555555554, "percentage": 48.95, "elapsed_time": "2:13:06", "remaining_time": "2:18:49", "throughput": 686.71, "total_tokens": 5484752} {"current_steps": 19585, "total_steps": 40000, "loss": 0.0, "lr": 2.5816668773338098e-05, "epoch": 217.61111111111111, "percentage": 48.96, "elapsed_time": "2:13:08", "remaining_time": "2:18:47", "throughput": 686.72, "total_tokens": 5486112} {"current_steps": 19590, "total_steps": 40000, "loss": 0.0, "lr": 2.580685647317216e-05, "epoch": 217.66666666666666, "percentage": 48.98, "elapsed_time": "2:13:10", "remaining_time": "2:18:45", "throughput": 686.73, "total_tokens": 5487536} {"current_steps": 19595, "total_steps": 40000, "loss": 0.0, "lr": 2.5797044048578818e-05, "epoch": 217.72222222222223, "percentage": 48.99, "elapsed_time": "2:13:12", "remaining_time": "2:18:43", "throughput": 686.74, "total_tokens": 5488928} {"current_steps": 19600, "total_steps": 40000, "loss": 0.0, "lr": 2.5787231501071262e-05, "epoch": 217.77777777777777, "percentage": 49.0, "elapsed_time": "2:13:14", "remaining_time": "2:18:40", "throughput": 686.75, "total_tokens": 5490352} {"current_steps": 19600, "total_steps": 40000, "eval_loss": 0.371354877948761, "epoch": 217.77777777777777, "percentage": 49.0, "elapsed_time": "2:13:15", "remaining_time": "2:18:42", "throughput": 686.64, "total_tokens": 5490352} {"current_steps": 19605, "total_steps": 40000, "loss": 0.0, "lr": 2.577741883216272e-05, "epoch": 217.83333333333334, "percentage": 49.01, "elapsed_time": "2:13:19", "remaining_time": "2:18:41", "throughput": 686.52, "total_tokens": 5491744} {"current_steps": 19610, "total_steps": 40000, "loss": 0.0, "lr": 2.576760604336642e-05, "epoch": 217.88888888888889, "percentage": 49.02, "elapsed_time": "2:13:21", "remaining_time": "2:18:39", "throughput": 686.53, "total_tokens": 5493200} {"current_steps": 19615, "total_steps": 40000, "loss": 0.0, "lr": 2.575779313619563e-05, "epoch": 217.94444444444446, "percentage": 49.04, "elapsed_time": "2:13:23", "remaining_time": "2:18:37", "throughput": 686.54, "total_tokens": 5494624} {"current_steps": 19620, "total_steps": 40000, "loss": 0.0, "lr": 2.5747980112163605e-05, "epoch": 218.0, "percentage": 49.05, "elapsed_time": "2:13:25", "remaining_time": "2:18:35", "throughput": 686.54, "total_tokens": 5496016} {"current_steps": 19625, "total_steps": 40000, "loss": 0.0, "lr": 2.5738166972783656e-05, "epoch": 218.05555555555554, "percentage": 49.06, "elapsed_time": "2:13:27", "remaining_time": "2:18:33", "throughput": 686.52, "total_tokens": 5497424} {"current_steps": 19630, "total_steps": 40000, "loss": 0.0, "lr": 2.5728353719569075e-05, "epoch": 218.11111111111111, "percentage": 49.08, "elapsed_time": "2:13:29", "remaining_time": "2:18:31", "throughput": 686.53, "total_tokens": 5498784} {"current_steps": 19635, "total_steps": 40000, "loss": 0.0, "lr": 2.57185403540332e-05, "epoch": 218.16666666666666, "percentage": 49.09, "elapsed_time": "2:13:31", "remaining_time": "2:18:29", "throughput": 686.53, "total_tokens": 5500176} {"current_steps": 19640, "total_steps": 40000, "loss": 0.0, "lr": 2.5708726877689375e-05, "epoch": 218.22222222222223, "percentage": 49.1, "elapsed_time": "2:13:33", "remaining_time": "2:18:27", "throughput": 686.54, "total_tokens": 5501584} {"current_steps": 19645, "total_steps": 40000, "loss": 0.0, "lr": 2.5698913292050964e-05, "epoch": 218.27777777777777, "percentage": 49.11, "elapsed_time": "2:13:35", "remaining_time": "2:18:25", "throughput": 686.55, "total_tokens": 5502992} {"current_steps": 19650, "total_steps": 40000, "loss": 0.0, "lr": 2.568909959863133e-05, "epoch": 218.33333333333334, "percentage": 49.12, "elapsed_time": "2:13:37", "remaining_time": "2:18:22", "throughput": 686.57, "total_tokens": 5504416} {"current_steps": 19655, "total_steps": 40000, "loss": 0.0, "lr": 2.5679285798943887e-05, "epoch": 218.38888888888889, "percentage": 49.14, "elapsed_time": "2:13:39", "remaining_time": "2:18:20", "throughput": 686.58, "total_tokens": 5505824} {"current_steps": 19660, "total_steps": 40000, "loss": 0.0, "lr": 2.5669471894502035e-05, "epoch": 218.44444444444446, "percentage": 49.15, "elapsed_time": "2:13:41", "remaining_time": "2:18:18", "throughput": 686.58, "total_tokens": 5507200} {"current_steps": 19665, "total_steps": 40000, "loss": 0.0, "lr": 2.56596578868192e-05, "epoch": 218.5, "percentage": 49.16, "elapsed_time": "2:13:43", "remaining_time": "2:18:16", "throughput": 686.58, "total_tokens": 5508544} {"current_steps": 19670, "total_steps": 40000, "loss": 0.0, "lr": 2.564984377740883e-05, "epoch": 218.55555555555554, "percentage": 49.18, "elapsed_time": "2:13:45", "remaining_time": "2:18:14", "throughput": 686.59, "total_tokens": 5509936} {"current_steps": 19675, "total_steps": 40000, "loss": 0.0, "lr": 2.564002956778438e-05, "epoch": 218.61111111111111, "percentage": 49.19, "elapsed_time": "2:13:47", "remaining_time": "2:18:12", "throughput": 686.6, "total_tokens": 5511360} {"current_steps": 19680, "total_steps": 40000, "loss": 0.0, "lr": 2.563021525945934e-05, "epoch": 218.66666666666666, "percentage": 49.2, "elapsed_time": "2:13:48", "remaining_time": "2:18:10", "throughput": 686.61, "total_tokens": 5512800} {"current_steps": 19685, "total_steps": 40000, "loss": 0.0, "lr": 2.562040085394718e-05, "epoch": 218.72222222222223, "percentage": 49.21, "elapsed_time": "2:13:50", "remaining_time": "2:18:07", "throughput": 686.62, "total_tokens": 5514192} {"current_steps": 19690, "total_steps": 40000, "loss": 0.0, "lr": 2.56105863527614e-05, "epoch": 218.77777777777777, "percentage": 49.23, "elapsed_time": "2:13:52", "remaining_time": "2:18:05", "throughput": 686.63, "total_tokens": 5515600} {"current_steps": 19695, "total_steps": 40000, "loss": 0.0, "lr": 2.5600771757415548e-05, "epoch": 218.83333333333334, "percentage": 49.24, "elapsed_time": "2:13:54", "remaining_time": "2:18:03", "throughput": 686.64, "total_tokens": 5516992} {"current_steps": 19700, "total_steps": 40000, "loss": 0.0, "lr": 2.5590957069423134e-05, "epoch": 218.88888888888889, "percentage": 49.25, "elapsed_time": "2:13:56", "remaining_time": "2:18:01", "throughput": 686.65, "total_tokens": 5518448} {"current_steps": 19705, "total_steps": 40000, "loss": 0.0, "lr": 2.5581142290297716e-05, "epoch": 218.94444444444446, "percentage": 49.26, "elapsed_time": "2:13:58", "remaining_time": "2:17:59", "throughput": 686.67, "total_tokens": 5519856} {"current_steps": 19710, "total_steps": 40000, "loss": 0.0, "lr": 2.557132742155285e-05, "epoch": 219.0, "percentage": 49.28, "elapsed_time": "2:14:00", "remaining_time": "2:17:57", "throughput": 686.66, "total_tokens": 5521264} {"current_steps": 19715, "total_steps": 40000, "loss": 0.0, "lr": 2.556151246470212e-05, "epoch": 219.05555555555554, "percentage": 49.29, "elapsed_time": "2:14:02", "remaining_time": "2:17:55", "throughput": 686.65, "total_tokens": 5522688} {"current_steps": 19720, "total_steps": 40000, "loss": 0.0, "lr": 2.5551697421259114e-05, "epoch": 219.11111111111111, "percentage": 49.3, "elapsed_time": "2:14:04", "remaining_time": "2:17:53", "throughput": 686.67, "total_tokens": 5524144} {"current_steps": 19725, "total_steps": 40000, "loss": 0.0, "lr": 2.554188229273743e-05, "epoch": 219.16666666666666, "percentage": 49.31, "elapsed_time": "2:14:06", "remaining_time": "2:17:51", "throughput": 686.67, "total_tokens": 5525520} {"current_steps": 19730, "total_steps": 40000, "loss": 0.0, "lr": 2.5532067080650678e-05, "epoch": 219.22222222222223, "percentage": 49.33, "elapsed_time": "2:14:08", "remaining_time": "2:17:49", "throughput": 686.68, "total_tokens": 5526928} {"current_steps": 19735, "total_steps": 40000, "loss": 0.0, "lr": 2.55222517865125e-05, "epoch": 219.27777777777777, "percentage": 49.34, "elapsed_time": "2:14:10", "remaining_time": "2:17:46", "throughput": 686.69, "total_tokens": 5528352} {"current_steps": 19740, "total_steps": 40000, "loss": 0.0, "lr": 2.5512436411836538e-05, "epoch": 219.33333333333334, "percentage": 49.35, "elapsed_time": "2:14:12", "remaining_time": "2:17:44", "throughput": 686.7, "total_tokens": 5529712} {"current_steps": 19745, "total_steps": 40000, "loss": 0.0, "lr": 2.5502620958136443e-05, "epoch": 219.38888888888889, "percentage": 49.36, "elapsed_time": "2:14:14", "remaining_time": "2:17:42", "throughput": 686.71, "total_tokens": 5531120} {"current_steps": 19750, "total_steps": 40000, "loss": 0.0, "lr": 2.5492805426925874e-05, "epoch": 219.44444444444446, "percentage": 49.38, "elapsed_time": "2:14:16", "remaining_time": "2:17:40", "throughput": 686.72, "total_tokens": 5532528} {"current_steps": 19755, "total_steps": 40000, "loss": 0.0, "lr": 2.5482989819718523e-05, "epoch": 219.5, "percentage": 49.39, "elapsed_time": "2:14:18", "remaining_time": "2:17:38", "throughput": 686.72, "total_tokens": 5533888} {"current_steps": 19760, "total_steps": 40000, "loss": 0.0, "lr": 2.5473174138028065e-05, "epoch": 219.55555555555554, "percentage": 49.4, "elapsed_time": "2:14:20", "remaining_time": "2:17:36", "throughput": 686.72, "total_tokens": 5535248} {"current_steps": 19765, "total_steps": 40000, "loss": 0.0, "lr": 2.5463358383368212e-05, "epoch": 219.61111111111111, "percentage": 49.41, "elapsed_time": "2:14:22", "remaining_time": "2:17:34", "throughput": 686.73, "total_tokens": 5536624} {"current_steps": 19770, "total_steps": 40000, "loss": 0.0, "lr": 2.545354255725267e-05, "epoch": 219.66666666666666, "percentage": 49.43, "elapsed_time": "2:14:24", "remaining_time": "2:17:31", "throughput": 686.74, "total_tokens": 5538064} {"current_steps": 19775, "total_steps": 40000, "loss": 0.0, "lr": 2.5443726661195165e-05, "epoch": 219.72222222222223, "percentage": 49.44, "elapsed_time": "2:14:26", "remaining_time": "2:17:29", "throughput": 686.75, "total_tokens": 5539488} {"current_steps": 19780, "total_steps": 40000, "loss": 0.0, "lr": 2.543391069670944e-05, "epoch": 219.77777777777777, "percentage": 49.45, "elapsed_time": "2:14:28", "remaining_time": "2:17:27", "throughput": 686.76, "total_tokens": 5540864} {"current_steps": 19785, "total_steps": 40000, "loss": 0.0, "lr": 2.5424094665309228e-05, "epoch": 219.83333333333334, "percentage": 49.46, "elapsed_time": "2:14:30", "remaining_time": "2:17:25", "throughput": 686.77, "total_tokens": 5542272} {"current_steps": 19790, "total_steps": 40000, "loss": 0.0, "lr": 2.5414278568508292e-05, "epoch": 219.88888888888889, "percentage": 49.48, "elapsed_time": "2:14:32", "remaining_time": "2:17:23", "throughput": 686.78, "total_tokens": 5543696} {"current_steps": 19795, "total_steps": 40000, "loss": 0.0, "lr": 2.540446240782039e-05, "epoch": 219.94444444444446, "percentage": 49.49, "elapsed_time": "2:14:33", "remaining_time": "2:17:21", "throughput": 686.79, "total_tokens": 5545072} {"current_steps": 19800, "total_steps": 40000, "loss": 0.0, "lr": 2.5394646184759307e-05, "epoch": 220.0, "percentage": 49.5, "elapsed_time": "2:14:36", "remaining_time": "2:17:19", "throughput": 686.77, "total_tokens": 5546432} {"current_steps": 19800, "total_steps": 40000, "eval_loss": 0.360029011964798, "epoch": 220.0, "percentage": 49.5, "elapsed_time": "2:14:37", "remaining_time": "2:17:20", "throughput": 686.67, "total_tokens": 5546432} {"current_steps": 19805, "total_steps": 40000, "loss": 0.0, "lr": 2.538482990083882e-05, "epoch": 220.05555555555554, "percentage": 49.51, "elapsed_time": "2:14:40", "remaining_time": "2:17:19", "throughput": 686.54, "total_tokens": 5547824} {"current_steps": 19810, "total_steps": 40000, "loss": 0.0, "lr": 2.5375013557572725e-05, "epoch": 220.11111111111111, "percentage": 49.53, "elapsed_time": "2:14:42", "remaining_time": "2:17:17", "throughput": 686.54, "total_tokens": 5549216} {"current_steps": 19815, "total_steps": 40000, "loss": 0.0, "lr": 2.536519715647483e-05, "epoch": 220.16666666666666, "percentage": 49.54, "elapsed_time": "2:14:44", "remaining_time": "2:17:15", "throughput": 686.55, "total_tokens": 5550608} {"current_steps": 19820, "total_steps": 40000, "loss": 0.0, "lr": 2.535538069905894e-05, "epoch": 220.22222222222223, "percentage": 49.55, "elapsed_time": "2:14:46", "remaining_time": "2:17:13", "throughput": 686.56, "total_tokens": 5552032} {"current_steps": 19825, "total_steps": 40000, "loss": 0.0, "lr": 2.534556418683888e-05, "epoch": 220.27777777777777, "percentage": 49.56, "elapsed_time": "2:14:48", "remaining_time": "2:17:11", "throughput": 686.57, "total_tokens": 5553472} {"current_steps": 19830, "total_steps": 40000, "loss": 0.0, "lr": 2.5335747621328486e-05, "epoch": 220.33333333333334, "percentage": 49.58, "elapsed_time": "2:14:50", "remaining_time": "2:17:09", "throughput": 686.58, "total_tokens": 5554864} {"current_steps": 19835, "total_steps": 40000, "loss": 0.0, "lr": 2.5325931004041586e-05, "epoch": 220.38888888888889, "percentage": 49.59, "elapsed_time": "2:14:52", "remaining_time": "2:17:07", "throughput": 686.59, "total_tokens": 5556288} {"current_steps": 19840, "total_steps": 40000, "loss": 0.0, "lr": 2.5316114336492032e-05, "epoch": 220.44444444444446, "percentage": 49.6, "elapsed_time": "2:14:54", "remaining_time": "2:17:05", "throughput": 686.57, "total_tokens": 5557648} {"current_steps": 19845, "total_steps": 40000, "loss": 0.0, "lr": 2.530629762019367e-05, "epoch": 220.5, "percentage": 49.61, "elapsed_time": "2:14:56", "remaining_time": "2:17:03", "throughput": 686.58, "total_tokens": 5559024} {"current_steps": 19850, "total_steps": 40000, "loss": 0.0, "lr": 2.5296480856660364e-05, "epoch": 220.55555555555554, "percentage": 49.62, "elapsed_time": "2:14:58", "remaining_time": "2:17:01", "throughput": 686.59, "total_tokens": 5560432} {"current_steps": 19855, "total_steps": 40000, "loss": 0.0, "lr": 2.528666404740599e-05, "epoch": 220.61111111111111, "percentage": 49.64, "elapsed_time": "2:15:00", "remaining_time": "2:16:58", "throughput": 686.6, "total_tokens": 5561856} {"current_steps": 19860, "total_steps": 40000, "loss": 0.0, "lr": 2.527684719394442e-05, "epoch": 220.66666666666666, "percentage": 49.65, "elapsed_time": "2:15:02", "remaining_time": "2:16:56", "throughput": 686.61, "total_tokens": 5563280} {"current_steps": 19865, "total_steps": 40000, "loss": 0.0, "lr": 2.526703029778953e-05, "epoch": 220.72222222222223, "percentage": 49.66, "elapsed_time": "2:15:04", "remaining_time": "2:16:54", "throughput": 686.62, "total_tokens": 5564688} {"current_steps": 19870, "total_steps": 40000, "loss": 0.0, "lr": 2.5257213360455208e-05, "epoch": 220.77777777777777, "percentage": 49.68, "elapsed_time": "2:15:06", "remaining_time": "2:16:52", "throughput": 686.63, "total_tokens": 5566048} {"current_steps": 19875, "total_steps": 40000, "loss": 0.0, "lr": 2.5247396383455353e-05, "epoch": 220.83333333333334, "percentage": 49.69, "elapsed_time": "2:15:08", "remaining_time": "2:16:50", "throughput": 686.64, "total_tokens": 5567440} {"current_steps": 19880, "total_steps": 40000, "loss": 0.0, "lr": 2.523757936830387e-05, "epoch": 220.88888888888889, "percentage": 49.7, "elapsed_time": "2:15:10", "remaining_time": "2:16:48", "throughput": 686.64, "total_tokens": 5568800} {"current_steps": 19885, "total_steps": 40000, "loss": 0.0, "lr": 2.5227762316514662e-05, "epoch": 220.94444444444446, "percentage": 49.71, "elapsed_time": "2:15:12", "remaining_time": "2:16:45", "throughput": 686.65, "total_tokens": 5570240} {"current_steps": 19890, "total_steps": 40000, "loss": 0.0, "lr": 2.5217945229601648e-05, "epoch": 221.0, "percentage": 49.73, "elapsed_time": "2:15:14", "remaining_time": "2:16:43", "throughput": 686.65, "total_tokens": 5571632} {"current_steps": 19895, "total_steps": 40000, "loss": 0.0, "lr": 2.5208128109078738e-05, "epoch": 221.05555555555554, "percentage": 49.74, "elapsed_time": "2:15:16", "remaining_time": "2:16:42", "throughput": 686.64, "total_tokens": 5573056} {"current_steps": 19900, "total_steps": 40000, "loss": 0.0, "lr": 2.5198310956459853e-05, "epoch": 221.11111111111111, "percentage": 49.75, "elapsed_time": "2:15:18", "remaining_time": "2:16:39", "throughput": 686.65, "total_tokens": 5574448} {"current_steps": 19905, "total_steps": 40000, "loss": 0.0, "lr": 2.518849377325893e-05, "epoch": 221.16666666666666, "percentage": 49.76, "elapsed_time": "2:15:20", "remaining_time": "2:16:37", "throughput": 686.65, "total_tokens": 5575824} {"current_steps": 19910, "total_steps": 40000, "loss": 0.0, "lr": 2.51786765609899e-05, "epoch": 221.22222222222223, "percentage": 49.78, "elapsed_time": "2:15:22", "remaining_time": "2:16:35", "throughput": 686.66, "total_tokens": 5577232} {"current_steps": 19915, "total_steps": 40000, "loss": 0.0, "lr": 2.5168859321166694e-05, "epoch": 221.27777777777777, "percentage": 49.79, "elapsed_time": "2:15:24", "remaining_time": "2:16:33", "throughput": 686.67, "total_tokens": 5578592} {"current_steps": 19920, "total_steps": 40000, "loss": 0.0, "lr": 2.515904205530326e-05, "epoch": 221.33333333333334, "percentage": 49.8, "elapsed_time": "2:15:26", "remaining_time": "2:16:31", "throughput": 686.68, "total_tokens": 5580016} {"current_steps": 19925, "total_steps": 40000, "loss": 0.0, "lr": 2.514922476491355e-05, "epoch": 221.38888888888889, "percentage": 49.81, "elapsed_time": "2:15:28", "remaining_time": "2:16:29", "throughput": 686.68, "total_tokens": 5581376} {"current_steps": 19930, "total_steps": 40000, "loss": 0.0, "lr": 2.51394074515115e-05, "epoch": 221.44444444444446, "percentage": 49.83, "elapsed_time": "2:15:29", "remaining_time": "2:16:27", "throughput": 686.69, "total_tokens": 5582768} {"current_steps": 19935, "total_steps": 40000, "loss": 0.0, "lr": 2.5129590116611067e-05, "epoch": 221.5, "percentage": 49.84, "elapsed_time": "2:15:31", "remaining_time": "2:16:24", "throughput": 686.69, "total_tokens": 5584128} {"current_steps": 19940, "total_steps": 40000, "loss": 0.0, "lr": 2.5119772761726212e-05, "epoch": 221.55555555555554, "percentage": 49.85, "elapsed_time": "2:15:33", "remaining_time": "2:16:22", "throughput": 686.71, "total_tokens": 5585568} {"current_steps": 19945, "total_steps": 40000, "loss": 0.0, "lr": 2.5109955388370893e-05, "epoch": 221.61111111111111, "percentage": 49.86, "elapsed_time": "2:15:35", "remaining_time": "2:16:20", "throughput": 686.71, "total_tokens": 5586928} {"current_steps": 19950, "total_steps": 40000, "loss": 0.0, "lr": 2.510013799805907e-05, "epoch": 221.66666666666666, "percentage": 49.88, "elapsed_time": "2:15:37", "remaining_time": "2:16:18", "throughput": 686.72, "total_tokens": 5588304} {"current_steps": 19955, "total_steps": 40000, "loss": 0.0, "lr": 2.5090320592304706e-05, "epoch": 221.72222222222223, "percentage": 49.89, "elapsed_time": "2:15:39", "remaining_time": "2:16:16", "throughput": 686.73, "total_tokens": 5589776} {"current_steps": 19960, "total_steps": 40000, "loss": 0.0, "lr": 2.5080503172621777e-05, "epoch": 221.77777777777777, "percentage": 49.9, "elapsed_time": "2:15:41", "remaining_time": "2:16:14", "throughput": 686.74, "total_tokens": 5591168} {"current_steps": 19965, "total_steps": 40000, "loss": 0.0, "lr": 2.5070685740524246e-05, "epoch": 221.83333333333334, "percentage": 49.91, "elapsed_time": "2:15:43", "remaining_time": "2:16:12", "throughput": 686.76, "total_tokens": 5592608} {"current_steps": 19970, "total_steps": 40000, "loss": 0.0, "lr": 2.5060868297526084e-05, "epoch": 221.88888888888889, "percentage": 49.93, "elapsed_time": "2:15:45", "remaining_time": "2:16:09", "throughput": 686.76, "total_tokens": 5594000} {"current_steps": 19975, "total_steps": 40000, "loss": 0.0, "lr": 2.5051050845141267e-05, "epoch": 221.94444444444446, "percentage": 49.94, "elapsed_time": "2:15:47", "remaining_time": "2:16:07", "throughput": 686.78, "total_tokens": 5595424} {"current_steps": 19980, "total_steps": 40000, "loss": 0.0, "lr": 2.5041233384883765e-05, "epoch": 222.0, "percentage": 49.95, "elapsed_time": "2:15:49", "remaining_time": "2:16:05", "throughput": 686.77, "total_tokens": 5596832} {"current_steps": 19985, "total_steps": 40000, "loss": 0.0, "lr": 2.5031415918267564e-05, "epoch": 222.05555555555554, "percentage": 49.96, "elapsed_time": "2:15:51", "remaining_time": "2:16:03", "throughput": 686.76, "total_tokens": 5598256} {"current_steps": 19990, "total_steps": 40000, "loss": 0.0, "lr": 2.5021598446806626e-05, "epoch": 222.11111111111111, "percentage": 49.98, "elapsed_time": "2:15:53", "remaining_time": "2:16:01", "throughput": 686.77, "total_tokens": 5599648} {"current_steps": 19995, "total_steps": 40000, "loss": 0.0, "lr": 2.5011780972014937e-05, "epoch": 222.16666666666666, "percentage": 49.99, "elapsed_time": "2:15:55", "remaining_time": "2:15:59", "throughput": 686.78, "total_tokens": 5601040} {"current_steps": 20000, "total_steps": 40000, "loss": 0.0, "lr": 2.5001963495406478e-05, "epoch": 222.22222222222223, "percentage": 50.0, "elapsed_time": "2:15:57", "remaining_time": "2:15:57", "throughput": 686.78, "total_tokens": 5602400} {"current_steps": 20000, "total_steps": 40000, "eval_loss": 0.40143242478370667, "epoch": 222.22222222222223, "percentage": 50.0, "elapsed_time": "2:15:58", "remaining_time": "2:15:58", "throughput": 686.67, "total_tokens": 5602400} {"current_steps": 20005, "total_steps": 40000, "loss": 0.0, "lr": 2.499214601849522e-05, "epoch": 222.27777777777777, "percentage": 50.01, "elapsed_time": "2:16:02", "remaining_time": "2:15:58", "throughput": 686.54, "total_tokens": 5603824} {"current_steps": 20010, "total_steps": 40000, "loss": 0.0, "lr": 2.4982328542795148e-05, "epoch": 222.33333333333334, "percentage": 50.02, "elapsed_time": "2:16:04", "remaining_time": "2:15:56", "throughput": 686.54, "total_tokens": 5605232} {"current_steps": 20015, "total_steps": 40000, "loss": 0.0, "lr": 2.497251106982024e-05, "epoch": 222.38888888888889, "percentage": 50.04, "elapsed_time": "2:16:06", "remaining_time": "2:15:54", "throughput": 686.55, "total_tokens": 5606608} {"current_steps": 20020, "total_steps": 40000, "loss": 0.0, "lr": 2.4962693601084458e-05, "epoch": 222.44444444444446, "percentage": 50.05, "elapsed_time": "2:16:08", "remaining_time": "2:15:52", "throughput": 686.55, "total_tokens": 5607984} {"current_steps": 20025, "total_steps": 40000, "loss": 0.0, "lr": 2.4952876138101794e-05, "epoch": 222.5, "percentage": 50.06, "elapsed_time": "2:16:10", "remaining_time": "2:15:49", "throughput": 686.56, "total_tokens": 5609392} {"current_steps": 20030, "total_steps": 40000, "loss": 0.0, "lr": 2.4943058682386233e-05, "epoch": 222.55555555555554, "percentage": 50.08, "elapsed_time": "2:16:12", "remaining_time": "2:15:47", "throughput": 686.57, "total_tokens": 5610800} {"current_steps": 20035, "total_steps": 40000, "loss": 0.0, "lr": 2.493324123545173e-05, "epoch": 222.61111111111111, "percentage": 50.09, "elapsed_time": "2:16:14", "remaining_time": "2:15:45", "throughput": 686.58, "total_tokens": 5612224} {"current_steps": 20040, "total_steps": 40000, "loss": 0.0, "lr": 2.4923423798812272e-05, "epoch": 222.66666666666666, "percentage": 50.1, "elapsed_time": "2:16:16", "remaining_time": "2:15:43", "throughput": 686.6, "total_tokens": 5613664} {"current_steps": 20045, "total_steps": 40000, "loss": 0.0, "lr": 2.4913606373981825e-05, "epoch": 222.72222222222223, "percentage": 50.11, "elapsed_time": "2:16:17", "remaining_time": "2:15:41", "throughput": 686.61, "total_tokens": 5615056} {"current_steps": 20050, "total_steps": 40000, "loss": 0.0, "lr": 2.4903788962474357e-05, "epoch": 222.77777777777777, "percentage": 50.12, "elapsed_time": "2:16:19", "remaining_time": "2:15:39", "throughput": 686.62, "total_tokens": 5616480} {"current_steps": 20055, "total_steps": 40000, "loss": 0.0, "lr": 2.489397156580385e-05, "epoch": 222.83333333333334, "percentage": 50.14, "elapsed_time": "2:16:21", "remaining_time": "2:15:36", "throughput": 686.62, "total_tokens": 5617856} {"current_steps": 20060, "total_steps": 40000, "loss": 0.0, "lr": 2.4884154185484246e-05, "epoch": 222.88888888888889, "percentage": 50.15, "elapsed_time": "2:16:23", "remaining_time": "2:15:34", "throughput": 686.63, "total_tokens": 5619264} {"current_steps": 20065, "total_steps": 40000, "loss": 0.0, "lr": 2.4874336823029526e-05, "epoch": 222.94444444444446, "percentage": 50.16, "elapsed_time": "2:16:25", "remaining_time": "2:15:32", "throughput": 686.64, "total_tokens": 5620640} {"current_steps": 20070, "total_steps": 40000, "loss": 0.0, "lr": 2.4864519479953656e-05, "epoch": 223.0, "percentage": 50.18, "elapsed_time": "2:16:27", "remaining_time": "2:15:30", "throughput": 686.63, "total_tokens": 5622016} {"current_steps": 20075, "total_steps": 40000, "loss": 0.0, "lr": 2.485470215777058e-05, "epoch": 223.05555555555554, "percentage": 50.19, "elapsed_time": "2:16:30", "remaining_time": "2:15:28", "throughput": 686.62, "total_tokens": 5623440} {"current_steps": 20080, "total_steps": 40000, "loss": 0.0, "lr": 2.4844884857994258e-05, "epoch": 223.11111111111111, "percentage": 50.2, "elapsed_time": "2:16:31", "remaining_time": "2:15:26", "throughput": 686.63, "total_tokens": 5624848} {"current_steps": 20085, "total_steps": 40000, "loss": 0.0, "lr": 2.4835067582138638e-05, "epoch": 223.16666666666666, "percentage": 50.21, "elapsed_time": "2:16:33", "remaining_time": "2:15:24", "throughput": 686.64, "total_tokens": 5626272} {"current_steps": 20090, "total_steps": 40000, "loss": 0.0, "lr": 2.4825250331717666e-05, "epoch": 223.22222222222223, "percentage": 50.22, "elapsed_time": "2:16:35", "remaining_time": "2:15:22", "throughput": 686.65, "total_tokens": 5627680} {"current_steps": 20095, "total_steps": 40000, "loss": 0.0, "lr": 2.4815433108245298e-05, "epoch": 223.27777777777777, "percentage": 50.24, "elapsed_time": "2:16:37", "remaining_time": "2:15:20", "throughput": 686.67, "total_tokens": 5629136} {"current_steps": 20100, "total_steps": 40000, "loss": 0.0, "lr": 2.4805615913235456e-05, "epoch": 223.33333333333334, "percentage": 50.25, "elapsed_time": "2:16:39", "remaining_time": "2:15:18", "throughput": 686.68, "total_tokens": 5630560} {"current_steps": 20105, "total_steps": 40000, "loss": 0.0, "lr": 2.479579874820208e-05, "epoch": 223.38888888888889, "percentage": 50.26, "elapsed_time": "2:16:41", "remaining_time": "2:15:15", "throughput": 686.69, "total_tokens": 5632016} {"current_steps": 20110, "total_steps": 40000, "loss": 0.0, "lr": 2.4785981614659115e-05, "epoch": 223.44444444444446, "percentage": 50.28, "elapsed_time": "2:16:43", "remaining_time": "2:15:13", "throughput": 686.7, "total_tokens": 5633392} {"current_steps": 20115, "total_steps": 40000, "loss": 0.0, "lr": 2.477616451412047e-05, "epoch": 223.5, "percentage": 50.29, "elapsed_time": "2:16:45", "remaining_time": "2:15:11", "throughput": 686.7, "total_tokens": 5634752} {"current_steps": 20120, "total_steps": 40000, "loss": 0.0, "lr": 2.476634744810007e-05, "epoch": 223.55555555555554, "percentage": 50.3, "elapsed_time": "2:16:47", "remaining_time": "2:15:09", "throughput": 686.71, "total_tokens": 5636128} {"current_steps": 20125, "total_steps": 40000, "loss": 0.0, "lr": 2.475653041811183e-05, "epoch": 223.61111111111111, "percentage": 50.31, "elapsed_time": "2:16:49", "remaining_time": "2:15:07", "throughput": 686.72, "total_tokens": 5637520} {"current_steps": 20130, "total_steps": 40000, "loss": 0.0, "lr": 2.4746713425669652e-05, "epoch": 223.66666666666666, "percentage": 50.32, "elapsed_time": "2:16:51", "remaining_time": "2:15:05", "throughput": 686.72, "total_tokens": 5638912} {"current_steps": 20135, "total_steps": 40000, "loss": 0.0, "lr": 2.4736896472287458e-05, "epoch": 223.72222222222223, "percentage": 50.34, "elapsed_time": "2:16:53", "remaining_time": "2:15:03", "throughput": 686.74, "total_tokens": 5640336} {"current_steps": 20140, "total_steps": 40000, "loss": 0.0, "lr": 2.4727079559479124e-05, "epoch": 223.77777777777777, "percentage": 50.35, "elapsed_time": "2:16:55", "remaining_time": "2:15:00", "throughput": 686.74, "total_tokens": 5641728} {"current_steps": 20145, "total_steps": 40000, "loss": 0.0, "lr": 2.4717262688758557e-05, "epoch": 223.83333333333334, "percentage": 50.36, "elapsed_time": "2:16:57", "remaining_time": "2:14:58", "throughput": 686.75, "total_tokens": 5643136} {"current_steps": 20150, "total_steps": 40000, "loss": 0.0, "lr": 2.4707445861639637e-05, "epoch": 223.88888888888889, "percentage": 50.38, "elapsed_time": "2:16:59", "remaining_time": "2:14:56", "throughput": 686.76, "total_tokens": 5644512} {"current_steps": 20155, "total_steps": 40000, "loss": 0.0, "lr": 2.4697629079636244e-05, "epoch": 223.94444444444446, "percentage": 50.39, "elapsed_time": "2:17:00", "remaining_time": "2:14:54", "throughput": 686.76, "total_tokens": 5645872} {"current_steps": 20160, "total_steps": 40000, "loss": 0.0, "lr": 2.4687812344262244e-05, "epoch": 224.0, "percentage": 50.4, "elapsed_time": "2:17:03", "remaining_time": "2:14:52", "throughput": 686.76, "total_tokens": 5647264} {"current_steps": 20165, "total_steps": 40000, "loss": 0.0, "lr": 2.46779956570315e-05, "epoch": 224.05555555555554, "percentage": 50.41, "elapsed_time": "2:17:05", "remaining_time": "2:14:50", "throughput": 686.74, "total_tokens": 5648640} {"current_steps": 20170, "total_steps": 40000, "loss": 0.0, "lr": 2.466817901945787e-05, "epoch": 224.11111111111111, "percentage": 50.42, "elapsed_time": "2:17:07", "remaining_time": "2:14:48", "throughput": 686.75, "total_tokens": 5650064} {"current_steps": 20175, "total_steps": 40000, "loss": 0.0, "lr": 2.4658362433055217e-05, "epoch": 224.16666666666666, "percentage": 50.44, "elapsed_time": "2:17:09", "remaining_time": "2:14:46", "throughput": 686.76, "total_tokens": 5651456} {"current_steps": 20180, "total_steps": 40000, "loss": 0.0, "lr": 2.4648545899337356e-05, "epoch": 224.22222222222223, "percentage": 50.45, "elapsed_time": "2:17:11", "remaining_time": "2:14:44", "throughput": 686.77, "total_tokens": 5652880} {"current_steps": 20185, "total_steps": 40000, "loss": 0.0, "lr": 2.4638729419818143e-05, "epoch": 224.27777777777777, "percentage": 50.46, "elapsed_time": "2:17:13", "remaining_time": "2:14:42", "throughput": 686.78, "total_tokens": 5654224} {"current_steps": 20190, "total_steps": 40000, "loss": 0.0, "lr": 2.46289129960114e-05, "epoch": 224.33333333333334, "percentage": 50.48, "elapsed_time": "2:17:14", "remaining_time": "2:14:39", "throughput": 686.79, "total_tokens": 5655664} {"current_steps": 20195, "total_steps": 40000, "loss": 0.0, "lr": 2.4619096629430924e-05, "epoch": 224.38888888888889, "percentage": 50.49, "elapsed_time": "2:17:16", "remaining_time": "2:14:37", "throughput": 686.8, "total_tokens": 5657072} {"current_steps": 20200, "total_steps": 40000, "loss": 0.0, "lr": 2.4609280321590543e-05, "epoch": 224.44444444444446, "percentage": 50.5, "elapsed_time": "2:17:18", "remaining_time": "2:14:35", "throughput": 686.81, "total_tokens": 5658464} {"current_steps": 20200, "total_steps": 40000, "eval_loss": 0.3992190957069397, "epoch": 224.44444444444446, "percentage": 50.5, "elapsed_time": "2:17:20", "remaining_time": "2:14:36", "throughput": 686.7, "total_tokens": 5658464} {"current_steps": 20205, "total_steps": 40000, "loss": 0.0, "lr": 2.4599464074004037e-05, "epoch": 224.5, "percentage": 50.51, "elapsed_time": "2:17:23", "remaining_time": "2:14:36", "throughput": 686.6, "total_tokens": 5659888} {"current_steps": 20210, "total_steps": 40000, "loss": 0.0, "lr": 2.4589647888185204e-05, "epoch": 224.55555555555554, "percentage": 50.52, "elapsed_time": "2:17:25", "remaining_time": "2:14:33", "throughput": 686.6, "total_tokens": 5661280} {"current_steps": 20215, "total_steps": 40000, "loss": 0.0, "lr": 2.4579831765647836e-05, "epoch": 224.61111111111111, "percentage": 50.54, "elapsed_time": "2:17:27", "remaining_time": "2:14:31", "throughput": 686.61, "total_tokens": 5662624} {"current_steps": 20220, "total_steps": 40000, "loss": 0.0, "lr": 2.4570015707905676e-05, "epoch": 224.66666666666666, "percentage": 50.55, "elapsed_time": "2:17:29", "remaining_time": "2:14:29", "throughput": 686.62, "total_tokens": 5664064} {"current_steps": 20225, "total_steps": 40000, "loss": 0.0, "lr": 2.4560199716472508e-05, "epoch": 224.72222222222223, "percentage": 50.56, "elapsed_time": "2:17:31", "remaining_time": "2:14:27", "throughput": 686.63, "total_tokens": 5665472} {"current_steps": 20230, "total_steps": 40000, "loss": 0.0, "lr": 2.455038379286207e-05, "epoch": 224.77777777777777, "percentage": 50.58, "elapsed_time": "2:17:33", "remaining_time": "2:14:25", "throughput": 686.64, "total_tokens": 5666880} {"current_steps": 20235, "total_steps": 40000, "loss": 0.0, "lr": 2.4540567938588095e-05, "epoch": 224.83333333333334, "percentage": 50.59, "elapsed_time": "2:17:35", "remaining_time": "2:14:23", "throughput": 686.64, "total_tokens": 5668272} {"current_steps": 20240, "total_steps": 40000, "loss": 0.0, "lr": 2.4530752155164328e-05, "epoch": 224.88888888888889, "percentage": 50.6, "elapsed_time": "2:17:36", "remaining_time": "2:14:21", "throughput": 686.65, "total_tokens": 5669648} {"current_steps": 20245, "total_steps": 40000, "loss": 0.0, "lr": 2.4520936444104463e-05, "epoch": 224.94444444444446, "percentage": 50.61, "elapsed_time": "2:17:38", "remaining_time": "2:14:19", "throughput": 686.66, "total_tokens": 5671056} {"current_steps": 20250, "total_steps": 40000, "loss": 0.0, "lr": 2.4511120806922218e-05, "epoch": 225.0, "percentage": 50.62, "elapsed_time": "2:17:41", "remaining_time": "2:14:17", "throughput": 686.65, "total_tokens": 5672432} {"current_steps": 20255, "total_steps": 40000, "loss": 0.0, "lr": 2.45013052451313e-05, "epoch": 225.05555555555554, "percentage": 50.64, "elapsed_time": "2:17:43", "remaining_time": "2:14:15", "throughput": 686.63, "total_tokens": 5673776} {"current_steps": 20260, "total_steps": 40000, "loss": 0.0, "lr": 2.4491489760245376e-05, "epoch": 225.11111111111111, "percentage": 50.65, "elapsed_time": "2:17:45", "remaining_time": "2:14:13", "throughput": 686.63, "total_tokens": 5675120} {"current_steps": 20265, "total_steps": 40000, "loss": 0.0, "lr": 2.4481674353778115e-05, "epoch": 225.16666666666666, "percentage": 50.66, "elapsed_time": "2:17:47", "remaining_time": "2:14:10", "throughput": 686.64, "total_tokens": 5676496} {"current_steps": 20270, "total_steps": 40000, "loss": 0.0, "lr": 2.447185902724319e-05, "epoch": 225.22222222222223, "percentage": 50.68, "elapsed_time": "2:17:49", "remaining_time": "2:14:08", "throughput": 686.65, "total_tokens": 5677888} {"current_steps": 20275, "total_steps": 40000, "loss": 0.0, "lr": 2.4462043782154233e-05, "epoch": 225.27777777777777, "percentage": 50.69, "elapsed_time": "2:17:50", "remaining_time": "2:14:06", "throughput": 686.65, "total_tokens": 5679280} {"current_steps": 20280, "total_steps": 40000, "loss": 0.0, "lr": 2.4452228620024895e-05, "epoch": 225.33333333333334, "percentage": 50.7, "elapsed_time": "2:17:52", "remaining_time": "2:14:04", "throughput": 686.66, "total_tokens": 5680688} {"current_steps": 20285, "total_steps": 40000, "loss": 0.0, "lr": 2.4442413542368776e-05, "epoch": 225.38888888888889, "percentage": 50.71, "elapsed_time": "2:17:54", "remaining_time": "2:14:02", "throughput": 686.68, "total_tokens": 5682144} {"current_steps": 20290, "total_steps": 40000, "loss": 0.0, "lr": 2.4432598550699502e-05, "epoch": 225.44444444444446, "percentage": 50.72, "elapsed_time": "2:17:56", "remaining_time": "2:14:00", "throughput": 686.69, "total_tokens": 5683584} {"current_steps": 20295, "total_steps": 40000, "loss": 0.0, "lr": 2.4422783646530663e-05, "epoch": 225.5, "percentage": 50.74, "elapsed_time": "2:17:58", "remaining_time": "2:13:58", "throughput": 686.7, "total_tokens": 5684992} {"current_steps": 20300, "total_steps": 40000, "loss": 0.0, "lr": 2.441296883137584e-05, "epoch": 225.55555555555554, "percentage": 50.75, "elapsed_time": "2:18:00", "remaining_time": "2:13:55", "throughput": 686.71, "total_tokens": 5686416} {"current_steps": 20305, "total_steps": 40000, "loss": 0.0, "lr": 2.4403154106748592e-05, "epoch": 225.61111111111111, "percentage": 50.76, "elapsed_time": "2:18:02", "remaining_time": "2:13:53", "throughput": 686.72, "total_tokens": 5687808} {"current_steps": 20310, "total_steps": 40000, "loss": 0.0, "lr": 2.4393339474162494e-05, "epoch": 225.66666666666666, "percentage": 50.78, "elapsed_time": "2:18:04", "remaining_time": "2:13:51", "throughput": 686.73, "total_tokens": 5689216} {"current_steps": 20315, "total_steps": 40000, "loss": 0.0, "lr": 2.4383524935131062e-05, "epoch": 225.72222222222223, "percentage": 50.79, "elapsed_time": "2:18:06", "remaining_time": "2:13:49", "throughput": 686.74, "total_tokens": 5690592} {"current_steps": 20320, "total_steps": 40000, "loss": 0.0, "lr": 2.437371049116784e-05, "epoch": 225.77777777777777, "percentage": 50.8, "elapsed_time": "2:18:08", "remaining_time": "2:13:47", "throughput": 686.75, "total_tokens": 5692016} {"current_steps": 20325, "total_steps": 40000, "loss": 0.0, "lr": 2.436389614378632e-05, "epoch": 225.83333333333334, "percentage": 50.81, "elapsed_time": "2:18:10", "remaining_time": "2:13:45", "throughput": 686.76, "total_tokens": 5693440} {"current_steps": 20330, "total_steps": 40000, "loss": 0.0, "lr": 2.435408189450002e-05, "epoch": 225.88888888888889, "percentage": 50.82, "elapsed_time": "2:18:12", "remaining_time": "2:13:43", "throughput": 686.76, "total_tokens": 5694800} {"current_steps": 20335, "total_steps": 40000, "loss": 0.0, "lr": 2.4344267744822406e-05, "epoch": 225.94444444444446, "percentage": 50.84, "elapsed_time": "2:18:14", "remaining_time": "2:13:40", "throughput": 686.77, "total_tokens": 5696208} {"current_steps": 20340, "total_steps": 40000, "loss": 0.0, "lr": 2.4334453696266944e-05, "epoch": 226.0, "percentage": 50.85, "elapsed_time": "2:18:16", "remaining_time": "2:13:38", "throughput": 686.77, "total_tokens": 5697600} {"current_steps": 20345, "total_steps": 40000, "loss": 0.0, "lr": 2.432463975034708e-05, "epoch": 226.05555555555554, "percentage": 50.86, "elapsed_time": "2:18:18", "remaining_time": "2:13:37", "throughput": 686.75, "total_tokens": 5698928} {"current_steps": 20350, "total_steps": 40000, "loss": 0.0, "lr": 2.4314825908576265e-05, "epoch": 226.11111111111111, "percentage": 50.88, "elapsed_time": "2:18:20", "remaining_time": "2:13:34", "throughput": 686.75, "total_tokens": 5700288} {"current_steps": 20355, "total_steps": 40000, "loss": 0.0, "lr": 2.4305012172467897e-05, "epoch": 226.16666666666666, "percentage": 50.89, "elapsed_time": "2:18:22", "remaining_time": "2:13:32", "throughput": 686.75, "total_tokens": 5701648} {"current_steps": 20360, "total_steps": 40000, "loss": 0.0, "lr": 2.4295198543535393e-05, "epoch": 226.22222222222223, "percentage": 50.9, "elapsed_time": "2:18:24", "remaining_time": "2:13:30", "throughput": 686.76, "total_tokens": 5703040} {"current_steps": 20365, "total_steps": 40000, "loss": 0.0, "lr": 2.4285385023292124e-05, "epoch": 226.27777777777777, "percentage": 50.91, "elapsed_time": "2:18:26", "remaining_time": "2:13:28", "throughput": 686.77, "total_tokens": 5704464} {"current_steps": 20370, "total_steps": 40000, "loss": 0.0, "lr": 2.427557161325147e-05, "epoch": 226.33333333333334, "percentage": 50.92, "elapsed_time": "2:18:28", "remaining_time": "2:13:26", "throughput": 686.77, "total_tokens": 5705824} {"current_steps": 20375, "total_steps": 40000, "loss": 0.0, "lr": 2.4265758314926778e-05, "epoch": 226.38888888888889, "percentage": 50.94, "elapsed_time": "2:18:30", "remaining_time": "2:13:24", "throughput": 686.79, "total_tokens": 5707280} {"current_steps": 20380, "total_steps": 40000, "loss": 0.0, "lr": 2.4255945129831373e-05, "epoch": 226.44444444444446, "percentage": 50.95, "elapsed_time": "2:18:32", "remaining_time": "2:13:22", "throughput": 686.8, "total_tokens": 5708752} {"current_steps": 20385, "total_steps": 40000, "loss": 0.0, "lr": 2.4246132059478578e-05, "epoch": 226.5, "percentage": 50.96, "elapsed_time": "2:18:33", "remaining_time": "2:13:19", "throughput": 686.81, "total_tokens": 5710144} {"current_steps": 20390, "total_steps": 40000, "loss": 0.0, "lr": 2.4236319105381706e-05, "epoch": 226.55555555555554, "percentage": 50.98, "elapsed_time": "2:18:35", "remaining_time": "2:13:17", "throughput": 686.82, "total_tokens": 5711536} {"current_steps": 20395, "total_steps": 40000, "loss": 0.0, "lr": 2.422650626905401e-05, "epoch": 226.61111111111111, "percentage": 50.99, "elapsed_time": "2:18:37", "remaining_time": "2:13:15", "throughput": 686.83, "total_tokens": 5712928} {"current_steps": 20400, "total_steps": 40000, "loss": 0.0, "lr": 2.4216693552008785e-05, "epoch": 226.66666666666666, "percentage": 51.0, "elapsed_time": "2:18:39", "remaining_time": "2:13:13", "throughput": 686.84, "total_tokens": 5714352} {"current_steps": 20400, "total_steps": 40000, "eval_loss": 0.38984403014183044, "epoch": 226.66666666666666, "percentage": 51.0, "elapsed_time": "2:18:41", "remaining_time": "2:13:14", "throughput": 686.73, "total_tokens": 5714352} {"current_steps": 20405, "total_steps": 40000, "loss": 0.0, "lr": 2.4206880955759247e-05, "epoch": 226.72222222222223, "percentage": 51.01, "elapsed_time": "2:18:44", "remaining_time": "2:13:14", "throughput": 686.61, "total_tokens": 5715696} {"current_steps": 20410, "total_steps": 40000, "loss": 0.0, "lr": 2.419706848181863e-05, "epoch": 226.77777777777777, "percentage": 51.02, "elapsed_time": "2:18:46", "remaining_time": "2:13:11", "throughput": 686.62, "total_tokens": 5717120} {"current_steps": 20415, "total_steps": 40000, "loss": 0.0, "lr": 2.4187256131700153e-05, "epoch": 226.83333333333334, "percentage": 51.04, "elapsed_time": "2:18:48", "remaining_time": "2:13:09", "throughput": 686.63, "total_tokens": 5718512} {"current_steps": 20420, "total_steps": 40000, "loss": 0.0, "lr": 2.4177443906916985e-05, "epoch": 226.88888888888889, "percentage": 51.05, "elapsed_time": "2:18:50", "remaining_time": "2:13:07", "throughput": 686.64, "total_tokens": 5719968} {"current_steps": 20425, "total_steps": 40000, "loss": 0.0, "lr": 2.4167631808982303e-05, "epoch": 226.94444444444446, "percentage": 51.06, "elapsed_time": "2:18:52", "remaining_time": "2:13:05", "throughput": 686.65, "total_tokens": 5721376} {"current_steps": 20430, "total_steps": 40000, "loss": 0.0, "lr": 2.4157819839409264e-05, "epoch": 227.0, "percentage": 51.08, "elapsed_time": "2:18:54", "remaining_time": "2:13:03", "throughput": 686.65, "total_tokens": 5722784} {"current_steps": 20435, "total_steps": 40000, "loss": 0.0, "lr": 2.414800799971098e-05, "epoch": 227.05555555555554, "percentage": 51.09, "elapsed_time": "2:18:56", "remaining_time": "2:13:01", "throughput": 686.63, "total_tokens": 5724144} {"current_steps": 20440, "total_steps": 40000, "loss": 0.0, "lr": 2.4138196291400582e-05, "epoch": 227.11111111111111, "percentage": 51.1, "elapsed_time": "2:18:58", "remaining_time": "2:12:59", "throughput": 686.64, "total_tokens": 5725584} {"current_steps": 20445, "total_steps": 40000, "loss": 0.0, "lr": 2.412838471599114e-05, "epoch": 227.16666666666666, "percentage": 51.11, "elapsed_time": "2:19:00", "remaining_time": "2:12:57", "throughput": 686.65, "total_tokens": 5726976} {"current_steps": 20450, "total_steps": 40000, "loss": 0.0, "lr": 2.411857327499572e-05, "epoch": 227.22222222222223, "percentage": 51.12, "elapsed_time": "2:19:02", "remaining_time": "2:12:55", "throughput": 686.66, "total_tokens": 5728416} {"current_steps": 20455, "total_steps": 40000, "loss": 0.0, "lr": 2.410876196992739e-05, "epoch": 227.27777777777777, "percentage": 51.14, "elapsed_time": "2:19:04", "remaining_time": "2:12:53", "throughput": 686.68, "total_tokens": 5729856} {"current_steps": 20460, "total_steps": 40000, "loss": 0.0, "lr": 2.4098950802299156e-05, "epoch": 227.33333333333334, "percentage": 51.15, "elapsed_time": "2:19:06", "remaining_time": "2:12:50", "throughput": 686.68, "total_tokens": 5731232} {"current_steps": 20465, "total_steps": 40000, "loss": 0.0, "lr": 2.4089139773624027e-05, "epoch": 227.38888888888889, "percentage": 51.16, "elapsed_time": "2:19:08", "remaining_time": "2:12:48", "throughput": 686.69, "total_tokens": 5732640} {"current_steps": 20470, "total_steps": 40000, "loss": 0.0, "lr": 2.4079328885415007e-05, "epoch": 227.44444444444446, "percentage": 51.18, "elapsed_time": "2:19:10", "remaining_time": "2:12:46", "throughput": 686.7, "total_tokens": 5734032} {"current_steps": 20475, "total_steps": 40000, "loss": 0.0, "lr": 2.4069518139185036e-05, "epoch": 227.5, "percentage": 51.19, "elapsed_time": "2:19:12", "remaining_time": "2:12:44", "throughput": 686.71, "total_tokens": 5735456} {"current_steps": 20480, "total_steps": 40000, "loss": 0.0, "lr": 2.405970753644706e-05, "epoch": 227.55555555555554, "percentage": 51.2, "elapsed_time": "2:19:13", "remaining_time": "2:12:42", "throughput": 686.71, "total_tokens": 5736800} {"current_steps": 20485, "total_steps": 40000, "loss": 0.0, "lr": 2.4049897078714e-05, "epoch": 227.61111111111111, "percentage": 51.21, "elapsed_time": "2:19:15", "remaining_time": "2:12:40", "throughput": 686.73, "total_tokens": 5738256} {"current_steps": 20490, "total_steps": 40000, "loss": 0.0, "lr": 2.404008676749874e-05, "epoch": 227.66666666666666, "percentage": 51.23, "elapsed_time": "2:19:17", "remaining_time": "2:12:38", "throughput": 686.74, "total_tokens": 5739632} {"current_steps": 20495, "total_steps": 40000, "loss": 0.0, "lr": 2.403027660431418e-05, "epoch": 227.72222222222223, "percentage": 51.24, "elapsed_time": "2:19:19", "remaining_time": "2:12:35", "throughput": 686.74, "total_tokens": 5741024} {"current_steps": 20500, "total_steps": 40000, "loss": 0.0, "lr": 2.402046659067314e-05, "epoch": 227.77777777777777, "percentage": 51.25, "elapsed_time": "2:19:21", "remaining_time": "2:12:33", "throughput": 686.75, "total_tokens": 5742416} {"current_steps": 20505, "total_steps": 40000, "loss": 0.0, "lr": 2.401065672808847e-05, "epoch": 227.83333333333334, "percentage": 51.26, "elapsed_time": "2:19:23", "remaining_time": "2:12:31", "throughput": 686.75, "total_tokens": 5743776} {"current_steps": 20510, "total_steps": 40000, "loss": 0.0, "lr": 2.400084701807296e-05, "epoch": 227.88888888888889, "percentage": 51.28, "elapsed_time": "2:19:25", "remaining_time": "2:12:29", "throughput": 686.76, "total_tokens": 5745184} {"current_steps": 20515, "total_steps": 40000, "loss": 0.0, "lr": 2.39910374621394e-05, "epoch": 227.94444444444446, "percentage": 51.29, "elapsed_time": "2:19:27", "remaining_time": "2:12:27", "throughput": 686.77, "total_tokens": 5746592} {"current_steps": 20520, "total_steps": 40000, "loss": 0.0, "lr": 2.3981228061800544e-05, "epoch": 228.0, "percentage": 51.3, "elapsed_time": "2:19:29", "remaining_time": "2:12:25", "throughput": 686.77, "total_tokens": 5748000} {"current_steps": 20525, "total_steps": 40000, "loss": 0.0, "lr": 2.3971418818569115e-05, "epoch": 228.05555555555554, "percentage": 51.31, "elapsed_time": "2:19:31", "remaining_time": "2:12:23", "throughput": 686.76, "total_tokens": 5749424} {"current_steps": 20530, "total_steps": 40000, "loss": 0.0, "lr": 2.3961609733957832e-05, "epoch": 228.11111111111111, "percentage": 51.32, "elapsed_time": "2:19:33", "remaining_time": "2:12:21", "throughput": 686.77, "total_tokens": 5750864} {"current_steps": 20535, "total_steps": 40000, "loss": 0.0, "lr": 2.395180080947939e-05, "epoch": 228.16666666666666, "percentage": 51.34, "elapsed_time": "2:19:35", "remaining_time": "2:12:19", "throughput": 686.78, "total_tokens": 5752288} {"current_steps": 20540, "total_steps": 40000, "loss": 0.0, "lr": 2.394199204664642e-05, "epoch": 228.22222222222223, "percentage": 51.35, "elapsed_time": "2:19:37", "remaining_time": "2:12:17", "throughput": 686.79, "total_tokens": 5753680} {"current_steps": 20545, "total_steps": 40000, "loss": 0.0, "lr": 2.3932183446971583e-05, "epoch": 228.27777777777777, "percentage": 51.36, "elapsed_time": "2:19:39", "remaining_time": "2:12:15", "throughput": 686.8, "total_tokens": 5755072} {"current_steps": 20550, "total_steps": 40000, "loss": 0.0, "lr": 2.3922375011967473e-05, "epoch": 228.33333333333334, "percentage": 51.38, "elapsed_time": "2:19:41", "remaining_time": "2:12:12", "throughput": 686.8, "total_tokens": 5756464} {"current_steps": 20555, "total_steps": 40000, "loss": 0.0, "lr": 2.3912566743146676e-05, "epoch": 228.38888888888889, "percentage": 51.39, "elapsed_time": "2:19:43", "remaining_time": "2:12:10", "throughput": 686.81, "total_tokens": 5757856} {"current_steps": 20560, "total_steps": 40000, "loss": 0.0, "lr": 2.390275864202176e-05, "epoch": 228.44444444444446, "percentage": 51.4, "elapsed_time": "2:19:45", "remaining_time": "2:12:08", "throughput": 686.82, "total_tokens": 5759264} {"current_steps": 20565, "total_steps": 40000, "loss": 0.0, "lr": 2.3892950710105243e-05, "epoch": 228.5, "percentage": 51.41, "elapsed_time": "2:19:47", "remaining_time": "2:12:06", "throughput": 686.83, "total_tokens": 5760640} {"current_steps": 20570, "total_steps": 40000, "loss": 0.0, "lr": 2.3883142948909635e-05, "epoch": 228.55555555555554, "percentage": 51.42, "elapsed_time": "2:19:49", "remaining_time": "2:12:04", "throughput": 686.83, "total_tokens": 5761984} {"current_steps": 20575, "total_steps": 40000, "loss": 0.0, "lr": 2.3873335359947433e-05, "epoch": 228.61111111111111, "percentage": 51.44, "elapsed_time": "2:19:51", "remaining_time": "2:12:02", "throughput": 686.84, "total_tokens": 5763408} {"current_steps": 20580, "total_steps": 40000, "loss": 0.0, "lr": 2.3863527944731066e-05, "epoch": 228.66666666666666, "percentage": 51.45, "elapsed_time": "2:19:53", "remaining_time": "2:12:00", "throughput": 686.85, "total_tokens": 5764816} {"current_steps": 20585, "total_steps": 40000, "loss": 0.0, "lr": 2.385372070477298e-05, "epoch": 228.72222222222223, "percentage": 51.46, "elapsed_time": "2:19:55", "remaining_time": "2:11:57", "throughput": 686.86, "total_tokens": 5766240} {"current_steps": 20590, "total_steps": 40000, "loss": 0.0, "lr": 2.384391364158556e-05, "epoch": 228.77777777777777, "percentage": 51.48, "elapsed_time": "2:19:57", "remaining_time": "2:11:55", "throughput": 686.86, "total_tokens": 5767600} {"current_steps": 20595, "total_steps": 40000, "loss": 0.0, "lr": 2.3834106756681185e-05, "epoch": 228.83333333333334, "percentage": 51.49, "elapsed_time": "2:19:58", "remaining_time": "2:11:53", "throughput": 686.87, "total_tokens": 5768992} {"current_steps": 20600, "total_steps": 40000, "loss": 0.0, "lr": 2.3824300051572206e-05, "epoch": 228.88888888888889, "percentage": 51.5, "elapsed_time": "2:20:00", "remaining_time": "2:11:51", "throughput": 686.88, "total_tokens": 5770416} {"current_steps": 20600, "total_steps": 40000, "eval_loss": 0.3507901728153229, "epoch": 228.88888888888889, "percentage": 51.5, "elapsed_time": "2:20:02", "remaining_time": "2:11:52", "throughput": 686.78, "total_tokens": 5770416} {"current_steps": 20605, "total_steps": 40000, "loss": 0.0, "lr": 2.3814493527770923e-05, "epoch": 228.94444444444446, "percentage": 51.51, "elapsed_time": "2:20:05", "remaining_time": "2:11:51", "throughput": 686.69, "total_tokens": 5771888} {"current_steps": 20610, "total_steps": 40000, "loss": 0.0, "lr": 2.3804687186789637e-05, "epoch": 229.0, "percentage": 51.52, "elapsed_time": "2:20:07", "remaining_time": "2:11:49", "throughput": 686.68, "total_tokens": 5773312} {"current_steps": 20615, "total_steps": 40000, "loss": 0.0, "lr": 2.379488103014062e-05, "epoch": 229.05555555555554, "percentage": 51.54, "elapsed_time": "2:20:09", "remaining_time": "2:11:47", "throughput": 686.67, "total_tokens": 5774688} {"current_steps": 20620, "total_steps": 40000, "loss": 0.0, "lr": 2.3785075059336086e-05, "epoch": 229.11111111111111, "percentage": 51.55, "elapsed_time": "2:20:11", "remaining_time": "2:11:45", "throughput": 686.68, "total_tokens": 5776096} {"current_steps": 20625, "total_steps": 40000, "loss": 0.0, "lr": 2.3775269275888248e-05, "epoch": 229.16666666666666, "percentage": 51.56, "elapsed_time": "2:20:13", "remaining_time": "2:11:43", "throughput": 686.69, "total_tokens": 5777536} {"current_steps": 20630, "total_steps": 40000, "loss": 0.0, "lr": 2.3765463681309274e-05, "epoch": 229.22222222222223, "percentage": 51.58, "elapsed_time": "2:20:15", "remaining_time": "2:11:41", "throughput": 686.69, "total_tokens": 5778912} {"current_steps": 20635, "total_steps": 40000, "loss": 0.0, "lr": 2.3755658277111313e-05, "epoch": 229.27777777777777, "percentage": 51.59, "elapsed_time": "2:20:17", "remaining_time": "2:11:39", "throughput": 686.7, "total_tokens": 5780320} {"current_steps": 20640, "total_steps": 40000, "loss": 0.0, "lr": 2.374585306480649e-05, "epoch": 229.33333333333334, "percentage": 51.6, "elapsed_time": "2:20:19", "remaining_time": "2:11:37", "throughput": 686.71, "total_tokens": 5781680} {"current_steps": 20645, "total_steps": 40000, "loss": 0.0, "lr": 2.3736048045906877e-05, "epoch": 229.38888888888889, "percentage": 51.61, "elapsed_time": "2:20:21", "remaining_time": "2:11:35", "throughput": 686.71, "total_tokens": 5783056} {"current_steps": 20650, "total_steps": 40000, "loss": 0.0, "lr": 2.372624322192454e-05, "epoch": 229.44444444444446, "percentage": 51.62, "elapsed_time": "2:20:23", "remaining_time": "2:11:33", "throughput": 686.72, "total_tokens": 5784448} {"current_steps": 20655, "total_steps": 40000, "loss": 0.0, "lr": 2.3716438594371516e-05, "epoch": 229.5, "percentage": 51.64, "elapsed_time": "2:20:25", "remaining_time": "2:11:30", "throughput": 686.73, "total_tokens": 5785872} {"current_steps": 20660, "total_steps": 40000, "loss": 0.0, "lr": 2.3706634164759784e-05, "epoch": 229.55555555555554, "percentage": 51.65, "elapsed_time": "2:20:27", "remaining_time": "2:11:28", "throughput": 686.74, "total_tokens": 5787264} {"current_steps": 20665, "total_steps": 40000, "loss": 0.0, "lr": 2.3696829934601323e-05, "epoch": 229.61111111111111, "percentage": 51.66, "elapsed_time": "2:20:29", "remaining_time": "2:11:26", "throughput": 686.74, "total_tokens": 5788640} {"current_steps": 20670, "total_steps": 40000, "loss": 0.0, "lr": 2.3687025905408053e-05, "epoch": 229.66666666666666, "percentage": 51.68, "elapsed_time": "2:20:31", "remaining_time": "2:11:24", "throughput": 686.75, "total_tokens": 5790064} {"current_steps": 20675, "total_steps": 40000, "loss": 0.0, "lr": 2.3677222078691886e-05, "epoch": 229.72222222222223, "percentage": 51.69, "elapsed_time": "2:20:32", "remaining_time": "2:11:22", "throughput": 686.76, "total_tokens": 5791456} {"current_steps": 20680, "total_steps": 40000, "loss": 0.0, "lr": 2.366741845596471e-05, "epoch": 229.77777777777777, "percentage": 51.7, "elapsed_time": "2:20:34", "remaining_time": "2:11:20", "throughput": 686.77, "total_tokens": 5792816} {"current_steps": 20685, "total_steps": 40000, "loss": 0.0, "lr": 2.3657615038738343e-05, "epoch": 229.83333333333334, "percentage": 51.71, "elapsed_time": "2:20:36", "remaining_time": "2:11:18", "throughput": 686.77, "total_tokens": 5794192} {"current_steps": 20690, "total_steps": 40000, "loss": 0.0, "lr": 2.3647811828524614e-05, "epoch": 229.88888888888889, "percentage": 51.73, "elapsed_time": "2:20:38", "remaining_time": "2:11:15", "throughput": 686.79, "total_tokens": 5795648} {"current_steps": 20695, "total_steps": 40000, "loss": 0.0, "lr": 2.363800882683529e-05, "epoch": 229.94444444444446, "percentage": 51.74, "elapsed_time": "2:20:40", "remaining_time": "2:11:13", "throughput": 686.8, "total_tokens": 5797056} {"current_steps": 20700, "total_steps": 40000, "loss": 0.0, "lr": 2.3628206035182125e-05, "epoch": 230.0, "percentage": 51.75, "elapsed_time": "2:20:42", "remaining_time": "2:11:11", "throughput": 686.79, "total_tokens": 5798464} {"current_steps": 20705, "total_steps": 40000, "loss": 0.0, "lr": 2.361840345507683e-05, "epoch": 230.05555555555554, "percentage": 51.76, "elapsed_time": "2:20:45", "remaining_time": "2:11:09", "throughput": 686.78, "total_tokens": 5799856} {"current_steps": 20710, "total_steps": 40000, "loss": 0.0, "lr": 2.3608601088031073e-05, "epoch": 230.11111111111111, "percentage": 51.78, "elapsed_time": "2:20:46", "remaining_time": "2:11:07", "throughput": 686.78, "total_tokens": 5801232} {"current_steps": 20715, "total_steps": 40000, "loss": 0.0, "lr": 2.3598798935556516e-05, "epoch": 230.16666666666666, "percentage": 51.79, "elapsed_time": "2:20:48", "remaining_time": "2:11:05", "throughput": 686.79, "total_tokens": 5802608} {"current_steps": 20720, "total_steps": 40000, "loss": 0.0, "lr": 2.3588996999164784e-05, "epoch": 230.22222222222223, "percentage": 51.8, "elapsed_time": "2:20:50", "remaining_time": "2:11:03", "throughput": 686.79, "total_tokens": 5803984} {"current_steps": 20725, "total_steps": 40000, "loss": 0.0, "lr": 2.3579195280367434e-05, "epoch": 230.27777777777777, "percentage": 51.81, "elapsed_time": "2:20:52", "remaining_time": "2:11:01", "throughput": 686.79, "total_tokens": 5805312} {"current_steps": 20730, "total_steps": 40000, "loss": 0.0, "lr": 2.356939378067603e-05, "epoch": 230.33333333333334, "percentage": 51.82, "elapsed_time": "2:20:54", "remaining_time": "2:10:59", "throughput": 686.8, "total_tokens": 5806672} {"current_steps": 20735, "total_steps": 40000, "loss": 0.0, "lr": 2.3559592501602092e-05, "epoch": 230.38888888888889, "percentage": 51.84, "elapsed_time": "2:20:56", "remaining_time": "2:10:57", "throughput": 686.81, "total_tokens": 5808080} {"current_steps": 20740, "total_steps": 40000, "loss": 0.0, "lr": 2.3549791444657076e-05, "epoch": 230.44444444444446, "percentage": 51.85, "elapsed_time": "2:20:58", "remaining_time": "2:10:54", "throughput": 686.82, "total_tokens": 5809504} {"current_steps": 20745, "total_steps": 40000, "loss": 0.0, "lr": 2.353999061135246e-05, "epoch": 230.5, "percentage": 51.86, "elapsed_time": "2:21:00", "remaining_time": "2:10:52", "throughput": 686.83, "total_tokens": 5810896} {"current_steps": 20750, "total_steps": 40000, "loss": 0.0, "lr": 2.3530190003199626e-05, "epoch": 230.55555555555554, "percentage": 51.88, "elapsed_time": "2:21:02", "remaining_time": "2:10:50", "throughput": 686.83, "total_tokens": 5812272} {"current_steps": 20755, "total_steps": 40000, "loss": 0.0, "lr": 2.3520389621709965e-05, "epoch": 230.61111111111111, "percentage": 51.89, "elapsed_time": "2:21:04", "remaining_time": "2:10:48", "throughput": 686.84, "total_tokens": 5813664} {"current_steps": 20760, "total_steps": 40000, "loss": 0.0, "lr": 2.351058946839483e-05, "epoch": 230.66666666666666, "percentage": 51.9, "elapsed_time": "2:21:06", "remaining_time": "2:10:46", "throughput": 686.85, "total_tokens": 5815072} {"current_steps": 20765, "total_steps": 40000, "loss": 0.0, "lr": 2.350078954476551e-05, "epoch": 230.72222222222223, "percentage": 51.91, "elapsed_time": "2:21:08", "remaining_time": "2:10:44", "throughput": 686.86, "total_tokens": 5816464} {"current_steps": 20770, "total_steps": 40000, "loss": 0.0, "lr": 2.3490989852333272e-05, "epoch": 230.77777777777777, "percentage": 51.92, "elapsed_time": "2:21:10", "remaining_time": "2:10:42", "throughput": 686.87, "total_tokens": 5817888} {"current_steps": 20775, "total_steps": 40000, "loss": 0.0, "lr": 2.3481190392609377e-05, "epoch": 230.83333333333334, "percentage": 51.94, "elapsed_time": "2:21:12", "remaining_time": "2:10:40", "throughput": 686.88, "total_tokens": 5819344} {"current_steps": 20780, "total_steps": 40000, "loss": 0.0, "lr": 2.3471391167105e-05, "epoch": 230.88888888888889, "percentage": 51.95, "elapsed_time": "2:21:14", "remaining_time": "2:10:37", "throughput": 686.89, "total_tokens": 5820784} {"current_steps": 20785, "total_steps": 40000, "loss": 0.0, "lr": 2.3461592177331325e-05, "epoch": 230.94444444444446, "percentage": 51.96, "elapsed_time": "2:21:16", "remaining_time": "2:10:35", "throughput": 686.9, "total_tokens": 5822192} {"current_steps": 20790, "total_steps": 40000, "loss": 0.0, "lr": 2.345179342479946e-05, "epoch": 231.0, "percentage": 51.98, "elapsed_time": "2:21:18", "remaining_time": "2:10:33", "throughput": 686.9, "total_tokens": 5823648} {"current_steps": 20795, "total_steps": 40000, "loss": 0.0, "lr": 2.3441994911020503e-05, "epoch": 231.05555555555554, "percentage": 51.99, "elapsed_time": "2:21:20", "remaining_time": "2:10:31", "throughput": 686.9, "total_tokens": 5825072} {"current_steps": 20800, "total_steps": 40000, "loss": 0.0, "lr": 2.3432196637505522e-05, "epoch": 231.11111111111111, "percentage": 52.0, "elapsed_time": "2:21:22", "remaining_time": "2:10:29", "throughput": 686.91, "total_tokens": 5826496} {"current_steps": 20800, "total_steps": 40000, "eval_loss": 0.37461018562316895, "epoch": 231.11111111111111, "percentage": 52.0, "elapsed_time": "2:21:23", "remaining_time": "2:10:30", "throughput": 686.8, "total_tokens": 5826496} {"current_steps": 20805, "total_steps": 40000, "loss": 0.0, "lr": 2.3422398605765515e-05, "epoch": 231.16666666666666, "percentage": 52.01, "elapsed_time": "2:21:26", "remaining_time": "2:10:29", "throughput": 686.7, "total_tokens": 5827840} {"current_steps": 20810, "total_steps": 40000, "loss": 0.0, "lr": 2.3412600817311462e-05, "epoch": 231.22222222222223, "percentage": 52.02, "elapsed_time": "2:21:28", "remaining_time": "2:10:27", "throughput": 686.7, "total_tokens": 5829232} {"current_steps": 20815, "total_steps": 40000, "loss": 0.0, "lr": 2.3402803273654326e-05, "epoch": 231.27777777777777, "percentage": 52.04, "elapsed_time": "2:21:30", "remaining_time": "2:10:25", "throughput": 686.71, "total_tokens": 5830656} {"current_steps": 20820, "total_steps": 40000, "loss": 0.0, "lr": 2.3393005976304983e-05, "epoch": 231.33333333333334, "percentage": 52.05, "elapsed_time": "2:21:32", "remaining_time": "2:10:23", "throughput": 686.72, "total_tokens": 5832016} {"current_steps": 20825, "total_steps": 40000, "loss": 0.0, "lr": 2.338320892677432e-05, "epoch": 231.38888888888889, "percentage": 52.06, "elapsed_time": "2:21:34", "remaining_time": "2:10:21", "throughput": 686.7, "total_tokens": 5833424} {"current_steps": 20830, "total_steps": 40000, "loss": 0.0, "lr": 2.3373412126573155e-05, "epoch": 231.44444444444446, "percentage": 52.08, "elapsed_time": "2:21:36", "remaining_time": "2:10:19", "throughput": 686.72, "total_tokens": 5834864} {"current_steps": 20835, "total_steps": 40000, "loss": 0.0, "lr": 2.3363615577212285e-05, "epoch": 231.5, "percentage": 52.09, "elapsed_time": "2:21:38", "remaining_time": "2:10:17", "throughput": 686.72, "total_tokens": 5836224} {"current_steps": 20840, "total_steps": 40000, "loss": 0.0, "lr": 2.3353819280202455e-05, "epoch": 231.55555555555554, "percentage": 52.1, "elapsed_time": "2:21:40", "remaining_time": "2:10:15", "throughput": 686.73, "total_tokens": 5837632} {"current_steps": 20845, "total_steps": 40000, "loss": 0.0, "lr": 2.334402323705438e-05, "epoch": 231.61111111111111, "percentage": 52.11, "elapsed_time": "2:21:42", "remaining_time": "2:10:13", "throughput": 686.74, "total_tokens": 5839040} {"current_steps": 20850, "total_steps": 40000, "loss": 0.0, "lr": 2.3334227449278725e-05, "epoch": 231.66666666666666, "percentage": 52.12, "elapsed_time": "2:21:44", "remaining_time": "2:10:11", "throughput": 686.75, "total_tokens": 5840464} {"current_steps": 20855, "total_steps": 40000, "loss": 0.0, "lr": 2.3324431918386143e-05, "epoch": 231.72222222222223, "percentage": 52.14, "elapsed_time": "2:21:46", "remaining_time": "2:10:08", "throughput": 686.76, "total_tokens": 5841856} {"current_steps": 20860, "total_steps": 40000, "loss": 0.0, "lr": 2.3314636645887207e-05, "epoch": 231.77777777777777, "percentage": 52.15, "elapsed_time": "2:21:48", "remaining_time": "2:10:06", "throughput": 686.77, "total_tokens": 5843232} {"current_steps": 20865, "total_steps": 40000, "loss": 0.0, "lr": 2.3304841633292487e-05, "epoch": 231.83333333333334, "percentage": 52.16, "elapsed_time": "2:21:50", "remaining_time": "2:10:04", "throughput": 686.78, "total_tokens": 5844640} {"current_steps": 20870, "total_steps": 40000, "loss": 0.0, "lr": 2.329504688211248e-05, "epoch": 231.88888888888889, "percentage": 52.18, "elapsed_time": "2:21:52", "remaining_time": "2:10:02", "throughput": 686.78, "total_tokens": 5846016} {"current_steps": 20875, "total_steps": 40000, "loss": 0.0, "lr": 2.3285252393857677e-05, "epoch": 231.94444444444446, "percentage": 52.19, "elapsed_time": "2:21:54", "remaining_time": "2:10:00", "throughput": 686.79, "total_tokens": 5847440} {"current_steps": 20880, "total_steps": 40000, "loss": 0.0, "lr": 2.327545817003851e-05, "epoch": 232.0, "percentage": 52.2, "elapsed_time": "2:21:56", "remaining_time": "2:09:58", "throughput": 686.78, "total_tokens": 5848816} {"current_steps": 20885, "total_steps": 40000, "loss": 0.0, "lr": 2.326566421216535e-05, "epoch": 232.05555555555554, "percentage": 52.21, "elapsed_time": "2:21:58", "remaining_time": "2:09:56", "throughput": 686.77, "total_tokens": 5850240} {"current_steps": 20890, "total_steps": 40000, "loss": 0.0, "lr": 2.3255870521748565e-05, "epoch": 232.11111111111111, "percentage": 52.23, "elapsed_time": "2:22:00", "remaining_time": "2:09:54", "throughput": 686.78, "total_tokens": 5851632} {"current_steps": 20895, "total_steps": 40000, "loss": 0.0, "lr": 2.3246077100298474e-05, "epoch": 232.16666666666666, "percentage": 52.24, "elapsed_time": "2:22:02", "remaining_time": "2:09:52", "throughput": 686.79, "total_tokens": 5853008} {"current_steps": 20900, "total_steps": 40000, "loss": 0.0, "lr": 2.3236283949325328e-05, "epoch": 232.22222222222223, "percentage": 52.25, "elapsed_time": "2:22:04", "remaining_time": "2:09:50", "throughput": 686.8, "total_tokens": 5854400} {"current_steps": 20905, "total_steps": 40000, "loss": 0.0, "lr": 2.3226491070339368e-05, "epoch": 232.27777777777777, "percentage": 52.26, "elapsed_time": "2:22:06", "remaining_time": "2:09:47", "throughput": 686.8, "total_tokens": 5855792} {"current_steps": 20910, "total_steps": 40000, "loss": 0.0, "lr": 2.3216698464850762e-05, "epoch": 232.33333333333334, "percentage": 52.28, "elapsed_time": "2:22:08", "remaining_time": "2:09:45", "throughput": 686.81, "total_tokens": 5857200} {"current_steps": 20915, "total_steps": 40000, "loss": 0.0, "lr": 2.320690613436967e-05, "epoch": 232.38888888888889, "percentage": 52.29, "elapsed_time": "2:22:10", "remaining_time": "2:09:43", "throughput": 686.82, "total_tokens": 5858608} {"current_steps": 20920, "total_steps": 40000, "loss": 0.0, "lr": 2.3197114080406192e-05, "epoch": 232.44444444444446, "percentage": 52.3, "elapsed_time": "2:22:11", "remaining_time": "2:09:41", "throughput": 686.83, "total_tokens": 5860016} {"current_steps": 20925, "total_steps": 40000, "loss": 0.0, "lr": 2.3187322304470365e-05, "epoch": 232.5, "percentage": 52.31, "elapsed_time": "2:22:13", "remaining_time": "2:09:39", "throughput": 686.84, "total_tokens": 5861392} {"current_steps": 20930, "total_steps": 40000, "loss": 0.0, "lr": 2.3177530808072222e-05, "epoch": 232.55555555555554, "percentage": 52.33, "elapsed_time": "2:22:15", "remaining_time": "2:09:37", "throughput": 686.85, "total_tokens": 5862832} {"current_steps": 20935, "total_steps": 40000, "loss": 0.0, "lr": 2.316773959272174e-05, "epoch": 232.61111111111111, "percentage": 52.34, "elapsed_time": "2:22:17", "remaining_time": "2:09:35", "throughput": 686.85, "total_tokens": 5864192} {"current_steps": 20940, "total_steps": 40000, "loss": 0.0, "lr": 2.3157948659928823e-05, "epoch": 232.66666666666666, "percentage": 52.35, "elapsed_time": "2:22:19", "remaining_time": "2:09:33", "throughput": 686.86, "total_tokens": 5865616} {"current_steps": 20945, "total_steps": 40000, "loss": 0.0, "lr": 2.3148158011203388e-05, "epoch": 232.72222222222223, "percentage": 52.36, "elapsed_time": "2:22:21", "remaining_time": "2:09:30", "throughput": 686.87, "total_tokens": 5867008} {"current_steps": 20950, "total_steps": 40000, "loss": 0.0, "lr": 2.3138367648055253e-05, "epoch": 232.77777777777777, "percentage": 52.38, "elapsed_time": "2:22:23", "remaining_time": "2:09:28", "throughput": 686.89, "total_tokens": 5868464} {"current_steps": 20955, "total_steps": 40000, "loss": 0.0, "lr": 2.312857757199422e-05, "epoch": 232.83333333333334, "percentage": 52.39, "elapsed_time": "2:22:25", "remaining_time": "2:09:26", "throughput": 686.89, "total_tokens": 5869856} {"current_steps": 20960, "total_steps": 40000, "loss": 0.0, "lr": 2.3118787784530048e-05, "epoch": 232.88888888888889, "percentage": 52.4, "elapsed_time": "2:22:27", "remaining_time": "2:09:24", "throughput": 686.91, "total_tokens": 5871280} {"current_steps": 20965, "total_steps": 40000, "loss": 0.0, "lr": 2.310899828717243e-05, "epoch": 232.94444444444446, "percentage": 52.41, "elapsed_time": "2:22:29", "remaining_time": "2:09:22", "throughput": 686.92, "total_tokens": 5872688} {"current_steps": 20970, "total_steps": 40000, "loss": 0.0, "lr": 2.309920908143104e-05, "epoch": 233.0, "percentage": 52.42, "elapsed_time": "2:22:31", "remaining_time": "2:09:20", "throughput": 686.91, "total_tokens": 5874080} {"current_steps": 20975, "total_steps": 40000, "loss": 0.0, "lr": 2.308942016881551e-05, "epoch": 233.05555555555554, "percentage": 52.44, "elapsed_time": "2:22:33", "remaining_time": "2:09:18", "throughput": 686.9, "total_tokens": 5875488} {"current_steps": 20980, "total_steps": 40000, "loss": 0.0, "lr": 2.307963155083539e-05, "epoch": 233.11111111111111, "percentage": 52.45, "elapsed_time": "2:22:35", "remaining_time": "2:09:16", "throughput": 686.9, "total_tokens": 5876848} {"current_steps": 20985, "total_steps": 40000, "loss": 0.0, "lr": 2.306984322900022e-05, "epoch": 233.16666666666666, "percentage": 52.46, "elapsed_time": "2:22:37", "remaining_time": "2:09:14", "throughput": 686.91, "total_tokens": 5878256} {"current_steps": 20990, "total_steps": 40000, "loss": 0.0, "lr": 2.3060055204819482e-05, "epoch": 233.22222222222223, "percentage": 52.48, "elapsed_time": "2:22:39", "remaining_time": "2:09:12", "throughput": 686.91, "total_tokens": 5879616} {"current_steps": 20995, "total_steps": 40000, "loss": 0.0, "lr": 2.3050267479802604e-05, "epoch": 233.27777777777777, "percentage": 52.49, "elapsed_time": "2:22:41", "remaining_time": "2:09:09", "throughput": 686.93, "total_tokens": 5881056} {"current_steps": 21000, "total_steps": 40000, "loss": 0.0, "lr": 2.304048005545899e-05, "epoch": 233.33333333333334, "percentage": 52.5, "elapsed_time": "2:22:43", "remaining_time": "2:09:07", "throughput": 686.94, "total_tokens": 5882496} {"current_steps": 21000, "total_steps": 40000, "eval_loss": 0.35755854845046997, "epoch": 233.33333333333334, "percentage": 52.5, "elapsed_time": "2:22:44", "remaining_time": "2:09:08", "throughput": 686.84, "total_tokens": 5882496} {"current_steps": 21005, "total_steps": 40000, "loss": 0.0, "lr": 2.3030692933297972e-05, "epoch": 233.38888888888889, "percentage": 52.51, "elapsed_time": "2:22:47", "remaining_time": "2:09:07", "throughput": 686.74, "total_tokens": 5883920} {"current_steps": 21010, "total_steps": 40000, "loss": 0.0, "lr": 2.3020906114828843e-05, "epoch": 233.44444444444446, "percentage": 52.52, "elapsed_time": "2:22:49", "remaining_time": "2:09:05", "throughput": 686.74, "total_tokens": 5885280} {"current_steps": 21015, "total_steps": 40000, "loss": 0.0, "lr": 2.301111960156088e-05, "epoch": 233.5, "percentage": 52.54, "elapsed_time": "2:22:51", "remaining_time": "2:09:03", "throughput": 686.75, "total_tokens": 5886672} {"current_steps": 21020, "total_steps": 40000, "loss": 0.0, "lr": 2.300133339500326e-05, "epoch": 233.55555555555554, "percentage": 52.55, "elapsed_time": "2:22:53", "remaining_time": "2:09:01", "throughput": 686.76, "total_tokens": 5888096} {"current_steps": 21025, "total_steps": 40000, "loss": 0.0, "lr": 2.2991547496665148e-05, "epoch": 233.61111111111111, "percentage": 52.56, "elapsed_time": "2:22:55", "remaining_time": "2:08:59", "throughput": 686.77, "total_tokens": 5889488} {"current_steps": 21030, "total_steps": 40000, "loss": 0.0, "lr": 2.298176190805565e-05, "epoch": 233.66666666666666, "percentage": 52.58, "elapsed_time": "2:22:57", "remaining_time": "2:08:57", "throughput": 686.78, "total_tokens": 5890880} {"current_steps": 21035, "total_steps": 40000, "loss": 0.0, "lr": 2.2971976630683826e-05, "epoch": 233.72222222222223, "percentage": 52.59, "elapsed_time": "2:22:59", "remaining_time": "2:08:55", "throughput": 686.79, "total_tokens": 5892288} {"current_steps": 21040, "total_steps": 40000, "loss": 0.0, "lr": 2.29621916660587e-05, "epoch": 233.77777777777777, "percentage": 52.6, "elapsed_time": "2:23:01", "remaining_time": "2:08:53", "throughput": 686.8, "total_tokens": 5893728} {"current_steps": 21045, "total_steps": 40000, "loss": 0.0, "lr": 2.295240701568922e-05, "epoch": 233.83333333333334, "percentage": 52.61, "elapsed_time": "2:23:03", "remaining_time": "2:08:50", "throughput": 686.8, "total_tokens": 5895088} {"current_steps": 21050, "total_steps": 40000, "loss": 0.0, "lr": 2.2942622681084312e-05, "epoch": 233.88888888888889, "percentage": 52.62, "elapsed_time": "2:23:05", "remaining_time": "2:08:48", "throughput": 686.81, "total_tokens": 5896496} {"current_steps": 21055, "total_steps": 40000, "loss": 0.0, "lr": 2.293283866375284e-05, "epoch": 233.94444444444446, "percentage": 52.64, "elapsed_time": "2:23:07", "remaining_time": "2:08:46", "throughput": 686.82, "total_tokens": 5897904} {"current_steps": 21060, "total_steps": 40000, "loss": 0.0, "lr": 2.2923054965203627e-05, "epoch": 234.0, "percentage": 52.65, "elapsed_time": "2:23:09", "remaining_time": "2:08:44", "throughput": 686.82, "total_tokens": 5899296} {"current_steps": 21065, "total_steps": 40000, "loss": 0.0, "lr": 2.2913271586945443e-05, "epoch": 234.05555555555554, "percentage": 52.66, "elapsed_time": "2:23:11", "remaining_time": "2:08:42", "throughput": 686.8, "total_tokens": 5900672} {"current_steps": 21070, "total_steps": 40000, "loss": 0.0, "lr": 2.290348853048699e-05, "epoch": 234.11111111111111, "percentage": 52.68, "elapsed_time": "2:23:13", "remaining_time": "2:08:40", "throughput": 686.81, "total_tokens": 5902064} {"current_steps": 21075, "total_steps": 40000, "loss": 0.0, "lr": 2.2893705797336956e-05, "epoch": 234.16666666666666, "percentage": 52.69, "elapsed_time": "2:23:15", "remaining_time": "2:08:38", "throughput": 686.82, "total_tokens": 5903456} {"current_steps": 21080, "total_steps": 40000, "loss": 0.0, "lr": 2.288392338900397e-05, "epoch": 234.22222222222223, "percentage": 52.7, "elapsed_time": "2:23:17", "remaining_time": "2:08:36", "throughput": 686.82, "total_tokens": 5904816} {"current_steps": 21085, "total_steps": 40000, "loss": 0.0, "lr": 2.2874141306996576e-05, "epoch": 234.27777777777777, "percentage": 52.71, "elapsed_time": "2:23:19", "remaining_time": "2:08:34", "throughput": 686.82, "total_tokens": 5906176} {"current_steps": 21090, "total_steps": 40000, "loss": 0.0, "lr": 2.2864359552823312e-05, "epoch": 234.33333333333334, "percentage": 52.73, "elapsed_time": "2:23:21", "remaining_time": "2:08:32", "throughput": 686.83, "total_tokens": 5907600} {"current_steps": 21095, "total_steps": 40000, "loss": 0.0, "lr": 2.2854578127992648e-05, "epoch": 234.38888888888889, "percentage": 52.74, "elapsed_time": "2:23:23", "remaining_time": "2:08:29", "throughput": 686.84, "total_tokens": 5908976} {"current_steps": 21100, "total_steps": 40000, "loss": 0.0, "lr": 2.2844797034012988e-05, "epoch": 234.44444444444446, "percentage": 52.75, "elapsed_time": "2:23:25", "remaining_time": "2:08:27", "throughput": 686.85, "total_tokens": 5910400} {"current_steps": 21105, "total_steps": 40000, "loss": 0.0, "lr": 2.2835016272392722e-05, "epoch": 234.5, "percentage": 52.76, "elapsed_time": "2:23:26", "remaining_time": "2:08:25", "throughput": 686.86, "total_tokens": 5911776} {"current_steps": 21110, "total_steps": 40000, "loss": 0.0, "lr": 2.2825235844640142e-05, "epoch": 234.55555555555554, "percentage": 52.78, "elapsed_time": "2:23:28", "remaining_time": "2:08:23", "throughput": 686.87, "total_tokens": 5913184} {"current_steps": 21115, "total_steps": 40000, "loss": 0.0, "lr": 2.2815455752263522e-05, "epoch": 234.61111111111111, "percentage": 52.79, "elapsed_time": "2:23:30", "remaining_time": "2:08:21", "throughput": 686.87, "total_tokens": 5914512} {"current_steps": 21120, "total_steps": 40000, "loss": 0.0, "lr": 2.2805675996771092e-05, "epoch": 234.66666666666666, "percentage": 52.8, "elapsed_time": "2:23:32", "remaining_time": "2:08:19", "throughput": 686.88, "total_tokens": 5915920} {"current_steps": 21125, "total_steps": 40000, "loss": 0.0, "lr": 2.2795896579670987e-05, "epoch": 234.72222222222223, "percentage": 52.81, "elapsed_time": "2:23:34", "remaining_time": "2:08:17", "throughput": 686.88, "total_tokens": 5917312} {"current_steps": 21130, "total_steps": 40000, "loss": 0.0, "lr": 2.2786117502471337e-05, "epoch": 234.77777777777777, "percentage": 52.83, "elapsed_time": "2:23:36", "remaining_time": "2:08:15", "throughput": 686.89, "total_tokens": 5918720} {"current_steps": 21135, "total_steps": 40000, "loss": 0.0, "lr": 2.2776338766680185e-05, "epoch": 234.83333333333334, "percentage": 52.84, "elapsed_time": "2:23:38", "remaining_time": "2:08:12", "throughput": 686.9, "total_tokens": 5920096} {"current_steps": 21140, "total_steps": 40000, "loss": 0.0, "lr": 2.2766560373805533e-05, "epoch": 234.88888888888889, "percentage": 52.85, "elapsed_time": "2:23:40", "remaining_time": "2:08:10", "throughput": 686.91, "total_tokens": 5921552} {"current_steps": 21145, "total_steps": 40000, "loss": 0.0, "lr": 2.2756782325355353e-05, "epoch": 234.94444444444446, "percentage": 52.86, "elapsed_time": "2:23:42", "remaining_time": "2:08:08", "throughput": 686.93, "total_tokens": 5923024} {"current_steps": 21150, "total_steps": 40000, "loss": 0.0, "lr": 2.2747004622837514e-05, "epoch": 235.0, "percentage": 52.88, "elapsed_time": "2:23:44", "remaining_time": "2:08:06", "throughput": 686.93, "total_tokens": 5924416} {"current_steps": 21155, "total_steps": 40000, "loss": 0.0, "lr": 2.2737227267759878e-05, "epoch": 235.05555555555554, "percentage": 52.89, "elapsed_time": "2:23:46", "remaining_time": "2:08:04", "throughput": 686.91, "total_tokens": 5925824} {"current_steps": 21160, "total_steps": 40000, "loss": 0.0, "lr": 2.272745026163024e-05, "epoch": 235.11111111111111, "percentage": 52.9, "elapsed_time": "2:23:48", "remaining_time": "2:08:02", "throughput": 686.92, "total_tokens": 5927232} {"current_steps": 21165, "total_steps": 40000, "loss": 0.0, "lr": 2.271767360595633e-05, "epoch": 235.16666666666666, "percentage": 52.91, "elapsed_time": "2:23:50", "remaining_time": "2:08:00", "throughput": 686.93, "total_tokens": 5928624} {"current_steps": 21170, "total_steps": 40000, "loss": 0.0, "lr": 2.270789730224583e-05, "epoch": 235.22222222222223, "percentage": 52.92, "elapsed_time": "2:23:52", "remaining_time": "2:07:58", "throughput": 686.94, "total_tokens": 5930048} {"current_steps": 21175, "total_steps": 40000, "loss": 0.0, "lr": 2.2698121352006367e-05, "epoch": 235.27777777777777, "percentage": 52.94, "elapsed_time": "2:23:54", "remaining_time": "2:07:56", "throughput": 686.95, "total_tokens": 5931472} {"current_steps": 21180, "total_steps": 40000, "loss": 0.0, "lr": 2.2688345756745517e-05, "epoch": 235.33333333333334, "percentage": 52.95, "elapsed_time": "2:23:56", "remaining_time": "2:07:54", "throughput": 686.96, "total_tokens": 5932864} {"current_steps": 21185, "total_steps": 40000, "loss": 0.0, "lr": 2.267857051797081e-05, "epoch": 235.38888888888889, "percentage": 52.96, "elapsed_time": "2:23:58", "remaining_time": "2:07:51", "throughput": 686.97, "total_tokens": 5934272} {"current_steps": 21190, "total_steps": 40000, "loss": 0.0, "lr": 2.2668795637189695e-05, "epoch": 235.44444444444446, "percentage": 52.98, "elapsed_time": "2:24:00", "remaining_time": "2:07:49", "throughput": 686.97, "total_tokens": 5935648} {"current_steps": 21195, "total_steps": 40000, "loss": 0.0, "lr": 2.2659021115909586e-05, "epoch": 235.5, "percentage": 52.99, "elapsed_time": "2:24:02", "remaining_time": "2:07:47", "throughput": 686.98, "total_tokens": 5937024} {"current_steps": 21200, "total_steps": 40000, "loss": 0.0, "lr": 2.2649246955637847e-05, "epoch": 235.55555555555554, "percentage": 53.0, "elapsed_time": "2:24:04", "remaining_time": "2:07:45", "throughput": 686.99, "total_tokens": 5938432} {"current_steps": 21200, "total_steps": 40000, "eval_loss": 0.3687517046928406, "epoch": 235.55555555555554, "percentage": 53.0, "elapsed_time": "2:24:05", "remaining_time": "2:07:46", "throughput": 686.88, "total_tokens": 5938432} {"current_steps": 21205, "total_steps": 40000, "loss": 0.0, "lr": 2.2639473157881766e-05, "epoch": 235.61111111111111, "percentage": 53.01, "elapsed_time": "2:24:08", "remaining_time": "2:07:45", "throughput": 686.79, "total_tokens": 5939824} {"current_steps": 21210, "total_steps": 40000, "loss": 0.0, "lr": 2.2629699724148594e-05, "epoch": 235.66666666666666, "percentage": 53.02, "elapsed_time": "2:24:10", "remaining_time": "2:07:43", "throughput": 686.79, "total_tokens": 5941184} {"current_steps": 21215, "total_steps": 40000, "loss": 0.0, "lr": 2.26199266559455e-05, "epoch": 235.72222222222223, "percentage": 53.04, "elapsed_time": "2:24:12", "remaining_time": "2:07:41", "throughput": 686.8, "total_tokens": 5942624} {"current_steps": 21220, "total_steps": 40000, "loss": 0.0, "lr": 2.2610153954779625e-05, "epoch": 235.77777777777777, "percentage": 53.05, "elapsed_time": "2:24:14", "remaining_time": "2:07:39", "throughput": 686.81, "total_tokens": 5944016} {"current_steps": 21225, "total_steps": 40000, "loss": 0.0, "lr": 2.2600381622158056e-05, "epoch": 235.83333333333334, "percentage": 53.06, "elapsed_time": "2:24:16", "remaining_time": "2:07:37", "throughput": 686.81, "total_tokens": 5945392} {"current_steps": 21230, "total_steps": 40000, "loss": 0.0, "lr": 2.2590609659587783e-05, "epoch": 235.88888888888889, "percentage": 53.08, "elapsed_time": "2:24:18", "remaining_time": "2:07:35", "throughput": 686.82, "total_tokens": 5946832} {"current_steps": 21235, "total_steps": 40000, "loss": 0.0, "lr": 2.2580838068575787e-05, "epoch": 235.94444444444446, "percentage": 53.09, "elapsed_time": "2:24:20", "remaining_time": "2:07:33", "throughput": 686.83, "total_tokens": 5948224} {"current_steps": 21240, "total_steps": 40000, "loss": 0.0, "lr": 2.257106685062896e-05, "epoch": 236.0, "percentage": 53.1, "elapsed_time": "2:24:22", "remaining_time": "2:07:31", "throughput": 686.83, "total_tokens": 5949648} {"current_steps": 21245, "total_steps": 40000, "loss": 0.0, "lr": 2.256129600725415e-05, "epoch": 236.05555555555554, "percentage": 53.11, "elapsed_time": "2:24:24", "remaining_time": "2:07:29", "throughput": 686.82, "total_tokens": 5951040} {"current_steps": 21250, "total_steps": 40000, "loss": 0.0, "lr": 2.2551525539958145e-05, "epoch": 236.11111111111111, "percentage": 53.12, "elapsed_time": "2:24:26", "remaining_time": "2:07:27", "throughput": 686.83, "total_tokens": 5952464} {"current_steps": 21255, "total_steps": 40000, "loss": 0.0, "lr": 2.2541755450247663e-05, "epoch": 236.16666666666666, "percentage": 53.14, "elapsed_time": "2:24:28", "remaining_time": "2:07:24", "throughput": 686.84, "total_tokens": 5953904} {"current_steps": 21260, "total_steps": 40000, "loss": 0.0, "lr": 2.2531985739629382e-05, "epoch": 236.22222222222223, "percentage": 53.15, "elapsed_time": "2:24:30", "remaining_time": "2:07:22", "throughput": 686.85, "total_tokens": 5955344} {"current_steps": 21265, "total_steps": 40000, "loss": 0.0, "lr": 2.2522216409609924e-05, "epoch": 236.27777777777777, "percentage": 53.16, "elapsed_time": "2:24:32", "remaining_time": "2:07:20", "throughput": 686.86, "total_tokens": 5956720} {"current_steps": 21270, "total_steps": 40000, "loss": 0.0, "lr": 2.2512447461695826e-05, "epoch": 236.33333333333334, "percentage": 53.17, "elapsed_time": "2:24:34", "remaining_time": "2:07:18", "throughput": 686.87, "total_tokens": 5958144} {"current_steps": 21275, "total_steps": 40000, "loss": 0.0, "lr": 2.2502678897393593e-05, "epoch": 236.38888888888889, "percentage": 53.19, "elapsed_time": "2:24:36", "remaining_time": "2:07:16", "throughput": 686.88, "total_tokens": 5959536} {"current_steps": 21280, "total_steps": 40000, "loss": 0.0, "lr": 2.2492910718209665e-05, "epoch": 236.44444444444446, "percentage": 53.2, "elapsed_time": "2:24:38", "remaining_time": "2:07:14", "throughput": 686.88, "total_tokens": 5960896} {"current_steps": 21285, "total_steps": 40000, "loss": 0.0, "lr": 2.2483142925650398e-05, "epoch": 236.5, "percentage": 53.21, "elapsed_time": "2:24:40", "remaining_time": "2:07:12", "throughput": 686.89, "total_tokens": 5962288} {"current_steps": 21290, "total_steps": 40000, "loss": 0.0, "lr": 2.247337552122213e-05, "epoch": 236.55555555555554, "percentage": 53.23, "elapsed_time": "2:24:42", "remaining_time": "2:07:09", "throughput": 686.9, "total_tokens": 5963696} {"current_steps": 21295, "total_steps": 40000, "loss": 0.0, "lr": 2.24636085064311e-05, "epoch": 236.61111111111111, "percentage": 53.24, "elapsed_time": "2:24:43", "remaining_time": "2:07:07", "throughput": 686.91, "total_tokens": 5965120} {"current_steps": 21300, "total_steps": 40000, "loss": 0.0, "lr": 2.245384188278351e-05, "epoch": 236.66666666666666, "percentage": 53.25, "elapsed_time": "2:24:45", "remaining_time": "2:07:05", "throughput": 686.91, "total_tokens": 5966480} {"current_steps": 21305, "total_steps": 40000, "loss": 0.0, "lr": 2.2444075651785513e-05, "epoch": 236.72222222222223, "percentage": 53.26, "elapsed_time": "2:24:47", "remaining_time": "2:07:03", "throughput": 686.92, "total_tokens": 5967920} {"current_steps": 21310, "total_steps": 40000, "loss": 0.0, "lr": 2.243430981494316e-05, "epoch": 236.77777777777777, "percentage": 53.27, "elapsed_time": "2:24:49", "remaining_time": "2:07:01", "throughput": 686.94, "total_tokens": 5969344} {"current_steps": 21315, "total_steps": 40000, "loss": 0.0, "lr": 2.2424544373762475e-05, "epoch": 236.83333333333334, "percentage": 53.29, "elapsed_time": "2:24:51", "remaining_time": "2:06:59", "throughput": 686.94, "total_tokens": 5970752} {"current_steps": 21320, "total_steps": 40000, "loss": 0.0, "lr": 2.2414779329749418e-05, "epoch": 236.88888888888889, "percentage": 53.3, "elapsed_time": "2:24:53", "remaining_time": "2:06:57", "throughput": 686.95, "total_tokens": 5972128} {"current_steps": 21325, "total_steps": 40000, "loss": 0.0, "lr": 2.2405014684409873e-05, "epoch": 236.94444444444446, "percentage": 53.31, "elapsed_time": "2:24:55", "remaining_time": "2:06:55", "throughput": 686.96, "total_tokens": 5973520} {"current_steps": 21330, "total_steps": 40000, "loss": 0.0, "lr": 2.239525043924968e-05, "epoch": 237.0, "percentage": 53.33, "elapsed_time": "2:24:57", "remaining_time": "2:06:53", "throughput": 686.95, "total_tokens": 5974880} {"current_steps": 21335, "total_steps": 40000, "loss": 0.0, "lr": 2.2385486595774592e-05, "epoch": 237.05555555555554, "percentage": 53.34, "elapsed_time": "2:24:59", "remaining_time": "2:06:51", "throughput": 686.92, "total_tokens": 5976208} {"current_steps": 21340, "total_steps": 40000, "loss": 0.0, "lr": 2.237572315549033e-05, "epoch": 237.11111111111111, "percentage": 53.35, "elapsed_time": "2:25:01", "remaining_time": "2:06:49", "throughput": 686.93, "total_tokens": 5977568} {"current_steps": 21345, "total_steps": 40000, "loss": 0.0, "lr": 2.2365960119902545e-05, "epoch": 237.16666666666666, "percentage": 53.36, "elapsed_time": "2:25:03", "remaining_time": "2:06:46", "throughput": 686.93, "total_tokens": 5978928} {"current_steps": 21350, "total_steps": 40000, "loss": 0.0, "lr": 2.2356197490516806e-05, "epoch": 237.22222222222223, "percentage": 53.37, "elapsed_time": "2:25:05", "remaining_time": "2:06:44", "throughput": 686.95, "total_tokens": 5980384} {"current_steps": 21355, "total_steps": 40000, "loss": 0.0, "lr": 2.234643526883863e-05, "epoch": 237.27777777777777, "percentage": 53.39, "elapsed_time": "2:25:07", "remaining_time": "2:06:42", "throughput": 686.96, "total_tokens": 5981824} {"current_steps": 21360, "total_steps": 40000, "loss": 0.0, "lr": 2.2336673456373497e-05, "epoch": 237.33333333333334, "percentage": 53.4, "elapsed_time": "2:25:09", "remaining_time": "2:06:40", "throughput": 686.97, "total_tokens": 5983248} {"current_steps": 21365, "total_steps": 40000, "loss": 0.0, "lr": 2.2326912054626772e-05, "epoch": 237.38888888888889, "percentage": 53.41, "elapsed_time": "2:25:11", "remaining_time": "2:06:38", "throughput": 686.98, "total_tokens": 5984656} {"current_steps": 21370, "total_steps": 40000, "loss": 0.0, "lr": 2.2317151065103813e-05, "epoch": 237.44444444444446, "percentage": 53.42, "elapsed_time": "2:25:13", "remaining_time": "2:06:36", "throughput": 686.99, "total_tokens": 5986064} {"current_steps": 21375, "total_steps": 40000, "loss": 0.0, "lr": 2.2307390489309865e-05, "epoch": 237.5, "percentage": 53.44, "elapsed_time": "2:25:15", "remaining_time": "2:06:34", "throughput": 686.99, "total_tokens": 5987424} {"current_steps": 21380, "total_steps": 40000, "loss": 0.0, "lr": 2.2297630328750146e-05, "epoch": 237.55555555555554, "percentage": 53.45, "elapsed_time": "2:25:17", "remaining_time": "2:06:32", "throughput": 687.0, "total_tokens": 5988848} {"current_steps": 21385, "total_steps": 40000, "loss": 0.0, "lr": 2.228787058492979e-05, "epoch": 237.61111111111111, "percentage": 53.46, "elapsed_time": "2:25:19", "remaining_time": "2:06:29", "throughput": 687.01, "total_tokens": 5990256} {"current_steps": 21390, "total_steps": 40000, "loss": 0.0, "lr": 2.2278111259353875e-05, "epoch": 237.66666666666666, "percentage": 53.47, "elapsed_time": "2:25:21", "remaining_time": "2:06:27", "throughput": 687.02, "total_tokens": 5991680} {"current_steps": 21395, "total_steps": 40000, "loss": 0.0, "lr": 2.2268352353527395e-05, "epoch": 237.72222222222223, "percentage": 53.49, "elapsed_time": "2:25:23", "remaining_time": "2:06:25", "throughput": 687.03, "total_tokens": 5993088} {"current_steps": 21400, "total_steps": 40000, "loss": 0.0, "lr": 2.225859386895533e-05, "epoch": 237.77777777777777, "percentage": 53.5, "elapsed_time": "2:25:25", "remaining_time": "2:06:23", "throughput": 687.04, "total_tokens": 5994480} {"current_steps": 21400, "total_steps": 40000, "eval_loss": 0.37031468749046326, "epoch": 237.77777777777777, "percentage": 53.5, "elapsed_time": "2:25:26", "remaining_time": "2:06:24", "throughput": 686.94, "total_tokens": 5994480} {"current_steps": 21405, "total_steps": 40000, "loss": 0.0, "lr": 2.2248835807142525e-05, "epoch": 237.83333333333334, "percentage": 53.51, "elapsed_time": "2:25:29", "remaining_time": "2:06:23", "throughput": 686.85, "total_tokens": 5995888} {"current_steps": 21410, "total_steps": 40000, "loss": 0.0, "lr": 2.2239078169593826e-05, "epoch": 237.88888888888889, "percentage": 53.52, "elapsed_time": "2:25:31", "remaining_time": "2:06:21", "throughput": 686.85, "total_tokens": 5997296} {"current_steps": 21415, "total_steps": 40000, "loss": 0.0, "lr": 2.222932095781396e-05, "epoch": 237.94444444444446, "percentage": 53.54, "elapsed_time": "2:25:33", "remaining_time": "2:06:19", "throughput": 686.86, "total_tokens": 5998720} {"current_steps": 21420, "total_steps": 40000, "loss": 0.0, "lr": 2.221956417330762e-05, "epoch": 238.0, "percentage": 53.55, "elapsed_time": "2:25:35", "remaining_time": "2:06:17", "throughput": 686.86, "total_tokens": 6000176} {"current_steps": 21425, "total_steps": 40000, "loss": 0.0, "lr": 2.2209807817579438e-05, "epoch": 238.05555555555554, "percentage": 53.56, "elapsed_time": "2:25:37", "remaining_time": "2:06:15", "throughput": 686.85, "total_tokens": 6001568} {"current_steps": 21430, "total_steps": 40000, "loss": 0.0, "lr": 2.220005189213394e-05, "epoch": 238.11111111111111, "percentage": 53.57, "elapsed_time": "2:25:39", "remaining_time": "2:06:13", "throughput": 686.85, "total_tokens": 6002944} {"current_steps": 21435, "total_steps": 40000, "loss": 0.0, "lr": 2.2190296398475624e-05, "epoch": 238.16666666666666, "percentage": 53.59, "elapsed_time": "2:25:41", "remaining_time": "2:06:11", "throughput": 686.86, "total_tokens": 6004368} {"current_steps": 21440, "total_steps": 40000, "loss": 0.0, "lr": 2.2180541338108926e-05, "epoch": 238.22222222222223, "percentage": 53.6, "elapsed_time": "2:25:43", "remaining_time": "2:06:09", "throughput": 686.87, "total_tokens": 6005728} {"current_steps": 21445, "total_steps": 40000, "loss": 0.0, "lr": 2.2170786712538176e-05, "epoch": 238.27777777777777, "percentage": 53.61, "elapsed_time": "2:25:45", "remaining_time": "2:06:07", "throughput": 686.87, "total_tokens": 6007104} {"current_steps": 21450, "total_steps": 40000, "loss": 0.0, "lr": 2.216103252326768e-05, "epoch": 238.33333333333334, "percentage": 53.62, "elapsed_time": "2:25:47", "remaining_time": "2:06:04", "throughput": 686.88, "total_tokens": 6008496} {"current_steps": 21455, "total_steps": 40000, "loss": 0.0, "lr": 2.2151278771801635e-05, "epoch": 238.38888888888889, "percentage": 53.64, "elapsed_time": "2:25:49", "remaining_time": "2:06:02", "throughput": 686.89, "total_tokens": 6009920} {"current_steps": 21460, "total_steps": 40000, "loss": 0.0, "lr": 2.21415254596442e-05, "epoch": 238.44444444444446, "percentage": 53.65, "elapsed_time": "2:25:51", "remaining_time": "2:06:00", "throughput": 686.9, "total_tokens": 6011328} {"current_steps": 21465, "total_steps": 40000, "loss": 0.0, "lr": 2.213177258829947e-05, "epoch": 238.5, "percentage": 53.66, "elapsed_time": "2:25:53", "remaining_time": "2:05:58", "throughput": 686.91, "total_tokens": 6012800} {"current_steps": 21470, "total_steps": 40000, "loss": 0.0, "lr": 2.2122020159271445e-05, "epoch": 238.55555555555554, "percentage": 53.67, "elapsed_time": "2:25:55", "remaining_time": "2:05:56", "throughput": 686.92, "total_tokens": 6014192} {"current_steps": 21475, "total_steps": 40000, "loss": 0.0, "lr": 2.2112268174064075e-05, "epoch": 238.61111111111111, "percentage": 53.69, "elapsed_time": "2:25:57", "remaining_time": "2:05:54", "throughput": 686.93, "total_tokens": 6015584} {"current_steps": 21480, "total_steps": 40000, "loss": 0.0, "lr": 2.2102516634181253e-05, "epoch": 238.66666666666666, "percentage": 53.7, "elapsed_time": "2:25:59", "remaining_time": "2:05:52", "throughput": 686.94, "total_tokens": 6016992} {"current_steps": 21485, "total_steps": 40000, "loss": 0.0, "lr": 2.209276554112677e-05, "epoch": 238.72222222222223, "percentage": 53.71, "elapsed_time": "2:26:01", "remaining_time": "2:05:50", "throughput": 686.94, "total_tokens": 6018384} {"current_steps": 21490, "total_steps": 40000, "loss": 0.0, "lr": 2.2083014896404384e-05, "epoch": 238.77777777777777, "percentage": 53.73, "elapsed_time": "2:26:03", "remaining_time": "2:05:47", "throughput": 686.95, "total_tokens": 6019840} {"current_steps": 21495, "total_steps": 40000, "loss": 0.0, "lr": 2.207326470151775e-05, "epoch": 238.83333333333334, "percentage": 53.74, "elapsed_time": "2:26:05", "remaining_time": "2:05:45", "throughput": 686.96, "total_tokens": 6021248} {"current_steps": 21500, "total_steps": 40000, "loss": 0.0, "lr": 2.2063514957970477e-05, "epoch": 238.88888888888889, "percentage": 53.75, "elapsed_time": "2:26:06", "remaining_time": "2:05:43", "throughput": 686.97, "total_tokens": 6022672} {"current_steps": 21505, "total_steps": 40000, "loss": 0.0, "lr": 2.205376566726611e-05, "epoch": 238.94444444444446, "percentage": 53.76, "elapsed_time": "2:26:08", "remaining_time": "2:05:41", "throughput": 686.98, "total_tokens": 6024048} {"current_steps": 21510, "total_steps": 40000, "loss": 0.0, "lr": 2.204401683090809e-05, "epoch": 239.0, "percentage": 53.77, "elapsed_time": "2:26:10", "remaining_time": "2:05:39", "throughput": 686.97, "total_tokens": 6025408} {"current_steps": 21515, "total_steps": 40000, "loss": 0.0, "lr": 2.203426845039982e-05, "epoch": 239.05555555555554, "percentage": 53.79, "elapsed_time": "2:26:13", "remaining_time": "2:05:37", "throughput": 686.96, "total_tokens": 6026832} {"current_steps": 21520, "total_steps": 40000, "loss": 0.0, "lr": 2.202452052724464e-05, "epoch": 239.11111111111111, "percentage": 53.8, "elapsed_time": "2:26:15", "remaining_time": "2:05:35", "throughput": 686.97, "total_tokens": 6028272} {"current_steps": 21525, "total_steps": 40000, "loss": 0.0, "lr": 2.2014773062945777e-05, "epoch": 239.16666666666666, "percentage": 53.81, "elapsed_time": "2:26:17", "remaining_time": "2:05:33", "throughput": 686.98, "total_tokens": 6029632} {"current_steps": 21530, "total_steps": 40000, "loss": 0.0, "lr": 2.2005026059006427e-05, "epoch": 239.22222222222223, "percentage": 53.83, "elapsed_time": "2:26:18", "remaining_time": "2:05:31", "throughput": 686.98, "total_tokens": 6031024} {"current_steps": 21535, "total_steps": 40000, "loss": 0.0, "lr": 2.1995279516929695e-05, "epoch": 239.27777777777777, "percentage": 53.84, "elapsed_time": "2:26:20", "remaining_time": "2:05:29", "throughput": 686.99, "total_tokens": 6032400} {"current_steps": 21540, "total_steps": 40000, "loss": 0.0, "lr": 2.1985533438218613e-05, "epoch": 239.33333333333334, "percentage": 53.85, "elapsed_time": "2:26:22", "remaining_time": "2:05:27", "throughput": 687.0, "total_tokens": 6033840} {"current_steps": 21545, "total_steps": 40000, "loss": 0.0, "lr": 2.197578782437617e-05, "epoch": 239.38888888888889, "percentage": 53.86, "elapsed_time": "2:26:24", "remaining_time": "2:05:24", "throughput": 687.01, "total_tokens": 6035264} {"current_steps": 21550, "total_steps": 40000, "loss": 0.0, "lr": 2.196604267690524e-05, "epoch": 239.44444444444446, "percentage": 53.87, "elapsed_time": "2:26:26", "remaining_time": "2:05:22", "throughput": 687.02, "total_tokens": 6036672} {"current_steps": 21555, "total_steps": 40000, "loss": 0.0, "lr": 2.195629799730865e-05, "epoch": 239.5, "percentage": 53.89, "elapsed_time": "2:26:28", "remaining_time": "2:05:20", "throughput": 687.03, "total_tokens": 6038064} {"current_steps": 21560, "total_steps": 40000, "loss": 0.0, "lr": 2.1946553787089173e-05, "epoch": 239.55555555555554, "percentage": 53.9, "elapsed_time": "2:26:30", "remaining_time": "2:05:18", "throughput": 687.04, "total_tokens": 6039504} {"current_steps": 21565, "total_steps": 40000, "loss": 0.0, "lr": 2.193681004774947e-05, "epoch": 239.61111111111111, "percentage": 53.91, "elapsed_time": "2:26:32", "remaining_time": "2:05:16", "throughput": 687.05, "total_tokens": 6040928} {"current_steps": 21570, "total_steps": 40000, "loss": 0.0, "lr": 2.1927066780792154e-05, "epoch": 239.66666666666666, "percentage": 53.92, "elapsed_time": "2:26:34", "remaining_time": "2:05:14", "throughput": 687.06, "total_tokens": 6042336} {"current_steps": 21575, "total_steps": 40000, "loss": 0.0, "lr": 2.191732398771975e-05, "epoch": 239.72222222222223, "percentage": 53.94, "elapsed_time": "2:26:36", "remaining_time": "2:05:12", "throughput": 687.06, "total_tokens": 6043712} {"current_steps": 21580, "total_steps": 40000, "loss": 0.0, "lr": 2.1907581670034725e-05, "epoch": 239.77777777777777, "percentage": 53.95, "elapsed_time": "2:26:38", "remaining_time": "2:05:10", "throughput": 687.07, "total_tokens": 6045072} {"current_steps": 21585, "total_steps": 40000, "loss": 0.0, "lr": 2.189783982923948e-05, "epoch": 239.83333333333334, "percentage": 53.96, "elapsed_time": "2:26:40", "remaining_time": "2:05:07", "throughput": 687.07, "total_tokens": 6046464} {"current_steps": 21590, "total_steps": 40000, "loss": 0.0, "lr": 2.1888098466836303e-05, "epoch": 239.88888888888889, "percentage": 53.97, "elapsed_time": "2:26:42", "remaining_time": "2:05:05", "throughput": 687.09, "total_tokens": 6047888} {"current_steps": 21595, "total_steps": 40000, "loss": 0.0, "lr": 2.1878357584327457e-05, "epoch": 239.94444444444446, "percentage": 53.99, "elapsed_time": "2:26:44", "remaining_time": "2:05:03", "throughput": 687.09, "total_tokens": 6049264} {"current_steps": 21600, "total_steps": 40000, "loss": 0.0, "lr": 2.1868617183215103e-05, "epoch": 240.0, "percentage": 54.0, "elapsed_time": "2:26:46", "remaining_time": "2:05:01", "throughput": 687.08, "total_tokens": 6050656} {"current_steps": 21600, "total_steps": 40000, "eval_loss": 0.3402942717075348, "epoch": 240.0, "percentage": 54.0, "elapsed_time": "2:26:47", "remaining_time": "2:05:02", "throughput": 686.98, "total_tokens": 6050656} {"current_steps": 21605, "total_steps": 40000, "loss": 0.0, "lr": 2.1858877265001327e-05, "epoch": 240.05555555555554, "percentage": 54.01, "elapsed_time": "2:26:51", "remaining_time": "2:05:01", "throughput": 686.87, "total_tokens": 6052064} {"current_steps": 21610, "total_steps": 40000, "loss": 0.0, "lr": 2.184913783118816e-05, "epoch": 240.11111111111111, "percentage": 54.02, "elapsed_time": "2:26:53", "remaining_time": "2:04:59", "throughput": 686.87, "total_tokens": 6053472} {"current_steps": 21615, "total_steps": 40000, "loss": 0.0, "lr": 2.1839398883277522e-05, "epoch": 240.16666666666666, "percentage": 54.04, "elapsed_time": "2:26:55", "remaining_time": "2:04:57", "throughput": 686.88, "total_tokens": 6054864} {"current_steps": 21620, "total_steps": 40000, "loss": 0.0, "lr": 2.182966042277129e-05, "epoch": 240.22222222222223, "percentage": 54.05, "elapsed_time": "2:26:56", "remaining_time": "2:04:55", "throughput": 686.89, "total_tokens": 6056240} {"current_steps": 21625, "total_steps": 40000, "loss": 0.0, "lr": 2.181992245117128e-05, "epoch": 240.27777777777777, "percentage": 54.06, "elapsed_time": "2:26:58", "remaining_time": "2:04:53", "throughput": 686.89, "total_tokens": 6057616} {"current_steps": 21630, "total_steps": 40000, "loss": 0.0, "lr": 2.181018496997918e-05, "epoch": 240.33333333333334, "percentage": 54.07, "elapsed_time": "2:27:00", "remaining_time": "2:04:51", "throughput": 686.9, "total_tokens": 6058992} {"current_steps": 21635, "total_steps": 40000, "loss": 0.0, "lr": 2.1800447980696648e-05, "epoch": 240.38888888888889, "percentage": 54.09, "elapsed_time": "2:27:02", "remaining_time": "2:04:49", "throughput": 686.91, "total_tokens": 6060432} {"current_steps": 21640, "total_steps": 40000, "loss": 0.0, "lr": 2.1790711484825248e-05, "epoch": 240.44444444444446, "percentage": 54.1, "elapsed_time": "2:27:04", "remaining_time": "2:04:47", "throughput": 686.92, "total_tokens": 6061840} {"current_steps": 21645, "total_steps": 40000, "loss": 0.0, "lr": 2.178097548386646e-05, "epoch": 240.5, "percentage": 54.11, "elapsed_time": "2:27:06", "remaining_time": "2:04:45", "throughput": 686.92, "total_tokens": 6063232} {"current_steps": 21650, "total_steps": 40000, "loss": 0.0, "lr": 2.1771239979321712e-05, "epoch": 240.55555555555554, "percentage": 54.12, "elapsed_time": "2:27:08", "remaining_time": "2:04:42", "throughput": 686.94, "total_tokens": 6064672} {"current_steps": 21655, "total_steps": 40000, "loss": 0.0, "lr": 2.1761504972692327e-05, "epoch": 240.61111111111111, "percentage": 54.14, "elapsed_time": "2:27:10", "remaining_time": "2:04:40", "throughput": 686.94, "total_tokens": 6066032} {"current_steps": 21660, "total_steps": 40000, "loss": 0.0, "lr": 2.1751770465479572e-05, "epoch": 240.66666666666666, "percentage": 54.15, "elapsed_time": "2:27:12", "remaining_time": "2:04:38", "throughput": 686.95, "total_tokens": 6067424} {"current_steps": 21665, "total_steps": 40000, "loss": 0.0, "lr": 2.174203645918464e-05, "epoch": 240.72222222222223, "percentage": 54.16, "elapsed_time": "2:27:14", "remaining_time": "2:04:36", "throughput": 686.96, "total_tokens": 6068864} {"current_steps": 21670, "total_steps": 40000, "loss": 0.0, "lr": 2.1732302955308624e-05, "epoch": 240.77777777777777, "percentage": 54.17, "elapsed_time": "2:27:16", "remaining_time": "2:04:34", "throughput": 686.97, "total_tokens": 6070304} {"current_steps": 21675, "total_steps": 40000, "loss": 0.0, "lr": 2.172256995535255e-05, "epoch": 240.83333333333334, "percentage": 54.19, "elapsed_time": "2:27:18", "remaining_time": "2:04:32", "throughput": 686.98, "total_tokens": 6071712} {"current_steps": 21680, "total_steps": 40000, "loss": 0.0, "lr": 2.171283746081739e-05, "epoch": 240.88888888888889, "percentage": 54.2, "elapsed_time": "2:27:20", "remaining_time": "2:04:30", "throughput": 686.99, "total_tokens": 6073088} {"current_steps": 21685, "total_steps": 40000, "loss": 0.0, "lr": 2.1703105473203988e-05, "epoch": 240.94444444444446, "percentage": 54.21, "elapsed_time": "2:27:22", "remaining_time": "2:04:28", "throughput": 686.99, "total_tokens": 6074448} {"current_steps": 21690, "total_steps": 40000, "loss": 0.0, "lr": 2.1693373994013168e-05, "epoch": 241.0, "percentage": 54.23, "elapsed_time": "2:27:24", "remaining_time": "2:04:26", "throughput": 686.98, "total_tokens": 6075856} {"current_steps": 21695, "total_steps": 40000, "loss": 0.0, "lr": 2.168364302474562e-05, "epoch": 241.05555555555554, "percentage": 54.24, "elapsed_time": "2:27:26", "remaining_time": "2:04:24", "throughput": 686.97, "total_tokens": 6077248} {"current_steps": 21700, "total_steps": 40000, "loss": 0.0, "lr": 2.167391256690199e-05, "epoch": 241.11111111111111, "percentage": 54.25, "elapsed_time": "2:27:28", "remaining_time": "2:04:21", "throughput": 686.98, "total_tokens": 6078656} {"current_steps": 21705, "total_steps": 40000, "loss": 0.0, "lr": 2.1664182621982855e-05, "epoch": 241.16666666666666, "percentage": 54.26, "elapsed_time": "2:27:30", "remaining_time": "2:04:19", "throughput": 686.99, "total_tokens": 6080096} {"current_steps": 21710, "total_steps": 40000, "loss": 0.0, "lr": 2.1654453191488673e-05, "epoch": 241.22222222222223, "percentage": 54.27, "elapsed_time": "2:27:32", "remaining_time": "2:04:17", "throughput": 687.0, "total_tokens": 6081488} {"current_steps": 21715, "total_steps": 40000, "loss": 0.0, "lr": 2.1644724276919846e-05, "epoch": 241.27777777777777, "percentage": 54.29, "elapsed_time": "2:27:34", "remaining_time": "2:04:15", "throughput": 687.01, "total_tokens": 6082928} {"current_steps": 21720, "total_steps": 40000, "loss": 0.0, "lr": 2.1634995879776715e-05, "epoch": 241.33333333333334, "percentage": 54.3, "elapsed_time": "2:27:36", "remaining_time": "2:04:13", "throughput": 687.02, "total_tokens": 6084304} {"current_steps": 21725, "total_steps": 40000, "loss": 0.0, "lr": 2.162526800155949e-05, "epoch": 241.38888888888889, "percentage": 54.31, "elapsed_time": "2:27:38", "remaining_time": "2:04:11", "throughput": 687.02, "total_tokens": 6085680} {"current_steps": 21730, "total_steps": 40000, "loss": 0.0, "lr": 2.1615540643768363e-05, "epoch": 241.44444444444446, "percentage": 54.33, "elapsed_time": "2:27:40", "remaining_time": "2:04:09", "throughput": 687.03, "total_tokens": 6087056} {"current_steps": 21735, "total_steps": 40000, "loss": 0.0, "lr": 2.160581380790339e-05, "epoch": 241.5, "percentage": 54.34, "elapsed_time": "2:27:41", "remaining_time": "2:04:07", "throughput": 687.04, "total_tokens": 6088464} {"current_steps": 21740, "total_steps": 40000, "loss": 0.0, "lr": 2.1596087495464586e-05, "epoch": 241.55555555555554, "percentage": 54.35, "elapsed_time": "2:27:43", "remaining_time": "2:04:05", "throughput": 687.04, "total_tokens": 6089856} {"current_steps": 21745, "total_steps": 40000, "loss": 0.0, "lr": 2.1586361707951866e-05, "epoch": 241.61111111111111, "percentage": 54.36, "elapsed_time": "2:27:45", "remaining_time": "2:04:02", "throughput": 687.05, "total_tokens": 6091248} {"current_steps": 21750, "total_steps": 40000, "loss": 0.0, "lr": 2.157663644686507e-05, "epoch": 241.66666666666666, "percentage": 54.37, "elapsed_time": "2:27:47", "remaining_time": "2:04:00", "throughput": 687.06, "total_tokens": 6092688} {"current_steps": 21755, "total_steps": 40000, "loss": 0.0, "lr": 2.156691171370396e-05, "epoch": 241.72222222222223, "percentage": 54.39, "elapsed_time": "2:27:49", "remaining_time": "2:03:58", "throughput": 687.07, "total_tokens": 6094064} {"current_steps": 21760, "total_steps": 40000, "loss": 0.0, "lr": 2.1557187509968195e-05, "epoch": 241.77777777777777, "percentage": 54.4, "elapsed_time": "2:27:51", "remaining_time": "2:03:56", "throughput": 687.07, "total_tokens": 6095456} {"current_steps": 21765, "total_steps": 40000, "loss": 0.0, "lr": 2.1547463837157382e-05, "epoch": 241.83333333333334, "percentage": 54.41, "elapsed_time": "2:27:53", "remaining_time": "2:03:54", "throughput": 687.08, "total_tokens": 6096880} {"current_steps": 21770, "total_steps": 40000, "loss": 0.0, "lr": 2.1537740696771045e-05, "epoch": 241.88888888888889, "percentage": 54.43, "elapsed_time": "2:27:55", "remaining_time": "2:03:52", "throughput": 687.09, "total_tokens": 6098304} {"current_steps": 21775, "total_steps": 40000, "loss": 0.0, "lr": 2.1528018090308587e-05, "epoch": 241.94444444444446, "percentage": 54.44, "elapsed_time": "2:27:57", "remaining_time": "2:03:50", "throughput": 687.11, "total_tokens": 6099760} {"current_steps": 21780, "total_steps": 40000, "loss": 0.0, "lr": 2.151829601926938e-05, "epoch": 242.0, "percentage": 54.45, "elapsed_time": "2:27:59", "remaining_time": "2:03:48", "throughput": 687.1, "total_tokens": 6101152} {"current_steps": 21785, "total_steps": 40000, "loss": 0.0, "lr": 2.1508574485152684e-05, "epoch": 242.05555555555554, "percentage": 54.46, "elapsed_time": "2:28:01", "remaining_time": "2:03:46", "throughput": 687.09, "total_tokens": 6102528} {"current_steps": 21790, "total_steps": 40000, "loss": 0.0, "lr": 2.1498853489457667e-05, "epoch": 242.11111111111111, "percentage": 54.47, "elapsed_time": "2:28:03", "remaining_time": "2:03:44", "throughput": 687.1, "total_tokens": 6103936} {"current_steps": 21795, "total_steps": 40000, "loss": 0.0, "lr": 2.1489133033683455e-05, "epoch": 242.16666666666666, "percentage": 54.49, "elapsed_time": "2:28:05", "remaining_time": "2:03:42", "throughput": 687.1, "total_tokens": 6105344} {"current_steps": 21800, "total_steps": 40000, "loss": 0.0, "lr": 2.1479413119329038e-05, "epoch": 242.22222222222223, "percentage": 54.5, "elapsed_time": "2:28:07", "remaining_time": "2:03:39", "throughput": 687.11, "total_tokens": 6106736} {"current_steps": 21800, "total_steps": 40000, "eval_loss": 0.3380020260810852, "epoch": 242.22222222222223, "percentage": 54.5, "elapsed_time": "2:28:08", "remaining_time": "2:03:40", "throughput": 687.01, "total_tokens": 6106736} {"current_steps": 21805, "total_steps": 40000, "loss": 0.0, "lr": 2.1469693747893355e-05, "epoch": 242.27777777777777, "percentage": 54.51, "elapsed_time": "2:28:12", "remaining_time": "2:03:40", "throughput": 686.9, "total_tokens": 6108144} {"current_steps": 21810, "total_steps": 40000, "loss": 0.0, "lr": 2.1459974920875274e-05, "epoch": 242.33333333333334, "percentage": 54.52, "elapsed_time": "2:28:14", "remaining_time": "2:03:38", "throughput": 686.91, "total_tokens": 6109584} {"current_steps": 21815, "total_steps": 40000, "loss": 0.0, "lr": 2.145025663977354e-05, "epoch": 242.38888888888889, "percentage": 54.54, "elapsed_time": "2:28:16", "remaining_time": "2:03:35", "throughput": 686.91, "total_tokens": 6110976} {"current_steps": 21820, "total_steps": 40000, "loss": 0.0, "lr": 2.1440538906086844e-05, "epoch": 242.44444444444446, "percentage": 54.55, "elapsed_time": "2:28:18", "remaining_time": "2:03:33", "throughput": 686.92, "total_tokens": 6112320} {"current_steps": 21825, "total_steps": 40000, "loss": 0.0, "lr": 2.1430821721313782e-05, "epoch": 242.5, "percentage": 54.56, "elapsed_time": "2:28:20", "remaining_time": "2:03:31", "throughput": 686.93, "total_tokens": 6113744} {"current_steps": 21830, "total_steps": 40000, "loss": 0.0, "lr": 2.142110508695286e-05, "epoch": 242.55555555555554, "percentage": 54.57, "elapsed_time": "2:28:22", "remaining_time": "2:03:29", "throughput": 686.94, "total_tokens": 6115168} {"current_steps": 21835, "total_steps": 40000, "loss": 0.0, "lr": 2.1411389004502515e-05, "epoch": 242.61111111111111, "percentage": 54.59, "elapsed_time": "2:28:24", "remaining_time": "2:03:27", "throughput": 686.94, "total_tokens": 6116528} {"current_steps": 21840, "total_steps": 40000, "loss": 0.0, "lr": 2.140167347546107e-05, "epoch": 242.66666666666666, "percentage": 54.6, "elapsed_time": "2:28:25", "remaining_time": "2:03:25", "throughput": 686.95, "total_tokens": 6117936} {"current_steps": 21845, "total_steps": 40000, "loss": 0.0, "lr": 2.1391958501326793e-05, "epoch": 242.72222222222223, "percentage": 54.61, "elapsed_time": "2:28:27", "remaining_time": "2:03:23", "throughput": 686.96, "total_tokens": 6119312} {"current_steps": 21850, "total_steps": 40000, "loss": 0.0, "lr": 2.1382244083597873e-05, "epoch": 242.77777777777777, "percentage": 54.62, "elapsed_time": "2:28:29", "remaining_time": "2:03:21", "throughput": 686.96, "total_tokens": 6120720} {"current_steps": 21855, "total_steps": 40000, "loss": 0.0, "lr": 2.137253022377237e-05, "epoch": 242.83333333333334, "percentage": 54.64, "elapsed_time": "2:28:31", "remaining_time": "2:03:18", "throughput": 686.97, "total_tokens": 6122144} {"current_steps": 21860, "total_steps": 40000, "loss": 0.0, "lr": 2.136281692334829e-05, "epoch": 242.88888888888889, "percentage": 54.65, "elapsed_time": "2:28:33", "remaining_time": "2:03:16", "throughput": 686.99, "total_tokens": 6123568} {"current_steps": 21865, "total_steps": 40000, "loss": 0.0, "lr": 2.135310418382356e-05, "epoch": 242.94444444444446, "percentage": 54.66, "elapsed_time": "2:28:35", "remaining_time": "2:03:14", "throughput": 686.99, "total_tokens": 6124976} {"current_steps": 21870, "total_steps": 40000, "loss": 0.0, "lr": 2.134339200669598e-05, "epoch": 243.0, "percentage": 54.67, "elapsed_time": "2:28:37", "remaining_time": "2:03:12", "throughput": 686.99, "total_tokens": 6126368} {"current_steps": 21875, "total_steps": 40000, "loss": 0.0, "lr": 2.133368039346331e-05, "epoch": 243.05555555555554, "percentage": 54.69, "elapsed_time": "2:28:39", "remaining_time": "2:03:10", "throughput": 686.98, "total_tokens": 6127760} {"current_steps": 21880, "total_steps": 40000, "loss": 0.0, "lr": 2.1323969345623195e-05, "epoch": 243.11111111111111, "percentage": 54.7, "elapsed_time": "2:28:41", "remaining_time": "2:03:08", "throughput": 686.99, "total_tokens": 6129232} {"current_steps": 21885, "total_steps": 40000, "loss": 0.0, "lr": 2.1314258864673207e-05, "epoch": 243.16666666666666, "percentage": 54.71, "elapsed_time": "2:28:43", "remaining_time": "2:03:06", "throughput": 687.0, "total_tokens": 6130640} {"current_steps": 21890, "total_steps": 40000, "loss": 0.0, "lr": 2.130454895211082e-05, "epoch": 243.22222222222223, "percentage": 54.73, "elapsed_time": "2:28:45", "remaining_time": "2:03:04", "throughput": 687.01, "total_tokens": 6132048} {"current_steps": 21895, "total_steps": 40000, "loss": 0.0, "lr": 2.129483960943342e-05, "epoch": 243.27777777777777, "percentage": 54.74, "elapsed_time": "2:28:47", "remaining_time": "2:03:02", "throughput": 687.01, "total_tokens": 6133440} {"current_steps": 21900, "total_steps": 40000, "loss": 0.0, "lr": 2.128513083813831e-05, "epoch": 243.33333333333334, "percentage": 54.75, "elapsed_time": "2:28:49", "remaining_time": "2:03:00", "throughput": 687.03, "total_tokens": 6134864} {"current_steps": 21905, "total_steps": 40000, "loss": 0.0, "lr": 2.1275422639722724e-05, "epoch": 243.38888888888889, "percentage": 54.76, "elapsed_time": "2:28:51", "remaining_time": "2:02:58", "throughput": 687.03, "total_tokens": 6136272} {"current_steps": 21910, "total_steps": 40000, "loss": 0.0, "lr": 2.126571501568376e-05, "epoch": 243.44444444444446, "percentage": 54.77, "elapsed_time": "2:28:53", "remaining_time": "2:02:55", "throughput": 687.04, "total_tokens": 6137664} {"current_steps": 21915, "total_steps": 40000, "loss": 0.0, "lr": 2.1256007967518478e-05, "epoch": 243.5, "percentage": 54.79, "elapsed_time": "2:28:55", "remaining_time": "2:02:53", "throughput": 687.05, "total_tokens": 6139072} {"current_steps": 21920, "total_steps": 40000, "loss": 0.0, "lr": 2.124630149672381e-05, "epoch": 243.55555555555554, "percentage": 54.8, "elapsed_time": "2:28:57", "remaining_time": "2:02:51", "throughput": 687.06, "total_tokens": 6140464} {"current_steps": 21925, "total_steps": 40000, "loss": 0.0, "lr": 2.1236595604796624e-05, "epoch": 243.61111111111111, "percentage": 54.81, "elapsed_time": "2:28:59", "remaining_time": "2:02:49", "throughput": 687.06, "total_tokens": 6141840} {"current_steps": 21930, "total_steps": 40000, "loss": 0.0, "lr": 2.1226890293233693e-05, "epoch": 243.66666666666666, "percentage": 54.83, "elapsed_time": "2:29:01", "remaining_time": "2:02:47", "throughput": 687.07, "total_tokens": 6143248} {"current_steps": 21935, "total_steps": 40000, "loss": 0.0, "lr": 2.1217185563531694e-05, "epoch": 243.72222222222223, "percentage": 54.84, "elapsed_time": "2:29:03", "remaining_time": "2:02:45", "throughput": 687.08, "total_tokens": 6144640} {"current_steps": 21940, "total_steps": 40000, "loss": 0.0, "lr": 2.120748141718721e-05, "epoch": 243.77777777777777, "percentage": 54.85, "elapsed_time": "2:29:05", "remaining_time": "2:02:43", "throughput": 687.09, "total_tokens": 6146048} {"current_steps": 21945, "total_steps": 40000, "loss": 0.0, "lr": 2.1197777855696765e-05, "epoch": 243.83333333333334, "percentage": 54.86, "elapsed_time": "2:29:07", "remaining_time": "2:02:41", "throughput": 687.1, "total_tokens": 6147472} {"current_steps": 21950, "total_steps": 40000, "loss": 0.0, "lr": 2.1188074880556746e-05, "epoch": 243.88888888888889, "percentage": 54.87, "elapsed_time": "2:29:08", "remaining_time": "2:02:38", "throughput": 687.1, "total_tokens": 6148848} {"current_steps": 21955, "total_steps": 40000, "loss": 0.0, "lr": 2.1178372493263495e-05, "epoch": 243.94444444444446, "percentage": 54.89, "elapsed_time": "2:29:10", "remaining_time": "2:02:36", "throughput": 687.11, "total_tokens": 6150288} {"current_steps": 21960, "total_steps": 40000, "loss": 0.0, "lr": 2.116867069531322e-05, "epoch": 244.0, "percentage": 54.9, "elapsed_time": "2:29:13", "remaining_time": "2:02:34", "throughput": 687.11, "total_tokens": 6151680} {"current_steps": 21965, "total_steps": 40000, "loss": 0.0, "lr": 2.1158969488202073e-05, "epoch": 244.05555555555554, "percentage": 54.91, "elapsed_time": "2:29:15", "remaining_time": "2:02:32", "throughput": 687.1, "total_tokens": 6153136} {"current_steps": 21970, "total_steps": 40000, "loss": 0.0, "lr": 2.114926887342611e-05, "epoch": 244.11111111111111, "percentage": 54.93, "elapsed_time": "2:29:17", "remaining_time": "2:02:30", "throughput": 687.11, "total_tokens": 6154528} {"current_steps": 21975, "total_steps": 40000, "loss": 0.0, "lr": 2.113956885248127e-05, "epoch": 244.16666666666666, "percentage": 54.94, "elapsed_time": "2:29:19", "remaining_time": "2:02:28", "throughput": 687.11, "total_tokens": 6155904} {"current_steps": 21980, "total_steps": 40000, "loss": 0.0, "lr": 2.112986942686342e-05, "epoch": 244.22222222222223, "percentage": 54.95, "elapsed_time": "2:29:21", "remaining_time": "2:02:26", "throughput": 687.12, "total_tokens": 6157328} {"current_steps": 21985, "total_steps": 40000, "loss": 0.0, "lr": 2.112017059806835e-05, "epoch": 244.27777777777777, "percentage": 54.96, "elapsed_time": "2:29:22", "remaining_time": "2:02:24", "throughput": 687.13, "total_tokens": 6158720} {"current_steps": 21990, "total_steps": 40000, "loss": 0.0, "lr": 2.1110472367591724e-05, "epoch": 244.33333333333334, "percentage": 54.97, "elapsed_time": "2:29:24", "remaining_time": "2:02:22", "throughput": 687.14, "total_tokens": 6160096} {"current_steps": 21995, "total_steps": 40000, "loss": 0.0, "lr": 2.1100774736929145e-05, "epoch": 244.38888888888889, "percentage": 54.99, "elapsed_time": "2:29:26", "remaining_time": "2:02:20", "throughput": 687.14, "total_tokens": 6161488} {"current_steps": 22000, "total_steps": 40000, "loss": 0.0, "lr": 2.10910777075761e-05, "epoch": 244.44444444444446, "percentage": 55.0, "elapsed_time": "2:29:28", "remaining_time": "2:02:18", "throughput": 687.15, "total_tokens": 6162896} {"current_steps": 22000, "total_steps": 40000, "eval_loss": 0.36523765325546265, "epoch": 244.44444444444446, "percentage": 55.0, "elapsed_time": "2:29:30", "remaining_time": "2:02:19", "throughput": 687.05, "total_tokens": 6162896} {"current_steps": 22005, "total_steps": 40000, "loss": 0.0, "lr": 2.108138128102799e-05, "epoch": 244.5, "percentage": 55.01, "elapsed_time": "2:29:33", "remaining_time": "2:02:18", "throughput": 686.96, "total_tokens": 6164320} {"current_steps": 22010, "total_steps": 40000, "loss": 0.0, "lr": 2.107168545878014e-05, "epoch": 244.55555555555554, "percentage": 55.02, "elapsed_time": "2:29:35", "remaining_time": "2:02:15", "throughput": 686.97, "total_tokens": 6165712} {"current_steps": 22015, "total_steps": 40000, "loss": 0.0, "lr": 2.106199024232775e-05, "epoch": 244.61111111111111, "percentage": 55.04, "elapsed_time": "2:29:37", "remaining_time": "2:02:13", "throughput": 686.98, "total_tokens": 6167120} {"current_steps": 22020, "total_steps": 40000, "loss": 0.0, "lr": 2.105229563316595e-05, "epoch": 244.66666666666666, "percentage": 55.05, "elapsed_time": "2:29:39", "remaining_time": "2:02:11", "throughput": 686.99, "total_tokens": 6168544} {"current_steps": 22025, "total_steps": 40000, "loss": 0.0, "lr": 2.1042601632789784e-05, "epoch": 244.72222222222223, "percentage": 55.06, "elapsed_time": "2:29:41", "remaining_time": "2:02:09", "throughput": 686.99, "total_tokens": 6169936} {"current_steps": 22030, "total_steps": 40000, "loss": 0.0, "lr": 2.103290824269417e-05, "epoch": 244.77777777777777, "percentage": 55.07, "elapsed_time": "2:29:43", "remaining_time": "2:02:07", "throughput": 687.0, "total_tokens": 6171296} {"current_steps": 22035, "total_steps": 40000, "loss": 0.0, "lr": 2.1023215464373965e-05, "epoch": 244.83333333333334, "percentage": 55.09, "elapsed_time": "2:29:44", "remaining_time": "2:02:05", "throughput": 687.0, "total_tokens": 6172656} {"current_steps": 22040, "total_steps": 40000, "loss": 0.0, "lr": 2.1013523299323908e-05, "epoch": 244.88888888888889, "percentage": 55.1, "elapsed_time": "2:29:46", "remaining_time": "2:02:03", "throughput": 687.01, "total_tokens": 6174096} {"current_steps": 22045, "total_steps": 40000, "loss": 0.0, "lr": 2.1003831749038654e-05, "epoch": 244.94444444444446, "percentage": 55.11, "elapsed_time": "2:29:48", "remaining_time": "2:02:01", "throughput": 687.02, "total_tokens": 6175504} {"current_steps": 22050, "total_steps": 40000, "loss": 0.0, "lr": 2.099414081501277e-05, "epoch": 245.0, "percentage": 55.12, "elapsed_time": "2:29:50", "remaining_time": "2:01:59", "throughput": 687.01, "total_tokens": 6176896} {"current_steps": 22055, "total_steps": 40000, "loss": 0.0, "lr": 2.09844504987407e-05, "epoch": 245.05555555555554, "percentage": 55.14, "elapsed_time": "2:29:53", "remaining_time": "2:01:57", "throughput": 687.0, "total_tokens": 6178272} {"current_steps": 22060, "total_steps": 40000, "loss": 0.0, "lr": 2.097476080171683e-05, "epoch": 245.11111111111111, "percentage": 55.15, "elapsed_time": "2:29:55", "remaining_time": "2:01:55", "throughput": 687.0, "total_tokens": 6179648} {"current_steps": 22065, "total_steps": 40000, "loss": 0.0, "lr": 2.0965071725435436e-05, "epoch": 245.16666666666666, "percentage": 55.16, "elapsed_time": "2:29:57", "remaining_time": "2:01:52", "throughput": 687.01, "total_tokens": 6181040} {"current_steps": 22070, "total_steps": 40000, "loss": 0.0, "lr": 2.0955383271390684e-05, "epoch": 245.22222222222223, "percentage": 55.17, "elapsed_time": "2:29:58", "remaining_time": "2:01:50", "throughput": 687.03, "total_tokens": 6182496} {"current_steps": 22075, "total_steps": 40000, "loss": 0.0, "lr": 2.094569544107666e-05, "epoch": 245.27777777777777, "percentage": 55.19, "elapsed_time": "2:30:00", "remaining_time": "2:01:48", "throughput": 687.03, "total_tokens": 6183904} {"current_steps": 22080, "total_steps": 40000, "loss": 0.0, "lr": 2.093600823598735e-05, "epoch": 245.33333333333334, "percentage": 55.2, "elapsed_time": "2:30:02", "remaining_time": "2:01:46", "throughput": 687.04, "total_tokens": 6185280} {"current_steps": 22085, "total_steps": 40000, "loss": 0.0, "lr": 2.092632165761663e-05, "epoch": 245.38888888888889, "percentage": 55.21, "elapsed_time": "2:30:04", "remaining_time": "2:01:44", "throughput": 687.04, "total_tokens": 6186640} {"current_steps": 22090, "total_steps": 40000, "loss": 0.0, "lr": 2.091663570745832e-05, "epoch": 245.44444444444446, "percentage": 55.23, "elapsed_time": "2:30:06", "remaining_time": "2:01:42", "throughput": 687.05, "total_tokens": 6188032} {"current_steps": 22095, "total_steps": 40000, "loss": 0.0, "lr": 2.0906950387006086e-05, "epoch": 245.5, "percentage": 55.24, "elapsed_time": "2:30:08", "remaining_time": "2:01:40", "throughput": 687.05, "total_tokens": 6189408} {"current_steps": 22100, "total_steps": 40000, "loss": 0.0, "lr": 2.0897265697753543e-05, "epoch": 245.55555555555554, "percentage": 55.25, "elapsed_time": "2:30:10", "remaining_time": "2:01:38", "throughput": 687.06, "total_tokens": 6190832} {"current_steps": 22105, "total_steps": 40000, "loss": 0.0, "lr": 2.088758164119419e-05, "epoch": 245.61111111111111, "percentage": 55.26, "elapsed_time": "2:30:12", "remaining_time": "2:01:36", "throughput": 687.07, "total_tokens": 6192208} {"current_steps": 22110, "total_steps": 40000, "loss": 0.0, "lr": 2.0877898218821428e-05, "epoch": 245.66666666666666, "percentage": 55.27, "elapsed_time": "2:30:14", "remaining_time": "2:01:33", "throughput": 687.08, "total_tokens": 6193616} {"current_steps": 22115, "total_steps": 40000, "loss": 0.0, "lr": 2.0868215432128565e-05, "epoch": 245.72222222222223, "percentage": 55.29, "elapsed_time": "2:30:16", "remaining_time": "2:01:31", "throughput": 