trainer_log.jsonl

{"current_steps": 10, "total_steps": 312, "loss": 0.7923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.03, "percentage": 3.21, "elapsed_time": "0:00:44", "remaining_time": "0:22:15"}
{"current_steps": 20, "total_steps": 312, "loss": 0.1889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.06, "percentage": 6.41, "elapsed_time": "0:01:24", "remaining_time": "0:20:33"}
{"current_steps": 30, "total_steps": 312, "loss": 0.1673, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000498554476723488, "epoch": 0.1, "percentage": 9.62, "elapsed_time": "0:02:05", "remaining_time": "0:19:39"}
{"current_steps": 40, "total_steps": 312, "loss": 0.1507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004942346231942955, "epoch": 0.13, "percentage": 12.82, "elapsed_time": "0:02:46", "remaining_time": "0:18:49"}
{"current_steps": 50, "total_steps": 312, "loss": 0.1385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004870903950030429, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:03:27", "remaining_time": "0:18:09"}
{"current_steps": 60, "total_steps": 312, "loss": 0.1593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047720440933487574, "epoch": 0.19, "percentage": 19.23, "elapsed_time": "0:04:10", "remaining_time": "0:17:30"}
{"current_steps": 70, "total_steps": 312, "loss": 0.1549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004646909895689508, "epoch": 0.22, "percentage": 22.44, "elapsed_time": "0:04:50", "remaining_time": "0:16:43"}
{"current_steps": 80, "total_steps": 312, "loss": 0.159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004496948432215913, "epoch": 0.26, "percentage": 25.64, "elapsed_time": "0:05:30", "remaining_time": "0:15:59"}
{"current_steps": 90, "total_steps": 312, "loss": 0.1562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004323893885216219, "epoch": 0.29, "percentage": 28.85, "elapsed_time": "0:06:10", "remaining_time": "0:15:13"}
{"current_steps": 100, "total_steps": 312, "loss": 0.1352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041297474896967814, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:06:53", "remaining_time": "0:14:36"}
{"current_steps": 110, "total_steps": 312, "loss": 0.1588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003916754390727794, "epoch": 0.35, "percentage": 35.26, "elapsed_time": "0:07:33", "remaining_time": "0:13:52"}
{"current_steps": 120, "total_steps": 312, "loss": 0.1523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003687377680167626, "epoch": 0.38, "percentage": 38.46, "elapsed_time": "0:08:15", "remaining_time": "0:13:12"}
{"current_steps": 130, "total_steps": 312, "loss": 0.1418, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003444269913009912, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:08:55", "remaining_time": "0:12:29"}
{"current_steps": 140, "total_steps": 312, "loss": 0.1428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003190242432743673, "epoch": 0.45, "percentage": 44.87, "elapsed_time": "0:09:38", "remaining_time": "0:11:50"}
{"current_steps": 150, "total_steps": 312, "loss": 0.1471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002928232860453694, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:10:18", "remaining_time": "0:11:08"}
{"current_steps": 160, "total_steps": 312, "loss": 0.1427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026612711236232914, "epoch": 0.51, "percentage": 51.28, "elapsed_time": "0:10:59", "remaining_time": "0:10:26"}
{"current_steps": 170, "total_steps": 312, "loss": 0.1366, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023924444174886733, "epoch": 0.54, "percentage": 54.49, "elapsed_time": "0:11:40", "remaining_time": "0:09:44"}
{"current_steps": 180, "total_steps": 312, "loss": 0.1463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021248615041383683, "epoch": 0.58, "percentage": 57.69, "elapsed_time": "0:12:21", "remaining_time": "0:09:03"}
{"current_steps": 190, "total_steps": 312, "loss": 0.1328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018616167622095327, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "0:13:03", "remaining_time": "0:08:22"}
{"current_steps": 200, "total_steps": 312, "loss": 0.134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001605754402917186, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:13:42", "remaining_time": "0:07:40"}
{"current_steps": 210, "total_steps": 312, "loss": 0.1417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013602332662288535, "epoch": 0.67, "percentage": 67.31, "elapsed_time": "0:14:22", "remaining_time": "0:06:59"}
{"current_steps": 220, "total_steps": 312, "loss": 0.1194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011278926042882027, "epoch": 0.7, "percentage": 70.51, "elapsed_time": "0:15:03", "remaining_time": "0:06:18"}
{"current_steps": 230, "total_steps": 312, "loss": 0.1359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.114192477745568e-05, "epoch": 0.74, "percentage": 73.72, "elapsed_time": "0:15:44", "remaining_time": "0:05:36"}
{"current_steps": 240, "total_steps": 312, "loss": 0.1244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.133165348925977e-05, "epoch": 0.77, "percentage": 76.92, "elapsed_time": "0:16:22", "remaining_time": "0:04:54"}
{"current_steps": 250, "total_steps": 312, "loss": 0.1367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3587536230321364e-05, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:17:05", "remaining_time": "0:04:14"}
{"current_steps": 260, "total_steps": 312, "loss": 0.1256, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.811476927679228e-05, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:17:47", "remaining_time": "0:03:33"}
{"current_steps": 270, "total_steps": 312, "loss": 0.1312, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5092282586939186e-05, "epoch": 0.86, "percentage": 86.54, "elapsed_time": "0:18:27", "remaining_time": "0:02:52"}
{"current_steps": 280, "total_steps": 312, "loss": 0.1272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.467067062178823e-05, "epoch": 0.9, "percentage": 89.74, "elapsed_time": "0:19:06", "remaining_time": "0:02:11"}
{"current_steps": 290, "total_steps": 312, "loss": 0.1241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.970450842734649e-06, "epoch": 0.93, "percentage": 92.95, "elapsed_time": "0:19:49", "remaining_time": "0:01:30"}
{"current_steps": 300, "total_steps": 312, "loss": 0.1234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0806700251775058e-06, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:20:32", "remaining_time": "0:00:49"}
{"current_steps": 310, "total_steps": 312, "loss": 0.1305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7874505027283307e-08, "epoch": 0.99, "percentage": 99.36, "elapsed_time": "0:21:12", "remaining_time": "0:00:08"}
{"current_steps": 312, "total_steps": 312, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:21:20", "remaining_time": "0:00:00"}