| {"current_steps": 10, "total_steps": 1500, "loss": 1.0519, "accuracy": 0.23749999701976776, "learning_rate": 4.999451708687114e-06, "epoch": 0.015695507161075144, "percentage": 0.67, "elapsed_time": "0:01:16", "remaining_time": "3:09:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 1.0494, "accuracy": 0.15000000596046448, "learning_rate": 4.997807075247147e-06, "epoch": 0.03139101432215029, "percentage": 1.33, "elapsed_time": "0:02:35", "remaining_time": "3:12:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 1.0375, "accuracy": 0.21250000596046448, "learning_rate": 4.9950668210706795e-06, "epoch": 0.047086521483225424, "percentage": 2.0, "elapsed_time": "0:03:50", "remaining_time": "3:08:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 1.0375, "accuracy": 0.20000000298023224, "learning_rate": 4.9912321481237616e-06, "epoch": 0.06278202864430057, "percentage": 2.67, "elapsed_time": "0:05:06", "remaining_time": "3:06:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 1.0341, "accuracy": 0.20000000298023224, "learning_rate": 4.986304738420684e-06, "epoch": 0.07847753580537571, "percentage": 3.33, "elapsed_time": "0:06:17", "remaining_time": "3:02:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 1.0295902490615845, "epoch": 0.07847753580537571, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 1.0385, "accuracy": 0.23749999701976776, "learning_rate": 4.980286753286196e-06, "epoch": 0.09417304296645085, "percentage": 4.0, "elapsed_time": "0:07:52", "remaining_time": "3:09:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 1.0417, "accuracy": 0.21250000596046448, "learning_rate": 4.973180832407471e-06, "epoch": 0.109868550127526, "percentage": 4.67, "elapsed_time": "0:09:09", "remaining_time": "3:07:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 1.0255, "accuracy": 0.1875, "learning_rate": 4.964990092676263e-06, "epoch": 0.12556405728860115, "percentage": 5.33, "elapsed_time": "0:10:26", "remaining_time": "3:05:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 1.0297, "accuracy": 0.21250000596046448, "learning_rate": 4.9557181268217225e-06, "epoch": 0.14125956444967627, "percentage": 6.0, "elapsed_time": "0:11:40", "remaining_time": "3:02:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 1.0285, "accuracy": 0.2750000059604645, "learning_rate": 4.9453690018345144e-06, "epoch": 0.15695507161075142, "percentage": 6.67, "elapsed_time": "0:12:55", "remaining_time": "3:01:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 1.0174708366394043, "epoch": 0.15695507161075142, "percentage": 6.67, "elapsed_time": "0:13:10", "remaining_time": "3:04:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 1.0364, "accuracy": 0.2874999940395355, "learning_rate": 4.933947257182901e-06, "epoch": 0.17265057877182657, "percentage": 7.33, "elapsed_time": "0:14:43", "remaining_time": "3:06:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 1.0242, "accuracy": 0.23749999701976776, "learning_rate": 4.921457902821578e-06, "epoch": 0.1883460859329017, "percentage": 8.0, "elapsed_time": "0:16:00", "remaining_time": "3:04:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 1.0162, "accuracy": 0.2874999940395355, "learning_rate": 4.907906416994146e-06, "epoch": 0.20404159309397685, "percentage": 8.67, "elapsed_time": "0:17:13", "remaining_time": "3:01:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 1.0008, "accuracy": 0.3125, "learning_rate": 4.893298743830168e-06, "epoch": 0.219737100255052, "percentage": 9.33, "elapsed_time": "0:18:29", "remaining_time": "2:59:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 1.0085, "accuracy": 0.3375000059604645, "learning_rate": 4.8776412907378845e-06, "epoch": 0.23543260741612712, "percentage": 10.0, "elapsed_time": "0:19:46", "remaining_time": "2:58:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9791463017463684, "epoch": 0.23543260741612712, "percentage": 10.0, "elapsed_time": "0:20:01", "remaining_time": "3:00:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9827, "accuracy": 0.42500001192092896, "learning_rate": 4.860940925593703e-06, "epoch": 0.2511281145772023, "percentage": 10.67, "elapsed_time": "0:21:36", "remaining_time": "3:00:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.9716, "accuracy": 0.4625000059604645, "learning_rate": 4.84320497372973e-06, "epoch": 0.2668236217382774, "percentage": 11.33, "elapsed_time": "0:22:54", "remaining_time": "2:59:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.9546, "accuracy": 0.4124999940395355, "learning_rate": 4.824441214720629e-06, "epoch": 0.28251912889935255, "percentage": 12.0, "elapsed_time": "0:24:12", "remaining_time": "2:57:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9472, "accuracy": 0.5249999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.2982146360604277, "percentage": 12.67, "elapsed_time": "0:25:29", "remaining_time": "2:55:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.9455, "accuracy": 0.375, "learning_rate": 4.783863644106502e-06, "epoch": 0.31391014322150285, "percentage": 13.33, "elapsed_time": "0:26:42", "remaining_time": "2:53:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.9283667802810669, "epoch": 0.31391014322150285, "percentage": 13.33, "elapsed_time": "0:26:57", "remaining_time": "2:55:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.9225, "accuracy": 0.48750001192092896, "learning_rate": 4.762067631165049e-06, "epoch": 0.329605650382578, "percentage": 14.0, "elapsed_time": "0:28:20", "remaining_time": "2:54:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.9264, "accuracy": 0.512499988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.34530115754365315, "percentage": 14.67, "elapsed_time": "0:29:38", "remaining_time": "2:52:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.9037, "accuracy": 0.512499988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.3609966647047283, "percentage": 15.33, "elapsed_time": "0:30:54", "remaining_time": "2:50:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.9154, "accuracy": 0.5625, "learning_rate": 4.690766700109659e-06, "epoch": 0.3766921718658034, "percentage": 16.0, "elapsed_time": "0:32:10", "remaining_time": "2:48:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.8774, "accuracy": 0.42500001192092896, "learning_rate": 4.665063509461098e-06, "epoch": 0.39238767902687854, "percentage": 16.67, "elapsed_time": "0:33:28", "remaining_time": "2:47:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8047741651535034, "epoch": 0.39238767902687854, "percentage": 16.67, "elapsed_time": "0:33:42", "remaining_time": "2:48:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.8197, "accuracy": 0.4375, "learning_rate": 4.638410650401267e-06, "epoch": 0.4080831861879537, "percentage": 17.33, "elapsed_time": "0:35:05", "remaining_time": "2:47:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7493, "accuracy": 0.4375, "learning_rate": 4.610819813755038e-06, "epoch": 0.42377869334902885, "percentage": 18.0, "elapsed_time": "0:36:21", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7638, "accuracy": 0.637499988079071, "learning_rate": 4.582303101775249e-06, "epoch": 0.439474200510104, "percentage": 18.67, "elapsed_time": "0:37:38", "remaining_time": "2:44:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.7466, "accuracy": 0.6625000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.45516970767117915, "percentage": 19.33, "elapsed_time": "0:38:56", "remaining_time": "2:42:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.6982, "accuracy": 0.699999988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.47086521483225424, "percentage": 20.0, "elapsed_time": "0:40:10", "remaining_time": "2:40:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.7422243356704712, "epoch": 0.47086521483225424, "percentage": 20.0, "elapsed_time": "0:40:25", "remaining_time": "2:41:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.7415, "accuracy": 0.6625000238418579, "learning_rate": 4.491324795060491e-06, "epoch": 0.4865607219933294, "percentage": 20.67, "elapsed_time": "0:41:46", "remaining_time": "2:40:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.7249, "accuracy": 0.6499999761581421, "learning_rate": 4.4592336433146e-06, "epoch": 0.5022562291544046, "percentage": 21.33, "elapsed_time": "0:43:03", "remaining_time": "2:38:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.6868, "accuracy": 0.6625000238418579, "learning_rate": 4.426283106939474e-06, "epoch": 0.5179517363154797, "percentage": 22.0, "elapsed_time": "0:44:20", "remaining_time": "2:37:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.706, "accuracy": 0.7250000238418579, "learning_rate": 4.3924876391293915e-06, "epoch": 0.5336472434765548, "percentage": 22.67, "elapsed_time": "0:45:35", "remaining_time": "2:35:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.674, "accuracy": 0.75, "learning_rate": 4.357862063693486e-06, "epoch": 0.5493427506376299, "percentage": 23.33, "elapsed_time": "0:46:45", "remaining_time": "2:33:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.6938430070877075, "epoch": 0.5493427506376299, "percentage": 23.33, "elapsed_time": "0:47:00", "remaining_time": "2:34:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.651, "accuracy": 0.6499999761581421, "learning_rate": 4.322421568553529e-06, "epoch": 0.5650382577987051, "percentage": 24.0, "elapsed_time": "0:48:29", "remaining_time": "2:33:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.665, "accuracy": 0.800000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.5807337649597802, "percentage": 24.67, "elapsed_time": "0:49:47", "remaining_time": "2:32:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.5998, "accuracy": 0.887499988079071, "learning_rate": 4.249158351283414e-06, "epoch": 0.5964292721208554, "percentage": 25.33, "elapsed_time": "0:51:09", "remaining_time": "2:30:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.5937, "accuracy": 0.824999988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.6121247792819305, "percentage": 26.0, "elapsed_time": "0:52:22", "remaining_time": "2:29:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.5722, "accuracy": 0.7749999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.6278202864430057, "percentage": 26.67, "elapsed_time": "0:53:33", "remaining_time": "2:27:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.5668805837631226, "epoch": 0.6278202864430057, "percentage": 26.67, "elapsed_time": "0:53:48", "remaining_time": "2:27:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.5412, "accuracy": 0.8374999761581421, "learning_rate": 4.133551509975264e-06, "epoch": 0.6435157936040808, "percentage": 27.33, "elapsed_time": "0:55:15", "remaining_time": "2:26:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.4652, "accuracy": 0.862500011920929, "learning_rate": 4.093559974371725e-06, "epoch": 0.659211300765156, "percentage": 28.0, "elapsed_time": "0:56:31", "remaining_time": "2:25:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.427, "accuracy": 0.8999999761581421, "learning_rate": 4.052869450695776e-06, "epoch": 0.6749068079262311, "percentage": 28.67, "elapsed_time": "0:57:45", "remaining_time": "2:23:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.4692, "accuracy": 0.8374999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.6906023150873063, "percentage": 29.33, "elapsed_time": "0:58:59", "remaining_time": "2:22:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.4218, "accuracy": 0.8500000238418579, "learning_rate": 3.969463130731183e-06, "epoch": 0.7062978222483814, "percentage": 30.0, "elapsed_time": "1:00:14", "remaining_time": "2:20:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.45794492959976196, "epoch": 0.7062978222483814, "percentage": 30.0, "elapsed_time": "1:00:28", "remaining_time": "2:21:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.3675, "accuracy": 0.8999999761581421, "learning_rate": 3.92678391921108e-06, "epoch": 0.7219933294094566, "percentage": 30.67, "elapsed_time": "1:01:58", "remaining_time": "2:20:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3653, "accuracy": 0.862500011920929, "learning_rate": 3.88347887310836e-06, "epoch": 0.7376888365705316, "percentage": 31.33, "elapsed_time": "1:03:11", "remaining_time": "2:18:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3439, "accuracy": 0.9125000238418579, "learning_rate": 3.839566987447492e-06, "epoch": 0.7533843437316068, "percentage": 32.0, "elapsed_time": "1:04:26", "remaining_time": "2:16:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3645, "accuracy": 0.8999999761581421, "learning_rate": 3.795067523432826e-06, "epoch": 0.7690798508926819, "percentage": 32.67, "elapsed_time": "1:05:44", "remaining_time": "2:15:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.3698, "accuracy": 0.9125000238418579, "learning_rate": 3.7500000000000005e-06, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:07:00", "remaining_time": "2:14:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.38915327191352844, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:07:14", "remaining_time": "2:14:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.3547, "accuracy": 0.875, "learning_rate": 3.7043841852542884e-06, "epoch": 0.8004708652148322, "percentage": 34.0, "elapsed_time": "1:08:40", "remaining_time": "2:13:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3718, "accuracy": 0.9375, "learning_rate": 3.658240087799655e-06, "epoch": 0.8161663723759074, "percentage": 34.67, "elapsed_time": "1:09:55", "remaining_time": "2:11:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.329, "accuracy": 0.925000011920929, "learning_rate": 3.611587947962319e-06, "epoch": 0.8318618795369825, "percentage": 35.33, "elapsed_time": "1:11:12", "remaining_time": "2:10:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.2544, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.8475573866980577, "percentage": 36.0, "elapsed_time": "1:12:26", "remaining_time": "2:08:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.2795, "accuracy": 0.925000011920929, "learning_rate": 3.516841607689501e-06, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:39", "remaining_time": "2:07:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.335475891828537, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:54", "remaining_time": "2:07:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.3008, "accuracy": 0.9125000238418579, "learning_rate": 3.4687889661302577e-06, "epoch": 0.878948401020208, "percentage": 37.33, "elapsed_time": "1:15:27", "remaining_time": "2:06:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.2816, "accuracy": 0.9375, "learning_rate": 3.4203113817116955e-06, "epoch": 0.8946439081812831, "percentage": 38.0, "elapsed_time": "1:16:44", "remaining_time": "2:05:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.2921, "accuracy": 0.9125000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.9103394153423583, "percentage": 38.67, "elapsed_time": "1:17:55", "remaining_time": "2:03:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.3155, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.9260349225034334, "percentage": 39.33, "elapsed_time": "1:19:11", "remaining_time": "2:02:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.2565, "accuracy": 0.9375, "learning_rate": 3.272542485937369e-06, "epoch": 0.9417304296645085, "percentage": 40.0, "elapsed_time": "1:20:30", "remaining_time": "2:00:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.30504748225212097, "epoch": 0.9417304296645085, "percentage": 40.0, "elapsed_time": "1:20:45", "remaining_time": "2:01:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.2527, "accuracy": 0.9624999761581421, "learning_rate": 3.222579492361179e-06, "epoch": 0.9574259368255836, "percentage": 40.67, "elapsed_time": "1:22:11", "remaining_time": "1:59:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.2895, "accuracy": 0.9624999761581421, "learning_rate": 3.1722995515381644e-06, "epoch": 0.9731214439866588, "percentage": 41.33, "elapsed_time": "1:23:28", "remaining_time": "1:58:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2284, "accuracy": 0.9750000238418579, "learning_rate": 3.121724717912138e-06, "epoch": 0.9888169511477339, "percentage": 42.0, "elapsed_time": "1:24:41", "remaining_time": "1:56:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2276, "accuracy": 0.9178082346916199, "learning_rate": 3.0708771752766397e-06, "epoch": 1.003139101432215, "percentage": 42.67, "elapsed_time": "1:25:50", "remaining_time": "1:55:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2353, "accuracy": 0.9375, "learning_rate": 3.019779227044398e-06, "epoch": 1.0188346085932902, "percentage": 43.33, "elapsed_time": "1:27:07", "remaining_time": "1:53:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.28009530901908875, "epoch": 1.0188346085932902, "percentage": 43.33, "elapsed_time": "1:27:22", "remaining_time": "1:54:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.2562, "accuracy": 0.9125000238418579, "learning_rate": 2.9684532864643123e-06, "epoch": 1.0345301157543654, "percentage": 44.0, "elapsed_time": "1:28:53", "remaining_time": "1:53:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2271, "accuracy": 0.987500011920929, "learning_rate": 2.9169218667902562e-06, "epoch": 1.0502256229154405, "percentage": 44.67, "elapsed_time": "1:30:10", "remaining_time": "1:51:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.179, "accuracy": 0.9375, "learning_rate": 2.8652075714060296e-06, "epoch": 1.0659211300765157, "percentage": 45.33, "elapsed_time": "1:31:27", "remaining_time": "1:50:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2541, "accuracy": 0.9750000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 1.0816166372375908, "percentage": 46.0, "elapsed_time": "1:32:45", "remaining_time": "1:48:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.1919, "accuracy": 0.987500011920929, "learning_rate": 2.761321158169134e-06, "epoch": 1.097312144398666, "percentage": 46.67, "elapsed_time": "1:33:59", "remaining_time": "1:47:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.25916898250579834, "epoch": 1.097312144398666, "percentage": 46.67, "elapsed_time": "1:34:13", "remaining_time": "1:47:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.2187, "accuracy": 0.9624999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 1.113007651559741, "percentage": 47.33, "elapsed_time": "1:35:41", "remaining_time": "1:46:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.1847, "accuracy": 0.9375, "learning_rate": 2.6569762988232838e-06, "epoch": 1.1287031587208163, "percentage": 48.0, "elapsed_time": "1:36:56", "remaining_time": "1:45:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.1914, "accuracy": 0.9125000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 1.1443986658818912, "percentage": 48.67, "elapsed_time": "1:38:09", "remaining_time": "1:43:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.2055, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 1.1600941730429664, "percentage": 49.33, "elapsed_time": "1:39:25", "remaining_time": "1:42:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.185, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 1.1757896802040415, "percentage": 50.0, "elapsed_time": "1:40:41", "remaining_time": "1:40:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.24307754635810852, "epoch": 1.1757896802040415, "percentage": 50.0, "elapsed_time": "1:40:56", "remaining_time": "1:40:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.1958, "accuracy": 0.9750000238418579, "learning_rate": 2.447643950291608e-06, "epoch": 1.1914851873651167, "percentage": 50.67, "elapsed_time": "1:42:33", "remaining_time": "1:39:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.1921, "accuracy": 0.949999988079071, "learning_rate": 2.3953108656770018e-06, "epoch": 1.2071806945261918, "percentage": 51.33, "elapsed_time": "1:43:49", "remaining_time": "1:38:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.1731, "accuracy": 0.987500011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 1.222876201687267, "percentage": 52.0, "elapsed_time": "1:45:03", "remaining_time": "1:36:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.1844, "accuracy": 0.949999988079071, "learning_rate": 2.290805391669212e-06, "epoch": 1.2385717088483421, "percentage": 52.67, "elapsed_time": "1:46:15", "remaining_time": "1:35:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.1638, "accuracy": 0.949999988079071, "learning_rate": 2.238678841830867e-06, "epoch": 1.2542672160094173, "percentage": 53.33, "elapsed_time": "1:47:32", "remaining_time": "1:34:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.21881447732448578, "epoch": 1.2542672160094173, "percentage": 53.33, "elapsed_time": "1:47:47", "remaining_time": "1:34:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.1827, "accuracy": 0.9624999761581421, "learning_rate": 2.186666916089239e-06, "epoch": 1.2699627231704924, "percentage": 54.0, "elapsed_time": "1:49:14", "remaining_time": "1:33:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.1716, "accuracy": 0.949999988079071, "learning_rate": 2.134792428593971e-06, "epoch": 1.2856582303315676, "percentage": 54.67, "elapsed_time": "1:50:31", "remaining_time": "1:31:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.1652, "accuracy": 0.9375, "learning_rate": 2.0830781332097446e-06, "epoch": 1.3013537374926427, "percentage": 55.33, "elapsed_time": "1:51:45", "remaining_time": "1:30:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.1881, "accuracy": 0.9375, "learning_rate": 2.031546713535688e-06, "epoch": 1.3170492446537179, "percentage": 56.0, "elapsed_time": "1:52:59", "remaining_time": "1:28:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2051, "accuracy": 0.987500011920929, "learning_rate": 1.9802207729556023e-06, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:54:15", "remaining_time": "1:27:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.20189520716667175, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:54:30", "remaining_time": "1:27:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.2083, "accuracy": 0.925000011920929, "learning_rate": 1.9291228247233607e-06, "epoch": 1.3484402589758682, "percentage": 57.33, "elapsed_time": "1:56:05", "remaining_time": "1:26:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.1782, "accuracy": 0.987500011920929, "learning_rate": 1.8782752820878636e-06, "epoch": 1.3641357661369433, "percentage": 58.0, "elapsed_time": "1:57:16", "remaining_time": "1:24:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.237, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 1.3798312732980185, "percentage": 58.67, "elapsed_time": "1:58:33", "remaining_time": "1:23:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.1904, "accuracy": 0.9624999761581421, "learning_rate": 1.7774205076388207e-06, "epoch": 1.3955267804590936, "percentage": 59.33, "elapsed_time": "1:59:49", "remaining_time": "1:22:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.1508, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:01:04", "remaining_time": "1:20:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.18640650808811188, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:01:18", "remaining_time": "1:20:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.1446, "accuracy": 0.987500011920929, "learning_rate": 1.677833383153542e-06, "epoch": 1.426917794781244, "percentage": 60.67, "elapsed_time": "2:02:51", "remaining_time": "1:19:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.163, "accuracy": 0.9750000238418579, "learning_rate": 1.6285698816954626e-06, "epoch": 1.442613301942319, "percentage": 61.33, "elapsed_time": "2:04:05", "remaining_time": "1:18:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.1773, "accuracy": 0.949999988079071, "learning_rate": 1.5796886182883053e-06, "epoch": 1.4583088091033942, "percentage": 62.0, "elapsed_time": "2:05:25", "remaining_time": "1:16:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.2058, "accuracy": 0.9624999761581421, "learning_rate": 1.5312110338697427e-06, "epoch": 1.4740043162644694, "percentage": 62.67, "elapsed_time": "2:06:39", "remaining_time": "1:15:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.1827, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 1.4896998234255445, "percentage": 63.33, "elapsed_time": "2:07:55", "remaining_time": "1:14:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.1744592934846878, "epoch": 1.4896998234255445, "percentage": 63.33, "elapsed_time": "2:08:09", "remaining_time": "1:14:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.1559, "accuracy": 0.949999988079071, "learning_rate": 1.4355517710873184e-06, "epoch": 1.5053953305866195, "percentage": 64.0, "elapsed_time": "2:09:42", "remaining_time": "1:12:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.1334, "accuracy": 0.9375, "learning_rate": 1.388412052037682e-06, "epoch": 1.5210908377476948, "percentage": 64.67, "elapsed_time": "2:10:55", "remaining_time": "1:11:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.1477, "accuracy": 0.949999988079071, "learning_rate": 1.3417599122003464e-06, "epoch": 1.5367863449087698, "percentage": 65.33, "elapsed_time": "2:12:11", "remaining_time": "1:10:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.1561, "accuracy": 0.949999988079071, "learning_rate": 1.2956158147457116e-06, "epoch": 1.5524818520698451, "percentage": 66.0, "elapsed_time": "2:13:24", "remaining_time": "1:08:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.1771, "accuracy": 0.9750000238418579, "learning_rate": 1.2500000000000007e-06, "epoch": 1.56817735923092, "percentage": 66.67, "elapsed_time": "2:14:35", "remaining_time": "1:07:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.16595196723937988, "epoch": 1.56817735923092, "percentage": 66.67, "elapsed_time": "2:14:50", "remaining_time": "1:07:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.1668, "accuracy": 0.9750000238418579, "learning_rate": 1.204932476567175e-06, "epoch": 1.5838728663919954, "percentage": 67.33, "elapsed_time": "2:16:15", "remaining_time": "1:06:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.1824, "accuracy": 0.9624999761581421, "learning_rate": 1.160433012552508e-06, "epoch": 1.5995683735530704, "percentage": 68.0, "elapsed_time": "2:17:32", "remaining_time": "1:04:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.1567, "accuracy": 0.987500011920929, "learning_rate": 1.11652112689164e-06, "epoch": 1.6152638807141457, "percentage": 68.67, "elapsed_time": "2:18:50", "remaining_time": "1:03:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.1682, "accuracy": 0.987500011920929, "learning_rate": 1.073216080788921e-06, "epoch": 1.6309593878752207, "percentage": 69.33, "elapsed_time": "2:20:07", "remaining_time": "1:01:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.1143, "accuracy": 0.9624999761581421, "learning_rate": 1.0305368692688175e-06, "epoch": 1.6466548950362958, "percentage": 70.0, "elapsed_time": "2:21:25", "remaining_time": "1:00:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.16117088496685028, "epoch": 1.6466548950362958, "percentage": 70.0, "elapsed_time": "2:21:39", "remaining_time": "1:00:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.1631, "accuracy": 1.0, "learning_rate": 9.88502212844063e-07, "epoch": 1.662350402197371, "percentage": 70.67, "elapsed_time": "2:22:58", "remaining_time": "0:59:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.1347, "accuracy": 1.0, "learning_rate": 9.471305493042243e-07, "epoch": 1.678045909358446, "percentage": 71.33, "elapsed_time": "2:24:16", "remaining_time": "0:57:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.1076, "accuracy": 0.9750000238418579, "learning_rate": 9.064400256282757e-07, "epoch": 1.6937414165195213, "percentage": 72.0, "elapsed_time": "2:25:34", "remaining_time": "0:56:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.1532, "accuracy": 0.9624999761581421, "learning_rate": 8.664484900247363e-07, "epoch": 1.7094369236805964, "percentage": 72.67, "elapsed_time": "2:26:45", "remaining_time": "0:55:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.1632, "accuracy": 0.9624999761581421, "learning_rate": 8.271734841028553e-07, "epoch": 1.7251324308416716, "percentage": 73.33, "elapsed_time": "2:27:58", "remaining_time": "0:53:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.1563359946012497, "epoch": 1.7251324308416716, "percentage": 73.33, "elapsed_time": "2:28:12", "remaining_time": "0:53:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.1579, "accuracy": 0.9624999761581421, "learning_rate": 7.886322351782782e-07, "epoch": 1.7408279380027467, "percentage": 74.0, "elapsed_time": "2:29:34", "remaining_time": "0:52:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.1603, "accuracy": 0.9375, "learning_rate": 7.508416487165862e-07, "epoch": 1.7565234451638219, "percentage": 74.67, "elapsed_time": "2:30:47", "remaining_time": "0:51:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.1428, "accuracy": 0.9750000238418579, "learning_rate": 7.138183009179922e-07, "epoch": 1.772218952324897, "percentage": 75.33, "elapsed_time": "2:32:03", "remaining_time": "0:49:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.163, "accuracy": 0.9375, "learning_rate": 6.775784314464717e-07, "epoch": 1.7879144594859722, "percentage": 76.0, "elapsed_time": "2:33:18", "remaining_time": "0:48:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.1288, "accuracy": 0.9750000238418579, "learning_rate": 6.421379363065142e-07, "epoch": 1.8036099666470473, "percentage": 76.67, "elapsed_time": "2:34:33", "remaining_time": "0:47:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.15526321530342102, "epoch": 1.8036099666470473, "percentage": 76.67, "elapsed_time": "2:34:48", "remaining_time": "0:47:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.1241, "accuracy": 0.9750000238418579, "learning_rate": 6.075123608706093e-07, "epoch": 1.8193054738081225, "percentage": 77.33, "elapsed_time": "2:36:29", "remaining_time": "0:45:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.1337, "accuracy": 0.9750000238418579, "learning_rate": 5.737168930605272e-07, "epoch": 1.8350009809691976, "percentage": 78.0, "elapsed_time": "2:37:45", "remaining_time": "0:44:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.1245, "accuracy": 0.9624999761581421, "learning_rate": 5.407663566854008e-07, "epoch": 1.8506964881302728, "percentage": 78.67, "elapsed_time": "2:39:02", "remaining_time": "0:43:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.1251, "accuracy": 0.987500011920929, "learning_rate": 5.086752049395094e-07, "epoch": 1.8663919952913477, "percentage": 79.33, "elapsed_time": "2:40:17", "remaining_time": "0:41:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.1543, "accuracy": 0.9624999761581421, "learning_rate": 4.774575140626317e-07, "epoch": 1.882087502452423, "percentage": 80.0, "elapsed_time": "2:41:33", "remaining_time": "0:40:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.1518644094467163, "epoch": 1.882087502452423, "percentage": 80.0, "elapsed_time": "2:41:47", "remaining_time": "0:40:26", "throughput": "0.00", "total_tokens": 0} | |