687.09, "total_tokens": 6195040} {"current_steps": 22120, "total_steps": 40000, "loss": 0.0, "lr": 2.0858533282608796e-05, "epoch": 245.77777777777777, "percentage": 55.3, "elapsed_time": "2:30:18", "remaining_time": "2:01:29", "throughput": 687.1, "total_tokens": 6196448} {"current_steps": 22125, "total_steps": 40000, "loss": 0.0, "lr": 2.084885177175524e-05, "epoch": 245.83333333333334, "percentage": 55.31, "elapsed_time": "2:30:20", "remaining_time": "2:01:27", "throughput": 687.11, "total_tokens": 6197872} {"current_steps": 22130, "total_steps": 40000, "loss": 0.0, "lr": 2.0839170901060917e-05, "epoch": 245.88888888888889, "percentage": 55.33, "elapsed_time": "2:30:22", "remaining_time": "2:01:25", "throughput": 687.12, "total_tokens": 6199312} {"current_steps": 22135, "total_steps": 40000, "loss": 0.0, "lr": 2.082949067201872e-05, "epoch": 245.94444444444446, "percentage": 55.34, "elapsed_time": "2:30:24", "remaining_time": "2:01:23", "throughput": 687.13, "total_tokens": 6200736} {"current_steps": 22140, "total_steps": 40000, "loss": 0.0, "lr": 2.0819811086121475e-05, "epoch": 246.0, "percentage": 55.35, "elapsed_time": "2:30:26", "remaining_time": "2:01:21", "throughput": 687.12, "total_tokens": 6202112} {"current_steps": 22145, "total_steps": 40000, "loss": 0.0, "lr": 2.08101321448619e-05, "epoch": 246.05555555555554, "percentage": 55.36, "elapsed_time": "2:30:28", "remaining_time": "2:01:19", "throughput": 687.11, "total_tokens": 6203488} {"current_steps": 22150, "total_steps": 40000, "loss": 0.0, "lr": 2.080045384973259e-05, "epoch": 246.11111111111111, "percentage": 55.38, "elapsed_time": "2:30:30", "remaining_time": "2:01:17", "throughput": 687.11, "total_tokens": 6204896} {"current_steps": 22155, "total_steps": 40000, "loss": 0.0, "lr": 2.0790776202226082e-05, "epoch": 246.16666666666666, "percentage": 55.39, "elapsed_time": "2:30:32", "remaining_time": "2:01:15", "throughput": 687.12, "total_tokens": 6206304} {"current_steps": 22160, "total_steps": 40000, "loss": 0.0, "lr": 2.078109920383477e-05, "epoch": 246.22222222222223, "percentage": 55.4, "elapsed_time": "2:30:34", "remaining_time": "2:01:13", "throughput": 687.12, "total_tokens": 6207664} {"current_steps": 22165, "total_steps": 40000, "loss": 0.0, "lr": 2.0771422856050978e-05, "epoch": 246.27777777777777, "percentage": 55.41, "elapsed_time": "2:30:36", "remaining_time": "2:01:10", "throughput": 687.13, "total_tokens": 6209040} {"current_steps": 22170, "total_steps": 40000, "loss": 0.0, "lr": 2.076174716036693e-05, "epoch": 246.33333333333334, "percentage": 55.43, "elapsed_time": "2:30:38", "remaining_time": "2:01:08", "throughput": 687.14, "total_tokens": 6210496} {"current_steps": 22175, "total_steps": 40000, "loss": 0.0, "lr": 2.075207211827472e-05, "epoch": 246.38888888888889, "percentage": 55.44, "elapsed_time": "2:30:40", "remaining_time": "2:01:06", "throughput": 687.15, "total_tokens": 6211888} {"current_steps": 22180, "total_steps": 40000, "loss": 0.0, "lr": 2.074239773126638e-05, "epoch": 246.44444444444446, "percentage": 55.45, "elapsed_time": "2:30:42", "remaining_time": "2:01:04", "throughput": 687.16, "total_tokens": 6213328} {"current_steps": 22185, "total_steps": 40000, "loss": 0.0, "lr": 2.073272400083382e-05, "epoch": 246.5, "percentage": 55.46, "elapsed_time": "2:30:43", "remaining_time": "2:01:02", "throughput": 687.17, "total_tokens": 6214752} {"current_steps": 22190, "total_steps": 40000, "loss": 0.0, "lr": 2.072305092846883e-05, "epoch": 246.55555555555554, "percentage": 55.47, "elapsed_time": "2:30:45", "remaining_time": "2:01:00", "throughput": 687.18, "total_tokens": 6216128} {"current_steps": 22195, "total_steps": 40000, "loss": 0.0, "lr": 2.0713378515663152e-05, "epoch": 246.61111111111111, "percentage": 55.49, "elapsed_time": "2:30:47", "remaining_time": "2:00:58", "throughput": 687.19, "total_tokens": 6217552} {"current_steps": 22200, "total_steps": 40000, "loss": 0.0, "lr": 2.070370676390836e-05, "epoch": 246.66666666666666, "percentage": 55.5, "elapsed_time": "2:30:49", "remaining_time": "2:00:56", "throughput": 687.2, "total_tokens": 6218976} {"current_steps": 22200, "total_steps": 40000, "eval_loss": 0.35795336961746216, "epoch": 246.66666666666666, "percentage": 55.5, "elapsed_time": "2:30:51", "remaining_time": "2:00:57", "throughput": 687.1, "total_tokens": 6218976} {"current_steps": 22205, "total_steps": 40000, "loss": 0.0, "lr": 2.0694035674695974e-05, "epoch": 246.72222222222223, "percentage": 55.51, "elapsed_time": "2:30:54", "remaining_time": "2:00:56", "throughput": 687.0, "total_tokens": 6220352} {"current_steps": 22210, "total_steps": 40000, "loss": 0.0, "lr": 2.0684365249517416e-05, "epoch": 246.77777777777777, "percentage": 55.53, "elapsed_time": "2:30:56", "remaining_time": "2:00:54", "throughput": 687.01, "total_tokens": 6221760} {"current_steps": 22215, "total_steps": 40000, "loss": 0.0, "lr": 2.067469548986396e-05, "epoch": 246.83333333333334, "percentage": 55.54, "elapsed_time": "2:30:58", "remaining_time": "2:00:51", "throughput": 687.02, "total_tokens": 6223200} {"current_steps": 22220, "total_steps": 40000, "loss": 0.0, "lr": 2.066502639722681e-05, "epoch": 246.88888888888889, "percentage": 55.55, "elapsed_time": "2:31:00", "remaining_time": "2:00:49", "throughput": 687.03, "total_tokens": 6224592} {"current_steps": 22225, "total_steps": 40000, "loss": 0.0, "lr": 2.065535797309708e-05, "epoch": 246.94444444444446, "percentage": 55.56, "elapsed_time": "2:31:02", "remaining_time": "2:00:47", "throughput": 687.03, "total_tokens": 6225968} {"current_steps": 22230, "total_steps": 40000, "loss": 0.0, "lr": 2.0645690218965736e-05, "epoch": 247.0, "percentage": 55.57, "elapsed_time": "2:31:04", "remaining_time": "2:00:45", "throughput": 687.02, "total_tokens": 6227344} {"current_steps": 22235, "total_steps": 40000, "loss": 0.0, "lr": 2.063602313632369e-05, "epoch": 247.05555555555554, "percentage": 55.59, "elapsed_time": "2:31:06", "remaining_time": "2:00:43", "throughput": 687.01, "total_tokens": 6228688} {"current_steps": 22240, "total_steps": 40000, "loss": 0.0, "lr": 2.0626356726661704e-05, "epoch": 247.11111111111111, "percentage": 55.6, "elapsed_time": "2:31:08", "remaining_time": "2:00:41", "throughput": 687.01, "total_tokens": 6230048} {"current_steps": 22245, "total_steps": 40000, "loss": 0.0, "lr": 2.0616690991470477e-05, "epoch": 247.16666666666666, "percentage": 55.61, "elapsed_time": "2:31:10", "remaining_time": "2:00:39", "throughput": 687.02, "total_tokens": 6231424} {"current_steps": 22250, "total_steps": 40000, "loss": 0.0, "lr": 2.0607025932240595e-05, "epoch": 247.22222222222223, "percentage": 55.62, "elapsed_time": "2:31:12", "remaining_time": "2:00:37", "throughput": 687.02, "total_tokens": 6232816} {"current_steps": 22255, "total_steps": 40000, "loss": 0.0, "lr": 2.059736155046251e-05, "epoch": 247.27777777777777, "percentage": 55.64, "elapsed_time": "2:31:14", "remaining_time": "2:00:35", "throughput": 687.03, "total_tokens": 6234192} {"current_steps": 22260, "total_steps": 40000, "loss": 0.0, "lr": 2.0587697847626603e-05, "epoch": 247.33333333333334, "percentage": 55.65, "elapsed_time": "2:31:16", "remaining_time": "2:00:33", "throughput": 687.04, "total_tokens": 6235616} {"current_steps": 22265, "total_steps": 40000, "loss": 0.0, "lr": 2.057803482522314e-05, "epoch": 247.38888888888889, "percentage": 55.66, "elapsed_time": "2:31:18", "remaining_time": "2:00:31", "throughput": 687.04, "total_tokens": 6237008} {"current_steps": 22270, "total_steps": 40000, "loss": 0.0, "lr": 2.056837248474227e-05, "epoch": 247.44444444444446, "percentage": 55.67, "elapsed_time": "2:31:19", "remaining_time": "2:00:28", "throughput": 687.05, "total_tokens": 6238384} {"current_steps": 22275, "total_steps": 40000, "loss": 0.0, "lr": 2.0558710827674064e-05, "epoch": 247.5, "percentage": 55.69, "elapsed_time": "2:31:21", "remaining_time": "2:00:26", "throughput": 687.06, "total_tokens": 6239824} {"current_steps": 22280, "total_steps": 40000, "loss": 0.0, "lr": 2.054904985550845e-05, "epoch": 247.55555555555554, "percentage": 55.7, "elapsed_time": "2:31:23", "remaining_time": "2:00:24", "throughput": 687.07, "total_tokens": 6241248} {"current_steps": 22285, "total_steps": 40000, "loss": 0.0, "lr": 2.0539389569735287e-05, "epoch": 247.61111111111111, "percentage": 55.71, "elapsed_time": "2:31:25", "remaining_time": "2:00:22", "throughput": 687.09, "total_tokens": 6242704} {"current_steps": 22290, "total_steps": 40000, "loss": 0.0, "lr": 2.052972997184431e-05, "epoch": 247.66666666666666, "percentage": 55.73, "elapsed_time": "2:31:27", "remaining_time": "2:00:20", "throughput": 687.1, "total_tokens": 6244128} {"current_steps": 22295, "total_steps": 40000, "loss": 0.0, "lr": 2.0520071063325146e-05, "epoch": 247.72222222222223, "percentage": 55.74, "elapsed_time": "2:31:29", "remaining_time": "2:00:18", "throughput": 687.1, "total_tokens": 6245504} {"current_steps": 22300, "total_steps": 40000, "loss": 0.0, "lr": 2.051041284566732e-05, "epoch": 247.77777777777777, "percentage": 55.75, "elapsed_time": "2:31:31", "remaining_time": "2:00:16", "throughput": 687.11, "total_tokens": 6246896} {"current_steps": 22305, "total_steps": 40000, "loss": 0.0, "lr": 2.050075532036026e-05, "epoch": 247.83333333333334, "percentage": 55.76, "elapsed_time": "2:31:33", "remaining_time": "2:00:14", "throughput": 687.12, "total_tokens": 6248352} {"current_steps": 22310, "total_steps": 40000, "loss": 0.0, "lr": 2.0491098488893264e-05, "epoch": 247.88888888888889, "percentage": 55.77, "elapsed_time": "2:31:35", "remaining_time": "2:00:11", "throughput": 687.13, "total_tokens": 6249808} {"current_steps": 22315, "total_steps": 40000, "loss": 0.0, "lr": 2.0481442352755546e-05, "epoch": 247.94444444444446, "percentage": 55.79, "elapsed_time": "2:31:37", "remaining_time": "2:00:09", "throughput": 687.14, "total_tokens": 6251200} {"current_steps": 22320, "total_steps": 40000, "loss": 0.0, "lr": 2.0471786913436198e-05, "epoch": 248.0, "percentage": 55.8, "elapsed_time": "2:31:39", "remaining_time": "2:00:07", "throughput": 687.14, "total_tokens": 6252608} {"current_steps": 22325, "total_steps": 40000, "loss": 0.0, "lr": 2.0462132172424218e-05, "epoch": 248.05555555555554, "percentage": 55.81, "elapsed_time": "2:31:41", "remaining_time": "2:00:05", "throughput": 687.13, "total_tokens": 6254032} {"current_steps": 22330, "total_steps": 40000, "loss": 0.0, "lr": 2.0452478131208484e-05, "epoch": 248.11111111111111, "percentage": 55.83, "elapsed_time": "2:31:43", "remaining_time": "2:00:03", "throughput": 687.14, "total_tokens": 6255440} {"current_steps": 22335, "total_steps": 40000, "loss": 0.0, "lr": 2.0442824791277765e-05, "epoch": 248.16666666666666, "percentage": 55.84, "elapsed_time": "2:31:45", "remaining_time": "2:00:01", "throughput": 687.14, "total_tokens": 6256832} {"current_steps": 22340, "total_steps": 40000, "loss": 0.0, "lr": 2.0433172154120727e-05, "epoch": 248.22222222222223, "percentage": 55.85, "elapsed_time": "2:31:47", "remaining_time": "1:59:59", "throughput": 687.15, "total_tokens": 6258224} {"current_steps": 22345, "total_steps": 40000, "loss": 0.0, "lr": 2.0423520221225947e-05, "epoch": 248.27777777777777, "percentage": 55.86, "elapsed_time": "2:31:49", "remaining_time": "1:59:57", "throughput": 687.16, "total_tokens": 6259616} {"current_steps": 22350, "total_steps": 40000, "loss": 0.0, "lr": 2.0413868994081848e-05, "epoch": 248.33333333333334, "percentage": 55.88, "elapsed_time": "2:31:51", "remaining_time": "1:59:55", "throughput": 687.16, "total_tokens": 6260992} {"current_steps": 22355, "total_steps": 40000, "loss": 0.0, "lr": 2.0404218474176795e-05, "epoch": 248.38888888888889, "percentage": 55.89, "elapsed_time": "2:31:53", "remaining_time": "1:59:53", "throughput": 687.17, "total_tokens": 6262368} {"current_steps": 22360, "total_steps": 40000, "loss": 0.0, "lr": 2.0394568662999002e-05, "epoch": 248.44444444444446, "percentage": 55.9, "elapsed_time": "2:31:55", "remaining_time": "1:59:51", "throughput": 687.17, "total_tokens": 6263776} {"current_steps": 22365, "total_steps": 40000, "loss": 0.0, "lr": 2.0384919562036593e-05, "epoch": 248.5, "percentage": 55.91, "elapsed_time": "2:31:57", "remaining_time": "1:59:48", "throughput": 687.19, "total_tokens": 6265216} {"current_steps": 22370, "total_steps": 40000, "loss": 0.0, "lr": 2.0375271172777593e-05, "epoch": 248.55555555555554, "percentage": 55.93, "elapsed_time": "2:31:59", "remaining_time": "1:59:46", "throughput": 687.2, "total_tokens": 6266640} {"current_steps": 22375, "total_steps": 40000, "loss": 0.0, "lr": 2.0365623496709885e-05, "epoch": 248.61111111111111, "percentage": 55.94, "elapsed_time": "2:32:01", "remaining_time": "1:59:44", "throughput": 687.2, "total_tokens": 6268000} {"current_steps": 22380, "total_steps": 40000, "loss": 0.0, "lr": 2.0355976535321283e-05, "epoch": 248.66666666666666, "percentage": 55.95, "elapsed_time": "2:32:03", "remaining_time": "1:59:42", "throughput": 687.21, "total_tokens": 6269392} {"current_steps": 22385, "total_steps": 40000, "loss": 0.0, "lr": 2.034633029009945e-05, "epoch": 248.72222222222223, "percentage": 55.96, "elapsed_time": "2:32:04", "remaining_time": "1:59:40", "throughput": 687.21, "total_tokens": 6270768} {"current_steps": 22390, "total_steps": 40000, "loss": 0.0, "lr": 2.0336684762531972e-05, "epoch": 248.77777777777777, "percentage": 55.97, "elapsed_time": "2:32:06", "remaining_time": "1:59:38", "throughput": 687.22, "total_tokens": 6272144} {"current_steps": 22395, "total_steps": 40000, "loss": 0.0, "lr": 2.032703995410631e-05, "epoch": 248.83333333333334, "percentage": 55.99, "elapsed_time": "2:32:08", "remaining_time": "1:59:36", "throughput": 687.22, "total_tokens": 6273536} {"current_steps": 22400, "total_steps": 40000, "loss": 0.0, "lr": 2.031739586630981e-05, "epoch": 248.88888888888889, "percentage": 56.0, "elapsed_time": "2:32:10", "remaining_time": "1:59:34", "throughput": 687.23, "total_tokens": 6274960} {"current_steps": 22400, "total_steps": 40000, "eval_loss": 0.3397849500179291, "epoch": 248.88888888888889, "percentage": 56.0, "elapsed_time": "2:32:12", "remaining_time": "1:59:35", "throughput": 687.14, "total_tokens": 6274960} {"current_steps": 22405, "total_steps": 40000, "loss": 0.0, "lr": 2.0307752500629707e-05, "epoch": 248.94444444444446, "percentage": 56.01, "elapsed_time": "2:32:15", "remaining_time": "1:59:34", "throughput": 687.05, "total_tokens": 6276400} {"current_steps": 22410, "total_steps": 40000, "loss": 0.0, "lr": 2.0298109858553144e-05, "epoch": 249.0, "percentage": 56.03, "elapsed_time": "2:32:17", "remaining_time": "1:59:32", "throughput": 687.04, "total_tokens": 6277792} {"current_steps": 22415, "total_steps": 40000, "loss": 0.0, "lr": 2.028846794156712e-05, "epoch": 249.05555555555554, "percentage": 56.04, "elapsed_time": "2:32:19", "remaining_time": "1:59:30", "throughput": 687.03, "total_tokens": 6279200} {"current_steps": 22420, "total_steps": 40000, "loss": 0.0, "lr": 2.027882675115856e-05, "epoch": 249.11111111111111, "percentage": 56.05, "elapsed_time": "2:32:21", "remaining_time": "1:59:28", "throughput": 687.04, "total_tokens": 6280576} {"current_steps": 22425, "total_steps": 40000, "loss": 0.0, "lr": 2.026918628881423e-05, "epoch": 249.16666666666666, "percentage": 56.06, "elapsed_time": "2:32:23", "remaining_time": "1:59:25", "throughput": 687.05, "total_tokens": 6281984} {"current_steps": 22430, "total_steps": 40000, "loss": 0.0, "lr": 2.0259546556020833e-05, "epoch": 249.22222222222223, "percentage": 56.07, "elapsed_time": "2:32:25", "remaining_time": "1:59:23", "throughput": 687.05, "total_tokens": 6283392} {"current_steps": 22435, "total_steps": 40000, "loss": 0.0, "lr": 2.024990755426493e-05, "epoch": 249.27777777777777, "percentage": 56.09, "elapsed_time": "2:32:27", "remaining_time": "1:59:21", "throughput": 687.06, "total_tokens": 6284784} {"current_steps": 22440, "total_steps": 40000, "loss": 0.0, "lr": 2.0240269285032975e-05, "epoch": 249.33333333333334, "percentage": 56.1, "elapsed_time": "2:32:29", "remaining_time": "1:59:19", "throughput": 687.07, "total_tokens": 6286176} {"current_steps": 22445, "total_steps": 40000, "loss": 0.0, "lr": 2.0230631749811306e-05, "epoch": 249.38888888888889, "percentage": 56.11, "elapsed_time": "2:32:31", "remaining_time": "1:59:17", "throughput": 687.07, "total_tokens": 6287568} {"current_steps": 22450, "total_steps": 40000, "loss": 0.0, "lr": 2.0220994950086162e-05, "epoch": 249.44444444444446, "percentage": 56.12, "elapsed_time": "2:32:33", "remaining_time": "1:59:15", "throughput": 687.08, "total_tokens": 6288944} {"current_steps": 22455, "total_steps": 40000, "loss": 0.0, "lr": 2.021135888734365e-05, "epoch": 249.5, "percentage": 56.14, "elapsed_time": "2:32:35", "remaining_time": "1:59:13", "throughput": 687.08, "total_tokens": 6290320} {"current_steps": 22460, "total_steps": 40000, "loss": 0.0, "lr": 2.0201723563069783e-05, "epoch": 249.55555555555554, "percentage": 56.15, "elapsed_time": "2:32:37", "remaining_time": "1:59:11", "throughput": 687.09, "total_tokens": 6291728} {"current_steps": 22465, "total_steps": 40000, "loss": 0.0, "lr": 2.0192088978750433e-05, "epoch": 249.61111111111111, "percentage": 56.16, "elapsed_time": "2:32:38", "remaining_time": "1:59:09", "throughput": 687.1, "total_tokens": 6293120} {"current_steps": 22470, "total_steps": 40000, "loss": 0.0, "lr": 2.0182455135871385e-05, "epoch": 249.66666666666666, "percentage": 56.17, "elapsed_time": "2:32:40", "remaining_time": "1:59:06", "throughput": 687.11, "total_tokens": 6294544} {"current_steps": 22475, "total_steps": 40000, "loss": 0.0, "lr": 2.0172822035918305e-05, "epoch": 249.72222222222223, "percentage": 56.19, "elapsed_time": "2:32:42", "remaining_time": "1:59:04", "throughput": 687.12, "total_tokens": 6295952} {"current_steps": 22480, "total_steps": 40000, "loss": 0.0, "lr": 2.016318968037671e-05, "epoch": 249.77777777777777, "percentage": 56.2, "elapsed_time": "2:32:44", "remaining_time": "1:59:02", "throughput": 687.12, "total_tokens": 6297344} {"current_steps": 22485, "total_steps": 40000, "loss": 0.0, "lr": 2.015355807073206e-05, "epoch": 249.83333333333334, "percentage": 56.21, "elapsed_time": "2:32:46", "remaining_time": "1:59:00", "throughput": 687.13, "total_tokens": 6298768} {"current_steps": 22490, "total_steps": 40000, "loss": 0.0, "lr": 2.0143927208469664e-05, "epoch": 249.88888888888889, "percentage": 56.23, "elapsed_time": "2:32:48", "remaining_time": "1:58:58", "throughput": 687.14, "total_tokens": 6300192} {"current_steps": 22495, "total_steps": 40000, "loss": 0.0, "lr": 2.0134297095074708e-05, "epoch": 249.94444444444446, "percentage": 56.24, "elapsed_time": "2:32:50", "remaining_time": "1:58:56", "throughput": 687.15, "total_tokens": 6301600} {"current_steps": 22500, "total_steps": 40000, "loss": 0.0, "lr": 2.0124667732032297e-05, "epoch": 250.0, "percentage": 56.25, "elapsed_time": "2:32:52", "remaining_time": "1:58:54", "throughput": 687.15, "total_tokens": 6303008} {"current_steps": 22505, "total_steps": 40000, "loss": 0.0, "lr": 2.011503912082738e-05, "epoch": 250.05555555555554, "percentage": 56.26, "elapsed_time": "2:32:54", "remaining_time": "1:58:52", "throughput": 687.14, "total_tokens": 6304448} {"current_steps": 22510, "total_steps": 40000, "loss": 0.0, "lr": 2.0105411262944823e-05, "epoch": 250.11111111111111, "percentage": 56.27, "elapsed_time": "2:32:56", "remaining_time": "1:58:50", "throughput": 687.15, "total_tokens": 6305904} {"current_steps": 22515, "total_steps": 40000, "loss": 0.0, "lr": 2.0095784159869366e-05, "epoch": 250.16666666666666, "percentage": 56.29, "elapsed_time": "2:32:58", "remaining_time": "1:58:48", "throughput": 687.16, "total_tokens": 6307296} {"current_steps": 22520, "total_steps": 40000, "loss": 0.0, "lr": 2.0086157813085608e-05, "epoch": 250.22222222222223, "percentage": 56.3, "elapsed_time": "2:33:00", "remaining_time": "1:58:46", "throughput": 687.17, "total_tokens": 6308688} {"current_steps": 22525, "total_steps": 40000, "loss": 0.0, "lr": 2.0076532224078068e-05, "epoch": 250.27777777777777, "percentage": 56.31, "elapsed_time": "2:33:02", "remaining_time": "1:58:43", "throughput": 687.17, "total_tokens": 6310080} {"current_steps": 22530, "total_steps": 40000, "loss": 0.0, "lr": 2.0066907394331142e-05, "epoch": 250.33333333333334, "percentage": 56.33, "elapsed_time": "2:33:04", "remaining_time": "1:58:41", "throughput": 687.18, "total_tokens": 6311472} {"current_steps": 22535, "total_steps": 40000, "loss": 0.0, "lr": 2.0057283325329077e-05, "epoch": 250.38888888888889, "percentage": 56.34, "elapsed_time": "2:33:06", "remaining_time": "1:58:39", "throughput": 687.19, "total_tokens": 6312864} {"current_steps": 22540, "total_steps": 40000, "loss": 0.0, "lr": 2.0047660018556047e-05, "epoch": 250.44444444444446, "percentage": 56.35, "elapsed_time": "2:33:08", "remaining_time": "1:58:37", "throughput": 687.2, "total_tokens": 6314272} {"current_steps": 22545, "total_steps": 40000, "loss": 0.0, "lr": 2.0038037475496075e-05, "epoch": 250.5, "percentage": 56.36, "elapsed_time": "2:33:10", "remaining_time": "1:58:35", "throughput": 687.2, "total_tokens": 6315616} {"current_steps": 22550, "total_steps": 40000, "loss": 0.0, "lr": 2.0028415697633073e-05, "epoch": 250.55555555555554, "percentage": 56.38, "elapsed_time": "2:33:12", "remaining_time": "1:58:33", "throughput": 687.21, "total_tokens": 6317072} {"current_steps": 22555, "total_steps": 40000, "loss": 0.0, "lr": 2.0018794686450858e-05, "epoch": 250.61111111111111, "percentage": 56.39, "elapsed_time": "2:33:14", "remaining_time": "1:58:31", "throughput": 687.22, "total_tokens": 6318464} {"current_steps": 22560, "total_steps": 40000, "loss": 0.0, "lr": 2.0009174443433088e-05, "epoch": 250.66666666666666, "percentage": 56.4, "elapsed_time": "2:33:16", "remaining_time": "1:58:29", "throughput": 687.23, "total_tokens": 6319888} {"current_steps": 22565, "total_steps": 40000, "loss": 0.0, "lr": 1.999955497006334e-05, "epoch": 250.72222222222223, "percentage": 56.41, "elapsed_time": "2:33:18", "remaining_time": "1:58:27", "throughput": 687.23, "total_tokens": 6321232} {"current_steps": 22570, "total_steps": 40000, "loss": 0.0, "lr": 1.9989936267825067e-05, "epoch": 250.77777777777777, "percentage": 56.43, "elapsed_time": "2:33:20", "remaining_time": "1:58:24", "throughput": 687.24, "total_tokens": 6322624} {"current_steps": 22575, "total_steps": 40000, "loss": 0.0, "lr": 1.9980318338201572e-05, "epoch": 250.83333333333334, "percentage": 56.44, "elapsed_time": "2:33:22", "remaining_time": "1:58:22", "throughput": 687.25, "total_tokens": 6324064} {"current_steps": 22580, "total_steps": 40000, "loss": 0.0, "lr": 1.997070118267607e-05, "epoch": 250.88888888888889, "percentage": 56.45, "elapsed_time": "2:33:23", "remaining_time": "1:58:20", "throughput": 687.26, "total_tokens": 6325472} {"current_steps": 22585, "total_steps": 40000, "loss": 0.0, "lr": 1.9961084802731654e-05, "epoch": 250.94444444444446, "percentage": 56.46, "elapsed_time": "2:33:25", "remaining_time": "1:58:18", "throughput": 687.26, "total_tokens": 6326848} {"current_steps": 22590, "total_steps": 40000, "loss": 0.0, "lr": 1.9951469199851273e-05, "epoch": 251.0, "percentage": 56.47, "elapsed_time": "2:33:27", "remaining_time": "1:58:16", "throughput": 687.25, "total_tokens": 6328224} {"current_steps": 22595, "total_steps": 40000, "loss": 0.0, "lr": 1.99418543755178e-05, "epoch": 251.05555555555554, "percentage": 56.49, "elapsed_time": "2:33:30", "remaining_time": "1:58:14", "throughput": 687.25, "total_tokens": 6329664} {"current_steps": 22600, "total_steps": 40000, "loss": 0.0, "lr": 1.9932240331213936e-05, "epoch": 251.11111111111111, "percentage": 56.5, "elapsed_time": "2:33:32", "remaining_time": "1:58:12", "throughput": 687.25, "total_tokens": 6331008} {"current_steps": 22600, "total_steps": 40000, "eval_loss": 0.3739665448665619, "epoch": 251.11111111111111, "percentage": 56.5, "elapsed_time": "2:33:33", "remaining_time": "1:58:13", "throughput": 687.15, "total_tokens": 6331008} {"current_steps": 22605, "total_steps": 40000, "loss": 0.0, "lr": 1.9922627068422297e-05, "epoch": 251.16666666666666, "percentage": 56.51, "elapsed_time": "2:33:36", "remaining_time": "1:58:12", "throughput": 687.06, "total_tokens": 6332400} {"current_steps": 22610, "total_steps": 40000, "loss": 0.0, "lr": 1.991301458862538e-05, "epoch": 251.22222222222223, "percentage": 56.53, "elapsed_time": "2:33:38", "remaining_time": "1:58:10", "throughput": 687.07, "total_tokens": 6333792} {"current_steps": 22615, "total_steps": 40000, "loss": 0.0, "lr": 1.9903402893305536e-05, "epoch": 251.27777777777777, "percentage": 56.54, "elapsed_time": "2:33:40", "remaining_time": "1:58:08", "throughput": 687.08, "total_tokens": 6335216} {"current_steps": 22620, "total_steps": 40000, "loss": 0.0, "lr": 1.9893791983945016e-05, "epoch": 251.33333333333334, "percentage": 56.55, "elapsed_time": "2:33:42", "remaining_time": "1:58:06", "throughput": 687.09, "total_tokens": 6336672} {"current_steps": 22625, "total_steps": 40000, "loss": 0.0, "lr": 1.988418186202594e-05, "epoch": 251.38888888888889, "percentage": 56.56, "elapsed_time": "2:33:44", "remaining_time": "1:58:03", "throughput": 687.1, "total_tokens": 6338080} {"current_steps": 22630, "total_steps": 40000, "loss": 0.0, "lr": 1.98745725290303e-05, "epoch": 251.44444444444446, "percentage": 56.57, "elapsed_time": "2:33:46", "remaining_time": "1:58:01", "throughput": 687.1, "total_tokens": 6339456} {"current_steps": 22635, "total_steps": 40000, "loss": 0.0, "lr": 1.986496398644e-05, "epoch": 251.5, "percentage": 56.59, "elapsed_time": "2:33:48", "remaining_time": "1:57:59", "throughput": 687.11, "total_tokens": 6340880} {"current_steps": 22640, "total_steps": 40000, "loss": 0.0, "lr": 1.9855356235736777e-05, "epoch": 251.55555555555554, "percentage": 56.6, "elapsed_time": "2:33:50", "remaining_time": "1:57:57", "throughput": 687.12, "total_tokens": 6342272} {"current_steps": 22645, "total_steps": 40000, "loss": 0.0, "lr": 1.9845749278402277e-05, "epoch": 251.61111111111111, "percentage": 56.61, "elapsed_time": "2:33:52", "remaining_time": "1:57:55", "throughput": 687.12, "total_tokens": 6343664} {"current_steps": 22650, "total_steps": 40000, "loss": 0.0, "lr": 1.9836143115918006e-05, "epoch": 251.66666666666666, "percentage": 56.62, "elapsed_time": "2:33:54", "remaining_time": "1:57:53", "throughput": 687.13, "total_tokens": 6345056} {"current_steps": 22655, "total_steps": 40000, "loss": 0.0, "lr": 1.9826537749765367e-05, "epoch": 251.72222222222223, "percentage": 56.64, "elapsed_time": "2:33:56", "remaining_time": "1:57:51", "throughput": 687.14, "total_tokens": 6346464} {"current_steps": 22660, "total_steps": 40000, "loss": 0.0, "lr": 1.9816933181425625e-05, "epoch": 251.77777777777777, "percentage": 56.65, "elapsed_time": "2:33:57", "remaining_time": "1:57:49", "throughput": 687.15, "total_tokens": 6347904} {"current_steps": 22665, "total_steps": 40000, "loss": 0.0, "lr": 1.9807329412379903e-05, "epoch": 251.83333333333334, "percentage": 56.66, "elapsed_time": "2:33:59", "remaining_time": "1:57:47", "throughput": 687.16, "total_tokens": 6349328} {"current_steps": 22670, "total_steps": 40000, "loss": 0.0, "lr": 1.9797726444109247e-05, "epoch": 251.88888888888889, "percentage": 56.67, "elapsed_time": "2:34:01", "remaining_time": "1:57:44", "throughput": 687.17, "total_tokens": 6350736} {"current_steps": 22675, "total_steps": 40000, "loss": 0.0, "lr": 1.9788124278094557e-05, "epoch": 251.94444444444446, "percentage": 56.69, "elapsed_time": "2:34:03", "remaining_time": "1:57:42", "throughput": 687.18, "total_tokens": 6352112} {"current_steps": 22680, "total_steps": 40000, "loss": 0.0, "lr": 1.9778522915816594e-05, "epoch": 252.0, "percentage": 56.7, "elapsed_time": "2:34:05", "remaining_time": "1:57:40", "throughput": 687.17, "total_tokens": 6353520} {"current_steps": 22685, "total_steps": 40000, "loss": 0.0, "lr": 1.9768922358756014e-05, "epoch": 252.05555555555554, "percentage": 56.71, "elapsed_time": "2:34:08", "remaining_time": "1:57:38", "throughput": 687.16, "total_tokens": 6354928} {"current_steps": 22690, "total_steps": 40000, "loss": 0.0, "lr": 1.9759322608393353e-05, "epoch": 252.11111111111111, "percentage": 56.73, "elapsed_time": "2:34:10", "remaining_time": "1:57:36", "throughput": 687.17, "total_tokens": 6356336} {"current_steps": 22695, "total_steps": 40000, "loss": 0.0, "lr": 1.9749723666208992e-05, "epoch": 252.16666666666666, "percentage": 56.74, "elapsed_time": "2:34:11", "remaining_time": "1:57:34", "throughput": 687.18, "total_tokens": 6357728} {"current_steps": 22700, "total_steps": 40000, "loss": 0.0, "lr": 1.9740125533683235e-05, "epoch": 252.22222222222223, "percentage": 56.75, "elapsed_time": "2:34:13", "remaining_time": "1:57:32", "throughput": 687.19, "total_tokens": 6359184} {"current_steps": 22705, "total_steps": 40000, "loss": 0.0, "lr": 1.9730528212296208e-05, "epoch": 252.27777777777777, "percentage": 56.76, "elapsed_time": "2:34:15", "remaining_time": "1:57:30", "throughput": 687.2, "total_tokens": 6360608} {"current_steps": 22710, "total_steps": 40000, "loss": 0.0, "lr": 1.9720931703527945e-05, "epoch": 252.33333333333334, "percentage": 56.77, "elapsed_time": "2:34:17", "remaining_time": "1:57:28", "throughput": 687.2, "total_tokens": 6362000} {"current_steps": 22715, "total_steps": 40000, "loss": 0.0, "lr": 1.9711336008858373e-05, "epoch": 252.38888888888889, "percentage": 56.79, "elapsed_time": "2:34:19", "remaining_time": "1:57:26", "throughput": 687.22, "total_tokens": 6363440} {"current_steps": 22720, "total_steps": 40000, "loss": 0.0, "lr": 1.9701741129767233e-05, "epoch": 252.44444444444446, "percentage": 56.8, "elapsed_time": "2:34:21", "remaining_time": "1:57:24", "throughput": 687.22, "total_tokens": 6364800} {"current_steps": 22725, "total_steps": 40000, "loss": 0.0, "lr": 1.9692147067734202e-05, "epoch": 252.5, "percentage": 56.81, "elapsed_time": "2:34:23", "remaining_time": "1:57:21", "throughput": 687.22, "total_tokens": 6366192} {"current_steps": 22730, "total_steps": 40000, "loss": 0.0, "lr": 1.96825538242388e-05, "epoch": 252.55555555555554, "percentage": 56.83, "elapsed_time": "2:34:25", "remaining_time": "1:57:19", "throughput": 687.23, "total_tokens": 6367568} {"current_steps": 22735, "total_steps": 40000, "loss": 0.0, "lr": 1.967296140076041e-05, "epoch": 252.61111111111111, "percentage": 56.84, "elapsed_time": "2:34:27", "remaining_time": "1:57:17", "throughput": 687.24, "total_tokens": 6368976} {"current_steps": 22740, "total_steps": 40000, "loss": 0.0, "lr": 1.966336979877833e-05, "epoch": 252.66666666666666, "percentage": 56.85, "elapsed_time": "2:34:29", "remaining_time": "1:57:15", "throughput": 687.25, "total_tokens": 6370384} {"current_steps": 22745, "total_steps": 40000, "loss": 0.0, "lr": 1.9653779019771678e-05, "epoch": 252.72222222222223, "percentage": 56.86, "elapsed_time": "2:34:31", "remaining_time": "1:57:13", "throughput": 687.26, "total_tokens": 6371824} {"current_steps": 22750, "total_steps": 40000, "loss": 0.0, "lr": 1.9644189065219488e-05, "epoch": 252.77777777777777, "percentage": 56.88, "elapsed_time": "2:34:33", "remaining_time": "1:57:11", "throughput": 687.27, "total_tokens": 6373248} {"current_steps": 22755, "total_steps": 40000, "loss": 0.0, "lr": 1.9634599936600655e-05, "epoch": 252.83333333333334, "percentage": 56.89, "elapsed_time": "2:34:35", "remaining_time": "1:57:09", "throughput": 687.27, "total_tokens": 6374624} {"current_steps": 22760, "total_steps": 40000, "loss": 0.0, "lr": 1.9625011635393935e-05, "epoch": 252.88888888888889, "percentage": 56.9, "elapsed_time": "2:34:37", "remaining_time": "1:57:07", "throughput": 687.28, "total_tokens": 6375984} {"current_steps": 22765, "total_steps": 40000, "loss": 0.0, "lr": 1.9615424163077963e-05, "epoch": 252.94444444444446, "percentage": 56.91, "elapsed_time": "2:34:39", "remaining_time": "1:57:05", "throughput": 687.28, "total_tokens": 6377344} {"current_steps": 22770, "total_steps": 40000, "loss": 0.0, "lr": 1.9605837521131263e-05, "epoch": 253.0, "percentage": 56.93, "elapsed_time": "2:34:41", "remaining_time": "1:57:03", "throughput": 687.28, "total_tokens": 6378784} {"current_steps": 22775, "total_steps": 40000, "loss": 0.0, "lr": 1.9596251711032192e-05, "epoch": 253.05555555555554, "percentage": 56.94, "elapsed_time": "2:34:43", "remaining_time": "1:57:01", "throughput": 687.27, "total_tokens": 6380192} {"current_steps": 22780, "total_steps": 40000, "loss": 0.0, "lr": 1.958666673425903e-05, "epoch": 253.11111111111111, "percentage": 56.95, "elapsed_time": "2:34:45", "remaining_time": "1:56:59", "throughput": 687.28, "total_tokens": 6381616} {"current_steps": 22785, "total_steps": 40000, "loss": 0.0, "lr": 1.957708259228987e-05, "epoch": 253.16666666666666, "percentage": 56.96, "elapsed_time": "2:34:47", "remaining_time": "1:56:56", "throughput": 687.28, "total_tokens": 6382992} {"current_steps": 22790, "total_steps": 40000, "loss": 0.0, "lr": 1.956749928660273e-05, "epoch": 253.22222222222223, "percentage": 56.97, "elapsed_time": "2:34:49", "remaining_time": "1:56:54", "throughput": 687.29, "total_tokens": 6384384} {"current_steps": 22795, "total_steps": 40000, "loss": 0.0, "lr": 1.955791681867547e-05, "epoch": 253.27777777777777, "percentage": 56.99, "elapsed_time": "2:34:51", "remaining_time": "1:56:52", "throughput": 687.29, "total_tokens": 6385712} {"current_steps": 22800, "total_steps": 40000, "loss": 0.0, "lr": 1.9548335189985824e-05, "epoch": 253.33333333333334, "percentage": 57.0, "elapsed_time": "2:34:53", "remaining_time": "1:56:50", "throughput": 687.3, "total_tokens": 6387152} {"current_steps": 22800, "total_steps": 40000, "eval_loss": 0.3142276108264923, "epoch": 253.33333333333334, "percentage": 57.0, "elapsed_time": "2:34:54", "remaining_time": "1:56:51", "throughput": 687.2, "total_tokens": 6387152} {"current_steps": 22805, "total_steps": 40000, "loss": 0.0, "lr": 1.9538754402011396e-05, "epoch": 253.38888888888889, "percentage": 57.01, "elapsed_time": "2:34:58", "remaining_time": "1:56:50", "throughput": 687.07, "total_tokens": 6388544} {"current_steps": 22810, "total_steps": 40000, "loss": 0.0, "lr": 1.952917445622968e-05, "epoch": 253.44444444444446, "percentage": 57.03, "elapsed_time": "2:35:00", "remaining_time": "1:56:48", "throughput": 687.07, "total_tokens": 6389920} {"current_steps": 22815, "total_steps": 40000, "loss": 0.0, "lr": 1.9519595354118005e-05, "epoch": 253.5, "percentage": 57.04, "elapsed_time": "2:35:02", "remaining_time": "1:56:46", "throughput": 687.06, "total_tokens": 6391296} {"current_steps": 22820, "total_steps": 40000, "loss": 0.0, "lr": 1.951001709715361e-05, "epoch": 253.55555555555554, "percentage": 57.05, "elapsed_time": "2:35:04", "remaining_time": "1:56:44", "throughput": 687.07, "total_tokens": 6392752} {"current_steps": 22825, "total_steps": 40000, "loss": 0.0, "lr": 1.9500439686813556e-05, "epoch": 253.61111111111111, "percentage": 57.06, "elapsed_time": "2:35:06", "remaining_time": "1:56:42", "throughput": 687.08, "total_tokens": 6394112} {"current_steps": 22830, "total_steps": 40000, "loss": 0.0, "lr": 1.949086312457482e-05, "epoch": 253.66666666666666, "percentage": 57.07, "elapsed_time": "2:35:08", "remaining_time": "1:56:40", "throughput": 687.08, "total_tokens": 6395488} {"current_steps": 22835, "total_steps": 40000, "loss": 0.0, "lr": 1.9481287411914223e-05, "epoch": 253.72222222222223, "percentage": 57.09, "elapsed_time": "2:35:10", "remaining_time": "1:56:38", "throughput": 687.09, "total_tokens": 6396912} {"current_steps": 22840, "total_steps": 40000, "loss": 0.0, "lr": 1.9471712550308457e-05, "epoch": 253.77777777777777, "percentage": 57.1, "elapsed_time": "2:35:12", "remaining_time": "1:56:36", "throughput": 687.1, "total_tokens": 6398336} {"current_steps": 22845, "total_steps": 40000, "loss": 0.0, "lr": 1.946213854123409e-05, "epoch": 253.83333333333334, "percentage": 57.11, "elapsed_time": "2:35:14", "remaining_time": "1:56:34", "throughput": 687.11, "total_tokens": 6399792} {"current_steps": 22850, "total_steps": 40000, "loss": 0.0, "lr": 1.9452565386167554e-05, "epoch": 253.88888888888889, "percentage": 57.12, "elapsed_time": "2:35:15", "remaining_time": "1:56:32", "throughput": 687.12, "total_tokens": 6401168} {"current_steps": 22855, "total_steps": 40000, "loss": 0.0, "lr": 1.9442993086585142e-05, "epoch": 253.94444444444446, "percentage": 57.14, "elapsed_time": "2:35:17", "remaining_time": "1:56:29", "throughput": 687.13, "total_tokens": 6402576} {"current_steps": 22860, "total_steps": 40000, "loss": 0.0, "lr": 1.9433421643963043e-05, "epoch": 254.0, "percentage": 57.15, "elapsed_time": "2:35:20", "remaining_time": "1:56:27", "throughput": 687.12, "total_tokens": 6403984} {"current_steps": 22865, "total_steps": 40000, "loss": 0.0, "lr": 1.942385105977727e-05, "epoch": 254.05555555555554, "percentage": 57.16, "elapsed_time": "2:35:22", "remaining_time": "1:56:26", "throughput": 687.12, "total_tokens": 6405424} {"current_steps": 22870, "total_steps": 40000, "loss": 0.0, "lr": 1.9414281335503743e-05, "epoch": 254.11111111111111, "percentage": 57.17, "elapsed_time": "2:35:24", "remaining_time": "1:56:23", "throughput": 687.12, "total_tokens": 6406816} {"current_steps": 22875, "total_steps": 40000, "loss": 0.0, "lr": 1.9404712472618232e-05, "epoch": 254.16666666666666, "percentage": 57.19, "elapsed_time": "2:35:26", "remaining_time": "1:56:21", "throughput": 687.13, "total_tokens": 6408192} {"current_steps": 22880, "total_steps": 40000, "loss": 0.0, "lr": 1.939514447259636e-05, "epoch": 254.22222222222223, "percentage": 57.2, "elapsed_time": "2:35:27", "remaining_time": "1:56:19", "throughput": 687.13, "total_tokens": 6409584} {"current_steps": 22885, "total_steps": 40000, "loss": 0.0, "lr": 1.938557733691365e-05, "epoch": 254.27777777777777, "percentage": 57.21, "elapsed_time": "2:35:29", "remaining_time": "1:56:17", "throughput": 687.14, "total_tokens": 6410944} {"current_steps": 22890, "total_steps": 40000, "loss": 0.0, "lr": 1.9376011067045476e-05, "epoch": 254.33333333333334, "percentage": 57.23, "elapsed_time": "2:35:31", "remaining_time": "1:56:15", "throughput": 687.14, "total_tokens": 6412336} {"current_steps": 22895, "total_steps": 40000, "loss": 0.0, "lr": 1.9366445664467065e-05, "epoch": 254.38888888888889, "percentage": 57.24, "elapsed_time": "2:35:33", "remaining_time": "1:56:13", "throughput": 687.15, "total_tokens": 6413760} {"current_steps": 22900, "total_steps": 40000, "loss": 0.0, "lr": 1.9356881130653533e-05, "epoch": 254.44444444444446, "percentage": 57.25, "elapsed_time": "2:35:35", "remaining_time": "1:56:11", "throughput": 687.16, "total_tokens": 6415184} {"current_steps": 22905, "total_steps": 40000, "loss": 0.0, "lr": 1.9347317467079846e-05, "epoch": 254.5, "percentage": 57.26, "elapsed_time": "2:35:37", "remaining_time": "1:56:09", "throughput": 687.17, "total_tokens": 6416576} {"current_steps": 22910, "total_steps": 40000, "loss": 0.0, "lr": 1.9337754675220836e-05, "epoch": 254.55555555555554, "percentage": 57.27, "elapsed_time": "2:35:39", "remaining_time": "1:56:07", "throughput": 687.18, "total_tokens": 6418000} {"current_steps": 22915, "total_steps": 40000, "loss": 0.0, "lr": 1.9328192756551218e-05, "epoch": 254.61111111111111, "percentage": 57.29, "elapsed_time": "2:35:41", "remaining_time": "1:56:04", "throughput": 687.19, "total_tokens": 6419392} {"current_steps": 22920, "total_steps": 40000, "loss": 0.0, "lr": 1.931863171254555e-05, "epoch": 254.66666666666666, "percentage": 57.3, "elapsed_time": "2:35:43", "remaining_time": "1:56:02", "throughput": 687.19, "total_tokens": 6420784} {"current_steps": 22925, "total_steps": 40000, "loss": 0.0, "lr": 1.930907154467826e-05, "epoch": 254.72222222222223, "percentage": 57.31, "elapsed_time": "2:35:45", "remaining_time": "1:56:00", "throughput": 687.2, "total_tokens": 6422224} {"current_steps": 22930, "total_steps": 40000, "loss": 0.0, "lr": 1.9299512254423673e-05, "epoch": 254.77777777777777, "percentage": 57.33, "elapsed_time": "2:35:47", "remaining_time": "1:55:58", "throughput": 687.21, "total_tokens": 6423632} {"current_steps": 22935, "total_steps": 40000, "loss": 0.0, "lr": 1.9289953843255914e-05, "epoch": 254.83333333333334, "percentage": 57.34, "elapsed_time": "2:35:49", "remaining_time": "1:55:56", "throughput": 687.22, "total_tokens": 6425056} {"current_steps": 22940, "total_steps": 40000, "loss": 0.0, "lr": 1.9280396312649048e-05, "epoch": 254.88888888888889, "percentage": 57.35, "elapsed_time": "2:35:51", "remaining_time": "1:55:54", "throughput": 687.23, "total_tokens": 6426464} {"current_steps": 22945, "total_steps": 40000, "loss": 0.0, "lr": 1.9270839664076936e-05, "epoch": 254.94444444444446, "percentage": 57.36, "elapsed_time": "2:35:53", "remaining_time": "1:55:52", "throughput": 687.23, "total_tokens": 6427824} {"current_steps": 22950, "total_steps": 40000, "loss": 0.0, "lr": 1.9261283899013345e-05, "epoch": 255.0, "percentage": 57.38, "elapsed_time": "2:35:55", "remaining_time": "1:55:50", "throughput": 687.23, "total_tokens": 6429216} {"current_steps": 22955, "total_steps": 40000, "loss": 0.0, "lr": 1.92517290189319e-05, "epoch": 255.05555555555554, "percentage": 57.39, "elapsed_time": "2:35:57", "remaining_time": "1:55:48", "throughput": 687.22, "total_tokens": 6430656} {"current_steps": 22960, "total_steps": 40000, "loss": 0.0, "lr": 1.924217502530607e-05, "epoch": 255.11111111111111, "percentage": 57.4, "elapsed_time": "2:35:59", "remaining_time": "1:55:46", "throughput": 687.23, "total_tokens": 6432048} {"current_steps": 22965, "total_steps": 40000, "loss": 0.0, "lr": 1.9232621919609207e-05, "epoch": 255.16666666666666, "percentage": 57.41, "elapsed_time": "2:36:01", "remaining_time": "1:55:44", "throughput": 687.23, "total_tokens": 6433440} {"current_steps": 22970, "total_steps": 40000, "loss": 0.0, "lr": 1.9223069703314534e-05, "epoch": 255.22222222222223, "percentage": 57.43, "elapsed_time": "2:36:03", "remaining_time": "1:55:41", "throughput": 687.24, "total_tokens": 6434816} {"current_steps": 22975, "total_steps": 40000, "loss": 0.0, "lr": 1.92135183778951e-05, "epoch": 255.27777777777777, "percentage": 57.44, "elapsed_time": "2:36:05", "remaining_time": "1:55:39", "throughput": 687.24, "total_tokens": 6436192} {"current_steps": 22980, "total_steps": 40000, "loss": 0.0, "lr": 1.9203967944823857e-05, "epoch": 255.33333333333334, "percentage": 57.45, "elapsed_time": "2:36:07", "remaining_time": "1:55:37", "throughput": 687.25, "total_tokens": 6437568} {"current_steps": 22985, "total_steps": 40000, "loss": 0.0, "lr": 1.9194418405573588e-05, "epoch": 255.38888888888889, "percentage": 57.46, "elapsed_time": "2:36:09", "remaining_time": "1:55:35", "throughput": 687.26, "total_tokens": 6438992} {"current_steps": 22990, "total_steps": 40000, "loss": 0.0, "lr": 1.9184869761616954e-05, "epoch": 255.44444444444446, "percentage": 57.48, "elapsed_time": "2:36:11", "remaining_time": "1:55:33", "throughput": 687.27, "total_tokens": 6440400} {"current_steps": 22995, "total_steps": 40000, "loss": 0.0, "lr": 1.9175322014426495e-05, "epoch": 255.5, "percentage": 57.49, "elapsed_time": "2:36:12", "remaining_time": "1:55:31", "throughput": 687.27, "total_tokens": 6441808} {"current_steps": 23000, "total_steps": 40000, "loss": 0.0, "lr": 1.9165775165474565e-05, "epoch": 255.55555555555554, "percentage": 57.5, "elapsed_time": "2:36:14", "remaining_time": "1:55:29", "throughput": 687.28, "total_tokens": 6443200} {"current_steps": 23000, "total_steps": 40000, "eval_loss": 0.36029791831970215, "epoch": 255.55555555555554, "percentage": 57.5, "elapsed_time": "2:36:16", "remaining_time": "1:55:30", "throughput": 687.19, "total_tokens": 6443200} {"current_steps": 23005, "total_steps": 40000, "loss": 0.0, "lr": 1.9156229216233434e-05, "epoch": 255.61111111111111, "percentage": 57.51, "elapsed_time": "2:36:19", "remaining_time": "1:55:29", "throughput": 687.1, "total_tokens": 6444592} {"current_steps": 23010, "total_steps": 40000, "loss": 0.0, "lr": 1.9146684168175184e-05, "epoch": 255.66666666666666, "percentage": 57.53, "elapsed_time": "2:36:21", "remaining_time": "1:55:27", "throughput": 687.1, "total_tokens": 6445936} {"current_steps": 23015, "total_steps": 40000, "loss": 0.0, "lr": 1.9137140022771796e-05, "epoch": 255.72222222222223, "percentage": 57.54, "elapsed_time": "2:36:23", "remaining_time": "1:55:24", "throughput": 687.11, "total_tokens": 6447392} {"current_steps": 23020, "total_steps": 40000, "loss": 0.0, "lr": 1.9127596781495103e-05, "epoch": 255.77777777777777, "percentage": 57.55, "elapsed_time": "2:36:25", "remaining_time": "1:55:22", "throughput": 687.12, "total_tokens": 6448784} {"current_steps": 23025, "total_steps": 40000, "loss": 0.0, "lr": 1.9118054445816767e-05, "epoch": 255.83333333333334, "percentage": 57.56, "elapsed_time": "2:36:27", "remaining_time": "1:55:20", "throughput": 687.12, "total_tokens": 6450176} {"current_steps": 23030, "total_steps": 40000, "loss": 0.0, "lr": 1.9108513017208356e-05, "epoch": 255.88888888888889, "percentage": 57.57, "elapsed_time": "2:36:29", "remaining_time": "1:55:18", "throughput": 687.13, "total_tokens": 6451600} {"current_steps": 23035, "total_steps": 40000, "loss": 0.0, "lr": 1.9098972497141287e-05, "epoch": 255.94444444444446, "percentage": 57.59, "elapsed_time": "2:36:31", "remaining_time": "1:55:16", "throughput": 687.14, "total_tokens": 6453008} {"current_steps": 23040, "total_steps": 40000, "loss": 0.0, "lr": 1.9089432887086806e-05, "epoch": 256.0, "percentage": 57.6, "elapsed_time": "2:36:33", "remaining_time": "1:55:14", "throughput": 687.13, "total_tokens": 6454416} {"current_steps": 23045, "total_steps": 40000, "loss": 0.0, "lr": 1.9079894188516056e-05, "epoch": 256.05555555555554, "percentage": 57.61, "elapsed_time": "2:36:35", "remaining_time": "1:55:12", "throughput": 687.12, "total_tokens": 6455824} {"current_steps": 23050, "total_steps": 40000, "loss": 0.0, "lr": 1.907035640290002e-05, "epoch": 256.1111111111111, "percentage": 57.63, "elapsed_time": "2:36:37", "remaining_time": "1:55:10", "throughput": 687.13, "total_tokens": 6457216} {"current_steps": 23055, "total_steps": 40000, "loss": 0.0, "lr": 1.9060819531709534e-05, "epoch": 256.1666666666667, "percentage": 57.64, "elapsed_time": "2:36:39", "remaining_time": "1:55:08", "throughput": 687.14, "total_tokens": 6458624} {"current_steps": 23060, "total_steps": 40000, "loss": 0.0, "lr": 1.9051283576415325e-05, "epoch": 256.22222222222223, "percentage": 57.65, "elapsed_time": "2:36:41", "remaining_time": "1:55:06", "throughput": 687.15, "total_tokens": 6460048} {"current_steps": 23065, "total_steps": 40000, "loss": 0.0, "lr": 1.904174853848793e-05, "epoch": 256.27777777777777, "percentage": 57.66, "elapsed_time": "2:36:43", "remaining_time": "1:55:04", "throughput": 687.17, "total_tokens": 6461536} {"current_steps": 23070, "total_steps": 40000, "loss": 0.0, "lr": 1.903221441939779e-05, "epoch": 256.3333333333333, "percentage": 57.67, "elapsed_time": "2:36:45", "remaining_time": "1:55:01", "throughput": 687.17, "total_tokens": 6462928} {"current_steps": 23075, "total_steps": 40000, "loss": 0.0, "lr": 1.9022681220615194e-05, "epoch": 256.3888888888889, "percentage": 57.69, "elapsed_time": "2:36:47", "remaining_time": "1:54:59", "throughput": 687.18, "total_tokens": 6464336} {"current_steps": 23080, "total_steps": 40000, "loss": 0.0, "lr": 1.9013148943610255e-05, "epoch": 256.44444444444446, "percentage": 57.7, "elapsed_time": "2:36:48", "remaining_time": "1:54:57", "throughput": 687.19, "total_tokens": 6465712} {"current_steps": 23085, "total_steps": 40000, "loss": 0.0, "lr": 1.9003617589852998e-05, "epoch": 256.5, "percentage": 57.71, "elapsed_time": "2:36:50", "remaining_time": "1:54:55", "throughput": 687.19, "total_tokens": 6467120} {"current_steps": 23090, "total_steps": 40000, "loss": 0.0, "lr": 1.899408716081326e-05, "epoch": 256.55555555555554, "percentage": 57.73, "elapsed_time": "2:36:52", "remaining_time": "1:54:53", "throughput": 687.19, "total_tokens": 6468464} {"current_steps": 23095, "total_steps": 40000, "loss": 0.0, "lr": 1.898455765796075e-05, "epoch": 256.6111111111111, "percentage": 57.74, "elapsed_time": "2:36:54", "remaining_time": "1:54:51", "throughput": 687.2, "total_tokens": 6469856} {"current_steps": 23100, "total_steps": 40000, "loss": 0.0, "lr": 1.8975029082765053e-05, "epoch": 256.6666666666667, "percentage": 57.75, "elapsed_time": "2:36:56", "remaining_time": "1:54:49", "throughput": 687.21, "total_tokens": 6471232} {"current_steps": 23105, "total_steps": 40000, "loss": 0.0, "lr": 1.8965501436695577e-05, "epoch": 256.72222222222223, "percentage": 57.76, "elapsed_time": "2:36:58", "remaining_time": "1:54:47", "throughput": 687.21, "total_tokens": 6472624} {"current_steps": 23110, "total_steps": 40000, "loss": 0.0, "lr": 1.895597472122161e-05, "epoch": 256.77777777777777, "percentage": 57.77, "elapsed_time": "2:37:00", "remaining_time": "1:54:45", "throughput": 687.22, "total_tokens": 6474016} {"current_steps": 23115, "total_steps": 40000, "loss": 0.0, "lr": 1.894644893781231e-05, "epoch": 256.8333333333333, "percentage": 57.79, "elapsed_time": "2:37:02", "remaining_time": "1:54:42", "throughput": 687.23, "total_tokens": 6475424} {"current_steps": 23120, "total_steps": 40000, "loss": 0.0, "lr": 1.893692408793665e-05, "epoch": 256.8888888888889, "percentage": 57.8, "elapsed_time": "2:37:04", "remaining_time": "1:54:40", "throughput": 687.24, "total_tokens": 6476848} {"current_steps": 23125, "total_steps": 40000, "loss": 0.0, "lr": 1.8927400173063493e-05, "epoch": 256.94444444444446, "percentage": 57.81, "elapsed_time": "2:37:06", "remaining_time": "1:54:38", "throughput": 687.25, "total_tokens": 6478272} {"current_steps": 23130, "total_steps": 40000, "loss": 0.0, "lr": 1.891787719466154e-05, "epoch": 257.0, "percentage": 57.83, "elapsed_time": "2:37:08", "remaining_time": "1:54:36", "throughput": 687.24, "total_tokens": 6479632} {"current_steps": 23135, "total_steps": 40000, "loss": 0.0, "lr": 1.8908355154199346e-05, "epoch": 257.05555555555554, "percentage": 57.84, "elapsed_time": "2:37:10", "remaining_time": "1:54:34", "throughput": 687.23, "total_tokens": 6481008} {"current_steps": 23140, "total_steps": 40000, "loss": 0.0, "lr": 1.8898834053145357e-05, "epoch": 257.1111111111111, "percentage": 57.85, "elapsed_time": "2:37:12", "remaining_time": "1:54:32", "throughput": 687.23, "total_tokens": 6482416} {"current_steps": 23145, "total_steps": 40000, "loss": 0.0, "lr": 1.8889313892967813e-05, "epoch": 257.1666666666667, "percentage": 57.86, "elapsed_time": "2:37:14", "remaining_time": "1:54:30", "throughput": 687.24, "total_tokens": 6483808} {"current_steps": 23150, "total_steps": 40000, "loss": 0.0, "lr": 1.8879794675134863e-05, "epoch": 257.22222222222223, "percentage": 57.88, "elapsed_time": "2:37:16", "remaining_time": "1:54:28", "throughput": 687.24, "total_tokens": 6485184} {"current_steps": 23155, "total_steps": 40000, "loss": 0.0, "lr": 1.8870276401114494e-05, "epoch": 257.27777777777777, "percentage": 57.89, "elapsed_time": "2:37:18", "remaining_time": "1:54:26", "throughput": 687.25, "total_tokens": 6486592} {"current_steps": 23160, "total_steps": 40000, "loss": 0.0, "lr": 1.886075907237453e-05, "epoch": 257.3333333333333, "percentage": 57.9, "elapsed_time": "2:37:20", "remaining_time": "1:54:24", "throughput": 687.26, "total_tokens": 6487984} {"current_steps": 23165, "total_steps": 40000, "loss": 0.0, "lr": 1.8851242690382672e-05, "epoch": 257.3888888888889, "percentage": 57.91, "elapsed_time": "2:37:22", "remaining_time": "1:54:22", "throughput": 687.27, "total_tokens": 6489392} {"current_steps": 23170, "total_steps": 40000, "loss": 0.0, "lr": 1.884172725660645e-05, "epoch": 257.44444444444446, "percentage": 57.93, "elapsed_time": "2:37:24", "remaining_time": "1:54:20", "throughput": 687.28, "total_tokens": 6490816} {"current_steps": 23175, "total_steps": 40000, "loss": 0.0, "lr": 1.8832212772513277e-05, "epoch": 257.5, "percentage": 57.94, "elapsed_time": "2:37:26", "remaining_time": "1:54:17", "throughput": 687.28, "total_tokens": 6492192} {"current_steps": 23180, "total_steps": 40000, "loss": 0.0, "lr": 1.8822699239570414e-05, "epoch": 257.55555555555554, "percentage": 57.95, "elapsed_time": "2:37:28", "remaining_time": "1:54:15", "throughput": 687.28, "total_tokens": 6493568} {"current_steps": 23185, "total_steps": 40000, "loss": 0.0, "lr": 1.8813186659244943e-05, "epoch": 257.6111111111111, "percentage": 57.96, "elapsed_time": "2:37:30", "remaining_time": "1:54:13", "throughput": 687.29, "total_tokens": 6494960} {"current_steps": 23190, "total_steps": 40000, "loss": 0.0, "lr": 1.880367503300385e-05, "epoch": 257.6666666666667, "percentage": 57.98, "elapsed_time": "2:37:32", "remaining_time": "1:54:11", "throughput": 687.29, "total_tokens": 6496304} {"current_steps": 23195, "total_steps": 40000, "loss": 0.0, "lr": 1.8794164362313927e-05, "epoch": 257.72222222222223, "percentage": 57.99, "elapsed_time": "2:37:33", "remaining_time": "1:54:09", "throughput": 687.29, "total_tokens": 6497664} {"current_steps": 23200, "total_steps": 40000, "loss": 0.0, "lr": 1.878465464864185e-05, "epoch": 257.77777777777777, "percentage": 58.0, "elapsed_time": "2:37:35", "remaining_time": "1:54:07", "throughput": 687.3, "total_tokens": 6499088} {"current_steps": 23200, "total_steps": 40000, "eval_loss": 0.3026605546474457, "epoch": 257.77777777777777, "percentage": 58.0, "elapsed_time": "2:37:37", "remaining_time": "1:54:08", "throughput": 687.21, "total_tokens": 6499088} {"current_steps": 23205, "total_steps": 40000, "loss": 0.0, "lr": 1.877514589345414e-05, "epoch": 257.8333333333333, "percentage": 58.01, "elapsed_time": "2:37:40", "remaining_time": "1:54:07", "throughput": 687.13, "total_tokens": 6500544} {"current_steps": 23210, "total_steps": 40000, "loss": 0.0, "lr": 1.876563809821715e-05, "epoch": 257.8888888888889, "percentage": 58.03, "elapsed_time": "2:37:42", "remaining_time": "1:54:05", "throughput": 687.13, "total_tokens": 6501968} {"current_steps": 23215, "total_steps": 40000, "loss": 0.0, "lr": 1.8756131264397106e-05, "epoch": 257.94444444444446, "percentage": 58.04, "elapsed_time": "2:37:44", "remaining_time": "1:54:02", "throughput": 687.13, "total_tokens": 6503296} {"current_steps": 23220, "total_steps": 40000, "loss": 0.0, "lr": 1.87466253934601e-05, "epoch": 258.0, "percentage": 58.05, "elapsed_time": "2:37:46", "remaining_time": "1:54:01", "throughput": 687.13, "total_tokens": 6504704} {"current_steps": 23225, "total_steps": 40000, "loss": 0.0, "lr": 1.8737120486872033e-05, "epoch": 258.05555555555554, "percentage": 58.06, "elapsed_time": "2:37:48", "remaining_time": "1:53:59", "throughput": 687.11, "total_tokens": 6506064} {"current_steps": 23230, "total_steps": 40000, "loss": 0.0, "lr": 1.8727616546098696e-05, "epoch": 258.1111111111111, "percentage": 58.07, "elapsed_time": "2:37:50", "remaining_time": "1:53:56", "throughput": 687.12, "total_tokens": 6507456} {"current_steps": 23235, "total_steps": 40000, "loss": 0.0, "lr": 1.8718113572605716e-05, "epoch": 258.1666666666667, "percentage": 58.09, "elapsed_time": "2:37:52", "remaining_time": "1:53:54", "throughput": 687.12, "total_tokens": 6508848} {"current_steps": 23240, "total_steps": 40000, "loss": 0.0, "lr": 1.8708611567858554e-05, "epoch": 258.22222222222223, "percentage": 58.1, "elapsed_time": "2:37:54", "remaining_time": "1:53:52", "throughput": 687.13, "total_tokens": 6510272} {"current_steps": 23245, "total_steps": 40000, "loss": 0.0, "lr": 1.8699110533322565e-05, "epoch": 258.27777777777777, "percentage": 58.11, "elapsed_time": "2:37:56", "remaining_time": "1:53:50", "throughput": 687.15, "total_tokens": 6511728} {"current_steps": 23250, "total_steps": 40000, "loss": 0.0, "lr": 1.8689610470462897e-05, "epoch": 258.3333333333333, "percentage": 58.13, "elapsed_time": "2:37:58", "remaining_time": "1:53:48", "throughput": 687.16, "total_tokens": 6513152} {"current_steps": 23255, "total_steps": 40000, "loss": 0.0, "lr": 1.8680111380744604e-05, "epoch": 258.3888888888889, "percentage": 58.14, "elapsed_time": "2:38:00", "remaining_time": "1:53:46", "throughput": 687.16, "total_tokens": 6514544} {"current_steps": 23260, "total_steps": 40000, "loss": 0.0, "lr": 1.8670613265632564e-05, "epoch": 258.44444444444446, "percentage": 58.15, "elapsed_time": "2:38:02", "remaining_time": "1:53:44", "throughput": 687.17, "total_tokens": 6515920} {"current_steps": 23265, "total_steps": 40000, "loss": 0.0, "lr": 1.866111612659149e-05, "epoch": 258.5, "percentage": 58.16, "elapsed_time": "2:38:04", "remaining_time": "1:53:42", "throughput": 687.17, "total_tokens": 6517280} {"current_steps": 23270, "total_steps": 40000, "loss": 0.0, "lr": 1.8651619965085967e-05, "epoch": 258.55555555555554, "percentage": 58.17, "elapsed_time": "2:38:06", "remaining_time": "1:53:40", "throughput": 687.18, "total_tokens": 6518720} {"current_steps": 23275, "total_steps": 40000, "loss": 0.0, "lr": 1.8642124782580433e-05, "epoch": 258.6111111111111, "percentage": 58.19, "elapsed_time": "2:38:08", "remaining_time": "1:53:37", "throughput": 687.19, "total_tokens": 6520144} {"current_steps": 23280, "total_steps": 40000, "loss": 0.0, "lr": 1.8632630580539144e-05, "epoch": 258.6666666666667, "percentage": 58.2, "elapsed_time": "2:38:10", "remaining_time": "1:53:35", "throughput": 687.2, "total_tokens": 6521552} {"current_steps": 23285, "total_steps": 40000, "loss": 0.0, "lr": 1.862313736042625e-05, "epoch": 258.72222222222223, "percentage": 58.21, "elapsed_time": "2:38:11", "remaining_time": "1:53:33", "throughput": 687.21, "total_tokens": 6522928} {"current_steps": 23290, "total_steps": 40000, "loss": 0.0, "lr": 1.8613645123705703e-05, "epoch": 258.77777777777777, "percentage": 58.23, "elapsed_time": "2:38:13", "remaining_time": "1:53:31", "throughput": 687.21, "total_tokens": 6524336} {"current_steps": 23295, "total_steps": 40000, "loss": 0.0, "lr": 1.8604153871841328e-05, "epoch": 258.8333333333333, "percentage": 58.24, "elapsed_time": "2:38:15", "remaining_time": "1:53:29", "throughput": 687.22, "total_tokens": 6525728} {"current_steps": 23300, "total_steps": 40000, "loss": 0.0, "lr": 1.859466360629682e-05, "epoch": 258.8888888888889, "percentage": 58.25, "elapsed_time": "2:38:17", "remaining_time": "1:53:27", "throughput": 687.23, "total_tokens": 6527120} {"current_steps": 23305, "total_steps": 40000, "loss": 0.0, "lr": 1.8585174328535666e-05, "epoch": 258.94444444444446, "percentage": 58.26, "elapsed_time": "2:38:19", "remaining_time": "1:53:25", "throughput": 687.23, "total_tokens": 6528496} {"current_steps": 23310, "total_steps": 40000, "loss": 0.0, "lr": 1.857568604002124e-05, "epoch": 259.0, "percentage": 58.27, "elapsed_time": "2:38:21", "remaining_time": "1:53:23", "throughput": 687.23, "total_tokens": 6529920} {"current_steps": 23315, "total_steps": 40000, "loss": 0.0, "lr": 1.8566198742216774e-05, "epoch": 259.05555555555554, "percentage": 58.29, "elapsed_time": "2:38:24", "remaining_time": "1:53:21", "throughput": 687.21, "total_tokens": 6531264} {"current_steps": 23320, "total_steps": 40000, "loss": 0.0, "lr": 1.85567124365853e-05, "epoch": 259.1111111111111, "percentage": 58.3, "elapsed_time": "2:38:25", "remaining_time": "1:53:19", "throughput": 687.22, "total_tokens": 6532688} {"current_steps": 23325, "total_steps": 40000, "loss": 0.0, "lr": 1.854722712458975e-05, "epoch": 259.1666666666667, "percentage": 58.31, "elapsed_time": "2:38:27", "remaining_time": "1:53:17", "throughput": 687.23, "total_tokens": 6534112} {"current_steps": 23330, "total_steps": 40000, "loss": 0.0, "lr": 1.853774280769286e-05, "epoch": 259.22222222222223, "percentage": 58.33, "elapsed_time": "2:38:29", "remaining_time": "1:53:15", "throughput": 687.24, "total_tokens": 6535536} {"current_steps": 23335, "total_steps": 40000, "loss": 0.0, "lr": 1.852825948735724e-05, "epoch": 259.27777777777777, "percentage": 58.34, "elapsed_time": "2:38:31", "remaining_time": "1:53:12", "throughput": 687.25, "total_tokens": 6536944} {"current_steps": 23340, "total_steps": 40000, "loss": 0.0, "lr": 1.851877716504534e-05, "epoch": 259.3333333333333, "percentage": 58.35, "elapsed_time": "2:38:33", "remaining_time": "1:53:10", "throughput": 687.25, "total_tokens": 6538320} {"current_steps": 23345, "total_steps": 40000, "loss": 0.0, "lr": 1.8509295842219448e-05, "epoch": 259.3888888888889, "percentage": 58.36, "elapsed_time": "2:38:35", "remaining_time": "1:53:08", "throughput": 687.26, "total_tokens": 6539728} {"current_steps": 23350, "total_steps": 40000, "loss": 0.0, "lr": 1.8499815520341697e-05, "epoch": 259.44444444444446, "percentage": 58.38, "elapsed_time": "2:38:37", "remaining_time": "1:53:06", "throughput": 687.27, "total_tokens": 6541136} {"current_steps": 23355, "total_steps": 40000, "loss": 0.0, "lr": 1.8490336200874094e-05, "epoch": 259.5, "percentage": 58.39, "elapsed_time": "2:38:39", "remaining_time": "1:53:04", "throughput": 687.28, "total_tokens": 6542560} {"current_steps": 23360, "total_steps": 40000, "loss": 0.0, "lr": 1.848085788527844e-05, "epoch": 259.55555555555554, "percentage": 58.4, "elapsed_time": "2:38:41", "remaining_time": "1:53:02", "throughput": 687.28, "total_tokens": 6543968} {"current_steps": 23365, "total_steps": 40000, "loss": 0.0, "lr": 1.847138057501644e-05, "epoch": 259.6111111111111, "percentage": 58.41, "elapsed_time": "2:38:43", "remaining_time": "1:53:00", "throughput": 687.29, "total_tokens": 6545376} {"current_steps": 23370, "total_steps": 40000, "loss": 0.0, "lr": 1.8461904271549582e-05, "epoch": 259.6666666666667, "percentage": 58.43, "elapsed_time": "2:38:45", "remaining_time": "1:52:58", "throughput": 687.3, "total_tokens": 6546784} {"current_steps": 23375, "total_steps": 40000, "loss": 0.0, "lr": 1.845242897633926e-05, "epoch": 259.72222222222223, "percentage": 58.44, "elapsed_time": "2:38:47", "remaining_time": "1:52:56", "throughput": 687.31, "total_tokens": 6548208} {"current_steps": 23380, "total_steps": 40000, "loss": 0.0, "lr": 1.844295469084667e-05, "epoch": 259.77777777777777, "percentage": 58.45, "elapsed_time": "2:38:49", "remaining_time": "1:52:54", "throughput": 687.31, "total_tokens": 6549584} {"current_steps": 23385, "total_steps": 40000, "loss": 0.0, "lr": 1.843348141653286e-05, "epoch": 259.8333333333333, "percentage": 58.46, "elapsed_time": "2:38:51", "remaining_time": "1:52:51", "throughput": 687.31, "total_tokens": 6550944} {"current_steps": 23390, "total_steps": 40000, "loss": 0.0, "lr": 1.842400915485874e-05, "epoch": 259.8888888888889, "percentage": 58.48, "elapsed_time": "2:38:53", "remaining_time": "1:52:49", "throughput": 687.32, "total_tokens": 6552336} {"current_steps": 23395, "total_steps": 40000, "loss": 0.0, "lr": 1.8414537907285053e-05, "epoch": 259.94444444444446, "percentage": 58.49, "elapsed_time": "2:38:55", "remaining_time": "1:52:47", "throughput": 687.33, "total_tokens": 6553744} {"current_steps": 23400, "total_steps": 40000, "loss": 0.0, "lr": 1.840506767527237e-05, "epoch": 260.0, "percentage": 58.5, "elapsed_time": "2:38:57", "remaining_time": "1:52:45", "throughput": 687.33, "total_tokens": 6555184} {"current_steps": 23400, "total_steps": 40000, "eval_loss": 0.34345296025276184, "epoch": 260.0, "percentage": 58.5, "elapsed_time": "2:38:58", "remaining_time": "1:52:46", "throughput": 687.24, "total_tokens": 6555184} {"current_steps": 23405, "total_steps": 40000, "loss": 0.0, "lr": 1.8395598460281137e-05, "epoch": 260.05555555555554, "percentage": 58.51, "elapsed_time": "2:39:02", "remaining_time": "1:52:45", "throughput": 687.13, "total_tokens": 6556624} {"current_steps": 23410, "total_steps": 40000, "loss": 0.0, "lr": 1.838613026377161e-05, "epoch": 260.1111111111111, "percentage": 58.53, "elapsed_time": "2:39:03", "remaining_time": "1:52:43", "throughput": 687.14, "total_tokens": 6558080} {"current_steps": 23415, "total_steps": 40000, "loss": 0.0, "lr": 1.8376663087203917e-05, "epoch": 260.1666666666667, "percentage": 58.54, "elapsed_time": "2:39:05", "remaining_time": "1:52:41", "throughput": 687.15, "total_tokens": 6559472} {"current_steps": 23420, "total_steps": 40000, "loss": 0.0, "lr": 1.8367196932038014e-05, "epoch": 260.22222222222223, "percentage": 58.55, "elapsed_time": "2:39:07", "remaining_time": "1:52:39", "throughput": 687.16, "total_tokens": 6560912} {"current_steps": 23425, "total_steps": 40000, "loss": 0.0, "lr": 1.8357731799733686e-05, "epoch": 260.27777777777777, "percentage": 58.56, "elapsed_time": "2:39:09", "remaining_time": "1:52:37", "throughput": 687.16, "total_tokens": 6562272} {"current_steps": 23430, "total_steps": 40000, "loss": 0.0, "lr": 1.8348267691750586e-05, "epoch": 260.3333333333333, "percentage": 58.58, "elapsed_time": "2:39:11", "remaining_time": "1:52:35", "throughput": 687.17, "total_tokens": 6563696} {"current_steps": 23435, "total_steps": 40000, "loss": 0.0, "lr": 1.833880460954821e-05, "epoch": 260.3888888888889, "percentage": 58.59, "elapsed_time": "2:39:13", "remaining_time": "1:52:33", "throughput": 687.18, "total_tokens": 6565088} {"current_steps": 23440, "total_steps": 40000, "loss": 0.0, "lr": 1.8329342554585866e-05, "epoch": 260.44444444444446, "percentage": 58.6, "elapsed_time": "2:39:15", "remaining_time": "1:52:30", "throughput": 687.18, "total_tokens": 6566464} {"current_steps": 23445, "total_steps": 40000, "loss": 0.0, "lr": 1.8319881528322735e-05, "epoch": 260.5, "percentage": 58.61, "elapsed_time": "2:39:17", "remaining_time": "1:52:28", "throughput": 687.19, "total_tokens": 6567840} {"current_steps": 23450, "total_steps": 40000, "loss": 0.0, "lr": 1.8310421532217815e-05, "epoch": 260.55555555555554, "percentage": 58.63, "elapsed_time": "2:39:19", "remaining_time": "1:52:26", "throughput": 687.2, "total_tokens": 6569248} {"current_steps": 23455, "total_steps": 40000, "loss": 0.0, "lr": 1.8300962567729958e-05, "epoch": 260.6111111111111, "percentage": 58.64, "elapsed_time": "2:39:21", "remaining_time": "1:52:24", "throughput": 687.2, "total_tokens": 6570672} {"current_steps": 23460, "total_steps": 40000, "loss": 0.0, "lr": 1.8291504636317866e-05, "epoch": 260.6666666666667, "percentage": 58.65, "elapsed_time": "2:39:23", "remaining_time": "1:52:22", "throughput": 687.21, "total_tokens": 6572048} {"current_steps": 23465, "total_steps": 40000, "loss": 0.0, "lr": 1.8282047739440055e-05, "epoch": 260.72222222222223, "percentage": 58.66, "elapsed_time": "2:39:25", "remaining_time": "1:52:20", "throughput": 687.22, "total_tokens": 6573472} {"current_steps": 23470, "total_steps": 40000, "loss": 0.0, "lr": 1.8272591878554903e-05, "epoch": 260.77777777777777, "percentage": 58.67, "elapsed_time": "2:39:27", "remaining_time": "1:52:18", "throughput": 687.23, "total_tokens": 6574864} {"current_steps": 23475, "total_steps": 40000, "loss": 0.0, "lr": 1.8263137055120638e-05, "epoch": 260.8333333333333, "percentage": 58.69, "elapsed_time": "2:39:29", "remaining_time": "1:52:16", "throughput": 687.23, "total_tokens": 6576272} {"current_steps": 23480, "total_steps": 40000, "loss": 0.0, "lr": 1.8253683270595295e-05, "epoch": 260.8888888888889, "percentage": 58.7, "elapsed_time": "2:39:31", "remaining_time": "1:52:14", "throughput": 687.24, "total_tokens": 6577680} {"current_steps": 23485, "total_steps": 40000, "loss": 0.0, "lr": 1.824423052643677e-05, "epoch": 260.94444444444446, "percentage": 58.71, "elapsed_time": "2:39:33", "remaining_time": "1:52:11", "throughput": 687.24, "total_tokens": 6579040} {"current_steps": 23490, "total_steps": 40000, "loss": 0.0, "lr": 1.82347788241028e-05, "epoch": 261.0, "percentage": 58.73, "elapsed_time": "2:39:35", "remaining_time": "1:52:09", "throughput": 687.24, "total_tokens": 6580432} {"current_steps": 23495, "total_steps": 40000, "loss": 0.0, "lr": 1.8225328165050942e-05, "epoch": 261.05555555555554, "percentage": 58.74, "elapsed_time": "2:39:37", "remaining_time": "1:52:08", "throughput": 687.22, "total_tokens": 6581808} {"current_steps": 23500, "total_steps": 40000, "loss": 0.0, "lr": 1.821587855073863e-05, "epoch": 261.1111111111111, "percentage": 58.75, "elapsed_time": "2:39:39", "remaining_time": "1:52:05", "throughput": 687.23, "total_tokens": 6583232} {"current_steps": 23505, "total_steps": 40000, "loss": 0.0, "lr": 1.8206429982623086e-05, "epoch": 261.1666666666667, "percentage": 58.76, "elapsed_time": "2:39:41", "remaining_time": "1:52:03", "throughput": 687.24, "total_tokens": 6584608} {"current_steps": 23510, "total_steps": 40000, "loss": 0.0, "lr": 1.8196982462161416e-05, "epoch": 261.22222222222223, "percentage": 58.77, "elapsed_time": "2:39:43", "remaining_time": "1:52:01", "throughput": 687.24, "total_tokens": 6586000} {"current_steps": 23515, "total_steps": 40000, "loss": 0.0, "lr": 1.818753599081055e-05, "epoch": 261.27777777777777, "percentage": 58.79, "elapsed_time": "2:39:45", "remaining_time": "1:51:59", "throughput": 687.25, "total_tokens": 6587408} {"current_steps": 23520, "total_steps": 40000, "loss": 0.0, "lr": 1.817809057002724e-05, "epoch": 261.3333333333333, "percentage": 58.8, "elapsed_time": "2:39:47", "remaining_time": "1:51:57", "throughput": 687.26, "total_tokens": 6588864} {"current_steps": 23525, "total_steps": 40000, "loss": 0.0, "lr": 1.8168646201268096e-05, "epoch": 261.3888888888889, "percentage": 58.81, "elapsed_time": "2:39:49", "remaining_time": "1:51:55", "throughput": 687.27, "total_tokens": 6590272} {"current_steps": 23530, "total_steps": 40000, "loss": 0.0, "lr": 1.8159202885989557e-05, "epoch": 261.44444444444446, "percentage": 58.83, "elapsed_time": "2:39:50", "remaining_time": "1:51:53", "throughput": 687.27, "total_tokens": 6591632} {"current_steps": 23535, "total_steps": 40000, "loss": 0.0, "lr": 1.814976062564789e-05, "epoch": 261.5, "percentage": 58.84, "elapsed_time": "2:39:52", "remaining_time": "1:51:51", "throughput": 687.28, "total_tokens": 6593008} {"current_steps": 23540, "total_steps": 40000, "loss": 0.0, "lr": 1.8140319421699234e-05, "epoch": 261.55555555555554, "percentage": 58.85, "elapsed_time": "2:39:54", "remaining_time": "1:51:49", "throughput": 687.28, "total_tokens": 6594384} {"current_steps": 23545, "total_steps": 40000, "loss": 0.0, "lr": 1.8130879275599515e-05, "epoch": 261.6111111111111, "percentage": 58.86, "elapsed_time": "2:39:56", "remaining_time": "1:51:46", "throughput": 687.29, "total_tokens": 6595808} {"current_steps": 23550, "total_steps": 40000, "loss": 0.0, "lr": 1.8121440188804544e-05, "epoch": 261.6666666666667, "percentage": 58.88, "elapsed_time": "2:39:58", "remaining_time": "1:51:44", "throughput": 687.31, "total_tokens": 6597264} {"current_steps": 23555, "total_steps": 40000, "loss": 0.0, "lr": 1.811200216276993e-05, "epoch": 261.72222222222223, "percentage": 58.89, "elapsed_time": "2:40:00", "remaining_time": "1:51:42", "throughput": 687.31, "total_tokens": 6598640} {"current_steps": 23560, "total_steps": 40000, "loss": 0.0, "lr": 1.810256519895115e-05, "epoch": 261.77777777777777, "percentage": 58.9, "elapsed_time": "2:40:02", "remaining_time": "1:51:40", "throughput": 687.32, "total_tokens": 6600064} {"current_steps": 23565, "total_steps": 40000, "loss": 0.0, "lr": 1.8093129298803494e-05, "epoch": 261.8333333333333, "percentage": 58.91, "elapsed_time": "2:40:04", "remaining_time": "1:51:38", "throughput": 687.32, "total_tokens": 6601440} {"current_steps": 23570, "total_steps": 40000, "loss": 0.0, "lr": 1.808369446378209e-05, "epoch": 261.8888888888889, "percentage": 58.93, "elapsed_time": "2:40:06", "remaining_time": "1:51:36", "throughput": 687.33, "total_tokens": 6602848} {"current_steps": 23575, "total_steps": 40000, "loss": 0.0, "lr": 1.8074260695341914e-05, "epoch": 261.94444444444446, "percentage": 58.94, "elapsed_time": "2:40:08", "remaining_time": "1:51:34", "throughput": 687.34, "total_tokens": 6604240} {"current_steps": 23580, "total_steps": 40000, "loss": 0.0, "lr": 1.8064827994937782e-05, "epoch": 262.0, "percentage": 58.95, "elapsed_time": "2:40:10", "remaining_time": "1:51:32", "throughput": 687.33, "total_tokens": 6605632} {"current_steps": 23585, "total_steps": 40000, "loss": 0.0, "lr": 1.8055396364024317e-05, "epoch": 262.05555555555554, "percentage": 58.96, "elapsed_time": "2:40:12", "remaining_time": "1:51:30", "throughput": 687.32, "total_tokens": 6606992} {"current_steps": 23590, "total_steps": 40000, "loss": 0.0, "lr": 1.804596580405601e-05, "epoch": 262.1111111111111, "percentage": 58.98, "elapsed_time": "2:40:14", "remaining_time": "1:51:28", "throughput": 687.33, "total_tokens": 6608416} {"current_steps": 23595, "total_steps": 40000, "loss": 0.0, "lr": 1.8036536316487174e-05, "epoch": 262.1666666666667, "percentage": 58.99, "elapsed_time": "2:40:16", "remaining_time": "1:51:26", "throughput": 687.34, "total_tokens": 6609872} {"current_steps": 23600, "total_steps": 40000, "loss": 0.0, "lr": 1.802710790277193e-05, "epoch": 262.22222222222223, "percentage": 59.0, "elapsed_time": "2:40:18", "remaining_time": "1:51:24", "throughput": 687.35, "total_tokens": 6611312} {"current_steps": 23600, "total_steps": 40000, "eval_loss": 0.3032988905906677, "epoch": 262.22222222222223, "percentage": 59.0, "elapsed_time": "2:40:19", "remaining_time": "1:51:24", "throughput": 687.26, "total_tokens": 6611312} {"current_steps": 23605, "total_steps": 40000, "loss": 0.0, "lr": 1.801768056436429e-05, "epoch": 262.27777777777777, "percentage": 59.01, "elapsed_time": "2:40:23", "remaining_time": "1:51:23", "throughput": 687.17, "total_tokens": 6612640} {"current_steps": 23610, "total_steps": 40000, "loss": 0.0, "lr": 1.8008254302718035e-05, "epoch": 262.3333333333333, "percentage": 59.03, "elapsed_time": "2:40:25", "remaining_time": "1:51:21", "throughput": 687.17, "total_tokens": 6614064} {"current_steps": 23615, "total_steps": 40000, "loss": 0.0, "lr": 1.7998829119286837e-05, "epoch": 262.3888888888889, "percentage": 59.04, "elapsed_time": "2:40:26", "remaining_time": "1:51:19", "throughput": 687.18, "total_tokens": 6615440} {"current_steps": 23620, "total_steps": 40000, "loss": 0.0, "lr": 1.798940501552418e-05, "epoch": 262.44444444444446, "percentage": 59.05, "elapsed_time": "2:40:28", "remaining_time": "1:51:17", "throughput": 687.18, "total_tokens": 6616816} {"current_steps": 23625, "total_steps": 40000, "loss": 0.0, "lr": 1.797998199288336e-05, "epoch": 262.5, "percentage": 59.06, "elapsed_time": "2:40:30", "remaining_time": "1:51:15", "throughput": 687.18, "total_tokens": 6618160} {"current_steps": 23630, "total_steps": 40000, "loss": 0.0, "lr": 1.7970560052817543e-05, "epoch": 262.55555555555554, "percentage": 59.08, "elapsed_time": "2:40:32", "remaining_time": "1:51:13", "throughput": 687.19, "total_tokens": 6619600} {"current_steps": 23635, "total_steps": 40000, "loss": 0.0, "lr": 1.7961139196779702e-05, "epoch": 262.6111111111111, "percentage": 59.09, "elapsed_time": "2:40:34", "remaining_time": "1:51:11", "throughput": 687.2, "total_tokens": 6621024} {"current_steps": 23640, "total_steps": 40000, "loss": 0.0, "lr": 1.7951719426222647e-05, "epoch": 262.6666666666667, "percentage": 59.1, "elapsed_time": "2:40:36", "remaining_time": "1:51:09", "throughput": 687.21, "total_tokens": 6622448} {"current_steps": 23645, "total_steps": 40000, "loss": 0.0, "lr": 1.794230074259904e-05, "epoch": 262.72222222222223, "percentage": 59.11, "elapsed_time": "2:40:38", "remaining_time": "1:51:06", "throughput": 687.22, "total_tokens": 6623872} {"current_steps": 23650, "total_steps": 40000, "loss": 0.0, "lr": 1.7932883147361336e-05, "epoch": 262.77777777777777, "percentage": 59.13, "elapsed_time": "2:40:40", "remaining_time": "1:51:04", "throughput": 687.23, "total_tokens": 6625264} {"current_steps": 23655, "total_steps": 40000, "loss": 0.0, "lr": 1.7923466641961865e-05, "epoch": 262.8333333333333, "percentage": 59.14, "elapsed_time": "2:40:42", "remaining_time": "1:51:02", "throughput": 687.23, "total_tokens": 6626640} {"current_steps": 23660, "total_steps": 40000, "loss": 0.0, "lr": 1.791405122785278e-05, "epoch": 262.8888888888889, "percentage": 59.15, "elapsed_time": "2:40:44", "remaining_time": "1:51:00", "throughput": 687.24, "total_tokens": 6628096} {"current_steps": 23665, "total_steps": 40000, "loss": 0.0, "lr": 1.7904636906486037e-05, "epoch": 262.94444444444446, "percentage": 59.16, "elapsed_time": "2:40:46", "remaining_time": "1:50:58", "throughput": 687.24, "total_tokens": 6629440} {"current_steps": 23670, "total_steps": 40000, "loss": 0.0, "lr": 1.7895223679313448e-05, "epoch": 263.0, "percentage": 59.17, "elapsed_time": "2:40:48", "remaining_time": "1:50:56", "throughput": 687.23, "total_tokens": 6630800} {"current_steps": 23675, "total_steps": 40000, "loss": 0.0, "lr": 1.7885811547786653e-05, "epoch": 263.05555555555554, "percentage": 59.19, "elapsed_time": "2:40:50", "remaining_time": "1:50:54", "throughput": 687.22, "total_tokens": 6632192} {"current_steps": 23680, "total_steps": 40000, "loss": 0.0, "lr": 1.7876400513357115e-05, "epoch": 263.1111111111111, "percentage": 59.2, "elapsed_time": "2:40:52", "remaining_time": "1:50:52", "throughput": 687.22, "total_tokens": 6633536} {"current_steps": 23685, "total_steps": 40000, "loss": 0.0, "lr": 1.7866990577476146e-05, "epoch": 263.1666666666667, "percentage": 59.21, "elapsed_time": "2:40:54", "remaining_time": "1:50:50", "throughput": 687.23, "total_tokens": 6634928} {"current_steps": 23690, "total_steps": 40000, "loss": 0.0, "lr": 1.7857581741594863e-05, "epoch": 263.22222222222223, "percentage": 59.23, "elapsed_time": "2:40:56", "remaining_time": "1:50:48", "throughput": 687.24, "total_tokens": 6636336} {"current_steps": 23695, "total_steps": 40000, "loss": 0.0, "lr": 1.7848174007164237e-05, "epoch": 263.27777777777777, "percentage": 59.24, "elapsed_time": "2:40:58", "remaining_time": "1:50:46", "throughput": 687.24, "total_tokens": 6637680} {"current_steps": 23700, "total_steps": 40000, "loss": 0.0, "lr": 1.7838767375635052e-05, "epoch": 263.3333333333333, "percentage": 59.25, "elapsed_time": "2:41:00", "remaining_time": "1:50:44", "throughput": 687.25, "total_tokens": 6639152} {"current_steps": 23705, "total_steps": 40000, "loss": 0.0, "lr": 1.782936184845793e-05, "epoch": 263.3888888888889, "percentage": 59.26, "elapsed_time": "2:41:02", "remaining_time": "1:50:41", "throughput": 687.26, "total_tokens": 6640560} {"current_steps": 23710, "total_steps": 40000, "loss": 0.0, "lr": 1.7819957427083334e-05, "epoch": 263.44444444444446, "percentage": 59.27, "elapsed_time": "2:41:04", "remaining_time": "1:50:39", "throughput": 687.26, "total_tokens": 6641904} {"current_steps": 23715, "total_steps": 40000, "loss": 0.0, "lr": 1.7810554112961516e-05, "epoch": 263.5, "percentage": 59.29, "elapsed_time": "2:41:06", "remaining_time": "1:50:37", "throughput": 687.27, "total_tokens": 6643328} {"current_steps": 23720, "total_steps": 40000, "loss": 0.0, "lr": 1.7801151907542607e-05, "epoch": 263.55555555555554, "percentage": 59.3, "elapsed_time": "2:41:08", "remaining_time": "1:50:35", "throughput": 687.28, "total_tokens": 6644720} {"current_steps": 23725, "total_steps": 40000, "loss": 0.0, "lr": 1.7791750812276547e-05, "epoch": 263.6111111111111, "percentage": 59.31, "elapsed_time": "2:41:10", "remaining_time": "1:50:33", "throughput": 687.29, "total_tokens": 6646128} {"current_steps": 23730, "total_steps": 40000, "loss": 0.0, "lr": 1.778235082861309e-05, "epoch": 263.6666666666667, "percentage": 59.33, "elapsed_time": "2:41:12", "remaining_time": "1:50:31", "throughput": 687.29, "total_tokens": 6647520} {"current_steps": 23735, "total_steps": 40000, "loss": 0.0, "lr": 1.777295195800184e-05, "epoch": 263.72222222222223, "percentage": 59.34, "elapsed_time": "2:41:13", "remaining_time": "1:50:29", "throughput": 687.3, "total_tokens": 6648896} {"current_steps": 23740, "total_steps": 40000, "loss": 0.0, "lr": 1.7763554201892215e-05, "epoch": 263.77777777777777, "percentage": 59.35, "elapsed_time": "2:41:15", "remaining_time": "1:50:27", "throughput": 687.3, "total_tokens": 6650304} {"current_steps": 23745, "total_steps": 40000, "loss": 0.0, "lr": 1.7754157561733476e-05, "epoch": 263.8333333333333, "percentage": 59.36, "elapsed_time": "2:41:17", "remaining_time": "1:50:25", "throughput": 687.31, "total_tokens": 6651680} {"current_steps": 23750, "total_steps": 40000, "loss": 0.0, "lr": 1.7744762038974702e-05, "epoch": 263.8888888888889, "percentage": 59.38, "elapsed_time": "2:41:19", "remaining_time": "1:50:23", "throughput": 687.31, "total_tokens": 6653056} {"current_steps": 23755, "total_steps": 40000, "loss": 0.0, "lr": 1.7735367635064788e-05, "epoch": 263.94444444444446, "percentage": 59.39, "elapsed_time": "2:41:21", "remaining_time": "1:50:20", "throughput": 687.33, "total_tokens": 6654544} {"current_steps": 23760, "total_steps": 40000, "loss": 0.0, "lr": 1.7725974351452474e-05, "epoch": 264.0, "percentage": 59.4, "elapsed_time": "2:41:23", "remaining_time": "1:50:18", "throughput": 687.33, "total_tokens": 6655968} {"current_steps": 23765, "total_steps": 40000, "loss": 0.0, "lr": 1.771658218958634e-05, "epoch": 264.05555555555554, "percentage": 59.41, "elapsed_time": "2:41:26", "remaining_time": "1:50:17", "throughput": 687.32, "total_tokens": 6657376} {"current_steps": 23770, "total_steps": 40000, "loss": 0.0, "lr": 1.770719115091475e-05, "epoch": 264.1111111111111, "percentage": 59.42, "elapsed_time": "2:41:28", "remaining_time": "1:50:14", "throughput": 687.32, "total_tokens": 6658800} {"current_steps": 23775, "total_steps": 40000, "loss": 0.0, "lr": 1.7697801236885935e-05, "epoch": 264.1666666666667, "percentage": 59.44, "elapsed_time": "2:41:29", "remaining_time": "1:50:12", "throughput": 687.33, "total_tokens": 6660192} {"current_steps": 23780, "total_steps": 40000, "loss": 0.0, "lr": 1.7688412448947944e-05, "epoch": 264.22222222222223, "percentage": 59.45, "elapsed_time": "2:41:31", "remaining_time": "1:50:10", "throughput": 687.33, "total_tokens": 6661552} {"current_steps": 23785, "total_steps": 40000, "loss": 0.0, "lr": 1.767902478854862e-05, "epoch": 264.27777777777777, "percentage": 59.46, "elapsed_time": "2:41:33", "remaining_time": "1:50:08", "throughput": 687.34, "total_tokens": 6662928} {"current_steps": 23790, "total_steps": 40000, "loss": 0.0, "lr": 1.766963825713569e-05, "epoch": 264.3333333333333, "percentage": 59.48, "elapsed_time": "2:41:35", "remaining_time": "1:50:06", "throughput": 687.34, "total_tokens": 6664304} {"current_steps": 23795, "total_steps": 40000, "loss": 0.0, "lr": 1.766025285615665e-05, "epoch": 264.3888888888889, "percentage": 59.49, "elapsed_time": "2:41:37", "remaining_time": "1:50:04", "throughput": 687.35, "total_tokens": 6665712} {"current_steps": 23800, "total_steps": 40000, "loss": 0.0, "lr": 1.7650868587058854e-05, "epoch": 264.44444444444446, "percentage": 59.5, "elapsed_time": "2:41:39", "remaining_time": "1:50:02", "throughput": 687.35, "total_tokens": 6667104} {"current_steps": 23800, "total_steps": 40000, "eval_loss": 0.307365745306015, "epoch": 264.44444444444446, "percentage": 59.5, "elapsed_time": "2:41:40", "remaining_time": "1:50:03", "throughput": 687.26, "total_tokens": 6667104} {"current_steps": 23805, "total_steps": 40000, "loss": 0.0, "lr": 1.7641485451289484e-05, "epoch": 264.5, "percentage": 59.51, "elapsed_time": "2:41:44", "remaining_time": "1:50:02", "throughput": 687.15, "total_tokens": 6668528} {"current_steps": 23810, "total_steps": 40000, "loss": 0.0, "lr": 1.7632103450295534e-05, "epoch": 264.55555555555554, "percentage": 59.52, "elapsed_time": "2:41:46", "remaining_time": "1:50:00", "throughput": 687.15, "total_tokens": 6669904} {"current_steps": 23815, "total_steps": 40000, "loss": 0.0, "lr": 1.762272258552381e-05, "epoch": 264.6111111111111, "percentage": 59.54, "elapsed_time": "2:41:48", "remaining_time": "1:49:58", "throughput": 687.16, "total_tokens": 6671328} {"current_steps": 23820, "total_steps": 40000, "loss": 0.0, "lr": 1.7613342858420988e-05, "epoch": 264.6666666666667, "percentage": 59.55, "elapsed_time": "2:41:50", "remaining_time": "1:49:55", "throughput": 687.16, "total_tokens": 6672704} {"current_steps": 23825, "total_steps": 40000, "loss": 0.0, "lr": 1.760396427043351e-05, "epoch": 264.72222222222223, "percentage": 59.56, "elapsed_time": "2:41:52", "remaining_time": "1:49:54", "throughput": 687.15, "total_tokens": 6674112} {"current_steps": 23830, "total_steps": 40000, "loss": 0.0, "lr": 1.7594586823007696e-05, "epoch": 264.77777777777777, "percentage": 59.58, "elapsed_time": "2:41:54", "remaining_time": "1:49:51", "throughput": 687.16, "total_tokens": 6675504} {"current_steps": 23835, "total_steps": 40000, "loss": 0.0, "lr": 1.7585210517589646e-05, "epoch": 264.8333333333333, "percentage": 59.59, "elapsed_time": "2:41:56", "remaining_time": "1:49:49", "throughput": 687.17, "total_tokens": 6676944} {"current_steps": 23840, "total_steps": 40000, "loss": 0.0, "lr": 1.7575835355625314e-05, "epoch": 264.8888888888889, "percentage": 59.6, "elapsed_time": "2:41:58", "remaining_time": "1:49:47", "throughput": 687.18, "total_tokens": 6678416} {"current_steps": 23845, "total_steps": 40000, "loss": 0.0, "lr": 1.756646133856048e-05, "epoch": 264.94444444444446, "percentage": 59.61, "elapsed_time": "2:42:00", "remaining_time": "1:49:45", "throughput": 687.18, "total_tokens": 6679760} {"current_steps": 23850, "total_steps": 40000, "loss": 0.0, "lr": 1.7557088467840714e-05, "epoch": 265.0, "percentage": 59.62, "elapsed_time": "2:42:02", "remaining_time": "1:49:43", "throughput": 687.18, "total_tokens": 6681136} {"current_steps": 23855, "total_steps": 40000, "loss": 0.0, "lr": 1.7547716744911438e-05, "epoch": 265.05555555555554, "percentage": 59.64, "elapsed_time": "2:42:04", "remaining_time": "1:49:41", "throughput": 687.16, "total_tokens": 6682496} {"current_steps": 23860, "total_steps": 40000, "loss": 0.0, "lr": 1.7538346171217902e-05, "epoch": 265.1111111111111, "percentage": 59.65, "elapsed_time": "2:42:06", "remaining_time": "1:49:39", "throughput": 687.16, "total_tokens": 6683872} {"current_steps": 23865, "total_steps": 40000, "loss": 0.0, "lr": 1.7528976748205146e-05, "epoch": 265.1666666666667, "percentage": 59.66, "elapsed_time": "2:42:08", "remaining_time": "1:49:37", "throughput": 687.17, "total_tokens": 6685280} {"current_steps": 23870, "total_steps": 40000, "loss": 0.0, "lr": 1.751960847731807e-05, "epoch": 265.22222222222223, "percentage": 59.67, "elapsed_time": "2:42:10", "remaining_time": "1:49:35", "throughput": 687.18, "total_tokens": 6686672} {"current_steps": 23875, "total_steps": 40000, "loss": 0.0, "lr": 1.7510241360001362e-05, "epoch": 265.27777777777777, "percentage": 59.69, "elapsed_time": "2:42:12", "remaining_time": "1:49:33", "throughput": 687.19, "total_tokens": 6688112} {"current_steps": 23880, "total_steps": 40000, "loss": 0.0, "lr": 1.7500875397699562e-05, "epoch": 265.3333333333333, "percentage": 59.7, "elapsed_time": "2:42:14", "remaining_time": "1:49:31", "throughput": 687.2, "total_tokens": 6689552} {"current_steps": 23885, "total_steps": 40000, "loss": 0.0, "lr": 1.7491510591857015e-05, "epoch": 265.3888888888889, "percentage": 59.71, "elapsed_time": "2:42:16", "remaining_time": "1:49:29", "throughput": 687.21, "total_tokens": 6690960} {"current_steps": 23890, "total_steps": 40000, "loss": 0.0, "lr": 1.7482146943917896e-05, "epoch": 265.44444444444446, "percentage": 59.72, "elapsed_time": "2:42:18", "remaining_time": "1:49:26", "throughput": 687.22, "total_tokens": 6692368} {"current_steps": 23895, "total_steps": 40000, "loss": 0.0, "lr": 1.7472784455326185e-05, "epoch": 265.5, "percentage": 59.74, "elapsed_time": "2:42:20", "remaining_time": "1:49:24", "throughput": 687.22, "total_tokens": 6693744} {"current_steps": 23900, "total_steps": 40000, "loss": 0.0, "lr": 1.746342312752572e-05, "epoch": 265.55555555555554, "percentage": 59.75, "elapsed_time": "2:42:22", "remaining_time": "1:49:22", "throughput": 687.23, "total_tokens": 6695152} {"current_steps": 23905, "total_steps": 40000, "loss": 0.0, "lr": 1.74540629619601e-05, "epoch": 265.6111111111111, "percentage": 59.76, "elapsed_time": "2:42:24", "remaining_time": "1:49:20", "throughput": 687.23, "total_tokens": 6696496} {"current_steps": 23910, "total_steps": 40000, "loss": 0.0, "lr": 1.7444703960072815e-05, "epoch": 265.6666666666667, "percentage": 59.77, "elapsed_time": "2:42:26", "remaining_time": "1:49:18", "throughput": 687.24, "total_tokens": 6697888} {"current_steps": 23915, "total_steps": 40000, "loss": 0.0, "lr": 1.7435346123307118e-05, "epoch": 265.72222222222223, "percentage": 59.79, "elapsed_time": "2:42:28", "remaining_time": "1:49:16", "throughput": 687.25, "total_tokens": 6699312} {"current_steps": 23920, "total_steps": 40000, "loss": 0.0, "lr": 1.742598945310611e-05, "epoch": 265.77777777777777, "percentage": 59.8, "elapsed_time": "2:42:29", "remaining_time": "1:49:14", "throughput": 687.25, "total_tokens": 6700672} {"current_steps": 23925, "total_steps": 40000, "loss": 0.0, "lr": 1.741663395091272e-05, "epoch": 265.8333333333333, "percentage": 59.81, "elapsed_time": "2:42:31", "remaining_time": "1:49:12", "throughput": 687.26, "total_tokens": 6702112} {"current_steps": 23930, "total_steps": 40000, "loss": 0.0, "lr": 1.7407279618169657e-05, "epoch": 265.8888888888889, "percentage": 59.82, "elapsed_time": "2:42:33", "remaining_time": "1:49:10", "throughput": 687.27, "total_tokens": 6703504} {"current_steps": 23935, "total_steps": 40000, "loss": 0.0, "lr": 1.73979264563195e-05, "epoch": 265.94444444444446, "percentage": 59.84, "elapsed_time": "2:42:35", "remaining_time": "1:49:08", "throughput": 687.28, "total_tokens": 6704928} {"current_steps": 23940, "total_steps": 40000, "loss": 0.0, "lr": 1.7388574466804625e-05, "epoch": 266.0, "percentage": 59.85, "elapsed_time": "2:42:37", "remaining_time": "1:49:06", "throughput": 687.28, "total_tokens": 6706368} {"current_steps": 23945, "total_steps": 40000, "loss": 0.0, "lr": 1.7379223651067207e-05, "epoch": 266.05555555555554, "percentage": 59.86, "elapsed_time": "2:42:40", "remaining_time": "1:49:04", "throughput": 687.27, "total_tokens": 6707760} {"current_steps": 23950, "total_steps": 40000, "loss": 0.0, "lr": 1.736987401054928e-05, "epoch": 266.1111111111111, "percentage": 59.88, "elapsed_time": "2:42:41", "remaining_time": "1:49:01", "throughput": 687.27, "total_tokens": 6709168} {"current_steps": 23955, "total_steps": 40000, "loss": 0.0, "lr": 1.736052554669266e-05, "epoch": 266.1666666666667, "percentage": 59.89, "elapsed_time": "2:42:43", "remaining_time": "1:48:59", "throughput": 687.28, "total_tokens": 6710576} {"current_steps": 23960, "total_steps": 40000, "loss": 0.0, "lr": 1.7351178260939007e-05, "epoch": 266.22222222222223, "percentage": 59.9, "elapsed_time": "2:42:45", "remaining_time": "1:48:57", "throughput": 687.29, "total_tokens": 6711984} {"current_steps": 23965, "total_steps": 40000, "loss": 0.0, "lr": 1.7341832154729794e-05, "epoch": 266.27777777777777, "percentage": 59.91, "elapsed_time": "2:42:47", "remaining_time": "1:48:55", "throughput": 687.29, "total_tokens": 6713360} {"current_steps": 23970, "total_steps": 40000, "loss": 0.0, "lr": 1.7332487229506286e-05, "epoch": 266.3333333333333, "percentage": 59.92, "elapsed_time": "2:42:49", "remaining_time": "1:48:53", "throughput": 687.3, "total_tokens": 6714704} {"current_steps": 23975, "total_steps": 40000, "loss": 0.0, "lr": 1.732314348670961e-05, "epoch": 266.3888888888889, "percentage": 59.94, "elapsed_time": "2:42:51", "remaining_time": "1:48:51", "throughput": 687.3, "total_tokens": 6716080} {"current_steps": 23980, "total_steps": 40000, "loss": 0.0, "lr": 1.7313800927780686e-05, "epoch": 266.44444444444446, "percentage": 59.95, "elapsed_time": "2:42:53", "remaining_time": "1:48:49", "throughput": 687.3, "total_tokens": 6717440} {"current_steps": 23985, "total_steps": 40000, "loss": 0.0, "lr": 1.7304459554160245e-05, "epoch": 266.5, "percentage": 59.96, "elapsed_time": "2:42:55", "remaining_time": "1:48:47", "throughput": 687.31, "total_tokens": 6718864} {"current_steps": 23990, "total_steps": 40000, "loss": 0.0, "lr": 1.7295119367288853e-05, "epoch": 266.55555555555554, "percentage": 59.98, "elapsed_time": "2:42:57", "remaining_time": "1:48:45", "throughput": 687.32, "total_tokens": 6720272} {"current_steps": 23995, "total_steps": 40000, "loss": 0.0, "lr": 1.728578036860688e-05, "epoch": 266.6111111111111, "percentage": 59.99, "elapsed_time": "2:42:59", "remaining_time": "1:48:43", "throughput": 687.32, "total_tokens": 6721616} {"current_steps": 24000, "total_steps": 40000, "loss": 0.0, "lr": 1.7276442559554513e-05, "epoch": 266.6666666666667, "percentage": 60.0, "elapsed_time": "2:43:01", "remaining_time": "1:48:40", "throughput": 687.33, "total_tokens": 6723024} {"current_steps": 24000, "total_steps": 40000, "eval_loss": 0.31588953733444214, "epoch": 266.6666666666667, "percentage": 60.0, "elapsed_time": "2:43:02", "remaining_time": "1:48:41", "throughput": 687.24, "total_tokens": 6723024} {"current_steps": 24005, "total_steps": 40000, "loss": 0.0, "lr": 1.726710594157177e-05, "epoch": 266.72222222222223, "percentage": 60.01, "elapsed_time": "2:43:05", "remaining_time": "1:48:40", "throughput": 687.15, "total_tokens": 6724384} {"current_steps": 24010, "total_steps": 40000, "loss": 0.0, "lr": 1.725777051609846e-05, "epoch": 266.77777777777777, "percentage": 60.02, "elapsed_time": "2:43:07", "remaining_time": "1:48:38", "throughput": 687.16, "total_tokens": 6725808} {"current_steps": 24015, "total_steps": 40000, "loss": 0.0, "lr": 1.7248436284574228e-05, "epoch": 266.8333333333333, "percentage": 60.04, "elapsed_time": "2:43:09", "remaining_time": "1:48:36", "throughput": 687.17, "total_tokens": 6727232} {"current_steps": 24020, "total_steps": 40000, "loss": 0.0, "lr": 1.723910324843855e-05, "epoch": 266.8888888888889, "percentage": 60.05, "elapsed_time": "2:43:11", "remaining_time": "1:48:34", "throughput": 687.18, "total_tokens": 6728656} {"current_steps": 24025, "total_steps": 40000, "loss": 0.0, "lr": 1.722977140913067e-05, "epoch": 266.94444444444446, "percentage": 60.06, "elapsed_time": "2:43:13", "remaining_time": "1:48:32", "throughput": 687.19, "total_tokens": 6730096} {"current_steps": 24030, "total_steps": 40000, "loss": 0.0, "lr": 1.7220440768089688e-05, "epoch": 267.0, "percentage": 60.08, "elapsed_time": "2:43:15", "remaining_time": "1:48:30", "throughput": 687.19, "total_tokens": 6731536} {"current_steps": 24035, "total_steps": 40000, "loss": 0.0, "lr": 1.7211111326754505e-05, "epoch": 267.05555555555554, "percentage": 60.09, "elapsed_time": "2:43:17", "remaining_time": "1:48:28", "throughput": 687.17, "total_tokens": 6732928} {"current_steps": 24040, "total_steps": 40000, "loss": 0.0, "lr": 1.720178308656383e-05, "epoch": 267.1111111111111, "percentage": 60.1, "elapsed_time": "2:43:19", "remaining_time": "1:48:26", "throughput": 687.18, "total_tokens": 6734352} {"current_steps": 24045, "total_steps": 40000, "loss": 0.0, "lr": 1.719245604895621e-05, "epoch": 267.1666666666667, "percentage": 60.11, "elapsed_time": "2:43:21", "remaining_time": "1:48:24", "throughput": 687.19, "total_tokens": 6735776} {"current_steps": 24050, "total_steps": 40000, "loss": 0.0, "lr": 1.7183130215369972e-05, "epoch": 267.22222222222223, "percentage": 60.12, "elapsed_time": "2:43:23", "remaining_time": "1:48:21", "throughput": 687.2, "total_tokens": 6737168} {"current_steps": 24055, "total_steps": 40000, "loss": 0.0, "lr": 1.7173805587243292e-05, "epoch": 267.27777777777777, "percentage": 60.14, "elapsed_time": "2:43:25", "remaining_time": "1:48:19", "throughput": 687.21, "total_tokens": 6738576} {"current_steps": 24060, "total_steps": 40000, "loss": 0.0, "lr": 1.7164482166014147e-05, "epoch": 267.3333333333333, "percentage": 60.15, "elapsed_time": "2:43:27", "remaining_time": "1:48:17", "throughput": 687.22, "total_tokens": 6740000} {"current_steps": 24065, "total_steps": 40000, "loss": 0.0, "lr": 1.7155159953120313e-05, "epoch": 267.3888888888889, "percentage": 60.16, "elapsed_time": "2:43:29", "remaining_time": "1:48:15", "throughput": 687.22, "total_tokens": 6741376} {"current_steps": 24070, "total_steps": 40000, "loss": 0.0, "lr": 1.714583894999941e-05, "epoch": 267.44444444444446, "percentage": 60.17, "elapsed_time": "2:43:31", "remaining_time": "1:48:13", "throughput": 687.23, "total_tokens": 6742768} {"current_steps": 24075, "total_steps": 40000, "loss": 0.0, "lr": 1.7136519158088826e-05, "epoch": 267.5, "percentage": 60.19, "elapsed_time": "2:43:33", "remaining_time": "1:48:11", "throughput": 687.23, "total_tokens": 6744176} {"current_steps": 24080, "total_steps": 40000, "loss": 0.0, "lr": 1.712720057882581e-05, "epoch": 267.55555555555554, "percentage": 60.2, "elapsed_time": "2:43:35", "remaining_time": "1:48:09", "throughput": 687.24, "total_tokens": 6745584} {"current_steps": 24085, "total_steps": 40000, "loss": 0.0, "lr": 1.7117883213647413e-05, "epoch": 267.6111111111111, "percentage": 60.21, "elapsed_time": "2:43:37", "remaining_time": "1:48:07", "throughput": 687.25, "total_tokens": 6746976} {"current_steps": 24090, "total_steps": 40000, "loss": 0.0, "lr": 1.710856706399046e-05, "epoch": 267.6666666666667, "percentage": 60.22, "elapsed_time": "2:43:39", "remaining_time": "1:48:05", "throughput": 687.26, "total_tokens": 6748416} {"current_steps": 24095, "total_steps": 40000, "loss": 0.0, "lr": 1.7099252131291648e-05, "epoch": 267.72222222222223, "percentage": 60.24, "elapsed_time": "2:43:41", "remaining_time": "1:48:02", "throughput": 687.27, "total_tokens": 6749856} {"current_steps": 24100, "total_steps": 40000, "loss": 0.0, "lr": 1.708993841698744e-05, "epoch": 267.77777777777777, "percentage": 60.25, "elapsed_time": "2:43:43", "remaining_time": "1:48:00", "throughput": 687.27, "total_tokens": 6751216} {"current_steps": 24105, "total_steps": 40000, "loss": 0.0, "lr": 1.7080625922514132e-05, "epoch": 267.8333333333333, "percentage": 60.26, "elapsed_time": "2:43:45", "remaining_time": "1:47:58", "throughput": 687.28, "total_tokens": 6752640} {"current_steps": 24110, "total_steps": 40000, "loss": 0.0, "lr": 1.7071314649307836e-05, "epoch": 267.8888888888889, "percentage": 60.27, "elapsed_time": "2:43:47", "remaining_time": "1:47:56", "throughput": 687.29, "total_tokens": 6754064} {"current_steps": 24115, "total_steps": 40000, "loss": 0.0, "lr": 1.7062004598804448e-05, "epoch": 267.94444444444446, "percentage": 60.29, "elapsed_time": "2:43:49", "remaining_time": "1:47:54", "throughput": 687.3, "total_tokens": 6755472} {"current_steps": 24120, "total_steps": 40000, "loss": 0.0, "lr": 1.7052695772439702e-05, "epoch": 268.0, "percentage": 60.3, "elapsed_time": "2:43:51", "remaining_time": "1:47:52", "throughput": 687.3, "total_tokens": 6756896} {"current_steps": 24125, "total_steps": 40000, "loss": 0.0, "lr": 1.7043388171649154e-05, "epoch": 268.05555555555554, "percentage": 60.31, "elapsed_time": "2:43:53", "remaining_time": "1:47:50", "throughput": 687.29, "total_tokens": 6758304} {"current_steps": 24130, "total_steps": 40000, "loss": 0.0, "lr": 1.7034081797868127e-05, "epoch": 268.1111111111111, "percentage": 60.32, "elapsed_time": "2:43:55", "remaining_time": "1:47:48", "throughput": 687.29, "total_tokens": 6759696} {"current_steps": 24135, "total_steps": 40000, "loss": 0.0, "lr": 1.70247766525318e-05, "epoch": 268.1666666666667, "percentage": 60.34, "elapsed_time": "2:43:57", "remaining_time": "1:47:46", "throughput": 687.3, "total_tokens": 6761120} {"current_steps": 24140, "total_steps": 40000, "loss": 0.0, "lr": 1.701547273707514e-05, "epoch": 268.22222222222223, "percentage": 60.35, "elapsed_time": "2:43:59", "remaining_time": "1:47:44", "throughput": 687.31, "total_tokens": 6762544} {"current_steps": 24145, "total_steps": 40000, "loss": 0.0, "lr": 1.7006170052932916e-05, "epoch": 268.27777777777777, "percentage": 60.36, "elapsed_time": "2:44:01", "remaining_time": "1:47:42", "throughput": 687.32, "total_tokens": 6764000} {"current_steps": 24150, "total_steps": 40000, "loss": 0.0, "lr": 1.6996868601539735e-05, "epoch": 268.3333333333333, "percentage": 60.38, "elapsed_time": "2:44:03", "remaining_time": "1:47:40", "throughput": 687.33, "total_tokens": 6765360} {"current_steps": 24155, "total_steps": 40000, "loss": 0.0, "lr": 1.6987568384329977e-05, "epoch": 268.3888888888889, "percentage": 60.39, "elapsed_time": "2:44:04", "remaining_time": "1:47:38", "throughput": 687.33, "total_tokens": 6766752} {"current_steps": 24160, "total_steps": 40000, "loss": 0.0, "lr": 1.6978269402737866e-05, "epoch": 268.44444444444446, "percentage": 60.4, "elapsed_time": "2:44:06", "remaining_time": "1:47:35", "throughput": 687.34, "total_tokens": 6768144} {"current_steps": 24165, "total_steps": 40000, "loss": 0.0, "lr": 1.696897165819743e-05, "epoch": 268.5, "percentage": 60.41, "elapsed_time": "2:44:08", "remaining_time": "1:47:33", "throughput": 687.35, "total_tokens": 6769568} {"current_steps": 24170, "total_steps": 40000, "loss": 0.0, "lr": 1.6959675152142487e-05, "epoch": 268.55555555555554, "percentage": 60.42, "elapsed_time": "2:44:10", "remaining_time": "1:47:31", "throughput": 687.36, "total_tokens": 6770976} {"current_steps": 24175, "total_steps": 40000, "loss": 0.0, "lr": 1.6950379886006667e-05, "epoch": 268.6111111111111, "percentage": 60.44, "elapsed_time": "2:44:12", "remaining_time": "1:47:29", "throughput": 687.36, "total_tokens": 6772352} {"current_steps": 24180, "total_steps": 40000, "loss": 0.0, "lr": 1.6941085861223438e-05, "epoch": 268.6666666666667, "percentage": 60.45, "elapsed_time": "2:44:14", "remaining_time": "1:47:27", "throughput": 687.37, "total_tokens": 6773760} {"current_steps": 24185, "total_steps": 40000, "loss": 0.0, "lr": 1.6931793079226034e-05, "epoch": 268.72222222222223, "percentage": 60.46, "elapsed_time": "2:44:16", "remaining_time": "1:47:25", "throughput": 687.38, "total_tokens": 6775184} {"current_steps": 24190, "total_steps": 40000, "loss": 0.0, "lr": 1.692250154144754e-05, "epoch": 268.77777777777777, "percentage": 60.48, "elapsed_time": "2:44:18", "remaining_time": "1:47:23", "throughput": 687.38, "total_tokens": 6776560} {"current_steps": 24195, "total_steps": 40000, "loss": 0.0, "lr": 1.6913211249320807e-05, "epoch": 268.8333333333333, "percentage": 60.49, "elapsed_time": "2:44:20", "remaining_time": "1:47:21", "throughput": 687.39, "total_tokens": 6777968} {"current_steps": 24200, "total_steps": 40000, "loss": 0.0, "lr": 1.6903922204278522e-05, "epoch": 268.8888888888889, "percentage": 60.5, "elapsed_time": "2:44:22", "remaining_time": "1:47:19", "throughput": 687.4, "total_tokens": 6779376} {"current_steps": 24200, "total_steps": 40000, "eval_loss": 0.31484660506248474, "epoch": 268.8888888888889, "percentage": 60.5, "elapsed_time": "2:44:23", "remaining_time": "1:47:19", "throughput": 687.31, "total_tokens": 6779376} {"current_steps": 24205, "total_steps": 40000, "loss": 0.0, "lr": 1.6894634407753186e-05, "epoch": 268.94444444444446, "percentage": 60.51, "elapsed_time": "2:44:26", "remaining_time": "1:47:18", "throughput": 687.22, "total_tokens": 6780752} {"current_steps": 24210, "total_steps": 40000, "loss": 0.0, "lr": 1.6885347861177077e-05, "epoch": 269.0, "percentage": 60.52, "elapsed_time": "2:44:29", "remaining_time": "1:47:16", "throughput": 687.21, "total_tokens": 6782096} {"current_steps": 24215, "total_steps": 40000, "loss": 0.0, "lr": 1.6876062565982298e-05, "epoch": 269.05555555555554, "percentage": 60.54, "elapsed_time": "2:44:31", "remaining_time": "1:47:14", "throughput": 687.19, "total_tokens": 6783504} {"current_steps": 24220, "total_steps": 40000, "loss": 0.0, "lr": 1.6866778523600774e-05, "epoch": 269.1111111111111, "percentage": 60.55, "elapsed_time": "2:44:33", "remaining_time": "1:47:12", "throughput": 687.2, "total_tokens": 6784912} {"current_steps": 24225, "total_steps": 40000, "loss": 0.0, "lr": 1.6857495735464195e-05, "epoch": 269.1666666666667, "percentage": 60.56, "elapsed_time": "2:44:35", "remaining_time": "1:47:10", "throughput": 687.2, "total_tokens": 6786272} {"current_steps": 24230, "total_steps": 40000, "loss": 0.0, "lr": 1.6848214203004115e-05, "epoch": 269.22222222222223, "percentage": 60.58, "elapsed_time": "2:44:37", "remaining_time": "1:47:08", "throughput": 687.2, "total_tokens": 6787616} {"current_steps": 24235, "total_steps": 40000, "loss": 0.0, "lr": 1.6838933927651835e-05, "epoch": 269.27777777777777, "percentage": 60.59, "elapsed_time": "2:44:39", "remaining_time": "1:47:06", "throughput": 687.21, "total_tokens": 6789024} {"current_steps": 24240, "total_steps": 40000, "loss": 0.0, "lr": 1.6829654910838506e-05, "epoch": 269.3333333333333, "percentage": 60.6, "elapsed_time": "2:44:41", "remaining_time": "1:47:04", "throughput": 687.22, "total_tokens": 6790432} {"current_steps": 24245, "total_steps": 40000, "loss": 0.0, "lr": 1.6820377153995065e-05, "epoch": 269.3888888888889, "percentage": 60.61, "elapsed_time": "2:44:42", "remaining_time": "1:47:02", "throughput": 687.23, "total_tokens": 6791856} {"current_steps": 24250, "total_steps": 40000, "loss": 0.0, "lr": 1.681110065855226e-05, "epoch": 269.44444444444446, "percentage": 60.62, "elapsed_time": "2:44:44", "remaining_time": "1:47:00", "throughput": 687.23, "total_tokens": 6793216} {"current_steps": 24255, "total_steps": 40000, "loss": 0.0, "lr": 1.6801825425940642e-05, "epoch": 269.5, "percentage": 60.64, "elapsed_time": "2:44:46", "remaining_time": "1:46:58", "throughput": 687.24, "total_tokens": 6794608} {"current_steps": 24260, "total_steps": 40000, "loss": 0.0, "lr": 1.679255145759056e-05, "epoch": 269.55555555555554, "percentage": 60.65, "elapsed_time": "2:44:48", "remaining_time": "1:46:55", "throughput": 687.24, "total_tokens": 6796016} {"current_steps": 24265, "total_steps": 40000, "loss": 0.0, "lr": 1.6783278754932187e-05, "epoch": 269.6111111111111, "percentage": 60.66, "elapsed_time": "2:44:50", "remaining_time": "1:46:53", "throughput": 687.25, "total_tokens": 6797440} {"current_steps": 24270, "total_steps": 40000, "loss": 0.0, "lr": 1.6774007319395496e-05, "epoch": 269.6666666666667, "percentage": 60.68, "elapsed_time": "2:44:52", "remaining_time": "1:46:51", "throughput": 687.26, "total_tokens": 6798848} {"current_steps": 24275, "total_steps": 40000, "loss": 0.0, "lr": 1.6764737152410243e-05, "epoch": 269.72222222222223, "percentage": 60.69, "elapsed_time": "2:44:54", "remaining_time": "1:46:49", "throughput": 687.27, "total_tokens": 6800240} {"current_steps": 24280, "total_steps": 40000, "loss": 0.0, "lr": 1.6755468255406016e-05, "epoch": 269.77777777777777, "percentage": 60.7, "elapsed_time": "2:44:56", "remaining_time": "1:46:47", "throughput": 687.27, "total_tokens": 6801600} {"current_steps": 24285, "total_steps": 40000, "loss": 0.0, "lr": 1.674620062981219e-05, "epoch": 269.8333333333333, "percentage": 60.71, "elapsed_time": "2:44:58", "remaining_time": "1:46:45", "throughput": 687.28, "total_tokens": 6803024} {"current_steps": 24290, "total_steps": 40000, "loss": 0.0, "lr": 1.6736934277057947e-05, "epoch": 269.8888888888889, "percentage": 60.72, "elapsed_time": "2:45:00", "remaining_time": "1:46:43", "throughput": 687.28, "total_tokens": 6804384} {"current_steps": 24295, "total_steps": 40000, "loss": 0.0, "lr": 1.6727669198572286e-05, "epoch": 269.94444444444446, "percentage": 60.74, "elapsed_time": "2:45:02", "remaining_time": "1:46:41", "throughput": 687.29, "total_tokens": 6805776} {"current_steps": 24300, "total_steps": 40000, "loss": 0.0, "lr": 1.6718405395783984e-05, "epoch": 270.0, "percentage": 60.75, "elapsed_time": "2:45:04", "remaining_time": "1:46:39", "throughput": 687.29, "total_tokens": 6807248} {"current_steps": 24305, "total_steps": 40000, "loss": 0.0, "lr": 1.6709142870121643e-05, "epoch": 270.05555555555554, "percentage": 60.76, "elapsed_time": "2:45:06", "remaining_time": "1:46:37", "throughput": 687.28, "total_tokens": 6808672} {"current_steps": 24310, "total_steps": 40000, "loss": 0.0, "lr": 1.669988162301367e-05, "epoch": 270.1111111111111, "percentage": 60.77, "elapsed_time": "2:45:08", "remaining_time": "1:46:35", "throughput": 687.28, "total_tokens": 6810032} {"current_steps": 24315, "total_steps": 40000, "loss": 0.0, "lr": 1.6690621655888243e-05, "epoch": 270.1666666666667, "percentage": 60.79, "elapsed_time": "2:45:10", "remaining_time": "1:46:33", "throughput": 687.28, "total_tokens": 6811376} {"current_steps": 24320, "total_steps": 40000, "loss": 0.0, "lr": 1.6681362970173386e-05, "epoch": 270.22222222222223, "percentage": 60.8, "elapsed_time": "2:45:12", "remaining_time": "1:46:30", "throughput": 687.29, "total_tokens": 6812800} {"current_steps": 24325, "total_steps": 40000, "loss": 0.0, "lr": 1.6672105567296904e-05, "epoch": 270.27777777777777, "percentage": 60.81, "elapsed_time": "2:45:14", "remaining_time": "1:46:28", "throughput": 687.3, "total_tokens": 6814208} {"current_steps": 24330, "total_steps": 40000, "loss": 0.0, "lr": 1.666284944868639e-05, "epoch": 270.3333333333333, "percentage": 60.82, "elapsed_time": "2:45:16", "remaining_time": "1:46:26", "throughput": 687.31, "total_tokens": 6815648} {"current_steps": 24335, "total_steps": 40000, "loss": 0.0, "lr": 1.665359461576927e-05, "epoch": 270.3888888888889, "percentage": 60.84, "elapsed_time": "2:45:18", "remaining_time": "1:46:24", "throughput": 687.32, "total_tokens": 6817040} {"current_steps": 24340, "total_steps": 40000, "loss": 0.0, "lr": 1.6644341069972736e-05, "epoch": 270.44444444444446, "percentage": 60.85, "elapsed_time": "2:45:20", "remaining_time": "1:46:22", "throughput": 687.32, "total_tokens": 6818416} {"current_steps": 24345, "total_steps": 40000, "loss": 0.0, "lr": 1.6635088812723813e-05, "epoch": 270.5, "percentage": 60.86, "elapsed_time": "2:45:22", "remaining_time": "1:46:20", "throughput": 687.33, "total_tokens": 6819792} {"current_steps": 24350, "total_steps": 40000, "loss": 0.0, "lr": 1.6625837845449328e-05, "epoch": 270.55555555555554, "percentage": 60.88, "elapsed_time": "2:45:24", "remaining_time": "1:46:18", "throughput": 687.34, "total_tokens": 6821216} {"current_steps": 24355, "total_steps": 40000, "loss": 0.0, "lr": 1.6616588169575874e-05, "epoch": 270.6111111111111, "percentage": 60.89, "elapsed_time": "2:45:26", "remaining_time": "1:46:16", "throughput": 687.34, "total_tokens": 6822576} {"current_steps": 24360, "total_steps": 40000, "loss": 0.0, "lr": 1.6607339786529878e-05, "epoch": 270.6666666666667, "percentage": 60.9, "elapsed_time": "2:45:28", "remaining_time": "1:46:14", "throughput": 687.35, "total_tokens": 6824016} {"current_steps": 24365, "total_steps": 40000, "loss": 0.0, "lr": 1.659809269773756e-05, "epoch": 270.72222222222223, "percentage": 60.91, "elapsed_time": "2:45:29", "remaining_time": "1:46:12", "throughput": 687.36, "total_tokens": 6825408} {"current_steps": 24370, "total_steps": 40000, "loss": 0.0, "lr": 1.658884690462493e-05, "epoch": 270.77777777777777, "percentage": 60.92, "elapsed_time": "2:45:31", "remaining_time": "1:46:09", "throughput": 687.36, "total_tokens": 6826784} {"current_steps": 24375, "total_steps": 40000, "loss": 0.0, "lr": 1.6579602408617813e-05, "epoch": 270.8333333333333, "percentage": 60.94, "elapsed_time": "2:45:33", "remaining_time": "1:46:07", "throughput": 687.37, "total_tokens": 6828192} {"current_steps": 24380, "total_steps": 40000, "loss": 0.0, "lr": 1.657035921114181e-05, "epoch": 270.8888888888889, "percentage": 60.95, "elapsed_time": "2:45:35", "remaining_time": "1:46:05", "throughput": 687.38, "total_tokens": 6829616} {"current_steps": 24385, "total_steps": 40000, "loss": 0.0, "lr": 1.656111731362236e-05, "epoch": 270.94444444444446, "percentage": 60.96, "elapsed_time": "2:45:37", "remaining_time": "1:46:03", "throughput": 687.39, "total_tokens": 6831024} {"current_steps": 24390, "total_steps": 40000, "loss": 0.0, "lr": 1.6551876717484666e-05, "epoch": 271.0, "percentage": 60.98, "elapsed_time": "2:45:39", "remaining_time": "1:46:01", "throughput": 687.38, "total_tokens": 6832448} {"current_steps": 24395, "total_steps": 40000, "loss": 0.0, "lr": 1.6542637424153752e-05, "epoch": 271.05555555555554, "percentage": 60.99, "elapsed_time": "2:45:41", "remaining_time": "1:45:59", "throughput": 687.37, "total_tokens": 6833792} {"current_steps": 24400, "total_steps": 40000, "loss": 0.0, "lr": 1.6533399435054418e-05, "epoch": 271.1111111111111, "percentage": 61.0, "elapsed_time": "2:45:43", "remaining_time": "1:45:57", "throughput": 687.38, "total_tokens": 6835232} {"current_steps": 24400, "total_steps": 40000, "eval_loss": 0.31009092926979065, "epoch": 271.1111111111111, "percentage": 61.0, "elapsed_time": "2:45:45", "remaining_time": "1:45:58", "throughput": 687.29, "total_tokens": 6835232} {"current_steps": 24405, "total_steps": 40000, "loss": 0.0, "lr": 1.6524162751611304e-05, "epoch": 271.1666666666667, "percentage": 61.01, "elapsed_time": "2:45:48", "remaining_time": "1:45:57", "throughput": 687.2, "total_tokens": 6836608} {"current_steps": 24410, "total_steps": 40000, "loss": 0.0, "lr": 1.6514927375248796e-05, "epoch": 271.22222222222223, "percentage": 61.02, "elapsed_time": "2:45:50", "remaining_time": "1:45:55", "throughput": 687.2, "total_tokens": 6838000} {"current_steps": 24415, "total_steps": 40000, "loss": 0.0, "lr": 1.6505693307391127e-05, "epoch": 271.27777777777777, "percentage": 61.04, "elapsed_time": "2:45:52", "remaining_time": "1:45:52", "throughput": 687.21, "total_tokens": 6839392} {"current_steps": 24420, "total_steps": 40000, "loss": 0.0, "lr": 1.6496460549462288e-05, "epoch": 271.3333333333333, "percentage": 61.05, "elapsed_time": "2:45:54", "remaining_time": "1:45:50", "throughput": 687.22, "total_tokens": 6840800} {"current_steps": 24425, "total_steps": 40000, "loss": 0.0, "lr": 1.6487229102886097e-05, "epoch": 271.3888888888889, "percentage": 61.06, "elapsed_time": "2:45:56", "remaining_time": "1:45:48", "throughput": 687.22, "total_tokens": 6842176} {"current_steps": 24430, "total_steps": 40000, "loss": 0.0, "lr": 1.6477998969086155e-05, "epoch": 271.44444444444446, "percentage": 61.08, "elapsed_time": "2:45:58", "remaining_time": "1:45:46", "throughput": 687.22, "total_tokens": 6843520} {"current_steps": 24435, "total_steps": 40000, "loss": 0.0, "lr": 1.646877014948587e-05, "epoch": 271.5, "percentage": 61.09, "elapsed_time": "2:46:00", "remaining_time": "1:45:44", "throughput": 687.23, "total_tokens": 6844944} {"current_steps": 24440, "total_steps": 40000, "loss": 0.0, "lr": 1.6459542645508433e-05, "epoch": 271.55555555555554, "percentage": 61.1, "elapsed_time": "2:46:02", "remaining_time": "1:45:42", "throughput": 687.24, "total_tokens": 6846400} {"current_steps": 24445, "total_steps": 40000, "loss": 0.0, "lr": 1.6450316458576852e-05, "epoch": 271.6111111111111, "percentage": 61.11, "elapsed_time": "2:46:04", "remaining_time": "1:45:40", "throughput": 687.25, "total_tokens": 6847776} {"current_steps": 24450, "total_steps": 40000, "loss": 0.0, "lr": 1.6441091590113912e-05, "epoch": 271.6666666666667, "percentage": 61.12, "elapsed_time": "2:46:05", "remaining_time": "1:45:38", "throughput": 687.26, "total_tokens": 6849200} {"current_steps": 24455, "total_steps": 40000, "loss": 0.0, "lr": 1.6431868041542213e-05, "epoch": 271.72222222222223, "percentage": 61.14, "elapsed_time": "2:46:07", "remaining_time": "1:45:36", "throughput": 687.27, "total_tokens": 6850624} {"current_steps": 24460, "total_steps": 40000, "loss": 0.0, "lr": 1.6422645814284123e-05, "epoch": 271.77777777777777, "percentage": 61.15, "elapsed_time": "2:46:09", "remaining_time": "1:45:34", "throughput": 687.28, "total_tokens": 6852048} {"current_steps": 24465, "total_steps": 40000, "loss": 0.0, "lr": 1.6413424909761846e-05, "epoch": 271.8333333333333, "percentage": 61.16, "elapsed_time": "2:46:11", "remaining_time": "1:45:31", "throughput": 687.28, "total_tokens": 6853440} {"current_steps": 24470, "total_steps": 40000, "loss": 0.0, "lr": 1.640420532939736e-05, "epoch": 271.8888888888889, "percentage": 61.18, "elapsed_time": "2:46:13", "remaining_time": "1:45:29", "throughput": 687.29, "total_tokens": 6854880} {"current_steps": 24475, "total_steps": 40000, "loss": 0.0, "lr": 1.639498707461242e-05, "epoch": 271.94444444444446, "percentage": 61.19, "elapsed_time": "2:46:15", "remaining_time": "1:45:27", "throughput": 687.3, "total_tokens": 6856240} {"current_steps": 24480, "total_steps": 40000, "loss": 0.0, "lr": 1.6385770146828614e-05, "epoch": 272.0, "percentage": 61.2, "elapsed_time": "2:46:17", "remaining_time": "1:45:25", "throughput": 687.29, "total_tokens": 6857680} {"current_steps": 24485, "total_steps": 40000, "loss": 0.0, "lr": 1.637655454746731e-05, "epoch": 272.05555555555554, "percentage": 61.21, "elapsed_time": "2:46:19", "remaining_time": "1:45:23", "throughput": 687.28, "total_tokens": 6859072} {"current_steps": 24490, "total_steps": 40000, "loss": 0.0, "lr": 1.6367340277949658e-05, "epoch": 272.1111111111111, "percentage": 61.22, "elapsed_time": "2:46:21", "remaining_time": "1:45:21", "throughput": 687.29, "total_tokens": 6860448} {"current_steps": 24495, "total_steps": 40000, "loss": 0.0, "lr": 1.635812733969663e-05, "epoch": 272.1666666666667, "percentage": 61.24, "elapsed_time": "2:46:23", "remaining_time": "1:45:19", "throughput": 687.29, "total_tokens": 6861824} {"current_steps": 24500, "total_steps": 40000, "loss": 0.0, "lr": 1.634891573412896e-05, "epoch": 272.22222222222223, "percentage": 61.25, "elapsed_time": "2:46:25", "remaining_time": "1:45:17", "throughput": 687.3, "total_tokens": 6863216} {"current_steps": 24505, "total_steps": 40000, "loss": 0.0, "lr": 1.6339705462667196e-05, "epoch": 272.27777777777777, "percentage": 61.26, "elapsed_time": "2:46:27", "remaining_time": "1:45:15", "throughput": 687.3, "total_tokens": 6864592} {"current_steps": 24510, "total_steps": 40000, "loss": 0.0, "lr": 1.633049652673169e-05, "epoch": 272.3333333333333, "percentage": 61.27, "elapsed_time": "2:46:29", "remaining_time": "1:45:13", "throughput": 687.31, "total_tokens": 6865984} {"current_steps": 24515, "total_steps": 40000, "loss": 0.0, "lr": 1.632128892774256e-05, "epoch": 272.3888888888889, "percentage": 61.29, "elapsed_time": "2:46:31", "remaining_time": "1:45:11", "throughput": 687.32, "total_tokens": 6867456} {"current_steps": 24520, "total_steps": 40000, "loss": 0.0, "lr": 1.6312082667119737e-05, "epoch": 272.44444444444446, "percentage": 61.3, "elapsed_time": "2:46:33", "remaining_time": "1:45:09", "throughput": 687.33, "total_tokens": 6868864} {"current_steps": 24525, "total_steps": 40000, "loss": 0.0, "lr": 1.630287774628296e-05, "epoch": 272.5, "percentage": 61.31, "elapsed_time": "2:46:35", "remaining_time": "1:45:07", "throughput": 687.33, "total_tokens": 6870240} {"current_steps": 24530, "total_steps": 40000, "loss": 0.0, "lr": 1.6293674166651718e-05, "epoch": 272.55555555555554, "percentage": 61.32, "elapsed_time": "2:46:37", "remaining_time": "1:45:04", "throughput": 687.34, "total_tokens": 6871616} {"current_steps": 24535, "total_steps": 40000, "loss": 0.0, "lr": 1.6284471929645338e-05, "epoch": 272.6111111111111, "percentage": 61.34, "elapsed_time": "2:46:39", "remaining_time": "1:45:02", "throughput": 687.35, "total_tokens": 6873040} {"current_steps": 24540, "total_steps": 40000, "loss": 0.0, "lr": 1.627527103668291e-05, "epoch": 272.6666666666667, "percentage": 61.35, "elapsed_time": "2:46:41", "remaining_time": "1:45:00", "throughput": 687.35, "total_tokens": 6874448} {"current_steps": 24545, "total_steps": 40000, "loss": 0.0, "lr": 1.6266071489183327e-05, "epoch": 272.72222222222223, "percentage": 61.36, "elapsed_time": "2:46:43", "remaining_time": "1:44:58", "throughput": 687.36, "total_tokens": 6875872} {"current_steps": 24550, "total_steps": 40000, "loss": 0.0, "lr": 1.6256873288565283e-05, "epoch": 272.77777777777777, "percentage": 61.38, "elapsed_time": "2:46:45", "remaining_time": "1:44:56", "throughput": 687.37, "total_tokens": 6877232} {"current_steps": 24555, "total_steps": 40000, "loss": 0.0, "lr": 1.6247676436247245e-05, "epoch": 272.8333333333333, "percentage": 61.39, "elapsed_time": "2:46:47", "remaining_time": "1:44:54", "throughput": 687.37, "total_tokens": 6878624} {"current_steps": 24560, "total_steps": 40000, "loss": 0.0, "lr": 1.6238480933647486e-05, "epoch": 272.8888888888889, "percentage": 61.4, "elapsed_time": "2:46:49", "remaining_time": "1:44:52", "throughput": 687.38, "total_tokens": 6880048} {"current_steps": 24565, "total_steps": 40000, "loss": 0.0, "lr": 1.6229286782184083e-05, "epoch": 272.94444444444446, "percentage": 61.41, "elapsed_time": "2:46:51", "remaining_time": "1:44:50", "throughput": 687.38, "total_tokens": 6881408} {"current_steps": 24570, "total_steps": 40000, "loss": 0.0, "lr": 1.622009398327487e-05, "epoch": 273.0, "percentage": 61.42, "elapsed_time": "2:46:53", "remaining_time": "1:44:48", "throughput": 687.38, "total_tokens": 6882832} {"current_steps": 24575, "total_steps": 40000, "loss": 0.0, "lr": 1.6210902538337502e-05, "epoch": 273.05555555555554, "percentage": 61.44, "elapsed_time": "2:46:55", "remaining_time": "1:44:46", "throughput": 687.37, "total_tokens": 6884224} {"current_steps": 24580, "total_steps": 40000, "loss": 0.0, "lr": 1.6201712448789413e-05, "epoch": 273.1111111111111, "percentage": 61.45, "elapsed_time": "2:46:57", "remaining_time": "1:44:44", "throughput": 687.37, "total_tokens": 6885600} {"current_steps": 24585, "total_steps": 40000, "loss": 0.0, "lr": 1.6192523716047827e-05, "epoch": 273.1666666666667, "percentage": 61.46, "elapsed_time": "2:46:59", "remaining_time": "1:44:42", "throughput": 687.38, "total_tokens": 6886992} {"current_steps": 24590, "total_steps": 40000, "loss": 0.0, "lr": 1.6183336341529776e-05, "epoch": 273.22222222222223, "percentage": 61.48, "elapsed_time": "2:47:01", "remaining_time": "1:44:40", "throughput": 687.38, "total_tokens": 6888352} {"current_steps": 24595, "total_steps": 40000, "loss": 0.0, "lr": 1.6174150326652047e-05, "epoch": 273.27777777777777, "percentage": 61.49, "elapsed_time": "2:47:03", "remaining_time": "1:44:37", "throughput": 687.39, "total_tokens": 6889728} {"current_steps": 24600, "total_steps": 40000, "loss": 0.0, "lr": 1.6164965672831256e-05, "epoch": 273.3333333333333, "percentage": 61.5, "elapsed_time": "2:47:05", "remaining_time": "1:44:35", "throughput": 687.39, "total_tokens": 6891104} {"current_steps": 24600, "total_steps": 40000, "eval_loss": 0.3030507564544678, "epoch": 273.3333333333333, "percentage": 61.5, "elapsed_time": "2:47:06", "remaining_time": "1:44:36", "throughput": 687.3, "total_tokens": 6891104} {"current_steps": 24605, "total_steps": 40000, "loss": 0.0, "lr": 1.6155782381483784e-05, "epoch": 273.3888888888889, "percentage": 61.51, "elapsed_time": "2:47:09", "remaining_time": "1:44:35", "throughput": 687.22, "total_tokens": 6892512} {"current_steps": 24610, "total_steps": 40000, "loss": 0.0, "lr": 1.6146600454025813e-05, "epoch": 273.44444444444446, "percentage": 61.52, "elapsed_time": "2:47:11", "remaining_time": "1:44:33", "throughput": 687.22, "total_tokens": 6893936} {"current_steps": 24615, "total_steps": 40000, "loss": 0.0, "lr": 1.6137419891873317e-05, "epoch": 273.5, "percentage": 61.54, "elapsed_time": "2:47:13", "remaining_time": "1:44:31", "throughput": 687.23, "total_tokens": 6895360} {"current_steps": 24620, "total_steps": 40000, "loss": 0.0, "lr": 1.6128240696442038e-05, "epoch": 273.55555555555554, "percentage": 61.55, "elapsed_time": "2:47:15", "remaining_time": "1:44:29", "throughput": 687.24, "total_tokens": 6896768} {"current_steps": 24625, "total_steps": 40000, "loss": 0.0, "lr": 1.611906286914753e-05, "epoch": 273.6111111111111, "percentage": 61.56, "elapsed_time": "2:47:17", "remaining_time": "1:44:26", "throughput": 687.25, "total_tokens": 6898160} {"current_steps": 24630, "total_steps": 40000, "loss": 0.0, "lr": 1.6109886411405144e-05, "epoch": 273.6666666666667, "percentage": 61.58, "elapsed_time": "2:47:19", "remaining_time": "1:44:24", "throughput": 687.26, "total_tokens": 6899600} {"current_steps": 24635, "total_steps": 40000, "loss": 0.0, "lr": 1.6100711324629985e-05, "epoch": 273.72222222222223, "percentage": 61.59, "elapsed_time": "2:47:21", "remaining_time": "1:44:22", "throughput": 687.26, "total_tokens": 6901008} {"current_steps": 24640, "total_steps": 40000, "loss": 0.0, "lr": 1.609153761023698e-05, "epoch": 273.77777777777777, "percentage": 61.6, "elapsed_time": "2:47:23", "remaining_time": "1:44:20", "throughput": 687.28, "total_tokens": 6902448} {"current_steps": 24645, "total_steps": 40000, "loss": 0.0, "lr": 1.608236526964083e-05, "epoch": 273.8333333333333, "percentage": 61.61, "elapsed_time": "2:47:25", "remaining_time": "1:44:18", "throughput": 687.28, "total_tokens": 6903840} {"current_steps": 24650, "total_steps": 40000, "loss": 0.0, "lr": 1.607319430425601e-05, "epoch": 273.8888888888889, "percentage": 61.62, "elapsed_time": "2:47:27", "remaining_time": "1:44:16", "throughput": 687.29, "total_tokens": 6905248} {"current_steps": 24655, "total_steps": 40000, "loss": 0.0, "lr": 1.606402471549682e-05, "epoch": 273.94444444444446, "percentage": 61.64, "elapsed_time": "2:47:29", "remaining_time": "1:44:14", "throughput": 