| {"current_steps": 10, "total_steps": 1500, "loss": 1.0492, "accuracy": 0.25, "learning_rate": 4.999451708687114e-06, "epoch": 0.015695507161075144, "percentage": 0.67, "elapsed_time": "0:01:14", "remaining_time": "3:05:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 1.0487, "accuracy": 0.16249999403953552, "learning_rate": 4.997807075247147e-06, "epoch": 0.03139101432215029, "percentage": 1.33, "elapsed_time": "0:02:34", "remaining_time": "3:10:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 1.0405, "accuracy": 0.1875, "learning_rate": 4.9950668210706795e-06, "epoch": 0.047086521483225424, "percentage": 2.0, "elapsed_time": "0:03:51", "remaining_time": "3:08:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 1.0369, "accuracy": 0.21250000596046448, "learning_rate": 4.9912321481237616e-06, "epoch": 0.06278202864430057, "percentage": 2.67, "elapsed_time": "0:05:08", "remaining_time": "3:07:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 1.0367, "accuracy": 0.21250000596046448, "learning_rate": 4.986304738420684e-06, "epoch": 0.07847753580537571, "percentage": 3.33, "elapsed_time": "0:06:23", "remaining_time": "3:05:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 1.0326261520385742, "epoch": 0.07847753580537571, "percentage": 3.33, "elapsed_time": "0:06:37", "remaining_time": "3:12:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 1.04, "accuracy": 0.25, "learning_rate": 4.980286753286196e-06, "epoch": 0.09417304296645085, "percentage": 4.0, "elapsed_time": "0:07:58", "remaining_time": "3:11:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 1.043, "accuracy": 0.21250000596046448, "learning_rate": 4.973180832407471e-06, "epoch": 0.109868550127526, "percentage": 4.67, "elapsed_time": "0:09:14", "remaining_time": "3:08:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 1.0285, "accuracy": 0.1875, "learning_rate": 4.964990092676263e-06, "epoch": 0.12556405728860115, "percentage": 5.33, "elapsed_time": "0:10:31", "remaining_time": "3:06:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 1.03, "accuracy": 0.22499999403953552, "learning_rate": 4.9557181268217225e-06, "epoch": 0.14125956444967627, "percentage": 6.0, "elapsed_time": "0:11:44", "remaining_time": "3:03:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 1.0309, "accuracy": 0.26249998807907104, "learning_rate": 4.9453690018345144e-06, "epoch": 0.15695507161075142, "percentage": 6.67, "elapsed_time": "0:13:01", "remaining_time": "3:02:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 1.020836353302002, "epoch": 0.15695507161075142, "percentage": 6.67, "elapsed_time": "0:13:16", "remaining_time": "3:05:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 1.0388, "accuracy": 0.30000001192092896, "learning_rate": 4.933947257182901e-06, "epoch": 0.17265057877182657, "percentage": 7.33, "elapsed_time": "0:14:38", "remaining_time": "3:04:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 1.0247, "accuracy": 0.25, "learning_rate": 4.921457902821578e-06, "epoch": 0.1883460859329017, "percentage": 8.0, "elapsed_time": "0:15:56", "remaining_time": "3:03:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 1.0169, "accuracy": 0.30000001192092896, "learning_rate": 4.907906416994146e-06, "epoch": 0.20404159309397685, "percentage": 8.67, "elapsed_time": "0:17:11", "remaining_time": "3:01:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9964, "accuracy": 0.3499999940395355, "learning_rate": 4.893298743830168e-06, "epoch": 0.219737100255052, "percentage": 9.33, "elapsed_time": "0:18:27", "remaining_time": "2:59:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 1.0073, "accuracy": 0.30000001192092896, "learning_rate": 4.8776412907378845e-06, "epoch": 0.23543260741612712, "percentage": 10.0, "elapsed_time": "0:19:45", "remaining_time": "2:57:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9802881479263306, "epoch": 0.23543260741612712, "percentage": 10.0, "elapsed_time": "0:19:59", "remaining_time": "2:59:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9795, "accuracy": 0.4124999940395355, "learning_rate": 4.860940925593703e-06, "epoch": 0.2511281145772023, "percentage": 10.67, "elapsed_time": "0:21:24", "remaining_time": "2:59:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.9694, "accuracy": 0.44999998807907104, "learning_rate": 4.84320497372973e-06, "epoch": 0.2668236217382774, "percentage": 11.33, "elapsed_time": "0:22:40", "remaining_time": "2:57:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.9488, "accuracy": 0.4625000059604645, "learning_rate": 4.824441214720629e-06, "epoch": 0.28251912889935255, "percentage": 12.0, "elapsed_time": "0:23:58", "remaining_time": "2:55:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9423, "accuracy": 0.512499988079071, "learning_rate": 4.804657878971252e-06, "epoch": 0.2982146360604277, "percentage": 12.67, "elapsed_time": "0:25:14", "remaining_time": "2:53:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.939, "accuracy": 0.42500001192092896, "learning_rate": 4.783863644106502e-06, "epoch": 0.31391014322150285, "percentage": 13.33, "elapsed_time": "0:26:28", "remaining_time": "2:52:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.9303967356681824, "epoch": 0.31391014322150285, "percentage": 13.33, "elapsed_time": "0:26:43", "remaining_time": "2:53:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.9107, "accuracy": 0.4749999940395355, "learning_rate": 4.762067631165049e-06, "epoch": 0.329605650382578, "percentage": 14.0, "elapsed_time": "0:28:07", "remaining_time": "2:52:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.9094, "accuracy": 0.5249999761581421, "learning_rate": 4.7392794005985324e-06, "epoch": 0.34530115754365315, "percentage": 14.67, "elapsed_time": "0:29:26", "remaining_time": "2:51:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.8871, "accuracy": 0.5249999761581421, "learning_rate": 4.715508948078037e-06, "epoch": 0.3609966647047283, "percentage": 15.33, "elapsed_time": "0:30:43", "remaining_time": "2:49:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.9037, "accuracy": 0.6000000238418579, "learning_rate": 4.690766700109659e-06, "epoch": 0.3766921718658034, "percentage": 16.0, "elapsed_time": "0:32:00", "remaining_time": "2:48:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.8606, "accuracy": 0.4375, "learning_rate": 4.665063509461098e-06, "epoch": 0.39238767902687854, "percentage": 16.67, "elapsed_time": "0:33:18", "remaining_time": "2:46:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8168494701385498, "epoch": 0.39238767902687854, "percentage": 16.67, "elapsed_time": "0:33:33", "remaining_time": "2:47:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.8138, "accuracy": 0.44999998807907104, "learning_rate": 4.638410650401267e-06, "epoch": 0.4080831861879537, "percentage": 17.33, "elapsed_time": "0:34:55", "remaining_time": "2:46:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7318, "accuracy": 0.512499988079071, "learning_rate": 4.610819813755038e-06, "epoch": 0.42377869334902885, "percentage": 18.0, "elapsed_time": "0:36:11", "remaining_time": "2:44:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7599, "accuracy": 0.6625000238418579, "learning_rate": 4.582303101775249e-06, "epoch": 0.439474200510104, "percentage": 18.67, "elapsed_time": "0:37:29", "remaining_time": "2:43:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.7336, "accuracy": 0.675000011920929, "learning_rate": 4.55287302283426e-06, "epoch": 0.45516970767117915, "percentage": 19.33, "elapsed_time": "0:38:45", "remaining_time": "2:41:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.6861, "accuracy": 0.75, "learning_rate": 4.522542485937369e-06, "epoch": 0.47086521483225424, "percentage": 20.0, "elapsed_time": "0:40:02", "remaining_time": "2:40:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.7583853602409363, "epoch": 0.47086521483225424, "percentage": 20.0, "elapsed_time": "0:40:17", "remaining_time": "2:41:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.7163, "accuracy": 0.6875, "learning_rate": 4.491324795060491e-06, "epoch": 0.4865607219933294, "percentage": 20.67, "elapsed_time": "0:41:37", "remaining_time": "2:39:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.6894, "accuracy": 0.675000011920929, "learning_rate": 4.4592336433146e-06, "epoch": 0.5022562291544046, "percentage": 21.33, "elapsed_time": "0:42:55", "remaining_time": "2:38:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.6607, "accuracy": 0.7875000238418579, "learning_rate": 4.426283106939474e-06, "epoch": 0.5179517363154797, "percentage": 22.0, "elapsed_time": "0:44:12", "remaining_time": "2:36:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.6381, "accuracy": 0.8500000238418579, "learning_rate": 4.3924876391293915e-06, "epoch": 0.5336472434765548, "percentage": 22.67, "elapsed_time": "0:45:32", "remaining_time": "2:35:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.5752, "accuracy": 0.862500011920929, "learning_rate": 4.357862063693486e-06, "epoch": 0.5493427506376299, "percentage": 23.33, "elapsed_time": "0:46:44", "remaining_time": "2:33:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5928590893745422, "epoch": 0.5493427506376299, "percentage": 23.33, "elapsed_time": "0:46:59", "remaining_time": "2:34:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.5275, "accuracy": 0.8125, "learning_rate": 4.322421568553529e-06, "epoch": 0.5650382577987051, "percentage": 24.0, "elapsed_time": "0:48:22", "remaining_time": "2:33:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.5113, "accuracy": 0.887499988079071, "learning_rate": 4.286181699082008e-06, "epoch": 0.5807337649597802, "percentage": 24.67, "elapsed_time": "0:49:38", "remaining_time": "2:31:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4862, "accuracy": 0.887499988079071, "learning_rate": 4.249158351283414e-06, "epoch": 0.5964292721208554, "percentage": 25.33, "elapsed_time": "0:50:59", "remaining_time": "2:30:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.5117, "accuracy": 0.8500000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.6121247792819305, "percentage": 26.0, "elapsed_time": "0:52:15", "remaining_time": "2:28:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.5182, "accuracy": 0.762499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.6278202864430057, "percentage": 26.67, "elapsed_time": "0:53:28", "remaining_time": "2:27:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.48699691891670227, "epoch": 0.6278202864430057, "percentage": 26.67, "elapsed_time": "0:53:43", "remaining_time": "2:27:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.5107, "accuracy": 0.800000011920929, "learning_rate": 4.133551509975264e-06, "epoch": 0.6435157936040808, "percentage": 27.33, "elapsed_time": "0:55:01", "remaining_time": "2:26:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.41, "accuracy": 0.8999999761581421, "learning_rate": 4.093559974371725e-06, "epoch": 0.659211300765156, "percentage": 28.0, "elapsed_time": "0:56:18", "remaining_time": "2:24:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.4122, "accuracy": 0.862500011920929, "learning_rate": 4.052869450695776e-06, "epoch": 0.6749068079262311, "percentage": 28.67, "elapsed_time": "0:57:32", "remaining_time": "2:23:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.4397, "accuracy": 0.8125, "learning_rate": 4.011497787155938e-06, "epoch": 0.6906023150873063, "percentage": 29.33, "elapsed_time": "0:58:47", "remaining_time": "2:21:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.444, "accuracy": 0.862500011920929, "learning_rate": 3.969463130731183e-06, "epoch": 0.7062978222483814, "percentage": 30.0, "elapsed_time": "1:00:02", "remaining_time": "2:20:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.435256689786911, "epoch": 0.7062978222483814, "percentage": 30.0, "elapsed_time": "1:00:17", "remaining_time": "2:20:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.3858, "accuracy": 0.925000011920929, "learning_rate": 3.92678391921108e-06, "epoch": 0.7219933294094566, "percentage": 30.67, "elapsed_time": "1:01:38", "remaining_time": "2:19:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.363, "accuracy": 0.862500011920929, "learning_rate": 3.88347887310836e-06, "epoch": 0.7376888365705316, "percentage": 31.33, "elapsed_time": "1:02:51", "remaining_time": "2:17:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3274, "accuracy": 0.925000011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.7533843437316068, "percentage": 32.0, "elapsed_time": "1:04:07", "remaining_time": "2:16:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3822, "accuracy": 0.9125000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.7690798508926819, "percentage": 32.67, "elapsed_time": "1:05:25", "remaining_time": "2:14:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.352, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:06:40", "remaining_time": "2:13:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3888731002807617, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:06:55", "remaining_time": "2:13:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.4009, "accuracy": 0.8500000238418579, "learning_rate": 3.7043841852542884e-06, "epoch": 0.8004708652148322, "percentage": 34.0, "elapsed_time": "1:08:19", "remaining_time": "2:12:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3327, "accuracy": 0.9125000238418579, "learning_rate": 3.658240087799655e-06, "epoch": 0.8161663723759074, "percentage": 34.67, "elapsed_time": "1:09:33", "remaining_time": "2:11:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.3255, "accuracy": 0.8999999761581421, "learning_rate": 3.611587947962319e-06, "epoch": 0.8318618795369825, "percentage": 35.33, "elapsed_time": "1:10:50", "remaining_time": "2:09:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.2941, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.8475573866980577, "percentage": 36.0, "elapsed_time": "1:12:05", "remaining_time": "2:08:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.3906, "accuracy": 0.8999999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:20", "remaining_time": "2:06:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.3577499985694885, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:34", "remaining_time": "2:07:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.3692, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.878948401020208, "percentage": 37.33, "elapsed_time": "1:15:00", "remaining_time": "2:05:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.3487, "accuracy": 0.9375, "learning_rate": 3.4203113817116955e-06, "epoch": 0.8946439081812831, "percentage": 38.0, "elapsed_time": "1:16:17", "remaining_time": "2:04:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.3717, "accuracy": 0.8500000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.9103394153423583, "percentage": 38.67, "elapsed_time": "1:17:30", "remaining_time": "2:02:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.3553, "accuracy": 0.887499988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.9260349225034334, "percentage": 39.33, "elapsed_time": "1:18:48", "remaining_time": "2:01:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.3086, "accuracy": 0.875, "learning_rate": 3.272542485937369e-06, "epoch": 0.9417304296645085, "percentage": 40.0, "elapsed_time": "1:20:08", "remaining_time": "2:00:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.33698391914367676, "epoch": 0.9417304296645085, "percentage": 40.0, "elapsed_time": "1:20:22", "remaining_time": "2:00:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.2886, "accuracy": 0.8999999761581421, "learning_rate": 3.222579492361179e-06, "epoch": 0.9574259368255836, "percentage": 40.67, "elapsed_time": "1:21:44", "remaining_time": "1:59:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.294, "accuracy": 0.8999999761581421, "learning_rate": 3.1722995515381644e-06, "epoch": 0.9731214439866588, "percentage": 41.33, "elapsed_time": "1:23:04", "remaining_time": "1:57:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2579, "accuracy": 0.9624999761581421, "learning_rate": 3.121724717912138e-06, "epoch": 0.9888169511477339, "percentage": 42.0, "elapsed_time": "1:24:19", "remaining_time": "1:56:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2449, "accuracy": 0.931506872177124, "learning_rate": 3.0708771752766397e-06, "epoch": 1.003139101432215, "percentage": 42.67, "elapsed_time": "1:25:29", "remaining_time": "1:54:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2976, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 1.0188346085932902, "percentage": 43.33, "elapsed_time": "1:26:48", "remaining_time": "1:53:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.31872284412384033, "epoch": 1.0188346085932902, "percentage": 43.33, "elapsed_time": "1:27:02", "remaining_time": "1:53:50", "throughput": "0.00", "total_tokens": 0} | |