| {"current_steps": 10, "total_steps": 1500, "loss": 7.3904, "accuracy": 0.550000011920929, "learning_rate": 4.999451708687114e-06, "epoch": 0.007248346470961312, "percentage": 0.67, "elapsed_time": "0:01:20", "remaining_time": "3:18:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 7.3756, "accuracy": 0.574999988079071, "learning_rate": 4.997807075247147e-06, "epoch": 0.014496692941922623, "percentage": 1.33, "elapsed_time": "0:02:34", "remaining_time": "3:10:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 7.451, "accuracy": 0.4375, "learning_rate": 4.9950668210706795e-06, "epoch": 0.021745039412883936, "percentage": 2.0, "elapsed_time": "0:03:48", "remaining_time": "3:06:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 7.3892, "accuracy": 0.6499999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.028993385883845247, "percentage": 2.67, "elapsed_time": "0:05:02", "remaining_time": "3:04:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 7.5171, "accuracy": 0.512499988079071, "learning_rate": 4.986304738420684e-06, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:19", "remaining_time": "3:03:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9120001792907715, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:50", "remaining_time": "3:18:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 7.3926, "accuracy": 0.5874999761581421, "learning_rate": 4.980286753286196e-06, "epoch": 0.04349007882576787, "percentage": 4.0, "elapsed_time": "0:08:19", "remaining_time": "3:19:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 7.185, "accuracy": 0.5874999761581421, "learning_rate": 4.973180832407471e-06, "epoch": 0.05073842529672919, "percentage": 4.67, "elapsed_time": "0:09:33", "remaining_time": "3:15:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 7.365, "accuracy": 0.5874999761581421, "learning_rate": 4.964990092676263e-06, "epoch": 0.057986771767690494, "percentage": 5.33, "elapsed_time": "0:10:49", "remaining_time": "3:12:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 7.2664, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.0652351182386518, "percentage": 6.0, "elapsed_time": "0:12:01", "remaining_time": "3:08:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 7.2542, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.07248346470961312, "percentage": 6.67, "elapsed_time": "0:13:15", "remaining_time": "3:05:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.891861081123352, "epoch": 0.07248346470961312, "percentage": 6.67, "elapsed_time": "0:13:46", "remaining_time": "3:12:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 7.1749, "accuracy": 0.550000011920929, "learning_rate": 4.933947257182901e-06, "epoch": 0.07973181118057443, "percentage": 7.33, "elapsed_time": "0:15:14", "remaining_time": "3:12:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 7.142, "accuracy": 0.637499988079071, "learning_rate": 4.921457902821578e-06, "epoch": 0.08698015765153574, "percentage": 8.0, "elapsed_time": "0:16:27", "remaining_time": "3:09:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 7.1438, "accuracy": 0.612500011920929, "learning_rate": 4.907906416994146e-06, "epoch": 0.09422850412249706, "percentage": 8.67, "elapsed_time": "0:17:39", "remaining_time": "3:06:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 7.1196, "accuracy": 0.625, "learning_rate": 4.893298743830168e-06, "epoch": 0.10147685059345837, "percentage": 9.33, "elapsed_time": "0:18:55", "remaining_time": "3:03:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 7.1227, "accuracy": 0.6499999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.10872519706441967, "percentage": 10.0, "elapsed_time": "0:20:07", "remaining_time": "3:01:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8760393261909485, "epoch": 0.10872519706441967, "percentage": 10.0, "elapsed_time": "0:20:37", "remaining_time": "3:05:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 7.0272, "accuracy": 0.5375000238418579, "learning_rate": 4.860940925593703e-06, "epoch": 0.11597354353538099, "percentage": 10.67, "elapsed_time": "0:22:04", "remaining_time": "3:04:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 7.1603, "accuracy": 0.637499988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.1232218900063423, "percentage": 11.33, "elapsed_time": "0:23:15", "remaining_time": "3:01:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 6.995, "accuracy": 0.637499988079071, "learning_rate": 4.824441214720629e-06, "epoch": 0.1304702364773036, "percentage": 12.0, "elapsed_time": "0:24:31", "remaining_time": "2:59:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 6.9941, "accuracy": 0.5874999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.13771858294826492, "percentage": 