687.3, "total_tokens": 6906640} {"current_steps": 24660, "total_steps": 40000, "loss": 0.0, "lr": 1.6054856504777312e-05, "epoch": 274.0, "percentage": 61.65, "elapsed_time": "2:47:31", "remaining_time": "1:44:12", "throughput": 687.29, "total_tokens": 6908000} {"current_steps": 24665, "total_steps": 40000, "loss": 0.0, "lr": 1.6045689673511334e-05, "epoch": 274.05555555555554, "percentage": 61.66, "elapsed_time": "2:47:33", "remaining_time": "1:44:10", "throughput": 687.28, "total_tokens": 6909408} {"current_steps": 24670, "total_steps": 40000, "loss": 0.0, "lr": 1.6036524223112548e-05, "epoch": 274.1111111111111, "percentage": 61.68, "elapsed_time": "2:47:35", "remaining_time": "1:44:08", "throughput": 687.29, "total_tokens": 6910848} {"current_steps": 24675, "total_steps": 40000, "loss": 0.0, "lr": 1.602736015499436e-05, "epoch": 274.1666666666667, "percentage": 61.69, "elapsed_time": "2:47:37", "remaining_time": "1:44:06", "throughput": 687.3, "total_tokens": 6912304} {"current_steps": 24680, "total_steps": 40000, "loss": 0.0, "lr": 1.601819747057e-05, "epoch": 274.22222222222223, "percentage": 61.7, "elapsed_time": "2:47:39", "remaining_time": "1:44:04", "throughput": 687.3, "total_tokens": 6913680} {"current_steps": 24685, "total_steps": 40000, "loss": 0.0, "lr": 1.6009036171252465e-05, "epoch": 274.27777777777777, "percentage": 61.71, "elapsed_time": "2:47:41", "remaining_time": "1:44:02", "throughput": 687.31, "total_tokens": 6915072} {"current_steps": 24690, "total_steps": 40000, "loss": 0.0, "lr": 1.599987625845453e-05, "epoch": 274.3333333333333, "percentage": 61.72, "elapsed_time": "2:47:43", "remaining_time": "1:43:59", "throughput": 687.32, "total_tokens": 6916496} {"current_steps": 24695, "total_steps": 40000, "loss": 0.0, "lr": 1.599071773358879e-05, "epoch": 274.3888888888889, "percentage": 61.74, "elapsed_time": "2:47:44", "remaining_time": "1:43:57", "throughput": 687.33, "total_tokens": 6917936} {"current_steps": 24700, "total_steps": 40000, "loss": 0.0, "lr": 1.598156059806758e-05, "epoch": 274.44444444444446, "percentage": 61.75, "elapsed_time": "2:47:46", "remaining_time": "1:43:55", "throughput": 687.33, "total_tokens": 6919312} {"current_steps": 24705, "total_steps": 40000, "loss": 0.0, "lr": 1.5972404853303062e-05, "epoch": 274.5, "percentage": 61.76, "elapsed_time": "2:47:48", "remaining_time": "1:43:53", "throughput": 687.34, "total_tokens": 6920720} {"current_steps": 24710, "total_steps": 40000, "loss": 0.0, "lr": 1.5963250500707172e-05, "epoch": 274.55555555555554, "percentage": 61.78, "elapsed_time": "2:47:50", "remaining_time": "1:43:51", "throughput": 687.35, "total_tokens": 6922112} {"current_steps": 24715, "total_steps": 40000, "loss": 0.0, "lr": 1.5954097541691612e-05, "epoch": 274.6111111111111, "percentage": 61.79, "elapsed_time": "2:47:52", "remaining_time": "1:43:49", "throughput": 687.36, "total_tokens": 6923552} {"current_steps": 24720, "total_steps": 40000, "loss": 0.0, "lr": 1.5944945977667884e-05, "epoch": 274.6666666666667, "percentage": 61.8, "elapsed_time": "2:47:54", "remaining_time": "1:43:47", "throughput": 687.37, "total_tokens": 6924976} {"current_steps": 24725, "total_steps": 40000, "loss": 0.0, "lr": 1.593579581004729e-05, "epoch": 274.72222222222223, "percentage": 61.81, "elapsed_time": "2:47:56", "remaining_time": "1:43:45", "throughput": 687.37, "total_tokens": 6926336} {"current_steps": 24730, "total_steps": 40000, "loss": 0.0, "lr": 1.592664704024088e-05, "epoch": 274.77777777777777, "percentage": 61.82, "elapsed_time": "2:47:58", "remaining_time": "1:43:43", "throughput": 687.37, "total_tokens": 6927664} {"current_steps": 24735, "total_steps": 40000, "loss": 0.0, "lr": 1.591749966965953e-05, "epoch": 274.8333333333333, "percentage": 61.84, "elapsed_time": "2:48:00", "remaining_time": "1:43:41", "throughput": 687.38, "total_tokens": 6929072} {"current_steps": 24740, "total_steps": 40000, "loss": 0.0, "lr": 1.5908353699713856e-05, "epoch": 274.8888888888889, "percentage": 61.85, "elapsed_time": "2:48:02", "remaining_time": "1:43:38", "throughput": 687.38, "total_tokens": 6930448} {"current_steps": 24745, "total_steps": 40000, "loss": 0.0, "lr": 1.5899209131814298e-05, "epoch": 274.94444444444446, "percentage": 61.86, "elapsed_time": "2:48:04", "remaining_time": "1:43:36", "throughput": 687.39, "total_tokens": 6931856} {"current_steps": 24750, "total_steps": 40000, "loss": 0.0, "lr": 1.5890065967371067e-05, "epoch": 275.0, "percentage": 61.88, "elapsed_time": "2:48:06", "remaining_time": "1:43:34", "throughput": 687.39, "total_tokens": 6933280} {"current_steps": 24755, "total_steps": 40000, "loss": 0.0, "lr": 1.5880924207794144e-05, "epoch": 275.05555555555554, "percentage": 61.89, "elapsed_time": "2:48:08", "remaining_time": "1:43:32", "throughput": 687.38, "total_tokens": 6934736} {"current_steps": 24760, "total_steps": 40000, "loss": 0.0, "lr": 1.5871783854493298e-05, "epoch": 275.1111111111111, "percentage": 61.9, "elapsed_time": "2:48:10", "remaining_time": "1:43:30", "throughput": 687.39, "total_tokens": 6936192} {"current_steps": 24765, "total_steps": 40000, "loss": 0.0, "lr": 1.5862644908878106e-05, "epoch": 275.1666666666667, "percentage": 61.91, "elapsed_time": "2:48:12", "remaining_time": "1:43:28", "throughput": 687.4, "total_tokens": 6937584} {"current_steps": 24770, "total_steps": 40000, "loss": 0.0, "lr": 1.5853507372357885e-05, "epoch": 275.22222222222223, "percentage": 61.92, "elapsed_time": "2:48:14", "remaining_time": "1:43:26", "throughput": 687.41, "total_tokens": 6939056} {"current_steps": 24775, "total_steps": 40000, "loss": 0.0, "lr": 1.5844371246341776e-05, "epoch": 275.27777777777777, "percentage": 61.94, "elapsed_time": "2:48:16", "remaining_time": "1:43:24", "throughput": 687.42, "total_tokens": 6940432} {"current_steps": 24780, "total_steps": 40000, "loss": 0.0, "lr": 1.5835236532238674e-05, "epoch": 275.3333333333333, "percentage": 61.95, "elapsed_time": "2:48:18", "remaining_time": "1:43:22", "throughput": 687.42, "total_tokens": 6941840} {"current_steps": 24785, "total_steps": 40000, "loss": 0.0, "lr": 1.582610323145727e-05, "epoch": 275.3888888888889, "percentage": 61.96, "elapsed_time": "2:48:20", "remaining_time": "1:43:20", "throughput": 687.43, "total_tokens": 6943232} {"current_steps": 24790, "total_steps": 40000, "loss": 0.0, "lr": 1.5816971345406035e-05, "epoch": 275.44444444444446, "percentage": 61.98, "elapsed_time": "2:48:22", "remaining_time": "1:43:18", "throughput": 687.43, "total_tokens": 6944608} {"current_steps": 24795, "total_steps": 40000, "loss": 0.0, "lr": 1.5807840875493225e-05, "epoch": 275.5, "percentage": 61.99, "elapsed_time": "2:48:24", "remaining_time": "1:43:16", "throughput": 687.44, "total_tokens": 6946032} {"current_steps": 24800, "total_steps": 40000, "loss": 0.0, "lr": 1.5798711823126854e-05, "epoch": 275.55555555555554, "percentage": 62.0, "elapsed_time": "2:48:26", "remaining_time": "1:43:14", "throughput": 687.45, "total_tokens": 6947456} {"current_steps": 24800, "total_steps": 40000, "eval_loss": 0.33908694982528687, "epoch": 275.55555555555554, "percentage": 62.0, "elapsed_time": "2:48:27", "remaining_time": "1:43:14", "throughput": 687.36, "total_tokens": 6947456} {"current_steps": 24805, "total_steps": 40000, "loss": 0.0, "lr": 1.578958418971477e-05, "epoch": 275.6111111111111, "percentage": 62.01, "elapsed_time": "2:48:31", "remaining_time": "1:43:13", "throughput": 687.24, "total_tokens": 6948880} {"current_steps": 24810, "total_steps": 40000, "loss": 0.0, "lr": 1.578045797666453e-05, "epoch": 275.6666666666667, "percentage": 62.02, "elapsed_time": "2:48:33", "remaining_time": "1:43:11", "throughput": 687.25, "total_tokens": 6950256} {"current_steps": 24815, "total_steps": 40000, "loss": 0.0, "lr": 1.5771333185383548e-05, "epoch": 275.72222222222223, "percentage": 62.04, "elapsed_time": "2:48:35", "remaining_time": "1:43:09", "throughput": 687.25, "total_tokens": 6951632} {"current_steps": 24820, "total_steps": 40000, "loss": 0.0, "lr": 1.576220981727895e-05, "epoch": 275.77777777777777, "percentage": 62.05, "elapsed_time": "2:48:37", "remaining_time": "1:43:07", "throughput": 687.25, "total_tokens": 6953008} {"current_steps": 24825, "total_steps": 40000, "loss": 0.0, "lr": 1.575308787375769e-05, "epoch": 275.8333333333333, "percentage": 62.06, "elapsed_time": "2:48:39", "remaining_time": "1:43:05", "throughput": 687.24, "total_tokens": 6954432} {"current_steps": 24830, "total_steps": 40000, "loss": 0.0, "lr": 1.5743967356226492e-05, "epoch": 275.8888888888889, "percentage": 62.08, "elapsed_time": "2:48:41", "remaining_time": "1:43:03", "throughput": 687.24, "total_tokens": 6955792} {"current_steps": 24835, "total_steps": 40000, "loss": 0.0, "lr": 1.5734848266091835e-05, "epoch": 275.94444444444446, "percentage": 62.09, "elapsed_time": "2:48:43", "remaining_time": "1:43:01", "throughput": 687.25, "total_tokens": 6957184} {"current_steps": 24840, "total_steps": 40000, "loss": 0.0, "lr": 1.572573060476001e-05, "epoch": 276.0, "percentage": 62.1, "elapsed_time": "2:48:45", "remaining_time": "1:42:59", "throughput": 687.24, "total_tokens": 6958576} {"current_steps": 24845, "total_steps": 40000, "loss": 0.0, "lr": 1.5716614373637085e-05, "epoch": 276.05555555555554, "percentage": 62.11, "elapsed_time": "2:48:47", "remaining_time": "1:42:57", "throughput": 687.23, "total_tokens": 6959984} {"current_steps": 24850, "total_steps": 40000, "loss": 0.0, "lr": 1.570749957412887e-05, "epoch": 276.1111111111111, "percentage": 62.12, "elapsed_time": "2:48:49", "remaining_time": "1:42:55", "throughput": 687.24, "total_tokens": 6961360} {"current_steps": 24855, "total_steps": 40000, "loss": 0.0, "lr": 1.5698386207641013e-05, "epoch": 276.1666666666667, "percentage": 62.14, "elapsed_time": "2:48:51", "remaining_time": "1:42:53", "throughput": 687.24, "total_tokens": 6962736} {"current_steps": 24860, "total_steps": 40000, "loss": 0.0, "lr": 1.5689274275578884e-05, "epoch": 276.22222222222223, "percentage": 62.15, "elapsed_time": "2:48:53", "remaining_time": "1:42:51", "throughput": 687.24, "total_tokens": 6964096} {"current_steps": 24865, "total_steps": 40000, "loss": 0.0, "lr": 1.5680163779347667e-05, "epoch": 276.27777777777777, "percentage": 62.16, "elapsed_time": "2:48:55", "remaining_time": "1:42:49", "throughput": 687.24, "total_tokens": 6965440} {"current_steps": 24870, "total_steps": 40000, "loss": 0.0, "lr": 1.5671054720352327e-05, "epoch": 276.3333333333333, "percentage": 62.18, "elapsed_time": "2:48:57", "remaining_time": "1:42:47", "throughput": 687.26, "total_tokens": 6966880} {"current_steps": 24875, "total_steps": 40000, "loss": 0.0, "lr": 1.566194709999757e-05, "epoch": 276.3888888888889, "percentage": 62.19, "elapsed_time": "2:48:59", "remaining_time": "1:42:45", "throughput": 687.26, "total_tokens": 6968272} {"current_steps": 24880, "total_steps": 40000, "loss": 0.0, "lr": 1.5652840919687933e-05, "epoch": 276.44444444444446, "percentage": 62.2, "elapsed_time": "2:49:01", "remaining_time": "1:42:42", "throughput": 687.27, "total_tokens": 6969680} {"current_steps": 24885, "total_steps": 40000, "loss": 0.0, "lr": 1.5643736180827676e-05, "epoch": 276.5, "percentage": 62.21, "elapsed_time": "2:49:03", "remaining_time": "1:42:40", "throughput": 687.28, "total_tokens": 6971072} {"current_steps": 24890, "total_steps": 40000, "loss": 0.0, "lr": 1.5634632884820878e-05, "epoch": 276.55555555555554, "percentage": 62.22, "elapsed_time": "2:49:04", "remaining_time": "1:42:38", "throughput": 687.29, "total_tokens": 6972496} {"current_steps": 24895, "total_steps": 40000, "loss": 0.0, "lr": 1.5625531033071395e-05, "epoch": 276.6111111111111, "percentage": 62.24, "elapsed_time": "2:49:06", "remaining_time": "1:42:36", "throughput": 687.29, "total_tokens": 6973840} {"current_steps": 24900, "total_steps": 40000, "loss": 0.0, "lr": 1.5616430626982828e-05, "epoch": 276.6666666666667, "percentage": 62.25, "elapsed_time": "2:49:08", "remaining_time": "1:42:34", "throughput": 687.3, "total_tokens": 6975312} {"current_steps": 24905, "total_steps": 40000, "loss": 0.0, "lr": 1.5607331667958575e-05, "epoch": 276.72222222222223, "percentage": 62.26, "elapsed_time": "2:49:10", "remaining_time": "1:42:32", "throughput": 687.31, "total_tokens": 6976752} {"current_steps": 24910, "total_steps": 40000, "loss": 0.0, "lr": 1.5598234157401824e-05, "epoch": 276.77777777777777, "percentage": 62.28, "elapsed_time": "2:49:12", "remaining_time": "1:42:30", "throughput": 687.32, "total_tokens": 6978160} {"current_steps": 24915, "total_steps": 40000, "loss": 0.0, "lr": 1.5589138096715503e-05, "epoch": 276.8333333333333, "percentage": 62.29, "elapsed_time": "2:49:14", "remaining_time": "1:42:28", "throughput": 687.33, "total_tokens": 6979584} {"current_steps": 24920, "total_steps": 40000, "loss": 0.0, "lr": 1.5580043487302365e-05, "epoch": 276.8888888888889, "percentage": 62.3, "elapsed_time": "2:49:16", "remaining_time": "1:42:26", "throughput": 687.34, "total_tokens": 6980992} {"current_steps": 24925, "total_steps": 40000, "loss": 0.0, "lr": 1.5570950330564888e-05, "epoch": 276.94444444444446, "percentage": 62.31, "elapsed_time": "2:49:18", "remaining_time": "1:42:24", "throughput": 687.35, "total_tokens": 6982416} {"current_steps": 24930, "total_steps": 40000, "loss": 0.0, "lr": 1.5561858627905367e-05, "epoch": 277.0, "percentage": 62.32, "elapsed_time": "2:49:20", "remaining_time": "1:42:22", "throughput": 687.34, "total_tokens": 6983808} {"current_steps": 24935, "total_steps": 40000, "loss": 0.0, "lr": 1.5552768380725857e-05, "epoch": 277.05555555555554, "percentage": 62.34, "elapsed_time": "2:49:22", "remaining_time": "1:42:20", "throughput": 687.33, "total_tokens": 6985200} {"current_steps": 24940, "total_steps": 40000, "loss": 0.0, "lr": 1.5543679590428183e-05, "epoch": 277.1111111111111, "percentage": 62.35, "elapsed_time": "2:49:24", "remaining_time": "1:42:17", "throughput": 687.33, "total_tokens": 6986576} {"current_steps": 24945, "total_steps": 40000, "loss": 0.0, "lr": 1.5534592258413943e-05, "epoch": 277.1666666666667, "percentage": 62.36, "elapsed_time": "2:49:26", "remaining_time": "1:42:15", "throughput": 687.34, "total_tokens": 6987968} {"current_steps": 24950, "total_steps": 40000, "loss": 0.0, "lr": 1.5525506386084538e-05, "epoch": 277.22222222222223, "percentage": 62.38, "elapsed_time": "2:49:28", "remaining_time": "1:42:13", "throughput": 687.35, "total_tokens": 6989376} {"current_steps": 24955, "total_steps": 40000, "loss": 0.0, "lr": 1.55164219748411e-05, "epoch": 277.27777777777777, "percentage": 62.39, "elapsed_time": "2:49:30", "remaining_time": "1:42:11", "throughput": 687.36, "total_tokens": 6990816} {"current_steps": 24960, "total_steps": 40000, "loss": 0.0, "lr": 1.550733902608459e-05, "epoch": 277.3333333333333, "percentage": 62.4, "elapsed_time": "2:49:32", "remaining_time": "1:42:09", "throughput": 687.36, "total_tokens": 6992240} {"current_steps": 24965, "total_steps": 40000, "loss": 0.0, "lr": 1.549825754121568e-05, "epoch": 277.3888888888889, "percentage": 62.41, "elapsed_time": "2:49:34", "remaining_time": "1:42:07", "throughput": 687.37, "total_tokens": 6993616} {"current_steps": 24970, "total_steps": 40000, "loss": 0.0, "lr": 1.5489177521634864e-05, "epoch": 277.44444444444446, "percentage": 62.42, "elapsed_time": "2:49:36", "remaining_time": "1:42:05", "throughput": 687.38, "total_tokens": 6995056} {"current_steps": 24975, "total_steps": 40000, "loss": 0.0, "lr": 1.5480098968742402e-05, "epoch": 277.5, "percentage": 62.44, "elapsed_time": "2:49:38", "remaining_time": "1:42:03", "throughput": 687.38, "total_tokens": 6996432} {"current_steps": 24980, "total_steps": 40000, "loss": 0.0, "lr": 1.5471021883938304e-05, "epoch": 277.55555555555554, "percentage": 62.45, "elapsed_time": "2:49:40", "remaining_time": "1:42:01", "throughput": 687.39, "total_tokens": 6997856} {"current_steps": 24985, "total_steps": 40000, "loss": 0.0, "lr": 1.546194626862238e-05, "epoch": 277.6111111111111, "percentage": 62.46, "elapsed_time": "2:49:42", "remaining_time": "1:41:59", "throughput": 687.4, "total_tokens": 6999232} {"current_steps": 24990, "total_steps": 40000, "loss": 0.0, "lr": 1.5452872124194216e-05, "epoch": 277.6666666666667, "percentage": 62.48, "elapsed_time": "2:49:44", "remaining_time": "1:41:57", "throughput": 687.41, "total_tokens": 7000672} {"current_steps": 24995, "total_steps": 40000, "loss": 0.0, "lr": 1.5443799452053136e-05, "epoch": 277.72222222222223, "percentage": 62.49, "elapsed_time": "2:49:46", "remaining_time": "1:41:54", "throughput": 687.41, "total_tokens": 7002064} {"current_steps": 25000, "total_steps": 40000, "loss": 0.0, "lr": 1.543472825359828e-05, "epoch": 277.77777777777777, "percentage": 62.5, "elapsed_time": "2:49:48", "remaining_time": "1:41:52", "throughput": 687.41, "total_tokens": 7003408} {"current_steps": 25000, "total_steps": 40000, "eval_loss": 0.34609031677246094, "epoch": 277.77777777777777, "percentage": 62.5, "elapsed_time": "2:49:49", "remaining_time": "1:41:53", "throughput": 687.33, "total_tokens": 7003408} {"current_steps": 25005, "total_steps": 40000, "loss": 0.0, "lr": 1.5425658530228522e-05, "epoch": 277.8333333333333, "percentage": 62.51, "elapsed_time": "2:49:52", "remaining_time": "1:41:52", "throughput": 687.24, "total_tokens": 7004832} {"current_steps": 25010, "total_steps": 40000, "loss": 0.0, "lr": 1.5416590283342546e-05, "epoch": 277.8888888888889, "percentage": 62.52, "elapsed_time": "2:49:54", "remaining_time": "1:41:50", "throughput": 687.25, "total_tokens": 7006240} {"current_steps": 25015, "total_steps": 40000, "loss": 0.0, "lr": 1.5407523514338783e-05, "epoch": 277.94444444444446, "percentage": 62.54, "elapsed_time": "2:49:56", "remaining_time": "1:41:48", "throughput": 687.26, "total_tokens": 7007648} {"current_steps": 25020, "total_steps": 40000, "loss": 0.0, "lr": 1.539845822461543e-05, "epoch": 278.0, "percentage": 62.55, "elapsed_time": "2:49:58", "remaining_time": "1:41:46", "throughput": 687.25, "total_tokens": 7009024} {"current_steps": 25025, "total_steps": 40000, "loss": 0.0, "lr": 1.538939441557048e-05, "epoch": 278.05555555555554, "percentage": 62.56, "elapsed_time": "2:50:00", "remaining_time": "1:41:44", "throughput": 687.24, "total_tokens": 7010432} {"current_steps": 25030, "total_steps": 40000, "loss": 0.0, "lr": 1.5380332088601696e-05, "epoch": 278.1111111111111, "percentage": 62.58, "elapsed_time": "2:50:02", "remaining_time": "1:41:42", "throughput": 687.25, "total_tokens": 7011840} {"current_steps": 25035, "total_steps": 40000, "loss": 0.0, "lr": 1.537127124510658e-05, "epoch": 278.1666666666667, "percentage": 62.59, "elapsed_time": "2:50:04", "remaining_time": "1:41:40", "throughput": 687.26, "total_tokens": 7013264} {"current_steps": 25040, "total_steps": 40000, "loss": 0.0, "lr": 1.5362211886482457e-05, "epoch": 278.22222222222223, "percentage": 62.6, "elapsed_time": "2:50:06", "remaining_time": "1:41:37", "throughput": 687.26, "total_tokens": 7014640} {"current_steps": 25045, "total_steps": 40000, "loss": 0.0, "lr": 1.5353154014126363e-05, "epoch": 278.27777777777777, "percentage": 62.61, "elapsed_time": "2:50:08", "remaining_time": "1:41:35", "throughput": 687.27, "total_tokens": 7016048} {"current_steps": 25050, "total_steps": 40000, "loss": 0.0, "lr": 1.534409762943515e-05, "epoch": 278.3333333333333, "percentage": 62.62, "elapsed_time": "2:50:10", "remaining_time": "1:41:33", "throughput": 687.27, "total_tokens": 7017408} {"current_steps": 25055, "total_steps": 40000, "loss": 0.0, "lr": 1.5335042733805438e-05, "epoch": 278.3888888888889, "percentage": 62.64, "elapsed_time": "2:50:12", "remaining_time": "1:41:31", "throughput": 687.27, "total_tokens": 7018784} {"current_steps": 25060, "total_steps": 40000, "loss": 0.0, "lr": 1.532598932863358e-05, "epoch": 278.44444444444446, "percentage": 62.65, "elapsed_time": "2:50:14", "remaining_time": "1:41:29", "throughput": 687.28, "total_tokens": 7020176} {"current_steps": 25065, "total_steps": 40000, "loss": 0.0, "lr": 1.531693741531574e-05, "epoch": 278.5, "percentage": 62.66, "elapsed_time": "2:50:16", "remaining_time": "1:41:27", "throughput": 687.29, "total_tokens": 7021616} {"current_steps": 25070, "total_steps": 40000, "loss": 0.0, "lr": 1.5307886995247844e-05, "epoch": 278.55555555555554, "percentage": 62.68, "elapsed_time": "2:50:18", "remaining_time": "1:41:25", "throughput": 687.29, "total_tokens": 7022976} {"current_steps": 25075, "total_steps": 40000, "loss": 0.0, "lr": 1.529883806982557e-05, "epoch": 278.6111111111111, "percentage": 62.69, "elapsed_time": "2:50:20", "remaining_time": "1:41:23", "throughput": 687.3, "total_tokens": 7024416} {"current_steps": 25080, "total_steps": 40000, "loss": 0.0, "lr": 1.5289790640444376e-05, "epoch": 278.6666666666667, "percentage": 62.7, "elapsed_time": "2:50:22", "remaining_time": "1:41:21", "throughput": 687.31, "total_tokens": 7025824} {"current_steps": 25085, "total_steps": 40000, "loss": 0.0, "lr": 1.5280744708499494e-05, "epoch": 278.72222222222223, "percentage": 62.71, "elapsed_time": "2:50:24", "remaining_time": "1:41:19", "throughput": 687.32, "total_tokens": 7027200} {"current_steps": 25090, "total_steps": 40000, "loss": 0.0, "lr": 1.527170027538591e-05, "epoch": 278.77777777777777, "percentage": 62.72, "elapsed_time": "2:50:26", "remaining_time": "1:41:16", "throughput": 687.32, "total_tokens": 7028608} {"current_steps": 25095, "total_steps": 40000, "loss": 0.0, "lr": 1.5262657342498407e-05, "epoch": 278.8333333333333, "percentage": 62.74, "elapsed_time": "2:50:27", "remaining_time": "1:41:14", "throughput": 687.33, "total_tokens": 7030000} {"current_steps": 25100, "total_steps": 40000, "loss": 0.0, "lr": 1.52536159112315e-05, "epoch": 278.8888888888889, "percentage": 62.75, "elapsed_time": "2:50:29", "remaining_time": "1:41:12", "throughput": 687.33, "total_tokens": 7031392} {"current_steps": 25105, "total_steps": 40000, "loss": 0.0, "lr": 1.5244575982979497e-05, "epoch": 278.94444444444446, "percentage": 62.76, "elapsed_time": "2:50:31", "remaining_time": "1:41:10", "throughput": 687.34, "total_tokens": 7032816} {"current_steps": 25110, "total_steps": 40000, "loss": 0.0, "lr": 1.5235537559136487e-05, "epoch": 279.0, "percentage": 62.78, "elapsed_time": "2:50:33", "remaining_time": "1:41:08", "throughput": 687.34, "total_tokens": 7034240} {"current_steps": 25115, "total_steps": 40000, "loss": 0.0, "lr": 1.5226500641096286e-05, "epoch": 279.05555555555554, "percentage": 62.79, "elapsed_time": "2:50:36", "remaining_time": "1:41:06", "throughput": 687.33, "total_tokens": 7035648} {"current_steps": 25120, "total_steps": 40000, "loss": 0.0, "lr": 1.5217465230252509e-05, "epoch": 279.1111111111111, "percentage": 62.8, "elapsed_time": "2:50:38", "remaining_time": "1:41:04", "throughput": 687.33, "total_tokens": 7036992} {"current_steps": 25125, "total_steps": 40000, "loss": 0.0, "lr": 1.5208431327998523e-05, "epoch": 279.1666666666667, "percentage": 62.81, "elapsed_time": "2:50:40", "remaining_time": "1:41:02", "throughput": 687.34, "total_tokens": 7038416} {"current_steps": 25130, "total_steps": 40000, "loss": 0.0, "lr": 1.5199398935727477e-05, "epoch": 279.22222222222223, "percentage": 62.82, "elapsed_time": "2:50:41", "remaining_time": "1:41:00", "throughput": 687.35, "total_tokens": 7039856} {"current_steps": 25135, "total_steps": 40000, "loss": 0.0, "lr": 1.5190368054832282e-05, "epoch": 279.27777777777777, "percentage": 62.84, "elapsed_time": "2:50:43", "remaining_time": "1:40:58", "throughput": 687.36, "total_tokens": 7041232} {"current_steps": 25140, "total_steps": 40000, "loss": 0.0, "lr": 1.5181338686705601e-05, "epoch": 279.3333333333333, "percentage": 62.85, "elapsed_time": "2:50:45", "remaining_time": "1:40:56", "throughput": 687.36, "total_tokens": 7042640} {"current_steps": 25145, "total_steps": 40000, "loss": 0.0, "lr": 1.5172310832739889e-05, "epoch": 279.3888888888889, "percentage": 62.86, "elapsed_time": "2:50:47", "remaining_time": "1:40:54", "throughput": 687.37, "total_tokens": 7044032} {"current_steps": 25150, "total_steps": 40000, "loss": 0.0, "lr": 1.5163284494327346e-05, "epoch": 279.44444444444446, "percentage": 62.88, "elapsed_time": "2:50:49", "remaining_time": "1:40:52", "throughput": 687.37, "total_tokens": 7045408} {"current_steps": 25155, "total_steps": 40000, "loss": 0.0, "lr": 1.5154259672859952e-05, "epoch": 279.5, "percentage": 62.89, "elapsed_time": "2:50:51", "remaining_time": "1:40:49", "throughput": 687.38, "total_tokens": 7046816} {"current_steps": 25160, "total_steps": 40000, "loss": 0.0, "lr": 1.5145236369729452e-05, "epoch": 279.55555555555554, "percentage": 62.9, "elapsed_time": "2:50:53", "remaining_time": "1:40:47", "throughput": 687.39, "total_tokens": 7048240} {"current_steps": 25165, "total_steps": 40000, "loss": 0.0, "lr": 1.5136214586327335e-05, "epoch": 279.6111111111111, "percentage": 62.91, "elapsed_time": "2:50:55", "remaining_time": "1:40:45", "throughput": 687.4, "total_tokens": 7049680} {"current_steps": 25170, "total_steps": 40000, "loss": 0.0, "lr": 1.5127194324044885e-05, "epoch": 279.6666666666667, "percentage": 62.92, "elapsed_time": "2:50:57", "remaining_time": "1:40:43", "throughput": 687.41, "total_tokens": 7051072} {"current_steps": 25175, "total_steps": 40000, "loss": 0.0, "lr": 1.5118175584273148e-05, "epoch": 279.72222222222223, "percentage": 62.94, "elapsed_time": "2:50:59", "remaining_time": "1:40:41", "throughput": 687.41, "total_tokens": 7052464} {"current_steps": 25180, "total_steps": 40000, "loss": 0.0, "lr": 1.5109158368402909e-05, "epoch": 279.77777777777777, "percentage": 62.95, "elapsed_time": "2:51:01", "remaining_time": "1:40:39", "throughput": 687.42, "total_tokens": 7053888} {"current_steps": 25185, "total_steps": 40000, "loss": 0.0, "lr": 1.5100142677824753e-05, "epoch": 279.8333333333333, "percentage": 62.96, "elapsed_time": "2:51:03", "remaining_time": "1:40:37", "throughput": 687.42, "total_tokens": 7055264} {"current_steps": 25190, "total_steps": 40000, "loss": 0.0, "lr": 1.509112851392901e-05, "epoch": 279.8888888888889, "percentage": 62.98, "elapsed_time": "2:51:05", "remaining_time": "1:40:35", "throughput": 687.43, "total_tokens": 7056704} {"current_steps": 25195, "total_steps": 40000, "loss": 0.0, "lr": 1.5082115878105763e-05, "epoch": 279.94444444444446, "percentage": 62.99, "elapsed_time": "2:51:07", "remaining_time": "1:40:33", "throughput": 687.44, "total_tokens": 7058128} {"current_steps": 25200, "total_steps": 40000, "loss": 0.0, "lr": 1.5073104771744892e-05, "epoch": 280.0, "percentage": 63.0, "elapsed_time": "2:51:09", "remaining_time": "1:40:31", "throughput": 687.44, "total_tokens": 7059536} {"current_steps": 25200, "total_steps": 40000, "eval_loss": 0.33790481090545654, "epoch": 280.0, "percentage": 63.0, "elapsed_time": "2:51:10", "remaining_time": "1:40:31", "throughput": 687.35, "total_tokens": 7059536} {"current_steps": 25205, "total_steps": 40000, "loss": 0.0, "lr": 1.5064095196236006e-05, "epoch": 280.05555555555554, "percentage": 63.01, "elapsed_time": "2:51:14", "remaining_time": "1:40:30", "throughput": 687.25, "total_tokens": 7060928} {"current_steps": 25210, "total_steps": 40000, "loss": 0.0, "lr": 1.50550871529685e-05, "epoch": 280.1111111111111, "percentage": 63.02, "elapsed_time": "2:51:16", "remaining_time": "1:40:28", "throughput": 687.26, "total_tokens": 7062384} {"current_steps": 25215, "total_steps": 40000, "loss": 0.0, "lr": 1.5046080643331546e-05, "epoch": 280.1666666666667, "percentage": 63.04, "elapsed_time": "2:51:18", "remaining_time": "1:40:26", "throughput": 687.27, "total_tokens": 7063792} {"current_steps": 25220, "total_steps": 40000, "loss": 0.0, "lr": 1.5037075668714028e-05, "epoch": 280.22222222222223, "percentage": 63.05, "elapsed_time": "2:51:20", "remaining_time": "1:40:24", "throughput": 687.27, "total_tokens": 7065200} {"current_steps": 25225, "total_steps": 40000, "loss": 0.0, "lr": 1.5028072230504656e-05, "epoch": 280.27777777777777, "percentage": 63.06, "elapsed_time": "2:51:21", "remaining_time": "1:40:22", "throughput": 687.28, "total_tokens": 7066560} {"current_steps": 25230, "total_steps": 40000, "loss": 0.0, "lr": 1.5019070330091861e-05, "epoch": 280.3333333333333, "percentage": 63.08, "elapsed_time": "2:51:23", "remaining_time": "1:40:20", "throughput": 687.28, "total_tokens": 7067984} {"current_steps": 25235, "total_steps": 40000, "loss": 0.0, "lr": 1.5010069968863843e-05, "epoch": 280.3888888888889, "percentage": 63.09, "elapsed_time": "2:51:25", "remaining_time": "1:40:18", "throughput": 687.29, "total_tokens": 7069360} {"current_steps": 25240, "total_steps": 40000, "loss": 0.0, "lr": 1.5001071148208584e-05, "epoch": 280.44444444444446, "percentage": 63.1, "elapsed_time": "2:51:27", "remaining_time": "1:40:16", "throughput": 687.29, "total_tokens": 7070720} {"current_steps": 25245, "total_steps": 40000, "loss": 0.0, "lr": 1.49920738695138e-05, "epoch": 280.5, "percentage": 63.11, "elapsed_time": "2:51:29", "remaining_time": "1:40:14", "throughput": 687.3, "total_tokens": 7072128} {"current_steps": 25250, "total_steps": 40000, "loss": 0.0, "lr": 1.4983078134166995e-05, "epoch": 280.55555555555554, "percentage": 63.12, "elapsed_time": "2:51:31", "remaining_time": "1:40:11", "throughput": 687.3, "total_tokens": 7073488} {"current_steps": 25255, "total_steps": 40000, "loss": 0.0, "lr": 1.4974083943555428e-05, "epoch": 280.6111111111111, "percentage": 63.14, "elapsed_time": "2:51:33", "remaining_time": "1:40:09", "throughput": 687.31, "total_tokens": 7074880} {"current_steps": 25260, "total_steps": 40000, "loss": 0.0, "lr": 1.496509129906611e-05, "epoch": 280.6666666666667, "percentage": 63.15, "elapsed_time": "2:51:35", "remaining_time": "1:40:07", "throughput": 687.32, "total_tokens": 7076336} {"current_steps": 25265, "total_steps": 40000, "loss": 0.0, "lr": 1.4956100202085809e-05, "epoch": 280.72222222222223, "percentage": 63.16, "elapsed_time": "2:51:37", "remaining_time": "1:40:05", "throughput": 687.33, "total_tokens": 7077744} {"current_steps": 25270, "total_steps": 40000, "loss": 0.0, "lr": 1.4947110654001093e-05, "epoch": 280.77777777777777, "percentage": 63.18, "elapsed_time": "2:51:39", "remaining_time": "1:40:03", "throughput": 687.33, "total_tokens": 7079136} {"current_steps": 25275, "total_steps": 40000, "loss": 0.0, "lr": 1.4938122656198234e-05, "epoch": 280.8333333333333, "percentage": 63.19, "elapsed_time": "2:51:41", "remaining_time": "1:40:01", "throughput": 687.34, "total_tokens": 7080528} {"current_steps": 25280, "total_steps": 40000, "loss": 0.0, "lr": 1.4929136210063316e-05, "epoch": 280.8888888888889, "percentage": 63.2, "elapsed_time": "2:51:43", "remaining_time": "1:39:59", "throughput": 687.34, "total_tokens": 7081904} {"current_steps": 25285, "total_steps": 40000, "loss": 0.0, "lr": 1.4920151316982146e-05, "epoch": 280.94444444444446, "percentage": 63.21, "elapsed_time": "2:51:45", "remaining_time": "1:39:57", "throughput": 687.35, "total_tokens": 7083344} {"current_steps": 25290, "total_steps": 40000, "loss": 0.0, "lr": 1.4911167978340312e-05, "epoch": 281.0, "percentage": 63.22, "elapsed_time": "2:51:47", "remaining_time": "1:39:55", "throughput": 687.35, "total_tokens": 7084736} {"current_steps": 25295, "total_steps": 40000, "loss": 0.0, "lr": 1.4902186195523166e-05, "epoch": 281.05555555555554, "percentage": 63.24, "elapsed_time": "2:51:49", "remaining_time": "1:39:53", "throughput": 687.33, "total_tokens": 7086096} {"current_steps": 25300, "total_steps": 40000, "loss": 0.0, "lr": 1.4893205969915805e-05, "epoch": 281.1111111111111, "percentage": 63.25, "elapsed_time": "2:51:51", "remaining_time": "1:39:51", "throughput": 687.34, "total_tokens": 7087520} {"current_steps": 25305, "total_steps": 40000, "loss": 0.0, "lr": 1.4884227302903086e-05, "epoch": 281.1666666666667, "percentage": 63.26, "elapsed_time": "2:51:53", "remaining_time": "1:39:49", "throughput": 687.35, "total_tokens": 7088976} {"current_steps": 25310, "total_steps": 40000, "loss": 0.0, "lr": 1.4875250195869653e-05, "epoch": 281.22222222222223, "percentage": 63.28, "elapsed_time": "2:51:55", "remaining_time": "1:39:47", "throughput": 687.36, "total_tokens": 7090384} {"current_steps": 25315, "total_steps": 40000, "loss": 0.0, "lr": 1.4866274650199862e-05, "epoch": 281.27777777777777, "percentage": 63.29, "elapsed_time": "2:51:57", "remaining_time": "1:39:44", "throughput": 687.37, "total_tokens": 7091792} {"current_steps": 25320, "total_steps": 40000, "loss": 0.0, "lr": 1.485730066727788e-05, "epoch": 281.3333333333333, "percentage": 63.3, "elapsed_time": "2:51:59", "remaining_time": "1:39:42", "throughput": 687.37, "total_tokens": 7093168} {"current_steps": 25325, "total_steps": 40000, "loss": 0.0, "lr": 1.4848328248487586e-05, "epoch": 281.3888888888889, "percentage": 63.31, "elapsed_time": "2:52:01", "remaining_time": "1:39:40", "throughput": 687.37, "total_tokens": 7094512} {"current_steps": 25330, "total_steps": 40000, "loss": 0.0, "lr": 1.4839357395212656e-05, "epoch": 281.44444444444446, "percentage": 63.32, "elapsed_time": "2:52:03", "remaining_time": "1:39:38", "throughput": 687.38, "total_tokens": 7095968} {"current_steps": 25335, "total_steps": 40000, "loss": 0.0, "lr": 1.4830388108836502e-05, "epoch": 281.5, "percentage": 63.34, "elapsed_time": "2:52:05", "remaining_time": "1:39:36", "throughput": 687.39, "total_tokens": 7097344} {"current_steps": 25340, "total_steps": 40000, "loss": 0.0, "lr": 1.4821420390742299e-05, "epoch": 281.55555555555554, "percentage": 63.35, "elapsed_time": "2:52:07", "remaining_time": "1:39:34", "throughput": 687.39, "total_tokens": 7098688} {"current_steps": 25345, "total_steps": 40000, "loss": 0.0, "lr": 1.4812454242312979e-05, "epoch": 281.6111111111111, "percentage": 63.36, "elapsed_time": "2:52:08", "remaining_time": "1:39:32", "throughput": 687.4, "total_tokens": 7100112} {"current_steps": 25350, "total_steps": 40000, "loss": 0.0, "lr": 1.4803489664931253e-05, "epoch": 281.6666666666667, "percentage": 63.38, "elapsed_time": "2:52:10", "remaining_time": "1:39:30", "throughput": 687.4, "total_tokens": 7101504} {"current_steps": 25355, "total_steps": 40000, "loss": 0.0, "lr": 1.4794526659979544e-05, "epoch": 281.72222222222223, "percentage": 63.39, "elapsed_time": "2:52:12", "remaining_time": "1:39:28", "throughput": 687.42, "total_tokens": 7102960} {"current_steps": 25360, "total_steps": 40000, "loss": 0.0, "lr": 1.4785565228840086e-05, "epoch": 281.77777777777777, "percentage": 63.4, "elapsed_time": "2:52:14", "remaining_time": "1:39:26", "throughput": 687.42, "total_tokens": 7104368} {"current_steps": 25365, "total_steps": 40000, "loss": 0.0, "lr": 1.4776605372894819e-05, "epoch": 281.8333333333333, "percentage": 63.41, "elapsed_time": "2:52:16", "remaining_time": "1:39:24", "throughput": 687.43, "total_tokens": 7105808} {"current_steps": 25370, "total_steps": 40000, "loss": 0.0, "lr": 1.4767647093525488e-05, "epoch": 281.8888888888889, "percentage": 63.42, "elapsed_time": "2:52:18", "remaining_time": "1:39:21", "throughput": 687.44, "total_tokens": 7107200} {"current_steps": 25375, "total_steps": 40000, "loss": 0.0, "lr": 1.4758690392113566e-05, "epoch": 281.94444444444446, "percentage": 63.44, "elapsed_time": "2:52:20", "remaining_time": "1:39:19", "throughput": 687.44, "total_tokens": 7108560} {"current_steps": 25380, "total_steps": 40000, "loss": 0.0, "lr": 1.4749735270040276e-05, "epoch": 282.0, "percentage": 63.45, "elapsed_time": "2:52:22", "remaining_time": "1:39:17", "throughput": 687.44, "total_tokens": 7109968} {"current_steps": 25385, "total_steps": 40000, "loss": 0.0, "lr": 1.4740781728686623e-05, "epoch": 282.05555555555554, "percentage": 63.46, "elapsed_time": "2:52:24", "remaining_time": "1:39:15", "throughput": 687.43, "total_tokens": 7111360} {"current_steps": 25390, "total_steps": 40000, "loss": 0.0, "lr": 1.4731829769433358e-05, "epoch": 282.1111111111111, "percentage": 63.48, "elapsed_time": "2:52:26", "remaining_time": "1:39:13", "throughput": 687.42, "total_tokens": 7112672} {"current_steps": 25395, "total_steps": 40000, "loss": 0.0, "lr": 1.4722879393660976e-05, "epoch": 282.1666666666667, "percentage": 63.49, "elapsed_time": "2:52:28", "remaining_time": "1:39:11", "throughput": 687.44, "total_tokens": 7114128} {"current_steps": 25400, "total_steps": 40000, "loss": 0.0, "lr": 1.4713930602749748e-05, "epoch": 282.22222222222223, "percentage": 63.5, "elapsed_time": "2:52:30", "remaining_time": "1:39:09", "throughput": 687.44, "total_tokens": 7115504} {"current_steps": 25400, "total_steps": 40000, "eval_loss": 0.34881898760795593, "epoch": 282.22222222222223, "percentage": 63.5, "elapsed_time": "2:52:32", "remaining_time": "1:39:10", "throughput": 687.35, "total_tokens": 7115504} {"current_steps": 25405, "total_steps": 40000, "loss": 0.0, "lr": 1.470498339807968e-05, "epoch": 282.27777777777777, "percentage": 63.51, "elapsed_time": "2:52:35", "remaining_time": "1:39:09", "throughput": 687.27, "total_tokens": 7116928} {"current_steps": 25410, "total_steps": 40000, "loss": 0.0, "lr": 1.4696037781030542e-05, "epoch": 282.3333333333333, "percentage": 63.52, "elapsed_time": "2:52:37", "remaining_time": "1:39:06", "throughput": 687.28, "total_tokens": 7118320} {"current_steps": 25415, "total_steps": 40000, "loss": 0.0, "lr": 1.4687093752981876e-05, "epoch": 282.3888888888889, "percentage": 63.54, "elapsed_time": "2:52:39", "remaining_time": "1:39:04", "throughput": 687.28, "total_tokens": 7119696} {"current_steps": 25420, "total_steps": 40000, "loss": 0.0, "lr": 1.4678151315312943e-05, "epoch": 282.44444444444446, "percentage": 63.55, "elapsed_time": "2:52:41", "remaining_time": "1:39:02", "throughput": 687.29, "total_tokens": 7121136} {"current_steps": 25425, "total_steps": 40000, "loss": 0.0, "lr": 1.4669210469402789e-05, "epoch": 282.5, "percentage": 63.56, "elapsed_time": "2:52:43", "remaining_time": "1:39:00", "throughput": 687.3, "total_tokens": 7122544} {"current_steps": 25430, "total_steps": 40000, "loss": 0.0, "lr": 1.4660271216630218e-05, "epoch": 282.55555555555554, "percentage": 63.58, "elapsed_time": "2:52:45", "remaining_time": "1:38:58", "throughput": 687.3, "total_tokens": 7123952} {"current_steps": 25435, "total_steps": 40000, "loss": 0.0, "lr": 1.4651333558373748e-05, "epoch": 282.6111111111111, "percentage": 63.59, "elapsed_time": "2:52:47", "remaining_time": "1:38:56", "throughput": 687.31, "total_tokens": 7125344} {"current_steps": 25440, "total_steps": 40000, "loss": 0.0, "lr": 1.4642397496011707e-05, "epoch": 282.6666666666667, "percentage": 63.6, "elapsed_time": "2:52:48", "remaining_time": "1:38:54", "throughput": 687.32, "total_tokens": 7126784} {"current_steps": 25445, "total_steps": 40000, "loss": 0.0, "lr": 1.4633463030922129e-05, "epoch": 282.72222222222223, "percentage": 63.61, "elapsed_time": "2:52:50", "remaining_time": "1:38:52", "throughput": 687.33, "total_tokens": 7128192} {"current_steps": 25450, "total_steps": 40000, "loss": 0.0, "lr": 1.462453016448282e-05, "epoch": 282.77777777777777, "percentage": 63.62, "elapsed_time": "2:52:52", "remaining_time": "1:38:50", "throughput": 687.33, "total_tokens": 7129600} {"current_steps": 25455, "total_steps": 40000, "loss": 0.0, "lr": 1.4615598898071354e-05, "epoch": 282.8333333333333, "percentage": 63.64, "elapsed_time": "2:52:54", "remaining_time": "1:38:48", "throughput": 687.34, "total_tokens": 7131024} {"current_steps": 25460, "total_steps": 40000, "loss": 0.0, "lr": 1.4606669233065026e-05, "epoch": 282.8888888888889, "percentage": 63.65, "elapsed_time": "2:52:56", "remaining_time": "1:38:46", "throughput": 687.35, "total_tokens": 7132416} {"current_steps": 25465, "total_steps": 40000, "loss": 0.0, "lr": 1.4597741170840914e-05, "epoch": 282.94444444444446, "percentage": 63.66, "elapsed_time": "2:52:58", "remaining_time": "1:38:43", "throughput": 687.35, "total_tokens": 7133808} {"current_steps": 25470, "total_steps": 40000, "loss": 0.0, "lr": 1.4588814712775853e-05, "epoch": 283.0, "percentage": 63.68, "elapsed_time": "2:53:00", "remaining_time": "1:38:41", "throughput": 687.35, "total_tokens": 7135216} {"current_steps": 25475, "total_steps": 40000, "loss": 0.0, "lr": 1.4579889860246382e-05, "epoch": 283.05555555555554, "percentage": 63.69, "elapsed_time": "2:53:02", "remaining_time": "1:38:40", "throughput": 687.34, "total_tokens": 7136592} {"current_steps": 25480, "total_steps": 40000, "loss": 0.0, "lr": 1.457096661462885e-05, "epoch": 283.1111111111111, "percentage": 63.7, "elapsed_time": "2:53:04", "remaining_time": "1:38:37", "throughput": 687.34, "total_tokens": 7137984} {"current_steps": 25485, "total_steps": 40000, "loss": 0.0, "lr": 1.4562044977299322e-05, "epoch": 283.1666666666667, "percentage": 63.71, "elapsed_time": "2:53:06", "remaining_time": "1:38:35", "throughput": 687.35, "total_tokens": 7139392} {"current_steps": 25490, "total_steps": 40000, "loss": 0.0, "lr": 1.4553124949633623e-05, "epoch": 283.22222222222223, "percentage": 63.73, "elapsed_time": "2:53:08", "remaining_time": "1:38:33", "throughput": 687.36, "total_tokens": 7140816} {"current_steps": 25495, "total_steps": 40000, "loss": 0.0, "lr": 1.4544206533007354e-05, "epoch": 283.27777777777777, "percentage": 63.74, "elapsed_time": "2:53:10", "remaining_time": "1:38:31", "throughput": 687.37, "total_tokens": 7142256} {"current_steps": 25500, "total_steps": 40000, "loss": 0.0, "lr": 1.4535289728795821e-05, "epoch": 283.3333333333333, "percentage": 63.75, "elapsed_time": "2:53:12", "remaining_time": "1:38:29", "throughput": 687.38, "total_tokens": 7143680} {"current_steps": 25505, "total_steps": 40000, "loss": 0.0, "lr": 1.4526374538374132e-05, "epoch": 283.3888888888889, "percentage": 63.76, "elapsed_time": "2:53:14", "remaining_time": "1:38:27", "throughput": 687.38, "total_tokens": 7145056} {"current_steps": 25510, "total_steps": 40000, "loss": 0.0, "lr": 1.4517460963117097e-05, "epoch": 283.44444444444446, "percentage": 63.78, "elapsed_time": "2:53:16", "remaining_time": "1:38:25", "throughput": 687.39, "total_tokens": 7146480} {"current_steps": 25515, "total_steps": 40000, "loss": 0.0, "lr": 1.4508549004399314e-05, "epoch": 283.5, "percentage": 63.79, "elapsed_time": "2:53:18", "remaining_time": "1:38:23", "throughput": 687.4, "total_tokens": 7147888} {"current_steps": 25520, "total_steps": 40000, "loss": 0.0, "lr": 1.449963866359513e-05, "epoch": 283.55555555555554, "percentage": 63.8, "elapsed_time": "2:53:20", "remaining_time": "1:38:21", "throughput": 687.4, "total_tokens": 7149232} {"current_steps": 25525, "total_steps": 40000, "loss": 0.0, "lr": 1.4490729942078607e-05, "epoch": 283.6111111111111, "percentage": 63.81, "elapsed_time": "2:53:22", "remaining_time": "1:38:19", "throughput": 687.4, "total_tokens": 7150624} {"current_steps": 25530, "total_steps": 40000, "loss": 0.0, "lr": 1.4481822841223608e-05, "epoch": 283.6666666666667, "percentage": 63.82, "elapsed_time": "2:53:24", "remaining_time": "1:38:16", "throughput": 687.41, "total_tokens": 7152048} {"current_steps": 25535, "total_steps": 40000, "loss": 0.0, "lr": 1.4472917362403704e-05, "epoch": 283.72222222222223, "percentage": 63.84, "elapsed_time": "2:53:26", "remaining_time": "1:38:14", "throughput": 687.42, "total_tokens": 7153456} {"current_steps": 25540, "total_steps": 40000, "loss": 0.0, "lr": 1.4464013506992224e-05, "epoch": 283.77777777777777, "percentage": 63.85, "elapsed_time": "2:53:28", "remaining_time": "1:38:12", "throughput": 687.43, "total_tokens": 7154832} {"current_steps": 25545, "total_steps": 40000, "loss": 0.0, "lr": 1.4455111276362277e-05, "epoch": 283.8333333333333, "percentage": 63.86, "elapsed_time": "2:53:30", "remaining_time": "1:38:10", "throughput": 687.44, "total_tokens": 7156272} {"current_steps": 25550, "total_steps": 40000, "loss": 0.0, "lr": 1.4446210671886676e-05, "epoch": 283.8888888888889, "percentage": 63.88, "elapsed_time": "2:53:32", "remaining_time": "1:38:08", "throughput": 687.44, "total_tokens": 7157664} {"current_steps": 25555, "total_steps": 40000, "loss": 0.0, "lr": 1.4437311694938015e-05, "epoch": 283.94444444444446, "percentage": 63.89, "elapsed_time": "2:53:33", "remaining_time": "1:38:06", "throughput": 687.45, "total_tokens": 7159072} {"current_steps": 25560, "total_steps": 40000, "loss": 0.0, "lr": 1.442841434688864e-05, "epoch": 284.0, "percentage": 63.9, "elapsed_time": "2:53:36", "remaining_time": "1:38:04", "throughput": 687.44, "total_tokens": 7160464} {"current_steps": 25565, "total_steps": 40000, "loss": 0.0, "lr": 1.4419518629110615e-05, "epoch": 284.05555555555554, "percentage": 63.91, "elapsed_time": "2:53:38", "remaining_time": "1:38:02", "throughput": 687.44, "total_tokens": 7161904} {"current_steps": 25570, "total_steps": 40000, "loss": 0.0, "lr": 1.4410624542975778e-05, "epoch": 284.1111111111111, "percentage": 63.92, "elapsed_time": "2:53:40", "remaining_time": "1:38:00", "throughput": 687.45, "total_tokens": 7163344} {"current_steps": 25575, "total_steps": 40000, "loss": 0.0, "lr": 1.4401732089855724e-05, "epoch": 284.1666666666667, "percentage": 63.94, "elapsed_time": "2:53:42", "remaining_time": "1:37:58", "throughput": 687.45, "total_tokens": 7164688} {"current_steps": 25580, "total_steps": 40000, "loss": 0.0, "lr": 1.4392841271121754e-05, "epoch": 284.22222222222223, "percentage": 63.95, "elapsed_time": "2:53:44", "remaining_time": "1:37:56", "throughput": 687.46, "total_tokens": 7166128} {"current_steps": 25585, "total_steps": 40000, "loss": 0.0, "lr": 1.438395208814497e-05, "epoch": 284.27777777777777, "percentage": 63.96, "elapsed_time": "2:53:46", "remaining_time": "1:37:54", "throughput": 687.47, "total_tokens": 7167552} {"current_steps": 25590, "total_steps": 40000, "loss": 0.0, "lr": 1.4375064542296174e-05, "epoch": 284.3333333333333, "percentage": 63.98, "elapsed_time": "2:53:47", "remaining_time": "1:37:52", "throughput": 687.47, "total_tokens": 7168960} {"current_steps": 25595, "total_steps": 40000, "loss": 0.0, "lr": 1.4366178634945946e-05, "epoch": 284.3888888888889, "percentage": 63.99, "elapsed_time": "2:53:49", "remaining_time": "1:37:50", "throughput": 687.47, "total_tokens": 7170304} {"current_steps": 25600, "total_steps": 40000, "loss": 0.0, "lr": 1.4357294367464616e-05, "epoch": 284.44444444444446, "percentage": 64.0, "elapsed_time": "2:53:51", "remaining_time": "1:37:47", "throughput": 687.48, "total_tokens": 7171744} {"current_steps": 25600, "total_steps": 40000, "eval_loss": 0.36703360080718994, "epoch": 284.44444444444446, "percentage": 64.0, "elapsed_time": "2:53:53", "remaining_time": "1:37:48", "throughput": 687.4, "total_tokens": 7171744} {"current_steps": 25605, "total_steps": 40000, "loss": 0.0, "lr": 1.434841174122224e-05, "epoch": 284.5, "percentage": 64.01, "elapsed_time": "2:53:56", "remaining_time": "1:37:47", "throughput": 687.32, "total_tokens": 7173152} {"current_steps": 25610, "total_steps": 40000, "loss": 0.0, "lr": 1.4339530757588615e-05, "epoch": 284.55555555555554, "percentage": 64.03, "elapsed_time": "2:53:58", "remaining_time": "1:37:45", "throughput": 687.32, "total_tokens": 7174496} {"current_steps": 25615, "total_steps": 40000, "loss": 0.0, "lr": 1.433065141793333e-05, "epoch": 284.6111111111111, "percentage": 64.04, "elapsed_time": "2:54:00", "remaining_time": "1:37:43", "throughput": 687.32, "total_tokens": 7175904} {"current_steps": 25620, "total_steps": 40000, "loss": 0.0, "lr": 1.4321773723625665e-05, "epoch": 284.6666666666667, "percentage": 64.05, "elapsed_time": "2:54:02", "remaining_time": "1:37:41", "throughput": 687.33, "total_tokens": 7177296} {"current_steps": 25625, "total_steps": 40000, "loss": 0.0, "lr": 1.4312897676034693e-05, "epoch": 284.72222222222223, "percentage": 64.06, "elapsed_time": "2:54:04", "remaining_time": "1:37:38", "throughput": 687.34, "total_tokens": 7178720} {"current_steps": 25630, "total_steps": 40000, "loss": 0.0, "lr": 1.4304023276529188e-05, "epoch": 284.77777777777777, "percentage": 64.08, "elapsed_time": "2:54:06", "remaining_time": "1:37:36", "throughput": 687.34, "total_tokens": 7180112} {"current_steps": 25635, "total_steps": 40000, "loss": 0.0, "lr": 1.4295150526477712e-05, "epoch": 284.8333333333333, "percentage": 64.09, "elapsed_time": "2:54:08", "remaining_time": "1:37:34", "throughput": 687.35, "total_tokens": 7181488} {"current_steps": 25640, "total_steps": 40000, "loss": 0.0, "lr": 1.4286279427248562e-05, "epoch": 284.8888888888889, "percentage": 64.1, "elapsed_time": "2:54:10", "remaining_time": "1:37:32", "throughput": 687.35, "total_tokens": 7182880} {"current_steps": 25645, "total_steps": 40000, "loss": 0.0, "lr": 1.4277409980209747e-05, "epoch": 284.94444444444446, "percentage": 64.11, "elapsed_time": "2:54:11", "remaining_time": "1:37:30", "throughput": 687.36, "total_tokens": 7184304} {"current_steps": 25650, "total_steps": 40000, "loss": 0.0, "lr": 1.4268542186729061e-05, "epoch": 285.0, "percentage": 64.12, "elapsed_time": "2:54:14", "remaining_time": "1:37:28", "throughput": 687.36, "total_tokens": 7185696} {"current_steps": 25655, "total_steps": 40000, "loss": 0.0, "lr": 1.4259676048174043e-05, "epoch": 285.05555555555554, "percentage": 64.14, "elapsed_time": "2:54:16", "remaining_time": "1:37:26", "throughput": 687.35, "total_tokens": 7187088} {"current_steps": 25660, "total_steps": 40000, "loss": 0.0, "lr": 1.4250811565911937e-05, "epoch": 285.1111111111111, "percentage": 64.15, "elapsed_time": "2:54:18", "remaining_time": "1:37:24", "throughput": 687.35, "total_tokens": 7188464} {"current_steps": 25665, "total_steps": 40000, "loss": 0.0, "lr": 1.4241948741309782e-05, "epoch": 285.1666666666667, "percentage": 64.16, "elapsed_time": "2:54:20", "remaining_time": "1:37:22", "throughput": 687.36, "total_tokens": 7189856} {"current_steps": 25670, "total_steps": 40000, "loss": 0.0, "lr": 1.4233087575734317e-05, "epoch": 285.22222222222223, "percentage": 64.18, "elapsed_time": "2:54:22", "remaining_time": "1:37:20", "throughput": 687.37, "total_tokens": 7191280} {"current_steps": 25675, "total_steps": 40000, "loss": 0.0, "lr": 1.422422807055206e-05, "epoch": 285.27777777777777, "percentage": 64.19, "elapsed_time": "2:54:24", "remaining_time": "1:37:18", "throughput": 687.37, "total_tokens": 7192704} {"current_steps": 25680, "total_steps": 40000, "loss": 0.0, "lr": 1.4215370227129243e-05, "epoch": 285.3333333333333, "percentage": 64.2, "elapsed_time": "2:54:25", "remaining_time": "1:37:16", "throughput": 687.39, "total_tokens": 7194160} {"current_steps": 25685, "total_steps": 40000, "loss": 0.0, "lr": 1.4206514046831876e-05, "epoch": 285.3888888888889, "percentage": 64.21, "elapsed_time": "2:54:27", "remaining_time": "1:37:14", "throughput": 687.39, "total_tokens": 7195536} {"current_steps": 25690, "total_steps": 40000, "loss": 0.0, "lr": 1.419765953102567e-05, "epoch": 285.44444444444446, "percentage": 64.22, "elapsed_time": "2:54:29", "remaining_time": "1:37:11", "throughput": 687.39, "total_tokens": 7196912} {"current_steps": 25695, "total_steps": 40000, "loss": 0.0, "lr": 1.4188806681076125e-05, "epoch": 285.5, "percentage": 64.24, "elapsed_time": "2:54:31", "remaining_time": "1:37:09", "throughput": 687.4, "total_tokens": 7198272} {"current_steps": 25700, "total_steps": 40000, "loss": 0.0, "lr": 1.4179955498348443e-05, "epoch": 285.55555555555554, "percentage": 64.25, "elapsed_time": "2:54:33", "remaining_time": "1:37:07", "throughput": 687.41, "total_tokens": 7199728} {"current_steps": 25705, "total_steps": 40000, "loss": 0.0, "lr": 1.4171105984207605e-05, "epoch": 285.6111111111111, "percentage": 64.26, "elapsed_time": "2:54:35", "remaining_time": "1:37:05", "throughput": 687.41, "total_tokens": 7201088} {"current_steps": 25710, "total_steps": 40000, "loss": 0.0, "lr": 1.4162258140018304e-05, "epoch": 285.6666666666667, "percentage": 64.28, "elapsed_time": "2:54:37", "remaining_time": "1:37:03", "throughput": 687.42, "total_tokens": 7202512} {"current_steps": 25715, "total_steps": 40000, "loss": 0.0, "lr": 1.4153411967144986e-05, "epoch": 285.72222222222223, "percentage": 64.29, "elapsed_time": "2:54:39", "remaining_time": "1:37:01", "throughput": 687.43, "total_tokens": 7203920} {"current_steps": 25720, "total_steps": 40000, "loss": 0.0, "lr": 1.4144567466951864e-05, "epoch": 285.77777777777777, "percentage": 64.3, "elapsed_time": "2:54:41", "remaining_time": "1:36:59", "throughput": 687.44, "total_tokens": 7205376} {"current_steps": 25725, "total_steps": 40000, "loss": 0.0, "lr": 1.4135724640802844e-05, "epoch": 285.8333333333333, "percentage": 64.31, "elapsed_time": "2:54:43", "remaining_time": "1:36:57", "throughput": 687.44, "total_tokens": 7206736} {"current_steps": 25730, "total_steps": 40000, "loss": 0.0, "lr": 1.4126883490061615e-05, "epoch": 285.8888888888889, "percentage": 64.33, "elapsed_time": "2:54:45", "remaining_time": "1:36:55", "throughput": 687.45, "total_tokens": 7208128} {"current_steps": 25735, "total_steps": 40000, "loss": 0.0, "lr": 1.4118044016091603e-05, "epoch": 285.94444444444446, "percentage": 64.34, "elapsed_time": "2:54:47", "remaining_time": "1:36:53", "throughput": 687.45, "total_tokens": 7209520} {"current_steps": 25740, "total_steps": 40000, "loss": 0.0, "lr": 1.410920622025594e-05, "epoch": 286.0, "percentage": 64.35, "elapsed_time": "2:54:49", "remaining_time": "1:36:51", "throughput": 687.45, "total_tokens": 7210944} {"current_steps": 25745, "total_steps": 40000, "loss": 0.0, "lr": 1.4100370103917554e-05, "epoch": 286.05555555555554, "percentage": 64.36, "elapsed_time": "2:54:51", "remaining_time": "1:36:49", "throughput": 687.44, "total_tokens": 7212304} {"current_steps": 25750, "total_steps": 40000, "loss": 0.0, "lr": 1.409153566843907e-05, "epoch": 286.1111111111111, "percentage": 64.38, "elapsed_time": "2:54:53", "remaining_time": "1:36:47", "throughput": 687.44, "total_tokens": 7213680} {"current_steps": 25755, "total_steps": 40000, "loss": 0.0, "lr": 1.408270291518286e-05, "epoch": 286.1666666666667, "percentage": 64.39, "elapsed_time": "2:54:55", "remaining_time": "1:36:45", "throughput": 687.45, "total_tokens": 7215104} {"current_steps": 25760, "total_steps": 40000, "loss": 0.0, "lr": 1.407387184551107e-05, "epoch": 286.22222222222223, "percentage": 64.4, "elapsed_time": "2:54:57", "remaining_time": "1:36:42", "throughput": 687.46, "total_tokens": 7216512} {"current_steps": 25765, "total_steps": 40000, "loss": 0.0, "lr": 1.4065042460785532e-05, "epoch": 286.27777777777777, "percentage": 64.41, "elapsed_time": "2:54:59", "remaining_time": "1:36:40", "throughput": 687.46, "total_tokens": 7217920} {"current_steps": 25770, "total_steps": 40000, "loss": 0.0, "lr": 1.405621476236787e-05, "epoch": 286.3333333333333, "percentage": 64.42, "elapsed_time": "2:55:01", "remaining_time": "1:36:38", "throughput": 687.47, "total_tokens": 7219344} {"current_steps": 25775, "total_steps": 40000, "loss": 0.0, "lr": 1.4047388751619423e-05, "epoch": 286.3888888888889, "percentage": 64.44, "elapsed_time": "2:55:03", "remaining_time": "1:36:36", "throughput": 687.48, "total_tokens": 7220720} {"current_steps": 25780, "total_steps": 40000, "loss": 0.0, "lr": 1.4038564429901264e-05, "epoch": 286.44444444444446, "percentage": 64.45, "elapsed_time": "2:55:05", "remaining_time": "1:36:34", "throughput": 687.48, "total_tokens": 7222112} {"current_steps": 25785, "total_steps": 40000, "loss": 0.0, "lr": 1.4029741798574227e-05, "epoch": 286.5, "percentage": 64.46, "elapsed_time": "2:55:07", "remaining_time": "1:36:32", "throughput": 687.49, "total_tokens": 7223520} {"current_steps": 25790, "total_steps": 40000, "loss": 0.0, "lr": 1.402092085899886e-05, "epoch": 286.55555555555554, "percentage": 64.48, "elapsed_time": "2:55:09", "remaining_time": "1:36:30", "throughput": 687.5, "total_tokens": 7224928} {"current_steps": 25795, "total_steps": 40000, "loss": 0.0, "lr": 1.4012101612535464e-05, "epoch": 286.6111111111111, "percentage": 64.49, "elapsed_time": "2:55:10", "remaining_time": "1:36:28", "throughput": 687.5, "total_tokens": 7226304} {"current_steps": 25800, "total_steps": 40000, "loss": 0.0, "lr": 1.4003284060544092e-05, "epoch": 286.6666666666667, "percentage": 64.5, "elapsed_time": "2:55:12", "remaining_time": "1:36:26", "throughput": 687.51, "total_tokens": 7227712} {"current_steps": 25800, "total_steps": 40000, "eval_loss": 0.3276625871658325, "epoch": 286.6666666666667, "percentage": 64.5, "elapsed_time": "2:55:14", "remaining_time": "1:36:26", "throughput": 687.42, "total_tokens": 7227712} {"current_steps": 25805, "total_steps": 40000, "loss": 0.0, "lr": 1.3994468204384504e-05, "epoch": 286.72222222222223, "percentage": 64.51, "elapsed_time": "2:55:17", "remaining_time": "1:36:25", "throughput": 687.34, "total_tokens": 7229136} {"current_steps": 25810, "total_steps": 40000, "loss": 0.0, "lr": 1.398565404541622e-05, "epoch": 286.77777777777777, "percentage": 64.53, "elapsed_time": "2:55:19", "remaining_time": "1:36:23", "throughput": 687.34, "total_tokens": 7230480} {"current_steps": 25815, "total_steps": 40000, "loss": 0.0, "lr": 1.3976841584998513e-05, "epoch": 286.8333333333333, "percentage": 64.54, "elapsed_time": "2:55:21", "remaining_time": "1:36:21", "throughput": 687.35, "total_tokens": 7231904} {"current_steps": 25820, "total_steps": 40000, "loss": 0.0, "lr": 1.3968030824490352e-05, "epoch": 286.8888888888889, "percentage": 64.55, "elapsed_time": "2:55:23", "remaining_time": "1:36:19", "throughput": 687.36, "total_tokens": 7233328} {"current_steps": 25825, "total_steps": 40000, "loss": 0.0, "lr": 1.3959221765250469e-05, "epoch": 286.94444444444446, "percentage": 64.56, "elapsed_time": "2:55:25", "remaining_time": "1:36:17", "throughput": 687.37, "total_tokens": 7234736} {"current_steps": 25830, "total_steps": 40000, "loss": 0.0, "lr": 1.3950414408637343e-05, "epoch": 287.0, "percentage": 64.58, "elapsed_time": "2:55:27", "remaining_time": "1:36:15", "throughput": 687.36, "total_tokens": 7236144} {"current_steps": 25835, "total_steps": 40000, "loss": 0.0, "lr": 1.3941608756009166e-05, "epoch": 287.05555555555554, "percentage": 64.59, "elapsed_time": "2:55:29", "remaining_time": "1:36:13", "throughput": 687.36, "total_tokens": 7237584} {"current_steps": 25840, "total_steps": 40000, "loss": 0.0, "lr": 1.3932804808723898e-05, "epoch": 287.1111111111111, "percentage": 64.6, "elapsed_time": "2:55:31", "remaining_time": "1:36:11", "throughput": 687.34, "total_tokens": 7238976} {"current_steps": 25845, "total_steps": 40000, "loss": 0.0, "lr": 1.3924002568139194e-05, "epoch": 287.1666666666667, "percentage": 64.61, "elapsed_time": "2:55:33", "remaining_time": "1:36:09", "throughput": 687.35, "total_tokens": 7240368} {"current_steps": 25850, "total_steps": 40000, "loss": 0.0, "lr": 1.3915202035612485e-05, "epoch": 287.22222222222223, "percentage": 64.62, "elapsed_time": "2:55:35", "remaining_time": "1:36:07", "throughput": 687.35, "total_tokens": 7241760} {"current_steps": 25855, "total_steps": 40000, "loss": 0.0, "lr": 1.3906403212500935e-05, "epoch": 287.27777777777777, "percentage": 64.64, "elapsed_time": "2:55:37", "remaining_time": "1:36:05", "throughput": 687.36, "total_tokens": 7243168} {"current_steps": 25860, "total_steps": 40000, "loss": 0.0, "lr": 1.3897606100161409e-05, "epoch": 287.3333333333333, "percentage": 64.65, "elapsed_time": "2:55:39", "remaining_time": "1:36:02", "throughput": 687.37, "total_tokens": 7244560} {"current_steps": 25865, "total_steps": 40000, "loss": 0.0, "lr": 1.388881069995055e-05, "epoch": 287.3888888888889, "percentage": 64.66, "elapsed_time": "2:55:41", "remaining_time": "1:36:00", "throughput": 687.37, "total_tokens": 7245952} {"current_steps": 25870, "total_steps": 40000, "loss": 0.0, "lr": 1.3880017013224708e-05, "epoch": 287.44444444444446, "percentage": 64.68, "elapsed_time": "2:55:43", "remaining_time": "1:35:58", "throughput": 687.38, "total_tokens": 7247328} {"current_steps": 25875, "total_steps": 40000, "loss": 0.0, "lr": 1.3871225041339984e-05, "epoch": 287.5, "percentage": 64.69, "elapsed_time": "2:55:45", "remaining_time": "1:35:56", "throughput": 687.38, "total_tokens": 7248720} {"current_steps": 25880, "total_steps": 40000, "loss": 0.0, "lr": 1.386243478565222e-05, "epoch": 287.55555555555554, "percentage": 64.7, "elapsed_time": "2:55:47", "remaining_time": "1:35:54", "throughput": 687.39, "total_tokens": 7250112} {"current_steps": 25885, "total_steps": 40000, "loss": 0.0, "lr": 1.3853646247516966e-05, "epoch": 287.6111111111111, "percentage": 64.71, "elapsed_time": "2:55:49", "remaining_time": "1:35:52", "throughput": 687.39, "total_tokens": 7251488} {"current_steps": 25890, "total_steps": 40000, "loss": 0.0, "lr": 1.3844859428289545e-05, "epoch": 287.6666666666667, "percentage": 64.72, "elapsed_time": "2:55:51", "remaining_time": "1:35:50", "throughput": 687.4, "total_tokens": 7252880} {"current_steps": 25895, "total_steps": 40000, "loss": 0.0, "lr": 1.3836074329324984e-05, "epoch": 287.72222222222223, "percentage": 64.74, "elapsed_time": "2:55:53", "remaining_time": "1:35:48", "throughput": 687.41, "total_tokens": 7254320} {"current_steps": 25900, "total_steps": 40000, "loss": 0.0, "lr": 1.3827290951978044e-05, "epoch": 287.77777777777777, "percentage": 64.75, "elapsed_time": "2:55:55", "remaining_time": "1:35:46", "throughput": 687.42, "total_tokens": 7255744} {"current_steps": 25905, "total_steps": 40000, "loss": 0.0, "lr": 1.381850929760326e-05, "epoch": 287.8333333333333, "percentage": 64.76, "elapsed_time": "2:55:57", "remaining_time": "1:35:44", "throughput": 687.42, "total_tokens": 7257136} {"current_steps": 25910, "total_steps": 40000, "loss": 0.0, "lr": 1.3809729367554842e-05, "epoch": 287.8888888888889, "percentage": 64.78, "elapsed_time": "2:55:58", "remaining_time": "1:35:42", "throughput": 687.43, "total_tokens": 7258512} {"current_steps": 25915, "total_steps": 40000, "loss": 0.0, "lr": 1.3800951163186784e-05, "epoch": 287.94444444444446, "percentage": 64.79, "elapsed_time": "2:56:00", "remaining_time": "1:35:39", "throughput": 687.43, "total_tokens": 7259936} {"current_steps": 25920, "total_steps": 40000, "loss": 0.0, "lr": 1.3792174685852801e-05, "epoch": 288.0, "percentage": 64.8, "elapsed_time": "2:56:03", "remaining_time": "1:35:37", "throughput": 687.43, "total_tokens": 7261328} {"current_steps": 25925, "total_steps": 40000, "loss": 0.0, "lr": 1.378339993690632e-05, "epoch": 288.05555555555554, "percentage": 64.81, "elapsed_time": "2:56:05", "remaining_time": "1:35:35", "throughput": 687.41, "total_tokens": 7262688} {"current_steps": 25930, "total_steps": 40000, "loss": 0.0, "lr": 1.3774626917700523e-05, "epoch": 288.1111111111111, "percentage": 64.83, "elapsed_time": "2:56:07", "remaining_time": "1:35:33", "throughput": 687.42, "total_tokens": 7264096} {"current_steps": 25935, "total_steps": 40000, "loss": 0.0, "lr": 1.3765855629588334e-05, "epoch": 288.1666666666667, "percentage": 64.84, "elapsed_time": "2:56:09", "remaining_time": "1:35:31", "throughput": 687.43, "total_tokens": 7265520} {"current_steps": 25940, "total_steps": 40000, "loss": 0.0, "lr": 1.3757086073922374e-05, "epoch": 288.22222222222223, "percentage": 64.85, "elapsed_time": "2:56:11", "remaining_time": "1:35:29", "throughput": 687.44, "total_tokens": 7266960} {"current_steps": 25945, "total_steps": 40000, "loss": 0.0, "lr": 1.3748318252055038e-05, "epoch": 288.27777777777777, "percentage": 64.86, "elapsed_time": "2:56:12", "remaining_time": "1:35:27", "throughput": 687.44, "total_tokens": 7268336} {"current_steps": 25950, "total_steps": 40000, "loss": 0.0, "lr": 1.3739552165338416e-05, "epoch": 288.3333333333333, "percentage": 64.88, "elapsed_time": "2:56:14", "remaining_time": "1:35:25", "throughput": 687.45, "total_tokens": 7269760} {"current_steps": 25955, "total_steps": 40000, "loss": 0.0, "lr": 1.3730787815124354e-05, "epoch": 288.3888888888889, "percentage": 64.89, "elapsed_time": "2:56:16", "remaining_time": "1:35:23", "throughput": 687.46, "total_tokens": 7271168} {"current_steps": 25960, "total_steps": 40000, "loss": 0.0, "lr": 1.3722025202764443e-05, "epoch": 288.44444444444446, "percentage": 64.9, "elapsed_time": "2:56:18", "remaining_time": "1:35:21", "throughput": 687.47, "total_tokens": 7272576} {"current_steps": 25965, "total_steps": 40000, "loss": 0.0, "lr": 1.371326432960997e-05, "epoch": 288.5, "percentage": 64.91, "elapsed_time": "2:56:20", "remaining_time": "1:35:19", "throughput": 687.47, "total_tokens": 7273952} {"current_steps": 25970, "total_steps": 40000, "loss": 0.0, "lr": 1.3704505197011969e-05, "epoch": 288.55555555555554, "percentage": 64.92, "elapsed_time": "2:56:22", "remaining_time": "1:35:17", "throughput": 687.48, "total_tokens": 7275344} {"current_steps": 25975, "total_steps": 40000, "loss": 0.0, "lr": 1.3695747806321224e-05, "epoch": 288.6111111111111, "percentage": 64.94, "elapsed_time": "2:56:24", "remaining_time": "1:35:15", "throughput": 687.48, "total_tokens": 7276736} {"current_steps": 25980, "total_steps": 40000, "loss": 0.0, "lr": 1.3686992158888212e-05, "epoch": 288.6666666666667, "percentage": 64.95, "elapsed_time": "2:56:26", "remaining_time": "1:35:12", "throughput": 687.49, "total_tokens": 7278176} {"current_steps": 25985, "total_steps": 40000, "loss": 0.0, "lr": 1.367823825606319e-05, "epoch": 288.72222222222223, "percentage": 64.96, "elapsed_time": "2:56:28", "remaining_time": "1:35:10", "throughput": 687.5, "total_tokens": 7279616} {"current_steps": 25990, "total_steps": 40000, "loss": 0.0, "lr": 1.36694860991961e-05, "epoch": 288.77777777777777, "percentage": 64.98, "elapsed_time": "2:56:30", "remaining_time": "1:35:08", "throughput": 687.51, "total_tokens": 7281056} {"current_steps": 25995, "total_steps": 40000, "loss": 0.0, "lr": 1.3660735689636636e-05, "epoch": 288.8333333333333, "percentage": 64.99, "elapsed_time": "2:56:32", "remaining_time": "1:35:06", "throughput": 687.51, "total_tokens": 7282432} {"current_steps": 26000, "total_steps": 40000, "loss": 0.0, "lr": 1.365198702873424e-05, "epoch": 288.8888888888889, "percentage": 65.0, "elapsed_time": "2:56:34", "remaining_time": "1:35:04", "throughput": 687.52, "total_tokens": 7283856} {"current_steps": 26000, "total_steps": 40000, "eval_loss": 0.3057142198085785, "epoch": 288.8888888888889, "percentage": 65.0, "elapsed_time": "2:56:35", "remaining_time": "1:35:05", "throughput": 687.44, "total_tokens": 7283856} {"current_steps": 26005, "total_steps": 40000, "loss": 0.0, "lr": 1.364324011783804e-05, "epoch": 288.94444444444446, "percentage": 65.01, "elapsed_time": "2:56:38", "remaining_time": "1:35:03", "throughput": 687.36, "total_tokens": 7285296} {"current_steps": 26010, "total_steps": 40000, "loss": 0.0, "lr": 1.3634494958296934e-05, "epoch": 289.0, "percentage": 65.03, "elapsed_time": "2:56:41", "remaining_time": "1:35:01", "throughput": 687.35, "total_tokens": 7286672} {"current_steps": 26015, "total_steps": 40000, "loss": 0.0, "lr": 1.3625751551459542e-05, "epoch": 289.05555555555554, "percentage": 65.04, "elapsed_time": "2:56:43", "remaining_time": "1:35:00", "throughput": 687.34, "total_tokens": 7288048} {"current_steps": 26020, "total_steps": 40000, "loss": 0.0, "lr": 1.3617009898674188e-05, "epoch": 289.1111111111111, "percentage": 65.05, "elapsed_time": "2:56:45", "remaining_time": "1:34:57", "throughput": 687.35, "total_tokens": 7289472} {"current_steps": 26025, "total_steps": 40000, "loss": 0.0, "lr": 1.3608270001288967e-05, "epoch": 289.1666666666667, "percentage": 65.06, "elapsed_time": "2:56:47", "remaining_time": "1:34:55", "throughput": 687.36, "total_tokens": 7290896} {"current_steps": 26030, "total_steps": 40000, "loss": 0.0, "lr": 1.359953186065166e-05, "epoch": 289.22222222222223, "percentage": 65.08, "elapsed_time": "2:56:49", "remaining_time": "1:34:53", "throughput": 687.36, "total_tokens": 7292304} {"current_steps": 26035, "total_steps": 40000, "loss": 0.0, "lr": 1.3590795478109814e-05, "epoch": 289.27777777777777, "percentage": 65.09, "elapsed_time": "2:56:51", "remaining_time": "1:34:51", "throughput": 687.37, "total_tokens": 7293696} {"current_steps": 26040, "total_steps": 40000, "loss": 0.0, "lr": 1.3582060855010675e-05, "epoch": 289.3333333333333, "percentage": 65.1, "elapsed_time": "2:56:52", "remaining_time": "1:34:49", "throughput": 687.37, "total_tokens": 7295072} {"current_steps": 26045, "total_steps": 40000, "loss": 0.0, "lr": 1.3573327992701245e-05, "epoch": 289.3888888888889, "percentage": 65.11, "elapsed_time": "2:56:54", "remaining_time": "1:34:47", "throughput": 687.38, "total_tokens": 7296480} {"current_steps": 26050, "total_steps": 40000, "loss": 0.0, "lr": 1.356459689252823e-05, "epoch": 289.44444444444446, "percentage": 65.12, "elapsed_time": "2:56:56", "remaining_time": "1:34:45", "throughput": 687.39, "total_tokens": 7297904} {"current_steps": 26055, "total_steps": 40000, "loss": 0.0, "lr": 1.3555867555838087e-05, "epoch": 289.5, "percentage": 65.14, "elapsed_time": "2:56:58", "remaining_time": "1:34:43", "throughput": 687.4, "total_tokens": 7299296} {"current_steps": 26060, "total_steps": 40000, "loss": 0.0, "lr": 1.3547139983976975e-05, "epoch": 289.55555555555554, "percentage": 65.15, "elapsed_time": "2:57:00", "remaining_time": "1:34:41", "throughput": 687.4, "total_tokens": 7300704} {"current_steps": 26065, "total_steps": 40000, "loss": 0.0, "lr": 1.3538414178290815e-05, "epoch": 289.6111111111111, "percentage": 65.16, "elapsed_time": "2:57:02", "remaining_time": "1:34:39", "throughput": 687.41, "total_tokens": 7302080} {"current_steps": 26070, "total_steps": 40000, "loss": 0.0, "lr": 1.3529690140125209e-05, "epoch": 289.6666666666667, "percentage": 65.18, "elapsed_time": "2:57:04", "remaining_time": "1:34:37", "throughput": 687.41, "total_tokens": 7303472} {"current_steps": 26075, "total_steps": 40000, "loss": 0.0, "lr": 1.352096787082553e-05, "epoch": 289.72222222222223, "percentage": 65.19, "elapsed_time": "2:57:06", "remaining_time": "1:34:34", "throughput": 687.42, "total_tokens": 7304864} {"current_steps": 26080, "total_steps": 40000, "loss": 0.0, "lr": 1.3512247371736871e-05, "epoch": 289.77777777777777, "percentage": 65.2, "elapsed_time": "2:57:08", "remaining_time": "1:34:32", "throughput": 687.43, "total_tokens": 7306272} {"current_steps": 26085, "total_steps": 40000, "loss": 0.0, "lr": 1.3503528644204022e-05, "epoch": 289.8333333333333, "percentage": 65.21, "elapsed_time": "2:57:10", "remaining_time": "1:34:30", "throughput": 687.44, "total_tokens": 7307712} {"current_steps": 26090, "total_steps": 40000, "loss": 0.0, "lr": 1.349481168957153e-05, "epoch": 289.8888888888889, "percentage": 65.22, "elapsed_time": "2:57:12", "remaining_time": "1:34:28", "throughput": 687.44, "total_tokens": 7309072} {"current_steps": 26095, "total_steps": 40000, "loss": 0.0, "lr": 1.3486096509183665e-05, "epoch": 289.94444444444446, "percentage": 65.24, "elapsed_time": "2:57:14", "remaining_time": "1:34:26", "throughput": 687.45, "total_tokens": 7310464} {"current_steps": 26100, "total_steps": 40000, "loss": 0.0, "lr": 1.3477383104384406e-05, "epoch": 290.0, "percentage": 65.25, "elapsed_time": "2:57:16", "remaining_time": "1:34:24", "throughput": 687.44, "total_tokens": 7311840} {"current_steps": 26105, "total_steps": 40000, "loss": 0.0, "lr": 1.3468671476517481e-05, "epoch": 290.05555555555554, "percentage": 65.26, "elapsed_time": "2:57:18", "remaining_time": "1:34:22", "throughput": 687.43, "total_tokens": 7313248} {"current_steps": 26110, "total_steps": 40000, "loss": 0.0, "lr": 1.3459961626926326e-05, "epoch": 290.1111111111111, "percentage": 65.28, "elapsed_time": "2:57:20", "remaining_time": "1:34:20", "throughput": 687.44, "total_tokens": 7314688} {"current_steps": 26115, "total_steps": 40000, "loss": 0.0, "lr": 1.3451253556954101e-05, "epoch": 290.1666666666667, "percentage": 65.29, "elapsed_time": "2:57:22", "remaining_time": "1:34:18", "throughput": 687.45, "total_tokens": 7316128} {"current_steps": 26120, "total_steps": 40000, "loss": 0.0, "lr": 1.3442547267943717e-05, "epoch": 290.22222222222223, "percentage": 65.3, "elapsed_time": "2:57:24", "remaining_time": "1:34:16", "throughput": 687.46, "total_tokens": 7317568} {"current_steps": 26125, "total_steps": 40000, "loss": 0.0, "lr": 1.3433842761237774e-05, "epoch": 290.27777777777777, "percentage": 65.31, "elapsed_time": "2:57:26", "remaining_time": "1:34:14", "throughput": 687.46, "total_tokens": 7318944} {"current_steps": 26130, "total_steps": 40000, "loss": 0.0, "lr": 1.3425140038178639e-05, "epoch": 290.3333333333333, "percentage": 65.33, "elapsed_time": "2:57:28", "remaining_time": "1:34:12", "throughput": 687.47, "total_tokens": 7320320} {"current_steps": 26135, "total_steps": 40000, "loss": 0.0, "lr": 1.3416439100108358e-05, "epoch": 290.3888888888889, "percentage": 65.34, "elapsed_time": "2:57:30", "remaining_time": "1:34:10", "throughput": 687.47, "total_tokens": 7321696} {"current_steps": 26140, "total_steps": 40000, "loss": 0.0, "lr": 1.3407739948368734e-05, "epoch": 290.44444444444446, "percentage": 65.35, "elapsed_time": "2:57:32", "remaining_time": "1:34:07", "throughput": 687.47, "total_tokens": 7323072} {"current_steps": 26145, "total_steps": 40000, "loss": 0.0, "lr": 1.3399042584301298e-05, "epoch": 290.5, "percentage": 65.36, "elapsed_time": "2:57:34", "remaining_time": "1:34:05", "throughput": 687.49, "total_tokens": 7324528} {"current_steps": 26150, "total_steps": 40000, "loss": 0.0, "lr": 1.3390347009247272e-05, "epoch": 290.55555555555554, "percentage": 65.38, "elapsed_time": "2:57:36", "remaining_time": "1:34:03", "throughput": 687.49, "total_tokens": 7325936} {"current_steps": 26155, "total_steps": 40000, "loss": 0.0, "lr": 1.3381653224547635e-05, "epoch": 290.6111111111111, "percentage": 65.39, "elapsed_time": "2:57:37", "remaining_time": "1:34:01", "throughput": 687.49, "total_tokens": 7327280} {"current_steps": 26160, "total_steps": 40000, "loss": 0.0, "lr": 1.3372961231543086e-05, "epoch": 290.6666666666667, "percentage": 65.4, "elapsed_time": "2:57:39", "remaining_time": "1:33:59", "throughput": 687.5, "total_tokens": 7328672} {"current_steps": 26165, "total_steps": 40000, "loss": 0.0, "lr": 1.3364271031574016e-05, "epoch": 290.72222222222223, "percentage": 65.41, "elapsed_time": "2:57:41", "remaining_time": "1:33:57", "throughput": 687.51, "total_tokens": 7330128} {"current_steps": 26170, "total_steps": 40000, "loss": 0.0, "lr": 1.335558262598059e-05, "epoch": 290.77777777777777, "percentage": 65.42, "elapsed_time": "2:57:43", "remaining_time": "1:33:55", "throughput": 687.51, "total_tokens": 7331472} {"current_steps": 26175, "total_steps": 40000, "loss": 0.0, "lr": 1.3346896016102645e-05, "epoch": 290.8333333333333, "percentage": 65.44, "elapsed_time": "2:57:45", "remaining_time": "1:33:53", "throughput": 687.52, "total_tokens": 7332848} {"current_steps": 26180, "total_steps": 40000, "loss": 0.0, "lr": 1.3338211203279788e-05, "epoch": 290.8888888888889, "percentage": 65.45, "elapsed_time": "2:57:47", "remaining_time": "1:33:51", "throughput": 687.52, "total_tokens": 7334256} {"current_steps": 26185, "total_steps": 40000, "loss": 0.0, "lr": 1.3329528188851303e-05, "epoch": 290.94444444444446, "percentage": 65.46, "elapsed_time": "2:57:49", "remaining_time": "1:33:49", "throughput": 687.53, "total_tokens": 7335648} {"current_steps": 26190, "total_steps": 40000, "loss": 0.0, "lr": 1.3320846974156242e-05, "epoch": 291.0, "percentage": 65.48, "elapsed_time": "2:57:51", "remaining_time": "1:33:47", "throughput": 687.53, "total_tokens": 7337056} {"current_steps": 26195, "total_steps": 40000, "loss": 0.0, "lr": 1.3312167560533337e-05, "epoch": 291.05555555555554, "percentage": 65.49, "elapsed_time": "2:57:53", "remaining_time": "1:33:45", "throughput": 687.52, "total_tokens": 7338464} {"current_steps": 26200, "total_steps": 40000, "loss": 0.0, "lr": 1.3303489949321082e-05, "epoch": 291.1111111111111, "percentage": 65.5, "elapsed_time": "2:57:55", "remaining_time": "1:33:43", "throughput": 687.52, "total_tokens": 7339872} {"current_steps": 26200, "total_steps": 40000, "eval_loss": 0.3654395043849945, "epoch": 291.1111111111111, "percentage": 65.5, "elapsed_time": "2:57:57", "remaining_time": "1:33:43", "throughput": 687.44, "total_tokens": 7339872} {"current_steps": 26205, "total_steps": 40000, "loss": 0.0, "lr": 1.3294814141857653e-05, "epoch": 291.1666666666667, "percentage": 65.51, "elapsed_time": "2:58:00", "remaining_time": "1:33:42", "throughput": 687.36, "total_tokens": 7341216} {"current_steps": 26210, "total_steps": 40000, "loss": 0.0, "lr": 1.3286140139480992e-05, "epoch": 291.22222222222223, "percentage": 65.53, "elapsed_time": "2:58:02", "remaining_time": "1:33:40", "throughput": 687.36, "total_tokens": 7342592} {"current_steps": 26215, "total_steps": 40000, "loss": 0.0, "lr": 1.3277467943528719e-05, "epoch": 291.27777777777777, "percentage": 65.54, "elapsed_time": "2:58:04", "remaining_time": "1:33:38", "throughput": 687.36, "total_tokens": 7344000} {"current_steps": 26220, "total_steps": 40000, "loss": 0.0, "lr": 1.3268797555338203e-05, "epoch": 291.3333333333333, "percentage": 65.55, "elapsed_time": "2:58:06", "remaining_time": "1:33:36", "throughput": 687.37, "total_tokens": 7345440} {"current_steps": 26225, "total_steps": 40000, "loss": 0.0, "lr": 1.3260128976246533e-05, "epoch": 291.3888888888889, "percentage": 65.56, "elapsed_time": "2:58:08", "remaining_time": "1:33:34", "throughput": 687.38, "total_tokens": 7346864} {"current_steps": 26230, "total_steps": 40000, "loss": 0.0, "lr": 1.32514622075905e-05, "epoch": 291.44444444444446, "percentage": 65.58, "elapsed_time": "2:58:10", "remaining_time": "1:33:32", "throughput": 687.39, "total_tokens": 7348240} {"current_steps": 26235, "total_steps": 40000, "loss": 0.0, "lr": 1.3242797250706638e-05, "epoch": 291.5, "percentage": 65.59, "elapsed_time": "2:58:12", "remaining_time": "1:33:29", "throughput": 687.39, "total_tokens": 7349632} {"current_steps": 26240, "total_steps": 40000, "loss": 0.0, "lr": 1.3234134106931195e-05, "epoch": 291.55555555555554, "percentage": 65.6, "elapsed_time": "2:58:13", "remaining_time": "1:33:27", "throughput": 687.4, "total_tokens": 7351040} {"current_steps": 26245, "total_steps": 40000, "loss": 0.0, "lr": 1.322547277760013e-05, "epoch": 291.6111111111111, "percentage": 65.61, "elapsed_time": "2:58:15", "remaining_time": "1:33:25", "throughput": 687.4, "total_tokens": 7352432} {"current_steps": 26250, "total_steps": 40000, "loss": 0.0, "lr": 1.3216813264049132e-05, "epoch": 291.6666666666667, "percentage": 65.62, "elapsed_time": "2:58:17", "remaining_time": "1:33:23", "throughput": 687.41, "total_tokens": 7353824} {"current_steps": 26255, "total_steps": 40000, "loss": 0.0, "lr": 1.32081555676136e-05, "epoch": 291.72222222222223, "percentage": 65.64, "elapsed_time": "2:58:19", "remaining_time": "1:33:21", "throughput": 687.42, "total_tokens": 7355232} {"current_steps": 26260, "total_steps": 40000, "loss": 0.0, "lr": 1.3199499689628674e-05, "epoch": 291.77777777777777, "percentage": 65.65, "elapsed_time": "2:58:21", "remaining_time": "1:33:19", "throughput": 687.43, "total_tokens": 7356672} {"current_steps": 26265, "total_steps": 40000, "loss": 0.0, "lr": 1.3190845631429192e-05, "epoch": 291.8333333333333, "percentage": 65.66, "elapsed_time": "2:58:23", "remaining_time": "1:33:17", "throughput": 687.44, "total_tokens": 7358144} {"current_steps": 26270, "total_steps": 40000, "loss": 0.0, "lr": 1.3182193394349704e-05, "epoch": 291.8888888888889, "percentage": 65.67, "elapsed_time": "2:58:25", "remaining_time": "1:33:15", "throughput": 687.45, "total_tokens": 7359568} {"current_steps": 26275, "total_steps": 40000, "loss": 0.0, "lr": 1.3173542979724507e-05, "epoch": 291.94444444444446, "percentage": 65.69, "elapsed_time": "2:58:27", "remaining_time": "1:33:13", "throughput": 687.46, "total_tokens": 7360976} {"current_steps": 26280, "total_steps": 40000, "loss": 0.0, "lr": 1.3164894388887617e-05, "epoch": 292.0, "percentage": 65.7, "elapsed_time": "2:58:29", "remaining_time": "1:33:11", "throughput": 687.45, "total_tokens": 7362384} {"current_steps": 26285, "total_steps": 40000, "loss": 0.0, "lr": 1.3156247623172727e-05, "epoch": 292.05555555555554, "percentage": 65.71, "elapsed_time": "2:58:31", "remaining_time": "1:33:09", "throughput": 687.44, "total_tokens": 7363760} {"current_steps": 26290, "total_steps": 40000, "loss": 0.0, "lr": 1.3147602683913302e-05, "epoch": 292.1111111111111, "percentage": 65.72, "elapsed_time": "2:58:33", "remaining_time": "1:33:07", "throughput": 687.45, "total_tokens": 7365152} {"current_steps": 26295, "total_steps": 40000, "loss": 0.0, "lr": 1.3138959572442481e-05, "epoch": 292.1666666666667, "percentage": 65.74, "elapsed_time": "2:58:35", "remaining_time": "1:33:05", "throughput": 687.45, "total_tokens": 7366560} {"current_steps": 26300, "total_steps": 40000, "loss": 0.0, "lr": 1.3130318290093146e-05, "epoch": 292.22222222222223, "percentage": 65.75, "elapsed_time": "2:58:37", "remaining_time": "1:33:02", "throughput": 687.45, "total_tokens": 7367920} {"current_steps": 26305, "total_steps": 40000, "loss": 0.0, "lr": 1.3121678838197909e-05, "epoch": 292.27777777777777, "percentage": 65.76, "elapsed_time": "2:58:39", "remaining_time": "1:33:00", "throughput": 687.46, "total_tokens": 7369344} {"current_steps": 26310, "total_steps": 40000, "loss": 0.0, "lr": 1.3113041218089056e-05, "epoch": 292.3333333333333, "percentage": 65.77, "elapsed_time": "2:58:41", "remaining_time": "1:32:58", "throughput": 687.47, "total_tokens": 7370752} {"current_steps": 26315, "total_steps": 40000, "loss": 0.0, "lr": 1.3104405431098626e-05, "epoch": 292.3888888888889, "percentage": 65.79, "elapsed_time": "2:58:43", "remaining_time": "1:32:56", "throughput": 687.48, "total_tokens": 7372176} {"current_steps": 26320, "total_steps": 40000, "loss": 0.0, "lr": 1.3095771478558377e-05, "epoch": 292.44444444444446, "percentage": 65.8, "elapsed_time": "2:58:45", "remaining_time": "1:32:54", "throughput": 687.48, "total_tokens": 7373568} {"current_steps": 26325, "total_steps": 40000, "loss": 0.0, "lr": 1.3087139361799766e-05, "epoch": 292.5, "percentage": 65.81, "elapsed_time": "2:58:47", "remaining_time": "1:32:52", "throughput": 687.49, "total_tokens": 7375008} {"current_steps": 26330, "total_steps": 40000, "loss": 0.0, "lr": 1.3078509082153964e-05, "epoch": 292.55555555555554, "percentage": 65.83, "elapsed_time": "2:58:49", "remaining_time": "1:32:50", "throughput": 687.5, "total_tokens": 7376384} {"current_steps": 26335, "total_steps": 40000, "loss": 0.0, "lr": 1.3069880640951885e-05, "epoch": 292.6111111111111, "percentage": 65.84, "elapsed_time": "2:58:51", "remaining_time": "1:32:48", "throughput": 687.5, "total_tokens": 7377776} {"current_steps": 26340, "total_steps": 40000, "loss": 0.0, "lr": 1.3061254039524123e-05, "epoch": 292.6666666666667, "percentage": 65.85, "elapsed_time": "2:58:53", "remaining_time": "1:32:46", "throughput": 687.51, "total_tokens": 7379200} {"current_steps": 26345, "total_steps": 40000, "loss": 0.0, "lr": 1.3052629279201028e-05, "epoch": 292.72222222222223, "percentage": 65.86, "elapsed_time": "2:58:55", "remaining_time": "1:32:44", "throughput": 687.52, "total_tokens": 7380608} {"current_steps": 26350, "total_steps": 40000, "loss": 0.0, "lr": 1.3044006361312633e-05, "epoch": 292.77777777777777, "percentage": 65.88, "elapsed_time": "2:58:57", "remaining_time": "1:32:42", "throughput": 687.52, "total_tokens": 7381984} {"current_steps": 26355, "total_steps": 40000, "loss": 0.0, "lr": 1.30353852871887e-05, "epoch": 292.8333333333333, "percentage": 65.89, "elapsed_time": "2:58:59", "remaining_time": "1:32:39", "throughput": 687.53, "total_tokens": 7383344} {"current_steps": 26360, "total_steps": 40000, "loss": 0.0, "lr": 1.302676605815873e-05, "epoch": 292.8888888888889, "percentage": 65.9, "elapsed_time": "2:59:00", "remaining_time": "1:32:37", "throughput": 687.53, "total_tokens": 7384752} {"current_steps": 26365, "total_steps": 40000, "loss": 0.0, "lr": 1.3018148675551884e-05, "epoch": 292.94444444444446, "percentage": 65.91, "elapsed_time": "2:59:02", "remaining_time": "1:32:35", "throughput": 687.54, "total_tokens": 7386160} {"current_steps": 26370, "total_steps": 40000, "loss": 0.0, "lr": 1.3009533140697094e-05, "epoch": 293.0, "percentage": 65.92, "elapsed_time": "2:59:04", "remaining_time": "1:32:33", "throughput": 687.53, "total_tokens": 7387504} {"current_steps": 26375, "total_steps": 40000, "loss": 0.0, "lr": 1.3000919454922966e-05, "epoch": 293.05555555555554, "percentage": 65.94, "elapsed_time": "2:59:07", "remaining_time": "1:32:31", "throughput": 687.52, "total_tokens": 7388864} {"current_steps": 26380, "total_steps": 40000, "loss": 0.0, "lr": 1.299230761955785e-05, "epoch": 293.1111111111111, "percentage": 65.95, "elapsed_time": "2:59:09", "remaining_time": "1:32:29", "throughput": 687.52, "total_tokens": 7390288} {"current_steps": 26385, "total_steps": 40000, "loss": 0.0, "lr": 1.2983697635929807e-05, "epoch": 293.1666666666667, "percentage": 65.96, "elapsed_time": "2:59:11", "remaining_time": "1:32:27", "throughput": 687.53, "total_tokens": 7391648} {"current_steps": 26390, "total_steps": 40000, "loss": 0.0, "lr": 1.2975089505366584e-05, "epoch": 293.22222222222223, "percentage": 65.97, "elapsed_time": "2:59:13", "remaining_time": "1:32:25", "throughput": 687.53, "total_tokens": 7393056} {"current_steps": 26395, "total_steps": 40000, "loss": 0.0, "lr": 1.2966483229195683e-05, "epoch": 293.27777777777777, "percentage": 65.99, "elapsed_time": "2:59:14", "remaining_time": "1:32:23", "throughput": 687.54, "total_tokens": 7394448} {"current_steps": 26400, "total_steps": 40000, "loss": 0.0, "lr": 1.2957878808744283e-05, "epoch": 293.3333333333333, "percentage": 66.0, "elapsed_time": "2:59:16", "remaining_time": "1:32:21", "throughput": 687.54, "total_tokens": 7395808} {"current_steps": 26400, "total_steps": 40000, "eval_loss": 0.32258859276771545, "epoch": 293.3333333333333, "percentage": 66.0, "elapsed_time": "2:59:18", "remaining_time": "1:32:22", "throughput": 687.46, "total_tokens": 7395808} {"current_steps": 26405, "total_steps": 40000, "loss": 0.0, "lr": 1.294927624533931e-05, "epoch": 293.3888888888889, "percentage": 66.01, "elapsed_time": "2:59:21", "remaining_time": "1:32:20", "throughput": 687.36, "total_tokens": 7397216} {"current_steps": 26410, "total_steps": 40000, "loss": 0.0, "lr": 1.2940675540307378e-05, "epoch": 293.44444444444446, "percentage": 66.03, "elapsed_time": "2:59:23", "remaining_time": "1:32:18", "throughput": 687.36, "total_tokens": 7398688} {"current_steps": 26415, "total_steps": 40000, "loss": 0.0, "lr": 1.2932076694974814e-05, "epoch": 293.5, "percentage": 66.04, "elapsed_time": "2:59:25", "remaining_time": "1:32:16", "throughput": 687.37, "total_tokens": 7400080} {"current_steps": 26420, "total_steps": 40000, "loss": 0.0, "lr": 1.2923479710667682e-05, "epoch": 293.55555555555554, "percentage": 66.05, "elapsed_time": "2:59:27", "remaining_time": "1:32:14", "throughput": 687.38, "total_tokens": 7401488} {"current_steps": 26425, "total_steps": 40000, "loss": 0.0, "lr": 1.2914884588711751e-05, "epoch": 293.6111111111111, "percentage": 66.06, "elapsed_time": "2:59:29", "remaining_time": "1:32:12", "throughput": 687.38, "total_tokens": 7402848} {"current_steps": 26430, "total_steps": 40000, "loss": 0.0, "lr": 1.2906291330432475e-05, "epoch": 293.6666666666667, "percentage": 66.07, "elapsed_time": "2:59:31", "remaining_time": "1:32:10", "throughput": 687.39, "total_tokens": 7404272} {"current_steps": 26435, "total_steps": 40000, "loss": 0.0, "lr": 1.2897699937155055e-05, "epoch": 293.72222222222223, "percentage": 66.09, "elapsed_time": "2:59:33", "remaining_time": "1:32:08", "throughput": 687.39, "total_tokens": 7405680} {"current_steps": 26440, "total_steps": 40000, "loss": 0.0, "lr": 1.2889110410204403e-05, "epoch": 293.77777777777777, "percentage": 66.1, "elapsed_time": "2:59:35", "remaining_time": "1:32:06", "throughput": 687.4, "total_tokens": 7407104} {"current_steps": 26445, "total_steps": 40000, "loss": 0.0, "lr": 1.2880522750905111e-05, "epoch": 293.8333333333333, "percentage": 66.11, "elapsed_time": "2:59:37", "remaining_time": "1:32:04", "throughput": 687.41, "total_tokens": 7408496} {"current_steps": 26450, "total_steps": 40000, "loss": 0.0, "lr": 1.2871936960581523e-05, "epoch": 293.8888888888889, "percentage": 66.12, "elapsed_time": "2:59:39", "remaining_time": "1:32:02", "throughput": 687.42, "total_tokens": 7409904} {"current_steps": 26455, "total_steps": 40000, "loss": 0.0, "lr": 1.2863353040557658e-05, "epoch": 293.94444444444446, "percentage": 66.14, "elapsed_time": "2:59:41", "remaining_time": "1:32:00", "throughput": 687.42, "total_tokens": 7411296} {"current_steps": 26460, "total_steps": 40000, "loss": 0.0, "lr": 1.2854770992157273e-05, "epoch": 294.0, "percentage": 66.15, "elapsed_time": "2:59:43", "remaining_time": "1:31:58", "throughput": 687.42, "total_tokens": 7412736} {"current_steps": 26465, "total_steps": 40000, "loss": 0.0, "lr": 1.2846190816703835e-05, "epoch": 294.05555555555554, "percentage": 66.16, "elapsed_time": "2:59:45", "remaining_time": "1:31:56", "throughput": 687.41, "total_tokens": 7414144} {"current_steps": 26470, "total_steps": 40000, "loss": 0.0, "lr": 1.2837612515520498e-05, "epoch": 294.1111111111111, "percentage": 66.17, "elapsed_time": "2:59:47", "remaining_time": "1:31:53", "throughput": 687.41, "total_tokens": 7415504} {"current_steps": 26475, "total_steps": 40000, "loss": 0.0, "lr": 1.2829036089930163e-05, "epoch": 294.1666666666667, "percentage": 66.19, "elapsed_time": "2:59:49", "remaining_time": "1:31:51", "throughput": 687.43, "total_tokens": 7416976} {"current_steps": 26480, "total_steps": 40000, "loss": 0.0, "lr": 1.2820461541255412e-05, "epoch": 294.22222222222223, "percentage": 66.2, "elapsed_time": "2:59:51", "remaining_time": "1:31:49", "throughput": 687.43, "total_tokens": 7418352} {"current_steps": 26485, "total_steps": 40000, "loss": 0.0, "lr": 1.2811888870818543e-05, "epoch": 294.27777777777777, "percentage": 66.21, "elapsed_time": "2:59:53", "remaining_time": "1:31:47", "throughput": 687.44, "total_tokens": 7419824} {"current_steps": 26490, "total_steps": 40000, "loss": 0.0, "lr": 1.2803318079941581e-05, "epoch": 294.3333333333333, "percentage": 66.22, "elapsed_time": "2:59:55", "remaining_time": "1:31:45", "throughput": 687.45, "total_tokens": 7421248} {"current_steps": 26495, "total_steps": 40000, "loss": 0.0, "lr": 1.2794749169946235e-05, "epoch": 294.3888888888889, "percentage": 66.24, "elapsed_time": "2:59:57", "remaining_time": "1:31:43", "throughput": 687.46, "total_tokens": 7422704} {"current_steps": 26500, "total_steps": 40000, "loss": 0.0, "lr": 1.2786182142153952e-05, "epoch": 294.44444444444446, "percentage": 66.25, "elapsed_time": "2:59:59", "remaining_time": "1:31:41", "throughput": 687.47, "total_tokens": 7424064} {"current_steps": 26505, "total_steps": 40000, "loss": 0.0, "lr": 1.2777616997885878e-05, "epoch": 294.5, "percentage": 66.26, "elapsed_time": "3:00:01", "remaining_time": "1:31:39", "throughput": 687.47, "total_tokens": 7425440} {"current_steps": 26510, "total_steps": 40000, "loss": 0.0, "lr": 1.2769053738462847e-05, "epoch": 294.55555555555554, "percentage": 66.27, "elapsed_time": "3:00:03", "remaining_time": "1:31:37", "throughput": 687.47, "total_tokens": 7426832} {"current_steps": 26515, "total_steps": 40000, "loss": 0.0, "lr": 1.2760492365205434e-05, "epoch": 294.6111111111111, "percentage": 66.29, "elapsed_time": "3:00:05", "remaining_time": "1:31:35", "throughput": 687.48, "total_tokens": 7428192} {"current_steps": 26520, "total_steps": 40000, "loss": 0.0, "lr": 1.2751932879433919e-05, "epoch": 294.6666666666667, "percentage": 66.3, "elapsed_time": "3:00:06", "remaining_time": "1:31:33", "throughput": 687.48, "total_tokens": 7429552} {"current_steps": 26525, "total_steps": 40000, "loss": 0.0, "lr": 1.2743375282468267e-05, "epoch": 294.72222222222223, "percentage": 66.31, "elapsed_time": "3:00:08", "remaining_time": "1:31:31", "throughput": 687.48, "total_tokens": 7430912} {"current_steps": 26530, "total_steps": 40000, "loss": 0.0, "lr": 1.2734819575628182e-05, "epoch": 294.77777777777777, "percentage": 66.33, "elapsed_time": "3:00:10", "remaining_time": "1:31:28", "throughput": 687.49, "total_tokens": 7432288} {"current_steps": 26535, "total_steps": 40000, "loss": 0.0, "lr": 1.2726265760233039e-05, "epoch": 294.8333333333333, "percentage": 66.34, "elapsed_time": "3:00:12", "remaining_time": "1:31:26", "throughput": 687.49, "total_tokens": 7433664} {"current_steps": 26540, "total_steps": 40000, "loss": 0.0, "lr": 1.271771383760197e-05, "epoch": 294.8888888888889, "percentage": 66.35, "elapsed_time": "3:00:14", "remaining_time": "1:31:24", "throughput": 687.5, "total_tokens": 7435056} {"current_steps": 26545, "total_steps": 40000, "loss": 0.0, "lr": 1.2709163809053764e-05, "epoch": 294.94444444444446, "percentage": 66.36, "elapsed_time": "3:00:16", "remaining_time": "1:31:22", "throughput": 687.51, "total_tokens": 7436496} {"current_steps": 26550, "total_steps": 40000, "loss": 0.0, "lr": 1.2700615675906963e-05, "epoch": 295.0, "percentage": 66.38, "elapsed_time": "3:00:18", "remaining_time": "1:31:20", "throughput": 687.5, "total_tokens": 7437888} {"current_steps": 26555, "total_steps": 40000, "loss": 0.0, "lr": 1.269206943947978e-05, "epoch": 295.05555555555554, "percentage": 66.39, "elapsed_time": "3:00:20", "remaining_time": "1:31:18", "throughput": 687.49, "total_tokens": 7439280} {"current_steps": 26560, "total_steps": 40000, "loss": 0.0, "lr": 1.2683525101090177e-05, "epoch": 295.1111111111111, "percentage": 66.4, "elapsed_time": "3:00:22", "remaining_time": "1:31:16", "throughput": 687.5, "total_tokens": 7440688} {"current_steps": 26565, "total_steps": 40000, "loss": 0.0, "lr": 1.2674982662055765e-05, "epoch": 295.1666666666667, "percentage": 66.41, "elapsed_time": "3:00:24", "remaining_time": "1:31:14", "throughput": 687.5, "total_tokens": 7442112} {"current_steps": 26570, "total_steps": 40000, "loss": 0.0, "lr": 1.2666442123693922e-05, "epoch": 295.22222222222223, "percentage": 66.42, "elapsed_time": "3:00:26", "remaining_time": "1:31:12", "throughput": 687.51, "total_tokens": 7443472} {"current_steps": 26575, "total_steps": 40000, "loss": 0.0, "lr": 1.265790348732169e-05, "epoch": 295.27777777777777, "percentage": 66.44, "elapsed_time": "3:00:28", "remaining_time": "1:31:10", "throughput": 687.51, "total_tokens": 7444816} {"current_steps": 26580, "total_steps": 40000, "loss": 0.0, "lr": 1.264936675425584e-05, "epoch": 295.3333333333333, "percentage": 66.45, "elapsed_time": "3:00:30", "remaining_time": "1:31:08", "throughput": 687.51, "total_tokens": 7446208} {"current_steps": 26585, "total_steps": 40000, "loss": 0.0, "lr": 1.2640831925812852e-05, "epoch": 295.3888888888889, "percentage": 66.46, "elapsed_time": "3:00:32", "remaining_time": "1:31:06", "throughput": 687.52, "total_tokens": 7447616} {"current_steps": 26590, "total_steps": 40000, "loss": 0.0, "lr": 1.263229900330889e-05, "epoch": 295.44444444444446, "percentage": 66.47, "elapsed_time": "3:00:34", "remaining_time": "1:31:04", "throughput": 687.53, "total_tokens": 7449072} {"current_steps": 26595, "total_steps": 40000, "loss": 0.0, "lr": 1.2623767988059843e-05, "epoch": 295.5, "percentage": 66.49, "elapsed_time": "3:00:36", "remaining_time": "1:31:02", "throughput": 687.54, "total_tokens": 7450464} {"current_steps": 26600, "total_steps": 40000, "loss": 0.0, "lr": 1.2615238881381309e-05, "epoch": 295.55555555555554, "percentage": 66.5, "elapsed_time": "3:00:38", "remaining_time": "1:30:59", "throughput": 687.55, "total_tokens": 7451904} {"current_steps": 26600, "total_steps": 40000, "eval_loss": 0.32041311264038086, "epoch": 295.55555555555554, "percentage": 66.5, "elapsed_time": "3:00:39", "remaining_time": "1:31:00", "throughput": 687.46, "total_tokens": 7451904} {"current_steps": 26605, "total_steps": 40000, "loss": 0.0, "lr": 1.2606711684588568e-05, "epoch": 295.6111111111111, "percentage": 66.51, "elapsed_time": "3:00:42", "remaining_time": "1:30:59", "throughput": 687.39, "total_tokens": 7453328} {"current_steps": 26610, "total_steps": 40000, "loss": 0.0, "lr": 1.2598186398996636e-05, "epoch": 295.6666666666667, "percentage": 66.53, "elapsed_time": "3:00:44", "remaining_time": "1:30:57", "throughput": 687.39, "total_tokens": 7454704} {"current_steps": 26615, "total_steps": 40000, "loss": 0.0, "lr": 1.2589663025920207e-05, "epoch": 295.72222222222223, "percentage": 66.54, "elapsed_time": "3:00:46", "remaining_time": "1:30:55", "throughput": 687.39, "total_tokens": 7456096} {"current_steps": 26620, "total_steps": 40000, "loss": 0.0, "lr": 1.2581141566673705e-05, "epoch": 295.77777777777777, "percentage": 66.55, "elapsed_time": "3:00:48", "remaining_time": "1:30:52", "throughput": 687.4, "total_tokens": 7457504} {"current_steps": 26625, "total_steps": 40000, "loss": 0.0, "lr": 1.257262202257124e-05, "epoch": 295.8333333333333, "percentage": 66.56, "elapsed_time": "3:00:50", "remaining_time": "1:30:50", "throughput": 687.41, "total_tokens": 7458928} {"current_steps": 26630, "total_steps": 40000, "loss": 0.0, "lr": 1.2564104394926618e-05, "epoch": 295.8888888888889, "percentage": 66.57, "elapsed_time": "3:00:52", "remaining_time": "1:30:48", "throughput": 687.41, "total_tokens": 7460320} {"current_steps": 26635, "total_steps": 40000, "loss": 0.0, "lr": 1.2555588685053383e-05, "epoch": 295.94444444444446, "percentage": 66.59, "elapsed_time": "3:00:54", "remaining_time": "1:30:46", "throughput": 687.42, "total_tokens": 7461728} {"current_steps": 26640, "total_steps": 40000, "loss": 0.0, "lr": 1.2547074894264762e-05, "epoch": 296.0, "percentage": 66.6, "elapsed_time": "3:00:56", "remaining_time": "1:30:44", "throughput": 687.41, "total_tokens": 7463072} {"current_steps": 26645, "total_steps": 40000, "loss": 0.0, "lr": 1.2538563023873679e-05, "epoch": 296.05555555555554, "percentage": 66.61, "elapsed_time": "3:00:58", "remaining_time": "1:30:42", "throughput": 687.4, "total_tokens": 7464480} {"current_steps": 26650, "total_steps": 40000, "loss": 0.0, "lr": 1.2530053075192789e-05, "epoch": 296.1111111111111, "percentage": 66.62, "elapsed_time": "3:01:00", "remaining_time": "1:30:40", "throughput": 687.41, "total_tokens": 7465872} {"current_steps": 26655, "total_steps": 40000, "loss": 0.0, "lr": 1.252154504953441e-05, "epoch": 296.1666666666667, "percentage": 66.64, "elapsed_time": "3:01:02", "remaining_time": "1:30:38", "throughput": 687.41, "total_tokens": 7467248} {"current_steps": 26660, "total_steps": 40000, "loss": 0.0, "lr": 1.25130389482106e-05, "epoch": 296.22222222222223, "percentage": 66.65, "elapsed_time": "3:01:04", "remaining_time": "1:30:36", "throughput": 687.41, "total_tokens": 7468592} {"current_steps": 26665, "total_steps": 40000, "loss": 0.0, "lr": 1.2504534772533116e-05, "epoch": 296.27777777777777, "percentage": 66.66, "elapsed_time": "3:01:06", "remaining_time": "1:30:34", "throughput": 687.42, "total_tokens": 7469984} {"current_steps": 26670, "total_steps": 40000, "loss": 0.0, "lr": 1.2496032523813387e-05, "epoch": 296.3333333333333, "percentage": 66.67, "elapsed_time": "3:01:08", "remaining_time": "1:30:32", "throughput": 687.42, "total_tokens": 7471392} {"current_steps": 26675, "total_steps": 40000, "loss": 0.0, "lr": 1.2487532203362576e-05, "epoch": 296.3888888888889, "percentage": 66.69, "elapsed_time": "3:01:10", "remaining_time": "1:30:30", "throughput": 687.43, "total_tokens": 7472816} {"current_steps": 26680, "total_steps": 40000, "loss": 0.0, "lr": 1.247903381249155e-05, "epoch": 296.44444444444446, "percentage": 66.7, "elapsed_time": "3:01:12", "remaining_time": "1:30:28", "throughput": 687.44, "total_tokens": 7474224} {"current_steps": 26685, "total_steps": 40000, "loss": 0.0, "lr": 1.2470537352510853e-05, "epoch": 296.5, "percentage": 66.71, "elapsed_time": "3:01:14", "remaining_time": "1:30:26", "throughput": 687.45, "total_tokens": 7475648} {"current_steps": 26690, "total_steps": 40000, "loss": 0.0, "lr": 1.2462042824730758e-05, "epoch": 296.55555555555554, "percentage": 66.72, "elapsed_time": "3:01:16", "remaining_time": "1:30:23", "throughput": 687.46, "total_tokens": 7477072} {"current_steps": 26695, "total_steps": 40000, "loss": 0.0, "lr": 1.245355023046122e-05, "epoch": 296.6111111111111, "percentage": 66.74, "elapsed_time": "3:01:18", "remaining_time": "1:30:21", "throughput": 687.46, "total_tokens": 7478432} {"current_steps": 26700, "total_steps": 40000, "loss": 0.0, "lr": 1.2445059571011896e-05, "epoch": 296.6666666666667, "percentage": 66.75, "elapsed_time": "3:01:20", "remaining_time": "1:30:19", "throughput": 687.47, "total_tokens": 7479840} {"current_steps": 26705, "total_steps": 40000, "loss": 0.0, "lr": 1.2436570847692173e-05, "epoch": 296.72222222222223, "percentage": 66.76, "elapsed_time": "3:01:22", "remaining_time": "1:30:17", "throughput": 687.47, "total_tokens": 7481200} {"current_steps": 26710, "total_steps": 40000, "loss": 0.0, "lr": 1.2428084061811096e-05, "epoch": 296.77777777777777, "percentage": 66.77, "elapsed_time": "3:01:24", "remaining_time": "1:30:15", "throughput": 687.48, "total_tokens": 7482640} {"current_steps": 26715, "total_steps": 40000, "loss": 0.0, "lr": 1.2419599214677447e-05, "epoch": 296.8333333333333, "percentage": 66.79, "elapsed_time": "3:01:26", "remaining_time": "1:30:13", "throughput": 687.49, "total_tokens": 7484064} {"current_steps": 26720, "total_steps": 40000, "loss": 0.0, "lr": 1.2411116307599702e-05, "epoch": 296.8888888888889, "percentage": 66.8, "elapsed_time": "3:01:28", "remaining_time": "1:30:11", "throughput": 687.49, "total_tokens": 7485456} {"current_steps": 26725, "total_steps": 40000, "loss": 0.0, "lr": 1.2402635341886016e-05, "epoch": 296.94444444444446, "percentage": 66.81, "elapsed_time": "3:01:30", "remaining_time": "1:30:09", "throughput": 687.5, "total_tokens": 7486864} {"current_steps": 26730, "total_steps": 40000, "loss": 0.0, "lr": 1.2394156318844278e-05, "epoch": 297.0, "percentage": 66.83, "elapsed_time": "3:01:32", "remaining_time": "1:30:07", "throughput": 687.49, "total_tokens": 7488272} {"current_steps": 26735, "total_steps": 40000, "loss": 0.0, "lr": 1.2385679239782039e-05, "epoch": 297.05555555555554, "percentage": 66.84, "elapsed_time": "3:01:34", "remaining_time": "1:30:05", "throughput": 687.48, "total_tokens": 7489664} {"current_steps": 26740, "total_steps": 40000, "loss": 0.0, "lr": 1.2377204106006585e-05, "epoch": 297.1111111111111, "percentage": 66.85, "elapsed_time": "3:01:36", "remaining_time": "1:30:03", "throughput": 687.49, "total_tokens": 7491056} {"current_steps": 26745, "total_steps": 40000, "loss": 0.0, "lr": 1.2368730918824891e-05, "epoch": 297.1666666666667, "percentage": 66.86, "elapsed_time": "3:01:38", "remaining_time": "1:30:01", "throughput": 687.49, "total_tokens": 7492432} {"current_steps": 26750, "total_steps": 40000, "loss": 0.0, "lr": 1.236025967954362e-05, "epoch": 297.22222222222223, "percentage": 66.88, "elapsed_time": "3:01:40", "remaining_time": "1:29:59", "throughput": 687.5, "total_tokens": 7493872} {"current_steps": 26755, "total_steps": 40000, "loss": 0.0, "lr": 1.2351790389469153e-05, "epoch": 297.27777777777777, "percentage": 66.89, "elapsed_time": "3:01:42", "remaining_time": "1:29:57", "throughput": 687.51, "total_tokens": 7495248} {"current_steps": 26760, "total_steps": 40000, "loss": 0.0, "lr": 1.234332304990755e-05, "epoch": 297.3333333333333, "percentage": 66.9, "elapsed_time": "3:01:44", "remaining_time": "1:29:54", "throughput": 687.51, "total_tokens": 7496624} {"current_steps": 26765, "total_steps": 40000, "loss": 0.0, "lr": 1.2334857662164593e-05, "epoch": 297.3888888888889, "percentage": 66.91, "elapsed_time": "3:01:45", "remaining_time": "1:29:52", "throughput": 687.52, "total_tokens": 7498032} {"current_steps": 26770, "total_steps": 40000, "loss": 0.0, "lr": 1.2326394227545743e-05, "epoch": 297.44444444444446, "percentage": 66.92, "elapsed_time": "3:01:47", "remaining_time": "1:29:50", "throughput": 687.52, "total_tokens": 7499440} {"current_steps": 26775, "total_steps": 40000, "loss": 0.0, "lr": 1.2317932747356162e-05, "epoch": 297.5, "percentage": 66.94, "elapsed_time": "3:01:49", "remaining_time": "1:29:48", "throughput": 687.53, "total_tokens": 7500816} {"current_steps": 26780, "total_steps": 40000, "loss": 0.0, "lr": 1.2309473222900726e-05, "epoch": 297.55555555555554, "percentage": 66.95, "elapsed_time": "3:01:51", "remaining_time": "1:29:46", "throughput": 687.54, "total_tokens": 7502240} {"current_steps": 26785, "total_steps": 40000, "loss": 0.0, "lr": 1.2301015655484006e-05, "epoch": 297.6111111111111, "percentage": 66.96, "elapsed_time": "3:01:53", "remaining_time": "1:29:44", "throughput": 687.54, "total_tokens": 7503584} {"current_steps": 26790, "total_steps": 40000, "loss": 0.0, "lr": 1.2292560046410245e-05, "epoch": 297.6666666666667, "percentage": 66.97, "elapsed_time": "3:01:55", "remaining_time": "1:29:42", "throughput": 687.54, "total_tokens": 7504976} {"current_steps": 26795, "total_steps": 40000, "loss": 0.0, "lr": 1.228410639698343e-05, "epoch": 297.72222222222223, "percentage": 66.99, "elapsed_time": "3:01:57", "remaining_time": "1:29:40", "throughput": 687.55, "total_tokens": 7506368} {"current_steps": 26800, "total_steps": 40000, "loss": 0.0, "lr": 1.2275654708507195e-05, "epoch": 297.77777777777777, "percentage": 67.0, "elapsed_time": "3:01:59", "remaining_time": "1:29:38", "throughput": 687.56, "total_tokens": 7507792} {"current_steps": 26800, "total_steps": 40000, "eval_loss": 0.31429359316825867, "epoch": 297.77777777777777, "percentage": 67.0, "elapsed_time": "3:02:00", "remaining_time": "1:29:38", "throughput": 687.47, "total_tokens": 7507792} {"current_steps": 26805, "total_steps": 40000, "loss": 0.0, "lr": 1.2267204982284908e-05, "epoch": 297.8333333333333, "percentage": 67.01, "elapsed_time": "3:02:05", "remaining_time": "1:29:38", "throughput": 687.33, "total_tokens": 7509232} {"current_steps": 26810, "total_steps": 40000, "loss": 0.0, "lr": 1.2258757219619635e-05, "epoch": 297.8888888888889, "percentage": 67.03, "elapsed_time": "3:02:07", "remaining_time": "1:29:35", "throughput": 687.34, "total_tokens": 7510608} {"current_steps": 26815, "total_steps": 40000, "loss": 0.0, "lr": 1.2250311421814104e-05, "epoch": 297.94444444444446, "percentage": 67.04, "elapsed_time": "3:02:09", "remaining_time": "1:29:33", "throughput": 687.34, "total_tokens": 7512000} {"current_steps": 26820, "total_steps": 40000, "loss": 0.0, "lr": 1.2241867590170772e-05, "epoch": 298.0, "percentage": 67.05, "elapsed_time": "3:02:11", "remaining_time": "1:29:31", "throughput": 687.34, "total_tokens": 7513456} {"current_steps": 26825, "total_steps": 40000, "loss": 0.0, "lr": 1.2233425725991799e-05, "epoch": 298.05555555555554, "percentage": 67.06, "elapsed_time": "3:02:13", "remaining_time": "1:29:29", "throughput": 687.32, "total_tokens": 7514800} {"current_steps": 26830, "total_steps": 40000, "loss": 0.0, "lr": 1.2224985830579003e-05, "epoch": 298.1111111111111, "percentage": 67.07, "elapsed_time": "3:02:15", "remaining_time": "1:29:27", "throughput": 687.33, "total_tokens": 7516192} {"current_steps": 26835, "total_steps": 40000, "loss": 0.0, "lr": 1.2216547905233944e-05, "epoch": 298.1666666666667, "percentage": 67.09, "elapsed_time": "3:02:17", "remaining_time": "1:29:25", "throughput": 687.33, "total_tokens": 7517600} {"current_steps": 26840, "total_steps": 40000, "loss": 0.0, "lr": 1.2208111951257842e-05, "epoch": 298.22222222222223, "percentage": 67.1, "elapsed_time": "3:02:19", "remaining_time": "1:29:23", "throughput": 687.33, "total_tokens": 7519024} {"current_steps": 26845, "total_steps": 40000, "loss": 0.0, "lr": 1.2199677969951622e-05, "epoch": 298.27777777777777, "percentage": 67.11, "elapsed_time": "3:02:21", "remaining_time": "1:29:21", "throughput": 687.33, "total_tokens": 7520416} {"current_steps": 26850, "total_steps": 40000, "loss": 0.0, "lr": 1.2191245962615927e-05, "epoch": 298.3333333333333, "percentage": 67.12, "elapsed_time": "3:02:23", "remaining_time": "1:29:19", "throughput": 687.34, "total_tokens": 7521872} {"current_steps": 26855, "total_steps": 40000, "loss": 0.0, "lr": 1.218281593055106e-05, "epoch": 298.3888888888889, "percentage": 67.14, "elapsed_time": "3:02:25", "remaining_time": "1:29:17", "throughput": 687.34, "total_tokens": 7523232} {"current_steps": 26860, "total_steps": 40000, "loss": 0.0, "lr": 1.217438787505705e-05, "epoch": 298.44444444444446, "percentage": 67.15, "elapsed_time": "3:02:27", "remaining_time": "1:29:15", "throughput": 687.35, "total_tokens": 7524672} {"current_steps": 26865, "total_steps": 40000, "loss": 0.0, "lr": 1.2165961797433615e-05, "epoch": 298.5, "percentage": 67.16, "elapsed_time": "3:02:29", "remaining_time": "1:29:13", "throughput": 687.36, "total_tokens": 7526064} {"current_steps": 26870, "total_steps": 40000, "loss": 0.0, "lr": 1.215753769898014e-05, "epoch": 298.55555555555554, "percentage": 67.17, "elapsed_time": "3:02:31", "remaining_time": "1:29:11", "throughput": 687.37, "total_tokens": 7527488} {"current_steps": 26875, "total_steps": 40000, "loss": 0.0, "lr": 1.2149115580995755e-05, "epoch": 298.6111111111111, "percentage": 67.19, "elapsed_time": "3:02:33", "remaining_time": "1:29:09", "throughput": 687.37, "total_tokens": 7528816} {"current_steps": 26880, "total_steps": 40000, "loss": 0.0, "lr": 1.2140695444779227e-05, "epoch": 298.6666666666667, "percentage": 67.2, "elapsed_time": "3:02:35", "remaining_time": "1:29:07", "throughput": 687.37, "total_tokens": 7530224} {"current_steps": 26885, "total_steps": 40000, "loss": 0.0, "lr": 1.2132277291629066e-05, "epoch": 298.72222222222223, "percentage": 67.21, "elapsed_time": "3:02:36", "remaining_time": "1:29:05", "throughput": 687.38, "total_tokens": 7531600} {"current_steps": 26890, "total_steps": 40000, "loss": 0.0, "lr": 1.2123861122843458e-05, "epoch": 298.77777777777777, "percentage": 67.22, "elapsed_time": "3:02:38", "remaining_time": "1:29:02", "throughput": 687.39, "total_tokens": 7533008} {"current_steps": 26895, "total_steps": 40000, "loss": 0.0, "lr": 1.2115446939720271e-05, "epoch": 298.8333333333333, "percentage": 67.24, "elapsed_time": "3:02:40", "remaining_time": "1:29:00", "throughput": 687.39, "total_tokens": 7534400} {"current_steps": 26900, "total_steps": 40000, "loss": 0.0, "lr": 1.210703474355708e-05, "epoch": 298.8888888888889, "percentage": 67.25, "elapsed_time": "3:02:42", "remaining_time": "1:28:58", "throughput": 687.4, "total_tokens": 7535776} {"current_steps": 26905, "total_steps": 40000, "loss": 0.0, "lr": 1.2098624535651164e-05, "epoch": 298.94444444444446, "percentage": 67.26, "elapsed_time": "3:02:44", "remaining_time": "1:28:56", "throughput": 687.4, "total_tokens": 7537184} {"current_steps": 26910, "total_steps": 40000, "loss": 0.0, "lr": 1.2090216317299477e-05, "epoch": 299.0, "percentage": 67.27, "elapsed_time": "3:02:46", "remaining_time": "1:28:54", "throughput": 687.4, "total_tokens": 7538640} {"current_steps": 26915, "total_steps": 40000, "loss": 0.0, "lr": 1.2081810089798668e-05, "epoch": 299.05555555555554, "percentage": 67.29, "elapsed_time": "3:02:49", "remaining_time": "1:28:52", "throughput": 687.39, "total_tokens": 7540048} {"current_steps": 26920, "total_steps": 40000, "loss": 0.0, "lr": 1.2073405854445072e-05, "epoch": 299.1111111111111, "percentage": 67.3, "elapsed_time": "3:02:50", "remaining_time": "1:28:50", "throughput": 687.4, "total_tokens": 7541424} {"current_steps": 26925, "total_steps": 40000, "loss": 0.0, "lr": 1.206500361253474e-05, "epoch": 299.1666666666667, "percentage": 67.31, "elapsed_time": "3:02:52", "remaining_time": "1:28:48", "throughput": 687.4, "total_tokens": 7542832} {"current_steps": 26930, "total_steps": 40000, "loss": 0.0, "lr": 1.2056603365363409e-05, "epoch": 299.22222222222223, "percentage": 67.33, "elapsed_time": "3:02:54", "remaining_time": "1:28:46", "throughput": 687.41, "total_tokens": 7544256} {"current_steps": 26935, "total_steps": 40000, "loss": 0.0, "lr": 1.2048205114226487e-05, "epoch": 299.27777777777777, "percentage": 67.34, "elapsed_time": "3:02:56", "remaining_time": "1:28:44", "throughput": 687.41, "total_tokens": 7545600} {"current_steps": 26940, "total_steps": 40000, "loss": 0.0, "lr": 1.2039808860419102e-05, "epoch": 299.3333333333333, "percentage": 67.35, "elapsed_time": "3:02:58", "remaining_time": "1:28:42", "throughput": 687.42, "total_tokens": 7547024} {"current_steps": 26945, "total_steps": 40000, "loss": 0.0, "lr": 1.2031414605236066e-05, "epoch": 299.3888888888889, "percentage": 67.36, "elapsed_time": "3:03:00", "remaining_time": "1:28:40", "throughput": 687.43, "total_tokens": 7548432} {"current_steps": 26950, "total_steps": 40000, "loss": 0.0, "lr": 1.2023022349971862e-05, "epoch": 299.44444444444446, "percentage": 67.38, "elapsed_time": "3:03:02", "remaining_time": "1:28:38", "throughput": 687.44, "total_tokens": 7549840} {"current_steps": 26955, "total_steps": 40000, "loss": 0.0, "lr": 1.20146320959207e-05, "epoch": 299.5, "percentage": 67.39, "elapsed_time": "3:03:04", "remaining_time": "1:28:36", "throughput": 687.45, "total_tokens": 7551280} {"current_steps": 26960, "total_steps": 40000, "loss": 0.0, "lr": 1.2006243844376445e-05, "epoch": 299.55555555555554, "percentage": 67.4, "elapsed_time": "3:03:06", "remaining_time": "1:28:33", "throughput": 687.45, "total_tokens": 7552640} {"current_steps": 26965, "total_steps": 40000, "loss": 0.0, "lr": 1.1997857596632678e-05, "epoch": 299.6111111111111, "percentage": 67.41, "elapsed_time": "3:03:08", "remaining_time": "1:28:31", "throughput": 687.45, "total_tokens": 7553984} {"current_steps": 26970, "total_steps": 40000, "loss": 0.0, "lr": 1.1989473353982672e-05, "epoch": 299.6666666666667, "percentage": 67.42, "elapsed_time": "3:03:10", "remaining_time": "1:28:29", "throughput": 687.46, "total_tokens": 7555408} {"current_steps": 26975, "total_steps": 40000, "loss": 0.0, "lr": 1.198109111771937e-05, "epoch": 299.72222222222223, "percentage": 67.44, "elapsed_time": "3:03:12", "remaining_time": "1:28:27", "throughput": 687.46, "total_tokens": 7556784} {"current_steps": 26980, "total_steps": 40000, "loss": 0.0, "lr": 1.197271088913543e-05, "epoch": 299.77777777777777, "percentage": 67.45, "elapsed_time": "3:03:14", "remaining_time": "1:28:25", "throughput": 687.47, "total_tokens": 7558176} {"current_steps": 26985, "total_steps": 40000, "loss": 0.0, "lr": 1.1964332669523182e-05, "epoch": 299.8333333333333, "percentage": 67.46, "elapsed_time": "3:03:16", "remaining_time": "1:28:23", "throughput": 687.48, "total_tokens": 7559648} {"current_steps": 26990, "total_steps": 40000, "loss": 0.0, "lr": 1.1955956460174645e-05, "epoch": 299.8888888888889, "percentage": 67.47, "elapsed_time": "3:03:18", "remaining_time": "1:28:21", "throughput": 687.49, "total_tokens": 7561056} {"current_steps": 26995, "total_steps": 40000, "loss": 0.0, "lr": 1.1947582262381552e-05, "epoch": 299.94444444444446, "percentage": 67.49, "elapsed_time": "3:03:20", "remaining_time": "1:28:19", "throughput": 687.49, "total_tokens": 7562464} {"current_steps": 27000, "total_steps": 40000, "loss": 0.0, "lr": 1.1939210077435293e-05, "epoch": 300.0, "percentage": 67.5, "elapsed_time": "3:03:22", "remaining_time": "1:28:17", "throughput": 687.49, "total_tokens": 7563888} {"current_steps": 27000, "total_steps": 40000, "eval_loss": 0.3090466856956482, "epoch": 300.0, "percentage": 67.5, "elapsed_time": "3:03:23", "remaining_time": "1:28:17", "throughput": 687.41, "total_tokens": 7563888} {"current_steps": 27005, "total_steps": 40000, "loss": 0.0, "lr": 1.193083990662697e-05, "epoch": 300.05555555555554, "percentage": 67.51, "elapsed_time": "3:03:27", "remaining_time": "1:28:16", "throughput": 687.32, "total_tokens": 7565312} {"current_steps": 27010, "total_steps": 40000, "loss": 0.0, "lr": 1.192247175124738e-05, "epoch": 300.1111111111111, "percentage": 67.53, "elapsed_time": "3:03:28", "remaining_time": "1:28:14", "throughput": 687.32, "total_tokens": 7566688} {"current_steps": 27015, "total_steps": 40000, "loss": 0.0, "lr": 1.191410561258698e-05, "epoch": 300.1666666666667, "percentage": 67.54, "elapsed_time": "3:03:30", "remaining_time": "1:28:12", "throughput": 687.32, "total_tokens": 7568096} {"current_steps": 27020, "total_steps": 40000, "loss": 0.0, "lr": 1.1905741491935944e-05, "epoch": 300.22222222222223, "percentage": 67.55, "elapsed_time": "3:03:32", "remaining_time": "1:28:10", "throughput": 687.33, "total_tokens": 7569472} {"current_steps": 27025, "total_steps": 40000, "loss": 0.0, "lr": 1.1897379390584129e-05, "epoch": 300.27777777777777, "percentage": 67.56, "elapsed_time": "3:03:34", "remaining_time": "1:28:08", "throughput": 687.34, "total_tokens": 7570944} {"current_steps": 27030, "total_steps": 40000, "loss": 0.0, "lr": 1.1889019309821062e-05, "epoch": 300.3333333333333, "percentage": 67.58, "elapsed_time": "3:03:36", "remaining_time": "1:28:06", "throughput": 687.35, "total_tokens": 7572384} {"current_steps": 27035, "total_steps": 40000, "loss": 0.0, "lr": 1.188066125093599e-05, "epoch": 300.3888888888889, "percentage": 67.59, "elapsed_time": "3:03:38", "remaining_time": "1:28:04", "throughput": 687.35, "total_tokens": 7573776} {"current_steps": 27040, "total_steps": 40000, "loss": 0.0, "lr": 1.1872305215217811e-05, "epoch": 300.44444444444446, "percentage": 67.6, "elapsed_time": "3:03:40", "remaining_time": "1:28:02", "throughput": 687.36, "total_tokens": 7575216} {"current_steps": 27045, "total_steps": 40000, "loss": 0.0, "lr": 1.186395120395514e-05, "epoch": 300.5, "percentage": 67.61, "elapsed_time": "3:03:42", "remaining_time": "1:28:00", "throughput": 687.37, "total_tokens": 7576656} {"current_steps": 27050, "total_steps": 40000, "loss": 0.0, "lr": 1.1855599218436283e-05, "epoch": 300.55555555555554, "percentage": 67.62, "elapsed_time": "3:03:44", "remaining_time": "1:27:57", "throughput": 687.38, "total_tokens": 7578048} {"current_steps": 27055, "total_steps": 40000, "loss": 0.0, "lr": 1.1847249259949209e-05, "epoch": 300.6111111111111, "percentage": 67.64, "elapsed_time": "3:03:46", "remaining_time": "1:27:55", "throughput": 687.38, "total_tokens": 7579392} {"current_steps": 27060, "total_steps": 40000, "loss": 0.0, "lr": 1.1838901329781574e-05, "epoch": 300.6666666666667, "percentage": 67.65, "elapsed_time": "3:03:48", "remaining_time": "1:27:53", "throughput": 687.38, "total_tokens": 7580752} {"current_steps": 27065, "total_steps": 40000, "loss": 0.0, "lr": 1.1830555429220758e-05, "epoch": 300.72222222222223, "percentage": 67.66, "elapsed_time": "3:03:50", "remaining_time": "1:27:51", "throughput": 687.39, "total_tokens": 7582144} {"current_steps": 27070, "total_steps": 40000, "loss": 0.0, "lr": 1.1822211559553784e-05, "epoch": 300.77777777777777, "percentage": 67.67, "elapsed_time": "3:03:52", "remaining_time": "1:27:49", "throughput": 687.39, "total_tokens": 7583488} {"current_steps": 27075, "total_steps": 40000, "loss": 0.0, "lr": 1.18138697220674e-05, "epoch": 300.8333333333333, "percentage": 67.69, "elapsed_time": "3:03:54", "remaining_time": "1:27:47", "throughput": 687.4, "total_tokens": 7584912} {"current_steps": 27080, "total_steps": 40000, "loss": 0.0, "lr": 1.1805529918048e-05, "epoch": 300.8888888888889, "percentage": 67.7, "elapsed_time": "3:03:56", "remaining_time": "1:27:45", "throughput": 687.4, "total_tokens": 7586256} {"current_steps": 27085, "total_steps": 40000, "loss": 0.0, "lr": 1.1797192148781702e-05, "epoch": 300.94444444444446, "percentage": 67.71, "elapsed_time": "3:03:58", "remaining_time": "1:27:43", "throughput": 687.4, "total_tokens": 7587648} {"current_steps": 27090, "total_steps": 40000, "loss": 0.0, "lr": 1.1788856415554297e-05, "epoch": 301.0, "percentage": 67.73, "elapsed_time": "3:04:00", "remaining_time": "1:27:41", "throughput": 687.4, "total_tokens": 7589088} {"current_steps": 27095, "total_steps": 40000, "loss": 0.0, "lr": 1.1780522719651249e-05, "epoch": 301.05555555555554, "percentage": 67.74, "elapsed_time": "3:04:02", "remaining_time": "1:27:39", "throughput": 687.39, "total_tokens": 7590512} {"current_steps": 27100, "total_steps": 40000, "loss": 0.0, "lr": 1.1772191062357721e-05, "epoch": 301.1111111111111, "percentage": 67.75, "elapsed_time": "3:04:04", "remaining_time": "1:27:37", "throughput": 687.4, "total_tokens": 7591920} {"current_steps": 27105, "total_steps": 40000, "loss": 0.0, "lr": 1.1763861444958573e-05, "epoch": 301.1666666666667, "percentage": 67.76, "elapsed_time": "3:04:06", "remaining_time": "1:27:35", "throughput": 687.4, "total_tokens": 7593296} {"current_steps": 27110, "total_steps": 40000, "loss": 0.0, "lr": 1.1755533868738317e-05, "epoch": 301.22222222222223, "percentage": 67.77, "elapsed_time": "3:04:08", "remaining_time": "1:27:33", "throughput": 687.41, "total_tokens": 7594688} {"current_steps": 27115, "total_steps": 40000, "loss": 0.0, "lr": 1.1747208334981185e-05, "epoch": 301.27777777777777, "percentage": 67.79, "elapsed_time": "3:04:10", "remaining_time": "1:27:31", "throughput": 687.41, "total_tokens": 7596032} {"current_steps": 27120, "total_steps": 40000, "loss": 0.0, "lr": 1.1738884844971067e-05, "epoch": 301.3333333333333, "percentage": 67.8, "elapsed_time": "3:04:12", "remaining_time": "1:27:28", "throughput": 687.42, "total_tokens": 7597472} {"current_steps": 27125, "total_steps": 40000, "loss": 0.0, "lr": 1.1730563399991563e-05, "epoch": 301.3888888888889, "percentage": 67.81, "elapsed_time": "3:04:14", "remaining_time": "1:27:26", "throughput": 687.43, "total_tokens": 7598896} {"current_steps": 27130, "total_steps": 40000, "loss": 0.0, "lr": 1.1722244001325938e-05, "epoch": 301.44444444444446, "percentage": 67.83, "elapsed_time": "3:04:16", "remaining_time": "1:27:24", "throughput": 687.44, "total_tokens": 7600336} {"current_steps": 27135, "total_steps": 40000, "loss": 0.0, "lr": 1.1713926650257137e-05, "epoch": 301.5, "percentage": 67.84, "elapsed_time": "3:04:17", "remaining_time": "1:27:22", "throughput": 687.45, "total_tokens": 7601776} {"current_steps": 27140, "total_steps": 40000, "loss": 0.0, "lr": 1.170561134806781e-05, "epoch": 301.55555555555554, "percentage": 67.85, "elapsed_time": "3:04:19", "remaining_time": "1:27:20", "throughput": 687.45, "total_tokens": 7603168} {"current_steps": 27145, "total_steps": 40000, "loss": 0.0, "lr": 1.1697298096040287e-05, "epoch": 301.6111111111111, "percentage": 67.86, "elapsed_time": "3:04:21", "remaining_time": "1:27:18", "throughput": 687.46, "total_tokens": 7604544} {"current_steps": 27150, "total_steps": 40000, "loss": 0.0, "lr": 1.1688986895456567e-05, "epoch": 301.6666666666667, "percentage": 67.88, "elapsed_time": "3:04:23", "remaining_time": "1:27:16", "throughput": 687.46, "total_tokens": 7605904} {"current_steps": 27155, "total_steps": 40000, "loss": 0.0, "lr": 1.1680677747598349e-05, "epoch": 301.72222222222223, "percentage": 67.89, "elapsed_time": "3:04:25", "remaining_time": "1:27:14", "throughput": 687.46, "total_tokens": 7607280} {"current_steps": 27160, "total_steps": 40000, "loss": 0.0, "lr": 1.1672370653746995e-05, "epoch": 301.77777777777777, "percentage": 67.9, "elapsed_time": "3:04:27", "remaining_time": "1:27:12", "throughput": 687.47, "total_tokens": 7608672} {"current_steps": 27165, "total_steps": 40000, "loss": 0.0, "lr": 1.166406561518357e-05, "epoch": 301.8333333333333, "percentage": 67.91, "elapsed_time": "3:04:29", "remaining_time": "1:27:10", "throughput": 687.47, "total_tokens": 7610064} {"current_steps": 27170, "total_steps": 40000, "loss": 0.0, "lr": 1.1655762633188826e-05, "epoch": 301.8888888888889, "percentage": 67.92, "elapsed_time": "3:04:31", "remaining_time": "1:27:08", "throughput": 687.48, "total_tokens": 7611488} {"current_steps": 27175, "total_steps": 40000, "loss": 0.0, "lr": 1.1647461709043172e-05, "epoch": 301.94444444444446, "percentage": 67.94, "elapsed_time": "3:04:33", "remaining_time": "1:27:06", "throughput": 687.49, "total_tokens": 7612896} {"current_steps": 27180, "total_steps": 40000, "loss": 0.0, "lr": 1.1639162844026722e-05, "epoch": 302.0, "percentage": 67.95, "elapsed_time": "3:04:35", "remaining_time": "1:27:04", "throughput": 687.48, "total_tokens": 7614288} {"current_steps": 27185, "total_steps": 40000, "loss": 0.0, "lr": 1.163086603941927e-05, "epoch": 302.05555555555554, "percentage": 67.96, "elapsed_time": "3:04:37", "remaining_time": "1:27:02", "throughput": 687.48, "total_tokens": 7615712} {"current_steps": 27190, "total_steps": 40000, "loss": 0.0, "lr": 1.1622571296500273e-05, "epoch": 302.1111111111111, "percentage": 67.97, "elapsed_time": "3:04:39", "remaining_time": "1:26:59", "throughput": 687.48, "total_tokens": 7617072} {"current_steps": 27195, "total_steps": 40000, "loss": 0.0, "lr": 1.1614278616548904e-05, "epoch": 302.1666666666667, "percentage": 67.99, "elapsed_time": "3:04:41", "remaining_time": "1:26:57", "throughput": 687.48, "total_tokens": 7618464} {"current_steps": 27200, "total_steps": 40000, "loss": 0.0, "lr": 1.1605988000843986e-05, "epoch": 302.22222222222223, "percentage": 