| {"current_steps": 10, "total_steps": 1500, "loss": 0.9442, "accuracy": 0.4124999940395355, "learning_rate": 4.999451708687114e-06, "epoch": 0.008594757198109154, "percentage": 0.67, "elapsed_time": "0:01:09", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.928, "accuracy": 0.550000011920929, "learning_rate": 4.997807075247147e-06, "epoch": 0.017189514396218308, "percentage": 1.33, "elapsed_time": "0:02:23", "remaining_time": "2:57:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9439, "accuracy": 0.4375, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02578427159432746, "percentage": 2.0, "elapsed_time": "0:03:37", "remaining_time": "2:57:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9184, "accuracy": 0.4124999940395355, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:48", "remaining_time": "2:55:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.5249999761581421, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:03", "remaining_time": "2:55:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9324354529380798, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:29", "remaining_time": "3:08:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9323, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:07:47", "remaining_time": "3:07:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9172, "accuracy": 0.48750001192092896, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:01", "remaining_time": "3:04:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9245, "accuracy": 0.48750001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:16", "remaining_time": "3:02:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9359, "accuracy": 0.5, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:30", "remaining_time": "3:00:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9066, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:42", "remaining_time": "2:57:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9236211180686951, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:08", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:26", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9299, "accuracy": 0.5874999761581421, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:15:43", "remaining_time": "3:00:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9109, "accuracy": 0.5375000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:16:56", "remaining_time": "2:58:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9138, "accuracy": 0.5625, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:12", "remaining_time": "2:56:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9157, "accuracy": 0.574999988079071, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:26", "remaining_time": "2:54:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.909102737903595, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:52", "remaining_time": "2:58:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9, "accuracy": 0.512499988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.13751611516974646, "percentage": 10.67, "elapsed_time": "0:21:11", "remaining_time": "2:57:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.896, "accuracy": 0.637499988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.1461108723678556, "percentage": 11.33, "elapsed_time": "0:22:25", "remaining_time": "2:55:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8911, "accuracy": 0.5625, "learning_rate": 4.824441214720629e-06, "epoch": 0.15470562956596476, "percentage": 12.0, "elapsed_time": "0:23:38", "remaining_time": "2:53:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9002, "accuracy": 0.6000000238418579, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:24:53", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8773, "accuracy": 0.574999988079071, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:03", "remaining_time": "2:49:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8721462488174438, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:28", "remaining_time": "2:52:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8484, "accuracy": 0.5375000238418579, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:27:50", "remaining_time": "2:50:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8499, "accuracy": 0.637499988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:05", "remaining_time": "2:49:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.826, "accuracy": 0.6499999761581421, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:18", "remaining_time": "2:47:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7992, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:33", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.7848, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:32:47", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7728626728057861, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:12", "remaining_time": "2:46:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.7273, "accuracy": 0.7124999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.22346368715083798, "percentage": 17.33, "elapsed_time": "0:34:29", "remaining_time": "2:44:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7483, "accuracy": 0.6875, "learning_rate": 4.610819813755038e-06, "epoch": 0.23205844434894715, "percentage": 18.0, "elapsed_time": "0:35:46", "remaining_time": "2:43:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7165, "accuracy": 0.612500011920929, "learning_rate": 4.582303101775249e-06, "epoch": 0.2406532015470563, "percentage": 18.67, "elapsed_time": "0:36:58", "remaining_time": "2:41:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.6685, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:10", "remaining_time": "2:39:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.625, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:25", "remaining_time": "2:37:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5855891704559326, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:51", "remaining_time": "2:39:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.512, "accuracy": 0.75, "learning_rate": 4.491324795060491e-06, "epoch": 0.2664374731413838, "percentage": 20.67, "elapsed_time": "0:41:11", "remaining_time": "2:38:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.5405, "accuracy": 0.6499999761581421, "learning_rate": 4.4592336433146e-06, "epoch": 0.2750322303394929, "percentage": 21.33, "elapsed_time": "0:42:25", "remaining_time": "2:36:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.5335, "accuracy": 0.637499988079071, "learning_rate": 4.426283106939474e-06, "epoch": 0.28362698753760207, "percentage": 22.0, "elapsed_time": "0:43:40", "remaining_time": "2:34:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.4903, "accuracy": 0.7124999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:44:52", "remaining_time": "2:33:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.5249, "accuracy": 0.5625, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:04", "remaining_time": "2:31:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5171241760253906, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:29", "remaining_time": "2:32:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.5067, "accuracy": 0.675000011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.3094112591319295, "percentage": 24.0, "elapsed_time": "0:47:46", "remaining_time": "2:31:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.4726, "accuracy": 0.800000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.31800601633003867, "percentage": 24.67, "elapsed_time": "0:48:58", "remaining_time": "2:29:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4801, "accuracy": 0.6625000238418579, "learning_rate": 4.249158351283414e-06, "epoch": 0.3266007735281478, "percentage": 25.33, "elapsed_time": "0:50:12", "remaining_time": "2:27:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4585, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:51:21", "remaining_time": "2:26:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.4771, "accuracy": 0.675000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:33", "remaining_time": "2:24:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47841358184814453, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:58", "remaining_time": "2:25:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.4449, "accuracy": 0.637499988079071, "learning_rate": 4.133551509975264e-06, "epoch": 0.3523850451224753, "percentage": 27.33, "elapsed_time": "0:54:22", "remaining_time": "2:24:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.4598, "accuracy": 0.699999988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.36097980232058446, "percentage": 28.0, "elapsed_time": "0:55:35", "remaining_time": "2:22:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.4275, "accuracy": 0.75, "learning_rate": 4.052869450695776e-06, "epoch": 0.3695745595186936, "percentage": 28.67, "elapsed_time": "0:56:48", "remaining_time": "2:21:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.4132, "accuracy": 0.75, "learning_rate": 4.011497787155938e-06, "epoch": 0.37816931671680276, "percentage": 29.33, "elapsed_time": "0:57:57", "remaining_time": "2:19:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.4266, "accuracy": 0.7749999761581421, "learning_rate": 3.969463130731183e-06, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:09", "remaining_time": "2:18:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.4397798478603363, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:35", "remaining_time": "2:19:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.367, "accuracy": 0.762499988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.39535883111302106, "percentage": 30.67, "elapsed_time": "1:00:53", "remaining_time": "2:17:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3957, "accuracy": 0.8374999761581421, "learning_rate": 3.88347887310836e-06, "epoch": 0.4039535883111302, "percentage": 31.33, "elapsed_time": "1:02:05", "remaining_time": "2:16:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3808, "accuracy": 0.824999988079071, "learning_rate": 3.839566987447492e-06, "epoch": 0.41254834550923936, "percentage": 32.0, "elapsed_time": "1:03:13", "remaining_time": "2:14:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3555, "accuracy": 0.875, "learning_rate": 3.795067523432826e-06, "epoch": 0.4211431027073485, "percentage": 32.67, "elapsed_time": "1:04:26", "remaining_time": "2:12:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.3211, "accuracy": 0.824999988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:05:37", "remaining_time": "2:11:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.37026864290237427, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:06:03", "remaining_time": "2:12:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.3375, "accuracy": 0.887499988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4383326171035668, "percentage": 34.0, "elapsed_time": "1:07:25", "remaining_time": "2:10:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3388, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.44692737430167595, "percentage": 34.67, "elapsed_time": "1:08:37", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.3281, "accuracy": 0.8500000238418579, "learning_rate": 3.611587947962319e-06, "epoch": 0.45552213149978515, "percentage": 35.33, "elapsed_time": "1:09:52", "remaining_time": "2:07:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.3565, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.4641168886978943, "percentage": 36.0, "elapsed_time": "1:11:05", "remaining_time": "2:06:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.3103, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:23", "remaining_time": "2:05:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.32732319831848145, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:49", "remaining_time": "2:05:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.3171, "accuracy": 0.887499988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4813064030941126, "percentage": 37.33, "elapsed_time": "1:14:02", "remaining_time": "2:04:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.331, "accuracy": 0.949999988079071, "learning_rate": 3.4203113817116955e-06, "epoch": 0.48990116029222175, "percentage": 38.0, "elapsed_time": "1:15:13", "remaining_time": "2:02:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.2557, "accuracy": 0.9750000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4984959174903309, "percentage": 38.67, "elapsed_time": "1:16:25", "remaining_time": "2:01:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.2921, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.50709067468844, "percentage": 39.33, "elapsed_time": "1:17:39", "remaining_time": "1:59:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.3225, "accuracy": 0.9125000238418579, "learning_rate": 3.272542485937369e-06, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:18:52", "remaining_time": "1:58:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.29786577820777893, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:19:18", "remaining_time": "1:58:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.2516, "accuracy": 0.9125000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.5242801890846583, "percentage": 40.67, "elapsed_time": "1:20:34", "remaining_time": "1:57:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.3062, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5328749462827675, "percentage": 41.33, "elapsed_time": "1:21:46", "remaining_time": "1:56:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2726, "accuracy": 0.9125000238418579, "learning_rate": 3.121724717912138e-06, "epoch": 0.5414697034808766, "percentage": 42.0, "elapsed_time": "1:22:57", "remaining_time": "1:54:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2861, "accuracy": 0.9125000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5500644606789858, "percentage": 42.67, "elapsed_time": "1:24:09", "remaining_time": "1:53:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2507, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:25:20", "remaining_time": "1:51:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.28581172227859497, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:25:46", "remaining_time": "1:52:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.2635, "accuracy": 0.9125000238418579, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5672539750752041, "percentage": 44.0, "elapsed_time": "1:27:00", "remaining_time": "1:50:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2854, "accuracy": 0.875, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5758487322733132, "percentage": 44.67, "elapsed_time": "1:28:11", "remaining_time": "1:49:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.2461, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5844434894714224, "percentage": 45.33, "elapsed_time": "1:29:20", "remaining_time": "1:47:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2458, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:30:30", "remaining_time": "1:46:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.2464, "accuracy": 0.925000011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:31:41", "remaining_time": "1:44:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26223084330558777, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:32:07", "remaining_time": "1:45:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.2785, "accuracy": 0.9624999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 0.6102277610657499, "percentage": 47.33, "elapsed_time": "1:33:23", "remaining_time": "1:43:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2623, "accuracy": 0.925000011920929, "learning_rate": 2.6569762988232838e-06, "epoch": 0.618822518263859, "percentage": 48.0, "elapsed_time": "1:34:36", "remaining_time": "1:42:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2702, "accuracy": 0.9125000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.6274172754619682, "percentage": 48.67, "elapsed_time": "1:35:48", "remaining_time": "1:41:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.2103, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6360120326600773, "percentage": 49.33, "elapsed_time": "1:37:00", "remaining_time": "1:39:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.2545, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:13", "remaining_time": "1:38:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2537091076374054, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:39", "remaining_time": "1:38:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2261, "accuracy": 0.9375, "learning_rate": 2.447643950291608e-06, "epoch": 0.6532015470562956, "percentage": 50.67, "elapsed_time": "1:40:01", "remaining_time": "1:37:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.2703, "accuracy": 0.862500011920929, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6617963042544048, "percentage": 51.33, "elapsed_time": "1:41:13", "remaining_time": "1:35:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.2493, "accuracy": 0.987500011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6703910614525139, "percentage": 52.0, "elapsed_time": "1:42:26", "remaining_time": "1:34:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.2461, "accuracy": 0.925000011920929, "learning_rate": 2.290805391669212e-06, "epoch": 0.6789858186506231, "percentage": 52.67, "elapsed_time": "1:43:39", "remaining_time": "1:33:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.2483, "accuracy": 0.925000011920929, "learning_rate": 2.238678841830867e-06, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:44:51", "remaining_time": "1:31:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.24035032093524933, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:45:17", "remaining_time": "1:32:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2647, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6961753330468414, "percentage": 54.0, "elapsed_time": "1:46:36", "remaining_time": "1:30:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.1888, "accuracy": 0.8999999761581421, "learning_rate": 2.134792428593971e-06, "epoch": 0.7047700902449506, "percentage": 54.67, "elapsed_time": "1:47:52", "remaining_time": "1:29:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2141, "accuracy": 0.949999988079071, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7133648474430597, "percentage": 55.33, "elapsed_time": "1:49:06", "remaining_time": "1:28:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.1953, "accuracy": 0.949999988079071, "learning_rate": 2.031546713535688e-06, "epoch": 0.7219596046411689, "percentage": 56.0, "elapsed_time": "1:50:14", "remaining_time": "1:26:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2395, "accuracy": 0.8999999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:31", "remaining_time": "1:25:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2363433688879013, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:56", "remaining_time": "1:25:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.2234, "accuracy": 0.925000011920929, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7391491190373872, "percentage": 57.33, "elapsed_time": "1:53:18", "remaining_time": "1:24:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.2045, "accuracy": 0.949999988079071, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7477438762354963, "percentage": 58.0, "elapsed_time": "1:54:28", "remaining_time": "1:22:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.231, "accuracy": 0.9125000238418579, "learning_rate": 1.827700448461836e-06, "epoch": 0.7563386334336055, "percentage": 58.67, "elapsed_time": "1:55:39", "remaining_time": "1:21:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.2398, "accuracy": 0.8999999761581421, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7649333906317146, "percentage": 59.33, "elapsed_time": "1:56:50", "remaining_time": "1:20:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.2388, "accuracy": 0.9750000238418579, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:58:00", "remaining_time": "1:18:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.22793449461460114, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:58:25", "remaining_time": "1:18:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.2267, "accuracy": 0.949999988079071, "learning_rate": 1.677833383153542e-06, "epoch": 0.7821229050279329, "percentage": 60.67, "elapsed_time": "1:59:46", "remaining_time": "1:17:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.2051, "accuracy": 0.925000011920929, "learning_rate": 1.6285698816954626e-06, "epoch": 0.7907176622260421, "percentage": 61.33, "elapsed_time": "2:01:00", "remaining_time": "1:16:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.2353, "accuracy": 0.949999988079071, "learning_rate": 1.5796886182883053e-06, "epoch": 0.7993124194241513, "percentage": 62.0, "elapsed_time": "2:02:14", "remaining_time": "1:14:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.2516, "accuracy": 0.875, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8079071766222604, "percentage": 62.67, "elapsed_time": "2:03:26", "remaining_time": "1:13:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.2299, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:04:39", "remaining_time": "1:12:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2293253093957901, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:05:05", "remaining_time": "1:12:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.2091, "accuracy": 0.9375, "learning_rate": 1.4355517710873184e-06, "epoch": 0.8250966910184787, "percentage": 64.0, "elapsed_time": "2:06:26", "remaining_time": "1:11:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.2295, "accuracy": 0.949999988079071, "learning_rate": 1.388412052037682e-06, "epoch": 0.8336914482165879, "percentage": 64.67, "elapsed_time": "2:07:39", "remaining_time": "1:09:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.1765, "accuracy": 0.9624999761581421, "learning_rate": 1.3417599122003464e-06, "epoch": 0.842286205414697, "percentage": 65.33, "elapsed_time": "2:08:56", "remaining_time": "1:08:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.2154, "accuracy": 0.9375, "learning_rate": 1.2956158147457116e-06, "epoch": 0.8508809626128062, "percentage": 66.0, "elapsed_time": "2:10:10", "remaining_time": "1:07:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.1983, "accuracy": 0.925000011920929, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:11:27", "remaining_time": "1:05:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.2214924544095993, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:11:53", "remaining_time": "1:05:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.2136, "accuracy": 0.949999988079071, "learning_rate": 1.204932476567175e-06, "epoch": 0.8680704770090245, "percentage": 67.33, "elapsed_time": "2:13:12", "remaining_time": "1:04:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.2506, "accuracy": 0.925000011920929, "learning_rate": 1.160433012552508e-06, "epoch": 0.8766652342071336, "percentage": 68.0, "elapsed_time": "2:14:28", "remaining_time": "1:03:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.2267, "accuracy": 0.9125000238418579, "learning_rate": 1.11652112689164e-06, "epoch": 0.8852599914052428, "percentage": 68.67, "elapsed_time": "2:15:40", "remaining_time": "1:01:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.2019, "accuracy": 0.887499988079071, "learning_rate": 1.073216080788921e-06, "epoch": 0.8938547486033519, "percentage": 69.33, "elapsed_time": "2:16:49", "remaining_time": "1:00:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.191, "accuracy": 0.949999988079071, "learning_rate": 1.0305368692688175e-06, "epoch": 0.9024495058014611, "percentage": 70.0, "elapsed_time": "2:18:00", "remaining_time": "0:59:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.21767112612724304, "epoch": 0.9024495058014611, "percentage": 70.0, "elapsed_time": "2:18:26", "remaining_time": "0:59:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.2254, "accuracy": 0.987500011920929, "learning_rate": 9.88502212844063e-07, "epoch": 0.9110442629995703, "percentage": 70.67, "elapsed_time": "2:19:48", "remaining_time": "0:58:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.1987, "accuracy": 0.9624999761581421, "learning_rate": 9.471305493042243e-07, "epoch": 0.9196390201976794, "percentage": 71.33, "elapsed_time": "2:20:59", "remaining_time": "0:56:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.1973, "accuracy": 0.9624999761581421, "learning_rate": 9.064400256282757e-07, "epoch": 0.9282337773957886, "percentage": 72.0, "elapsed_time": "2:22:12", "remaining_time": "0:55:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.2126, "accuracy": 0.949999988079071, "learning_rate": 8.664484900247363e-07, "epoch": 0.9368285345938977, "percentage": 72.67, "elapsed_time": "2:23:27", "remaining_time": "0:53:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.1904, "accuracy": 0.9624999761581421, "learning_rate": 8.271734841028553e-07, "epoch": 0.9454232917920069, "percentage": 73.33, "elapsed_time": "2:24:39", "remaining_time": "0:52:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.21661873161792755, "epoch": 0.9454232917920069, "percentage": 73.33, "elapsed_time": "2:25:05", "remaining_time": "0:52:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.1988, "accuracy": 0.9624999761581421, "learning_rate": 7.886322351782782e-07, "epoch": 0.954018048990116, "percentage": 74.0, "elapsed_time": "2:26:26", "remaining_time": "0:51:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.1683, "accuracy": 0.949999988079071, "learning_rate": 7.508416487165862e-07, "epoch": 0.9626128061882252, "percentage": 74.67, "elapsed_time": "2:27:41", "remaining_time": "0:50:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.1859, "accuracy": 0.8999999761581421, "learning_rate": 7.138183009179922e-07, "epoch": 0.9712075633863343, "percentage": 75.33, "elapsed_time": "2:28:54", "remaining_time": "0:48:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.175, "accuracy": 0.9375, "learning_rate": 6.775784314464717e-07, "epoch": 0.9798023205844435, "percentage": 76.0, "elapsed_time": "2:30:05", "remaining_time": "0:47:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.1612, "accuracy": 0.9624999761581421, "learning_rate": 6.421379363065142e-07, "epoch": 0.9883970777825526, "percentage": 76.67, "elapsed_time": "2:31:16", "remaining_time": "0:46:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.2131287306547165, "epoch": 0.9883970777825526, "percentage": 76.67, "elapsed_time": "2:31:42", "remaining_time": "0:46:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.22, "accuracy": 0.9375, "learning_rate": 6.075123608706093e-07, "epoch": 0.9969918349806618, "percentage": 77.33, "elapsed_time": "2:32:55", "remaining_time": "0:44:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.1738, "accuracy": 0.9605262875556946, "learning_rate": 5.737168930605272e-07, "epoch": 1.0051568543188656, "percentage": 78.0, "elapsed_time": "2:34:04", "remaining_time": "0:43:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.2176, "accuracy": 0.9624999761581421, "learning_rate": 5.407663566854008e-07, "epoch": 1.0137516115169747, "percentage": 78.67, "elapsed_time": "2:35:16", "remaining_time": "0:42:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.1689, "accuracy": 0.9624999761581421, "learning_rate": 5.086752049395094e-07, "epoch": 1.0223463687150838, "percentage": 79.33, "elapsed_time": "2:36:27", "remaining_time": "0:40:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.2052, "accuracy": 0.9125000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:37:43", "remaining_time": "0:39:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2119421511888504, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:38:09", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.2114, "accuracy": 0.925000011920929, "learning_rate": 4.4712697716573994e-07, "epoch": 1.0395358831113022, "percentage": 80.67, "elapsed_time": "2:39:25", "remaining_time": "0:38:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.1962, "accuracy": 0.949999988079071, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0481306403094113, "percentage": 81.33, "elapsed_time": "2:40:40", "remaining_time": "0:36:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.1811, "accuracy": 1.0, "learning_rate": 3.891801862449629e-07, "epoch": 1.0567253975075204, "percentage": 82.0, "elapsed_time": "2:41:53", "remaining_time": "0:35:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.1833, "accuracy": 0.9624999761581421, "learning_rate": 3.615893495987335e-07, "epoch": 1.0653201547056295, "percentage": 82.67, "elapsed_time": "2:43:05", "remaining_time": "0:34:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.1952, "accuracy": 0.9750000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:44:19", "remaining_time": "0:32:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.21290886402130127, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:44:45", "remaining_time": "0:32:57", "throughput": "0.00", "total_tokens": 0} | |