| {"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} | |