| {"current_steps": 5, "total_steps": 1140, "loss": 1.0586, "lr": 1.7543859649122807e-06, "epoch": 0.08771929824561403, "percentage": 0.44, "elapsed_time": "0:00:01", "remaining_time": "0:07:16", "throughput": 1681.94, "total_tokens": 3232} |
| {"current_steps": 10, "total_steps": 1140, "loss": 1.0315, "lr": 3.9473684210526315e-06, "epoch": 0.17543859649122806, "percentage": 0.88, "elapsed_time": "0:00:03", "remaining_time": "0:05:59", "throughput": 2023.28, "total_tokens": 6432} |
| {"current_steps": 15, "total_steps": 1140, "loss": 0.9965, "lr": 6.140350877192982e-06, "epoch": 0.2631578947368421, "percentage": 1.32, "elapsed_time": "0:00:04", "remaining_time": "0:05:25", "throughput": 2159.23, "total_tokens": 9376} |
| {"current_steps": 20, "total_steps": 1140, "loss": 0.9492, "lr": 8.333333333333334e-06, "epoch": 0.3508771929824561, "percentage": 1.75, "elapsed_time": "0:00:05", "remaining_time": "0:05:11", "throughput": 2235.94, "total_tokens": 12448} |
| {"current_steps": 25, "total_steps": 1140, "loss": 0.841, "lr": 1.0526315789473684e-05, "epoch": 0.43859649122807015, "percentage": 2.19, "elapsed_time": "0:00:06", "remaining_time": "0:05:00", "throughput": 2294.73, "total_tokens": 15456} |
| {"current_steps": 30, "total_steps": 1140, "loss": 0.4148, "lr": 1.2719298245614037e-05, "epoch": 0.5263157894736842, "percentage": 2.63, "elapsed_time": "0:00:07", "remaining_time": "0:04:54", "throughput": 2333.76, "total_tokens": 18592} |
| {"current_steps": 35, "total_steps": 1140, "loss": 0.1678, "lr": 1.4912280701754386e-05, "epoch": 0.6140350877192983, "percentage": 3.07, "elapsed_time": "0:00:09", "remaining_time": "0:05:03", "throughput": 2409.67, "total_tokens": 23136} |
| {"current_steps": 40, "total_steps": 1140, "loss": 0.085, "lr": 1.7105263157894737e-05, "epoch": 0.7017543859649122, "percentage": 3.51, "elapsed_time": "0:00:10", "remaining_time": "0:04:59", "throughput": 2432.17, "total_tokens": 26496} |
| {"current_steps": 45, "total_steps": 1140, "loss": 0.2507, "lr": 1.929824561403509e-05, "epoch": 0.7894736842105263, "percentage": 3.95, "elapsed_time": "0:00:12", "remaining_time": "0:04:55", "throughput": 2445.79, "total_tokens": 29728} |
| {"current_steps": 50, "total_steps": 1140, "loss": 0.2552, "lr": 2.149122807017544e-05, "epoch": 0.8771929824561403, "percentage": 4.39, "elapsed_time": "0:00:13", "remaining_time": "0:04:52", "throughput": 2462.86, "total_tokens": 33024} |
| {"current_steps": 55, "total_steps": 1140, "loss": 0.135, "lr": 2.368421052631579e-05, "epoch": 0.9649122807017544, "percentage": 4.82, "elapsed_time": "0:00:14", "remaining_time": "0:04:47", "throughput": 2462.02, "total_tokens": 35904} |
| {"current_steps": 57, "total_steps": 1140, "eval_loss": 0.14342579245567322, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:15", "remaining_time": "0:04:56", "throughput": 2335.57, "total_tokens": 36480} |
| {"current_steps": 60, "total_steps": 1140, "loss": 0.0674, "lr": 2.5877192982456143e-05, "epoch": 1.0526315789473684, "percentage": 5.26, "elapsed_time": "0:00:17", "remaining_time": "0:05:15", "throughput": 2171.02, "total_tokens": 38016} |
| {"current_steps": 65, "total_steps": 1140, "loss": 0.0944, "lr": 2.8070175438596492e-05, "epoch": 1.1403508771929824, "percentage": 5.7, "elapsed_time": "0:00:18", "remaining_time": "0:05:12", "throughput": 2155.94, "total_tokens": 40800} |
| {"current_steps": 70, "total_steps": 1140, "loss": 0.2026, "lr": 3.0263157894736844e-05, "epoch": 1.2280701754385965, "percentage": 6.14, "elapsed_time": "0:00:20", "remaining_time": "0:05:06", "throughput": 2174.6, "total_tokens": 43648} |
| {"current_steps": 75, "total_steps": 1140, "loss": 0.2489, "lr": 3.24561403508772e-05, "epoch": 1.3157894736842106, "percentage": 6.58, "elapsed_time": "0:00:21", "remaining_time": "0:04:59", "throughput": 2184.5, "total_tokens": 46112} |
| {"current_steps": 80, "total_steps": 1140, "loss": 0.0975, "lr": 3.4649122807017546e-05, "epoch": 1.4035087719298245, "percentage": 7.02, "elapsed_time": "0:00:22", "remaining_time": "0:04:57", "throughput": 2211.14, "total_tokens": 49632} |
| {"current_steps": 85, "total_steps": 1140, "loss": 0.0394, "lr": 3.6842105263157895e-05, "epoch": 1.4912280701754386, "percentage": 7.46, "elapsed_time": "0:00:23", "remaining_time": "0:04:54", "throughput": 2232.69, "total_tokens": 53024} |
| {"current_steps": 90, "total_steps": 1140, "loss": 0.1608, "lr": 3.9035087719298244e-05, "epoch": 1.5789473684210527, "percentage": 7.89, "elapsed_time": "0:00:25", "remaining_time": "0:04:53", "throughput": 2255.87, "total_tokens": 56672} |
| {"current_steps": 95, "total_steps": 1140, "loss": 0.3092, "lr": 4.12280701754386e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:00:26", "remaining_time": "0:04:48", "throughput": 2263.56, "total_tokens": 59296} |
| {"current_steps": 100, "total_steps": 1140, "loss": 0.1174, "lr": 4.342105263157895e-05, "epoch": 1.7543859649122808, "percentage": 8.77, "elapsed_time": "0:00:27", "remaining_time": "0:04:45", "throughput": 2274.69, "total_tokens": 62528} |
| {"current_steps": 105, "total_steps": 1140, "loss": 0.01, "lr": 4.56140350877193e-05, "epoch": 1.8421052631578947, "percentage": 9.21, "elapsed_time": "0:00:28", "remaining_time": "0:04:43", "throughput": 2288.95, "total_tokens": 65856} |
| {"current_steps": 110, "total_steps": 1140, "loss": 0.2326, "lr": 4.780701754385965e-05, "epoch": 1.9298245614035088, "percentage": 9.65, "elapsed_time": "0:00:30", "remaining_time": "0:04:42", "throughput": 2305.52, "total_tokens": 69664} |
| {"current_steps": 114, "total_steps": 1140, "eval_loss": 0.10932660102844238, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:31", "remaining_time": "0:04:47", "throughput": 2259.58, "total_tokens": 72112} |
| {"current_steps": 115, "total_steps": 1140, "loss": 0.2628, "lr": 5e-05, "epoch": 2.017543859649123, "percentage": 10.09, "elapsed_time": "0:00:33", "remaining_time": "0:04:57", "throughput": 2180.0, "total_tokens": 72848} |
|
|