| {"current_steps": 10, "total_steps": 1500, "loss": 0.9405, "accuracy": 0.4375, "learning_rate": 4.999451708687114e-06, "epoch": 0.008594757198109154, "percentage": 0.67, "elapsed_time": "0:01:11", "remaining_time": "2:57:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9294, "accuracy": 0.6000000238418579, "learning_rate": 4.997807075247147e-06, "epoch": 0.017189514396218308, "percentage": 1.33, "elapsed_time": "0:02:27", "remaining_time": "3:01:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9338, "accuracy": 0.4625000059604645, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02578427159432746, "percentage": 2.0, "elapsed_time": "0:03:44", "remaining_time": "3:03:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9202, "accuracy": 0.4625000059604645, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:59", "remaining_time": "3:02:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9213, "accuracy": 0.550000011920929, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:16", "remaining_time": "3:02:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9250189065933228, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:42", "remaining_time": "3:14:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9255, "accuracy": 0.512499988079071, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:08:01", "remaining_time": "3:12:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9155, "accuracy": 0.512499988079071, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:18", "remaining_time": "3:10:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9191, "accuracy": 0.48750001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:34", "remaining_time": "3:07:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9255, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:49", "remaining_time": "3:05:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9022, "accuracy": 0.625, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:07", "remaining_time": "3:03:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9166209697723389, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:33", "remaining_time": "3:09:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.9128, "accuracy": 0.42500001192092896, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:58", "remaining_time": "3:09:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9179, "accuracy": 0.5249999761581421, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:16:14", "remaining_time": "3:06:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.8978, "accuracy": 0.550000011920929, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:17:27", "remaining_time": "3:03:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9117, "accuracy": 0.5874999761581421, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:45", "remaining_time": "3:02:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9007, "accuracy": 0.625, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:20:01", "remaining_time": "3:00:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8991575241088867, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:20:27", "remaining_time": "3:04:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.8854, "accuracy": 0.5625, "learning_rate": 4.860940925593703e-06, "epoch": 0.13751611516974646, "percentage": 10.67, "elapsed_time": "0:21:44", "remaining_time": "3:02:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.8884, "accuracy": 0.625, "learning_rate": 4.84320497372973e-06, "epoch": 0.1461108723678556, "percentage": 11.33, "elapsed_time": "0:23:00", "remaining_time": "2:59:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8756, "accuracy": 0.574999988079071, "learning_rate": 4.824441214720629e-06, "epoch": 0.15470562956596476, "percentage": 12.0, "elapsed_time": "0:24:15", "remaining_time": "2:57:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.8781, "accuracy": 0.612500011920929, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:25:30", "remaining_time": "2:55:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8531, "accuracy": 0.6000000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:42", "remaining_time": "2:53:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8484573364257812, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:27:08", "remaining_time": "2:56:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8211, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:28:28", "remaining_time": "2:54:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8331, "accuracy": 0.675000011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:44", "remaining_time": "2:53:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.7986, "accuracy": 0.6625000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:58", "remaining_time": "2:51:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7708, "accuracy": 0.675000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:32:12", "remaining_time": "2:49:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.7722, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:27", "remaining_time": "2:47:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7410055994987488, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:53", "remaining_time": "2:49:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.6933, "accuracy": 0.75, "learning_rate": 4.638410650401267e-06, "epoch": 0.22346368715083798, "percentage": 17.33, "elapsed_time": "0:35:17", "remaining_time": "2:48:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7265, "accuracy": 0.699999988079071, "learning_rate": 4.610819813755038e-06, "epoch": 0.23205844434894715, "percentage": 18.0, "elapsed_time": "0:36:33", "remaining_time": "2:46:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.6725, "accuracy": 0.6625000238418579, "learning_rate": 4.582303101775249e-06, "epoch": 0.2406532015470563, "percentage": 18.67, "elapsed_time": "0:37:48", "remaining_time": "2:44:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.571, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:39:03", "remaining_time": "2:42:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.5782, "accuracy": 0.612500011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:20", "remaining_time": "2:41:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.563686728477478, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:46", "remaining_time": "2:43:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.5253, "accuracy": 0.75, "learning_rate": 4.491324795060491e-06, "epoch": 0.2664374731413838, "percentage": 20.67, "elapsed_time": "0:42:10", "remaining_time": "2:41:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.5294, "accuracy": 0.675000011920929, "learning_rate": 4.4592336433146e-06, "epoch": 0.2750322303394929, "percentage": 21.33, "elapsed_time": "0:43:30", "remaining_time": "2:40:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.548, "accuracy": 0.625, "learning_rate": 4.426283106939474e-06, "epoch": 0.28362698753760207, "percentage": 22.0, "elapsed_time": "0:44:48", "remaining_time": "2:38:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.4797, "accuracy": 0.699999988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:46:05", "remaining_time": "2:37:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.5126, "accuracy": 0.574999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:47:20", "remaining_time": "2:35:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5108997821807861, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:47:46", "remaining_time": "2:36:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.5031, "accuracy": 0.6625000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.3094112591319295, "percentage": 24.0, "elapsed_time": "0:49:07", "remaining_time": "2:35:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.4662, "accuracy": 0.7875000238418579, "learning_rate": 4.286181699082008e-06, "epoch": 0.31800601633003867, "percentage": 24.67, "elapsed_time": "0:50:20", "remaining_time": "2:33:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4829, "accuracy": 0.6625000238418579, "learning_rate": 4.249158351283414e-06, "epoch": 0.3266007735281478, "percentage": 25.33, "elapsed_time": "0:51:40", "remaining_time": "2:32:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4538, "accuracy": 0.637499988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:52:52", "remaining_time": "2:30:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.4847, "accuracy": 0.699999988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:54:06", "remaining_time": "2:28:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47303518652915955, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:54:32", "remaining_time": "2:29:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.4398, "accuracy": 0.675000011920929, "learning_rate": 4.133551509975264e-06, "epoch": 0.3523850451224753, "percentage": 27.33, "elapsed_time": "0:55:57", "remaining_time": "2:28:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.4774, "accuracy": 0.7124999761581421, "learning_rate": 4.093559974371725e-06, "epoch": 0.36097980232058446, "percentage": 28.0, "elapsed_time": "0:57:15", "remaining_time": "2:27:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.4158, "accuracy": 0.7749999761581421, "learning_rate": 4.052869450695776e-06, "epoch": 0.3695745595186936, "percentage": 28.67, "elapsed_time": "0:58:32", "remaining_time": "2:25:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.3916, "accuracy": 0.862500011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.37816931671680276, "percentage": 29.33, "elapsed_time": "0:59:47", "remaining_time": "2:24:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.368, "accuracy": 0.887499988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "1:01:03", "remaining_time": "2:22:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.3982011079788208, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "1:01:29", "remaining_time": "2:23:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.3584, "accuracy": 0.8125, "learning_rate": 3.92678391921108e-06, "epoch": 0.39535883111302106, "percentage": 30.67, "elapsed_time": "1:02:47", "remaining_time": "2:21:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3709, "accuracy": 0.8500000238418579, "learning_rate": 3.88347887310836e-06, "epoch": 0.4039535883111302, "percentage": 31.33, "elapsed_time": "1:04:00", "remaining_time": "2:20:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3837, "accuracy": 0.8374999761581421, "learning_rate": 3.839566987447492e-06, "epoch": 0.41254834550923936, "percentage": 32.0, "elapsed_time": "1:05:12", "remaining_time": "2:18:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3112, "accuracy": 0.875, "learning_rate": 3.795067523432826e-06, "epoch": 0.4211431027073485, "percentage": 32.67, "elapsed_time": "1:06:25", "remaining_time": "2:16:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.3069, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:07:37", "remaining_time": "2:15:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.35469338297843933, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:08:03", "remaining_time": "2:16:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.3468, "accuracy": 0.887499988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4383326171035668, "percentage": 34.0, "elapsed_time": "1:09:27", "remaining_time": "2:14:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3092, "accuracy": 0.8999999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.44692737430167595, "percentage": 34.67, "elapsed_time": "1:10:42", "remaining_time": "2:13:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.3044, "accuracy": 0.862500011920929, "learning_rate": 3.611587947962319e-06, "epoch": 0.45552213149978515, "percentage": 35.33, "elapsed_time": "1:11:58", "remaining_time": "2:11:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.3376, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.4641168886978943, "percentage": 36.0, "elapsed_time": "1:13:14", "remaining_time": "2:10:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.2937, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:14:37", "remaining_time": "2:08:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.33076339960098267, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:15:03", "remaining_time": "2:09:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.2983, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4813064030941126, "percentage": 37.33, "elapsed_time": "1:16:24", "remaining_time": "2:08:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.3014, "accuracy": 0.987500011920929, "learning_rate": 3.4203113817116955e-06, "epoch": 0.48990116029222175, "percentage": 38.0, "elapsed_time": "1:17:37", "remaining_time": "2:06:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.2752, "accuracy": 0.9375, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4984959174903309, "percentage": 38.67, "elapsed_time": "1:18:55", "remaining_time": "2:05:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.2968, "accuracy": 0.9375, "learning_rate": 3.3221666168464584e-06, "epoch": 0.50709067468844, "percentage": 39.33, "elapsed_time": "1:20:11", "remaining_time": "2:03:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.2971, "accuracy": 0.925000011920929, "learning_rate": 3.272542485937369e-06, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:21:27", "remaining_time": "2:02:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.3210188150405884, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:21:54", "remaining_time": "2:02:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.2508, "accuracy": 0.9125000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.5242801890846583, "percentage": 40.67, "elapsed_time": "1:23:14", "remaining_time": "2:01:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.3102, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5328749462827675, "percentage": 41.33, "elapsed_time": "1:24:31", "remaining_time": "1:59:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2967, "accuracy": 0.925000011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.5414697034808766, "percentage": 42.0, "elapsed_time": "1:25:43", "remaining_time": "1:58:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2949, "accuracy": 0.925000011920929, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5500644606789858, "percentage": 42.67, "elapsed_time": "1:26:59", "remaining_time": "1:56:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2591, "accuracy": 0.949999988079071, "learning_rate": 3.019779227044398e-06, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:28:13", "remaining_time": "1:55:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.2849542498588562, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:28:39", "remaining_time": "1:55:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.2769, "accuracy": 0.8999999761581421, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5672539750752041, "percentage": 44.0, "elapsed_time": "1:29:56", "remaining_time": "1:54:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2768, "accuracy": 0.9125000238418579, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5758487322733132, "percentage": 44.67, "elapsed_time": "1:31:13", "remaining_time": "1:53:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.2279, "accuracy": 0.9750000238418579, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5844434894714224, "percentage": 45.33, "elapsed_time": "1:32:24", "remaining_time": "1:51:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2303, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:33:37", "remaining_time": "1:49:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.2378, "accuracy": 0.9624999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:34:51", "remaining_time": "1:48:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.2825009524822235, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:35:17", "remaining_time": "1:48:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.2785, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.6102277610657499, "percentage": 47.33, "elapsed_time": "1:36:40", "remaining_time": "1:47:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2601, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.618822518263859, "percentage": 48.0, "elapsed_time": "1:37:58", "remaining_time": "1:46:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2575, "accuracy": 0.9125000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.6274172754619682, "percentage": 48.67, "elapsed_time": "1:39:14", "remaining_time": "1:44:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.1993, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6360120326600773, "percentage": 49.33, "elapsed_time": "1:40:32", "remaining_time": "1:43:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.232, "accuracy": 0.9375, "learning_rate": 2.5e-06, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:41:46", "remaining_time": "1:41:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2789475917816162, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:42:12", "remaining_time": "1:42:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2308, "accuracy": 0.9375, "learning_rate": 2.447643950291608e-06, "epoch": 0.6532015470562956, "percentage": 50.67, "elapsed_time": "1:43:36", "remaining_time": "1:40:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.2568, "accuracy": 0.887499988079071, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6617963042544048, "percentage": 51.33, "elapsed_time": "1:44:52", "remaining_time": "1:39:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.2412, "accuracy": 0.9750000238418579, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6703910614525139, "percentage": 52.0, "elapsed_time": "1:46:08", "remaining_time": "1:37:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.2296, "accuracy": 0.925000011920929, "learning_rate": 2.290805391669212e-06, "epoch": 0.6789858186506231, "percentage": 52.67, "elapsed_time": "1:47:24", "remaining_time": "1:36:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.2168, "accuracy": 0.887499988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:48:37", "remaining_time": "1:35:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.2762486934661865, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:49:03", "remaining_time": "1:35:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2642, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6961753330468414, "percentage": 54.0, "elapsed_time": "1:50:28", "remaining_time": "1:34:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.1911, "accuracy": 0.8999999761581421, "learning_rate": 2.134792428593971e-06, "epoch": 0.7047700902449506, "percentage": 54.67, "elapsed_time": "1:51:47", "remaining_time": "1:32:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2169, "accuracy": 0.949999988079071, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7133648474430597, "percentage": 55.33, "elapsed_time": "1:53:03", "remaining_time": "1:31:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.2036, "accuracy": 0.9375, "learning_rate": 2.031546713535688e-06, "epoch": 0.7219596046411689, "percentage": 56.0, "elapsed_time": "1:54:16", "remaining_time": "1:29:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2401, "accuracy": 0.8999999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:55:35", "remaining_time": "1:28:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.25881054997444153, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:56:01", "remaining_time": "1:28:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.236, "accuracy": 0.9125000238418579, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7391491190373872, "percentage": 57.33, "elapsed_time": "1:57:22", "remaining_time": "1:27:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.2133, "accuracy": 0.9624999761581421, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7477438762354963, "percentage": 58.0, "elapsed_time": "1:58:32", "remaining_time": "1:25:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.225, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 0.7563386334336055, "percentage": 58.67, "elapsed_time": "1:59:44", "remaining_time": "1:24:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.2081, "accuracy": 0.925000011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7649333906317146, "percentage": 59.33, "elapsed_time": "2:00:57", "remaining_time": "1:22:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.2286, "accuracy": 0.949999988079071, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "2:02:12", "remaining_time": "1:21:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.24709106981754303, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "2:02:38", "remaining_time": "1:21:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.2157, "accuracy": 