trainer_log.jsonl

{"current_steps": 5, "total_steps": 250, "loss": 5.4501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019987369566060176, "epoch": 0.02, "percentage": 2.0, "elapsed_time": "0:00:06", "remaining_time": "0:05:30"}
{"current_steps": 10, "total_steps": 250, "loss": 4.9761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019949510169813003, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:12", "remaining_time": "0:05:04"}
{"current_steps": 15, "total_steps": 250, "loss": 4.0797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001986685944207868, "epoch": 0.06, "percentage": 6.0, "elapsed_time": "0:00:19", "remaining_time": "0:05:07"}
{"current_steps": 20, "total_steps": 250, "loss": 2.9864, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019745268727865774, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:00:27", "remaining_time": "0:05:13"}
{"current_steps": 25, "total_steps": 250, "loss": 2.8715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001958521789017376, "epoch": 0.1, "percentage": 10.0, "elapsed_time": "0:00:35", "remaining_time": "0:05:16"}
{"current_steps": 30, "total_steps": 250, "loss": 2.4938, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019387338576538744, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:00:42", "remaining_time": "0:05:13"}
{"current_steps": 35, "total_steps": 250, "loss": 2.4925, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019152411726209176, "epoch": 0.14, "percentage": 14.0, "elapsed_time": "0:00:50", "remaining_time": "0:05:11"}
{"current_steps": 40, "total_steps": 250, "loss": 2.5641, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001899405251566371, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:00:58", "remaining_time": "0:05:08"}
{"current_steps": 45, "total_steps": 250, "loss": 2.8727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001870183754669526, "epoch": 0.18, "percentage": 18.0, "elapsed_time": "0:01:07", "remaining_time": "0:05:06"}
{"current_steps": 50, "total_steps": 250, "loss": 2.9301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001837528040042142, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:14", "remaining_time": "0:04:56"}
{"current_steps": 55, "total_steps": 250, "loss": 2.5419, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018015669848708767, "epoch": 0.22, "percentage": 22.0, "elapsed_time": "0:01:21", "remaining_time": "0:04:47"}
{"current_steps": 60, "total_steps": 250, "loss": 2.5677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001762442511011448, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:01:27", "remaining_time": "0:04:37"}
{"current_steps": 65, "total_steps": 250, "loss": 2.5559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001720309024887907, "epoch": 0.26, "percentage": 26.0, "elapsed_time": "0:01:36", "remaining_time": "0:04:33"}
{"current_steps": 70, "total_steps": 250, "loss": 2.5763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016753328081210245, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:43", "remaining_time": "0:04:25"}
{"current_steps": 75, "total_steps": 250, "loss": 2.4963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016276913612907007, "epoch": 0.3, "percentage": 30.0, "elapsed_time": "0:01:50", "remaining_time": "0:04:18"}
{"current_steps": 80, "total_steps": 250, "loss": 2.5602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015775727034222675, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:01:57", "remaining_time": "0:04:09"}
{"current_steps": 85, "total_steps": 250, "loss": 2.6872, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001525174629961296, "epoch": 0.34, "percentage": 34.0, "elapsed_time": "0:02:03", "remaining_time": "0:03:59"}
{"current_steps": 90, "total_steps": 250, "loss": 2.4969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001470703932165333, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:02:09", "remaining_time": "0:03:50"}
{"current_steps": 95, "total_steps": 250, "loss": 2.4725, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014143755809932845, "epoch": 0.38, "percentage": 38.0, "elapsed_time": "0:02:17", "remaining_time": "0:03:44"}
{"current_steps": 100, "total_steps": 250, "loss": 2.3662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013564118787132506, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:02:23", "remaining_time": "0:03:35"}
{"current_steps": 105, "total_steps": 250, "loss": 2.3748, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001297041581577035, "epoch": 0.42, "percentage": 42.0, "elapsed_time": "0:02:33", "remaining_time": "0:03:31"}
{"current_steps": 110, "total_steps": 250, "loss": 2.4374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012364989970237248, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:02:39", "remaining_time": "0:03:23"}
{"current_steps": 115, "total_steps": 250, "loss": 2.2459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011750230589752762, "epoch": 0.46, "percentage": 46.0, "elapsed_time": "0:02:47", "remaining_time": "0:03:16"}
{"current_steps": 120, "total_steps": 250, "loss": 2.6068, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011128563848734816, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:02:53", "remaining_time": "0:03:08"}
{"current_steps": 125, "total_steps": 250, "loss": 2.6697, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010502443181797697, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:03:00", "remaining_time": "0:03:00"}
{"current_steps": 130, "total_steps": 250, "loss": 2.1541, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.874339601166473e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:03:08", "remaining_time": "0:02:53"}
{"current_steps": 135, "total_steps": 250, "loss": 2.5094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.246731944720675e-05, "epoch": 0.54, "percentage": 54.0, "elapsed_time": "0:03:14", "remaining_time": "0:02:45"}
{"current_steps": 140, "total_steps": 250, "loss": 2.693, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.62209709315362e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:03:22", "remaining_time": "0:02:39"}
{"current_steps": 145, "total_steps": 250, "loss": 2.4028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.002900194855932e-05, "epoch": 0.58, "percentage": 58.0, "elapsed_time": "0:03:29", "remaining_time": "0:02:31"}
{"current_steps": 150, "total_steps": 250, "loss": 2.5198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.391584937101033e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:03:36", "remaining_time": "0:02:24"}
{"current_steps": 155, "total_steps": 250, "loss": 2.3054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.790563901927907e-05, "epoch": 0.62, "percentage": 62.0, "elapsed_time": "0:03:42", "remaining_time": "0:02:16"}
{"current_steps": 160, "total_steps": 250, "loss": 2.3357, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.20220904478199e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:03:49", "remaining_time": "0:02:09"}
{"current_steps": 165, "total_steps": 250, "loss": 2.1626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.6288423334906735e-05, "epoch": 0.66, "percentage": 66.0, "elapsed_time": "0:03:56", "remaining_time": "0:02:01"}
{"current_steps": 170, "total_steps": 250, "loss": 2.398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.072726584517086e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:04:03", "remaining_time": "0:01:54"}
{"current_steps": 175, "total_steps": 250, "loss": 2.4083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5360565326573104e-05, "epoch": 0.7, "percentage": 70.0, "elapsed_time": "0:04:11", "remaining_time": "0:01:47"}
{"current_steps": 180, "total_steps": 250, "loss": 2.3016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.020950169424815e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:04:17", "remaining_time": "0:01:40"}
{"current_steps": 185, "total_steps": 250, "loss": 2.1456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.52944038430556e-05, "epoch": 0.74, "percentage": 74.0, "elapsed_time": "0:04:25", "remaining_time": "0:01:33"}
{"current_steps": 190, "total_steps": 250, "loss": 2.3501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.063466941871952e-05, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:04:31", "remaining_time": "0:01:25"}
{"current_steps": 195, "total_steps": 250, "loss": 2.4699, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.624868826418262e-05, "epoch": 0.78, "percentage": 78.0, "elapsed_time": "0:04:37", "remaining_time": "0:01:18"}
{"current_steps": 200, "total_steps": 250, "loss": 2.5444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2153769843297667e-05, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:04:43", "remaining_time": "0:01:10"}
{"current_steps": 205, "total_steps": 250, "loss": 2.3116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8366074928281607e-05, "epoch": 0.82, "percentage": 82.0, "elapsed_time": "0:04:52", "remaining_time": "0:01:04"}
{"current_steps": 210, "total_steps": 250, "loss": 2.5006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4900551820530828e-05, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:04:59", "remaining_time": "0:00:57"}
{"current_steps": 215, "total_steps": 250, "loss": 2.2932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1770877356504683e-05, "epoch": 0.86, "percentage": 86.0, "elapsed_time": "0:05:05", "remaining_time": "0:00:49"}
{"current_steps": 220, "total_steps": 250, "loss": 2.22, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.989402931500434e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:05:12", "remaining_time": "0:00:42"}
{"current_steps": 225, "total_steps": 250, "loss": 2.4223, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.5671057543387985e-06, "epoch": 0.9, "percentage": 90.0, "elapsed_time": "0:05:18", "remaining_time": "0:00:35"}
{"current_steps": 230, "total_steps": 250, "loss": 2.294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.513545525335705e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:05:26", "remaining_time": "0:00:28"}
{"current_steps": 235, "total_steps": 250, "loss": 2.2694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.836826708532603e-06, "epoch": 0.94, "percentage": 94.0, "elapsed_time": "0:05:33", "remaining_time": "0:00:21"}
{"current_steps": 240, "total_steps": 250, "loss": 2.4213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.543566547079467e-06, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:05:41", "remaining_time": "0:00:14"}
{"current_steps": 245, "total_steps": 250, "loss": 2.6469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.388689479991605e-07, "epoch": 0.98, "percentage": 98.0, "elapsed_time": "0:05:48", "remaining_time": "0:00:07"}
{"current_steps": 250, "total_steps": 250, "loss": 2.6638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2630433939825327e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:05:54", "remaining_time": "0:00:00"}
{"current_steps": 250, "total_steps": 250, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:05:54", "remaining_time": "0:00:00"}