Files
open_reward_agent_sft_lf/trainer_log.jsonl
ModelHub XC ce5246e3fd 初始化项目,由ModelHub XC社区提供模型
Model: varshak1/open_reward_agent_sft_lf
Source: Original Platform
2026-06-16 07:50:16 +08:00

22 lines
4.1 KiB
JSON

{"current_steps": 10, "total_steps": 205, "loss": 1.6103919982910155, "lr": 6.545454545454546e-06, "epoch": 0.04884004884004884, "percentage": 4.88, "elapsed_time": "0:01:30", "remaining_time": "0:29:33"}
{"current_steps": 20, "total_steps": 205, "loss": 1.1710912704467773, "lr": 7.9664804049057e-06, "epoch": 0.09768009768009768, "percentage": 9.76, "elapsed_time": "0:02:55", "remaining_time": "0:27:04"}
{"current_steps": 30, "total_steps": 205, "loss": 1.0446645736694335, "lr": 7.831269296751948e-06, "epoch": 0.14652014652014653, "percentage": 14.63, "elapsed_time": "0:04:19", "remaining_time": "0:25:14"}
{"current_steps": 40, "total_steps": 205, "loss": 0.9899624824523926, "lr": 7.595806964341581e-06, "epoch": 0.19536019536019536, "percentage": 19.51, "elapsed_time": "0:05:44", "remaining_time": "0:23:39"}
{"current_steps": 50, "total_steps": 205, "loss": 0.9951982498168945, "lr": 7.266254652228843e-06, "epoch": 0.2442002442002442, "percentage": 24.39, "elapsed_time": "0:07:11", "remaining_time": "0:22:17"}
{"current_steps": 60, "total_steps": 205, "loss": 0.9782312393188477, "lr": 6.851235618187317e-06, "epoch": 0.29304029304029305, "percentage": 29.27, "elapsed_time": "0:08:34", "remaining_time": "0:20:42"}
{"current_steps": 70, "total_steps": 205, "loss": 0.9667717933654785, "lr": 6.36160949202369e-06, "epoch": 0.3418803418803419, "percentage": 34.15, "elapsed_time": "0:09:58", "remaining_time": "0:19:13"}
{"current_steps": 80, "total_steps": 205, "loss": 0.9572884559631347, "lr": 5.810188116178156e-06, "epoch": 0.3907203907203907, "percentage": 39.02, "elapsed_time": "0:11:20", "remaining_time": "0:17:43"}
{"current_steps": 90, "total_steps": 205, "loss": 0.9558270454406739, "lr": 5.211400303591802e-06, "epoch": 0.43956043956043955, "percentage": 43.9, "elapsed_time": "0:12:45", "remaining_time": "0:16:17"}
{"current_steps": 100, "total_steps": 205, "loss": 0.9527605056762696, "lr": 4.580914284981961e-06, "epoch": 0.4884004884004884, "percentage": 48.78, "elapsed_time": "0:14:08", "remaining_time": "0:14:51"}
{"current_steps": 110, "total_steps": 205, "loss": 0.9419396400451661, "lr": 3.935227724789994e-06, "epoch": 0.5372405372405372, "percentage": 53.66, "elapsed_time": "0:15:33", "remaining_time": "0:13:26"}
{"current_steps": 120, "total_steps": 205, "loss": 0.9319709777832031, "lr": 3.2912360336831093e-06, "epoch": 0.5860805860805861, "percentage": 58.54, "elapsed_time": "0:16:57", "remaining_time": "0:12:00"}
{"current_steps": 130, "total_steps": 205, "loss": 0.9522204399108887, "lr": 2.665790273396718e-06, "epoch": 0.6349206349206349, "percentage": 63.41, "elapsed_time": "0:18:20", "remaining_time": "0:10:34"}
{"current_steps": 140, "total_steps": 205, "loss": 0.9412946701049805, "lr": 2.0752562220367795e-06, "epoch": 0.6837606837606838, "percentage": 68.29, "elapsed_time": "0:19:47", "remaining_time": "0:09:11"}
{"current_steps": 150, "total_steps": 205, "loss": 0.9191699981689453, "lr": 1.5350861375962904e-06, "epoch": 0.7326007326007326, "percentage": 73.17, "elapsed_time": "0:21:11", "remaining_time": "0:07:46"}
{"current_steps": 160, "total_steps": 205, "loss": 0.9190822601318359, "lr": 1.0594144251711994e-06, "epoch": 0.7814407814407814, "percentage": 78.05, "elapsed_time": "0:22:37", "remaining_time": "0:06:21"}
{"current_steps": 170, "total_steps": 205, "loss": 0.9286371231079101, "lr": 6.606877878829161e-07, "epoch": 0.8302808302808303, "percentage": 82.93, "elapsed_time": "0:24:01", "remaining_time": "0:04:56"}
{"current_steps": 180, "total_steps": 205, "loss": 0.9289794921875, "lr": 3.4933953919383984e-07, "epoch": 0.8791208791208791, "percentage": 87.8, "elapsed_time": "0:25:24", "remaining_time": "0:03:31"}
{"current_steps": 190, "total_steps": 205, "loss": 0.919953727722168, "lr": 1.3351659874955546e-07, "epoch": 0.927960927960928, "percentage": 92.68, "elapsed_time": "0:26:51", "remaining_time": "0:02:07"}
{"current_steps": 200, "total_steps": 205, "loss": 0.9213088989257813, "lr": 1.8866315333544213e-08, "epoch": 0.9768009768009768, "percentage": 97.56, "elapsed_time": "0:28:14", "remaining_time": "0:00:42"}
{"current_steps": 205, "total_steps": 205, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:29:56", "remaining_time": "0:00:00"}