12.67, "elapsed_time": "0:25:45", "remaining_time": "2:57:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 7.0413, "accuracy": 0.6499999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:26:59", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8543878793716431, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:27:29", "remaining_time": "2:58:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 6.882, "accuracy": 0.5874999761581421, "learning_rate": 4.762067631165049e-06, "epoch": 0.15221527589018755, "percentage": 14.0, "elapsed_time": "0:28:57", "remaining_time": "2:57:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 6.9158, "accuracy": 0.699999988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.15946362236114886, "percentage": 14.67, "elapsed_time": "0:30:10", "remaining_time": "2:55:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 6.8503, "accuracy": 0.699999988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.16671196883211017, "percentage": 15.33, "elapsed_time": "0:31:25", "remaining_time": "2:53:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 6.667, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.1739603153030715, "percentage": 16.0, "elapsed_time": "0:32:40", "remaining_time": "2:51:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 6.7146, "accuracy": 0.5625, "learning_rate": 4.665063509461098e-06, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:00", "remaining_time": "2:50:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8070082664489746, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:30", "remaining_time": "2:52:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 6.5743, "accuracy": 0.637499988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.18845700824499412, "percentage": 17.33, "elapsed_time": "0:35:59", "remaining_time": "2:51:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 6.4931, "accuracy": 0.5874999761581421, "learning_rate": 4.610819813755038e-06, "epoch": 0.19570535471595543, "percentage": 18.0, "elapsed_time": "0:37:16", "remaining_time": "2:49:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 6.2272, "accuracy": 0.550000011920929, "learning_rate": 4.582303101775249e-06, "epoch": 0.20295370118691675, "percentage": 18.67, "elapsed_time": "0:38:32", "remaining_time": "2:47:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 5.7937, "accuracy": 0.7124999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.21020204765787803, "percentage": 19.33, "elapsed_time": "0:39:45", "remaining_time": "2:45:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 5.741, "accuracy": 0.6875, "learning_rate": 4.522542485937369e-06, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:40:58", "remaining_time": "2:43:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.6990054845809937, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:41:28", "remaining_time": "2:45:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 5.3005, "accuracy": 0.625, "learning_rate": 4.491324795060491e-06, "epoch": 0.22469874059980066, "percentage": 20.67, "elapsed_time": "0:42:55", "remaining_time": "2:44:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 5.2832, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.23194708707076198, "percentage": 21.33, "elapsed_time": "0:44:06", "remaining_time": "2:42:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 5.1977, "accuracy": 0.6875, "learning_rate": 4.426283106939474e-06, "epoch": 0.2391954335417233, "percentage": 22.0, "elapsed_time": "0:45:18", "remaining_time": "2:40:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 4.7181, "accuracy": 0.625, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2464437800126846, "percentage": 22.67, "elapsed_time": "0:46:31", "remaining_time": "2:38:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 4.6111, "accuracy": 0.675000011920929, "learning_rate": 4.357862063693486e-06, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:47:45", "remaining_time": "2:36:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.571855366230011, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:48:15", "remaining_time": "2:38:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 4.8991, "accuracy": 0.6625000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.2609404729546072, "percentage": 24.0, "elapsed_time": "0:49:40", "remaining_time": "2:37:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 4.6471, "accuracy": 0.637499988079071, "learning_rate": 4.286181699082008e-06, "epoch": 0.26818881942556855, "percentage": 24.67, "elapsed_time": "0:50:54", "remaining_time": "2:35:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 4.4326, "accuracy": 0.637499988079071, "learning_rate": 4.249158351283414e-06, "epoch": 0.27543716589652983, "percentage": 25.33, "elapsed_time": "0:52:08", "remaining_time": "2:33:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 4.3874, "accuracy": 0.824999988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.2826855123674912, "percentage": 26.0, "elapsed_time": "0:53:27", "remaining_time": "2:32:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 4.2388, "accuracy": 0.6875, "learning_rate": 4.172826515897146e-06, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:54:42", "remaining_time": "2:30:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.49557629227638245, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:55:12", "remaining_time": "2:31:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 3.9161, "accuracy": 0.7124999761581421, "learning_rate": 4.133551509975264e-06, "epoch": 0.2971822053094138, "percentage": 27.33, "elapsed_time": "0:56:41", "remaining_time": "2:30:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 3.8304, "accuracy": 0.762499988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.3044305517803751, "percentage": 28.0, "elapsed_time": "0:57:58", "remaining_time": "2:29:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 3.7662, "accuracy": 0.7250000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.31167889825133643, "percentage": 28.67, "elapsed_time": "0:59:12", "remaining_time": "2:27:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 3.4493, "accuracy": 0.7749999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.3189272447222977, "percentage": 29.33, "elapsed_time": "1:00:28", "remaining_time": "2:25:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 4.0187, "accuracy": 0.8125, "learning_rate": 3.969463130731183e-06, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.45260879397392273, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:02:13", "remaining_time": "2:25:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 3.5788, "accuracy": 0.7124999761581421, "learning_rate": 3.92678391921108e-06, "epoch": 0.33342393766422035, "percentage": 30.67, "elapsed_time": "1:03:41", "remaining_time": "2:24:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 3.5681, "accuracy": 0.75, "learning_rate": 3.88347887310836e-06, "epoch": 0.34067228413518164, "percentage": 31.33, "elapsed_time": "1:04:56", "remaining_time": "2:22:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 3.2884, "accuracy": 0.862500011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.347920630606143, "percentage": 32.0, "elapsed_time": "1:06:13", "remaining_time": "2:20:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 3.5505, "accuracy": 0.7749999761581421, "learning_rate": 3.795067523432826e-06, "epoch": 0.35516897707710426, "percentage": 32.67, "elapsed_time": "1:07:28", "remaining_time": "2:19:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 3.3992, "accuracy": 0.800000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.3624173235480656, "percentage": 33.33, "elapsed_time": "1:08:42", "remaining_time": "2:17:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.40332508087158203, "epoch": 0.3624173235480656, "percentage": 33.33, "elapsed_time": "1:09:12", "remaining_time": "2:18:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 3.2045, "accuracy": 0.824999988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.3696656700190269, "percentage": 34.0, "elapsed_time": "1:10:37", "remaining_time": "2:17:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 3.2997, "accuracy": 0.9125000238418579, "learning_rate": 3.658240087799655e-06, "epoch": 0.37691401648998824, "percentage": 34.67, "elapsed_time": "1:11:47", "remaining_time": "2:15:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 2.7084, "accuracy": 0.925000011920929, "learning_rate": 3.611587947962319e-06, "epoch": 0.3841623629609495, "percentage": 35.33, "elapsed_time": "1:13:04", "remaining_time": "2:13:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 2.85, "accuracy": 0.8374999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.39141070943191086, "percentage": 36.0, "elapsed_time": "1:14:16", "remaining_time": "2:12:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 2.6406, "accuracy": 0.875, "learning_rate": 3.516841607689501e-06, "epoch": 0.39865905590287215, "percentage": 36.67, "elapsed_time": "1:15:28", "remaining_time": "2:10:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30369508266448975, "epoch": 0.39865905590287215, "percentage": 36.67, "elapsed_time": "1:15:58", "remaining_time": "2:11:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 2.1664, "accuracy": 0.949999988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4059074023738335, "percentage": 37.33, "elapsed_time": "1:17:26", "remaining_time": "2:09:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 2.2641, "accuracy": 0.949999988079071, "learning_rate": 3.4203113817116955e-06, "epoch": 0.4131557488447948, "percentage": 38.0, "elapsed_time": "1:18:38", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 2.3099, "accuracy": 0.887499988079071, "learning_rate": 3.3714301183045382e-06, "epoch": 0.42040409531575607, "percentage": 38.67, "elapsed_time": "1:19:51", "remaining_time": "2:06:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 2.0248, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.4276524417867174, "percentage": 39.33, "elapsed_time": "1:21:07", "remaining_time": "2:05:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 2.0191, "accuracy": 0.949999988079071, "learning_rate": 3.272542485937369e-06, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:21", "remaining_time": "2:03:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.22690872848033905, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:51", "remaining_time": "2:04:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 1.6936, "accuracy": 0.9375, "learning_rate": 3.222579492361179e-06, "epoch": 0.44214913472864004, "percentage": 40.67, "elapsed_time": "1:24:18", "remaining_time": "2:03:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 1.6215, "accuracy": 0.9750000238418579, "learning_rate": 3.1722995515381644e-06, "epoch": 0.4493974811996013, "percentage": 41.33, "elapsed_time": "1:25:33", "remaining_time": "2:01:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 1.7936, "accuracy": 0.9125000238418579, "learning_rate": 3.121724717912138e-06, "epoch": 0.45664582767056267, "percentage": 42.0, "elapsed_time": "1:26:52", "remaining_time": "1:59:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 1.7631, "accuracy": 0.9750000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.46389417414152395, "percentage": 42.67, "elapsed_time": "1:28:06", "remaining_time": "1:58:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 1.5531, "accuracy": 0.987500011920929, "learning_rate": 3.019779227044398e-06, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:22", "remaining_time": "1:56:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.21141496300697327, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:52", "remaining_time": "1:57:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 1.3669, "accuracy": 0.987500011920929, "learning_rate": 2.9684532864643123e-06, "epoch": 0.4783908670834466, "percentage": 44.0, "elapsed_time": "1:31:18", "remaining_time": "1:56:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 1.8781, "accuracy": 0.9624999761581421, "learning_rate": 2.9169218667902562e-06, "epoch": 0.4856392135544079, "percentage": 44.67, "elapsed_time": "1:32:32", "remaining_time": "1:54:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 1.2831, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.4928875600253692, "percentage": 45.33, "elapsed_time": "1:33:46", "remaining_time": "1:53:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 1.0306, "accuracy": 0.9750000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 0.5001359064963306, "percentage": 46.0, "elapsed_time": "1:35:02", "remaining_time": "1:51:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 1.1941, "accuracy": 0.987500011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.5073842529672918, "percentage": 46.67, "elapsed_time": "1:36:13", "remaining_time": "1:49:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.1846819519996643, "epoch": 0.5073842529672918, "percentage": 46.67, "elapsed_time": "1:36:44", "remaining_time": "1:50:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 1.7604, "accuracy": 0.9125000238418579, "learning_rate": 2.70919460833079e-06, "epoch": 0.5146325994382531, "percentage": 47.33, "elapsed_time": "1:38:10", "remaining_time": "1:49:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 1.2509, "accuracy": 0.9750000238418579, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5218809459092144, "percentage": 48.0, "elapsed_time": "1:39:29", "remaining_time": "1:47:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 1.2837, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.5291292923801758, "percentage": 48.67, "elapsed_time": "1:40:45", "remaining_time": "1:46:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 1.2981, "accuracy": 0.9624999761581421, "learning_rate": 2.5523560497083927e-06, "epoch": 0.5363776388511371, "percentage": 49.33, "elapsed_time": "1:41:59", "remaining_time": "1:44:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 1.1198, "accuracy": 0.9750000238418579, "learning_rate": 2.5e-06, "epoch": 0.5436259853220984, "percentage": 50.0, "elapsed_time": "1:43:18", "remaining_time": "1:43:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.15141016244888306, "epoch": 0.5436259853220984, "percentage": 50.0, "elapsed_time": "1:43:48", "remaining_time": "1:43:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 1.1826, "accuracy": 0.9375, "learning_rate": 2.447643950291608e-06, "epoch": 0.5508743317930597, "percentage": 50.67, "elapsed_time": "1:45:13", "remaining_time": "1:42:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 1.2527, "accuracy": 1.0, "learning_rate": 2.3953108656770018e-06, "epoch": 0.5581226782640211, "percentage": 51.33, "elapsed_time": "1:46:32", "remaining_time": "1:41:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.7915, "accuracy": 0.987500011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 0.5653710247349824, "percentage": 52.0, "elapsed_time": "1:47:45", "remaining_time": "1:39:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.9819, "accuracy": 0.9750000238418579, "learning_rate": 2.290805391669212e-06, "epoch": 0.5726193712059436, "percentage": 52.67, "elapsed_time": "1:49:01", "remaining_time": "1:37:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 1.0712, "accuracy": 0.9750000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 0.5798677176769049, "percentage": 53.33, "elapsed_time": "1:50:13", "remaining_time": "1:36:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.12996967136859894, "epoch": 0.5798677176769049, "percentage": 53.33, "elapsed_time": "1:50:44", "remaining_time": "1:36:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 1.2619, "accuracy": 0.949999988079071, "learning_rate": 2.186666916089239e-06, "epoch": 0.5871160641478663, "percentage": 54.0, "elapsed_time": "1:52:10", "remaining_time": "1:35:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 1.0105, "accuracy": 0.987500011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.5943644106188276, "percentage": 54.67, "elapsed_time": "1:53:24", "remaining_time": "1:34:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.8295, "accuracy": 0.9375, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6016127570897889, "percentage": 55.33, "elapsed_time": "1:54:40", "remaining_time": "1:32:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.9398, "accuracy": 0.987500011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.6088611035607502, "percentage": 56.0, "elapsed_time": "1:55:54", "remaining_time": "1:31:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.8919, "accuracy": 1.0, "learning_rate": 1.9802207729556023e-06, "epoch": 0.6161094500317115, "percentage": 56.67, "elapsed_time": "1:57:08", "remaining_time": "1:29:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.11857374012470245, "epoch": 0.6161094500317115, "percentage": 56.67, "elapsed_time": "1:57:38", "remaining_time": "1:29:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.9668, "accuracy": 0.949999988079071, "learning_rate": 1.9291228247233607e-06, "epoch": 0.6233577965026729, "percentage": 57.33, "elapsed_time": "1:59:04", "remaining_time": "1:28:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.623, "accuracy": 0.987500011920929, "learning_rate": 1.8782752820878636e-06, "epoch": 0.6306061429736342, "percentage": 58.0, "elapsed_time": "2:00:22", "remaining_time": "1:27:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.8222, "accuracy": 0.987500011920929, "learning_rate": 1.827700448461836e-06, "epoch": 0.6378544894445954, "percentage": 58.67, "elapsed_time": "2:01:34", "remaining_time": "1:25:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.7366, "accuracy": 1.0, "learning_rate": 1.7774205076388207e-06, "epoch": 0.6451028359155567, "percentage": 59.33, "elapsed_time": "2:02:52", "remaining_time": "1:24:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 1.1936, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 0.6523511823865181, "percentage": 60.0, "elapsed_time": "2:04:10", "remaining_time": "1:22:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.11673425137996674, "epoch": 0.6523511823865181, "percentage": 60.0, "elapsed_time": "2:04:40", "remaining_time": "1:23:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.6817, "accuracy": 0.987500011920929, "learning_rate": 1.677833383153542e-06, "epoch": 0.6595995288574794, "percentage": 60.67, "elapsed_time": "2:06:08", "remaining_time": "1:21:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.8751, "accuracy": 0.987500011920929, "learning_rate": 1.6285698816954626e-06, "epoch": 0.6668478753284407, "percentage": 61.33, "elapsed_time": "2:07:21", "remaining_time": "1:20:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.8639, "accuracy": 0.9750000238418579, "learning_rate": 1.5796886182883053e-06, "epoch": 0.674096221799402, "percentage": 62.0, "elapsed_time": "2:08:35", "remaining_time": "1:18:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.8294, "accuracy": 0.949999988079071, "learning_rate": 1.5312110338697427e-06, "epoch": 0.6813445682703633, "percentage": 62.67, "elapsed_time": "2:09:46", "remaining_time": "1:17:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.9113, "accuracy": 0.949999988079071, "learning_rate": 1.4831583923105e-06, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:01", "remaining_time": "1:15:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.1089157834649086, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:31", "remaining_time": "1:16:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.8595, "accuracy": 0.9750000238418579, "learning_rate": 1.4355517710873184e-06, "epoch": 0.695841261212286, "percentage": 64.0, "elapsed_time": "2:12:55", "remaining_time": "1:14:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.9415, "accuracy": 0.987500011920929, "learning_rate": 1.388412052037682e-06, "epoch": 0.7030896076832472, "percentage": 64.67, "elapsed_time": "2:14:07", "remaining_time": "1:13:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.8961, "accuracy": 0.9624999761581421, "learning_rate": 1.3417599122003464e-06, "epoch": 0.7103379541542085, "percentage": 65.33, "elapsed_time": "2:15:18", "remaining_time": "1:11:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.7882, "accuracy": 1.0, "learning_rate": 1.2956158147457116e-06, "epoch": 0.7175863006251699, "percentage": 66.0, "elapsed_time": "2:16:37", "remaining_time": "1:10:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 1.135, "accuracy": 0.949999988079071, "learning_rate": 1.2500000000000007e-06, "epoch": 0.7248346470961312, "percentage": 66.67, "elapsed_time": "2:17:55", "remaining_time": "1:08:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.1021483913064003, "epoch": 0.7248346470961312, "percentage": 66.67, "elapsed_time": "2:18:25", "remaining_time": "1:09:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.769, "accuracy": 1.0, "learning_rate": 1.204932476567175e-06, "epoch": 0.7320829935670925, "percentage": 67.33, "elapsed_time": "2:19:50", "remaining_time": "1:07:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.5362, "accuracy": 0.987500011920929, "learning_rate": 1.160433012552508e-06, "epoch": 0.7393313400380538, "percentage": 68.0, "elapsed_time": "2:21:05", "remaining_time": "1:06:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.8026, "accuracy": 0.9750000238418579, "learning_rate": 1.11652112689164e-06, "epoch": 0.7465796865090152, "percentage": 68.67, "elapsed_time": "2:22:21", "remaining_time": "1:04:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.7519, "accuracy": 0.987500011920929, "learning_rate": 1.073216080788921e-06, "epoch": 0.7538280329799765, "percentage": 69.33, "elapsed_time": "2:23:38", "remaining_time": "1:03:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.5528, "accuracy": 0.9750000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 0.7610763794509378, "percentage": 70.0, "elapsed_time": "2:24:52", "remaining_time": "1:02:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.1007753536105156, "epoch": 0.7610763794509378, "percentage": 70.0, "elapsed_time": "2:25:22", "remaining_time": "1:02:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.792, "accuracy": 0.987500011920929, "learning_rate": 9.88502212844063e-07, "epoch": 0.768324725921899, "percentage": 70.67, "elapsed_time": "2:26:52", "remaining_time": "1:00:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.5324, "accuracy": 0.987500011920929, "learning_rate": 9.471305493042243e-07, "epoch": 0.7755730723928603, "percentage": 71.33, "elapsed_time": "2:28:10", "remaining_time": "0:59:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.5667, "accuracy": 1.0, "learning_rate": 9.064400256282757e-07, "epoch": 0.7828214188638217, "percentage": 72.0, "elapsed_time": "2:29:26", "remaining_time": "0:58:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.6379, "accuracy": 0.9750000238418579, "learning_rate": 8.664484900247363e-07, "epoch": 0.790069765334783, "percentage": 72.67, "elapsed_time": "2:30:40", "remaining_time": "0:56:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.6618, "accuracy": 0.987500011920929, "learning_rate": 8.271734841028553e-07, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:31:57", "remaining_time": "0:55:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.0923290029168129, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:32:27", "remaining_time": "0:55:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.5303, "accuracy": 0.987500011920929, "learning_rate": 7.886322351782782e-07, "epoch": 0.8045664582767056, "percentage": 74.0, "elapsed_time": "2:33:53", "remaining_time": "0:54:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.9835, "accuracy": 0.987500011920929, "learning_rate": 7.508416487165862e-07, "epoch": 0.811814804747667, "percentage": 74.67, "elapsed_time": "2:35:10", "remaining_time": "0:52:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.9257, "accuracy": 1.0, "learning_rate": 7.138183009179922e-07, "epoch": 0.8190631512186283, "percentage": 75.33, "elapsed_time": "2:36:28", "remaining_time": "0:51:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.5027, "accuracy": 0.9750000238418579, "learning_rate": 6.775784314464717e-07, "epoch": 0.8263114976895896, "percentage": 76.0, "elapsed_time": "2:37:41", "remaining_time": "0:49:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.7009, "accuracy": 0.987500011920929, "learning_rate": 6.421379363065142e-07, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:38:55", "remaining_time": "0:48:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.09489800035953522, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:39:25", "remaining_time": "0:48:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.9432, "accuracy": 0.9624999761581421, "learning_rate": 6.075123608706093e-07, "epoch": 0.8408081906315121, "percentage": 77.33, "elapsed_time": "2:40:53", "remaining_time": "0:47:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.5761, "accuracy": 0.987500011920929, "learning_rate": 5.737168930605272e-07, "epoch": 0.8480565371024735, "percentage": 78.0, "elapsed_time": "2:42:06", "remaining_time": "0:45:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.8883, "accuracy": 0.949999988079071, "learning_rate": 5.407663566854008e-07, "epoch": 0.8553048835734348, "percentage": 78.67, "elapsed_time": "2:43:22", "remaining_time": "0:44:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 1.1177, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.8625532300443961, "percentage": 79.33, "elapsed_time": "2:44:37", "remaining_time": "0:42:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.4369, "accuracy": 1.0, "learning_rate": 4.774575140626317e-07, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:45:55", "remaining_time": "0:41:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.08837977796792984, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:46:25", "remaining_time": "0:41:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.4923, "accuracy": 1.0, "learning_rate": 4.4712697716573994e-07, "epoch": 0.8770499229863188, "percentage": 80.67, "elapsed_time": "2:47:51", "remaining_time": "0:40:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.7736, "accuracy": 0.9750000238418579, "learning_rate": 4.1769689822475147e-07, "epoch": 0.8842982694572801, "percentage": 81.33, "elapsed_time": "2:49:04", "remaining_time": "0:38:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.6428, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 0.8915466159282414, "percentage": 82.0, "elapsed_time": "2:50:17", "remaining_time": "0:37:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.5315, "accuracy": 1.0, "learning_rate": 3.615893495987335e-07, "epoch": 0.8987949623992026, "percentage": 82.67, "elapsed_time": "2:51:29", "remaining_time": "0:35:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.9809, "accuracy": 0.987500011920929, "learning_rate": 3.3493649053890325e-07, "epoch": 0.906043308870164, "percentage": 83.33, "elapsed_time": "2:52:47", "remaining_time": "0:34:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.08777090907096863, "epoch": 0.906043308870164, "percentage": 83.33, "elapsed_time": "2:53:17", "remaining_time": "0:34:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 1.1088, "accuracy": 0.987500011920929, "learning_rate": 3.092332998903416e-07, "epoch": 0.9132916553411253, "percentage": 84.0, "elapsed_time": "2:54:44", "remaining_time": "0:33:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.8384, "accuracy": 0.949999988079071, "learning_rate": 2.844910519219632e-07, "epoch": 0.9205400018120866, "percentage": 84.67, "elapsed_time": "2:55:58", "remaining_time": "0:31:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.6228, "accuracy": 0.987500011920929, "learning_rate": 2.6072059940146775e-07, "epoch": 0.9277883482830479, "percentage": 85.33, "elapsed_time": "2:57:16", "remaining_time": "0:30:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 1.1599, "accuracy": 1.0, "learning_rate": 2.3793236883495164e-07, "epoch": 0.9350366947540092, "percentage": 86.0, "elapsed_time": "2:58:27", "remaining_time": "0:29:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.5808, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "2:59:43", "remaining_time": "0:27:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.09216763824224472, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "3:00:13", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.8332, "accuracy": 0.987500011920929, "learning_rate": 1.95342121028749e-07, "epoch": 0.9495333876959319, "percentage": 87.33, "elapsed_time": "3:01:40", "remaining_time": "0:26:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.642, "accuracy": 0.987500011920929, "learning_rate": 1.7555878527937164e-07, "epoch": 0.9567817341668932, "percentage": 88.0, "elapsed_time": "3:02:53", "remaining_time": "0:24:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.4295, "accuracy": 1.0, "learning_rate": 1.567950262702714e-07, "epoch": 0.9640300806378544, "percentage": 88.67, "elapsed_time": "3:04:07", "remaining_time": "0:23:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 1.3939, "accuracy": 0.9750000238418579, "learning_rate": 1.3905907440629752e-07, "epoch": 0.9712784271088158, "percentage": 89.33, "elapsed_time": "3:05:22", "remaining_time": "0:22:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.7096, "accuracy": 1.0, "learning_rate": 1.223587092621162e-07, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:06:38", "remaining_time": "0:20:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.08608455955982208, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:07:08", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.9750000238418579, "learning_rate": 1.067012561698319e-07, "epoch": 0.9857751200507384, "percentage": 90.67, "elapsed_time": "3:08:36", "remaining_time": "0:19:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.6913, "accuracy": 0.9750000238418579, "learning_rate": 9.209358300585474e-08, "epoch": 0.9930234665216997, "percentage": 91.33, "elapsed_time": "3:09:51", "remaining_time": "0:18:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.3924, "accuracy": 1.0, "learning_rate": 7.854209717842231e-08, "epoch": 1.0, "percentage": 92.0, "elapsed_time": "3:11:02", "remaining_time": "0:16:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 1.4012, "accuracy": 0.9125000238418579, "learning_rate": 6.605274281709929e-08, "epoch": 1.0072483464709614, "percentage": 92.67, "elapsed_time": "3:12:14", "remaining_time": "0:15:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.6699, "accuracy": 0.9375, "learning_rate": 5.463099816548578e-08, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:28", "remaining_time": "0:13:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.08683376014232635, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:58", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.7684, "accuracy": 1.0, "learning_rate": 4.428187317827848e-08, "epoch": 1.021745039412884, "percentage": 94.0, "elapsed_time": "3:15:22", "remaining_time": "0:12:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.6473, "accuracy": 1.0, "learning_rate": 3.5009907323737826e-08, "epoch": 1.0289933858838451, "percentage": 94.67, "elapsed_time": "3:16:37", "remaining_time": "0:11:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.5875, "accuracy": 0.987500011920929, "learning_rate": 2.681916759252917e-08, "epoch": 1.0362417323548065, "percentage": 95.33, "elapsed_time": "3:17:52", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.7658, "accuracy": 0.987500011920929, "learning_rate": 1.9713246713805588e-08, "epoch": 1.043490078825768, "percentage": 96.0, "elapsed_time": "3:19:11", "remaining_time": "0:08:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.6331, "accuracy": 0.987500011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.0507384252967291, "percentage": 96.67, "elapsed_time": "3:20:24", "remaining_time": "0:06:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.08744800090789795, "epoch": 1.0507384252967291, "percentage": 96.67, "elapsed_time": "3:20:55", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.709, "accuracy": 0.9624999761581421, "learning_rate": 8.767851876239075e-09, "epoch": 1.0579867717676905, "percentage": 97.33, "elapsed_time": "3:22:21", "remaining_time": "0:05:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.5232, "accuracy": 1.0, "learning_rate": 4.933178929321103e-09, "epoch": 1.0652351182386517, "percentage": 98.0, "elapsed_time": "3:23:37", "remaining_time": "0:04:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.7016, "accuracy": 0.949999988079071, "learning_rate": 2.192924752854042e-09, "epoch": 1.072483464709613, "percentage": 98.67, "elapsed_time": "3:24:51", "remaining_time": "0:02:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.454, "accuracy": 0.987500011920929, "learning_rate": 5.48291312886251e-10, "epoch": 1.0797318111805745, "percentage": 99.33, "elapsed_time": "3:26:08", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.3791, "accuracy": 1.0, "learning_rate": 0.0, "epoch": 1.0869801576515357, "percentage": 100.0, "elapsed_time": "3:27:22", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.08840522915124893, "epoch": 1.0869801576515357, "percentage": 100.0, "elapsed_time": "3:27:53", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 1.0869801576515357, "percentage": 100.0, "elapsed_time": "3:28:05", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |