| {"current_steps": 5, "total_steps": 1140, "loss": 1.069, "lr": 1.7543859649122807e-06, "epoch": 0.08771929824561403, "percentage": 0.44, "elapsed_time": "0:00:01", "remaining_time": "0:06:29", "throughput": 1883.34, "total_tokens": 3232} | |
| {"current_steps": 10, "total_steps": 1140, "loss": 1.0468, "lr": 3.9473684210526315e-06, "epoch": 0.17543859649122806, "percentage": 0.88, "elapsed_time": "0:00:02", "remaining_time": "0:05:11", "throughput": 2335.71, "total_tokens": 6432} | |
| {"current_steps": 15, "total_steps": 1140, "loss": 1.0459, "lr": 6.140350877192982e-06, "epoch": 0.2631578947368421, "percentage": 1.32, "elapsed_time": "0:00:03", "remaining_time": "0:04:38", "throughput": 2528.56, "total_tokens": 9376} | |
| {"current_steps": 20, "total_steps": 1140, "loss": 1.0752, "lr": 8.333333333333334e-06, "epoch": 0.3508771929824561, "percentage": 1.75, "elapsed_time": "0:00:04", "remaining_time": "0:04:24", "throughput": 2636.23, "total_tokens": 12448} | |
| {"current_steps": 25, "total_steps": 1140, "loss": 1.1407, "lr": 1.0526315789473684e-05, "epoch": 0.43859649122807015, "percentage": 2.19, "elapsed_time": "0:00:05", "remaining_time": "0:04:13", "throughput": 2720.36, "total_tokens": 15456} | |
| {"current_steps": 30, "total_steps": 1140, "loss": 1.0609, "lr": 1.2719298245614037e-05, "epoch": 0.5263157894736842, "percentage": 2.63, "elapsed_time": "0:00:06", "remaining_time": "0:04:07", "throughput": 2774.18, "total_tokens": 18592} | |
| {"current_steps": 35, "total_steps": 1140, "loss": 1.1162, "lr": 1.4912280701754386e-05, "epoch": 0.6140350877192983, "percentage": 3.07, "elapsed_time": "0:00:08", "remaining_time": "0:04:14", "throughput": 2872.32, "total_tokens": 23136} | |
| {"current_steps": 40, "total_steps": 1140, "loss": 1.2, "lr": 1.7105263157894737e-05, "epoch": 0.7017543859649122, "percentage": 3.51, "elapsed_time": "0:00:09", "remaining_time": "0:04:10", "throughput": 2904.91, "total_tokens": 26496} | |
| {"current_steps": 45, "total_steps": 1140, "loss": 1.1708, "lr": 1.929824561403509e-05, "epoch": 0.7894736842105263, "percentage": 3.95, "elapsed_time": "0:00:10", "remaining_time": "0:04:07", "throughput": 2925.76, "total_tokens": 29728} | |
| {"current_steps": 50, "total_steps": 1140, "loss": 1.1806, "lr": 2.149122807017544e-05, "epoch": 0.8771929824561403, "percentage": 4.39, "elapsed_time": "0:00:11", "remaining_time": "0:04:03", "throughput": 2951.81, "total_tokens": 33024} | |
| {"current_steps": 55, "total_steps": 1140, "loss": 1.0901, "lr": 2.368421052631579e-05, "epoch": 0.9649122807017544, "percentage": 4.82, "elapsed_time": "0:00:12", "remaining_time": "0:03:59", "throughput": 2953.86, "total_tokens": 35904} | |
| {"current_steps": 57, "total_steps": 1140, "eval_loss": 1.0707911252975464, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:13", "remaining_time": "0:04:07", "throughput": 2803.76, "total_tokens": 36480} | |
| {"current_steps": 60, "total_steps": 1140, "loss": 0.9906, "lr": 2.5877192982456143e-05, "epoch": 1.0526315789473684, "percentage": 5.26, "elapsed_time": "0:00:14", "remaining_time": "0:04:17", "throughput": 2658.23, "total_tokens": 38016} | |
| {"current_steps": 65, "total_steps": 1140, "loss": 1.1274, "lr": 2.8070175438596492e-05, "epoch": 1.1403508771929824, "percentage": 5.7, "elapsed_time": "0:00:15", "remaining_time": "0:04:12", "throughput": 2677.14, "total_tokens": 40800} | |
| {"current_steps": 70, "total_steps": 1140, "loss": 1.1537, "lr": 3.0263157894736844e-05, "epoch": 1.2280701754385965, "percentage": 6.14, "elapsed_time": "0:00:16", "remaining_time": "0:04:07", "throughput": 2694.56, "total_tokens": 43648} | |
| {"current_steps": 75, "total_steps": 1140, "loss": 1.1593, "lr": 3.24561403508772e-05, "epoch": 1.3157894736842106, "percentage": 6.58, "elapsed_time": "0:00:17", "remaining_time": "0:04:02", "throughput": 2703.61, "total_tokens": 46112} | |
| {"current_steps": 80, "total_steps": 1140, "loss": 1.1648, "lr": 3.4649122807017546e-05, "epoch": 1.4035087719298245, "percentage": 7.02, "elapsed_time": "0:00:18", "remaining_time": "0:04:00", "throughput": 2733.27, "total_tokens": 49632} | |
| {"current_steps": 85, "total_steps": 1140, "loss": 1.0933, "lr": 3.6842105263157895e-05, "epoch": 1.4912280701754386, "percentage": 7.46, "elapsed_time": "0:00:19", "remaining_time": "0:03:58", "throughput": 2756.39, "total_tokens": 53024} | |
| {"current_steps": 90, "total_steps": 1140, "loss": 1.0782, "lr": 3.9035087719298244e-05, "epoch": 1.5789473684210527, "percentage": 7.89, "elapsed_time": "0:00:20", "remaining_time": "0:03:57", "throughput": 2781.7, "total_tokens": 56672} | |
| {"current_steps": 95, "total_steps": 1140, "loss": 1.1739, "lr": 4.12280701754386e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:00:21", "remaining_time": "0:03:53", "throughput": 2790.43, "total_tokens": 59296} | |
| {"current_steps": 100, "total_steps": 1140, "loss": 1.1216, "lr": 4.342105263157895e-05, "epoch": 1.7543859649122808, "percentage": 8.77, "elapsed_time": "0:00:22", "remaining_time": "0:03:52", "throughput": 2801.73, "total_tokens": 62528} | |
| {"current_steps": 105, "total_steps": 1140, "loss": 0.7745, "lr": 4.56140350877193e-05, "epoch": 1.8421052631578947, "percentage": 9.21, "elapsed_time": "0:00:23", "remaining_time": "0:03:50", "throughput": 2817.61, "total_tokens": 65856} | |
| {"current_steps": 110, "total_steps": 1140, "loss": 1.1542, "lr": 4.780701754385965e-05, "epoch": 1.9298245614035088, "percentage": 9.65, "elapsed_time": "0:00:24", "remaining_time": "0:03:50", "throughput": 2835.89, "total_tokens": 69664} | |
| {"current_steps": 114, "total_steps": 1140, "eval_loss": 1.0541099309921265, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:25", "remaining_time": "0:03:53", "throughput": 2774.97, "total_tokens": 72112} | |
| {"current_steps": 115, "total_steps": 1140, "loss": 1.1969, "lr": 5e-05, "epoch": 2.017543859649123, "percentage": 10.09, "elapsed_time": "0:00:26", "remaining_time": "0:04:00", "throughput": 2700.74, "total_tokens": 72848} | |
| {"current_steps": 120, "total_steps": 1140, "loss": 1.217, "lr": 4.999707014206475e-05, "epoch": 2.1052631578947367, "percentage": 10.53, "elapsed_time": "0:00:27", "remaining_time": "0:03:57", "throughput": 2713.45, "total_tokens": 75888} | |
| {"current_steps": 125, "total_steps": 1140, "loss": 1.0263, "lr": 4.9988281254984414e-05, "epoch": 2.192982456140351, "percentage": 10.96, "elapsed_time": "0:00:28", "remaining_time": "0:03:54", "throughput": 2726.54, "total_tokens": 78896} | |
| {"current_steps": 130, "total_steps": 1140, "loss": 0.9664, "lr": 4.997363539877422e-05, "epoch": 2.280701754385965, "percentage": 11.4, "elapsed_time": "0:00:30", "remaining_time": "0:03:53", "throughput": 2742.36, "total_tokens": 82288} | |
| {"current_steps": 135, "total_steps": 1140, "loss": 1.2093, "lr": 4.9953136006256415e-05, "epoch": 2.3684210526315788, "percentage": 11.84, "elapsed_time": "0:00:31", "remaining_time": "0:03:51", "throughput": 2758.38, "total_tokens": 85936} | |
| {"current_steps": 140, "total_steps": 1140, "loss": 1.2388, "lr": 4.9926787882255636e-05, "epoch": 2.456140350877193, "percentage": 12.28, "elapsed_time": "0:00:32", "remaining_time": "0:03:49", "throughput": 2766.73, "total_tokens": 88784} | |
| {"current_steps": 145, "total_steps": 1140, "loss": 1.0375, "lr": 4.9894597202472696e-05, "epoch": 2.543859649122807, "percentage": 12.72, "elapsed_time": "0:00:33", "remaining_time": "0:03:46", "throughput": 2773.88, "total_tokens": 91696} | |
| {"current_steps": 150, "total_steps": 1140, "loss": 0.9317, "lr": 4.985657151203706e-05, "epoch": 2.6315789473684212, "percentage": 13.16, "elapsed_time": "0:00:34", "remaining_time": "0:03:45", "throughput": 2786.09, "total_tokens": 95024} | |
| {"current_steps": 155, "total_steps": 1140, "loss": 0.9987, "lr": 4.9812719723738435e-05, "epoch": 2.719298245614035, "percentage": 13.6, "elapsed_time": "0:00:35", "remaining_time": "0:03:43", "throughput": 2796.64, "total_tokens": 98512} | |
| {"current_steps": 160, "total_steps": 1140, "loss": 1.3112, "lr": 4.976305211593758e-05, "epoch": 2.807017543859649, "percentage": 14.04, "elapsed_time": "0:00:36", "remaining_time": "0:03:42", "throughput": 2805.27, "total_tokens": 101744} | |
| {"current_steps": 165, "total_steps": 1140, "loss": 0.7924, "lr": 4.970758033015731e-05, "epoch": 2.8947368421052633, "percentage": 14.47, "elapsed_time": "0:00:37", "remaining_time": "0:03:40", "throughput": 2816.86, "total_tokens": 105264} | |
| {"current_steps": 170, "total_steps": 1140, "loss": 1.0468, "lr": 4.9646317368353743e-05, "epoch": 2.982456140350877, "percentage": 14.91, "elapsed_time": "0:00:38", "remaining_time": "0:03:39", "throughput": 2824.35, "total_tokens": 108592} | |
| {"current_steps": 171, "total_steps": 1140, "eval_loss": 1.0170763731002808, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:00:39", "remaining_time": "0:03:41", "throughput": 2776.32, "total_tokens": 108712} | |
| {"current_steps": 175, "total_steps": 1140, "loss": 1.2408, "lr": 4.957927758986888e-05, "epoch": 3.0701754385964914, "percentage": 15.35, "elapsed_time": "0:00:40", "remaining_time": "0:03:45", "throughput": 2735.28, "total_tokens": 111976} | |