| {"current_steps": 10, "total_steps": 1500, "loss": 0.952, "accuracy": 0.4375, "learning_rate": 4.999451708687114e-06, "epoch": 0.010660980810234541, "percentage": 0.67, "elapsed_time": "0:01:16", "remaining_time": "3:10:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9726, "accuracy": 0.4124999940395355, "learning_rate": 4.997807075247147e-06, "epoch": 0.021321961620469083, "percentage": 1.33, "elapsed_time": "0:02:35", "remaining_time": "3:11:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9622, "accuracy": 0.5, "learning_rate": 4.9950668210706795e-06, "epoch": 0.031982942430703626, "percentage": 2.0, "elapsed_time": "0:03:53", "remaining_time": "3:10:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9403, "accuracy": 0.4000000059604645, "learning_rate": 4.9912321481237616e-06, "epoch": 0.042643923240938165, "percentage": 2.67, "elapsed_time": "0:05:07", "remaining_time": "3:06:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9588, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:25", "remaining_time": "3:06:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9551004767417908, "epoch": 0.053304904051172705, "percentage": 3.33, "elapsed_time": "0:06:46", "remaining_time": "3:16:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9636, "accuracy": 0.4625000059604645, "learning_rate": 4.980286753286196e-06, "epoch": 0.06396588486140725, "percentage": 4.0, "elapsed_time": "0:08:09", "remaining_time": "3:15:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9677, "accuracy": 0.36250001192092896, "learning_rate": 4.973180832407471e-06, "epoch": 0.07462686567164178, "percentage": 4.67, "elapsed_time": "0:09:28", "remaining_time": "3:13:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9609, "accuracy": 0.42500001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.08528784648187633, "percentage": 5.33, "elapsed_time": "0:10:43", "remaining_time": "3:10:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9587, "accuracy": 0.4749999940395355, "learning_rate": 4.9557181268217225e-06, "epoch": 0.09594882729211088, "percentage": 6.0, "elapsed_time": "0:11:56", "remaining_time": "3:07:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9548, "accuracy": 0.5625, "learning_rate": 4.9453690018345144e-06, "epoch": 0.10660980810234541, "percentage": 6.67, "elapsed_time": "0:13:12", "remaining_time": "3:05:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.947841465473175, "epoch": 0.10660980810234541, "percentage": 6.67, "elapsed_time": "0:13:34", "remaining_time": "3:10:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.9487, "accuracy": 0.550000011920929, "learning_rate": 4.933947257182901e-06, "epoch": 0.11727078891257996, "percentage": 7.33, "elapsed_time": "0:14:53", "remaining_time": "3:08:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9483, "accuracy": 0.4749999940395355, "learning_rate": 4.921457902821578e-06, "epoch": 0.1279317697228145, "percentage": 8.0, "elapsed_time": "0:16:08", "remaining_time": "3:05:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.957, "accuracy": 0.48750001192092896, "learning_rate": 4.907906416994146e-06, "epoch": 0.13859275053304904, "percentage": 8.67, "elapsed_time": "0:17:27", "remaining_time": "3:04:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9373, "accuracy": 0.42500001192092896, "learning_rate": 4.893298743830168e-06, "epoch": 0.14925373134328357, "percentage": 9.33, "elapsed_time": "0:18:47", "remaining_time": "3:02:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9388, "accuracy": 0.5375000238418579, "learning_rate": 4.8776412907378845e-06, "epoch": 0.15991471215351813, "percentage": 10.0, "elapsed_time": "0:20:03", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9302574396133423, "epoch": 0.15991471215351813, "percentage": 10.0, "elapsed_time": "0:20:25", "remaining_time": "3:03:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9396, "accuracy": 0.512499988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.17057569296375266, "percentage": 10.67, "elapsed_time": "0:21:47", "remaining_time": "3:02:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.9222, "accuracy": 0.5375000238418579, "learning_rate": 4.84320497372973e-06, "epoch": 0.1812366737739872, "percentage": 11.33, "elapsed_time": "0:23:01", "remaining_time": "3:00:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.9052, "accuracy": 0.675000011920929, "learning_rate": 4.824441214720629e-06, "epoch": 0.19189765458422176, "percentage": 12.0, "elapsed_time": "0:24:16", "remaining_time": "2:57:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.8996, "accuracy": 0.6875, "learning_rate": 4.804657878971252e-06, "epoch": 0.2025586353944563, "percentage": 12.67, "elapsed_time": "0:25:34", "remaining_time": "2:56:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.9015, "accuracy": 