0.925000011920929, "learning_rate": 1.677833383153542e-06, "epoch": 0.7821229050279329, "percentage": 60.67, "elapsed_time": "2:04:02", "remaining_time": "1:20:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.1969, "accuracy": 0.949999988079071, "learning_rate": 1.6285698816954626e-06, "epoch": 0.7907176622260421, "percentage": 61.33, "elapsed_time": "2:05:17", "remaining_time": "1:18:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.2309, "accuracy": 0.949999988079071, "learning_rate": 1.5796886182883053e-06, "epoch": 0.7993124194241513, "percentage": 62.0, "elapsed_time": "2:06:33", "remaining_time": "1:17:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.2452, "accuracy": 0.9125000238418579, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8079071766222604, "percentage": 62.67, "elapsed_time": "2:07:47", "remaining_time": "1:16:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.2346, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:09:01", "remaining_time": "1:14:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2422085404396057, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:09:27", "remaining_time": "1:14:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.2177, "accuracy": 0.925000011920929, "learning_rate": 1.4355517710873184e-06, "epoch": 0.8250966910184787, "percentage": 64.0, "elapsed_time": "2:10:48", "remaining_time": "1:13:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.2371, "accuracy": 0.949999988079071, "learning_rate": 1.388412052037682e-06, "epoch": 0.8336914482165879, "percentage": 64.67, "elapsed_time": "2:12:03", "remaining_time": "1:12:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.1649, "accuracy": 0.9624999761581421, "learning_rate": 1.3417599122003464e-06, "epoch": 0.842286205414697, "percentage": 65.33, "elapsed_time": "2:13:16", "remaining_time": "1:10:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.2277, "accuracy": 0.9375, "learning_rate": 1.2956158147457116e-06, "epoch": 0.8508809626128062, "percentage": 66.0, "elapsed_time": "2:14:32", "remaining_time": "1:09:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.196, "accuracy": 0.8999999761581421, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:15:50", "remaining_time": "1:07:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.23557204008102417, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:16:16", "remaining_time": "1:08:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.2284, "accuracy": 0.9125000238418579, "learning_rate": 1.204932476567175e-06, "epoch": 0.8680704770090245, "percentage": 67.33, "elapsed_time": "2:17:36", "remaining_time": "1:06:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.2366, "accuracy": 0.9375, "learning_rate": 1.160433012552508e-06, "epoch": 0.8766652342071336, "percentage": 68.0, "elapsed_time": "2:18:53", "remaining_time": "1:05:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.2331, "accuracy": 0.925000011920929, "learning_rate": 1.11652112689164e-06, "epoch": 0.8852599914052428, "percentage": 68.67, "elapsed_time": "2:20:04", "remaining_time": "1:03:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.2102, "accuracy": 0.949999988079071, "learning_rate": 1.073216080788921e-06, "epoch": 0.8938547486033519, "percentage": 69.33, "elapsed_time": "2:21:18", "remaining_time": "1:02:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.2133, "accuracy": 0.9125000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 0.9024495058014611, "percentage": 70.0, "elapsed_time": "2:22:32", "remaining_time": "1:01:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.23113711178302765, "epoch": 0.9024495058014611, "percentage": 70.0, "elapsed_time": "2:22:58", "remaining_time": "1:01:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.2111, "accuracy": 0.9624999761581421, "learning_rate": 9.88502212844063e-07, "epoch": 0.9110442629995703, "percentage": 70.67, "elapsed_time": "2:24:21", "remaining_time": "0:59:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.2161, "accuracy": 0.949999988079071, "learning_rate": 9.471305493042243e-07, "epoch": 0.9196390201976794, "percentage": 71.33, "elapsed_time": "2:25:35", "remaining_time": "0:58:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.1827, "accuracy": 0.9750000238418579, "learning_rate": 9.064400256282757e-07, "epoch": 0.9282337773957886, "percentage": 72.0, "elapsed_time": "2:26:50", "remaining_time": "0:57:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.1889, "accuracy": 0.949999988079071, "learning_rate": 8.664484900247363e-07, "epoch": 0.9368285345938977, "percentage": 72.67, "elapsed_time": "2:28:06", "remaining_time": "0:55:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.1875, "accuracy": 0.9750000238418579, "learning_rate": 8.271734841028553e-07, "epoch": 0.9454232917920069, "percentage": 73.33, "elapsed_time": "2:29:21", "remaining_time": "0:54:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.23036065697669983, "epoch": 0.9454232917920069, "percentage": 73.33, "elapsed_time": "2:29:47", "remaining_time": "0:54:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.2247, "accuracy": 0.949999988079071, "learning_rate": 7.886322351782782e-07, "epoch": 0.954018048990116, "percentage": 74.0, "elapsed_time": "2:31:13", "remaining_time": "0:53:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.1955, "accuracy": 0.9375, "learning_rate": 7.508416487165862e-07, "epoch": 0.9626128061882252, "percentage": 74.67, "elapsed_time": "2:32:29", "remaining_time": "0:51:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.1866, "accuracy": 0.9125000238418579, "learning_rate": 7.138183009179922e-07, "epoch": 0.9712075633863343, "percentage": 75.33, "elapsed_time": "2:33:45", "remaining_time": "0:50:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.1777, "accuracy": 0.9375, "learning_rate": 6.775784314464717e-07, "epoch": 0.9798023205844435, "percentage": 76.0, "elapsed_time": "2:34:57", "remaining_time": "0:48:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.174, "accuracy": 0.925000011920929, "learning_rate": 6.421379363065142e-07, "epoch": 0.9883970777825526, "percentage": 76.67, "elapsed_time": "2:36:12", "remaining_time": "0:47:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.23454926908016205, "epoch": 0.9883970777825526, "percentage": 76.67, "elapsed_time": "2:36:38", "remaining_time": "0:47:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.2112, "accuracy": 0.9375, "learning_rate": 6.075123608706093e-07, "epoch": 0.9969918349806618, "percentage": 77.33, "elapsed_time": "2:37:56", "remaining_time": "0:46:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.1771, "accuracy": 0.9210526347160339, "learning_rate": 5.737168930605272e-07, "epoch": 1.0051568543188656, "percentage": 78.0, "elapsed_time": "2:39:09", "remaining_time": "0:44:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.1885, "accuracy": 0.987500011920929, "learning_rate": 5.407663566854008e-07, "epoch": 1.0137516115169747, "percentage": 78.67, "elapsed_time": "2:40:25", "remaining_time": "0:43:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.1936, "accuracy": 0.9125000238418579, "learning_rate": 5.086752049395094e-07, "epoch": 1.0223463687150838, "percentage": 79.33, "elapsed_time": "2:41:38", "remaining_time": "0:42:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.2017, "accuracy": 0.8999999761581421, "learning_rate": 4.774575140626317e-07, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:42:57", "remaining_time": "0:40:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.23177994787693024, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:43:23", "remaining_time": "0:40:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.2086, "accuracy": 0.949999988079071, "learning_rate": 4.4712697716573994e-07, "epoch": 1.0395358831113022, "percentage": 80.67, "elapsed_time": "2:44:45", "remaining_time": "0:39:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.2236, "accuracy": 0.9624999761581421, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0481306403094113, "percentage": 81.33, "elapsed_time": "2:45:56", "remaining_time": "0:38:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.1751, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.0567253975075204, "percentage": 82.0, "elapsed_time": "2:47:10", "remaining_time": "0:36:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.1854, "accuracy": 0.949999988079071, "learning_rate": 3.615893495987335e-07, "epoch": 1.0653201547056295, "percentage": 82.67, "elapsed_time": "2:48:22", "remaining_time": "0:35:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.1974, "accuracy": 0.9624999761581421, "learning_rate": 3.3493649053890325e-07, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:49:36", "remaining_time": "0:33:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.23058351874351501, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:50:02", "remaining_time": "0:34:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 0.1837, "accuracy": 0.9125000238418579, "learning_rate": 3.092332998903416e-07, "epoch": 1.0825096691018479, "percentage": 84.0, "elapsed_time": "2:51:22", "remaining_time": "0:32:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.1835, "accuracy": 0.9125000238418579, "learning_rate": 2.844910519219632e-07, "epoch": 1.091104426299957, "percentage": 84.67, "elapsed_time": "2:52:35", "remaining_time": "0:31:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.2018, "accuracy": 0.9375, "learning_rate": 2.6072059940146775e-07, "epoch": 1.0996991834980663, "percentage": 85.33, "elapsed_time": "2:53:49", "remaining_time": "0:29:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 0.184, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1082939406961754, "percentage": 86.0, "elapsed_time": "2:55:06", "remaining_time": "0:28:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.2124, "accuracy": 0.949999988079071, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1168886978942845, "percentage": 86.67, "elapsed_time": "2:56:18", "remaining_time": "0:27:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.2303474247455597, "epoch": 1.1168886978942845, "percentage": 86.67, "elapsed_time": "2:56:45", "remaining_time": "0:27:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.1944, "accuracy": 0.9624999761581421, "learning_rate": 1.95342121028749e-07, "epoch": 1.1254834550923936, "percentage": 87.33, "elapsed_time": "2:58:08", "remaining_time": "0:25:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.1642, "accuracy": 0.9750000238418579, "learning_rate": 1.7555878527937164e-07, "epoch": 1.1340782122905029, "percentage": 88.0, "elapsed_time": "2:59:24", "remaining_time": "0:24:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.1671, "accuracy": 0.9750000238418579, "learning_rate": 1.567950262702714e-07, "epoch": 1.142672969488612, "percentage": 88.67, "elapsed_time": "3:00:40", "remaining_time": "0:23:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 0.1908, "accuracy": 0.9375, "learning_rate": 1.3905907440629752e-07, "epoch": 1.151267726686721, "percentage": 89.33, "elapsed_time": "3:01:57", "remaining_time": "0:21:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.1838, "accuracy": 0.9750000238418579, "learning_rate": 1.223587092621162e-07, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "3:03:15", "remaining_time": "0:20:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.2298813760280609, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "3:03:41", "remaining_time": "0:20:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.2262, "accuracy": 0.8999999761581421, "learning_rate": 1.067012561698319e-07, "epoch": 1.1684572410829395, "percentage": 90.67, "elapsed_time": "3:05:00", "remaining_time": "0:19:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.2028, "accuracy": 0.9375, "learning_rate": 9.209358300585474e-08, "epoch": 1.1770519982810486, "percentage": 91.33, "elapsed_time": "3:06:16", "remaining_time": "0:17:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.1786, "accuracy": 0.9375, "learning_rate": 7.854209717842231e-08, "epoch": 1.1856467554791577, "percentage": 92.0, "elapsed_time": "3:07:32", "remaining_time": "0:16:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 0.2157, "accuracy": 0.8999999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.1942415126772667, "percentage": 92.67, "elapsed_time": "3:08:51", "remaining_time": "0:14:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.1987, "accuracy": 0.9375, "learning_rate": 5.463099816548578e-08, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:10:04", "remaining_time": "0:13:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.23176495730876923, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:10:30", "remaining_time": "0:13:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.2081, "accuracy": 0.9125000238418579, "learning_rate": 4.428187317827848e-08, "epoch": 1.2114310270734852, "percentage": 94.0, "elapsed_time": "3:11:53", "remaining_time": "0:12:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.1874, "accuracy": 0.9750000238418579, "learning_rate": 3.5009907323737826e-08, "epoch": 1.2200257842715942, "percentage": 94.67, "elapsed_time": "3:13:05", "remaining_time": "0:10:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.2412, "accuracy": 0.9375, "learning_rate": 2.681916759252917e-08, "epoch": 1.2286205414697036, "percentage": 95.33, "elapsed_time": "3:14:24", "remaining_time": "0:09:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.1934, "accuracy": 0.9375, "learning_rate": 1.9713246713805588e-08, "epoch": 1.2372152986678127, "percentage": 96.0, "elapsed_time": "3:15:38", "remaining_time": "0:08:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.2094, "accuracy": 0.887499988079071, "learning_rate": 1.3695261579316776e-08, "epoch": 1.2458100558659218, "percentage": 96.67, "elapsed_time": "3:16:51", "remaining_time": "0:06:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.23184645175933838, "epoch": 1.2458100558659218, "percentage": 96.67, "elapsed_time": "3:17:17", "remaining_time": "0:06:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.159, "accuracy": 0.9750000238418579, "learning_rate": 8.767851876239075e-09, "epoch": 1.2544048130640308, "percentage": 97.33, "elapsed_time": "3:18:38", "remaining_time": "0:05:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.192, "accuracy": 0.9624999761581421, "learning_rate": 4.933178929321103e-09, "epoch": 1.2629995702621402, "percentage": 98.0, "elapsed_time": "3:19:54", "remaining_time": "0:04:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.2087, "accuracy": 0.9750000238418579, "learning_rate": 2.192924752854042e-09, "epoch": 1.2715943274602493, "percentage": 98.67, "elapsed_time": "3:21:09", "remaining_time": "0:02:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.1914, "accuracy": 0.949999988079071, "learning_rate": 5.48291312886251e-10, "epoch": 1.2801890846583583, "percentage": 99.33, "elapsed_time": "3:22:24", "remaining_time": "0:01:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.1984, "accuracy": 0.9624999761581421, "learning_rate": 0.0, "epoch": 1.2887838418564677, "percentage": 100.0, "elapsed_time": "3:23:38", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.2293597012758255, "epoch": 1.2887838418564677, "percentage": 100.0, "elapsed_time": "3:24:04", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 1.2887838418564677, "percentage": 100.0, "elapsed_time": "3:24:10", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |