| {"current_steps": 5, "total_steps": 1140, "loss": 1.0752, "lr": 1.7543859649122807e-06, "epoch": 0.08771929824561403, "percentage": 0.44, "elapsed_time": "0:00:01", "remaining_time": "0:06:19", "throughput": 1952.15, "total_tokens": 3264} |
| {"current_steps": 10, "total_steps": 1140, "loss": 1.0574, "lr": 3.9473684210526315e-06, "epoch": 0.17543859649122806, "percentage": 0.88, "elapsed_time": "0:00:02", "remaining_time": "0:05:10", "throughput": 2303.49, "total_tokens": 6336} |
| {"current_steps": 15, "total_steps": 1140, "loss": 1.03, "lr": 6.140350877192982e-06, "epoch": 0.2631578947368421, "percentage": 1.32, "elapsed_time": "0:00:03", "remaining_time": "0:04:38", "throughput": 2467.95, "total_tokens": 9152} |
| {"current_steps": 20, "total_steps": 1140, "loss": 1.0561, "lr": 8.333333333333334e-06, "epoch": 0.3508771929824561, "percentage": 1.75, "elapsed_time": "0:00:04", "remaining_time": "0:04:30", "throughput": 2597.72, "total_tokens": 12544} |
| {"current_steps": 25, "total_steps": 1140, "loss": 1.2617, "lr": 1.0526315789473684e-05, "epoch": 0.43859649122807015, "percentage": 2.19, "elapsed_time": "0:00:05", "remaining_time": "0:04:17", "throughput": 2645.1, "total_tokens": 15296} |
| {"current_steps": 30, "total_steps": 1140, "loss": 1.1751, "lr": 1.2719298245614037e-05, "epoch": 0.5263157894736842, "percentage": 2.63, "elapsed_time": "0:00:06", "remaining_time": "0:04:14", "throughput": 2699.38, "total_tokens": 18560} |
| {"current_steps": 35, "total_steps": 1140, "loss": 1.0189, "lr": 1.4912280701754386e-05, "epoch": 0.6140350877192983, "percentage": 3.07, "elapsed_time": "0:00:07", "remaining_time": "0:04:11", "throughput": 2730.37, "total_tokens": 21728} |
| {"current_steps": 40, "total_steps": 1140, "loss": 1.1097, "lr": 1.7105263157894737e-05, "epoch": 0.7017543859649122, "percentage": 3.51, "elapsed_time": "0:00:09", "remaining_time": "0:04:10", "throughput": 2784.43, "total_tokens": 25408} |
| {"current_steps": 45, "total_steps": 1140, "loss": 1.15, "lr": 1.929824561403509e-05, "epoch": 0.7894736842105263, "percentage": 3.95, "elapsed_time": "0:00:10", "remaining_time": "0:04:12", "throughput": 2809.06, "total_tokens": 29152} |
| {"current_steps": 50, "total_steps": 1140, "loss": 1.0129, "lr": 2.149122807017544e-05, "epoch": 0.8771929824561403, "percentage": 4.39, "elapsed_time": "0:00:11", "remaining_time": "0:04:09", "throughput": 2823.02, "total_tokens": 32320} |
| {"current_steps": 55, "total_steps": 1140, "loss": 1.0221, "lr": 2.368421052631579e-05, "epoch": 0.9649122807017544, "percentage": 4.82, "elapsed_time": "0:00:12", "remaining_time": "0:04:07", "throughput": 2827.79, "total_tokens": 35488} |
| {"current_steps": 57, "total_steps": 1140, "eval_loss": 1.1781166791915894, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:13", "remaining_time": "0:04:16", "throughput": 2673.6, "total_tokens": 36072} |
| {"current_steps": 60, "total_steps": 1140, "loss": 1.3096, "lr": 2.5877192982456143e-05, "epoch": 1.0526315789473684, "percentage": 5.26, "elapsed_time": "0:00:14", "remaining_time": "0:04:27", "throughput": 2524.5, "total_tokens": 37544} |
| {"current_steps": 65, "total_steps": 1140, "loss": 1.0301, "lr": 2.8070175438596492e-05, "epoch": 1.1403508771929824, "percentage": 5.7, "elapsed_time": "0:00:16", "remaining_time": "0:04:30", "throughput": 2539.09, "total_tokens": 41512} |
| {"current_steps": 70, "total_steps": 1140, "loss": 1.1433, "lr": 3.0263157894736844e-05, "epoch": 1.2280701754385965, "percentage": 6.14, "elapsed_time": "0:00:17", "remaining_time": "0:04:27", "throughput": 2569.03, "total_tokens": 44936} |
| {"current_steps": 75, "total_steps": 1140, "loss": 1.1616, "lr": 3.24561403508772e-05, "epoch": 1.3157894736842106, "percentage": 6.58, "elapsed_time": "0:00:18", "remaining_time": "0:04:25", "throughput": 2602.98, "total_tokens": 48680} |
| {"current_steps": 80, "total_steps": 1140, "loss": 1.0325, "lr": 3.4649122807017546e-05, "epoch": 1.4035087719298245, "percentage": 7.02, "elapsed_time": "0:00:19", "remaining_time": "0:04:23", "throughput": 2627.13, "total_tokens": 52168} |
| {"current_steps": 85, "total_steps": 1140, "loss": 1.2118, "lr": 3.6842105263157895e-05, "epoch": 1.4912280701754386, "percentage": 7.46, "elapsed_time": "0:00:20", "remaining_time": "0:04:20", "throughput": 2644.66, "total_tokens": 55464} |
| {"current_steps": 90, "total_steps": 1140, "loss": 1.0729, "lr": 3.9035087719298244e-05, "epoch": 1.5789473684210527, "percentage": 7.89, "elapsed_time": "0:00:21", "remaining_time": "0:04:14", "throughput": 2652.05, "total_tokens": 57960} |
| {"current_steps": 95, "total_steps": 1140, "loss": 0.7965, "lr": 4.12280701754386e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:00:23", "remaining_time": "0:04:13", "throughput": 2676.23, "total_tokens": 61672} |
| {"current_steps": 100, "total_steps": 1140, "loss": 1.1929, "lr": 4.342105263157895e-05, "epoch": 1.7543859649122808, "percentage": 8.77, "elapsed_time": "0:00:24", "remaining_time": "0:04:10", "throughput": 2688.53, "total_tokens": 64872} |
| {"current_steps": 105, "total_steps": 1140, "loss": 0.9678, "lr": 4.56140350877193e-05, "epoch": 1.8421052631578947, "percentage": 9.21, "elapsed_time": "0:00:25", "remaining_time": "0:04:07", "throughput": 2701.25, "total_tokens": 67848} |
| {"current_steps": 110, "total_steps": 1140, "loss": 0.7632, "lr": 4.780701754385965e-05, "epoch": 1.9298245614035088, "percentage": 9.65, "elapsed_time": "0:00:26", "remaining_time": "0:04:04", "throughput": 2712.02, "total_tokens": 70728} |
| {"current_steps": 114, "total_steps": 1140, "eval_loss": 0.5822951197624207, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:27", "remaining_time": "0:04:07", "throughput": 2647.16, "total_tokens": 72896} |
| {"current_steps": 115, "total_steps": 1140, "loss": 0.4447, "lr": 5e-05, "epoch": 2.017543859649123, "percentage": 10.09, "elapsed_time": "0:00:28", "remaining_time": "0:04:14", "throughput": 2581.73, "total_tokens": 73664} |
| {"current_steps": 120, "total_steps": 1140, "loss": 0.412, "lr": 4.999707014206475e-05, "epoch": 2.1052631578947367, "percentage": 10.53, "elapsed_time": "0:00:29", "remaining_time": "0:04:11", "throughput": 2589.08, "total_tokens": 76736} |
| {"current_steps": 125, "total_steps": 1140, "loss": 0.2476, "lr": 4.9988281254984414e-05, "epoch": 2.192982456140351, "percentage": 10.96, "elapsed_time": "0:00:30", "remaining_time": "0:04:08", "throughput": 2602.24, "total_tokens": 79744} |
| {"current_steps": 130, "total_steps": 1140, "loss": 0.2851, "lr": 4.997363539877422e-05, "epoch": 2.280701754385965, "percentage": 11.4, "elapsed_time": "0:00:31", "remaining_time": "0:04:06", "throughput": 2613.41, "total_tokens": 82848} |
| {"current_steps": 135, "total_steps": 1140, "loss": 0.1626, "lr": 4.9953136006256415e-05, "epoch": 2.3684210526315788, "percentage": 11.84, "elapsed_time": "0:00:33", "remaining_time": "0:04:06", "throughput": 2635.79, "total_tokens": 87200} |
| {"current_steps": 140, "total_steps": 1140, "loss": 0.2189, "lr": 4.9926787882255636e-05, "epoch": 2.456140350877193, "percentage": 12.28, "elapsed_time": "0:00:34", "remaining_time": "0:04:03", "throughput": 2642.59, "total_tokens": 90176} |
| {"current_steps": 145, "total_steps": 1140, "loss": 0.3855, "lr": 4.9894597202472696e-05, "epoch": 2.543859649122807, "percentage": 12.72, "elapsed_time": "0:00:35", "remaining_time": "0:04:01", "throughput": 2652.12, "total_tokens": 93408} |
| {"current_steps": 150, "total_steps": 1140, "loss": 0.1882, "lr": 4.985657151203706e-05, "epoch": 2.6315789473684212, "percentage": 13.16, "elapsed_time": "0:00:36", "remaining_time": "0:03:59", "throughput": 2662.87, "total_tokens": 96800} |
| {"current_steps": 155, "total_steps": 1140, "loss": 0.2126, "lr": 4.9812719723738435e-05, "epoch": 2.719298245614035, "percentage": 13.6, "elapsed_time": "0:00:37", "remaining_time": "0:03:57", "throughput": 2670.39, "total_tokens": 99968} |
| {"current_steps": 160, "total_steps": 1140, "loss": 0.2543, "lr": 4.976305211593758e-05, "epoch": 2.807017543859649, "percentage": 14.04, "elapsed_time": "0:00:38", "remaining_time": "0:03:55", "throughput": 2676.73, "total_tokens": 103040} |
| {"current_steps": 165, "total_steps": 1140, "loss": 0.1125, "lr": 4.970758033015731e-05, "epoch": 2.8947368421052633, "percentage": 14.47, "elapsed_time": "0:00:39", "remaining_time": "0:03:53", "throughput": 2683.07, "total_tokens": 105856} |
| {"current_steps": 170, "total_steps": 1140, "loss": 0.1503, "lr": 4.9646317368353743e-05, "epoch": 2.982456140350877, "percentage": 14.91, "elapsed_time": "0:00:40", "remaining_time": "0:03:51", "throughput": 2690.83, "total_tokens": 108992} |
| {"current_steps": 171, "total_steps": 1140, "eval_loss": 0.1778637170791626, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:00:41", "remaining_time": "0:03:53", "throughput": 2641.93, "total_tokens": 109080} |
| {"current_steps": 175, "total_steps": 1140, "loss": 0.0728, "lr": 4.957927758986888e-05, "epoch": 3.0701754385964914, "percentage": 15.35, "elapsed_time": "0:00:42", "remaining_time": "0:03:56", "throughput": 2595.15, "total_tokens": 111320} |
| {"current_steps": 180, "total_steps": 1140, "loss": 0.1846, "lr": 4.9506476708064865e-05, "epoch": 3.1578947368421053, "percentage": 15.79, "elapsed_time": "0:00:44", "remaining_time": "0:03:54", "throughput": 2606.99, "total_tokens": 114840} |
| {"current_steps": 185, "total_steps": 1140, "loss": 0.086, "lr": 4.9427931786641e-05, "epoch": 3.245614035087719, "percentage": 16.23, "elapsed_time": "0:00:45", "remaining_time": "0:03:52", "throughput": 2614.15, "total_tokens": 117720} |
| {"current_steps": 190, "total_steps": 1140, "loss": 0.3332, "lr": 4.93436612356342e-05, "epoch": 3.3333333333333335, "percentage": 16.67, "elapsed_time": "0:00:46", "remaining_time": "0:03:51", "throughput": 2625.55, "total_tokens": 121400} |
| {"current_steps": 195, "total_steps": 1140, "loss": 0.1894, "lr": 4.925368480710385e-05, "epoch": 3.4210526315789473, "percentage": 17.11, "elapsed_time": "0:00:47", "remaining_time": "0:03:50", "throughput": 2637.62, "total_tokens": 125208} |
| {"current_steps": 200, "total_steps": 1140, "loss": 0.0976, "lr": 4.915802359050222e-05, "epoch": 3.5087719298245617, "percentage": 17.54, "elapsed_time": "0:00:48", "remaining_time": "0:03:48", "throughput": 2645.71, "total_tokens": 128568} |
| {"current_steps": 205, "total_steps": 1140, "loss": 0.1704, "lr": 4.905670000773126e-05, "epoch": 3.5964912280701755, "percentage": 17.98, "elapsed_time": "0:00:49", "remaining_time": "0:03:46", "throughput": 2653.46, "total_tokens": 131864} |
| {"current_steps": 210, "total_steps": 1140, "loss": 0.0976, "lr": 4.894973780788722e-05, "epoch": 3.6842105263157894, "percentage": 18.42, "elapsed_time": "0:00:50", "remaining_time": "0:03:44", "throughput": 2660.97, "total_tokens": 134872} |
| {"current_steps": 215, "total_steps": 1140, "loss": 0.135, "lr": 4.88371620616941e-05, "epoch": 3.7719298245614032, "percentage": 18.86, "elapsed_time": "0:00:51", "remaining_time": "0:03:42", "throughput": 2665.55, "total_tokens": 137784} |
| {"current_steps": 220, "total_steps": 1140, "loss": 0.1422, "lr": 4.871899915562736e-05, "epoch": 3.8596491228070176, "percentage": 19.3, "elapsed_time": "0:00:52", "remaining_time": "0:03:40", "throughput": 2670.8, "total_tokens": 140888} |
| {"current_steps": 225, "total_steps": 1140, "loss": 0.1435, "lr": 4.8595276785729236e-05, "epoch": 3.9473684210526314, "percentage": 19.74, "elapsed_time": "0:00:53", "remaining_time": "0:03:39", "throughput": 2678.41, "total_tokens": 144440} |
| {"current_steps": 228, "total_steps": 1140, "eval_loss": 0.17110419273376465, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:00:55", "remaining_time": "0:03:40", "throughput": 2645.0, "total_tokens": 145936} |
| {"current_steps": 230, "total_steps": 1140, "loss": 0.9541, "lr": 4.846602395111711e-05, "epoch": 4.035087719298246, "percentage": 20.18, "elapsed_time": "0:00:56", "remaining_time": "0:03:43", "throughput": 2610.15, "total_tokens": 147152} |
| {"current_steps": 235, "total_steps": 1140, "loss": 0.1009, "lr": 4.833127094718643e-05, "epoch": 4.12280701754386, "percentage": 20.61, "elapsed_time": "0:00:57", "remaining_time": "0:03:41", "throughput": 2615.54, "total_tokens": 150416} |
| {"current_steps": 240, "total_steps": 1140, "loss": 0.1769, "lr": 4.819104935850983e-05, "epoch": 4.2105263157894735, "percentage": 21.05, "elapsed_time": "0:00:58", "remaining_time": "0:03:39", "throughput": 2621.34, "total_tokens": 153328} |
| {"current_steps": 245, "total_steps": 1140, "loss": 0.1577, "lr": 4.804539205143405e-05, "epoch": 4.298245614035087, "percentage": 21.49, "elapsed_time": "0:00:59", "remaining_time": "0:03:37", "throughput": 2627.83, "total_tokens": 156720} |
| {"current_steps": 250, "total_steps": 1140, "loss": 0.1781, "lr": 4.789433316637644e-05, "epoch": 4.385964912280702, "percentage": 21.93, "elapsed_time": "0:01:00", "remaining_time": "0:03:36", "throughput": 2633.56, "total_tokens": 159920} |
| {"current_steps": 255, "total_steps": 1140, "loss": 0.0684, "lr": 4.7737908109822854e-05, "epoch": 4.473684210526316, "percentage": 22.37, "elapsed_time": "0:01:01", "remaining_time": "0:03:34", "throughput": 2636.25, "total_tokens": 162576} |
| {"current_steps": 260, "total_steps": 1140, "loss": 0.087, "lr": 4.757615354602874e-05, "epoch": 4.56140350877193, "percentage": 22.81, "elapsed_time": "0:01:02", "remaining_time": "0:03:31", "throughput": 2639.47, "total_tokens": 165200} |
| {"current_steps": 265, "total_steps": 1140, "loss": 0.117, "lr": 4.7409107388425504e-05, "epoch": 4.649122807017544, "percentage": 23.25, "elapsed_time": "0:01:03", "remaining_time": "0:03:30", "throughput": 2647.93, "total_tokens": 168656} |
| {"current_steps": 270, "total_steps": 1140, "loss": 0.2653, "lr": 4.723680879073396e-05, "epoch": 4.7368421052631575, "percentage": 23.68, "elapsed_time": "0:01:04", "remaining_time": "0:03:29", "throughput": 2655.12, "total_tokens": 172528} |
| {"current_steps": 275, "total_steps": 1140, "loss": 0.1166, "lr": 4.70592981377872e-05, "epoch": 4.824561403508772, "percentage": 24.12, "elapsed_time": "0:01:06", "remaining_time": "0:03:28", "throughput": 2661.63, "total_tokens": 176016} |
| {"current_steps": 280, "total_steps": 1140, "loss": 0.2535, "lr": 4.6876617036064844e-05, "epoch": 4.912280701754386, "percentage": 24.56, "elapsed_time": "0:01:07", "remaining_time": "0:03:26", "throughput": 2668.02, "total_tokens": 179504} |
| {"current_steps": 285, "total_steps": 1140, "loss": 0.148, "lr": 4.668880830394093e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:01:08", "remaining_time": "0:03:24", "throughput": 2666.61, "total_tokens": 182024} |
| {"current_steps": 285, "total_steps": 1140, "eval_loss": 0.17396755516529083, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:01:08", "remaining_time": "0:03:26", "throughput": 2643.2, "total_tokens": 182024} |
| {"current_steps": 290, "total_steps": 1140, "loss": 0.0897, "lr": 4.649591596164778e-05, "epoch": 5.087719298245614, "percentage": 25.44, "elapsed_time": "0:01:10", "remaining_time": "0:03:27", "throughput": 2621.23, "total_tokens": 185800} |
| {"current_steps": 295, "total_steps": 1140, "loss": 0.1741, "lr": 4.629798522095818e-05, "epoch": 5.175438596491228, "percentage": 25.88, "elapsed_time": "0:01:11", "remaining_time": "0:03:25", "throughput": 2624.01, "total_tokens": 188360} |
| {"current_steps": 300, "total_steps": 1140, "loss": 0.2149, "lr": 4.6095062474588225e-05, "epoch": 5.2631578947368425, "percentage": 26.32, "elapsed_time": "0:01:13", "remaining_time": "0:03:24", "throughput": 2632.39, "total_tokens": 192232} |
| {"current_steps": 305, "total_steps": 1140, "loss": 0.087, "lr": 4.588719528532342e-05, "epoch": 5.350877192982456, "percentage": 26.75, "elapsed_time": "0:01:14", "remaining_time": "0:03:22", "throughput": 2638.6, "total_tokens": 195592} |
| {"current_steps": 310, "total_steps": 1140, "loss": 0.1364, "lr": 4.5674432374870455e-05, "epoch": 5.43859649122807, "percentage": 27.19, "elapsed_time": "0:01:15", "remaining_time": "0:03:21", "throughput": 2641.99, "total_tokens": 198632} |
| {"current_steps": 315, "total_steps": 1140, "loss": 0.1228, "lr": 4.545682361243748e-05, "epoch": 5.526315789473684, "percentage": 27.63, "elapsed_time": "0:01:16", "remaining_time": "0:03:19", "throughput": 2645.56, "total_tokens": 201480} |
| {"current_steps": 320, "total_steps": 1140, "loss": 0.1765, "lr": 4.5234420003045236e-05, "epoch": 5.614035087719298, "percentage": 28.07, "elapsed_time": "0:01:17", "remaining_time": "0:03:17", "throughput": 2650.21, "total_tokens": 204584} |
| {"current_steps": 325, "total_steps": 1140, "loss": 0.1121, "lr": 4.5007273675572104e-05, "epoch": 5.701754385964913, "percentage": 28.51, "elapsed_time": "0:01:18", "remaining_time": "0:03:16", "throughput": 2656.54, "total_tokens": 208136} |
| {"current_steps": 330, "total_steps": 1140, "loss": 0.1778, "lr": 4.4775437870535685e-05, "epoch": 5.7894736842105265, "percentage": 28.95, "elapsed_time": "0:01:19", "remaining_time": "0:03:15", "throughput": 2661.57, "total_tokens": 211560} |
| {"current_steps": 335, "total_steps": 1140, "loss": 0.2377, "lr": 4.4538966927613836e-05, "epoch": 5.87719298245614, "percentage": 29.39, "elapsed_time": "0:01:20", "remaining_time": "0:03:13", "throughput": 2663.86, "total_tokens": 214472} |
| {"current_steps": 340, "total_steps": 1140, "loss": 0.0421, "lr": 4.4297916272908024e-05, "epoch": 5.964912280701754, "percentage": 29.82, "elapsed_time": "0:01:21", "remaining_time": "0:03:12", "throughput": 2669.22, "total_tokens": 217864} |
| {"current_steps": 342, "total_steps": 1140, "eval_loss": 0.16923700273036957, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:01:22", "remaining_time": "0:03:12", "throughput": 2646.17, "total_tokens": 218672} |
| {"current_steps": 345, "total_steps": 1140, "loss": 0.0716, "lr": 4.405234240595214e-05, "epoch": 6.052631578947368, "percentage": 30.26, "elapsed_time": "0:01:24", "remaining_time": "0:03:13", "throughput": 2618.34, "total_tokens": 220272} |
| {"current_steps": 350, "total_steps": 1140, "loss": 0.1109, "lr": 4.3802302886469606e-05, "epoch": 6.140350877192983, "percentage": 30.7, "elapsed_time": "0:01:25", "remaining_time": "0:03:12", "throughput": 2621.57, "total_tokens": 223440} |
| {"current_steps": 355, "total_steps": 1140, "loss": 0.2074, "lr": 4.3547856320882044e-05, "epoch": 6.228070175438597, "percentage": 31.14, "elapsed_time": "0:01:26", "remaining_time": "0:03:10", "throughput": 2624.92, "total_tokens": 226352} |
| {"current_steps": 360, "total_steps": 1140, "loss": 0.1339, "lr": 4.328906234857259e-05, "epoch": 6.315789473684211, "percentage": 31.58, "elapsed_time": "0:01:27", "remaining_time": "0:03:09", "throughput": 2629.19, "total_tokens": 229584} |
| {"current_steps": 365, "total_steps": 1140, "loss": 0.152, "lr": 4.302598162790712e-05, "epoch": 6.4035087719298245, "percentage": 32.02, "elapsed_time": "0:01:28", "remaining_time": "0:03:07", "throughput": 2631.51, "total_tokens": 232304} |
| {"current_steps": 370, "total_steps": 1140, "loss": 0.1077, "lr": 4.27586758220166e-05, "epoch": 6.491228070175438, "percentage": 32.46, "elapsed_time": "0:01:29", "remaining_time": "0:03:06", "throughput": 2639.52, "total_tokens": 236656} |
| {"current_steps": 375, "total_steps": 1140, "loss": 0.1673, "lr": 4.2487207584343955e-05, "epoch": 6.578947368421053, "percentage": 32.89, "elapsed_time": "0:01:30", "remaining_time": "0:03:04", "throughput": 2642.59, "total_tokens": 239568} |
| {"current_steps": 380, "total_steps": 1140, "loss": 0.0353, "lr": 4.2211640543958796e-05, "epoch": 6.666666666666667, "percentage": 33.33, "elapsed_time": "0:01:31", "remaining_time": "0:03:03", "throughput": 2645.38, "total_tokens": 242544} |
| {"current_steps": 385, "total_steps": 1140, "loss": 0.0675, "lr": 4.193203929064353e-05, "epoch": 6.754385964912281, "percentage": 33.77, "elapsed_time": "0:01:32", "remaining_time": "0:03:01", "throughput": 2648.84, "total_tokens": 245584} |
| {"current_steps": 390, "total_steps": 1140, "loss": 0.229, "lr": 4.164846935975421e-05, "epoch": 6.842105263157895, "percentage": 34.21, "elapsed_time": "0:01:33", "remaining_time": "0:03:00", "throughput": 2652.9, "total_tokens": 248880} |
| {"current_steps": 395, "total_steps": 1140, "loss": 0.1542, "lr": 4.136099721685983e-05, "epoch": 6.9298245614035086, "percentage": 34.65, "elapsed_time": "0:01:34", "remaining_time": "0:02:58", "throughput": 2655.78, "total_tokens": 251856} |
| {"current_steps": 399, "total_steps": 1140, "eval_loss": 0.17160974442958832, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:01:36", "remaining_time": "0:02:59", "throughput": 2637.62, "total_tokens": 254232} |
| {"current_steps": 400, "total_steps": 1140, "loss": 0.1185, "lr": 4.1069690242163484e-05, "epoch": 7.017543859649122, "percentage": 35.09, "elapsed_time": "0:01:37", "remaining_time": "0:03:00", "throughput": 2617.53, "total_tokens": 254808} |
| {"current_steps": 405, "total_steps": 1140, "loss": 0.2134, "lr": 4.0774616714709316e-05, "epoch": 7.105263157894737, "percentage": 35.53, "elapsed_time": "0:01:38", "remaining_time": "0:02:58", "throughput": 2618.84, "total_tokens": 257752} |
| {"current_steps": 410, "total_steps": 1140, "loss": 0.0765, "lr": 4.047584579637857e-05, "epoch": 7.192982456140351, "percentage": 35.96, "elapsed_time": "0:01:39", "remaining_time": "0:02:57", "throughput": 2622.51, "total_tokens": 261176} |
| {"current_steps": 415, "total_steps": 1140, "loss": 0.0959, "lr": 4.0173447515678916e-05, "epoch": 7.280701754385965, "percentage": 36.4, "elapsed_time": "0:01:40", "remaining_time": "0:02:55", "throughput": 2626.97, "total_tokens": 264568} |
| {"current_steps": 420, "total_steps": 1140, "loss": 0.1044, "lr": 3.986749275133057e-05, "epoch": 7.368421052631579, "percentage": 36.84, "elapsed_time": "0:01:41", "remaining_time": "0:02:54", "throughput": 2630.12, "total_tokens": 267672} |
| {"current_steps": 425, "total_steps": 1140, "loss": 0.1419, "lr": 3.955805321565304e-05, "epoch": 7.456140350877193, "percentage": 37.28, "elapsed_time": "0:01:42", "remaining_time": "0:02:53", "throughput": 2635.77, "total_tokens": 271448} |
| {"current_steps": 430, "total_steps": 1140, "loss": 0.0795, "lr": 3.9245201437756654e-05, "epoch": 7.543859649122807, "percentage": 37.72, "elapsed_time": "0:01:44", "remaining_time": "0:02:51", "throughput": 2639.13, "total_tokens": 274616} |
| {"current_steps": 435, "total_steps": 1140, "loss": 0.0528, "lr": 3.892901074654255e-05, "epoch": 7.631578947368421, "percentage": 38.16, "elapsed_time": "0:01:45", "remaining_time": "0:02:50", "throughput": 2641.92, "total_tokens": 277656} |
| {"current_steps": 440, "total_steps": 1140, "loss": 0.233, "lr": 3.860955525351516e-05, "epoch": 7.719298245614035, "percentage": 38.6, "elapsed_time": "0:01:46", "remaining_time": "0:02:49", "throughput": 2646.93, "total_tokens": 281400} |
| {"current_steps": 445, "total_steps": 1140, "loss": 0.0888, "lr": 3.82869098354114e-05, "epoch": 7.807017543859649, "percentage": 39.04, "elapsed_time": "0:01:47", "remaining_time": "0:02:47", "throughput": 2650.09, "total_tokens": 284536} |
| {"current_steps": 450, "total_steps": 1140, "loss": 0.2388, "lr": 3.796115011665034e-05, "epoch": 7.894736842105263, "percentage": 39.47, "elapsed_time": "0:01:48", "remaining_time": "0:02:46", "throughput": 2652.27, "total_tokens": 287512} |
| {"current_steps": 455, "total_steps": 1140, "loss": 0.1302, "lr": 3.763235245160775e-05, "epoch": 7.982456140350877, "percentage": 39.91, "elapsed_time": "0:01:49", "remaining_time": "0:02:44", "throughput": 2655.92, "total_tokens": 290776} |
| {"current_steps": 456, "total_steps": 1140, "eval_loss": 0.169868603348732, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:01:50", "remaining_time": "0:02:45", "throughput": 2638.09, "total_tokens": 290912} |
| {"current_steps": 460, "total_steps": 1140, "loss": 0.2689, "lr": 3.7300593906719464e-05, "epoch": 8.070175438596491, "percentage": 40.35, "elapsed_time": "0:01:52", "remaining_time": "0:02:45", "throughput": 2622.59, "total_tokens": 293856} |
| {"current_steps": 465, "total_steps": 1140, "loss": 0.0836, "lr": 3.69659522424179e-05, "epoch": 8.157894736842104, "percentage": 40.79, "elapsed_time": "0:01:53", "remaining_time": "0:02:44", "throughput": 2626.62, "total_tokens": 297376} |
| {"current_steps": 470, "total_steps": 1140, "loss": 0.0851, "lr": 3.662850589490592e-05, "epoch": 8.24561403508772, "percentage": 41.23, "elapsed_time": "0:01:54", "remaining_time": "0:02:42", "throughput": 2627.29, "total_tokens": 299776} |
| {"current_steps": 475, "total_steps": 1140, "loss": 0.1218, "lr": 3.628833395777224e-05, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "0:01:55", "remaining_time": "0:02:41", "throughput": 2630.7, "total_tokens": 302912} |
| {"current_steps": 480, "total_steps": 1140, "loss": 0.0532, "lr": 3.59455161634528e-05, "epoch": 8.421052631578947, "percentage": 42.11, "elapsed_time": "0:01:56", "remaining_time": "0:02:39", "throughput": 2633.95, "total_tokens": 305888} |
| {"current_steps": 485, "total_steps": 1140, "loss": 0.1109, "lr": 3.560013286454242e-05, "epoch": 8.508771929824562, "percentage": 42.54, "elapsed_time": "0:01:57", "remaining_time": "0:02:38", "throughput": 2638.16, "total_tokens": 309344} |
| {"current_steps": 490, "total_steps": 1140, "loss": 0.179, "lr": 3.5252265014961006e-05, "epoch": 8.596491228070175, "percentage": 42.98, "elapsed_time": "0:01:58", "remaining_time": "0:02:37", "throughput": 2640.29, "total_tokens": 312576} |
| {"current_steps": 495, "total_steps": 1140, "loss": 0.0352, "lr": 3.490199415097892e-05, "epoch": 8.68421052631579, "percentage": 43.42, "elapsed_time": "0:01:59", "remaining_time": "0:02:35", "throughput": 2642.86, "total_tokens": 315552} |
| {"current_steps": 500, "total_steps": 1140, "loss": 0.2252, "lr": 3.45494023721058e-05, "epoch": 8.771929824561404, "percentage": 43.86, "elapsed_time": "0:02:00", "remaining_time": "0:02:34", "throughput": 2645.78, "total_tokens": 318912} |
| {"current_steps": 505, "total_steps": 1140, "loss": 0.145, "lr": 3.4194572321847336e-05, "epoch": 8.859649122807017, "percentage": 44.3, "elapsed_time": "0:02:01", "remaining_time": "0:02:32", "throughput": 2647.51, "total_tokens": 321696} |
| {"current_steps": 510, "total_steps": 1140, "loss": 0.0934, "lr": 3.383758716833459e-05, "epoch": 8.947368421052632, "percentage": 44.74, "elapsed_time": "0:02:02", "remaining_time": "0:02:31", "throughput": 2650.9, "total_tokens": 325152} |
| {"current_steps": 513, "total_steps": 1140, "eval_loss": 0.1684989184141159, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:02:03", "remaining_time": "0:02:31", "throughput": 2635.88, "total_tokens": 326432} |
| {"current_steps": 515, "total_steps": 1140, "loss": 0.0306, "lr": 3.347853058483037e-05, "epoch": 9.035087719298245, "percentage": 45.18, "elapsed_time": "0:02:05", "remaining_time": "0:02:31", "throughput": 2620.23, "total_tokens": 327584} |
| {"current_steps": 520, "total_steps": 1140, "loss": 0.0661, "lr": 3.311748673011709e-05, "epoch": 9.12280701754386, "percentage": 45.61, "elapsed_time": "0:02:06", "remaining_time": "0:02:30", "throughput": 2622.64, "total_tokens": 331200} |
| {"current_steps": 525, "total_steps": 1140, "loss": 0.1946, "lr": 3.275454022877097e-05, "epoch": 9.210526315789474, "percentage": 46.05, "elapsed_time": "0:02:07", "remaining_time": "0:02:29", "throughput": 2625.44, "total_tokens": 334272} |
| {"current_steps": 530, "total_steps": 1140, "loss": 0.186, "lr": 3.238977615132697e-05, "epoch": 9.298245614035087, "percentage": 46.49, "elapsed_time": "0:02:08", "remaining_time": "0:02:27", "throughput": 2628.03, "total_tokens": 337312} |
| {"current_steps": 535, "total_steps": 1140, "loss": 0.0622, "lr": 3.202327999433924e-05, "epoch": 9.385964912280702, "percentage": 46.93, "elapsed_time": "0:02:09", "remaining_time": "0:02:26", "throughput": 2630.07, "total_tokens": 340352} |
| {"current_steps": 540, "total_steps": 1140, "loss": 0.1712, "lr": 3.165513766034167e-05, "epoch": 9.473684210526315, "percentage": 47.37, "elapsed_time": "0:02:10", "remaining_time": "0:02:24", "throughput": 2630.9, "total_tokens": 342848} |
| {"current_steps": 545, "total_steps": 1140, "loss": 0.1511, "lr": 3.128543543771336e-05, "epoch": 9.56140350877193, "percentage": 47.81, "elapsed_time": "0:02:11", "remaining_time": "0:02:23", "throughput": 2635.18, "total_tokens": 346816} |
| {"current_steps": 550, "total_steps": 1140, "loss": 0.0358, "lr": 3.091425998045356e-05, "epoch": 9.649122807017545, "percentage": 48.25, "elapsed_time": "0:02:12", "remaining_time": "0:02:22", "throughput": 2637.72, "total_tokens": 349824} |
| {"current_steps": 555, "total_steps": 1140, "loss": 0.1735, "lr": 3.0541698287870965e-05, "epoch": 9.736842105263158, "percentage": 48.68, "elapsed_time": "0:02:13", "remaining_time": "0:02:20", "throughput": 2641.45, "total_tokens": 353152} |
| {"current_steps": 560, "total_steps": 1140, "loss": 0.1294, "lr": 3.01678376841921e-05, "epoch": 9.824561403508772, "percentage": 49.12, "elapsed_time": "0:02:14", "remaining_time": "0:02:19", "throughput": 2644.03, "total_tokens": 356384} |
| {"current_steps": 565, "total_steps": 1140, "loss": 0.1055, "lr": 2.9792765798093465e-05, "epoch": 9.912280701754385, "percentage": 49.56, "elapsed_time": "0:02:15", "remaining_time": "0:02:18", "throughput": 2646.15, "total_tokens": 359424} |
| {"current_steps": 570, "total_steps": 1140, "loss": 0.0439, "lr": 2.94165705421624e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:02:16", "remaining_time": "0:02:16", "throughput": 2646.16, "total_tokens": 362240} |
| {"current_steps": 570, "total_steps": 1140, "eval_loss": 0.16682939231395721, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:02:17", "remaining_time": "0:02:17", "throughput": 2634.51, "total_tokens": 362240} |
| {"current_steps": 575, "total_steps": 1140, "loss": 0.0788, "lr": 2.9039340092291373e-05, "epoch": 10.087719298245615, "percentage": 50.44, "elapsed_time": "0:02:19", "remaining_time": "0:02:16", "throughput": 2621.83, "total_tokens": 365312} |
| {"current_steps": 580, "total_steps": 1140, "loss": 0.1636, "lr": 2.8661162867010543e-05, "epoch": 10.175438596491228, "percentage": 50.88, "elapsed_time": "0:02:20", "remaining_time": "0:02:15", "throughput": 2624.96, "total_tokens": 368704} |
| {"current_steps": 585, "total_steps": 1140, "loss": 0.164, "lr": 2.8282127506763456e-05, "epoch": 10.263157894736842, "percentage": 51.32, "elapsed_time": "0:02:21", "remaining_time": "0:02:14", "throughput": 2628.41, "total_tokens": 372160} |
| {"current_steps": 590, "total_steps": 1140, "loss": 0.1611, "lr": 2.7902322853130757e-05, "epoch": 10.350877192982455, "percentage": 51.75, "elapsed_time": "0:02:22", "remaining_time": "0:02:12", "throughput": 2630.46, "total_tokens": 375168} |
| {"current_steps": 595, "total_steps": 1140, "loss": 0.0615, "lr": 2.752183792800671e-05, "epoch": 10.43859649122807, "percentage": 52.19, "elapsed_time": "0:02:23", "remaining_time": "0:02:11", "throughput": 2632.7, "total_tokens": 378208} |
| {"current_steps": 600, "total_steps": 1140, "loss": 0.1507, "lr": 2.7140761912733474e-05, "epoch": 10.526315789473685, "percentage": 52.63, "elapsed_time": "0:02:24", "remaining_time": "0:02:10", "throughput": 2635.35, "total_tokens": 381408} |
| {"current_steps": 605, "total_steps": 1140, "loss": 0.1174, "lr": 2.6759184127198046e-05, "epoch": 10.614035087719298, "percentage": 53.07, "elapsed_time": "0:02:25", "remaining_time": "0:02:08", "throughput": 2636.37, "total_tokens": 384192} |
| {"current_steps": 610, "total_steps": 1140, "loss": 0.0855, "lr": 2.6377194008896637e-05, "epoch": 10.701754385964913, "percentage": 53.51, "elapsed_time": "0:02:26", "remaining_time": "0:02:07", "throughput": 2638.65, "total_tokens": 387328} |
| {"current_steps": 615, "total_steps": 1140, "loss": 0.1172, "lr": 2.5994881091971605e-05, "epoch": 10.789473684210526, "percentage": 53.95, "elapsed_time": "0:02:27", "remaining_time": "0:02:06", "throughput": 2642.0, "total_tokens": 391008} |
| {"current_steps": 620, "total_steps": 1140, "loss": 0.0348, "lr": 2.5612334986225623e-05, "epoch": 10.87719298245614, "percentage": 54.39, "elapsed_time": "0:02:29", "remaining_time": "0:02:04", "throughput": 2644.84, "total_tokens": 394112} |
| {"current_steps": 625, "total_steps": 1140, "loss": 0.1436, "lr": 2.5229645356118163e-05, "epoch": 10.964912280701755, "percentage": 54.82, "elapsed_time": "0:02:30", "remaining_time": "0:02:03", "throughput": 2646.39, "total_tokens": 397120} |
| {"current_steps": 627, "total_steps": 1140, "eval_loss": 0.16373665630817413, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "0:02:31", "remaining_time": "0:02:03", "throughput": 2633.72, "total_tokens": 397880} |
| {"current_steps": 630, "total_steps": 1140, "loss": 0.0709, "lr": 2.4846901899749185e-05, "epoch": 11.052631578947368, "percentage": 55.26, "elapsed_time": "0:02:32", "remaining_time": "0:02:03", "throughput": 2620.97, "total_tokens": 400024} |
| {"current_steps": 635, "total_steps": 1140, "loss": 0.2151, "lr": 2.4464194327834926e-05, "epoch": 11.140350877192983, "percentage": 55.7, "elapsed_time": "0:02:33", "remaining_time": "0:02:02", "throughput": 2624.05, "total_tokens": 403544} |
| {"current_steps": 640, "total_steps": 1140, "loss": 0.067, "lr": 2.4081612342680694e-05, "epoch": 11.228070175438596, "percentage": 56.14, "elapsed_time": "0:02:34", "remaining_time": "0:02:01", "throughput": 2627.17, "total_tokens": 407192} |
| {"current_steps": 645, "total_steps": 1140, "loss": 0.1594, "lr": 2.369924561715569e-05, "epoch": 11.31578947368421, "percentage": 56.58, "elapsed_time": "0:02:36", "remaining_time": "0:01:59", "throughput": 2629.41, "total_tokens": 410328} |
| {"current_steps": 650, "total_steps": 1140, "loss": 0.1185, "lr": 2.3317183773674718e-05, "epoch": 11.403508771929825, "percentage": 57.02, "elapsed_time": "0:02:37", "remaining_time": "0:01:58", "throughput": 2631.17, "total_tokens": 413176} |
| {"current_steps": 655, "total_steps": 1140, "loss": 0.1009, "lr": 2.2935516363191693e-05, "epoch": 11.491228070175438, "percentage": 57.46, "elapsed_time": "0:02:37", "remaining_time": "0:01:56", "throughput": 2632.55, "total_tokens": 415928} |
| {"current_steps": 660, "total_steps": 1140, "loss": 0.104, "lr": 2.2554332844209904e-05, "epoch": 11.578947368421053, "percentage": 57.89, "elapsed_time": "0:02:39", "remaining_time": "0:01:55", "throughput": 2634.95, "total_tokens": 418968} |
| {"current_steps": 665, "total_steps": 1140, "loss": 0.0887, "lr": 2.2173722561813987e-05, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "0:02:40", "remaining_time": "0:01:54", "throughput": 2637.38, "total_tokens": 422392} |
| {"current_steps": 670, "total_steps": 1140, "loss": 0.1313, "lr": 2.179377472672842e-05, "epoch": 11.75438596491228, "percentage": 58.77, "elapsed_time": "0:02:41", "remaining_time": "0:01:53", "throughput": 2639.41, "total_tokens": 425592} |
| {"current_steps": 675, "total_steps": 1140, "loss": 0.0682, "lr": 2.1414578394407597e-05, "epoch": 11.842105263157894, "percentage": 59.21, "elapsed_time": "0:02:42", "remaining_time": "0:01:51", "throughput": 2641.33, "total_tokens": 428664} |
| {"current_steps": 680, "total_steps": 1140, "loss": 0.0766, "lr": 2.1036222444162147e-05, "epoch": 11.929824561403509, "percentage": 59.65, "elapsed_time": "0:02:43", "remaining_time": "0:01:50", "throughput": 2643.07, "total_tokens": 431576} |
| {"current_steps": 684, "total_steps": 1140, "eval_loss": 0.16736947000026703, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:02:44", "remaining_time": "0:01:49", "throughput": 2631.97, "total_tokens": 433352} |
| {"current_steps": 685, "total_steps": 1140, "loss": 0.1394, "lr": 2.0658795558326743e-05, "epoch": 12.017543859649123, "percentage": 60.09, "elapsed_time": "0:02:45", "remaining_time": "0:01:49", "throughput": 2619.88, "total_tokens": 433864} |
| {"current_steps": 690, "total_steps": 1140, "loss": 0.0829, "lr": 2.0282386201473894e-05, "epoch": 12.105263157894736, "percentage": 60.53, "elapsed_time": "0:02:46", "remaining_time": "0:01:48", "throughput": 2623.19, "total_tokens": 437160} |
| {"current_steps": 695, "total_steps": 1140, "loss": 0.1179, "lr": 1.99070825996789e-05, "epoch": 12.192982456140351, "percentage": 60.96, "elapsed_time": "0:02:47", "remaining_time": "0:01:47", "throughput": 2625.31, "total_tokens": 440264} |
| {"current_steps": 700, "total_steps": 1140, "loss": 0.1595, "lr": 1.9532972719840607e-05, "epoch": 12.280701754385966, "percentage": 61.4, "elapsed_time": "0:02:48", "remaining_time": "0:01:46", "throughput": 2628.33, "total_tokens": 443720} |
| {"current_steps": 705, "total_steps": 1140, "loss": 0.0891, "lr": 1.9160144249063035e-05, "epoch": 12.368421052631579, "percentage": 61.84, "elapsed_time": "0:02:49", "remaining_time": "0:01:44", "throughput": 2628.98, "total_tokens": 446184} |
| {"current_steps": 710, "total_steps": 1140, "loss": 0.1518, "lr": 1.8788684574102467e-05, "epoch": 12.456140350877194, "percentage": 62.28, "elapsed_time": "0:02:50", "remaining_time": "0:01:43", "throughput": 2630.47, "total_tokens": 449800} |
| {"current_steps": 715, "total_steps": 1140, "loss": 0.1242, "lr": 1.8418680760885027e-05, "epoch": 12.543859649122806, "percentage": 62.72, "elapsed_time": "0:02:52", "remaining_time": "0:01:42", "throughput": 2633.28, "total_tokens": 453512} |
| {"current_steps": 720, "total_steps": 1140, "loss": 0.1386, "lr": 1.805021953409934e-05, "epoch": 12.631578947368421, "percentage": 63.16, "elapsed_time": "0:02:53", "remaining_time": "0:01:41", "throughput": 2635.5, "total_tokens": 456712} |
| {"current_steps": 725, "total_steps": 1140, "loss": 0.0818, "lr": 1.7683387256869353e-05, "epoch": 12.719298245614034, "percentage": 63.6, "elapsed_time": "0:02:54", "remaining_time": "0:01:39", "throughput": 2637.25, "total_tokens": 459624} |
| {"current_steps": 730, "total_steps": 1140, "loss": 0.048, "lr": 1.7318269910511736e-05, "epoch": 12.807017543859649, "percentage": 64.04, "elapsed_time": "0:02:55", "remaining_time": "0:01:38", "throughput": 2639.39, "total_tokens": 462792} |
| {"current_steps": 735, "total_steps": 1140, "loss": 0.1374, "lr": 1.6954953074382863e-05, "epoch": 12.894736842105264, "percentage": 64.47, "elapsed_time": "0:02:56", "remaining_time": "0:01:37", "throughput": 2641.14, "total_tokens": 465960} |
| {"current_steps": 740, "total_steps": 1140, "loss": 0.0927, "lr": 1.659352190581993e-05, "epoch": 12.982456140350877, "percentage": 64.91, "elapsed_time": "0:02:57", "remaining_time": "0:01:35", "throughput": 2643.6, "total_tokens": 469480} |
| {"current_steps": 741, "total_steps": 1140, "eval_loss": 0.16528616845607758, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "0:02:58", "remaining_time": "0:01:36", "throughput": 2632.37, "total_tokens": 469568} |
| {"current_steps": 745, "total_steps": 1140, "loss": 0.0564, "lr": 1.6234061120181142e-05, "epoch": 13.070175438596491, "percentage": 65.35, "elapsed_time": "0:03:00", "remaining_time": "0:01:35", "throughput": 2622.16, "total_tokens": 472512} |
| {"current_steps": 750, "total_steps": 1140, "loss": 0.2084, "lr": 1.5876654970989308e-05, "epoch": 13.157894736842104, "percentage": 65.79, "elapsed_time": "0:03:01", "remaining_time": "0:01:34", "throughput": 2623.89, "total_tokens": 475552} |
| {"current_steps": 755, "total_steps": 1140, "loss": 0.0635, "lr": 1.552138723018382e-05, "epoch": 13.24561403508772, "percentage": 66.23, "elapsed_time": "0:03:02", "remaining_time": "0:01:32", "throughput": 2625.76, "total_tokens": 478400} |
| {"current_steps": 760, "total_steps": 1140, "loss": 0.1836, "lr": 1.5168341168485423e-05, "epoch": 13.333333333333334, "percentage": 66.67, "elapsed_time": "0:03:03", "remaining_time": "0:01:31", "throughput": 2628.48, "total_tokens": 482208} |
| {"current_steps": 765, "total_steps": 1140, "loss": 0.1271, "lr": 1.4817599535878565e-05, "epoch": 13.421052631578947, "percentage": 67.11, "elapsed_time": "0:03:04", "remaining_time": "0:01:30", "throughput": 2629.94, "total_tokens": 484992} |
| {"current_steps": 770, "total_steps": 1140, "loss": 0.1617, "lr": 1.4469244542215682e-05, "epoch": 13.508771929824562, "percentage": 67.54, "elapsed_time": "0:03:05", "remaining_time": "0:01:29", "throughput": 2631.91, "total_tokens": 488160} |
| {"current_steps": 775, "total_steps": 1140, "loss": 0.0246, "lr": 1.4123357837948175e-05, "epoch": 13.596491228070175, "percentage": 67.98, "elapsed_time": "0:03:06", "remaining_time": "0:01:27", "throughput": 2633.57, "total_tokens": 491136} |
| {"current_steps": 780, "total_steps": 1140, "loss": 0.0617, "lr": 1.3780020494988446e-05, "epoch": 13.68421052631579, "percentage": 68.42, "elapsed_time": "0:03:07", "remaining_time": "0:01:26", "throughput": 2634.7, "total_tokens": 493824} |
| {"current_steps": 785, "total_steps": 1140, "loss": 0.1239, "lr": 1.3439312987707615e-05, "epoch": 13.771929824561404, "percentage": 68.86, "elapsed_time": "0:03:08", "remaining_time": "0:01:25", "throughput": 2635.9, "total_tokens": 496960} |
| {"current_steps": 790, "total_steps": 1140, "loss": 0.1333, "lr": 1.3101315174073162e-05, "epoch": 13.859649122807017, "percentage": 69.3, "elapsed_time": "0:03:09", "remaining_time": "0:01:23", "throughput": 2637.92, "total_tokens": 500032} |
| {"current_steps": 795, "total_steps": 1140, "loss": 0.0488, "lr": 1.2766106276931223e-05, "epoch": 13.947368421052632, "percentage": 69.74, "elapsed_time": "0:03:10", "remaining_time": "0:01:22", "throughput": 2639.73, "total_tokens": 503296} |
| {"current_steps": 798, "total_steps": 1140, "eval_loss": 0.1684103161096573, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "0:03:11", "remaining_time": "0:01:22", "throughput": 2630.85, "total_tokens": 505048} |
| {"current_steps": 800, "total_steps": 1140, "loss": 0.1163, "lr": 1.243376486543755e-05, "epoch": 14.035087719298245, "percentage": 70.18, "elapsed_time": "0:03:13", "remaining_time": "0:01:22", "throughput": 2620.93, "total_tokens": 506136} |
| {"current_steps": 805, "total_steps": 1140, "loss": 0.0638, "lr": 1.2104368836641908e-05, "epoch": 14.12280701754386, "percentage": 70.61, "elapsed_time": "0:03:14", "remaining_time": "0:01:20", "throughput": 2621.8, "total_tokens": 509432} |
| {"current_steps": 810, "total_steps": 1140, "loss": 0.1865, "lr": 1.1777995397229771e-05, "epoch": 14.210526315789474, "percentage": 71.05, "elapsed_time": "0:03:15", "remaining_time": "0:01:19", "throughput": 2623.09, "total_tokens": 512088} |
| {"current_steps": 815, "total_steps": 1140, "loss": 0.0795, "lr": 1.1454721045426073e-05, "epoch": 14.298245614035087, "percentage": 71.49, "elapsed_time": "0:03:16", "remaining_time": "0:01:18", "throughput": 2625.56, "total_tokens": 515736} |
| {"current_steps": 820, "total_steps": 1140, "loss": 0.2313, "lr": 1.113462155306478e-05, "epoch": 14.385964912280702, "percentage": 71.93, "elapsed_time": "0:03:17", "remaining_time": "0:01:17", "throughput": 2627.32, "total_tokens": 518808} |
| {"current_steps": 825, "total_steps": 1140, "loss": 0.0668, "lr": 1.0817771947828934e-05, "epoch": 14.473684210526315, "percentage": 72.37, "elapsed_time": "0:03:18", "remaining_time": "0:01:15", "throughput": 2629.58, "total_tokens": 522456} |
| {"current_steps": 830, "total_steps": 1140, "loss": 0.0941, "lr": 1.0504246495664932e-05, "epoch": 14.56140350877193, "percentage": 72.81, "elapsed_time": "0:03:19", "remaining_time": "0:01:14", "throughput": 2631.92, "total_tokens": 525816} |
| {"current_steps": 835, "total_steps": 1140, "loss": 0.0827, "lr": 1.0194118683375503e-05, "epoch": 14.649122807017545, "percentage": 73.25, "elapsed_time": "0:03:20", "remaining_time": "0:01:13", "throughput": 2633.52, "total_tokens": 528856} |
| {"current_steps": 840, "total_steps": 1140, "loss": 0.0716, "lr": 9.887461201395176e-06, "epoch": 14.736842105263158, "percentage": 73.68, "elapsed_time": "0:03:21", "remaining_time": "0:01:12", "throughput": 2634.59, "total_tokens": 531704} |
| {"current_steps": 845, "total_steps": 1140, "loss": 0.0978, "lr": 9.584345926752524e-06, "epoch": 14.824561403508772, "percentage": 74.12, "elapsed_time": "0:03:22", "remaining_time": "0:01:10", "throughput": 2637.1, "total_tokens": 535256} |
| {"current_steps": 850, "total_steps": 1140, "loss": 0.0831, "lr": 9.284843906222948e-06, "epoch": 14.912280701754385, "percentage": 74.56, "elapsed_time": "0:03:24", "remaining_time": "0:01:09", "throughput": 2639.28, "total_tokens": 538744} |
| {"current_steps": 855, "total_steps": 1140, "loss": 0.054, "lr": 8.98902533967618e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:03:25", "remaining_time": "0:01:08", "throughput": 2638.59, "total_tokens": 541088} |
| {"current_steps": 855, "total_steps": 1140, "eval_loss": 0.16769246757030487, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:03:25", "remaining_time": "0:01:08", "throughput": 2630.84, "total_tokens": 541088} |
| {"current_steps": 860, "total_steps": 1140, "loss": 0.1421, "lr": 8.696959563622174e-06, "epoch": 15.087719298245615, "percentage": 75.44, "elapsed_time": "0:03:27", "remaining_time": "0:01:07", "throughput": 2621.73, "total_tokens": 544032} |
| {"current_steps": 865, "total_steps": 1140, "loss": 0.1449, "lr": 8.40871503495947e-06, "epoch": 15.175438596491228, "percentage": 75.88, "elapsed_time": "0:03:28", "remaining_time": "0:01:06", "throughput": 2623.57, "total_tokens": 547360} |
| {"current_steps": 870, "total_steps": 1140, "loss": 0.1799, "lr": 8.124359314929622e-06, "epoch": 15.263157894736842, "percentage": 76.32, "elapsed_time": "0:03:29", "remaining_time": "0:01:05", "throughput": 2625.56, "total_tokens": 550560} |
| {"current_steps": 875, "total_steps": 1140, "loss": 0.0431, "lr": 7.843959053281663e-06, "epoch": 15.350877192982455, "percentage": 76.75, "elapsed_time": "0:03:30", "remaining_time": "0:01:03", "throughput": 2627.24, "total_tokens": 553632} |
| {"current_steps": 880, "total_steps": 1140, "loss": 0.1225, "lr": 7.5675799726501155e-06, "epoch": 15.43859649122807, "percentage": 77.19, "elapsed_time": "0:03:31", "remaining_time": "0:01:02", "throughput": 2629.35, "total_tokens": 557184} |
| {"current_steps": 885, "total_steps": 1140, "loss": 0.1155, "lr": 7.295286853150391e-06, "epoch": 15.526315789473685, "percentage": 77.63, "elapsed_time": "0:03:33", "remaining_time": "0:01:01", "throughput": 2631.8, "total_tokens": 560896} |
| {"current_steps": 890, "total_steps": 1140, "loss": 0.0485, "lr": 7.027143517195023e-06, "epoch": 15.614035087719298, "percentage": 78.07, "elapsed_time": "0:03:34", "remaining_time": "0:01:00", "throughput": 2634.72, "total_tokens": 564864} |
| {"current_steps": 895, "total_steps": 1140, "loss": 0.1101, "lr": 6.763212814534484e-06, "epoch": 15.701754385964913, "percentage": 78.51, "elapsed_time": "0:03:35", "remaining_time": "0:00:58", "throughput": 2636.36, "total_tokens": 568160} |
| {"current_steps": 900, "total_steps": 1140, "loss": 0.0698, "lr": 6.503556607525838e-06, "epoch": 15.789473684210526, "percentage": 78.95, "elapsed_time": "0:03:36", "remaining_time": "0:00:57", "throughput": 2637.8, "total_tokens": 571136} |
| {"current_steps": 905, "total_steps": 1140, "loss": 0.0968, "lr": 6.248235756632984e-06, "epoch": 15.87719298245614, "percentage": 79.39, "elapsed_time": "0:03:37", "remaining_time": "0:00:56", "throughput": 2639.59, "total_tokens": 574272} |
| {"current_steps": 910, "total_steps": 1140, "loss": 0.116, "lr": 5.997310106161589e-06, "epoch": 15.964912280701755, "percentage": 79.82, "elapsed_time": "0:03:38", "remaining_time": "0:00:55", "throughput": 2640.36, "total_tokens": 576864} |
| {"current_steps": 912, "total_steps": 1140, "eval_loss": 0.16834516823291779, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:03:39", "remaining_time": "0:00:54", "throughput": 2631.57, "total_tokens": 577512} |
| {"current_steps": 915, "total_steps": 1140, "loss": 0.1738, "lr": 5.7508384702323226e-06, "epoch": 16.05263157894737, "percentage": 80.26, "elapsed_time": "0:03:40", "remaining_time": "0:00:54", "throughput": 2623.22, "total_tokens": 579272} |
| {"current_steps": 920, "total_steps": 1140, "loss": 0.0412, "lr": 5.508878618995439e-06, "epoch": 16.140350877192983, "percentage": 80.7, "elapsed_time": "0:03:41", "remaining_time": "0:00:53", "throughput": 2623.76, "total_tokens": 582472} |
| {"current_steps": 925, "total_steps": 1140, "loss": 0.1432, "lr": 5.271487265090163e-06, "epoch": 16.228070175438596, "percentage": 81.14, "elapsed_time": "0:03:42", "remaining_time": "0:00:51", "throughput": 2624.09, "total_tokens": 584872} |
| {"current_steps": 930, "total_steps": 1140, "loss": 0.0739, "lr": 5.038720050351842e-06, "epoch": 16.31578947368421, "percentage": 81.58, "elapsed_time": "0:03:43", "remaining_time": "0:00:50", "throughput": 2625.09, "total_tokens": 587592} |
| {"current_steps": 935, "total_steps": 1140, "loss": 0.1136, "lr": 4.810631532770182e-06, "epoch": 16.403508771929825, "percentage": 82.02, "elapsed_time": "0:03:44", "remaining_time": "0:00:49", "throughput": 2626.47, "total_tokens": 590888} |
| {"current_steps": 940, "total_steps": 1140, "loss": 0.0824, "lr": 4.587275173701428e-06, "epoch": 16.49122807017544, "percentage": 82.46, "elapsed_time": "0:03:46", "remaining_time": "0:00:48", "throughput": 2628.96, "total_tokens": 594504} |
| {"current_steps": 945, "total_steps": 1140, "loss": 0.113, "lr": 4.368703325337667e-06, "epoch": 16.57894736842105, "percentage": 82.89, "elapsed_time": "0:03:47", "remaining_time": "0:00:46", "throughput": 2631.06, "total_tokens": 598152} |
| {"current_steps": 950, "total_steps": 1140, "loss": 0.0814, "lr": 4.154967218436037e-06, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "0:03:48", "remaining_time": "0:00:45", "throughput": 2632.87, "total_tokens": 601288} |
| {"current_steps": 955, "total_steps": 1140, "loss": 0.2507, "lr": 3.94611695031086e-06, "epoch": 16.75438596491228, "percentage": 83.77, "elapsed_time": "0:03:49", "remaining_time": "0:00:44", "throughput": 2635.2, "total_tokens": 605064} |
| {"current_steps": 960, "total_steps": 1140, "loss": 0.0622, "lr": 3.74220147309135e-06, "epoch": 16.842105263157894, "percentage": 84.21, "elapsed_time": "0:03:50", "remaining_time": "0:00:43", "throughput": 2636.64, "total_tokens": 608200} |
| {"current_steps": 965, "total_steps": 1140, "loss": 0.0392, "lr": 3.543268582247844e-06, "epoch": 16.92982456140351, "percentage": 84.65, "elapsed_time": "0:03:51", "remaining_time": "0:00:42", "throughput": 2638.58, "total_tokens": 611752} |
| {"current_steps": 969, "total_steps": 1140, "eval_loss": 0.17154988646507263, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "0:03:53", "remaining_time": "0:00:41", "throughput": 2631.79, "total_tokens": 614128} |
| {"current_steps": 970, "total_steps": 1140, "loss": 0.0407, "lr": 3.3493649053890326e-06, "epoch": 17.017543859649123, "percentage": 85.09, "elapsed_time": "0:03:54", "remaining_time": "0:00:41", "throughput": 2623.65, "total_tokens": 614832} |
| {"current_steps": 975, "total_steps": 1140, "loss": 0.1085, "lr": 3.1605358913330385e-06, "epoch": 17.105263157894736, "percentage": 85.53, "elapsed_time": "0:03:55", "remaining_time": "0:00:39", "throughput": 2624.42, "total_tokens": 618032} |
| {"current_steps": 980, "total_steps": 1140, "loss": 0.1136, "lr": 2.9768257994546662e-06, "epoch": 17.19298245614035, "percentage": 85.96, "elapsed_time": "0:03:56", "remaining_time": "0:00:38", "throughput": 2625.56, "total_tokens": 620944} |
| {"current_steps": 985, "total_steps": 1140, "loss": 0.0963, "lr": 2.7982776893115627e-06, "epoch": 17.280701754385966, "percentage": 86.4, "elapsed_time": "0:03:57", "remaining_time": "0:00:37", "throughput": 2627.75, "total_tokens": 624720} |
| {"current_steps": 990, "total_steps": 1140, "loss": 0.0907, "lr": 2.624933410551508e-06, "epoch": 17.36842105263158, "percentage": 86.84, "elapsed_time": "0:03:58", "remaining_time": "0:00:36", "throughput": 2629.14, "total_tokens": 627632} |
| {"current_steps": 995, "total_steps": 1140, "loss": 0.079, "lr": 2.456833593103361e-06, "epoch": 17.45614035087719, "percentage": 87.28, "elapsed_time": "0:03:59", "remaining_time": "0:00:34", "throughput": 2630.43, "total_tokens": 630768} |
| {"current_steps": 1000, "total_steps": 1140, "loss": 0.0352, "lr": 2.2940176376538445e-06, "epoch": 17.54385964912281, "percentage": 87.72, "elapsed_time": "0:04:00", "remaining_time": "0:00:33", "throughput": 2631.81, "total_tokens": 633616} |
| {"current_steps": 1005, "total_steps": 1140, "loss": 0.1026, "lr": 2.136523706412477e-06, "epoch": 17.63157894736842, "percentage": 88.16, "elapsed_time": "0:04:01", "remaining_time": "0:00:32", "throughput": 2633.33, "total_tokens": 636720} |
| {"current_steps": 1010, "total_steps": 1140, "loss": 0.2101, "lr": 1.984388714166799e-06, "epoch": 17.719298245614034, "percentage": 88.6, "elapsed_time": "0:04:02", "remaining_time": "0:00:31", "throughput": 2634.62, "total_tokens": 639696} |
| {"current_steps": 1015, "total_steps": 1140, "loss": 0.0806, "lr": 1.837648319629956e-06, "epoch": 17.80701754385965, "percentage": 89.04, "elapsed_time": "0:04:03", "remaining_time": "0:00:30", "throughput": 2635.35, "total_tokens": 642320} |
| {"current_steps": 1020, "total_steps": 1140, "loss": 0.0863, "lr": 1.6963369170826943e-06, "epoch": 17.894736842105264, "percentage": 89.47, "elapsed_time": "0:04:05", "remaining_time": "0:00:28", "throughput": 2637.63, "total_tokens": 646416} |
| {"current_steps": 1025, "total_steps": 1140, "loss": 0.1652, "lr": 1.5604876283117326e-06, "epoch": 17.982456140350877, "percentage": 89.91, "elapsed_time": "0:04:06", "remaining_time": "0:00:27", "throughput": 2639.13, "total_tokens": 649488} |
| {"current_steps": 1026, "total_steps": 1140, "eval_loss": 0.16611041128635406, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:04:06", "remaining_time": "0:00:27", "throughput": 2630.42, "total_tokens": 649608} |
| {"current_steps": 1030, "total_steps": 1140, "loss": 0.1597, "lr": 1.4301322948464147e-06, "epoch": 18.07017543859649, "percentage": 90.35, "elapsed_time": "0:04:08", "remaining_time": "0:00:26", "throughput": 2623.94, "total_tokens": 652360} |
| {"current_steps": 1035, "total_steps": 1140, "loss": 0.0381, "lr": 1.3053014704953987e-06, "epoch": 18.157894736842106, "percentage": 90.79, "elapsed_time": "0:04:09", "remaining_time": "0:00:25", "throughput": 2625.57, "total_tokens": 655912} |
| {"current_steps": 1040, "total_steps": 1140, "loss": 0.091, "lr": 1.1860244141851773e-06, "epoch": 18.24561403508772, "percentage": 91.23, "elapsed_time": "0:04:10", "remaining_time": "0:00:24", "throughput": 2626.36, "total_tokens": 658728} |
| {"current_steps": 1045, "total_steps": 1140, "loss": 0.1058, "lr": 1.0723290831021471e-06, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "0:04:11", "remaining_time": "0:00:22", "throughput": 2627.72, "total_tokens": 661960} |
| {"current_steps": 1050, "total_steps": 1140, "loss": 0.1121, "lr": 9.642421261397472e-07, "epoch": 18.42105263157895, "percentage": 92.11, "elapsed_time": "0:04:13", "remaining_time": "0:00:21", "throughput": 2629.41, "total_tokens": 665352} |
| {"current_steps": 1055, "total_steps": 1140, "loss": 0.0667, "lr": 8.617888776522642e-07, "epoch": 18.50877192982456, "percentage": 92.54, "elapsed_time": "0:04:14", "remaining_time": "0:00:20", "throughput": 2630.78, "total_tokens": 668584} |
| {"current_steps": 1060, "total_steps": 1140, "loss": 0.0835, "lr": 7.649933515167407e-07, "epoch": 18.596491228070175, "percentage": 92.98, "elapsed_time": "0:04:15", "remaining_time": "0:00:19", "throughput": 2632.91, "total_tokens": 672232} |
| {"current_steps": 1065, "total_steps": 1140, "loss": 0.0619, "lr": 6.738782355044049e-07, "epoch": 18.68421052631579, "percentage": 93.42, "elapsed_time": "0:04:16", "remaining_time": "0:00:18", "throughput": 2633.98, "total_tokens": 675208} |
| {"current_steps": 1070, "total_steps": 1140, "loss": 0.1326, "lr": 5.88464885962911e-07, "epoch": 18.771929824561404, "percentage": 93.86, "elapsed_time": "0:04:17", "remaining_time": "0:00:16", "throughput": 2635.03, "total_tokens": 678216} |
| {"current_steps": 1075, "total_steps": 1140, "loss": 0.2085, "lr": 5.087733228106517e-07, "epoch": 18.859649122807017, "percentage": 94.3, "elapsed_time": "0:04:18", "remaining_time": "0:00:15", "throughput": 2635.76, "total_tokens": 680808} |
| {"current_steps": 1080, "total_steps": 1140, "loss": 0.0601, "lr": 4.3482222484432513e-07, "epoch": 18.94736842105263, "percentage": 94.74, "elapsed_time": "0:04:19", "remaining_time": "0:00:14", "throughput": 2637.39, "total_tokens": 684104} |
| {"current_steps": 1083, "total_steps": 1140, "eval_loss": 0.1681518256664276, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:04:20", "remaining_time": "0:00:13", "throughput": 2630.11, "total_tokens": 685200} |
| {"current_steps": 1085, "total_steps": 1140, "loss": 0.1252, "lr": 3.666289253608235e-07, "epoch": 19.035087719298247, "percentage": 95.18, "elapsed_time": "0:04:21", "remaining_time": "0:00:13", "throughput": 2623.22, "total_tokens": 686608} |
| {"current_steps": 1090, "total_steps": 1140, "loss": 0.049, "lr": 3.0420940809451624e-07, "epoch": 19.12280701754386, "percentage": 95.61, "elapsed_time": "0:04:22", "remaining_time": "0:00:12", "throughput": 2623.93, "total_tokens": 689616} |
| {"current_steps": 1095, "total_steps": 1140, "loss": 0.0456, "lr": 2.47578303470844e-07, "epoch": 19.210526315789473, "percentage": 96.05, "elapsed_time": "0:04:23", "remaining_time": "0:00:10", "throughput": 2625.31, "total_tokens": 692784} |
| {"current_steps": 1100, "total_steps": 1140, "loss": 0.0582, "lr": 1.96748885177106e-07, "epoch": 19.29824561403509, "percentage": 96.49, "elapsed_time": "0:04:25", "remaining_time": "0:00:09", "throughput": 2627.0, "total_tokens": 696176} |
| {"current_steps": 1105, "total_steps": 1140, "loss": 0.253, "lr": 1.517330670512629e-07, "epoch": 19.385964912280702, "percentage": 96.93, "elapsed_time": "0:04:26", "remaining_time": "0:00:08", "throughput": 2628.29, "total_tokens": 699184} |
| {"current_steps": 1110, "total_steps": 1140, "loss": 0.0827, "lr": 1.125414002894759e-07, "epoch": 19.473684210526315, "percentage": 97.37, "elapsed_time": "0:04:27", "remaining_time": "0:00:07", "throughput": 2629.72, "total_tokens": 702448} |
| {"current_steps": 1115, "total_steps": 1140, "loss": 0.0775, "lr": 7.918307097301014e-08, "epoch": 19.56140350877193, "percentage": 97.81, "elapsed_time": "0:04:28", "remaining_time": "0:00:06", "throughput": 2630.47, "total_tokens": 705232} |
| {"current_steps": 1120, "total_steps": 1140, "loss": 0.1479, "lr": 5.166589791513465e-08, "epoch": 19.649122807017545, "percentage": 98.25, "elapsed_time": "0:04:29", "remaining_time": "0:00:04", "throughput": 2632.54, "total_tokens": 708624} |
| {"current_steps": 1125, "total_steps": 1140, "loss": 0.125, "lr": 2.999633082847453e-08, "epoch": 19.736842105263158, "percentage": 98.68, "elapsed_time": "0:04:30", "remaining_time": "0:00:03", "throughput": 2633.39, "total_tokens": 711568} |
| {"current_steps": 1130, "total_steps": 1140, "loss": 0.071, "lr": 1.4179448813278484e-08, "epoch": 19.82456140350877, "percentage": 99.12, "elapsed_time": "0:04:31", "remaining_time": "0:00:02", "throughput": 2634.98, "total_tokens": 715216} |
| {"current_steps": 1135, "total_steps": 1140, "loss": 0.1223, "lr": 4.218959166932268e-09, "epoch": 19.912280701754387, "percentage": 99.56, "elapsed_time": "0:04:32", "remaining_time": "0:00:01", "throughput": 2636.22, "total_tokens": 718288} |
| {"current_steps": 1140, "total_steps": 1140, "loss": 0.0863, "lr": 1.1719651499819683e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:33", "remaining_time": "0:00:00", "throughput": 2636.96, "total_tokens": 721856} |
| {"current_steps": 1140, "total_steps": 1140, "eval_loss": 0.16840095818042755, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:34", "remaining_time": "0:00:00", "throughput": 2631.11, "total_tokens": 721856} |
| {"current_steps": 1140, "total_steps": 1140, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:35", "remaining_time": "0:00:00", "throughput": 2623.85, "total_tokens": 721856} |
|
|