0.5375000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.21321961620469082, "percentage": 13.33, "elapsed_time": "0:26:50", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8796805143356323, "epoch": 0.21321961620469082, "percentage": 13.33, "elapsed_time": "0:27:12", "remaining_time": "2:56:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8898, "accuracy": 0.4625000059604645, "learning_rate": 4.762067631165049e-06, "epoch": 0.22388059701492538, "percentage": 14.0, "elapsed_time": "0:28:37", "remaining_time": "2:55:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8806, "accuracy": 0.5375000238418579, "learning_rate": 4.7392794005985324e-06, "epoch": 0.2345415778251599, "percentage": 14.67, "elapsed_time": "0:29:52", "remaining_time": "2:53:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.8778, "accuracy": 0.550000011920929, "learning_rate": 4.715508948078037e-06, "epoch": 0.24520255863539445, "percentage": 15.33, "elapsed_time": "0:31:07", "remaining_time": "2:51:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.8551, "accuracy": 0.5874999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.255863539445629, "percentage": 16.0, "elapsed_time": "0:32:19", "remaining_time": "2:49:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.8416, "accuracy": 0.7250000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.26652452025586354, "percentage": 16.67, "elapsed_time": "0:33:34", "remaining_time": "2:47:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8036603331565857, "epoch": 0.26652452025586354, "percentage": 16.67, "elapsed_time": "0:33:56", "remaining_time": "2:49:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.7811, "accuracy": 0.6499999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.2771855010660981, "percentage": 17.33, "elapsed_time": "0:35:19", "remaining_time": "2:48:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7391, "accuracy": 0.5249999761581421, "learning_rate": 4.610819813755038e-06, "epoch": 0.2878464818763326, "percentage": 18.0, "elapsed_time": "0:36:37", "remaining_time": "2:46:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7419, "accuracy": 0.6000000238418579, "learning_rate": 4.582303101775249e-06, "epoch": 0.29850746268656714, "percentage": 18.67, "elapsed_time": "0:37:51", "remaining_time": "2:44:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.7235, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.3091684434968017, "percentage": 19.33, "elapsed_time": "0:39:05", "remaining_time": "2:43:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.7058, "accuracy": 0.637499988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.31982942430703626, "percentage": 20.0, "elapsed_time": "0:40:22", "remaining_time": "2:41:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.6695442199707031, "epoch": 0.31982942430703626, "percentage": 20.0, "elapsed_time": "0:40:43", "remaining_time": "2:42:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.6988, "accuracy": 0.612500011920929, "learning_rate": 4.491324795060491e-06, "epoch": 0.3304904051172708, "percentage": 20.67, "elapsed_time": "0:42:07", "remaining_time": "2:41:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.6811, "accuracy": 0.625, "learning_rate": 4.4592336433146e-06, "epoch": 0.3411513859275053, "percentage": 21.33, "elapsed_time": "0:43:23", "remaining_time": "2:39:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.6614, "accuracy": 0.699999988079071, "learning_rate": 4.426283106939474e-06, "epoch": 0.35181236673773986, "percentage": 22.0, "elapsed_time": "0:44:36", "remaining_time": "2:38:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.6583, "accuracy": 0.574999988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3624733475479744, "percentage": 22.67, "elapsed_time": "0:45:47", "remaining_time": "2:36:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.5911, "accuracy": 0.699999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.373134328358209, "percentage": 23.33, "elapsed_time": "0:47:03", "remaining_time": "2:34:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5961893200874329, "epoch": 0.373134328358209, "percentage": 23.33, "elapsed_time": "0:47:24", "remaining_time": "2:35:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.58, "accuracy": 0.737500011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.3837953091684435, "percentage": 24.0, "elapsed_time": "0:48:48", "remaining_time": "2:34:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.5823, "accuracy": 0.75, "learning_rate": 4.286181699082008e-06, "epoch": 0.39445628997867804, "percentage": 24.67, "elapsed_time": "0:50:05", "remaining_time": "2:32:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.5675, "accuracy": 0.737500011920929, "learning_rate": 4.249158351283414e-06, "epoch": 0.4051172707889126, "percentage": 25.33, "elapsed_time": "0:51:22", "remaining_time": "2:31:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4969, "accuracy": 0.8500000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.4157782515991471, "percentage": 26.0, "elapsed_time": "0:52:40", "remaining_time": "2:29:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.5135, "accuracy": 0.8374999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:53:56", "remaining_time": "2:28:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47455134987831116, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:54:18", "remaining_time": "2:29:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.498, "accuracy": 0.8500000238418579, "learning_rate": 4.133551509975264e-06, "epoch": 0.43710021321961623, "percentage": 27.33, "elapsed_time": "0:55:41", "remaining_time": "2:28:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.4494, "accuracy": 0.862500011920929, "learning_rate": 4.093559974371725e-06, "epoch": 0.44776119402985076, "percentage": 28.0, "elapsed_time": "0:56:57", "remaining_time": "2:26:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.4796, "accuracy": 0.8500000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.4584221748400853, "percentage": 28.67, "elapsed_time": "0:58:11", "remaining_time": "2:24:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.4468, "accuracy": 0.862500011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.4690831556503198, "percentage": 29.33, "elapsed_time": "0:59:26", "remaining_time": "2:23:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.4073, "accuracy": 0.887499988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.47974413646055436, "percentage": 30.0, "elapsed_time": "1:00:40", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.41499289870262146, "epoch": 0.47974413646055436, "percentage": 30.0, "elapsed_time": "1:01:02", "remaining_time": "2:22:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.4004, "accuracy": 0.949999988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.4904051172707889, "percentage": 30.67, "elapsed_time": "1:02:22", "remaining_time": "2:21:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3976, "accuracy": 0.875, "learning_rate": 3.88347887310836e-06, "epoch": 0.5010660980810234, "percentage": 31.33, "elapsed_time": "1:03:38", "remaining_time": "2:19:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3982, "accuracy": 0.8999999761581421, "learning_rate": 3.839566987447492e-06, "epoch": 0.511727078891258, "percentage": 32.0, "elapsed_time": "1:04:49", "remaining_time": "2:17:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3974, "accuracy": 0.9125000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.5223880597014925, "percentage": 32.67, "elapsed_time": "1:06:04", "remaining_time": "2:16:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.367, "accuracy": 0.925000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.5330490405117271, "percentage": 33.33, "elapsed_time": "1:07:22", "remaining_time": "2:14:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.387028306722641, "epoch": 0.5330490405117271, "percentage": 33.33, "elapsed_time": "1:07:43", "remaining_time": "2:15:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.3776, "accuracy": 0.925000011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.5437100213219617, "percentage": 34.0, "elapsed_time": "1:09:03", "remaining_time": "2:14:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3999, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.5543710021321961, "percentage": 34.67, "elapsed_time": "1:10:21", "remaining_time": "2:12:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.3346, "accuracy": 0.9125000238418579, "learning_rate": 3.611587947962319e-06, "epoch": 0.5650319829424307, "percentage": 35.33, "elapsed_time": "1:11:39", "remaining_time": "2:11:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.3675, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.5756929637526652, "percentage": 36.0, "elapsed_time": "1:12:59", "remaining_time": "2:09:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.3921, "accuracy": 0.862500011920929, "learning_rate": 3.516841607689501e-06, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:16", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.35785165429115295, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:38", "remaining_time": "2:08:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.3701, "accuracy": 0.887499988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.5970149253731343, "percentage": 37.33, "elapsed_time": "1:15:56", "remaining_time": "2:07:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.3481, "accuracy": 0.8999999761581421, "learning_rate": 3.4203113817116955e-06, "epoch": 0.6076759061833689, "percentage": 38.0, "elapsed_time": "1:17:14", "remaining_time": "2:06:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.3571, "accuracy": 0.9125000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.6183368869936035, "percentage": 38.67, "elapsed_time": "1:18:27", "remaining_time": "2:04:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.3666, "accuracy": 0.875, "learning_rate": 3.3221666168464584e-06, "epoch": 0.6289978678038379, "percentage": 39.33, "elapsed_time": "1:19:43", "remaining_time": "2:02:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.3017, "accuracy": 0.862500011920929, "learning_rate": 3.272542485937369e-06, "epoch": 0.6396588486140725, "percentage": 40.0, "elapsed_time": "1:20:54", "remaining_time": "2:01:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.3409230411052704, "epoch": 0.6396588486140725, "percentage": 40.0, "elapsed_time": "1:21:16", "remaining_time": "2:01:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.3429, "accuracy": 0.9375, "learning_rate": 3.222579492361179e-06, "epoch": 0.650319829424307, "percentage": 40.67, "elapsed_time": "1:22:40", "remaining_time": "2:00:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.3355, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.6609808102345416, "percentage": 41.33, "elapsed_time": "1:23:54", "remaining_time": "1:59:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.3218, "accuracy": 0.925000011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.6716417910447762, "percentage": 42.0, "elapsed_time": "1:25:12", "remaining_time": "1:57:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2868, "accuracy": 0.925000011920929, "learning_rate": 3.0708771752766397e-06, "epoch": 0.6823027718550106, "percentage": 42.67, "elapsed_time": "1:26:27", "remaining_time": "1:56:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.3491, "accuracy": 0.9375, "learning_rate": 3.019779227044398e-06, "epoch": 0.6929637526652452, "percentage": 43.33, "elapsed_time": "1:27:45", "remaining_time": "1:54:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.31618499755859375, "epoch": 0.6929637526652452, "percentage": 43.33, "elapsed_time": "1:28:06", "remaining_time": "1:55:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.9125000238418579, "learning_rate": 2.9684532864643123e-06, "epoch": 0.7036247334754797, "percentage": 44.0, "elapsed_time": "1:29:29", "remaining_time": "1:53:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2887, "accuracy": 0.9375, "learning_rate": 2.9169218667902562e-06, "epoch": 0.7142857142857143, "percentage": 44.67, "elapsed_time": "1:30:46", "remaining_time": "1:52:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.3319, "accuracy": 0.9624999761581421, "learning_rate": 2.8652075714060296e-06, "epoch": 0.7249466950959488, "percentage": 45.33, "elapsed_time": "1:32:04", "remaining_time": "1:51:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2362, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.7356076759061834, "percentage": 46.0, "elapsed_time": "1:33:21", "remaining_time": "1:49:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.3257, "accuracy": 0.925000011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.746268656716418, "percentage": 46.67, "elapsed_time": "1:34:37", "remaining_time": "1:48:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.3062504529953003, "epoch": 0.746268656716418, "percentage": 46.67, "elapsed_time": "1:34:58", "remaining_time": "1:48:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.3255, "accuracy": 0.8999999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 0.7569296375266524, "percentage": 47.33, "elapsed_time": "1:36:19", "remaining_time": "1:47:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2845, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.767590618336887, "percentage": 48.0, "elapsed_time": "1:37:35", "remaining_time": "1:45:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2696, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.7782515991471215, "percentage": 48.67, "elapsed_time": "1:38:53", "remaining_time": "1:44:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.2622, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.7889125799573561, "percentage": 49.33, "elapsed_time": "1:40:11", "remaining_time": "1:42:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.3243, "accuracy": 0.887499988079071, "learning_rate": 2.5e-06, "epoch": 0.7995735607675906, "percentage": 50.0, "elapsed_time": "1:41:21", "remaining_time": "1:41:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2867603600025177, "epoch": 0.7995735607675906, "percentage": 50.0, "elapsed_time": "1:41:43", "remaining_time": "1:41:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2394, "accuracy": 0.9125000238418579, "learning_rate": 2.447643950291608e-06, "epoch": 0.8102345415778252, "percentage": 50.67, "elapsed_time": "1:43:08", "remaining_time": "1:40:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.3113, "accuracy": 0.925000011920929, "learning_rate": 2.3953108656770018e-06, "epoch": 0.8208955223880597, "percentage": 51.33, "elapsed_time": "1:44:25", "remaining_time": "1:38:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.3043, "accuracy": 0.9125000238418579, "learning_rate": 2.3430237011767166e-06, "epoch": 0.8315565031982942, "percentage": 52.0, "elapsed_time": "1:45:44", "remaining_time": "1:37:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.2825, "accuracy": 0.9375, "learning_rate": 2.290805391669212e-06, "epoch": 0.8422174840085288, "percentage": 52.67, "elapsed_time": "1:46:59", "remaining_time": "1:36:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.3094, "accuracy": 0.949999988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.8528784648187633, "percentage": 53.33, "elapsed_time": "1:48:15", "remaining_time": "1:34:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.27349653840065, "epoch": 0.8528784648187633, "percentage": 53.33, "elapsed_time": "1:48:36", "remaining_time": "1:35:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2923, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.8635394456289979, "percentage": 54.0, "elapsed_time": "1:49:58", "remaining_time": "1:33:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.2767, "accuracy": 0.862500011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.8742004264392325, "percentage": 54.67, "elapsed_time": "1:51:16", "remaining_time": "1:32:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2587, "accuracy": 0.8999999761581421, "learning_rate": 2.0830781332097446e-06, "epoch": 0.8848614072494669, "percentage": 55.33, "elapsed_time": "1:52:32", "remaining_time": "1:30:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.2985, "accuracy": 0.9750000238418579, "learning_rate": 2.031546713535688e-06, "epoch": 0.8955223880597015, "percentage": 56.0, "elapsed_time": "1:53:49", "remaining_time": "1:29:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.278, "accuracy": 0.949999988079071, "learning_rate": 1.9802207729556023e-06, "epoch": 0.906183368869936, "percentage": 56.67, "elapsed_time": "1:55:03", "remaining_time": "1:27:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2656216025352478, "epoch": 0.906183368869936, "percentage": 56.67, "elapsed_time": "1:55:24", "remaining_time": "1:28:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.252, "accuracy": 0.9624999761581421, "learning_rate": 1.9291228247233607e-06, "epoch": 0.9168443496801706, "percentage": 57.33, "elapsed_time": "1:56:47", "remaining_time": "1:26:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.3087, "accuracy": 0.9125000238418579, "learning_rate": 1.8782752820878636e-06, "epoch": 0.9275053304904051, "percentage": 58.0, "elapsed_time": "1:58:07", "remaining_time": "1:25:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.2733, "accuracy": 0.9375, "learning_rate": 1.827700448461836e-06, "epoch": 0.9381663113006397, "percentage": 58.67, "elapsed_time": "1:59:26", "remaining_time": "1:24:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.2365, "accuracy": 0.925000011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 0.9488272921108742, "percentage": 59.33, "elapsed_time": "2:00:44", "remaining_time": "1:22:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.2397, "accuracy": 0.8999999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 0.9594882729211087, "percentage": 60.0, "elapsed_time": "2:02:02", "remaining_time": "1:21:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2578875720500946, "epoch": 0.9594882729211087, "percentage": 60.0, "elapsed_time": "2:02:23", "remaining_time": "1:21:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.2498, "accuracy": 0.925000011920929, "learning_rate": 1.677833383153542e-06, "epoch": 0.9701492537313433, "percentage": 60.67, "elapsed_time": "2:03:42", "remaining_time": "1:20:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.243, "accuracy": 0.875, "learning_rate": 1.6285698816954626e-06, "epoch": 0.9808102345415778, "percentage": 61.33, "elapsed_time": "2:04:56", "remaining_time": "1:18:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.2851, "accuracy": 0.925000011920929, "learning_rate": 1.5796886182883053e-06, "epoch": 0.9914712153518124, "percentage": 62.0, "elapsed_time": "2:06:14", "remaining_time": "1:17:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.2524, "accuracy": 0.9125000238418579, "learning_rate": 1.5312110338697427e-06, "epoch": 1.0021321961620469, "percentage": 62.67, "elapsed_time": "2:07:31", "remaining_time": "1:15:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.2788, "accuracy": 0.925000011920929, "learning_rate": 1.4831583923105e-06, "epoch": 1.0127931769722816, "percentage": 63.33, "elapsed_time": "2:08:46", "remaining_time": "1:14:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2563049793243408, "epoch": 1.0127931769722816, "percentage": 63.33, "elapsed_time": "2:09:08", "remaining_time": "1:14:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.2394, "accuracy": 0.887499988079071, "learning_rate": 1.4355517710873184e-06, "epoch": 1.023454157782516, "percentage": 64.0, "elapsed_time": "2:10:31", "remaining_time": "1:13:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.2419, "accuracy": 0.949999988079071, "learning_rate": 1.388412052037682e-06, "epoch": 1.0341151385927505, "percentage": 64.67, "elapsed_time": "2:11:50", "remaining_time": "1:12:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.275, "accuracy": 0.925000011920929, "learning_rate": 1.3417599122003464e-06, "epoch": 1.044776119402985, "percentage": 65.33, "elapsed_time": "2:13:05", "remaining_time": "1:10:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.2523, "accuracy": 0.925000011920929, "learning_rate": 1.2956158147457116e-06, "epoch": 1.0554371002132197, "percentage": 66.0, "elapsed_time": "2:14:19", "remaining_time": "1:09:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.281, "accuracy": 0.9750000238418579, "learning_rate": 1.2500000000000007e-06, "epoch": 1.0660980810234542, "percentage": 66.67, "elapsed_time": "2:15:33", "remaining_time": "1:07:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.257539838552475, "epoch": 1.0660980810234542, "percentage": 66.67, "elapsed_time": "2:15:55", "remaining_time": "1:07:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.2471, "accuracy": 0.9125000238418579, "learning_rate": 1.204932476567175e-06, "epoch": 1.0767590618336886, "percentage": 67.33, "elapsed_time": "2:17:16", "remaining_time": "1:06:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.2664, "accuracy": 0.925000011920929, "learning_rate": 1.160433012552508e-06, "epoch": 1.0874200426439233, "percentage": 68.0, "elapsed_time": "2:18:33", "remaining_time": "1:05:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.237, "accuracy": 0.925000011920929, "learning_rate": 1.11652112689164e-06, "epoch": 1.0980810234541578, "percentage": 68.67, "elapsed_time": "2:19:48", "remaining_time": "1:03:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.2152, "accuracy": 0.8999999761581421, "learning_rate": 1.073216080788921e-06, "epoch": 1.1087420042643923, "percentage": 69.33, "elapsed_time": "2:21:07", "remaining_time": "1:02:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.2337, "accuracy": 0.887499988079071, "learning_rate": 1.0305368692688175e-06, "epoch": 1.1194029850746268, "percentage": 70.0, "elapsed_time": "2:22:24", "remaining_time": "1:01:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.24803213775157928, "epoch": 1.1194029850746268, "percentage": 70.0, "elapsed_time": "2:22:46", "remaining_time": "1:01:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.226, "accuracy": 0.9750000238418579, "learning_rate": 9.88502212844063e-07, "epoch": 1.1300639658848615, "percentage": 70.67, "elapsed_time": "2:24:10", "remaining_time": "0:59:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.2819, "accuracy": 0.8999999761581421, "learning_rate": 9.471305493042243e-07, "epoch": 1.140724946695096, "percentage": 71.33, "elapsed_time": "2:25:29", "remaining_time": "0:58:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.2449, "accuracy": 0.9624999761581421, "learning_rate": 9.064400256282757e-07, "epoch": 1.1513859275053304, "percentage": 72.0, "elapsed_time": "2:26:45", "remaining_time": "0:57:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.2137, "accuracy": 0.9125000238418579, "learning_rate": 8.664484900247363e-07, "epoch": 1.1620469083155651, "percentage": 72.67, "elapsed_time": "2:28:01", "remaining_time": "0:55:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.2413, "accuracy": 0.9375, "learning_rate": 8.271734841028553e-07, "epoch": 1.1727078891257996, "percentage": 73.33, "elapsed_time": "2:29:18", "remaining_time": "0:54:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.24271255731582642, "epoch": 1.1727078891257996, "percentage": 73.33, "elapsed_time": "2:29:39", "remaining_time": "0:54:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.2099, "accuracy": 0.9375, "learning_rate": 7.886322351782782e-07, "epoch": 1.183368869936034, "percentage": 74.0, "elapsed_time": "2:31:04", "remaining_time": "0:53:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.2527, "accuracy": 0.9125000238418579, "learning_rate": 7.508416487165862e-07, "epoch": 1.1940298507462686, "percentage": 74.67, "elapsed_time": "2:32:20", "remaining_time": "0:51:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.2229, "accuracy": 0.9125000238418579, "learning_rate": 7.138183009179922e-07, "epoch": 1.2046908315565032, "percentage": 75.33, "elapsed_time": "2:33:36", "remaining_time": "0:50:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.887499988079071, "learning_rate": 6.775784314464717e-07, "epoch": 1.2153518123667377, "percentage": 76.0, "elapsed_time": "2:34:55", "remaining_time": "0:48:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.2625, "accuracy": 0.949999988079071, "learning_rate": 6.421379363065142e-07, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:13", "remaining_time": "0:47:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.23817622661590576, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:34", "remaining_time": "0:47:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.2479, "accuracy": 0.9125000238418579, "learning_rate": 6.075123608706093e-07, "epoch": 1.236673773987207, "percentage": 77.33, "elapsed_time": "2:37:55", "remaining_time": "0:46:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.2096, "accuracy": 0.9125000238418579, "learning_rate": 5.737168930605272e-07, "epoch": 1.2473347547974414, "percentage": 78.0, "elapsed_time": "2:39:11", "remaining_time": "0:44:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.2542, "accuracy": 0.925000011920929, "learning_rate": 5.407663566854008e-07, "epoch": 1.2579957356076759, "percentage": 78.67, "elapsed_time": "2:40:28", "remaining_time": "0:43:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.26, "accuracy": 0.9624999761581421, "learning_rate": 5.086752049395094e-07, "epoch": 1.2686567164179103, "percentage": 79.33, "elapsed_time": "2:41:42", "remaining_time": "0:42:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.2364, "accuracy": 0.9125000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.279317697228145, "percentage": 80.0, "elapsed_time": "2:42:56", "remaining_time": "0:40:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.23450209200382233, "epoch": 1.279317697228145, "percentage": 80.0, "elapsed_time": "2:43:17", "remaining_time": "0:40:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.2392, "accuracy": 0.9624999761581421, "learning_rate": 4.4712697716573994e-07, "epoch": 1.2899786780383795, "percentage": 80.67, "elapsed_time": "2:44:43", "remaining_time": "0:39:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.2178, "accuracy": 0.9624999761581421, "learning_rate": 4.1769689822475147e-07, "epoch": 1.3006396588486142, "percentage": 81.33, "elapsed_time": "2:45:59", "remaining_time": "0:38:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.2408, "accuracy": 0.9375, "learning_rate": 3.891801862449629e-07, "epoch": 1.3113006396588487, "percentage": 82.0, "elapsed_time": "2:47:13", "remaining_time": "0:36:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.2236, "accuracy": 0.9375, "learning_rate": 3.615893495987335e-07, "epoch": 1.3219616204690832, "percentage": 82.67, "elapsed_time": "2:48:30", "remaining_time": "0:35:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.234, "accuracy": 0.9125000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.3326226012793176, "percentage": 83.33, "elapsed_time": "2:49:48", "remaining_time": "0:33:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.23487773537635803, "epoch": 1.3326226012793176, "percentage": 83.33, "elapsed_time": "2:50:09", "remaining_time": "0:34:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 0.2243, "accuracy": 0.875, "learning_rate": 3.092332998903416e-07, "epoch": 1.3432835820895521, "percentage": 84.0, "elapsed_time": "2:51:33", "remaining_time": "0:32:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.2266, "accuracy": 0.949999988079071, "learning_rate": 2.844910519219632e-07, "epoch": 1.3539445628997868, "percentage": 84.67, "elapsed_time": "2:52:48", "remaining_time": "0:31:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.2063, "accuracy": 0.9750000238418579, "learning_rate": 2.6072059940146775e-07, "epoch": 1.3646055437100213, "percentage": 85.33, "elapsed_time": "2:54:09", "remaining_time": "0:29:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 0.2538, "accuracy": 0.9624999761581421, "learning_rate": 2.3793236883495164e-07, "epoch": 1.375266524520256, "percentage": 86.0, "elapsed_time": "2:55:27", "remaining_time": "0:28:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.2363, "accuracy": 0.949999988079071, "learning_rate": 2.1613635589349756e-07, "epoch": 1.3859275053304905, "percentage": 86.67, "elapsed_time": "2:56:43", "remaining_time": "0:27:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.2328612357378006, "epoch": 1.3859275053304905, "percentage": 86.67, "elapsed_time": "2:57:04", "remaining_time": "0:27:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.2443, "accuracy": 0.862500011920929, "learning_rate": 1.95342121028749e-07, "epoch": 1.396588486140725, "percentage": 87.33, "elapsed_time": "2:58:24", "remaining_time": "0:25:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.1976, "accuracy": 0.949999988079071, "learning_rate": 1.7555878527937164e-07, "epoch": 1.4072494669509594, "percentage": 88.0, "elapsed_time": "2:59:37", "remaining_time": "0:24:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.2462, "accuracy": 0.949999988079071, "learning_rate": 1.567950262702714e-07, "epoch": 1.417910447761194, "percentage": 88.67, "elapsed_time": "3:00:51", "remaining_time": "0:23:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 0.2305, "accuracy": 0.8999999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.4285714285714286, "percentage": 89.33, "elapsed_time": "3:02:04", "remaining_time": "0:21:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.2559, "accuracy": 0.887499988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.439232409381663, "percentage": 90.0, "elapsed_time": "3:03:24", "remaining_time": "0:20:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.2323991060256958, "epoch": 1.439232409381663, "percentage": 90.0, "elapsed_time": "3:03:45", "remaining_time": "0:20:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.2207, "accuracy": 0.887499988079071, "learning_rate": 1.067012561698319e-07, "epoch": 1.4498933901918978, "percentage": 90.67, "elapsed_time": "3:05:06", "remaining_time": "0:19:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.2425, "accuracy": 0.949999988079071, "learning_rate": 9.209358300585474e-08, "epoch": 1.4605543710021323, "percentage": 91.33, "elapsed_time": "3:06:20", "remaining_time": "0:17:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.2071, "accuracy": 0.8999999761581421, "learning_rate": 7.854209717842231e-08, "epoch": 1.4712153518123667, "percentage": 92.0, "elapsed_time": "3:07:33", "remaining_time": "0:16:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 0.2444, "accuracy": 0.9375, "learning_rate": 6.605274281709929e-08, "epoch": 1.4818763326226012, "percentage": 92.67, "elapsed_time": "3:08:47", "remaining_time": "0:14:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.2212, "accuracy": 0.949999988079071, "learning_rate": 5.463099816548578e-08, "epoch": 1.4925373134328357, "percentage": 93.33, "elapsed_time": "3:10:01", "remaining_time": "0:13:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.23210352659225464, "epoch": 1.4925373134328357, "percentage": 93.33, "elapsed_time": "3:10:23", "remaining_time": "0:13:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.252, "accuracy": 0.8999999761581421, "learning_rate": 4.428187317827848e-08, "epoch": 1.5031982942430704, "percentage": 94.0, "elapsed_time": "3:11:45", "remaining_time": "0:12:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.2341, "accuracy": 0.887499988079071, "learning_rate": 3.5009907323737826e-08, "epoch": 1.5138592750533049, "percentage": 94.67, "elapsed_time": "3:13:02", "remaining_time": "0:10:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.2172, "accuracy": 0.949999988079071, "learning_rate": 2.681916759252917e-08, "epoch": 1.5245202558635396, "percentage": 95.33, "elapsed_time": "3:14:19", "remaining_time": "0:09:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.2221, "accuracy": 0.9375, "learning_rate": 1.9713246713805588e-08, "epoch": 1.535181236673774, "percentage": 96.0, "elapsed_time": "3:15:36", "remaining_time": "0:08:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.2011, "accuracy": 0.9750000238418579, "learning_rate": 1.3695261579316776e-08, "epoch": 1.5458422174840085, "percentage": 96.67, "elapsed_time": "3:16:49", "remaining_time": "0:06:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.23077060282230377, "epoch": 1.5458422174840085, "percentage": 96.67, "elapsed_time": "3:17:11", "remaining_time": "0:06:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.2664, "accuracy": 0.925000011920929, "learning_rate": 8.767851876239075e-09, "epoch": 1.556503198294243, "percentage": 97.33, "elapsed_time": "3:18:32", "remaining_time": "0:05:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.27, "accuracy": 0.887499988079071, "learning_rate": 4.933178929321103e-09, "epoch": 1.5671641791044775, "percentage": 98.0, "elapsed_time": "3:19:53", "remaining_time": "0:04:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.2171, "accuracy": 0.9624999761581421, "learning_rate": 2.192924752854042e-09, "epoch": 1.5778251599147122, "percentage": 98.67, "elapsed_time": "3:21:04", "remaining_time": "0:02:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.2333, "accuracy": 0.9375, "learning_rate": 5.48291312886251e-10, "epoch": 1.5884861407249466, "percentage": 99.33, "elapsed_time": "3:22:21", "remaining_time": "0:01:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.263, "accuracy": 0.887499988079071, "learning_rate": 0.0, "epoch": 1.5991471215351813, "percentage": 100.0, "elapsed_time": "3:23:39", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.2312908172607422, "epoch": 1.5991471215351813, "percentage": 100.0, "elapsed_time": "3:24:01", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 1.5991471215351813, "percentage": 100.0, "elapsed_time": "3:24:08", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |