| {"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} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.3013, "accuracy": 0.887499988079071, "learning_rate": 2.9684532864643123e-06, "epoch": 1.0345301157543654, "percentage": 44.0, "elapsed_time": "1:28:29", "remaining_time": "1:52:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2677, "accuracy": 0.8999999761581421, "learning_rate": 2.9169218667902562e-06, "epoch": 1.0502256229154405, "percentage": 44.67, "elapsed_time": "1:29:46", "remaining_time": "1:51:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.2321, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 1.0659211300765157, "percentage": 45.33, "elapsed_time": "1:31:03", "remaining_time": "1:49:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2593, "accuracy": 0.9125000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 1.0816166372375908, "percentage": 46.0, "elapsed_time": "1:32:21", "remaining_time": "1:48:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.263, "accuracy": 0.9375, "learning_rate": 2.761321158169134e-06, "epoch": 1.097312144398666, "percentage": 46.67, "elapsed_time": "1:33:36", "remaining_time": "1:46:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.3023497760295868, "epoch": 1.097312144398666, "percentage": 46.67, "elapsed_time": "1:33:51", "remaining_time": "1:47:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.2707, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 1.113007651559741, "percentage": 47.33, "elapsed_time": "1:35:14", "remaining_time": "1:45:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2443, "accuracy": 0.9125000238418579, "learning_rate": 2.6569762988232838e-06, "epoch": 1.1287031587208163, "percentage": 48.0, "elapsed_time": "1:36:28", "remaining_time": "1:44:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2657, "accuracy": 0.8999999761581421, "learning_rate": 2.604689134322999e-06, "epoch": 1.1443986658818912, "percentage": 48.67, "elapsed_time": "1:37:44", "remaining_time": "1:43:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.2234, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 1.1600941730429664, "percentage": 49.33, "elapsed_time": "1:38:59", "remaining_time": "1:41:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.2895, "accuracy": 0.887499988079071, "learning_rate": 2.5e-06, "epoch": 1.1757896802040415, "percentage": 50.0, "elapsed_time": "1:40:17", "remaining_time": "1:40:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2885077893733978, "epoch": 1.1757896802040415, "percentage": 50.0, "elapsed_time": "1:40:31", "remaining_time": "1:40:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2696, "accuracy": 0.9624999761581421, "learning_rate": 2.447643950291608e-06, "epoch": 1.1914851873651167, "percentage": 50.67, "elapsed_time": "1:41:55", "remaining_time": "1:39:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.2692, "accuracy": 0.9125000238418579, "learning_rate": 2.3953108656770018e-06, "epoch": 1.2071806945261918, "percentage": 51.33, "elapsed_time": "1:43:09", "remaining_time": "1:37:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.248, "accuracy": 0.9750000238418579, "learning_rate": 2.3430237011767166e-06, "epoch": 1.222876201687267, "percentage": 52.0, "elapsed_time": "1:44:23", "remaining_time": "1:36:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.2549, "accuracy": 1.0, "learning_rate": 2.290805391669212e-06, "epoch": 1.2385717088483421, "percentage": 52.67, "elapsed_time": "1:45:36", "remaining_time": "1:34:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.3082, "accuracy": 0.925000011920929, "learning_rate": 2.238678841830867e-06, "epoch": 1.2542672160094173, "percentage": 53.33, "elapsed_time": "1:46:56", "remaining_time": "1:33:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.27581357955932617, "epoch": 1.2542672160094173, "percentage": 53.33, "elapsed_time": "1:47:10", "remaining_time": "1:33:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2454, "accuracy": 0.9375, "learning_rate": 2.186666916089239e-06, "epoch": 1.2699627231704924, "percentage": 54.0, "elapsed_time": "1:48:30", "remaining_time": "1:32:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.2172, "accuracy": 0.9125000238418579, "learning_rate": 2.134792428593971e-06, "epoch": 1.2856582303315676, "percentage": 54.67, "elapsed_time": "1:49:46", "remaining_time": "1:31:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2231, "accuracy": 0.925000011920929, "learning_rate": 2.0830781332097446e-06, "epoch": 1.3013537374926427, "percentage": 55.33, "elapsed_time": "1:51:01", "remaining_time": "1:29:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.2584, "accuracy": 0.9125000238418579, "learning_rate": 2.031546713535688e-06, "epoch": 1.3170492446537179, "percentage": 56.0, "elapsed_time": "1:52:17", "remaining_time": "1:28:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2242, "accuracy": 0.9125000238418579, "learning_rate": 1.9802207729556023e-06, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:53:35", "remaining_time": "1:26:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2621641755104065, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:53:49", "remaining_time": "1:27:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.2711, "accuracy": 0.9125000238418579, "learning_rate": 1.9291228247233607e-06, "epoch": 1.3484402589758682, "percentage": 57.33, "elapsed_time": "1:55:13", "remaining_time": "1:25:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.2569, "accuracy": 0.9624999761581421, "learning_rate": 1.8782752820878636e-06, "epoch": 1.3641357661369433, "percentage": 58.0, "elapsed_time": "1:56:28", "remaining_time": "1:24:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.2876, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 1.3798312732980185, "percentage": 58.67, "elapsed_time": "1:57:46", "remaining_time": "1:22:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.2502, "accuracy": 0.925000011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 1.3955267804590936, "percentage": 59.33, "elapsed_time": "1:59:02", "remaining_time": "1:21:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.2162, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:00:20", "remaining_time": "1:20:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2529076933860779, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:00:34", "remaining_time": "1:20:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.212, "accuracy": 0.949999988079071, "learning_rate": 1.677833383153542e-06, "epoch": 1.426917794781244, "percentage": 60.67, "elapsed_time": "2:01:54", "remaining_time": "1:19:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.2343, "accuracy": 0.9375, "learning_rate": 1.6285698816954626e-06, "epoch": 1.442613301942319, "percentage": 61.33, "elapsed_time": "2:03:09", "remaining_time": "1:17:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.2487, "accuracy": 0.925000011920929, "learning_rate": 1.5796886182883053e-06, "epoch": 1.4583088091033942, "percentage": 62.0, "elapsed_time": "2:04:26", "remaining_time": "1:16:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.2609, "accuracy": 0.9375, "learning_rate": 1.5312110338697427e-06, "epoch": 1.4740043162644694, "percentage": 62.67, "elapsed_time": "2:05:43", "remaining_time": "1:14:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.2398, "accuracy": 0.8999999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 1.4896998234255445, "percentage": 63.33, "elapsed_time": "2:06:58", "remaining_time": "1:13:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.24798962473869324, "epoch": 1.4896998234255445, "percentage": 63.33, "elapsed_time": "2:07:13", "remaining_time": "1:13:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.1948, "accuracy": 0.8999999761581421, "learning_rate": 1.4355517710873184e-06, "epoch": 1.5053953305866195, "percentage": 64.0, "elapsed_time": "2:08:40", "remaining_time": "1:12:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.1888, "accuracy": 0.987500011920929, "learning_rate": 1.388412052037682e-06, "epoch": 1.5210908377476948, "percentage": 64.67, "elapsed_time": "2:09:54", "remaining_time": "1:10:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.231, "accuracy": 0.925000011920929, "learning_rate": 1.3417599122003464e-06, "epoch": 1.5367863449087698, "percentage": 65.33, "elapsed_time": "2:11:10", "remaining_time": "1:09:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.2265, "accuracy": 0.925000011920929, "learning_rate": 1.2956158147457116e-06, "epoch": 1.5524818520698451, "percentage": 66.0, "elapsed_time": "2:12:23", "remaining_time": "1:08:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.216, "accuracy": 0.9624999761581421, "learning_rate": 1.2500000000000007e-06, "epoch": 1.56817735923092, "percentage": 66.67, "elapsed_time": "2:13:35", "remaining_time": "1:06:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.2481767237186432, "epoch": 1.56817735923092, "percentage": 66.67, "elapsed_time": "2:13:49", "remaining_time": "1:06:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.2443, "accuracy": 0.987500011920929, "learning_rate": 1.204932476567175e-06, "epoch": 1.5838728663919954, "percentage": 67.33, "elapsed_time": "2:15:14", "remaining_time": "1:05:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.2226, "accuracy": 0.949999988079071, "learning_rate": 1.160433012552508e-06, "epoch": 1.5995683735530704, "percentage": 68.0, "elapsed_time": "2:16:32", "remaining_time": "1:04:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.2303, "accuracy": 0.9624999761581421, "learning_rate": 1.11652112689164e-06, "epoch": 1.6152638807141457, "percentage": 68.67, "elapsed_time": "2:17:50", "remaining_time": "1:02:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.2634, "accuracy": 0.9125000238418579, "learning_rate": 1.073216080788921e-06, "epoch": 1.6309593878752207, "percentage": 69.33, "elapsed_time": "2:19:08", "remaining_time": "1:01:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.1713, "accuracy": 0.9375, "learning_rate": 1.0305368692688175e-06, "epoch": 1.6466548950362958, "percentage": 70.0, "elapsed_time": "2:20:28", "remaining_time": "1:00:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.24250496923923492, "epoch": 1.6466548950362958, "percentage": 70.0, "elapsed_time": "2:20:43", "remaining_time": "1:00:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.2143, "accuracy": 0.987500011920929, "learning_rate": 9.88502212844063e-07, "epoch": 1.662350402197371, "percentage": 70.67, "elapsed_time": "2:22:03", "remaining_time": "0:58:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.2361, "accuracy": 0.949999988079071, "learning_rate": 9.471305493042243e-07, "epoch": 1.678045909358446, "percentage": 71.33, "elapsed_time": "2:23:20", "remaining_time": "0:57:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.1957, "accuracy": 0.949999988079071, "learning_rate": 9.064400256282757e-07, "epoch": 1.6937414165195213, "percentage": 72.0, "elapsed_time": "2:24:38", "remaining_time": "0:56:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.186, "accuracy": 0.9375, "learning_rate": 8.664484900247363e-07, "epoch": 1.7094369236805964, "percentage": 72.67, "elapsed_time": "2:25:50", "remaining_time": "0:54:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.2264, "accuracy": 0.9624999761581421, "learning_rate": 8.271734841028553e-07, "epoch": 1.7251324308416716, "percentage": 73.33, "elapsed_time": "2:27:06", "remaining_time": "0:53:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2400711625814438, "epoch": 1.7251324308416716, "percentage": 73.33, "elapsed_time": "2:27:20", "remaining_time": "0:53:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.2786, "accuracy": 0.9375, "learning_rate": 7.886322351782782e-07, "epoch": 1.7408279380027467, "percentage": 74.0, "elapsed_time": "2:28:39", "remaining_time": "0:52:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.1998, "accuracy": 0.9375, "learning_rate": 7.508416487165862e-07, "epoch": 1.7565234451638219, "percentage": 74.67, "elapsed_time": "2:29:53", "remaining_time": "0:50:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.1823, "accuracy": 0.949999988079071, "learning_rate": 7.138183009179922e-07, "epoch": 1.772218952324897, "percentage": 75.33, "elapsed_time": "2:31:10", "remaining_time": "0:49:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.2494, "accuracy": 0.8999999761581421, "learning_rate": 6.775784314464717e-07, "epoch": 1.7879144594859722, "percentage": 76.0, "elapsed_time": "2:32:26", "remaining_time": "0:48:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.2365, "accuracy": 0.9750000238418579, "learning_rate": 6.421379363065142e-07, "epoch": 1.8036099666470473, "percentage": 76.67, "elapsed_time": "2:33:43", "remaining_time": "0:46:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.23765961825847626, "epoch": 1.8036099666470473, "percentage": 76.67, "elapsed_time": "2:33:58", "remaining_time": "0:46:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.2043, "accuracy": 0.949999988079071, "learning_rate": 6.075123608706093e-07, "epoch": 1.8193054738081225, "percentage": 77.33, "elapsed_time": "2:35:22", "remaining_time": "0:45:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.1923, "accuracy": 0.9624999761581421, "learning_rate": 5.737168930605272e-07, "epoch": 1.8350009809691976, "percentage": 78.0, "elapsed_time": "2:36:38", "remaining_time": "0:44:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.2206, "accuracy": 0.987500011920929, "learning_rate": 5.407663566854008e-07, "epoch": 1.8506964881302728, "percentage": 78.67, "elapsed_time": "2:37:55", "remaining_time": "0:42:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.2338, "accuracy": 0.925000011920929, "learning_rate": 5.086752049395094e-07, "epoch": 1.8663919952913477, "percentage": 79.33, "elapsed_time": "2:39:11", "remaining_time": "0:41:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.2028, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 1.882087502452423, "percentage": 80.0, "elapsed_time": "2:40:27", "remaining_time": "0:40:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.23520438373088837, "epoch": 1.882087502452423, "percentage": 80.0, "elapsed_time": "2:40:42", "remaining_time": "0:40:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.2082, "accuracy": 0.9125000238418579, "learning_rate": 4.4712697716573994e-07, "epoch": 1.897783009613498, "percentage": 80.67, "elapsed_time": "2:42:08", "remaining_time": "0:38:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.2287, "accuracy": 0.949999988079071, "learning_rate": 4.1769689822475147e-07, "epoch": 1.9134785167745734, "percentage": 81.33, "elapsed_time": "2:43:24", "remaining_time": "0:37:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.2681, "accuracy": 0.9624999761581421, "learning_rate": 3.891801862449629e-07, "epoch": 1.9291740239356483, "percentage": 82.0, "elapsed_time": "2:44:38", "remaining_time": "0:36:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.213, "accuracy": 0.9624999761581421, "learning_rate": 3.615893495987335e-07, "epoch": 1.9448695310967237, "percentage": 82.67, "elapsed_time": "2:45:54", "remaining_time": "0:34:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.2177, "accuracy": 0.987500011920929, "learning_rate": 3.3493649053890325e-07, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:47:11", "remaining_time": "0:33:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.23355062305927277, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:47:25", "remaining_time": "0:33:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 0.2015, "accuracy": 0.925000011920929, "learning_rate": 3.092332998903416e-07, "epoch": 1.976260545418874, "percentage": 84.0, "elapsed_time": "2:48:49", "remaining_time": "0:32:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.238, "accuracy": 0.9375, "learning_rate": 2.844910519219632e-07, "epoch": 1.991956052579949, "percentage": 84.67, "elapsed_time": "2:50:08", "remaining_time": "0:30:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.1594, "accuracy": 0.9726027250289917, "learning_rate": 2.6072059940146775e-07, "epoch": 2.00627820286443, "percentage": 85.33, "elapsed_time": "2:51:16", "remaining_time": "0:29:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 0.2518, "accuracy": 0.925000011920929, "learning_rate": 2.3793236883495164e-07, "epoch": 2.021973710025505, "percentage": 86.0, "elapsed_time": "2:52:31", "remaining_time": "0:28:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.1959, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 2.0376692171865805, "percentage": 86.67, "elapsed_time": "2:53:51", "remaining_time": "0:26:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.233205184340477, "epoch": 2.0376692171865805, "percentage": 86.67, "elapsed_time": "2:54:05", "remaining_time": "0:26:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.2139, "accuracy": 0.949999988079071, "learning_rate": 1.95342121028749e-07, "epoch": 2.0533647243476554, "percentage": 87.33, "elapsed_time": "2:55:30", "remaining_time": "0:25:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.1976, "accuracy": 0.949999988079071, "learning_rate": 1.7555878527937164e-07, "epoch": 2.0690602315087308, "percentage": 88.0, "elapsed_time": "2:56:46", "remaining_time": "0:24:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.2012, "accuracy": 0.949999988079071, "learning_rate": 1.567950262702714e-07, "epoch": 2.0847557386698057, "percentage": 88.67, "elapsed_time": "2:58:00", "remaining_time": "0:22:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 0.2045, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 2.100451245830881, "percentage": 89.33, "elapsed_time": "2:59:14", "remaining_time": "0:21:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.1997, "accuracy": 