68.0, "elapsed_time": "3:04:43", "remaining_time": "1:26:55", "throughput": 687.49, "total_tokens": 7619872} {"current_steps": 27200, "total_steps": 40000, "eval_loss": 0.3612271845340729, "epoch": 302.22222222222223, "percentage": 68.0, "elapsed_time": "3:04:44", "remaining_time": "1:26:56", "throughput": 687.41, "total_tokens": 7619872} {"current_steps": 27205, "total_steps": 40000, "loss": 0.0, "lr": 1.1597699450664028e-05, "epoch": 302.27777777777777, "percentage": 68.01, "elapsed_time": "3:04:48", "remaining_time": "1:26:54", "throughput": 687.34, "total_tokens": 7621296} {"current_steps": 27210, "total_steps": 40000, "loss": 0.0, "lr": 1.1589412967287252e-05, "epoch": 302.3333333333333, "percentage": 68.03, "elapsed_time": "3:04:50", "remaining_time": "1:26:52", "throughput": 687.35, "total_tokens": 7622752} {"current_steps": 27215, "total_steps": 40000, "loss": 0.0, "lr": 1.1581128551991514e-05, "epoch": 302.3888888888889, "percentage": 68.04, "elapsed_time": "3:04:52", "remaining_time": "1:26:50", "throughput": 687.35, "total_tokens": 7624144} {"current_steps": 27220, "total_steps": 40000, "loss": 0.0, "lr": 1.1572846206054383e-05, "epoch": 302.44444444444446, "percentage": 68.05, "elapsed_time": "3:04:54", "remaining_time": "1:26:48", "throughput": 687.35, "total_tokens": 7625536} {"current_steps": 27225, "total_steps": 40000, "loss": 0.0, "lr": 1.1564565930753113e-05, "epoch": 302.5, "percentage": 68.06, "elapsed_time": "3:04:56", "remaining_time": "1:26:46", "throughput": 687.36, "total_tokens": 7626928} {"current_steps": 27230, "total_steps": 40000, "loss": 0.0, "lr": 1.1556287727364606e-05, "epoch": 302.55555555555554, "percentage": 68.08, "elapsed_time": "3:04:57", "remaining_time": "1:26:44", "throughput": 687.36, "total_tokens": 7628272} {"current_steps": 27235, "total_steps": 40000, "loss": 0.0, "lr": 1.1548011597165489e-05, "epoch": 302.6111111111111, "percentage": 68.09, "elapsed_time": "3:04:59", "remaining_time": "1:26:42", "throughput": 687.36, "total_tokens": 7629664} {"current_steps": 27240, "total_steps": 40000, "loss": 0.0, "lr": 1.1539737541432019e-05, "epoch": 302.6666666666667, "percentage": 68.1, "elapsed_time": "3:05:01", "remaining_time": "1:26:40", "throughput": 687.37, "total_tokens": 7631088} {"current_steps": 27245, "total_steps": 40000, "loss": 0.0, "lr": 1.1531465561440174e-05, "epoch": 302.72222222222223, "percentage": 68.11, "elapsed_time": "3:05:03", "remaining_time": "1:26:38", "throughput": 687.38, "total_tokens": 7632528} {"current_steps": 27250, "total_steps": 40000, "loss": 0.0, "lr": 1.1523195658465605e-05, "epoch": 302.77777777777777, "percentage": 68.12, "elapsed_time": "3:05:05", "remaining_time": "1:26:36", "throughput": 687.39, "total_tokens": 7633904} {"current_steps": 27255, "total_steps": 40000, "loss": 0.0, "lr": 1.1514927833783618e-05, "epoch": 302.8333333333333, "percentage": 68.14, "elapsed_time": "3:05:07", "remaining_time": "1:26:34", "throughput": 687.39, "total_tokens": 7635296} {"current_steps": 27260, "total_steps": 40000, "loss": 0.0, "lr": 1.150666208866922e-05, "epoch": 302.8888888888889, "percentage": 68.15, "elapsed_time": "3:05:09", "remaining_time": "1:26:32", "throughput": 687.39, "total_tokens": 7636640} {"current_steps": 27265, "total_steps": 40000, "loss": 0.0, "lr": 1.1498398424397106e-05, "epoch": 302.94444444444446, "percentage": 68.16, "elapsed_time": "3:05:11", "remaining_time": "1:26:29", "throughput": 687.4, "total_tokens": 7638080} {"current_steps": 27270, "total_steps": 40000, "loss": 0.0, "lr": 1.1490136842241628e-05, "epoch": 303.0, "percentage": 68.17, "elapsed_time": "3:05:13", "remaining_time": "1:26:27", "throughput": 687.4, "total_tokens": 7639472} {"current_steps": 27275, "total_steps": 40000, "loss": 0.0, "lr": 1.1481877343476813e-05, "epoch": 303.05555555555554, "percentage": 68.19, "elapsed_time": "3:05:15", "remaining_time": "1:26:26", "throughput": 687.39, "total_tokens": 7640864} {"current_steps": 27280, "total_steps": 40000, "loss": 0.0, "lr": 1.14736199293764e-05, "epoch": 303.1111111111111, "percentage": 68.2, "elapsed_time": "3:05:17", "remaining_time": "1:26:23", "throughput": 687.39, "total_tokens": 7642208} {"current_steps": 27285, "total_steps": 40000, "loss": 0.0, "lr": 1.1465364601213771e-05, "epoch": 303.1666666666667, "percentage": 68.21, "elapsed_time": "3:05:19", "remaining_time": "1:26:21", "throughput": 687.39, "total_tokens": 7643584} {"current_steps": 27290, "total_steps": 40000, "loss": 0.0, "lr": 1.1457111360262012e-05, "epoch": 303.22222222222223, "percentage": 68.23, "elapsed_time": "3:05:21", "remaining_time": "1:26:19", "throughput": 687.4, "total_tokens": 7644976} {"current_steps": 27295, "total_steps": 40000, "loss": 0.0, "lr": 1.1448860207793869e-05, "epoch": 303.27777777777777, "percentage": 68.24, "elapsed_time": "3:05:23", "remaining_time": "1:26:17", "throughput": 687.4, "total_tokens": 7646400} {"current_steps": 27300, "total_steps": 40000, "loss": 0.0, "lr": 1.144061114508177e-05, "epoch": 303.3333333333333, "percentage": 68.25, "elapsed_time": "3:05:25", "remaining_time": "1:26:15", "throughput": 687.41, "total_tokens": 7647824} {"current_steps": 27305, "total_steps": 40000, "loss": 0.0, "lr": 1.1432364173397842e-05, "epoch": 303.3888888888889, "percentage": 68.26, "elapsed_time": "3:05:27", "remaining_time": "1:26:13", "throughput": 687.42, "total_tokens": 7649232} {"current_steps": 27310, "total_steps": 40000, "loss": 0.0, "lr": 1.1424119294013852e-05, "epoch": 303.44444444444446, "percentage": 68.27, "elapsed_time": "3:05:29", "remaining_time": "1:26:11", "throughput": 687.43, "total_tokens": 7650656} {"current_steps": 27315, "total_steps": 40000, "loss": 0.0, "lr": 1.1415876508201279e-05, "epoch": 303.5, "percentage": 68.29, "elapsed_time": "3:05:31", "remaining_time": "1:26:09", "throughput": 687.44, "total_tokens": 7652080} {"current_steps": 27320, "total_steps": 40000, "loss": 0.0, "lr": 1.140763581723125e-05, "epoch": 303.55555555555554, "percentage": 68.3, "elapsed_time": "3:05:33", "remaining_time": "1:26:07", "throughput": 687.45, "total_tokens": 7653520} {"current_steps": 27325, "total_steps": 40000, "loss": 0.0, "lr": 1.1399397222374588e-05, "epoch": 303.6111111111111, "percentage": 68.31, "elapsed_time": "3:05:35", "remaining_time": "1:26:05", "throughput": 687.45, "total_tokens": 7654896} {"current_steps": 27330, "total_steps": 40000, "loss": 0.0, "lr": 1.1391160724901804e-05, "epoch": 303.6666666666667, "percentage": 68.33, "elapsed_time": "3:05:37", "remaining_time": "1:26:03", "throughput": 687.45, "total_tokens": 7656272} {"current_steps": 27335, "total_steps": 40000, "loss": 0.0, "lr": 1.138292632608304e-05, "epoch": 303.72222222222223, "percentage": 68.34, "elapsed_time": "3:05:39", "remaining_time": "1:26:01", "throughput": 687.46, "total_tokens": 7657680} {"current_steps": 27340, "total_steps": 40000, "loss": 0.0, "lr": 1.1374694027188174e-05, "epoch": 303.77777777777777, "percentage": 68.35, "elapsed_time": "3:05:41", "remaining_time": "1:25:58", "throughput": 687.47, "total_tokens": 7659136} {"current_steps": 27345, "total_steps": 40000, "loss": 0.0, "lr": 1.1366463829486711e-05, "epoch": 303.8333333333333, "percentage": 68.36, "elapsed_time": "3:05:42", "remaining_time": "1:25:56", "throughput": 687.48, "total_tokens": 7660592} {"current_steps": 27350, "total_steps": 40000, "loss": 0.0, "lr": 1.1358235734247849e-05, "epoch": 303.8888888888889, "percentage": 68.38, "elapsed_time": "3:05:44", "remaining_time": "1:25:54", "throughput": 687.49, "total_tokens": 7662000} {"current_steps": 27355, "total_steps": 40000, "loss": 0.0, "lr": 1.1350009742740478e-05, "epoch": 303.94444444444446, "percentage": 68.39, "elapsed_time": "3:05:46", "remaining_time": "1:25:52", "throughput": 687.5, "total_tokens": 7663392} {"current_steps": 27360, "total_steps": 40000, "loss": 0.0, "lr": 1.134178585623313e-05, "epoch": 304.0, "percentage": 68.4, "elapsed_time": "3:05:48", "remaining_time": "1:25:50", "throughput": 687.49, "total_tokens": 7664784} {"current_steps": 27365, "total_steps": 40000, "loss": 0.0, "lr": 1.1333564075994047e-05, "epoch": 304.05555555555554, "percentage": 68.41, "elapsed_time": "3:05:51", "remaining_time": "1:25:48", "throughput": 687.48, "total_tokens": 7666192} {"current_steps": 27370, "total_steps": 40000, "loss": 0.0, "lr": 1.1325344403291133e-05, "epoch": 304.1111111111111, "percentage": 68.42, "elapsed_time": "3:05:53", "remaining_time": "1:25:46", "throughput": 687.49, "total_tokens": 7667616} {"current_steps": 27375, "total_steps": 40000, "loss": 0.0, "lr": 1.1317126839391951e-05, "epoch": 304.1666666666667, "percentage": 68.44, "elapsed_time": "3:05:55", "remaining_time": "1:25:44", "throughput": 687.49, "total_tokens": 7669008} {"current_steps": 27380, "total_steps": 40000, "loss": 0.0, "lr": 1.1308911385563766e-05, "epoch": 304.22222222222223, "percentage": 68.45, "elapsed_time": "3:05:56", "remaining_time": "1:25:42", "throughput": 687.5, "total_tokens": 7670432} {"current_steps": 27385, "total_steps": 40000, "loss": 0.0, "lr": 1.1300698043073494e-05, "epoch": 304.27777777777777, "percentage": 68.46, "elapsed_time": "3:05:58", "remaining_time": "1:25:40", "throughput": 687.51, "total_tokens": 7671824} {"current_steps": 27390, "total_steps": 40000, "loss": 0.0, "lr": 1.1292486813187736e-05, "epoch": 304.3333333333333, "percentage": 68.47, "elapsed_time": "3:06:00", "remaining_time": "1:25:38", "throughput": 687.51, "total_tokens": 7673216} {"current_steps": 27395, "total_steps": 40000, "loss": 0.0, "lr": 1.1284277697172782e-05, "epoch": 304.3888888888889, "percentage": 68.49, "elapsed_time": "3:06:02", "remaining_time": "1:25:36", "throughput": 687.52, "total_tokens": 7674608} {"current_steps": 27400, "total_steps": 40000, "loss": 0.0, "lr": 1.127607069629456e-05, "epoch": 304.44444444444446, "percentage": 68.5, "elapsed_time": "3:06:04", "remaining_time": "1:25:34", "throughput": 687.53, "total_tokens": 7676016} {"current_steps": 27400, "total_steps": 40000, "eval_loss": 0.3266785740852356, "epoch": 304.44444444444446, "percentage": 68.5, "elapsed_time": "3:06:05", "remaining_time": "1:25:34", "throughput": 687.45, "total_tokens": 7676016} {"current_steps": 27405, "total_steps": 40000, "loss": 0.0, "lr": 1.1267865811818701e-05, "epoch": 304.5, "percentage": 68.51, "elapsed_time": "3:06:09", "remaining_time": "1:25:33", "throughput": 687.37, "total_tokens": 7677376} {"current_steps": 27410, "total_steps": 40000, "loss": 0.0, "lr": 1.1259663045010513e-05, "epoch": 304.55555555555554, "percentage": 68.53, "elapsed_time": "3:06:11", "remaining_time": "1:25:31", "throughput": 687.36, "total_tokens": 7678720} {"current_steps": 27415, "total_steps": 40000, "loss": 0.0, "lr": 1.1251462397134957e-05, "epoch": 304.6111111111111, "percentage": 68.54, "elapsed_time": "3:06:13", "remaining_time": "1:25:29", "throughput": 687.37, "total_tokens": 7680144} {"current_steps": 27420, "total_steps": 40000, "loss": 0.0, "lr": 1.1243263869456664e-05, "epoch": 304.6666666666667, "percentage": 68.55, "elapsed_time": "3:06:15", "remaining_time": "1:25:27", "throughput": 687.38, "total_tokens": 7681536} {"current_steps": 27425, "total_steps": 40000, "loss": 0.0, "lr": 1.1235067463239967e-05, "epoch": 304.72222222222223, "percentage": 68.56, "elapsed_time": "3:06:17", "remaining_time": "1:25:24", "throughput": 687.38, "total_tokens": 7682944} {"current_steps": 27430, "total_steps": 40000, "loss": 0.0, "lr": 1.122687317974884e-05, "epoch": 304.77777777777777, "percentage": 68.58, "elapsed_time": "3:06:19", "remaining_time": "1:25:22", "throughput": 687.39, "total_tokens": 7684336} {"current_steps": 27435, "total_steps": 40000, "loss": 0.0, "lr": 1.1218681020246963e-05, "epoch": 304.8333333333333, "percentage": 68.59, "elapsed_time": "3:06:20", "remaining_time": "1:25:20", "throughput": 687.4, "total_tokens": 7685744} {"current_steps": 27440, "total_steps": 40000, "loss": 0.0, "lr": 1.1210490985997652e-05, "epoch": 304.8888888888889, "percentage": 68.6, "elapsed_time": "3:06:22", "remaining_time": "1:25:18", "throughput": 687.4, "total_tokens": 7687120} {"current_steps": 27445, "total_steps": 40000, "loss": 0.0, "lr": 1.1202303078263917e-05, "epoch": 304.94444444444446, "percentage": 68.61, "elapsed_time": "3:06:24", "remaining_time": "1:25:16", "throughput": 687.41, "total_tokens": 7688560} {"current_steps": 27450, "total_steps": 40000, "loss": 0.0, "lr": 1.1194117298308451e-05, "epoch": 305.0, "percentage": 68.62, "elapsed_time": "3:06:26", "remaining_time": "1:25:14", "throughput": 687.4, "total_tokens": 7689952} {"current_steps": 27455, "total_steps": 40000, "loss": 0.0, "lr": 1.1185933647393585e-05, "epoch": 305.05555555555554, "percentage": 68.64, "elapsed_time": "3:06:29", "remaining_time": "1:25:12", "throughput": 687.4, "total_tokens": 7691360} {"current_steps": 27460, "total_steps": 40000, "loss": 0.0, "lr": 1.1177752126781354e-05, "epoch": 305.1111111111111, "percentage": 68.65, "elapsed_time": "3:06:31", "remaining_time": "1:25:10", "throughput": 687.4, "total_tokens": 7692784} {"current_steps": 27465, "total_steps": 40000, "loss": 0.0, "lr": 1.1169572737733441e-05, "epoch": 305.1666666666667, "percentage": 68.66, "elapsed_time": "3:06:33", "remaining_time": "1:25:08", "throughput": 687.4, "total_tokens": 7694144} {"current_steps": 27470, "total_steps": 40000, "loss": 0.0, "lr": 1.1161395481511216e-05, "epoch": 305.22222222222223, "percentage": 68.67, "elapsed_time": "3:06:34", "remaining_time": "1:25:06", "throughput": 687.41, "total_tokens": 7695536} {"current_steps": 27475, "total_steps": 40000, "loss": 0.0, "lr": 1.1153220359375722e-05, "epoch": 305.27777777777777, "percentage": 68.69, "elapsed_time": "3:06:36", "remaining_time": "1:25:04", "throughput": 687.42, "total_tokens": 7696928} {"current_steps": 27480, "total_steps": 40000, "loss": 0.0, "lr": 1.114504737258765e-05, "epoch": 305.3333333333333, "percentage": 68.7, "elapsed_time": "3:06:38", "remaining_time": "1:25:02", "throughput": 687.43, "total_tokens": 7698368} {"current_steps": 27485, "total_steps": 40000, "loss": 0.0, "lr": 1.1136876522407393e-05, "epoch": 305.3888888888889, "percentage": 68.71, "elapsed_time": "3:06:40", "remaining_time": "1:25:00", "throughput": 687.43, "total_tokens": 7699776} {"current_steps": 27490, "total_steps": 40000, "loss": 0.0, "lr": 1.1128707810094985e-05, "epoch": 305.44444444444446, "percentage": 68.73, "elapsed_time": "3:06:42", "remaining_time": "1:24:58", "throughput": 687.44, "total_tokens": 7701200} {"current_steps": 27495, "total_steps": 40000, "loss": 0.0, "lr": 1.1120541236910157e-05, "epoch": 305.5, "percentage": 68.74, "elapsed_time": "3:06:44", "remaining_time": "1:24:55", "throughput": 687.45, "total_tokens": 7702576} {"current_steps": 27500, "total_steps": 40000, "loss": 0.0, "lr": 1.111237680411229e-05, "epoch": 305.55555555555554, "percentage": 68.75, "elapsed_time": "3:06:46", "remaining_time": "1:24:53", "throughput": 687.45, "total_tokens": 7703984} {"current_steps": 27505, "total_steps": 40000, "loss": 0.0, "lr": 1.1104214512960433e-05, "epoch": 305.6111111111111, "percentage": 68.76, "elapsed_time": "3:06:48", "remaining_time": "1:24:51", "throughput": 687.46, "total_tokens": 7705360} {"current_steps": 27510, "total_steps": 40000, "loss": 0.0, "lr": 1.1096054364713327e-05, "epoch": 305.6666666666667, "percentage": 68.77, "elapsed_time": "3:06:50", "remaining_time": "1:24:49", "throughput": 687.46, "total_tokens": 7706752} {"current_steps": 27515, "total_steps": 40000, "loss": 0.0, "lr": 1.1087896360629371e-05, "epoch": 305.72222222222223, "percentage": 68.79, "elapsed_time": "3:06:52", "remaining_time": "1:24:47", "throughput": 687.46, "total_tokens": 7708112} {"current_steps": 27520, "total_steps": 40000, "loss": 0.0, "lr": 1.107974050196662e-05, "epoch": 305.77777777777777, "percentage": 68.8, "elapsed_time": "3:06:54", "remaining_time": "1:24:45", "throughput": 687.47, "total_tokens": 7709504} {"current_steps": 27525, "total_steps": 40000, "loss": 0.0, "lr": 1.1071586789982816e-05, "epoch": 305.8333333333333, "percentage": 68.81, "elapsed_time": "3:06:56", "remaining_time": "1:24:43", "throughput": 687.47, "total_tokens": 7710912} {"current_steps": 27530, "total_steps": 40000, "loss": 0.0, "lr": 1.1063435225935373e-05, "epoch": 305.8888888888889, "percentage": 68.83, "elapsed_time": "3:06:58", "remaining_time": "1:24:41", "throughput": 687.48, "total_tokens": 7712320} {"current_steps": 27535, "total_steps": 40000, "loss": 0.0, "lr": 1.1055285811081348e-05, "epoch": 305.94444444444446, "percentage": 68.84, "elapsed_time": "3:07:00", "remaining_time": "1:24:39", "throughput": 687.49, "total_tokens": 7713712} {"current_steps": 27540, "total_steps": 40000, "loss": 0.0, "lr": 1.1047138546677499e-05, "epoch": 306.0, "percentage": 68.85, "elapsed_time": "3:07:02", "remaining_time": "1:24:37", "throughput": 687.48, "total_tokens": 7715104} {"current_steps": 27545, "total_steps": 40000, "loss": 0.0, "lr": 1.1038993433980219e-05, "epoch": 306.05555555555554, "percentage": 68.86, "elapsed_time": "3:07:04", "remaining_time": "1:24:35", "throughput": 687.47, "total_tokens": 7716528} {"current_steps": 27550, "total_steps": 40000, "loss": 0.0, "lr": 1.1030850474245597e-05, "epoch": 306.1111111111111, "percentage": 68.88, "elapsed_time": "3:07:06", "remaining_time": "1:24:33", "throughput": 687.48, "total_tokens": 7717968} {"current_steps": 27555, "total_steps": 40000, "loss": 0.0, "lr": 1.102270966872939e-05, "epoch": 306.1666666666667, "percentage": 68.89, "elapsed_time": "3:07:08", "remaining_time": "1:24:31", "throughput": 687.49, "total_tokens": 7719360} {"current_steps": 27560, "total_steps": 40000, "loss": 0.0, "lr": 1.1014571018687e-05, "epoch": 306.22222222222223, "percentage": 68.9, "elapsed_time": "3:07:10", "remaining_time": "1:24:29", "throughput": 687.49, "total_tokens": 7720768} {"current_steps": 27565, "total_steps": 40000, "loss": 0.0, "lr": 1.1006434525373502e-05, "epoch": 306.27777777777777, "percentage": 68.91, "elapsed_time": "3:07:12", "remaining_time": "1:24:27", "throughput": 687.5, "total_tokens": 7722160} {"current_steps": 27570, "total_steps": 40000, "loss": 0.0, "lr": 1.0998300190043664e-05, "epoch": 306.3333333333333, "percentage": 68.92, "elapsed_time": "3:07:14", "remaining_time": "1:24:24", "throughput": 687.51, "total_tokens": 7723552} {"current_steps": 27575, "total_steps": 40000, "loss": 0.0, "lr": 1.0990168013951882e-05, "epoch": 306.3888888888889, "percentage": 68.94, "elapsed_time": "3:07:16", "remaining_time": "1:24:22", "throughput": 687.51, "total_tokens": 7724944} {"current_steps": 27580, "total_steps": 40000, "loss": 0.0, "lr": 1.0982037998352263e-05, "epoch": 306.44444444444446, "percentage": 68.95, "elapsed_time": "3:07:18", "remaining_time": "1:24:20", "throughput": 687.51, "total_tokens": 7726320} {"current_steps": 27585, "total_steps": 40000, "loss": 0.0, "lr": 1.0973910144498534e-05, "epoch": 306.5, "percentage": 68.96, "elapsed_time": "3:07:20", "remaining_time": "1:24:18", "throughput": 687.52, "total_tokens": 7727728} {"current_steps": 27590, "total_steps": 40000, "loss": 0.0, "lr": 1.0965784453644123e-05, "epoch": 306.55555555555554, "percentage": 68.97, "elapsed_time": "3:07:21", "remaining_time": "1:24:16", "throughput": 687.52, "total_tokens": 7729104} {"current_steps": 27595, "total_steps": 40000, "loss": 0.0, "lr": 1.0957660927042127e-05, "epoch": 306.6111111111111, "percentage": 68.99, "elapsed_time": "3:07:23", "remaining_time": "1:24:14", "throughput": 687.53, "total_tokens": 7730464} {"current_steps": 27600, "total_steps": 40000, "loss": 0.0, "lr": 1.094953956594527e-05, "epoch": 306.6666666666667, "percentage": 69.0, "elapsed_time": "3:07:25", "remaining_time": "1:24:12", "throughput": 687.53, "total_tokens": 7731872} {"current_steps": 27600, "total_steps": 40000, "eval_loss": 0.30818554759025574, "epoch": 306.6666666666667, "percentage": 69.0, "elapsed_time": "3:07:27", "remaining_time": "1:24:13", "throughput": 687.45, "total_tokens": 7731872} {"current_steps": 27605, "total_steps": 40000, "loss": 0.0, "lr": 1.0941420371605981e-05, "epoch": 306.72222222222223, "percentage": 69.01, "elapsed_time": "3:07:30", "remaining_time": "1:24:11", "throughput": 687.38, "total_tokens": 7733312} {"current_steps": 27610, "total_steps": 40000, "loss": 0.0, "lr": 1.0933303345276354e-05, "epoch": 306.77777777777777, "percentage": 69.03, "elapsed_time": "3:07:32", "remaining_time": "1:24:09", "throughput": 687.38, "total_tokens": 7734736} {"current_steps": 27615, "total_steps": 40000, "loss": 0.0, "lr": 1.0925188488208112e-05, "epoch": 306.8333333333333, "percentage": 69.04, "elapsed_time": "3:07:34", "remaining_time": "1:24:07", "throughput": 687.39, "total_tokens": 7736112} {"current_steps": 27620, "total_steps": 40000, "loss": 0.0, "lr": 1.0917075801652694e-05, "epoch": 306.8888888888889, "percentage": 69.05, "elapsed_time": "3:07:36", "remaining_time": "1:24:05", "throughput": 687.39, "total_tokens": 7737520} {"current_steps": 27625, "total_steps": 40000, "loss": 0.0, "lr": 1.0908965286861151e-05, "epoch": 306.94444444444446, "percentage": 69.06, "elapsed_time": "3:07:38", "remaining_time": "1:24:03", "throughput": 687.4, "total_tokens": 7738928} {"current_steps": 27630, "total_steps": 40000, "loss": 0.0, "lr": 1.090085694508425e-05, "epoch": 307.0, "percentage": 69.08, "elapsed_time": "3:07:40", "remaining_time": "1:24:01", "throughput": 687.39, "total_tokens": 7740304} {"current_steps": 27635, "total_steps": 40000, "loss": 0.0, "lr": 1.089275077757238e-05, "epoch": 307.05555555555554, "percentage": 69.09, "elapsed_time": "3:07:42", "remaining_time": "1:23:59", "throughput": 687.38, "total_tokens": 7741680} {"current_steps": 27640, "total_steps": 40000, "loss": 0.0, "lr": 1.0884646785575633e-05, "epoch": 307.1111111111111, "percentage": 69.1, "elapsed_time": "3:07:44", "remaining_time": "1:23:57", "throughput": 687.39, "total_tokens": 7743104} {"current_steps": 27645, "total_steps": 40000, "loss": 0.0, "lr": 1.0876544970343728e-05, "epoch": 307.1666666666667, "percentage": 69.11, "elapsed_time": "3:07:46", "remaining_time": "1:23:55", "throughput": 687.4, "total_tokens": 7744528} {"current_steps": 27650, "total_steps": 40000, "loss": 0.0, "lr": 1.0868445333126082e-05, "epoch": 307.22222222222223, "percentage": 69.12, "elapsed_time": "3:07:48", "remaining_time": "1:23:53", "throughput": 687.41, "total_tokens": 7745952} {"current_steps": 27655, "total_steps": 40000, "loss": 0.0, "lr": 1.0860347875171745e-05, "epoch": 307.27777777777777, "percentage": 69.14, "elapsed_time": "3:07:50", "remaining_time": "1:23:50", "throughput": 687.42, "total_tokens": 7747392} {"current_steps": 27660, "total_steps": 40000, "loss": 0.0, "lr": 1.0852252597729465e-05, "epoch": 307.3333333333333, "percentage": 69.15, "elapsed_time": "3:07:52", "remaining_time": "1:23:48", "throughput": 687.42, "total_tokens": 7748784} {"current_steps": 27665, "total_steps": 40000, "loss": 0.0, "lr": 1.0844159502047615e-05, "epoch": 307.3888888888889, "percentage": 69.16, "elapsed_time": "3:07:54", "remaining_time": "1:23:46", "throughput": 687.42, "total_tokens": 7750160} {"current_steps": 27670, "total_steps": 40000, "loss": 0.0, "lr": 1.0836068589374265e-05, "epoch": 307.44444444444446, "percentage": 69.17, "elapsed_time": "3:07:56", "remaining_time": "1:23:44", "throughput": 687.43, "total_tokens": 7751568} {"current_steps": 27675, "total_steps": 40000, "loss": 0.0, "lr": 1.0827979860957144e-05, "epoch": 307.5, "percentage": 69.19, "elapsed_time": "3:07:58", "remaining_time": "1:23:42", "throughput": 687.44, "total_tokens": 7752976} {"current_steps": 27680, "total_steps": 40000, "loss": 0.0, "lr": 1.0819893318043615e-05, "epoch": 307.55555555555554, "percentage": 69.2, "elapsed_time": "3:08:00", "remaining_time": "1:23:40", "throughput": 687.44, "total_tokens": 7754368} {"current_steps": 27685, "total_steps": 40000, "loss": 0.0, "lr": 1.0811808961880734e-05, "epoch": 307.6111111111111, "percentage": 69.21, "elapsed_time": "3:08:01", "remaining_time": "1:23:38", "throughput": 687.45, "total_tokens": 7755744} {"current_steps": 27690, "total_steps": 40000, "loss": 0.0, "lr": 1.080372679371522e-05, "epoch": 307.6666666666667, "percentage": 69.23, "elapsed_time": "3:08:03", "remaining_time": "1:23:36", "throughput": 687.45, "total_tokens": 7757168} {"current_steps": 27695, "total_steps": 40000, "loss": 0.0, "lr": 1.0795646814793428e-05, "epoch": 307.72222222222223, "percentage": 69.24, "elapsed_time": "3:08:05", "remaining_time": "1:23:34", "throughput": 687.46, "total_tokens": 7758544} {"current_steps": 27700, "total_steps": 40000, "loss": 0.0, "lr": 1.078756902636141e-05, "epoch": 307.77777777777777, "percentage": 69.25, "elapsed_time": "3:08:07", "remaining_time": "1:23:32", "throughput": 687.47, "total_tokens": 7760000} {"current_steps": 27705, "total_steps": 40000, "loss": 0.0, "lr": 1.077949342966485e-05, "epoch": 307.8333333333333, "percentage": 69.26, "elapsed_time": "3:08:09", "remaining_time": "1:23:30", "throughput": 687.47, "total_tokens": 7761376} {"current_steps": 27710, "total_steps": 40000, "loss": 0.0, "lr": 1.0771420025949103e-05, "epoch": 307.8888888888889, "percentage": 69.27, "elapsed_time": "3:08:11", "remaining_time": "1:23:28", "throughput": 687.48, "total_tokens": 7762784} {"current_steps": 27715, "total_steps": 40000, "loss": 0.0, "lr": 1.0763348816459204e-05, "epoch": 307.94444444444446, "percentage": 69.29, "elapsed_time": "3:08:13", "remaining_time": "1:23:26", "throughput": 687.48, "total_tokens": 7764128} {"current_steps": 27720, "total_steps": 40000, "loss": 0.0, "lr": 1.0755279802439816e-05, "epoch": 308.0, "percentage": 69.3, "elapsed_time": "3:08:15", "remaining_time": "1:23:24", "throughput": 687.48, "total_tokens": 7765584} {"current_steps": 27725, "total_steps": 40000, "loss": 0.0, "lr": 1.0747212985135293e-05, "epoch": 308.05555555555554, "percentage": 69.31, "elapsed_time": "3:08:17", "remaining_time": "1:23:22", "throughput": 687.47, "total_tokens": 7767008} {"current_steps": 27730, "total_steps": 40000, "loss": 0.0, "lr": 1.073914836578965e-05, "epoch": 308.1111111111111, "percentage": 69.33, "elapsed_time": "3:08:19", "remaining_time": "1:23:19", "throughput": 687.48, "total_tokens": 7768400} {"current_steps": 27735, "total_steps": 40000, "loss": 0.0, "lr": 1.0731085945646529e-05, "epoch": 308.1666666666667, "percentage": 69.34, "elapsed_time": "3:08:21", "remaining_time": "1:23:17", "throughput": 687.48, "total_tokens": 7769792} {"current_steps": 27740, "total_steps": 40000, "loss": 0.0, "lr": 1.0723025725949285e-05, "epoch": 308.22222222222223, "percentage": 69.35, "elapsed_time": "3:08:23", "remaining_time": "1:23:15", "throughput": 687.49, "total_tokens": 7771184} {"current_steps": 27745, "total_steps": 40000, "loss": 0.0, "lr": 1.0714967707940875e-05, "epoch": 308.27777777777777, "percentage": 69.36, "elapsed_time": "3:08:25", "remaining_time": "1:23:13", "throughput": 687.49, "total_tokens": 7772544} {"current_steps": 27750, "total_steps": 40000, "loss": 0.0, "lr": 1.0706911892863963e-05, "epoch": 308.3333333333333, "percentage": 69.38, "elapsed_time": "3:08:27", "remaining_time": "1:23:11", "throughput": 687.5, "total_tokens": 7773952} {"current_steps": 27755, "total_steps": 40000, "loss": 0.0, "lr": 1.0698858281960866e-05, "epoch": 308.3888888888889, "percentage": 69.39, "elapsed_time": "3:08:29", "remaining_time": "1:23:09", "throughput": 687.5, "total_tokens": 7775312} {"current_steps": 27760, "total_steps": 40000, "loss": 0.0, "lr": 1.069080687647353e-05, "epoch": 308.44444444444446, "percentage": 69.4, "elapsed_time": "3:08:31", "remaining_time": "1:23:07", "throughput": 687.5, "total_tokens": 7776672} {"current_steps": 27765, "total_steps": 40000, "loss": 0.0, "lr": 1.0682757677643596e-05, "epoch": 308.5, "percentage": 69.41, "elapsed_time": "3:08:33", "remaining_time": "1:23:05", "throughput": 687.51, "total_tokens": 7778080} {"current_steps": 27770, "total_steps": 40000, "loss": 0.0, "lr": 1.0674710686712359e-05, "epoch": 308.55555555555554, "percentage": 69.42, "elapsed_time": "3:08:35", "remaining_time": "1:23:03", "throughput": 687.52, "total_tokens": 7779504} {"current_steps": 27775, "total_steps": 40000, "loss": 0.0, "lr": 1.0666665904920756e-05, "epoch": 308.6111111111111, "percentage": 69.44, "elapsed_time": "3:08:37", "remaining_time": "1:23:01", "throughput": 687.52, "total_tokens": 7780896} {"current_steps": 27780, "total_steps": 40000, "loss": 0.0, "lr": 1.0658623333509385e-05, "epoch": 308.6666666666667, "percentage": 69.45, "elapsed_time": "3:08:39", "remaining_time": "1:22:59", "throughput": 687.53, "total_tokens": 7782320} {"current_steps": 27785, "total_steps": 40000, "loss": 0.0, "lr": 1.0650582973718532e-05, "epoch": 308.72222222222223, "percentage": 69.46, "elapsed_time": "3:08:41", "remaining_time": "1:22:57", "throughput": 687.54, "total_tokens": 7783760} {"current_steps": 27790, "total_steps": 40000, "loss": 0.0, "lr": 1.0642544826788098e-05, "epoch": 308.77777777777777, "percentage": 69.47, "elapsed_time": "3:08:43", "remaining_time": "1:22:54", "throughput": 687.55, "total_tokens": 7785152} {"current_steps": 27795, "total_steps": 40000, "loss": 0.0, "lr": 1.063450889395769e-05, "epoch": 308.8333333333333, "percentage": 69.49, "elapsed_time": "3:08:45", "remaining_time": "1:22:52", "throughput": 687.55, "total_tokens": 7786560} {"current_steps": 27800, "total_steps": 40000, "loss": 0.0, "lr": 1.062647517646653e-05, "epoch": 308.8888888888889, "percentage": 69.5, "elapsed_time": "3:08:46", "remaining_time": "1:22:50", "throughput": 687.55, "total_tokens": 7787920} {"current_steps": 27800, "total_steps": 40000, "eval_loss": 0.3292129337787628, "epoch": 308.8888888888889, "percentage": 69.5, "elapsed_time": "3:08:48", "remaining_time": "1:22:51", "throughput": 687.48, "total_tokens": 7787920} {"current_steps": 27805, "total_steps": 40000, "loss": 0.0, "lr": 1.0618443675553527e-05, "epoch": 308.94444444444446, "percentage": 69.51, "elapsed_time": "3:08:51", "remaining_time": "1:22:49", "throughput": 687.39, "total_tokens": 7789312} {"current_steps": 27810, "total_steps": 40000, "loss": 0.0, "lr": 1.0610414392457247e-05, "epoch": 309.0, "percentage": 69.53, "elapsed_time": "3:08:53", "remaining_time": "1:22:48", "throughput": 687.38, "total_tokens": 7790736} {"current_steps": 27815, "total_steps": 40000, "loss": 0.0, "lr": 1.0602387328415888e-05, "epoch": 309.05555555555554, "percentage": 69.54, "elapsed_time": "3:08:56", "remaining_time": "1:22:46", "throughput": 687.37, "total_tokens": 7792096} {"current_steps": 27820, "total_steps": 40000, "loss": 0.0, "lr": 1.0594362484667347e-05, "epoch": 309.1111111111111, "percentage": 69.55, "elapsed_time": "3:08:58", "remaining_time": "1:22:43", "throughput": 687.38, "total_tokens": 7793520} {"current_steps": 27825, "total_steps": 40000, "loss": 0.0, "lr": 1.0586339862449132e-05, "epoch": 309.1666666666667, "percentage": 69.56, "elapsed_time": "3:09:00", "remaining_time": "1:22:41", "throughput": 687.38, "total_tokens": 7794944} {"current_steps": 27830, "total_steps": 40000, "loss": 0.0, "lr": 1.0578319462998445e-05, "epoch": 309.22222222222223, "percentage": 69.58, "elapsed_time": "3:09:01", "remaining_time": "1:22:39", "throughput": 687.39, "total_tokens": 7796352} {"current_steps": 27835, "total_steps": 40000, "loss": 0.0, "lr": 1.057030128755214e-05, "epoch": 309.27777777777777, "percentage": 69.59, "elapsed_time": "3:09:03", "remaining_time": "1:22:37", "throughput": 687.4, "total_tokens": 7797760} {"current_steps": 27840, "total_steps": 40000, "loss": 0.0, "lr": 1.0562285337346703e-05, "epoch": 309.3333333333333, "percentage": 69.6, "elapsed_time": "3:09:05", "remaining_time": "1:22:35", "throughput": 687.41, "total_tokens": 7799200} {"current_steps": 27845, "total_steps": 40000, "loss": 0.0, "lr": 1.0554271613618308e-05, "epoch": 309.3888888888889, "percentage": 69.61, "elapsed_time": "3:09:07", "remaining_time": "1:22:33", "throughput": 687.41, "total_tokens": 7800592} {"current_steps": 27850, "total_steps": 40000, "loss": 0.0, "lr": 1.054626011760276e-05, "epoch": 309.44444444444446, "percentage": 69.62, "elapsed_time": "3:09:09", "remaining_time": "1:22:31", "throughput": 687.42, "total_tokens": 7802000} {"current_steps": 27855, "total_steps": 40000, "loss": 0.0, "lr": 1.0538250850535549e-05, "epoch": 309.5, "percentage": 69.64, "elapsed_time": "3:09:11", "remaining_time": "1:22:29", "throughput": 687.43, "total_tokens": 7803408} {"current_steps": 27860, "total_steps": 40000, "loss": 0.0, "lr": 1.0530243813651794e-05, "epoch": 309.55555555555554, "percentage": 69.65, "elapsed_time": "3:09:13", "remaining_time": "1:22:27", "throughput": 687.43, "total_tokens": 7804784} {"current_steps": 27865, "total_steps": 40000, "loss": 0.0, "lr": 1.0522239008186271e-05, "epoch": 309.6111111111111, "percentage": 69.66, "elapsed_time": "3:09:15", "remaining_time": "1:22:25", "throughput": 687.42, "total_tokens": 7806160} {"current_steps": 27870, "total_steps": 40000, "loss": 0.0, "lr": 1.0514236435373434e-05, "epoch": 309.6666666666667, "percentage": 69.67, "elapsed_time": "3:09:17", "remaining_time": "1:22:23", "throughput": 687.42, "total_tokens": 7807536} {"current_steps": 27875, "total_steps": 40000, "loss": 0.0, "lr": 1.0506236096447386e-05, "epoch": 309.72222222222223, "percentage": 69.69, "elapsed_time": "3:09:19", "remaining_time": "1:22:21", "throughput": 687.43, "total_tokens": 7808928} {"current_steps": 27880, "total_steps": 40000, "loss": 0.0, "lr": 1.049823799264186e-05, "epoch": 309.77777777777777, "percentage": 69.7, "elapsed_time": "3:09:21", "remaining_time": "1:22:19", "throughput": 687.43, "total_tokens": 7810352} {"current_steps": 27885, "total_steps": 40000, "loss": 0.0, "lr": 1.049024212519028e-05, "epoch": 309.8333333333333, "percentage": 69.71, "elapsed_time": "3:09:23", "remaining_time": "1:22:17", "throughput": 687.44, "total_tokens": 7811760} {"current_steps": 27890, "total_steps": 40000, "loss": 0.0, "lr": 1.0482248495325713e-05, "epoch": 309.8888888888889, "percentage": 69.73, "elapsed_time": "3:09:25", "remaining_time": "1:22:14", "throughput": 687.45, "total_tokens": 7813184} {"current_steps": 27895, "total_steps": 40000, "loss": 0.0, "lr": 1.047425710428086e-05, "epoch": 309.94444444444446, "percentage": 69.74, "elapsed_time": "3:09:27", "remaining_time": "1:22:12", "throughput": 687.46, "total_tokens": 7814640} {"current_steps": 27900, "total_steps": 40000, "loss": 0.0, "lr": 1.0466267953288114e-05, "epoch": 310.0, "percentage": 69.75, "elapsed_time": "3:09:29", "remaining_time": "1:22:10", "throughput": 687.45, "total_tokens": 7816016} {"current_steps": 27905, "total_steps": 40000, "loss": 0.0, "lr": 1.0458281043579482e-05, "epoch": 310.05555555555554, "percentage": 69.76, "elapsed_time": "3:09:31", "remaining_time": "1:22:08", "throughput": 687.44, "total_tokens": 7817392} {"current_steps": 27910, "total_steps": 40000, "loss": 0.0, "lr": 1.0450296376386657e-05, "epoch": 310.1111111111111, "percentage": 69.77, "elapsed_time": "3:09:33", "remaining_time": "1:22:06", "throughput": 687.44, "total_tokens": 7818768} {"current_steps": 27915, "total_steps": 40000, "loss": 0.0, "lr": 1.044231395294098e-05, "epoch": 310.1666666666667, "percentage": 69.79, "elapsed_time": "3:09:35", "remaining_time": "1:22:04", "throughput": 687.45, "total_tokens": 7820208} {"current_steps": 27920, "total_steps": 40000, "loss": 0.0, "lr": 1.0434333774473435e-05, "epoch": 310.22222222222223, "percentage": 69.8, "elapsed_time": "3:09:37", "remaining_time": "1:22:02", "throughput": 687.46, "total_tokens": 7821616} {"current_steps": 27925, "total_steps": 40000, "loss": 0.0, "lr": 1.0426355842214657e-05, "epoch": 310.27777777777777, "percentage": 69.81, "elapsed_time": "3:09:39", "remaining_time": "1:22:00", "throughput": 687.47, "total_tokens": 7823040} {"current_steps": 27930, "total_steps": 40000, "loss": 0.0, "lr": 1.0418380157394963e-05, "epoch": 310.3333333333333, "percentage": 69.83, "elapsed_time": "3:09:41", "remaining_time": "1:21:58", "throughput": 687.48, "total_tokens": 7824464} {"current_steps": 27935, "total_steps": 40000, "loss": 0.0, "lr": 1.0410406721244281e-05, "epoch": 310.3888888888889, "percentage": 69.84, "elapsed_time": "3:09:43", "remaining_time": "1:21:56", "throughput": 687.48, "total_tokens": 7825840} {"current_steps": 27940, "total_steps": 40000, "loss": 0.0, "lr": 1.0402435534992238e-05, "epoch": 310.44444444444446, "percentage": 69.85, "elapsed_time": "3:09:45", "remaining_time": "1:21:54", "throughput": 687.49, "total_tokens": 7827280} {"current_steps": 27945, "total_steps": 40000, "loss": 0.0, "lr": 1.0394466599868071e-05, "epoch": 310.5, "percentage": 69.86, "elapsed_time": "3:09:47", "remaining_time": "1:21:52", "throughput": 687.49, "total_tokens": 7828672} {"current_steps": 27950, "total_steps": 40000, "loss": 0.0, "lr": 1.0386499917100697e-05, "epoch": 310.55555555555554, "percentage": 69.88, "elapsed_time": "3:09:49", "remaining_time": "1:21:50", "throughput": 687.5, "total_tokens": 7830080} {"current_steps": 27955, "total_steps": 40000, "loss": 0.0, "lr": 1.0378535487918692e-05, "epoch": 310.6111111111111, "percentage": 69.89, "elapsed_time": "3:09:51", "remaining_time": "1:21:48", "throughput": 687.5, "total_tokens": 7831440} {"current_steps": 27960, "total_steps": 40000, "loss": 0.0, "lr": 1.037057331355025e-05, "epoch": 310.6666666666667, "percentage": 69.9, "elapsed_time": "3:09:53", "remaining_time": "1:21:46", "throughput": 687.51, "total_tokens": 7832880} {"current_steps": 27965, "total_steps": 40000, "loss": 0.0, "lr": 1.0362613395223247e-05, "epoch": 310.72222222222223, "percentage": 69.91, "elapsed_time": "3:09:55", "remaining_time": "1:21:43", "throughput": 687.51, "total_tokens": 7834240} {"current_steps": 27970, "total_steps": 40000, "loss": 0.0, "lr": 1.0354655734165212e-05, "epoch": 310.77777777777777, "percentage": 69.92, "elapsed_time": "3:09:56", "remaining_time": "1:21:41", "throughput": 687.52, "total_tokens": 7835616} {"current_steps": 27975, "total_steps": 40000, "loss": 0.0, "lr": 1.03467003316033e-05, "epoch": 310.8333333333333, "percentage": 69.94, "elapsed_time": "3:09:58", "remaining_time": "1:21:39", "throughput": 687.53, "total_tokens": 7837056} {"current_steps": 27980, "total_steps": 40000, "loss": 0.0, "lr": 1.033874718876435e-05, "epoch": 310.8888888888889, "percentage": 69.95, "elapsed_time": "3:10:00", "remaining_time": "1:21:37", "throughput": 687.53, "total_tokens": 7838448} {"current_steps": 27985, "total_steps": 40000, "loss": 0.0, "lr": 1.0330796306874818e-05, "epoch": 310.94444444444446, "percentage": 69.96, "elapsed_time": "3:10:02", "remaining_time": "1:21:35", "throughput": 687.54, "total_tokens": 7839856} {"current_steps": 27990, "total_steps": 40000, "loss": 0.0, "lr": 1.032284768716085e-05, "epoch": 311.0, "percentage": 69.97, "elapsed_time": "3:10:04", "remaining_time": "1:21:33", "throughput": 687.54, "total_tokens": 7841264} {"current_steps": 27995, "total_steps": 40000, "loss": 0.0, "lr": 1.0314901330848206e-05, "epoch": 311.05555555555554, "percentage": 69.99, "elapsed_time": "3:10:07", "remaining_time": "1:21:31", "throughput": 687.53, "total_tokens": 7842672} {"current_steps": 28000, "total_steps": 40000, "loss": 0.0, "lr": 1.030695723916233e-05, "epoch": 311.1111111111111, "percentage": 70.0, "elapsed_time": "3:10:08", "remaining_time": "1:21:29", "throughput": 687.54, "total_tokens": 7844080} {"current_steps": 28000, "total_steps": 40000, "eval_loss": 0.315041720867157, "epoch": 311.1111111111111, "percentage": 70.0, "elapsed_time": "3:10:10", "remaining_time": "1:21:30", "throughput": 687.46, "total_tokens": 7844080} {"current_steps": 28005, "total_steps": 40000, "loss": 0.0, "lr": 1.0299015413328289e-05, "epoch": 311.1666666666667, "percentage": 70.01, "elapsed_time": "3:10:13", "remaining_time": "1:21:28", "throughput": 687.38, "total_tokens": 7845488} {"current_steps": 28010, "total_steps": 40000, "loss": 0.0, "lr": 1.0291075854570809e-05, "epoch": 311.22222222222223, "percentage": 70.03, "elapsed_time": "3:10:15", "remaining_time": "1:21:26", "throughput": 687.39, "total_tokens": 7846928} {"current_steps": 28015, "total_steps": 40000, "loss": 0.0, "lr": 1.0283138564114275e-05, "epoch": 311.27777777777777, "percentage": 70.04, "elapsed_time": "3:10:17", "remaining_time": "1:21:24", "throughput": 687.4, "total_tokens": 7848368} {"current_steps": 28020, "total_steps": 40000, "loss": 0.0, "lr": 1.027520354318273e-05, "epoch": 311.3333333333333, "percentage": 70.05, "elapsed_time": "3:10:19", "remaining_time": "1:21:22", "throughput": 687.4, "total_tokens": 7849744} {"current_steps": 28025, "total_steps": 40000, "loss": 0.0, "lr": 1.0267270792999828e-05, "epoch": 311.3888888888889, "percentage": 70.06, "elapsed_time": "3:10:21", "remaining_time": "1:21:20", "throughput": 687.4, "total_tokens": 7851120} {"current_steps": 28030, "total_steps": 40000, "loss": 0.0, "lr": 1.0259340314788919e-05, "epoch": 311.44444444444446, "percentage": 70.08, "elapsed_time": "3:10:23", "remaining_time": "1:21:18", "throughput": 687.41, "total_tokens": 7852560} {"current_steps": 28035, "total_steps": 40000, "loss": 0.0, "lr": 1.0251412109772979e-05, "epoch": 311.5, "percentage": 70.09, "elapsed_time": "3:10:25", "remaining_time": "1:21:16", "throughput": 687.42, "total_tokens": 7854000} {"current_steps": 28040, "total_steps": 40000, "loss": 0.0, "lr": 1.0243486179174627e-05, "epoch": 311.55555555555554, "percentage": 70.1, "elapsed_time": "3:10:27", "remaining_time": "1:21:14", "throughput": 687.43, "total_tokens": 7855408} {"current_steps": 28045, "total_steps": 40000, "loss": 0.0, "lr": 1.0235562524216158e-05, "epoch": 311.6111111111111, "percentage": 70.11, "elapsed_time": "3:10:29", "remaining_time": "1:21:11", "throughput": 687.44, "total_tokens": 7856800} {"current_steps": 28050, "total_steps": 40000, "loss": 0.0, "lr": 1.022764114611948e-05, "epoch": 311.6666666666667, "percentage": 70.12, "elapsed_time": "3:10:31", "remaining_time": "1:21:09", "throughput": 687.44, "total_tokens": 7858192} {"current_steps": 28055, "total_steps": 40000, "loss": 0.0, "lr": 1.0219722046106178e-05, "epoch": 311.72222222222223, "percentage": 70.14, "elapsed_time": "3:10:33", "remaining_time": "1:21:07", "throughput": 687.45, "total_tokens": 7859616} {"current_steps": 28060, "total_steps": 40000, "loss": 0.0, "lr": 1.0211805225397486e-05, "epoch": 311.77777777777777, "percentage": 70.15, "elapsed_time": "3:10:34", "remaining_time": "1:21:05", "throughput": 687.45, "total_tokens": 7861008} {"current_steps": 28065, "total_steps": 40000, "loss": 0.0, "lr": 1.020389068521426e-05, "epoch": 311.8333333333333, "percentage": 70.16, "elapsed_time": "3:10:36", "remaining_time": "1:21:03", "throughput": 687.46, "total_tokens": 7862400} {"current_steps": 28070, "total_steps": 40000, "loss": 0.0, "lr": 1.0195978426777039e-05, "epoch": 311.8888888888889, "percentage": 70.17, "elapsed_time": "3:10:38", "remaining_time": "1:21:01", "throughput": 687.46, "total_tokens": 7863776} {"current_steps": 28075, "total_steps": 40000, "loss": 0.0, "lr": 1.0188068451305982e-05, "epoch": 311.94444444444446, "percentage": 70.19, "elapsed_time": "3:10:40", "remaining_time": "1:20:59", "throughput": 687.47, "total_tokens": 7865152} {"current_steps": 28080, "total_steps": 40000, "loss": 0.0, "lr": 1.0180160760020902e-05, "epoch": 312.0, "percentage": 70.2, "elapsed_time": "3:10:42", "remaining_time": "1:20:57", "throughput": 687.46, "total_tokens": 7866496} {"current_steps": 28085, "total_steps": 40000, "loss": 0.0, "lr": 1.0172255354141278e-05, "epoch": 312.05555555555554, "percentage": 70.21, "elapsed_time": "3:10:45", "remaining_time": "1:20:55", "throughput": 687.45, "total_tokens": 7867888} {"current_steps": 28090, "total_steps": 40000, "loss": 0.0, "lr": 1.0164352234886205e-05, "epoch": 312.1111111111111, "percentage": 70.23, "elapsed_time": "3:10:47", "remaining_time": "1:20:53", "throughput": 687.45, "total_tokens": 7869264} {"current_steps": 28095, "total_steps": 40000, "loss": 0.0, "lr": 1.0156451403474454e-05, "epoch": 312.1666666666667, "percentage": 70.24, "elapsed_time": "3:10:48", "remaining_time": "1:20:51", "throughput": 687.45, "total_tokens": 7870624} {"current_steps": 28100, "total_steps": 40000, "loss": 0.0, "lr": 1.0148552861124443e-05, "epoch": 312.22222222222223, "percentage": 70.25, "elapsed_time": "3:10:50", "remaining_time": "1:20:49", "throughput": 687.46, "total_tokens": 7872016} {"current_steps": 28105, "total_steps": 40000, "loss": 0.0, "lr": 1.0140656609054205e-05, "epoch": 312.27777777777777, "percentage": 70.26, "elapsed_time": "3:10:52", "remaining_time": "1:20:47", "throughput": 687.46, "total_tokens": 7873408} {"current_steps": 28110, "total_steps": 40000, "loss": 0.0, "lr": 1.0132762648481455e-05, "epoch": 312.3333333333333, "percentage": 70.28, "elapsed_time": "3:10:54", "remaining_time": "1:20:45", "throughput": 687.47, "total_tokens": 7874832} {"current_steps": 28115, "total_steps": 40000, "loss": 0.0, "lr": 1.0124870980623543e-05, "epoch": 312.3888888888889, "percentage": 70.29, "elapsed_time": "3:10:56", "remaining_time": "1:20:43", "throughput": 687.48, "total_tokens": 7876240} {"current_steps": 28120, "total_steps": 40000, "loss": 0.0, "lr": 1.0116981606697453e-05, "epoch": 312.44444444444446, "percentage": 70.3, "elapsed_time": "3:10:58", "remaining_time": "1:20:41", "throughput": 687.48, "total_tokens": 7877616} {"current_steps": 28125, "total_steps": 40000, "loss": 0.0, "lr": 1.0109094527919838e-05, "epoch": 312.5, "percentage": 70.31, "elapsed_time": "3:11:00", "remaining_time": "1:20:38", "throughput": 687.48, "total_tokens": 7878992} {"current_steps": 28130, "total_steps": 40000, "loss": 0.0, "lr": 1.010120974550697e-05, "epoch": 312.55555555555554, "percentage": 70.33, "elapsed_time": "3:11:02", "remaining_time": "1:20:36", "throughput": 687.49, "total_tokens": 7880352} {"current_steps": 28135, "total_steps": 40000, "loss": 0.0, "lr": 1.0093327260674795e-05, "epoch": 312.6111111111111, "percentage": 70.34, "elapsed_time": "3:11:04", "remaining_time": "1:20:34", "throughput": 687.49, "total_tokens": 7881744} {"current_steps": 28140, "total_steps": 40000, "loss": 0.0, "lr": 1.0085447074638878e-05, "epoch": 312.6666666666667, "percentage": 70.35, "elapsed_time": "3:11:06", "remaining_time": "1:20:32", "throughput": 687.49, "total_tokens": 7883120} {"current_steps": 28145, "total_steps": 40000, "loss": 0.0, "lr": 1.0077569188614461e-05, "epoch": 312.72222222222223, "percentage": 70.36, "elapsed_time": "3:11:08", "remaining_time": "1:20:30", "throughput": 687.5, "total_tokens": 7884544} {"current_steps": 28150, "total_steps": 40000, "loss": 0.0, "lr": 1.0069693603816393e-05, "epoch": 312.77777777777777, "percentage": 70.38, "elapsed_time": "3:11:10", "remaining_time": "1:20:28", "throughput": 687.51, "total_tokens": 7885984} {"current_steps": 28155, "total_steps": 40000, "loss": 0.0, "lr": 1.0061820321459204e-05, "epoch": 312.8333333333333, "percentage": 70.39, "elapsed_time": "3:11:12", "remaining_time": "1:20:26", "throughput": 687.52, "total_tokens": 7887392} {"current_steps": 28160, "total_steps": 40000, "loss": 0.0, "lr": 1.0053949342757038e-05, "epoch": 312.8888888888889, "percentage": 70.4, "elapsed_time": "3:11:14", "remaining_time": "1:20:24", "throughput": 687.53, "total_tokens": 7888816} {"current_steps": 28165, "total_steps": 40000, "loss": 0.0, "lr": 1.0046080668923717e-05, "epoch": 312.94444444444446, "percentage": 70.41, "elapsed_time": "3:11:16", "remaining_time": "1:20:22", "throughput": 687.54, "total_tokens": 7890272} {"current_steps": 28170, "total_steps": 40000, "loss": 0.0, "lr": 1.003821430117267e-05, "epoch": 313.0, "percentage": 70.43, "elapsed_time": "3:11:18", "remaining_time": "1:20:20", "throughput": 687.53, "total_tokens": 7891648} {"current_steps": 28175, "total_steps": 40000, "loss": 0.0, "lr": 1.0030350240716999e-05, "epoch": 313.05555555555554, "percentage": 70.44, "elapsed_time": "3:11:20", "remaining_time": "1:20:18", "throughput": 687.52, "total_tokens": 7893056} {"current_steps": 28180, "total_steps": 40000, "loss": 0.0, "lr": 1.0022488488769449e-05, "epoch": 313.1111111111111, "percentage": 70.45, "elapsed_time": "3:11:22", "remaining_time": "1:20:16", "throughput": 687.52, "total_tokens": 7894400} {"current_steps": 28185, "total_steps": 40000, "loss": 0.0, "lr": 1.0014629046542387e-05, "epoch": 313.1666666666667, "percentage": 70.46, "elapsed_time": "3:11:24", "remaining_time": "1:20:14", "throughput": 687.53, "total_tokens": 7895824} {"current_steps": 28190, "total_steps": 40000, "loss": 0.0, "lr": 1.0006771915247842e-05, "epoch": 313.22222222222223, "percentage": 70.47, "elapsed_time": "3:11:26", "remaining_time": "1:20:12", "throughput": 687.54, "total_tokens": 7897248} {"current_steps": 28195, "total_steps": 40000, "loss": 0.0, "lr": 9.998917096097495e-06, "epoch": 313.27777777777777, "percentage": 70.49, "elapsed_time": "3:11:28", "remaining_time": "1:20:10", "throughput": 687.54, "total_tokens": 7898624} {"current_steps": 28200, "total_steps": 40000, "loss": 0.0, "lr": 9.991064590302638e-06, "epoch": 313.3333333333333, "percentage": 70.5, "elapsed_time": "3:11:30", "remaining_time": "1:20:07", "throughput": 687.55, "total_tokens": 7900064} {"current_steps": 28200, "total_steps": 40000, "eval_loss": 0.3051114082336426, "epoch": 313.3333333333333, "percentage": 70.5, "elapsed_time": "3:11:31", "remaining_time": "1:20:08", "throughput": 687.47, "total_tokens": 7900064} {"current_steps": 28205, "total_steps": 40000, "loss": 0.0, "lr": 9.983214399074241e-06, "epoch": 313.3888888888889, "percentage": 70.51, "elapsed_time": "3:11:34", "remaining_time": "1:20:06", "throughput": 687.4, "total_tokens": 7901472} {"current_steps": 28210, "total_steps": 40000, "loss": 0.0, "lr": 9.975366523622893e-06, "epoch": 313.44444444444446, "percentage": 70.53, "elapsed_time": "3:11:36", "remaining_time": "1:20:04", "throughput": 687.4, "total_tokens": 7902880} {"current_steps": 28215, "total_steps": 40000, "loss": 0.0, "lr": 9.967520965158841e-06, "epoch": 313.5, "percentage": 70.54, "elapsed_time": "3:11:38", "remaining_time": "1:20:02", "throughput": 687.41, "total_tokens": 7904256} {"current_steps": 28220, "total_steps": 40000, "loss": 0.0, "lr": 9.95967772489197e-06, "epoch": 313.55555555555554, "percentage": 70.55, "elapsed_time": "3:11:40", "remaining_time": "1:20:00", "throughput": 687.41, "total_tokens": 7905680} {"current_steps": 28225, "total_steps": 40000, "loss": 0.0, "lr": 9.951836804031794e-06, "epoch": 313.6111111111111, "percentage": 70.56, "elapsed_time": "3:11:42", "remaining_time": "1:19:58", "throughput": 687.42, "total_tokens": 7907072} {"current_steps": 28230, "total_steps": 40000, "loss": 0.0, "lr": 9.943998203787489e-06, "epoch": 313.6666666666667, "percentage": 70.58, "elapsed_time": "3:11:44", "remaining_time": "1:19:56", "throughput": 687.43, "total_tokens": 7908496} {"current_steps": 28235, "total_steps": 40000, "loss": 0.0, "lr": 9.936161925367874e-06, "epoch": 313.72222222222223, "percentage": 70.59, "elapsed_time": "3:11:46", "remaining_time": "1:19:54", "throughput": 687.43, "total_tokens": 7909904} {"current_steps": 28240, "total_steps": 40000, "loss": 0.0, "lr": 9.928327969981386e-06, "epoch": 313.77777777777777, "percentage": 70.6, "elapsed_time": "3:11:48", "remaining_time": "1:19:52", "throughput": 687.44, "total_tokens": 7911328} {"current_steps": 28245, "total_steps": 40000, "loss": 0.0, "lr": 9.920496338836135e-06, "epoch": 313.8333333333333, "percentage": 70.61, "elapsed_time": "3:11:50", "remaining_time": "1:19:50", "throughput": 687.45, "total_tokens": 7912720} {"current_steps": 28250, "total_steps": 40000, "loss": 0.0, "lr": 9.912667033139844e-06, "epoch": 313.8888888888889, "percentage": 70.62, "elapsed_time": "3:11:52", "remaining_time": "1:19:48", "throughput": 687.45, "total_tokens": 7914064} {"current_steps": 28255, "total_steps": 40000, "loss": 0.0, "lr": 9.904840054099893e-06, "epoch": 313.94444444444446, "percentage": 70.64, "elapsed_time": "3:11:54", "remaining_time": "1:19:46", "throughput": 687.45, "total_tokens": 7915456} {"current_steps": 28260, "total_steps": 40000, "loss": 0.0, "lr": 9.897015402923312e-06, "epoch": 314.0, "percentage": 70.65, "elapsed_time": "3:11:56", "remaining_time": "1:19:44", "throughput": 687.44, "total_tokens": 7916784} {"current_steps": 28265, "total_steps": 40000, "loss": 0.0, "lr": 9.889193080816744e-06, "epoch": 314.05555555555554, "percentage": 70.66, "elapsed_time": "3:11:58", "remaining_time": "1:19:42", "throughput": 687.43, "total_tokens": 7918176} {"current_steps": 28270, "total_steps": 40000, "loss": 0.0, "lr": 9.881373088986498e-06, "epoch": 314.1111111111111, "percentage": 70.67, "elapsed_time": "3:12:00", "remaining_time": "1:19:40", "throughput": 687.44, "total_tokens": 7919584} {"current_steps": 28275, "total_steps": 40000, "loss": 0.0, "lr": 9.873555428638523e-06, "epoch": 314.1666666666667, "percentage": 70.69, "elapsed_time": "3:12:02", "remaining_time": "1:19:38", "throughput": 687.44, "total_tokens": 7920960} {"current_steps": 28280, "total_steps": 40000, "loss": 0.0, "lr": 9.865740100978383e-06, "epoch": 314.22222222222223, "percentage": 70.7, "elapsed_time": "3:12:04", "remaining_time": "1:19:35", "throughput": 687.45, "total_tokens": 7922384} {"current_steps": 28285, "total_steps": 40000, "loss": 0.0, "lr": 9.857927107211315e-06, "epoch": 314.27777777777777, "percentage": 70.71, "elapsed_time": "3:12:06", "remaining_time": "1:19:33", "throughput": 687.45, "total_tokens": 7923744} {"current_steps": 28290, "total_steps": 40000, "loss": 0.0, "lr": 9.850116448542177e-06, "epoch": 314.3333333333333, "percentage": 70.73, "elapsed_time": "3:12:08", "remaining_time": "1:19:31", "throughput": 687.45, "total_tokens": 7925104} {"current_steps": 28295, "total_steps": 40000, "loss": 0.0, "lr": 9.842308126175457e-06, "epoch": 314.3888888888889, "percentage": 70.74, "elapsed_time": "3:12:10", "remaining_time": "1:19:29", "throughput": 687.46, "total_tokens": 7926496} {"current_steps": 28300, "total_steps": 40000, "loss": 0.0, "lr": 9.834502141315315e-06, "epoch": 314.44444444444446, "percentage": 70.75, "elapsed_time": "3:12:12", "remaining_time": "1:19:27", "throughput": 687.47, "total_tokens": 7927904} {"current_steps": 28305, "total_steps": 40000, "loss": 0.0, "lr": 9.82669849516552e-06, "epoch": 314.5, "percentage": 70.76, "elapsed_time": "3:12:13", "remaining_time": "1:19:25", "throughput": 687.47, "total_tokens": 7929328} {"current_steps": 28310, "total_steps": 40000, "loss": 0.0, "lr": 9.818897188929493e-06, "epoch": 314.55555555555554, "percentage": 70.78, "elapsed_time": "3:12:15", "remaining_time": "1:19:23", "throughput": 687.48, "total_tokens": 7930736} {"current_steps": 28315, "total_steps": 40000, "loss": 0.0, "lr": 9.811098223810309e-06, "epoch": 314.6111111111111, "percentage": 70.79, "elapsed_time": "3:12:17", "remaining_time": "1:19:21", "throughput": 687.48, "total_tokens": 7932112} {"current_steps": 28320, "total_steps": 40000, "loss": 0.0, "lr": 9.803301601010641e-06, "epoch": 314.6666666666667, "percentage": 70.8, "elapsed_time": "3:12:19", "remaining_time": "1:19:19", "throughput": 687.49, "total_tokens": 7933536} {"current_steps": 28325, "total_steps": 40000, "loss": 0.0, "lr": 9.795507321732853e-06, "epoch": 314.72222222222223, "percentage": 70.81, "elapsed_time": "3:12:21", "remaining_time": "1:19:17", "throughput": 687.5, "total_tokens": 7934928} {"current_steps": 28330, "total_steps": 40000, "loss": 0.0, "lr": 9.787715387178898e-06, "epoch": 314.77777777777777, "percentage": 70.83, "elapsed_time": "3:12:23", "remaining_time": "1:19:15", "throughput": 687.51, "total_tokens": 7936400} {"current_steps": 28335, "total_steps": 40000, "loss": 0.0, "lr": 9.779925798550399e-06, "epoch": 314.8333333333333, "percentage": 70.84, "elapsed_time": "3:12:25", "remaining_time": "1:19:13", "throughput": 687.51, "total_tokens": 7937792} {"current_steps": 28340, "total_steps": 40000, "loss": 0.0, "lr": 9.772138557048619e-06, "epoch": 314.8888888888889, "percentage": 70.85, "elapsed_time": "3:12:27", "remaining_time": "1:19:11", "throughput": 687.52, "total_tokens": 7939184} {"current_steps": 28345, "total_steps": 40000, "loss": 0.0, "lr": 9.764353663874426e-06, "epoch": 314.94444444444446, "percentage": 70.86, "elapsed_time": "3:12:29", "remaining_time": "1:19:08", "throughput": 687.53, "total_tokens": 7940624} {"current_steps": 28350, "total_steps": 40000, "loss": 0.0, "lr": 9.756571120228375e-06, "epoch": 315.0, "percentage": 70.88, "elapsed_time": "3:12:31", "remaining_time": "1:19:06", "throughput": 687.52, "total_tokens": 7942016} {"current_steps": 28355, "total_steps": 40000, "loss": 0.0, "lr": 9.748790927310605e-06, "epoch": 315.05555555555554, "percentage": 70.89, "elapsed_time": "3:12:33", "remaining_time": "1:19:04", "throughput": 687.51, "total_tokens": 7943392} {"current_steps": 28360, "total_steps": 40000, "loss": 0.0, "lr": 9.741013086320946e-06, "epoch": 315.1111111111111, "percentage": 70.9, "elapsed_time": "3:12:35", "remaining_time": "1:19:02", "throughput": 687.52, "total_tokens": 7944784} {"current_steps": 28365, "total_steps": 40000, "loss": 0.0, "lr": 9.733237598458821e-06, "epoch": 315.1666666666667, "percentage": 70.91, "elapsed_time": "3:12:37", "remaining_time": "1:19:00", "throughput": 687.52, "total_tokens": 7946176} {"current_steps": 28370, "total_steps": 40000, "loss": 0.0, "lr": 9.725464464923308e-06, "epoch": 315.22222222222223, "percentage": 70.93, "elapsed_time": "3:12:39", "remaining_time": "1:18:58", "throughput": 687.53, "total_tokens": 7947568} {"current_steps": 28375, "total_steps": 40000, "loss": 0.0, "lr": 9.717693686913123e-06, "epoch": 315.27777777777777, "percentage": 70.94, "elapsed_time": "3:12:41", "remaining_time": "1:18:56", "throughput": 687.53, "total_tokens": 7948976} {"current_steps": 28380, "total_steps": 40000, "loss": 0.0, "lr": 9.709925265626632e-06, "epoch": 315.3333333333333, "percentage": 70.95, "elapsed_time": "3:12:43", "remaining_time": "1:18:54", "throughput": 687.54, "total_tokens": 7950320} {"current_steps": 28385, "total_steps": 40000, "loss": 0.0, "lr": 9.702159202261801e-06, "epoch": 315.3888888888889, "percentage": 70.96, "elapsed_time": "3:12:45", "remaining_time": "1:18:52", "throughput": 687.54, "total_tokens": 7951728} {"current_steps": 28390, "total_steps": 40000, "loss": 0.0, "lr": 9.694395498016268e-06, "epoch": 315.44444444444446, "percentage": 70.97, "elapsed_time": "3:12:47", "remaining_time": "1:18:50", "throughput": 687.55, "total_tokens": 7953152} {"current_steps": 28395, "total_steps": 40000, "loss": 0.0, "lr": 9.686634154087298e-06, "epoch": 315.5, "percentage": 70.99, "elapsed_time": "3:12:49", "remaining_time": "1:18:48", "throughput": 687.56, "total_tokens": 7954624} {"current_steps": 28400, "total_steps": 40000, "loss": 0.0, "lr": 9.678875171671776e-06, "epoch": 315.55555555555554, "percentage": 71.0, "elapsed_time": "3:12:51", "remaining_time": "1:18:46", "throughput": 687.57, "total_tokens": 7956016} {"current_steps": 28400, "total_steps": 40000, "eval_loss": 0.3159722685813904, "epoch": 315.55555555555554, "percentage": 71.0, "elapsed_time": "3:12:52", "remaining_time": "1:18:46", "throughput": 687.49, "total_tokens": 7956016} {"current_steps": 28405, "total_steps": 40000, "loss": 0.0, "lr": 9.671118551966246e-06, "epoch": 315.6111111111111, "percentage": 71.01, "elapsed_time": "3:12:55", "remaining_time": "1:18:45", "throughput": 687.42, "total_tokens": 7957440} {"current_steps": 28410, "total_steps": 40000, "loss": 0.0, "lr": 9.66336429616686e-06, "epoch": 315.6666666666667, "percentage": 71.03, "elapsed_time": "3:12:57", "remaining_time": "1:18:43", "throughput": 687.42, "total_tokens": 7958864} {"current_steps": 28415, "total_steps": 40000, "loss": 0.0, "lr": 9.655612405469436e-06, "epoch": 315.72222222222223, "percentage": 71.04, "elapsed_time": "3:12:59", "remaining_time": "1:18:41", "throughput": 687.43, "total_tokens": 7960272} {"current_steps": 28420, "total_steps": 40000, "loss": 0.0, "lr": 9.647862881069413e-06, "epoch": 315.77777777777777, "percentage": 71.05, "elapsed_time": "3:13:01", "remaining_time": "1:18:39", "throughput": 687.44, "total_tokens": 7961680} {"current_steps": 28425, "total_steps": 40000, "loss": 0.0, "lr": 9.640115724161855e-06, "epoch": 315.8333333333333, "percentage": 71.06, "elapsed_time": "3:13:03", "remaining_time": "1:18:37", "throughput": 687.44, "total_tokens": 7963088} {"current_steps": 28430, "total_steps": 40000, "loss": 0.0, "lr": 9.632370935941483e-06, "epoch": 315.8888888888889, "percentage": 71.08, "elapsed_time": "3:13:05", "remaining_time": "1:18:34", "throughput": 687.45, "total_tokens": 7964464} {"current_steps": 28435, "total_steps": 40000, "loss": 0.0, "lr": 9.624628517602634e-06, "epoch": 315.94444444444446, "percentage": 71.09, "elapsed_time": "3:13:07", "remaining_time": "1:18:32", "throughput": 687.45, "total_tokens": 7965872} {"current_steps": 28440, "total_steps": 40000, "loss": 0.0, "lr": 9.61688847033928e-06, "epoch": 316.0, "percentage": 71.1, "elapsed_time": "3:13:09", "remaining_time": "1:18:30", "throughput": 687.45, "total_tokens": 7967264} {"current_steps": 28445, "total_steps": 40000, "loss": 0.0, "lr": 9.609150795345051e-06, "epoch": 316.05555555555554, "percentage": 71.11, "elapsed_time": "3:13:11", "remaining_time": "1:18:28", "throughput": 687.44, "total_tokens": 7968720} {"current_steps": 28450, "total_steps": 40000, "loss": 0.0, "lr": 9.601415493813171e-06, "epoch": 316.1111111111111, "percentage": 71.12, "elapsed_time": "3:13:13", "remaining_time": "1:18:26", "throughput": 687.45, "total_tokens": 7970112} {"current_steps": 28455, "total_steps": 40000, "loss": 0.0, "lr": 9.593682566936533e-06, "epoch": 316.1666666666667, "percentage": 71.14, "elapsed_time": "3:13:15", "remaining_time": "1:18:24", "throughput": 687.45, "total_tokens": 7971520} {"current_steps": 28460, "total_steps": 40000, "loss": 0.0, "lr": 9.58595201590766e-06, "epoch": 316.22222222222223, "percentage": 71.15, "elapsed_time": "3:13:17", "remaining_time": "1:18:22", "throughput": 687.46, "total_tokens": 7972896} {"current_steps": 28465, "total_steps": 40000, "loss": 0.0, "lr": 9.578223841918681e-06, "epoch": 316.27777777777777, "percentage": 71.16, "elapsed_time": "3:13:19", "remaining_time": "1:18:20", "throughput": 687.47, "total_tokens": 7974320} {"current_steps": 28470, "total_steps": 40000, "loss": 0.0, "lr": 9.570498046161389e-06, "epoch": 316.3333333333333, "percentage": 71.17, "elapsed_time": "3:13:21", "remaining_time": "1:18:18", "throughput": 687.47, "total_tokens": 7975760} {"current_steps": 28475, "total_steps": 40000, "loss": 0.0, "lr": 9.562774629827206e-06, "epoch": 316.3888888888889, "percentage": 71.19, "elapsed_time": "3:13:23", "remaining_time": "1:18:16", "throughput": 687.48, "total_tokens": 7977184} {"current_steps": 28480, "total_steps": 40000, "loss": 0.0, "lr": 9.555053594107163e-06, "epoch": 316.44444444444446, "percentage": 71.2, "elapsed_time": "3:13:25", "remaining_time": "1:18:14", "throughput": 687.49, "total_tokens": 7978576} {"current_steps": 28485, "total_steps": 40000, "loss": 0.0, "lr": 9.547334940191957e-06, "epoch": 316.5, "percentage": 71.21, "elapsed_time": "3:13:27", "remaining_time": "1:18:12", "throughput": 687.49, "total_tokens": 7979952} {"current_steps": 28490, "total_steps": 40000, "loss": 0.0, "lr": 9.539618669271886e-06, "epoch": 316.55555555555554, "percentage": 71.23, "elapsed_time": "3:13:29", "remaining_time": "1:18:10", "throughput": 687.5, "total_tokens": 7981376} {"current_steps": 28495, "total_steps": 40000, "loss": 0.0, "lr": 9.531904782536904e-06, "epoch": 316.6111111111111, "percentage": 71.24, "elapsed_time": "3:13:31", "remaining_time": "1:18:08", "throughput": 687.5, "total_tokens": 7982720} {"current_steps": 28500, "total_steps": 40000, "loss": 0.0, "lr": 9.524193281176597e-06, "epoch": 316.6666666666667, "percentage": 71.25, "elapsed_time": "3:13:33", "remaining_time": "1:18:06", "throughput": 687.5, "total_tokens": 7984096} {"current_steps": 28505, "total_steps": 40000, "loss": 0.0, "lr": 9.516484166380165e-06, "epoch": 316.72222222222223, "percentage": 71.26, "elapsed_time": "3:13:35", "remaining_time": "1:18:03", "throughput": 687.51, "total_tokens": 7985472} {"current_steps": 28510, "total_steps": 40000, "loss": 0.0, "lr": 9.508777439336447e-06, "epoch": 316.77777777777777, "percentage": 71.28, "elapsed_time": "3:13:37", "remaining_time": "1:18:01", "throughput": 687.51, "total_tokens": 7986832} {"current_steps": 28515, "total_steps": 40000, "loss": 0.0, "lr": 9.50107310123393e-06, "epoch": 316.8333333333333, "percentage": 71.29, "elapsed_time": "3:13:38", "remaining_time": "1:17:59", "throughput": 687.51, "total_tokens": 7988224} {"current_steps": 28520, "total_steps": 40000, "loss": 0.0, "lr": 9.493371153260702e-06, "epoch": 316.8888888888889, "percentage": 71.3, "elapsed_time": "3:13:40", "remaining_time": "1:17:57", "throughput": 687.53, "total_tokens": 7989680} {"current_steps": 28525, "total_steps": 40000, "loss": 0.0, "lr": 9.485671596604523e-06, "epoch": 316.94444444444446, "percentage": 71.31, "elapsed_time": "3:13:42", "remaining_time": "1:17:55", "throughput": 687.53, "total_tokens": 7991056} {"current_steps": 28530, "total_steps": 40000, "loss": 0.0, "lr": 9.477974432452738e-06, "epoch": 317.0, "percentage": 71.33, "elapsed_time": "3:13:44", "remaining_time": "1:17:53", "throughput": 687.53, "total_tokens": 7992464} {"current_steps": 28535, "total_steps": 40000, "loss": 0.0, "lr": 9.470279661992356e-06, "epoch": 317.05555555555554, "percentage": 71.34, "elapsed_time": "3:13:47", "remaining_time": "1:17:51", "throughput": 687.52, "total_tokens": 7993856} {"current_steps": 28540, "total_steps": 40000, "loss": 0.0, "lr": 9.462587286410021e-06, "epoch": 317.1111111111111, "percentage": 71.35, "elapsed_time": "3:13:49", "remaining_time": "1:17:49", "throughput": 687.52, "total_tokens": 7995264} {"current_steps": 28545, "total_steps": 40000, "loss": 0.0, "lr": 9.454897306891972e-06, "epoch": 317.1666666666667, "percentage": 71.36, "elapsed_time": "3:13:51", "remaining_time": "1:17:47", "throughput": 687.52, "total_tokens": 7996624} {"current_steps": 28550, "total_steps": 40000, "loss": 0.0, "lr": 9.44720972462411e-06, "epoch": 317.22222222222223, "percentage": 71.38, "elapsed_time": "3:13:52", "remaining_time": "1:17:45", "throughput": 687.54, "total_tokens": 7998096} {"current_steps": 28555, "total_steps": 40000, "loss": 0.0, "lr": 9.439524540791964e-06, "epoch": 317.27777777777777, "percentage": 71.39, "elapsed_time": "3:13:54", "remaining_time": "1:17:43", "throughput": 687.54, "total_tokens": 7999472} {"current_steps": 28560, "total_steps": 40000, "loss": 0.0, "lr": 9.431841756580673e-06, "epoch": 317.3333333333333, "percentage": 71.4, "elapsed_time": "3:13:56", "remaining_time": "1:17:41", "throughput": 687.54, "total_tokens": 8000864} {"current_steps": 28565, "total_steps": 40000, "loss": 0.0, "lr": 9.42416137317503e-06, "epoch": 317.3888888888889, "percentage": 71.41, "elapsed_time": "3:13:58", "remaining_time": "1:17:39", "throughput": 687.55, "total_tokens": 8002272} {"current_steps": 28570, "total_steps": 40000, "loss": 0.0, "lr": 9.416483391759437e-06, "epoch": 317.44444444444446, "percentage": 71.43, "elapsed_time": "3:14:00", "remaining_time": "1:17:37", "throughput": 687.55, "total_tokens": 8003632} {"current_steps": 28575, "total_steps": 40000, "loss": 0.0, "lr": 9.408807813517945e-06, "epoch": 317.5, "percentage": 71.44, "elapsed_time": "3:14:02", "remaining_time": "1:17:35", "throughput": 687.56, "total_tokens": 8005008} {"current_steps": 28580, "total_steps": 40000, "loss": 0.0, "lr": 9.401134639634221e-06, "epoch": 317.55555555555554, "percentage": 71.45, "elapsed_time": "3:14:04", "remaining_time": "1:17:32", "throughput": 687.56, "total_tokens": 8006432} {"current_steps": 28585, "total_steps": 40000, "loss": 0.0, "lr": 9.393463871291555e-06, "epoch": 317.6111111111111, "percentage": 71.46, "elapsed_time": "3:14:06", "remaining_time": "1:17:30", "throughput": 687.57, "total_tokens": 8007840} {"current_steps": 28590, "total_steps": 40000, "loss": 0.0, "lr": 9.385795509672881e-06, "epoch": 317.6666666666667, "percentage": 71.47, "elapsed_time": "3:14:08", "remaining_time": "1:17:28", "throughput": 687.58, "total_tokens": 8009264} {"current_steps": 28595, "total_steps": 40000, "loss": 0.0, "lr": 9.378129555960771e-06, "epoch": 317.72222222222223, "percentage": 71.49, "elapsed_time": "3:14:10", "remaining_time": "1:17:26", "throughput": 687.59, "total_tokens": 8010720} {"current_steps": 28600, "total_steps": 40000, "loss": 0.0, "lr": 9.370466011337392e-06, "epoch": 317.77777777777777, "percentage": 71.5, "elapsed_time": "3:14:12", "remaining_time": "1:17:24", "throughput": 687.6, "total_tokens": 8012160} {"current_steps": 28600, "total_steps": 40000, "eval_loss": 0.3321463465690613, "epoch": 317.77777777777777, "percentage": 71.5, "elapsed_time": "3:14:13", "remaining_time": "1:17:25", "throughput": 687.52, "total_tokens": 8012160} {"current_steps": 28605, "total_steps": 40000, "loss": 0.0, "lr": 9.362804876984573e-06, "epoch": 317.8333333333333, "percentage": 71.51, "elapsed_time": "3:14:17", "remaining_time": "1:17:23", "throughput": 687.43, "total_tokens": 8013584} {"current_steps": 28610, "total_steps": 40000, "loss": 0.0, "lr": 9.355146154083747e-06, "epoch": 317.8888888888889, "percentage": 71.53, "elapsed_time": "3:14:19", "remaining_time": "1:17:21", "throughput": 687.43, "total_tokens": 8014992} {"current_steps": 28615, "total_steps": 40000, "loss": 0.0, "lr": 9.347489843815987e-06, "epoch": 317.94444444444446, "percentage": 71.54, "elapsed_time": "3:14:21", "remaining_time": "1:17:19", "throughput": 687.43, "total_tokens": 8016384} {"current_steps": 28620, "total_steps": 40000, "loss": 0.0, "lr": 9.339835947362002e-06, "epoch": 318.0, "percentage": 71.55, "elapsed_time": "3:14:23", "remaining_time": "1:17:17", "throughput": 687.43, "total_tokens": 8017776} {"current_steps": 28625, "total_steps": 40000, "loss": 0.0, "lr": 9.332184465902105e-06, "epoch": 318.05555555555554, "percentage": 71.56, "elapsed_time": "3:14:25", "remaining_time": "1:17:15", "throughput": 687.42, "total_tokens": 8019168} {"current_steps": 28630, "total_steps": 40000, "loss": 0.0, "lr": 9.324535400616266e-06, "epoch": 318.1111111111111, "percentage": 71.58, "elapsed_time": "3:14:27", "remaining_time": "1:17:13", "throughput": 687.43, "total_tokens": 8020592} {"current_steps": 28635, "total_steps": 40000, "loss": 0.0, "lr": 9.31688875268405e-06, "epoch": 318.1666666666667, "percentage": 71.59, "elapsed_time": "3:14:29", "remaining_time": "1:17:11", "throughput": 687.43, "total_tokens": 8021984} {"current_steps": 28640, "total_steps": 40000, "loss": 0.0, "lr": 9.309244523284674e-06, "epoch": 318.22222222222223, "percentage": 71.6, "elapsed_time": "3:14:31", "remaining_time": "1:17:09", "throughput": 687.44, "total_tokens": 8023376} {"current_steps": 28645, "total_steps": 40000, "loss": 0.0, "lr": 9.301602713596982e-06, "epoch": 318.27777777777777, "percentage": 71.61, "elapsed_time": "3:14:33", "remaining_time": "1:17:07", "throughput": 687.45, "total_tokens": 8024816} {"current_steps": 28650, "total_steps": 40000, "loss": 0.0, "lr": 9.293963324799432e-06, "epoch": 318.3333333333333, "percentage": 71.62, "elapsed_time": "3:14:35", "remaining_time": "1:17:05", "throughput": 687.45, "total_tokens": 8026160} {"current_steps": 28655, "total_steps": 40000, "loss": 0.0, "lr": 9.286326358070104e-06, "epoch": 318.3888888888889, "percentage": 71.64, "elapsed_time": "3:14:37", "remaining_time": "1:17:03", "throughput": 687.46, "total_tokens": 8027600} {"current_steps": 28660, "total_steps": 40000, "loss": 0.0, "lr": 9.278691814586729e-06, "epoch": 318.44444444444446, "percentage": 71.65, "elapsed_time": "3:14:39", "remaining_time": "1:17:01", "throughput": 687.46, "total_tokens": 8029024} {"current_steps": 28665, "total_steps": 40000, "loss": 0.0, "lr": 9.271059695526635e-06, "epoch": 318.5, "percentage": 71.66, "elapsed_time": "3:14:41", "remaining_time": "1:16:59", "throughput": 687.47, "total_tokens": 8030448} {"current_steps": 28670, "total_steps": 40000, "loss": 0.0, "lr": 9.263430002066805e-06, "epoch": 318.55555555555554, "percentage": 71.67, "elapsed_time": "3:14:43", "remaining_time": "1:16:57", "throughput": 687.47, "total_tokens": 8031792} {"current_steps": 28675, "total_steps": 40000, "loss": 0.0, "lr": 9.25580273538382e-06, "epoch": 318.6111111111111, "percentage": 71.69, "elapsed_time": "3:14:45", "remaining_time": "1:16:54", "throughput": 687.48, "total_tokens": 8033200} {"current_steps": 28680, "total_steps": 40000, "loss": 0.0, "lr": 9.248177896653907e-06, "epoch": 318.6666666666667, "percentage": 71.7, "elapsed_time": "3:14:46", "remaining_time": "1:16:52", "throughput": 687.48, "total_tokens": 8034624} {"current_steps": 28685, "total_steps": 40000, "loss": 0.0, "lr": 9.240555487052918e-06, "epoch": 318.72222222222223, "percentage": 71.71, "elapsed_time": "3:14:48", "remaining_time": "1:16:50", "throughput": 687.49, "total_tokens": 8036048} {"current_steps": 28690, "total_steps": 40000, "loss": 0.0, "lr": 9.232935507756313e-06, "epoch": 318.77777777777777, "percentage": 71.73, "elapsed_time": "3:14:50", "remaining_time": "1:16:48", "throughput": 687.49, "total_tokens": 8037392} {"current_steps": 28695, "total_steps": 40000, "loss": 0.0, "lr": 9.225317959939193e-06, "epoch": 318.8333333333333, "percentage": 71.74, "elapsed_time": "3:14:52", "remaining_time": "1:16:46", "throughput": 687.5, "total_tokens": 8038816} {"current_steps": 28700, "total_steps": 40000, "loss": 0.0, "lr": 9.217702844776287e-06, "epoch": 318.8888888888889, "percentage": 71.75, "elapsed_time": "3:14:54", "remaining_time": "1:16:44", "throughput": 687.51, "total_tokens": 8040240} {"current_steps": 28705, "total_steps": 40000, "loss": 0.0, "lr": 9.210090163441929e-06, "epoch": 318.94444444444446, "percentage": 71.76, "elapsed_time": "3:14:56", "remaining_time": "1:16:42", "throughput": 687.51, "total_tokens": 8041568} {"current_steps": 28710, "total_steps": 40000, "loss": 0.0, "lr": 9.202479917110105e-06, "epoch": 319.0, "percentage": 71.78, "elapsed_time": "3:14:58", "remaining_time": "1:16:40", "throughput": 687.5, "total_tokens": 8042944} {"current_steps": 28715, "total_steps": 40000, "loss": 0.0, "lr": 9.194872106954392e-06, "epoch": 319.05555555555554, "percentage": 71.79, "elapsed_time": "3:15:01", "remaining_time": "1:16:38", "throughput": 687.49, "total_tokens": 8044320} {"current_steps": 28720, "total_steps": 40000, "loss": 0.0, "lr": 9.187266734148029e-06, "epoch": 319.1111111111111, "percentage": 71.8, "elapsed_time": "3:15:02", "remaining_time": "1:16:36", "throughput": 687.49, "total_tokens": 8045712} {"current_steps": 28725, "total_steps": 40000, "loss": 0.0, "lr": 9.179663799863849e-06, "epoch": 319.1666666666667, "percentage": 71.81, "elapsed_time": "3:15:04", "remaining_time": "1:16:34", "throughput": 687.5, "total_tokens": 8047104} {"current_steps": 28730, "total_steps": 40000, "loss": 0.0, "lr": 9.172063305274317e-06, "epoch": 319.22222222222223, "percentage": 71.83, "elapsed_time": "3:15:06", "remaining_time": "1:16:32", "throughput": 687.51, "total_tokens": 8048496} {"current_steps": 28735, "total_steps": 40000, "loss": 0.0, "lr": 9.164465251551527e-06, "epoch": 319.27777777777777, "percentage": 71.84, "elapsed_time": "3:15:08", "remaining_time": "1:16:30", "throughput": 687.51, "total_tokens": 8049872} {"current_steps": 28740, "total_steps": 40000, "loss": 0.0, "lr": 9.156869639867205e-06, "epoch": 319.3333333333333, "percentage": 71.85, "elapsed_time": "3:15:10", "remaining_time": "1:16:28", "throughput": 687.52, "total_tokens": 8051296} {"current_steps": 28745, "total_steps": 40000, "loss": 0.0, "lr": 9.149276471392677e-06, "epoch": 319.3888888888889, "percentage": 71.86, "elapsed_time": "3:15:12", "remaining_time": "1:16:26", "throughput": 687.53, "total_tokens": 8052720} {"current_steps": 28750, "total_steps": 40000, "loss": 0.0, "lr": 9.141685747298914e-06, "epoch": 319.44444444444446, "percentage": 71.88, "elapsed_time": "3:15:14", "remaining_time": "1:16:23", "throughput": 687.53, "total_tokens": 8054160} {"current_steps": 28755, "total_steps": 40000, "loss": 0.0, "lr": 9.13409746875649e-06, "epoch": 319.5, "percentage": 71.89, "elapsed_time": "3:15:16", "remaining_time": "1:16:21", "throughput": 687.54, "total_tokens": 8055552} {"current_steps": 28760, "total_steps": 40000, "loss": 0.0, "lr": 9.12651163693562e-06, "epoch": 319.55555555555554, "percentage": 71.9, "elapsed_time": "3:15:18", "remaining_time": "1:16:19", "throughput": 687.55, "total_tokens": 8057008} {"current_steps": 28765, "total_steps": 40000, "loss": 0.0, "lr": 9.11892825300614e-06, "epoch": 319.6111111111111, "percentage": 71.91, "elapsed_time": "3:15:20", "remaining_time": "1:16:17", "throughput": 687.56, "total_tokens": 8058448} {"current_steps": 28770, "total_steps": 40000, "loss": 0.0, "lr": 9.111347318137491e-06, "epoch": 319.6666666666667, "percentage": 71.92, "elapsed_time": "3:15:22", "remaining_time": "1:16:15", "throughput": 687.56, "total_tokens": 8059840} {"current_steps": 28775, "total_steps": 40000, "loss": 0.0, "lr": 9.103768833498755e-06, "epoch": 319.72222222222223, "percentage": 71.94, "elapsed_time": "3:15:24", "remaining_time": "1:16:13", "throughput": 687.57, "total_tokens": 8061248} {"current_steps": 28780, "total_steps": 40000, "loss": 0.0, "lr": 9.096192800258639e-06, "epoch": 319.77777777777777, "percentage": 71.95, "elapsed_time": "3:15:26", "remaining_time": "1:16:11", "throughput": 687.57, "total_tokens": 8062608} {"current_steps": 28785, "total_steps": 40000, "loss": 0.0, "lr": 9.088619219585443e-06, "epoch": 319.8333333333333, "percentage": 71.96, "elapsed_time": "3:15:28", "remaining_time": "1:16:09", "throughput": 687.58, "total_tokens": 8064032} {"current_steps": 28790, "total_steps": 40000, "loss": 0.0, "lr": 9.081048092647127e-06, "epoch": 319.8888888888889, "percentage": 71.97, "elapsed_time": "3:15:30", "remaining_time": "1:16:07", "throughput": 687.59, "total_tokens": 8065440} {"current_steps": 28795, "total_steps": 40000, "loss": 0.0, "lr": 9.073479420611245e-06, "epoch": 319.94444444444446, "percentage": 71.99, "elapsed_time": "3:15:32", "remaining_time": "1:16:05", "throughput": 687.59, "total_tokens": 8066864} {"current_steps": 28800, "total_steps": 40000, "loss": 0.0, "lr": 9.065913204644974e-06, "epoch": 320.0, "percentage": 72.0, "elapsed_time": "3:15:34", "remaining_time": "1:16:03", "throughput": 687.59, "total_tokens": 8068256} {"current_steps": 28800, "total_steps": 40000, "eval_loss": 0.355111300945282, "epoch": 320.0, "percentage": 72.0, "elapsed_time": "3:15:35", "remaining_time": "1:16:03", "throughput": 687.51, "total_tokens": 8068256} {"current_steps": 28805, "total_steps": 40000, "loss": 0.0, "lr": 9.058349445915135e-06, "epoch": 320.05555555555554, "percentage": 72.01, "elapsed_time": "3:15:39", "remaining_time": "1:16:02", "throughput": 687.39, "total_tokens": 8069664} {"current_steps": 28810, "total_steps": 40000, "loss": 0.0, "lr": 9.050788145588138e-06, "epoch": 320.1111111111111, "percentage": 72.02, "elapsed_time": "3:15:41", "remaining_time": "1:16:00", "throughput": 687.39, "total_tokens": 8071072} {"current_steps": 28815, "total_steps": 40000, "loss": 0.0, "lr": 9.043229304830039e-06, "epoch": 320.1666666666667, "percentage": 72.04, "elapsed_time": "3:15:43", "remaining_time": "1:15:58", "throughput": 687.4, "total_tokens": 8072528} {"current_steps": 28820, "total_steps": 40000, "loss": 0.0, "lr": 9.035672924806515e-06, "epoch": 320.22222222222223, "percentage": 72.05, "elapsed_time": "3:15:45", "remaining_time": "1:15:56", "throughput": 687.4, "total_tokens": 8073904} {"current_steps": 28825, "total_steps": 40000, "loss": 0.0, "lr": 9.028119006682839e-06, "epoch": 320.27777777777777, "percentage": 72.06, "elapsed_time": "3:15:47", "remaining_time": "1:15:54", "throughput": 687.41, "total_tokens": 8075296} {"current_steps": 28830, "total_steps": 40000, "loss": 0.0, "lr": 9.020567551623935e-06, "epoch": 320.3333333333333, "percentage": 72.08, "elapsed_time": "3:15:49", "remaining_time": "1:15:52", "throughput": 687.41, "total_tokens": 8076640} {"current_steps": 28835, "total_steps": 40000, "loss": 0.0, "lr": 9.013018560794318e-06, "epoch": 320.3888888888889, "percentage": 72.09, "elapsed_time": "3:15:51", "remaining_time": "1:15:50", "throughput": 687.39, "total_tokens": 8078000} {"current_steps": 28840, "total_steps": 40000, "loss": 0.0, "lr": 9.005472035358139e-06, "epoch": 320.44444444444446, "percentage": 72.1, "elapsed_time": "3:15:53", "remaining_time": "1:15:48", "throughput": 687.4, "total_tokens": 8079408} {"current_steps": 28845, "total_steps": 40000, "loss": 0.0, "lr": 8.997927976479185e-06, "epoch": 320.5, "percentage": 72.11, "elapsed_time": "3:15:55", "remaining_time": "1:15:46", "throughput": 687.4, "total_tokens": 8080784} {"current_steps": 28850, "total_steps": 40000, "loss": 0.0, "lr": 8.99038638532082e-06, "epoch": 320.55555555555554, "percentage": 72.12, "elapsed_time": "3:15:57", "remaining_time": "1:15:44", "throughput": 687.41, "total_tokens": 8082192} {"current_steps": 28855, "total_steps": 40000, "loss": 0.0, "lr": 8.982847263046065e-06, "epoch": 320.6111111111111, "percentage": 72.14, "elapsed_time": "3:15:59", "remaining_time": "1:15:41", "throughput": 687.42, "total_tokens": 8083632} {"current_steps": 28860, "total_steps": 40000, "loss": 0.0, "lr": 8.975310610817555e-06, "epoch": 320.6666666666667, "percentage": 72.15, "elapsed_time": "3:16:01", "remaining_time": "1:15:39", "throughput": 687.42, "total_tokens": 8085024} {"current_steps": 28865, "total_steps": 40000, "loss": 0.0, "lr": 8.967776429797528e-06, "epoch": 320.72222222222223, "percentage": 72.16, "elapsed_time": "3:16:03", "remaining_time": "1:15:37", "throughput": 687.43, "total_tokens": 8086448} {"current_steps": 28870, "total_steps": 40000, "loss": 0.0, "lr": 8.960244721147842e-06, "epoch": 320.77777777777777, "percentage": 72.17, "elapsed_time": "3:16:05", "remaining_time": "1:15:35", "throughput": 687.44, "total_tokens": 8087840} {"current_steps": 28875, "total_steps": 40000, "loss": 0.0, "lr": 8.952715486029995e-06, "epoch": 320.8333333333333, "percentage": 72.19, "elapsed_time": "3:16:07", "remaining_time": "1:15:33", "throughput": 687.44, "total_tokens": 8089248} {"current_steps": 28880, "total_steps": 40000, "loss": 0.0, "lr": 8.945188725605075e-06, "epoch": 320.8888888888889, "percentage": 72.2, "elapsed_time": "3:16:09", "remaining_time": "1:15:31", "throughput": 687.45, "total_tokens": 8090624} {"current_steps": 28885, "total_steps": 40000, "loss": 0.0, "lr": 8.937664441033817e-06, "epoch": 320.94444444444446, "percentage": 72.21, "elapsed_time": "3:16:11", "remaining_time": "1:15:29", "throughput": 687.45, "total_tokens": 8092000} {"current_steps": 28890, "total_steps": 40000, "loss": 0.0, "lr": 8.930142633476549e-06, "epoch": 321.0, "percentage": 72.22, "elapsed_time": "3:16:13", "remaining_time": "1:15:27", "throughput": 687.45, "total_tokens": 8093408} {"current_steps": 28895, "total_steps": 40000, "loss": 0.0, "lr": 8.92262330409323e-06, "epoch": 321.05555555555554, "percentage": 72.24, "elapsed_time": "3:16:15", "remaining_time": "1:15:25", "throughput": 687.43, "total_tokens": 8094768} {"current_steps": 28900, "total_steps": 40000, "loss": 0.0, "lr": 8.915106454043448e-06, "epoch": 321.1111111111111, "percentage": 72.25, "elapsed_time": "3:16:17", "remaining_time": "1:15:23", "throughput": 687.44, "total_tokens": 8096176} {"current_steps": 28905, "total_steps": 40000, "loss": 0.0, "lr": 8.90759208448638e-06, "epoch": 321.1666666666667, "percentage": 72.26, "elapsed_time": "3:16:19", "remaining_time": "1:15:21", "throughput": 687.44, "total_tokens": 8097536} {"current_steps": 28910, "total_steps": 40000, "loss": 0.0, "lr": 8.900080196580848e-06, "epoch": 321.22222222222223, "percentage": 72.28, "elapsed_time": "3:16:21", "remaining_time": "1:15:19", "throughput": 687.45, "total_tokens": 8098928} {"current_steps": 28915, "total_steps": 40000, "loss": 0.0, "lr": 8.892570791485267e-06, "epoch": 321.27777777777777, "percentage": 72.29, "elapsed_time": "3:16:23", "remaining_time": "1:15:17", "throughput": 687.46, "total_tokens": 8100416} {"current_steps": 28920, "total_steps": 40000, "loss": 0.0, "lr": 8.885063870357688e-06, "epoch": 321.3333333333333, "percentage": 72.3, "elapsed_time": "3:16:25", "remaining_time": "1:15:15", "throughput": 687.47, "total_tokens": 8101856} {"current_steps": 28925, "total_steps": 40000, "loss": 0.0, "lr": 8.87755943435578e-06, "epoch": 321.3888888888889, "percentage": 72.31, "elapsed_time": "3:16:26", "remaining_time": "1:15:13", "throughput": 687.47, "total_tokens": 8103248} {"current_steps": 28930, "total_steps": 40000, "loss": 0.0, "lr": 8.87005748463681e-06, "epoch": 321.44444444444446, "percentage": 72.32, "elapsed_time": "3:16:28", "remaining_time": "1:15:11", "throughput": 687.48, "total_tokens": 8104640} {"current_steps": 28935, "total_steps": 40000, "loss": 0.0, "lr": 8.862558022357681e-06, "epoch": 321.5, "percentage": 72.34, "elapsed_time": "3:16:30", "remaining_time": "1:15:08", "throughput": 687.48, "total_tokens": 8106032} {"current_steps": 28940, "total_steps": 40000, "loss": 0.0, "lr": 8.855061048674903e-06, "epoch": 321.55555555555554, "percentage": 72.35, "elapsed_time": "3:16:32", "remaining_time": "1:15:06", "throughput": 687.49, "total_tokens": 8107392} {"current_steps": 28945, "total_steps": 40000, "loss": 0.0, "lr": 8.847566564744595e-06, "epoch": 321.6111111111111, "percentage": 72.36, "elapsed_time": "3:16:34", "remaining_time": "1:15:04", "throughput": 687.49, "total_tokens": 8108816} {"current_steps": 28950, "total_steps": 40000, "loss": 0.0, "lr": 8.840074571722512e-06, "epoch": 321.6666666666667, "percentage": 72.38, "elapsed_time": "3:16:36", "remaining_time": "1:15:02", "throughput": 687.5, "total_tokens": 8110224} {"current_steps": 28955, "total_steps": 40000, "loss": 0.0, "lr": 8.832585070764002e-06, "epoch": 321.72222222222223, "percentage": 72.39, "elapsed_time": "3:16:38", "remaining_time": "1:15:00", "throughput": 687.5, "total_tokens": 8111584} {"current_steps": 28960, "total_steps": 40000, "loss": 0.0, "lr": 8.825098063024045e-06, "epoch": 321.77777777777777, "percentage": 72.4, "elapsed_time": "3:16:40", "remaining_time": "1:14:58", "throughput": 687.51, "total_tokens": 8113008} {"current_steps": 28965, "total_steps": 40000, "loss": 0.0, "lr": 8.817613549657244e-06, "epoch": 321.8333333333333, "percentage": 72.41, "elapsed_time": "3:16:42", "remaining_time": "1:14:56", "throughput": 687.52, "total_tokens": 8114416} {"current_steps": 28970, "total_steps": 40000, "loss": 0.0, "lr": 8.810131531817783e-06, "epoch": 321.8888888888889, "percentage": 72.42, "elapsed_time": "3:16:44", "remaining_time": "1:14:54", "throughput": 687.52, "total_tokens": 8115792} {"current_steps": 28975, "total_steps": 40000, "loss": 0.0, "lr": 8.802652010659496e-06, "epoch": 321.94444444444446, "percentage": 72.44, "elapsed_time": "3:16:46", "remaining_time": "1:14:52", "throughput": 687.53, "total_tokens": 8117184} {"current_steps": 28980, "total_steps": 40000, "loss": 0.0, "lr": 8.795174987335827e-06, "epoch": 322.0, "percentage": 72.45, "elapsed_time": "3:16:48", "remaining_time": "1:14:50", "throughput": 687.52, "total_tokens": 8118592} {"current_steps": 28985, "total_steps": 40000, "loss": 0.0, "lr": 8.787700462999807e-06, "epoch": 322.05555555555554, "percentage": 72.46, "elapsed_time": "3:16:50", "remaining_time": "1:14:48", "throughput": 687.51, "total_tokens": 8120000} {"current_steps": 28990, "total_steps": 40000, "loss": 0.0, "lr": 8.780228438804122e-06, "epoch": 322.1111111111111, "percentage": 72.47, "elapsed_time": "3:16:52", "remaining_time": "1:14:46", "throughput": 687.52, "total_tokens": 8121392} {"current_steps": 28995, "total_steps": 40000, "loss": 0.0, "lr": 8.772758915901032e-06, "epoch": 322.1666666666667, "percentage": 72.49, "elapsed_time": "3:16:54", "remaining_time": "1:14:44", "throughput": 687.52, "total_tokens": 8122784} {"current_steps": 29000, "total_steps": 40000, "loss": 0.0, "lr": 8.765291895442443e-06, "epoch": 322.22222222222223, "percentage": 72.5, "elapsed_time": "3:16:56", "remaining_time": "1:14:42", "throughput": 687.52, "total_tokens": 8124112} {"current_steps": 29000, "total_steps": 40000, "eval_loss": 0.3725336790084839, "epoch": 322.22222222222223, "percentage": 72.5, "elapsed_time": "3:16:57", "remaining_time": "1:14:42", "throughput": 687.45, "total_tokens": 8124112} {"current_steps": 29005, "total_steps": 40000, "loss": 0.0, "lr": 8.75782737857987e-06, "epoch": 322.27777777777777, "percentage": 72.51, "elapsed_time": "3:17:01", "remaining_time": "1:14:41", "throughput": 687.37, "total_tokens": 8125536} {"current_steps": 29010, "total_steps": 40000, "loss": 0.0, "lr": 8.750365366464425e-06, "epoch": 322.3333333333333, "percentage": 72.52, "elapsed_time": "3:17:03", "remaining_time": "1:14:39", "throughput": 687.38, "total_tokens": 8126992} {"current_steps": 29015, "total_steps": 40000, "loss": 0.0, "lr": 8.742905860246838e-06, "epoch": 322.3888888888889, "percentage": 72.54, "elapsed_time": "3:17:05", "remaining_time": "1:14:36", "throughput": 687.38, "total_tokens": 8128368} {"current_steps": 29020, "total_steps": 40000, "loss": 0.0, "lr": 8.735448861077478e-06, "epoch": 322.44444444444446, "percentage": 72.55, "elapsed_time": "3:17:07", "remaining_time": "1:14:34", "throughput": 687.39, "total_tokens": 8129792} {"current_steps": 29025, "total_steps": 40000, "loss": 0.0, "lr": 8.727994370106288e-06, "epoch": 322.5, "percentage": 72.56, "elapsed_time": "3:17:08", "remaining_time": "1:14:32", "throughput": 687.39, "total_tokens": 8131136} {"current_steps": 29030, "total_steps": 40000, "loss": 0.0, "lr": 8.720542388482861e-06, "epoch": 322.55555555555554, "percentage": 72.58, "elapsed_time": "3:17:10", "remaining_time": "1:14:30", "throughput": 687.4, "total_tokens": 8132528} {"current_steps": 29035, "total_steps": 40000, "loss": 0.0, "lr": 8.71309291735637e-06, "epoch": 322.6111111111111, "percentage": 72.59, "elapsed_time": "3:17:12", "remaining_time": "1:14:28", "throughput": 687.4, "total_tokens": 8133872} {"current_steps": 29040, "total_steps": 40000, "loss": 0.0, "lr": 8.705645957875621e-06, "epoch": 322.6666666666667, "percentage": 72.6, "elapsed_time": "3:17:14", "remaining_time": "1:14:26", "throughput": 687.4, "total_tokens": 8135264} {"current_steps": 29045, "total_steps": 40000, "loss": 0.0, "lr": 8.698201511189048e-06, "epoch": 322.72222222222223, "percentage": 72.61, "elapsed_time": "3:17:16", "remaining_time": "1:14:24", "throughput": 687.4, "total_tokens": 8136640} {"current_steps": 29050, "total_steps": 40000, "loss": 0.0, "lr": 8.690759578444649e-06, "epoch": 322.77777777777777, "percentage": 72.62, "elapsed_time": "3:17:18", "remaining_time": "1:14:22", "throughput": 687.41, "total_tokens": 8138096} {"current_steps": 29055, "total_steps": 40000, "loss": 0.0, "lr": 8.68332016079008e-06, "epoch": 322.8333333333333, "percentage": 72.64, "elapsed_time": "3:17:20", "remaining_time": "1:14:20", "throughput": 687.42, "total_tokens": 8139552} {"current_steps": 29060, "total_steps": 40000, "loss": 0.0, "lr": 8.6758832593726e-06, "epoch": 322.8888888888889, "percentage": 72.65, "elapsed_time": "3:17:22", "remaining_time": "1:14:18", "throughput": 687.43, "total_tokens": 8140976} {"current_steps": 29065, "total_steps": 40000, "loss": 0.0, "lr": 8.668448875339053e-06, "epoch": 322.94444444444446, "percentage": 72.66, "elapsed_time": "3:17:24", "remaining_time": "1:14:16", "throughput": 687.44, "total_tokens": 8142384} {"current_steps": 29070, "total_steps": 40000, "loss": 0.0, "lr": 8.661017009835933e-06, "epoch": 323.0, "percentage": 72.67, "elapsed_time": "3:17:26", "remaining_time": "1:14:14", "throughput": 687.43, "total_tokens": 8143760} {"current_steps": 29075, "total_steps": 40000, "loss": 0.0, "lr": 8.653587664009311e-06, "epoch": 323.05555555555554, "percentage": 72.69, "elapsed_time": "3:17:28", "remaining_time": "1:14:12", "throughput": 687.42, "total_tokens": 8145152} {"current_steps": 29080, "total_steps": 40000, "loss": 0.0, "lr": 8.646160839004902e-06, "epoch": 323.1111111111111, "percentage": 72.7, "elapsed_time": "3:17:30", "remaining_time": "1:14:10", "throughput": 687.43, "total_tokens": 8146544} {"current_steps": 29085, "total_steps": 40000, "loss": 0.0, "lr": 8.638736535967998e-06, "epoch": 323.1666666666667, "percentage": 72.71, "elapsed_time": "3:17:32", "remaining_time": "1:14:08", "throughput": 687.43, "total_tokens": 8147920} {"current_steps": 29090, "total_steps": 40000, "loss": 0.0, "lr": 8.631314756043535e-06, "epoch": 323.22222222222223, "percentage": 72.72, "elapsed_time": "3:17:34", "remaining_time": "1:14:06", "throughput": 687.44, "total_tokens": 8149312} {"current_steps": 29095, "total_steps": 40000, "loss": 0.0, "lr": 8.62389550037603e-06, "epoch": 323.27777777777777, "percentage": 72.74, "elapsed_time": "3:17:36", "remaining_time": "1:14:03", "throughput": 687.44, "total_tokens": 8150736} {"current_steps": 29100, "total_steps": 40000, "loss": 0.0, "lr": 8.616478770109646e-06, "epoch": 323.3333333333333, "percentage": 72.75, "elapsed_time": "3:17:38", "remaining_time": "1:14:01", "throughput": 687.45, "total_tokens": 8152128} {"current_steps": 29105, "total_steps": 40000, "loss": 0.0, "lr": 8.609064566388111e-06, "epoch": 323.3888888888889, "percentage": 72.76, "elapsed_time": "3:17:40", "remaining_time": "1:13:59", "throughput": 687.45, "total_tokens": 8153504} {"current_steps": 29110, "total_steps": 40000, "loss": 0.0, "lr": 8.601652890354815e-06, "epoch": 323.44444444444446, "percentage": 72.78, "elapsed_time": "3:17:42", "remaining_time": "1:13:57", "throughput": 687.46, "total_tokens": 8154928} {"current_steps": 29115, "total_steps": 40000, "loss": 0.0, "lr": 8.594243743152705e-06, "epoch": 323.5, "percentage": 72.79, "elapsed_time": "3:17:44", "remaining_time": "1:13:55", "throughput": 687.46, "total_tokens": 8156320} {"current_steps": 29120, "total_steps": 40000, "loss": 0.0, "lr": 8.58683712592438e-06, "epoch": 323.55555555555554, "percentage": 72.8, "elapsed_time": "3:17:46", "remaining_time": "1:13:53", "throughput": 687.47, "total_tokens": 8157696} {"current_steps": 29125, "total_steps": 40000, "loss": 0.0, "lr": 8.579433039812037e-06, "epoch": 323.6111111111111, "percentage": 72.81, "elapsed_time": "3:17:48", "remaining_time": "1:13:51", "throughput": 687.47, "total_tokens": 8159104} {"current_steps": 29130, "total_steps": 40000, "loss": 0.0, "lr": 8.572031485957466e-06, "epoch": 323.6666666666667, "percentage": 72.82, "elapsed_time": "3:17:50", "remaining_time": "1:13:49", "throughput": 687.48, "total_tokens": 8160528} {"current_steps": 29135, "total_steps": 40000, "loss": 0.0, "lr": 8.564632465502084e-06, "epoch": 323.72222222222223, "percentage": 72.84, "elapsed_time": "3:17:52", "remaining_time": "1:13:47", "throughput": 687.48, "total_tokens": 8161904} {"current_steps": 29140, "total_steps": 40000, "loss": 0.0, "lr": 8.557235979586928e-06, "epoch": 323.77777777777777, "percentage": 72.85, "elapsed_time": "3:17:54", "remaining_time": "1:13:45", "throughput": 687.49, "total_tokens": 8163312} {"current_steps": 29145, "total_steps": 40000, "loss": 0.0, "lr": 8.549842029352606e-06, "epoch": 323.8333333333333, "percentage": 72.86, "elapsed_time": "3:17:56", "remaining_time": "1:13:43", "throughput": 687.5, "total_tokens": 8164736} {"current_steps": 29150, "total_steps": 40000, "loss": 0.0, "lr": 8.542450615939376e-06, "epoch": 323.8888888888889, "percentage": 72.88, "elapsed_time": "3:17:57", "remaining_time": "1:13:41", "throughput": 687.5, "total_tokens": 8166144} {"current_steps": 29155, "total_steps": 40000, "loss": 0.0, "lr": 8.535061740487082e-06, "epoch": 323.94444444444446, "percentage": 72.89, "elapsed_time": "3:17:59", "remaining_time": "1:13:39", "throughput": 687.51, "total_tokens": 8167552} {"current_steps": 29160, "total_steps": 40000, "loss": 0.0, "lr": 8.527675404135168e-06, "epoch": 324.0, "percentage": 72.9, "elapsed_time": "3:18:02", "remaining_time": "1:13:37", "throughput": 687.51, "total_tokens": 8168976} {"current_steps": 29165, "total_steps": 40000, "loss": 0.0, "lr": 8.520291608022724e-06, "epoch": 324.05555555555554, "percentage": 72.91, "elapsed_time": "3:18:04", "remaining_time": "1:13:35", "throughput": 687.5, "total_tokens": 8170336} {"current_steps": 29170, "total_steps": 40000, "loss": 0.0, "lr": 8.512910353288398e-06, "epoch": 324.1111111111111, "percentage": 72.92, "elapsed_time": "3:18:06", "remaining_time": "1:13:32", "throughput": 687.5, "total_tokens": 8171712} {"current_steps": 29175, "total_steps": 40000, "loss": 0.0, "lr": 8.505531641070486e-06, "epoch": 324.1666666666667, "percentage": 72.94, "elapsed_time": "3:18:08", "remaining_time": "1:13:30", "throughput": 687.5, "total_tokens": 8173088} {"current_steps": 29180, "total_steps": 40000, "loss": 0.0, "lr": 8.498155472506885e-06, "epoch": 324.22222222222223, "percentage": 72.95, "elapsed_time": "3:18:10", "remaining_time": "1:13:28", "throughput": 687.51, "total_tokens": 8174528} {"current_steps": 29185, "total_steps": 40000, "loss": 0.0, "lr": 8.49078184873508e-06, "epoch": 324.27777777777777, "percentage": 72.96, "elapsed_time": "3:18:11", "remaining_time": "1:13:26", "throughput": 687.52, "total_tokens": 8175936} {"current_steps": 29190, "total_steps": 40000, "loss": 0.0, "lr": 8.483410770892188e-06, "epoch": 324.3333333333333, "percentage": 72.97, "elapsed_time": "3:18:13", "remaining_time": "1:13:24", "throughput": 687.53, "total_tokens": 8177408} {"current_steps": 29195, "total_steps": 40000, "loss": 0.0, "lr": 8.476042240114909e-06, "epoch": 324.3888888888889, "percentage": 72.99, "elapsed_time": "3:18:15", "remaining_time": "1:13:22", "throughput": 687.54, "total_tokens": 8178816} {"current_steps": 29200, "total_steps": 40000, "loss": 0.0, "lr": 8.468676257539568e-06, "epoch": 324.44444444444446, "percentage": 73.0, "elapsed_time": "3:18:17", "remaining_time": "1:13:20", "throughput": 687.54, "total_tokens": 8180192} {"current_steps": 29200, "total_steps": 40000, "eval_loss": 0.3379303514957428, "epoch": 324.44444444444446, "percentage": 73.0, "elapsed_time": "3:18:19", "remaining_time": "1:13:21", "throughput": 687.47, "total_tokens": 8180192} {"current_steps": 29205, "total_steps": 40000, "loss": 0.0, "lr": 8.4613128243021e-06, "epoch": 324.5, "percentage": 73.01, "elapsed_time": "3:18:22", "remaining_time": "1:13:19", "throughput": 687.37, "total_tokens": 8181632} {"current_steps": 29210, "total_steps": 40000, "loss": 0.0, "lr": 8.453951941538028e-06, "epoch": 324.55555555555554, "percentage": 73.02, "elapsed_time": "3:18:24", "remaining_time": "1:13:17", "throughput": 687.37, "total_tokens": 8183008} {"current_steps": 29215, "total_steps": 40000, "loss": 0.0, "lr": 8.446593610382495e-06, "epoch": 324.6111111111111, "percentage": 73.04, "elapsed_time": "3:18:26", "remaining_time": "1:13:15", "throughput": 687.38, "total_tokens": 8184416} {"current_steps": 29220, "total_steps": 40000, "loss": 0.0, "lr": 8.439237831970259e-06, "epoch": 324.6666666666667, "percentage": 73.05, "elapsed_time": "3:18:28", "remaining_time": "1:13:13", "throughput": 687.39, "total_tokens": 8185824} {"current_steps": 29225, "total_steps": 40000, "loss": 0.0, "lr": 8.431884607435667e-06, "epoch": 324.72222222222223, "percentage": 73.06, "elapsed_time": "3:18:30", "remaining_time": "1:13:11", "throughput": 687.39, "total_tokens": 8187216} {"current_steps": 29230, "total_steps": 40000, "loss": 0.0, "lr": 8.424533937912665e-06, "epoch": 324.77777777777777, "percentage": 73.08, "elapsed_time": "3:18:32", "remaining_time": "1:13:09", "throughput": 687.39, "total_tokens": 8188576} {"current_steps": 29235, "total_steps": 40000, "loss": 0.0, "lr": 8.41718582453484e-06, "epoch": 324.8333333333333, "percentage": 73.09, "elapsed_time": "3:18:34", "remaining_time": "1:13:07", "throughput": 687.4, "total_tokens": 8189968} {"current_steps": 29240, "total_steps": 40000, "loss": 0.0, "lr": 8.409840268435346e-06, "epoch": 324.8888888888889, "percentage": 73.1, "elapsed_time": "3:18:36", "remaining_time": "1:13:05", "throughput": 687.4, "total_tokens": 8191376} {"current_steps": 29245, "total_steps": 40000, "loss": 0.0, "lr": 8.402497270746976e-06, "epoch": 324.94444444444446, "percentage": 73.11, "elapsed_time": "3:18:38", "remaining_time": "1:13:03", "throughput": 687.41, "total_tokens": 8192832} {"current_steps": 29250, "total_steps": 40000, "loss": 0.0, "lr": 8.395156832602095e-06, "epoch": 325.0, "percentage": 73.12, "elapsed_time": "3:18:40", "remaining_time": "1:13:01", "throughput": 687.41, "total_tokens": 8194208} {"current_steps": 29255, "total_steps": 40000, "loss": 0.0, "lr": 8.387818955132707e-06, "epoch": 325.05555555555554, "percentage": 73.14, "elapsed_time": "3:18:42", "remaining_time": "1:12:59", "throughput": 687.4, "total_tokens": 8195664} {"current_steps": 29260, "total_steps": 40000, "loss": 0.0, "lr": 8.38048363947039e-06, "epoch": 325.1111111111111, "percentage": 73.15, "elapsed_time": "3:18:44", "remaining_time": "1:12:56", "throughput": 687.41, "total_tokens": 8197040} {"current_steps": 29265, "total_steps": 40000, "loss": 0.0, "lr": 8.373150886746351e-06, "epoch": 325.1666666666667, "percentage": 73.16, "elapsed_time": "3:18:46", "remaining_time": "1:12:54", "throughput": 687.41, "total_tokens": 8198416} {"current_steps": 29270, "total_steps": 40000, "loss": 0.0, "lr": 8.365820698091397e-06, "epoch": 325.22222222222223, "percentage": 73.17, "elapsed_time": "3:18:48", "remaining_time": "1:12:52", "throughput": 687.42, "total_tokens": 8199840} {"current_steps": 29275, "total_steps": 40000, "loss": 0.0, "lr": 8.358493074635922e-06, "epoch": 325.27777777777777, "percentage": 73.19, "elapsed_time": "3:18:50", "remaining_time": "1:12:50", "throughput": 687.42, "total_tokens": 8201232} {"current_steps": 29280, "total_steps": 40000, "loss": 0.0, "lr": 8.351168017509948e-06, "epoch": 325.3333333333333, "percentage": 73.2, "elapsed_time": "3:18:52", "remaining_time": "1:12:48", "throughput": 687.43, "total_tokens": 8202624} {"current_steps": 29285, "total_steps": 40000, "loss": 0.0, "lr": 8.343845527843094e-06, "epoch": 325.3888888888889, "percentage": 73.21, "elapsed_time": "3:18:54", "remaining_time": "1:12:46", "throughput": 687.44, "total_tokens": 8204064} {"current_steps": 29290, "total_steps": 40000, "loss": 0.0, "lr": 8.336525606764566e-06, "epoch": 325.44444444444446, "percentage": 73.22, "elapsed_time": "3:18:56", "remaining_time": "1:12:44", "throughput": 687.44, "total_tokens": 8205456} {"current_steps": 29295, "total_steps": 40000, "loss": 0.0, "lr": 8.329208255403204e-06, "epoch": 325.5, "percentage": 73.24, "elapsed_time": "3:18:58", "remaining_time": "1:12:42", "throughput": 687.45, "total_tokens": 8206896} {"current_steps": 29300, "total_steps": 40000, "loss": 0.0, "lr": 8.321893474887426e-06, "epoch": 325.55555555555554, "percentage": 73.25, "elapsed_time": "3:19:00", "remaining_time": "1:12:40", "throughput": 687.46, "total_tokens": 8208320} {"current_steps": 29305, "total_steps": 40000, "loss": 0.0, "lr": 8.31458126634526e-06, "epoch": 325.6111111111111, "percentage": 73.26, "elapsed_time": "3:19:02", "remaining_time": "1:12:38", "throughput": 687.46, "total_tokens": 8209712} {"current_steps": 29310, "total_steps": 40000, "loss": 0.0, "lr": 8.30727163090435e-06, "epoch": 325.6666666666667, "percentage": 73.28, "elapsed_time": "3:19:03", "remaining_time": "1:12:36", "throughput": 687.47, "total_tokens": 8211136} {"current_steps": 29315, "total_steps": 40000, "loss": 0.0, "lr": 8.29996456969192e-06, "epoch": 325.72222222222223, "percentage": 73.29, "elapsed_time": "3:19:05", "remaining_time": "1:12:34", "throughput": 687.48, "total_tokens": 8212528} {"current_steps": 29320, "total_steps": 40000, "loss": 0.0, "lr": 8.292660083834818e-06, "epoch": 325.77777777777777, "percentage": 73.3, "elapsed_time": "3:19:07", "remaining_time": "1:12:32", "throughput": 687.48, "total_tokens": 8213936} {"current_steps": 29325, "total_steps": 40000, "loss": 0.0, "lr": 8.2853581744595e-06, "epoch": 325.8333333333333, "percentage": 73.31, "elapsed_time": "3:19:09", "remaining_time": "1:12:30", "throughput": 687.48, "total_tokens": 8215264} {"current_steps": 29330, "total_steps": 40000, "loss": 0.0, "lr": 8.278058842691991e-06, "epoch": 325.8888888888889, "percentage": 73.32, "elapsed_time": "3:19:11", "remaining_time": "1:12:27", "throughput": 687.49, "total_tokens": 8216688} {"current_steps": 29335, "total_steps": 40000, "loss": 0.0, "lr": 8.27076208965796e-06, "epoch": 325.94444444444446, "percentage": 73.34, "elapsed_time": "3:19:13", "remaining_time": "1:12:25", "throughput": 687.5, "total_tokens": 8218096} {"current_steps": 29340, "total_steps": 40000, "loss": 0.0, "lr": 8.263467916482637e-06, "epoch": 326.0, "percentage": 73.35, "elapsed_time": "3:19:15", "remaining_time": "1:12:23", "throughput": 687.49, "total_tokens": 8219488} {"current_steps": 29345, "total_steps": 40000, "loss": 0.0, "lr": 8.256176324290885e-06, "epoch": 326.05555555555554, "percentage": 73.36, "elapsed_time": "3:19:17", "remaining_time": "1:12:21", "throughput": 687.48, "total_tokens": 8220864} {"current_steps": 29350, "total_steps": 40000, "loss": 0.0, "lr": 8.248887314207168e-06, "epoch": 326.1111111111111, "percentage": 73.38, "elapsed_time": "3:19:19", "remaining_time": "1:12:19", "throughput": 687.48, "total_tokens": 8222240} {"current_steps": 29355, "total_steps": 40000, "loss": 0.0, "lr": 8.24160088735553e-06, "epoch": 326.1666666666667, "percentage": 73.39, "elapsed_time": "3:19:21", "remaining_time": "1:12:17", "throughput": 687.49, "total_tokens": 8223664} {"current_steps": 29360, "total_steps": 40000, "loss": 0.0, "lr": 8.234317044859629e-06, "epoch": 326.22222222222223, "percentage": 73.4, "elapsed_time": "3:19:23", "remaining_time": "1:12:15", "throughput": 687.49, "total_tokens": 8225056} {"current_steps": 29365, "total_steps": 40000, "loss": 0.0, "lr": 8.227035787842744e-06, "epoch": 326.27777777777777, "percentage": 73.41, "elapsed_time": "3:19:25", "remaining_time": "1:12:13", "throughput": 687.5, "total_tokens": 8226464} {"current_steps": 29370, "total_steps": 40000, "loss": 0.0, "lr": 8.219757117427721e-06, "epoch": 326.3333333333333, "percentage": 73.42, "elapsed_time": "3:19:27", "remaining_time": "1:12:11", "throughput": 687.51, "total_tokens": 8227888} {"current_steps": 29375, "total_steps": 40000, "loss": 0.0, "lr": 8.212481034737014e-06, "epoch": 326.3888888888889, "percentage": 73.44, "elapsed_time": "3:19:29", "remaining_time": "1:12:09", "throughput": 687.51, "total_tokens": 8229232} {"current_steps": 29380, "total_steps": 40000, "loss": 0.0, "lr": 8.205207540892707e-06, "epoch": 326.44444444444446, "percentage": 73.45, "elapsed_time": "3:19:31", "remaining_time": "1:12:07", "throughput": 687.51, "total_tokens": 8230640} {"current_steps": 29385, "total_steps": 40000, "loss": 0.0, "lr": 8.197936637016442e-06, "epoch": 326.5, "percentage": 73.46, "elapsed_time": "3:19:33", "remaining_time": "1:12:05", "throughput": 687.53, "total_tokens": 8232096} {"current_steps": 29390, "total_steps": 40000, "loss": 0.0, "lr": 8.190668324229508e-06, "epoch": 326.55555555555554, "percentage": 73.47, "elapsed_time": "3:19:35", "remaining_time": "1:12:03", "throughput": 687.53, "total_tokens": 8233504} {"current_steps": 29395, "total_steps": 40000, "loss": 0.0, "lr": 8.183402603652749e-06, "epoch": 326.6111111111111, "percentage": 73.49, "elapsed_time": "3:19:37", "remaining_time": "1:12:01", "throughput": 687.54, "total_tokens": 8234896} {"current_steps": 29400, "total_steps": 40000, "loss": 0.0, "lr": 8.176139476406635e-06, "epoch": 326.6666666666667, "percentage": 73.5, "elapsed_time": "3:19:39", "remaining_time": "1:11:59", "throughput": 687.54, "total_tokens": 8236304} {"current_steps": 29400, "total_steps": 40000, "eval_loss": 0.3741936683654785, "epoch": 326.6666666666667, "percentage": 73.5, "elapsed_time": "3:19:40", "remaining_time": "1:11:59", "throughput": 687.47, "total_tokens": 8236304} {"current_steps": 29405, "total_steps": 40000, "loss": 0.0, "lr": 8.16887894361125e-06, "epoch": 326.72222222222223, "percentage": 73.51, "elapsed_time": "3:19:44", "remaining_time": "1:11:58", "throughput": 687.38, "total_tokens": 8237680} {"current_steps": 29410, "total_steps": 40000, "loss": 0.0, "lr": 8.161621006386233e-06, "epoch": 326.77777777777777, "percentage": 73.52, "elapsed_time": "3:19:46", "remaining_time": "1:11:55", "throughput": 687.39, "total_tokens": 8239088} {"current_steps": 29415, "total_steps": 40000, "loss": 0.0, "lr": 8.154365665850869e-06, "epoch": 326.8333333333333, "percentage": 73.54, "elapsed_time": "3:19:48", "remaining_time": "1:11:53", "throughput": 687.39, "total_tokens": 8240496} {"current_steps": 29420, "total_steps": 40000, "loss": 0.0, "lr": 8.147112923124005e-06, "epoch": 326.8888888888889, "percentage": 73.55, "elapsed_time": "3:19:49", "remaining_time": "1:11:51", "throughput": 687.4, "total_tokens": 8241904} {"current_steps": 29425, "total_steps": 40000, "loss": 0.0, "lr": 8.13986277932412e-06, "epoch": 326.94444444444446, "percentage": 73.56, "elapsed_time": "3:19:51", "remaining_time": "1:11:49", "throughput": 687.4, "total_tokens": 8243296} {"current_steps": 29430, "total_steps": 40000, "loss": 0.0, "lr": 8.132615235569277e-06, "epoch": 327.0, "percentage": 73.58, "elapsed_time": "3:19:54", "remaining_time": "1:11:47", "throughput": 687.4, "total_tokens": 8244688} {"current_steps": 29435, "total_steps": 40000, "loss": 0.0, "lr": 8.125370292977124e-06, "epoch": 327.05555555555554, "percentage": 73.59, "elapsed_time": "3:19:56", "remaining_time": "1:11:45", "throughput": 687.39, "total_tokens": 8246064} {"current_steps": 29440, "total_steps": 40000, "loss": 0.0, "lr": 8.118127952664944e-06, "epoch": 327.1111111111111, "percentage": 73.6, "elapsed_time": "3:19:58", "remaining_time": "1:11:43", "throughput": 687.4, "total_tokens": 8247488} {"current_steps": 29445, "total_steps": 40000, "loss": 0.0, "lr": 8.110888215749574e-06, "epoch": 327.1666666666667, "percentage": 73.61, "elapsed_time": "3:20:00", "remaining_time": "1:11:41", "throughput": 687.4, "total_tokens": 8248880} {"current_steps": 29450, "total_steps": 40000, "loss": 0.0, "lr": 8.10365108334749e-06, "epoch": 327.22222222222223, "percentage": 73.62, "elapsed_time": "3:20:02", "remaining_time": "1:11:39", "throughput": 687.41, "total_tokens": 8250304} {"current_steps": 29455, "total_steps": 40000, "loss": 0.0, "lr": 8.096416556574743e-06, "epoch": 327.27777777777777, "percentage": 73.64, "elapsed_time": "3:20:04", "remaining_time": "1:11:37", "throughput": 687.41, "total_tokens": 8251696} {"current_steps": 29460, "total_steps": 40000, "loss": 0.0, "lr": 8.08918463654698e-06, "epoch": 327.3333333333333, "percentage": 73.65, "elapsed_time": "3:20:05", "remaining_time": "1:11:35", "throughput": 687.42, "total_tokens": 8253088} {"current_steps": 29465, "total_steps": 40000, "loss": 0.0, "lr": 8.081955324379458e-06, "epoch": 327.3888888888889, "percentage": 73.66, "elapsed_time": "3:20:07", "remaining_time": "1:11:33", "throughput": 687.42, "total_tokens": 8254496} {"current_steps": 29470, "total_steps": 40000, "loss": 0.0, "lr": 8.074728621187039e-06, "epoch": 327.44444444444446, "percentage": 73.67, "elapsed_time": "3:20:09", "remaining_time": "1:11:31", "throughput": 687.43, "total_tokens": 8255856} {"current_steps": 29475, "total_steps": 40000, "loss": 0.0, "lr": 8.067504528084158e-06, "epoch": 327.5, "percentage": 73.69, "elapsed_time": "3:20:11", "remaining_time": "1:11:29", "throughput": 687.43, "total_tokens": 8257264} {"current_steps": 29480, "total_steps": 40000, "loss": 0.0, "lr": 8.060283046184861e-06, "epoch": 327.55555555555554, "percentage": 73.7, "elapsed_time": "3:20:13", "remaining_time": "1:11:27", "throughput": 687.44, "total_tokens": 8258656} {"current_steps": 29485, "total_steps": 40000, "loss": 0.0, "lr": 8.053064176602806e-06, "epoch": 327.6111111111111, "percentage": 73.71, "elapsed_time": "3:20:15", "remaining_time": "1:11:25", "throughput": 687.44, "total_tokens": 8260080} {"current_steps": 29490, "total_steps": 40000, "loss": 0.0, "lr": 8.045847920451216e-06, "epoch": 327.6666666666667, "percentage": 73.72, "elapsed_time": "3:20:17", "remaining_time": "1:11:22", "throughput": 687.45, "total_tokens": 8261488} {"current_steps": 29495, "total_steps": 40000, "loss": 0.0, "lr": 8.038634278842944e-06, "epoch": 327.72222222222223, "percentage": 73.74, "elapsed_time": "3:20:19", "remaining_time": "1:11:20", "throughput": 687.45, "total_tokens": 8262832} {"current_steps": 29500, "total_steps": 40000, "loss": 0.0, "lr": 8.031423252890408e-06, "epoch": 327.77777777777777, "percentage": 73.75, "elapsed_time": "3:20:21", "remaining_time": "1:11:18", "throughput": 687.46, "total_tokens": 8264240} {"current_steps": 29505, "total_steps": 40000, "loss": 0.0, "lr": 8.024214843705646e-06, "epoch": 327.8333333333333, "percentage": 73.76, "elapsed_time": "3:20:23", "remaining_time": "1:11:16", "throughput": 687.46, "total_tokens": 8265616} {"current_steps": 29510, "total_steps": 40000, "loss": 0.0, "lr": 8.017009052400295e-06, "epoch": 327.8888888888889, "percentage": 73.78, "elapsed_time": "3:20:25", "remaining_time": "1:11:14", "throughput": 687.47, "total_tokens": 8267024} {"current_steps": 29515, "total_steps": 40000, "loss": 0.0, "lr": 8.00980588008557e-06, "epoch": 327.94444444444446, "percentage": 73.79, "elapsed_time": "3:20:27", "remaining_time": "1:11:12", "throughput": 687.47, "total_tokens": 8268432} {"current_steps": 29520, "total_steps": 40000, "loss": 0.0, "lr": 8.002605327872282e-06, "epoch": 328.0, "percentage": 73.8, "elapsed_time": "3:20:29", "remaining_time": "1:11:10", "throughput": 687.47, "total_tokens": 8269856} {"current_steps": 29525, "total_steps": 40000, "loss": 0.0, "lr": 7.995407396870862e-06, "epoch": 328.05555555555554, "percentage": 73.81, "elapsed_time": "3:20:31", "remaining_time": "1:11:08", "throughput": 687.46, "total_tokens": 8271264} {"current_steps": 29530, "total_steps": 40000, "loss": 0.0, "lr": 7.988212088191307e-06, "epoch": 328.1111111111111, "percentage": 73.83, "elapsed_time": "3:20:33", "remaining_time": "1:11:06", "throughput": 687.47, "total_tokens": 8272672} {"current_steps": 29535, "total_steps": 40000, "loss": 0.0, "lr": 7.98101940294324e-06, "epoch": 328.1666666666667, "percentage": 73.84, "elapsed_time": "3:20:35", "remaining_time": "1:11:04", "throughput": 687.48, "total_tokens": 8274112} {"current_steps": 29540, "total_steps": 40000, "loss": 0.0, "lr": 7.973829342235847e-06, "epoch": 328.22222222222223, "percentage": 73.85, "elapsed_time": "3:20:37", "remaining_time": "1:11:02", "throughput": 687.49, "total_tokens": 8275536} {"current_steps": 29545, "total_steps": 40000, "loss": 0.0, "lr": 7.966641907177936e-06, "epoch": 328.27777777777777, "percentage": 73.86, "elapsed_time": "3:20:39", "remaining_time": "1:11:00", "throughput": 687.49, "total_tokens": 8276944} {"current_steps": 29550, "total_steps": 40000, "loss": 0.0, "lr": 7.959457098877901e-06, "epoch": 328.3333333333333, "percentage": 73.88, "elapsed_time": "3:20:41", "remaining_time": "1:10:58", "throughput": 687.5, "total_tokens": 8278336} {"current_steps": 29555, "total_steps": 40000, "loss": 0.0, "lr": 7.952274918443719e-06, "epoch": 328.3888888888889, "percentage": 73.89, "elapsed_time": "3:20:43", "remaining_time": "1:10:56", "throughput": 687.5, "total_tokens": 8279712} {"current_steps": 29560, "total_steps": 40000, "loss": 0.0, "lr": 7.945095366982983e-06, "epoch": 328.44444444444446, "percentage": 73.9, "elapsed_time": "3:20:45", "remaining_time": "1:10:54", "throughput": 687.5, "total_tokens": 8281104} {"current_steps": 29565, "total_steps": 40000, "loss": 0.0, "lr": 7.937918445602871e-06, "epoch": 328.5, "percentage": 73.91, "elapsed_time": "3:20:47", "remaining_time": "1:10:52", "throughput": 687.51, "total_tokens": 8282544} {"current_steps": 29570, "total_steps": 40000, "loss": 0.0, "lr": 7.930744155410145e-06, "epoch": 328.55555555555554, "percentage": 73.92, "elapsed_time": "3:20:49", "remaining_time": "1:10:49", "throughput": 687.52, "total_tokens": 8283920} {"current_steps": 29575, "total_steps": 40000, "loss": 0.0, "lr": 7.923572497511181e-06, "epoch": 328.6111111111111, "percentage": 73.94, "elapsed_time": "3:20:51", "remaining_time": "1:10:47", "throughput": 687.52, "total_tokens": 8285296} {"current_steps": 29580, "total_steps": 40000, "loss": 0.0, "lr": 7.916403473011927e-06, "epoch": 328.6666666666667, "percentage": 73.95, "elapsed_time": "3:20:52", "remaining_time": "1:10:45", "throughput": 687.53, "total_tokens": 8286704} {"current_steps": 29585, "total_steps": 40000, "loss": 0.0, "lr": 7.909237083017953e-06, "epoch": 328.72222222222223, "percentage": 73.96, "elapsed_time": "3:20:54", "remaining_time": "1:10:43", "throughput": 687.53, "total_tokens": 8288112} {"current_steps": 29590, "total_steps": 40000, "loss": 0.0, "lr": 7.902073328634389e-06, "epoch": 328.77777777777777, "percentage": 73.98, "elapsed_time": "3:20:56", "remaining_time": "1:10:41", "throughput": 687.53, "total_tokens": 8289472} {"current_steps": 29595, "total_steps": 40000, "loss": 0.0, "lr": 7.894912210965987e-06, "epoch": 328.8333333333333, "percentage": 73.99, "elapsed_time": "3:20:58", "remaining_time": "1:10:39", "throughput": 687.54, "total_tokens": 8290896} {"current_steps": 29600, "total_steps": 40000, "loss": 0.0, "lr": 7.887753731117075e-06, "epoch": 328.8888888888889, "percentage": 74.0, "elapsed_time": "3:21:00", "remaining_time": "1:10:37", "throughput": 687.54, "total_tokens": 8292272} {"current_steps": 29600, "total_steps": 40000, "eval_loss": 0.3082268238067627, "epoch": 328.8888888888889, "percentage": 74.0, "elapsed_time": "3:21:02", "remaining_time": "1:10:38", "throughput": 687.47, "total_tokens": 8292272} {"current_steps": 29605, "total_steps": 40000, "loss": 0.0, "lr": 7.880597890191587e-06, "epoch": 328.94444444444446, "percentage": 74.01, "elapsed_time": "3:21:05", "remaining_time": "1:10:36", "throughput": 687.4, "total_tokens": 8293712} {"current_steps": 29610, "total_steps": 40000, "loss": 0.0, "lr": 7.873444689293036e-06, "epoch": 329.0, "percentage": 74.02, "elapsed_time": "3:21:07", "remaining_time": "1:10:34", "throughput": 687.39, "total_tokens": 8295152} {"current_steps": 29615, "total_steps": 40000, "loss": 0.0, "lr": 7.866294129524548e-06, "epoch": 329.05555555555554, "percentage": 74.04, "elapsed_time": "3:21:09", "remaining_time": "1:10:32", "throughput": 687.38, "total_tokens": 8296512} {"current_steps": 29620, "total_steps": 40000, "loss": 0.0, "lr": 7.859146211988811e-06, "epoch": 329.1111111111111, "percentage": 74.05, "elapsed_time": "3:21:11", "remaining_time": "1:10:30", "throughput": 687.38, "total_tokens": 8297888} {"current_steps": 29625, "total_steps": 40000, "loss": 0.0, "lr": 7.852000937788134e-06, "epoch": 329.1666666666667, "percentage": 74.06, "elapsed_time": "3:21:13", "remaining_time": "1:10:28", "throughput": 687.39, "total_tokens": 8299264} {"current_steps": 29630, "total_steps": 40000, "loss": 0.0, "lr": 7.844858308024416e-06, "epoch": 329.22222222222223, "percentage": 74.08, "elapsed_time": "3:21:15", "remaining_time": "1:10:26", "throughput": 687.4, "total_tokens": 8300720} {"current_steps": 29635, "total_steps": 40000, "loss": 0.0, "lr": 7.837718323799122e-06, "epoch": 329.27777777777777, "percentage": 74.09, "elapsed_time": "3:21:17", "remaining_time": "1:10:24", "throughput": 687.4, "total_tokens": 8302096} {"current_steps": 29640, "total_steps": 40000, "loss": 0.0, "lr": 7.83058098621334e-06, "epoch": 329.3333333333333, "percentage": 74.1, "elapsed_time": "3:21:19", "remaining_time": "1:10:22", "throughput": 687.4, "total_tokens": 8303488} {"current_steps": 29645, "total_steps": 40000, "loss": 0.0, "lr": 7.823446296367739e-06, "epoch": 329.3888888888889, "percentage": 74.11, "elapsed_time": "3:21:21", "remaining_time": "1:10:20", "throughput": 687.41, "total_tokens": 8304912} {"current_steps": 29650, "total_steps": 40000, "loss": 0.0, "lr": 7.81631425536257e-06, "epoch": 329.44444444444446, "percentage": 74.12, "elapsed_time": "3:21:23", "remaining_time": "1:10:17", "throughput": 687.42, "total_tokens": 8306320} {"current_steps": 29655, "total_steps": 40000, "loss": 0.0, "lr": 7.809184864297689e-06, "epoch": 329.5, "percentage": 74.14, "elapsed_time": "3:21:25", "remaining_time": "1:10:15", "throughput": 687.42, "total_tokens": 8307728} {"current_steps": 29660, "total_steps": 40000, "loss": 0.0, "lr": 7.802058124272532e-06, "epoch": 329.55555555555554, "percentage": 74.15, "elapsed_time": "3:21:27", "remaining_time": "1:10:13", "throughput": 687.43, "total_tokens": 8309136} {"current_steps": 29665, "total_steps": 40000, "loss": 0.0, "lr": 7.79493403638614e-06, "epoch": 329.6111111111111, "percentage": 74.16, "elapsed_time": "3:21:29", "remaining_time": "1:10:11", "throughput": 687.43, "total_tokens": 8310496} {"current_steps": 29670, "total_steps": 40000, "loss": 0.0, "lr": 7.787812601737132e-06, "epoch": 329.6666666666667, "percentage": 74.17, "elapsed_time": "3:21:31", "remaining_time": "1:10:09", "throughput": 687.44, "total_tokens": 8311904} {"current_steps": 29675, "total_steps": 40000, "loss": 0.0, "lr": 7.780693821423715e-06, "epoch": 329.72222222222223, "percentage": 74.19, "elapsed_time": "3:21:33", "remaining_time": "1:10:07", "throughput": 687.44, "total_tokens": 8313328} {"current_steps": 29680, "total_steps": 40000, "loss": 0.0, "lr": 7.773577696543705e-06, "epoch": 329.77777777777777, "percentage": 74.2, "elapsed_time": "3:21:35", "remaining_time": "1:10:05", "throughput": 687.45, "total_tokens": 8314752} {"current_steps": 29685, "total_steps": 40000, "loss": 0.0, "lr": 7.7664642281945e-06, "epoch": 329.8333333333333, "percentage": 74.21, "elapsed_time": "3:21:36", "remaining_time": "1:10:03", "throughput": 687.45, "total_tokens": 8316112} {"current_steps": 29690, "total_steps": 40000, "loss": 0.0, "lr": 7.759353417473072e-06, "epoch": 329.8888888888889, "percentage": 74.22, "elapsed_time": "3:21:38", "remaining_time": "1:10:01", "throughput": 687.46, "total_tokens": 8317552} {"current_steps": 29695, "total_steps": 40000, "loss": 0.0, "lr": 7.752245265476016e-06, "epoch": 329.94444444444446, "percentage": 74.24, "elapsed_time": "3:21:40", "remaining_time": "1:09:59", "throughput": 687.48, "total_tokens": 8319024} {"current_steps": 29700, "total_steps": 40000, "loss": 0.0, "lr": 7.745139773299481e-06, "epoch": 330.0, "percentage": 74.25, "elapsed_time": "3:21:42", "remaining_time": "1:09:57", "throughput": 687.47, "total_tokens": 8320448} {"current_steps": 29705, "total_steps": 40000, "loss": 0.0, "lr": 7.738036942039232e-06, "epoch": 330.05555555555554, "percentage": 74.26, "elapsed_time": "3:21:45", "remaining_time": "1:09:55", "throughput": 687.47, "total_tokens": 8321872} {"current_steps": 29710, "total_steps": 40000, "loss": 0.0, "lr": 7.73093677279062e-06, "epoch": 330.1111111111111, "percentage": 74.28, "elapsed_time": "3:21:47", "remaining_time": "1:09:53", "throughput": 687.47, "total_tokens": 8323232} {"current_steps": 29715, "total_steps": 40000, "loss": 0.0, "lr": 7.72383926664857e-06, "epoch": 330.1666666666667, "percentage": 74.29, "elapsed_time": "3:21:49", "remaining_time": "1:09:51", "throughput": 687.48, "total_tokens": 8324656} {"current_steps": 29720, "total_steps": 40000, "loss": 0.0, "lr": 7.716744424707606e-06, "epoch": 330.22222222222223, "percentage": 74.3, "elapsed_time": "3:21:50", "remaining_time": "1:09:49", "throughput": 687.48, "total_tokens": 8326048} {"current_steps": 29725, "total_steps": 40000, "loss": 0.0, "lr": 7.709652248061858e-06, "epoch": 330.27777777777777, "percentage": 74.31, "elapsed_time": "3:21:52", "remaining_time": "1:09:47", "throughput": 687.48, "total_tokens": 8327408} {"current_steps": 29730, "total_steps": 40000, "loss": 0.0, "lr": 7.702562737805017e-06, "epoch": 330.3333333333333, "percentage": 74.33, "elapsed_time": "3:21:54", "remaining_time": "1:09:44", "throughput": 687.48, "total_tokens": 8328768} {"current_steps": 29735, "total_steps": 40000, "loss": 0.0, "lr": 7.695475895030365e-06, "epoch": 330.3888888888889, "percentage": 74.34, "elapsed_time": "3:21:56", "remaining_time": "1:09:42", "throughput": 687.5, "total_tokens": 8330256} {"current_steps": 29740, "total_steps": 40000, "loss": 0.0, "lr": 7.6883917208308e-06, "epoch": 330.44444444444446, "percentage": 74.35, "elapsed_time": "3:21:58", "remaining_time": "1:09:40", "throughput": 687.51, "total_tokens": 8331728} {"current_steps": 29745, "total_steps": 40000, "loss": 0.0, "lr": 7.681310216298778e-06, "epoch": 330.5, "percentage": 74.36, "elapsed_time": "3:22:00", "remaining_time": "1:09:38", "throughput": 687.51, "total_tokens": 8333104} {"current_steps": 29750, "total_steps": 40000, "loss": 0.0, "lr": 7.674231382526367e-06, "epoch": 330.55555555555554, "percentage": 74.38, "elapsed_time": "3:22:02", "remaining_time": "1:09:36", "throughput": 687.52, "total_tokens": 8334528} {"current_steps": 29755, "total_steps": 40000, "loss": 0.0, "lr": 7.667155220605198e-06, "epoch": 330.6111111111111, "percentage": 74.39, "elapsed_time": "3:22:04", "remaining_time": "1:09:34", "throughput": 687.52, "total_tokens": 8335920} {"current_steps": 29760, "total_steps": 40000, "loss": 0.0, "lr": 7.660081731626515e-06, "epoch": 330.6666666666667, "percentage": 74.4, "elapsed_time": "3:22:06", "remaining_time": "1:09:32", "throughput": 687.53, "total_tokens": 8337344} {"current_steps": 29765, "total_steps": 40000, "loss": 0.0, "lr": 7.653010916681141e-06, "epoch": 330.72222222222223, "percentage": 74.41, "elapsed_time": "3:22:08", "remaining_time": "1:09:30", "throughput": 687.53, "total_tokens": 8338720} {"current_steps": 29770, "total_steps": 40000, "loss": 0.0, "lr": 7.645942776859472e-06, "epoch": 330.77777777777777, "percentage": 74.42, "elapsed_time": "3:22:10", "remaining_time": "1:09:28", "throughput": 687.54, "total_tokens": 8340112} {"current_steps": 29775, "total_steps": 40000, "loss": 0.0, "lr": 7.63887731325152e-06, "epoch": 330.8333333333333, "percentage": 74.44, "elapsed_time": "3:22:12", "remaining_time": "1:09:26", "throughput": 687.54, "total_tokens": 8341488} {"current_steps": 29780, "total_steps": 40000, "loss": 0.0, "lr": 7.63181452694685e-06, "epoch": 330.8888888888889, "percentage": 74.45, "elapsed_time": "3:22:14", "remaining_time": "1:09:24", "throughput": 687.55, "total_tokens": 8342864} {"current_steps": 29785, "total_steps": 40000, "loss": 0.0, "lr": 7.624754419034644e-06, "epoch": 330.94444444444446, "percentage": 74.46, "elapsed_time": "3:22:16", "remaining_time": "1:09:22", "throughput": 687.55, "total_tokens": 8344256} {"current_steps": 29790, "total_steps": 40000, "loss": 0.0, "lr": 7.6176969906036645e-06, "epoch": 331.0, "percentage": 74.48, "elapsed_time": "3:22:18", "remaining_time": "1:09:20", "throughput": 687.55, "total_tokens": 8345648} {"current_steps": 29795, "total_steps": 40000, "loss": 0.0, "lr": 7.610642242742242e-06, "epoch": 331.05555555555554, "percentage": 74.49, "elapsed_time": "3:22:20", "remaining_time": "1:09:18", "throughput": 687.52, "total_tokens": 8347040} {"current_steps": 29800, "total_steps": 40000, "loss": 0.0, "lr": 7.603590176538322e-06, "epoch": 331.1111111111111, "percentage": 74.5, "elapsed_time": "3:22:22", "remaining_time": "1:09:16", "throughput": 687.52, "total_tokens": 8348416} {"current_steps": 29800, "total_steps": 40000, "eval_loss": 0.38023608922958374, "epoch": 331.1111111111111, "percentage": 74.5, "elapsed_time": "3:22:24", "remaining_time": "1:09:16", "throughput": 687.45, "total_tokens": 8348416} {"current_steps": 29805, "total_steps": 40000, "loss": 0.0, "lr": 7.596540793079404e-06, "epoch": 331.1666666666667, "percentage": 74.51, "elapsed_time": "3:22:27", "remaining_time": "1:09:15", "throughput": 687.37, "total_tokens": 8349872} {"current_steps": 29810, "total_steps": 40000, "loss": 0.0, "lr": 7.5894940934526125e-06, "epoch": 331.22222222222223, "percentage": 74.52, "elapsed_time": "3:22:29", "remaining_time": "1:09:13", "throughput": 687.38, "total_tokens": 8351296} {"current_steps": 29815, "total_steps": 40000, "loss": 0.0, "lr": 7.582450078744621e-06, "epoch": 331.27777777777777, "percentage": 74.54, "elapsed_time": "3:22:31", "remaining_time": "1:09:11", "throughput": 687.38, "total_tokens": 8352688} {"current_steps": 29820, "total_steps": 40000, "loss": 0.0, "lr": 7.575408750041707e-06, "epoch": 331.3333333333333, "percentage": 74.55, "elapsed_time": "3:22:33", "remaining_time": "1:09:08", "throughput": 687.39, "total_tokens": 8354064} {"current_steps": 29825, "total_steps": 40000, "loss": 0.0, "lr": 7.568370108429732e-06, "epoch": 331.3888888888889, "percentage": 74.56, "elapsed_time": "3:22:35", "remaining_time": "1:09:06", "throughput": 687.39, "total_tokens": 8355504} {"current_steps": 29830, "total_steps": 40000, "loss": 0.0, "lr": 7.561334154994154e-06, "epoch": 331.44444444444446, "percentage": 74.58, "elapsed_time": "3:22:37", "remaining_time": "1:09:04", "throughput": 687.4, "total_tokens": 8356912} {"current_steps": 29835, "total_steps": 40000, "loss": 0.0, "lr": 7.55430089081999e-06, "epoch": 331.5, "percentage": 74.59, "elapsed_time": "3:22:39", "remaining_time": "1:09:02", "throughput": 687.4, "total_tokens": 8358288} {"current_steps": 29840, "total_steps": 40000, "loss": 0.0, "lr": 7.547270316991864e-06, "epoch": 331.55555555555554, "percentage": 74.6, "elapsed_time": "3:22:41", "remaining_time": "1:09:00", "throughput": 687.41, "total_tokens": 8359680} {"current_steps": 29845, "total_steps": 40000, "loss": 0.0, "lr": 7.5402424345939884e-06, "epoch": 331.6111111111111, "percentage": 74.61, "elapsed_time": "3:22:43", "remaining_time": "1:08:58", "throughput": 687.41, "total_tokens": 8361040} {"current_steps": 29850, "total_steps": 40000, "loss": 0.0, "lr": 7.533217244710133e-06, "epoch": 331.6666666666667, "percentage": 74.62, "elapsed_time": "3:22:45", "remaining_time": "1:08:56", "throughput": 687.42, "total_tokens": 8362448} {"current_steps": 29855, "total_steps": 40000, "loss": 0.0, "lr": 7.52619474842369e-06, "epoch": 331.72222222222223, "percentage": 74.64, "elapsed_time": "3:22:46", "remaining_time": "1:08:54", "throughput": 687.43, "total_tokens": 8363872} {"current_steps": 29860, "total_steps": 40000, "loss": 0.0, "lr": 7.519174946817597e-06, "epoch": 331.77777777777777, "percentage": 74.65, "elapsed_time": "3:22:48", "remaining_time": "1:08:52", "throughput": 687.43, "total_tokens": 8365264} {"current_steps": 29865, "total_steps": 40000, "loss": 0.0, "lr": 7.512157840974407e-06, "epoch": 331.8333333333333, "percentage": 74.66, "elapsed_time": "3:22:50", "remaining_time": "1:08:50", "throughput": 687.44, "total_tokens": 8366704} {"current_steps": 29870, "total_steps": 40000, "loss": 0.0, "lr": 7.5051434319762496e-06, "epoch": 331.8888888888889, "percentage": 74.67, "elapsed_time": "3:22:52", "remaining_time": "1:08:48", "throughput": 687.45, "total_tokens": 8368112} {"current_steps": 29875, "total_steps": 40000, "loss": 0.0, "lr": 7.498131720904822e-06, "epoch": 331.94444444444446, "percentage": 74.69, "elapsed_time": "3:22:54", "remaining_time": "1:08:46", "throughput": 687.45, "total_tokens": 8369536} {"current_steps": 29880, "total_steps": 40000, "loss": 0.0, "lr": 7.491122708841433e-06, "epoch": 332.0, "percentage": 74.7, "elapsed_time": "3:22:56", "remaining_time": "1:08:44", "throughput": 687.45, "total_tokens": 8370896} {"current_steps": 29885, "total_steps": 40000, "loss": 0.0, "lr": 7.4841163968669524e-06, "epoch": 332.05555555555554, "percentage": 74.71, "elapsed_time": "3:22:58", "remaining_time": "1:08:42", "throughput": 687.44, "total_tokens": 8372320} {"current_steps": 29890, "total_steps": 40000, "loss": 0.0, "lr": 7.4771127860618355e-06, "epoch": 332.1111111111111, "percentage": 74.72, "elapsed_time": "3:23:00", "remaining_time": "1:08:40", "throughput": 687.44, "total_tokens": 8373680} {"current_steps": 29895, "total_steps": 40000, "loss": 0.0, "lr": 7.470111877506139e-06, "epoch": 332.1666666666667, "percentage": 74.74, "elapsed_time": "3:23:02", "remaining_time": "1:08:38", "throughput": 687.45, "total_tokens": 8375072} {"current_steps": 29900, "total_steps": 40000, "loss": 0.0, "lr": 7.463113672279479e-06, "epoch": 332.22222222222223, "percentage": 74.75, "elapsed_time": "3:23:04", "remaining_time": "1:08:35", "throughput": 687.45, "total_tokens": 8376464} {"current_steps": 29905, "total_steps": 40000, "loss": 0.0, "lr": 7.456118171461071e-06, "epoch": 332.27777777777777, "percentage": 74.76, "elapsed_time": "3:23:06", "remaining_time": "1:08:33", "throughput": 687.46, "total_tokens": 8377856} {"current_steps": 29910, "total_steps": 40000, "loss": 0.0, "lr": 7.449125376129721e-06, "epoch": 332.3333333333333, "percentage": 74.78, "elapsed_time": "3:23:08", "remaining_time": "1:08:31", "throughput": 687.46, "total_tokens": 8379296} {"current_steps": 29915, "total_steps": 40000, "loss": 0.0, "lr": 7.442135287363788e-06, "epoch": 332.3888888888889, "percentage": 74.79, "elapsed_time": "3:23:10", "remaining_time": "1:08:29", "throughput": 687.47, "total_tokens": 8380672} {"current_steps": 29920, "total_steps": 40000, "loss": 0.0, "lr": 7.435147906241247e-06, "epoch": 332.44444444444446, "percentage": 74.8, "elapsed_time": "3:23:12", "remaining_time": "1:08:27", "throughput": 687.47, "total_tokens": 8382048} {"current_steps": 29925, "total_steps": 40000, "loss": 0.0, "lr": 7.428163233839624e-06, "epoch": 332.5, "percentage": 74.81, "elapsed_time": "3:23:14", "remaining_time": "1:08:25", "throughput": 687.48, "total_tokens": 8383440} {"current_steps": 29930, "total_steps": 40000, "loss": 0.0, "lr": 7.4211812712360525e-06, "epoch": 332.55555555555554, "percentage": 74.83, "elapsed_time": "3:23:16", "remaining_time": "1:08:23", "throughput": 687.48, "total_tokens": 8384848} {"current_steps": 29935, "total_steps": 40000, "loss": 0.0, "lr": 7.4142020195072464e-06, "epoch": 332.6111111111111, "percentage": 74.84, "elapsed_time": "3:23:18", "remaining_time": "1:08:21", "throughput": 687.49, "total_tokens": 8386256} {"current_steps": 29940, "total_steps": 40000, "loss": 0.0, "lr": 7.407225479729479e-06, "epoch": 332.6666666666667, "percentage": 74.85, "elapsed_time": "3:23:20", "remaining_time": "1:08:19", "throughput": 687.5, "total_tokens": 8387696} {"current_steps": 29945, "total_steps": 40000, "loss": 0.0, "lr": 7.400251652978632e-06, "epoch": 332.72222222222223, "percentage": 74.86, "elapsed_time": "3:23:22", "remaining_time": "1:08:17", "throughput": 687.5, "total_tokens": 8389088} {"current_steps": 29950, "total_steps": 40000, "loss": 0.0, "lr": 7.393280540330147e-06, "epoch": 332.77777777777777, "percentage": 74.88, "elapsed_time": "3:23:24", "remaining_time": "1:08:15", "throughput": 687.51, "total_tokens": 8390480} {"current_steps": 29955, "total_steps": 40000, "loss": 0.0, "lr": 7.386312142859069e-06, "epoch": 332.8333333333333, "percentage": 74.89, "elapsed_time": "3:23:26", "remaining_time": "1:08:13", "throughput": 687.51, "total_tokens": 8391888} {"current_steps": 29960, "total_steps": 40000, "loss": 0.0, "lr": 7.379346461640008e-06, "epoch": 332.8888888888889, "percentage": 74.9, "elapsed_time": "3:23:28", "remaining_time": "1:08:11", "throughput": 687.52, "total_tokens": 8393264} {"current_steps": 29965, "total_steps": 40000, "loss": 0.0, "lr": 7.372383497747149e-06, "epoch": 332.94444444444446, "percentage": 74.91, "elapsed_time": "3:23:30", "remaining_time": "1:08:09", "throughput": 687.52, "total_tokens": 8394640} {"current_steps": 29970, "total_steps": 40000, "loss": 0.0, "lr": 7.3654232522542775e-06, "epoch": 333.0, "percentage": 74.92, "elapsed_time": "3:23:32", "remaining_time": "1:08:07", "throughput": 687.52, "total_tokens": 8396048} {"current_steps": 29975, "total_steps": 40000, "loss": 0.0, "lr": 7.358465726234756e-06, "epoch": 333.05555555555554, "percentage": 74.94, "elapsed_time": "3:23:34", "remaining_time": "1:08:05", "throughput": 687.51, "total_tokens": 8397424} {"current_steps": 29980, "total_steps": 40000, "loss": 0.0, "lr": 7.351510920761512e-06, "epoch": 333.1111111111111, "percentage": 74.95, "elapsed_time": "3:23:36", "remaining_time": "1:08:02", "throughput": 687.51, "total_tokens": 8398816} {"current_steps": 29985, "total_steps": 40000, "loss": 0.0, "lr": 7.344558836907067e-06, "epoch": 333.1666666666667, "percentage": 74.96, "elapsed_time": "3:23:38", "remaining_time": "1:08:00", "throughput": 687.52, "total_tokens": 8400240} {"current_steps": 29990, "total_steps": 40000, "loss": 0.0, "lr": 7.3376094757435285e-06, "epoch": 333.22222222222223, "percentage": 74.98, "elapsed_time": "3:23:40", "remaining_time": "1:07:58", "throughput": 687.52, "total_tokens": 8401648} {"current_steps": 29995, "total_steps": 40000, "loss": 0.0, "lr": 7.330662838342561e-06, "epoch": 333.27777777777777, "percentage": 74.99, "elapsed_time": "3:23:42", "remaining_time": "1:07:56", "throughput": 687.53, "total_tokens": 8403040} {"current_steps": 30000, "total_steps": 40000, "loss": 0.0, "lr": 7.323718925775438e-06, "epoch": 333.3333333333333, "percentage": 75.0, "elapsed_time": "3:23:44", "remaining_time": "1:07:54", "throughput": 687.53, "total_tokens": 8404432} {"current_steps": 30000, "total_steps": 40000, "eval_loss": 0.3238731026649475, "epoch": 333.3333333333333, "percentage": 75.0, "elapsed_time": "3:23:45", "remaining_time": "1:07:55", "throughput": 687.46, "total_tokens": 8404432} {"current_steps": 30005, "total_steps": 40000, "loss": 0.0, "lr": 7.316777739112985e-06, "epoch": 333.3888888888889, "percentage": 75.01, "elapsed_time": "3:23:48", "remaining_time": "1:07:53", "throughput": 687.39, "total_tokens": 8405792} {"current_steps": 30010, "total_steps": 40000, "loss": 0.0, "lr": 7.309839279425626e-06, "epoch": 333.44444444444446, "percentage": 75.02, "elapsed_time": "3:23:50", "remaining_time": "1:07:51", "throughput": 687.39, "total_tokens": 8407200} {"current_steps": 30015, "total_steps": 40000, "loss": 0.0, "lr": 7.302903547783366e-06, "epoch": 333.5, "percentage": 75.04, "elapsed_time": "3:23:52", "remaining_time": "1:07:49", "throughput": 687.39, "total_tokens": 8408544} {"current_steps": 30020, "total_steps": 40000, "loss": 0.0, "lr": 7.2959705452557644e-06, "epoch": 333.55555555555554, "percentage": 75.05, "elapsed_time": "3:23:54", "remaining_time": "1:07:47", "throughput": 687.4, "total_tokens": 8409984} {"current_steps": 30025, "total_steps": 40000, "loss": 0.0, "lr": 7.289040272911996e-06, "epoch": 333.6111111111111, "percentage": 75.06, "elapsed_time": "3:23:56", "remaining_time": "1:07:45", "throughput": 687.4, "total_tokens": 8411376} {"current_steps": 30030, "total_steps": 40000, "loss": 0.0, "lr": 7.282112731820789e-06, "epoch": 333.6666666666667, "percentage": 75.08, "elapsed_time": "3:23:58", "remaining_time": "1:07:43", "throughput": 687.41, "total_tokens": 8412800} {"current_steps": 30035, "total_steps": 40000, "loss": 0.0, "lr": 7.275187923050447e-06, "epoch": 333.72222222222223, "percentage": 75.09, "elapsed_time": "3:24:00", "remaining_time": "1:07:41", "throughput": 687.41, "total_tokens": 8414176} {"current_steps": 30040, "total_steps": 40000, "loss": 0.0, "lr": 7.268265847668879e-06, "epoch": 333.77777777777777, "percentage": 75.1, "elapsed_time": "3:24:02", "remaining_time": "1:07:39", "throughput": 687.42, "total_tokens": 8415600} {"current_steps": 30045, "total_steps": 40000, "loss": 0.0, "lr": 7.261346506743538e-06, "epoch": 333.8333333333333, "percentage": 75.11, "elapsed_time": "3:24:04", "remaining_time": "1:07:36", "throughput": 687.43, "total_tokens": 8416976} {"current_steps": 30050, "total_steps": 40000, "loss": 0.0, "lr": 7.254429901341486e-06, "epoch": 333.8888888888889, "percentage": 75.12, "elapsed_time": "3:24:06", "remaining_time": "1:07:34", "throughput": 687.43, "total_tokens": 8418368} {"current_steps": 30055, "total_steps": 40000, "loss": 0.0, "lr": 7.247516032529356e-06, "epoch": 333.94444444444446, "percentage": 75.14, "elapsed_time": "3:24:08", "remaining_time": "1:07:32", "throughput": 687.44, "total_tokens": 8419776} {"current_steps": 30060, "total_steps": 40000, "loss": 0.0, "lr": 7.240604901373338e-06, "epoch": 334.0, "percentage": 75.15, "elapsed_time": "3:24:10", "remaining_time": "1:07:30", "throughput": 687.44, "total_tokens": 8421216} {"current_steps": 30065, "total_steps": 40000, "loss": 0.0, "lr": 7.233696508939223e-06, "epoch": 334.05555555555554, "percentage": 75.16, "elapsed_time": "3:24:12", "remaining_time": "1:07:28", "throughput": 687.43, "total_tokens": 8422656} {"current_steps": 30070, "total_steps": 40000, "loss": 0.0, "lr": 7.226790856292376e-06, "epoch": 334.1111111111111, "percentage": 75.17, "elapsed_time": "3:24:14", "remaining_time": "1:07:26", "throughput": 687.44, "total_tokens": 8424048} {"current_steps": 30075, "total_steps": 40000, "loss": 0.0, "lr": 7.219887944497727e-06, "epoch": 334.1666666666667, "percentage": 75.19, "elapsed_time": "3:24:16", "remaining_time": "1:07:24", "throughput": 687.44, "total_tokens": 8425440} {"current_steps": 30080, "total_steps": 40000, "loss": 0.0, "lr": 7.2129877746198e-06, "epoch": 334.22222222222223, "percentage": 75.2, "elapsed_time": "3:24:18", "remaining_time": "1:07:22", "throughput": 687.45, "total_tokens": 8426832} {"current_steps": 30085, "total_steps": 40000, "loss": 0.0, "lr": 7.20609034772268e-06, "epoch": 334.27777777777777, "percentage": 75.21, "elapsed_time": "3:24:20", "remaining_time": "1:07:20", "throughput": 687.45, "total_tokens": 8428272} {"current_steps": 30090, "total_steps": 40000, "loss": 0.0, "lr": 7.19919566487004e-06, "epoch": 334.3333333333333, "percentage": 75.22, "elapsed_time": "3:24:22", "remaining_time": "1:07:18", "throughput": 687.46, "total_tokens": 8429648} {"current_steps": 30095, "total_steps": 40000, "loss": 0.0, "lr": 7.192303727125132e-06, "epoch": 334.3888888888889, "percentage": 75.24, "elapsed_time": "3:24:24", "remaining_time": "1:07:16", "throughput": 687.46, "total_tokens": 8431056} {"current_steps": 30100, "total_steps": 40000, "loss": 0.0, "lr": 7.185414535550777e-06, "epoch": 334.44444444444446, "percentage": 75.25, "elapsed_time": "3:24:25", "remaining_time": "1:07:14", "throughput": 687.47, "total_tokens": 8432432} {"current_steps": 30105, "total_steps": 40000, "loss": 0.0, "lr": 7.178528091209363e-06, "epoch": 334.5, "percentage": 75.26, "elapsed_time": "3:24:27", "remaining_time": "1:07:12", "throughput": 687.47, "total_tokens": 8433792} {"current_steps": 30110, "total_steps": 40000, "loss": 0.0, "lr": 7.171644395162888e-06, "epoch": 334.55555555555554, "percentage": 75.28, "elapsed_time": "3:24:29", "remaining_time": "1:07:10", "throughput": 687.47, "total_tokens": 8435152} {"current_steps": 30115, "total_steps": 40000, "loss": 0.0, "lr": 7.164763448472881e-06, "epoch": 334.6111111111111, "percentage": 75.29, "elapsed_time": "3:24:31", "remaining_time": "1:07:08", "throughput": 687.47, "total_tokens": 8436528} {"current_steps": 30120, "total_steps": 40000, "loss": 0.0, "lr": 7.157885252200491e-06, "epoch": 334.6666666666667, "percentage": 75.3, "elapsed_time": "3:24:33", "remaining_time": "1:07:06", "throughput": 687.48, "total_tokens": 8437968} {"current_steps": 30125, "total_steps": 40000, "loss": 0.0, "lr": 7.151009807406403e-06, "epoch": 334.72222222222223, "percentage": 75.31, "elapsed_time": "3:24:35", "remaining_time": "1:07:03", "throughput": 687.49, "total_tokens": 8439328} {"current_steps": 30130, "total_steps": 40000, "loss": 0.0, "lr": 7.144137115150909e-06, "epoch": 334.77777777777777, "percentage": 75.33, "elapsed_time": "3:24:37", "remaining_time": "1:07:01", "throughput": 687.49, "total_tokens": 8440736} {"current_steps": 30135, "total_steps": 40000, "loss": 0.0, "lr": 7.1372671764938725e-06, "epoch": 334.8333333333333, "percentage": 75.34, "elapsed_time": "3:24:39", "remaining_time": "1:06:59", "throughput": 687.5, "total_tokens": 8442160} {"current_steps": 30140, "total_steps": 40000, "loss": 0.0, "lr": 7.130399992494705e-06, "epoch": 334.8888888888889, "percentage": 75.35, "elapsed_time": "3:24:41", "remaining_time": "1:06:57", "throughput": 687.51, "total_tokens": 8443584} {"current_steps": 30145, "total_steps": 40000, "loss": 0.0, "lr": 7.123535564212419e-06, "epoch": 334.94444444444446, "percentage": 75.36, "elapsed_time": "3:24:43", "remaining_time": "1:06:55", "throughput": 687.52, "total_tokens": 8445024} {"current_steps": 30150, "total_steps": 40000, "loss": 0.0, "lr": 7.116673892705611e-06, "epoch": 335.0, "percentage": 75.38, "elapsed_time": "3:24:45", "remaining_time": "1:06:53", "throughput": 687.51, "total_tokens": 8446416} {"current_steps": 30155, "total_steps": 40000, "loss": 0.0, "lr": 7.109814979032415e-06, "epoch": 335.05555555555554, "percentage": 75.39, "elapsed_time": "3:24:47", "remaining_time": "1:06:51", "throughput": 687.5, "total_tokens": 8447840} {"current_steps": 30160, "total_steps": 40000, "loss": 0.0, "lr": 7.102958824250577e-06, "epoch": 335.1111111111111, "percentage": 75.4, "elapsed_time": "3:24:49", "remaining_time": "1:06:49", "throughput": 687.5, "total_tokens": 8449184} {"current_steps": 30165, "total_steps": 40000, "loss": 0.0, "lr": 7.096105429417393e-06, "epoch": 335.1666666666667, "percentage": 75.41, "elapsed_time": "3:24:51", "remaining_time": "1:06:47", "throughput": 687.51, "total_tokens": 8450608} {"current_steps": 30170, "total_steps": 40000, "loss": 0.0, "lr": 7.0892547955897506e-06, "epoch": 335.22222222222223, "percentage": 75.42, "elapsed_time": "3:24:53", "remaining_time": "1:06:45", "throughput": 687.52, "total_tokens": 8452080} {"current_steps": 30175, "total_steps": 40000, "loss": 0.0, "lr": 7.0824069238241e-06, "epoch": 335.27777777777777, "percentage": 75.44, "elapsed_time": "3:24:55", "remaining_time": "1:06:43", "throughput": 687.53, "total_tokens": 8453504} {"current_steps": 30180, "total_steps": 40000, "loss": 0.0, "lr": 7.075561815176462e-06, "epoch": 335.3333333333333, "percentage": 75.45, "elapsed_time": "3:24:57", "remaining_time": "1:06:41", "throughput": 687.53, "total_tokens": 8454848} {"current_steps": 30185, "total_steps": 40000, "loss": 0.0, "lr": 7.068719470702445e-06, "epoch": 335.3888888888889, "percentage": 75.46, "elapsed_time": "3:24:59", "remaining_time": "1:06:39", "throughput": 687.54, "total_tokens": 8456272} {"current_steps": 30190, "total_steps": 40000, "loss": 0.0, "lr": 7.061879891457229e-06, "epoch": 335.44444444444446, "percentage": 75.48, "elapsed_time": "3:25:01", "remaining_time": "1:06:37", "throughput": 687.54, "total_tokens": 8457632} {"current_steps": 30195, "total_steps": 40000, "loss": 0.0, "lr": 7.0550430784955515e-06, "epoch": 335.5, "percentage": 75.49, "elapsed_time": "3:25:03", "remaining_time": "1:06:35", "throughput": 687.54, "total_tokens": 8459008} {"current_steps": 30200, "total_steps": 40000, "loss": 0.0, "lr": 7.048209032871752e-06, "epoch": 335.55555555555554, "percentage": 75.5, "elapsed_time": "3:25:05", "remaining_time": "1:06:33", "throughput": 687.55, "total_tokens": 8460384} {"current_steps": 30200, "total_steps": 40000, "eval_loss": 0.34168726205825806, "epoch": 335.55555555555554, "percentage": 75.5, "elapsed_time": "3:25:06", "remaining_time": "1:06:33", "throughput": 687.47, "total_tokens": 8460384} {"current_steps": 30205, "total_steps": 40000, "loss": 0.0, "lr": 7.0413777556397055e-06, "epoch": 335.6111111111111, "percentage": 75.51, "elapsed_time": "3:25:09", "remaining_time": "1:06:31", "throughput": 687.41, "total_tokens": 8461840} {"current_steps": 30210, "total_steps": 40000, "loss": 0.0, "lr": 7.0345492478528925e-06, "epoch": 335.6666666666667, "percentage": 75.52, "elapsed_time": "3:25:11", "remaining_time": "1:06:29", "throughput": 687.41, "total_tokens": 8463200} {"current_steps": 30215, "total_steps": 40000, "loss": 0.0, "lr": 7.02772351056436e-06, "epoch": 335.72222222222223, "percentage": 75.54, "elapsed_time": "3:25:13", "remaining_time": "1:06:27", "throughput": 687.41, "total_tokens": 8464576} {"current_steps": 30220, "total_steps": 40000, "loss": 0.0, "lr": 7.020900544826709e-06, "epoch": 335.77777777777777, "percentage": 75.55, "elapsed_time": "3:25:15", "remaining_time": "1:06:25", "throughput": 687.41, "total_tokens": 8465952} {"current_steps": 30225, "total_steps": 40000, "loss": 0.0, "lr": 7.014080351692134e-06, "epoch": 335.8333333333333, "percentage": 75.56, "elapsed_time": "3:25:17", "remaining_time": "1:06:23", "throughput": 687.42, "total_tokens": 8467360} {"current_steps": 30230, "total_steps": 40000, "loss": 0.0, "lr": 7.0072629322124024e-06, "epoch": 335.8888888888889, "percentage": 75.58, "elapsed_time": "3:25:19", "remaining_time": "1:06:21", "throughput": 687.43, "total_tokens": 8468768} {"current_steps": 30235, "total_steps": 40000, "loss": 0.0, "lr": 7.000448287438827e-06, "epoch": 335.94444444444446, "percentage": 75.59, "elapsed_time": "3:25:21", "remaining_time": "1:06:19", "throughput": 687.43, "total_tokens": 8470224} {"current_steps": 30240, "total_steps": 40000, "loss": 0.0, "lr": 6.993636418422331e-06, "epoch": 336.0, "percentage": 75.6, "elapsed_time": "3:25:23", "remaining_time": "1:06:17", "throughput": 687.43, "total_tokens": 8471600} {"current_steps": 30245, "total_steps": 40000, "loss": 0.0, "lr": 6.986827326213383e-06, "epoch": 336.05555555555554, "percentage": 75.61, "elapsed_time": "3:25:25", "remaining_time": "1:06:15", "throughput": 687.43, "total_tokens": 8473056} {"current_steps": 30250, "total_steps": 40000, "loss": 0.0, "lr": 6.9800210118620205e-06, "epoch": 336.1111111111111, "percentage": 75.62, "elapsed_time": "3:25:27", "remaining_time": "1:06:13", "throughput": 687.43, "total_tokens": 8474448} {"current_steps": 30255, "total_steps": 40000, "loss": 0.0, "lr": 6.973217476417876e-06, "epoch": 336.1666666666667, "percentage": 75.64, "elapsed_time": "3:25:29", "remaining_time": "1:06:11", "throughput": 687.44, "total_tokens": 8475856} {"current_steps": 30260, "total_steps": 40000, "loss": 0.0, "lr": 6.96641672093013e-06, "epoch": 336.22222222222223, "percentage": 75.65, "elapsed_time": "3:25:31", "remaining_time": "1:06:09", "throughput": 687.44, "total_tokens": 8477232} {"current_steps": 30265, "total_steps": 40000, "loss": 0.0, "lr": 6.95961874644755e-06, "epoch": 336.27777777777777, "percentage": 75.66, "elapsed_time": "3:25:33", "remaining_time": "1:06:07", "throughput": 687.44, "total_tokens": 8478608} {"current_steps": 30270, "total_steps": 40000, "loss": 0.0, "lr": 6.952823554018476e-06, "epoch": 336.3333333333333, "percentage": 75.67, "elapsed_time": "3:25:35", "remaining_time": "1:06:05", "throughput": 687.45, "total_tokens": 8480064} {"current_steps": 30275, "total_steps": 40000, "loss": 0.0, "lr": 6.946031144690798e-06, "epoch": 336.3888888888889, "percentage": 75.69, "elapsed_time": "3:25:37", "remaining_time": "1:06:03", "throughput": 687.46, "total_tokens": 8481472} {"current_steps": 30280, "total_steps": 40000, "loss": 0.0, "lr": 6.939241519512005e-06, "epoch": 336.44444444444446, "percentage": 75.7, "elapsed_time": "3:25:39", "remaining_time": "1:06:00", "throughput": 687.46, "total_tokens": 8482848} {"current_steps": 30285, "total_steps": 40000, "loss": 0.0, "lr": 6.932454679529129e-06, "epoch": 336.5, "percentage": 75.71, "elapsed_time": "3:25:41", "remaining_time": "1:05:58", "throughput": 687.47, "total_tokens": 8484272} {"current_steps": 30290, "total_steps": 40000, "loss": 0.0, "lr": 6.925670625788791e-06, "epoch": 336.55555555555554, "percentage": 75.72, "elapsed_time": "3:25:43", "remaining_time": "1:05:56", "throughput": 687.48, "total_tokens": 8485680} {"current_steps": 30295, "total_steps": 40000, "loss": 0.0, "lr": 6.918889359337186e-06, "epoch": 336.6111111111111, "percentage": 75.74, "elapsed_time": "3:25:45", "remaining_time": "1:05:54", "throughput": 687.48, "total_tokens": 8487088} {"current_steps": 30300, "total_steps": 40000, "loss": 0.0, "lr": 6.912110881220058e-06, "epoch": 336.6666666666667, "percentage": 75.75, "elapsed_time": "3:25:47", "remaining_time": "1:05:52", "throughput": 687.48, "total_tokens": 8488448} {"current_steps": 30305, "total_steps": 40000, "loss": 0.0, "lr": 6.905335192482735e-06, "epoch": 336.72222222222223, "percentage": 75.76, "elapsed_time": "3:25:49", "remaining_time": "1:05:50", "throughput": 687.49, "total_tokens": 8489856} {"current_steps": 30310, "total_steps": 40000, "loss": 0.0, "lr": 6.8985622941701275e-06, "epoch": 336.77777777777777, "percentage": 75.78, "elapsed_time": "3:25:51", "remaining_time": "1:05:48", "throughput": 687.49, "total_tokens": 8491248} {"current_steps": 30315, "total_steps": 40000, "loss": 0.0, "lr": 6.89179218732669e-06, "epoch": 336.8333333333333, "percentage": 75.79, "elapsed_time": "3:25:52", "remaining_time": "1:05:46", "throughput": 687.49, "total_tokens": 8492592} {"current_steps": 30320, "total_steps": 40000, "loss": 0.0, "lr": 6.8850248729964595e-06, "epoch": 336.8888888888889, "percentage": 75.8, "elapsed_time": "3:25:54", "remaining_time": "1:05:44", "throughput": 687.5, "total_tokens": 8493968} {"current_steps": 30325, "total_steps": 40000, "loss": 0.0, "lr": 6.8782603522230314e-06, "epoch": 336.94444444444446, "percentage": 75.81, "elapsed_time": "3:25:56", "remaining_time": "1:05:42", "throughput": 687.5, "total_tokens": 8495376} {"current_steps": 30330, "total_steps": 40000, "loss": 0.0, "lr": 6.871498626049591e-06, "epoch": 337.0, "percentage": 75.83, "elapsed_time": "3:25:58", "remaining_time": "1:05:40", "throughput": 687.5, "total_tokens": 8496752} {"current_steps": 30335, "total_steps": 40000, "loss": 0.0, "lr": 6.8647396955188875e-06, "epoch": 337.05555555555554, "percentage": 75.84, "elapsed_time": "3:26:01", "remaining_time": "1:05:38", "throughput": 687.49, "total_tokens": 8498160} {"current_steps": 30340, "total_steps": 40000, "loss": 0.0, "lr": 6.857983561673218e-06, "epoch": 337.1111111111111, "percentage": 75.85, "elapsed_time": "3:26:03", "remaining_time": "1:05:36", "throughput": 687.49, "total_tokens": 8499568} {"current_steps": 30345, "total_steps": 40000, "loss": 0.0, "lr": 6.851230225554467e-06, "epoch": 337.1666666666667, "percentage": 75.86, "elapsed_time": "3:26:05", "remaining_time": "1:05:34", "throughput": 687.5, "total_tokens": 8500992} {"current_steps": 30350, "total_steps": 40000, "loss": 0.0, "lr": 6.8444796882040946e-06, "epoch": 337.22222222222223, "percentage": 75.88, "elapsed_time": "3:26:06", "remaining_time": "1:05:32", "throughput": 687.51, "total_tokens": 8502416} {"current_steps": 30355, "total_steps": 40000, "loss": 0.0, "lr": 6.837731950663106e-06, "epoch": 337.27777777777777, "percentage": 75.89, "elapsed_time": "3:26:08", "remaining_time": "1:05:30", "throughput": 687.52, "total_tokens": 8503840} {"current_steps": 30360, "total_steps": 40000, "loss": 0.0, "lr": 6.830987013972098e-06, "epoch": 337.3333333333333, "percentage": 75.9, "elapsed_time": "3:26:10", "remaining_time": "1:05:28", "throughput": 687.52, "total_tokens": 8505232} {"current_steps": 30365, "total_steps": 40000, "loss": 0.0, "lr": 6.82424487917121e-06, "epoch": 337.3888888888889, "percentage": 75.91, "elapsed_time": "3:26:12", "remaining_time": "1:05:25", "throughput": 687.53, "total_tokens": 8506640} {"current_steps": 30370, "total_steps": 40000, "loss": 0.0, "lr": 6.8175055473001735e-06, "epoch": 337.44444444444446, "percentage": 75.92, "elapsed_time": "3:26:14", "remaining_time": "1:05:23", "throughput": 687.53, "total_tokens": 8508048} {"current_steps": 30375, "total_steps": 40000, "loss": 0.0, "lr": 6.8107690193982855e-06, "epoch": 337.5, "percentage": 75.94, "elapsed_time": "3:26:16", "remaining_time": "1:05:21", "throughput": 687.53, "total_tokens": 8509392} {"current_steps": 30380, "total_steps": 40000, "loss": 0.0, "lr": 6.804035296504385e-06, "epoch": 337.55555555555554, "percentage": 75.95, "elapsed_time": "3:26:18", "remaining_time": "1:05:19", "throughput": 687.54, "total_tokens": 8510784} {"current_steps": 30385, "total_steps": 40000, "loss": 0.0, "lr": 6.797304379656916e-06, "epoch": 337.6111111111111, "percentage": 75.96, "elapsed_time": "3:26:20", "remaining_time": "1:05:17", "throughput": 687.54, "total_tokens": 8512208} {"current_steps": 30390, "total_steps": 40000, "loss": 0.0, "lr": 6.790576269893861e-06, "epoch": 337.6666666666667, "percentage": 75.98, "elapsed_time": "3:26:22", "remaining_time": "1:05:15", "throughput": 687.55, "total_tokens": 8513600} {"current_steps": 30395, "total_steps": 40000, "loss": 0.0, "lr": 6.783850968252772e-06, "epoch": 337.72222222222223, "percentage": 75.99, "elapsed_time": "3:26:24", "remaining_time": "1:05:13", "throughput": 687.55, "total_tokens": 8514992} {"current_steps": 30400, "total_steps": 40000, "loss": 0.0, "lr": 6.777128475770789e-06, "epoch": 337.77777777777777, "percentage": 76.0, "elapsed_time": "3:26:26", "remaining_time": "1:05:11", "throughput": 687.56, "total_tokens": 8516432} {"current_steps": 30400, "total_steps": 40000, "eval_loss": 0.3461856544017792, "epoch": 337.77777777777777, "percentage": 76.0, "elapsed_time": "3:26:27", "remaining_time": "1:05:11", "throughput": 687.49, "total_tokens": 8516432} {"current_steps": 30405, "total_steps": 40000, "loss": 0.0, "lr": 6.77040879348459e-06, "epoch": 337.8333333333333, "percentage": 76.01, "elapsed_time": "3:26:31", "remaining_time": "1:05:10", "throughput": 687.42, "total_tokens": 8517840} {"current_steps": 30410, "total_steps": 40000, "loss": 0.0, "lr": 6.763691922430443e-06, "epoch": 337.8888888888889, "percentage": 76.02, "elapsed_time": "3:26:33", "remaining_time": "1:05:08", "throughput": 687.42, "total_tokens": 8519248} {"current_steps": 30415, "total_steps": 40000, "loss": 0.0, "lr": 6.756977863644178e-06, "epoch": 337.94444444444446, "percentage": 76.04, "elapsed_time": "3:26:35", "remaining_time": "1:05:06", "throughput": 687.42, "total_tokens": 8520640} {"current_steps": 30420, "total_steps": 40000, "loss": 0.0, "lr": 6.7502666181611804e-06, "epoch": 338.0, "percentage": 76.05, "elapsed_time": "3:26:37", "remaining_time": "1:05:04", "throughput": 687.42, "total_tokens": 8522032} {"current_steps": 30425, "total_steps": 40000, "loss": 0.0, "lr": 6.743558187016405e-06, "epoch": 338.05555555555554, "percentage": 76.06, "elapsed_time": "3:26:39", "remaining_time": "1:05:02", "throughput": 687.41, "total_tokens": 8523456} {"current_steps": 30430, "total_steps": 40000, "loss": 0.0, "lr": 6.7368525712443925e-06, "epoch": 338.1111111111111, "percentage": 76.08, "elapsed_time": "3:26:41", "remaining_time": "1:05:00", "throughput": 687.42, "total_tokens": 8524864} {"current_steps": 30435, "total_steps": 40000, "loss": 0.0, "lr": 6.7301497718792155e-06, "epoch": 338.1666666666667, "percentage": 76.09, "elapsed_time": "3:26:43", "remaining_time": "1:04:58", "throughput": 687.43, "total_tokens": 8526288} {"current_steps": 30440, "total_steps": 40000, "loss": 0.0, "lr": 6.723449789954544e-06, "epoch": 338.22222222222223, "percentage": 76.1, "elapsed_time": "3:26:45", "remaining_time": "1:04:55", "throughput": 687.43, "total_tokens": 8527664} {"current_steps": 30445, "total_steps": 40000, "loss": 0.0, "lr": 6.716752626503586e-06, "epoch": 338.27777777777777, "percentage": 76.11, "elapsed_time": "3:26:47", "remaining_time": "1:04:53", "throughput": 687.44, "total_tokens": 8529088} {"current_steps": 30450, "total_steps": 40000, "loss": 0.0, "lr": 6.710058282559131e-06, "epoch": 338.3333333333333, "percentage": 76.12, "elapsed_time": "3:26:49", "remaining_time": "1:04:51", "throughput": 687.44, "total_tokens": 8530480} {"current_steps": 30455, "total_steps": 40000, "loss": 0.0, "lr": 6.703366759153545e-06, "epoch": 338.3888888888889, "percentage": 76.14, "elapsed_time": "3:26:51", "remaining_time": "1:04:49", "throughput": 687.44, "total_tokens": 8531840} {"current_steps": 30460, "total_steps": 40000, "loss": 0.0, "lr": 6.6966780573187335e-06, "epoch": 338.44444444444446, "percentage": 76.15, "elapsed_time": "3:26:52", "remaining_time": "1:04:47", "throughput": 687.44, "total_tokens": 8533216} {"current_steps": 30465, "total_steps": 40000, "loss": 0.0, "lr": 6.689992178086174e-06, "epoch": 338.5, "percentage": 76.16, "elapsed_time": "3:26:54", "remaining_time": "1:04:45", "throughput": 687.45, "total_tokens": 8534640} {"current_steps": 30470, "total_steps": 40000, "loss": 0.0, "lr": 6.683309122486925e-06, "epoch": 338.55555555555554, "percentage": 76.17, "elapsed_time": "3:26:56", "remaining_time": "1:04:43", "throughput": 687.45, "total_tokens": 8535968} {"current_steps": 30475, "total_steps": 40000, "loss": 0.0, "lr": 6.676628891551584e-06, "epoch": 338.6111111111111, "percentage": 76.19, "elapsed_time": "3:26:58", "remaining_time": "1:04:41", "throughput": 687.46, "total_tokens": 8537360} {"current_steps": 30480, "total_steps": 40000, "loss": 0.0, "lr": 6.6699514863103385e-06, "epoch": 338.6666666666667, "percentage": 76.2, "elapsed_time": "3:27:00", "remaining_time": "1:04:39", "throughput": 687.46, "total_tokens": 8538752} {"current_steps": 30485, "total_steps": 40000, "loss": 0.0, "lr": 6.663276907792921e-06, "epoch": 338.72222222222223, "percentage": 76.21, "elapsed_time": "3:27:02", "remaining_time": "1:04:37", "throughput": 687.47, "total_tokens": 8540176} {"current_steps": 30490, "total_steps": 40000, "loss": 0.0, "lr": 6.656605157028634e-06, "epoch": 338.77777777777777, "percentage": 76.22, "elapsed_time": "3:27:04", "remaining_time": "1:04:35", "throughput": 687.48, "total_tokens": 8541648} {"current_steps": 30495, "total_steps": 40000, "loss": 0.0, "lr": 6.649936235046358e-06, "epoch": 338.8333333333333, "percentage": 76.24, "elapsed_time": "3:27:06", "remaining_time": "1:04:33", "throughput": 687.48, "total_tokens": 8543040} {"current_steps": 30500, "total_steps": 40000, "loss": 0.0, "lr": 6.643270142874508e-06, "epoch": 338.8888888888889, "percentage": 76.25, "elapsed_time": "3:27:08", "remaining_time": "1:04:31", "throughput": 687.49, "total_tokens": 8544496} {"current_steps": 30505, "total_steps": 40000, "loss": 0.0, "lr": 6.636606881541094e-06, "epoch": 338.94444444444446, "percentage": 76.26, "elapsed_time": "3:27:10", "remaining_time": "1:04:29", "throughput": 687.5, "total_tokens": 8545888} {"current_steps": 30510, "total_steps": 40000, "loss": 0.0, "lr": 6.629946452073662e-06, "epoch": 339.0, "percentage": 76.28, "elapsed_time": "3:27:12", "remaining_time": "1:04:27", "throughput": 687.5, "total_tokens": 8547280} {"current_steps": 30515, "total_steps": 40000, "loss": 0.0, "lr": 6.6232888554993375e-06, "epoch": 339.05555555555554, "percentage": 76.29, "elapsed_time": "3:27:14", "remaining_time": "1:04:25", "throughput": 687.49, "total_tokens": 8548672} {"current_steps": 30520, "total_steps": 40000, "loss": 0.0, "lr": 6.616634092844817e-06, "epoch": 339.1111111111111, "percentage": 76.3, "elapsed_time": "3:27:16", "remaining_time": "1:04:23", "throughput": 687.49, "total_tokens": 8550080} {"current_steps": 30525, "total_steps": 40000, "loss": 0.0, "lr": 6.609982165136331e-06, "epoch": 339.1666666666667, "percentage": 76.31, "elapsed_time": "3:27:18", "remaining_time": "1:04:20", "throughput": 687.49, "total_tokens": 8551456} {"current_steps": 30530, "total_steps": 40000, "loss": 0.0, "lr": 6.603333073399706e-06, "epoch": 339.22222222222223, "percentage": 76.33, "elapsed_time": "3:27:20", "remaining_time": "1:04:18", "throughput": 687.5, "total_tokens": 8552880} {"current_steps": 30535, "total_steps": 40000, "loss": 0.0, "lr": 6.596686818660308e-06, "epoch": 339.27777777777777, "percentage": 76.34, "elapsed_time": "3:27:22", "remaining_time": "1:04:16", "throughput": 687.5, "total_tokens": 8554240} {"current_steps": 30540, "total_steps": 40000, "loss": 0.0, "lr": 6.590043401943066e-06, "epoch": 339.3333333333333, "percentage": 76.35, "elapsed_time": "3:27:24", "remaining_time": "1:04:14", "throughput": 687.51, "total_tokens": 8555664} {"current_steps": 30545, "total_steps": 40000, "loss": 0.0, "lr": 6.583402824272494e-06, "epoch": 339.3888888888889, "percentage": 76.36, "elapsed_time": "3:27:26", "remaining_time": "1:04:12", "throughput": 687.51, "total_tokens": 8557056} {"current_steps": 30550, "total_steps": 40000, "loss": 0.0, "lr": 6.576765086672634e-06, "epoch": 339.44444444444446, "percentage": 76.38, "elapsed_time": "3:27:28", "remaining_time": "1:04:10", "throughput": 687.52, "total_tokens": 8558448} {"current_steps": 30555, "total_steps": 40000, "loss": 0.0, "lr": 6.57013019016712e-06, "epoch": 339.5, "percentage": 76.39, "elapsed_time": "3:27:30", "remaining_time": "1:04:08", "throughput": 687.53, "total_tokens": 8559920} {"current_steps": 30560, "total_steps": 40000, "loss": 0.0, "lr": 6.563498135779142e-06, "epoch": 339.55555555555554, "percentage": 76.4, "elapsed_time": "3:27:32", "remaining_time": "1:04:06", "throughput": 687.54, "total_tokens": 8561328} {"current_steps": 30565, "total_steps": 40000, "loss": 0.0, "lr": 6.556868924531431e-06, "epoch": 339.6111111111111, "percentage": 76.41, "elapsed_time": "3:27:34", "remaining_time": "1:04:04", "throughput": 687.54, "total_tokens": 8562704} {"current_steps": 30570, "total_steps": 40000, "loss": 0.0, "lr": 6.550242557446304e-06, "epoch": 339.6666666666667, "percentage": 76.42, "elapsed_time": "3:27:36", "remaining_time": "1:04:02", "throughput": 687.54, "total_tokens": 8564080} {"current_steps": 30575, "total_steps": 40000, "loss": 0.0, "lr": 6.543619035545634e-06, "epoch": 339.72222222222223, "percentage": 76.44, "elapsed_time": "3:27:38", "remaining_time": "1:04:00", "throughput": 687.55, "total_tokens": 8565472} {"current_steps": 30580, "total_steps": 40000, "loss": 0.0, "lr": 6.53699835985084e-06, "epoch": 339.77777777777777, "percentage": 76.45, "elapsed_time": "3:27:39", "remaining_time": "1:03:58", "throughput": 687.55, "total_tokens": 8566896} {"current_steps": 30585, "total_steps": 40000, "loss": 0.0, "lr": 6.530380531382927e-06, "epoch": 339.8333333333333, "percentage": 76.46, "elapsed_time": "3:27:41", "remaining_time": "1:03:56", "throughput": 687.56, "total_tokens": 8568272} {"current_steps": 30590, "total_steps": 40000, "loss": 0.0, "lr": 6.523765551162433e-06, "epoch": 339.8888888888889, "percentage": 76.48, "elapsed_time": "3:27:43", "remaining_time": "1:03:54", "throughput": 687.56, "total_tokens": 8569664} {"current_steps": 30595, "total_steps": 40000, "loss": 0.0, "lr": 6.517153420209476e-06, "epoch": 339.94444444444446, "percentage": 76.49, "elapsed_time": "3:27:45", "remaining_time": "1:03:52", "throughput": 687.57, "total_tokens": 8571056} {"current_steps": 30600, "total_steps": 40000, "loss": 0.0, "lr": 6.510544139543739e-06, "epoch": 340.0, "percentage": 76.5, "elapsed_time": "3:27:47", "remaining_time": "1:03:50", "throughput": 687.57, "total_tokens": 8572496} {"current_steps": 30600, "total_steps": 40000, "eval_loss": 0.35483676195144653, "epoch": 340.0, "percentage": 76.5, "elapsed_time": "3:27:49", "remaining_time": "1:03:50", "throughput": 687.49, "total_tokens": 8572496} {"current_steps": 30605, "total_steps": 40000, "loss": 0.0, "lr": 6.503937710184452e-06, "epoch": 340.05555555555554, "percentage": 76.51, "elapsed_time": "3:27:53", "remaining_time": "1:03:48", "throughput": 687.39, "total_tokens": 8573872} {"current_steps": 30610, "total_steps": 40000, "loss": 0.0, "lr": 6.4973341331503954e-06, "epoch": 340.1111111111111, "percentage": 76.53, "elapsed_time": "3:27:55", "remaining_time": "1:03:46", "throughput": 687.4, "total_tokens": 8575280} {"current_steps": 30615, "total_steps": 40000, "loss": 0.0, "lr": 6.490733409459942e-06, "epoch": 340.1666666666667, "percentage": 76.54, "elapsed_time": "3:27:56", "remaining_time": "1:03:44", "throughput": 687.4, "total_tokens": 8576672} {"current_steps": 30620, "total_steps": 40000, "loss": 0.0, "lr": 6.484135540130995e-06, "epoch": 340.22222222222223, "percentage": 76.55, "elapsed_time": "3:27:58", "remaining_time": "1:03:42", "throughput": 687.41, "total_tokens": 8578112} {"current_steps": 30625, "total_steps": 40000, "loss": 0.0, "lr": 6.4775405261810364e-06, "epoch": 340.27777777777777, "percentage": 76.56, "elapsed_time": "3:28:00", "remaining_time": "1:03:40", "throughput": 687.41, "total_tokens": 8579520} {"current_steps": 30630, "total_steps": 40000, "loss": 0.0, "lr": 6.470948368627092e-06, "epoch": 340.3333333333333, "percentage": 76.58, "elapsed_time": "3:28:02", "remaining_time": "1:03:38", "throughput": 687.42, "total_tokens": 8580912} {"current_steps": 30635, "total_steps": 40000, "loss": 0.0, "lr": 6.464359068485756e-06, "epoch": 340.3888888888889, "percentage": 76.59, "elapsed_time": "3:28:04", "remaining_time": "1:03:36", "throughput": 687.42, "total_tokens": 8582304} {"current_steps": 30640, "total_steps": 40000, "loss": 0.0, "lr": 6.457772626773195e-06, "epoch": 340.44444444444446, "percentage": 76.6, "elapsed_time": "3:28:06", "remaining_time": "1:03:34", "throughput": 687.43, "total_tokens": 8583744} {"current_steps": 30645, "total_steps": 40000, "loss": 0.0, "lr": 6.451189044505104e-06, "epoch": 340.5, "percentage": 76.61, "elapsed_time": "3:28:08", "remaining_time": "1:03:32", "throughput": 687.43, "total_tokens": 8585120} {"current_steps": 30650, "total_steps": 40000, "loss": 0.0, "lr": 6.44460832269676e-06, "epoch": 340.55555555555554, "percentage": 76.62, "elapsed_time": "3:28:10", "remaining_time": "1:03:30", "throughput": 687.44, "total_tokens": 8586560} {"current_steps": 30655, "total_steps": 40000, "loss": 0.0, "lr": 6.438030462363001e-06, "epoch": 340.6111111111111, "percentage": 76.64, "elapsed_time": "3:28:12", "remaining_time": "1:03:28", "throughput": 687.45, "total_tokens": 8587936} {"current_steps": 30660, "total_steps": 40000, "loss": 0.0, "lr": 6.431455464518205e-06, "epoch": 340.6666666666667, "percentage": 76.65, "elapsed_time": "3:28:14", "remaining_time": "1:03:26", "throughput": 687.45, "total_tokens": 8589264} {"current_steps": 30665, "total_steps": 40000, "loss": 0.0, "lr": 6.424883330176326e-06, "epoch": 340.72222222222223, "percentage": 76.66, "elapsed_time": "3:28:16", "remaining_time": "1:03:24", "throughput": 687.45, "total_tokens": 8590688} {"current_steps": 30670, "total_steps": 40000, "loss": 0.0, "lr": 6.418314060350864e-06, "epoch": 340.77777777777777, "percentage": 76.68, "elapsed_time": "3:28:18", "remaining_time": "1:03:22", "throughput": 687.46, "total_tokens": 8592080} {"current_steps": 30675, "total_steps": 40000, "loss": 0.0, "lr": 6.4117476560548895e-06, "epoch": 340.8333333333333, "percentage": 76.69, "elapsed_time": "3:28:20", "remaining_time": "1:03:20", "throughput": 687.46, "total_tokens": 8593456} {"current_steps": 30680, "total_steps": 40000, "loss": 0.0, "lr": 6.405184118301016e-06, "epoch": 340.8888888888889, "percentage": 76.7, "elapsed_time": "3:28:22", "remaining_time": "1:03:17", "throughput": 687.47, "total_tokens": 8594896} {"current_steps": 30685, "total_steps": 40000, "loss": 0.0, "lr": 6.398623448101434e-06, "epoch": 340.94444444444446, "percentage": 76.71, "elapsed_time": "3:28:24", "remaining_time": "1:03:15", "throughput": 687.47, "total_tokens": 8596256} {"current_steps": 30690, "total_steps": 40000, "loss": 0.0, "lr": 6.392065646467871e-06, "epoch": 341.0, "percentage": 76.72, "elapsed_time": "3:28:26", "remaining_time": "1:03:13", "throughput": 687.47, "total_tokens": 8597664} {"current_steps": 30695, "total_steps": 40000, "loss": 0.0, "lr": 6.385510714411632e-06, "epoch": 341.05555555555554, "percentage": 76.74, "elapsed_time": "3:28:28", "remaining_time": "1:03:11", "throughput": 687.46, "total_tokens": 8599088} {"current_steps": 30700, "total_steps": 40000, "loss": 0.0, "lr": 6.378958652943559e-06, "epoch": 341.1111111111111, "percentage": 76.75, "elapsed_time": "3:28:30", "remaining_time": "1:03:09", "throughput": 687.46, "total_tokens": 8600496} {"current_steps": 30705, "total_steps": 40000, "loss": 0.0, "lr": 6.3724094630740776e-06, "epoch": 341.1666666666667, "percentage": 76.76, "elapsed_time": "3:28:32", "remaining_time": "1:03:07", "throughput": 687.47, "total_tokens": 8601904} {"current_steps": 30710, "total_steps": 40000, "loss": 0.0, "lr": 6.365863145813136e-06, "epoch": 341.22222222222223, "percentage": 76.78, "elapsed_time": "3:28:34", "remaining_time": "1:03:05", "throughput": 687.48, "total_tokens": 8603328} {"current_steps": 30715, "total_steps": 40000, "loss": 0.0, "lr": 6.359319702170269e-06, "epoch": 341.27777777777777, "percentage": 76.79, "elapsed_time": "3:28:36", "remaining_time": "1:03:03", "throughput": 687.48, "total_tokens": 8604720} {"current_steps": 30720, "total_steps": 40000, "loss": 0.0, "lr": 6.352779133154566e-06, "epoch": 341.3333333333333, "percentage": 76.8, "elapsed_time": "3:28:38", "remaining_time": "1:03:01", "throughput": 687.49, "total_tokens": 8606144} {"current_steps": 30725, "total_steps": 40000, "loss": 0.0, "lr": 6.346241439774648e-06, "epoch": 341.3888888888889, "percentage": 76.81, "elapsed_time": "3:28:40", "remaining_time": "1:02:59", "throughput": 687.5, "total_tokens": 8607568} {"current_steps": 30730, "total_steps": 40000, "loss": 0.0, "lr": 6.339706623038716e-06, "epoch": 341.44444444444446, "percentage": 76.83, "elapsed_time": "3:28:42", "remaining_time": "1:02:57", "throughput": 687.5, "total_tokens": 8608960} {"current_steps": 30735, "total_steps": 40000, "loss": 0.0, "lr": 6.333174683954532e-06, "epoch": 341.5, "percentage": 76.84, "elapsed_time": "3:28:44", "remaining_time": "1:02:55", "throughput": 687.5, "total_tokens": 8610320} {"current_steps": 30740, "total_steps": 40000, "loss": 0.0, "lr": 6.326645623529387e-06, "epoch": 341.55555555555554, "percentage": 76.85, "elapsed_time": "3:28:45", "remaining_time": "1:02:53", "throughput": 687.51, "total_tokens": 8611696} {"current_steps": 30745, "total_steps": 40000, "loss": 0.0, "lr": 6.320119442770156e-06, "epoch": 341.6111111111111, "percentage": 76.86, "elapsed_time": "3:28:47", "remaining_time": "1:02:51", "throughput": 687.51, "total_tokens": 8613136} {"current_steps": 30750, "total_steps": 40000, "loss": 0.0, "lr": 6.313596142683254e-06, "epoch": 341.6666666666667, "percentage": 76.88, "elapsed_time": "3:28:49", "remaining_time": "1:02:49", "throughput": 687.52, "total_tokens": 8614544} {"current_steps": 30755, "total_steps": 40000, "loss": 0.0, "lr": 6.307075724274647e-06, "epoch": 341.72222222222223, "percentage": 76.89, "elapsed_time": "3:28:51", "remaining_time": "1:02:47", "throughput": 687.52, "total_tokens": 8615920} {"current_steps": 30760, "total_steps": 40000, "loss": 0.0, "lr": 6.300558188549882e-06, "epoch": 341.77777777777777, "percentage": 76.9, "elapsed_time": "3:28:53", "remaining_time": "1:02:45", "throughput": 687.53, "total_tokens": 8617312} {"current_steps": 30765, "total_steps": 40000, "loss": 0.0, "lr": 6.29404353651403e-06, "epoch": 341.8333333333333, "percentage": 76.91, "elapsed_time": "3:28:55", "remaining_time": "1:02:42", "throughput": 687.53, "total_tokens": 8618688} {"current_steps": 30770, "total_steps": 40000, "loss": 0.0, "lr": 6.287531769171737e-06, "epoch": 341.8888888888889, "percentage": 76.92, "elapsed_time": "3:28:57", "remaining_time": "1:02:40", "throughput": 687.53, "total_tokens": 8620064} {"current_steps": 30775, "total_steps": 40000, "loss": 0.0, "lr": 6.2810228875272045e-06, "epoch": 341.94444444444446, "percentage": 76.94, "elapsed_time": "3:28:59", "remaining_time": "1:02:38", "throughput": 687.54, "total_tokens": 8621424} {"current_steps": 30780, "total_steps": 40000, "loss": 0.0, "lr": 6.274516892584179e-06, "epoch": 342.0, "percentage": 76.95, "elapsed_time": "3:29:01", "remaining_time": "1:02:36", "throughput": 687.54, "total_tokens": 8622864} {"current_steps": 30785, "total_steps": 40000, "loss": 0.0, "lr": 6.268013785345969e-06, "epoch": 342.05555555555554, "percentage": 76.96, "elapsed_time": "3:29:03", "remaining_time": "1:02:34", "throughput": 687.53, "total_tokens": 8624288} {"current_steps": 30790, "total_steps": 40000, "loss": 0.0, "lr": 6.26151356681543e-06, "epoch": 342.1111111111111, "percentage": 76.98, "elapsed_time": "3:29:05", "remaining_time": "1:02:32", "throughput": 687.53, "total_tokens": 8625680} {"current_steps": 30795, "total_steps": 40000, "loss": 0.0, "lr": 6.255016237994981e-06, "epoch": 342.1666666666667, "percentage": 76.99, "elapsed_time": "3:29:07", "remaining_time": "1:02:30", "throughput": 687.54, "total_tokens": 8627056} {"current_steps": 30800, "total_steps": 40000, "loss": 0.0, "lr": 6.248521799886603e-06, "epoch": 342.22222222222223, "percentage": 77.0, "elapsed_time": "3:29:09", "remaining_time": "1:02:28", "throughput": 687.53, "total_tokens": 8628448} {"current_steps": 30800, "total_steps": 40000, "eval_loss": 0.31406450271606445, "epoch": 342.22222222222223, "percentage": 77.0, "elapsed_time": "3:29:11", "remaining_time": "1:02:29", "throughput": 687.46, "total_tokens": 8628448} {"current_steps": 30805, "total_steps": 40000, "loss": 0.0, "lr": 6.242030253491798e-06, "epoch": 342.27777777777777, "percentage": 77.01, "elapsed_time": "3:29:15", "remaining_time": "1:02:27", "throughput": 687.35, "total_tokens": 8629840} {"current_steps": 30810, "total_steps": 40000, "loss": 0.0, "lr": 6.235541599811656e-06, "epoch": 342.3333333333333, "percentage": 77.03, "elapsed_time": "3:29:17", "remaining_time": "1:02:25", "throughput": 687.35, "total_tokens": 8631264} {"current_steps": 30815, "total_steps": 40000, "loss": 0.0, "lr": 6.229055839846814e-06, "epoch": 342.3888888888889, "percentage": 77.04, "elapsed_time": "3:29:19", "remaining_time": "1:02:23", "throughput": 687.36, "total_tokens": 8632624} {"current_steps": 30820, "total_steps": 40000, "loss": 0.0, "lr": 6.222572974597455e-06, "epoch": 342.44444444444446, "percentage": 77.05, "elapsed_time": "3:29:21", "remaining_time": "1:02:21", "throughput": 687.36, "total_tokens": 8634000} {"current_steps": 30825, "total_steps": 40000, "loss": 0.0, "lr": 6.216093005063306e-06, "epoch": 342.5, "percentage": 77.06, "elapsed_time": "3:29:23", "remaining_time": "1:02:19", "throughput": 687.36, "total_tokens": 8635440} {"current_steps": 30830, "total_steps": 40000, "loss": 0.0, "lr": 6.209615932243678e-06, "epoch": 342.55555555555554, "percentage": 77.08, "elapsed_time": "3:29:25", "remaining_time": "1:02:17", "throughput": 687.37, "total_tokens": 8636816} {"current_steps": 30835, "total_steps": 40000, "loss": 0.0, "lr": 6.203141757137399e-06, "epoch": 342.6111111111111, "percentage": 77.09, "elapsed_time": "3:29:26", "remaining_time": "1:02:15", "throughput": 687.37, "total_tokens": 8638224} {"current_steps": 30840, "total_steps": 40000, "loss": 0.0, "lr": 6.196670480742886e-06, "epoch": 342.6666666666667, "percentage": 77.1, "elapsed_time": "3:29:28", "remaining_time": "1:02:13", "throughput": 687.38, "total_tokens": 8639664} {"current_steps": 30845, "total_steps": 40000, "loss": 0.0, "lr": 6.190202104058074e-06, "epoch": 342.72222222222223, "percentage": 77.11, "elapsed_time": "3:29:30", "remaining_time": "1:02:11", "throughput": 687.39, "total_tokens": 8641072} {"current_steps": 30850, "total_steps": 40000, "loss": 0.0, "lr": 6.183736628080475e-06, "epoch": 342.77777777777777, "percentage": 77.12, "elapsed_time": "3:29:32", "remaining_time": "1:02:09", "throughput": 687.39, "total_tokens": 8642480} {"current_steps": 30855, "total_steps": 40000, "loss": 0.0, "lr": 6.177274053807155e-06, "epoch": 342.8333333333333, "percentage": 77.14, "elapsed_time": "3:29:34", "remaining_time": "1:02:06", "throughput": 687.4, "total_tokens": 8643888} {"current_steps": 30860, "total_steps": 40000, "loss": 0.0, "lr": 6.170814382234713e-06, "epoch": 342.8888888888889, "percentage": 77.15, "elapsed_time": "3:29:36", "remaining_time": "1:02:04", "throughput": 687.41, "total_tokens": 8645344} {"current_steps": 30865, "total_steps": 40000, "loss": 0.0, "lr": 6.16435761435932e-06, "epoch": 342.94444444444446, "percentage": 77.16, "elapsed_time": "3:29:38", "remaining_time": "1:02:02", "throughput": 687.42, "total_tokens": 8646752} {"current_steps": 30870, "total_steps": 40000, "loss": 0.0, "lr": 6.157903751176681e-06, "epoch": 343.0, "percentage": 77.18, "elapsed_time": "3:29:40", "remaining_time": "1:02:00", "throughput": 687.42, "total_tokens": 8648192} {"current_steps": 30875, "total_steps": 40000, "loss": 0.0, "lr": 6.151452793682066e-06, "epoch": 343.05555555555554, "percentage": 77.19, "elapsed_time": "3:29:42", "remaining_time": "1:01:58", "throughput": 687.41, "total_tokens": 8649584} {"current_steps": 30880, "total_steps": 40000, "loss": 0.0, "lr": 6.145004742870305e-06, "epoch": 343.1111111111111, "percentage": 77.2, "elapsed_time": "3:29:44", "remaining_time": "1:01:56", "throughput": 687.41, "total_tokens": 8650992} {"current_steps": 30885, "total_steps": 40000, "loss": 0.0, "lr": 6.138559599735752e-06, "epoch": 343.1666666666667, "percentage": 77.21, "elapsed_time": "3:29:46", "remaining_time": "1:01:54", "throughput": 687.42, "total_tokens": 8652448} {"current_steps": 30890, "total_steps": 40000, "loss": 0.0, "lr": 6.132117365272344e-06, "epoch": 343.22222222222223, "percentage": 77.22, "elapsed_time": "3:29:48", "remaining_time": "1:01:52", "throughput": 687.43, "total_tokens": 8653872} {"current_steps": 30895, "total_steps": 40000, "loss": 0.0, "lr": 6.125678040473545e-06, "epoch": 343.27777777777777, "percentage": 77.24, "elapsed_time": "3:29:50", "remaining_time": "1:01:50", "throughput": 687.43, "total_tokens": 8655280} {"current_steps": 30900, "total_steps": 40000, "loss": 0.0, "lr": 6.1192416263323755e-06, "epoch": 343.3333333333333, "percentage": 77.25, "elapsed_time": "3:29:52", "remaining_time": "1:01:48", "throughput": 687.44, "total_tokens": 8656656} {"current_steps": 30905, "total_steps": 40000, "loss": 0.0, "lr": 6.112808123841424e-06, "epoch": 343.3888888888889, "percentage": 77.26, "elapsed_time": "3:29:54", "remaining_time": "1:01:46", "throughput": 687.44, "total_tokens": 8658048} {"current_steps": 30910, "total_steps": 40000, "loss": 0.0, "lr": 6.106377533992805e-06, "epoch": 343.44444444444446, "percentage": 77.28, "elapsed_time": "3:29:56", "remaining_time": "1:01:44", "throughput": 687.45, "total_tokens": 8659424} {"current_steps": 30915, "total_steps": 40000, "loss": 0.0, "lr": 6.099949857778204e-06, "epoch": 343.5, "percentage": 77.29, "elapsed_time": "3:29:58", "remaining_time": "1:01:42", "throughput": 687.45, "total_tokens": 8660784} {"current_steps": 30920, "total_steps": 40000, "loss": 0.0, "lr": 6.093525096188852e-06, "epoch": 343.55555555555554, "percentage": 77.3, "elapsed_time": "3:30:00", "remaining_time": "1:01:40", "throughput": 687.45, "total_tokens": 8662160} {"current_steps": 30925, "total_steps": 40000, "loss": 0.0, "lr": 6.087103250215518e-06, "epoch": 343.6111111111111, "percentage": 77.31, "elapsed_time": "3:30:02", "remaining_time": "1:01:38", "throughput": 687.46, "total_tokens": 8663584} {"current_steps": 30930, "total_steps": 40000, "loss": 0.0, "lr": 6.080684320848537e-06, "epoch": 343.6666666666667, "percentage": 77.33, "elapsed_time": "3:30:04", "remaining_time": "1:01:36", "throughput": 687.46, "total_tokens": 8664992} {"current_steps": 30935, "total_steps": 40000, "loss": 0.0, "lr": 6.074268309077794e-06, "epoch": 343.72222222222223, "percentage": 77.34, "elapsed_time": "3:30:06", "remaining_time": "1:01:34", "throughput": 687.47, "total_tokens": 8666400} {"current_steps": 30940, "total_steps": 40000, "loss": 0.0, "lr": 6.067855215892709e-06, "epoch": 343.77777777777777, "percentage": 77.35, "elapsed_time": "3:30:08", "remaining_time": "1:01:31", "throughput": 687.48, "total_tokens": 8667840} {"current_steps": 30945, "total_steps": 40000, "loss": 0.0, "lr": 6.061445042282271e-06, "epoch": 343.8333333333333, "percentage": 77.36, "elapsed_time": "3:30:10", "remaining_time": "1:01:29", "throughput": 687.49, "total_tokens": 8669248} {"current_steps": 30950, "total_steps": 40000, "loss": 0.0, "lr": 6.055037789234999e-06, "epoch": 343.8888888888889, "percentage": 77.38, "elapsed_time": "3:30:12", "remaining_time": "1:01:27", "throughput": 687.49, "total_tokens": 8670688} {"current_steps": 30955, "total_steps": 40000, "loss": 0.0, "lr": 6.048633457738975e-06, "epoch": 343.94444444444446, "percentage": 77.39, "elapsed_time": "3:30:13", "remaining_time": "1:01:25", "throughput": 687.5, "total_tokens": 8672080} {"current_steps": 30960, "total_steps": 40000, "loss": 0.0, "lr": 6.042232048781837e-06, "epoch": 344.0, "percentage": 77.4, "elapsed_time": "3:30:16", "remaining_time": "1:01:23", "throughput": 687.49, "total_tokens": 8673456} {"current_steps": 30965, "total_steps": 40000, "loss": 0.0, "lr": 6.035833563350757e-06, "epoch": 344.05555555555554, "percentage": 77.41, "elapsed_time": "3:30:18", "remaining_time": "1:01:21", "throughput": 687.48, "total_tokens": 8674784} {"current_steps": 30970, "total_steps": 40000, "loss": 0.0, "lr": 6.0294380024324525e-06, "epoch": 344.1111111111111, "percentage": 77.42, "elapsed_time": "3:30:20", "remaining_time": "1:01:19", "throughput": 687.49, "total_tokens": 8676224} {"current_steps": 30975, "total_steps": 40000, "loss": 0.0, "lr": 6.023045367013213e-06, "epoch": 344.1666666666667, "percentage": 77.44, "elapsed_time": "3:30:22", "remaining_time": "1:01:17", "throughput": 687.49, "total_tokens": 8677600} {"current_steps": 30980, "total_steps": 40000, "loss": 0.0, "lr": 6.016655658078851e-06, "epoch": 344.22222222222223, "percentage": 77.45, "elapsed_time": "3:30:24", "remaining_time": "1:01:15", "throughput": 687.49, "total_tokens": 8678960} {"current_steps": 30985, "total_steps": 40000, "loss": 0.0, "lr": 6.010268876614753e-06, "epoch": 344.27777777777777, "percentage": 77.46, "elapsed_time": "3:30:26", "remaining_time": "1:01:13", "throughput": 687.5, "total_tokens": 8680368} {"current_steps": 30990, "total_steps": 40000, "loss": 0.0, "lr": 6.0038850236058266e-06, "epoch": 344.3333333333333, "percentage": 77.48, "elapsed_time": "3:30:27", "remaining_time": "1:01:11", "throughput": 687.51, "total_tokens": 8681824} {"current_steps": 30995, "total_steps": 40000, "loss": 0.0, "lr": 5.997504100036549e-06, "epoch": 344.3888888888889, "percentage": 77.49, "elapsed_time": "3:30:29", "remaining_time": "1:01:09", "throughput": 687.52, "total_tokens": 8683264} {"current_steps": 31000, "total_steps": 40000, "loss": 0.0, "lr": 5.991126106890949e-06, "epoch": 344.44444444444446, "percentage": 77.5, "elapsed_time": "3:30:31", "remaining_time": "1:01:07", "throughput": 687.52, "total_tokens": 8684672} {"current_steps": 31000, "total_steps": 40000, "eval_loss": 0.3563522696495056, "epoch": 344.44444444444446, "percentage": 77.5, "elapsed_time": "3:30:33", "remaining_time": "1:01:07", "throughput": 687.45, "total_tokens": 8684672} {"current_steps": 31005, "total_steps": 40000, "loss": 0.0, "lr": 5.984751045152576e-06, "epoch": 344.5, "percentage": 77.51, "elapsed_time": "3:30:36", "remaining_time": "1:01:06", "throughput": 687.39, "total_tokens": 8686096} {"current_steps": 31010, "total_steps": 40000, "loss": 0.0, "lr": 5.978378915804553e-06, "epoch": 344.55555555555554, "percentage": 77.53, "elapsed_time": "3:30:38", "remaining_time": "1:01:03", "throughput": 687.39, "total_tokens": 8687472} {"current_steps": 31015, "total_steps": 40000, "loss": 0.0, "lr": 5.972009719829547e-06, "epoch": 344.6111111111111, "percentage": 77.54, "elapsed_time": "3:30:40", "remaining_time": "1:01:01", "throughput": 687.39, "total_tokens": 8688848} {"current_steps": 31020, "total_steps": 40000, "loss": 0.0, "lr": 5.965643458209755e-06, "epoch": 344.6666666666667, "percentage": 77.55, "elapsed_time": "3:30:42", "remaining_time": "1:00:59", "throughput": 687.4, "total_tokens": 8690272} {"current_steps": 31025, "total_steps": 40000, "loss": 0.0, "lr": 5.95928013192695e-06, "epoch": 344.72222222222223, "percentage": 77.56, "elapsed_time": "3:30:44", "remaining_time": "1:00:57", "throughput": 687.4, "total_tokens": 8691680} {"current_steps": 31030, "total_steps": 40000, "loss": 0.0, "lr": 5.952919741962423e-06, "epoch": 344.77777777777777, "percentage": 77.58, "elapsed_time": "3:30:46", "remaining_time": "1:00:55", "throughput": 687.41, "total_tokens": 8693104} {"current_steps": 31035, "total_steps": 40000, "loss": 0.0, "lr": 5.946562289297042e-06, "epoch": 344.8333333333333, "percentage": 77.59, "elapsed_time": "3:30:48", "remaining_time": "1:00:53", "throughput": 687.42, "total_tokens": 8694512} {"current_steps": 31040, "total_steps": 40000, "loss": 0.0, "lr": 5.9402077749111855e-06, "epoch": 344.8888888888889, "percentage": 77.6, "elapsed_time": "3:30:50", "remaining_time": "1:00:51", "throughput": 687.42, "total_tokens": 8695920} {"current_steps": 31045, "total_steps": 40000, "loss": 0.0, "lr": 5.933856199784821e-06, "epoch": 344.94444444444446, "percentage": 77.61, "elapsed_time": "3:30:51", "remaining_time": "1:00:49", "throughput": 687.43, "total_tokens": 8697328} {"current_steps": 31050, "total_steps": 40000, "loss": 0.0, "lr": 5.927507564897419e-06, "epoch": 345.0, "percentage": 77.62, "elapsed_time": "3:30:54", "remaining_time": "1:00:47", "throughput": 687.42, "total_tokens": 8698720} {"current_steps": 31055, "total_steps": 40000, "loss": 0.0, "lr": 5.9211618712280395e-06, "epoch": 345.05555555555554, "percentage": 77.64, "elapsed_time": "3:30:56", "remaining_time": "1:00:45", "throughput": 687.42, "total_tokens": 8700112} {"current_steps": 31060, "total_steps": 40000, "loss": 0.0, "lr": 5.914819119755255e-06, "epoch": 345.1111111111111, "percentage": 77.65, "elapsed_time": "3:30:58", "remaining_time": "1:00:43", "throughput": 687.42, "total_tokens": 8701488} {"current_steps": 31065, "total_steps": 40000, "loss": 0.0, "lr": 5.908479311457205e-06, "epoch": 345.1666666666667, "percentage": 77.66, "elapsed_time": "3:31:00", "remaining_time": "1:00:41", "throughput": 687.42, "total_tokens": 8702880} {"current_steps": 31070, "total_steps": 40000, "loss": 0.0, "lr": 5.902142447311559e-06, "epoch": 345.22222222222223, "percentage": 77.68, "elapsed_time": "3:31:02", "remaining_time": "1:00:39", "throughput": 687.43, "total_tokens": 8704320} {"current_steps": 31075, "total_steps": 40000, "loss": 0.0, "lr": 5.895808528295546e-06, "epoch": 345.27777777777777, "percentage": 77.69, "elapsed_time": "3:31:04", "remaining_time": "1:00:37", "throughput": 687.44, "total_tokens": 8705776} {"current_steps": 31080, "total_steps": 40000, "loss": 0.0, "lr": 5.889477555385941e-06, "epoch": 345.3333333333333, "percentage": 77.7, "elapsed_time": "3:31:05", "remaining_time": "1:00:35", "throughput": 687.45, "total_tokens": 8707168} {"current_steps": 31085, "total_steps": 40000, "loss": 0.0, "lr": 5.883149529559051e-06, "epoch": 345.3888888888889, "percentage": 77.71, "elapsed_time": "3:31:07", "remaining_time": "1:00:33", "throughput": 687.45, "total_tokens": 8708576} {"current_steps": 31090, "total_steps": 40000, "loss": 0.0, "lr": 5.876824451790738e-06, "epoch": 345.44444444444446, "percentage": 77.72, "elapsed_time": "3:31:09", "remaining_time": "1:00:31", "throughput": 687.46, "total_tokens": 8709952} {"current_steps": 31095, "total_steps": 40000, "loss": 0.0, "lr": 5.87050232305642e-06, "epoch": 345.5, "percentage": 77.74, "elapsed_time": "3:31:11", "remaining_time": "1:00:28", "throughput": 687.46, "total_tokens": 8711328} {"current_steps": 31100, "total_steps": 40000, "loss": 0.0, "lr": 5.864183144331034e-06, "epoch": 345.55555555555554, "percentage": 77.75, "elapsed_time": "3:31:13", "remaining_time": "1:00:26", "throughput": 687.46, "total_tokens": 8712720} {"current_steps": 31105, "total_steps": 40000, "loss": 0.0, "lr": 5.857866916589089e-06, "epoch": 345.6111111111111, "percentage": 77.76, "elapsed_time": "3:31:15", "remaining_time": "1:00:24", "throughput": 687.47, "total_tokens": 8714112} {"current_steps": 31110, "total_steps": 40000, "loss": 0.0, "lr": 5.8515536408046216e-06, "epoch": 345.6666666666667, "percentage": 77.78, "elapsed_time": "3:31:17", "remaining_time": "1:00:22", "throughput": 687.48, "total_tokens": 8715568} {"current_steps": 31115, "total_steps": 40000, "loss": 0.0, "lr": 5.845243317951208e-06, "epoch": 345.72222222222223, "percentage": 77.79, "elapsed_time": "3:31:19", "remaining_time": "1:00:20", "throughput": 687.49, "total_tokens": 8717008} {"current_steps": 31120, "total_steps": 40000, "loss": 0.0, "lr": 5.838935949001997e-06, "epoch": 345.77777777777777, "percentage": 77.8, "elapsed_time": "3:31:21", "remaining_time": "1:00:18", "throughput": 687.49, "total_tokens": 8718352} {"current_steps": 31125, "total_steps": 40000, "loss": 0.0, "lr": 5.8326315349296476e-06, "epoch": 345.8333333333333, "percentage": 77.81, "elapsed_time": "3:31:23", "remaining_time": "1:00:16", "throughput": 687.49, "total_tokens": 8719728} {"current_steps": 31130, "total_steps": 40000, "loss": 0.0, "lr": 5.826330076706396e-06, "epoch": 345.8888888888889, "percentage": 77.83, "elapsed_time": "3:31:25", "remaining_time": "1:00:14", "throughput": 687.5, "total_tokens": 8721168} {"current_steps": 31135, "total_steps": 40000, "loss": 0.0, "lr": 5.820031575303988e-06, "epoch": 345.94444444444446, "percentage": 77.84, "elapsed_time": "3:31:27", "remaining_time": "1:00:12", "throughput": 687.5, "total_tokens": 8722544} {"current_steps": 31140, "total_steps": 40000, "loss": 0.0, "lr": 5.813736031693745e-06, "epoch": 346.0, "percentage": 77.85, "elapsed_time": "3:31:29", "remaining_time": "1:00:10", "throughput": 687.5, "total_tokens": 8723936} {"current_steps": 31145, "total_steps": 40000, "loss": 0.0, "lr": 5.807443446846522e-06, "epoch": 346.05555555555554, "percentage": 77.86, "elapsed_time": "3:31:31", "remaining_time": "1:00:08", "throughput": 687.5, "total_tokens": 8725408} {"current_steps": 31150, "total_steps": 40000, "loss": 0.0, "lr": 5.801153821732699e-06, "epoch": 346.1111111111111, "percentage": 77.88, "elapsed_time": "3:31:33", "remaining_time": "1:00:06", "throughput": 687.5, "total_tokens": 8726816} {"current_steps": 31155, "total_steps": 40000, "loss": 0.0, "lr": 5.794867157322229e-06, "epoch": 346.1666666666667, "percentage": 77.89, "elapsed_time": "3:31:35", "remaining_time": "1:00:04", "throughput": 687.51, "total_tokens": 8728240} {"current_steps": 31160, "total_steps": 40000, "loss": 0.0, "lr": 5.788583454584593e-06, "epoch": 346.22222222222223, "percentage": 77.9, "elapsed_time": "3:31:37", "remaining_time": "1:00:02", "throughput": 687.51, "total_tokens": 8729600} {"current_steps": 31165, "total_steps": 40000, "loss": 0.0, "lr": 5.7823027144888075e-06, "epoch": 346.27777777777777, "percentage": 77.91, "elapsed_time": "3:31:39", "remaining_time": "1:00:00", "throughput": 687.52, "total_tokens": 8731024} {"current_steps": 31170, "total_steps": 40000, "loss": 0.0, "lr": 5.776024938003455e-06, "epoch": 346.3333333333333, "percentage": 77.92, "elapsed_time": "3:31:41", "remaining_time": "0:59:58", "throughput": 687.53, "total_tokens": 8732464} {"current_steps": 31175, "total_steps": 40000, "loss": 0.0, "lr": 5.7697501260966345e-06, "epoch": 346.3888888888889, "percentage": 77.94, "elapsed_time": "3:31:43", "remaining_time": "0:59:56", "throughput": 687.53, "total_tokens": 8733872} {"current_steps": 31180, "total_steps": 40000, "loss": 0.0, "lr": 5.7634782797360145e-06, "epoch": 346.44444444444446, "percentage": 77.95, "elapsed_time": "3:31:45", "remaining_time": "0:59:53", "throughput": 687.54, "total_tokens": 8735264} {"current_steps": 31185, "total_steps": 40000, "loss": 0.0, "lr": 5.757209399888777e-06, "epoch": 346.5, "percentage": 77.96, "elapsed_time": "3:31:47", "remaining_time": "0:59:51", "throughput": 687.54, "total_tokens": 8736672} {"current_steps": 31190, "total_steps": 40000, "loss": 0.0, "lr": 5.750943487521679e-06, "epoch": 346.55555555555554, "percentage": 77.98, "elapsed_time": "3:31:49", "remaining_time": "0:59:49", "throughput": 687.55, "total_tokens": 8738048} {"current_steps": 31195, "total_steps": 40000, "loss": 0.0, "lr": 5.744680543600986e-06, "epoch": 346.6111111111111, "percentage": 77.99, "elapsed_time": "3:31:50", "remaining_time": "0:59:47", "throughput": 687.55, "total_tokens": 8739408} {"current_steps": 31200, "total_steps": 40000, "loss": 0.0, "lr": 5.738420569092537e-06, "epoch": 346.6666666666667, "percentage": 78.0, "elapsed_time": "3:31:52", "remaining_time": "0:59:45", "throughput": 687.55, "total_tokens": 8740800} {"current_steps": 31200, "total_steps": 40000, "eval_loss": 0.30873173475265503, "epoch": 346.6666666666667, "percentage": 78.0, "elapsed_time": "3:31:54", "remaining_time": "0:59:46", "throughput": 687.48, "total_tokens": 8740800} {"current_steps": 31205, "total_steps": 40000, "loss": 0.0, "lr": 5.732163564961684e-06, "epoch": 346.72222222222223, "percentage": 78.01, "elapsed_time": "3:31:57", "remaining_time": "0:59:44", "throughput": 687.41, "total_tokens": 8742240} {"current_steps": 31210, "total_steps": 40000, "loss": 0.0, "lr": 5.725909532173354e-06, "epoch": 346.77777777777777, "percentage": 78.03, "elapsed_time": "3:31:59", "remaining_time": "0:59:42", "throughput": 687.41, "total_tokens": 8743600} {"current_steps": 31215, "total_steps": 40000, "loss": 0.0, "lr": 5.719658471691977e-06, "epoch": 346.8333333333333, "percentage": 78.04, "elapsed_time": "3:32:01", "remaining_time": "0:59:40", "throughput": 687.41, "total_tokens": 8744992} {"current_steps": 31220, "total_steps": 40000, "loss": 0.0, "lr": 5.71341038448156e-06, "epoch": 346.8888888888889, "percentage": 78.05, "elapsed_time": "3:32:03", "remaining_time": "0:59:38", "throughput": 687.42, "total_tokens": 8746352} {"current_steps": 31225, "total_steps": 40000, "loss": 0.0, "lr": 5.707165271505635e-06, "epoch": 346.94444444444446, "percentage": 78.06, "elapsed_time": "3:32:05", "remaining_time": "0:59:36", "throughput": 687.42, "total_tokens": 8747728} {"current_steps": 31230, "total_steps": 40000, "loss": 0.0, "lr": 5.700923133727271e-06, "epoch": 347.0, "percentage": 78.08, "elapsed_time": "3:32:07", "remaining_time": "0:59:34", "throughput": 687.42, "total_tokens": 8749152} {"current_steps": 31235, "total_steps": 40000, "loss": 0.0, "lr": 5.694683972109083e-06, "epoch": 347.05555555555554, "percentage": 78.09, "elapsed_time": "3:32:09", "remaining_time": "0:59:32", "throughput": 687.41, "total_tokens": 8750560} {"current_steps": 31240, "total_steps": 40000, "loss": 0.0, "lr": 5.688447787613241e-06, "epoch": 347.1111111111111, "percentage": 78.1, "elapsed_time": "3:32:11", "remaining_time": "0:59:30", "throughput": 687.41, "total_tokens": 8751936} {"current_steps": 31245, "total_steps": 40000, "loss": 0.0, "lr": 5.6822145812014285e-06, "epoch": 347.1666666666667, "percentage": 78.11, "elapsed_time": "3:32:13", "remaining_time": "0:59:28", "throughput": 687.42, "total_tokens": 8753328} {"current_steps": 31250, "total_steps": 40000, "loss": 0.0, "lr": 5.675984353834896e-06, "epoch": 347.22222222222223, "percentage": 78.12, "elapsed_time": "3:32:15", "remaining_time": "0:59:25", "throughput": 687.43, "total_tokens": 8754784} {"current_steps": 31255, "total_steps": 40000, "loss": 0.0, "lr": 5.66975710647441e-06, "epoch": 347.27777777777777, "percentage": 78.14, "elapsed_time": "3:32:17", "remaining_time": "0:59:23", "throughput": 687.43, "total_tokens": 8756192} {"current_steps": 31260, "total_steps": 40000, "loss": 0.0, "lr": 5.663532840080304e-06, "epoch": 347.3333333333333, "percentage": 78.15, "elapsed_time": "3:32:19", "remaining_time": "0:59:21", "throughput": 687.44, "total_tokens": 8757568} {"current_steps": 31265, "total_steps": 40000, "loss": 0.0, "lr": 5.6573115556124325e-06, "epoch": 347.3888888888889, "percentage": 78.16, "elapsed_time": "3:32:21", "remaining_time": "0:59:19", "throughput": 687.44, "total_tokens": 8758976} {"current_steps": 31270, "total_steps": 40000, "loss": 0.0, "lr": 5.651093254030185e-06, "epoch": 347.44444444444446, "percentage": 78.17, "elapsed_time": "3:32:23", "remaining_time": "0:59:17", "throughput": 687.45, "total_tokens": 8760368} {"current_steps": 31275, "total_steps": 40000, "loss": 0.0, "lr": 5.644877936292514e-06, "epoch": 347.5, "percentage": 78.19, "elapsed_time": "3:32:25", "remaining_time": "0:59:15", "throughput": 687.45, "total_tokens": 8761680} {"current_steps": 31280, "total_steps": 40000, "loss": 0.0, "lr": 5.638665603357901e-06, "epoch": 347.55555555555554, "percentage": 78.2, "elapsed_time": "3:32:27", "remaining_time": "0:59:13", "throughput": 687.45, "total_tokens": 8763120} {"current_steps": 31285, "total_steps": 40000, "loss": 0.0, "lr": 5.632456256184357e-06, "epoch": 347.6111111111111, "percentage": 78.21, "elapsed_time": "3:32:29", "remaining_time": "0:59:11", "throughput": 687.46, "total_tokens": 8764576} {"current_steps": 31290, "total_steps": 40000, "loss": 0.0, "lr": 5.626249895729452e-06, "epoch": 347.6666666666667, "percentage": 78.22, "elapsed_time": "3:32:31", "remaining_time": "0:59:09", "throughput": 687.47, "total_tokens": 8766000} {"current_steps": 31295, "total_steps": 40000, "loss": 0.0, "lr": 5.620046522950273e-06, "epoch": 347.72222222222223, "percentage": 78.24, "elapsed_time": "3:32:33", "remaining_time": "0:59:07", "throughput": 687.48, "total_tokens": 8767440} {"current_steps": 31300, "total_steps": 40000, "loss": 0.0, "lr": 5.613846138803464e-06, "epoch": 347.77777777777777, "percentage": 78.25, "elapsed_time": "3:32:34", "remaining_time": "0:59:05", "throughput": 687.48, "total_tokens": 8768832} {"current_steps": 31305, "total_steps": 40000, "loss": 0.0, "lr": 5.607648744245206e-06, "epoch": 347.8333333333333, "percentage": 78.26, "elapsed_time": "3:32:36", "remaining_time": "0:59:03", "throughput": 687.49, "total_tokens": 8770240} {"current_steps": 31310, "total_steps": 40000, "loss": 0.0, "lr": 5.601454340231207e-06, "epoch": 347.8888888888889, "percentage": 78.27, "elapsed_time": "3:32:38", "remaining_time": "0:59:01", "throughput": 687.49, "total_tokens": 8771632} {"current_steps": 31315, "total_steps": 40000, "loss": 0.0, "lr": 5.595262927716724e-06, "epoch": 347.94444444444446, "percentage": 78.29, "elapsed_time": "3:32:40", "remaining_time": "0:58:59", "throughput": 687.5, "total_tokens": 8773008} {"current_steps": 31320, "total_steps": 40000, "loss": 0.0, "lr": 5.589074507656561e-06, "epoch": 348.0, "percentage": 78.3, "elapsed_time": "3:32:42", "remaining_time": "0:58:57", "throughput": 687.49, "total_tokens": 8774384} {"current_steps": 31325, "total_steps": 40000, "loss": 0.0, "lr": 5.582889081005044e-06, "epoch": 348.05555555555554, "percentage": 78.31, "elapsed_time": "3:32:45", "remaining_time": "0:58:55", "throughput": 687.48, "total_tokens": 8775744} {"current_steps": 31330, "total_steps": 40000, "loss": 0.0, "lr": 5.5767066487160316e-06, "epoch": 348.1111111111111, "percentage": 78.33, "elapsed_time": "3:32:47", "remaining_time": "0:58:53", "throughput": 687.49, "total_tokens": 8777168} {"current_steps": 31335, "total_steps": 40000, "loss": 0.0, "lr": 5.570527211742949e-06, "epoch": 348.1666666666667, "percentage": 78.34, "elapsed_time": "3:32:48", "remaining_time": "0:58:50", "throughput": 687.49, "total_tokens": 8778576} {"current_steps": 31340, "total_steps": 40000, "loss": 0.0, "lr": 5.564350771038731e-06, "epoch": 348.22222222222223, "percentage": 78.35, "elapsed_time": "3:32:50", "remaining_time": "0:58:48", "throughput": 687.5, "total_tokens": 8780016} {"current_steps": 31345, "total_steps": 40000, "loss": 0.0, "lr": 5.558177327555875e-06, "epoch": 348.27777777777777, "percentage": 78.36, "elapsed_time": "3:32:52", "remaining_time": "0:58:46", "throughput": 687.51, "total_tokens": 8781472} {"current_steps": 31350, "total_steps": 40000, "loss": 0.0, "lr": 5.552006882246388e-06, "epoch": 348.3333333333333, "percentage": 78.38, "elapsed_time": "3:32:54", "remaining_time": "0:58:44", "throughput": 687.51, "total_tokens": 8782832} {"current_steps": 31355, "total_steps": 40000, "loss": 0.0, "lr": 5.545839436061839e-06, "epoch": 348.3888888888889, "percentage": 78.39, "elapsed_time": "3:32:56", "remaining_time": "0:58:42", "throughput": 687.52, "total_tokens": 8784240} {"current_steps": 31360, "total_steps": 40000, "loss": 0.0, "lr": 5.539674989953331e-06, "epoch": 348.44444444444446, "percentage": 78.4, "elapsed_time": "3:32:58", "remaining_time": "0:58:40", "throughput": 687.52, "total_tokens": 8785664} {"current_steps": 31365, "total_steps": 40000, "loss": 0.0, "lr": 5.533513544871488e-06, "epoch": 348.5, "percentage": 78.41, "elapsed_time": "3:33:00", "remaining_time": "0:58:38", "throughput": 687.53, "total_tokens": 8787072} {"current_steps": 31370, "total_steps": 40000, "loss": 0.0, "lr": 5.527355101766493e-06, "epoch": 348.55555555555554, "percentage": 78.42, "elapsed_time": "3:33:02", "remaining_time": "0:58:36", "throughput": 687.54, "total_tokens": 8788480} {"current_steps": 31375, "total_steps": 40000, "loss": 0.0, "lr": 5.521199661588044e-06, "epoch": 348.6111111111111, "percentage": 78.44, "elapsed_time": "3:33:04", "remaining_time": "0:58:34", "throughput": 687.54, "total_tokens": 8789840} {"current_steps": 31380, "total_steps": 40000, "loss": 0.0, "lr": 5.5150472252853944e-06, "epoch": 348.6666666666667, "percentage": 78.45, "elapsed_time": "3:33:06", "remaining_time": "0:58:32", "throughput": 687.55, "total_tokens": 8791280} {"current_steps": 31385, "total_steps": 40000, "loss": 0.0, "lr": 5.50889779380733e-06, "epoch": 348.72222222222223, "percentage": 78.46, "elapsed_time": "3:33:08", "remaining_time": "0:58:30", "throughput": 687.55, "total_tokens": 8792656} {"current_steps": 31390, "total_steps": 40000, "loss": 0.0, "lr": 5.5027513681021605e-06, "epoch": 348.77777777777777, "percentage": 78.47, "elapsed_time": "3:33:10", "remaining_time": "0:58:28", "throughput": 687.55, "total_tokens": 8794000} {"current_steps": 31395, "total_steps": 40000, "loss": 0.0, "lr": 5.4966079491177545e-06, "epoch": 348.8333333333333, "percentage": 78.49, "elapsed_time": "3:33:12", "remaining_time": "0:58:26", "throughput": 687.56, "total_tokens": 8795408} {"current_steps": 31400, "total_steps": 40000, "loss": 0.0, "lr": 5.490467537801491e-06, "epoch": 348.8888888888889, "percentage": 78.5, "elapsed_time": "3:33:14", "remaining_time": "0:58:24", "throughput": 687.56, "total_tokens": 8796784} {"current_steps": 31400, "total_steps": 40000, "eval_loss": 0.32893458008766174, "epoch": 348.8888888888889, "percentage": 78.5, "elapsed_time": "3:33:15", "remaining_time": "0:58:24", "throughput": 687.49, "total_tokens": 8796784} {"current_steps": 31405, "total_steps": 40000, "loss": 0.0, "lr": 5.484330135100313e-06, "epoch": 348.94444444444446, "percentage": 78.51, "elapsed_time": "3:33:19", "remaining_time": "0:58:22", "throughput": 687.4, "total_tokens": 8798192} {"current_steps": 31410, "total_steps": 40000, "loss": 0.0, "lr": 5.4781957419606785e-06, "epoch": 349.0, "percentage": 78.53, "elapsed_time": "3:33:21", "remaining_time": "0:58:20", "throughput": 687.39, "total_tokens": 8799552} {"current_steps": 31415, "total_steps": 40000, "loss": 0.0, "lr": 5.472064359328577e-06, "epoch": 349.05555555555554, "percentage": 78.54, "elapsed_time": "3:33:23", "remaining_time": "0:58:18", "throughput": 687.38, "total_tokens": 8800928} {"current_steps": 31420, "total_steps": 40000, "loss": 0.0, "lr": 5.4659359881495565e-06, "epoch": 349.1111111111111, "percentage": 78.55, "elapsed_time": "3:33:25", "remaining_time": "0:58:16", "throughput": 687.38, "total_tokens": 8802320} {"current_steps": 31425, "total_steps": 40000, "loss": 0.0, "lr": 5.4598106293686916e-06, "epoch": 349.1666666666667, "percentage": 78.56, "elapsed_time": "3:33:27", "remaining_time": "0:58:14", "throughput": 687.39, "total_tokens": 8803744} {"current_steps": 31430, "total_steps": 40000, "loss": 0.0, "lr": 5.45368828393058e-06, "epoch": 349.22222222222223, "percentage": 78.57, "elapsed_time": "3:33:29", "remaining_time": "0:58:12", "throughput": 687.4, "total_tokens": 8805152} {"current_steps": 31435, "total_steps": 40000, "loss": 0.0, "lr": 5.44756895277937e-06, "epoch": 349.27777777777777, "percentage": 78.59, "elapsed_time": "3:33:31", "remaining_time": "0:58:10", "throughput": 687.4, "total_tokens": 8806528} {"current_steps": 31440, "total_steps": 40000, "loss": 0.0, "lr": 5.441452636858746e-06, "epoch": 349.3333333333333, "percentage": 78.6, "elapsed_time": "3:33:33", "remaining_time": "0:58:08", "throughput": 687.4, "total_tokens": 8807936} {"current_steps": 31445, "total_steps": 40000, "loss": 0.0, "lr": 5.435339337111905e-06, "epoch": 349.3888888888889, "percentage": 78.61, "elapsed_time": "3:33:35", "remaining_time": "0:58:06", "throughput": 687.41, "total_tokens": 8809344} {"current_steps": 31450, "total_steps": 40000, "loss": 0.0, "lr": 5.42922905448161e-06, "epoch": 349.44444444444446, "percentage": 78.62, "elapsed_time": "3:33:37", "remaining_time": "0:58:04", "throughput": 687.42, "total_tokens": 8810752} {"current_steps": 31455, "total_steps": 40000, "loss": 0.0, "lr": 5.423121789910129e-06, "epoch": 349.5, "percentage": 78.64, "elapsed_time": "3:33:39", "remaining_time": "0:58:02", "throughput": 687.42, "total_tokens": 8812144} {"current_steps": 31460, "total_steps": 40000, "loss": 0.0, "lr": 5.417017544339287e-06, "epoch": 349.55555555555554, "percentage": 78.65, "elapsed_time": "3:33:41", "remaining_time": "0:58:00", "throughput": 687.43, "total_tokens": 8813552} {"current_steps": 31465, "total_steps": 40000, "loss": 0.0, "lr": 5.410916318710443e-06, "epoch": 349.6111111111111, "percentage": 78.66, "elapsed_time": "3:33:42", "remaining_time": "0:57:58", "throughput": 687.43, "total_tokens": 8814944} {"current_steps": 31470, "total_steps": 40000, "loss": 0.0, "lr": 5.404818113964466e-06, "epoch": 349.6666666666667, "percentage": 78.67, "elapsed_time": "3:33:44", "remaining_time": "0:57:56", "throughput": 687.44, "total_tokens": 8816368} {"current_steps": 31475, "total_steps": 40000, "loss": 0.0, "lr": 5.398722931041792e-06, "epoch": 349.72222222222223, "percentage": 78.69, "elapsed_time": "3:33:46", "remaining_time": "0:57:54", "throughput": 687.44, "total_tokens": 8817744} {"current_steps": 31480, "total_steps": 40000, "loss": 0.0, "lr": 5.392630770882367e-06, "epoch": 349.77777777777777, "percentage": 78.7, "elapsed_time": "3:33:48", "remaining_time": "0:57:52", "throughput": 687.45, "total_tokens": 8819136} {"current_steps": 31485, "total_steps": 40000, "loss": 0.0, "lr": 5.3865416344256705e-06, "epoch": 349.8333333333333, "percentage": 78.71, "elapsed_time": "3:33:50", "remaining_time": "0:57:50", "throughput": 687.45, "total_tokens": 8820576} {"current_steps": 31490, "total_steps": 40000, "loss": 0.0, "lr": 5.380455522610742e-06, "epoch": 349.8888888888889, "percentage": 78.72, "elapsed_time": "3:33:52", "remaining_time": "0:57:47", "throughput": 687.46, "total_tokens": 8822000} {"current_steps": 31495, "total_steps": 40000, "loss": 0.0, "lr": 5.374372436376116e-06, "epoch": 349.94444444444446, "percentage": 78.74, "elapsed_time": "3:33:54", "remaining_time": "0:57:45", "throughput": 687.47, "total_tokens": 8823376} {"current_steps": 31500, "total_steps": 40000, "loss": 0.0, "lr": 5.368292376659895e-06, "epoch": 350.0, "percentage": 78.75, "elapsed_time": "3:33:56", "remaining_time": "0:57:43", "throughput": 687.46, "total_tokens": 8824784} {"current_steps": 31505, "total_steps": 40000, "loss": 0.0, "lr": 5.362215344399701e-06, "epoch": 350.05555555555554, "percentage": 78.76, "elapsed_time": "3:33:58", "remaining_time": "0:57:41", "throughput": 687.45, "total_tokens": 8826192} {"current_steps": 31510, "total_steps": 40000, "loss": 0.0, "lr": 5.356141340532678e-06, "epoch": 350.1111111111111, "percentage": 78.77, "elapsed_time": "3:34:00", "remaining_time": "0:57:39", "throughput": 687.46, "total_tokens": 8827568} {"current_steps": 31515, "total_steps": 40000, "loss": 0.0, "lr": 5.350070365995522e-06, "epoch": 350.1666666666667, "percentage": 78.79, "elapsed_time": "3:34:02", "remaining_time": "0:57:37", "throughput": 687.46, "total_tokens": 8828976} {"current_steps": 31520, "total_steps": 40000, "loss": 0.0, "lr": 5.344002421724459e-06, "epoch": 350.22222222222223, "percentage": 78.8, "elapsed_time": "3:34:04", "remaining_time": "0:57:35", "throughput": 687.46, "total_tokens": 8830336} {"current_steps": 31525, "total_steps": 40000, "loss": 0.0, "lr": 5.337937508655228e-06, "epoch": 350.27777777777777, "percentage": 78.81, "elapsed_time": "3:34:06", "remaining_time": "0:57:33", "throughput": 687.46, "total_tokens": 8831712} {"current_steps": 31530, "total_steps": 40000, "loss": 0.0, "lr": 5.331875627723126e-06, "epoch": 350.3333333333333, "percentage": 78.83, "elapsed_time": "3:34:08", "remaining_time": "0:57:31", "throughput": 687.47, "total_tokens": 8833120} {"current_steps": 31535, "total_steps": 40000, "loss": 0.0, "lr": 5.325816779862963e-06, "epoch": 350.3888888888889, "percentage": 78.84, "elapsed_time": "3:34:10", "remaining_time": "0:57:29", "throughput": 687.47, "total_tokens": 8834528} {"current_steps": 31540, "total_steps": 40000, "loss": 0.0, "lr": 5.319760966009102e-06, "epoch": 350.44444444444446, "percentage": 78.85, "elapsed_time": "3:34:12", "remaining_time": "0:57:27", "throughput": 687.47, "total_tokens": 8835920} {"current_steps": 31545, "total_steps": 40000, "loss": 0.0, "lr": 5.3137081870954096e-06, "epoch": 350.5, "percentage": 78.86, "elapsed_time": "3:34:14", "remaining_time": "0:57:25", "throughput": 687.48, "total_tokens": 8837376} {"current_steps": 31550, "total_steps": 40000, "loss": 0.0, "lr": 5.307658444055313e-06, "epoch": 350.55555555555554, "percentage": 78.88, "elapsed_time": "3:34:16", "remaining_time": "0:57:23", "throughput": 687.49, "total_tokens": 8838816} {"current_steps": 31555, "total_steps": 40000, "loss": 0.0, "lr": 5.301611737821749e-06, "epoch": 350.6111111111111, "percentage": 78.89, "elapsed_time": "3:34:18", "remaining_time": "0:57:21", "throughput": 687.48, "total_tokens": 8840160} {"current_steps": 31560, "total_steps": 40000, "loss": 0.0, "lr": 5.295568069327206e-06, "epoch": 350.6666666666667, "percentage": 78.9, "elapsed_time": "3:34:20", "remaining_time": "0:57:19", "throughput": 687.48, "total_tokens": 8841520} {"current_steps": 31565, "total_steps": 40000, "loss": 0.0, "lr": 5.289527439503683e-06, "epoch": 350.72222222222223, "percentage": 78.91, "elapsed_time": "3:34:22", "remaining_time": "0:57:17", "throughput": 687.49, "total_tokens": 8842912} {"current_steps": 31570, "total_steps": 40000, "loss": 0.0, "lr": 5.28348984928273e-06, "epoch": 350.77777777777777, "percentage": 78.92, "elapsed_time": "3:34:24", "remaining_time": "0:57:15", "throughput": 687.49, "total_tokens": 8844304} {"current_steps": 31575, "total_steps": 40000, "loss": 0.0, "lr": 5.27745529959541e-06, "epoch": 350.8333333333333, "percentage": 78.94, "elapsed_time": "3:34:26", "remaining_time": "0:57:13", "throughput": 687.49, "total_tokens": 8845728} {"current_steps": 31580, "total_steps": 40000, "loss": 0.0, "lr": 5.271423791372335e-06, "epoch": 350.8888888888889, "percentage": 78.95, "elapsed_time": "3:34:28", "remaining_time": "0:57:11", "throughput": 687.5, "total_tokens": 8847168} {"current_steps": 31585, "total_steps": 40000, "loss": 0.0, "lr": 5.26539532554364e-06, "epoch": 350.94444444444446, "percentage": 78.96, "elapsed_time": "3:34:30", "remaining_time": "0:57:09", "throughput": 687.5, "total_tokens": 8848592} {"current_steps": 31590, "total_steps": 40000, "loss": 0.0, "lr": 5.25936990303898e-06, "epoch": 351.0, "percentage": 78.97, "elapsed_time": "3:34:32", "remaining_time": "0:57:07", "throughput": 687.5, "total_tokens": 8849984} {"current_steps": 31595, "total_steps": 40000, "loss": 0.0, "lr": 5.253347524787555e-06, "epoch": 351.05555555555554, "percentage": 78.99, "elapsed_time": "3:34:35", "remaining_time": "0:57:05", "throughput": 687.48, "total_tokens": 8851344} {"current_steps": 31600, "total_steps": 40000, "loss": 0.0, "lr": 5.2473281917181035e-06, "epoch": 351.1111111111111, "percentage": 79.0, "elapsed_time": "3:34:36", "remaining_time": "0:57:02", "throughput": 687.49, "total_tokens": 8852784} {"current_steps": 31600, "total_steps": 40000, "eval_loss": 0.32816341519355774, "epoch": 351.1111111111111, "percentage": 79.0, "elapsed_time": "3:34:38", "remaining_time": "0:57:03", "throughput": 687.42, "total_tokens": 8852784} {"current_steps": 31605, "total_steps": 40000, "loss": 0.0, "lr": 5.241311904758864e-06, "epoch": 351.1666666666667, "percentage": 79.01, "elapsed_time": "3:34:41", "remaining_time": "0:57:01", "throughput": 687.35, "total_tokens": 8854192} {"current_steps": 31610, "total_steps": 40000, "loss": 0.0, "lr": 5.23529866483764e-06, "epoch": 351.22222222222223, "percentage": 79.03, "elapsed_time": "3:34:43", "remaining_time": "0:56:59", "throughput": 687.35, "total_tokens": 8855568} {"current_steps": 31615, "total_steps": 40000, "loss": 0.0, "lr": 5.229288472881732e-06, "epoch": 351.27777777777777, "percentage": 79.04, "elapsed_time": "3:34:45", "remaining_time": "0:56:57", "throughput": 687.35, "total_tokens": 8856976} {"current_steps": 31620, "total_steps": 40000, "loss": 0.0, "lr": 5.2232813298180025e-06, "epoch": 351.3333333333333, "percentage": 79.05, "elapsed_time": "3:34:47", "remaining_time": "0:56:55", "throughput": 687.35, "total_tokens": 8858400} {"current_steps": 31625, "total_steps": 40000, "loss": 0.0, "lr": 5.217277236572824e-06, "epoch": 351.3888888888889, "percentage": 79.06, "elapsed_time": "3:34:49", "remaining_time": "0:56:53", "throughput": 687.36, "total_tokens": 8859792} {"current_steps": 31630, "total_steps": 40000, "loss": 0.0, "lr": 5.211276194072093e-06, "epoch": 351.44444444444446, "percentage": 79.07, "elapsed_time": "3:34:51", "remaining_time": "0:56:51", "throughput": 687.36, "total_tokens": 8861184} {"current_steps": 31635, "total_steps": 40000, "loss": 0.0, "lr": 5.205278203241254e-06, "epoch": 351.5, "percentage": 79.09, "elapsed_time": "3:34:53", "remaining_time": "0:56:49", "throughput": 687.36, "total_tokens": 8862592} {"current_steps": 31640, "total_steps": 40000, "loss": 0.0, "lr": 5.199283265005278e-06, "epoch": 351.55555555555554, "percentage": 79.1, "elapsed_time": "3:34:55", "remaining_time": "0:56:47", "throughput": 687.36, "total_tokens": 8863984} {"current_steps": 31645, "total_steps": 40000, "loss": 0.0, "lr": 5.193291380288648e-06, "epoch": 351.6111111111111, "percentage": 79.11, "elapsed_time": "3:34:57", "remaining_time": "0:56:45", "throughput": 687.37, "total_tokens": 8865376} {"current_steps": 31650, "total_steps": 40000, "loss": 0.0, "lr": 5.1873025500153995e-06, "epoch": 351.6666666666667, "percentage": 79.12, "elapsed_time": "3:34:59", "remaining_time": "0:56:43", "throughput": 687.37, "total_tokens": 8866768} {"current_steps": 31655, "total_steps": 40000, "loss": 0.0, "lr": 5.181316775109071e-06, "epoch": 351.72222222222223, "percentage": 79.14, "elapsed_time": "3:35:01", "remaining_time": "0:56:41", "throughput": 687.37, "total_tokens": 8868160} {"current_steps": 31660, "total_steps": 40000, "loss": 0.0, "lr": 5.1753340564927564e-06, "epoch": 351.77777777777777, "percentage": 79.15, "elapsed_time": "3:35:03", "remaining_time": "0:56:39", "throughput": 687.37, "total_tokens": 8869584} {"current_steps": 31665, "total_steps": 40000, "loss": 0.0, "lr": 5.169354395089068e-06, "epoch": 351.8333333333333, "percentage": 79.16, "elapsed_time": "3:35:05", "remaining_time": "0:56:37", "throughput": 687.37, "total_tokens": 8870960} {"current_steps": 31670, "total_steps": 40000, "loss": 0.0, "lr": 5.1633777918201346e-06, "epoch": 351.8888888888889, "percentage": 79.17, "elapsed_time": "3:35:07", "remaining_time": "0:56:35", "throughput": 687.38, "total_tokens": 8872384} {"current_steps": 31675, "total_steps": 40000, "loss": 0.0, "lr": 5.157404247607625e-06, "epoch": 351.94444444444446, "percentage": 79.19, "elapsed_time": "3:35:09", "remaining_time": "0:56:32", "throughput": 687.39, "total_tokens": 8873840} {"current_steps": 31680, "total_steps": 40000, "loss": 0.0, "lr": 5.1514337633727454e-06, "epoch": 352.0, "percentage": 79.2, "elapsed_time": "3:35:11", "remaining_time": "0:56:30", "throughput": 687.38, "total_tokens": 8875232} {"current_steps": 31685, "total_steps": 40000, "loss": 0.0, "lr": 5.145466340036206e-06, "epoch": 352.05555555555554, "percentage": 79.21, "elapsed_time": "3:35:13", "remaining_time": "0:56:28", "throughput": 687.37, "total_tokens": 8876640} {"current_steps": 31690, "total_steps": 40000, "loss": 0.0, "lr": 5.139501978518274e-06, "epoch": 352.1111111111111, "percentage": 79.22, "elapsed_time": "3:35:15", "remaining_time": "0:56:26", "throughput": 687.37, "total_tokens": 8878000} {"current_steps": 31695, "total_steps": 40000, "loss": 0.0, "lr": 5.133540679738716e-06, "epoch": 352.1666666666667, "percentage": 79.24, "elapsed_time": "3:35:17", "remaining_time": "0:56:24", "throughput": 687.38, "total_tokens": 8879472} {"current_steps": 31700, "total_steps": 40000, "loss": 0.0, "lr": 5.127582444616838e-06, "epoch": 352.22222222222223, "percentage": 79.25, "elapsed_time": "3:35:19", "remaining_time": "0:56:22", "throughput": 687.38, "total_tokens": 8880864} {"current_steps": 31705, "total_steps": 40000, "loss": 0.0, "lr": 5.121627274071486e-06, "epoch": 352.27777777777777, "percentage": 79.26, "elapsed_time": "3:35:21", "remaining_time": "0:56:20", "throughput": 687.38, "total_tokens": 8882256} {"current_steps": 31710, "total_steps": 40000, "loss": 0.0, "lr": 5.115675169021009e-06, "epoch": 352.3333333333333, "percentage": 79.27, "elapsed_time": "3:35:23", "remaining_time": "0:56:18", "throughput": 687.39, "total_tokens": 8883696} {"current_steps": 31715, "total_steps": 40000, "loss": 0.0, "lr": 5.1097261303832994e-06, "epoch": 352.3888888888889, "percentage": 79.29, "elapsed_time": "3:35:25", "remaining_time": "0:56:16", "throughput": 687.39, "total_tokens": 8885088} {"current_steps": 31720, "total_steps": 40000, "loss": 0.0, "lr": 5.103780159075788e-06, "epoch": 352.44444444444446, "percentage": 79.3, "elapsed_time": "3:35:27", "remaining_time": "0:56:14", "throughput": 687.39, "total_tokens": 8886432} {"current_steps": 31725, "total_steps": 40000, "loss": 0.0, "lr": 5.0978372560154e-06, "epoch": 352.5, "percentage": 79.31, "elapsed_time": "3:35:29", "remaining_time": "0:56:12", "throughput": 687.4, "total_tokens": 8887872} {"current_steps": 31730, "total_steps": 40000, "loss": 0.0, "lr": 5.091897422118619e-06, "epoch": 352.55555555555554, "percentage": 79.33, "elapsed_time": "3:35:31", "remaining_time": "0:56:10", "throughput": 687.4, "total_tokens": 8889328} {"current_steps": 31735, "total_steps": 40000, "loss": 0.0, "lr": 5.0859606583014305e-06, "epoch": 352.6111111111111, "percentage": 79.34, "elapsed_time": "3:35:33", "remaining_time": "0:56:08", "throughput": 687.41, "total_tokens": 8890768} {"current_steps": 31740, "total_steps": 40000, "loss": 0.0, "lr": 5.080026965479365e-06, "epoch": 352.6666666666667, "percentage": 79.35, "elapsed_time": "3:35:35", "remaining_time": "0:56:06", "throughput": 687.41, "total_tokens": 8892144} {"current_steps": 31745, "total_steps": 40000, "loss": 0.0, "lr": 5.074096344567475e-06, "epoch": 352.72222222222223, "percentage": 79.36, "elapsed_time": "3:35:37", "remaining_time": "0:56:04", "throughput": 687.41, "total_tokens": 8893568} {"current_steps": 31750, "total_steps": 40000, "loss": 0.0, "lr": 5.0681687964803294e-06, "epoch": 352.77777777777777, "percentage": 79.38, "elapsed_time": "3:35:39", "remaining_time": "0:56:02", "throughput": 687.42, "total_tokens": 8894960} {"current_steps": 31755, "total_steps": 40000, "loss": 0.0, "lr": 5.06224432213204e-06, "epoch": 352.8333333333333, "percentage": 79.39, "elapsed_time": "3:35:41", "remaining_time": "0:56:00", "throughput": 687.42, "total_tokens": 8896368} {"current_steps": 31760, "total_steps": 40000, "loss": 0.0, "lr": 5.056322922436224e-06, "epoch": 352.8888888888889, "percentage": 79.4, "elapsed_time": "3:35:43", "remaining_time": "0:55:58", "throughput": 687.42, "total_tokens": 8897776} {"current_steps": 31765, "total_steps": 40000, "loss": 0.0, "lr": 5.0504045983060465e-06, "epoch": 352.94444444444446, "percentage": 79.41, "elapsed_time": "3:35:45", "remaining_time": "0:55:56", "throughput": 687.43, "total_tokens": 8899216} {"current_steps": 31770, "total_steps": 40000, "loss": 0.0, "lr": 5.044489350654183e-06, "epoch": 353.0, "percentage": 79.42, "elapsed_time": "3:35:47", "remaining_time": "0:55:54", "throughput": 687.42, "total_tokens": 8900592} {"current_steps": 31775, "total_steps": 40000, "loss": 0.0, "lr": 5.038577180392831e-06, "epoch": 353.05555555555554, "percentage": 79.44, "elapsed_time": "3:35:50", "remaining_time": "0:55:52", "throughput": 687.41, "total_tokens": 8902032} {"current_steps": 31780, "total_steps": 40000, "loss": 0.0, "lr": 5.032668088433729e-06, "epoch": 353.1111111111111, "percentage": 79.45, "elapsed_time": "3:35:52", "remaining_time": "0:55:50", "throughput": 687.42, "total_tokens": 8903440} {"current_steps": 31785, "total_steps": 40000, "loss": 0.0, "lr": 5.02676207568814e-06, "epoch": 353.1666666666667, "percentage": 79.46, "elapsed_time": "3:35:54", "remaining_time": "0:55:48", "throughput": 687.42, "total_tokens": 8904864} {"current_steps": 31790, "total_steps": 40000, "loss": 0.0, "lr": 5.02085914306683e-06, "epoch": 353.22222222222223, "percentage": 79.47, "elapsed_time": "3:35:56", "remaining_time": "0:55:45", "throughput": 687.42, "total_tokens": 8906288} {"current_steps": 31795, "total_steps": 40000, "loss": 0.0, "lr": 5.014959291480123e-06, "epoch": 353.27777777777777, "percentage": 79.49, "elapsed_time": "3:35:58", "remaining_time": "0:55:43", "throughput": 687.43, "total_tokens": 8907664} {"current_steps": 31800, "total_steps": 40000, "loss": 0.0, "lr": 5.009062521837835e-06, "epoch": 353.3333333333333, "percentage": 79.5, "elapsed_time": "3:36:00", "remaining_time": "0:55:41", "throughput": 687.43, "total_tokens": 8909040} {"current_steps": 31800, "total_steps": 40000, "eval_loss": 0.38202881813049316, "epoch": 353.3333333333333, "percentage": 79.5, "elapsed_time": "3:36:01", "remaining_time": "0:55:42", "throughput": 687.36, "total_tokens": 8909040} {"current_steps": 31805, "total_steps": 40000, "loss": 0.0, "lr": 5.003168835049324e-06, "epoch": 353.3888888888889, "percentage": 79.51, "elapsed_time": "3:36:04", "remaining_time": "0:55:40", "throughput": 687.29, "total_tokens": 8910432} {"current_steps": 31810, "total_steps": 40000, "loss": 0.0, "lr": 4.997278232023483e-06, "epoch": 353.44444444444446, "percentage": 79.53, "elapsed_time": "3:36:06", "remaining_time": "0:55:38", "throughput": 687.27, "total_tokens": 8911840} {"current_steps": 31815, "total_steps": 40000, "loss": 0.0, "lr": 4.9913907136687036e-06, "epoch": 353.5, "percentage": 79.54, "elapsed_time": "3:36:08", "remaining_time": "0:55:36", "throughput": 687.28, "total_tokens": 8913264} {"current_steps": 31820, "total_steps": 40000, "loss": 0.0, "lr": 4.985506280892918e-06, "epoch": 353.55555555555554, "percentage": 79.55, "elapsed_time": "3:36:10", "remaining_time": "0:55:34", "throughput": 687.28, "total_tokens": 8914640} {"current_steps": 31825, "total_steps": 40000, "loss": 0.0, "lr": 4.979624934603589e-06, "epoch": 353.6111111111111, "percentage": 79.56, "elapsed_time": "3:36:12", "remaining_time": "0:55:32", "throughput": 687.28, "total_tokens": 8916048} {"current_steps": 31830, "total_steps": 40000, "loss": 0.0, "lr": 4.97374667570768e-06, "epoch": 353.6666666666667, "percentage": 79.57, "elapsed_time": "3:36:14", "remaining_time": "0:55:30", "throughput": 687.28, "total_tokens": 8917456} {"current_steps": 31835, "total_steps": 40000, "loss": 0.0, "lr": 4.967871505111704e-06, "epoch": 353.72222222222223, "percentage": 79.59, "elapsed_time": "3:36:16", "remaining_time": "0:55:28", "throughput": 687.28, "total_tokens": 8918848} {"current_steps": 31840, "total_steps": 40000, "loss": 0.0, "lr": 4.961999423721686e-06, "epoch": 353.77777777777777, "percentage": 79.6, "elapsed_time": "3:36:18", "remaining_time": "0:55:26", "throughput": 687.29, "total_tokens": 8920256} {"current_steps": 31845, "total_steps": 40000, "loss": 0.0, "lr": 4.956130432443159e-06, "epoch": 353.8333333333333, "percentage": 79.61, "elapsed_time": "3:36:20", "remaining_time": "0:55:24", "throughput": 687.29, "total_tokens": 8921680} {"current_steps": 31850, "total_steps": 40000, "loss": 0.0, "lr": 4.950264532181215e-06, "epoch": 353.8888888888889, "percentage": 79.62, "elapsed_time": "3:36:22", "remaining_time": "0:55:22", "throughput": 687.29, "total_tokens": 8923040} {"current_steps": 31855, "total_steps": 40000, "loss": 0.0, "lr": 4.944401723840433e-06, "epoch": 353.94444444444446, "percentage": 79.64, "elapsed_time": "3:36:24", "remaining_time": "0:55:20", "throughput": 687.3, "total_tokens": 8924448} {"current_steps": 31860, "total_steps": 40000, "loss": 0.0, "lr": 4.938542008324942e-06, "epoch": 354.0, "percentage": 79.65, "elapsed_time": "3:36:27", "remaining_time": "0:55:18", "throughput": 687.29, "total_tokens": 8925856} {"current_steps": 31865, "total_steps": 40000, "loss": 0.0, "lr": 4.9326853865383855e-06, "epoch": 354.05555555555554, "percentage": 79.66, "elapsed_time": "3:36:29", "remaining_time": "0:55:16", "throughput": 687.28, "total_tokens": 8927232} {"current_steps": 31870, "total_steps": 40000, "loss": 0.0, "lr": 4.926831859383918e-06, "epoch": 354.1111111111111, "percentage": 79.67, "elapsed_time": "3:36:31", "remaining_time": "0:55:14", "throughput": 687.28, "total_tokens": 8928640} {"current_steps": 31875, "total_steps": 40000, "loss": 0.0, "lr": 4.92098142776424e-06, "epoch": 354.1666666666667, "percentage": 79.69, "elapsed_time": "3:36:33", "remaining_time": "0:55:11", "throughput": 687.28, "total_tokens": 8930032} {"current_steps": 31880, "total_steps": 40000, "loss": 0.0, "lr": 4.91513409258155e-06, "epoch": 354.22222222222223, "percentage": 79.7, "elapsed_time": "3:36:35", "remaining_time": "0:55:09", "throughput": 687.28, "total_tokens": 8931376} {"current_steps": 31885, "total_steps": 40000, "loss": 0.0, "lr": 4.909289854737581e-06, "epoch": 354.27777777777777, "percentage": 79.71, "elapsed_time": "3:36:37", "remaining_time": "0:55:07", "throughput": 687.28, "total_tokens": 8932768} {"current_steps": 31890, "total_steps": 40000, "loss": 0.0, "lr": 4.903448715133602e-06, "epoch": 354.3333333333333, "percentage": 79.72, "elapsed_time": "3:36:39", "remaining_time": "0:55:05", "throughput": 687.29, "total_tokens": 8934176} {"current_steps": 31895, "total_steps": 40000, "loss": 0.0, "lr": 4.897610674670372e-06, "epoch": 354.3888888888889, "percentage": 79.74, "elapsed_time": "3:36:41", "remaining_time": "0:55:03", "throughput": 687.29, "total_tokens": 8935584} {"current_steps": 31900, "total_steps": 40000, "loss": 0.0, "lr": 4.8917757342482e-06, "epoch": 354.44444444444446, "percentage": 79.75, "elapsed_time": "3:36:43", "remaining_time": "0:55:01", "throughput": 687.29, "total_tokens": 8936976} {"current_steps": 31905, "total_steps": 40000, "loss": 0.0, "lr": 4.885943894766909e-06, "epoch": 354.5, "percentage": 79.76, "elapsed_time": "3:36:45", "remaining_time": "0:54:59", "throughput": 687.3, "total_tokens": 8938368} {"current_steps": 31910, "total_steps": 40000, "loss": 0.0, "lr": 4.880115157125842e-06, "epoch": 354.55555555555554, "percentage": 79.77, "elapsed_time": "3:36:47", "remaining_time": "0:54:57", "throughput": 687.3, "total_tokens": 8939792} {"current_steps": 31915, "total_steps": 40000, "loss": 0.0, "lr": 4.874289522223857e-06, "epoch": 354.6111111111111, "percentage": 79.79, "elapsed_time": "3:36:49", "remaining_time": "0:54:55", "throughput": 687.31, "total_tokens": 8941232} {"current_steps": 31920, "total_steps": 40000, "loss": 0.0, "lr": 4.868466990959339e-06, "epoch": 354.6666666666667, "percentage": 79.8, "elapsed_time": "3:36:51", "remaining_time": "0:54:53", "throughput": 687.31, "total_tokens": 8942656} {"current_steps": 31925, "total_steps": 40000, "loss": 0.0, "lr": 4.8626475642301964e-06, "epoch": 354.72222222222223, "percentage": 79.81, "elapsed_time": "3:36:53", "remaining_time": "0:54:51", "throughput": 687.31, "total_tokens": 8944064} {"current_steps": 31930, "total_steps": 40000, "loss": 0.0, "lr": 4.856831242933871e-06, "epoch": 354.77777777777777, "percentage": 79.83, "elapsed_time": "3:36:55", "remaining_time": "0:54:49", "throughput": 687.31, "total_tokens": 8945456} {"current_steps": 31935, "total_steps": 40000, "loss": 0.0, "lr": 4.851018027967294e-06, "epoch": 354.8333333333333, "percentage": 79.84, "elapsed_time": "3:36:57", "remaining_time": "0:54:47", "throughput": 687.32, "total_tokens": 8946864} {"current_steps": 31940, "total_steps": 40000, "loss": 0.0, "lr": 4.845207920226946e-06, "epoch": 354.8888888888889, "percentage": 79.85, "elapsed_time": "3:36:59", "remaining_time": "0:54:45", "throughput": 687.32, "total_tokens": 8948256} {"current_steps": 31945, "total_steps": 40000, "loss": 0.0, "lr": 4.839400920608825e-06, "epoch": 354.94444444444446, "percentage": 79.86, "elapsed_time": "3:37:01", "remaining_time": "0:54:43", "throughput": 687.32, "total_tokens": 8949664} {"current_steps": 31950, "total_steps": 40000, "loss": 0.0, "lr": 4.83359703000843e-06, "epoch": 355.0, "percentage": 79.88, "elapsed_time": "3:37:03", "remaining_time": "0:54:41", "throughput": 687.32, "total_tokens": 8951120} {"current_steps": 31955, "total_steps": 40000, "loss": 0.0, "lr": 4.827796249320804e-06, "epoch": 355.05555555555554, "percentage": 79.89, "elapsed_time": "3:37:05", "remaining_time": "0:54:39", "throughput": 687.31, "total_tokens": 8952496} {"current_steps": 31960, "total_steps": 40000, "loss": 0.0, "lr": 4.82199857944049e-06, "epoch": 355.1111111111111, "percentage": 79.9, "elapsed_time": "3:37:07", "remaining_time": "0:54:37", "throughput": 687.32, "total_tokens": 8953936} {"current_steps": 31965, "total_steps": 40000, "loss": 0.0, "lr": 4.8162040212615695e-06, "epoch": 355.1666666666667, "percentage": 79.91, "elapsed_time": "3:37:09", "remaining_time": "0:54:35", "throughput": 687.32, "total_tokens": 8955360} {"current_steps": 31970, "total_steps": 40000, "loss": 0.0, "lr": 4.810412575677639e-06, "epoch": 355.22222222222223, "percentage": 79.92, "elapsed_time": "3:37:11", "remaining_time": "0:54:33", "throughput": 687.32, "total_tokens": 8956736} {"current_steps": 31975, "total_steps": 40000, "loss": 0.0, "lr": 4.804624243581801e-06, "epoch": 355.27777777777777, "percentage": 79.94, "elapsed_time": "3:37:13", "remaining_time": "0:54:31", "throughput": 687.33, "total_tokens": 8958128} {"current_steps": 31980, "total_steps": 40000, "loss": 0.0, "lr": 4.798839025866703e-06, "epoch": 355.3333333333333, "percentage": 79.95, "elapsed_time": "3:37:15", "remaining_time": "0:54:29", "throughput": 687.33, "total_tokens": 8959552} {"current_steps": 31985, "total_steps": 40000, "loss": 0.0, "lr": 4.793056923424491e-06, "epoch": 355.3888888888889, "percentage": 79.96, "elapsed_time": "3:37:17", "remaining_time": "0:54:26", "throughput": 687.33, "total_tokens": 8960960} {"current_steps": 31990, "total_steps": 40000, "loss": 0.0, "lr": 4.78727793714683e-06, "epoch": 355.44444444444446, "percentage": 79.97, "elapsed_time": "3:37:19", "remaining_time": "0:54:24", "throughput": 687.33, "total_tokens": 8962320} {"current_steps": 31995, "total_steps": 40000, "loss": 0.0, "lr": 4.7815020679249285e-06, "epoch": 355.5, "percentage": 79.99, "elapsed_time": "3:37:21", "remaining_time": "0:54:22", "throughput": 687.33, "total_tokens": 8963712} {"current_steps": 32000, "total_steps": 40000, "loss": 0.0, "lr": 4.775729316649483e-06, "epoch": 355.55555555555554, "percentage": 80.0, "elapsed_time": "3:37:23", "remaining_time": "0:54:20", "throughput": 687.33, "total_tokens": 8965104} {"current_steps": 32000, "total_steps": 40000, "eval_loss": 0.351626455783844, "epoch": 355.55555555555554, "percentage": 80.0, "elapsed_time": "3:37:24", "remaining_time": "0:54:21", "throughput": 687.27, "total_tokens": 8965104} {"current_steps": 32005, "total_steps": 40000, "loss": 0.0, "lr": 4.769959684210728e-06, "epoch": 355.6111111111111, "percentage": 80.01, "elapsed_time": "3:37:27", "remaining_time": "0:54:19", "throughput": 687.2, "total_tokens": 8966512} {"current_steps": 32010, "total_steps": 40000, "loss": 0.0, "lr": 4.764193171498426e-06, "epoch": 355.6666666666667, "percentage": 80.03, "elapsed_time": "3:37:29", "remaining_time": "0:54:17", "throughput": 687.2, "total_tokens": 8967904} {"current_steps": 32015, "total_steps": 40000, "loss": 0.0, "lr": 4.75842977940183e-06, "epoch": 355.72222222222223, "percentage": 80.04, "elapsed_time": "3:37:31", "remaining_time": "0:54:15", "throughput": 687.2, "total_tokens": 8969344} {"current_steps": 32020, "total_steps": 40000, "loss": 0.0, "lr": 4.752669508809729e-06, "epoch": 355.77777777777777, "percentage": 80.05, "elapsed_time": "3:37:33", "remaining_time": "0:54:13", "throughput": 687.21, "total_tokens": 8970816} {"current_steps": 32025, "total_steps": 40000, "loss": 0.0, "lr": 4.746912360610445e-06, "epoch": 355.8333333333333, "percentage": 80.06, "elapsed_time": "3:37:35", "remaining_time": "0:54:11", "throughput": 687.22, "total_tokens": 8972224} {"current_steps": 32030, "total_steps": 40000, "loss": 0.0, "lr": 4.741158335691781e-06, "epoch": 355.8888888888889, "percentage": 80.08, "elapsed_time": "3:37:37", "remaining_time": "0:54:09", "throughput": 687.22, "total_tokens": 8973584} {"current_steps": 32035, "total_steps": 40000, "loss": 0.0, "lr": 4.7354074349410994e-06, "epoch": 355.94444444444446, "percentage": 80.09, "elapsed_time": "3:37:39", "remaining_time": "0:54:07", "throughput": 687.22, "total_tokens": 8975008} {"current_steps": 32040, "total_steps": 40000, "loss": 0.0, "lr": 4.729659659245245e-06, "epoch": 356.0, "percentage": 80.1, "elapsed_time": "3:37:42", "remaining_time": "0:54:05", "throughput": 687.22, "total_tokens": 8976416} {"current_steps": 32045, "total_steps": 40000, "loss": 0.0, "lr": 4.723915009490601e-06, "epoch": 356.05555555555554, "percentage": 80.11, "elapsed_time": "3:37:44", "remaining_time": "0:54:03", "throughput": 687.21, "total_tokens": 8977840} {"current_steps": 32050, "total_steps": 40000, "loss": 0.0, "lr": 4.718173486563077e-06, "epoch": 356.1111111111111, "percentage": 80.12, "elapsed_time": "3:37:46", "remaining_time": "0:54:01", "throughput": 687.21, "total_tokens": 8979264} {"current_steps": 32055, "total_steps": 40000, "loss": 0.0, "lr": 4.71243509134808e-06, "epoch": 356.1666666666667, "percentage": 80.14, "elapsed_time": "3:37:48", "remaining_time": "0:53:59", "throughput": 687.21, "total_tokens": 8980656} {"current_steps": 32060, "total_steps": 40000, "loss": 0.0, "lr": 4.706699824730532e-06, "epoch": 356.22222222222223, "percentage": 80.15, "elapsed_time": "3:37:50", "remaining_time": "0:53:56", "throughput": 687.22, "total_tokens": 8982064} {"current_steps": 32065, "total_steps": 40000, "loss": 0.0, "lr": 4.700967687594901e-06, "epoch": 356.27777777777777, "percentage": 80.16, "elapsed_time": "3:37:52", "remaining_time": "0:53:54", "throughput": 687.22, "total_tokens": 8983472} {"current_steps": 32070, "total_steps": 40000, "loss": 0.0, "lr": 4.69523868082514e-06, "epoch": 356.3333333333333, "percentage": 80.17, "elapsed_time": "3:37:54", "remaining_time": "0:53:52", "throughput": 687.22, "total_tokens": 8984832} {"current_steps": 32075, "total_steps": 40000, "loss": 0.0, "lr": 4.689512805304747e-06, "epoch": 356.3888888888889, "percentage": 80.19, "elapsed_time": "3:37:56", "remaining_time": "0:53:50", "throughput": 687.22, "total_tokens": 8986224} {"current_steps": 32080, "total_steps": 40000, "loss": 0.0, "lr": 4.683790061916707e-06, "epoch": 356.44444444444446, "percentage": 80.2, "elapsed_time": "3:37:58", "remaining_time": "0:53:48", "throughput": 687.23, "total_tokens": 8987664} {"current_steps": 32085, "total_steps": 40000, "loss": 0.0, "lr": 4.678070451543551e-06, "epoch": 356.5, "percentage": 80.21, "elapsed_time": "3:38:00", "remaining_time": "0:53:46", "throughput": 687.23, "total_tokens": 8989088} {"current_steps": 32090, "total_steps": 40000, "loss": 0.0, "lr": 4.6723539750673204e-06, "epoch": 356.55555555555554, "percentage": 80.23, "elapsed_time": "3:38:02", "remaining_time": "0:53:44", "throughput": 687.24, "total_tokens": 8990512} {"current_steps": 32095, "total_steps": 40000, "loss": 0.0, "lr": 4.666640633369551e-06, "epoch": 356.6111111111111, "percentage": 80.24, "elapsed_time": "3:38:04", "remaining_time": "0:53:42", "throughput": 687.24, "total_tokens": 8991936} {"current_steps": 32100, "total_steps": 40000, "loss": 0.0, "lr": 4.660930427331323e-06, "epoch": 356.6666666666667, "percentage": 80.25, "elapsed_time": "3:38:05", "remaining_time": "0:53:40", "throughput": 687.25, "total_tokens": 8993328} {"current_steps": 32105, "total_steps": 40000, "loss": 0.0, "lr": 4.6552233578332244e-06, "epoch": 356.72222222222223, "percentage": 80.26, "elapsed_time": "3:38:08", "remaining_time": "0:53:38", "throughput": 687.25, "total_tokens": 8994704} {"current_steps": 32110, "total_steps": 40000, "loss": 0.0, "lr": 4.649519425755347e-06, "epoch": 356.77777777777777, "percentage": 80.27, "elapsed_time": "3:38:10", "remaining_time": "0:53:36", "throughput": 687.25, "total_tokens": 8996128} {"current_steps": 32115, "total_steps": 40000, "loss": 0.0, "lr": 4.64381863197732e-06, "epoch": 356.8333333333333, "percentage": 80.29, "elapsed_time": "3:38:11", "remaining_time": "0:53:34", "throughput": 687.25, "total_tokens": 8997504} {"current_steps": 32120, "total_steps": 40000, "loss": 0.0, "lr": 4.638120977378269e-06, "epoch": 356.8888888888889, "percentage": 80.3, "elapsed_time": "3:38:13", "remaining_time": "0:53:32", "throughput": 687.25, "total_tokens": 8998848} {"current_steps": 32125, "total_steps": 40000, "loss": 0.0, "lr": 4.632426462836848e-06, "epoch": 356.94444444444446, "percentage": 80.31, "elapsed_time": "3:38:15", "remaining_time": "0:53:30", "throughput": 687.25, "total_tokens": 9000256} {"current_steps": 32130, "total_steps": 40000, "loss": 0.0, "lr": 4.626735089231224e-06, "epoch": 357.0, "percentage": 80.33, "elapsed_time": "3:38:18", "remaining_time": "0:53:28", "throughput": 687.25, "total_tokens": 9001696} {"current_steps": 32135, "total_steps": 40000, "loss": 0.0, "lr": 4.621046857439068e-06, "epoch": 357.05555555555554, "percentage": 80.34, "elapsed_time": "3:38:20", "remaining_time": "0:53:26", "throughput": 687.24, "total_tokens": 9003120} {"current_steps": 32140, "total_steps": 40000, "loss": 0.0, "lr": 4.615361768337587e-06, "epoch": 357.1111111111111, "percentage": 80.35, "elapsed_time": "3:38:22", "remaining_time": "0:53:24", "throughput": 687.25, "total_tokens": 9004544} {"current_steps": 32145, "total_steps": 40000, "loss": 0.0, "lr": 4.6096798228034946e-06, "epoch": 357.1666666666667, "percentage": 80.36, "elapsed_time": "3:38:24", "remaining_time": "0:53:22", "throughput": 687.25, "total_tokens": 9005920} {"current_steps": 32150, "total_steps": 40000, "loss": 0.0, "lr": 4.604001021713008e-06, "epoch": 357.22222222222223, "percentage": 80.38, "elapsed_time": "3:38:26", "remaining_time": "0:53:20", "throughput": 687.25, "total_tokens": 9007376} {"current_steps": 32155, "total_steps": 40000, "loss": 0.0, "lr": 4.598325365941883e-06, "epoch": 357.27777777777777, "percentage": 80.39, "elapsed_time": "3:38:28", "remaining_time": "0:53:18", "throughput": 687.26, "total_tokens": 9008768} {"current_steps": 32160, "total_steps": 40000, "loss": 0.0, "lr": 4.5926528563653645e-06, "epoch": 357.3333333333333, "percentage": 80.4, "elapsed_time": "3:38:30", "remaining_time": "0:53:16", "throughput": 687.26, "total_tokens": 9010160} {"current_steps": 32165, "total_steps": 40000, "loss": 0.0, "lr": 4.5869834938582295e-06, "epoch": 357.3888888888889, "percentage": 80.41, "elapsed_time": "3:38:32", "remaining_time": "0:53:13", "throughput": 687.26, "total_tokens": 9011520} {"current_steps": 32170, "total_steps": 40000, "loss": 0.0, "lr": 4.581317279294772e-06, "epoch": 357.44444444444446, "percentage": 80.42, "elapsed_time": "3:38:34", "remaining_time": "0:53:11", "throughput": 687.26, "total_tokens": 9012912} {"current_steps": 32175, "total_steps": 40000, "loss": 0.0, "lr": 4.57565421354878e-06, "epoch": 357.5, "percentage": 80.44, "elapsed_time": "3:38:36", "remaining_time": "0:53:09", "throughput": 687.27, "total_tokens": 9014352} {"current_steps": 32180, "total_steps": 40000, "loss": 0.0, "lr": 4.569994297493579e-06, "epoch": 357.55555555555554, "percentage": 80.45, "elapsed_time": "3:38:38", "remaining_time": "0:53:07", "throughput": 687.27, "total_tokens": 9015792} {"current_steps": 32185, "total_steps": 40000, "loss": 0.0, "lr": 4.564337532002002e-06, "epoch": 357.6111111111111, "percentage": 80.46, "elapsed_time": "3:38:40", "remaining_time": "0:53:05", "throughput": 687.28, "total_tokens": 9017168} {"current_steps": 32190, "total_steps": 40000, "loss": 0.0, "lr": 4.55868391794638e-06, "epoch": 357.6666666666667, "percentage": 80.47, "elapsed_time": "3:38:42", "remaining_time": "0:53:03", "throughput": 687.28, "total_tokens": 9018576} {"current_steps": 32195, "total_steps": 40000, "loss": 0.0, "lr": 4.553033456198588e-06, "epoch": 357.72222222222223, "percentage": 80.49, "elapsed_time": "3:38:44", "remaining_time": "0:53:01", "throughput": 687.28, "total_tokens": 9019952} {"current_steps": 32200, "total_steps": 40000, "loss": 0.0, "lr": 4.54738614762999e-06, "epoch": 357.77777777777777, "percentage": 80.5, "elapsed_time": "3:38:46", "remaining_time": "0:52:59", "throughput": 687.28, "total_tokens": 9021344} {"current_steps": 32200, "total_steps": 40000, "eval_loss": 0.3088778853416443, "epoch": 357.77777777777777, "percentage": 80.5, "elapsed_time": "3:38:47", "remaining_time": "0:52:59", "throughput": 687.21, "total_tokens": 9021344} {"current_steps": 32205, "total_steps": 40000, "loss": 0.0, "lr": 4.541741993111465e-06, "epoch": 357.8333333333333, "percentage": 80.51, "elapsed_time": "3:38:50", "remaining_time": "0:52:58", "throughput": 687.13, "total_tokens": 9022720} {"current_steps": 32210, "total_steps": 40000, "loss": 0.0, "lr": 4.536100993513423e-06, "epoch": 357.8888888888889, "percentage": 80.53, "elapsed_time": "3:38:53", "remaining_time": "0:52:56", "throughput": 687.13, "total_tokens": 9024096} {"current_steps": 32215, "total_steps": 40000, "loss": 0.0, "lr": 4.530463149705768e-06, "epoch": 357.94444444444446, "percentage": 80.54, "elapsed_time": "3:38:55", "remaining_time": "0:52:54", "throughput": 687.13, "total_tokens": 9025520} {"current_steps": 32220, "total_steps": 40000, "loss": 0.0, "lr": 4.524828462557934e-06, "epoch": 358.0, "percentage": 80.55, "elapsed_time": "3:38:57", "remaining_time": "0:52:52", "throughput": 687.13, "total_tokens": 9026912} {"current_steps": 32225, "total_steps": 40000, "loss": 0.0, "lr": 4.5191969329388625e-06, "epoch": 358.05555555555554, "percentage": 80.56, "elapsed_time": "3:38:59", "remaining_time": "0:52:50", "throughput": 687.12, "total_tokens": 9028320} {"current_steps": 32230, "total_steps": 40000, "loss": 0.0, "lr": 4.5135685617169965e-06, "epoch": 358.1111111111111, "percentage": 80.58, "elapsed_time": "3:39:01", "remaining_time": "0:52:48", "throughput": 687.12, "total_tokens": 9029760} {"current_steps": 32235, "total_steps": 40000, "loss": 0.0, "lr": 4.507943349760313e-06, "epoch": 358.1666666666667, "percentage": 80.59, "elapsed_time": "3:39:03", "remaining_time": "0:52:46", "throughput": 687.13, "total_tokens": 9031184} {"current_steps": 32240, "total_steps": 40000, "loss": 0.0, "lr": 4.502321297936277e-06, "epoch": 358.22222222222223, "percentage": 80.6, "elapsed_time": "3:39:05", "remaining_time": "0:52:44", "throughput": 687.13, "total_tokens": 9032592} {"current_steps": 32245, "total_steps": 40000, "loss": 0.0, "lr": 4.496702407111888e-06, "epoch": 358.27777777777777, "percentage": 80.61, "elapsed_time": "3:39:07", "remaining_time": "0:52:41", "throughput": 687.13, "total_tokens": 9033968} {"current_steps": 32250, "total_steps": 40000, "loss": 0.0, "lr": 4.491086678153653e-06, "epoch": 358.3333333333333, "percentage": 80.62, "elapsed_time": "3:39:09", "remaining_time": "0:52:39", "throughput": 687.14, "total_tokens": 9035440} {"current_steps": 32255, "total_steps": 40000, "loss": 0.0, "lr": 4.485474111927579e-06, "epoch": 358.3888888888889, "percentage": 80.64, "elapsed_time": "3:39:11", "remaining_time": "0:52:37", "throughput": 687.14, "total_tokens": 9036832} {"current_steps": 32260, "total_steps": 40000, "loss": 0.0, "lr": 4.479864709299197e-06, "epoch": 358.44444444444446, "percentage": 80.65, "elapsed_time": "3:39:13", "remaining_time": "0:52:35", "throughput": 687.14, "total_tokens": 9038240} {"current_steps": 32265, "total_steps": 40000, "loss": 0.0, "lr": 4.474258471133555e-06, "epoch": 358.5, "percentage": 80.66, "elapsed_time": "3:39:15", "remaining_time": "0:52:33", "throughput": 687.15, "total_tokens": 9039648} {"current_steps": 32270, "total_steps": 40000, "loss": 0.0, "lr": 4.4686553982952014e-06, "epoch": 358.55555555555554, "percentage": 80.67, "elapsed_time": "3:39:17", "remaining_time": "0:52:31", "throughput": 687.15, "total_tokens": 9041040} {"current_steps": 32275, "total_steps": 40000, "loss": 0.0, "lr": 4.463055491648191e-06, "epoch": 358.6111111111111, "percentage": 80.69, "elapsed_time": "3:39:19", "remaining_time": "0:52:29", "throughput": 687.16, "total_tokens": 9042448} {"current_steps": 32280, "total_steps": 40000, "loss": 0.0, "lr": 4.457458752056112e-06, "epoch": 358.6666666666667, "percentage": 80.7, "elapsed_time": "3:39:21", "remaining_time": "0:52:27", "throughput": 687.16, "total_tokens": 9043856} {"current_steps": 32285, "total_steps": 40000, "loss": 0.0, "lr": 4.451865180382042e-06, "epoch": 358.72222222222223, "percentage": 80.71, "elapsed_time": "3:39:23", "remaining_time": "0:52:25", "throughput": 687.16, "total_tokens": 9045248} {"current_steps": 32290, "total_steps": 40000, "loss": 0.0, "lr": 4.4462747774885936e-06, "epoch": 358.77777777777777, "percentage": 80.73, "elapsed_time": "3:39:25", "remaining_time": "0:52:23", "throughput": 687.16, "total_tokens": 9046624} {"current_steps": 32295, "total_steps": 40000, "loss": 0.0, "lr": 4.440687544237859e-06, "epoch": 358.8333333333333, "percentage": 80.74, "elapsed_time": "3:39:27", "remaining_time": "0:52:21", "throughput": 687.17, "total_tokens": 9048016} {"current_steps": 32300, "total_steps": 40000, "loss": 0.0, "lr": 4.435103481491471e-06, "epoch": 358.8888888888889, "percentage": 80.75, "elapsed_time": "3:39:29", "remaining_time": "0:52:19", "throughput": 687.17, "total_tokens": 9049408} {"current_steps": 32305, "total_steps": 40000, "loss": 0.0, "lr": 4.429522590110569e-06, "epoch": 358.94444444444446, "percentage": 80.76, "elapsed_time": "3:39:31", "remaining_time": "0:52:17", "throughput": 687.17, "total_tokens": 9050816} {"current_steps": 32310, "total_steps": 40000, "loss": 0.0, "lr": 4.423944870955779e-06, "epoch": 359.0, "percentage": 80.77, "elapsed_time": "3:39:33", "remaining_time": "0:52:15", "throughput": 687.16, "total_tokens": 9052176} {"current_steps": 32315, "total_steps": 40000, "loss": 0.0, "lr": 4.418370324887272e-06, "epoch": 359.05555555555554, "percentage": 80.79, "elapsed_time": "3:39:35", "remaining_time": "0:52:13", "throughput": 687.15, "total_tokens": 9053616} {"current_steps": 32320, "total_steps": 40000, "loss": 0.0, "lr": 4.412798952764699e-06, "epoch": 359.1111111111111, "percentage": 80.8, "elapsed_time": "3:39:37", "remaining_time": "0:52:11", "throughput": 687.16, "total_tokens": 9055056} {"current_steps": 32325, "total_steps": 40000, "loss": 0.0, "lr": 4.407230755447245e-06, "epoch": 359.1666666666667, "percentage": 80.81, "elapsed_time": "3:39:39", "remaining_time": "0:52:09", "throughput": 687.16, "total_tokens": 9056448} {"current_steps": 32330, "total_steps": 40000, "loss": 0.0, "lr": 4.401665733793598e-06, "epoch": 359.22222222222223, "percentage": 80.83, "elapsed_time": "3:39:41", "remaining_time": "0:52:07", "throughput": 687.16, "total_tokens": 9057824} {"current_steps": 32335, "total_steps": 40000, "loss": 0.0, "lr": 4.3961038886619425e-06, "epoch": 359.27777777777777, "percentage": 80.84, "elapsed_time": "3:39:43", "remaining_time": "0:52:05", "throughput": 687.17, "total_tokens": 9059280} {"current_steps": 32340, "total_steps": 40000, "loss": 0.0, "lr": 4.39054522091e-06, "epoch": 359.3333333333333, "percentage": 80.85, "elapsed_time": "3:39:45", "remaining_time": "0:52:03", "throughput": 687.17, "total_tokens": 9060656} {"current_steps": 32345, "total_steps": 40000, "loss": 0.0, "lr": 4.384989731394979e-06, "epoch": 359.3888888888889, "percentage": 80.86, "elapsed_time": "3:39:47", "remaining_time": "0:52:01", "throughput": 687.18, "total_tokens": 9062048} {"current_steps": 32350, "total_steps": 40000, "loss": 0.0, "lr": 4.379437420973598e-06, "epoch": 359.44444444444446, "percentage": 80.88, "elapsed_time": "3:39:49", "remaining_time": "0:51:58", "throughput": 687.18, "total_tokens": 9063440} {"current_steps": 32355, "total_steps": 40000, "loss": 0.0, "lr": 4.373888290502107e-06, "epoch": 359.5, "percentage": 80.89, "elapsed_time": "3:39:51", "remaining_time": "0:51:56", "throughput": 687.18, "total_tokens": 9064848} {"current_steps": 32360, "total_steps": 40000, "loss": 0.0, "lr": 4.36834234083624e-06, "epoch": 359.55555555555554, "percentage": 80.9, "elapsed_time": "3:39:53", "remaining_time": "0:51:54", "throughput": 687.18, "total_tokens": 9066208} {"current_steps": 32365, "total_steps": 40000, "loss": 0.0, "lr": 4.362799572831258e-06, "epoch": 359.6111111111111, "percentage": 80.91, "elapsed_time": "3:39:55", "remaining_time": "0:51:52", "throughput": 687.18, "total_tokens": 9067600} {"current_steps": 32370, "total_steps": 40000, "loss": 0.0, "lr": 4.35725998734193e-06, "epoch": 359.6666666666667, "percentage": 80.92, "elapsed_time": "3:39:57", "remaining_time": "0:51:50", "throughput": 687.18, "total_tokens": 9068976} {"current_steps": 32375, "total_steps": 40000, "loss": 0.0, "lr": 4.3517235852225195e-06, "epoch": 359.72222222222223, "percentage": 80.94, "elapsed_time": "3:39:59", "remaining_time": "0:51:48", "throughput": 687.18, "total_tokens": 9070368} {"current_steps": 32380, "total_steps": 40000, "loss": 0.0, "lr": 4.346190367326822e-06, "epoch": 359.77777777777777, "percentage": 80.95, "elapsed_time": "3:40:01", "remaining_time": "0:51:46", "throughput": 687.18, "total_tokens": 9071776} {"current_steps": 32385, "total_steps": 40000, "loss": 0.0, "lr": 4.340660334508115e-06, "epoch": 359.8333333333333, "percentage": 80.96, "elapsed_time": "3:40:03", "remaining_time": "0:51:44", "throughput": 687.19, "total_tokens": 9073200} {"current_steps": 32390, "total_steps": 40000, "loss": 0.0, "lr": 4.335133487619206e-06, "epoch": 359.8888888888889, "percentage": 80.97, "elapsed_time": "3:40:05", "remaining_time": "0:51:42", "throughput": 687.19, "total_tokens": 9074576} {"current_steps": 32395, "total_steps": 40000, "loss": 0.0, "lr": 4.329609827512409e-06, "epoch": 359.94444444444446, "percentage": 80.99, "elapsed_time": "3:40:07", "remaining_time": "0:51:40", "throughput": 687.2, "total_tokens": 9076032} {"current_steps": 32400, "total_steps": 40000, "loss": 0.0, "lr": 4.324089355039531e-06, "epoch": 360.0, "percentage": 81.0, "elapsed_time": "3:40:09", "remaining_time": "0:51:38", "throughput": 687.2, "total_tokens": 9077456} {"current_steps": 32400, "total_steps": 40000, "eval_loss": 0.382182776927948, "epoch": 360.0, "percentage": 81.0, "elapsed_time": "3:40:10", "remaining_time": "0:51:38", "throughput": 687.13, "total_tokens": 9077456} {"current_steps": 32405, "total_steps": 40000, "loss": 0.0, "lr": 4.3185720710519075e-06, "epoch": 360.05555555555554, "percentage": 81.01, "elapsed_time": "3:40:14", "remaining_time": "0:51:37", "throughput": 687.04, "total_tokens": 9078848} {"current_steps": 32410, "total_steps": 40000, "loss": 0.0, "lr": 4.3130579764003724e-06, "epoch": 360.1111111111111, "percentage": 81.03, "elapsed_time": "3:40:16", "remaining_time": "0:51:35", "throughput": 687.04, "total_tokens": 9080304} {"current_steps": 32415, "total_steps": 40000, "loss": 0.0, "lr": 4.307547071935267e-06, "epoch": 360.1666666666667, "percentage": 81.04, "elapsed_time": "3:40:18", "remaining_time": "0:51:33", "throughput": 687.05, "total_tokens": 9081664} {"current_steps": 32420, "total_steps": 40000, "loss": 0.0, "lr": 4.302039358506435e-06, "epoch": 360.22222222222223, "percentage": 81.05, "elapsed_time": "3:40:20", "remaining_time": "0:51:31", "throughput": 687.05, "total_tokens": 9083072} {"current_steps": 32425, "total_steps": 40000, "loss": 0.0, "lr": 4.296534836963245e-06, "epoch": 360.27777777777777, "percentage": 81.06, "elapsed_time": "3:40:22", "remaining_time": "0:51:28", "throughput": 687.05, "total_tokens": 9084464} {"current_steps": 32430, "total_steps": 40000, "loss": 0.0, "lr": 4.291033508154555e-06, "epoch": 360.3333333333333, "percentage": 81.08, "elapsed_time": "3:40:24", "remaining_time": "0:51:26", "throughput": 687.06, "total_tokens": 9085904} {"current_steps": 32435, "total_steps": 40000, "loss": 0.0, "lr": 4.285535372928748e-06, "epoch": 360.3888888888889, "percentage": 81.09, "elapsed_time": "3:40:26", "remaining_time": "0:51:24", "throughput": 687.06, "total_tokens": 9087296} {"current_steps": 32440, "total_steps": 40000, "loss": 0.0, "lr": 4.280040432133695e-06, "epoch": 360.44444444444446, "percentage": 81.1, "elapsed_time": "3:40:28", "remaining_time": "0:51:22", "throughput": 687.06, "total_tokens": 9088672} {"current_steps": 32445, "total_steps": 40000, "loss": 0.0, "lr": 4.274548686616789e-06, "epoch": 360.5, "percentage": 81.11, "elapsed_time": "3:40:30", "remaining_time": "0:51:20", "throughput": 687.06, "total_tokens": 9090064} {"current_steps": 32450, "total_steps": 40000, "loss": 0.0, "lr": 4.2690601372249364e-06, "epoch": 360.55555555555554, "percentage": 81.12, "elapsed_time": "3:40:32", "remaining_time": "0:51:18", "throughput": 687.07, "total_tokens": 9091504} {"current_steps": 32455, "total_steps": 40000, "loss": 0.0, "lr": 4.263574784804525e-06, "epoch": 360.6111111111111, "percentage": 81.14, "elapsed_time": "3:40:34", "remaining_time": "0:51:16", "throughput": 687.07, "total_tokens": 9092896} {"current_steps": 32460, "total_steps": 40000, "loss": 0.0, "lr": 4.258092630201479e-06, "epoch": 360.6666666666667, "percentage": 81.15, "elapsed_time": "3:40:36", "remaining_time": "0:51:14", "throughput": 687.07, "total_tokens": 9094256} {"current_steps": 32465, "total_steps": 40000, "loss": 0.0, "lr": 4.252613674261202e-06, "epoch": 360.72222222222223, "percentage": 81.16, "elapsed_time": "3:40:38", "remaining_time": "0:51:12", "throughput": 687.07, "total_tokens": 9095632} {"current_steps": 32470, "total_steps": 40000, "loss": 0.0, "lr": 4.2471379178286224e-06, "epoch": 360.77777777777777, "percentage": 81.17, "elapsed_time": "3:40:40", "remaining_time": "0:51:10", "throughput": 687.07, "total_tokens": 9096976} {"current_steps": 32475, "total_steps": 40000, "loss": 0.0, "lr": 4.241665361748181e-06, "epoch": 360.8333333333333, "percentage": 81.19, "elapsed_time": "3:40:42", "remaining_time": "0:51:08", "throughput": 687.08, "total_tokens": 9098384} {"current_steps": 32480, "total_steps": 40000, "loss": 0.0, "lr": 4.2361960068637994e-06, "epoch": 360.8888888888889, "percentage": 81.2, "elapsed_time": "3:40:44", "remaining_time": "0:51:06", "throughput": 687.08, "total_tokens": 9099792} {"current_steps": 32485, "total_steps": 40000, "loss": 0.0, "lr": 4.230729854018933e-06, "epoch": 360.94444444444446, "percentage": 81.21, "elapsed_time": "3:40:46", "remaining_time": "0:51:04", "throughput": 687.08, "total_tokens": 9101232} {"current_steps": 32490, "total_steps": 40000, "loss": 0.0, "lr": 4.225266904056521e-06, "epoch": 361.0, "percentage": 81.23, "elapsed_time": "3:40:48", "remaining_time": "0:51:02", "throughput": 687.08, "total_tokens": 9102656} {"current_steps": 32495, "total_steps": 40000, "loss": 0.0, "lr": 4.21980715781903e-06, "epoch": 361.05555555555554, "percentage": 81.24, "elapsed_time": "3:40:50", "remaining_time": "0:51:00", "throughput": 687.06, "total_tokens": 9104000} {"current_steps": 32500, "total_steps": 40000, "loss": 0.0, "lr": 4.214350616148416e-06, "epoch": 361.1111111111111, "percentage": 81.25, "elapsed_time": "3:40:52", "remaining_time": "0:50:58", "throughput": 687.07, "total_tokens": 9105408} {"current_steps": 32505, "total_steps": 40000, "loss": 0.0, "lr": 4.20889727988614e-06, "epoch": 361.1666666666667, "percentage": 81.26, "elapsed_time": "3:40:54", "remaining_time": "0:50:56", "throughput": 687.07, "total_tokens": 9106800} {"current_steps": 32510, "total_steps": 40000, "loss": 0.0, "lr": 4.20344714987318e-06, "epoch": 361.22222222222223, "percentage": 81.27, "elapsed_time": "3:40:56", "remaining_time": "0:50:54", "throughput": 687.08, "total_tokens": 9108272} {"current_steps": 32515, "total_steps": 40000, "loss": 0.0, "lr": 4.198000226950022e-06, "epoch": 361.27777777777777, "percentage": 81.29, "elapsed_time": "3:40:58", "remaining_time": "0:50:52", "throughput": 687.08, "total_tokens": 9109680} {"current_steps": 32520, "total_steps": 40000, "loss": 0.0, "lr": 4.192556511956635e-06, "epoch": 361.3333333333333, "percentage": 81.3, "elapsed_time": "3:41:00", "remaining_time": "0:50:50", "throughput": 687.08, "total_tokens": 9111072} {"current_steps": 32525, "total_steps": 40000, "loss": 0.0, "lr": 4.18711600573252e-06, "epoch": 361.3888888888889, "percentage": 81.31, "elapsed_time": "3:41:02", "remaining_time": "0:50:48", "throughput": 687.08, "total_tokens": 9112480} {"current_steps": 32530, "total_steps": 40000, "loss": 0.0, "lr": 4.181678709116671e-06, "epoch": 361.44444444444446, "percentage": 81.33, "elapsed_time": "3:41:04", "remaining_time": "0:50:45", "throughput": 687.09, "total_tokens": 9113840} {"current_steps": 32535, "total_steps": 40000, "loss": 0.0, "lr": 4.1762446229475785e-06, "epoch": 361.5, "percentage": 81.34, "elapsed_time": "3:41:06", "remaining_time": "0:50:43", "throughput": 687.09, "total_tokens": 9115232} {"current_steps": 32540, "total_steps": 40000, "loss": 0.0, "lr": 4.17081374806326e-06, "epoch": 361.55555555555554, "percentage": 81.35, "elapsed_time": "3:41:08", "remaining_time": "0:50:41", "throughput": 687.1, "total_tokens": 9116656} {"current_steps": 32545, "total_steps": 40000, "loss": 0.0, "lr": 4.165386085301212e-06, "epoch": 361.6111111111111, "percentage": 81.36, "elapsed_time": "3:41:10", "remaining_time": "0:50:39", "throughput": 687.1, "total_tokens": 9118064} {"current_steps": 32550, "total_steps": 40000, "loss": 0.0, "lr": 4.1599616354984525e-06, "epoch": 361.6666666666667, "percentage": 81.38, "elapsed_time": "3:41:12", "remaining_time": "0:50:37", "throughput": 687.1, "total_tokens": 9119504} {"current_steps": 32555, "total_steps": 40000, "loss": 0.0, "lr": 4.154540399491508e-06, "epoch": 361.72222222222223, "percentage": 81.39, "elapsed_time": "3:41:14", "remaining_time": "0:50:35", "throughput": 687.1, "total_tokens": 9120928} {"current_steps": 32560, "total_steps": 40000, "loss": 0.0, "lr": 4.149122378116394e-06, "epoch": 361.77777777777777, "percentage": 81.4, "elapsed_time": "3:41:16", "remaining_time": "0:50:33", "throughput": 687.1, "total_tokens": 9122272} {"current_steps": 32565, "total_steps": 40000, "loss": 0.0, "lr": 4.14370757220863e-06, "epoch": 361.8333333333333, "percentage": 81.41, "elapsed_time": "3:41:18", "remaining_time": "0:50:31", "throughput": 687.11, "total_tokens": 9123680} {"current_steps": 32570, "total_steps": 40000, "loss": 0.0, "lr": 4.138295982603263e-06, "epoch": 361.8888888888889, "percentage": 81.42, "elapsed_time": "3:41:20", "remaining_time": "0:50:29", "throughput": 687.12, "total_tokens": 9125136} {"current_steps": 32575, "total_steps": 40000, "loss": 0.0, "lr": 4.132887610134814e-06, "epoch": 361.94444444444446, "percentage": 81.44, "elapsed_time": "3:41:22", "remaining_time": "0:50:27", "throughput": 687.12, "total_tokens": 9126560} {"current_steps": 32580, "total_steps": 40000, "loss": 0.0, "lr": 4.127482455637335e-06, "epoch": 362.0, "percentage": 81.45, "elapsed_time": "3:41:24", "remaining_time": "0:50:25", "throughput": 687.11, "total_tokens": 9127984} {"current_steps": 32585, "total_steps": 40000, "loss": 0.0, "lr": 4.1220805199443545e-06, "epoch": 362.05555555555554, "percentage": 81.46, "elapsed_time": "3:41:26", "remaining_time": "0:50:23", "throughput": 687.1, "total_tokens": 9129392} {"current_steps": 32590, "total_steps": 40000, "loss": 0.0, "lr": 4.116681803888925e-06, "epoch": 362.1111111111111, "percentage": 81.47, "elapsed_time": "3:41:28", "remaining_time": "0:50:21", "throughput": 687.11, "total_tokens": 9130768} {"current_steps": 32595, "total_steps": 40000, "loss": 0.0, "lr": 4.111286308303605e-06, "epoch": 362.1666666666667, "percentage": 81.49, "elapsed_time": "3:41:30", "remaining_time": "0:50:19", "throughput": 687.12, "total_tokens": 9132224} {"current_steps": 32600, "total_steps": 40000, "loss": 0.0, "lr": 4.105894034020433e-06, "epoch": 362.22222222222223, "percentage": 81.5, "elapsed_time": "3:41:32", "remaining_time": "0:50:17", "throughput": 687.12, "total_tokens": 9133648} {"current_steps": 32600, "total_steps": 40000, "eval_loss": 0.3347680866718292, "epoch": 362.22222222222223, "percentage": 81.5, "elapsed_time": "3:41:33", "remaining_time": "0:50:17", "throughput": 687.06, "total_tokens": 9133648} {"current_steps": 32605, "total_steps": 40000, "loss": 0.0, "lr": 4.100504981870975e-06, "epoch": 362.27777777777777, "percentage": 81.51, "elapsed_time": "3:41:37", "remaining_time": "0:50:16", "throughput": 686.96, "total_tokens": 9135056} {"current_steps": 32610, "total_steps": 40000, "loss": 0.0, "lr": 4.0951191526862915e-06, "epoch": 362.3333333333333, "percentage": 81.53, "elapsed_time": "3:41:39", "remaining_time": "0:50:14", "throughput": 686.95, "total_tokens": 9136384} {"current_steps": 32615, "total_steps": 40000, "loss": 0.0, "lr": 4.089736547296938e-06, "epoch": 362.3888888888889, "percentage": 81.54, "elapsed_time": "3:41:42", "remaining_time": "0:50:11", "throughput": 686.95, "total_tokens": 9137760} {"current_steps": 32620, "total_steps": 40000, "loss": 0.0, "lr": 4.08435716653299e-06, "epoch": 362.44444444444446, "percentage": 81.55, "elapsed_time": "3:41:43", "remaining_time": "0:50:09", "throughput": 686.94, "total_tokens": 9139088} {"current_steps": 32625, "total_steps": 40000, "loss": 0.0, "lr": 4.0789810112240005e-06, "epoch": 362.5, "percentage": 81.56, "elapsed_time": "3:41:45", "remaining_time": "0:50:07", "throughput": 686.95, "total_tokens": 9140496} {"current_steps": 32630, "total_steps": 40000, "loss": 0.0, "lr": 4.073608082199057e-06, "epoch": 362.55555555555554, "percentage": 81.58, "elapsed_time": "3:41:47", "remaining_time": "0:50:05", "throughput": 686.95, "total_tokens": 9141872} {"current_steps": 32635, "total_steps": 40000, "loss": 0.0, "lr": 4.068238380286718e-06, "epoch": 362.6111111111111, "percentage": 81.59, "elapsed_time": "3:41:49", "remaining_time": "0:50:03", "throughput": 686.95, "total_tokens": 9143264} {"current_steps": 32640, "total_steps": 40000, "loss": 0.0, "lr": 4.062871906315072e-06, "epoch": 362.6666666666667, "percentage": 81.6, "elapsed_time": "3:41:51", "remaining_time": "0:50:01", "throughput": 686.96, "total_tokens": 9144672} {"current_steps": 32645, "total_steps": 40000, "loss": 0.0, "lr": 4.057508661111686e-06, "epoch": 362.72222222222223, "percentage": 81.61, "elapsed_time": "3:41:53", "remaining_time": "0:49:59", "throughput": 686.95, "total_tokens": 9145984} {"current_steps": 32650, "total_steps": 40000, "loss": 0.0, "lr": 4.052148645503648e-06, "epoch": 362.77777777777777, "percentage": 81.62, "elapsed_time": "3:41:55", "remaining_time": "0:49:57", "throughput": 686.95, "total_tokens": 9147424} {"current_steps": 32655, "total_steps": 40000, "loss": 0.0, "lr": 4.046791860317531e-06, "epoch": 362.8333333333333, "percentage": 81.64, "elapsed_time": "3:41:57", "remaining_time": "0:49:55", "throughput": 686.96, "total_tokens": 9148832} {"current_steps": 32660, "total_steps": 40000, "loss": 0.0, "lr": 4.041438306379431e-06, "epoch": 362.8888888888889, "percentage": 81.65, "elapsed_time": "3:41:59", "remaining_time": "0:49:53", "throughput": 686.96, "total_tokens": 9150256} {"current_steps": 32665, "total_steps": 40000, "loss": 0.0, "lr": 4.036087984514916e-06, "epoch": 362.94444444444446, "percentage": 81.66, "elapsed_time": "3:42:01", "remaining_time": "0:49:51", "throughput": 686.97, "total_tokens": 9151696} {"current_steps": 32670, "total_steps": 40000, "loss": 0.0, "lr": 4.030740895549084e-06, "epoch": 363.0, "percentage": 81.67, "elapsed_time": "3:42:03", "remaining_time": "0:49:49", "throughput": 686.97, "total_tokens": 9153136} {"current_steps": 32675, "total_steps": 40000, "loss": 0.0, "lr": 4.025397040306531e-06, "epoch": 363.05555555555554, "percentage": 81.69, "elapsed_time": "3:42:06", "remaining_time": "0:49:47", "throughput": 686.96, "total_tokens": 9154528} {"current_steps": 32680, "total_steps": 40000, "loss": 0.0, "lr": 4.0200564196113285e-06, "epoch": 363.1111111111111, "percentage": 81.7, "elapsed_time": "3:42:08", "remaining_time": "0:49:45", "throughput": 686.96, "total_tokens": 9155904} {"current_steps": 32685, "total_steps": 40000, "loss": 0.0, "lr": 4.014719034287079e-06, "epoch": 363.1666666666667, "percentage": 81.71, "elapsed_time": "3:42:10", "remaining_time": "0:49:43", "throughput": 686.96, "total_tokens": 9157296} {"current_steps": 32690, "total_steps": 40000, "loss": 0.0, "lr": 4.0093848851568775e-06, "epoch": 363.22222222222223, "percentage": 81.73, "elapsed_time": "3:42:12", "remaining_time": "0:49:41", "throughput": 686.96, "total_tokens": 9158688} {"current_steps": 32695, "total_steps": 40000, "loss": 0.0, "lr": 4.004053973043304e-06, "epoch": 363.27777777777777, "percentage": 81.74, "elapsed_time": "3:42:14", "remaining_time": "0:49:39", "throughput": 686.96, "total_tokens": 9160080} {"current_steps": 32700, "total_steps": 40000, "loss": 0.0, "lr": 3.998726298768465e-06, "epoch": 363.3333333333333, "percentage": 81.75, "elapsed_time": "3:42:16", "remaining_time": "0:49:37", "throughput": 686.97, "total_tokens": 9161488} {"current_steps": 32705, "total_steps": 40000, "loss": 0.0, "lr": 3.99340186315395e-06, "epoch": 363.3888888888889, "percentage": 81.76, "elapsed_time": "3:42:18", "remaining_time": "0:49:35", "throughput": 686.97, "total_tokens": 9162880} {"current_steps": 32710, "total_steps": 40000, "loss": 0.0, "lr": 3.988080667020849e-06, "epoch": 363.44444444444446, "percentage": 81.77, "elapsed_time": "3:42:20", "remaining_time": "0:49:33", "throughput": 686.98, "total_tokens": 9164320} {"current_steps": 32715, "total_steps": 40000, "loss": 0.0, "lr": 3.982762711189766e-06, "epoch": 363.5, "percentage": 81.79, "elapsed_time": "3:42:22", "remaining_time": "0:49:31", "throughput": 686.98, "total_tokens": 9165712} {"current_steps": 32720, "total_steps": 40000, "loss": 0.0, "lr": 3.977447996480785e-06, "epoch": 363.55555555555554, "percentage": 81.8, "elapsed_time": "3:42:24", "remaining_time": "0:49:28", "throughput": 686.97, "total_tokens": 9167072} {"current_steps": 32725, "total_steps": 40000, "loss": 0.0, "lr": 3.97213652371351e-06, "epoch": 363.6111111111111, "percentage": 81.81, "elapsed_time": "3:42:26", "remaining_time": "0:49:26", "throughput": 686.97, "total_tokens": 9168448} {"current_steps": 32730, "total_steps": 40000, "loss": 0.0, "lr": 3.966828293707042e-06, "epoch": 363.6666666666667, "percentage": 81.83, "elapsed_time": "3:42:28", "remaining_time": "0:49:24", "throughput": 686.98, "total_tokens": 9169856} {"current_steps": 32735, "total_steps": 40000, "loss": 0.0, "lr": 3.961523307279963e-06, "epoch": 363.72222222222223, "percentage": 81.84, "elapsed_time": "3:42:29", "remaining_time": "0:49:22", "throughput": 686.98, "total_tokens": 9171248} {"current_steps": 32740, "total_steps": 40000, "loss": 0.0, "lr": 3.956221565250382e-06, "epoch": 363.77777777777777, "percentage": 81.85, "elapsed_time": "3:42:31", "remaining_time": "0:49:20", "throughput": 686.99, "total_tokens": 9172656} {"current_steps": 32745, "total_steps": 40000, "loss": 0.0, "lr": 3.950923068435883e-06, "epoch": 363.8333333333333, "percentage": 81.86, "elapsed_time": "3:42:33", "remaining_time": "0:49:18", "throughput": 686.99, "total_tokens": 9174064} {"current_steps": 32750, "total_steps": 40000, "loss": 0.0, "lr": 3.945627817653566e-06, "epoch": 363.8888888888889, "percentage": 81.88, "elapsed_time": "3:42:35", "remaining_time": "0:49:16", "throughput": 686.99, "total_tokens": 9175456} {"current_steps": 32755, "total_steps": 40000, "loss": 0.0, "lr": 3.9403358137200335e-06, "epoch": 363.94444444444446, "percentage": 81.89, "elapsed_time": "3:42:38", "remaining_time": "0:49:14", "throughput": 687.0, "total_tokens": 9176928} {"current_steps": 32760, "total_steps": 40000, "loss": 0.0, "lr": 3.9350470574513605e-06, "epoch": 364.0, "percentage": 81.9, "elapsed_time": "3:42:40", "remaining_time": "0:49:12", "throughput": 686.99, "total_tokens": 9178320} {"current_steps": 32765, "total_steps": 40000, "loss": 0.0, "lr": 3.9297615496631525e-06, "epoch": 364.05555555555554, "percentage": 81.91, "elapsed_time": "3:42:42", "remaining_time": "0:49:10", "throughput": 686.98, "total_tokens": 9179728} {"current_steps": 32770, "total_steps": 40000, "loss": 0.0, "lr": 3.924479291170505e-06, "epoch": 364.1111111111111, "percentage": 81.92, "elapsed_time": "3:42:44", "remaining_time": "0:49:08", "throughput": 687.0, "total_tokens": 9181216} {"current_steps": 32775, "total_steps": 40000, "loss": 0.0, "lr": 3.919200282788002e-06, "epoch": 364.1666666666667, "percentage": 81.94, "elapsed_time": "3:42:46", "remaining_time": "0:49:06", "throughput": 687.0, "total_tokens": 9182592} {"current_steps": 32780, "total_steps": 40000, "loss": 0.0, "lr": 3.913924525329726e-06, "epoch": 364.22222222222223, "percentage": 81.95, "elapsed_time": "3:42:48", "remaining_time": "0:49:04", "throughput": 687.0, "total_tokens": 9183984} {"current_steps": 32785, "total_steps": 40000, "loss": 0.0, "lr": 3.908652019609279e-06, "epoch": 364.27777777777777, "percentage": 81.96, "elapsed_time": "3:42:50", "remaining_time": "0:49:02", "throughput": 687.0, "total_tokens": 9185408} {"current_steps": 32790, "total_steps": 40000, "loss": 0.0, "lr": 3.9033827664397364e-06, "epoch": 364.3333333333333, "percentage": 81.97, "elapsed_time": "3:42:52", "remaining_time": "0:49:00", "throughput": 687.0, "total_tokens": 9186784} {"current_steps": 32795, "total_steps": 40000, "loss": 0.0, "lr": 3.898116766633694e-06, "epoch": 364.3888888888889, "percentage": 81.99, "elapsed_time": "3:42:54", "remaining_time": "0:48:58", "throughput": 686.99, "total_tokens": 9188192} {"current_steps": 32800, "total_steps": 40000, "loss": 0.0, "lr": 3.8928540210032225e-06, "epoch": 364.44444444444446, "percentage": 82.0, "elapsed_time": "3:42:56", "remaining_time": "0:48:56", "throughput": 686.99, "total_tokens": 9189616} {"current_steps": 32800, "total_steps": 40000, "eval_loss": 0.384141206741333, "epoch": 364.44444444444446, "percentage": 82.0, "elapsed_time": "3:42:57", "remaining_time": "0:48:56", "throughput": 686.93, "total_tokens": 9189616} {"current_steps": 32805, "total_steps": 40000, "loss": 0.0, "lr": 3.887594530359909e-06, "epoch": 364.5, "percentage": 82.01, "elapsed_time": "3:43:01", "remaining_time": "0:48:54", "throughput": 686.83, "total_tokens": 9191040} {"current_steps": 32810, "total_steps": 40000, "loss": 0.0, "lr": 3.88233829551484e-06, "epoch": 364.55555555555554, "percentage": 82.03, "elapsed_time": "3:43:03", "remaining_time": "0:48:52", "throughput": 686.84, "total_tokens": 9192432} {"current_steps": 32815, "total_steps": 40000, "loss": 0.0, "lr": 3.877085317278581e-06, "epoch": 364.6111111111111, "percentage": 82.04, "elapsed_time": "3:43:05", "remaining_time": "0:48:50", "throughput": 686.84, "total_tokens": 9193808} {"current_steps": 32820, "total_steps": 40000, "loss": 0.0, "lr": 3.87183559646122e-06, "epoch": 364.6666666666667, "percentage": 82.05, "elapsed_time": "3:43:07", "remaining_time": "0:48:48", "throughput": 686.84, "total_tokens": 9195184} {"current_steps": 32825, "total_steps": 40000, "loss": 0.0, "lr": 3.866589133872317e-06, "epoch": 364.72222222222223, "percentage": 82.06, "elapsed_time": "3:43:09", "remaining_time": "0:48:46", "throughput": 686.84, "total_tokens": 9196576} {"current_steps": 32830, "total_steps": 40000, "loss": 0.0, "lr": 3.861345930320948e-06, "epoch": 364.77777777777777, "percentage": 82.08, "elapsed_time": "3:43:11", "remaining_time": "0:48:44", "throughput": 686.84, "total_tokens": 9197952} {"current_steps": 32835, "total_steps": 40000, "loss": 0.0, "lr": 3.856105986615688e-06, "epoch": 364.8333333333333, "percentage": 82.09, "elapsed_time": "3:43:13", "remaining_time": "0:48:42", "throughput": 686.84, "total_tokens": 9199360} {"current_steps": 32840, "total_steps": 40000, "loss": 0.0, "lr": 3.850869303564589e-06, "epoch": 364.8888888888889, "percentage": 82.1, "elapsed_time": "3:43:15", "remaining_time": "0:48:40", "throughput": 686.85, "total_tokens": 9200800} {"current_steps": 32845, "total_steps": 40000, "loss": 0.0, "lr": 3.845635881975226e-06, "epoch": 364.94444444444446, "percentage": 82.11, "elapsed_time": "3:43:17", "remaining_time": "0:48:38", "throughput": 686.85, "total_tokens": 9202144} {"current_steps": 32850, "total_steps": 40000, "loss": 0.0, "lr": 3.840405722654647e-06, "epoch": 365.0, "percentage": 82.12, "elapsed_time": "3:43:19", "remaining_time": "0:48:36", "throughput": 686.84, "total_tokens": 9203520} {"current_steps": 32855, "total_steps": 40000, "loss": 0.0, "lr": 3.835178826409419e-06, "epoch": 365.05555555555554, "percentage": 82.14, "elapsed_time": "3:43:21", "remaining_time": "0:48:34", "throughput": 686.83, "total_tokens": 9204928} {"current_steps": 32860, "total_steps": 40000, "loss": 0.0, "lr": 3.8299551940455895e-06, "epoch": 365.1111111111111, "percentage": 82.15, "elapsed_time": "3:43:23", "remaining_time": "0:48:32", "throughput": 686.84, "total_tokens": 9206304} {"current_steps": 32865, "total_steps": 40000, "loss": 0.0, "lr": 3.824734826368703e-06, "epoch": 365.1666666666667, "percentage": 82.16, "elapsed_time": "3:43:25", "remaining_time": "0:48:30", "throughput": 686.83, "total_tokens": 9207680} {"current_steps": 32870, "total_steps": 40000, "loss": 0.0, "lr": 3.819517724183813e-06, "epoch": 365.22222222222223, "percentage": 82.17, "elapsed_time": "3:43:28", "remaining_time": "0:48:28", "throughput": 686.84, "total_tokens": 9209152} {"current_steps": 32875, "total_steps": 40000, "loss": 0.0, "lr": 3.8143038882954648e-06, "epoch": 365.27777777777777, "percentage": 82.19, "elapsed_time": "3:43:30", "remaining_time": "0:48:26", "throughput": 686.84, "total_tokens": 9210560} {"current_steps": 32880, "total_steps": 40000, "loss": 0.0, "lr": 3.8090933195076867e-06, "epoch": 365.3333333333333, "percentage": 82.2, "elapsed_time": "3:43:32", "remaining_time": "0:48:24", "throughput": 686.85, "total_tokens": 9212016} {"current_steps": 32885, "total_steps": 40000, "loss": 0.0, "lr": 3.8038860186240198e-06, "epoch": 365.3888888888889, "percentage": 82.21, "elapsed_time": "3:43:34", "remaining_time": "0:48:22", "throughput": 686.85, "total_tokens": 9213456} {"current_steps": 32890, "total_steps": 40000, "loss": 0.0, "lr": 3.7986819864475026e-06, "epoch": 365.44444444444446, "percentage": 82.23, "elapsed_time": "3:43:35", "remaining_time": "0:48:20", "throughput": 686.86, "total_tokens": 9214816} {"current_steps": 32895, "total_steps": 40000, "loss": 0.0, "lr": 3.793481223780651e-06, "epoch": 365.5, "percentage": 82.24, "elapsed_time": "3:43:37", "remaining_time": "0:48:18", "throughput": 686.86, "total_tokens": 9216240} {"current_steps": 32900, "total_steps": 40000, "loss": 0.0, "lr": 3.788283731425496e-06, "epoch": 365.55555555555554, "percentage": 82.25, "elapsed_time": "3:43:39", "remaining_time": "0:48:16", "throughput": 686.87, "total_tokens": 9217648} {"current_steps": 32905, "total_steps": 40000, "loss": 0.0, "lr": 3.7830895101835488e-06, "epoch": 365.6111111111111, "percentage": 82.26, "elapsed_time": "3:43:41", "remaining_time": "0:48:14", "throughput": 686.87, "total_tokens": 9219040} {"current_steps": 32910, "total_steps": 40000, "loss": 0.0, "lr": 3.7778985608558274e-06, "epoch": 365.6666666666667, "percentage": 82.27, "elapsed_time": "3:43:43", "remaining_time": "0:48:11", "throughput": 686.87, "total_tokens": 9220480} {"current_steps": 32915, "total_steps": 40000, "loss": 0.0, "lr": 3.7727108842428443e-06, "epoch": 365.72222222222223, "percentage": 82.29, "elapsed_time": "3:43:45", "remaining_time": "0:48:09", "throughput": 686.87, "total_tokens": 9221872} {"current_steps": 32920, "total_steps": 40000, "loss": 0.0, "lr": 3.7675264811446065e-06, "epoch": 365.77777777777777, "percentage": 82.3, "elapsed_time": "3:43:47", "remaining_time": "0:48:07", "throughput": 686.87, "total_tokens": 9223264} {"current_steps": 32925, "total_steps": 40000, "loss": 0.0, "lr": 3.7623453523605994e-06, "epoch": 365.8333333333333, "percentage": 82.31, "elapsed_time": "3:43:49", "remaining_time": "0:48:05", "throughput": 686.87, "total_tokens": 9224656} {"current_steps": 32930, "total_steps": 40000, "loss": 0.0, "lr": 3.757167498689834e-06, "epoch": 365.8888888888889, "percentage": 82.33, "elapsed_time": "3:43:51", "remaining_time": "0:48:03", "throughput": 686.87, "total_tokens": 9226000} {"current_steps": 32935, "total_steps": 40000, "loss": 0.0, "lr": 3.7519929209307914e-06, "epoch": 365.94444444444446, "percentage": 82.34, "elapsed_time": "3:43:53", "remaining_time": "0:48:01", "throughput": 686.88, "total_tokens": 9227360} {"current_steps": 32940, "total_steps": 40000, "loss": 0.0, "lr": 3.746821619881463e-06, "epoch": 366.0, "percentage": 82.35, "elapsed_time": "3:43:55", "remaining_time": "0:47:59", "throughput": 686.87, "total_tokens": 9228736} {"current_steps": 32945, "total_steps": 40000, "loss": 0.0, "lr": 3.74165359633932e-06, "epoch": 366.05555555555554, "percentage": 82.36, "elapsed_time": "3:43:58", "remaining_time": "0:47:57", "throughput": 686.86, "total_tokens": 9230144} {"current_steps": 32950, "total_steps": 40000, "loss": 0.0, "lr": 3.736488851101341e-06, "epoch": 366.1111111111111, "percentage": 82.38, "elapsed_time": "3:44:00", "remaining_time": "0:47:55", "throughput": 686.87, "total_tokens": 9231552} {"current_steps": 32955, "total_steps": 40000, "loss": 0.0, "lr": 3.7313273849640035e-06, "epoch": 366.1666666666667, "percentage": 82.39, "elapsed_time": "3:44:02", "remaining_time": "0:47:53", "throughput": 686.86, "total_tokens": 9232928} {"current_steps": 32960, "total_steps": 40000, "loss": 0.0, "lr": 3.7261691987232533e-06, "epoch": 366.22222222222223, "percentage": 82.4, "elapsed_time": "3:44:04", "remaining_time": "0:47:51", "throughput": 686.86, "total_tokens": 9234320} {"current_steps": 32965, "total_steps": 40000, "loss": 0.0, "lr": 3.7210142931745575e-06, "epoch": 366.27777777777777, "percentage": 82.41, "elapsed_time": "3:44:06", "remaining_time": "0:47:49", "throughput": 686.86, "total_tokens": 9235664} {"current_steps": 32970, "total_steps": 40000, "loss": 0.0, "lr": 3.7158626691128712e-06, "epoch": 366.3333333333333, "percentage": 82.42, "elapsed_time": "3:44:08", "remaining_time": "0:47:47", "throughput": 686.86, "total_tokens": 9237056} {"current_steps": 32975, "total_steps": 40000, "loss": 0.0, "lr": 3.710714327332629e-06, "epoch": 366.3888888888889, "percentage": 82.44, "elapsed_time": "3:44:10", "remaining_time": "0:47:45", "throughput": 686.86, "total_tokens": 9238432} {"current_steps": 32980, "total_steps": 40000, "loss": 0.0, "lr": 3.7055692686277815e-06, "epoch": 366.44444444444446, "percentage": 82.45, "elapsed_time": "3:44:12", "remaining_time": "0:47:43", "throughput": 686.87, "total_tokens": 9239840} {"current_steps": 32985, "total_steps": 40000, "loss": 0.0, "lr": 3.70042749379175e-06, "epoch": 366.5, "percentage": 82.46, "elapsed_time": "3:44:14", "remaining_time": "0:47:41", "throughput": 686.87, "total_tokens": 9241232} {"current_steps": 32990, "total_steps": 40000, "loss": 0.0, "lr": 3.6952890036174693e-06, "epoch": 366.55555555555554, "percentage": 82.47, "elapsed_time": "3:44:15", "remaining_time": "0:47:39", "throughput": 686.88, "total_tokens": 9242640} {"current_steps": 32995, "total_steps": 40000, "loss": 0.0, "lr": 3.690153798897353e-06, "epoch": 366.6111111111111, "percentage": 82.49, "elapsed_time": "3:44:17", "remaining_time": "0:47:37", "throughput": 686.89, "total_tokens": 9244096} {"current_steps": 33000, "total_steps": 40000, "loss": 0.0, "lr": 3.6850218804233225e-06, "epoch": 366.6666666666667, "percentage": 82.5, "elapsed_time": "3:44:19", "remaining_time": "0:47:35", "throughput": 686.89, "total_tokens": 9245504} {"current_steps": 33000, "total_steps": 40000, "eval_loss": 0.37106671929359436, "epoch": 366.6666666666667, "percentage": 82.5, "elapsed_time": "3:44:21", "remaining_time": "0:47:35", "throughput": 686.82, "total_tokens": 9245504} {"current_steps": 33005, "total_steps": 40000, "loss": 0.0, "lr": 3.679893248986779e-06, "epoch": 366.72222222222223, "percentage": 82.51, "elapsed_time": "3:44:24", "remaining_time": "0:47:33", "throughput": 686.74, "total_tokens": 9246896} {"current_steps": 33010, "total_steps": 40000, "loss": 0.0, "lr": 3.6747679053786147e-06, "epoch": 366.77777777777777, "percentage": 82.53, "elapsed_time": "3:44:26", "remaining_time": "0:47:31", "throughput": 686.75, "total_tokens": 9248336} {"current_steps": 33015, "total_steps": 40000, "loss": 0.0, "lr": 3.669645850389228e-06, "epoch": 366.8333333333333, "percentage": 82.54, "elapsed_time": "3:44:28", "remaining_time": "0:47:29", "throughput": 686.75, "total_tokens": 9249760} {"current_steps": 33020, "total_steps": 40000, "loss": 0.0, "lr": 3.664527084808514e-06, "epoch": 366.8888888888889, "percentage": 82.55, "elapsed_time": "3:44:30", "remaining_time": "0:47:27", "throughput": 686.75, "total_tokens": 9251136} {"current_steps": 33025, "total_steps": 40000, "loss": 0.0, "lr": 3.6594116094258337e-06, "epoch": 366.94444444444446, "percentage": 82.56, "elapsed_time": "3:44:32", "remaining_time": "0:47:25", "throughput": 686.75, "total_tokens": 9252512} {"current_steps": 33030, "total_steps": 40000, "loss": 0.0, "lr": 3.6542994250300665e-06, "epoch": 367.0, "percentage": 82.58, "elapsed_time": "3:44:34", "remaining_time": "0:47:23", "throughput": 686.75, "total_tokens": 9253952} {"current_steps": 33035, "total_steps": 40000, "loss": 0.0, "lr": 3.6491905324095825e-06, "epoch": 367.05555555555554, "percentage": 82.59, "elapsed_time": "3:44:37", "remaining_time": "0:47:21", "throughput": 686.74, "total_tokens": 9255360} {"current_steps": 33040, "total_steps": 40000, "loss": 0.0, "lr": 3.644084932352221e-06, "epoch": 367.1111111111111, "percentage": 82.6, "elapsed_time": "3:44:39", "remaining_time": "0:47:19", "throughput": 686.75, "total_tokens": 9256704} {"current_steps": 33045, "total_steps": 40000, "loss": 0.0, "lr": 3.6389826256453457e-06, "epoch": 367.1666666666667, "percentage": 82.61, "elapsed_time": "3:44:41", "remaining_time": "0:47:17", "throughput": 686.75, "total_tokens": 9258096} {"current_steps": 33050, "total_steps": 40000, "loss": 0.0, "lr": 3.633883613075781e-06, "epoch": 367.22222222222223, "percentage": 82.62, "elapsed_time": "3:44:43", "remaining_time": "0:47:15", "throughput": 686.75, "total_tokens": 9259488} {"current_steps": 33055, "total_steps": 40000, "loss": 0.0, "lr": 3.6287878954298693e-06, "epoch": 367.27777777777777, "percentage": 82.64, "elapsed_time": "3:44:45", "remaining_time": "0:47:13", "throughput": 686.75, "total_tokens": 9260880} {"current_steps": 33060, "total_steps": 40000, "loss": 0.0, "lr": 3.6236954734934354e-06, "epoch": 367.3333333333333, "percentage": 82.65, "elapsed_time": "3:44:47", "remaining_time": "0:47:11", "throughput": 686.75, "total_tokens": 9262320} {"current_steps": 33065, "total_steps": 40000, "loss": 0.0, "lr": 3.618606348051784e-06, "epoch": 367.3888888888889, "percentage": 82.66, "elapsed_time": "3:44:49", "remaining_time": "0:47:09", "throughput": 686.75, "total_tokens": 9263696} {"current_steps": 33070, "total_steps": 40000, "loss": 0.0, "lr": 3.6135205198897376e-06, "epoch": 367.44444444444446, "percentage": 82.67, "elapsed_time": "3:44:51", "remaining_time": "0:47:07", "throughput": 686.75, "total_tokens": 9265072} {"current_steps": 33075, "total_steps": 40000, "loss": 0.0, "lr": 3.6084379897915854e-06, "epoch": 367.5, "percentage": 82.69, "elapsed_time": "3:44:53", "remaining_time": "0:47:05", "throughput": 686.75, "total_tokens": 9266480} {"current_steps": 33080, "total_steps": 40000, "loss": 0.0, "lr": 3.6033587585411115e-06, "epoch": 367.55555555555554, "percentage": 82.7, "elapsed_time": "3:44:55", "remaining_time": "0:47:03", "throughput": 686.76, "total_tokens": 9267920} {"current_steps": 33085, "total_steps": 40000, "loss": 0.0, "lr": 3.5982828269216117e-06, "epoch": 367.6111111111111, "percentage": 82.71, "elapsed_time": "3:44:57", "remaining_time": "0:47:00", "throughput": 686.77, "total_tokens": 9269328} {"current_steps": 33090, "total_steps": 40000, "loss": 0.0, "lr": 3.593210195715843e-06, "epoch": 367.6666666666667, "percentage": 82.73, "elapsed_time": "3:44:58", "remaining_time": "0:46:58", "throughput": 686.77, "total_tokens": 9270736} {"current_steps": 33095, "total_steps": 40000, "loss": 0.0, "lr": 3.5881408657060773e-06, "epoch": 367.72222222222223, "percentage": 82.74, "elapsed_time": "3:45:00", "remaining_time": "0:46:56", "throughput": 686.78, "total_tokens": 9272128} {"current_steps": 33100, "total_steps": 40000, "loss": 0.0, "lr": 3.583074837674075e-06, "epoch": 367.77777777777777, "percentage": 82.75, "elapsed_time": "3:45:02", "remaining_time": "0:46:54", "throughput": 686.78, "total_tokens": 9273488} {"current_steps": 33105, "total_steps": 40000, "loss": 0.0, "lr": 3.578012112401069e-06, "epoch": 367.8333333333333, "percentage": 82.76, "elapsed_time": "3:45:04", "remaining_time": "0:46:52", "throughput": 686.78, "total_tokens": 9274928} {"current_steps": 33110, "total_steps": 40000, "loss": 0.0, "lr": 3.5729526906677996e-06, "epoch": 367.8888888888889, "percentage": 82.78, "elapsed_time": "3:45:06", "remaining_time": "0:46:50", "throughput": 686.79, "total_tokens": 9276400} {"current_steps": 33115, "total_steps": 40000, "loss": 0.0, "lr": 3.5678965732545007e-06, "epoch": 367.94444444444446, "percentage": 82.79, "elapsed_time": "3:45:08", "remaining_time": "0:46:48", "throughput": 686.79, "total_tokens": 9277776} {"current_steps": 33120, "total_steps": 40000, "loss": 0.0, "lr": 3.562843760940876e-06, "epoch": 368.0, "percentage": 82.8, "elapsed_time": "3:45:11", "remaining_time": "0:46:46", "throughput": 686.78, "total_tokens": 9279200} {"current_steps": 33125, "total_steps": 40000, "loss": 0.0, "lr": 3.5577942545061473e-06, "epoch": 368.05555555555554, "percentage": 82.81, "elapsed_time": "3:45:13", "remaining_time": "0:46:44", "throughput": 686.77, "total_tokens": 9280608} {"current_steps": 33130, "total_steps": 40000, "loss": 0.0, "lr": 3.5527480547289967e-06, "epoch": 368.1111111111111, "percentage": 82.83, "elapsed_time": "3:45:15", "remaining_time": "0:46:42", "throughput": 686.77, "total_tokens": 9281984} {"current_steps": 33135, "total_steps": 40000, "loss": 0.0, "lr": 3.547705162387624e-06, "epoch": 368.1666666666667, "percentage": 82.84, "elapsed_time": "3:45:17", "remaining_time": "0:46:40", "throughput": 686.78, "total_tokens": 9283408} {"current_steps": 33140, "total_steps": 40000, "loss": 0.0, "lr": 3.542665578259699e-06, "epoch": 368.22222222222223, "percentage": 82.85, "elapsed_time": "3:45:19", "remaining_time": "0:46:38", "throughput": 686.78, "total_tokens": 9284800} {"current_steps": 33145, "total_steps": 40000, "loss": 0.0, "lr": 3.5376293031223945e-06, "epoch": 368.27777777777777, "percentage": 82.86, "elapsed_time": "3:45:21", "remaining_time": "0:46:36", "throughput": 686.79, "total_tokens": 9286208} {"current_steps": 33150, "total_steps": 40000, "loss": 0.0, "lr": 3.5325963377523614e-06, "epoch": 368.3333333333333, "percentage": 82.88, "elapsed_time": "3:45:23", "remaining_time": "0:46:34", "throughput": 686.79, "total_tokens": 9287568} {"current_steps": 33155, "total_steps": 40000, "loss": 0.0, "lr": 3.5275666829257536e-06, "epoch": 368.3888888888889, "percentage": 82.89, "elapsed_time": "3:45:25", "remaining_time": "0:46:32", "throughput": 686.79, "total_tokens": 9288992} {"current_steps": 33160, "total_steps": 40000, "loss": 0.0, "lr": 3.5225403394181955e-06, "epoch": 368.44444444444446, "percentage": 82.9, "elapsed_time": "3:45:27", "remaining_time": "0:46:30", "throughput": 686.79, "total_tokens": 9290384} {"current_steps": 33165, "total_steps": 40000, "loss": 0.0, "lr": 3.517517308004828e-06, "epoch": 368.5, "percentage": 82.91, "elapsed_time": "3:45:29", "remaining_time": "0:46:28", "throughput": 686.8, "total_tokens": 9291824} {"current_steps": 33170, "total_steps": 40000, "loss": 0.0, "lr": 3.512497589460251e-06, "epoch": 368.55555555555554, "percentage": 82.93, "elapsed_time": "3:45:31", "remaining_time": "0:46:26", "throughput": 686.8, "total_tokens": 9293248} {"current_steps": 33175, "total_steps": 40000, "loss": 0.0, "lr": 3.5074811845585727e-06, "epoch": 368.6111111111111, "percentage": 82.94, "elapsed_time": "3:45:33", "remaining_time": "0:46:24", "throughput": 686.8, "total_tokens": 9294624} {"current_steps": 33180, "total_steps": 40000, "loss": 0.0, "lr": 3.5024680940733937e-06, "epoch": 368.6666666666667, "percentage": 82.95, "elapsed_time": "3:45:35", "remaining_time": "0:46:22", "throughput": 686.8, "total_tokens": 9295984} {"current_steps": 33185, "total_steps": 40000, "loss": 0.0, "lr": 3.4974583187777852e-06, "epoch": 368.72222222222223, "percentage": 82.96, "elapsed_time": "3:45:37", "remaining_time": "0:46:20", "throughput": 686.8, "total_tokens": 9297392} {"current_steps": 33190, "total_steps": 40000, "loss": 0.0, "lr": 3.4924518594443204e-06, "epoch": 368.77777777777777, "percentage": 82.97, "elapsed_time": "3:45:39", "remaining_time": "0:46:17", "throughput": 686.8, "total_tokens": 9298752} {"current_steps": 33195, "total_steps": 40000, "loss": 0.0, "lr": 3.4874487168450682e-06, "epoch": 368.8333333333333, "percentage": 82.99, "elapsed_time": "3:45:41", "remaining_time": "0:46:15", "throughput": 686.81, "total_tokens": 9300112} {"current_steps": 33200, "total_steps": 40000, "loss": 0.0, "lr": 3.482448891751558e-06, "epoch": 368.8888888888889, "percentage": 83.0, "elapsed_time": "3:45:43", "remaining_time": "0:46:13", "throughput": 686.81, "total_tokens": 9301520} {"current_steps": 33200, "total_steps": 40000, "eval_loss": 0.349362313747406, "epoch": 368.8888888888889, "percentage": 83.0, "elapsed_time": "3:45:44", "remaining_time": "0:46:14", "throughput": 686.75, "total_tokens": 9301520} {"current_steps": 33205, "total_steps": 40000, "loss": 0.0, "lr": 3.477452384934843e-06, "epoch": 368.94444444444446, "percentage": 83.01, "elapsed_time": "3:45:49", "remaining_time": "0:46:12", "throughput": 686.62, "total_tokens": 9302976} {"current_steps": 33210, "total_steps": 40000, "loss": 0.0, "lr": 3.472459197165434e-06, "epoch": 369.0, "percentage": 83.03, "elapsed_time": "3:45:51", "remaining_time": "0:46:10", "throughput": 686.61, "total_tokens": 9304400} {"current_steps": 33215, "total_steps": 40000, "loss": 0.0, "lr": 3.4674693292133518e-06, "epoch": 369.05555555555554, "percentage": 83.04, "elapsed_time": "3:45:53", "remaining_time": "0:46:08", "throughput": 686.6, "total_tokens": 9305840} {"current_steps": 33220, "total_steps": 40000, "loss": 0.0, "lr": 3.4624827818480977e-06, "epoch": 369.1111111111111, "percentage": 83.05, "elapsed_time": "3:45:55", "remaining_time": "0:46:06", "throughput": 686.6, "total_tokens": 9307216} {"current_steps": 33225, "total_steps": 40000, "loss": 0.0, "lr": 3.4574995558386474e-06, "epoch": 369.1666666666667, "percentage": 83.06, "elapsed_time": "3:45:57", "remaining_time": "0:46:04", "throughput": 686.6, "total_tokens": 9308624} {"current_steps": 33230, "total_steps": 40000, "loss": 0.0, "lr": 3.452519651953487e-06, "epoch": 369.22222222222223, "percentage": 83.08, "elapsed_time": "3:45:59", "remaining_time": "0:46:02", "throughput": 686.6, "total_tokens": 9310032} {"current_steps": 33235, "total_steps": 40000, "loss": 0.0, "lr": 3.447543070960585e-06, "epoch": 369.27777777777777, "percentage": 83.09, "elapsed_time": "3:46:01", "remaining_time": "0:46:00", "throughput": 686.6, "total_tokens": 9311440} {"current_steps": 33240, "total_steps": 40000, "loss": 0.0, "lr": 3.4425698136273778e-06, "epoch": 369.3333333333333, "percentage": 83.1, "elapsed_time": "3:46:03", "remaining_time": "0:45:58", "throughput": 686.6, "total_tokens": 9312864} {"current_steps": 33245, "total_steps": 40000, "loss": 0.0, "lr": 3.437599880720821e-06, "epoch": 369.3888888888889, "percentage": 83.11, "elapsed_time": "3:46:05", "remaining_time": "0:45:56", "throughput": 686.61, "total_tokens": 9314304} {"current_steps": 33250, "total_steps": 40000, "loss": 0.0, "lr": 3.4326332730073267e-06, "epoch": 369.44444444444446, "percentage": 83.12, "elapsed_time": "3:46:07", "remaining_time": "0:45:54", "throughput": 686.62, "total_tokens": 9315680} {"current_steps": 33255, "total_steps": 40000, "loss": 0.0, "lr": 3.427669991252813e-06, "epoch": 369.5, "percentage": 83.14, "elapsed_time": "3:46:09", "remaining_time": "0:45:52", "throughput": 686.62, "total_tokens": 9317056} {"current_steps": 33260, "total_steps": 40000, "loss": 0.0, "lr": 3.42271003622269e-06, "epoch": 369.55555555555554, "percentage": 83.15, "elapsed_time": "3:46:11", "remaining_time": "0:45:50", "throughput": 686.62, "total_tokens": 9318448} {"current_steps": 33265, "total_steps": 40000, "loss": 0.0, "lr": 3.4177534086818286e-06, "epoch": 369.6111111111111, "percentage": 83.16, "elapsed_time": "3:46:13", "remaining_time": "0:45:48", "throughput": 686.63, "total_tokens": 9319824} {"current_steps": 33270, "total_steps": 40000, "loss": 0.0, "lr": 3.412800109394612e-06, "epoch": 369.6666666666667, "percentage": 83.17, "elapsed_time": "3:46:15", "remaining_time": "0:45:46", "throughput": 686.64, "total_tokens": 9321296} {"current_steps": 33275, "total_steps": 40000, "loss": 0.0, "lr": 3.4078501391249044e-06, "epoch": 369.72222222222223, "percentage": 83.19, "elapsed_time": "3:46:17", "remaining_time": "0:45:44", "throughput": 686.64, "total_tokens": 9322688} {"current_steps": 33280, "total_steps": 40000, "loss": 0.0, "lr": 3.4029034986360453e-06, "epoch": 369.77777777777777, "percentage": 83.2, "elapsed_time": "3:46:19", "remaining_time": "0:45:41", "throughput": 686.64, "total_tokens": 9324096} {"current_steps": 33285, "total_steps": 40000, "loss": 0.0, "lr": 3.397960188690877e-06, "epoch": 369.8333333333333, "percentage": 83.21, "elapsed_time": "3:46:21", "remaining_time": "0:45:39", "throughput": 686.64, "total_tokens": 9325456} {"current_steps": 33290, "total_steps": 40000, "loss": 0.0, "lr": 3.393020210051717e-06, "epoch": 369.8888888888889, "percentage": 83.23, "elapsed_time": "3:46:23", "remaining_time": "0:45:37", "throughput": 686.64, "total_tokens": 9326848} {"current_steps": 33295, "total_steps": 40000, "loss": 0.0, "lr": 3.3880835634803655e-06, "epoch": 369.94444444444446, "percentage": 83.24, "elapsed_time": "3:46:25", "remaining_time": "0:45:35", "throughput": 686.64, "total_tokens": 9328288} {"current_steps": 33300, "total_steps": 40000, "loss": 0.0, "lr": 3.383150249738126e-06, "epoch": 370.0, "percentage": 83.25, "elapsed_time": "3:46:27", "remaining_time": "0:45:33", "throughput": 686.63, "total_tokens": 9329712} {"current_steps": 33305, "total_steps": 40000, "loss": 0.0, "lr": 3.3782202695857663e-06, "epoch": 370.05555555555554, "percentage": 83.26, "elapsed_time": "3:46:29", "remaining_time": "0:45:31", "throughput": 686.62, "total_tokens": 9331120} {"current_steps": 33310, "total_steps": 40000, "loss": 0.0, "lr": 3.373293623783558e-06, "epoch": 370.1111111111111, "percentage": 83.28, "elapsed_time": "3:46:31", "remaining_time": "0:45:29", "throughput": 686.63, "total_tokens": 9332528} {"current_steps": 33315, "total_steps": 40000, "loss": 0.0, "lr": 3.368370313091257e-06, "epoch": 370.1666666666667, "percentage": 83.29, "elapsed_time": "3:46:33", "remaining_time": "0:45:27", "throughput": 686.64, "total_tokens": 9333968} {"current_steps": 33320, "total_steps": 40000, "loss": 0.0, "lr": 3.363450338268087e-06, "epoch": 370.22222222222223, "percentage": 83.3, "elapsed_time": "3:46:35", "remaining_time": "0:45:25", "throughput": 686.64, "total_tokens": 9335344} {"current_steps": 33325, "total_steps": 40000, "loss": 0.0, "lr": 3.358533700072783e-06, "epoch": 370.27777777777777, "percentage": 83.31, "elapsed_time": "3:46:37", "remaining_time": "0:45:23", "throughput": 686.64, "total_tokens": 9336720} {"current_steps": 33330, "total_steps": 40000, "loss": 0.0, "lr": 3.3536203992635377e-06, "epoch": 370.3333333333333, "percentage": 83.33, "elapsed_time": "3:46:39", "remaining_time": "0:45:21", "throughput": 686.65, "total_tokens": 9338160} {"current_steps": 33335, "total_steps": 40000, "loss": 0.0, "lr": 3.348710436598057e-06, "epoch": 370.3888888888889, "percentage": 83.34, "elapsed_time": "3:46:41", "remaining_time": "0:45:19", "throughput": 686.66, "total_tokens": 9339584} {"current_steps": 33340, "total_steps": 40000, "loss": 0.0, "lr": 3.3438038128335155e-06, "epoch": 370.44444444444446, "percentage": 83.35, "elapsed_time": "3:46:43", "remaining_time": "0:45:17", "throughput": 686.66, "total_tokens": 9340992} {"current_steps": 33345, "total_steps": 40000, "loss": 0.0, "lr": 3.338900528726571e-06, "epoch": 370.5, "percentage": 83.36, "elapsed_time": "3:46:45", "remaining_time": "0:45:15", "throughput": 686.66, "total_tokens": 9342400} {"current_steps": 33350, "total_steps": 40000, "loss": 0.0, "lr": 3.3340005850333812e-06, "epoch": 370.55555555555554, "percentage": 83.38, "elapsed_time": "3:46:47", "remaining_time": "0:45:13", "throughput": 686.66, "total_tokens": 9343760} {"current_steps": 33355, "total_steps": 40000, "loss": 0.0, "lr": 3.329103982509568e-06, "epoch": 370.6111111111111, "percentage": 83.39, "elapsed_time": "3:46:49", "remaining_time": "0:45:11", "throughput": 686.66, "total_tokens": 9345152} {"current_steps": 33360, "total_steps": 40000, "loss": 0.0, "lr": 3.324210721910259e-06, "epoch": 370.6666666666667, "percentage": 83.4, "elapsed_time": "3:46:51", "remaining_time": "0:45:09", "throughput": 686.66, "total_tokens": 9346528} {"current_steps": 33365, "total_steps": 40000, "loss": 0.0, "lr": 3.319320803990053e-06, "epoch": 370.72222222222223, "percentage": 83.41, "elapsed_time": "3:46:53", "remaining_time": "0:45:07", "throughput": 686.66, "total_tokens": 9347920} {"current_steps": 33370, "total_steps": 40000, "loss": 0.0, "lr": 3.3144342295030274e-06, "epoch": 370.77777777777777, "percentage": 83.43, "elapsed_time": "3:46:55", "remaining_time": "0:45:05", "throughput": 686.65, "total_tokens": 9349296} {"current_steps": 33375, "total_steps": 40000, "loss": 0.0, "lr": 3.309550999202765e-06, "epoch": 370.8333333333333, "percentage": 83.44, "elapsed_time": "3:46:57", "remaining_time": "0:45:03", "throughput": 686.66, "total_tokens": 9350656} {"current_steps": 33380, "total_steps": 40000, "loss": 0.0, "lr": 3.3046711138423197e-06, "epoch": 370.8888888888889, "percentage": 83.45, "elapsed_time": "3:46:59", "remaining_time": "0:45:01", "throughput": 686.66, "total_tokens": 9352064} {"current_steps": 33385, "total_steps": 40000, "loss": 0.0, "lr": 3.2997945741742255e-06, "epoch": 370.94444444444446, "percentage": 83.46, "elapsed_time": "3:47:01", "remaining_time": "0:44:59", "throughput": 686.67, "total_tokens": 9353472} {"current_steps": 33390, "total_steps": 40000, "loss": 0.0, "lr": 3.2949213809505082e-06, "epoch": 371.0, "percentage": 83.47, "elapsed_time": "3:47:03", "remaining_time": "0:44:56", "throughput": 686.67, "total_tokens": 9354896} {"current_steps": 33395, "total_steps": 40000, "loss": 0.0, "lr": 3.2900515349226834e-06, "epoch": 371.05555555555554, "percentage": 83.49, "elapsed_time": "3:47:05", "remaining_time": "0:44:54", "throughput": 686.66, "total_tokens": 9356288} {"current_steps": 33400, "total_steps": 40000, "loss": 0.0, "lr": 3.285185036841731e-06, "epoch": 371.1111111111111, "percentage": 83.5, "elapsed_time": "3:47:07", "remaining_time": "0:44:52", "throughput": 686.67, "total_tokens": 9357712} {"current_steps": 33400, "total_steps": 40000, "eval_loss": 0.33894291520118713, "epoch": 371.1111111111111, "percentage": 83.5, "elapsed_time": "3:47:09", "remaining_time": "0:44:53", "throughput": 686.6, "total_tokens": 9357712} {"current_steps": 33405, "total_steps": 40000, "loss": 0.0, "lr": 3.2803218874581377e-06, "epoch": 371.1666666666667, "percentage": 83.51, "elapsed_time": "3:47:12", "remaining_time": "0:44:51", "throughput": 686.53, "total_tokens": 9359120} {"current_steps": 33410, "total_steps": 40000, "loss": 0.0, "lr": 3.2754620875218494e-06, "epoch": 371.22222222222223, "percentage": 83.53, "elapsed_time": "3:47:14", "remaining_time": "0:44:49", "throughput": 686.54, "total_tokens": 9360560} {"current_steps": 33415, "total_steps": 40000, "loss": 0.0, "lr": 3.2706056377823146e-06, "epoch": 371.27777777777777, "percentage": 83.54, "elapsed_time": "3:47:16", "remaining_time": "0:44:47", "throughput": 686.53, "total_tokens": 9361888} {"current_steps": 33420, "total_steps": 40000, "loss": 0.0, "lr": 3.2657525389884647e-06, "epoch": 371.3333333333333, "percentage": 83.55, "elapsed_time": "3:47:18", "remaining_time": "0:44:45", "throughput": 686.53, "total_tokens": 9363296} {"current_steps": 33425, "total_steps": 40000, "loss": 0.0, "lr": 3.260902791888698e-06, "epoch": 371.3888888888889, "percentage": 83.56, "elapsed_time": "3:47:20", "remaining_time": "0:44:43", "throughput": 686.53, "total_tokens": 9364720} {"current_steps": 33430, "total_steps": 40000, "loss": 0.0, "lr": 3.2560563972309166e-06, "epoch": 371.44444444444446, "percentage": 83.58, "elapsed_time": "3:47:22", "remaining_time": "0:44:41", "throughput": 686.53, "total_tokens": 9366160} {"current_steps": 33435, "total_steps": 40000, "loss": 0.0, "lr": 3.251213355762489e-06, "epoch": 371.5, "percentage": 83.59, "elapsed_time": "3:47:24", "remaining_time": "0:44:39", "throughput": 686.53, "total_tokens": 9367568} {"current_steps": 33440, "total_steps": 40000, "loss": 0.0, "lr": 3.2463736682302707e-06, "epoch": 371.55555555555554, "percentage": 83.6, "elapsed_time": "3:47:26", "remaining_time": "0:44:37", "throughput": 686.54, "total_tokens": 9368976} {"current_steps": 33445, "total_steps": 40000, "loss": 0.0, "lr": 3.2415373353806124e-06, "epoch": 371.6111111111111, "percentage": 83.61, "elapsed_time": "3:47:28", "remaining_time": "0:44:35", "throughput": 686.54, "total_tokens": 9370384} {"current_steps": 33450, "total_steps": 40000, "loss": 0.0, "lr": 3.236704357959322e-06, "epoch": 371.6666666666667, "percentage": 83.62, "elapsed_time": "3:47:30", "remaining_time": "0:44:32", "throughput": 686.54, "total_tokens": 9371744} {"current_steps": 33455, "total_steps": 40000, "loss": 0.0, "lr": 3.2318747367117154e-06, "epoch": 371.72222222222223, "percentage": 83.64, "elapsed_time": "3:47:32", "remaining_time": "0:44:30", "throughput": 686.55, "total_tokens": 9373136} {"current_steps": 33460, "total_steps": 40000, "loss": 0.0, "lr": 3.227048472382585e-06, "epoch": 371.77777777777777, "percentage": 83.65, "elapsed_time": "3:47:34", "remaining_time": "0:44:28", "throughput": 686.55, "total_tokens": 9374512} {"current_steps": 33465, "total_steps": 40000, "loss": 0.0, "lr": 3.2222255657161915e-06, "epoch": 371.8333333333333, "percentage": 83.66, "elapsed_time": "3:47:36", "remaining_time": "0:44:26", "throughput": 686.56, "total_tokens": 9375936} {"current_steps": 33470, "total_steps": 40000, "loss": 0.0, "lr": 3.2174060174562924e-06, "epoch": 371.8888888888889, "percentage": 83.67, "elapsed_time": "3:47:38", "remaining_time": "0:44:24", "throughput": 686.56, "total_tokens": 9377296} {"current_steps": 33475, "total_steps": 40000, "loss": 0.0, "lr": 3.2125898283461298e-06, "epoch": 371.94444444444446, "percentage": 83.69, "elapsed_time": "3:47:40", "remaining_time": "0:44:22", "throughput": 686.57, "total_tokens": 9378736} {"current_steps": 33480, "total_steps": 40000, "loss": 0.0, "lr": 3.207776999128406e-06, "epoch": 372.0, "percentage": 83.7, "elapsed_time": "3:47:42", "remaining_time": "0:44:20", "throughput": 686.56, "total_tokens": 9380112} {"current_steps": 33485, "total_steps": 40000, "loss": 0.0, "lr": 3.202967530545331e-06, "epoch": 372.05555555555554, "percentage": 83.71, "elapsed_time": "3:47:44", "remaining_time": "0:44:18", "throughput": 686.55, "total_tokens": 9381520} {"current_steps": 33490, "total_steps": 40000, "loss": 0.0, "lr": 3.1981614233385778e-06, "epoch": 372.1111111111111, "percentage": 83.73, "elapsed_time": "3:47:46", "remaining_time": "0:44:16", "throughput": 686.55, "total_tokens": 9382880} {"current_steps": 33495, "total_steps": 40000, "loss": 0.0, "lr": 3.1933586782493115e-06, "epoch": 372.1666666666667, "percentage": 83.74, "elapsed_time": "3:47:48", "remaining_time": "0:44:14", "throughput": 686.55, "total_tokens": 9384256} {"current_steps": 33500, "total_steps": 40000, "loss": 0.0, "lr": 3.188559296018184e-06, "epoch": 372.22222222222223, "percentage": 83.75, "elapsed_time": "3:47:50", "remaining_time": "0:44:12", "throughput": 686.54, "total_tokens": 9385632} {"current_steps": 33505, "total_steps": 40000, "loss": 0.0, "lr": 3.1837632773853098e-06, "epoch": 372.27777777777777, "percentage": 83.76, "elapsed_time": "3:47:52", "remaining_time": "0:44:10", "throughput": 686.54, "total_tokens": 9387040} {"current_steps": 33510, "total_steps": 40000, "loss": 0.0, "lr": 3.178970623090294e-06, "epoch": 372.3333333333333, "percentage": 83.78, "elapsed_time": "3:47:54", "remaining_time": "0:44:08", "throughput": 686.54, "total_tokens": 9388416} {"current_steps": 33515, "total_steps": 40000, "loss": 0.0, "lr": 3.174181333872234e-06, "epoch": 372.3888888888889, "percentage": 83.79, "elapsed_time": "3:47:56", "remaining_time": "0:44:06", "throughput": 686.54, "total_tokens": 9389792} {"current_steps": 33520, "total_steps": 40000, "loss": 0.0, "lr": 3.169395410469686e-06, "epoch": 372.44444444444446, "percentage": 83.8, "elapsed_time": "3:47:58", "remaining_time": "0:44:04", "throughput": 686.54, "total_tokens": 9391216} {"current_steps": 33525, "total_steps": 40000, "loss": 0.0, "lr": 3.164612853620713e-06, "epoch": 372.5, "percentage": 83.81, "elapsed_time": "3:48:00", "remaining_time": "0:44:02", "throughput": 686.55, "total_tokens": 9392656} {"current_steps": 33530, "total_steps": 40000, "loss": 0.0, "lr": 3.1598336640628333e-06, "epoch": 372.55555555555554, "percentage": 83.83, "elapsed_time": "3:48:02", "remaining_time": "0:44:00", "throughput": 686.56, "total_tokens": 9394064} {"current_steps": 33535, "total_steps": 40000, "loss": 0.0, "lr": 3.155057842533063e-06, "epoch": 372.6111111111111, "percentage": 83.84, "elapsed_time": "3:48:04", "remaining_time": "0:43:58", "throughput": 686.56, "total_tokens": 9395488} {"current_steps": 33540, "total_steps": 40000, "loss": 0.0, "lr": 3.1502853897678984e-06, "epoch": 372.6666666666667, "percentage": 83.85, "elapsed_time": "3:48:06", "remaining_time": "0:43:56", "throughput": 686.57, "total_tokens": 9396880} {"current_steps": 33545, "total_steps": 40000, "loss": 0.0, "lr": 3.1455163065033017e-06, "epoch": 372.72222222222223, "percentage": 83.86, "elapsed_time": "3:48:08", "remaining_time": "0:43:54", "throughput": 686.58, "total_tokens": 9398304} {"current_steps": 33550, "total_steps": 40000, "loss": 0.0, "lr": 3.140750593474734e-06, "epoch": 372.77777777777777, "percentage": 83.88, "elapsed_time": "3:48:10", "remaining_time": "0:43:52", "throughput": 686.58, "total_tokens": 9399680} {"current_steps": 33555, "total_steps": 40000, "loss": 0.0, "lr": 3.1359882514171294e-06, "epoch": 372.8333333333333, "percentage": 83.89, "elapsed_time": "3:48:12", "remaining_time": "0:43:49", "throughput": 686.58, "total_tokens": 9401040} {"current_steps": 33560, "total_steps": 40000, "loss": 0.0, "lr": 3.1312292810648903e-06, "epoch": 372.8888888888889, "percentage": 83.9, "elapsed_time": "3:48:14", "remaining_time": "0:43:47", "throughput": 686.58, "total_tokens": 9402432} {"current_steps": 33565, "total_steps": 40000, "loss": 0.0, "lr": 3.1264736831519204e-06, "epoch": 372.94444444444446, "percentage": 83.91, "elapsed_time": "3:48:16", "remaining_time": "0:43:45", "throughput": 686.59, "total_tokens": 9403888} {"current_steps": 33570, "total_steps": 40000, "loss": 0.0, "lr": 3.1217214584115863e-06, "epoch": 373.0, "percentage": 83.93, "elapsed_time": "3:48:18", "remaining_time": "0:43:43", "throughput": 686.58, "total_tokens": 9405296} {"current_steps": 33575, "total_steps": 40000, "loss": 0.0, "lr": 3.116972607576746e-06, "epoch": 373.05555555555554, "percentage": 83.94, "elapsed_time": "3:48:20", "remaining_time": "0:43:41", "throughput": 686.57, "total_tokens": 9406688} {"current_steps": 33580, "total_steps": 40000, "loss": 0.0, "lr": 3.1122271313797303e-06, "epoch": 373.1111111111111, "percentage": 83.95, "elapsed_time": "3:48:23", "remaining_time": "0:43:39", "throughput": 686.57, "total_tokens": 9408064} {"current_steps": 33585, "total_steps": 40000, "loss": 0.0, "lr": 3.107485030552343e-06, "epoch": 373.1666666666667, "percentage": 83.96, "elapsed_time": "3:48:25", "remaining_time": "0:43:37", "throughput": 686.57, "total_tokens": 9409440} {"current_steps": 33590, "total_steps": 40000, "loss": 0.0, "lr": 3.1027463058258848e-06, "epoch": 373.22222222222223, "percentage": 83.97, "elapsed_time": "3:48:27", "remaining_time": "0:43:35", "throughput": 686.57, "total_tokens": 9410864} {"current_steps": 33595, "total_steps": 40000, "loss": 0.0, "lr": 3.0980109579311273e-06, "epoch": 373.27777777777777, "percentage": 83.99, "elapsed_time": "3:48:29", "remaining_time": "0:43:33", "throughput": 686.57, "total_tokens": 9412256} {"current_steps": 33600, "total_steps": 40000, "loss": 0.0, "lr": 3.093278987598314e-06, "epoch": 373.3333333333333, "percentage": 84.0, "elapsed_time": "3:48:31", "remaining_time": "0:43:31", "throughput": 686.57, "total_tokens": 9413712} {"current_steps": 33600, "total_steps": 40000, "eval_loss": 0.3505513072013855, "epoch": 373.3333333333333, "percentage": 84.0, "elapsed_time": "3:48:32", "remaining_time": "0:43:31", "throughput": 686.51, "total_tokens": 9413712} {"current_steps": 33605, "total_steps": 40000, "loss": 0.0, "lr": 3.0885503955571826e-06, "epoch": 373.3888888888889, "percentage": 84.01, "elapsed_time": "3:48:35", "remaining_time": "0:43:30", "throughput": 686.44, "total_tokens": 9415120} {"current_steps": 33610, "total_steps": 40000, "loss": 0.0, "lr": 3.0838251825369313e-06, "epoch": 373.44444444444446, "percentage": 84.03, "elapsed_time": "3:48:37", "remaining_time": "0:43:28", "throughput": 686.44, "total_tokens": 9416496} {"current_steps": 33615, "total_steps": 40000, "loss": 0.0, "lr": 3.0791033492662517e-06, "epoch": 373.5, "percentage": 84.04, "elapsed_time": "3:48:39", "remaining_time": "0:43:26", "throughput": 686.44, "total_tokens": 9417872} {"current_steps": 33620, "total_steps": 40000, "loss": 0.0, "lr": 3.0743848964733203e-06, "epoch": 373.55555555555554, "percentage": 84.05, "elapsed_time": "3:48:41", "remaining_time": "0:43:23", "throughput": 686.45, "total_tokens": 9419296} {"current_steps": 33625, "total_steps": 40000, "loss": 0.0, "lr": 3.0696698248857625e-06, "epoch": 373.6111111111111, "percentage": 84.06, "elapsed_time": "3:48:43", "remaining_time": "0:43:21", "throughput": 686.45, "total_tokens": 9420656} {"current_steps": 33630, "total_steps": 40000, "loss": 0.0, "lr": 3.0649581352307192e-06, "epoch": 373.6666666666667, "percentage": 84.08, "elapsed_time": "3:48:45", "remaining_time": "0:43:19", "throughput": 686.46, "total_tokens": 9422112} {"current_steps": 33635, "total_steps": 40000, "loss": 0.0, "lr": 3.060249828234776e-06, "epoch": 373.72222222222223, "percentage": 84.09, "elapsed_time": "3:48:47", "remaining_time": "0:43:17", "throughput": 686.47, "total_tokens": 9423488} {"current_steps": 33640, "total_steps": 40000, "loss": 0.0, "lr": 3.055544904624025e-06, "epoch": 373.77777777777777, "percentage": 84.1, "elapsed_time": "3:48:49", "remaining_time": "0:43:15", "throughput": 686.47, "total_tokens": 9424880} {"current_steps": 33645, "total_steps": 40000, "loss": 0.0, "lr": 3.050843365124026e-06, "epoch": 373.8333333333333, "percentage": 84.11, "elapsed_time": "3:48:51", "remaining_time": "0:43:13", "throughput": 686.48, "total_tokens": 9426320} {"current_steps": 33650, "total_steps": 40000, "loss": 0.0, "lr": 3.0461452104598083e-06, "epoch": 373.8888888888889, "percentage": 84.12, "elapsed_time": "3:48:53", "remaining_time": "0:43:11", "throughput": 686.48, "total_tokens": 9427712} {"current_steps": 33655, "total_steps": 40000, "loss": 0.0, "lr": 3.0414504413558836e-06, "epoch": 373.94444444444446, "percentage": 84.14, "elapsed_time": "3:48:55", "remaining_time": "0:43:09", "throughput": 686.48, "total_tokens": 9429104} {"current_steps": 33660, "total_steps": 40000, "loss": 0.0, "lr": 3.0367590585362564e-06, "epoch": 374.0, "percentage": 84.15, "elapsed_time": "3:48:57", "remaining_time": "0:43:07", "throughput": 686.48, "total_tokens": 9430544} {"current_steps": 33665, "total_steps": 40000, "loss": 0.0, "lr": 3.0320710627243813e-06, "epoch": 374.05555555555554, "percentage": 84.16, "elapsed_time": "3:48:59", "remaining_time": "0:43:05", "throughput": 686.47, "total_tokens": 9431984} {"current_steps": 33670, "total_steps": 40000, "loss": 0.0, "lr": 3.027386454643222e-06, "epoch": 374.1111111111111, "percentage": 84.17, "elapsed_time": "3:49:01", "remaining_time": "0:43:03", "throughput": 686.47, "total_tokens": 9433360} {"current_steps": 33675, "total_steps": 40000, "loss": 0.0, "lr": 3.0227052350151914e-06, "epoch": 374.1666666666667, "percentage": 84.19, "elapsed_time": "3:49:03", "remaining_time": "0:43:01", "throughput": 686.46, "total_tokens": 9434720} {"current_steps": 33680, "total_steps": 40000, "loss": 0.0, "lr": 3.0180274045621957e-06, "epoch": 374.22222222222223, "percentage": 84.2, "elapsed_time": "3:49:05", "remaining_time": "0:42:59", "throughput": 686.46, "total_tokens": 9436112} {"current_steps": 33685, "total_steps": 40000, "loss": 0.0, "lr": 3.013352964005625e-06, "epoch": 374.27777777777777, "percentage": 84.21, "elapsed_time": "3:49:07", "remaining_time": "0:42:57", "throughput": 686.47, "total_tokens": 9437520} {"current_steps": 33690, "total_steps": 40000, "loss": 0.0, "lr": 3.0086819140663218e-06, "epoch": 374.3333333333333, "percentage": 84.23, "elapsed_time": "3:49:10", "remaining_time": "0:42:55", "throughput": 686.46, "total_tokens": 9438896} {"current_steps": 33695, "total_steps": 40000, "loss": 0.0, "lr": 3.0040142554646265e-06, "epoch": 374.3888888888889, "percentage": 84.24, "elapsed_time": "3:49:12", "remaining_time": "0:42:53", "throughput": 686.46, "total_tokens": 9440256} {"current_steps": 33700, "total_steps": 40000, "loss": 0.0, "lr": 2.999349988920361e-06, "epoch": 374.44444444444446, "percentage": 84.25, "elapsed_time": "3:49:14", "remaining_time": "0:42:51", "throughput": 686.47, "total_tokens": 9441696} {"current_steps": 33705, "total_steps": 40000, "loss": 0.0, "lr": 2.994689115152796e-06, "epoch": 374.5, "percentage": 84.26, "elapsed_time": "3:49:16", "remaining_time": "0:42:49", "throughput": 686.47, "total_tokens": 9443088} {"current_steps": 33710, "total_steps": 40000, "loss": 0.0, "lr": 2.9900316348807105e-06, "epoch": 374.55555555555554, "percentage": 84.28, "elapsed_time": "3:49:17", "remaining_time": "0:42:47", "throughput": 686.48, "total_tokens": 9444496} {"current_steps": 33715, "total_steps": 40000, "loss": 0.0, "lr": 2.985377548822338e-06, "epoch": 374.6111111111111, "percentage": 84.29, "elapsed_time": "3:49:19", "remaining_time": "0:42:45", "throughput": 686.48, "total_tokens": 9445904} {"current_steps": 33720, "total_steps": 40000, "loss": 0.0, "lr": 2.980726857695404e-06, "epoch": 374.6666666666667, "percentage": 84.3, "elapsed_time": "3:49:21", "remaining_time": "0:42:43", "throughput": 686.48, "total_tokens": 9447296} {"current_steps": 33725, "total_steps": 40000, "loss": 0.0, "lr": 2.9760795622171017e-06, "epoch": 374.72222222222223, "percentage": 84.31, "elapsed_time": "3:49:23", "remaining_time": "0:42:40", "throughput": 686.49, "total_tokens": 9448688} {"current_steps": 33730, "total_steps": 40000, "loss": 0.0, "lr": 2.971435663104094e-06, "epoch": 374.77777777777777, "percentage": 84.33, "elapsed_time": "3:49:25", "remaining_time": "0:42:38", "throughput": 686.5, "total_tokens": 9450112} {"current_steps": 33735, "total_steps": 40000, "loss": 0.0, "lr": 2.9667951610725385e-06, "epoch": 374.8333333333333, "percentage": 84.34, "elapsed_time": "3:49:27", "remaining_time": "0:42:36", "throughput": 686.5, "total_tokens": 9451504} {"current_steps": 33740, "total_steps": 40000, "loss": 0.0, "lr": 2.9621580568380575e-06, "epoch": 374.8888888888889, "percentage": 84.35, "elapsed_time": "3:49:29", "remaining_time": "0:42:34", "throughput": 686.5, "total_tokens": 9452816} {"current_steps": 33745, "total_steps": 40000, "loss": 0.0, "lr": 2.9575243511157453e-06, "epoch": 374.94444444444446, "percentage": 84.36, "elapsed_time": "3:49:31", "remaining_time": "0:42:32", "throughput": 686.51, "total_tokens": 9454272} {"current_steps": 33750, "total_steps": 40000, "loss": 0.0, "lr": 2.952894044620186e-06, "epoch": 375.0, "percentage": 84.38, "elapsed_time": "3:49:33", "remaining_time": "0:42:30", "throughput": 686.5, "total_tokens": 9455664} {"current_steps": 33755, "total_steps": 40000, "loss": 0.0, "lr": 2.948267138065419e-06, "epoch": 375.05555555555554, "percentage": 84.39, "elapsed_time": "3:49:35", "remaining_time": "0:42:28", "throughput": 686.49, "total_tokens": 9457088} {"current_steps": 33760, "total_steps": 40000, "loss": 0.0, "lr": 2.943643632164983e-06, "epoch": 375.1111111111111, "percentage": 84.4, "elapsed_time": "3:49:37", "remaining_time": "0:42:26", "throughput": 686.49, "total_tokens": 9458464} {"current_steps": 33765, "total_steps": 40000, "loss": 0.0, "lr": 2.939023527631879e-06, "epoch": 375.1666666666667, "percentage": 84.41, "elapsed_time": "3:49:40", "remaining_time": "0:42:24", "throughput": 686.5, "total_tokens": 9459936} {"current_steps": 33770, "total_steps": 40000, "loss": 0.0, "lr": 2.934406825178576e-06, "epoch": 375.22222222222223, "percentage": 84.42, "elapsed_time": "3:49:42", "remaining_time": "0:42:22", "throughput": 686.5, "total_tokens": 9461328} {"current_steps": 33775, "total_steps": 40000, "loss": 0.0, "lr": 2.9297935255170357e-06, "epoch": 375.27777777777777, "percentage": 84.44, "elapsed_time": "3:49:44", "remaining_time": "0:42:20", "throughput": 686.5, "total_tokens": 9462752} {"current_steps": 33780, "total_steps": 40000, "loss": 0.0, "lr": 2.925183629358691e-06, "epoch": 375.3333333333333, "percentage": 84.45, "elapsed_time": "3:49:46", "remaining_time": "0:42:18", "throughput": 686.5, "total_tokens": 9464112} {"current_steps": 33785, "total_steps": 40000, "loss": 0.0, "lr": 2.9205771374144346e-06, "epoch": 375.3888888888889, "percentage": 84.46, "elapsed_time": "3:49:48", "remaining_time": "0:42:16", "throughput": 686.5, "total_tokens": 9465536} {"current_steps": 33790, "total_steps": 40000, "loss": 0.0, "lr": 2.915974050394657e-06, "epoch": 375.44444444444446, "percentage": 84.47, "elapsed_time": "3:49:50", "remaining_time": "0:42:14", "throughput": 686.5, "total_tokens": 9466912} {"current_steps": 33795, "total_steps": 40000, "loss": 0.0, "lr": 2.9113743690092067e-06, "epoch": 375.5, "percentage": 84.49, "elapsed_time": "3:49:52", "remaining_time": "0:42:12", "throughput": 686.48, "total_tokens": 9468288} {"current_steps": 33800, "total_steps": 40000, "loss": 0.0, "lr": 2.906778093967402e-06, "epoch": 375.55555555555554, "percentage": 84.5, "elapsed_time": "3:49:54", "remaining_time": "0:42:10", "throughput": 686.48, "total_tokens": 9469696} {"current_steps": 33800, "total_steps": 40000, "eval_loss": 0.3593387305736542, "epoch": 375.55555555555554, "percentage": 84.5, "elapsed_time": "3:49:55", "remaining_time": "0:42:10", "throughput": 686.42, "total_tokens": 9469696} {"current_steps": 33805, "total_steps": 40000, "loss": 0.0, "lr": 2.9021852259780656e-06, "epoch": 375.6111111111111, "percentage": 84.51, "elapsed_time": "3:49:59", "remaining_time": "0:42:08", "throughput": 686.35, "total_tokens": 9471072} {"current_steps": 33810, "total_steps": 40000, "loss": 0.0, "lr": 2.8975957657494583e-06, "epoch": 375.6666666666667, "percentage": 84.52, "elapsed_time": "3:50:01", "remaining_time": "0:42:06", "throughput": 686.35, "total_tokens": 9472496} {"current_steps": 33815, "total_steps": 40000, "loss": 0.0, "lr": 2.8930097139893417e-06, "epoch": 375.72222222222223, "percentage": 84.54, "elapsed_time": "3:50:03", "remaining_time": "0:42:04", "throughput": 686.35, "total_tokens": 9473888} {"current_steps": 33820, "total_steps": 40000, "loss": 0.0, "lr": 2.888427071404945e-06, "epoch": 375.77777777777777, "percentage": 84.55, "elapsed_time": "3:50:05", "remaining_time": "0:42:02", "throughput": 686.36, "total_tokens": 9475280} {"current_steps": 33825, "total_steps": 40000, "loss": 0.0, "lr": 2.8838478387029606e-06, "epoch": 375.8333333333333, "percentage": 84.56, "elapsed_time": "3:50:07", "remaining_time": "0:42:00", "throughput": 686.36, "total_tokens": 9476688} {"current_steps": 33830, "total_steps": 40000, "loss": 0.0, "lr": 2.8792720165895737e-06, "epoch": 375.8888888888889, "percentage": 84.58, "elapsed_time": "3:50:09", "remaining_time": "0:41:58", "throughput": 686.37, "total_tokens": 9478064} {"current_steps": 33835, "total_steps": 40000, "loss": 0.0, "lr": 2.874699605770423e-06, "epoch": 375.94444444444446, "percentage": 84.59, "elapsed_time": "3:50:10", "remaining_time": "0:41:56", "throughput": 686.38, "total_tokens": 9479488} {"current_steps": 33840, "total_steps": 40000, "loss": 0.0, "lr": 2.8701306069506383e-06, "epoch": 376.0, "percentage": 84.6, "elapsed_time": "3:50:13", "remaining_time": "0:41:54", "throughput": 686.37, "total_tokens": 9480912} {"current_steps": 33845, "total_steps": 40000, "loss": 0.0, "lr": 2.8655650208348178e-06, "epoch": 376.05555555555554, "percentage": 84.61, "elapsed_time": "3:50:15", "remaining_time": "0:41:52", "throughput": 686.36, "total_tokens": 9482304} {"current_steps": 33850, "total_steps": 40000, "loss": 0.0, "lr": 2.8610028481270257e-06, "epoch": 376.1111111111111, "percentage": 84.62, "elapsed_time": "3:50:17", "remaining_time": "0:41:50", "throughput": 686.37, "total_tokens": 9483712} {"current_steps": 33855, "total_steps": 40000, "loss": 0.0, "lr": 2.856444089530813e-06, "epoch": 376.1666666666667, "percentage": 84.64, "elapsed_time": "3:50:19", "remaining_time": "0:41:48", "throughput": 686.38, "total_tokens": 9485120} {"current_steps": 33860, "total_steps": 40000, "loss": 0.0, "lr": 2.8518887457491955e-06, "epoch": 376.22222222222223, "percentage": 84.65, "elapsed_time": "3:50:21", "remaining_time": "0:41:46", "throughput": 686.38, "total_tokens": 9486496} {"current_steps": 33865, "total_steps": 40000, "loss": 0.0, "lr": 2.8473368174846666e-06, "epoch": 376.27777777777777, "percentage": 84.66, "elapsed_time": "3:50:23", "remaining_time": "0:41:44", "throughput": 686.38, "total_tokens": 9487920} {"current_steps": 33870, "total_steps": 40000, "loss": 0.0, "lr": 2.842788305439184e-06, "epoch": 376.3333333333333, "percentage": 84.67, "elapsed_time": "3:50:25", "remaining_time": "0:41:42", "throughput": 686.38, "total_tokens": 9489360} {"current_steps": 33875, "total_steps": 40000, "loss": 0.0, "lr": 2.8382432103141925e-06, "epoch": 376.3888888888889, "percentage": 84.69, "elapsed_time": "3:50:27", "remaining_time": "0:41:40", "throughput": 686.38, "total_tokens": 9490720} {"current_steps": 33880, "total_steps": 40000, "loss": 0.0, "lr": 2.833701532810598e-06, "epoch": 376.44444444444446, "percentage": 84.7, "elapsed_time": "3:50:29", "remaining_time": "0:41:38", "throughput": 686.38, "total_tokens": 9492080} {"current_steps": 33885, "total_steps": 40000, "loss": 0.0, "lr": 2.8291632736287877e-06, "epoch": 376.5, "percentage": 84.71, "elapsed_time": "3:50:31", "remaining_time": "0:41:36", "throughput": 686.37, "total_tokens": 9493440} {"current_steps": 33890, "total_steps": 40000, "loss": 0.0, "lr": 2.824628433468615e-06, "epoch": 376.55555555555554, "percentage": 84.72, "elapsed_time": "3:50:33", "remaining_time": "0:41:33", "throughput": 686.37, "total_tokens": 9494800} {"current_steps": 33895, "total_steps": 40000, "loss": 0.0, "lr": 2.8200970130294073e-06, "epoch": 376.6111111111111, "percentage": 84.74, "elapsed_time": "3:50:35", "remaining_time": "0:41:31", "throughput": 686.37, "total_tokens": 9496208} {"current_steps": 33900, "total_steps": 40000, "loss": 0.0, "lr": 2.8155690130099775e-06, "epoch": 376.6666666666667, "percentage": 84.75, "elapsed_time": "3:50:37", "remaining_time": "0:41:29", "throughput": 686.37, "total_tokens": 9497600} {"current_steps": 33905, "total_steps": 40000, "loss": 0.0, "lr": 2.8110444341085895e-06, "epoch": 376.72222222222223, "percentage": 84.76, "elapsed_time": "3:50:39", "remaining_time": "0:41:27", "throughput": 686.38, "total_tokens": 9499024} {"current_steps": 33910, "total_steps": 40000, "loss": 0.0, "lr": 2.806523277022996e-06, "epoch": 376.77777777777777, "percentage": 84.78, "elapsed_time": "3:50:41", "remaining_time": "0:41:25", "throughput": 686.38, "total_tokens": 9500416} {"current_steps": 33915, "total_steps": 40000, "loss": 0.0, "lr": 2.802005542450409e-06, "epoch": 376.8333333333333, "percentage": 84.79, "elapsed_time": "3:50:43", "remaining_time": "0:41:23", "throughput": 686.38, "total_tokens": 9501808} {"current_steps": 33920, "total_steps": 40000, "loss": 0.0, "lr": 2.797491231087526e-06, "epoch": 376.8888888888889, "percentage": 84.8, "elapsed_time": "3:50:45", "remaining_time": "0:41:21", "throughput": 686.38, "total_tokens": 9503248} {"current_steps": 33925, "total_steps": 40000, "loss": 0.0, "lr": 2.7929803436305137e-06, "epoch": 376.94444444444446, "percentage": 84.81, "elapsed_time": "3:50:47", "remaining_time": "0:41:19", "throughput": 686.39, "total_tokens": 9504672} {"current_steps": 33930, "total_steps": 40000, "loss": 0.0, "lr": 2.788472880774998e-06, "epoch": 377.0, "percentage": 84.82, "elapsed_time": "3:50:49", "remaining_time": "0:41:17", "throughput": 686.39, "total_tokens": 9506128} {"current_steps": 33935, "total_steps": 40000, "loss": 0.0, "lr": 2.7839688432160977e-06, "epoch": 377.05555555555554, "percentage": 84.84, "elapsed_time": "3:50:51", "remaining_time": "0:41:15", "throughput": 686.39, "total_tokens": 9507568} {"current_steps": 33940, "total_steps": 40000, "loss": 0.0, "lr": 2.779468231648383e-06, "epoch": 377.1111111111111, "percentage": 84.85, "elapsed_time": "3:50:53", "remaining_time": "0:41:13", "throughput": 686.39, "total_tokens": 9508960} {"current_steps": 33945, "total_steps": 40000, "loss": 0.0, "lr": 2.774971046765906e-06, "epoch": 377.1666666666667, "percentage": 84.86, "elapsed_time": "3:50:55", "remaining_time": "0:41:11", "throughput": 686.4, "total_tokens": 9510368} {"current_steps": 33950, "total_steps": 40000, "loss": 0.0, "lr": 2.770477289262194e-06, "epoch": 377.22222222222223, "percentage": 84.88, "elapsed_time": "3:50:57", "remaining_time": "0:41:09", "throughput": 686.4, "total_tokens": 9511728} {"current_steps": 33955, "total_steps": 40000, "loss": 0.0, "lr": 2.765986959830233e-06, "epoch": 377.27777777777777, "percentage": 84.89, "elapsed_time": "3:50:59", "remaining_time": "0:41:07", "throughput": 686.4, "total_tokens": 9513120} {"current_steps": 33960, "total_steps": 40000, "loss": 0.0, "lr": 2.761500059162492e-06, "epoch": 377.3333333333333, "percentage": 84.9, "elapsed_time": "3:51:01", "remaining_time": "0:41:05", "throughput": 686.41, "total_tokens": 9514592} {"current_steps": 33965, "total_steps": 40000, "loss": 0.0, "lr": 2.757016587950914e-06, "epoch": 377.3888888888889, "percentage": 84.91, "elapsed_time": "3:51:03", "remaining_time": "0:41:03", "throughput": 686.41, "total_tokens": 9515936} {"current_steps": 33970, "total_steps": 40000, "loss": 0.0, "lr": 2.752536546886897e-06, "epoch": 377.44444444444446, "percentage": 84.92, "elapsed_time": "3:51:05", "remaining_time": "0:41:01", "throughput": 686.42, "total_tokens": 9517360} {"current_steps": 33975, "total_steps": 40000, "loss": 0.0, "lr": 2.7480599366613234e-06, "epoch": 377.5, "percentage": 84.94, "elapsed_time": "3:51:07", "remaining_time": "0:40:59", "throughput": 686.43, "total_tokens": 9518800} {"current_steps": 33980, "total_steps": 40000, "loss": 0.0, "lr": 2.7435867579645473e-06, "epoch": 377.55555555555554, "percentage": 84.95, "elapsed_time": "3:51:09", "remaining_time": "0:40:57", "throughput": 686.43, "total_tokens": 9520224} {"current_steps": 33985, "total_steps": 40000, "loss": 0.0, "lr": 2.739117011486378e-06, "epoch": 377.6111111111111, "percentage": 84.96, "elapsed_time": "3:51:11", "remaining_time": "0:40:55", "throughput": 686.43, "total_tokens": 9521600} {"current_steps": 33990, "total_steps": 40000, "loss": 0.0, "lr": 2.7346506979161216e-06, "epoch": 377.6666666666667, "percentage": 84.97, "elapsed_time": "3:51:13", "remaining_time": "0:40:53", "throughput": 686.43, "total_tokens": 9522960} {"current_steps": 33995, "total_steps": 40000, "loss": 0.0, "lr": 2.7301878179425227e-06, "epoch": 377.72222222222223, "percentage": 84.99, "elapsed_time": "3:51:15", "remaining_time": "0:40:50", "throughput": 686.43, "total_tokens": 9524320} {"current_steps": 34000, "total_steps": 40000, "loss": 0.0, "lr": 2.7257283722538244e-06, "epoch": 377.77777777777777, "percentage": 85.0, "elapsed_time": "3:51:17", "remaining_time": "0:40:48", "throughput": 686.43, "total_tokens": 9525760} {"current_steps": 34000, "total_steps": 40000, "eval_loss": 0.35832586884498596, "epoch": 377.77777777777777, "percentage": 85.0, "elapsed_time": "3:51:18", "remaining_time": "0:40:49", "throughput": 686.37, "total_tokens": 9525760} {"current_steps": 34005, "total_steps": 40000, "loss": 0.0, "lr": 2.7212723615377326e-06, "epoch": 377.8333333333333, "percentage": 85.01, "elapsed_time": "3:51:22", "remaining_time": "0:40:47", "throughput": 686.26, "total_tokens": 9527120} {"current_steps": 34010, "total_steps": 40000, "loss": 0.0, "lr": 2.7168197864814145e-06, "epoch": 377.8888888888889, "percentage": 85.02, "elapsed_time": "3:51:24", "remaining_time": "0:40:45", "throughput": 686.26, "total_tokens": 9528512} {"current_steps": 34015, "total_steps": 40000, "loss": 0.0, "lr": 2.712370647771509e-06, "epoch": 377.94444444444446, "percentage": 85.04, "elapsed_time": "3:51:26", "remaining_time": "0:40:43", "throughput": 686.26, "total_tokens": 9529920} {"current_steps": 34020, "total_steps": 40000, "loss": 0.0, "lr": 2.707924946094137e-06, "epoch": 378.0, "percentage": 85.05, "elapsed_time": "3:51:28", "remaining_time": "0:40:41", "throughput": 686.25, "total_tokens": 9531264} {"current_steps": 34025, "total_steps": 40000, "loss": 0.0, "lr": 2.7034826821348723e-06, "epoch": 378.05555555555554, "percentage": 85.06, "elapsed_time": "3:51:31", "remaining_time": "0:40:39", "throughput": 686.24, "total_tokens": 9532656} {"current_steps": 34030, "total_steps": 40000, "loss": 0.0, "lr": 2.6990438565787786e-06, "epoch": 378.1111111111111, "percentage": 85.08, "elapsed_time": "3:51:33", "remaining_time": "0:40:37", "throughput": 686.23, "total_tokens": 9533984} {"current_steps": 34035, "total_steps": 40000, "loss": 0.0, "lr": 2.6946084701103714e-06, "epoch": 378.1666666666667, "percentage": 85.09, "elapsed_time": "3:51:35", "remaining_time": "0:40:35", "throughput": 686.23, "total_tokens": 9535360} {"current_steps": 34040, "total_steps": 40000, "loss": 0.0, "lr": 2.6901765234136428e-06, "epoch": 378.22222222222223, "percentage": 85.1, "elapsed_time": "3:51:37", "remaining_time": "0:40:33", "throughput": 686.23, "total_tokens": 9536784} {"current_steps": 34045, "total_steps": 40000, "loss": 0.0, "lr": 2.685748017172063e-06, "epoch": 378.27777777777777, "percentage": 85.11, "elapsed_time": "3:51:39", "remaining_time": "0:40:31", "throughput": 686.24, "total_tokens": 9538208} {"current_steps": 34050, "total_steps": 40000, "loss": 0.0, "lr": 2.681322952068549e-06, "epoch": 378.3333333333333, "percentage": 85.12, "elapsed_time": "3:51:41", "remaining_time": "0:40:29", "throughput": 686.24, "total_tokens": 9539616} {"current_steps": 34055, "total_steps": 40000, "loss": 0.0, "lr": 2.6769013287855137e-06, "epoch": 378.3888888888889, "percentage": 85.14, "elapsed_time": "3:51:43", "remaining_time": "0:40:27", "throughput": 686.25, "total_tokens": 9541024} {"current_steps": 34060, "total_steps": 40000, "loss": 0.0, "lr": 2.6724831480048286e-06, "epoch": 378.44444444444446, "percentage": 85.15, "elapsed_time": "3:51:45", "remaining_time": "0:40:25", "throughput": 686.25, "total_tokens": 9542400} {"current_steps": 34065, "total_steps": 40000, "loss": 0.0, "lr": 2.66806841040782e-06, "epoch": 378.5, "percentage": 85.16, "elapsed_time": "3:51:47", "remaining_time": "0:40:22", "throughput": 686.25, "total_tokens": 9543792} {"current_steps": 34070, "total_steps": 40000, "loss": 0.0, "lr": 2.6636571166753083e-06, "epoch": 378.55555555555554, "percentage": 85.17, "elapsed_time": "3:51:49", "remaining_time": "0:40:20", "throughput": 686.26, "total_tokens": 9545232} {"current_steps": 34075, "total_steps": 40000, "loss": 0.0, "lr": 2.6592492674875598e-06, "epoch": 378.6111111111111, "percentage": 85.19, "elapsed_time": "3:51:50", "remaining_time": "0:40:18", "throughput": 686.27, "total_tokens": 9546640} {"current_steps": 34080, "total_steps": 40000, "loss": 0.0, "lr": 2.6548448635243305e-06, "epoch": 378.6666666666667, "percentage": 85.2, "elapsed_time": "3:51:52", "remaining_time": "0:40:16", "throughput": 686.28, "total_tokens": 9548080} {"current_steps": 34085, "total_steps": 40000, "loss": 0.0, "lr": 2.650443905464828e-06, "epoch": 378.72222222222223, "percentage": 85.21, "elapsed_time": "3:51:54", "remaining_time": "0:40:14", "throughput": 686.28, "total_tokens": 9549456} {"current_steps": 34090, "total_steps": 40000, "loss": 0.0, "lr": 2.646046393987739e-06, "epoch": 378.77777777777777, "percentage": 85.22, "elapsed_time": "3:51:56", "remaining_time": "0:40:12", "throughput": 686.28, "total_tokens": 9550848} {"current_steps": 34095, "total_steps": 40000, "loss": 0.0, "lr": 2.64165232977121e-06, "epoch": 378.8333333333333, "percentage": 85.24, "elapsed_time": "3:51:58", "remaining_time": "0:40:10", "throughput": 686.29, "total_tokens": 9552256} {"current_steps": 34100, "total_steps": 40000, "loss": 0.0, "lr": 2.6372617134928695e-06, "epoch": 378.8888888888889, "percentage": 85.25, "elapsed_time": "3:52:00", "remaining_time": "0:40:08", "throughput": 686.29, "total_tokens": 9553664} {"current_steps": 34105, "total_steps": 40000, "loss": 0.0, "lr": 2.6328745458297943e-06, "epoch": 378.94444444444446, "percentage": 85.26, "elapsed_time": "3:52:02", "remaining_time": "0:40:06", "throughput": 686.3, "total_tokens": 9555072} {"current_steps": 34110, "total_steps": 40000, "loss": 0.0, "lr": 2.6284908274585546e-06, "epoch": 379.0, "percentage": 85.28, "elapsed_time": "3:52:04", "remaining_time": "0:40:04", "throughput": 686.3, "total_tokens": 9556464} {"current_steps": 34115, "total_steps": 40000, "loss": 0.0, "lr": 2.6241105590551595e-06, "epoch": 379.05555555555554, "percentage": 85.29, "elapsed_time": "3:52:06", "remaining_time": "0:40:02", "throughput": 686.29, "total_tokens": 9557888} {"current_steps": 34120, "total_steps": 40000, "loss": 0.0, "lr": 2.6197337412951105e-06, "epoch": 379.1111111111111, "percentage": 85.3, "elapsed_time": "3:52:08", "remaining_time": "0:40:00", "throughput": 686.3, "total_tokens": 9559312} {"current_steps": 34125, "total_steps": 40000, "loss": 0.0, "lr": 2.6153603748533705e-06, "epoch": 379.1666666666667, "percentage": 85.31, "elapsed_time": "3:52:10", "remaining_time": "0:39:58", "throughput": 686.3, "total_tokens": 9560720} {"current_steps": 34130, "total_steps": 40000, "loss": 0.0, "lr": 2.6109904604043585e-06, "epoch": 379.22222222222223, "percentage": 85.32, "elapsed_time": "3:52:12", "remaining_time": "0:39:56", "throughput": 686.3, "total_tokens": 9562144} {"current_steps": 34135, "total_steps": 40000, "loss": 0.0, "lr": 2.6066239986219765e-06, "epoch": 379.27777777777777, "percentage": 85.34, "elapsed_time": "3:52:14", "remaining_time": "0:39:54", "throughput": 686.3, "total_tokens": 9563552} {"current_steps": 34140, "total_steps": 40000, "loss": 0.0, "lr": 2.602260990179592e-06, "epoch": 379.3333333333333, "percentage": 85.35, "elapsed_time": "3:52:16", "remaining_time": "0:39:52", "throughput": 686.3, "total_tokens": 9564944} {"current_steps": 34145, "total_steps": 40000, "loss": 0.0, "lr": 2.5979014357500248e-06, "epoch": 379.3888888888889, "percentage": 85.36, "elapsed_time": "3:52:18", "remaining_time": "0:39:50", "throughput": 686.3, "total_tokens": 9566368} {"current_steps": 34150, "total_steps": 40000, "loss": 0.0, "lr": 2.5935453360055844e-06, "epoch": 379.44444444444446, "percentage": 85.38, "elapsed_time": "3:52:21", "remaining_time": "0:39:48", "throughput": 686.3, "total_tokens": 9567776} {"current_steps": 34155, "total_steps": 40000, "loss": 0.0, "lr": 2.5891926916180283e-06, "epoch": 379.5, "percentage": 85.39, "elapsed_time": "3:52:23", "remaining_time": "0:39:46", "throughput": 686.3, "total_tokens": 9569136} {"current_steps": 34160, "total_steps": 40000, "loss": 0.0, "lr": 2.5848435032585883e-06, "epoch": 379.55555555555554, "percentage": 85.4, "elapsed_time": "3:52:25", "remaining_time": "0:39:44", "throughput": 686.3, "total_tokens": 9570512} {"current_steps": 34165, "total_steps": 40000, "loss": 0.0, "lr": 2.58049777159797e-06, "epoch": 379.6111111111111, "percentage": 85.41, "elapsed_time": "3:52:27", "remaining_time": "0:39:42", "throughput": 686.3, "total_tokens": 9571920} {"current_steps": 34170, "total_steps": 40000, "loss": 0.0, "lr": 2.576155497306332e-06, "epoch": 379.6666666666667, "percentage": 85.42, "elapsed_time": "3:52:29", "remaining_time": "0:39:39", "throughput": 686.3, "total_tokens": 9573296} {"current_steps": 34175, "total_steps": 40000, "loss": 0.0, "lr": 2.57181668105331e-06, "epoch": 379.72222222222223, "percentage": 85.44, "elapsed_time": "3:52:31", "remaining_time": "0:39:37", "throughput": 686.3, "total_tokens": 9574672} {"current_steps": 34180, "total_steps": 40000, "loss": 0.0, "lr": 2.567481323508014e-06, "epoch": 379.77777777777777, "percentage": 85.45, "elapsed_time": "3:52:33", "remaining_time": "0:39:35", "throughput": 686.3, "total_tokens": 9576032} {"current_steps": 34185, "total_steps": 40000, "loss": 0.0, "lr": 2.5631494253389954e-06, "epoch": 379.8333333333333, "percentage": 85.46, "elapsed_time": "3:52:35", "remaining_time": "0:39:33", "throughput": 686.29, "total_tokens": 9577408} {"current_steps": 34190, "total_steps": 40000, "loss": 0.0, "lr": 2.5588209872142997e-06, "epoch": 379.8888888888889, "percentage": 85.47, "elapsed_time": "3:52:37", "remaining_time": "0:39:31", "throughput": 686.3, "total_tokens": 9578864} {"current_steps": 34195, "total_steps": 40000, "loss": 0.0, "lr": 2.5544960098014186e-06, "epoch": 379.94444444444446, "percentage": 85.49, "elapsed_time": "3:52:39", "remaining_time": "0:39:29", "throughput": 686.3, "total_tokens": 9580288} {"current_steps": 34200, "total_steps": 40000, "loss": 0.0, "lr": 2.550174493767318e-06, "epoch": 380.0, "percentage": 85.5, "elapsed_time": "3:52:41", "remaining_time": "0:39:27", "throughput": 686.3, "total_tokens": 9581648} {"current_steps": 34200, "total_steps": 40000, "eval_loss": 0.38547393679618835, "epoch": 380.0, "percentage": 85.5, "elapsed_time": "3:52:42", "remaining_time": "0:39:27", "throughput": 686.23, "total_tokens": 9581648} {"current_steps": 34205, "total_steps": 40000, "loss": 0.0, "lr": 2.545856439778438e-06, "epoch": 380.05555555555554, "percentage": 85.51, "elapsed_time": "3:52:46", "remaining_time": "0:39:26", "throughput": 686.15, "total_tokens": 9583024} {"current_steps": 34210, "total_steps": 40000, "loss": 0.0, "lr": 2.541541848500667e-06, "epoch": 380.1111111111111, "percentage": 85.52, "elapsed_time": "3:52:48", "remaining_time": "0:39:24", "throughput": 686.15, "total_tokens": 9584400} {"current_steps": 34215, "total_steps": 40000, "loss": 0.0, "lr": 2.5372307205993733e-06, "epoch": 380.1666666666667, "percentage": 85.54, "elapsed_time": "3:52:50", "remaining_time": "0:39:22", "throughput": 686.15, "total_tokens": 9585808} {"current_steps": 34220, "total_steps": 40000, "loss": 0.0, "lr": 2.5329230567393917e-06, "epoch": 380.22222222222223, "percentage": 85.55, "elapsed_time": "3:52:52", "remaining_time": "0:39:20", "throughput": 686.16, "total_tokens": 9587216} {"current_steps": 34225, "total_steps": 40000, "loss": 0.0, "lr": 2.5286188575850164e-06, "epoch": 380.27777777777777, "percentage": 85.56, "elapsed_time": "3:52:54", "remaining_time": "0:39:17", "throughput": 686.16, "total_tokens": 9588624} {"current_steps": 34230, "total_steps": 40000, "loss": 0.0, "lr": 2.5243181237999984e-06, "epoch": 380.3333333333333, "percentage": 85.58, "elapsed_time": "3:52:56", "remaining_time": "0:39:15", "throughput": 686.17, "total_tokens": 9590048} {"current_steps": 34235, "total_steps": 40000, "loss": 0.0, "lr": 2.520020856047578e-06, "epoch": 380.3888888888889, "percentage": 85.59, "elapsed_time": "3:52:58", "remaining_time": "0:39:13", "throughput": 686.18, "total_tokens": 9591472} {"current_steps": 34240, "total_steps": 40000, "loss": 0.0, "lr": 2.515727054990438e-06, "epoch": 380.44444444444446, "percentage": 85.6, "elapsed_time": "3:53:00", "remaining_time": "0:39:11", "throughput": 686.18, "total_tokens": 9592864} {"current_steps": 34245, "total_steps": 40000, "loss": 0.0, "lr": 2.511436721290747e-06, "epoch": 380.5, "percentage": 85.61, "elapsed_time": "3:53:02", "remaining_time": "0:39:09", "throughput": 686.19, "total_tokens": 9594288} {"current_steps": 34250, "total_steps": 40000, "loss": 0.0, "lr": 2.5071498556101164e-06, "epoch": 380.55555555555554, "percentage": 85.62, "elapsed_time": "3:53:03", "remaining_time": "0:39:07", "throughput": 686.19, "total_tokens": 9595696} {"current_steps": 34255, "total_steps": 40000, "loss": 0.0, "lr": 2.5028664586096485e-06, "epoch": 380.6111111111111, "percentage": 85.64, "elapsed_time": "3:53:05", "remaining_time": "0:39:05", "throughput": 686.19, "total_tokens": 9597040} {"current_steps": 34260, "total_steps": 40000, "loss": 0.0, "lr": 2.498586530949881e-06, "epoch": 380.6666666666667, "percentage": 85.65, "elapsed_time": "3:53:07", "remaining_time": "0:39:03", "throughput": 686.2, "total_tokens": 9598464} {"current_steps": 34265, "total_steps": 40000, "loss": 0.0, "lr": 2.4943100732908427e-06, "epoch": 380.72222222222223, "percentage": 85.66, "elapsed_time": "3:53:09", "remaining_time": "0:39:01", "throughput": 686.21, "total_tokens": 9599920} {"current_steps": 34270, "total_steps": 40000, "loss": 0.0, "lr": 2.4900370862920188e-06, "epoch": 380.77777777777777, "percentage": 85.67, "elapsed_time": "3:53:11", "remaining_time": "0:38:59", "throughput": 686.21, "total_tokens": 9601296} {"current_steps": 34275, "total_steps": 40000, "loss": 0.0, "lr": 2.4857675706123518e-06, "epoch": 380.8333333333333, "percentage": 85.69, "elapsed_time": "3:53:13", "remaining_time": "0:38:57", "throughput": 686.22, "total_tokens": 9602672} {"current_steps": 34280, "total_steps": 40000, "loss": 0.0, "lr": 2.4815015269102543e-06, "epoch": 380.8888888888889, "percentage": 85.7, "elapsed_time": "3:53:15", "remaining_time": "0:38:55", "throughput": 686.22, "total_tokens": 9604080} {"current_steps": 34285, "total_steps": 40000, "loss": 0.0, "lr": 2.477238955843611e-06, "epoch": 380.94444444444446, "percentage": 85.71, "elapsed_time": "3:53:17", "remaining_time": "0:38:53", "throughput": 686.22, "total_tokens": 9605504} {"current_steps": 34290, "total_steps": 40000, "loss": 0.0, "lr": 2.4729798580697573e-06, "epoch": 381.0, "percentage": 85.72, "elapsed_time": "3:53:19", "remaining_time": "0:38:51", "throughput": 686.21, "total_tokens": 9606864} {"current_steps": 34295, "total_steps": 40000, "loss": 0.0, "lr": 2.4687242342455034e-06, "epoch": 381.05555555555554, "percentage": 85.74, "elapsed_time": "3:53:22", "remaining_time": "0:38:49", "throughput": 686.19, "total_tokens": 9608192} {"current_steps": 34300, "total_steps": 40000, "loss": 0.0, "lr": 2.4644720850271196e-06, "epoch": 381.1111111111111, "percentage": 85.75, "elapsed_time": "3:53:24", "remaining_time": "0:38:47", "throughput": 686.19, "total_tokens": 9609600} {"current_steps": 34305, "total_steps": 40000, "loss": 0.0, "lr": 2.4602234110703364e-06, "epoch": 381.1666666666667, "percentage": 85.76, "elapsed_time": "3:53:26", "remaining_time": "0:38:45", "throughput": 686.2, "total_tokens": 9611024} {"current_steps": 34310, "total_steps": 40000, "loss": 0.0, "lr": 2.4559782130303576e-06, "epoch": 381.22222222222223, "percentage": 85.78, "elapsed_time": "3:53:28", "remaining_time": "0:38:43", "throughput": 686.2, "total_tokens": 9612416} {"current_steps": 34315, "total_steps": 40000, "loss": 0.0, "lr": 2.451736491561843e-06, "epoch": 381.27777777777777, "percentage": 85.79, "elapsed_time": "3:53:30", "remaining_time": "0:38:41", "throughput": 686.2, "total_tokens": 9613856} {"current_steps": 34320, "total_steps": 40000, "loss": 0.0, "lr": 2.4474982473189163e-06, "epoch": 381.3333333333333, "percentage": 85.8, "elapsed_time": "3:53:32", "remaining_time": "0:38:39", "throughput": 686.2, "total_tokens": 9615232} {"current_steps": 34325, "total_steps": 40000, "loss": 0.0, "lr": 2.4432634809551796e-06, "epoch": 381.3888888888889, "percentage": 85.81, "elapsed_time": "3:53:34", "remaining_time": "0:38:37", "throughput": 686.2, "total_tokens": 9616624} {"current_steps": 34330, "total_steps": 40000, "loss": 0.0, "lr": 2.439032193123675e-06, "epoch": 381.44444444444446, "percentage": 85.82, "elapsed_time": "3:53:36", "remaining_time": "0:38:34", "throughput": 686.2, "total_tokens": 9618016} {"current_steps": 34335, "total_steps": 40000, "loss": 0.0, "lr": 2.4348043844769297e-06, "epoch": 381.5, "percentage": 85.84, "elapsed_time": "3:53:38", "remaining_time": "0:38:32", "throughput": 686.2, "total_tokens": 9619408} {"current_steps": 34340, "total_steps": 40000, "loss": 0.0, "lr": 2.4305800556669146e-06, "epoch": 381.55555555555554, "percentage": 85.85, "elapsed_time": "3:53:40", "remaining_time": "0:38:30", "throughput": 686.2, "total_tokens": 9620800} {"current_steps": 34345, "total_steps": 40000, "loss": 0.0, "lr": 2.426359207345083e-06, "epoch": 381.6111111111111, "percentage": 85.86, "elapsed_time": "3:53:42", "remaining_time": "0:38:28", "throughput": 686.2, "total_tokens": 9622224} {"current_steps": 34350, "total_steps": 40000, "loss": 0.0, "lr": 2.4221418401623396e-06, "epoch": 381.6666666666667, "percentage": 85.88, "elapsed_time": "3:53:44", "remaining_time": "0:38:26", "throughput": 686.2, "total_tokens": 9623616} {"current_steps": 34355, "total_steps": 40000, "loss": 0.0, "lr": 2.4179279547690557e-06, "epoch": 381.72222222222223, "percentage": 85.89, "elapsed_time": "3:53:46", "remaining_time": "0:38:24", "throughput": 686.2, "total_tokens": 9625024} {"current_steps": 34360, "total_steps": 40000, "loss": 0.0, "lr": 2.413717551815062e-06, "epoch": 381.77777777777777, "percentage": 85.9, "elapsed_time": "3:53:48", "remaining_time": "0:38:22", "throughput": 686.2, "total_tokens": 9626416} {"current_steps": 34365, "total_steps": 40000, "loss": 0.0, "lr": 2.409510631949666e-06, "epoch": 381.8333333333333, "percentage": 85.91, "elapsed_time": "3:53:50", "remaining_time": "0:38:20", "throughput": 686.2, "total_tokens": 9627808} {"current_steps": 34370, "total_steps": 40000, "loss": 0.0, "lr": 2.405307195821618e-06, "epoch": 381.8888888888889, "percentage": 85.92, "elapsed_time": "3:53:52", "remaining_time": "0:38:18", "throughput": 686.2, "total_tokens": 9629184} {"current_steps": 34375, "total_steps": 40000, "loss": 0.0, "lr": 2.4011072440791372e-06, "epoch": 381.94444444444446, "percentage": 85.94, "elapsed_time": "3:53:54", "remaining_time": "0:38:16", "throughput": 686.21, "total_tokens": 9630608} {"current_steps": 34380, "total_steps": 40000, "loss": 0.0, "lr": 2.3969107773699233e-06, "epoch": 382.0, "percentage": 85.95, "elapsed_time": "3:53:56", "remaining_time": "0:38:14", "throughput": 686.21, "total_tokens": 9632016} {"current_steps": 34385, "total_steps": 40000, "loss": 0.0, "lr": 2.3927177963411096e-06, "epoch": 382.05555555555554, "percentage": 85.96, "elapsed_time": "3:53:58", "remaining_time": "0:38:12", "throughput": 686.2, "total_tokens": 9633456} {"current_steps": 34390, "total_steps": 40000, "loss": 0.0, "lr": 2.3885283016393144e-06, "epoch": 382.1111111111111, "percentage": 85.97, "elapsed_time": "3:54:00", "remaining_time": "0:38:10", "throughput": 686.2, "total_tokens": 9634800} {"current_steps": 34395, "total_steps": 40000, "loss": 0.0, "lr": 2.3843422939106076e-06, "epoch": 382.1666666666667, "percentage": 85.99, "elapsed_time": "3:54:02", "remaining_time": "0:38:08", "throughput": 686.21, "total_tokens": 9636176} {"current_steps": 34400, "total_steps": 40000, "loss": 0.0, "lr": 2.380159773800525e-06, "epoch": 382.22222222222223, "percentage": 86.0, "elapsed_time": "3:54:04", "remaining_time": "0:38:06", "throughput": 686.22, "total_tokens": 9637632} {"current_steps": 34400, "total_steps": 40000, "eval_loss": 0.3392062485218048, "epoch": 382.22222222222223, "percentage": 86.0, "elapsed_time": "3:54:05", "remaining_time": "0:38:06", "throughput": 686.15, "total_tokens": 9637632} {"current_steps": 34405, "total_steps": 40000, "loss": 0.0, "lr": 2.3759807419540675e-06, "epoch": 382.27777777777777, "percentage": 86.01, "elapsed_time": "3:54:09", "remaining_time": "0:38:04", "throughput": 686.08, "total_tokens": 9639056} {"current_steps": 34410, "total_steps": 40000, "loss": 0.0, "lr": 2.3718051990156835e-06, "epoch": 382.3333333333333, "percentage": 86.02, "elapsed_time": "3:54:11", "remaining_time": "0:38:02", "throughput": 686.08, "total_tokens": 9640496} {"current_steps": 34415, "total_steps": 40000, "loss": 0.0, "lr": 2.367633145629311e-06, "epoch": 382.3888888888889, "percentage": 86.04, "elapsed_time": "3:54:13", "remaining_time": "0:38:00", "throughput": 686.09, "total_tokens": 9641888} {"current_steps": 34420, "total_steps": 40000, "loss": 0.0, "lr": 2.363464582438316e-06, "epoch": 382.44444444444446, "percentage": 86.05, "elapsed_time": "3:54:15", "remaining_time": "0:37:58", "throughput": 686.09, "total_tokens": 9643264} {"current_steps": 34425, "total_steps": 40000, "loss": 0.0, "lr": 2.3592995100855526e-06, "epoch": 382.5, "percentage": 86.06, "elapsed_time": "3:54:17", "remaining_time": "0:37:56", "throughput": 686.1, "total_tokens": 9644672} {"current_steps": 34430, "total_steps": 40000, "loss": 0.0, "lr": 2.3551379292133273e-06, "epoch": 382.55555555555554, "percentage": 86.08, "elapsed_time": "3:54:19", "remaining_time": "0:37:54", "throughput": 686.1, "total_tokens": 9646080} {"current_steps": 34435, "total_steps": 40000, "loss": 0.0, "lr": 2.3509798404634047e-06, "epoch": 382.6111111111111, "percentage": 86.09, "elapsed_time": "3:54:21", "remaining_time": "0:37:52", "throughput": 686.1, "total_tokens": 9647440} {"current_steps": 34440, "total_steps": 40000, "loss": 0.0, "lr": 2.346825244477019e-06, "epoch": 382.6666666666667, "percentage": 86.1, "elapsed_time": "3:54:23", "remaining_time": "0:37:50", "throughput": 686.11, "total_tokens": 9648880} {"current_steps": 34445, "total_steps": 40000, "loss": 0.0, "lr": 2.3426741418948545e-06, "epoch": 382.72222222222223, "percentage": 86.11, "elapsed_time": "3:54:25", "remaining_time": "0:37:48", "throughput": 686.12, "total_tokens": 9650288} {"current_steps": 34450, "total_steps": 40000, "loss": 0.0, "lr": 2.3385265333570715e-06, "epoch": 382.77777777777777, "percentage": 86.12, "elapsed_time": "3:54:27", "remaining_time": "0:37:46", "throughput": 686.12, "total_tokens": 9651664} {"current_steps": 34455, "total_steps": 40000, "loss": 0.0, "lr": 2.334382419503278e-06, "epoch": 382.8333333333333, "percentage": 86.14, "elapsed_time": "3:54:28", "remaining_time": "0:37:44", "throughput": 686.12, "total_tokens": 9653040} {"current_steps": 34460, "total_steps": 40000, "loss": 0.0, "lr": 2.3302418009725465e-06, "epoch": 382.8888888888889, "percentage": 86.15, "elapsed_time": "3:54:30", "remaining_time": "0:37:42", "throughput": 686.13, "total_tokens": 9654432} {"current_steps": 34465, "total_steps": 40000, "loss": 0.0, "lr": 2.326104678403415e-06, "epoch": 382.94444444444446, "percentage": 86.16, "elapsed_time": "3:54:32", "remaining_time": "0:37:40", "throughput": 686.13, "total_tokens": 9655808} {"current_steps": 34470, "total_steps": 40000, "loss": 0.0, "lr": 2.321971052433883e-06, "epoch": 383.0, "percentage": 86.17, "elapsed_time": "3:54:34", "remaining_time": "0:37:38", "throughput": 686.13, "total_tokens": 9657216} {"current_steps": 34475, "total_steps": 40000, "loss": 0.0, "lr": 2.3178409237014004e-06, "epoch": 383.05555555555554, "percentage": 86.19, "elapsed_time": "3:54:37", "remaining_time": "0:37:36", "throughput": 686.12, "total_tokens": 9658640} {"current_steps": 34480, "total_steps": 40000, "loss": 0.0, "lr": 2.313714292842889e-06, "epoch": 383.1111111111111, "percentage": 86.2, "elapsed_time": "3:54:39", "remaining_time": "0:37:33", "throughput": 686.12, "total_tokens": 9660048} {"current_steps": 34485, "total_steps": 40000, "loss": 0.0, "lr": 2.309591160494734e-06, "epoch": 383.1666666666667, "percentage": 86.21, "elapsed_time": "3:54:41", "remaining_time": "0:37:31", "throughput": 686.12, "total_tokens": 9661488} {"current_steps": 34490, "total_steps": 40000, "loss": 0.0, "lr": 2.305471527292763e-06, "epoch": 383.22222222222223, "percentage": 86.22, "elapsed_time": "3:54:43", "remaining_time": "0:37:29", "throughput": 686.12, "total_tokens": 9662880} {"current_steps": 34495, "total_steps": 40000, "loss": 0.0, "lr": 2.3013553938722817e-06, "epoch": 383.27777777777777, "percentage": 86.24, "elapsed_time": "3:54:45", "remaining_time": "0:37:27", "throughput": 686.12, "total_tokens": 9664288} {"current_steps": 34500, "total_steps": 40000, "loss": 0.0, "lr": 2.297242760868043e-06, "epoch": 383.3333333333333, "percentage": 86.25, "elapsed_time": "3:54:47", "remaining_time": "0:37:25", "throughput": 686.13, "total_tokens": 9665728} {"current_steps": 34505, "total_steps": 40000, "loss": 0.0, "lr": 2.2931336289142735e-06, "epoch": 383.3888888888889, "percentage": 86.26, "elapsed_time": "3:54:49", "remaining_time": "0:37:23", "throughput": 686.13, "total_tokens": 9667120} {"current_steps": 34510, "total_steps": 40000, "loss": 0.0, "lr": 2.289027998644655e-06, "epoch": 383.44444444444446, "percentage": 86.28, "elapsed_time": "3:54:51", "remaining_time": "0:37:21", "throughput": 686.12, "total_tokens": 9668512} {"current_steps": 34515, "total_steps": 40000, "loss": 0.0, "lr": 2.2849258706923228e-06, "epoch": 383.5, "percentage": 86.29, "elapsed_time": "3:54:53", "remaining_time": "0:37:19", "throughput": 686.12, "total_tokens": 9669872} {"current_steps": 34520, "total_steps": 40000, "loss": 0.0, "lr": 2.2808272456898705e-06, "epoch": 383.55555555555554, "percentage": 86.3, "elapsed_time": "3:54:55", "remaining_time": "0:37:17", "throughput": 686.12, "total_tokens": 9671280} {"current_steps": 34525, "total_steps": 40000, "loss": 0.0, "lr": 2.2767321242693707e-06, "epoch": 383.6111111111111, "percentage": 86.31, "elapsed_time": "3:54:57", "remaining_time": "0:37:15", "throughput": 686.12, "total_tokens": 9672672} {"current_steps": 34530, "total_steps": 40000, "loss": 0.0, "lr": 2.272640507062329e-06, "epoch": 383.6666666666667, "percentage": 86.33, "elapsed_time": "3:54:59", "remaining_time": "0:37:13", "throughput": 686.12, "total_tokens": 9674048} {"current_steps": 34535, "total_steps": 40000, "loss": 0.0, "lr": 2.2685523946997382e-06, "epoch": 383.72222222222223, "percentage": 86.34, "elapsed_time": "3:55:01", "remaining_time": "0:37:11", "throughput": 686.12, "total_tokens": 9675472} {"current_steps": 34540, "total_steps": 40000, "loss": 0.0, "lr": 2.2644677878120245e-06, "epoch": 383.77777777777777, "percentage": 86.35, "elapsed_time": "3:55:03", "remaining_time": "0:37:09", "throughput": 686.12, "total_tokens": 9676864} {"current_steps": 34545, "total_steps": 40000, "loss": 0.0, "lr": 2.2603866870290897e-06, "epoch": 383.8333333333333, "percentage": 86.36, "elapsed_time": "3:55:05", "remaining_time": "0:37:07", "throughput": 686.13, "total_tokens": 9678288} {"current_steps": 34550, "total_steps": 40000, "loss": 0.0, "lr": 2.256309092980294e-06, "epoch": 383.8888888888889, "percentage": 86.38, "elapsed_time": "3:55:07", "remaining_time": "0:37:05", "throughput": 686.13, "total_tokens": 9679696} {"current_steps": 34555, "total_steps": 40000, "loss": 0.0, "lr": 2.252235006294448e-06, "epoch": 383.94444444444446, "percentage": 86.39, "elapsed_time": "3:55:09", "remaining_time": "0:37:03", "throughput": 686.13, "total_tokens": 9681104} {"current_steps": 34560, "total_steps": 40000, "loss": 0.0, "lr": 2.2481644275998333e-06, "epoch": 384.0, "percentage": 86.4, "elapsed_time": "3:55:11", "remaining_time": "0:37:01", "throughput": 686.12, "total_tokens": 9682528} {"current_steps": 34565, "total_steps": 40000, "loss": 0.0, "lr": 2.2440973575241832e-06, "epoch": 384.05555555555554, "percentage": 86.41, "elapsed_time": "3:55:14", "remaining_time": "0:36:59", "throughput": 686.11, "total_tokens": 9683920} {"current_steps": 34570, "total_steps": 40000, "loss": 0.0, "lr": 2.240033796694685e-06, "epoch": 384.1111111111111, "percentage": 86.42, "elapsed_time": "3:55:16", "remaining_time": "0:36:57", "throughput": 686.11, "total_tokens": 9685280} {"current_steps": 34575, "total_steps": 40000, "loss": 0.0, "lr": 2.235973745737999e-06, "epoch": 384.1666666666667, "percentage": 86.44, "elapsed_time": "3:55:18", "remaining_time": "0:36:55", "throughput": 686.11, "total_tokens": 9686656} {"current_steps": 34580, "total_steps": 40000, "loss": 0.0, "lr": 2.2319172052802263e-06, "epoch": 384.22222222222223, "percentage": 86.45, "elapsed_time": "3:55:20", "remaining_time": "0:36:53", "throughput": 686.11, "total_tokens": 9688064} {"current_steps": 34585, "total_steps": 40000, "loss": 0.0, "lr": 2.2278641759469477e-06, "epoch": 384.27777777777777, "percentage": 86.46, "elapsed_time": "3:55:22", "remaining_time": "0:36:51", "throughput": 686.11, "total_tokens": 9689456} {"current_steps": 34590, "total_steps": 40000, "loss": 0.0, "lr": 2.2238146583631825e-06, "epoch": 384.3333333333333, "percentage": 86.48, "elapsed_time": "3:55:24", "remaining_time": "0:36:49", "throughput": 686.12, "total_tokens": 9690848} {"current_steps": 34595, "total_steps": 40000, "loss": 0.0, "lr": 2.2197686531534256e-06, "epoch": 384.3888888888889, "percentage": 86.49, "elapsed_time": "3:55:26", "remaining_time": "0:36:47", "throughput": 686.12, "total_tokens": 9692208} {"current_steps": 34600, "total_steps": 40000, "loss": 0.0, "lr": 2.2157261609416087e-06, "epoch": 384.44444444444446, "percentage": 86.5, "elapsed_time": "3:55:28", "remaining_time": "0:36:44", "throughput": 686.12, "total_tokens": 9693568} {"current_steps": 34600, "total_steps": 40000, "eval_loss": 0.3269561529159546, "epoch": 384.44444444444446, "percentage": 86.5, "elapsed_time": "3:55:29", "remaining_time": "0:36:45", "throughput": 686.06, "total_tokens": 9693568} {"current_steps": 34605, "total_steps": 40000, "loss": 0.0, "lr": 2.211687182351149e-06, "epoch": 384.5, "percentage": 86.51, "elapsed_time": "3:55:32", "remaining_time": "0:36:43", "throughput": 685.99, "total_tokens": 9694960} {"current_steps": 34610, "total_steps": 40000, "loss": 0.0, "lr": 2.2076517180048993e-06, "epoch": 384.55555555555554, "percentage": 86.52, "elapsed_time": "3:55:34", "remaining_time": "0:36:41", "throughput": 686.0, "total_tokens": 9696400} {"current_steps": 34615, "total_steps": 40000, "loss": 0.0, "lr": 2.2036197685251834e-06, "epoch": 384.6111111111111, "percentage": 86.54, "elapsed_time": "3:55:36", "remaining_time": "0:36:39", "throughput": 686.0, "total_tokens": 9697808} {"current_steps": 34620, "total_steps": 40000, "loss": 0.0, "lr": 2.199591334533771e-06, "epoch": 384.6666666666667, "percentage": 86.55, "elapsed_time": "3:55:38", "remaining_time": "0:36:37", "throughput": 686.01, "total_tokens": 9699216} {"current_steps": 34625, "total_steps": 40000, "loss": 0.0, "lr": 2.1955664166519036e-06, "epoch": 384.72222222222223, "percentage": 86.56, "elapsed_time": "3:55:40", "remaining_time": "0:36:35", "throughput": 686.01, "total_tokens": 9700656} {"current_steps": 34630, "total_steps": 40000, "loss": 0.0, "lr": 2.1915450155002793e-06, "epoch": 384.77777777777777, "percentage": 86.58, "elapsed_time": "3:55:42", "remaining_time": "0:36:33", "throughput": 686.02, "total_tokens": 9702080} {"current_steps": 34635, "total_steps": 40000, "loss": 0.0, "lr": 2.187527131699038e-06, "epoch": 384.8333333333333, "percentage": 86.59, "elapsed_time": "3:55:44", "remaining_time": "0:36:30", "throughput": 686.03, "total_tokens": 9703520} {"current_steps": 34640, "total_steps": 40000, "loss": 0.0, "lr": 2.18351276586779e-06, "epoch": 384.8888888888889, "percentage": 86.6, "elapsed_time": "3:55:46", "remaining_time": "0:36:28", "throughput": 686.04, "total_tokens": 9704976} {"current_steps": 34645, "total_steps": 40000, "loss": 0.0, "lr": 2.1795019186256092e-06, "epoch": 384.94444444444446, "percentage": 86.61, "elapsed_time": "3:55:48", "remaining_time": "0:36:26", "throughput": 686.04, "total_tokens": 9706400} {"current_steps": 34650, "total_steps": 40000, "loss": 0.0, "lr": 2.1754945905910094e-06, "epoch": 385.0, "percentage": 86.62, "elapsed_time": "3:55:50", "remaining_time": "0:36:24", "throughput": 686.04, "total_tokens": 9707776} {"current_steps": 34655, "total_steps": 40000, "loss": 0.0, "lr": 2.171490782381977e-06, "epoch": 385.05555555555554, "percentage": 86.64, "elapsed_time": "3:55:52", "remaining_time": "0:36:22", "throughput": 686.03, "total_tokens": 9709200} {"current_steps": 34660, "total_steps": 40000, "loss": 0.0, "lr": 2.1674904946159425e-06, "epoch": 385.1111111111111, "percentage": 86.65, "elapsed_time": "3:55:54", "remaining_time": "0:36:20", "throughput": 686.03, "total_tokens": 9710544} {"current_steps": 34665, "total_steps": 40000, "loss": 0.0, "lr": 2.16349372790981e-06, "epoch": 385.1666666666667, "percentage": 86.66, "elapsed_time": "3:55:56", "remaining_time": "0:36:18", "throughput": 686.04, "total_tokens": 9711904} {"current_steps": 34670, "total_steps": 40000, "loss": 0.0, "lr": 2.159500482879928e-06, "epoch": 385.22222222222223, "percentage": 86.67, "elapsed_time": "3:55:58", "remaining_time": "0:36:16", "throughput": 686.05, "total_tokens": 9713360} {"current_steps": 34675, "total_steps": 40000, "loss": 0.0, "lr": 2.155510760142096e-06, "epoch": 385.27777777777777, "percentage": 86.69, "elapsed_time": "3:56:00", "remaining_time": "0:36:14", "throughput": 686.04, "total_tokens": 9714672} {"current_steps": 34680, "total_steps": 40000, "loss": 0.0, "lr": 2.151524560311588e-06, "epoch": 385.3333333333333, "percentage": 86.7, "elapsed_time": "3:56:02", "remaining_time": "0:36:12", "throughput": 686.05, "total_tokens": 9716048} {"current_steps": 34685, "total_steps": 40000, "loss": 0.0, "lr": 2.147541884003129e-06, "epoch": 385.3888888888889, "percentage": 86.71, "elapsed_time": "3:56:04", "remaining_time": "0:36:10", "throughput": 686.05, "total_tokens": 9717456} {"current_steps": 34690, "total_steps": 40000, "loss": 0.0, "lr": 2.1435627318308895e-06, "epoch": 385.44444444444446, "percentage": 86.72, "elapsed_time": "3:56:06", "remaining_time": "0:36:08", "throughput": 686.06, "total_tokens": 9718832} {"current_steps": 34695, "total_steps": 40000, "loss": 0.0, "lr": 2.139587104408511e-06, "epoch": 385.5, "percentage": 86.74, "elapsed_time": "3:56:08", "remaining_time": "0:36:06", "throughput": 686.06, "total_tokens": 9720224} {"current_steps": 34700, "total_steps": 40000, "loss": 0.0, "lr": 2.1356150023490783e-06, "epoch": 385.55555555555554, "percentage": 86.75, "elapsed_time": "3:56:10", "remaining_time": "0:36:04", "throughput": 686.07, "total_tokens": 9721680} {"current_steps": 34705, "total_steps": 40000, "loss": 0.0, "lr": 2.1316464262651464e-06, "epoch": 385.6111111111111, "percentage": 86.76, "elapsed_time": "3:56:12", "remaining_time": "0:36:02", "throughput": 686.07, "total_tokens": 9723088} {"current_steps": 34710, "total_steps": 40000, "loss": 0.0, "lr": 2.1276813767687224e-06, "epoch": 385.6666666666667, "percentage": 86.78, "elapsed_time": "3:56:14", "remaining_time": "0:36:00", "throughput": 686.07, "total_tokens": 9724480} {"current_steps": 34715, "total_steps": 40000, "loss": 0.0, "lr": 2.123719854471254e-06, "epoch": 385.72222222222223, "percentage": 86.79, "elapsed_time": "3:56:16", "remaining_time": "0:35:58", "throughput": 686.08, "total_tokens": 9725904} {"current_steps": 34720, "total_steps": 40000, "loss": 0.0, "lr": 2.119761859983668e-06, "epoch": 385.77777777777777, "percentage": 86.8, "elapsed_time": "3:56:18", "remaining_time": "0:35:56", "throughput": 686.08, "total_tokens": 9727296} {"current_steps": 34725, "total_steps": 40000, "loss": 0.0, "lr": 2.1158073939163386e-06, "epoch": 385.8333333333333, "percentage": 86.81, "elapsed_time": "3:56:20", "remaining_time": "0:35:54", "throughput": 686.08, "total_tokens": 9728704} {"current_steps": 34730, "total_steps": 40000, "loss": 0.0, "lr": 2.111856456879088e-06, "epoch": 385.8888888888889, "percentage": 86.83, "elapsed_time": "3:56:22", "remaining_time": "0:35:52", "throughput": 686.08, "total_tokens": 9730096} {"current_steps": 34735, "total_steps": 40000, "loss": 0.0, "lr": 2.1079090494811993e-06, "epoch": 385.94444444444446, "percentage": 86.84, "elapsed_time": "3:56:24", "remaining_time": "0:35:49", "throughput": 686.08, "total_tokens": 9731536} {"current_steps": 34740, "total_steps": 40000, "loss": 0.0, "lr": 2.103965172331418e-06, "epoch": 386.0, "percentage": 86.85, "elapsed_time": "3:56:26", "remaining_time": "0:35:47", "throughput": 686.07, "total_tokens": 9732960} {"current_steps": 34745, "total_steps": 40000, "loss": 0.0, "lr": 2.100024826037933e-06, "epoch": 386.05555555555554, "percentage": 86.86, "elapsed_time": "3:56:28", "remaining_time": "0:35:45", "throughput": 686.06, "total_tokens": 9734320} {"current_steps": 34750, "total_steps": 40000, "loss": 0.0, "lr": 2.0960880112084027e-06, "epoch": 386.1111111111111, "percentage": 86.88, "elapsed_time": "3:56:30", "remaining_time": "0:35:43", "throughput": 686.06, "total_tokens": 9735728} {"current_steps": 34755, "total_steps": 40000, "loss": 0.0, "lr": 2.092154728449927e-06, "epoch": 386.1666666666667, "percentage": 86.89, "elapsed_time": "3:56:32", "remaining_time": "0:35:41", "throughput": 686.06, "total_tokens": 9737120} {"current_steps": 34760, "total_steps": 40000, "loss": 0.0, "lr": 2.0882249783690687e-06, "epoch": 386.22222222222223, "percentage": 86.9, "elapsed_time": "3:56:34", "remaining_time": "0:35:39", "throughput": 686.06, "total_tokens": 9738560} {"current_steps": 34765, "total_steps": 40000, "loss": 0.0, "lr": 2.084298761571851e-06, "epoch": 386.27777777777777, "percentage": 86.91, "elapsed_time": "3:56:36", "remaining_time": "0:35:37", "throughput": 686.06, "total_tokens": 9739952} {"current_steps": 34770, "total_steps": 40000, "loss": 0.0, "lr": 2.080376078663737e-06, "epoch": 386.3333333333333, "percentage": 86.92, "elapsed_time": "3:56:38", "remaining_time": "0:35:35", "throughput": 686.06, "total_tokens": 9741344} {"current_steps": 34775, "total_steps": 40000, "loss": 0.0, "lr": 2.0764569302496593e-06, "epoch": 386.3888888888889, "percentage": 86.94, "elapsed_time": "3:56:40", "remaining_time": "0:35:33", "throughput": 686.07, "total_tokens": 9742752} {"current_steps": 34780, "total_steps": 40000, "loss": 0.0, "lr": 2.0725413169339957e-06, "epoch": 386.44444444444446, "percentage": 86.95, "elapsed_time": "3:56:42", "remaining_time": "0:35:31", "throughput": 686.07, "total_tokens": 9744176} {"current_steps": 34785, "total_steps": 40000, "loss": 0.0, "lr": 2.068629239320588e-06, "epoch": 386.5, "percentage": 86.96, "elapsed_time": "3:56:44", "remaining_time": "0:35:29", "throughput": 686.07, "total_tokens": 9745536} {"current_steps": 34790, "total_steps": 40000, "loss": 0.0, "lr": 2.064720698012726e-06, "epoch": 386.55555555555554, "percentage": 86.98, "elapsed_time": "3:56:47", "remaining_time": "0:35:27", "throughput": 686.06, "total_tokens": 9746976} {"current_steps": 34795, "total_steps": 40000, "loss": 0.0, "lr": 2.0608156936131522e-06, "epoch": 386.6111111111111, "percentage": 86.99, "elapsed_time": "3:56:49", "remaining_time": "0:35:25", "throughput": 686.06, "total_tokens": 9748368} {"current_steps": 34800, "total_steps": 40000, "loss": 0.0, "lr": 2.056914226724074e-06, "epoch": 386.6666666666667, "percentage": 87.0, "elapsed_time": "3:56:51", "remaining_time": "0:35:23", "throughput": 686.06, "total_tokens": 9749792} {"current_steps": 34800, "total_steps": 40000, "eval_loss": 0.37162813544273376, "epoch": 386.6666666666667, "percentage": 87.0, "elapsed_time": "3:56:52", "remaining_time": "0:35:23", "throughput": 685.99, "total_tokens": 9749792} {"current_steps": 34805, "total_steps": 40000, "loss": 0.0, "lr": 2.0530162979471385e-06, "epoch": 386.72222222222223, "percentage": 87.01, "elapsed_time": "3:56:56", "remaining_time": "0:35:21", "throughput": 685.92, "total_tokens": 9751200} {"current_steps": 34810, "total_steps": 40000, "loss": 0.0, "lr": 2.0491219078834667e-06, "epoch": 386.77777777777777, "percentage": 87.02, "elapsed_time": "3:56:58", "remaining_time": "0:35:19", "throughput": 685.92, "total_tokens": 9752576} {"current_steps": 34815, "total_steps": 40000, "loss": 0.0, "lr": 2.045231057133612e-06, "epoch": 386.8333333333333, "percentage": 87.04, "elapsed_time": "3:57:00", "remaining_time": "0:35:17", "throughput": 685.92, "total_tokens": 9753968} {"current_steps": 34820, "total_steps": 40000, "loss": 0.0, "lr": 2.0413437462975944e-06, "epoch": 386.8888888888889, "percentage": 87.05, "elapsed_time": "3:57:02", "remaining_time": "0:35:15", "throughput": 685.92, "total_tokens": 9755360} {"current_steps": 34825, "total_steps": 40000, "loss": 0.0, "lr": 2.0374599759748843e-06, "epoch": 386.94444444444446, "percentage": 87.06, "elapsed_time": "3:57:04", "remaining_time": "0:35:13", "throughput": 685.92, "total_tokens": 9756784} {"current_steps": 34830, "total_steps": 40000, "loss": 0.0, "lr": 2.033579746764419e-06, "epoch": 387.0, "percentage": 87.08, "elapsed_time": "3:57:06", "remaining_time": "0:35:11", "throughput": 685.91, "total_tokens": 9758160} {"current_steps": 34835, "total_steps": 40000, "loss": 0.0, "lr": 2.029703059264565e-06, "epoch": 387.05555555555554, "percentage": 87.09, "elapsed_time": "3:57:08", "remaining_time": "0:35:09", "throughput": 685.9, "total_tokens": 9759536} {"current_steps": 34840, "total_steps": 40000, "loss": 0.0, "lr": 2.02582991407316e-06, "epoch": 387.1111111111111, "percentage": 87.1, "elapsed_time": "3:57:10", "remaining_time": "0:35:07", "throughput": 685.89, "total_tokens": 9760896} {"current_steps": 34845, "total_steps": 40000, "loss": 0.0, "lr": 2.0219603117874992e-06, "epoch": 387.1666666666667, "percentage": 87.11, "elapsed_time": "3:57:12", "remaining_time": "0:35:05", "throughput": 685.89, "total_tokens": 9762272} {"current_steps": 34850, "total_steps": 40000, "loss": 0.0, "lr": 2.0180942530043156e-06, "epoch": 387.22222222222223, "percentage": 87.12, "elapsed_time": "3:57:14", "remaining_time": "0:35:03", "throughput": 685.9, "total_tokens": 9763648} {"current_steps": 34855, "total_steps": 40000, "loss": 0.0, "lr": 2.0142317383198107e-06, "epoch": 387.27777777777777, "percentage": 87.14, "elapsed_time": "3:57:16", "remaining_time": "0:35:01", "throughput": 685.9, "total_tokens": 9765072} {"current_steps": 34860, "total_steps": 40000, "loss": 0.0, "lr": 2.0103727683296243e-06, "epoch": 387.3333333333333, "percentage": 87.15, "elapsed_time": "3:57:18", "remaining_time": "0:34:59", "throughput": 685.91, "total_tokens": 9766496} {"current_steps": 34865, "total_steps": 40000, "loss": 0.0, "lr": 2.0065173436288636e-06, "epoch": 387.3888888888889, "percentage": 87.16, "elapsed_time": "3:57:20", "remaining_time": "0:34:57", "throughput": 685.91, "total_tokens": 9767888} {"current_steps": 34870, "total_steps": 40000, "loss": 0.0, "lr": 2.002665464812087e-06, "epoch": 387.44444444444446, "percentage": 87.17, "elapsed_time": "3:57:22", "remaining_time": "0:34:55", "throughput": 685.92, "total_tokens": 9769312} {"current_steps": 34875, "total_steps": 40000, "loss": 0.0, "lr": 1.998817132473291e-06, "epoch": 387.5, "percentage": 87.19, "elapsed_time": "3:57:24", "remaining_time": "0:34:53", "throughput": 685.93, "total_tokens": 9770768} {"current_steps": 34880, "total_steps": 40000, "loss": 0.0, "lr": 1.9949723472059507e-06, "epoch": 387.55555555555554, "percentage": 87.2, "elapsed_time": "3:57:26", "remaining_time": "0:34:51", "throughput": 685.94, "total_tokens": 9772240} {"current_steps": 34885, "total_steps": 40000, "loss": 0.0, "lr": 1.9911311096029726e-06, "epoch": 387.6111111111111, "percentage": 87.21, "elapsed_time": "3:57:28", "remaining_time": "0:34:49", "throughput": 685.94, "total_tokens": 9773648} {"current_steps": 34890, "total_steps": 40000, "loss": 0.0, "lr": 1.9872934202567224e-06, "epoch": 387.6666666666667, "percentage": 87.22, "elapsed_time": "3:57:30", "remaining_time": "0:34:47", "throughput": 685.95, "total_tokens": 9775040} {"current_steps": 34895, "total_steps": 40000, "loss": 0.0, "lr": 1.9834592797590257e-06, "epoch": 387.72222222222223, "percentage": 87.24, "elapsed_time": "3:57:32", "remaining_time": "0:34:45", "throughput": 685.95, "total_tokens": 9776448} {"current_steps": 34900, "total_steps": 40000, "loss": 0.0, "lr": 1.979628688701149e-06, "epoch": 387.77777777777777, "percentage": 87.25, "elapsed_time": "3:57:34", "remaining_time": "0:34:43", "throughput": 685.96, "total_tokens": 9777888} {"current_steps": 34905, "total_steps": 40000, "loss": 0.0, "lr": 1.9758016476738193e-06, "epoch": 387.8333333333333, "percentage": 87.26, "elapsed_time": "3:57:36", "remaining_time": "0:34:40", "throughput": 685.97, "total_tokens": 9779328} {"current_steps": 34910, "total_steps": 40000, "loss": 0.0, "lr": 1.971978157267221e-06, "epoch": 387.8888888888889, "percentage": 87.28, "elapsed_time": "3:57:38", "remaining_time": "0:34:38", "throughput": 685.97, "total_tokens": 9780688} {"current_steps": 34915, "total_steps": 40000, "loss": 0.0, "lr": 1.968158218070973e-06, "epoch": 387.94444444444446, "percentage": 87.29, "elapsed_time": "3:57:40", "remaining_time": "0:34:36", "throughput": 685.98, "total_tokens": 9782064} {"current_steps": 34920, "total_steps": 40000, "loss": 0.0, "lr": 1.9643418306741682e-06, "epoch": 388.0, "percentage": 87.3, "elapsed_time": "3:57:42", "remaining_time": "0:34:34", "throughput": 685.97, "total_tokens": 9783408} {"current_steps": 34925, "total_steps": 40000, "loss": 0.0, "lr": 1.9605289956653337e-06, "epoch": 388.05555555555554, "percentage": 87.31, "elapsed_time": "3:57:44", "remaining_time": "0:34:32", "throughput": 685.96, "total_tokens": 9784832} {"current_steps": 34930, "total_steps": 40000, "loss": 0.0, "lr": 1.9567197136324626e-06, "epoch": 388.1111111111111, "percentage": 87.33, "elapsed_time": "3:57:46", "remaining_time": "0:34:30", "throughput": 685.97, "total_tokens": 9786240} {"current_steps": 34935, "total_steps": 40000, "loss": 0.0, "lr": 1.9529139851629935e-06, "epoch": 388.1666666666667, "percentage": 87.34, "elapsed_time": "3:57:48", "remaining_time": "0:34:28", "throughput": 685.98, "total_tokens": 9787664} {"current_steps": 34940, "total_steps": 40000, "loss": 0.0, "lr": 1.949111810843812e-06, "epoch": 388.22222222222223, "percentage": 87.35, "elapsed_time": "3:57:50", "remaining_time": "0:34:26", "throughput": 685.98, "total_tokens": 9789088} {"current_steps": 34945, "total_steps": 40000, "loss": 0.0, "lr": 1.9453131912612694e-06, "epoch": 388.27777777777777, "percentage": 87.36, "elapsed_time": "3:57:52", "remaining_time": "0:34:24", "throughput": 685.99, "total_tokens": 9790528} {"current_steps": 34950, "total_steps": 40000, "loss": 0.0, "lr": 1.941518127001149e-06, "epoch": 388.3333333333333, "percentage": 87.38, "elapsed_time": "3:57:54", "remaining_time": "0:34:22", "throughput": 686.0, "total_tokens": 9791952} {"current_steps": 34955, "total_steps": 40000, "loss": 0.0, "lr": 1.9377266186487107e-06, "epoch": 388.3888888888889, "percentage": 87.39, "elapsed_time": "3:57:56", "remaining_time": "0:34:20", "throughput": 686.0, "total_tokens": 9793312} {"current_steps": 34960, "total_steps": 40000, "loss": 0.0, "lr": 1.9339386667886483e-06, "epoch": 388.44444444444446, "percentage": 87.4, "elapsed_time": "3:57:57", "remaining_time": "0:34:18", "throughput": 686.0, "total_tokens": 9794688} {"current_steps": 34965, "total_steps": 40000, "loss": 0.0, "lr": 1.9301542720051024e-06, "epoch": 388.5, "percentage": 87.41, "elapsed_time": "3:57:59", "remaining_time": "0:34:16", "throughput": 686.01, "total_tokens": 9796080} {"current_steps": 34970, "total_steps": 40000, "loss": 0.0, "lr": 1.926373434881684e-06, "epoch": 388.55555555555554, "percentage": 87.42, "elapsed_time": "3:58:01", "remaining_time": "0:34:14", "throughput": 686.01, "total_tokens": 9797440} {"current_steps": 34975, "total_steps": 40000, "loss": 0.0, "lr": 1.9225961560014468e-06, "epoch": 388.6111111111111, "percentage": 87.44, "elapsed_time": "3:58:03", "remaining_time": "0:34:12", "throughput": 686.01, "total_tokens": 9798832} {"current_steps": 34980, "total_steps": 40000, "loss": 0.0, "lr": 1.918822435946885e-06, "epoch": 388.6666666666667, "percentage": 87.45, "elapsed_time": "3:58:05", "remaining_time": "0:34:10", "throughput": 686.02, "total_tokens": 9800240} {"current_steps": 34985, "total_steps": 40000, "loss": 0.0, "lr": 1.915052275299961e-06, "epoch": 388.72222222222223, "percentage": 87.46, "elapsed_time": "3:58:07", "remaining_time": "0:34:08", "throughput": 686.02, "total_tokens": 9801616} {"current_steps": 34990, "total_steps": 40000, "loss": 0.0, "lr": 1.9112856746420854e-06, "epoch": 388.77777777777777, "percentage": 87.48, "elapsed_time": "3:58:09", "remaining_time": "0:34:06", "throughput": 686.03, "total_tokens": 9803072} {"current_steps": 34995, "total_steps": 40000, "loss": 0.0, "lr": 1.907522634554104e-06, "epoch": 388.8333333333333, "percentage": 87.49, "elapsed_time": "3:58:11", "remaining_time": "0:34:03", "throughput": 686.03, "total_tokens": 9804448} {"current_steps": 35000, "total_steps": 40000, "loss": 0.0, "lr": 1.9037631556163337e-06, "epoch": 388.8888888888889, "percentage": 87.5, "elapsed_time": "3:58:13", "remaining_time": "0:34:01", "throughput": 686.04, "total_tokens": 9805840} {"current_steps": 35000, "total_steps": 40000, "eval_loss": 0.34753549098968506, "epoch": 388.8888888888889, "percentage": 87.5, "elapsed_time": "3:58:14", "remaining_time": "0:34:02", "throughput": 685.97, "total_tokens": 9805840} {"current_steps": 35005, "total_steps": 40000, "loss": 0.0, "lr": 1.9000072384085272e-06, "epoch": 388.94444444444446, "percentage": 87.51, "elapsed_time": "3:58:18", "remaining_time": "0:34:00", "throughput": 685.91, "total_tokens": 9807200} {"current_steps": 35010, "total_steps": 40000, "loss": 0.0, "lr": 1.8962548835098987e-06, "epoch": 389.0, "percentage": 87.52, "elapsed_time": "3:58:20", "remaining_time": "0:33:58", "throughput": 685.91, "total_tokens": 9808608} {"current_steps": 35015, "total_steps": 40000, "loss": 0.0, "lr": 1.8925060914991077e-06, "epoch": 389.05555555555554, "percentage": 87.54, "elapsed_time": "3:58:22", "remaining_time": "0:33:56", "throughput": 685.9, "total_tokens": 9810032} {"current_steps": 35020, "total_steps": 40000, "loss": 0.0, "lr": 1.888760862954264e-06, "epoch": 389.1111111111111, "percentage": 87.55, "elapsed_time": "3:58:24", "remaining_time": "0:33:54", "throughput": 685.9, "total_tokens": 9811424} {"current_steps": 35025, "total_steps": 40000, "loss": 0.0, "lr": 1.8850191984529309e-06, "epoch": 389.1666666666667, "percentage": 87.56, "elapsed_time": "3:58:26", "remaining_time": "0:33:52", "throughput": 685.9, "total_tokens": 9812816} {"current_steps": 35030, "total_steps": 40000, "loss": 0.0, "lr": 1.8812810985721186e-06, "epoch": 389.22222222222223, "percentage": 87.58, "elapsed_time": "3:58:28", "remaining_time": "0:33:50", "throughput": 685.9, "total_tokens": 9814176} {"current_steps": 35035, "total_steps": 40000, "loss": 0.0, "lr": 1.8775465638882856e-06, "epoch": 389.27777777777777, "percentage": 87.59, "elapsed_time": "3:58:30", "remaining_time": "0:33:48", "throughput": 685.9, "total_tokens": 9815552} {"current_steps": 35040, "total_steps": 40000, "loss": 0.0, "lr": 1.8738155949773517e-06, "epoch": 389.3333333333333, "percentage": 87.6, "elapsed_time": "3:58:32", "remaining_time": "0:33:45", "throughput": 685.9, "total_tokens": 9816976} {"current_steps": 35045, "total_steps": 40000, "loss": 0.0, "lr": 1.8700881924146707e-06, "epoch": 389.3888888888889, "percentage": 87.61, "elapsed_time": "3:58:34", "remaining_time": "0:33:43", "throughput": 685.9, "total_tokens": 9818416} {"current_steps": 35050, "total_steps": 40000, "loss": 0.0, "lr": 1.8663643567750577e-06, "epoch": 389.44444444444446, "percentage": 87.62, "elapsed_time": "3:58:36", "remaining_time": "0:33:41", "throughput": 685.91, "total_tokens": 9819840} {"current_steps": 35055, "total_steps": 40000, "loss": 0.0, "lr": 1.8626440886327813e-06, "epoch": 389.5, "percentage": 87.64, "elapsed_time": "3:58:38", "remaining_time": "0:33:39", "throughput": 685.9, "total_tokens": 9821216} {"current_steps": 35060, "total_steps": 40000, "loss": 0.0, "lr": 1.8589273885615432e-06, "epoch": 389.55555555555554, "percentage": 87.65, "elapsed_time": "3:58:40", "remaining_time": "0:33:37", "throughput": 685.91, "total_tokens": 9822640} {"current_steps": 35065, "total_steps": 40000, "loss": 0.0, "lr": 1.8552142571345133e-06, "epoch": 389.6111111111111, "percentage": 87.66, "elapsed_time": "3:58:42", "remaining_time": "0:33:35", "throughput": 685.91, "total_tokens": 9824064} {"current_steps": 35070, "total_steps": 40000, "loss": 0.0, "lr": 1.8515046949243025e-06, "epoch": 389.6666666666667, "percentage": 87.67, "elapsed_time": "3:58:44", "remaining_time": "0:33:33", "throughput": 685.91, "total_tokens": 9825520} {"current_steps": 35075, "total_steps": 40000, "loss": 0.0, "lr": 1.8477987025029674e-06, "epoch": 389.72222222222223, "percentage": 87.69, "elapsed_time": "3:58:46", "remaining_time": "0:33:31", "throughput": 685.91, "total_tokens": 9826864} {"current_steps": 35080, "total_steps": 40000, "loss": 0.0, "lr": 1.8440962804420232e-06, "epoch": 389.77777777777777, "percentage": 87.7, "elapsed_time": "3:58:48", "remaining_time": "0:33:29", "throughput": 685.91, "total_tokens": 9828272} {"current_steps": 35085, "total_steps": 40000, "loss": 0.0, "lr": 1.8403974293124265e-06, "epoch": 389.8333333333333, "percentage": 87.71, "elapsed_time": "3:58:50", "remaining_time": "0:33:27", "throughput": 685.91, "total_tokens": 9829632} {"current_steps": 35090, "total_steps": 40000, "loss": 0.0, "lr": 1.8367021496845854e-06, "epoch": 389.8888888888889, "percentage": 87.72, "elapsed_time": "3:58:52", "remaining_time": "0:33:25", "throughput": 685.91, "total_tokens": 9831072} {"current_steps": 35095, "total_steps": 40000, "loss": 0.0, "lr": 1.8330104421283662e-06, "epoch": 389.94444444444446, "percentage": 87.74, "elapsed_time": "3:58:54", "remaining_time": "0:33:23", "throughput": 685.91, "total_tokens": 9832448} {"current_steps": 35100, "total_steps": 40000, "loss": 0.0, "lr": 1.8293223072130717e-06, "epoch": 390.0, "percentage": 87.75, "elapsed_time": "3:58:57", "remaining_time": "0:33:21", "throughput": 685.9, "total_tokens": 9833840} {"current_steps": 35105, "total_steps": 40000, "loss": 0.0, "lr": 1.8256377455074525e-06, "epoch": 390.05555555555554, "percentage": 87.76, "elapsed_time": "3:58:59", "remaining_time": "0:33:19", "throughput": 685.89, "total_tokens": 9835216} {"current_steps": 35110, "total_steps": 40000, "loss": 0.0, "lr": 1.8219567575797263e-06, "epoch": 390.1111111111111, "percentage": 87.78, "elapsed_time": "3:59:01", "remaining_time": "0:33:17", "throughput": 685.89, "total_tokens": 9836640} {"current_steps": 35115, "total_steps": 40000, "loss": 0.0, "lr": 1.8182793439975365e-06, "epoch": 390.1666666666667, "percentage": 87.79, "elapsed_time": "3:59:03", "remaining_time": "0:33:15", "throughput": 685.9, "total_tokens": 9838096} {"current_steps": 35120, "total_steps": 40000, "loss": 0.0, "lr": 1.8146055053279958e-06, "epoch": 390.22222222222223, "percentage": 87.8, "elapsed_time": "3:59:05", "remaining_time": "0:33:13", "throughput": 685.9, "total_tokens": 9839456} {"current_steps": 35125, "total_steps": 40000, "loss": 0.0, "lr": 1.8109352421376486e-06, "epoch": 390.27777777777777, "percentage": 87.81, "elapsed_time": "3:59:07", "remaining_time": "0:33:11", "throughput": 685.9, "total_tokens": 9840832} {"current_steps": 35130, "total_steps": 40000, "loss": 0.0, "lr": 1.8072685549924972e-06, "epoch": 390.3333333333333, "percentage": 87.83, "elapsed_time": "3:59:09", "remaining_time": "0:33:09", "throughput": 685.9, "total_tokens": 9842256} {"current_steps": 35135, "total_steps": 40000, "loss": 0.0, "lr": 1.8036054444579982e-06, "epoch": 390.3888888888889, "percentage": 87.84, "elapsed_time": "3:59:11", "remaining_time": "0:33:07", "throughput": 685.9, "total_tokens": 9843632} {"current_steps": 35140, "total_steps": 40000, "loss": 0.0, "lr": 1.7999459110990407e-06, "epoch": 390.44444444444446, "percentage": 87.85, "elapsed_time": "3:59:13", "remaining_time": "0:33:05", "throughput": 685.9, "total_tokens": 9845056} {"current_steps": 35145, "total_steps": 40000, "loss": 0.0, "lr": 1.7962899554799712e-06, "epoch": 390.5, "percentage": 87.86, "elapsed_time": "3:59:15", "remaining_time": "0:33:03", "throughput": 685.9, "total_tokens": 9846416} {"current_steps": 35150, "total_steps": 40000, "loss": 0.0, "lr": 1.7926375781645937e-06, "epoch": 390.55555555555554, "percentage": 87.88, "elapsed_time": "3:59:17", "remaining_time": "0:33:01", "throughput": 685.9, "total_tokens": 9847808} {"current_steps": 35155, "total_steps": 40000, "loss": 0.0, "lr": 1.7889887797161359e-06, "epoch": 390.6111111111111, "percentage": 87.89, "elapsed_time": "3:59:19", "remaining_time": "0:32:59", "throughput": 685.9, "total_tokens": 9849184} {"current_steps": 35160, "total_steps": 40000, "loss": 0.0, "lr": 1.7853435606973028e-06, "epoch": 390.6666666666667, "percentage": 87.9, "elapsed_time": "3:59:21", "remaining_time": "0:32:56", "throughput": 685.9, "total_tokens": 9850576} {"current_steps": 35165, "total_steps": 40000, "loss": 0.0, "lr": 1.781701921670223e-06, "epoch": 390.72222222222223, "percentage": 87.91, "elapsed_time": "3:59:23", "remaining_time": "0:32:54", "throughput": 685.89, "total_tokens": 9851920} {"current_steps": 35170, "total_steps": 40000, "loss": 0.0, "lr": 1.7780638631964886e-06, "epoch": 390.77777777777777, "percentage": 87.92, "elapsed_time": "3:59:25", "remaining_time": "0:32:52", "throughput": 685.9, "total_tokens": 9853392} {"current_steps": 35175, "total_steps": 40000, "loss": 0.0, "lr": 1.7744293858371314e-06, "epoch": 390.8333333333333, "percentage": 87.94, "elapsed_time": "3:59:27", "remaining_time": "0:32:50", "throughput": 685.9, "total_tokens": 9854816} {"current_steps": 35180, "total_steps": 40000, "loss": 0.0, "lr": 1.770798490152631e-06, "epoch": 390.8888888888889, "percentage": 87.95, "elapsed_time": "3:59:29", "remaining_time": "0:32:48", "throughput": 685.9, "total_tokens": 9856240} {"current_steps": 35185, "total_steps": 40000, "loss": 0.0, "lr": 1.767171176702917e-06, "epoch": 390.94444444444446, "percentage": 87.96, "elapsed_time": "3:59:31", "remaining_time": "0:32:46", "throughput": 685.9, "total_tokens": 9857616} {"current_steps": 35190, "total_steps": 40000, "loss": 0.0, "lr": 1.7635474460473755e-06, "epoch": 391.0, "percentage": 87.98, "elapsed_time": "3:59:33", "remaining_time": "0:32:44", "throughput": 685.9, "total_tokens": 9859056} {"current_steps": 35195, "total_steps": 40000, "loss": 0.0, "lr": 1.7599272987448206e-06, "epoch": 391.05555555555554, "percentage": 87.99, "elapsed_time": "3:59:36", "remaining_time": "0:32:42", "throughput": 685.89, "total_tokens": 9860480} {"current_steps": 35200, "total_steps": 40000, "loss": 0.0, "lr": 1.7563107353535362e-06, "epoch": 391.1111111111111, "percentage": 88.0, "elapsed_time": "3:59:38", "remaining_time": "0:32:40", "throughput": 685.89, "total_tokens": 9861856} {"current_steps": 35200, "total_steps": 40000, "eval_loss": 0.35917389392852783, "epoch": 391.1111111111111, "percentage": 88.0, "elapsed_time": "3:59:39", "remaining_time": "0:32:40", "throughput": 685.83, "total_tokens": 9861856} {"current_steps": 35205, "total_steps": 40000, "loss": 0.0, "lr": 1.7526977564312263e-06, "epoch": 391.1666666666667, "percentage": 88.01, "elapsed_time": "3:59:42", "remaining_time": "0:32:38", "throughput": 685.76, "total_tokens": 9863248} {"current_steps": 35210, "total_steps": 40000, "loss": 0.0, "lr": 1.7490883625350701e-06, "epoch": 391.22222222222223, "percentage": 88.02, "elapsed_time": "3:59:45", "remaining_time": "0:32:36", "throughput": 685.75, "total_tokens": 9864592} {"current_steps": 35215, "total_steps": 40000, "loss": 0.0, "lr": 1.7454825542216807e-06, "epoch": 391.27777777777777, "percentage": 88.04, "elapsed_time": "3:59:47", "remaining_time": "0:32:34", "throughput": 685.75, "total_tokens": 9866000} {"current_steps": 35220, "total_steps": 40000, "loss": 0.0, "lr": 1.7418803320471105e-06, "epoch": 391.3333333333333, "percentage": 88.05, "elapsed_time": "3:59:49", "remaining_time": "0:32:32", "throughput": 685.76, "total_tokens": 9867360} {"current_steps": 35225, "total_steps": 40000, "loss": 0.0, "lr": 1.7382816965668737e-06, "epoch": 391.3888888888889, "percentage": 88.06, "elapsed_time": "3:59:50", "remaining_time": "0:32:30", "throughput": 685.76, "total_tokens": 9868752} {"current_steps": 35230, "total_steps": 40000, "loss": 0.0, "lr": 1.7346866483359285e-06, "epoch": 391.44444444444446, "percentage": 88.08, "elapsed_time": "3:59:52", "remaining_time": "0:32:28", "throughput": 685.77, "total_tokens": 9870160} {"current_steps": 35235, "total_steps": 40000, "loss": 0.0, "lr": 1.7310951879086657e-06, "epoch": 391.5, "percentage": 88.09, "elapsed_time": "3:59:54", "remaining_time": "0:32:26", "throughput": 685.77, "total_tokens": 9871552} {"current_steps": 35240, "total_steps": 40000, "loss": 0.0, "lr": 1.7275073158389471e-06, "epoch": 391.55555555555554, "percentage": 88.1, "elapsed_time": "3:59:56", "remaining_time": "0:32:24", "throughput": 685.78, "total_tokens": 9872960} {"current_steps": 35245, "total_steps": 40000, "loss": 0.0, "lr": 1.723923032680061e-06, "epoch": 391.6111111111111, "percentage": 88.11, "elapsed_time": "3:59:58", "remaining_time": "0:32:22", "throughput": 685.78, "total_tokens": 9874352} {"current_steps": 35250, "total_steps": 40000, "loss": 0.0, "lr": 1.7203423389847428e-06, "epoch": 391.6666666666667, "percentage": 88.12, "elapsed_time": "4:00:00", "remaining_time": "0:32:20", "throughput": 685.79, "total_tokens": 9875792} {"current_steps": 35255, "total_steps": 40000, "loss": 0.0, "lr": 1.7167652353051928e-06, "epoch": 391.72222222222223, "percentage": 88.14, "elapsed_time": "4:00:02", "remaining_time": "0:32:18", "throughput": 685.79, "total_tokens": 9877216} {"current_steps": 35260, "total_steps": 40000, "loss": 0.0, "lr": 1.7131917221930333e-06, "epoch": 391.77777777777777, "percentage": 88.15, "elapsed_time": "4:00:04", "remaining_time": "0:32:16", "throughput": 685.8, "total_tokens": 9878656} {"current_steps": 35265, "total_steps": 40000, "loss": 0.0, "lr": 1.7096218001993513e-06, "epoch": 391.8333333333333, "percentage": 88.16, "elapsed_time": "4:00:06", "remaining_time": "0:32:14", "throughput": 685.81, "total_tokens": 9880048} {"current_steps": 35270, "total_steps": 40000, "loss": 0.0, "lr": 1.706055469874676e-06, "epoch": 391.8888888888889, "percentage": 88.17, "elapsed_time": "4:00:08", "remaining_time": "0:32:12", "throughput": 685.82, "total_tokens": 9881488} {"current_steps": 35275, "total_steps": 40000, "loss": 0.0, "lr": 1.702492731768976e-06, "epoch": 391.94444444444446, "percentage": 88.19, "elapsed_time": "4:00:10", "remaining_time": "0:32:10", "throughput": 685.82, "total_tokens": 9882848} {"current_steps": 35280, "total_steps": 40000, "loss": 0.0, "lr": 1.6989335864316724e-06, "epoch": 392.0, "percentage": 88.2, "elapsed_time": "4:00:12", "remaining_time": "0:32:08", "throughput": 685.81, "total_tokens": 9884240} {"current_steps": 35285, "total_steps": 40000, "loss": 0.0, "lr": 1.6953780344116265e-06, "epoch": 392.05555555555554, "percentage": 88.21, "elapsed_time": "4:00:14", "remaining_time": "0:32:06", "throughput": 685.81, "total_tokens": 9885664} {"current_steps": 35290, "total_steps": 40000, "loss": 0.0, "lr": 1.6918260762571497e-06, "epoch": 392.1111111111111, "percentage": 88.22, "elapsed_time": "4:00:16", "remaining_time": "0:32:04", "throughput": 685.81, "total_tokens": 9887040} {"current_steps": 35295, "total_steps": 40000, "loss": 0.0, "lr": 1.6882777125160093e-06, "epoch": 392.1666666666667, "percentage": 88.24, "elapsed_time": "4:00:18", "remaining_time": "0:32:02", "throughput": 685.81, "total_tokens": 9888400} {"current_steps": 35300, "total_steps": 40000, "loss": 0.0, "lr": 1.6847329437353899e-06, "epoch": 392.22222222222223, "percentage": 88.25, "elapsed_time": "4:00:20", "remaining_time": "0:32:00", "throughput": 685.82, "total_tokens": 9889808} {"current_steps": 35305, "total_steps": 40000, "loss": 0.0, "lr": 1.6811917704619511e-06, "epoch": 392.27777777777777, "percentage": 88.26, "elapsed_time": "4:00:22", "remaining_time": "0:31:57", "throughput": 685.82, "total_tokens": 9891200} {"current_steps": 35310, "total_steps": 40000, "loss": 0.0, "lr": 1.67765419324179e-06, "epoch": 392.3333333333333, "percentage": 88.28, "elapsed_time": "4:00:24", "remaining_time": "0:31:55", "throughput": 685.83, "total_tokens": 9892592} {"current_steps": 35315, "total_steps": 40000, "loss": 0.0, "lr": 1.6741202126204364e-06, "epoch": 392.3888888888889, "percentage": 88.29, "elapsed_time": "4:00:26", "remaining_time": "0:31:53", "throughput": 685.83, "total_tokens": 9893984} {"current_steps": 35320, "total_steps": 40000, "loss": 0.0, "lr": 1.6705898291428767e-06, "epoch": 392.44444444444446, "percentage": 88.3, "elapsed_time": "4:00:28", "remaining_time": "0:31:51", "throughput": 685.84, "total_tokens": 9895376} {"current_steps": 35325, "total_steps": 40000, "loss": 0.0, "lr": 1.6670630433535395e-06, "epoch": 392.5, "percentage": 88.31, "elapsed_time": "4:00:30", "remaining_time": "0:31:49", "throughput": 685.84, "total_tokens": 9896800} {"current_steps": 35330, "total_steps": 40000, "loss": 0.0, "lr": 1.6635398557962979e-06, "epoch": 392.55555555555554, "percentage": 88.33, "elapsed_time": "4:00:32", "remaining_time": "0:31:47", "throughput": 685.85, "total_tokens": 9898176} {"current_steps": 35335, "total_steps": 40000, "loss": 0.0, "lr": 1.660020267014481e-06, "epoch": 392.6111111111111, "percentage": 88.34, "elapsed_time": "4:00:33", "remaining_time": "0:31:45", "throughput": 685.86, "total_tokens": 9899632} {"current_steps": 35340, "total_steps": 40000, "loss": 0.0, "lr": 1.6565042775508438e-06, "epoch": 392.6666666666667, "percentage": 88.35, "elapsed_time": "4:00:35", "remaining_time": "0:31:43", "throughput": 685.86, "total_tokens": 9901024} {"current_steps": 35345, "total_steps": 40000, "loss": 0.0, "lr": 1.6529918879475997e-06, "epoch": 392.72222222222223, "percentage": 88.36, "elapsed_time": "4:00:37", "remaining_time": "0:31:41", "throughput": 685.87, "total_tokens": 9902448} {"current_steps": 35350, "total_steps": 40000, "loss": 0.0, "lr": 1.6494830987464043e-06, "epoch": 392.77777777777777, "percentage": 88.38, "elapsed_time": "4:00:39", "remaining_time": "0:31:39", "throughput": 685.87, "total_tokens": 9903808} {"current_steps": 35355, "total_steps": 40000, "loss": 0.0, "lr": 1.6459779104883555e-06, "epoch": 392.8333333333333, "percentage": 88.39, "elapsed_time": "4:00:41", "remaining_time": "0:31:37", "throughput": 685.88, "total_tokens": 9905248} {"current_steps": 35360, "total_steps": 40000, "loss": 0.0, "lr": 1.6424763237140013e-06, "epoch": 392.8888888888889, "percentage": 88.4, "elapsed_time": "4:00:43", "remaining_time": "0:31:35", "throughput": 685.88, "total_tokens": 9906672} {"current_steps": 35365, "total_steps": 40000, "loss": 0.0, "lr": 1.6389783389633207e-06, "epoch": 392.94444444444446, "percentage": 88.41, "elapsed_time": "4:00:45", "remaining_time": "0:31:33", "throughput": 685.89, "total_tokens": 9908064} {"current_steps": 35370, "total_steps": 40000, "loss": 0.0, "lr": 1.6354839567757546e-06, "epoch": 393.0, "percentage": 88.42, "elapsed_time": "4:00:47", "remaining_time": "0:31:31", "throughput": 685.89, "total_tokens": 9909488} {"current_steps": 35375, "total_steps": 40000, "loss": 0.0, "lr": 1.6319931776901831e-06, "epoch": 393.05555555555554, "percentage": 88.44, "elapsed_time": "4:00:49", "remaining_time": "0:31:29", "throughput": 685.88, "total_tokens": 9910864} {"current_steps": 35380, "total_steps": 40000, "loss": 0.0, "lr": 1.6285060022449229e-06, "epoch": 393.1111111111111, "percentage": 88.45, "elapsed_time": "4:00:51", "remaining_time": "0:31:27", "throughput": 685.88, "total_tokens": 9912272} {"current_steps": 35385, "total_steps": 40000, "loss": 0.0, "lr": 1.6250224309777434e-06, "epoch": 393.1666666666667, "percentage": 88.46, "elapsed_time": "4:00:53", "remaining_time": "0:31:25", "throughput": 685.89, "total_tokens": 9913680} {"current_steps": 35390, "total_steps": 40000, "loss": 0.0, "lr": 1.6215424644258515e-06, "epoch": 393.22222222222223, "percentage": 88.48, "elapsed_time": "4:00:55", "remaining_time": "0:31:23", "throughput": 685.89, "total_tokens": 9915088} {"current_steps": 35395, "total_steps": 40000, "loss": 0.0, "lr": 1.6180661031259036e-06, "epoch": 393.27777777777777, "percentage": 88.49, "elapsed_time": "4:00:57", "remaining_time": "0:31:20", "throughput": 685.9, "total_tokens": 9916480} {"current_steps": 35400, "total_steps": 40000, "loss": 0.0, "lr": 1.614593347613999e-06, "epoch": 393.3333333333333, "percentage": 88.5, "elapsed_time": "4:00:59", "remaining_time": "0:31:18", "throughput": 685.9, "total_tokens": 9917904} {"current_steps": 35400, "total_steps": 40000, "eval_loss": 0.35188406705856323, "epoch": 393.3333333333333, "percentage": 88.5, "elapsed_time": "4:01:00", "remaining_time": "0:31:19", "throughput": 685.84, "total_tokens": 9917904} {"current_steps": 35405, "total_steps": 40000, "loss": 0.0, "lr": 1.6111241984256758e-06, "epoch": 393.3888888888889, "percentage": 88.51, "elapsed_time": "4:01:04", "remaining_time": "0:31:17", "throughput": 685.77, "total_tokens": 9919264} {"current_steps": 35410, "total_steps": 40000, "loss": 0.0, "lr": 1.6076586560959257e-06, "epoch": 393.44444444444446, "percentage": 88.52, "elapsed_time": "4:01:06", "remaining_time": "0:31:15", "throughput": 685.78, "total_tokens": 9920672} {"current_steps": 35415, "total_steps": 40000, "loss": 0.0, "lr": 1.604196721159182e-06, "epoch": 393.5, "percentage": 88.54, "elapsed_time": "4:01:08", "remaining_time": "0:31:13", "throughput": 685.78, "total_tokens": 9922048} {"current_steps": 35420, "total_steps": 40000, "loss": 0.0, "lr": 1.6007383941493092e-06, "epoch": 393.55555555555554, "percentage": 88.55, "elapsed_time": "4:01:10", "remaining_time": "0:31:11", "throughput": 685.79, "total_tokens": 9923472} {"current_steps": 35425, "total_steps": 40000, "loss": 0.0, "lr": 1.5972836755996285e-06, "epoch": 393.6111111111111, "percentage": 88.56, "elapsed_time": "4:01:12", "remaining_time": "0:31:09", "throughput": 685.79, "total_tokens": 9924864} {"current_steps": 35430, "total_steps": 40000, "loss": 0.0, "lr": 1.5938325660429076e-06, "epoch": 393.6666666666667, "percentage": 88.58, "elapsed_time": "4:01:14", "remaining_time": "0:31:06", "throughput": 685.8, "total_tokens": 9926256} {"current_steps": 35435, "total_steps": 40000, "loss": 0.0, "lr": 1.5903850660113378e-06, "epoch": 393.72222222222223, "percentage": 88.59, "elapsed_time": "4:01:16", "remaining_time": "0:31:04", "throughput": 685.8, "total_tokens": 9927664} {"current_steps": 35440, "total_steps": 40000, "loss": 0.0, "lr": 1.5869411760365826e-06, "epoch": 393.77777777777777, "percentage": 88.6, "elapsed_time": "4:01:17", "remaining_time": "0:31:02", "throughput": 685.81, "total_tokens": 9929072} {"current_steps": 35445, "total_steps": 40000, "loss": 0.0, "lr": 1.58350089664972e-06, "epoch": 393.8333333333333, "percentage": 88.61, "elapsed_time": "4:01:19", "remaining_time": "0:31:00", "throughput": 685.81, "total_tokens": 9930464} {"current_steps": 35450, "total_steps": 40000, "loss": 0.0, "lr": 1.5800642283812865e-06, "epoch": 393.8888888888889, "percentage": 88.62, "elapsed_time": "4:01:21", "remaining_time": "0:30:58", "throughput": 685.82, "total_tokens": 9931872} {"current_steps": 35455, "total_steps": 40000, "loss": 0.0, "lr": 1.5766311717612698e-06, "epoch": 393.94444444444446, "percentage": 88.64, "elapsed_time": "4:01:23", "remaining_time": "0:30:56", "throughput": 685.82, "total_tokens": 9933296} {"current_steps": 35460, "total_steps": 40000, "loss": 0.0, "lr": 1.5732017273190818e-06, "epoch": 394.0, "percentage": 88.65, "elapsed_time": "4:01:25", "remaining_time": "0:30:54", "throughput": 685.82, "total_tokens": 9934640} {"current_steps": 35465, "total_steps": 40000, "loss": 0.0, "lr": 1.5697758955835806e-06, "epoch": 394.05555555555554, "percentage": 88.66, "elapsed_time": "4:01:28", "remaining_time": "0:30:52", "throughput": 685.81, "total_tokens": 9936064} {"current_steps": 35470, "total_steps": 40000, "loss": 0.0, "lr": 1.566353677083085e-06, "epoch": 394.1111111111111, "percentage": 88.67, "elapsed_time": "4:01:30", "remaining_time": "0:30:50", "throughput": 685.81, "total_tokens": 9937424} {"current_steps": 35475, "total_steps": 40000, "loss": 0.0, "lr": 1.562935072345334e-06, "epoch": 394.1666666666667, "percentage": 88.69, "elapsed_time": "4:01:32", "remaining_time": "0:30:48", "throughput": 685.81, "total_tokens": 9938816} {"current_steps": 35480, "total_steps": 40000, "loss": 0.0, "lr": 1.5595200818975281e-06, "epoch": 394.22222222222223, "percentage": 88.7, "elapsed_time": "4:01:34", "remaining_time": "0:30:46", "throughput": 685.81, "total_tokens": 9940192} {"current_steps": 35485, "total_steps": 40000, "loss": 0.0, "lr": 1.5561087062662905e-06, "epoch": 394.27777777777777, "percentage": 88.71, "elapsed_time": "4:01:36", "remaining_time": "0:30:44", "throughput": 685.81, "total_tokens": 9941568} {"current_steps": 35490, "total_steps": 40000, "loss": 0.0, "lr": 1.5527009459777087e-06, "epoch": 394.3333333333333, "percentage": 88.72, "elapsed_time": "4:01:38", "remaining_time": "0:30:42", "throughput": 685.81, "total_tokens": 9942976} {"current_steps": 35495, "total_steps": 40000, "loss": 0.0, "lr": 1.5492968015572984e-06, "epoch": 394.3888888888889, "percentage": 88.74, "elapsed_time": "4:01:40", "remaining_time": "0:30:40", "throughput": 685.81, "total_tokens": 9944448} {"current_steps": 35500, "total_steps": 40000, "loss": 0.0, "lr": 1.5458962735300203e-06, "epoch": 394.44444444444446, "percentage": 88.75, "elapsed_time": "4:01:42", "remaining_time": "0:30:38", "throughput": 685.82, "total_tokens": 9945856} {"current_steps": 35505, "total_steps": 40000, "loss": 0.0, "lr": 1.54249936242028e-06, "epoch": 394.5, "percentage": 88.76, "elapsed_time": "4:01:44", "remaining_time": "0:30:36", "throughput": 685.82, "total_tokens": 9947280} {"current_steps": 35510, "total_steps": 40000, "loss": 0.0, "lr": 1.5391060687519222e-06, "epoch": 394.55555555555554, "percentage": 88.78, "elapsed_time": "4:01:46", "remaining_time": "0:30:34", "throughput": 685.82, "total_tokens": 9948640} {"current_steps": 35515, "total_steps": 40000, "loss": 0.0, "lr": 1.5357163930482367e-06, "epoch": 394.6111111111111, "percentage": 88.79, "elapsed_time": "4:01:48", "remaining_time": "0:30:32", "throughput": 685.82, "total_tokens": 9950048} {"current_steps": 35520, "total_steps": 40000, "loss": 0.0, "lr": 1.532330335831955e-06, "epoch": 394.6666666666667, "percentage": 88.8, "elapsed_time": "4:01:50", "remaining_time": "0:30:30", "throughput": 685.82, "total_tokens": 9951504} {"current_steps": 35525, "total_steps": 40000, "loss": 0.0, "lr": 1.5289478976252491e-06, "epoch": 394.72222222222223, "percentage": 88.81, "elapsed_time": "4:01:52", "remaining_time": "0:30:28", "throughput": 685.82, "total_tokens": 9952880} {"current_steps": 35530, "total_steps": 40000, "loss": 0.0, "lr": 1.5255690789497345e-06, "epoch": 394.77777777777777, "percentage": 88.83, "elapsed_time": "4:01:54", "remaining_time": "0:30:26", "throughput": 685.82, "total_tokens": 9954304} {"current_steps": 35535, "total_steps": 40000, "loss": 0.0, "lr": 1.5221938803264641e-06, "epoch": 394.8333333333333, "percentage": 88.84, "elapsed_time": "4:01:56", "remaining_time": "0:30:24", "throughput": 685.82, "total_tokens": 9955728} {"current_steps": 35540, "total_steps": 40000, "loss": 0.0, "lr": 1.518822302275938e-06, "epoch": 394.8888888888889, "percentage": 88.85, "elapsed_time": "4:01:58", "remaining_time": "0:30:21", "throughput": 685.83, "total_tokens": 9957136} {"current_steps": 35545, "total_steps": 40000, "loss": 0.0, "lr": 1.5154543453180958e-06, "epoch": 394.94444444444446, "percentage": 88.86, "elapsed_time": "4:02:00", "remaining_time": "0:30:19", "throughput": 685.83, "total_tokens": 9958576} {"current_steps": 35550, "total_steps": 40000, "loss": 0.0, "lr": 1.5120900099723167e-06, "epoch": 395.0, "percentage": 88.88, "elapsed_time": "4:02:02", "remaining_time": "0:30:17", "throughput": 685.82, "total_tokens": 9959920} {"current_steps": 35555, "total_steps": 40000, "loss": 0.0, "lr": 1.5087292967574273e-06, "epoch": 395.05555555555554, "percentage": 88.89, "elapsed_time": "4:02:04", "remaining_time": "0:30:15", "throughput": 685.81, "total_tokens": 9961312} {"current_steps": 35560, "total_steps": 40000, "loss": 0.0, "lr": 1.5053722061916908e-06, "epoch": 395.1111111111111, "percentage": 88.9, "elapsed_time": "4:02:07", "remaining_time": "0:30:13", "throughput": 685.8, "total_tokens": 9962672} {"current_steps": 35565, "total_steps": 40000, "loss": 0.0, "lr": 1.5020187387928124e-06, "epoch": 395.1666666666667, "percentage": 88.91, "elapsed_time": "4:02:09", "remaining_time": "0:30:11", "throughput": 685.8, "total_tokens": 9964032} {"current_steps": 35570, "total_steps": 40000, "loss": 0.0, "lr": 1.4986688950779343e-06, "epoch": 395.22222222222223, "percentage": 88.92, "elapsed_time": "4:02:11", "remaining_time": "0:30:09", "throughput": 685.81, "total_tokens": 9965488} {"current_steps": 35575, "total_steps": 40000, "loss": 0.0, "lr": 1.495322675563654e-06, "epoch": 395.27777777777777, "percentage": 88.94, "elapsed_time": "4:02:13", "remaining_time": "0:30:07", "throughput": 685.81, "total_tokens": 9966912} {"current_steps": 35580, "total_steps": 40000, "loss": 0.0, "lr": 1.4919800807659922e-06, "epoch": 395.3333333333333, "percentage": 88.95, "elapsed_time": "4:02:15", "remaining_time": "0:30:05", "throughput": 685.81, "total_tokens": 9968288} {"current_steps": 35585, "total_steps": 40000, "loss": 0.0, "lr": 1.4886411112004255e-06, "epoch": 395.3888888888889, "percentage": 88.96, "elapsed_time": "4:02:17", "remaining_time": "0:30:03", "throughput": 685.81, "total_tokens": 9969696} {"current_steps": 35590, "total_steps": 40000, "loss": 0.0, "lr": 1.4853057673818588e-06, "epoch": 395.44444444444446, "percentage": 88.98, "elapsed_time": "4:02:19", "remaining_time": "0:30:01", "throughput": 685.81, "total_tokens": 9971072} {"current_steps": 35595, "total_steps": 40000, "loss": 0.0, "lr": 1.481974049824647e-06, "epoch": 395.5, "percentage": 88.99, "elapsed_time": "4:02:21", "remaining_time": "0:29:59", "throughput": 685.81, "total_tokens": 9972464} {"current_steps": 35600, "total_steps": 40000, "loss": 0.0, "lr": 1.4786459590425849e-06, "epoch": 395.55555555555554, "percentage": 89.0, "elapsed_time": "4:02:23", "remaining_time": "0:29:57", "throughput": 685.81, "total_tokens": 9973888} {"current_steps": 35600, "total_steps": 40000, "eval_loss": 0.36891934275627136, "epoch": 395.55555555555554, "percentage": 89.0, "elapsed_time": "4:02:24", "remaining_time": "0:29:57", "throughput": 685.75, "total_tokens": 9973888} {"current_steps": 35605, "total_steps": 40000, "loss": 0.0, "lr": 1.4753214955489036e-06, "epoch": 395.6111111111111, "percentage": 89.01, "elapsed_time": "4:02:28", "remaining_time": "0:29:55", "throughput": 685.66, "total_tokens": 9975296} {"current_steps": 35610, "total_steps": 40000, "loss": 0.0, "lr": 1.4720006598562737e-06, "epoch": 395.6666666666667, "percentage": 89.03, "elapsed_time": "4:02:30", "remaining_time": "0:29:53", "throughput": 685.66, "total_tokens": 9976704} {"current_steps": 35615, "total_steps": 40000, "loss": 0.0, "lr": 1.4686834524768185e-06, "epoch": 395.72222222222223, "percentage": 89.04, "elapsed_time": "4:02:32", "remaining_time": "0:29:51", "throughput": 685.66, "total_tokens": 9978112} {"current_steps": 35620, "total_steps": 40000, "loss": 0.0, "lr": 1.4653698739220844e-06, "epoch": 395.77777777777777, "percentage": 89.05, "elapsed_time": "4:02:34", "remaining_time": "0:29:49", "throughput": 685.66, "total_tokens": 9979520} {"current_steps": 35625, "total_steps": 40000, "loss": 0.0, "lr": 1.4620599247030715e-06, "epoch": 395.8333333333333, "percentage": 89.06, "elapsed_time": "4:02:36", "remaining_time": "0:29:47", "throughput": 685.66, "total_tokens": 9980896} {"current_steps": 35630, "total_steps": 40000, "loss": 0.0, "lr": 1.4587536053302125e-06, "epoch": 395.8888888888889, "percentage": 89.08, "elapsed_time": "4:02:38", "remaining_time": "0:29:45", "throughput": 685.66, "total_tokens": 9982320} {"current_steps": 35635, "total_steps": 40000, "loss": 0.0, "lr": 1.4554509163133862e-06, "epoch": 395.94444444444446, "percentage": 89.09, "elapsed_time": "4:02:40", "remaining_time": "0:29:43", "throughput": 685.66, "total_tokens": 9983728} {"current_steps": 35640, "total_steps": 40000, "loss": 0.0, "lr": 1.4521518581619098e-06, "epoch": 396.0, "percentage": 89.1, "elapsed_time": "4:02:42", "remaining_time": "0:29:41", "throughput": 685.66, "total_tokens": 9985136} {"current_steps": 35645, "total_steps": 40000, "loss": 0.0, "lr": 1.4488564313845348e-06, "epoch": 396.05555555555554, "percentage": 89.11, "elapsed_time": "4:02:45", "remaining_time": "0:29:39", "throughput": 685.64, "total_tokens": 9986544} {"current_steps": 35650, "total_steps": 40000, "loss": 0.0, "lr": 1.4455646364894603e-06, "epoch": 396.1111111111111, "percentage": 89.12, "elapsed_time": "4:02:47", "remaining_time": "0:29:37", "throughput": 685.64, "total_tokens": 9987936} {"current_steps": 35655, "total_steps": 40000, "loss": 0.0, "lr": 1.4422764739843247e-06, "epoch": 396.1666666666667, "percentage": 89.14, "elapsed_time": "4:02:49", "remaining_time": "0:29:35", "throughput": 685.64, "total_tokens": 9989312} {"current_steps": 35660, "total_steps": 40000, "loss": 0.0, "lr": 1.4389919443762e-06, "epoch": 396.22222222222223, "percentage": 89.15, "elapsed_time": "4:02:51", "remaining_time": "0:29:33", "throughput": 685.64, "total_tokens": 9990704} {"current_steps": 35665, "total_steps": 40000, "loss": 0.0, "lr": 1.4357110481716063e-06, "epoch": 396.27777777777777, "percentage": 89.16, "elapsed_time": "4:02:53", "remaining_time": "0:29:31", "throughput": 685.65, "total_tokens": 9992144} {"current_steps": 35670, "total_steps": 40000, "loss": 0.0, "lr": 1.4324337858764941e-06, "epoch": 396.3333333333333, "percentage": 89.18, "elapsed_time": "4:02:55", "remaining_time": "0:29:29", "throughput": 685.65, "total_tokens": 9993552} {"current_steps": 35675, "total_steps": 40000, "loss": 0.0, "lr": 1.4291601579962622e-06, "epoch": 396.3888888888889, "percentage": 89.19, "elapsed_time": "4:02:57", "remaining_time": "0:29:27", "throughput": 685.65, "total_tokens": 9994992} {"current_steps": 35680, "total_steps": 40000, "loss": 0.0, "lr": 1.42589016503574e-06, "epoch": 396.44444444444446, "percentage": 89.2, "elapsed_time": "4:02:59", "remaining_time": "0:29:25", "throughput": 685.66, "total_tokens": 9996464} {"current_steps": 35685, "total_steps": 40000, "loss": 0.0, "lr": 1.4226238074992099e-06, "epoch": 396.5, "percentage": 89.21, "elapsed_time": "4:03:01", "remaining_time": "0:29:23", "throughput": 685.66, "total_tokens": 9997888} {"current_steps": 35690, "total_steps": 40000, "loss": 0.0, "lr": 1.4193610858903778e-06, "epoch": 396.55555555555554, "percentage": 89.22, "elapsed_time": "4:03:03", "remaining_time": "0:29:21", "throughput": 685.66, "total_tokens": 9999312} {"current_steps": 35695, "total_steps": 40000, "loss": 0.0, "lr": 1.416102000712402e-06, "epoch": 396.6111111111111, "percentage": 89.24, "elapsed_time": "4:03:05", "remaining_time": "0:29:19", "throughput": 685.66, "total_tokens": 10000688} {"current_steps": 35700, "total_steps": 40000, "loss": 0.0, "lr": 1.4128465524678668e-06, "epoch": 396.6666666666667, "percentage": 89.25, "elapsed_time": "4:03:07", "remaining_time": "0:29:17", "throughput": 685.66, "total_tokens": 10002064} {"current_steps": 35705, "total_steps": 40000, "loss": 0.0, "lr": 1.4095947416588124e-06, "epoch": 396.72222222222223, "percentage": 89.26, "elapsed_time": "4:03:09", "remaining_time": "0:29:14", "throughput": 685.66, "total_tokens": 10003472} {"current_steps": 35710, "total_steps": 40000, "loss": 0.0, "lr": 1.4063465687866983e-06, "epoch": 396.77777777777777, "percentage": 89.28, "elapsed_time": "4:03:11", "remaining_time": "0:29:12", "throughput": 685.66, "total_tokens": 10004880} {"current_steps": 35715, "total_steps": 40000, "loss": 0.0, "lr": 1.4031020343524438e-06, "epoch": 396.8333333333333, "percentage": 89.29, "elapsed_time": "4:03:13", "remaining_time": "0:29:10", "throughput": 685.67, "total_tokens": 10006320} {"current_steps": 35720, "total_steps": 40000, "loss": 0.0, "lr": 1.3998611388563926e-06, "epoch": 396.8888888888889, "percentage": 89.3, "elapsed_time": "4:03:15", "remaining_time": "0:29:08", "throughput": 685.66, "total_tokens": 10007712} {"current_steps": 35725, "total_steps": 40000, "loss": 0.0, "lr": 1.3966238827983314e-06, "epoch": 396.94444444444446, "percentage": 89.31, "elapsed_time": "4:03:17", "remaining_time": "0:29:06", "throughput": 685.66, "total_tokens": 10009088} {"current_steps": 35730, "total_steps": 40000, "loss": 0.0, "lr": 1.393390266677483e-06, "epoch": 397.0, "percentage": 89.33, "elapsed_time": "4:03:19", "remaining_time": "0:29:04", "throughput": 685.65, "total_tokens": 10010400} {"current_steps": 35735, "total_steps": 40000, "loss": 0.0, "lr": 1.3901602909925204e-06, "epoch": 397.05555555555554, "percentage": 89.34, "elapsed_time": "4:03:22", "remaining_time": "0:29:02", "throughput": 685.64, "total_tokens": 10011808} {"current_steps": 35740, "total_steps": 40000, "loss": 0.0, "lr": 1.3869339562415373e-06, "epoch": 397.1111111111111, "percentage": 89.35, "elapsed_time": "4:03:24", "remaining_time": "0:29:00", "throughput": 685.64, "total_tokens": 10013264} {"current_steps": 35745, "total_steps": 40000, "loss": 0.0, "lr": 1.38371126292208e-06, "epoch": 397.1666666666667, "percentage": 89.36, "elapsed_time": "4:03:26", "remaining_time": "0:28:58", "throughput": 685.65, "total_tokens": 10014688} {"current_steps": 35750, "total_steps": 40000, "loss": 0.0, "lr": 1.3804922115311286e-06, "epoch": 397.22222222222223, "percentage": 89.38, "elapsed_time": "4:03:28", "remaining_time": "0:28:56", "throughput": 685.65, "total_tokens": 10016096} {"current_steps": 35755, "total_steps": 40000, "loss": 0.0, "lr": 1.3772768025650945e-06, "epoch": 397.27777777777777, "percentage": 89.39, "elapsed_time": "4:03:30", "remaining_time": "0:28:54", "throughput": 685.64, "total_tokens": 10017456} {"current_steps": 35760, "total_steps": 40000, "loss": 0.0, "lr": 1.3740650365198448e-06, "epoch": 397.3333333333333, "percentage": 89.4, "elapsed_time": "4:03:32", "remaining_time": "0:28:52", "throughput": 685.64, "total_tokens": 10018832} {"current_steps": 35765, "total_steps": 40000, "loss": 0.0, "lr": 1.3708569138906612e-06, "epoch": 397.3888888888889, "percentage": 89.41, "elapsed_time": "4:03:34", "remaining_time": "0:28:50", "throughput": 685.64, "total_tokens": 10020240} {"current_steps": 35770, "total_steps": 40000, "loss": 0.0, "lr": 1.367652435172287e-06, "epoch": 397.44444444444446, "percentage": 89.42, "elapsed_time": "4:03:36", "remaining_time": "0:28:48", "throughput": 685.63, "total_tokens": 10021632} {"current_steps": 35775, "total_steps": 40000, "loss": 0.0, "lr": 1.364451600858893e-06, "epoch": 397.5, "percentage": 89.44, "elapsed_time": "4:03:38", "remaining_time": "0:28:46", "throughput": 685.63, "total_tokens": 10023056} {"current_steps": 35780, "total_steps": 40000, "loss": 0.0, "lr": 1.3612544114440823e-06, "epoch": 397.55555555555554, "percentage": 89.45, "elapsed_time": "4:03:40", "remaining_time": "0:28:44", "throughput": 685.64, "total_tokens": 10024496} {"current_steps": 35785, "total_steps": 40000, "loss": 0.0, "lr": 1.3580608674209072e-06, "epoch": 397.6111111111111, "percentage": 89.46, "elapsed_time": "4:03:42", "remaining_time": "0:28:42", "throughput": 685.64, "total_tokens": 10025888} {"current_steps": 35790, "total_steps": 40000, "loss": 0.0, "lr": 1.3548709692818434e-06, "epoch": 397.6666666666667, "percentage": 89.48, "elapsed_time": "4:03:44", "remaining_time": "0:28:40", "throughput": 685.64, "total_tokens": 10027296} {"current_steps": 35795, "total_steps": 40000, "loss": 0.0, "lr": 1.3516847175188223e-06, "epoch": 397.72222222222223, "percentage": 89.49, "elapsed_time": "4:03:46", "remaining_time": "0:28:38", "throughput": 685.64, "total_tokens": 10028656} {"current_steps": 35800, "total_steps": 40000, "loss": 0.0, "lr": 1.348502112623204e-06, "epoch": 397.77777777777777, "percentage": 89.5, "elapsed_time": "4:03:48", "remaining_time": "0:28:36", "throughput": 685.64, "total_tokens": 10030096} {"current_steps": 35800, "total_steps": 40000, "eval_loss": 0.33812960982322693, "epoch": 397.77777777777777, "percentage": 89.5, "elapsed_time": "4:03:50", "remaining_time": "0:28:36", "throughput": 685.58, "total_tokens": 10030096} {"current_steps": 35805, "total_steps": 40000, "loss": 0.0, "lr": 1.3453231550857787e-06, "epoch": 397.8333333333333, "percentage": 89.51, "elapsed_time": "4:03:53", "remaining_time": "0:28:34", "throughput": 685.51, "total_tokens": 10031488} {"current_steps": 35810, "total_steps": 40000, "loss": 0.0, "lr": 1.3421478453967878e-06, "epoch": 397.8888888888889, "percentage": 89.53, "elapsed_time": "4:03:55", "remaining_time": "0:28:32", "throughput": 685.52, "total_tokens": 10032880} {"current_steps": 35815, "total_steps": 40000, "loss": 0.0, "lr": 1.3389761840459065e-06, "epoch": 397.94444444444446, "percentage": 89.54, "elapsed_time": "4:03:57", "remaining_time": "0:28:30", "throughput": 685.52, "total_tokens": 10034320} {"current_steps": 35820, "total_steps": 40000, "loss": 0.0, "lr": 1.3358081715222376e-06, "epoch": 398.0, "percentage": 89.55, "elapsed_time": "4:03:59", "remaining_time": "0:28:28", "throughput": 685.52, "total_tokens": 10035680} {"current_steps": 35825, "total_steps": 40000, "loss": 0.0, "lr": 1.3326438083143295e-06, "epoch": 398.05555555555554, "percentage": 89.56, "elapsed_time": "4:04:01", "remaining_time": "0:28:26", "throughput": 685.51, "total_tokens": 10037104} {"current_steps": 35830, "total_steps": 40000, "loss": 0.0, "lr": 1.3294830949101723e-06, "epoch": 398.1111111111111, "percentage": 89.58, "elapsed_time": "4:04:03", "remaining_time": "0:28:24", "throughput": 685.52, "total_tokens": 10038496} {"current_steps": 35835, "total_steps": 40000, "loss": 0.0, "lr": 1.3263260317971815e-06, "epoch": 398.1666666666667, "percentage": 89.59, "elapsed_time": "4:04:05", "remaining_time": "0:28:22", "throughput": 685.52, "total_tokens": 10039904} {"current_steps": 35840, "total_steps": 40000, "loss": 0.0, "lr": 1.3231726194622208e-06, "epoch": 398.22222222222223, "percentage": 89.6, "elapsed_time": "4:04:07", "remaining_time": "0:28:20", "throughput": 685.53, "total_tokens": 10041312} {"current_steps": 35845, "total_steps": 40000, "loss": 0.0, "lr": 1.3200228583915814e-06, "epoch": 398.27777777777777, "percentage": 89.61, "elapsed_time": "4:04:09", "remaining_time": "0:28:18", "throughput": 685.53, "total_tokens": 10042720} {"current_steps": 35850, "total_steps": 40000, "loss": 0.0, "lr": 1.3168767490709971e-06, "epoch": 398.3333333333333, "percentage": 89.62, "elapsed_time": "4:04:11", "remaining_time": "0:28:16", "throughput": 685.54, "total_tokens": 10044096} {"current_steps": 35855, "total_steps": 40000, "loss": 0.0, "lr": 1.3137342919856437e-06, "epoch": 398.3888888888889, "percentage": 89.64, "elapsed_time": "4:04:13", "remaining_time": "0:28:13", "throughput": 685.54, "total_tokens": 10045488} {"current_steps": 35860, "total_steps": 40000, "loss": 0.0, "lr": 1.310595487620117e-06, "epoch": 398.44444444444446, "percentage": 89.65, "elapsed_time": "4:04:15", "remaining_time": "0:28:11", "throughput": 685.55, "total_tokens": 10046896} {"current_steps": 35865, "total_steps": 40000, "loss": 0.0, "lr": 1.3074603364584715e-06, "epoch": 398.5, "percentage": 89.66, "elapsed_time": "4:04:17", "remaining_time": "0:28:09", "throughput": 685.55, "total_tokens": 10048288} {"current_steps": 35870, "total_steps": 40000, "loss": 0.0, "lr": 1.3043288389841758e-06, "epoch": 398.55555555555554, "percentage": 89.68, "elapsed_time": "4:04:19", "remaining_time": "0:28:07", "throughput": 685.55, "total_tokens": 10049648} {"current_steps": 35875, "total_steps": 40000, "loss": 0.0, "lr": 1.3012009956801546e-06, "epoch": 398.6111111111111, "percentage": 89.69, "elapsed_time": "4:04:21", "remaining_time": "0:28:05", "throughput": 685.56, "total_tokens": 10051104} {"current_steps": 35880, "total_steps": 40000, "loss": 0.0, "lr": 1.2980768070287586e-06, "epoch": 398.6666666666667, "percentage": 89.7, "elapsed_time": "4:04:23", "remaining_time": "0:28:03", "throughput": 685.56, "total_tokens": 10052480} {"current_steps": 35885, "total_steps": 40000, "loss": 0.0, "lr": 1.2949562735117716e-06, "epoch": 398.72222222222223, "percentage": 89.71, "elapsed_time": "4:04:25", "remaining_time": "0:28:01", "throughput": 685.57, "total_tokens": 10053856} {"current_steps": 35890, "total_steps": 40000, "loss": 0.0, "lr": 1.291839395610428e-06, "epoch": 398.77777777777777, "percentage": 89.72, "elapsed_time": "4:04:26", "remaining_time": "0:27:59", "throughput": 685.57, "total_tokens": 10055264} {"current_steps": 35895, "total_steps": 40000, "loss": 0.0, "lr": 1.2887261738053852e-06, "epoch": 398.8333333333333, "percentage": 89.74, "elapsed_time": "4:04:28", "remaining_time": "0:27:57", "throughput": 685.58, "total_tokens": 10056672} {"current_steps": 35900, "total_steps": 40000, "loss": 0.0, "lr": 1.2856166085767396e-06, "epoch": 398.8888888888889, "percentage": 89.75, "elapsed_time": "4:04:30", "remaining_time": "0:27:55", "throughput": 685.58, "total_tokens": 10058032} {"current_steps": 35905, "total_steps": 40000, "loss": 0.0, "lr": 1.2825107004040272e-06, "epoch": 398.94444444444446, "percentage": 89.76, "elapsed_time": "4:04:32", "remaining_time": "0:27:53", "throughput": 685.59, "total_tokens": 10059440} {"current_steps": 35910, "total_steps": 40000, "loss": 0.0, "lr": 1.2794084497662146e-06, "epoch": 399.0, "percentage": 89.78, "elapsed_time": "4:04:34", "remaining_time": "0:27:51", "throughput": 685.59, "total_tokens": 10060880} {"current_steps": 35915, "total_steps": 40000, "loss": 0.0, "lr": 1.276309857141711e-06, "epoch": 399.05555555555554, "percentage": 89.79, "elapsed_time": "4:04:37", "remaining_time": "0:27:49", "throughput": 685.58, "total_tokens": 10062320} {"current_steps": 35920, "total_steps": 40000, "loss": 0.0, "lr": 1.273214923008359e-06, "epoch": 399.1111111111111, "percentage": 89.8, "elapsed_time": "4:04:39", "remaining_time": "0:27:47", "throughput": 685.59, "total_tokens": 10063728} {"current_steps": 35925, "total_steps": 40000, "loss": 0.0, "lr": 1.2701236478434352e-06, "epoch": 399.1666666666667, "percentage": 89.81, "elapsed_time": "4:04:40", "remaining_time": "0:27:45", "throughput": 685.59, "total_tokens": 10065152} {"current_steps": 35930, "total_steps": 40000, "loss": 0.0, "lr": 1.2670360321236502e-06, "epoch": 399.22222222222223, "percentage": 89.83, "elapsed_time": "4:04:42", "remaining_time": "0:27:43", "throughput": 685.6, "total_tokens": 10066576} {"current_steps": 35935, "total_steps": 40000, "loss": 0.0, "lr": 1.2639520763251617e-06, "epoch": 399.27777777777777, "percentage": 89.84, "elapsed_time": "4:04:44", "remaining_time": "0:27:41", "throughput": 685.61, "total_tokens": 10068000} {"current_steps": 35940, "total_steps": 40000, "loss": 0.0, "lr": 1.2608717809235448e-06, "epoch": 399.3333333333333, "percentage": 89.85, "elapsed_time": "4:04:46", "remaining_time": "0:27:39", "throughput": 685.61, "total_tokens": 10069392} {"current_steps": 35945, "total_steps": 40000, "loss": 0.0, "lr": 1.2577951463938282e-06, "epoch": 399.3888888888889, "percentage": 89.86, "elapsed_time": "4:04:48", "remaining_time": "0:27:37", "throughput": 685.62, "total_tokens": 10070784} {"current_steps": 35950, "total_steps": 40000, "loss": 0.0, "lr": 1.2547221732104569e-06, "epoch": 399.44444444444446, "percentage": 89.88, "elapsed_time": "4:04:50", "remaining_time": "0:27:34", "throughput": 685.62, "total_tokens": 10072192} {"current_steps": 35955, "total_steps": 40000, "loss": 0.0, "lr": 1.25165286184733e-06, "epoch": 399.5, "percentage": 89.89, "elapsed_time": "4:04:52", "remaining_time": "0:27:32", "throughput": 685.62, "total_tokens": 10073552} {"current_steps": 35960, "total_steps": 40000, "loss": 0.0, "lr": 1.248587212777777e-06, "epoch": 399.55555555555554, "percentage": 89.9, "elapsed_time": "4:04:54", "remaining_time": "0:27:30", "throughput": 685.63, "total_tokens": 10074976} {"current_steps": 35965, "total_steps": 40000, "loss": 0.0, "lr": 1.2455252264745532e-06, "epoch": 399.6111111111111, "percentage": 89.91, "elapsed_time": "4:04:56", "remaining_time": "0:27:28", "throughput": 685.63, "total_tokens": 10076384} {"current_steps": 35970, "total_steps": 40000, "loss": 0.0, "lr": 1.2424669034098528e-06, "epoch": 399.6666666666667, "percentage": 89.92, "elapsed_time": "4:04:58", "remaining_time": "0:27:26", "throughput": 685.64, "total_tokens": 10077776} {"current_steps": 35975, "total_steps": 40000, "loss": 0.0, "lr": 1.2394122440553185e-06, "epoch": 399.72222222222223, "percentage": 89.94, "elapsed_time": "4:05:00", "remaining_time": "0:27:24", "throughput": 685.64, "total_tokens": 10079168} {"current_steps": 35980, "total_steps": 40000, "loss": 0.0, "lr": 1.2363612488820037e-06, "epoch": 399.77777777777777, "percentage": 89.95, "elapsed_time": "4:05:02", "remaining_time": "0:27:22", "throughput": 685.65, "total_tokens": 10080608} {"current_steps": 35985, "total_steps": 40000, "loss": 0.0, "lr": 1.2333139183604208e-06, "epoch": 399.8333333333333, "percentage": 89.96, "elapsed_time": "4:05:04", "remaining_time": "0:27:20", "throughput": 685.66, "total_tokens": 10082016} {"current_steps": 35990, "total_steps": 40000, "loss": 0.0, "lr": 1.2302702529604998e-06, "epoch": 399.8888888888889, "percentage": 89.98, "elapsed_time": "4:05:06", "remaining_time": "0:27:18", "throughput": 685.66, "total_tokens": 10083424} {"current_steps": 35995, "total_steps": 40000, "loss": 0.0, "lr": 1.227230253151615e-06, "epoch": 399.94444444444446, "percentage": 89.99, "elapsed_time": "4:05:08", "remaining_time": "0:27:16", "throughput": 685.67, "total_tokens": 10084800} {"current_steps": 36000, "total_steps": 40000, "loss": 0.0, "lr": 1.2241939194025748e-06, "epoch": 400.0, "percentage": 90.0, "elapsed_time": "4:05:10", "remaining_time": "0:27:14", "throughput": 685.66, "total_tokens": 10086192} {"current_steps": 36000, "total_steps": 40000, "eval_loss": 0.3451782464981079, "epoch": 400.0, "percentage": 90.0, "elapsed_time": "4:05:11", "remaining_time": "0:27:14", "throughput": 685.6, "total_tokens": 10086192} {"current_steps": 36005, "total_steps": 40000, "loss": 0.0, "lr": 1.2211612521816156e-06, "epoch": 400.05555555555554, "percentage": 90.01, "elapsed_time": "4:05:15", "remaining_time": "0:27:12", "throughput": 685.51, "total_tokens": 10087664} {"current_steps": 36010, "total_steps": 40000, "loss": 0.0, "lr": 1.2181322519564137e-06, "epoch": 400.1111111111111, "percentage": 90.03, "elapsed_time": "4:05:17", "remaining_time": "0:27:10", "throughput": 685.51, "total_tokens": 10089088} {"current_steps": 36015, "total_steps": 40000, "loss": 0.0, "lr": 1.2151069191940839e-06, "epoch": 400.1666666666667, "percentage": 90.04, "elapsed_time": "4:05:19", "remaining_time": "0:27:08", "throughput": 685.52, "total_tokens": 10090512} {"current_steps": 36020, "total_steps": 40000, "loss": 0.0, "lr": 1.2120852543611644e-06, "epoch": 400.22222222222223, "percentage": 90.05, "elapsed_time": "4:05:21", "remaining_time": "0:27:06", "throughput": 685.52, "total_tokens": 10091968} {"current_steps": 36025, "total_steps": 40000, "loss": 0.0, "lr": 1.2090672579236379e-06, "epoch": 400.27777777777777, "percentage": 90.06, "elapsed_time": "4:05:23", "remaining_time": "0:27:04", "throughput": 685.53, "total_tokens": 10093408} {"current_steps": 36030, "total_steps": 40000, "loss": 0.0, "lr": 1.2060529303469126e-06, "epoch": 400.3333333333333, "percentage": 90.08, "elapsed_time": "4:05:25", "remaining_time": "0:27:02", "throughput": 685.54, "total_tokens": 10094800} {"current_steps": 36035, "total_steps": 40000, "loss": 0.0, "lr": 1.2030422720958445e-06, "epoch": 400.3888888888889, "percentage": 90.09, "elapsed_time": "4:05:27", "remaining_time": "0:27:00", "throughput": 685.54, "total_tokens": 10096176} {"current_steps": 36040, "total_steps": 40000, "loss": 0.0, "lr": 1.200035283634704e-06, "epoch": 400.44444444444446, "percentage": 90.1, "elapsed_time": "4:05:29", "remaining_time": "0:26:58", "throughput": 685.54, "total_tokens": 10097568} {"current_steps": 36045, "total_steps": 40000, "loss": 0.0, "lr": 1.1970319654272144e-06, "epoch": 400.5, "percentage": 90.11, "elapsed_time": "4:05:31", "remaining_time": "0:26:56", "throughput": 685.55, "total_tokens": 10098992} {"current_steps": 36050, "total_steps": 40000, "loss": 0.0, "lr": 1.1940323179365192e-06, "epoch": 400.55555555555554, "percentage": 90.12, "elapsed_time": "4:05:33", "remaining_time": "0:26:54", "throughput": 685.55, "total_tokens": 10100352} {"current_steps": 36055, "total_steps": 40000, "loss": 0.0, "lr": 1.1910363416252095e-06, "epoch": 400.6111111111111, "percentage": 90.14, "elapsed_time": "4:05:35", "remaining_time": "0:26:52", "throughput": 685.56, "total_tokens": 10101744} {"current_steps": 36060, "total_steps": 40000, "loss": 0.0, "lr": 1.1880440369552964e-06, "epoch": 400.6666666666667, "percentage": 90.15, "elapsed_time": "4:05:37", "remaining_time": "0:26:50", "throughput": 685.56, "total_tokens": 10103120} {"current_steps": 36065, "total_steps": 40000, "loss": 0.0, "lr": 1.1850554043882328e-06, "epoch": 400.72222222222223, "percentage": 90.16, "elapsed_time": "4:05:38", "remaining_time": "0:26:48", "throughput": 685.56, "total_tokens": 10104496} {"current_steps": 36070, "total_steps": 40000, "loss": 0.0, "lr": 1.1820704443849028e-06, "epoch": 400.77777777777777, "percentage": 90.18, "elapsed_time": "4:05:40", "remaining_time": "0:26:46", "throughput": 685.57, "total_tokens": 10105920} {"current_steps": 36075, "total_steps": 40000, "loss": 0.0, "lr": 1.1790891574056219e-06, "epoch": 400.8333333333333, "percentage": 90.19, "elapsed_time": "4:05:42", "remaining_time": "0:26:44", "throughput": 685.58, "total_tokens": 10107328} {"current_steps": 36080, "total_steps": 40000, "loss": 0.0, "lr": 1.1761115439101523e-06, "epoch": 400.8888888888889, "percentage": 90.2, "elapsed_time": "4:05:44", "remaining_time": "0:26:41", "throughput": 685.58, "total_tokens": 10108688} {"current_steps": 36085, "total_steps": 40000, "loss": 0.0, "lr": 1.1731376043576659e-06, "epoch": 400.94444444444446, "percentage": 90.21, "elapsed_time": "4:05:46", "remaining_time": "0:26:39", "throughput": 685.58, "total_tokens": 10110080} {"current_steps": 36090, "total_steps": 40000, "loss": 0.0, "lr": 1.1701673392067875e-06, "epoch": 401.0, "percentage": 90.22, "elapsed_time": "4:05:48", "remaining_time": "0:26:37", "throughput": 685.57, "total_tokens": 10111424} {"current_steps": 36095, "total_steps": 40000, "loss": 0.0, "lr": 1.1672007489155757e-06, "epoch": 401.05555555555554, "percentage": 90.24, "elapsed_time": "4:05:51", "remaining_time": "0:26:35", "throughput": 685.57, "total_tokens": 10112880} {"current_steps": 36100, "total_steps": 40000, "loss": 0.0, "lr": 1.164237833941506e-06, "epoch": 401.1111111111111, "percentage": 90.25, "elapsed_time": "4:05:52", "remaining_time": "0:26:33", "throughput": 685.58, "total_tokens": 10114320} {"current_steps": 36105, "total_steps": 40000, "loss": 0.0, "lr": 1.1612785947415022e-06, "epoch": 401.1666666666667, "percentage": 90.26, "elapsed_time": "4:05:54", "remaining_time": "0:26:31", "throughput": 685.58, "total_tokens": 10115728} {"current_steps": 36110, "total_steps": 40000, "loss": 0.0, "lr": 1.1583230317719185e-06, "epoch": 401.22222222222223, "percentage": 90.28, "elapsed_time": "4:05:56", "remaining_time": "0:26:29", "throughput": 685.59, "total_tokens": 10117136} {"current_steps": 36115, "total_steps": 40000, "loss": 0.0, "lr": 1.1553711454885318e-06, "epoch": 401.27777777777777, "percentage": 90.29, "elapsed_time": "4:05:58", "remaining_time": "0:26:27", "throughput": 685.59, "total_tokens": 10118496} {"current_steps": 36120, "total_steps": 40000, "loss": 0.0, "lr": 1.152422936346567e-06, "epoch": 401.3333333333333, "percentage": 90.3, "elapsed_time": "4:06:00", "remaining_time": "0:26:25", "throughput": 685.59, "total_tokens": 10119856} {"current_steps": 36125, "total_steps": 40000, "loss": 0.0, "lr": 1.1494784048006718e-06, "epoch": 401.3888888888889, "percentage": 90.31, "elapsed_time": "4:06:02", "remaining_time": "0:26:23", "throughput": 685.6, "total_tokens": 10121232} {"current_steps": 36130, "total_steps": 40000, "loss": 0.0, "lr": 1.1465375513049326e-06, "epoch": 401.44444444444446, "percentage": 90.33, "elapsed_time": "4:06:04", "remaining_time": "0:26:21", "throughput": 685.6, "total_tokens": 10122624} {"current_steps": 36135, "total_steps": 40000, "loss": 0.0, "lr": 1.1436003763128616e-06, "epoch": 401.5, "percentage": 90.34, "elapsed_time": "4:06:06", "remaining_time": "0:26:19", "throughput": 685.61, "total_tokens": 10124064} {"current_steps": 36140, "total_steps": 40000, "loss": 0.0, "lr": 1.1406668802774106e-06, "epoch": 401.55555555555554, "percentage": 90.35, "elapsed_time": "4:06:08", "remaining_time": "0:26:17", "throughput": 685.61, "total_tokens": 10125456} {"current_steps": 36145, "total_steps": 40000, "loss": 0.0, "lr": 1.137737063650965e-06, "epoch": 401.6111111111111, "percentage": 90.36, "elapsed_time": "4:06:10", "remaining_time": "0:26:15", "throughput": 685.62, "total_tokens": 10126864} {"current_steps": 36150, "total_steps": 40000, "loss": 0.0, "lr": 1.1348109268853323e-06, "epoch": 401.6666666666667, "percentage": 90.38, "elapsed_time": "4:06:12", "remaining_time": "0:26:13", "throughput": 685.62, "total_tokens": 10128288} {"current_steps": 36155, "total_steps": 40000, "loss": 0.0, "lr": 1.1318884704317634e-06, "epoch": 401.72222222222223, "percentage": 90.39, "elapsed_time": "4:06:14", "remaining_time": "0:26:11", "throughput": 685.63, "total_tokens": 10129712} {"current_steps": 36160, "total_steps": 40000, "loss": 0.0, "lr": 1.1289696947409417e-06, "epoch": 401.77777777777777, "percentage": 90.4, "elapsed_time": "4:06:16", "remaining_time": "0:26:09", "throughput": 685.64, "total_tokens": 10131120} {"current_steps": 36165, "total_steps": 40000, "loss": 0.0, "lr": 1.126054600262974e-06, "epoch": 401.8333333333333, "percentage": 90.41, "elapsed_time": "4:06:18", "remaining_time": "0:26:07", "throughput": 685.64, "total_tokens": 10132512} {"current_steps": 36170, "total_steps": 40000, "loss": 0.0, "lr": 1.1231431874474064e-06, "epoch": 401.8888888888889, "percentage": 90.42, "elapsed_time": "4:06:20", "remaining_time": "0:26:05", "throughput": 685.64, "total_tokens": 10133872} {"current_steps": 36175, "total_steps": 40000, "loss": 0.0, "lr": 1.12023545674321e-06, "epoch": 401.94444444444446, "percentage": 90.44, "elapsed_time": "4:06:22", "remaining_time": "0:26:02", "throughput": 685.65, "total_tokens": 10135280} {"current_steps": 36180, "total_steps": 40000, "loss": 0.0, "lr": 1.117331408598804e-06, "epoch": 402.0, "percentage": 90.45, "elapsed_time": "4:06:24", "remaining_time": "0:26:00", "throughput": 685.64, "total_tokens": 10136672} {"current_steps": 36185, "total_steps": 40000, "loss": 0.0, "lr": 1.1144310434620191e-06, "epoch": 402.05555555555554, "percentage": 90.46, "elapsed_time": "4:06:26", "remaining_time": "0:25:58", "throughput": 685.64, "total_tokens": 10138096} {"current_steps": 36190, "total_steps": 40000, "loss": 0.0, "lr": 1.1115343617801365e-06, "epoch": 402.1111111111111, "percentage": 90.48, "elapsed_time": "4:06:28", "remaining_time": "0:25:56", "throughput": 685.64, "total_tokens": 10139472} {"current_steps": 36195, "total_steps": 40000, "loss": 0.0, "lr": 1.1086413639998515e-06, "epoch": 402.1666666666667, "percentage": 90.49, "elapsed_time": "4:06:30", "remaining_time": "0:25:54", "throughput": 685.65, "total_tokens": 10140896} {"current_steps": 36200, "total_steps": 40000, "loss": 0.0, "lr": 1.1057520505673103e-06, "epoch": 402.22222222222223, "percentage": 90.5, "elapsed_time": "4:06:32", "remaining_time": "0:25:52", "throughput": 685.65, "total_tokens": 10142304} {"current_steps": 36200, "total_steps": 40000, "eval_loss": 0.33484143018722534, "epoch": 402.22222222222223, "percentage": 90.5, "elapsed_time": "4:06:33", "remaining_time": "0:25:52", "throughput": 685.59, "total_tokens": 10142304} {"current_steps": 36205, "total_steps": 40000, "loss": 0.0, "lr": 1.1028664219280727e-06, "epoch": 402.27777777777777, "percentage": 90.51, "elapsed_time": "4:06:36", "remaining_time": "0:25:50", "throughput": 685.54, "total_tokens": 10143712} {"current_steps": 36210, "total_steps": 40000, "loss": 0.0, "lr": 1.0999844785271468e-06, "epoch": 402.3333333333333, "percentage": 90.53, "elapsed_time": "4:06:38", "remaining_time": "0:25:48", "throughput": 685.54, "total_tokens": 10145136} {"current_steps": 36215, "total_steps": 40000, "loss": 0.0, "lr": 1.097106220808955e-06, "epoch": 402.3888888888889, "percentage": 90.54, "elapsed_time": "4:06:40", "remaining_time": "0:25:46", "throughput": 685.54, "total_tokens": 10146512} {"current_steps": 36220, "total_steps": 40000, "loss": 0.0, "lr": 1.0942316492173698e-06, "epoch": 402.44444444444446, "percentage": 90.55, "elapsed_time": "4:06:42", "remaining_time": "0:25:44", "throughput": 685.55, "total_tokens": 10147920} {"current_steps": 36225, "total_steps": 40000, "loss": 0.0, "lr": 1.0913607641956841e-06, "epoch": 402.5, "percentage": 90.56, "elapsed_time": "4:06:44", "remaining_time": "0:25:42", "throughput": 685.55, "total_tokens": 10149264} {"current_steps": 36230, "total_steps": 40000, "loss": 0.0, "lr": 1.0884935661866213e-06, "epoch": 402.55555555555554, "percentage": 90.58, "elapsed_time": "4:06:46", "remaining_time": "0:25:40", "throughput": 685.55, "total_tokens": 10150672} {"current_steps": 36235, "total_steps": 40000, "loss": 0.0, "lr": 1.0856300556323418e-06, "epoch": 402.6111111111111, "percentage": 90.59, "elapsed_time": "4:06:48", "remaining_time": "0:25:38", "throughput": 685.56, "total_tokens": 10152080} {"current_steps": 36240, "total_steps": 40000, "loss": 0.0, "lr": 1.0827702329744365e-06, "epoch": 402.6666666666667, "percentage": 90.6, "elapsed_time": "4:06:50", "remaining_time": "0:25:36", "throughput": 685.56, "total_tokens": 10153456} {"current_steps": 36245, "total_steps": 40000, "loss": 0.0, "lr": 1.0799140986539197e-06, "epoch": 402.72222222222223, "percentage": 90.61, "elapsed_time": "4:06:52", "remaining_time": "0:25:34", "throughput": 685.57, "total_tokens": 10154864} {"current_steps": 36250, "total_steps": 40000, "loss": 0.0, "lr": 1.0770616531112526e-06, "epoch": 402.77777777777777, "percentage": 90.62, "elapsed_time": "4:06:54", "remaining_time": "0:25:32", "throughput": 685.57, "total_tokens": 10156288} {"current_steps": 36255, "total_steps": 40000, "loss": 0.0, "lr": 1.0742128967863085e-06, "epoch": 402.8333333333333, "percentage": 90.64, "elapsed_time": "4:06:56", "remaining_time": "0:25:30", "throughput": 685.58, "total_tokens": 10157696} {"current_steps": 36260, "total_steps": 40000, "loss": 0.0, "lr": 1.071367830118411e-06, "epoch": 402.8888888888889, "percentage": 90.65, "elapsed_time": "4:06:58", "remaining_time": "0:25:28", "throughput": 685.58, "total_tokens": 10159072} {"current_steps": 36265, "total_steps": 40000, "loss": 0.0, "lr": 1.068526453546298e-06, "epoch": 402.94444444444446, "percentage": 90.66, "elapsed_time": "4:07:00", "remaining_time": "0:25:26", "throughput": 685.59, "total_tokens": 10160464} {"current_steps": 36270, "total_steps": 40000, "loss": 0.0, "lr": 1.0656887675081467e-06, "epoch": 403.0, "percentage": 90.67, "elapsed_time": "4:07:02", "remaining_time": "0:25:24", "throughput": 685.58, "total_tokens": 10161824} {"current_steps": 36275, "total_steps": 40000, "loss": 0.0, "lr": 1.0628547724415628e-06, "epoch": 403.05555555555554, "percentage": 90.69, "elapsed_time": "4:07:04", "remaining_time": "0:25:22", "throughput": 685.57, "total_tokens": 10163184} {"current_steps": 36280, "total_steps": 40000, "loss": 0.0, "lr": 1.0600244687835881e-06, "epoch": 403.1111111111111, "percentage": 90.7, "elapsed_time": "4:07:06", "remaining_time": "0:25:20", "throughput": 685.58, "total_tokens": 10164592} {"current_steps": 36285, "total_steps": 40000, "loss": 0.0, "lr": 1.0571978569706876e-06, "epoch": 403.1666666666667, "percentage": 90.71, "elapsed_time": "4:07:08", "remaining_time": "0:25:18", "throughput": 685.58, "total_tokens": 10166000} {"current_steps": 36290, "total_steps": 40000, "loss": 0.0, "lr": 1.0543749374387652e-06, "epoch": 403.22222222222223, "percentage": 90.72, "elapsed_time": "4:07:10", "remaining_time": "0:25:16", "throughput": 685.58, "total_tokens": 10167360} {"current_steps": 36295, "total_steps": 40000, "loss": 0.0, "lr": 1.051555710623142e-06, "epoch": 403.27777777777777, "percentage": 90.74, "elapsed_time": "4:07:12", "remaining_time": "0:25:14", "throughput": 685.59, "total_tokens": 10168752} {"current_steps": 36300, "total_steps": 40000, "loss": 0.0, "lr": 1.0487401769585847e-06, "epoch": 403.3333333333333, "percentage": 90.75, "elapsed_time": "4:07:14", "remaining_time": "0:25:12", "throughput": 685.59, "total_tokens": 10170144} {"current_steps": 36305, "total_steps": 40000, "loss": 0.0, "lr": 1.0459283368792845e-06, "epoch": 403.3888888888889, "percentage": 90.76, "elapsed_time": "4:07:16", "remaining_time": "0:25:09", "throughput": 685.6, "total_tokens": 10171568} {"current_steps": 36310, "total_steps": 40000, "loss": 0.0, "lr": 1.043120190818858e-06, "epoch": 403.44444444444446, "percentage": 90.77, "elapsed_time": "4:07:17", "remaining_time": "0:25:07", "throughput": 685.6, "total_tokens": 10172992} {"current_steps": 36315, "total_steps": 40000, "loss": 0.0, "lr": 1.0403157392103596e-06, "epoch": 403.5, "percentage": 90.79, "elapsed_time": "4:07:19", "remaining_time": "0:25:05", "throughput": 685.61, "total_tokens": 10174384} {"current_steps": 36320, "total_steps": 40000, "loss": 0.0, "lr": 1.0375149824862735e-06, "epoch": 403.55555555555554, "percentage": 90.8, "elapsed_time": "4:07:22", "remaining_time": "0:25:03", "throughput": 685.61, "total_tokens": 10175776} {"current_steps": 36325, "total_steps": 40000, "loss": 0.0, "lr": 1.034717921078507e-06, "epoch": 403.6111111111111, "percentage": 90.81, "elapsed_time": "4:07:24", "remaining_time": "0:25:01", "throughput": 685.61, "total_tokens": 10177232} {"current_steps": 36330, "total_steps": 40000, "loss": 0.0, "lr": 1.0319245554184009e-06, "epoch": 403.6666666666667, "percentage": 90.83, "elapsed_time": "4:07:26", "remaining_time": "0:24:59", "throughput": 685.61, "total_tokens": 10178640} {"current_steps": 36335, "total_steps": 40000, "loss": 0.0, "lr": 1.0291348859367361e-06, "epoch": 403.72222222222223, "percentage": 90.84, "elapsed_time": "4:07:28", "remaining_time": "0:24:57", "throughput": 685.61, "total_tokens": 10180048} {"current_steps": 36340, "total_steps": 40000, "loss": 0.0, "lr": 1.0263489130637016e-06, "epoch": 403.77777777777777, "percentage": 90.85, "elapsed_time": "4:07:30", "remaining_time": "0:24:55", "throughput": 685.62, "total_tokens": 10181488} {"current_steps": 36345, "total_steps": 40000, "loss": 0.0, "lr": 1.0235666372289427e-06, "epoch": 403.8333333333333, "percentage": 90.86, "elapsed_time": "4:07:32", "remaining_time": "0:24:53", "throughput": 685.62, "total_tokens": 10182912} {"current_steps": 36350, "total_steps": 40000, "loss": 0.0, "lr": 1.0207880588615076e-06, "epoch": 403.8888888888889, "percentage": 90.88, "elapsed_time": "4:07:34", "remaining_time": "0:24:51", "throughput": 685.62, "total_tokens": 10184320} {"current_steps": 36355, "total_steps": 40000, "loss": 0.0, "lr": 1.0180131783898984e-06, "epoch": 403.94444444444446, "percentage": 90.89, "elapsed_time": "4:07:36", "remaining_time": "0:24:49", "throughput": 685.62, "total_tokens": 10185696} {"current_steps": 36360, "total_steps": 40000, "loss": 0.0, "lr": 1.0152419962420362e-06, "epoch": 404.0, "percentage": 90.9, "elapsed_time": "4:07:38", "remaining_time": "0:24:47", "throughput": 685.61, "total_tokens": 10187088} {"current_steps": 36365, "total_steps": 40000, "loss": 0.0, "lr": 1.0124745128452685e-06, "epoch": 404.05555555555554, "percentage": 90.91, "elapsed_time": "4:07:40", "remaining_time": "0:24:45", "throughput": 685.6, "total_tokens": 10188496} {"current_steps": 36370, "total_steps": 40000, "loss": 0.0, "lr": 1.0097107286263758e-06, "epoch": 404.1111111111111, "percentage": 90.92, "elapsed_time": "4:07:42", "remaining_time": "0:24:43", "throughput": 685.6, "total_tokens": 10189824} {"current_steps": 36375, "total_steps": 40000, "loss": 0.0, "lr": 1.00695064401157e-06, "epoch": 404.1666666666667, "percentage": 90.94, "elapsed_time": "4:07:44", "remaining_time": "0:24:41", "throughput": 685.6, "total_tokens": 10191280} {"current_steps": 36380, "total_steps": 40000, "loss": 0.0, "lr": 1.0041942594264886e-06, "epoch": 404.22222222222223, "percentage": 90.95, "elapsed_time": "4:07:46", "remaining_time": "0:24:39", "throughput": 685.6, "total_tokens": 10192672} {"current_steps": 36385, "total_steps": 40000, "loss": 0.0, "lr": 1.001441575296208e-06, "epoch": 404.27777777777777, "percentage": 90.96, "elapsed_time": "4:07:48", "remaining_time": "0:24:37", "throughput": 685.61, "total_tokens": 10194096} {"current_steps": 36390, "total_steps": 40000, "loss": 0.0, "lr": 9.986925920452139e-07, "epoch": 404.3333333333333, "percentage": 90.97, "elapsed_time": "4:07:50", "remaining_time": "0:24:35", "throughput": 685.61, "total_tokens": 10195520} {"current_steps": 36395, "total_steps": 40000, "loss": 0.0, "lr": 9.959473100974475e-07, "epoch": 404.3888888888889, "percentage": 90.99, "elapsed_time": "4:07:52", "remaining_time": "0:24:33", "throughput": 685.61, "total_tokens": 10196912} {"current_steps": 36400, "total_steps": 40000, "loss": 0.0, "lr": 9.932057298762564e-07, "epoch": 404.44444444444446, "percentage": 91.0, "elapsed_time": "4:07:54", "remaining_time": "0:24:31", "throughput": 685.61, "total_tokens": 10198320} {"current_steps": 36400, "total_steps": 40000, "eval_loss": 0.3221988081932068, "epoch": 404.44444444444446, "percentage": 91.0, "elapsed_time": "4:07:56", "remaining_time": "0:24:31", "throughput": 685.55, "total_tokens": 10198320} {"current_steps": 36405, "total_steps": 40000, "loss": 0.0, "lr": 9.90467851804433e-07, "epoch": 404.5, "percentage": 91.01, "elapsed_time": "4:07:59", "remaining_time": "0:24:29", "throughput": 685.49, "total_tokens": 10199744} {"current_steps": 36410, "total_steps": 40000, "loss": 0.0, "lr": 9.877336763041895e-07, "epoch": 404.55555555555554, "percentage": 91.03, "elapsed_time": "4:08:01", "remaining_time": "0:24:27", "throughput": 685.48, "total_tokens": 10201136} {"current_steps": 36415, "total_steps": 40000, "loss": 0.0, "lr": 9.850032037971662e-07, "epoch": 404.6111111111111, "percentage": 91.04, "elapsed_time": "4:08:03", "remaining_time": "0:24:25", "throughput": 685.49, "total_tokens": 10202560} {"current_steps": 36420, "total_steps": 40000, "loss": 0.0, "lr": 9.822764347044406e-07, "epoch": 404.6666666666667, "percentage": 91.05, "elapsed_time": "4:08:05", "remaining_time": "0:24:23", "throughput": 685.49, "total_tokens": 10203968} {"current_steps": 36425, "total_steps": 40000, "loss": 0.0, "lr": 9.795533694465175e-07, "epoch": 404.72222222222223, "percentage": 91.06, "elapsed_time": "4:08:07", "remaining_time": "0:24:21", "throughput": 685.49, "total_tokens": 10205360} {"current_steps": 36430, "total_steps": 40000, "loss": 0.0, "lr": 9.768340084433197e-07, "epoch": 404.77777777777777, "percentage": 91.07, "elapsed_time": "4:08:09", "remaining_time": "0:24:19", "throughput": 685.49, "total_tokens": 10206784} {"current_steps": 36435, "total_steps": 40000, "loss": 0.0, "lr": 9.741183521142143e-07, "epoch": 404.8333333333333, "percentage": 91.09, "elapsed_time": "4:08:11", "remaining_time": "0:24:17", "throughput": 685.49, "total_tokens": 10208192} {"current_steps": 36440, "total_steps": 40000, "loss": 0.0, "lr": 9.714064008779889e-07, "epoch": 404.8888888888889, "percentage": 91.1, "elapsed_time": "4:08:13", "remaining_time": "0:24:15", "throughput": 685.49, "total_tokens": 10209536} {"current_steps": 36445, "total_steps": 40000, "loss": 0.0, "lr": 9.686981551528584e-07, "epoch": 404.94444444444446, "percentage": 91.11, "elapsed_time": "4:08:15", "remaining_time": "0:24:13", "throughput": 685.49, "total_tokens": 10210912} {"current_steps": 36450, "total_steps": 40000, "loss": 0.0, "lr": 9.65993615356467e-07, "epoch": 405.0, "percentage": 91.12, "elapsed_time": "4:08:18", "remaining_time": "0:24:10", "throughput": 685.48, "total_tokens": 10212320} {"current_steps": 36455, "total_steps": 40000, "loss": 0.0, "lr": 9.632927819058917e-07, "epoch": 405.05555555555554, "percentage": 91.14, "elapsed_time": "4:08:20", "remaining_time": "0:24:08", "throughput": 685.47, "total_tokens": 10213696} {"current_steps": 36460, "total_steps": 40000, "loss": 0.0, "lr": 9.605956552176305e-07, "epoch": 405.1111111111111, "percentage": 91.15, "elapsed_time": "4:08:22", "remaining_time": "0:24:06", "throughput": 685.47, "total_tokens": 10215120} {"current_steps": 36465, "total_steps": 40000, "loss": 0.0, "lr": 9.579022357076223e-07, "epoch": 405.1666666666667, "percentage": 91.16, "elapsed_time": "4:08:24", "remaining_time": "0:24:04", "throughput": 685.47, "total_tokens": 10216528} {"current_steps": 36470, "total_steps": 40000, "loss": 0.0, "lr": 9.552125237912158e-07, "epoch": 405.22222222222223, "percentage": 91.17, "elapsed_time": "4:08:26", "remaining_time": "0:24:02", "throughput": 685.47, "total_tokens": 10217904} {"current_steps": 36475, "total_steps": 40000, "loss": 0.0, "lr": 9.525265198832096e-07, "epoch": 405.27777777777777, "percentage": 91.19, "elapsed_time": "4:08:28", "remaining_time": "0:24:00", "throughput": 685.47, "total_tokens": 10219264} {"current_steps": 36480, "total_steps": 40000, "loss": 0.0, "lr": 9.498442243978112e-07, "epoch": 405.3333333333333, "percentage": 91.2, "elapsed_time": "4:08:30", "remaining_time": "0:23:58", "throughput": 685.47, "total_tokens": 10220688} {"current_steps": 36485, "total_steps": 40000, "loss": 0.0, "lr": 9.471656377486649e-07, "epoch": 405.3888888888889, "percentage": 91.21, "elapsed_time": "4:08:32", "remaining_time": "0:23:56", "throughput": 685.47, "total_tokens": 10222048} {"current_steps": 36490, "total_steps": 40000, "loss": 0.0, "lr": 9.444907603488456e-07, "epoch": 405.44444444444446, "percentage": 91.22, "elapsed_time": "4:08:34", "remaining_time": "0:23:54", "throughput": 685.47, "total_tokens": 10223504} {"current_steps": 36495, "total_steps": 40000, "loss": 0.0, "lr": 9.418195926108514e-07, "epoch": 405.5, "percentage": 91.24, "elapsed_time": "4:08:36", "remaining_time": "0:23:52", "throughput": 685.47, "total_tokens": 10224896} {"current_steps": 36500, "total_steps": 40000, "loss": 0.0, "lr": 9.391521349466053e-07, "epoch": 405.55555555555554, "percentage": 91.25, "elapsed_time": "4:08:38", "remaining_time": "0:23:50", "throughput": 685.48, "total_tokens": 10226336} {"current_steps": 36505, "total_steps": 40000, "loss": 0.0, "lr": 9.364883877674758e-07, "epoch": 405.6111111111111, "percentage": 91.26, "elapsed_time": "4:08:40", "remaining_time": "0:23:48", "throughput": 685.48, "total_tokens": 10227744} {"current_steps": 36510, "total_steps": 40000, "loss": 0.0, "lr": 9.33828351484231e-07, "epoch": 405.6666666666667, "percentage": 91.27, "elapsed_time": "4:08:42", "remaining_time": "0:23:46", "throughput": 685.48, "total_tokens": 10229168} {"current_steps": 36515, "total_steps": 40000, "loss": 0.0, "lr": 9.311720265070906e-07, "epoch": 405.72222222222223, "percentage": 91.29, "elapsed_time": "4:08:44", "remaining_time": "0:23:44", "throughput": 685.48, "total_tokens": 10230512} {"current_steps": 36520, "total_steps": 40000, "loss": 0.0, "lr": 9.285194132456931e-07, "epoch": 405.77777777777777, "percentage": 91.3, "elapsed_time": "4:08:46", "remaining_time": "0:23:42", "throughput": 685.48, "total_tokens": 10231904} {"current_steps": 36525, "total_steps": 40000, "loss": 0.0, "lr": 9.258705121091032e-07, "epoch": 405.8333333333333, "percentage": 91.31, "elapsed_time": "4:08:48", "remaining_time": "0:23:40", "throughput": 685.48, "total_tokens": 10233264} {"current_steps": 36530, "total_steps": 40000, "loss": 0.0, "lr": 9.232253235058136e-07, "epoch": 405.8888888888889, "percentage": 91.33, "elapsed_time": "4:08:50", "remaining_time": "0:23:38", "throughput": 685.48, "total_tokens": 10234688} {"current_steps": 36535, "total_steps": 40000, "loss": 0.0, "lr": 9.205838478437478e-07, "epoch": 405.94444444444446, "percentage": 91.34, "elapsed_time": "4:08:52", "remaining_time": "0:23:36", "throughput": 685.48, "total_tokens": 10236096} {"current_steps": 36540, "total_steps": 40000, "loss": 0.0, "lr": 9.179460855302524e-07, "epoch": 406.0, "percentage": 91.35, "elapsed_time": "4:08:54", "remaining_time": "0:23:34", "throughput": 685.47, "total_tokens": 10237488} {"current_steps": 36545, "total_steps": 40000, "loss": 0.0, "lr": 9.153120369721046e-07, "epoch": 406.05555555555554, "percentage": 91.36, "elapsed_time": "4:08:57", "remaining_time": "0:23:32", "throughput": 685.46, "total_tokens": 10238880} {"current_steps": 36550, "total_steps": 40000, "loss": 0.0, "lr": 9.126817025755103e-07, "epoch": 406.1111111111111, "percentage": 91.38, "elapsed_time": "4:08:59", "remaining_time": "0:23:30", "throughput": 685.46, "total_tokens": 10240304} {"current_steps": 36555, "total_steps": 40000, "loss": 0.0, "lr": 9.100550827460947e-07, "epoch": 406.1666666666667, "percentage": 91.39, "elapsed_time": "4:09:01", "remaining_time": "0:23:28", "throughput": 685.46, "total_tokens": 10241648} {"current_steps": 36560, "total_steps": 40000, "loss": 0.0, "lr": 9.0743217788892e-07, "epoch": 406.22222222222223, "percentage": 91.4, "elapsed_time": "4:09:03", "remaining_time": "0:23:26", "throughput": 685.46, "total_tokens": 10243104} {"current_steps": 36565, "total_steps": 40000, "loss": 0.0, "lr": 9.048129884084683e-07, "epoch": 406.27777777777777, "percentage": 91.41, "elapsed_time": "4:09:05", "remaining_time": "0:23:23", "throughput": 685.46, "total_tokens": 10244480} {"current_steps": 36570, "total_steps": 40000, "loss": 0.0, "lr": 9.021975147086553e-07, "epoch": 406.3333333333333, "percentage": 91.42, "elapsed_time": "4:09:07", "remaining_time": "0:23:21", "throughput": 685.46, "total_tokens": 10245872} {"current_steps": 36575, "total_steps": 40000, "loss": 0.0, "lr": 8.995857571928141e-07, "epoch": 406.3888888888889, "percentage": 91.44, "elapsed_time": "4:09:09", "remaining_time": "0:23:19", "throughput": 685.46, "total_tokens": 10247264} {"current_steps": 36580, "total_steps": 40000, "loss": 0.0, "lr": 8.969777162637139e-07, "epoch": 406.44444444444446, "percentage": 91.45, "elapsed_time": "4:09:11", "remaining_time": "0:23:17", "throughput": 685.46, "total_tokens": 10248656} {"current_steps": 36585, "total_steps": 40000, "loss": 0.0, "lr": 8.943733923235525e-07, "epoch": 406.5, "percentage": 91.46, "elapsed_time": "4:09:13", "remaining_time": "0:23:15", "throughput": 685.46, "total_tokens": 10250032} {"current_steps": 36590, "total_steps": 40000, "loss": 0.0, "lr": 8.917727857739394e-07, "epoch": 406.55555555555554, "percentage": 91.47, "elapsed_time": "4:09:15", "remaining_time": "0:23:13", "throughput": 685.46, "total_tokens": 10251424} {"current_steps": 36595, "total_steps": 40000, "loss": 0.0, "lr": 8.891758970159258e-07, "epoch": 406.6111111111111, "percentage": 91.49, "elapsed_time": "4:09:17", "remaining_time": "0:23:11", "throughput": 685.47, "total_tokens": 10252864} {"current_steps": 36600, "total_steps": 40000, "loss": 0.0, "lr": 8.86582726449986e-07, "epoch": 406.6666666666667, "percentage": 91.5, "elapsed_time": "4:09:19", "remaining_time": "0:23:09", "throughput": 685.47, "total_tokens": 10254256} {"current_steps": 36600, "total_steps": 40000, "eval_loss": 0.37285032868385315, "epoch": 406.6666666666667, "percentage": 91.5, "elapsed_time": "4:09:20", "remaining_time": "0:23:09", "throughput": 685.41, "total_tokens": 10254256} {"current_steps": 36605, "total_steps": 40000, "loss": 0.0, "lr": 8.839932744760165e-07, "epoch": 406.72222222222223, "percentage": 91.51, "elapsed_time": "4:09:24", "remaining_time": "0:23:07", "throughput": 685.34, "total_tokens": 10255648} {"current_steps": 36610, "total_steps": 40000, "loss": 0.0, "lr": 8.814075414933482e-07, "epoch": 406.77777777777777, "percentage": 91.53, "elapsed_time": "4:09:26", "remaining_time": "0:23:05", "throughput": 685.34, "total_tokens": 10257040} {"current_steps": 36615, "total_steps": 40000, "loss": 0.0, "lr": 8.788255279007257e-07, "epoch": 406.8333333333333, "percentage": 91.54, "elapsed_time": "4:09:28", "remaining_time": "0:23:03", "throughput": 685.34, "total_tokens": 10258448} {"current_steps": 36620, "total_steps": 40000, "loss": 0.0, "lr": 8.762472340963362e-07, "epoch": 406.8888888888889, "percentage": 91.55, "elapsed_time": "4:09:30", "remaining_time": "0:23:01", "throughput": 685.34, "total_tokens": 10259872} {"current_steps": 36625, "total_steps": 40000, "loss": 0.0, "lr": 8.736726604777811e-07, "epoch": 406.94444444444446, "percentage": 91.56, "elapsed_time": "4:09:32", "remaining_time": "0:22:59", "throughput": 685.34, "total_tokens": 10261216} {"current_steps": 36630, "total_steps": 40000, "loss": 0.0, "lr": 8.711018074420901e-07, "epoch": 407.0, "percentage": 91.57, "elapsed_time": "4:09:34", "remaining_time": "0:22:57", "throughput": 685.33, "total_tokens": 10262608} {"current_steps": 36635, "total_steps": 40000, "loss": 0.0, "lr": 8.685346753857209e-07, "epoch": 407.05555555555554, "percentage": 91.59, "elapsed_time": "4:09:36", "remaining_time": "0:22:55", "throughput": 685.32, "total_tokens": 10263984} {"current_steps": 36640, "total_steps": 40000, "loss": 0.0, "lr": 8.659712647045654e-07, "epoch": 407.1111111111111, "percentage": 91.6, "elapsed_time": "4:09:38", "remaining_time": "0:22:53", "throughput": 685.32, "total_tokens": 10265376} {"current_steps": 36645, "total_steps": 40000, "loss": 0.0, "lr": 8.634115757939209e-07, "epoch": 407.1666666666667, "percentage": 91.61, "elapsed_time": "4:09:40", "remaining_time": "0:22:51", "throughput": 685.32, "total_tokens": 10266752} {"current_steps": 36650, "total_steps": 40000, "loss": 0.0, "lr": 8.608556090485387e-07, "epoch": 407.22222222222223, "percentage": 91.62, "elapsed_time": "4:09:42", "remaining_time": "0:22:49", "throughput": 685.32, "total_tokens": 10268144} {"current_steps": 36655, "total_steps": 40000, "loss": 0.0, "lr": 8.583033648625671e-07, "epoch": 407.27777777777777, "percentage": 91.64, "elapsed_time": "4:09:45", "remaining_time": "0:22:47", "throughput": 685.32, "total_tokens": 10269536} {"current_steps": 36660, "total_steps": 40000, "loss": 0.0, "lr": 8.557548436295998e-07, "epoch": 407.3333333333333, "percentage": 91.65, "elapsed_time": "4:09:47", "remaining_time": "0:22:45", "throughput": 685.32, "total_tokens": 10270896} {"current_steps": 36665, "total_steps": 40000, "loss": 0.0, "lr": 8.532100457426556e-07, "epoch": 407.3888888888889, "percentage": 91.66, "elapsed_time": "4:09:49", "remaining_time": "0:22:43", "throughput": 685.32, "total_tokens": 10272368} {"current_steps": 36670, "total_steps": 40000, "loss": 0.0, "lr": 8.506689715941679e-07, "epoch": 407.44444444444446, "percentage": 91.67, "elapsed_time": "4:09:51", "remaining_time": "0:22:41", "throughput": 685.32, "total_tokens": 10273760} {"current_steps": 36675, "total_steps": 40000, "loss": 0.0, "lr": 8.481316215760011e-07, "epoch": 407.5, "percentage": 91.69, "elapsed_time": "4:09:53", "remaining_time": "0:22:39", "throughput": 685.32, "total_tokens": 10275120} {"current_steps": 36680, "total_steps": 40000, "loss": 0.0, "lr": 8.455979960794558e-07, "epoch": 407.55555555555554, "percentage": 91.7, "elapsed_time": "4:09:55", "remaining_time": "0:22:37", "throughput": 685.33, "total_tokens": 10276576} {"current_steps": 36685, "total_steps": 40000, "loss": 0.0, "lr": 8.430680954952364e-07, "epoch": 407.6111111111111, "percentage": 91.71, "elapsed_time": "4:09:57", "remaining_time": "0:22:35", "throughput": 685.32, "total_tokens": 10277936} {"current_steps": 36690, "total_steps": 40000, "loss": 0.0, "lr": 8.405419202134974e-07, "epoch": 407.6666666666667, "percentage": 91.72, "elapsed_time": "4:09:59", "remaining_time": "0:22:33", "throughput": 685.32, "total_tokens": 10279328} {"current_steps": 36695, "total_steps": 40000, "loss": 0.0, "lr": 8.380194706237993e-07, "epoch": 407.72222222222223, "percentage": 91.74, "elapsed_time": "4:10:01", "remaining_time": "0:22:31", "throughput": 685.32, "total_tokens": 10280720} {"current_steps": 36700, "total_steps": 40000, "loss": 0.0, "lr": 8.355007471151366e-07, "epoch": 407.77777777777777, "percentage": 91.75, "elapsed_time": "4:10:03", "remaining_time": "0:22:29", "throughput": 685.33, "total_tokens": 10282160} {"current_steps": 36705, "total_steps": 40000, "loss": 0.0, "lr": 8.329857500759292e-07, "epoch": 407.8333333333333, "percentage": 91.76, "elapsed_time": "4:10:05", "remaining_time": "0:22:27", "throughput": 685.33, "total_tokens": 10283536} {"current_steps": 36710, "total_steps": 40000, "loss": 0.0, "lr": 8.304744798940194e-07, "epoch": 407.8888888888889, "percentage": 91.77, "elapsed_time": "4:10:07", "remaining_time": "0:22:24", "throughput": 685.33, "total_tokens": 10284944} {"current_steps": 36715, "total_steps": 40000, "loss": 0.0, "lr": 8.279669369566756e-07, "epoch": 407.94444444444446, "percentage": 91.79, "elapsed_time": "4:10:09", "remaining_time": "0:22:22", "throughput": 685.33, "total_tokens": 10286304} {"current_steps": 36720, "total_steps": 40000, "loss": 0.0, "lr": 8.254631216505993e-07, "epoch": 408.0, "percentage": 91.8, "elapsed_time": "4:10:11", "remaining_time": "0:22:20", "throughput": 685.32, "total_tokens": 10287728} {"current_steps": 36725, "total_steps": 40000, "loss": 0.0, "lr": 8.229630343619038e-07, "epoch": 408.05555555555554, "percentage": 91.81, "elapsed_time": "4:10:13", "remaining_time": "0:22:18", "throughput": 685.31, "total_tokens": 10289136} {"current_steps": 36730, "total_steps": 40000, "loss": 0.0, "lr": 8.204666754761392e-07, "epoch": 408.1111111111111, "percentage": 91.83, "elapsed_time": "4:10:15", "remaining_time": "0:22:16", "throughput": 685.31, "total_tokens": 10290528} {"current_steps": 36735, "total_steps": 40000, "loss": 0.0, "lr": 8.179740453782669e-07, "epoch": 408.1666666666667, "percentage": 91.84, "elapsed_time": "4:10:17", "remaining_time": "0:22:14", "throughput": 685.31, "total_tokens": 10291936} {"current_steps": 36740, "total_steps": 40000, "loss": 0.0, "lr": 8.154851444526907e-07, "epoch": 408.22222222222223, "percentage": 91.85, "elapsed_time": "4:10:19", "remaining_time": "0:22:12", "throughput": 685.31, "total_tokens": 10293312} {"current_steps": 36745, "total_steps": 40000, "loss": 0.0, "lr": 8.129999730832283e-07, "epoch": 408.27777777777777, "percentage": 91.86, "elapsed_time": "4:10:21", "remaining_time": "0:22:10", "throughput": 685.31, "total_tokens": 10294656} {"current_steps": 36750, "total_steps": 40000, "loss": 0.0, "lr": 8.105185316531178e-07, "epoch": 408.3333333333333, "percentage": 91.88, "elapsed_time": "4:10:23", "remaining_time": "0:22:08", "throughput": 685.31, "total_tokens": 10296048} {"current_steps": 36755, "total_steps": 40000, "loss": 0.0, "lr": 8.08040820545039e-07, "epoch": 408.3888888888889, "percentage": 91.89, "elapsed_time": "4:10:25", "remaining_time": "0:22:06", "throughput": 685.31, "total_tokens": 10297440} {"current_steps": 36760, "total_steps": 40000, "loss": 0.0, "lr": 8.055668401410782e-07, "epoch": 408.44444444444446, "percentage": 91.9, "elapsed_time": "4:10:28", "remaining_time": "0:22:04", "throughput": 685.31, "total_tokens": 10298880} {"current_steps": 36765, "total_steps": 40000, "loss": 0.0, "lr": 8.030965908227578e-07, "epoch": 408.5, "percentage": 91.91, "elapsed_time": "4:10:30", "remaining_time": "0:22:02", "throughput": 685.31, "total_tokens": 10300304} {"current_steps": 36770, "total_steps": 40000, "loss": 0.0, "lr": 8.006300729710203e-07, "epoch": 408.55555555555554, "percentage": 91.92, "elapsed_time": "4:10:32", "remaining_time": "0:22:00", "throughput": 685.3, "total_tokens": 10301712} {"current_steps": 36775, "total_steps": 40000, "loss": 0.0, "lr": 7.981672869662337e-07, "epoch": 408.6111111111111, "percentage": 91.94, "elapsed_time": "4:10:34", "remaining_time": "0:21:58", "throughput": 685.3, "total_tokens": 10303104} {"current_steps": 36780, "total_steps": 40000, "loss": 0.0, "lr": 7.957082331881888e-07, "epoch": 408.6666666666667, "percentage": 91.95, "elapsed_time": "4:10:36", "remaining_time": "0:21:56", "throughput": 685.3, "total_tokens": 10304496} {"current_steps": 36785, "total_steps": 40000, "loss": 0.0, "lr": 7.932529120161069e-07, "epoch": 408.72222222222223, "percentage": 91.96, "elapsed_time": "4:10:38", "remaining_time": "0:21:54", "throughput": 685.3, "total_tokens": 10305856} {"current_steps": 36790, "total_steps": 40000, "loss": 0.0, "lr": 7.908013238286243e-07, "epoch": 408.77777777777777, "percentage": 91.97, "elapsed_time": "4:10:40", "remaining_time": "0:21:52", "throughput": 685.31, "total_tokens": 10307312} {"current_steps": 36795, "total_steps": 40000, "loss": 0.0, "lr": 7.883534690038136e-07, "epoch": 408.8333333333333, "percentage": 91.99, "elapsed_time": "4:10:42", "remaining_time": "0:21:50", "throughput": 685.31, "total_tokens": 10308704} {"current_steps": 36800, "total_steps": 40000, "loss": 0.0, "lr": 7.859093479191559e-07, "epoch": 408.8888888888889, "percentage": 92.0, "elapsed_time": "4:10:44", "remaining_time": "0:21:48", "throughput": 685.31, "total_tokens": 10310096} {"current_steps": 36800, "total_steps": 40000, "eval_loss": 0.3391804099082947, "epoch": 408.8888888888889, "percentage": 92.0, "elapsed_time": "4:10:45", "remaining_time": "0:21:48", "throughput": 685.25, "total_tokens": 10310096} {"current_steps": 36805, "total_steps": 40000, "loss": 0.0, "lr": 7.834689609515722e-07, "epoch": 408.94444444444446, "percentage": 92.01, "elapsed_time": "4:10:49", "remaining_time": "0:21:46", "throughput": 685.19, "total_tokens": 10311536} {"current_steps": 36810, "total_steps": 40000, "loss": 0.0, "lr": 7.810323084774002e-07, "epoch": 409.0, "percentage": 92.03, "elapsed_time": "4:10:51", "remaining_time": "0:21:44", "throughput": 685.18, "total_tokens": 10312928} {"current_steps": 36815, "total_steps": 40000, "loss": 0.0, "lr": 7.785993908723976e-07, "epoch": 409.05555555555554, "percentage": 92.04, "elapsed_time": "4:10:53", "remaining_time": "0:21:42", "throughput": 685.17, "total_tokens": 10314304} {"current_steps": 36820, "total_steps": 40000, "loss": 0.0, "lr": 7.761702085117534e-07, "epoch": 409.1111111111111, "percentage": 92.05, "elapsed_time": "4:10:55", "remaining_time": "0:21:40", "throughput": 685.17, "total_tokens": 10315696} {"current_steps": 36825, "total_steps": 40000, "loss": 0.0, "lr": 7.737447617700844e-07, "epoch": 409.1666666666667, "percentage": 92.06, "elapsed_time": "4:10:57", "remaining_time": "0:21:38", "throughput": 685.17, "total_tokens": 10317104} {"current_steps": 36830, "total_steps": 40000, "loss": 0.0, "lr": 7.713230510214136e-07, "epoch": 409.22222222222223, "percentage": 92.07, "elapsed_time": "4:10:59", "remaining_time": "0:21:36", "throughput": 685.17, "total_tokens": 10318496} {"current_steps": 36835, "total_steps": 40000, "loss": 0.0, "lr": 7.689050766392092e-07, "epoch": 409.27777777777777, "percentage": 92.09, "elapsed_time": "4:11:01", "remaining_time": "0:21:34", "throughput": 685.17, "total_tokens": 10319872} {"current_steps": 36840, "total_steps": 40000, "loss": 0.0, "lr": 7.664908389963477e-07, "epoch": 409.3333333333333, "percentage": 92.1, "elapsed_time": "4:11:03", "remaining_time": "0:21:32", "throughput": 685.17, "total_tokens": 10321296} {"current_steps": 36845, "total_steps": 40000, "loss": 0.0, "lr": 7.64080338465134e-07, "epoch": 409.3888888888889, "percentage": 92.11, "elapsed_time": "4:11:05", "remaining_time": "0:21:30", "throughput": 685.17, "total_tokens": 10322704} {"current_steps": 36850, "total_steps": 40000, "loss": 0.0, "lr": 7.616735754173043e-07, "epoch": 409.44444444444446, "percentage": 92.12, "elapsed_time": "4:11:07", "remaining_time": "0:21:28", "throughput": 685.17, "total_tokens": 10324064} {"current_steps": 36855, "total_steps": 40000, "loss": 0.0, "lr": 7.592705502240005e-07, "epoch": 409.5, "percentage": 92.14, "elapsed_time": "4:11:09", "remaining_time": "0:21:25", "throughput": 685.17, "total_tokens": 10325456} {"current_steps": 36860, "total_steps": 40000, "loss": 0.0, "lr": 7.568712632558095e-07, "epoch": 409.55555555555554, "percentage": 92.15, "elapsed_time": "4:11:11", "remaining_time": "0:21:23", "throughput": 685.17, "total_tokens": 10326816} {"current_steps": 36865, "total_steps": 40000, "loss": 0.0, "lr": 7.544757148827297e-07, "epoch": 409.6111111111111, "percentage": 92.16, "elapsed_time": "4:11:13", "remaining_time": "0:21:21", "throughput": 685.17, "total_tokens": 10328240} {"current_steps": 36870, "total_steps": 40000, "loss": 0.0, "lr": 7.520839054741797e-07, "epoch": 409.6666666666667, "percentage": 92.17, "elapsed_time": "4:11:16", "remaining_time": "0:21:19", "throughput": 685.17, "total_tokens": 10329664} {"current_steps": 36875, "total_steps": 40000, "loss": 0.0, "lr": 7.496958353990113e-07, "epoch": 409.72222222222223, "percentage": 92.19, "elapsed_time": "4:11:18", "remaining_time": "0:21:17", "throughput": 685.17, "total_tokens": 10331056} {"current_steps": 36880, "total_steps": 40000, "loss": 0.0, "lr": 7.473115050254941e-07, "epoch": 409.77777777777777, "percentage": 92.2, "elapsed_time": "4:11:20", "remaining_time": "0:21:15", "throughput": 685.18, "total_tokens": 10332528} {"current_steps": 36885, "total_steps": 40000, "loss": 0.0, "lr": 7.449309147213173e-07, "epoch": 409.8333333333333, "percentage": 92.21, "elapsed_time": "4:11:22", "remaining_time": "0:21:13", "throughput": 685.18, "total_tokens": 10333904} {"current_steps": 36890, "total_steps": 40000, "loss": 0.0, "lr": 7.425540648536067e-07, "epoch": 409.8888888888889, "percentage": 92.22, "elapsed_time": "4:11:24", "remaining_time": "0:21:11", "throughput": 685.18, "total_tokens": 10335280} {"current_steps": 36895, "total_steps": 40000, "loss": 0.0, "lr": 7.40180955788894e-07, "epoch": 409.94444444444446, "percentage": 92.24, "elapsed_time": "4:11:26", "remaining_time": "0:21:09", "throughput": 685.18, "total_tokens": 10336656} {"current_steps": 36900, "total_steps": 40000, "loss": 0.0, "lr": 7.378115878931474e-07, "epoch": 410.0, "percentage": 92.25, "elapsed_time": "4:11:28", "remaining_time": "0:21:07", "throughput": 685.17, "total_tokens": 10338112} {"current_steps": 36905, "total_steps": 40000, "loss": 0.0, "lr": 7.354459615317527e-07, "epoch": 410.05555555555554, "percentage": 92.26, "elapsed_time": "4:11:30", "remaining_time": "0:21:05", "throughput": 685.17, "total_tokens": 10339568} {"current_steps": 36910, "total_steps": 40000, "loss": 0.0, "lr": 7.33084077069518e-07, "epoch": 410.1111111111111, "percentage": 92.27, "elapsed_time": "4:11:32", "remaining_time": "0:21:03", "throughput": 685.17, "total_tokens": 10340992} {"current_steps": 36915, "total_steps": 40000, "loss": 0.0, "lr": 7.307259348706768e-07, "epoch": 410.1666666666667, "percentage": 92.29, "elapsed_time": "4:11:34", "remaining_time": "0:21:01", "throughput": 685.17, "total_tokens": 10342384} {"current_steps": 36920, "total_steps": 40000, "loss": 0.0, "lr": 7.283715352988801e-07, "epoch": 410.22222222222223, "percentage": 92.3, "elapsed_time": "4:11:36", "remaining_time": "0:20:59", "throughput": 685.17, "total_tokens": 10343776} {"current_steps": 36925, "total_steps": 40000, "loss": 0.0, "lr": 7.260208787172068e-07, "epoch": 410.27777777777777, "percentage": 92.31, "elapsed_time": "4:11:38", "remaining_time": "0:20:57", "throughput": 685.17, "total_tokens": 10345152} {"current_steps": 36930, "total_steps": 40000, "loss": 0.0, "lr": 7.23673965488167e-07, "epoch": 410.3333333333333, "percentage": 92.33, "elapsed_time": "4:11:40", "remaining_time": "0:20:55", "throughput": 685.17, "total_tokens": 10346576} {"current_steps": 36935, "total_steps": 40000, "loss": 0.0, "lr": 7.213307959736709e-07, "epoch": 410.3888888888889, "percentage": 92.34, "elapsed_time": "4:11:42", "remaining_time": "0:20:53", "throughput": 685.17, "total_tokens": 10347984} {"current_steps": 36940, "total_steps": 40000, "loss": 0.0, "lr": 7.189913705350715e-07, "epoch": 410.44444444444446, "percentage": 92.35, "elapsed_time": "4:11:44", "remaining_time": "0:20:51", "throughput": 685.17, "total_tokens": 10349392} {"current_steps": 36945, "total_steps": 40000, "loss": 0.0, "lr": 7.166556895331411e-07, "epoch": 410.5, "percentage": 92.36, "elapsed_time": "4:11:46", "remaining_time": "0:20:49", "throughput": 685.17, "total_tokens": 10350768} {"current_steps": 36950, "total_steps": 40000, "loss": 0.0, "lr": 7.143237533280639e-07, "epoch": 410.55555555555554, "percentage": 92.38, "elapsed_time": "4:11:48", "remaining_time": "0:20:47", "throughput": 685.17, "total_tokens": 10352112} {"current_steps": 36955, "total_steps": 40000, "loss": 0.0, "lr": 7.119955622794578e-07, "epoch": 410.6111111111111, "percentage": 92.39, "elapsed_time": "4:11:50", "remaining_time": "0:20:45", "throughput": 685.17, "total_tokens": 10353504} {"current_steps": 36960, "total_steps": 40000, "loss": 0.0, "lr": 7.096711167463577e-07, "epoch": 410.6666666666667, "percentage": 92.4, "elapsed_time": "4:11:52", "remaining_time": "0:20:43", "throughput": 685.17, "total_tokens": 10354912} {"current_steps": 36965, "total_steps": 40000, "loss": 0.0, "lr": 7.073504170872213e-07, "epoch": 410.72222222222223, "percentage": 92.41, "elapsed_time": "4:11:54", "remaining_time": "0:20:41", "throughput": 685.17, "total_tokens": 10356288} {"current_steps": 36970, "total_steps": 40000, "loss": 0.0, "lr": 7.05033463659932e-07, "epoch": 410.77777777777777, "percentage": 92.42, "elapsed_time": "4:11:56", "remaining_time": "0:20:38", "throughput": 685.17, "total_tokens": 10357712} {"current_steps": 36975, "total_steps": 40000, "loss": 0.0, "lr": 7.027202568217928e-07, "epoch": 410.8333333333333, "percentage": 92.44, "elapsed_time": "4:11:58", "remaining_time": "0:20:36", "throughput": 685.18, "total_tokens": 10359120} {"current_steps": 36980, "total_steps": 40000, "loss": 0.0, "lr": 7.004107969295293e-07, "epoch": 410.8888888888889, "percentage": 92.45, "elapsed_time": "4:12:00", "remaining_time": "0:20:34", "throughput": 685.18, "total_tokens": 10360528} {"current_steps": 36985, "total_steps": 40000, "loss": 0.0, "lr": 6.9810508433929e-07, "epoch": 410.94444444444446, "percentage": 92.46, "elapsed_time": "4:12:02", "remaining_time": "0:20:32", "throughput": 685.18, "total_tokens": 10361936} {"current_steps": 36990, "total_steps": 40000, "loss": 0.0, "lr": 6.958031194066406e-07, "epoch": 411.0, "percentage": 92.47, "elapsed_time": "4:12:05", "remaining_time": "0:20:30", "throughput": 685.17, "total_tokens": 10363344} {"current_steps": 36995, "total_steps": 40000, "loss": 0.0, "lr": 6.935049024865776e-07, "epoch": 411.05555555555554, "percentage": 92.49, "elapsed_time": "4:12:07", "remaining_time": "0:20:28", "throughput": 685.16, "total_tokens": 10364752} {"current_steps": 37000, "total_steps": 40000, "loss": 0.0, "lr": 6.912104339335118e-07, "epoch": 411.1111111111111, "percentage": 92.5, "elapsed_time": "4:12:09", "remaining_time": "0:20:26", "throughput": 685.16, "total_tokens": 10366160} {"current_steps": 37000, "total_steps": 40000, "eval_loss": 0.3407905697822571, "epoch": 411.1111111111111, "percentage": 92.5, "elapsed_time": "4:12:10", "remaining_time": "0:20:26", "throughput": 685.11, "total_tokens": 10366160} {"current_steps": 37005, "total_steps": 40000, "loss": 0.0, "lr": 6.889197141012799e-07, "epoch": 411.1666666666667, "percentage": 92.51, "elapsed_time": "4:12:14", "remaining_time": "0:20:24", "throughput": 685.04, "total_tokens": 10367568} {"current_steps": 37010, "total_steps": 40000, "loss": 0.0, "lr": 6.866327433431435e-07, "epoch": 411.22222222222223, "percentage": 92.53, "elapsed_time": "4:12:16", "remaining_time": "0:20:22", "throughput": 685.04, "total_tokens": 10368960} {"current_steps": 37015, "total_steps": 40000, "loss": 0.0, "lr": 6.843495220117735e-07, "epoch": 411.27777777777777, "percentage": 92.54, "elapsed_time": "4:12:18", "remaining_time": "0:20:20", "throughput": 685.04, "total_tokens": 10370336} {"current_steps": 37020, "total_steps": 40000, "loss": 0.0, "lr": 6.820700504592798e-07, "epoch": 411.3333333333333, "percentage": 92.55, "elapsed_time": "4:12:20", "remaining_time": "0:20:18", "throughput": 685.04, "total_tokens": 10371728} {"current_steps": 37025, "total_steps": 40000, "loss": 0.0, "lr": 6.797943290371839e-07, "epoch": 411.3888888888889, "percentage": 92.56, "elapsed_time": "4:12:22", "remaining_time": "0:20:16", "throughput": 685.04, "total_tokens": 10373136} {"current_steps": 37030, "total_steps": 40000, "loss": 0.0, "lr": 6.775223580964274e-07, "epoch": 411.44444444444446, "percentage": 92.58, "elapsed_time": "4:12:24", "remaining_time": "0:20:14", "throughput": 685.04, "total_tokens": 10374528} {"current_steps": 37035, "total_steps": 40000, "loss": 0.0, "lr": 6.7525413798738e-07, "epoch": 411.5, "percentage": 92.59, "elapsed_time": "4:12:26", "remaining_time": "0:20:12", "throughput": 685.04, "total_tokens": 10375936} {"current_steps": 37040, "total_steps": 40000, "loss": 0.0, "lr": 6.729896690598259e-07, "epoch": 411.55555555555554, "percentage": 92.6, "elapsed_time": "4:12:28", "remaining_time": "0:20:10", "throughput": 685.05, "total_tokens": 10377376} {"current_steps": 37045, "total_steps": 40000, "loss": 0.0, "lr": 6.707289516629772e-07, "epoch": 411.6111111111111, "percentage": 92.61, "elapsed_time": "4:12:30", "remaining_time": "0:20:08", "throughput": 685.05, "total_tokens": 10378752} {"current_steps": 37050, "total_steps": 40000, "loss": 0.0, "lr": 6.684719861454692e-07, "epoch": 411.6666666666667, "percentage": 92.62, "elapsed_time": "4:12:32", "remaining_time": "0:20:06", "throughput": 685.05, "total_tokens": 10380144} {"current_steps": 37055, "total_steps": 40000, "loss": 0.0, "lr": 6.662187728553481e-07, "epoch": 411.72222222222223, "percentage": 92.64, "elapsed_time": "4:12:34", "remaining_time": "0:20:04", "throughput": 685.05, "total_tokens": 10381568} {"current_steps": 37060, "total_steps": 40000, "loss": 0.0, "lr": 6.639693121400892e-07, "epoch": 411.77777777777777, "percentage": 92.65, "elapsed_time": "4:12:36", "remaining_time": "0:20:02", "throughput": 685.05, "total_tokens": 10382992} {"current_steps": 37065, "total_steps": 40000, "loss": 0.0, "lr": 6.617236043465868e-07, "epoch": 411.8333333333333, "percentage": 92.66, "elapsed_time": "4:12:38", "remaining_time": "0:20:00", "throughput": 685.05, "total_tokens": 10384416} {"current_steps": 37070, "total_steps": 40000, "loss": 0.0, "lr": 6.594816498211587e-07, "epoch": 411.8888888888889, "percentage": 92.67, "elapsed_time": "4:12:40", "remaining_time": "0:19:58", "throughput": 685.05, "total_tokens": 10385808} {"current_steps": 37075, "total_steps": 40000, "loss": 0.0, "lr": 6.572434489095447e-07, "epoch": 411.94444444444446, "percentage": 92.69, "elapsed_time": "4:12:42", "remaining_time": "0:19:56", "throughput": 685.06, "total_tokens": 10387216} {"current_steps": 37080, "total_steps": 40000, "loss": 0.0, "lr": 6.550090019568994e-07, "epoch": 412.0, "percentage": 92.7, "elapsed_time": "4:12:44", "remaining_time": "0:19:54", "throughput": 685.05, "total_tokens": 10388592} {"current_steps": 37085, "total_steps": 40000, "loss": 0.0, "lr": 6.527783093078027e-07, "epoch": 412.05555555555554, "percentage": 92.71, "elapsed_time": "4:12:47", "remaining_time": "0:19:52", "throughput": 685.04, "total_tokens": 10389984} {"current_steps": 37090, "total_steps": 40000, "loss": 0.0, "lr": 6.5055137130626e-07, "epoch": 412.1111111111111, "percentage": 92.73, "elapsed_time": "4:12:49", "remaining_time": "0:19:50", "throughput": 685.04, "total_tokens": 10391392} {"current_steps": 37095, "total_steps": 40000, "loss": 0.0, "lr": 6.483281882956854e-07, "epoch": 412.1666666666667, "percentage": 92.74, "elapsed_time": "4:12:51", "remaining_time": "0:19:48", "throughput": 685.04, "total_tokens": 10392784} {"current_steps": 37100, "total_steps": 40000, "loss": 0.0, "lr": 6.461087606189298e-07, "epoch": 412.22222222222223, "percentage": 92.75, "elapsed_time": "4:12:53", "remaining_time": "0:19:46", "throughput": 685.04, "total_tokens": 10394160} {"current_steps": 37105, "total_steps": 40000, "loss": 0.0, "lr": 6.438930886182554e-07, "epoch": 412.27777777777777, "percentage": 92.76, "elapsed_time": "4:12:55", "remaining_time": "0:19:43", "throughput": 685.04, "total_tokens": 10395568} {"current_steps": 37110, "total_steps": 40000, "loss": 0.0, "lr": 6.416811726353417e-07, "epoch": 412.3333333333333, "percentage": 92.77, "elapsed_time": "4:12:57", "remaining_time": "0:19:41", "throughput": 685.04, "total_tokens": 10397008} {"current_steps": 37115, "total_steps": 40000, "loss": 0.0, "lr": 6.394730130112991e-07, "epoch": 412.3888888888889, "percentage": 92.79, "elapsed_time": "4:12:59", "remaining_time": "0:19:39", "throughput": 685.05, "total_tokens": 10398464} {"current_steps": 37120, "total_steps": 40000, "loss": 0.0, "lr": 6.372686100866471e-07, "epoch": 412.44444444444446, "percentage": 92.8, "elapsed_time": "4:13:01", "remaining_time": "0:19:37", "throughput": 685.04, "total_tokens": 10399824} {"current_steps": 37125, "total_steps": 40000, "loss": 0.0, "lr": 6.350679642013413e-07, "epoch": 412.5, "percentage": 92.81, "elapsed_time": "4:13:03", "remaining_time": "0:19:35", "throughput": 685.04, "total_tokens": 10401216} {"current_steps": 37130, "total_steps": 40000, "loss": 0.0, "lr": 6.328710756947437e-07, "epoch": 412.55555555555554, "percentage": 92.83, "elapsed_time": "4:13:05", "remaining_time": "0:19:33", "throughput": 685.04, "total_tokens": 10402624} {"current_steps": 37135, "total_steps": 40000, "loss": 0.0, "lr": 6.306779449056416e-07, "epoch": 412.6111111111111, "percentage": 92.84, "elapsed_time": "4:13:07", "remaining_time": "0:19:31", "throughput": 685.05, "total_tokens": 10404016} {"current_steps": 37140, "total_steps": 40000, "loss": 0.0, "lr": 6.284885721722422e-07, "epoch": 412.6666666666667, "percentage": 92.85, "elapsed_time": "4:13:09", "remaining_time": "0:19:29", "throughput": 685.05, "total_tokens": 10405408} {"current_steps": 37145, "total_steps": 40000, "loss": 0.0, "lr": 6.26302957832181e-07, "epoch": 412.72222222222223, "percentage": 92.86, "elapsed_time": "4:13:11", "remaining_time": "0:19:27", "throughput": 685.05, "total_tokens": 10406800} {"current_steps": 37150, "total_steps": 40000, "loss": 0.0, "lr": 6.241211022224997e-07, "epoch": 412.77777777777777, "percentage": 92.88, "elapsed_time": "4:13:13", "remaining_time": "0:19:25", "throughput": 685.05, "total_tokens": 10408176} {"current_steps": 37155, "total_steps": 40000, "loss": 0.0, "lr": 6.219430056796732e-07, "epoch": 412.8333333333333, "percentage": 92.89, "elapsed_time": "4:13:15", "remaining_time": "0:19:23", "throughput": 685.05, "total_tokens": 10409584} {"current_steps": 37160, "total_steps": 40000, "loss": 0.0, "lr": 6.19768668539586e-07, "epoch": 412.8888888888889, "percentage": 92.9, "elapsed_time": "4:13:17", "remaining_time": "0:19:21", "throughput": 685.05, "total_tokens": 10410976} {"current_steps": 37165, "total_steps": 40000, "loss": 0.0, "lr": 6.175980911375528e-07, "epoch": 412.94444444444446, "percentage": 92.91, "elapsed_time": "4:13:19", "remaining_time": "0:19:19", "throughput": 685.05, "total_tokens": 10412464} {"current_steps": 37170, "total_steps": 40000, "loss": 0.0, "lr": 6.154312738083034e-07, "epoch": 413.0, "percentage": 92.92, "elapsed_time": "4:13:21", "remaining_time": "0:19:17", "throughput": 685.04, "total_tokens": 10413840} {"current_steps": 37175, "total_steps": 40000, "loss": 0.0, "lr": 6.132682168859843e-07, "epoch": 413.05555555555554, "percentage": 92.94, "elapsed_time": "4:13:23", "remaining_time": "0:19:15", "throughput": 685.03, "total_tokens": 10415232} {"current_steps": 37180, "total_steps": 40000, "loss": 0.0, "lr": 6.111089207041704e-07, "epoch": 413.1111111111111, "percentage": 92.95, "elapsed_time": "4:13:26", "remaining_time": "0:19:13", "throughput": 685.03, "total_tokens": 10416576} {"current_steps": 37185, "total_steps": 40000, "loss": 0.0, "lr": 6.089533855958507e-07, "epoch": 413.1666666666667, "percentage": 92.96, "elapsed_time": "4:13:28", "remaining_time": "0:19:11", "throughput": 685.03, "total_tokens": 10417952} {"current_steps": 37190, "total_steps": 40000, "loss": 0.0, "lr": 6.068016118934372e-07, "epoch": 413.22222222222223, "percentage": 92.97, "elapsed_time": "4:13:30", "remaining_time": "0:19:09", "throughput": 685.03, "total_tokens": 10419424} {"current_steps": 37195, "total_steps": 40000, "loss": 0.0, "lr": 6.04653599928759e-07, "epoch": 413.27777777777777, "percentage": 92.99, "elapsed_time": "4:13:32", "remaining_time": "0:19:07", "throughput": 685.03, "total_tokens": 10420800} {"current_steps": 37200, "total_steps": 40000, "loss": 0.0, "lr": 6.025093500330675e-07, "epoch": 413.3333333333333, "percentage": 93.0, "elapsed_time": "4:13:34", "remaining_time": "0:19:05", "throughput": 685.03, "total_tokens": 10422192} {"current_steps": 37200, "total_steps": 40000, "eval_loss": 0.352642685174942, "epoch": 413.3333333333333, "percentage": 93.0, "elapsed_time": "4:13:35", "remaining_time": "0:19:05", "throughput": 684.98, "total_tokens": 10422192} {"current_steps": 37205, "total_steps": 40000, "loss": 0.0, "lr": 6.003688625370291e-07, "epoch": 413.3888888888889, "percentage": 93.01, "elapsed_time": "4:13:38", "remaining_time": "0:19:03", "throughput": 684.91, "total_tokens": 10423584} {"current_steps": 37210, "total_steps": 40000, "loss": 0.0, "lr": 5.982321377707406e-07, "epoch": 413.44444444444446, "percentage": 93.03, "elapsed_time": "4:13:40", "remaining_time": "0:19:01", "throughput": 684.91, "total_tokens": 10425008} {"current_steps": 37215, "total_steps": 40000, "loss": 0.0, "lr": 5.96099176063708e-07, "epoch": 413.5, "percentage": 93.04, "elapsed_time": "4:13:42", "remaining_time": "0:18:59", "throughput": 684.92, "total_tokens": 10426464} {"current_steps": 37220, "total_steps": 40000, "loss": 0.0, "lr": 5.93969977744857e-07, "epoch": 413.55555555555554, "percentage": 93.05, "elapsed_time": "4:13:44", "remaining_time": "0:18:57", "throughput": 684.92, "total_tokens": 10427856} {"current_steps": 37225, "total_steps": 40000, "loss": 0.0, "lr": 5.918445431425445e-07, "epoch": 413.6111111111111, "percentage": 93.06, "elapsed_time": "4:13:47", "remaining_time": "0:18:55", "throughput": 684.92, "total_tokens": 10429248} {"current_steps": 37230, "total_steps": 40000, "loss": 0.0, "lr": 5.897228725845333e-07, "epoch": 413.6666666666667, "percentage": 93.08, "elapsed_time": "4:13:49", "remaining_time": "0:18:53", "throughput": 684.92, "total_tokens": 10430672} {"current_steps": 37235, "total_steps": 40000, "loss": 0.0, "lr": 5.876049663980171e-07, "epoch": 413.72222222222223, "percentage": 93.09, "elapsed_time": "4:13:51", "remaining_time": "0:18:51", "throughput": 684.92, "total_tokens": 10432064} {"current_steps": 37240, "total_steps": 40000, "loss": 0.0, "lr": 5.854908249095959e-07, "epoch": 413.77777777777777, "percentage": 93.1, "elapsed_time": "4:13:53", "remaining_time": "0:18:48", "throughput": 684.92, "total_tokens": 10433488} {"current_steps": 37245, "total_steps": 40000, "loss": 0.0, "lr": 5.833804484453031e-07, "epoch": 413.8333333333333, "percentage": 93.11, "elapsed_time": "4:13:55", "remaining_time": "0:18:46", "throughput": 684.92, "total_tokens": 10434912} {"current_steps": 37250, "total_steps": 40000, "loss": 0.0, "lr": 5.81273837330587e-07, "epoch": 413.8888888888889, "percentage": 93.12, "elapsed_time": "4:13:57", "remaining_time": "0:18:44", "throughput": 684.93, "total_tokens": 10436336} {"current_steps": 37255, "total_steps": 40000, "loss": 0.0, "lr": 5.791709918903071e-07, "epoch": 413.94444444444446, "percentage": 93.14, "elapsed_time": "4:13:59", "remaining_time": "0:18:42", "throughput": 684.93, "total_tokens": 10437744} {"current_steps": 37260, "total_steps": 40000, "loss": 0.0, "lr": 5.770719124487483e-07, "epoch": 414.0, "percentage": 93.15, "elapsed_time": "4:14:01", "remaining_time": "0:18:40", "throughput": 684.92, "total_tokens": 10439136} {"current_steps": 37265, "total_steps": 40000, "loss": 0.0, "lr": 5.749765993296241e-07, "epoch": 414.05555555555554, "percentage": 93.16, "elapsed_time": "4:14:03", "remaining_time": "0:18:38", "throughput": 684.91, "total_tokens": 10440576} {"current_steps": 37270, "total_steps": 40000, "loss": 0.0, "lr": 5.728850528560509e-07, "epoch": 414.1111111111111, "percentage": 93.17, "elapsed_time": "4:14:05", "remaining_time": "0:18:36", "throughput": 684.91, "total_tokens": 10441984} {"current_steps": 37275, "total_steps": 40000, "loss": 0.0, "lr": 5.707972733505707e-07, "epoch": 414.1666666666667, "percentage": 93.19, "elapsed_time": "4:14:07", "remaining_time": "0:18:34", "throughput": 684.91, "total_tokens": 10443344} {"current_steps": 37280, "total_steps": 40000, "loss": 0.0, "lr": 5.687132611351509e-07, "epoch": 414.22222222222223, "percentage": 93.2, "elapsed_time": "4:14:09", "remaining_time": "0:18:32", "throughput": 684.91, "total_tokens": 10444720} {"current_steps": 37285, "total_steps": 40000, "loss": 0.0, "lr": 5.666330165311651e-07, "epoch": 414.27777777777777, "percentage": 93.21, "elapsed_time": "4:14:11", "remaining_time": "0:18:30", "throughput": 684.91, "total_tokens": 10446096} {"current_steps": 37290, "total_steps": 40000, "loss": 0.0, "lr": 5.645565398594204e-07, "epoch": 414.3333333333333, "percentage": 93.23, "elapsed_time": "4:14:13", "remaining_time": "0:18:28", "throughput": 684.91, "total_tokens": 10447504} {"current_steps": 37295, "total_steps": 40000, "loss": 0.0, "lr": 5.624838314401304e-07, "epoch": 414.3888888888889, "percentage": 93.24, "elapsed_time": "4:14:15", "remaining_time": "0:18:26", "throughput": 684.91, "total_tokens": 10448896} {"current_steps": 37300, "total_steps": 40000, "loss": 0.0, "lr": 5.604148915929336e-07, "epoch": 414.44444444444446, "percentage": 93.25, "elapsed_time": "4:14:17", "remaining_time": "0:18:24", "throughput": 684.91, "total_tokens": 10450288} {"current_steps": 37305, "total_steps": 40000, "loss": 0.0, "lr": 5.583497206368887e-07, "epoch": 414.5, "percentage": 93.26, "elapsed_time": "4:14:19", "remaining_time": "0:18:22", "throughput": 684.91, "total_tokens": 10451648} {"current_steps": 37310, "total_steps": 40000, "loss": 0.0, "lr": 5.562883188904688e-07, "epoch": 414.55555555555554, "percentage": 93.27, "elapsed_time": "4:14:21", "remaining_time": "0:18:20", "throughput": 684.91, "total_tokens": 10453088} {"current_steps": 37315, "total_steps": 40000, "loss": 0.0, "lr": 5.542306866715724e-07, "epoch": 414.6111111111111, "percentage": 93.29, "elapsed_time": "4:14:23", "remaining_time": "0:18:18", "throughput": 684.91, "total_tokens": 10454480} {"current_steps": 37320, "total_steps": 40000, "loss": 0.0, "lr": 5.52176824297504e-07, "epoch": 414.6666666666667, "percentage": 93.3, "elapsed_time": "4:14:25", "remaining_time": "0:18:16", "throughput": 684.92, "total_tokens": 10455872} {"current_steps": 37325, "total_steps": 40000, "loss": 0.0, "lr": 5.501267320850018e-07, "epoch": 414.72222222222223, "percentage": 93.31, "elapsed_time": "4:14:27", "remaining_time": "0:18:14", "throughput": 684.92, "total_tokens": 10457328} {"current_steps": 37330, "total_steps": 40000, "loss": 0.0, "lr": 5.480804103502157e-07, "epoch": 414.77777777777777, "percentage": 93.33, "elapsed_time": "4:14:29", "remaining_time": "0:18:12", "throughput": 684.92, "total_tokens": 10458704} {"current_steps": 37335, "total_steps": 40000, "loss": 0.0, "lr": 5.460378594087101e-07, "epoch": 414.8333333333333, "percentage": 93.34, "elapsed_time": "4:14:32", "remaining_time": "0:18:10", "throughput": 684.92, "total_tokens": 10460112} {"current_steps": 37340, "total_steps": 40000, "loss": 0.0, "lr": 5.439990795754773e-07, "epoch": 414.8888888888889, "percentage": 93.35, "elapsed_time": "4:14:34", "remaining_time": "0:18:08", "throughput": 684.92, "total_tokens": 10461520} {"current_steps": 37345, "total_steps": 40000, "loss": 0.0, "lr": 5.419640711649188e-07, "epoch": 414.94444444444446, "percentage": 93.36, "elapsed_time": "4:14:36", "remaining_time": "0:18:06", "throughput": 684.92, "total_tokens": 10462944} {"current_steps": 37350, "total_steps": 40000, "loss": 0.0, "lr": 5.399328344908583e-07, "epoch": 415.0, "percentage": 93.38, "elapsed_time": "4:14:38", "remaining_time": "0:18:03", "throughput": 684.92, "total_tokens": 10464384} {"current_steps": 37355, "total_steps": 40000, "loss": 0.0, "lr": 5.379053698665399e-07, "epoch": 415.05555555555554, "percentage": 93.39, "elapsed_time": "4:14:40", "remaining_time": "0:18:01", "throughput": 684.91, "total_tokens": 10465808} {"current_steps": 37360, "total_steps": 40000, "loss": 0.0, "lr": 5.358816776046216e-07, "epoch": 415.1111111111111, "percentage": 93.4, "elapsed_time": "4:14:42", "remaining_time": "0:17:59", "throughput": 684.91, "total_tokens": 10467200} {"current_steps": 37365, "total_steps": 40000, "loss": 0.0, "lr": 5.338617580171817e-07, "epoch": 415.1666666666667, "percentage": 93.41, "elapsed_time": "4:14:44", "remaining_time": "0:17:57", "throughput": 684.91, "total_tokens": 10468608} {"current_steps": 37370, "total_steps": 40000, "loss": 0.0, "lr": 5.318456114157239e-07, "epoch": 415.22222222222223, "percentage": 93.42, "elapsed_time": "4:14:46", "remaining_time": "0:17:55", "throughput": 684.91, "total_tokens": 10470016} {"current_steps": 37375, "total_steps": 40000, "loss": 0.0, "lr": 5.298332381111576e-07, "epoch": 415.27777777777777, "percentage": 93.44, "elapsed_time": "4:14:48", "remaining_time": "0:17:53", "throughput": 684.92, "total_tokens": 10471408} {"current_steps": 37380, "total_steps": 40000, "loss": 0.0, "lr": 5.27824638413818e-07, "epoch": 415.3333333333333, "percentage": 93.45, "elapsed_time": "4:14:50", "remaining_time": "0:17:51", "throughput": 684.91, "total_tokens": 10472800} {"current_steps": 37385, "total_steps": 40000, "loss": 0.0, "lr": 5.258198126334546e-07, "epoch": 415.3888888888889, "percentage": 93.46, "elapsed_time": "4:14:52", "remaining_time": "0:17:49", "throughput": 684.91, "total_tokens": 10474176} {"current_steps": 37390, "total_steps": 40000, "loss": 0.0, "lr": 5.238187610792367e-07, "epoch": 415.44444444444446, "percentage": 93.47, "elapsed_time": "4:14:54", "remaining_time": "0:17:47", "throughput": 684.91, "total_tokens": 10475536} {"current_steps": 37395, "total_steps": 40000, "loss": 0.0, "lr": 5.218214840597563e-07, "epoch": 415.5, "percentage": 93.49, "elapsed_time": "4:14:56", "remaining_time": "0:17:45", "throughput": 684.91, "total_tokens": 10476928} {"current_steps": 37400, "total_steps": 40000, "loss": 0.0, "lr": 5.198279818830115e-07, "epoch": 415.55555555555554, "percentage": 93.5, "elapsed_time": "4:14:58", "remaining_time": "0:17:43", "throughput": 684.92, "total_tokens": 10478368} {"current_steps": 37400, "total_steps": 40000, "eval_loss": 0.3385472893714905, "epoch": 415.55555555555554, "percentage": 93.5, "elapsed_time": "4:15:00", "remaining_time": "0:17:43", "throughput": 684.86, "total_tokens": 10478368} {"current_steps": 37405, "total_steps": 40000, "loss": 0.0, "lr": 5.178382548564287e-07, "epoch": 415.6111111111111, "percentage": 93.51, "elapsed_time": "4:15:03", "remaining_time": "0:17:41", "throughput": 684.79, "total_tokens": 10479744} {"current_steps": 37410, "total_steps": 40000, "loss": 0.0, "lr": 5.15852303286854e-07, "epoch": 415.6666666666667, "percentage": 93.53, "elapsed_time": "4:15:05", "remaining_time": "0:17:39", "throughput": 684.79, "total_tokens": 10481152} {"current_steps": 37415, "total_steps": 40000, "loss": 0.0, "lr": 5.138701274805396e-07, "epoch": 415.72222222222223, "percentage": 93.54, "elapsed_time": "4:15:07", "remaining_time": "0:17:37", "throughput": 684.8, "total_tokens": 10482576} {"current_steps": 37420, "total_steps": 40000, "loss": 0.0, "lr": 5.118917277431606e-07, "epoch": 415.77777777777777, "percentage": 93.55, "elapsed_time": "4:15:09", "remaining_time": "0:17:35", "throughput": 684.8, "total_tokens": 10483952} {"current_steps": 37425, "total_steps": 40000, "loss": 0.0, "lr": 5.099171043798145e-07, "epoch": 415.8333333333333, "percentage": 93.56, "elapsed_time": "4:15:11", "remaining_time": "0:17:33", "throughput": 684.81, "total_tokens": 10485344} {"current_steps": 37430, "total_steps": 40000, "loss": 0.0, "lr": 5.079462576950133e-07, "epoch": 415.8888888888889, "percentage": 93.58, "elapsed_time": "4:15:13", "remaining_time": "0:17:31", "throughput": 684.81, "total_tokens": 10486736} {"current_steps": 37435, "total_steps": 40000, "loss": 0.0, "lr": 5.059791879926862e-07, "epoch": 415.94444444444446, "percentage": 93.59, "elapsed_time": "4:15:15", "remaining_time": "0:17:29", "throughput": 684.81, "total_tokens": 10488128} {"current_steps": 37440, "total_steps": 40000, "loss": 0.0, "lr": 5.040158955761793e-07, "epoch": 416.0, "percentage": 93.6, "elapsed_time": "4:15:17", "remaining_time": "0:17:27", "throughput": 684.81, "total_tokens": 10489552} {"current_steps": 37445, "total_steps": 40000, "loss": 0.0, "lr": 5.020563807482559e-07, "epoch": 416.05555555555554, "percentage": 93.61, "elapsed_time": "4:15:19", "remaining_time": "0:17:25", "throughput": 684.81, "total_tokens": 10490992} {"current_steps": 37450, "total_steps": 40000, "loss": 0.0, "lr": 5.001006438110995e-07, "epoch": 416.1111111111111, "percentage": 93.62, "elapsed_time": "4:15:21", "remaining_time": "0:17:23", "throughput": 684.81, "total_tokens": 10492368} {"current_steps": 37455, "total_steps": 40000, "loss": 0.0, "lr": 4.981486850663075e-07, "epoch": 416.1666666666667, "percentage": 93.64, "elapsed_time": "4:15:23", "remaining_time": "0:17:21", "throughput": 684.81, "total_tokens": 10493728} {"current_steps": 37460, "total_steps": 40000, "loss": 0.0, "lr": 4.962005048149005e-07, "epoch": 416.22222222222223, "percentage": 93.65, "elapsed_time": "4:15:25", "remaining_time": "0:17:19", "throughput": 684.82, "total_tokens": 10495088} {"current_steps": 37465, "total_steps": 40000, "loss": 0.0, "lr": 4.942561033573073e-07, "epoch": 416.27777777777777, "percentage": 93.66, "elapsed_time": "4:15:27", "remaining_time": "0:17:17", "throughput": 684.82, "total_tokens": 10496448} {"current_steps": 37470, "total_steps": 40000, "loss": 0.0, "lr": 4.923154809933827e-07, "epoch": 416.3333333333333, "percentage": 93.67, "elapsed_time": "4:15:29", "remaining_time": "0:17:15", "throughput": 684.82, "total_tokens": 10497856} {"current_steps": 37475, "total_steps": 40000, "loss": 0.0, "lr": 4.903786380223957e-07, "epoch": 416.3888888888889, "percentage": 93.69, "elapsed_time": "4:15:31", "remaining_time": "0:17:12", "throughput": 684.83, "total_tokens": 10499280} {"current_steps": 37480, "total_steps": 40000, "loss": 0.0, "lr": 4.884455747430266e-07, "epoch": 416.44444444444446, "percentage": 93.7, "elapsed_time": "4:15:33", "remaining_time": "0:17:10", "throughput": 684.83, "total_tokens": 10500704} {"current_steps": 37485, "total_steps": 40000, "loss": 0.0, "lr": 4.865162914533816e-07, "epoch": 416.5, "percentage": 93.71, "elapsed_time": "4:15:35", "remaining_time": "0:17:08", "throughput": 684.84, "total_tokens": 10502096} {"current_steps": 37490, "total_steps": 40000, "loss": 0.0, "lr": 4.845907884509809e-07, "epoch": 416.55555555555554, "percentage": 93.73, "elapsed_time": "4:15:37", "remaining_time": "0:17:06", "throughput": 684.84, "total_tokens": 10503440} {"current_steps": 37495, "total_steps": 40000, "loss": 0.0, "lr": 4.82669066032762e-07, "epoch": 416.6111111111111, "percentage": 93.74, "elapsed_time": "4:15:38", "remaining_time": "0:17:04", "throughput": 684.85, "total_tokens": 10504848} {"current_steps": 37500, "total_steps": 40000, "loss": 0.0, "lr": 4.807511244950768e-07, "epoch": 416.6666666666667, "percentage": 93.75, "elapsed_time": "4:15:40", "remaining_time": "0:17:02", "throughput": 684.85, "total_tokens": 10506256} {"current_steps": 37505, "total_steps": 40000, "loss": 0.0, "lr": 4.788369641336943e-07, "epoch": 416.72222222222223, "percentage": 93.76, "elapsed_time": "4:15:42", "remaining_time": "0:17:00", "throughput": 684.85, "total_tokens": 10507632} {"current_steps": 37510, "total_steps": 40000, "loss": 0.0, "lr": 4.769265852438032e-07, "epoch": 416.77777777777777, "percentage": 93.77, "elapsed_time": "4:15:44", "remaining_time": "0:16:58", "throughput": 684.86, "total_tokens": 10509056} {"current_steps": 37515, "total_steps": 40000, "loss": 0.0, "lr": 4.750199881200124e-07, "epoch": 416.8333333333333, "percentage": 93.79, "elapsed_time": "4:15:46", "remaining_time": "0:16:56", "throughput": 684.87, "total_tokens": 10510464} {"current_steps": 37520, "total_steps": 40000, "loss": 0.0, "lr": 4.7311717305633664e-07, "epoch": 416.8888888888889, "percentage": 93.8, "elapsed_time": "4:15:48", "remaining_time": "0:16:54", "throughput": 684.87, "total_tokens": 10511872} {"current_steps": 37525, "total_steps": 40000, "loss": 0.0, "lr": 4.7121814034621623e-07, "epoch": 416.94444444444446, "percentage": 93.81, "elapsed_time": "4:15:50", "remaining_time": "0:16:52", "throughput": 684.88, "total_tokens": 10513296} {"current_steps": 37530, "total_steps": 40000, "loss": 0.0, "lr": 4.693228902825114e-07, "epoch": 417.0, "percentage": 93.83, "elapsed_time": "4:15:52", "remaining_time": "0:16:50", "throughput": 684.88, "total_tokens": 10514720} {"current_steps": 37535, "total_steps": 40000, "loss": 0.0, "lr": 4.6743142315748277e-07, "epoch": 417.05555555555554, "percentage": 93.84, "elapsed_time": "4:15:54", "remaining_time": "0:16:48", "throughput": 684.86, "total_tokens": 10516048} {"current_steps": 37540, "total_steps": 40000, "loss": 0.0, "lr": 4.655437392628276e-07, "epoch": 417.1111111111111, "percentage": 93.85, "elapsed_time": "4:15:56", "remaining_time": "0:16:46", "throughput": 684.87, "total_tokens": 10517424} {"current_steps": 37545, "total_steps": 40000, "loss": 0.0, "lr": 4.636598388896463e-07, "epoch": 417.1666666666667, "percentage": 93.86, "elapsed_time": "4:15:58", "remaining_time": "0:16:44", "throughput": 684.87, "total_tokens": 10518800} {"current_steps": 37550, "total_steps": 40000, "loss": 0.0, "lr": 4.6177972232845925e-07, "epoch": 417.22222222222223, "percentage": 93.88, "elapsed_time": "4:16:00", "remaining_time": "0:16:42", "throughput": 684.87, "total_tokens": 10520160} {"current_steps": 37555, "total_steps": 40000, "loss": 0.0, "lr": 4.5990338986920953e-07, "epoch": 417.27777777777777, "percentage": 93.89, "elapsed_time": "4:16:02", "remaining_time": "0:16:40", "throughput": 684.88, "total_tokens": 10521584} {"current_steps": 37560, "total_steps": 40000, "loss": 0.0, "lr": 4.5803084180124633e-07, "epoch": 417.3333333333333, "percentage": 93.9, "elapsed_time": "4:16:04", "remaining_time": "0:16:38", "throughput": 684.88, "total_tokens": 10522992} {"current_steps": 37565, "total_steps": 40000, "loss": 0.0, "lr": 4.561620784133386e-07, "epoch": 417.3888888888889, "percentage": 93.91, "elapsed_time": "4:16:06", "remaining_time": "0:16:36", "throughput": 684.89, "total_tokens": 10524368} {"current_steps": 37570, "total_steps": 40000, "loss": 0.0, "lr": 4.5429709999367796e-07, "epoch": 417.44444444444446, "percentage": 93.92, "elapsed_time": "4:16:08", "remaining_time": "0:16:34", "throughput": 684.89, "total_tokens": 10525792} {"current_steps": 37575, "total_steps": 40000, "loss": 0.0, "lr": 4.5243590682986223e-07, "epoch": 417.5, "percentage": 93.94, "elapsed_time": "4:16:10", "remaining_time": "0:16:31", "throughput": 684.9, "total_tokens": 10527184} {"current_steps": 37580, "total_steps": 40000, "loss": 0.0, "lr": 4.5057849920891735e-07, "epoch": 417.55555555555554, "percentage": 93.95, "elapsed_time": "4:16:12", "remaining_time": "0:16:29", "throughput": 684.91, "total_tokens": 10528656} {"current_steps": 37585, "total_steps": 40000, "loss": 0.0, "lr": 4.487248774172698e-07, "epoch": 417.6111111111111, "percentage": 93.96, "elapsed_time": "4:16:14", "remaining_time": "0:16:27", "throughput": 684.91, "total_tokens": 10530048} {"current_steps": 37590, "total_steps": 40000, "loss": 0.0, "lr": 4.4687504174077965e-07, "epoch": 417.6666666666667, "percentage": 93.97, "elapsed_time": "4:16:16", "remaining_time": "0:16:25", "throughput": 684.92, "total_tokens": 10531472} {"current_steps": 37595, "total_steps": 40000, "loss": 0.0, "lr": 4.450289924647133e-07, "epoch": 417.72222222222223, "percentage": 93.99, "elapsed_time": "4:16:18", "remaining_time": "0:16:23", "throughput": 684.92, "total_tokens": 10532864} {"current_steps": 37600, "total_steps": 40000, "loss": 0.0, "lr": 4.431867298737513e-07, "epoch": 417.77777777777777, "percentage": 94.0, "elapsed_time": "4:16:20", "remaining_time": "0:16:21", "throughput": 684.92, "total_tokens": 10534240} {"current_steps": 37600, "total_steps": 40000, "eval_loss": 0.3754492700099945, "epoch": 417.77777777777777, "percentage": 94.0, "elapsed_time": "4:16:21", "remaining_time": "0:16:21", "throughput": 684.87, "total_tokens": 10534240} {"current_steps": 37605, "total_steps": 40000, "loss": 0.0, "lr": 4.41348254251997e-07, "epoch": 417.8333333333333, "percentage": 94.01, "elapsed_time": "4:16:24", "remaining_time": "0:16:19", "throughput": 684.81, "total_tokens": 10535680} {"current_steps": 37610, "total_steps": 40000, "loss": 0.0, "lr": 4.395135658829652e-07, "epoch": 417.8888888888889, "percentage": 94.03, "elapsed_time": "4:16:26", "remaining_time": "0:16:17", "throughput": 684.81, "total_tokens": 10537040} {"current_steps": 37615, "total_steps": 40000, "loss": 0.0, "lr": 4.376826650495852e-07, "epoch": 417.94444444444446, "percentage": 94.04, "elapsed_time": "4:16:28", "remaining_time": "0:16:15", "throughput": 684.82, "total_tokens": 10538496} {"current_steps": 37620, "total_steps": 40000, "loss": 0.0, "lr": 4.358555520342117e-07, "epoch": 418.0, "percentage": 94.05, "elapsed_time": "4:16:30", "remaining_time": "0:16:13", "throughput": 684.81, "total_tokens": 10539888} {"current_steps": 37625, "total_steps": 40000, "loss": 0.0, "lr": 4.3403222711860257e-07, "epoch": 418.05555555555554, "percentage": 94.06, "elapsed_time": "4:16:33", "remaining_time": "0:16:11", "throughput": 684.81, "total_tokens": 10541312} {"current_steps": 37630, "total_steps": 40000, "loss": 0.0, "lr": 4.3221269058394133e-07, "epoch": 418.1111111111111, "percentage": 94.08, "elapsed_time": "4:16:35", "remaining_time": "0:16:09", "throughput": 684.81, "total_tokens": 10542672} {"current_steps": 37635, "total_steps": 40000, "loss": 0.0, "lr": 4.303969427108173e-07, "epoch": 418.1666666666667, "percentage": 94.09, "elapsed_time": "4:16:36", "remaining_time": "0:16:07", "throughput": 684.82, "total_tokens": 10544112} {"current_steps": 37640, "total_steps": 40000, "loss": 0.0, "lr": 4.2858498377924825e-07, "epoch": 418.22222222222223, "percentage": 94.1, "elapsed_time": "4:16:38", "remaining_time": "0:16:05", "throughput": 684.82, "total_tokens": 10545472} {"current_steps": 37645, "total_steps": 40000, "loss": 0.0, "lr": 4.267768140686579e-07, "epoch": 418.27777777777777, "percentage": 94.11, "elapsed_time": "4:16:40", "remaining_time": "0:16:03", "throughput": 684.82, "total_tokens": 10546848} {"current_steps": 37650, "total_steps": 40000, "loss": 0.0, "lr": 4.2497243385788975e-07, "epoch": 418.3333333333333, "percentage": 94.12, "elapsed_time": "4:16:42", "remaining_time": "0:16:01", "throughput": 684.83, "total_tokens": 10548224} {"current_steps": 37655, "total_steps": 40000, "loss": 0.0, "lr": 4.231718434251991e-07, "epoch": 418.3888888888889, "percentage": 94.14, "elapsed_time": "4:16:44", "remaining_time": "0:15:59", "throughput": 684.83, "total_tokens": 10549584} {"current_steps": 37660, "total_steps": 40000, "loss": 0.0, "lr": 4.213750430482666e-07, "epoch": 418.44444444444446, "percentage": 94.15, "elapsed_time": "4:16:46", "remaining_time": "0:15:57", "throughput": 684.83, "total_tokens": 10550960} {"current_steps": 37665, "total_steps": 40000, "loss": 0.0, "lr": 4.1958203300417054e-07, "epoch": 418.5, "percentage": 94.16, "elapsed_time": "4:16:48", "remaining_time": "0:15:55", "throughput": 684.84, "total_tokens": 10552416} {"current_steps": 37670, "total_steps": 40000, "loss": 0.0, "lr": 4.177928135694259e-07, "epoch": 418.55555555555554, "percentage": 94.17, "elapsed_time": "4:16:50", "remaining_time": "0:15:53", "throughput": 684.84, "total_tokens": 10553808} {"current_steps": 37675, "total_steps": 40000, "loss": 0.0, "lr": 4.1600738501994807e-07, "epoch": 418.6111111111111, "percentage": 94.19, "elapsed_time": "4:16:52", "remaining_time": "0:15:51", "throughput": 684.85, "total_tokens": 10555232} {"current_steps": 37680, "total_steps": 40000, "loss": 0.0, "lr": 4.1422574763107237e-07, "epoch": 418.6666666666667, "percentage": 94.2, "elapsed_time": "4:16:54", "remaining_time": "0:15:49", "throughput": 684.85, "total_tokens": 10556576} {"current_steps": 37685, "total_steps": 40000, "loss": 0.0, "lr": 4.124479016775512e-07, "epoch": 418.72222222222223, "percentage": 94.21, "elapsed_time": "4:16:56", "remaining_time": "0:15:47", "throughput": 684.86, "total_tokens": 10557984} {"current_steps": 37690, "total_steps": 40000, "loss": 0.0, "lr": 4.106738474335514e-07, "epoch": 418.77777777777777, "percentage": 94.23, "elapsed_time": "4:16:58", "remaining_time": "0:15:44", "throughput": 684.86, "total_tokens": 10559376} {"current_steps": 37695, "total_steps": 40000, "loss": 0.0, "lr": 4.089035851726486e-07, "epoch": 418.8333333333333, "percentage": 94.24, "elapsed_time": "4:17:00", "remaining_time": "0:15:42", "throughput": 684.86, "total_tokens": 10560768} {"current_steps": 37700, "total_steps": 40000, "loss": 0.0, "lr": 4.0713711516784937e-07, "epoch": 418.8888888888889, "percentage": 94.25, "elapsed_time": "4:17:02", "remaining_time": "0:15:40", "throughput": 684.87, "total_tokens": 10562160} {"current_steps": 37705, "total_steps": 40000, "loss": 0.0, "lr": 4.05374437691558e-07, "epoch": 418.94444444444446, "percentage": 94.26, "elapsed_time": "4:17:04", "remaining_time": "0:15:38", "throughput": 684.87, "total_tokens": 10563584} {"current_steps": 37710, "total_steps": 40000, "loss": 0.0, "lr": 4.036155530156044e-07, "epoch": 419.0, "percentage": 94.27, "elapsed_time": "4:17:06", "remaining_time": "0:15:36", "throughput": 684.87, "total_tokens": 10564960} {"current_steps": 37715, "total_steps": 40000, "loss": 0.0, "lr": 4.018604614112298e-07, "epoch": 419.05555555555554, "percentage": 94.29, "elapsed_time": "4:17:08", "remaining_time": "0:15:34", "throughput": 684.86, "total_tokens": 10566336} {"current_steps": 37720, "total_steps": 40000, "loss": 0.0, "lr": 4.0010916314908996e-07, "epoch": 419.1111111111111, "percentage": 94.3, "elapsed_time": "4:17:10", "remaining_time": "0:15:32", "throughput": 684.87, "total_tokens": 10567760} {"current_steps": 37725, "total_steps": 40000, "loss": 0.0, "lr": 3.983616584992578e-07, "epoch": 419.1666666666667, "percentage": 94.31, "elapsed_time": "4:17:12", "remaining_time": "0:15:30", "throughput": 684.87, "total_tokens": 10569152} {"current_steps": 37730, "total_steps": 40000, "loss": 0.0, "lr": 3.9661794773122595e-07, "epoch": 419.22222222222223, "percentage": 94.33, "elapsed_time": "4:17:14", "remaining_time": "0:15:28", "throughput": 684.88, "total_tokens": 10570528} {"current_steps": 37735, "total_steps": 40000, "loss": 0.0, "lr": 3.9487803111388777e-07, "epoch": 419.27777777777777, "percentage": 94.34, "elapsed_time": "4:17:16", "remaining_time": "0:15:26", "throughput": 684.88, "total_tokens": 10571936} {"current_steps": 37740, "total_steps": 40000, "loss": 0.0, "lr": 3.9314190891556747e-07, "epoch": 419.3333333333333, "percentage": 94.35, "elapsed_time": "4:17:18", "remaining_time": "0:15:24", "throughput": 684.89, "total_tokens": 10573360} {"current_steps": 37745, "total_steps": 40000, "loss": 0.0, "lr": 3.914095814039925e-07, "epoch": 419.3888888888889, "percentage": 94.36, "elapsed_time": "4:17:20", "remaining_time": "0:15:22", "throughput": 684.89, "total_tokens": 10574736} {"current_steps": 37750, "total_steps": 40000, "loss": 0.0, "lr": 3.896810488463104e-07, "epoch": 419.44444444444446, "percentage": 94.38, "elapsed_time": "4:17:22", "remaining_time": "0:15:20", "throughput": 684.9, "total_tokens": 10576176} {"current_steps": 37755, "total_steps": 40000, "loss": 0.0, "lr": 3.8795631150908565e-07, "epoch": 419.5, "percentage": 94.39, "elapsed_time": "4:17:23", "remaining_time": "0:15:18", "throughput": 684.9, "total_tokens": 10577600} {"current_steps": 37760, "total_steps": 40000, "loss": 0.0, "lr": 3.862353696582888e-07, "epoch": 419.55555555555554, "percentage": 94.4, "elapsed_time": "4:17:25", "remaining_time": "0:15:16", "throughput": 684.91, "total_tokens": 10579024} {"current_steps": 37765, "total_steps": 40000, "loss": 0.0, "lr": 3.8451822355931313e-07, "epoch": 419.6111111111111, "percentage": 94.41, "elapsed_time": "4:17:27", "remaining_time": "0:15:14", "throughput": 684.91, "total_tokens": 10580400} {"current_steps": 37770, "total_steps": 40000, "loss": 0.0, "lr": 3.82804873476969e-07, "epoch": 419.6666666666667, "percentage": 94.42, "elapsed_time": "4:17:29", "remaining_time": "0:15:12", "throughput": 684.92, "total_tokens": 10581792} {"current_steps": 37775, "total_steps": 40000, "loss": 0.0, "lr": 3.810953196754702e-07, "epoch": 419.72222222222223, "percentage": 94.44, "elapsed_time": "4:17:31", "remaining_time": "0:15:10", "throughput": 684.91, "total_tokens": 10583168} {"current_steps": 37780, "total_steps": 40000, "loss": 0.0, "lr": 3.793895624184529e-07, "epoch": 419.77777777777777, "percentage": 94.45, "elapsed_time": "4:17:33", "remaining_time": "0:15:08", "throughput": 684.91, "total_tokens": 10584544} {"current_steps": 37785, "total_steps": 40000, "loss": 0.0, "lr": 3.776876019689679e-07, "epoch": 419.8333333333333, "percentage": 94.46, "elapsed_time": "4:17:35", "remaining_time": "0:15:06", "throughput": 684.92, "total_tokens": 10585952} {"current_steps": 37790, "total_steps": 40000, "loss": 0.0, "lr": 3.7598943858947743e-07, "epoch": 419.8888888888889, "percentage": 94.47, "elapsed_time": "4:17:37", "remaining_time": "0:15:03", "throughput": 684.92, "total_tokens": 10587392} {"current_steps": 37795, "total_steps": 40000, "loss": 0.0, "lr": 3.742950725418637e-07, "epoch": 419.94444444444446, "percentage": 94.49, "elapsed_time": "4:17:39", "remaining_time": "0:15:01", "throughput": 684.93, "total_tokens": 10588784} {"current_steps": 37800, "total_steps": 40000, "loss": 0.0, "lr": 3.726045040874093e-07, "epoch": 420.0, "percentage": 94.5, "elapsed_time": "4:17:41", "remaining_time": "0:14:59", "throughput": 684.93, "total_tokens": 10590208} {"current_steps": 37800, "total_steps": 40000, "eval_loss": 0.42338746786117554, "epoch": 420.0, "percentage": 94.5, "elapsed_time": "4:17:43", "remaining_time": "0:14:59", "throughput": 684.87, "total_tokens": 10590208} {"current_steps": 37805, "total_steps": 40000, "loss": 0.0, "lr": 3.709177334868308e-07, "epoch": 420.05555555555554, "percentage": 94.51, "elapsed_time": "4:17:46", "remaining_time": "0:14:58", "throughput": 684.8, "total_tokens": 10591632} {"current_steps": 37810, "total_steps": 40000, "loss": 0.0, "lr": 3.692347610002478e-07, "epoch": 420.1111111111111, "percentage": 94.53, "elapsed_time": "4:17:48", "remaining_time": "0:14:55", "throughput": 684.8, "total_tokens": 10593040} {"current_steps": 37815, "total_steps": 40000, "loss": 0.0, "lr": 3.675555868871916e-07, "epoch": 420.1666666666667, "percentage": 94.54, "elapsed_time": "4:17:50", "remaining_time": "0:14:53", "throughput": 684.81, "total_tokens": 10594464} {"current_steps": 37820, "total_steps": 40000, "loss": 0.0, "lr": 3.658802114066162e-07, "epoch": 420.22222222222223, "percentage": 94.55, "elapsed_time": "4:17:52", "remaining_time": "0:14:51", "throughput": 684.81, "total_tokens": 10595872} {"current_steps": 37825, "total_steps": 40000, "loss": 0.0, "lr": 3.6420863481688437e-07, "epoch": 420.27777777777777, "percentage": 94.56, "elapsed_time": "4:17:54", "remaining_time": "0:14:49", "throughput": 684.82, "total_tokens": 10597264} {"current_steps": 37830, "total_steps": 40000, "loss": 0.0, "lr": 3.625408573757705e-07, "epoch": 420.3333333333333, "percentage": 94.58, "elapsed_time": "4:17:56", "remaining_time": "0:14:47", "throughput": 684.82, "total_tokens": 10598672} {"current_steps": 37835, "total_steps": 40000, "loss": 0.0, "lr": 3.608768793404743e-07, "epoch": 420.3888888888889, "percentage": 94.59, "elapsed_time": "4:17:58", "remaining_time": "0:14:45", "throughput": 684.83, "total_tokens": 10600096} {"current_steps": 37840, "total_steps": 40000, "loss": 0.0, "lr": 3.592167009675934e-07, "epoch": 420.44444444444446, "percentage": 94.6, "elapsed_time": "4:18:00", "remaining_time": "0:14:43", "throughput": 684.83, "total_tokens": 10601472} {"current_steps": 37845, "total_steps": 40000, "loss": 0.0, "lr": 3.575603225131563e-07, "epoch": 420.5, "percentage": 94.61, "elapsed_time": "4:18:02", "remaining_time": "0:14:41", "throughput": 684.84, "total_tokens": 10602864} {"current_steps": 37850, "total_steps": 40000, "loss": 0.0, "lr": 3.55907744232592e-07, "epoch": 420.55555555555554, "percentage": 94.62, "elapsed_time": "4:18:04", "remaining_time": "0:14:39", "throughput": 684.85, "total_tokens": 10604320} {"current_steps": 37855, "total_steps": 40000, "loss": 0.0, "lr": 3.5425896638075217e-07, "epoch": 420.6111111111111, "percentage": 94.64, "elapsed_time": "4:18:06", "remaining_time": "0:14:37", "throughput": 684.85, "total_tokens": 10605696} {"current_steps": 37860, "total_steps": 40000, "loss": 0.0, "lr": 3.5261398921189736e-07, "epoch": 420.6666666666667, "percentage": 94.65, "elapsed_time": "4:18:08", "remaining_time": "0:14:35", "throughput": 684.85, "total_tokens": 10607088} {"current_steps": 37865, "total_steps": 40000, "loss": 0.0, "lr": 3.509728129797024e-07, "epoch": 420.72222222222223, "percentage": 94.66, "elapsed_time": "4:18:10", "remaining_time": "0:14:33", "throughput": 684.86, "total_tokens": 10608528} {"current_steps": 37870, "total_steps": 40000, "loss": 0.0, "lr": 3.4933543793725656e-07, "epoch": 420.77777777777777, "percentage": 94.67, "elapsed_time": "4:18:11", "remaining_time": "0:14:31", "throughput": 684.87, "total_tokens": 10609936} {"current_steps": 37875, "total_steps": 40000, "loss": 0.0, "lr": 3.4770186433707163e-07, "epoch": 420.8333333333333, "percentage": 94.69, "elapsed_time": "4:18:13", "remaining_time": "0:14:29", "throughput": 684.87, "total_tokens": 10611312} {"current_steps": 37880, "total_steps": 40000, "loss": 0.0, "lr": 3.4607209243105453e-07, "epoch": 420.8888888888889, "percentage": 94.7, "elapsed_time": "4:18:15", "remaining_time": "0:14:27", "throughput": 684.87, "total_tokens": 10612704} {"current_steps": 37885, "total_steps": 40000, "loss": 0.0, "lr": 3.444461224705431e-07, "epoch": 420.94444444444446, "percentage": 94.71, "elapsed_time": "4:18:17", "remaining_time": "0:14:25", "throughput": 684.88, "total_tokens": 10614096} {"current_steps": 37890, "total_steps": 40000, "loss": 0.0, "lr": 3.4282395470628116e-07, "epoch": 421.0, "percentage": 94.73, "elapsed_time": "4:18:19", "remaining_time": "0:14:23", "throughput": 684.87, "total_tokens": 10615488} {"current_steps": 37895, "total_steps": 40000, "loss": 0.0, "lr": 3.4120558938842417e-07, "epoch": 421.05555555555554, "percentage": 94.74, "elapsed_time": "4:18:22", "remaining_time": "0:14:21", "throughput": 684.87, "total_tokens": 10616864} {"current_steps": 37900, "total_steps": 40000, "loss": 0.0, "lr": 3.395910267665503e-07, "epoch": 421.1111111111111, "percentage": 94.75, "elapsed_time": "4:18:24", "remaining_time": "0:14:19", "throughput": 684.87, "total_tokens": 10618272} {"current_steps": 37905, "total_steps": 40000, "loss": 0.0, "lr": 3.3798026708964094e-07, "epoch": 421.1666666666667, "percentage": 94.76, "elapsed_time": "4:18:25", "remaining_time": "0:14:17", "throughput": 684.88, "total_tokens": 10619680} {"current_steps": 37910, "total_steps": 40000, "loss": 0.0, "lr": 3.3637331060609456e-07, "epoch": 421.22222222222223, "percentage": 94.77, "elapsed_time": "4:18:27", "remaining_time": "0:14:14", "throughput": 684.88, "total_tokens": 10621072} {"current_steps": 37915, "total_steps": 40000, "loss": 0.0, "lr": 3.3477015756372966e-07, "epoch": 421.27777777777777, "percentage": 94.79, "elapsed_time": "4:18:29", "remaining_time": "0:14:12", "throughput": 684.88, "total_tokens": 10622448} {"current_steps": 37920, "total_steps": 40000, "loss": 0.0, "lr": 3.3317080820976785e-07, "epoch": 421.3333333333333, "percentage": 94.8, "elapsed_time": "4:18:31", "remaining_time": "0:14:10", "throughput": 684.89, "total_tokens": 10623872} {"current_steps": 37925, "total_steps": 40000, "loss": 0.0, "lr": 3.315752627908508e-07, "epoch": 421.3888888888889, "percentage": 94.81, "elapsed_time": "4:18:33", "remaining_time": "0:14:08", "throughput": 684.9, "total_tokens": 10625280} {"current_steps": 37930, "total_steps": 40000, "loss": 0.0, "lr": 3.299835215530317e-07, "epoch": 421.44444444444446, "percentage": 94.83, "elapsed_time": "4:18:35", "remaining_time": "0:14:06", "throughput": 684.9, "total_tokens": 10626656} {"current_steps": 37935, "total_steps": 40000, "loss": 0.0, "lr": 3.2839558474177245e-07, "epoch": 421.5, "percentage": 94.84, "elapsed_time": "4:18:37", "remaining_time": "0:14:04", "throughput": 684.9, "total_tokens": 10628032} {"current_steps": 37940, "total_steps": 40000, "loss": 0.0, "lr": 3.2681145260196056e-07, "epoch": 421.55555555555554, "percentage": 94.85, "elapsed_time": "4:18:39", "remaining_time": "0:14:02", "throughput": 684.91, "total_tokens": 10629408} {"current_steps": 37945, "total_steps": 40000, "loss": 0.0, "lr": 3.252311253778839e-07, "epoch": 421.6111111111111, "percentage": 94.86, "elapsed_time": "4:18:41", "remaining_time": "0:14:00", "throughput": 684.91, "total_tokens": 10630800} {"current_steps": 37950, "total_steps": 40000, "loss": 0.0, "lr": 3.2365460331325034e-07, "epoch": 421.6666666666667, "percentage": 94.88, "elapsed_time": "4:18:43", "remaining_time": "0:13:58", "throughput": 684.92, "total_tokens": 10632240} {"current_steps": 37955, "total_steps": 40000, "loss": 0.0, "lr": 3.2208188665117934e-07, "epoch": 421.72222222222223, "percentage": 94.89, "elapsed_time": "4:18:45", "remaining_time": "0:13:56", "throughput": 684.92, "total_tokens": 10633600} {"current_steps": 37960, "total_steps": 40000, "loss": 0.0, "lr": 3.205129756342018e-07, "epoch": 421.77777777777777, "percentage": 94.9, "elapsed_time": "4:18:47", "remaining_time": "0:13:54", "throughput": 684.93, "total_tokens": 10635040} {"current_steps": 37965, "total_steps": 40000, "loss": 0.0, "lr": 3.189478705042659e-07, "epoch": 421.8333333333333, "percentage": 94.91, "elapsed_time": "4:18:49", "remaining_time": "0:13:52", "throughput": 684.93, "total_tokens": 10636480} {"current_steps": 37970, "total_steps": 40000, "loss": 0.0, "lr": 3.173865715027341e-07, "epoch": 421.8888888888889, "percentage": 94.92, "elapsed_time": "4:18:51", "remaining_time": "0:13:50", "throughput": 684.94, "total_tokens": 10637872} {"current_steps": 37975, "total_steps": 40000, "loss": 0.0, "lr": 3.158290788703694e-07, "epoch": 421.94444444444446, "percentage": 94.94, "elapsed_time": "4:18:53", "remaining_time": "0:13:48", "throughput": 684.94, "total_tokens": 10639312} {"current_steps": 37980, "total_steps": 40000, "loss": 0.0, "lr": 3.1427539284736297e-07, "epoch": 422.0, "percentage": 94.95, "elapsed_time": "4:18:55", "remaining_time": "0:13:46", "throughput": 684.94, "total_tokens": 10640720} {"current_steps": 37985, "total_steps": 40000, "loss": 0.0, "lr": 3.127255136733093e-07, "epoch": 422.05555555555554, "percentage": 94.96, "elapsed_time": "4:18:57", "remaining_time": "0:13:44", "throughput": 684.94, "total_tokens": 10642176} {"current_steps": 37990, "total_steps": 40000, "loss": 0.0, "lr": 3.1117944158722544e-07, "epoch": 422.1111111111111, "percentage": 94.97, "elapsed_time": "4:18:59", "remaining_time": "0:13:42", "throughput": 684.94, "total_tokens": 10643568} {"current_steps": 37995, "total_steps": 40000, "loss": 0.0, "lr": 3.0963717682752635e-07, "epoch": 422.1666666666667, "percentage": 94.99, "elapsed_time": "4:19:01", "remaining_time": "0:13:40", "throughput": 684.95, "total_tokens": 10644976} {"current_steps": 38000, "total_steps": 40000, "loss": 0.0, "lr": 3.080987196320578e-07, "epoch": 422.22222222222223, "percentage": 95.0, "elapsed_time": "4:19:03", "remaining_time": "0:13:38", "throughput": 684.95, "total_tokens": 10646384} {"current_steps": 38000, "total_steps": 40000, "eval_loss": 0.3726119101047516, "epoch": 422.22222222222223, "percentage": 95.0, "elapsed_time": "4:19:04", "remaining_time": "0:13:38", "throughput": 684.9, "total_tokens": 10646384} {"current_steps": 38005, "total_steps": 40000, "loss": 0.0, "lr": 3.065640702380607e-07, "epoch": 422.27777777777777, "percentage": 95.01, "elapsed_time": "4:19:07", "remaining_time": "0:13:36", "throughput": 684.84, "total_tokens": 10647824} {"current_steps": 38010, "total_steps": 40000, "loss": 0.0, "lr": 3.050332288822011e-07, "epoch": 422.3333333333333, "percentage": 95.03, "elapsed_time": "4:19:09", "remaining_time": "0:13:34", "throughput": 684.85, "total_tokens": 10649232} {"current_steps": 38015, "total_steps": 40000, "loss": 0.0, "lr": 3.035061958005542e-07, "epoch": 422.3888888888889, "percentage": 95.04, "elapsed_time": "4:19:11", "remaining_time": "0:13:32", "throughput": 684.85, "total_tokens": 10650672} {"current_steps": 38020, "total_steps": 40000, "loss": 0.0, "lr": 3.019829712286093e-07, "epoch": 422.44444444444446, "percentage": 95.05, "elapsed_time": "4:19:13", "remaining_time": "0:13:30", "throughput": 684.86, "total_tokens": 10652064} {"current_steps": 38025, "total_steps": 40000, "loss": 0.0, "lr": 3.004635554012647e-07, "epoch": 422.5, "percentage": 95.06, "elapsed_time": "4:19:15", "remaining_time": "0:13:27", "throughput": 684.86, "total_tokens": 10653456} {"current_steps": 38030, "total_steps": 40000, "loss": 0.0, "lr": 2.9894794855283017e-07, "epoch": 422.55555555555554, "percentage": 95.08, "elapsed_time": "4:19:17", "remaining_time": "0:13:25", "throughput": 684.86, "total_tokens": 10654832} {"current_steps": 38035, "total_steps": 40000, "loss": 0.0, "lr": 2.9743615091703816e-07, "epoch": 422.6111111111111, "percentage": 95.09, "elapsed_time": "4:19:19", "remaining_time": "0:13:23", "throughput": 684.87, "total_tokens": 10656240} {"current_steps": 38040, "total_steps": 40000, "loss": 0.0, "lr": 2.959281627270216e-07, "epoch": 422.6666666666667, "percentage": 95.1, "elapsed_time": "4:19:21", "remaining_time": "0:13:21", "throughput": 684.88, "total_tokens": 10657664} {"current_steps": 38045, "total_steps": 40000, "loss": 0.0, "lr": 2.944239842153362e-07, "epoch": 422.72222222222223, "percentage": 95.11, "elapsed_time": "4:19:23", "remaining_time": "0:13:19", "throughput": 684.88, "total_tokens": 10659040} {"current_steps": 38050, "total_steps": 40000, "loss": 0.0, "lr": 2.929236156139381e-07, "epoch": 422.77777777777777, "percentage": 95.12, "elapsed_time": "4:19:25", "remaining_time": "0:13:17", "throughput": 684.89, "total_tokens": 10660480} {"current_steps": 38055, "total_steps": 40000, "loss": 0.0, "lr": 2.9142705715420883e-07, "epoch": 422.8333333333333, "percentage": 95.14, "elapsed_time": "4:19:27", "remaining_time": "0:13:15", "throughput": 684.89, "total_tokens": 10661872} {"current_steps": 38060, "total_steps": 40000, "loss": 0.0, "lr": 2.8993430906693595e-07, "epoch": 422.8888888888889, "percentage": 95.15, "elapsed_time": "4:19:29", "remaining_time": "0:13:13", "throughput": 684.89, "total_tokens": 10663264} {"current_steps": 38065, "total_steps": 40000, "loss": 0.0, "lr": 2.88445371582316e-07, "epoch": 422.94444444444446, "percentage": 95.16, "elapsed_time": "4:19:31", "remaining_time": "0:13:11", "throughput": 684.9, "total_tokens": 10664608} {"current_steps": 38070, "total_steps": 40000, "loss": 0.0, "lr": 2.8696024492996796e-07, "epoch": 423.0, "percentage": 95.17, "elapsed_time": "4:19:33", "remaining_time": "0:13:09", "throughput": 684.89, "total_tokens": 10665984} {"current_steps": 38075, "total_steps": 40000, "loss": 0.0, "lr": 2.854789293389115e-07, "epoch": 423.05555555555554, "percentage": 95.19, "elapsed_time": "4:19:35", "remaining_time": "0:13:07", "throughput": 684.88, "total_tokens": 10667376} {"current_steps": 38080, "total_steps": 40000, "loss": 0.0, "lr": 2.8400142503758606e-07, "epoch": 423.1111111111111, "percentage": 95.2, "elapsed_time": "4:19:37", "remaining_time": "0:13:05", "throughput": 684.89, "total_tokens": 10668736} {"current_steps": 38085, "total_steps": 40000, "loss": 0.0, "lr": 2.8252773225384276e-07, "epoch": 423.1666666666667, "percentage": 95.21, "elapsed_time": "4:19:39", "remaining_time": "0:13:03", "throughput": 684.89, "total_tokens": 10670112} {"current_steps": 38090, "total_steps": 40000, "loss": 0.0, "lr": 2.8105785121494143e-07, "epoch": 423.22222222222223, "percentage": 95.23, "elapsed_time": "4:19:41", "remaining_time": "0:13:01", "throughput": 684.9, "total_tokens": 10671568} {"current_steps": 38095, "total_steps": 40000, "loss": 0.0, "lr": 2.795917821475563e-07, "epoch": 423.27777777777777, "percentage": 95.24, "elapsed_time": "4:19:43", "remaining_time": "0:12:59", "throughput": 684.9, "total_tokens": 10672960} {"current_steps": 38100, "total_steps": 40000, "loss": 0.0, "lr": 2.78129525277776e-07, "epoch": 423.3333333333333, "percentage": 95.25, "elapsed_time": "4:19:45", "remaining_time": "0:12:57", "throughput": 684.91, "total_tokens": 10674352} {"current_steps": 38105, "total_steps": 40000, "loss": 0.0, "lr": 2.766710808310952e-07, "epoch": 423.3888888888889, "percentage": 95.26, "elapsed_time": "4:19:47", "remaining_time": "0:12:55", "throughput": 684.91, "total_tokens": 10675760} {"current_steps": 38110, "total_steps": 40000, "loss": 0.0, "lr": 2.7521644903242827e-07, "epoch": 423.44444444444446, "percentage": 95.28, "elapsed_time": "4:19:48", "remaining_time": "0:12:53", "throughput": 684.92, "total_tokens": 10677184} {"current_steps": 38115, "total_steps": 40000, "loss": 0.0, "lr": 2.7376563010609593e-07, "epoch": 423.5, "percentage": 95.29, "elapsed_time": "4:19:50", "remaining_time": "0:12:51", "throughput": 684.92, "total_tokens": 10678624} {"current_steps": 38120, "total_steps": 40000, "loss": 0.0, "lr": 2.72318624275833e-07, "epoch": 423.55555555555554, "percentage": 95.3, "elapsed_time": "4:19:52", "remaining_time": "0:12:49", "throughput": 684.93, "total_tokens": 10679984} {"current_steps": 38125, "total_steps": 40000, "loss": 0.0, "lr": 2.7087543176478324e-07, "epoch": 423.6111111111111, "percentage": 95.31, "elapsed_time": "4:19:54", "remaining_time": "0:12:46", "throughput": 684.93, "total_tokens": 10681360} {"current_steps": 38130, "total_steps": 40000, "loss": 0.0, "lr": 2.694360527955103e-07, "epoch": 423.6666666666667, "percentage": 95.33, "elapsed_time": "4:19:56", "remaining_time": "0:12:44", "throughput": 684.94, "total_tokens": 10682816} {"current_steps": 38135, "total_steps": 40000, "loss": 0.0, "lr": 2.680004875899811e-07, "epoch": 423.72222222222223, "percentage": 95.34, "elapsed_time": "4:19:58", "remaining_time": "0:12:42", "throughput": 684.94, "total_tokens": 10684224} {"current_steps": 38140, "total_steps": 40000, "loss": 0.0, "lr": 2.665687363695768e-07, "epoch": 423.77777777777777, "percentage": 95.35, "elapsed_time": "4:20:00", "remaining_time": "0:12:40", "throughput": 684.95, "total_tokens": 10685632} {"current_steps": 38145, "total_steps": 40000, "loss": 0.0, "lr": 2.6514079935509584e-07, "epoch": 423.8333333333333, "percentage": 95.36, "elapsed_time": "4:20:02", "remaining_time": "0:12:38", "throughput": 684.95, "total_tokens": 10687056} {"current_steps": 38150, "total_steps": 40000, "loss": 0.0, "lr": 2.6371667676673983e-07, "epoch": 423.8888888888889, "percentage": 95.38, "elapsed_time": "4:20:04", "remaining_time": "0:12:36", "throughput": 684.96, "total_tokens": 10688464} {"current_steps": 38155, "total_steps": 40000, "loss": 0.0, "lr": 2.6229636882412755e-07, "epoch": 423.94444444444446, "percentage": 95.39, "elapsed_time": "4:20:06", "remaining_time": "0:12:34", "throughput": 684.96, "total_tokens": 10689840} {"current_steps": 38160, "total_steps": 40000, "loss": 0.0, "lr": 2.6087987574628935e-07, "epoch": 424.0, "percentage": 95.4, "elapsed_time": "4:20:08", "remaining_time": "0:12:32", "throughput": 684.96, "total_tokens": 10691216} {"current_steps": 38165, "total_steps": 40000, "loss": 0.0, "lr": 2.5946719775166437e-07, "epoch": 424.05555555555554, "percentage": 95.41, "elapsed_time": "4:20:10", "remaining_time": "0:12:30", "throughput": 684.95, "total_tokens": 10692544} {"current_steps": 38170, "total_steps": 40000, "loss": 0.0, "lr": 2.5805833505810616e-07, "epoch": 424.1111111111111, "percentage": 95.43, "elapsed_time": "4:20:12", "remaining_time": "0:12:28", "throughput": 684.95, "total_tokens": 10693920} {"current_steps": 38175, "total_steps": 40000, "loss": 0.0, "lr": 2.566532878828798e-07, "epoch": 424.1666666666667, "percentage": 95.44, "elapsed_time": "4:20:14", "remaining_time": "0:12:26", "throughput": 684.96, "total_tokens": 10695376} {"current_steps": 38180, "total_steps": 40000, "loss": 0.0, "lr": 2.552520564426619e-07, "epoch": 424.22222222222223, "percentage": 95.45, "elapsed_time": "4:20:16", "remaining_time": "0:12:24", "throughput": 684.96, "total_tokens": 10696752} {"current_steps": 38185, "total_steps": 40000, "loss": 0.0, "lr": 2.5385464095353803e-07, "epoch": 424.27777777777777, "percentage": 95.46, "elapsed_time": "4:20:18", "remaining_time": "0:12:22", "throughput": 684.97, "total_tokens": 10698160} {"current_steps": 38190, "total_steps": 40000, "loss": 0.0, "lr": 2.5246104163100804e-07, "epoch": 424.3333333333333, "percentage": 95.47, "elapsed_time": "4:20:20", "remaining_time": "0:12:20", "throughput": 684.97, "total_tokens": 10699552} {"current_steps": 38195, "total_steps": 40000, "loss": 0.0, "lr": 2.510712586899833e-07, "epoch": 424.3888888888889, "percentage": 95.49, "elapsed_time": "4:20:22", "remaining_time": "0:12:18", "throughput": 684.97, "total_tokens": 10700912} {"current_steps": 38200, "total_steps": 40000, "loss": 0.0, "lr": 2.4968529234478124e-07, "epoch": 424.44444444444446, "percentage": 95.5, "elapsed_time": "4:20:24", "remaining_time": "0:12:16", "throughput": 684.98, "total_tokens": 10702336} {"current_steps": 38200, "total_steps": 40000, "eval_loss": 0.34964871406555176, "epoch": 424.44444444444446, "percentage": 95.5, "elapsed_time": "4:20:25", "remaining_time": "0:12:16", "throughput": 684.92, "total_tokens": 10702336} {"current_steps": 38205, "total_steps": 40000, "loss": 0.0, "lr": 2.483031428091448e-07, "epoch": 424.5, "percentage": 95.51, "elapsed_time": "4:20:28", "remaining_time": "0:12:14", "throughput": 684.86, "total_tokens": 10703728} {"current_steps": 38210, "total_steps": 40000, "loss": 0.0, "lr": 2.469248102962091e-07, "epoch": 424.55555555555554, "percentage": 95.53, "elapsed_time": "4:20:30", "remaining_time": "0:12:12", "throughput": 684.87, "total_tokens": 10705200} {"current_steps": 38215, "total_steps": 40000, "loss": 0.0, "lr": 2.4555029501853455e-07, "epoch": 424.6111111111111, "percentage": 95.54, "elapsed_time": "4:20:32", "remaining_time": "0:12:10", "throughput": 684.87, "total_tokens": 10706560} {"current_steps": 38220, "total_steps": 40000, "loss": 0.0, "lr": 2.441795971880906e-07, "epoch": 424.6666666666667, "percentage": 95.55, "elapsed_time": "4:20:34", "remaining_time": "0:12:08", "throughput": 684.88, "total_tokens": 10707968} {"current_steps": 38225, "total_steps": 40000, "loss": 0.0, "lr": 2.4281271701625255e-07, "epoch": 424.72222222222223, "percentage": 95.56, "elapsed_time": "4:20:36", "remaining_time": "0:12:06", "throughput": 684.88, "total_tokens": 10709360} {"current_steps": 38230, "total_steps": 40000, "loss": 0.0, "lr": 2.4144965471381007e-07, "epoch": 424.77777777777777, "percentage": 95.58, "elapsed_time": "4:20:38", "remaining_time": "0:12:04", "throughput": 684.89, "total_tokens": 10710752} {"current_steps": 38235, "total_steps": 40000, "loss": 0.0, "lr": 2.400904104909674e-07, "epoch": 424.8333333333333, "percentage": 95.59, "elapsed_time": "4:20:40", "remaining_time": "0:12:02", "throughput": 684.9, "total_tokens": 10712224} {"current_steps": 38240, "total_steps": 40000, "loss": 0.0, "lr": 2.3873498455733725e-07, "epoch": 424.8888888888889, "percentage": 95.6, "elapsed_time": "4:20:42", "remaining_time": "0:11:59", "throughput": 684.9, "total_tokens": 10713600} {"current_steps": 38245, "total_steps": 40000, "loss": 0.0, "lr": 2.3738337712194137e-07, "epoch": 424.94444444444446, "percentage": 95.61, "elapsed_time": "4:20:44", "remaining_time": "0:11:57", "throughput": 684.91, "total_tokens": 10715024} {"current_steps": 38250, "total_steps": 40000, "loss": 0.0, "lr": 2.3603558839321305e-07, "epoch": 425.0, "percentage": 95.62, "elapsed_time": "4:20:46", "remaining_time": "0:11:55", "throughput": 684.9, "total_tokens": 10716432} {"current_steps": 38255, "total_steps": 40000, "loss": 0.0, "lr": 2.3469161857900267e-07, "epoch": 425.05555555555554, "percentage": 95.64, "elapsed_time": "4:20:48", "remaining_time": "0:11:53", "throughput": 684.9, "total_tokens": 10717840} {"current_steps": 38260, "total_steps": 40000, "loss": 0.0, "lr": 2.3335146788656393e-07, "epoch": 425.1111111111111, "percentage": 95.65, "elapsed_time": "4:20:50", "remaining_time": "0:11:51", "throughput": 684.9, "total_tokens": 10719264} {"current_steps": 38265, "total_steps": 40000, "loss": 0.0, "lr": 2.3201513652256757e-07, "epoch": 425.1666666666667, "percentage": 95.66, "elapsed_time": "4:20:52", "remaining_time": "0:11:49", "throughput": 684.91, "total_tokens": 10720656} {"current_steps": 38270, "total_steps": 40000, "loss": 0.0, "lr": 2.3068262469308766e-07, "epoch": 425.22222222222223, "percentage": 95.67, "elapsed_time": "4:20:54", "remaining_time": "0:11:47", "throughput": 684.91, "total_tokens": 10722064} {"current_steps": 38275, "total_steps": 40000, "loss": 0.0, "lr": 2.2935393260362093e-07, "epoch": 425.27777777777777, "percentage": 95.69, "elapsed_time": "4:20:56", "remaining_time": "0:11:45", "throughput": 684.92, "total_tokens": 10723456} {"current_steps": 38280, "total_steps": 40000, "loss": 0.0, "lr": 2.2802906045906458e-07, "epoch": 425.3333333333333, "percentage": 95.7, "elapsed_time": "4:20:58", "remaining_time": "0:11:43", "throughput": 684.92, "total_tokens": 10724832} {"current_steps": 38285, "total_steps": 40000, "loss": 0.0, "lr": 2.2670800846373018e-07, "epoch": 425.3888888888889, "percentage": 95.71, "elapsed_time": "4:21:00", "remaining_time": "0:11:41", "throughput": 684.93, "total_tokens": 10726256} {"current_steps": 38290, "total_steps": 40000, "loss": 0.0, "lr": 2.2539077682134367e-07, "epoch": 425.44444444444446, "percentage": 95.73, "elapsed_time": "4:21:02", "remaining_time": "0:11:39", "throughput": 684.93, "total_tokens": 10727632} {"current_steps": 38295, "total_steps": 40000, "loss": 0.0, "lr": 2.2407736573503423e-07, "epoch": 425.5, "percentage": 95.74, "elapsed_time": "4:21:04", "remaining_time": "0:11:37", "throughput": 684.94, "total_tokens": 10729072} {"current_steps": 38300, "total_steps": 40000, "loss": 0.0, "lr": 2.2276777540735093e-07, "epoch": 425.55555555555554, "percentage": 95.75, "elapsed_time": "4:21:06", "remaining_time": "0:11:35", "throughput": 684.94, "total_tokens": 10730448} {"current_steps": 38305, "total_steps": 40000, "loss": 0.0, "lr": 2.2146200604024613e-07, "epoch": 425.6111111111111, "percentage": 95.76, "elapsed_time": "4:21:08", "remaining_time": "0:11:33", "throughput": 684.95, "total_tokens": 10731872} {"current_steps": 38310, "total_steps": 40000, "loss": 0.0, "lr": 2.2016005783508375e-07, "epoch": 425.6666666666667, "percentage": 95.78, "elapsed_time": "4:21:10", "remaining_time": "0:11:31", "throughput": 684.95, "total_tokens": 10733280} {"current_steps": 38315, "total_steps": 40000, "loss": 0.0, "lr": 2.1886193099264763e-07, "epoch": 425.72222222222223, "percentage": 95.79, "elapsed_time": "4:21:12", "remaining_time": "0:11:29", "throughput": 684.95, "total_tokens": 10734656} {"current_steps": 38320, "total_steps": 40000, "loss": 0.0, "lr": 2.175676257131165e-07, "epoch": 425.77777777777777, "percentage": 95.8, "elapsed_time": "4:21:14", "remaining_time": "0:11:27", "throughput": 684.96, "total_tokens": 10736064} {"current_steps": 38325, "total_steps": 40000, "loss": 0.0, "lr": 2.162771421960974e-07, "epoch": 425.8333333333333, "percentage": 95.81, "elapsed_time": "4:21:15", "remaining_time": "0:11:25", "throughput": 684.96, "total_tokens": 10737456} {"current_steps": 38330, "total_steps": 40000, "loss": 0.0, "lr": 2.1499048064059224e-07, "epoch": 425.8888888888889, "percentage": 95.83, "elapsed_time": "4:21:17", "remaining_time": "0:11:23", "throughput": 684.97, "total_tokens": 10738848} {"current_steps": 38335, "total_steps": 40000, "loss": 0.0, "lr": 2.1370764124502285e-07, "epoch": 425.94444444444446, "percentage": 95.84, "elapsed_time": "4:21:19", "remaining_time": "0:11:21", "throughput": 684.97, "total_tokens": 10740224} {"current_steps": 38340, "total_steps": 40000, "loss": 0.0, "lr": 2.1242862420721988e-07, "epoch": 426.0, "percentage": 95.85, "elapsed_time": "4:21:21", "remaining_time": "0:11:18", "throughput": 684.97, "total_tokens": 10741664} {"current_steps": 38345, "total_steps": 40000, "loss": 0.0, "lr": 2.1115342972442276e-07, "epoch": 426.05555555555554, "percentage": 95.86, "elapsed_time": "4:21:24", "remaining_time": "0:11:16", "throughput": 684.96, "total_tokens": 10743024} {"current_steps": 38350, "total_steps": 40000, "loss": 0.0, "lr": 2.0988205799328252e-07, "epoch": 426.1111111111111, "percentage": 95.88, "elapsed_time": "4:21:26", "remaining_time": "0:11:14", "throughput": 684.96, "total_tokens": 10744416} {"current_steps": 38355, "total_steps": 40000, "loss": 0.0, "lr": 2.0861450920986182e-07, "epoch": 426.1666666666667, "percentage": 95.89, "elapsed_time": "4:21:28", "remaining_time": "0:11:12", "throughput": 684.97, "total_tokens": 10745840} {"current_steps": 38360, "total_steps": 40000, "loss": 0.0, "lr": 2.07350783569632e-07, "epoch": 426.22222222222223, "percentage": 95.9, "elapsed_time": "4:21:29", "remaining_time": "0:11:10", "throughput": 684.97, "total_tokens": 10747200} {"current_steps": 38365, "total_steps": 40000, "loss": 0.0, "lr": 2.060908812674761e-07, "epoch": 426.27777777777777, "percentage": 95.91, "elapsed_time": "4:21:31", "remaining_time": "0:11:08", "throughput": 684.98, "total_tokens": 10748608} {"current_steps": 38370, "total_steps": 40000, "loss": 0.0, "lr": 2.0483480249768317e-07, "epoch": 426.3333333333333, "percentage": 95.93, "elapsed_time": "4:21:33", "remaining_time": "0:11:06", "throughput": 684.98, "total_tokens": 10749952} {"current_steps": 38375, "total_steps": 40000, "loss": 0.0, "lr": 2.035825474539621e-07, "epoch": 426.3888888888889, "percentage": 95.94, "elapsed_time": "4:21:35", "remaining_time": "0:11:04", "throughput": 684.98, "total_tokens": 10751360} {"current_steps": 38380, "total_steps": 40000, "loss": 0.0, "lr": 2.0233411632942235e-07, "epoch": 426.44444444444446, "percentage": 95.95, "elapsed_time": "4:21:37", "remaining_time": "0:11:02", "throughput": 684.99, "total_tokens": 10752800} {"current_steps": 38385, "total_steps": 40000, "loss": 0.0, "lr": 2.0108950931658764e-07, "epoch": 426.5, "percentage": 95.96, "elapsed_time": "4:21:39", "remaining_time": "0:11:00", "throughput": 684.99, "total_tokens": 10754144} {"current_steps": 38390, "total_steps": 40000, "loss": 0.0, "lr": 1.998487266073934e-07, "epoch": 426.55555555555554, "percentage": 95.97, "elapsed_time": "4:21:41", "remaining_time": "0:10:58", "throughput": 685.0, "total_tokens": 10755584} {"current_steps": 38395, "total_steps": 40000, "loss": 0.0, "lr": 1.986117683931865e-07, "epoch": 426.6111111111111, "percentage": 95.99, "elapsed_time": "4:21:43", "remaining_time": "0:10:56", "throughput": 685.0, "total_tokens": 10757008} {"current_steps": 38400, "total_steps": 40000, "loss": 0.0, "lr": 1.9737863486471442e-07, "epoch": 426.6666666666667, "percentage": 96.0, "elapsed_time": "4:21:45", "remaining_time": "0:10:54", "throughput": 685.01, "total_tokens": 10758400} {"current_steps": 38400, "total_steps": 40000, "eval_loss": 0.34045541286468506, "epoch": 426.6666666666667, "percentage": 96.0, "elapsed_time": "4:21:46", "remaining_time": "0:10:54", "throughput": 684.95, "total_tokens": 10758400} {"current_steps": 38405, "total_steps": 40000, "loss": 0.0, "lr": 1.9614932621215e-07, "epoch": 426.72222222222223, "percentage": 96.01, "elapsed_time": "4:21:50", "remaining_time": "0:10:52", "throughput": 684.9, "total_tokens": 10759840} {"current_steps": 38410, "total_steps": 40000, "loss": 0.0, "lr": 1.9492384262506102e-07, "epoch": 426.77777777777777, "percentage": 96.03, "elapsed_time": "4:21:52", "remaining_time": "0:10:50", "throughput": 684.9, "total_tokens": 10761264} {"current_steps": 38415, "total_steps": 40000, "loss": 0.0, "lr": 1.9370218429243524e-07, "epoch": 426.8333333333333, "percentage": 96.04, "elapsed_time": "4:21:54", "remaining_time": "0:10:48", "throughput": 684.91, "total_tokens": 10762688} {"current_steps": 38420, "total_steps": 40000, "loss": 0.0, "lr": 1.9248435140267197e-07, "epoch": 426.8888888888889, "percentage": 96.05, "elapsed_time": "4:21:55", "remaining_time": "0:10:46", "throughput": 684.91, "total_tokens": 10764096} {"current_steps": 38425, "total_steps": 40000, "loss": 0.0, "lr": 1.9127034414356814e-07, "epoch": 426.94444444444446, "percentage": 96.06, "elapsed_time": "4:21:57", "remaining_time": "0:10:44", "throughput": 684.92, "total_tokens": 10765504} {"current_steps": 38430, "total_steps": 40000, "loss": 0.0, "lr": 1.9006016270234627e-07, "epoch": 427.0, "percentage": 96.08, "elapsed_time": "4:22:00", "remaining_time": "0:10:42", "throughput": 684.92, "total_tokens": 10766912} {"current_steps": 38435, "total_steps": 40000, "loss": 0.0, "lr": 1.888538072656293e-07, "epoch": 427.05555555555554, "percentage": 96.09, "elapsed_time": "4:22:02", "remaining_time": "0:10:40", "throughput": 684.91, "total_tokens": 10768304} {"current_steps": 38440, "total_steps": 40000, "loss": 0.0, "lr": 1.8765127801944893e-07, "epoch": 427.1111111111111, "percentage": 96.1, "elapsed_time": "4:22:04", "remaining_time": "0:10:38", "throughput": 684.92, "total_tokens": 10769760} {"current_steps": 38445, "total_steps": 40000, "loss": 0.0, "lr": 1.8645257514925406e-07, "epoch": 427.1666666666667, "percentage": 96.11, "elapsed_time": "4:22:06", "remaining_time": "0:10:36", "throughput": 684.92, "total_tokens": 10771168} {"current_steps": 38450, "total_steps": 40000, "loss": 0.0, "lr": 1.8525769883989685e-07, "epoch": 427.22222222222223, "percentage": 96.12, "elapsed_time": "4:22:08", "remaining_time": "0:10:34", "throughput": 684.93, "total_tokens": 10772544} {"current_steps": 38455, "total_steps": 40000, "loss": 0.0, "lr": 1.8406664927564654e-07, "epoch": 427.27777777777777, "percentage": 96.14, "elapsed_time": "4:22:09", "remaining_time": "0:10:31", "throughput": 684.93, "total_tokens": 10773952} {"current_steps": 38460, "total_steps": 40000, "loss": 0.0, "lr": 1.8287942664017566e-07, "epoch": 427.3333333333333, "percentage": 96.15, "elapsed_time": "4:22:11", "remaining_time": "0:10:29", "throughput": 684.94, "total_tokens": 10775344} {"current_steps": 38465, "total_steps": 40000, "loss": 0.0, "lr": 1.8169603111656552e-07, "epoch": 427.3888888888889, "percentage": 96.16, "elapsed_time": "4:22:13", "remaining_time": "0:10:27", "throughput": 684.94, "total_tokens": 10776736} {"current_steps": 38470, "total_steps": 40000, "loss": 0.0, "lr": 1.805164628873146e-07, "epoch": 427.44444444444446, "percentage": 96.17, "elapsed_time": "4:22:15", "remaining_time": "0:10:25", "throughput": 684.94, "total_tokens": 10778096} {"current_steps": 38475, "total_steps": 40000, "loss": 0.0, "lr": 1.793407221343274e-07, "epoch": 427.5, "percentage": 96.19, "elapsed_time": "4:22:17", "remaining_time": "0:10:23", "throughput": 684.95, "total_tokens": 10779504} {"current_steps": 38480, "total_steps": 40000, "loss": 0.0, "lr": 1.781688090389172e-07, "epoch": 427.55555555555554, "percentage": 96.2, "elapsed_time": "4:22:19", "remaining_time": "0:10:21", "throughput": 684.95, "total_tokens": 10780928} {"current_steps": 38485, "total_steps": 40000, "loss": 0.0, "lr": 1.770007237818061e-07, "epoch": 427.6111111111111, "percentage": 96.21, "elapsed_time": "4:22:21", "remaining_time": "0:10:19", "throughput": 684.96, "total_tokens": 10782336} {"current_steps": 38490, "total_steps": 40000, "loss": 0.0, "lr": 1.7583646654313059e-07, "epoch": 427.6666666666667, "percentage": 96.23, "elapsed_time": "4:22:23", "remaining_time": "0:10:17", "throughput": 684.96, "total_tokens": 10783744} {"current_steps": 38495, "total_steps": 40000, "loss": 0.0, "lr": 1.7467603750242757e-07, "epoch": 427.72222222222223, "percentage": 96.24, "elapsed_time": "4:22:25", "remaining_time": "0:10:15", "throughput": 684.97, "total_tokens": 10785136} {"current_steps": 38500, "total_steps": 40000, "loss": 0.0, "lr": 1.7351943683865944e-07, "epoch": 427.77777777777777, "percentage": 96.25, "elapsed_time": "4:22:27", "remaining_time": "0:10:13", "throughput": 684.97, "total_tokens": 10786528} {"current_steps": 38505, "total_steps": 40000, "loss": 0.0, "lr": 1.723666647301808e-07, "epoch": 427.8333333333333, "percentage": 96.26, "elapsed_time": "4:22:29", "remaining_time": "0:10:11", "throughput": 684.98, "total_tokens": 10787952} {"current_steps": 38510, "total_steps": 40000, "loss": 0.0, "lr": 1.712177213547661e-07, "epoch": 427.8888888888889, "percentage": 96.28, "elapsed_time": "4:22:31", "remaining_time": "0:10:09", "throughput": 684.98, "total_tokens": 10789312} {"current_steps": 38515, "total_steps": 40000, "loss": 0.0, "lr": 1.7007260688959581e-07, "epoch": 427.94444444444446, "percentage": 96.29, "elapsed_time": "4:22:33", "remaining_time": "0:10:07", "throughput": 684.98, "total_tokens": 10790720} {"current_steps": 38520, "total_steps": 40000, "loss": 0.0, "lr": 1.68931321511262e-07, "epoch": 428.0, "percentage": 96.3, "elapsed_time": "4:22:35", "remaining_time": "0:10:05", "throughput": 684.98, "total_tokens": 10792096} {"current_steps": 38525, "total_steps": 40000, "loss": 0.0, "lr": 1.6779386539576835e-07, "epoch": 428.05555555555554, "percentage": 96.31, "elapsed_time": "4:22:37", "remaining_time": "0:10:03", "throughput": 684.97, "total_tokens": 10793472} {"current_steps": 38530, "total_steps": 40000, "loss": 0.0, "lr": 1.666602387185162e-07, "epoch": 428.1111111111111, "percentage": 96.33, "elapsed_time": "4:22:39", "remaining_time": "0:10:01", "throughput": 684.98, "total_tokens": 10794880} {"current_steps": 38535, "total_steps": 40000, "loss": 0.0, "lr": 1.655304416543352e-07, "epoch": 428.1666666666667, "percentage": 96.34, "elapsed_time": "4:22:41", "remaining_time": "0:09:59", "throughput": 684.98, "total_tokens": 10796224} {"current_steps": 38540, "total_steps": 40000, "loss": 0.0, "lr": 1.6440447437744698e-07, "epoch": 428.22222222222223, "percentage": 96.35, "elapsed_time": "4:22:43", "remaining_time": "0:09:57", "throughput": 684.98, "total_tokens": 10797648} {"current_steps": 38545, "total_steps": 40000, "loss": 0.0, "lr": 1.6328233706149332e-07, "epoch": 428.27777777777777, "percentage": 96.36, "elapsed_time": "4:22:45", "remaining_time": "0:09:55", "throughput": 684.99, "total_tokens": 10799088} {"current_steps": 38550, "total_steps": 40000, "loss": 0.0, "lr": 1.6216402987951906e-07, "epoch": 428.3333333333333, "percentage": 96.38, "elapsed_time": "4:22:47", "remaining_time": "0:09:53", "throughput": 684.99, "total_tokens": 10800432} {"current_steps": 38555, "total_steps": 40000, "loss": 0.0, "lr": 1.6104955300398627e-07, "epoch": 428.3888888888889, "percentage": 96.39, "elapsed_time": "4:22:49", "remaining_time": "0:09:51", "throughput": 685.0, "total_tokens": 10801824} {"current_steps": 38560, "total_steps": 40000, "loss": 0.0, "lr": 1.5993890660675748e-07, "epoch": 428.44444444444446, "percentage": 96.4, "elapsed_time": "4:22:51", "remaining_time": "0:09:48", "throughput": 685.0, "total_tokens": 10803248} {"current_steps": 38565, "total_steps": 40000, "loss": 0.0, "lr": 1.5883209085910678e-07, "epoch": 428.5, "percentage": 96.41, "elapsed_time": "4:22:53", "remaining_time": "0:09:46", "throughput": 685.01, "total_tokens": 10804656} {"current_steps": 38570, "total_steps": 40000, "loss": 0.0, "lr": 1.5772910593172264e-07, "epoch": 428.55555555555554, "percentage": 96.43, "elapsed_time": "4:22:55", "remaining_time": "0:09:44", "throughput": 685.01, "total_tokens": 10806080} {"current_steps": 38575, "total_steps": 40000, "loss": 0.0, "lr": 1.5662995199469954e-07, "epoch": 428.6111111111111, "percentage": 96.44, "elapsed_time": "4:22:56", "remaining_time": "0:09:42", "throughput": 685.01, "total_tokens": 10807440} {"current_steps": 38580, "total_steps": 40000, "loss": 0.0, "lr": 1.5553462921753802e-07, "epoch": 428.6666666666667, "percentage": 96.45, "elapsed_time": "4:22:58", "remaining_time": "0:09:40", "throughput": 685.02, "total_tokens": 10808848} {"current_steps": 38585, "total_steps": 40000, "loss": 0.0, "lr": 1.544431377691502e-07, "epoch": 428.72222222222223, "percentage": 96.46, "elapsed_time": "4:23:00", "remaining_time": "0:09:38", "throughput": 685.02, "total_tokens": 10810272} {"current_steps": 38590, "total_steps": 40000, "loss": 0.0, "lr": 1.5335547781785975e-07, "epoch": 428.77777777777777, "percentage": 96.47, "elapsed_time": "4:23:02", "remaining_time": "0:09:36", "throughput": 685.03, "total_tokens": 10811664} {"current_steps": 38595, "total_steps": 40000, "loss": 0.0, "lr": 1.5227164953139917e-07, "epoch": 428.8333333333333, "percentage": 96.49, "elapsed_time": "4:23:04", "remaining_time": "0:09:34", "throughput": 685.03, "total_tokens": 10813072} {"current_steps": 38600, "total_steps": 40000, "loss": 0.0, "lr": 1.511916530769042e-07, "epoch": 428.8888888888889, "percentage": 96.5, "elapsed_time": "4:23:06", "remaining_time": "0:09:32", "throughput": 685.04, "total_tokens": 10814480} {"current_steps": 38600, "total_steps": 40000, "eval_loss": 0.35227808356285095, "epoch": 428.8888888888889, "percentage": 96.5, "elapsed_time": "4:23:07", "remaining_time": "0:09:32", "throughput": 684.98, "total_tokens": 10814480} {"current_steps": 38605, "total_steps": 40000, "loss": 0.0, "lr": 1.5011548862092773e-07, "epoch": 428.94444444444446, "percentage": 96.51, "elapsed_time": "4:23:11", "remaining_time": "0:09:30", "throughput": 684.92, "total_tokens": 10815872} {"current_steps": 38610, "total_steps": 40000, "loss": 0.0, "lr": 1.490431563294231e-07, "epoch": 429.0, "percentage": 96.53, "elapsed_time": "4:23:13", "remaining_time": "0:09:28", "throughput": 684.91, "total_tokens": 10817248} {"current_steps": 38615, "total_steps": 40000, "loss": 0.0, "lr": 1.4797465636776365e-07, "epoch": 429.05555555555554, "percentage": 96.54, "elapsed_time": "4:23:15", "remaining_time": "0:09:26", "throughput": 684.91, "total_tokens": 10818608} {"current_steps": 38620, "total_steps": 40000, "loss": 0.0, "lr": 1.4690998890072027e-07, "epoch": 429.1111111111111, "percentage": 96.55, "elapsed_time": "4:23:17", "remaining_time": "0:09:24", "throughput": 684.91, "total_tokens": 10819952} {"current_steps": 38625, "total_steps": 40000, "loss": 0.0, "lr": 1.4584915409248112e-07, "epoch": 429.1666666666667, "percentage": 96.56, "elapsed_time": "4:23:19", "remaining_time": "0:09:22", "throughput": 684.91, "total_tokens": 10821360} {"current_steps": 38630, "total_steps": 40000, "loss": 0.0, "lr": 1.4479215210663754e-07, "epoch": 429.22222222222223, "percentage": 96.58, "elapsed_time": "4:23:21", "remaining_time": "0:09:20", "throughput": 684.92, "total_tokens": 10822784} {"current_steps": 38635, "total_steps": 40000, "loss": 0.0, "lr": 1.4373898310619528e-07, "epoch": 429.27777777777777, "percentage": 96.59, "elapsed_time": "4:23:23", "remaining_time": "0:09:18", "throughput": 684.92, "total_tokens": 10824192} {"current_steps": 38640, "total_steps": 40000, "loss": 0.0, "lr": 1.4268964725356604e-07, "epoch": 429.3333333333333, "percentage": 96.6, "elapsed_time": "4:23:25", "remaining_time": "0:09:16", "throughput": 684.92, "total_tokens": 10825552} {"current_steps": 38645, "total_steps": 40000, "loss": 0.0, "lr": 1.4164414471056764e-07, "epoch": 429.3888888888889, "percentage": 96.61, "elapsed_time": "4:23:27", "remaining_time": "0:09:14", "throughput": 684.93, "total_tokens": 10826976} {"current_steps": 38650, "total_steps": 40000, "loss": 0.0, "lr": 1.4060247563843497e-07, "epoch": 429.44444444444446, "percentage": 96.62, "elapsed_time": "4:23:29", "remaining_time": "0:09:12", "throughput": 684.94, "total_tokens": 10828384} {"current_steps": 38655, "total_steps": 40000, "loss": 0.0, "lr": 1.3956464019780068e-07, "epoch": 429.5, "percentage": 96.64, "elapsed_time": "4:23:31", "remaining_time": "0:09:10", "throughput": 684.94, "total_tokens": 10829776} {"current_steps": 38660, "total_steps": 40000, "loss": 0.0, "lr": 1.385306385487145e-07, "epoch": 429.55555555555554, "percentage": 96.65, "elapsed_time": "4:23:33", "remaining_time": "0:09:08", "throughput": 684.94, "total_tokens": 10831168} {"current_steps": 38665, "total_steps": 40000, "loss": 0.0, "lr": 1.3750047085063222e-07, "epoch": 429.6111111111111, "percentage": 96.66, "elapsed_time": "4:23:35", "remaining_time": "0:09:06", "throughput": 684.95, "total_tokens": 10832576} {"current_steps": 38670, "total_steps": 40000, "loss": 0.0, "lr": 1.3647413726242119e-07, "epoch": 429.6666666666667, "percentage": 96.67, "elapsed_time": "4:23:37", "remaining_time": "0:09:04", "throughput": 684.95, "total_tokens": 10833984} {"current_steps": 38675, "total_steps": 40000, "loss": 0.0, "lr": 1.3545163794235205e-07, "epoch": 429.72222222222223, "percentage": 96.69, "elapsed_time": "4:23:39", "remaining_time": "0:09:01", "throughput": 684.96, "total_tokens": 10835392} {"current_steps": 38680, "total_steps": 40000, "loss": 0.0, "lr": 1.3443297304810698e-07, "epoch": 429.77777777777777, "percentage": 96.7, "elapsed_time": "4:23:40", "remaining_time": "0:08:59", "throughput": 684.96, "total_tokens": 10836800} {"current_steps": 38685, "total_steps": 40000, "loss": 0.0, "lr": 1.3341814273677977e-07, "epoch": 429.8333333333333, "percentage": 96.71, "elapsed_time": "4:23:42", "remaining_time": "0:08:57", "throughput": 684.97, "total_tokens": 10838208} {"current_steps": 38690, "total_steps": 40000, "loss": 0.0, "lr": 1.324071471648647e-07, "epoch": 429.8888888888889, "percentage": 96.73, "elapsed_time": "4:23:44", "remaining_time": "0:08:55", "throughput": 684.98, "total_tokens": 10839632} {"current_steps": 38695, "total_steps": 40000, "loss": 0.0, "lr": 1.3139998648827312e-07, "epoch": 429.94444444444446, "percentage": 96.74, "elapsed_time": "4:23:46", "remaining_time": "0:08:53", "throughput": 684.98, "total_tokens": 10840992} {"current_steps": 38700, "total_steps": 40000, "loss": 0.0, "lr": 1.3039666086232526e-07, "epoch": 430.0, "percentage": 96.75, "elapsed_time": "4:23:48", "remaining_time": "0:08:51", "throughput": 684.98, "total_tokens": 10842416} {"current_steps": 38705, "total_steps": 40000, "loss": 0.0, "lr": 1.2939717044174183e-07, "epoch": 430.05555555555554, "percentage": 96.76, "elapsed_time": "4:23:51", "remaining_time": "0:08:49", "throughput": 684.97, "total_tokens": 10843824} {"current_steps": 38710, "total_steps": 40000, "loss": 0.0, "lr": 1.284015153806578e-07, "epoch": 430.1111111111111, "percentage": 96.78, "elapsed_time": "4:23:53", "remaining_time": "0:08:47", "throughput": 684.97, "total_tokens": 10845200} {"current_steps": 38715, "total_steps": 40000, "loss": 0.0, "lr": 1.274096958326171e-07, "epoch": 430.1666666666667, "percentage": 96.79, "elapsed_time": "4:23:54", "remaining_time": "0:08:45", "throughput": 684.98, "total_tokens": 10846592} {"current_steps": 38720, "total_steps": 40000, "loss": 0.0, "lr": 1.2642171195056952e-07, "epoch": 430.22222222222223, "percentage": 96.8, "elapsed_time": "4:23:56", "remaining_time": "0:08:43", "throughput": 684.98, "total_tokens": 10848016} {"current_steps": 38725, "total_steps": 40000, "loss": 0.0, "lr": 1.2543756388687377e-07, "epoch": 430.27777777777777, "percentage": 96.81, "elapsed_time": "4:23:58", "remaining_time": "0:08:41", "throughput": 684.99, "total_tokens": 10849408} {"current_steps": 38730, "total_steps": 40000, "loss": 0.0, "lr": 1.2445725179330014e-07, "epoch": 430.3333333333333, "percentage": 96.83, "elapsed_time": "4:24:00", "remaining_time": "0:08:39", "throughput": 684.99, "total_tokens": 10850816} {"current_steps": 38735, "total_steps": 40000, "loss": 0.0, "lr": 1.2348077582102212e-07, "epoch": 430.3888888888889, "percentage": 96.84, "elapsed_time": "4:24:02", "remaining_time": "0:08:37", "throughput": 685.0, "total_tokens": 10852256} {"current_steps": 38740, "total_steps": 40000, "loss": 0.0, "lr": 1.2250813612062762e-07, "epoch": 430.44444444444446, "percentage": 96.85, "elapsed_time": "4:24:04", "remaining_time": "0:08:35", "throughput": 685.0, "total_tokens": 10853632} {"current_steps": 38745, "total_steps": 40000, "loss": 0.0, "lr": 1.215393328421105e-07, "epoch": 430.5, "percentage": 96.86, "elapsed_time": "4:24:06", "remaining_time": "0:08:33", "throughput": 685.01, "total_tokens": 10855024} {"current_steps": 38750, "total_steps": 40000, "loss": 0.0, "lr": 1.2057436613486796e-07, "epoch": 430.55555555555554, "percentage": 96.88, "elapsed_time": "4:24:08", "remaining_time": "0:08:31", "throughput": 685.01, "total_tokens": 10856368} {"current_steps": 38755, "total_steps": 40000, "loss": 0.0, "lr": 1.1961323614771424e-07, "epoch": 430.6111111111111, "percentage": 96.89, "elapsed_time": "4:24:10", "remaining_time": "0:08:29", "throughput": 685.01, "total_tokens": 10857792} {"current_steps": 38760, "total_steps": 40000, "loss": 0.0, "lr": 1.1865594302886418e-07, "epoch": 430.6666666666667, "percentage": 96.9, "elapsed_time": "4:24:12", "remaining_time": "0:08:27", "throughput": 685.02, "total_tokens": 10859200} {"current_steps": 38765, "total_steps": 40000, "loss": 0.0, "lr": 1.1770248692594687e-07, "epoch": 430.72222222222223, "percentage": 96.91, "elapsed_time": "4:24:14", "remaining_time": "0:08:25", "throughput": 685.02, "total_tokens": 10860560} {"current_steps": 38770, "total_steps": 40000, "loss": 0.0, "lr": 1.167528679859975e-07, "epoch": 430.77777777777777, "percentage": 96.92, "elapsed_time": "4:24:16", "remaining_time": "0:08:23", "throughput": 685.02, "total_tokens": 10861984} {"current_steps": 38775, "total_steps": 40000, "loss": 0.0, "lr": 1.1580708635545446e-07, "epoch": 430.8333333333333, "percentage": 96.94, "elapsed_time": "4:24:18", "remaining_time": "0:08:21", "throughput": 685.03, "total_tokens": 10863440} {"current_steps": 38780, "total_steps": 40000, "loss": 0.0, "lr": 1.1486514218017885e-07, "epoch": 430.8888888888889, "percentage": 96.95, "elapsed_time": "4:24:20", "remaining_time": "0:08:18", "throughput": 685.03, "total_tokens": 10864816} {"current_steps": 38785, "total_steps": 40000, "loss": 0.0, "lr": 1.1392703560542117e-07, "epoch": 430.94444444444446, "percentage": 96.96, "elapsed_time": "4:24:22", "remaining_time": "0:08:16", "throughput": 685.03, "total_tokens": 10866208} {"current_steps": 38790, "total_steps": 40000, "loss": 0.0, "lr": 1.129927667758518e-07, "epoch": 431.0, "percentage": 96.97, "elapsed_time": "4:24:24", "remaining_time": "0:08:14", "throughput": 685.03, "total_tokens": 10867632} {"current_steps": 38795, "total_steps": 40000, "loss": 0.0, "lr": 1.1206233583554992e-07, "epoch": 431.05555555555554, "percentage": 96.99, "elapsed_time": "4:24:26", "remaining_time": "0:08:12", "throughput": 685.02, "total_tokens": 10869024} {"current_steps": 38800, "total_steps": 40000, "loss": 0.0, "lr": 1.1113574292799523e-07, "epoch": 431.1111111111111, "percentage": 97.0, "elapsed_time": "4:24:28", "remaining_time": "0:08:10", "throughput": 685.02, "total_tokens": 10870400} {"current_steps": 38800, "total_steps": 40000, "eval_loss": 0.37556880712509155, "epoch": 431.1111111111111, "percentage": 97.0, "elapsed_time": "4:24:29", "remaining_time": "0:08:10", "throughput": 684.97, "total_tokens": 10870400} {"current_steps": 38805, "total_steps": 40000, "loss": 0.0, "lr": 1.1021298819608449e-07, "epoch": 431.1666666666667, "percentage": 97.01, "elapsed_time": "4:24:33", "remaining_time": "0:08:08", "throughput": 684.91, "total_tokens": 10871840} {"current_steps": 38810, "total_steps": 40000, "loss": 0.0, "lr": 1.0929407178211226e-07, "epoch": 431.22222222222223, "percentage": 97.02, "elapsed_time": "4:24:35", "remaining_time": "0:08:06", "throughput": 684.91, "total_tokens": 10873232} {"current_steps": 38815, "total_steps": 40000, "loss": 0.0, "lr": 1.0837899382779293e-07, "epoch": 431.27777777777777, "percentage": 97.04, "elapsed_time": "4:24:37", "remaining_time": "0:08:04", "throughput": 684.91, "total_tokens": 10874592} {"current_steps": 38820, "total_steps": 40000, "loss": 0.0, "lr": 1.0746775447423862e-07, "epoch": 431.3333333333333, "percentage": 97.05, "elapsed_time": "4:24:39", "remaining_time": "0:08:02", "throughput": 684.92, "total_tokens": 10876000} {"current_steps": 38825, "total_steps": 40000, "loss": 0.0, "lr": 1.0656035386197583e-07, "epoch": 431.3888888888889, "percentage": 97.06, "elapsed_time": "4:24:41", "remaining_time": "0:08:00", "throughput": 684.92, "total_tokens": 10877344} {"current_steps": 38830, "total_steps": 40000, "loss": 0.0, "lr": 1.0565679213093982e-07, "epoch": 431.44444444444446, "percentage": 97.08, "elapsed_time": "4:24:43", "remaining_time": "0:07:58", "throughput": 684.92, "total_tokens": 10878720} {"current_steps": 38835, "total_steps": 40000, "loss": 0.0, "lr": 1.0475706942046638e-07, "epoch": 431.5, "percentage": 97.09, "elapsed_time": "4:24:45", "remaining_time": "0:07:56", "throughput": 684.92, "total_tokens": 10880064} {"current_steps": 38840, "total_steps": 40000, "loss": 0.0, "lr": 1.0386118586930282e-07, "epoch": 431.55555555555554, "percentage": 97.1, "elapsed_time": "4:24:46", "remaining_time": "0:07:54", "throughput": 684.93, "total_tokens": 10881488} {"current_steps": 38845, "total_steps": 40000, "loss": 0.0, "lr": 1.0296914161561367e-07, "epoch": 431.6111111111111, "percentage": 97.11, "elapsed_time": "4:24:48", "remaining_time": "0:07:52", "throughput": 684.94, "total_tokens": 10882896} {"current_steps": 38850, "total_steps": 40000, "loss": 0.0, "lr": 1.0208093679695552e-07, "epoch": 431.6666666666667, "percentage": 97.12, "elapsed_time": "4:24:50", "remaining_time": "0:07:50", "throughput": 684.94, "total_tokens": 10884256} {"current_steps": 38855, "total_steps": 40000, "loss": 0.0, "lr": 1.0119657155030493e-07, "epoch": 431.72222222222223, "percentage": 97.14, "elapsed_time": "4:24:52", "remaining_time": "0:07:48", "throughput": 684.94, "total_tokens": 10885600} {"current_steps": 38860, "total_steps": 40000, "loss": 0.0, "lr": 1.003160460120417e-07, "epoch": 431.77777777777777, "percentage": 97.15, "elapsed_time": "4:24:54", "remaining_time": "0:07:46", "throughput": 684.95, "total_tokens": 10887056} {"current_steps": 38865, "total_steps": 40000, "loss": 0.0, "lr": 9.943936031795165e-08, "epoch": 431.8333333333333, "percentage": 97.16, "elapsed_time": "4:24:56", "remaining_time": "0:07:44", "throughput": 684.95, "total_tokens": 10888464} {"current_steps": 38870, "total_steps": 40000, "loss": 0.0, "lr": 9.856651460323219e-08, "epoch": 431.8888888888889, "percentage": 97.17, "elapsed_time": "4:24:58", "remaining_time": "0:07:42", "throughput": 684.96, "total_tokens": 10889920} {"current_steps": 38875, "total_steps": 40000, "loss": 0.0, "lr": 9.769750900248953e-08, "epoch": 431.94444444444446, "percentage": 97.19, "elapsed_time": "4:25:00", "remaining_time": "0:07:40", "throughput": 684.96, "total_tokens": 10891312} {"current_steps": 38880, "total_steps": 40000, "loss": 0.0, "lr": 9.683234364973038e-08, "epoch": 432.0, "percentage": 97.2, "elapsed_time": "4:25:02", "remaining_time": "0:07:38", "throughput": 684.96, "total_tokens": 10892736} {"current_steps": 38885, "total_steps": 40000, "loss": 0.0, "lr": 9.597101867837854e-08, "epoch": 432.05555555555554, "percentage": 97.21, "elapsed_time": "4:25:04", "remaining_time": "0:07:36", "throughput": 684.95, "total_tokens": 10894112} {"current_steps": 38890, "total_steps": 40000, "loss": 0.0, "lr": 9.511353422125835e-08, "epoch": 432.1111111111111, "percentage": 97.22, "elapsed_time": "4:25:06", "remaining_time": "0:07:34", "throughput": 684.96, "total_tokens": 10895504} {"current_steps": 38895, "total_steps": 40000, "loss": 0.0, "lr": 9.42598904106029e-08, "epoch": 432.1666666666667, "percentage": 97.24, "elapsed_time": "4:25:08", "remaining_time": "0:07:31", "throughput": 684.96, "total_tokens": 10896864} {"current_steps": 38900, "total_steps": 40000, "loss": 0.0, "lr": 9.341008737806245e-08, "epoch": 432.22222222222223, "percentage": 97.25, "elapsed_time": "4:25:10", "remaining_time": "0:07:29", "throughput": 684.97, "total_tokens": 10898272} {"current_steps": 38905, "total_steps": 40000, "loss": 0.0, "lr": 9.256412525467661e-08, "epoch": 432.27777777777777, "percentage": 97.26, "elapsed_time": "4:25:12", "remaining_time": "0:07:27", "throughput": 684.97, "total_tokens": 10899680} {"current_steps": 38910, "total_steps": 40000, "loss": 0.0, "lr": 9.172200417091326e-08, "epoch": 432.3333333333333, "percentage": 97.28, "elapsed_time": "4:25:14", "remaining_time": "0:07:25", "throughput": 684.98, "total_tokens": 10901088} {"current_steps": 38915, "total_steps": 40000, "loss": 0.0, "lr": 9.088372425663239e-08, "epoch": 432.3888888888889, "percentage": 97.29, "elapsed_time": "4:25:16", "remaining_time": "0:07:23", "throughput": 684.98, "total_tokens": 10902496} {"current_steps": 38920, "total_steps": 40000, "loss": 0.0, "lr": 9.004928564110837e-08, "epoch": 432.44444444444446, "percentage": 97.3, "elapsed_time": "4:25:18", "remaining_time": "0:07:21", "throughput": 684.98, "total_tokens": 10903872} {"current_steps": 38925, "total_steps": 40000, "loss": 0.0, "lr": 8.92186884530244e-08, "epoch": 432.5, "percentage": 97.31, "elapsed_time": "4:25:20", "remaining_time": "0:07:19", "throughput": 684.98, "total_tokens": 10905232} {"current_steps": 38930, "total_steps": 40000, "loss": 0.0, "lr": 8.83919328204641e-08, "epoch": 432.55555555555554, "percentage": 97.32, "elapsed_time": "4:25:22", "remaining_time": "0:07:17", "throughput": 684.99, "total_tokens": 10906624} {"current_steps": 38935, "total_steps": 40000, "loss": 0.0, "lr": 8.756901887093105e-08, "epoch": 432.6111111111111, "percentage": 97.34, "elapsed_time": "4:25:24", "remaining_time": "0:07:15", "throughput": 684.99, "total_tokens": 10907984} {"current_steps": 38940, "total_steps": 40000, "loss": 0.0, "lr": 8.674994673132098e-08, "epoch": 432.6666666666667, "percentage": 97.35, "elapsed_time": "4:25:26", "remaining_time": "0:07:13", "throughput": 685.0, "total_tokens": 10909392} {"current_steps": 38945, "total_steps": 40000, "loss": 0.0, "lr": 8.593471652794949e-08, "epoch": 432.72222222222223, "percentage": 97.36, "elapsed_time": "4:25:28", "remaining_time": "0:07:11", "throughput": 685.0, "total_tokens": 10910784} {"current_steps": 38950, "total_steps": 40000, "loss": 0.0, "lr": 8.512332838653548e-08, "epoch": 432.77777777777777, "percentage": 97.38, "elapsed_time": "4:25:30", "remaining_time": "0:07:09", "throughput": 685.01, "total_tokens": 10912208} {"current_steps": 38955, "total_steps": 40000, "loss": 0.0, "lr": 8.431578243220106e-08, "epoch": 432.8333333333333, "percentage": 97.39, "elapsed_time": "4:25:32", "remaining_time": "0:07:07", "throughput": 685.01, "total_tokens": 10913616} {"current_steps": 38960, "total_steps": 40000, "loss": 0.0, "lr": 8.351207878948552e-08, "epoch": 432.8888888888889, "percentage": 97.4, "elapsed_time": "4:25:33", "remaining_time": "0:07:05", "throughput": 685.02, "total_tokens": 10915040} {"current_steps": 38965, "total_steps": 40000, "loss": 0.0, "lr": 8.271221758232583e-08, "epoch": 432.94444444444446, "percentage": 97.41, "elapsed_time": "4:25:35", "remaining_time": "0:07:03", "throughput": 685.02, "total_tokens": 10916480} {"current_steps": 38970, "total_steps": 40000, "loss": 0.0, "lr": 8.191619893407332e-08, "epoch": 433.0, "percentage": 97.42, "elapsed_time": "4:25:38", "remaining_time": "0:07:01", "throughput": 685.02, "total_tokens": 10917888} {"current_steps": 38975, "total_steps": 40000, "loss": 0.0, "lr": 8.112402296748534e-08, "epoch": 433.05555555555554, "percentage": 97.44, "elapsed_time": "4:25:40", "remaining_time": "0:06:59", "throughput": 685.02, "total_tokens": 10919344} {"current_steps": 38980, "total_steps": 40000, "loss": 0.0, "lr": 8.033568980471973e-08, "epoch": 433.1111111111111, "percentage": 97.45, "elapsed_time": "4:25:42", "remaining_time": "0:06:57", "throughput": 685.02, "total_tokens": 10920752} {"current_steps": 38985, "total_steps": 40000, "loss": 0.0, "lr": 7.955119956735146e-08, "epoch": 433.1666666666667, "percentage": 97.46, "elapsed_time": "4:25:44", "remaining_time": "0:06:55", "throughput": 685.03, "total_tokens": 10922112} {"current_steps": 38990, "total_steps": 40000, "loss": 0.0, "lr": 7.877055237636155e-08, "epoch": 433.22222222222223, "percentage": 97.47, "elapsed_time": "4:25:46", "remaining_time": "0:06:53", "throughput": 685.03, "total_tokens": 10923504} {"current_steps": 38995, "total_steps": 40000, "loss": 0.0, "lr": 7.79937483521287e-08, "epoch": 433.27777777777777, "percentage": 97.49, "elapsed_time": "4:25:47", "remaining_time": "0:06:51", "throughput": 685.03, "total_tokens": 10924912} {"current_steps": 39000, "total_steps": 40000, "loss": 0.0, "lr": 7.722078761444873e-08, "epoch": 433.3333333333333, "percentage": 97.5, "elapsed_time": "4:25:49", "remaining_time": "0:06:48", "throughput": 685.04, "total_tokens": 10926320} {"current_steps": 39000, "total_steps": 40000, "eval_loss": 0.39856666326522827, "epoch": 433.3333333333333, "percentage": 97.5, "elapsed_time": "4:25:51", "remaining_time": "0:06:49", "throughput": 684.98, "total_tokens": 10926320} {"current_steps": 39005, "total_steps": 40000, "loss": 0.0, "lr": 7.645167028252631e-08, "epoch": 433.3888888888889, "percentage": 97.51, "elapsed_time": "4:25:54", "remaining_time": "0:06:46", "throughput": 684.93, "total_tokens": 10927680} {"current_steps": 39010, "total_steps": 40000, "loss": 0.0, "lr": 7.568639647496379e-08, "epoch": 433.44444444444446, "percentage": 97.52, "elapsed_time": "4:25:56", "remaining_time": "0:06:44", "throughput": 684.93, "total_tokens": 10929072} {"current_steps": 39015, "total_steps": 40000, "loss": 0.0, "lr": 7.492496630977508e-08, "epoch": 433.5, "percentage": 97.54, "elapsed_time": "4:25:58", "remaining_time": "0:06:42", "throughput": 684.93, "total_tokens": 10930464} {"current_steps": 39020, "total_steps": 40000, "loss": 0.0, "lr": 7.416737990438571e-08, "epoch": 433.55555555555554, "percentage": 97.55, "elapsed_time": "4:26:00", "remaining_time": "0:06:40", "throughput": 684.94, "total_tokens": 10931872} {"current_steps": 39025, "total_steps": 40000, "loss": 0.0, "lr": 7.341363737562445e-08, "epoch": 433.6111111111111, "percentage": 97.56, "elapsed_time": "4:26:02", "remaining_time": "0:06:38", "throughput": 684.94, "total_tokens": 10933328} {"current_steps": 39030, "total_steps": 40000, "loss": 0.0, "lr": 7.266373883972887e-08, "epoch": 433.6666666666667, "percentage": 97.58, "elapsed_time": "4:26:04", "remaining_time": "0:06:36", "throughput": 684.95, "total_tokens": 10934720} {"current_steps": 39035, "total_steps": 40000, "loss": 0.0, "lr": 7.191768441233981e-08, "epoch": 433.72222222222223, "percentage": 97.59, "elapsed_time": "4:26:06", "remaining_time": "0:06:34", "throughput": 684.95, "total_tokens": 10936144} {"current_steps": 39040, "total_steps": 40000, "loss": 0.0, "lr": 7.11754742085069e-08, "epoch": 433.77777777777777, "percentage": 97.6, "elapsed_time": "4:26:08", "remaining_time": "0:06:32", "throughput": 684.96, "total_tokens": 10937568} {"current_steps": 39045, "total_steps": 40000, "loss": 0.0, "lr": 7.043710834269413e-08, "epoch": 433.8333333333333, "percentage": 97.61, "elapsed_time": "4:26:10", "remaining_time": "0:06:30", "throughput": 684.97, "total_tokens": 10938960} {"current_steps": 39050, "total_steps": 40000, "loss": 0.0, "lr": 6.970258692876319e-08, "epoch": 433.8888888888889, "percentage": 97.62, "elapsed_time": "4:26:12", "remaining_time": "0:06:28", "throughput": 684.97, "total_tokens": 10940320} {"current_steps": 39055, "total_steps": 40000, "loss": 0.0, "lr": 6.897191007998738e-08, "epoch": 433.94444444444446, "percentage": 97.64, "elapsed_time": "4:26:13", "remaining_time": "0:06:26", "throughput": 684.97, "total_tokens": 10941712} {"current_steps": 39060, "total_steps": 40000, "loss": 0.0, "lr": 6.824507790904599e-08, "epoch": 434.0, "percentage": 97.65, "elapsed_time": "4:26:16", "remaining_time": "0:06:24", "throughput": 684.97, "total_tokens": 10943104} {"current_steps": 39065, "total_steps": 40000, "loss": 0.0, "lr": 6.752209052802439e-08, "epoch": 434.05555555555554, "percentage": 97.66, "elapsed_time": "4:26:18", "remaining_time": "0:06:22", "throughput": 684.96, "total_tokens": 10944512} {"current_steps": 39070, "total_steps": 40000, "loss": 0.0, "lr": 6.680294804841946e-08, "epoch": 434.1111111111111, "percentage": 97.67, "elapsed_time": "4:26:20", "remaining_time": "0:06:20", "throughput": 684.96, "total_tokens": 10945872} {"current_steps": 39075, "total_steps": 40000, "loss": 0.0, "lr": 6.608765058112865e-08, "epoch": 434.1666666666667, "percentage": 97.69, "elapsed_time": "4:26:22", "remaining_time": "0:06:18", "throughput": 684.97, "total_tokens": 10947264} {"current_steps": 39080, "total_steps": 40000, "loss": 0.0, "lr": 6.537619823646368e-08, "epoch": 434.22222222222223, "percentage": 97.7, "elapsed_time": "4:26:24", "remaining_time": "0:06:16", "throughput": 684.97, "total_tokens": 10948640} {"current_steps": 39085, "total_steps": 40000, "loss": 0.0, "lr": 6.466859112413404e-08, "epoch": 434.27777777777777, "percentage": 97.71, "elapsed_time": "4:26:26", "remaining_time": "0:06:14", "throughput": 684.98, "total_tokens": 10950096} {"current_steps": 39090, "total_steps": 40000, "loss": 0.0, "lr": 6.39648293532663e-08, "epoch": 434.3333333333333, "percentage": 97.72, "elapsed_time": "4:26:27", "remaining_time": "0:06:12", "throughput": 684.98, "total_tokens": 10951504} {"current_steps": 39095, "total_steps": 40000, "loss": 0.0, "lr": 6.32649130323848e-08, "epoch": 434.3888888888889, "percentage": 97.74, "elapsed_time": "4:26:29", "remaining_time": "0:06:10", "throughput": 684.99, "total_tokens": 10952912} {"current_steps": 39100, "total_steps": 40000, "loss": 0.0, "lr": 6.256884226943094e-08, "epoch": 434.44444444444446, "percentage": 97.75, "elapsed_time": "4:26:31", "remaining_time": "0:06:08", "throughput": 684.99, "total_tokens": 10954304} {"current_steps": 39105, "total_steps": 40000, "loss": 0.0, "lr": 6.187661717174386e-08, "epoch": 434.5, "percentage": 97.76, "elapsed_time": "4:26:33", "remaining_time": "0:06:06", "throughput": 685.0, "total_tokens": 10955712} {"current_steps": 39110, "total_steps": 40000, "loss": 0.0, "lr": 6.118823784607708e-08, "epoch": 434.55555555555554, "percentage": 97.78, "elapsed_time": "4:26:35", "remaining_time": "0:06:04", "throughput": 685.0, "total_tokens": 10957056} {"current_steps": 39115, "total_steps": 40000, "loss": 0.0, "lr": 6.050370439858178e-08, "epoch": 434.6111111111111, "percentage": 97.79, "elapsed_time": "4:26:37", "remaining_time": "0:06:01", "throughput": 685.0, "total_tokens": 10958432} {"current_steps": 39120, "total_steps": 40000, "loss": 0.0, "lr": 5.98230169348235e-08, "epoch": 434.6666666666667, "percentage": 97.8, "elapsed_time": "4:26:39", "remaining_time": "0:05:59", "throughput": 685.01, "total_tokens": 10959824} {"current_steps": 39125, "total_steps": 40000, "loss": 0.0, "lr": 5.914617555977664e-08, "epoch": 434.72222222222223, "percentage": 97.81, "elapsed_time": "4:26:41", "remaining_time": "0:05:57", "throughput": 685.01, "total_tokens": 10961248} {"current_steps": 39130, "total_steps": 40000, "loss": 0.0, "lr": 5.8473180377816017e-08, "epoch": 434.77777777777777, "percentage": 97.82, "elapsed_time": "4:26:43", "remaining_time": "0:05:55", "throughput": 685.02, "total_tokens": 10962640} {"current_steps": 39135, "total_steps": 40000, "loss": 0.0, "lr": 5.780403149272251e-08, "epoch": 434.8333333333333, "percentage": 97.84, "elapsed_time": "4:26:45", "remaining_time": "0:05:53", "throughput": 685.02, "total_tokens": 10964080} {"current_steps": 39140, "total_steps": 40000, "loss": 0.0, "lr": 5.7138729007694126e-08, "epoch": 434.8888888888889, "percentage": 97.85, "elapsed_time": "4:26:47", "remaining_time": "0:05:51", "throughput": 685.03, "total_tokens": 10965504} {"current_steps": 39145, "total_steps": 40000, "loss": 0.0, "lr": 5.64772730253238e-08, "epoch": 434.94444444444446, "percentage": 97.86, "elapsed_time": "4:26:49", "remaining_time": "0:05:49", "throughput": 685.04, "total_tokens": 10966928} {"current_steps": 39150, "total_steps": 40000, "loss": 0.0, "lr": 5.5819663647618814e-08, "epoch": 435.0, "percentage": 97.88, "elapsed_time": "4:26:51", "remaining_time": "0:05:47", "throughput": 685.03, "total_tokens": 10968336} {"current_steps": 39155, "total_steps": 40000, "loss": 0.0, "lr": 5.5165900975989723e-08, "epoch": 435.05555555555554, "percentage": 97.89, "elapsed_time": "4:26:53", "remaining_time": "0:05:45", "throughput": 685.03, "total_tokens": 10969728} {"current_steps": 39160, "total_steps": 40000, "loss": 0.0, "lr": 5.451598511125311e-08, "epoch": 435.1111111111111, "percentage": 97.9, "elapsed_time": "4:26:55", "remaining_time": "0:05:43", "throughput": 685.03, "total_tokens": 10971168} {"current_steps": 39165, "total_steps": 40000, "loss": 0.0, "lr": 5.3869916153637124e-08, "epoch": 435.1666666666667, "percentage": 97.91, "elapsed_time": "4:26:57", "remaining_time": "0:05:41", "throughput": 685.03, "total_tokens": 10972512} {"current_steps": 39170, "total_steps": 40000, "loss": 0.0, "lr": 5.322769420277318e-08, "epoch": 435.22222222222223, "percentage": 97.92, "elapsed_time": "4:26:59", "remaining_time": "0:05:39", "throughput": 685.03, "total_tokens": 10973856} {"current_steps": 39175, "total_steps": 40000, "loss": 0.0, "lr": 5.258931935769873e-08, "epoch": 435.27777777777777, "percentage": 97.94, "elapsed_time": "4:27:01", "remaining_time": "0:05:37", "throughput": 685.04, "total_tokens": 10975264} {"current_steps": 39180, "total_steps": 40000, "loss": 0.0, "lr": 5.19547917168628e-08, "epoch": 435.3333333333333, "percentage": 97.95, "elapsed_time": "4:27:03", "remaining_time": "0:05:35", "throughput": 685.04, "total_tokens": 10976608} {"current_steps": 39185, "total_steps": 40000, "loss": 0.0, "lr": 5.13241113781121e-08, "epoch": 435.3888888888889, "percentage": 97.96, "elapsed_time": "4:27:05", "remaining_time": "0:05:33", "throughput": 685.05, "total_tokens": 10978032} {"current_steps": 39190, "total_steps": 40000, "loss": 0.0, "lr": 5.0697278438707755e-08, "epoch": 435.44444444444446, "percentage": 97.97, "elapsed_time": "4:27:07", "remaining_time": "0:05:31", "throughput": 685.05, "total_tokens": 10979440} {"current_steps": 39195, "total_steps": 40000, "loss": 0.0, "lr": 5.0074292995316854e-08, "epoch": 435.5, "percentage": 97.99, "elapsed_time": "4:27:09", "remaining_time": "0:05:29", "throughput": 685.06, "total_tokens": 10980832} {"current_steps": 39200, "total_steps": 40000, "loss": 0.0, "lr": 4.945515514400978e-08, "epoch": 435.55555555555554, "percentage": 98.0, "elapsed_time": "4:27:11", "remaining_time": "0:05:27", "throughput": 685.06, "total_tokens": 10982240} {"current_steps": 39200, "total_steps": 40000, "eval_loss": 0.35255178809165955, "epoch": 435.55555555555554, "percentage": 98.0, "elapsed_time": "4:27:12", "remaining_time": "0:05:27", "throughput": 685.01, "total_tokens": 10982240} {"current_steps": 39205, "total_steps": 40000, "loss": 0.0, "lr": 4.883986498026571e-08, "epoch": 435.6111111111111, "percentage": 98.01, "elapsed_time": "4:27:15", "remaining_time": "0:05:25", "throughput": 684.95, "total_tokens": 10983568} {"current_steps": 39210, "total_steps": 40000, "loss": 0.0, "lr": 4.822842259896987e-08, "epoch": 435.6666666666667, "percentage": 98.02, "elapsed_time": "4:27:17", "remaining_time": "0:05:23", "throughput": 684.95, "total_tokens": 10984944} {"current_steps": 39215, "total_steps": 40000, "loss": 0.0, "lr": 4.762082809441626e-08, "epoch": 435.72222222222223, "percentage": 98.04, "elapsed_time": "4:27:19", "remaining_time": "0:05:21", "throughput": 684.95, "total_tokens": 10986320} {"current_steps": 39220, "total_steps": 40000, "loss": 0.0, "lr": 4.7017081560302156e-08, "epoch": 435.77777777777777, "percentage": 98.05, "elapsed_time": "4:27:21", "remaining_time": "0:05:19", "throughput": 684.95, "total_tokens": 10987696} {"current_steps": 39225, "total_steps": 40000, "loss": 0.0, "lr": 4.6417183089730866e-08, "epoch": 435.8333333333333, "percentage": 98.06, "elapsed_time": "4:27:23", "remaining_time": "0:05:16", "throughput": 684.96, "total_tokens": 10989200} {"current_steps": 39230, "total_steps": 40000, "loss": 0.0, "lr": 4.5821132775217265e-08, "epoch": 435.8888888888889, "percentage": 98.08, "elapsed_time": "4:27:25", "remaining_time": "0:05:14", "throughput": 684.97, "total_tokens": 10990640} {"current_steps": 39235, "total_steps": 40000, "loss": 0.0, "lr": 4.5228930708679504e-08, "epoch": 435.94444444444446, "percentage": 98.09, "elapsed_time": "4:27:27", "remaining_time": "0:05:12", "throughput": 684.98, "total_tokens": 10992064} {"current_steps": 39240, "total_steps": 40000, "loss": 0.0, "lr": 4.464057698144175e-08, "epoch": 436.0, "percentage": 98.1, "elapsed_time": "4:27:29", "remaining_time": "0:05:10", "throughput": 684.98, "total_tokens": 10993520} {"current_steps": 39245, "total_steps": 40000, "loss": 0.0, "lr": 4.4056071684236974e-08, "epoch": 436.05555555555554, "percentage": 98.11, "elapsed_time": "4:27:31", "remaining_time": "0:05:08", "throughput": 684.97, "total_tokens": 10994944} {"current_steps": 39250, "total_steps": 40000, "loss": 0.0, "lr": 4.347541490719864e-08, "epoch": 436.1111111111111, "percentage": 98.12, "elapsed_time": "4:27:33", "remaining_time": "0:05:06", "throughput": 684.98, "total_tokens": 10996368} {"current_steps": 39255, "total_steps": 40000, "loss": 0.0, "lr": 4.2898606739877336e-08, "epoch": 436.1666666666667, "percentage": 98.14, "elapsed_time": "4:27:35", "remaining_time": "0:05:04", "throughput": 684.98, "total_tokens": 10997792} {"current_steps": 39260, "total_steps": 40000, "loss": 0.0, "lr": 4.232564727122135e-08, "epoch": 436.22222222222223, "percentage": 98.15, "elapsed_time": "4:27:37", "remaining_time": "0:05:02", "throughput": 684.99, "total_tokens": 10999216} {"current_steps": 39265, "total_steps": 40000, "loss": 0.0, "lr": 4.1756536589585004e-08, "epoch": 436.27777777777777, "percentage": 98.16, "elapsed_time": "4:27:39", "remaining_time": "0:05:00", "throughput": 684.99, "total_tokens": 11000576} {"current_steps": 39270, "total_steps": 40000, "loss": 0.0, "lr": 4.119127478273976e-08, "epoch": 436.3333333333333, "percentage": 98.17, "elapsed_time": "4:27:41", "remaining_time": "0:04:58", "throughput": 685.0, "total_tokens": 11002032} {"current_steps": 39275, "total_steps": 40000, "loss": 0.0, "lr": 4.062986193784923e-08, "epoch": 436.3888888888889, "percentage": 98.19, "elapsed_time": "4:27:43", "remaining_time": "0:04:56", "throughput": 685.0, "total_tokens": 11003392} {"current_steps": 39280, "total_steps": 40000, "loss": 0.0, "lr": 4.007229814149416e-08, "epoch": 436.44444444444446, "percentage": 98.2, "elapsed_time": "4:27:45", "remaining_time": "0:04:54", "throughput": 685.01, "total_tokens": 11004768} {"current_steps": 39285, "total_steps": 40000, "loss": 0.0, "lr": 3.951858347965576e-08, "epoch": 436.5, "percentage": 98.21, "elapsed_time": "4:27:47", "remaining_time": "0:04:52", "throughput": 685.01, "total_tokens": 11006128} {"current_steps": 39290, "total_steps": 40000, "loss": 0.0, "lr": 3.896871803772684e-08, "epoch": 436.55555555555554, "percentage": 98.22, "elapsed_time": "4:27:49", "remaining_time": "0:04:50", "throughput": 685.01, "total_tokens": 11007552} {"current_steps": 39295, "total_steps": 40000, "loss": 0.0, "lr": 3.842270190050068e-08, "epoch": 436.6111111111111, "percentage": 98.24, "elapsed_time": "4:27:51", "remaining_time": "0:04:48", "throughput": 685.02, "total_tokens": 11008928} {"current_steps": 39300, "total_steps": 40000, "loss": 0.0, "lr": 3.7880535152179376e-08, "epoch": 436.6666666666667, "percentage": 98.25, "elapsed_time": "4:27:53", "remaining_time": "0:04:46", "throughput": 685.02, "total_tokens": 11010272} {"current_steps": 39305, "total_steps": 40000, "loss": 0.0, "lr": 3.734221787637382e-08, "epoch": 436.72222222222223, "percentage": 98.26, "elapsed_time": "4:27:54", "remaining_time": "0:04:44", "throughput": 685.02, "total_tokens": 11011664} {"current_steps": 39310, "total_steps": 40000, "loss": 0.0, "lr": 3.680775015609817e-08, "epoch": 436.77777777777777, "percentage": 98.28, "elapsed_time": "4:27:56", "remaining_time": "0:04:42", "throughput": 685.02, "total_tokens": 11013024} {"current_steps": 39315, "total_steps": 40000, "loss": 0.0, "lr": 3.627713207377537e-08, "epoch": 436.8333333333333, "percentage": 98.29, "elapsed_time": "4:27:58", "remaining_time": "0:04:40", "throughput": 685.03, "total_tokens": 11014480} {"current_steps": 39320, "total_steps": 40000, "loss": 0.0, "lr": 3.575036371123164e-08, "epoch": 436.8888888888889, "percentage": 98.3, "elapsed_time": "4:28:00", "remaining_time": "0:04:38", "throughput": 685.04, "total_tokens": 11015888} {"current_steps": 39325, "total_steps": 40000, "loss": 0.0, "lr": 3.5227445149704776e-08, "epoch": 436.94444444444446, "percentage": 98.31, "elapsed_time": "4:28:02", "remaining_time": "0:04:36", "throughput": 685.04, "total_tokens": 11017328} {"current_steps": 39330, "total_steps": 40000, "loss": 0.0, "lr": 3.470837646983027e-08, "epoch": 437.0, "percentage": 98.32, "elapsed_time": "4:28:04", "remaining_time": "0:04:34", "throughput": 685.04, "total_tokens": 11018736} {"current_steps": 39335, "total_steps": 40000, "loss": 0.0, "lr": 3.419315775165799e-08, "epoch": 437.05555555555554, "percentage": 98.34, "elapsed_time": "4:28:06", "remaining_time": "0:04:31", "throughput": 685.03, "total_tokens": 11020080} {"current_steps": 39340, "total_steps": 40000, "loss": 0.0, "lr": 3.368178907464103e-08, "epoch": 437.1111111111111, "percentage": 98.35, "elapsed_time": "4:28:08", "remaining_time": "0:04:29", "throughput": 685.03, "total_tokens": 11021472} {"current_steps": 39345, "total_steps": 40000, "loss": 0.0, "lr": 3.317427051763855e-08, "epoch": 437.1666666666667, "percentage": 98.36, "elapsed_time": "4:28:10", "remaining_time": "0:04:27", "throughput": 685.04, "total_tokens": 11022912} {"current_steps": 39350, "total_steps": 40000, "loss": 0.0, "lr": 3.267060215891571e-08, "epoch": 437.22222222222223, "percentage": 98.38, "elapsed_time": "4:28:12", "remaining_time": "0:04:25", "throughput": 685.05, "total_tokens": 11024304} {"current_steps": 39355, "total_steps": 40000, "loss": 0.0, "lr": 3.217078407614649e-08, "epoch": 437.27777777777777, "percentage": 98.39, "elapsed_time": "4:28:14", "remaining_time": "0:04:23", "throughput": 685.05, "total_tokens": 11025712} {"current_steps": 39360, "total_steps": 40000, "loss": 0.0, "lr": 3.1674816346405345e-08, "epoch": 437.3333333333333, "percentage": 98.4, "elapsed_time": "4:28:16", "remaining_time": "0:04:21", "throughput": 685.05, "total_tokens": 11027104} {"current_steps": 39365, "total_steps": 40000, "loss": 0.0, "lr": 3.11826990461811e-08, "epoch": 437.3888888888889, "percentage": 98.41, "elapsed_time": "4:28:18", "remaining_time": "0:04:19", "throughput": 685.06, "total_tokens": 11028448} {"current_steps": 39370, "total_steps": 40000, "loss": 0.0, "lr": 3.069443225136304e-08, "epoch": 437.44444444444446, "percentage": 98.42, "elapsed_time": "4:28:20", "remaining_time": "0:04:17", "throughput": 685.06, "total_tokens": 11029856} {"current_steps": 39375, "total_steps": 40000, "loss": 0.0, "lr": 3.021001603724372e-08, "epoch": 437.5, "percentage": 98.44, "elapsed_time": "4:28:22", "remaining_time": "0:04:15", "throughput": 685.06, "total_tokens": 11031264} {"current_steps": 39380, "total_steps": 40000, "loss": 0.0, "lr": 2.9729450478532818e-08, "epoch": 437.55555555555554, "percentage": 98.45, "elapsed_time": "4:28:24", "remaining_time": "0:04:13", "throughput": 685.07, "total_tokens": 11032672} {"current_steps": 39385, "total_steps": 40000, "loss": 0.0, "lr": 2.9252735649337726e-08, "epoch": 437.6111111111111, "percentage": 98.46, "elapsed_time": "4:28:26", "remaining_time": "0:04:11", "throughput": 685.08, "total_tokens": 11034128} {"current_steps": 39390, "total_steps": 40000, "loss": 0.0, "lr": 2.8779871623171863e-08, "epoch": 437.6666666666667, "percentage": 98.47, "elapsed_time": "4:28:28", "remaining_time": "0:04:09", "throughput": 685.08, "total_tokens": 11035520} {"current_steps": 39395, "total_steps": 40000, "loss": 0.0, "lr": 2.8310858472957448e-08, "epoch": 437.72222222222223, "percentage": 98.49, "elapsed_time": "4:28:30", "remaining_time": "0:04:07", "throughput": 685.09, "total_tokens": 11036928} {"current_steps": 39400, "total_steps": 40000, "loss": 0.0, "lr": 2.784569627101996e-08, "epoch": 437.77777777777777, "percentage": 98.5, "elapsed_time": "4:28:32", "remaining_time": "0:04:05", "throughput": 685.09, "total_tokens": 11038352} {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.39003992080688477, "epoch": 437.77777777777777, "percentage": 98.5, "elapsed_time": "4:28:33", "remaining_time": "0:04:05", "throughput": 685.04, "total_tokens": 11038352} {"current_steps": 39405, "total_steps": 40000, "loss": 0.0, "lr": 2.738438508909924e-08, "epoch": 437.8333333333333, "percentage": 98.51, "elapsed_time": "4:28:36", "remaining_time": "0:04:03", "throughput": 684.98, "total_tokens": 11039744} {"current_steps": 39410, "total_steps": 40000, "loss": 0.0, "lr": 2.692692499833005e-08, "epoch": 437.8888888888889, "percentage": 98.52, "elapsed_time": "4:28:38", "remaining_time": "0:04:01", "throughput": 684.98, "total_tokens": 11041136} {"current_steps": 39415, "total_steps": 40000, "loss": 0.0, "lr": 2.647331606926151e-08, "epoch": 437.94444444444446, "percentage": 98.54, "elapsed_time": "4:28:40", "remaining_time": "0:03:59", "throughput": 684.99, "total_tokens": 11042544} {"current_steps": 39420, "total_steps": 40000, "loss": 0.0, "lr": 2.6023558371843225e-08, "epoch": 438.0, "percentage": 98.55, "elapsed_time": "4:28:42", "remaining_time": "0:03:57", "throughput": 684.99, "total_tokens": 11043936} {"current_steps": 39425, "total_steps": 40000, "loss": 0.0, "lr": 2.557765197543638e-08, "epoch": 438.05555555555554, "percentage": 98.56, "elapsed_time": "4:28:45", "remaining_time": "0:03:55", "throughput": 684.98, "total_tokens": 11045312} {"current_steps": 39430, "total_steps": 40000, "loss": 0.0, "lr": 2.513559694880263e-08, "epoch": 438.1111111111111, "percentage": 98.58, "elapsed_time": "4:28:47", "remaining_time": "0:03:53", "throughput": 684.98, "total_tokens": 11046736} {"current_steps": 39435, "total_steps": 40000, "loss": 0.0, "lr": 2.469739336011523e-08, "epoch": 438.1666666666667, "percentage": 98.59, "elapsed_time": "4:28:48", "remaining_time": "0:03:51", "throughput": 684.99, "total_tokens": 11048112} {"current_steps": 39440, "total_steps": 40000, "loss": 0.0, "lr": 2.4263041276947894e-08, "epoch": 438.22222222222223, "percentage": 98.6, "elapsed_time": "4:28:50", "remaining_time": "0:03:49", "throughput": 684.99, "total_tokens": 11049552} {"current_steps": 39445, "total_steps": 40000, "loss": 0.0, "lr": 2.3832540766283164e-08, "epoch": 438.27777777777777, "percentage": 98.61, "elapsed_time": "4:28:52", "remaining_time": "0:03:46", "throughput": 685.0, "total_tokens": 11050976} {"current_steps": 39450, "total_steps": 40000, "loss": 0.0, "lr": 2.3405891894512366e-08, "epoch": 438.3333333333333, "percentage": 98.62, "elapsed_time": "4:28:54", "remaining_time": "0:03:44", "throughput": 685.0, "total_tokens": 11052400} {"current_steps": 39455, "total_steps": 40000, "loss": 0.0, "lr": 2.29830947274301e-08, "epoch": 438.3888888888889, "percentage": 98.64, "elapsed_time": "4:28:56", "remaining_time": "0:03:42", "throughput": 685.01, "total_tokens": 11053824} {"current_steps": 39460, "total_steps": 40000, "loss": 0.0, "lr": 2.2564149330231432e-08, "epoch": 438.44444444444446, "percentage": 98.65, "elapsed_time": "4:28:58", "remaining_time": "0:03:40", "throughput": 685.01, "total_tokens": 11055168} {"current_steps": 39465, "total_steps": 40000, "loss": 0.0, "lr": 2.2149055767528572e-08, "epoch": 438.5, "percentage": 98.66, "elapsed_time": "4:29:00", "remaining_time": "0:03:38", "throughput": 685.02, "total_tokens": 11056592} {"current_steps": 39470, "total_steps": 40000, "loss": 0.0, "lr": 2.1737814103334197e-08, "epoch": 438.55555555555554, "percentage": 98.67, "elapsed_time": "4:29:02", "remaining_time": "0:03:36", "throughput": 685.02, "total_tokens": 11058000} {"current_steps": 39475, "total_steps": 40000, "loss": 0.0, "lr": 2.1330424401064253e-08, "epoch": 438.6111111111111, "percentage": 98.69, "elapsed_time": "4:29:04", "remaining_time": "0:03:34", "throughput": 685.03, "total_tokens": 11059392} {"current_steps": 39480, "total_steps": 40000, "loss": 0.0, "lr": 2.092688672354348e-08, "epoch": 438.6666666666667, "percentage": 98.7, "elapsed_time": "4:29:06", "remaining_time": "0:03:32", "throughput": 685.03, "total_tokens": 11060784} {"current_steps": 39485, "total_steps": 40000, "loss": 0.0, "lr": 2.0527201133005435e-08, "epoch": 438.72222222222223, "percentage": 98.71, "elapsed_time": "4:29:08", "remaining_time": "0:03:30", "throughput": 685.03, "total_tokens": 11062128} {"current_steps": 39490, "total_steps": 40000, "loss": 0.0, "lr": 2.0131367691084148e-08, "epoch": 438.77777777777777, "percentage": 98.72, "elapsed_time": "4:29:10", "remaining_time": "0:03:28", "throughput": 685.04, "total_tokens": 11063552} {"current_steps": 39495, "total_steps": 40000, "loss": 0.0, "lr": 1.9739386458819675e-08, "epoch": 438.8333333333333, "percentage": 98.74, "elapsed_time": "4:29:12", "remaining_time": "0:03:26", "throughput": 685.04, "total_tokens": 11064992} {"current_steps": 39500, "total_steps": 40000, "loss": 0.0, "lr": 1.9351257496666442e-08, "epoch": 438.8888888888889, "percentage": 98.75, "elapsed_time": "4:29:14", "remaining_time": "0:03:24", "throughput": 685.05, "total_tokens": 11066368} {"current_steps": 39505, "total_steps": 40000, "loss": 0.0, "lr": 1.896698086447657e-08, "epoch": 438.94444444444446, "percentage": 98.76, "elapsed_time": "4:29:16", "remaining_time": "0:03:22", "throughput": 685.05, "total_tokens": 11067792} {"current_steps": 39510, "total_steps": 40000, "loss": 0.0, "lr": 1.8586556621505436e-08, "epoch": 439.0, "percentage": 98.78, "elapsed_time": "4:29:18", "remaining_time": "0:03:20", "throughput": 685.05, "total_tokens": 11069168} {"current_steps": 39515, "total_steps": 40000, "loss": 0.0, "lr": 1.820998482642833e-08, "epoch": 439.05555555555554, "percentage": 98.79, "elapsed_time": "4:29:20", "remaining_time": "0:03:18", "throughput": 685.04, "total_tokens": 11070560} {"current_steps": 39520, "total_steps": 40000, "loss": 0.0, "lr": 1.7837265537309912e-08, "epoch": 439.1111111111111, "percentage": 98.8, "elapsed_time": "4:29:22", "remaining_time": "0:03:16", "throughput": 685.05, "total_tokens": 11072000} {"current_steps": 39525, "total_steps": 40000, "loss": 0.0, "lr": 1.7468398811629206e-08, "epoch": 439.1666666666667, "percentage": 98.81, "elapsed_time": "4:29:24", "remaining_time": "0:03:14", "throughput": 685.05, "total_tokens": 11073360} {"current_steps": 39530, "total_steps": 40000, "loss": 0.0, "lr": 1.710338470627404e-08, "epoch": 439.22222222222223, "percentage": 98.83, "elapsed_time": "4:29:26", "remaining_time": "0:03:12", "throughput": 685.05, "total_tokens": 11074768} {"current_steps": 39535, "total_steps": 40000, "loss": 0.0, "lr": 1.6742223277529945e-08, "epoch": 439.27777777777777, "percentage": 98.84, "elapsed_time": "4:29:28", "remaining_time": "0:03:10", "throughput": 685.06, "total_tokens": 11076176} {"current_steps": 39540, "total_steps": 40000, "loss": 0.0, "lr": 1.6384914581094036e-08, "epoch": 439.3333333333333, "percentage": 98.85, "elapsed_time": "4:29:30", "remaining_time": "0:03:08", "throughput": 685.06, "total_tokens": 11077536} {"current_steps": 39545, "total_steps": 40000, "loss": 0.0, "lr": 1.6031458672069455e-08, "epoch": 439.3888888888889, "percentage": 98.86, "elapsed_time": "4:29:32", "remaining_time": "0:03:06", "throughput": 685.07, "total_tokens": 11078960} {"current_steps": 39550, "total_steps": 40000, "loss": 0.0, "lr": 1.5681855604962602e-08, "epoch": 439.44444444444446, "percentage": 98.88, "elapsed_time": "4:29:34", "remaining_time": "0:03:04", "throughput": 685.07, "total_tokens": 11080304} {"current_steps": 39555, "total_steps": 40000, "loss": 0.0, "lr": 1.5336105433683135e-08, "epoch": 439.5, "percentage": 98.89, "elapsed_time": "4:29:35", "remaining_time": "0:03:01", "throughput": 685.07, "total_tokens": 11081744} {"current_steps": 39560, "total_steps": 40000, "loss": 0.0, "lr": 1.499420821155506e-08, "epoch": 439.55555555555554, "percentage": 98.9, "elapsed_time": "4:29:37", "remaining_time": "0:02:59", "throughput": 685.08, "total_tokens": 11083120} {"current_steps": 39565, "total_steps": 40000, "loss": 0.0, "lr": 1.4656163991302874e-08, "epoch": 439.6111111111111, "percentage": 98.91, "elapsed_time": "4:29:39", "remaining_time": "0:02:57", "throughput": 685.08, "total_tokens": 11084512} {"current_steps": 39570, "total_steps": 40000, "loss": 0.0, "lr": 1.4321972825051544e-08, "epoch": 439.6666666666667, "percentage": 98.92, "elapsed_time": "4:29:41", "remaining_time": "0:02:55", "throughput": 685.09, "total_tokens": 11085904} {"current_steps": 39575, "total_steps": 40000, "loss": 0.0, "lr": 1.3991634764345951e-08, "epoch": 439.72222222222223, "percentage": 98.94, "elapsed_time": "4:29:43", "remaining_time": "0:02:53", "throughput": 685.09, "total_tokens": 11087344} {"current_steps": 39580, "total_steps": 40000, "loss": 0.0, "lr": 1.3665149860120352e-08, "epoch": 439.77777777777777, "percentage": 98.95, "elapsed_time": "4:29:45", "remaining_time": "0:02:51", "throughput": 685.1, "total_tokens": 11088752} {"current_steps": 39585, "total_steps": 40000, "loss": 0.0, "lr": 1.3342518162728912e-08, "epoch": 439.8333333333333, "percentage": 98.96, "elapsed_time": "4:29:47", "remaining_time": "0:02:49", "throughput": 685.1, "total_tokens": 11090128} {"current_steps": 39590, "total_steps": 40000, "loss": 0.0, "lr": 1.30237397219235e-08, "epoch": 439.8888888888889, "percentage": 98.98, "elapsed_time": "4:29:49", "remaining_time": "0:02:47", "throughput": 685.11, "total_tokens": 11091552} {"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 1.2708814586862016e-08, "epoch": 439.94444444444446, "percentage": 98.99, "elapsed_time": "4:29:51", "remaining_time": "0:02:45", "throughput": 685.11, "total_tokens": 11092912} {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:53", "remaining_time": "0:02:43", "throughput": 685.11, "total_tokens": 11094352} {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.3569253385066986, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:54", "remaining_time": "0:02:43", "throughput": 685.05, "total_tokens": 11094352} {"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 440.05555555555554, "percentage": 99.01, "elapsed_time": "4:29:58", "remaining_time": "0:02:41", "throughput": 684.99, "total_tokens": 11095760} {"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 1.17871594988328e-08, "epoch": 440.1111111111111, "percentage": 99.02, "elapsed_time": "4:30:00", "remaining_time": "0:02:39", "throughput": 684.99, "total_tokens": 11097184} {"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 1.1487648066466072e-08, "epoch": 440.1666666666667, "percentage": 99.04, "elapsed_time": "4:30:02", "remaining_time": "0:02:37", "throughput": 684.99, "total_tokens": 11098544} {"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 1.1191990176728784e-08, "epoch": 440.22222222222223, "percentage": 99.05, "elapsed_time": "4:30:04", "remaining_time": "0:02:35", "throughput": 685.0, "total_tokens": 11099968} {"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 1.0900185875215018e-08, "epoch": 440.27777777777777, "percentage": 99.06, "elapsed_time": "4:30:06", "remaining_time": "0:02:33", "throughput": 685.0, "total_tokens": 11101360} {"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 1.0612235206924891e-08, "epoch": 440.3333333333333, "percentage": 99.08, "elapsed_time": "4:30:08", "remaining_time": "0:02:31", "throughput": 685.01, "total_tokens": 11102800} {"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 1.0328138216264549e-08, "epoch": 440.3888888888889, "percentage": 99.09, "elapsed_time": "4:30:10", "remaining_time": "0:02:29", "throughput": 685.02, "total_tokens": 11104240} {"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 1.004789494704339e-08, "epoch": 440.44444444444446, "percentage": 99.1, "elapsed_time": "4:30:12", "remaining_time": "0:02:27", "throughput": 685.02, "total_tokens": 11105648} {"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 9.771505442482397e-09, "epoch": 440.5, "percentage": 99.11, "elapsed_time": "4:30:14", "remaining_time": "0:02:25", "throughput": 685.03, "total_tokens": 11107072} {"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 9.498969745200259e-09, "epoch": 440.55555555555554, "percentage": 99.12, "elapsed_time": "4:30:15", "remaining_time": "0:02:23", "throughput": 685.03, "total_tokens": 11108448} {"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 9.230287897230017e-09, "epoch": 440.6111111111111, "percentage": 99.14, "elapsed_time": "4:30:17", "remaining_time": "0:02:21", "throughput": 685.04, "total_tokens": 11109840} {"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 8.965459940002419e-09, "epoch": 440.6666666666667, "percentage": 99.15, "elapsed_time": "4:30:19", "remaining_time": "0:02:19", "throughput": 685.04, "total_tokens": 11111264} {"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 8.704485914357019e-09, "epoch": 440.72222222222223, "percentage": 99.16, "elapsed_time": "4:30:21", "remaining_time": "0:02:17", "throughput": 685.05, "total_tokens": 11112704} {"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 8.447365860539402e-09, "epoch": 440.77777777777777, "percentage": 99.17, "elapsed_time": "4:30:23", "remaining_time": "0:02:14", "throughput": 685.05, "total_tokens": 11114112} {"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 8.194099818201184e-09, "epoch": 440.8333333333333, "percentage": 99.19, "elapsed_time": "4:30:25", "remaining_time": "0:02:12", "throughput": 685.06, "total_tokens": 11115488} {"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 7.944687826400011e-09, "epoch": 440.8888888888889, "percentage": 99.2, "elapsed_time": "4:30:27", "remaining_time": "0:02:10", "throughput": 685.06, "total_tokens": 11116880} {"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 7.699129923599557e-09, "epoch": 440.94444444444446, "percentage": 99.21, "elapsed_time": "4:30:29", "remaining_time": "0:02:08", "throughput": 685.06, "total_tokens": 11118256} {"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 7.457426147663982e-09, "epoch": 441.0, "percentage": 99.22, "elapsed_time": "4:30:31", "remaining_time": "0:02:06", "throughput": 685.06, "total_tokens": 11119632} {"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 7.219576535871797e-09, "epoch": 441.05555555555554, "percentage": 99.24, "elapsed_time": "4:30:33", "remaining_time": "0:02:04", "throughput": 685.05, "total_tokens": 11121008} {"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 6.985581124896445e-09, "epoch": 441.1111111111111, "percentage": 99.25, "elapsed_time": "4:30:35", "remaining_time": "0:02:02", "throughput": 685.06, "total_tokens": 11122448} {"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 6.755439950828501e-09, "epoch": 441.1666666666667, "percentage": 99.26, "elapsed_time": "4:30:37", "remaining_time": "0:02:00", "throughput": 685.06, "total_tokens": 11123856} {"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 6.5291530491562444e-09, "epoch": 441.22222222222223, "percentage": 99.28, "elapsed_time": "4:30:39", "remaining_time": "0:01:58", "throughput": 685.07, "total_tokens": 11125264} {"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 6.3067204547739845e-09, "epoch": 441.27777777777777, "percentage": 99.29, "elapsed_time": "4:30:41", "remaining_time": "0:01:56", "throughput": 685.07, "total_tokens": 11126640} {"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 6.088142201987612e-09, "epoch": 441.3333333333333, "percentage": 99.3, "elapsed_time": "4:30:43", "remaining_time": "0:01:54", "throughput": 685.07, "total_tokens": 11128048} {"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 5.873418324503499e-09, "epoch": 441.3888888888889, "percentage": 99.31, "elapsed_time": "4:30:45", "remaining_time": "0:01:52", "throughput": 685.08, "total_tokens": 11129456} {"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 5.6625488554340465e-09, "epoch": 441.44444444444446, "percentage": 99.33, "elapsed_time": "4:30:47", "remaining_time": "0:01:50", "throughput": 685.09, "total_tokens": 11130880} {"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 5.455533827297688e-09, "epoch": 441.5, "percentage": 99.34, "elapsed_time": "4:30:49", "remaining_time": "0:01:48", "throughput": 685.09, "total_tokens": 11132288} {"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 5.252373272018885e-09, "epoch": 441.55555555555554, "percentage": 99.35, "elapsed_time": "4:30:51", "remaining_time": "0:01:46", "throughput": 685.09, "total_tokens": 11133696} {"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 5.053067220925356e-09, "epoch": 441.6111111111111, "percentage": 99.36, "elapsed_time": "4:30:53", "remaining_time": "0:01:44", "throughput": 685.1, "total_tokens": 11135104} {"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 4.857615704759177e-09, "epoch": 441.6666666666667, "percentage": 99.38, "elapsed_time": "4:30:55", "remaining_time": "0:01:42", "throughput": 685.1, "total_tokens": 11136480} {"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 4.666018753654577e-09, "epoch": 441.72222222222223, "percentage": 99.39, "elapsed_time": "4:30:57", "remaining_time": "0:01:40", "throughput": 685.11, "total_tokens": 11137888} {"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 4.478276397162917e-09, "epoch": 441.77777777777777, "percentage": 99.4, "elapsed_time": "4:30:59", "remaining_time": "0:01:38", "throughput": 685.11, "total_tokens": 11139232} {"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 4.294388664233262e-09, "epoch": 441.8333333333333, "percentage": 99.41, "elapsed_time": "4:31:01", "remaining_time": "0:01:36", "throughput": 685.11, "total_tokens": 11140608} {"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 4.114355583223484e-09, "epoch": 441.8888888888889, "percentage": 99.42, "elapsed_time": "4:31:02", "remaining_time": "0:01:34", "throughput": 685.12, "total_tokens": 11142032} {"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 3.9381771818974845e-09, "epoch": 441.94444444444446, "percentage": 99.44, "elapsed_time": "4:31:04", "remaining_time": "0:01:32", "throughput": 685.12, "total_tokens": 11143440} {"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 3.765853487427973e-09, "epoch": 442.0, "percentage": 99.45, "elapsed_time": "4:31:07", "remaining_time": "0:01:29", "throughput": 685.12, "total_tokens": 11144800} {"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 3.5973845263825857e-09, "epoch": 442.05555555555554, "percentage": 99.46, "elapsed_time": "4:31:09", "remaining_time": "0:01:27", "throughput": 685.11, "total_tokens": 11146208} {"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 3.4327703247488684e-09, "epoch": 442.1111111111111, "percentage": 99.48, "elapsed_time": "4:31:11", "remaining_time": "0:01:25", "throughput": 685.11, "total_tokens": 11147648} {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 442.1666666666667, "percentage": 99.49, "elapsed_time": "4:31:13", "remaining_time": "0:01:23", "throughput": 685.11, "total_tokens": 11149008} {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:31:15", "remaining_time": "0:01:21", "throughput": 685.11, "total_tokens": 11150400} {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3495562970638275, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:31:16", "remaining_time": "0:01:21", "throughput": 685.06, "total_tokens": 11150400} {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "4:31:19", "remaining_time": "0:01:19", "throughput": 685.0, "total_tokens": 11151792} {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "4:31:21", "remaining_time": "0:01:17", "throughput": 685.01, "total_tokens": 11153232} {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "4:31:23", "remaining_time": "0:01:15", "throughput": 685.01, "total_tokens": 11154624} {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "4:31:25", "remaining_time": "0:01:13", "throughput": 685.01, "total_tokens": 11156016} {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "4:31:27", "remaining_time": "0:01:11", "throughput": 685.02, "total_tokens": 11157392} {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "4:31:29", "remaining_time": "0:01:09", "throughput": 685.02, "total_tokens": 11158704} {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "4:31:31", "remaining_time": "0:01:07", "throughput": 685.02, "total_tokens": 11160112} {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "4:31:33", "remaining_time": "0:01:05", "throughput": 685.03, "total_tokens": 11161520} {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "4:31:35", "remaining_time": "0:01:03", "throughput": 685.03, "total_tokens": 11162912} {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "4:31:37", "remaining_time": "0:01:01", "throughput": 685.04, "total_tokens": 11164320} {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "4:31:39", "remaining_time": "0:00:59", "throughput": 685.04, "total_tokens": 11165712} {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "4:31:41", "remaining_time": "0:00:57", "throughput": 685.05, "total_tokens": 11167168} {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "4:31:43", "remaining_time": "0:00:55", "throughput": 685.06, "total_tokens": 11168608} {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "4:31:45", "remaining_time": "0:00:53", "throughput": 685.05, "total_tokens": 11170064} {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "4:31:47", "remaining_time": "0:00:51", "throughput": 685.05, "total_tokens": 11171456} {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "4:31:49", "remaining_time": "0:00:49", "throughput": 685.05, "total_tokens": 11172832} {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "4:31:51", "remaining_time": "0:00:47", "throughput": 685.06, "total_tokens": 11174288} {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "4:31:53", "remaining_time": "0:00:44", "throughput": 685.06, "total_tokens": 11175664} {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "4:31:55", "remaining_time": "0:00:42", "throughput": 685.07, "total_tokens": 11177056} {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "4:31:57", "remaining_time": "0:00:40", "throughput": 685.07, "total_tokens": 11178480} {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "4:31:59", "remaining_time": "0:00:38", "throughput": 685.07, "total_tokens": 11179856} {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "4:32:01", "remaining_time": "0:00:36", "throughput": 685.08, "total_tokens": 11181264} {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "4:32:03", "remaining_time": "0:00:34", "throughput": 685.08, "total_tokens": 11182624} {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "4:32:05", "remaining_time": "0:00:32", "throughput": 685.09, "total_tokens": 11184032} {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "4:32:06", "remaining_time": "0:00:30", "throughput": 685.09, "total_tokens": 11185440} {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "4:32:08", "remaining_time": "0:00:28", "throughput": 685.09, "total_tokens": 11186816} {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "4:32:10", "remaining_time": "0:00:26", "throughput": 685.1, "total_tokens": 11188224} {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "4:32:12", "remaining_time": "0:00:24", "throughput": 685.11, "total_tokens": 11189664} {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "4:32:14", "remaining_time": "0:00:22", "throughput": 685.11, "total_tokens": 11191072} {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "4:32:16", "remaining_time": "0:00:20", "throughput": 685.12, "total_tokens": 11192480} {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "4:32:18", "remaining_time": "0:00:18", "throughput": 685.12, "total_tokens": 11193888} {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "4:32:20", "remaining_time": "0:00:16", "throughput": 685.12, "total_tokens": 11195264} {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "4:32:22", "remaining_time": "0:00:14", "throughput": 685.11, "total_tokens": 11196624} {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "4:32:24", "remaining_time": "0:00:12", "throughput": 685.11, "total_tokens": 11198016} {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "4:32:26", "remaining_time": "0:00:10", "throughput": 685.12, "total_tokens": 11199440} {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "4:32:28", "remaining_time": "0:00:08", "throughput": 685.12, "total_tokens": 11200880} {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "4:32:30", "remaining_time": "0:00:06", "throughput": 685.13, "total_tokens": 11202304} {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "4:32:32", "remaining_time": "0:00:04", "throughput": 685.13, "total_tokens": 11203696} {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "4:32:34", "remaining_time": "0:00:02", "throughput": 685.14, "total_tokens": 11205088} {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:36", "remaining_time": "0:00:00", "throughput": 685.14, "total_tokens": 11206480} {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.33738812804222107, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:37", "remaining_time": "0:00:00", "throughput": 685.09, "total_tokens": 11206480} {"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:39", "remaining_time": "0:00:00", "throughput": 685.03, "total_tokens": 11206480}