0.9750000238418579, "learning_rate": 1.223587092621162e-07, "epoch": 2.116146752991956, "percentage": 90.0, "elapsed_time": "3:00:27", "remaining_time": "0:20:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.22972312569618225, "epoch": 2.116146752991956, "percentage": 90.0, "elapsed_time": "3:00:41", "remaining_time": "0:20:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.2174, "accuracy": 0.9375, "learning_rate": 1.067012561698319e-07, "epoch": 2.1318422601530314, "percentage": 90.67, "elapsed_time": "3:02:04", "remaining_time": "0:18:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.2393, "accuracy": 0.9624999761581421, "learning_rate": 9.209358300585474e-08, "epoch": 2.1475377673141063, "percentage": 91.33, "elapsed_time": "3:03:23", "remaining_time": "0:17:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.1748, "accuracy": 0.9624999761581421, "learning_rate": 7.854209717842231e-08, "epoch": 2.1632332744751817, "percentage": 92.0, "elapsed_time": "3:04:39", "remaining_time": "0:16:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 0.2023, "accuracy": 0.949999988079071, "learning_rate": 6.605274281709929e-08, "epoch": 2.1789287816362566, "percentage": 92.67, "elapsed_time": "3:05:57", "remaining_time": "0:14:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.1709, "accuracy": 0.9750000238418579, "learning_rate": 5.463099816548578e-08, "epoch": 2.194624288797332, "percentage": 93.33, "elapsed_time": "3:07:15", "remaining_time": "0:13:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.23232795298099518, "epoch": 2.194624288797332, "percentage": 93.33, "elapsed_time": "3:07:30", "remaining_time": "0:13:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.1956, "accuracy": 0.987500011920929, "learning_rate": 4.428187317827848e-08, "epoch": 2.210319795958407, "percentage": 94.0, "elapsed_time": "3:08:56", "remaining_time": "0:12:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.1901, "accuracy": 0.949999988079071, "learning_rate": 3.5009907323737826e-08, "epoch": 2.226015303119482, "percentage": 94.67, "elapsed_time": "3:10:13", "remaining_time": "0:10:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.2107, "accuracy": 0.9375, "learning_rate": 2.681916759252917e-08, "epoch": 2.241710810280557, "percentage": 95.33, "elapsed_time": "3:11:30", "remaining_time": "0:09:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.21, "accuracy": 0.9624999761581421, "learning_rate": 1.9713246713805588e-08, "epoch": 2.2574063174416326, "percentage": 96.0, "elapsed_time": "3:12:47", "remaining_time": "0:08:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.1988, "accuracy": 0.949999988079071, "learning_rate": 1.3695261579316776e-08, "epoch": 2.2731018246027075, "percentage": 96.67, "elapsed_time": "3:14:07", "remaining_time": "0:06:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.22916901111602783, "epoch": 2.2731018246027075, "percentage": 96.67, "elapsed_time": "3:14:22", "remaining_time": "0:06:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.2268, "accuracy": 0.949999988079071, "learning_rate": 8.767851876239075e-09, "epoch": 2.2887973317637824, "percentage": 97.33, "elapsed_time": "3:15:42", "remaining_time": "0:05:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.2348, "accuracy": 0.9624999761581421, "learning_rate": 4.933178929321103e-09, "epoch": 2.304492838924858, "percentage": 98.0, "elapsed_time": "3:17:02", "remaining_time": "0:04:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.2136, "accuracy": 0.9125000238418579, "learning_rate": 2.192924752854042e-09, "epoch": 2.3201883460859327, "percentage": 98.67, "elapsed_time": "3:18:18", "remaining_time": "0:02:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.2158, "accuracy": 0.9375, "learning_rate": 5.48291312886251e-10, "epoch": 2.335883853247008, "percentage": 99.33, "elapsed_time": "3:19:37", "remaining_time": "0:01:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.2075, "accuracy": 0.949999988079071, "learning_rate": 0.0, "epoch": 2.351579360408083, "percentage": 100.0, "elapsed_time": "3:20:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.2305595576763153, "epoch": 2.351579360408083, "percentage": 100.0, "elapsed_time": "3:21:11", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 2.351579360408083, "percentage": 100.0, "elapsed_time": "3:21:18", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |