| {"current_steps": 5, "total_steps": 5360, "loss": 13.2168, "lr": 3.7313432835820895e-07, "epoch": 0.009328358208955223, "percentage": 0.09, "elapsed_time": "0:00:00", "remaining_time": "0:17:00", "throughput": 1275.74, "total_tokens": 1216} |
| {"current_steps": 10, "total_steps": 5360, "loss": 13.33, "lr": 8.395522388059702e-07, "epoch": 0.018656716417910446, "percentage": 0.19, "elapsed_time": "0:00:01", "remaining_time": "0:12:25", "throughput": 1814.17, "total_tokens": 2528} |
| {"current_steps": 15, "total_steps": 5360, "loss": 13.2815, "lr": 1.3059701492537314e-06, "epoch": 0.027985074626865673, "percentage": 0.28, "elapsed_time": "0:00:01", "remaining_time": "0:11:00", "throughput": 2242.95, "total_tokens": 4160} |
| {"current_steps": 20, "total_steps": 5360, "loss": 13.1251, "lr": 1.7723880597014925e-06, "epoch": 0.03731343283582089, "percentage": 0.37, "elapsed_time": "0:00:02", "remaining_time": "0:10:12", "throughput": 2398.27, "total_tokens": 5504} |
| {"current_steps": 25, "total_steps": 5360, "loss": 13.0321, "lr": 2.238805970149254e-06, "epoch": 0.04664179104477612, "percentage": 0.47, "elapsed_time": "0:00:02", "remaining_time": "0:09:44", "throughput": 2524.67, "total_tokens": 6912} |
| {"current_steps": 30, "total_steps": 5360, "loss": 13.1437, "lr": 2.705223880597015e-06, "epoch": 0.055970149253731345, "percentage": 0.56, "elapsed_time": "0:00:03", "remaining_time": "0:09:31", "throughput": 2654.43, "total_tokens": 8544} |
| {"current_steps": 35, "total_steps": 5360, "loss": 13.1011, "lr": 3.171641791044776e-06, "epoch": 0.06529850746268656, "percentage": 0.65, "elapsed_time": "0:00:03", "remaining_time": "0:09:12", "throughput": 2667.58, "total_tokens": 9696} |
| {"current_steps": 40, "total_steps": 5360, "loss": 13.3047, "lr": 3.6380597014925376e-06, "epoch": 0.07462686567164178, "percentage": 0.75, "elapsed_time": "0:00:04", "remaining_time": "0:09:00", "throughput": 2700.65, "total_tokens": 10976} |
| {"current_steps": 45, "total_steps": 5360, "loss": 13.4022, "lr": 4.1044776119402985e-06, "epoch": 0.08395522388059702, "percentage": 0.84, "elapsed_time": "0:00:04", "remaining_time": "0:08:51", "throughput": 2736.59, "total_tokens": 12320} |
| {"current_steps": 50, "total_steps": 5360, "loss": 13.1273, "lr": 4.57089552238806e-06, "epoch": 0.09328358208955224, "percentage": 0.93, "elapsed_time": "0:00:04", "remaining_time": "0:08:46", "throughput": 2805.94, "total_tokens": 13920} |
| {"current_steps": 55, "total_steps": 5360, "loss": 12.9637, "lr": 5.037313432835821e-06, "epoch": 0.10261194029850747, "percentage": 1.03, "elapsed_time": "0:00:05", "remaining_time": "0:08:42", "throughput": 2851.44, "total_tokens": 15456} |
| {"current_steps": 60, "total_steps": 5360, "loss": 12.7974, "lr": 5.503731343283583e-06, "epoch": 0.11194029850746269, "percentage": 1.12, "elapsed_time": "0:00:05", "remaining_time": "0:08:38", "throughput": 2875.05, "total_tokens": 16864} |
| {"current_steps": 65, "total_steps": 5360, "loss": 12.7056, "lr": 5.970149253731343e-06, "epoch": 0.12126865671641791, "percentage": 1.21, "elapsed_time": "0:00:06", "remaining_time": "0:08:36", "throughput": 2892.5, "total_tokens": 18336} |
| {"current_steps": 70, "total_steps": 5360, "loss": 13.0199, "lr": 6.436567164179105e-06, "epoch": 0.13059701492537312, "percentage": 1.31, "elapsed_time": "0:00:06", "remaining_time": "0:08:32", "throughput": 2903.84, "total_tokens": 19712} |
| {"current_steps": 75, "total_steps": 5360, "loss": 12.9362, "lr": 6.902985074626867e-06, "epoch": 0.13992537313432835, "percentage": 1.4, "elapsed_time": "0:00:07", "remaining_time": "0:08:29", "throughput": 2924.87, "total_tokens": 21152} |
| {"current_steps": 80, "total_steps": 5360, "loss": 12.9771, "lr": 7.369402985074628e-06, "epoch": 0.14925373134328357, "percentage": 1.49, "elapsed_time": "0:00:07", "remaining_time": "0:08:26", "throughput": 2936.82, "total_tokens": 22560} |
| {"current_steps": 85, "total_steps": 5360, "loss": 12.8802, "lr": 7.835820895522389e-06, "epoch": 0.15858208955223882, "percentage": 1.59, "elapsed_time": "0:00:08", "remaining_time": "0:08:24", "throughput": 2948.14, "total_tokens": 23968} |
| {"current_steps": 90, "total_steps": 5360, "loss": 12.6029, "lr": 8.30223880597015e-06, "epoch": 0.16791044776119404, "percentage": 1.68, "elapsed_time": "0:00:08", "remaining_time": "0:08:24", "throughput": 2971.74, "total_tokens": 25600} |
| {"current_steps": 95, "total_steps": 5360, "loss": 12.9174, "lr": 8.768656716417911e-06, "epoch": 0.17723880597014927, "percentage": 1.77, "elapsed_time": "0:00:09", "remaining_time": "0:08:21", "throughput": 2972.58, "total_tokens": 26912} |
| {"current_steps": 100, "total_steps": 5360, "loss": 12.9595, "lr": 9.235074626865672e-06, "epoch": 0.1865671641791045, "percentage": 1.87, "elapsed_time": "0:00:09", "remaining_time": "0:08:21", "throughput": 2988.55, "total_tokens": 28512} |
| {"current_steps": 105, "total_steps": 5360, "loss": 12.563, "lr": 9.701492537313434e-06, "epoch": 0.1958955223880597, "percentage": 1.96, "elapsed_time": "0:00:09", "remaining_time": "0:08:20", "throughput": 2991.56, "total_tokens": 29888} |
| {"current_steps": 110, "total_steps": 5360, "loss": 12.834, "lr": 1.0167910447761195e-05, "epoch": 0.20522388059701493, "percentage": 2.05, "elapsed_time": "0:00:10", "remaining_time": "0:08:18", "throughput": 2996.96, "total_tokens": 31296} |
| {"current_steps": 115, "total_steps": 5360, "loss": 12.7311, "lr": 1.0634328358208955e-05, "epoch": 0.21455223880597016, "percentage": 2.15, "elapsed_time": "0:00:10", "remaining_time": "0:08:17", "throughput": 3004.07, "total_tokens": 32736} |
| {"current_steps": 120, "total_steps": 5360, "loss": 12.5369, "lr": 1.1100746268656717e-05, "epoch": 0.22388059701492538, "percentage": 2.24, "elapsed_time": "0:00:11", "remaining_time": "0:08:16", "throughput": 3013.76, "total_tokens": 34240} |
| {"current_steps": 125, "total_steps": 5360, "loss": 12.1094, "lr": 1.1567164179104478e-05, "epoch": 0.2332089552238806, "percentage": 2.33, "elapsed_time": "0:00:11", "remaining_time": "0:08:14", "throughput": 3017.05, "total_tokens": 35648} |
| {"current_steps": 130, "total_steps": 5360, "loss": 12.5198, "lr": 1.203358208955224e-05, "epoch": 0.24253731343283583, "percentage": 2.43, "elapsed_time": "0:00:12", "remaining_time": "0:08:13", "throughput": 3017.13, "total_tokens": 36992} |
| {"current_steps": 135, "total_steps": 5360, "loss": 12.3252, "lr": 1.25e-05, "epoch": 0.251865671641791, "percentage": 2.52, "elapsed_time": "0:00:12", "remaining_time": "0:08:12", "throughput": 3027.65, "total_tokens": 38528} |
| {"current_steps": 140, "total_steps": 5360, "loss": 12.3243, "lr": 1.2966417910447761e-05, "epoch": 0.26119402985074625, "percentage": 2.61, "elapsed_time": "0:00:13", "remaining_time": "0:08:10", "throughput": 3026.83, "total_tokens": 39840} |
| {"current_steps": 145, "total_steps": 5360, "loss": 12.2945, "lr": 1.3432835820895523e-05, "epoch": 0.27052238805970147, "percentage": 2.71, "elapsed_time": "0:00:13", "remaining_time": "0:08:09", "throughput": 3027.97, "total_tokens": 41216} |
| {"current_steps": 150, "total_steps": 5360, "loss": 12.3962, "lr": 1.3899253731343284e-05, "epoch": 0.2798507462686567, "percentage": 2.8, "elapsed_time": "0:00:14", "remaining_time": "0:08:08", "throughput": 3030.41, "total_tokens": 42624} |
| {"current_steps": 155, "total_steps": 5360, "loss": 12.1956, "lr": 1.4365671641791046e-05, "epoch": 0.2891791044776119, "percentage": 2.89, "elapsed_time": "0:00:14", "remaining_time": "0:08:07", "throughput": 3041.11, "total_tokens": 44192} |
| {"current_steps": 160, "total_steps": 5360, "loss": 12.2616, "lr": 1.4832089552238807e-05, "epoch": 0.29850746268656714, "percentage": 2.99, "elapsed_time": "0:00:14", "remaining_time": "0:08:06", "throughput": 3038.11, "total_tokens": 45504} |
| {"current_steps": 165, "total_steps": 5360, "loss": 11.4618, "lr": 1.529850746268657e-05, "epoch": 0.30783582089552236, "percentage": 3.08, "elapsed_time": "0:00:15", "remaining_time": "0:08:07", "throughput": 3058.0, "total_tokens": 47360} |
| {"current_steps": 170, "total_steps": 5360, "loss": 12.2382, "lr": 1.5764925373134328e-05, "epoch": 0.31716417910447764, "percentage": 3.17, "elapsed_time": "0:00:15", "remaining_time": "0:08:06", "throughput": 3054.93, "total_tokens": 48640} |
| {"current_steps": 175, "total_steps": 5360, "loss": 11.5946, "lr": 1.623134328358209e-05, "epoch": 0.32649253731343286, "percentage": 3.26, "elapsed_time": "0:00:16", "remaining_time": "0:08:05", "throughput": 3054.33, "total_tokens": 50016} |
| {"current_steps": 180, "total_steps": 5360, "loss": 11.8057, "lr": 1.6697761194029852e-05, "epoch": 0.3358208955223881, "percentage": 3.36, "elapsed_time": "0:00:16", "remaining_time": "0:08:03", "throughput": 3051.42, "total_tokens": 51296} |
| {"current_steps": 185, "total_steps": 5360, "loss": 11.8073, "lr": 1.716417910447761e-05, "epoch": 0.3451492537313433, "percentage": 3.45, "elapsed_time": "0:00:17", "remaining_time": "0:08:02", "throughput": 3047.94, "total_tokens": 52576} |
| {"current_steps": 190, "total_steps": 5360, "loss": 11.7853, "lr": 1.7630597014925373e-05, "epoch": 0.35447761194029853, "percentage": 3.54, "elapsed_time": "0:00:17", "remaining_time": "0:08:01", "throughput": 3054.06, "total_tokens": 54080} |
| {"current_steps": 195, "total_steps": 5360, "loss": 11.7581, "lr": 1.8097014925373135e-05, "epoch": 0.36380597014925375, "percentage": 3.64, "elapsed_time": "0:00:18", "remaining_time": "0:08:00", "throughput": 3052.84, "total_tokens": 55392} |
| {"current_steps": 200, "total_steps": 5360, "loss": 11.6818, "lr": 1.8563432835820898e-05, "epoch": 0.373134328358209, "percentage": 3.73, "elapsed_time": "0:00:18", "remaining_time": "0:07:59", "throughput": 3058.15, "total_tokens": 56864} |
| {"current_steps": 205, "total_steps": 5360, "loss": 11.4672, "lr": 1.9029850746268656e-05, "epoch": 0.3824626865671642, "percentage": 3.82, "elapsed_time": "0:00:19", "remaining_time": "0:07:59", "throughput": 3064.02, "total_tokens": 58368} |
| {"current_steps": 210, "total_steps": 5360, "loss": 11.498, "lr": 1.949626865671642e-05, "epoch": 0.3917910447761194, "percentage": 3.92, "elapsed_time": "0:00:19", "remaining_time": "0:07:58", "throughput": 3063.6, "total_tokens": 59744} |
| {"current_steps": 215, "total_steps": 5360, "loss": 11.2536, "lr": 1.996268656716418e-05, "epoch": 0.40111940298507465, "percentage": 4.01, "elapsed_time": "0:00:19", "remaining_time": "0:07:57", "throughput": 3064.79, "total_tokens": 61152} |
| {"current_steps": 220, "total_steps": 5360, "loss": 11.4211, "lr": 2.042910447761194e-05, "epoch": 0.41044776119402987, "percentage": 4.1, "elapsed_time": "0:00:20", "remaining_time": "0:07:56", "throughput": 3062.42, "total_tokens": 62496} |
| {"current_steps": 225, "total_steps": 5360, "loss": 11.8296, "lr": 2.0895522388059702e-05, "epoch": 0.4197761194029851, "percentage": 4.2, "elapsed_time": "0:00:20", "remaining_time": "0:07:55", "throughput": 3060.29, "total_tokens": 63808} |
| {"current_steps": 230, "total_steps": 5360, "loss": 11.4402, "lr": 2.1361940298507464e-05, "epoch": 0.4291044776119403, "percentage": 4.29, "elapsed_time": "0:00:21", "remaining_time": "0:07:54", "throughput": 3057.68, "total_tokens": 65088} |
| {"current_steps": 235, "total_steps": 5360, "loss": 11.4326, "lr": 2.1828358208955223e-05, "epoch": 0.43843283582089554, "percentage": 4.38, "elapsed_time": "0:00:21", "remaining_time": "0:07:54", "throughput": 3059.4, "total_tokens": 66496} |
| {"current_steps": 240, "total_steps": 5360, "loss": 11.2131, "lr": 2.2294776119402985e-05, "epoch": 0.44776119402985076, "percentage": 4.48, "elapsed_time": "0:00:22", "remaining_time": "0:07:53", "throughput": 3059.54, "total_tokens": 67872} |
| {"current_steps": 245, "total_steps": 5360, "loss": 11.4295, "lr": 2.2761194029850747e-05, "epoch": 0.457089552238806, "percentage": 4.57, "elapsed_time": "0:00:22", "remaining_time": "0:07:52", "throughput": 3058.67, "total_tokens": 69216} |
| {"current_steps": 250, "total_steps": 5360, "loss": 11.3182, "lr": 2.3227611940298506e-05, "epoch": 0.4664179104477612, "percentage": 4.66, "elapsed_time": "0:00:23", "remaining_time": "0:07:51", "throughput": 3067.09, "total_tokens": 70816} |
| {"current_steps": 255, "total_steps": 5360, "loss": 10.9973, "lr": 2.369402985074627e-05, "epoch": 0.47574626865671643, "percentage": 4.76, "elapsed_time": "0:00:23", "remaining_time": "0:07:51", "throughput": 3068.79, "total_tokens": 72224} |
| {"current_steps": 260, "total_steps": 5360, "loss": 11.2015, "lr": 2.416044776119403e-05, "epoch": 0.48507462686567165, "percentage": 4.85, "elapsed_time": "0:00:23", "remaining_time": "0:07:50", "throughput": 3068.11, "total_tokens": 73600} |
| {"current_steps": 265, "total_steps": 5360, "loss": 10.6497, "lr": 2.4626865671641793e-05, "epoch": 0.4944029850746269, "percentage": 4.94, "elapsed_time": "0:00:24", "remaining_time": "0:07:50", "throughput": 3071.66, "total_tokens": 75168} |
| {"current_steps": 268, "total_steps": 5360, "eval_loss": 10.7962064743042, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:27", "remaining_time": "0:08:39", "throughput": 2777.69, "total_tokens": 75936} |
| {"current_steps": 270, "total_steps": 5360, "loss": 10.7378, "lr": 2.5093283582089555e-05, "epoch": 0.503731343283582, "percentage": 5.04, "elapsed_time": "0:00:28", "remaining_time": "0:09:00", "throughput": 2667.75, "total_tokens": 76544} |
| {"current_steps": 275, "total_steps": 5360, "loss": 11.0643, "lr": 2.5559701492537314e-05, "epoch": 0.5130597014925373, "percentage": 5.13, "elapsed_time": "0:00:29", "remaining_time": "0:08:59", "throughput": 2675.2, "total_tokens": 78080} |
| {"current_steps": 280, "total_steps": 5360, "loss": 10.4075, "lr": 2.6026119402985076e-05, "epoch": 0.5223880597014925, "percentage": 5.22, "elapsed_time": "0:00:29", "remaining_time": "0:08:57", "throughput": 2683.34, "total_tokens": 79520} |
| {"current_steps": 285, "total_steps": 5360, "loss": 10.5867, "lr": 2.6492537313432835e-05, "epoch": 0.5317164179104478, "percentage": 5.32, "elapsed_time": "0:00:30", "remaining_time": "0:08:55", "throughput": 2691.26, "total_tokens": 80992} |
| {"current_steps": 290, "total_steps": 5360, "loss": 10.5364, "lr": 2.69589552238806e-05, "epoch": 0.5410447761194029, "percentage": 5.41, "elapsed_time": "0:00:30", "remaining_time": "0:08:54", "throughput": 2698.51, "total_tokens": 82496} |
| {"current_steps": 295, "total_steps": 5360, "loss": 10.6677, "lr": 2.742537313432836e-05, "epoch": 0.5503731343283582, "percentage": 5.5, "elapsed_time": "0:00:31", "remaining_time": "0:08:52", "throughput": 2699.21, "total_tokens": 83712} |
| {"current_steps": 300, "total_steps": 5360, "loss": 10.2373, "lr": 2.789179104477612e-05, "epoch": 0.5597014925373134, "percentage": 5.6, "elapsed_time": "0:00:31", "remaining_time": "0:08:50", "throughput": 2704.28, "total_tokens": 85120} |
| {"current_steps": 305, "total_steps": 5360, "loss": 10.891, "lr": 2.835820895522388e-05, "epoch": 0.5690298507462687, "percentage": 5.69, "elapsed_time": "0:00:31", "remaining_time": "0:08:49", "throughput": 2711.71, "total_tokens": 86560} |
| {"current_steps": 310, "total_steps": 5360, "loss": 10.2735, "lr": 2.8824626865671646e-05, "epoch": 0.5783582089552238, "percentage": 5.78, "elapsed_time": "0:00:32", "remaining_time": "0:08:47", "throughput": 2717.25, "total_tokens": 87936} |
| {"current_steps": 315, "total_steps": 5360, "loss": 10.2151, "lr": 2.92910447761194e-05, "epoch": 0.5876865671641791, "percentage": 5.88, "elapsed_time": "0:00:32", "remaining_time": "0:08:45", "throughput": 2722.79, "total_tokens": 89312} |
| {"current_steps": 320, "total_steps": 5360, "loss": 9.8693, "lr": 2.9757462686567167e-05, "epoch": 0.5970149253731343, "percentage": 5.97, "elapsed_time": "0:00:33", "remaining_time": "0:08:43", "throughput": 2724.5, "total_tokens": 90560} |
| {"current_steps": 325, "total_steps": 5360, "loss": 10.2992, "lr": 3.0223880597014926e-05, "epoch": 0.6063432835820896, "percentage": 6.06, "elapsed_time": "0:00:33", "remaining_time": "0:08:41", "throughput": 2729.45, "total_tokens": 91936} |
| {"current_steps": 330, "total_steps": 5360, "loss": 9.7121, "lr": 3.069029850746269e-05, "epoch": 0.6156716417910447, "percentage": 6.16, "elapsed_time": "0:00:34", "remaining_time": "0:08:40", "throughput": 2735.22, "total_tokens": 93344} |
| {"current_steps": 335, "total_steps": 5360, "loss": 10.5188, "lr": 3.115671641791045e-05, "epoch": 0.625, "percentage": 6.25, "elapsed_time": "0:00:34", "remaining_time": "0:08:38", "throughput": 2736.27, "total_tokens": 94560} |
| {"current_steps": 340, "total_steps": 5360, "loss": 10.3016, "lr": 3.162313432835821e-05, "epoch": 0.6343283582089553, "percentage": 6.34, "elapsed_time": "0:00:35", "remaining_time": "0:08:36", "throughput": 2743.14, "total_tokens": 96032} |
| {"current_steps": 345, "total_steps": 5360, "loss": 9.9344, "lr": 3.208955223880597e-05, "epoch": 0.6436567164179104, "percentage": 6.44, "elapsed_time": "0:00:35", "remaining_time": "0:08:35", "throughput": 2749.86, "total_tokens": 97504} |
| {"current_steps": 350, "total_steps": 5360, "loss": 9.9471, "lr": 3.2555970149253733e-05, "epoch": 0.6529850746268657, "percentage": 6.53, "elapsed_time": "0:00:35", "remaining_time": "0:08:33", "throughput": 2750.98, "total_tokens": 98720} |
| {"current_steps": 355, "total_steps": 5360, "loss": 9.4285, "lr": 3.302238805970149e-05, "epoch": 0.6623134328358209, "percentage": 6.62, "elapsed_time": "0:00:36", "remaining_time": "0:08:32", "throughput": 2754.8, "total_tokens": 100064} |
| {"current_steps": 360, "total_steps": 5360, "loss": 9.6716, "lr": 3.348880597014926e-05, "epoch": 0.6716417910447762, "percentage": 6.72, "elapsed_time": "0:00:36", "remaining_time": "0:08:30", "throughput": 2761.17, "total_tokens": 101536} |
| {"current_steps": 365, "total_steps": 5360, "loss": 9.6609, "lr": 3.395522388059701e-05, "epoch": 0.6809701492537313, "percentage": 6.81, "elapsed_time": "0:00:37", "remaining_time": "0:08:29", "throughput": 2769.1, "total_tokens": 103072} |
| {"current_steps": 370, "total_steps": 5360, "loss": 9.6861, "lr": 3.4421641791044776e-05, "epoch": 0.6902985074626866, "percentage": 6.9, "elapsed_time": "0:00:37", "remaining_time": "0:08:27", "throughput": 2772.28, "total_tokens": 104416} |
| {"current_steps": 375, "total_steps": 5360, "loss": 9.5197, "lr": 3.488805970149254e-05, "epoch": 0.6996268656716418, "percentage": 7.0, "elapsed_time": "0:00:38", "remaining_time": "0:08:26", "throughput": 2778.06, "total_tokens": 105952} |
| {"current_steps": 380, "total_steps": 5360, "loss": 9.164, "lr": 3.53544776119403e-05, "epoch": 0.7089552238805971, "percentage": 7.09, "elapsed_time": "0:00:38", "remaining_time": "0:08:25", "throughput": 2785.0, "total_tokens": 107520} |
| {"current_steps": 385, "total_steps": 5360, "loss": 9.4597, "lr": 3.582089552238806e-05, "epoch": 0.7182835820895522, "percentage": 7.18, "elapsed_time": "0:00:39", "remaining_time": "0:08:25", "throughput": 2794.61, "total_tokens": 109248} |
| {"current_steps": 390, "total_steps": 5360, "loss": 10.0959, "lr": 3.6287313432835824e-05, "epoch": 0.7276119402985075, "percentage": 7.28, "elapsed_time": "0:00:39", "remaining_time": "0:08:24", "throughput": 2798.74, "total_tokens": 110752} |
| {"current_steps": 395, "total_steps": 5360, "loss": 9.446, "lr": 3.675373134328358e-05, "epoch": 0.7369402985074627, "percentage": 7.37, "elapsed_time": "0:00:40", "remaining_time": "0:08:23", "throughput": 2805.61, "total_tokens": 112320} |
| {"current_steps": 400, "total_steps": 5360, "loss": 9.4224, "lr": 3.722014925373135e-05, "epoch": 0.746268656716418, "percentage": 7.46, "elapsed_time": "0:00:40", "remaining_time": "0:08:21", "throughput": 2810.9, "total_tokens": 113792} |
| {"current_steps": 405, "total_steps": 5360, "loss": 9.3109, "lr": 3.7686567164179104e-05, "epoch": 0.7555970149253731, "percentage": 7.56, "elapsed_time": "0:00:40", "remaining_time": "0:08:20", "throughput": 2817.15, "total_tokens": 115328} |
| {"current_steps": 410, "total_steps": 5360, "loss": 9.397, "lr": 3.8152985074626867e-05, "epoch": 0.7649253731343284, "percentage": 7.65, "elapsed_time": "0:00:41", "remaining_time": "0:08:19", "throughput": 2821.74, "total_tokens": 116800} |
| {"current_steps": 415, "total_steps": 5360, "loss": 8.4697, "lr": 3.861940298507463e-05, "epoch": 0.7742537313432836, "percentage": 7.74, "elapsed_time": "0:00:41", "remaining_time": "0:08:19", "throughput": 2830.66, "total_tokens": 118592} |
| {"current_steps": 420, "total_steps": 5360, "loss": 9.0921, "lr": 3.908582089552239e-05, "epoch": 0.7835820895522388, "percentage": 7.84, "elapsed_time": "0:00:42", "remaining_time": "0:08:17", "throughput": 2833.09, "total_tokens": 119936} |
| {"current_steps": 425, "total_steps": 5360, "loss": 9.4084, "lr": 3.9552238805970146e-05, "epoch": 0.792910447761194, "percentage": 7.93, "elapsed_time": "0:00:42", "remaining_time": "0:08:16", "throughput": 2835.46, "total_tokens": 121280} |
| {"current_steps": 430, "total_steps": 5360, "loss": 8.8077, "lr": 4.0018656716417915e-05, "epoch": 0.8022388059701493, "percentage": 8.02, "elapsed_time": "0:00:43", "remaining_time": "0:08:15", "throughput": 2843.23, "total_tokens": 122944} |
| {"current_steps": 435, "total_steps": 5360, "loss": 9.3722, "lr": 4.048507462686567e-05, "epoch": 0.8115671641791045, "percentage": 8.12, "elapsed_time": "0:00:43", "remaining_time": "0:08:14", "throughput": 2845.81, "total_tokens": 124320} |
| {"current_steps": 440, "total_steps": 5360, "loss": 9.1341, "lr": 4.095149253731343e-05, "epoch": 0.8208955223880597, "percentage": 8.21, "elapsed_time": "0:00:44", "remaining_time": "0:08:13", "throughput": 2850.4, "total_tokens": 125888} |
| {"current_steps": 445, "total_steps": 5360, "loss": 9.4208, "lr": 4.1417910447761195e-05, "epoch": 0.8302238805970149, "percentage": 8.3, "elapsed_time": "0:00:44", "remaining_time": "0:08:12", "throughput": 2853.38, "total_tokens": 127296} |
| {"current_steps": 450, "total_steps": 5360, "loss": 9.0534, "lr": 4.188432835820896e-05, "epoch": 0.8395522388059702, "percentage": 8.4, "elapsed_time": "0:00:45", "remaining_time": "0:08:11", "throughput": 2853.48, "total_tokens": 128512} |
| {"current_steps": 455, "total_steps": 5360, "loss": 9.0785, "lr": 4.235074626865671e-05, "epoch": 0.8488805970149254, "percentage": 8.49, "elapsed_time": "0:00:45", "remaining_time": "0:08:10", "throughput": 2858.17, "total_tokens": 130048} |
| {"current_steps": 460, "total_steps": 5360, "loss": 9.25, "lr": 4.281716417910448e-05, "epoch": 0.8582089552238806, "percentage": 8.58, "elapsed_time": "0:00:45", "remaining_time": "0:08:09", "throughput": 2860.27, "total_tokens": 131424} |
| {"current_steps": 465, "total_steps": 5360, "loss": 9.1648, "lr": 4.328358208955224e-05, "epoch": 0.8675373134328358, "percentage": 8.68, "elapsed_time": "0:00:46", "remaining_time": "0:08:08", "throughput": 2861.24, "total_tokens": 132704} |
| {"current_steps": 470, "total_steps": 5360, "loss": 9.5206, "lr": 4.375e-05, "epoch": 0.8768656716417911, "percentage": 8.77, "elapsed_time": "0:00:46", "remaining_time": "0:08:07", "throughput": 2863.31, "total_tokens": 134048} |
| {"current_steps": 475, "total_steps": 5360, "loss": 9.046, "lr": 4.421641791044777e-05, "epoch": 0.8861940298507462, "percentage": 8.86, "elapsed_time": "0:00:47", "remaining_time": "0:08:05", "throughput": 2865.44, "total_tokens": 135392} |
| {"current_steps": 480, "total_steps": 5360, "loss": 9.6769, "lr": 4.4682835820895524e-05, "epoch": 0.8955223880597015, "percentage": 8.96, "elapsed_time": "0:00:47", "remaining_time": "0:08:05", "throughput": 2867.78, "total_tokens": 136832} |
| {"current_steps": 485, "total_steps": 5360, "loss": 9.2715, "lr": 4.5149253731343286e-05, "epoch": 0.9048507462686567, "percentage": 9.05, "elapsed_time": "0:00:48", "remaining_time": "0:08:04", "throughput": 2872.05, "total_tokens": 138336} |
| {"current_steps": 490, "total_steps": 5360, "loss": 8.908, "lr": 4.561567164179105e-05, "epoch": 0.914179104477612, "percentage": 9.14, "elapsed_time": "0:00:48", "remaining_time": "0:08:03", "throughput": 2876.15, "total_tokens": 139840} |
| {"current_steps": 495, "total_steps": 5360, "loss": 9.2125, "lr": 4.608208955223881e-05, "epoch": 0.9235074626865671, "percentage": 9.24, "elapsed_time": "0:00:49", "remaining_time": "0:08:02", "throughput": 2879.39, "total_tokens": 141344} |
| {"current_steps": 500, "total_steps": 5360, "loss": 9.3081, "lr": 4.6548507462686566e-05, "epoch": 0.9328358208955224, "percentage": 9.33, "elapsed_time": "0:00:49", "remaining_time": "0:08:01", "throughput": 2883.23, "total_tokens": 142848} |
| {"current_steps": 505, "total_steps": 5360, "loss": 9.1954, "lr": 4.7014925373134335e-05, "epoch": 0.9421641791044776, "percentage": 9.42, "elapsed_time": "0:00:49", "remaining_time": "0:08:00", "throughput": 2887.72, "total_tokens": 144384} |
| {"current_steps": 510, "total_steps": 5360, "loss": 9.1012, "lr": 4.748134328358209e-05, "epoch": 0.9514925373134329, "percentage": 9.51, "elapsed_time": "0:00:50", "remaining_time": "0:07:59", "throughput": 2889.63, "total_tokens": 145760} |
| {"current_steps": 515, "total_steps": 5360, "loss": 8.5388, "lr": 4.794776119402985e-05, "epoch": 0.960820895522388, "percentage": 9.61, "elapsed_time": "0:00:50", "remaining_time": "0:07:58", "throughput": 2891.96, "total_tokens": 147168} |
| {"current_steps": 520, "total_steps": 5360, "loss": 8.7257, "lr": 4.8414179104477615e-05, "epoch": 0.9701492537313433, "percentage": 9.7, "elapsed_time": "0:00:51", "remaining_time": "0:07:57", "throughput": 2892.92, "total_tokens": 148480} |
| {"current_steps": 525, "total_steps": 5360, "loss": 8.7671, "lr": 4.888059701492538e-05, "epoch": 0.9794776119402985, "percentage": 9.79, "elapsed_time": "0:00:51", "remaining_time": "0:07:56", "throughput": 2894.99, "total_tokens": 149920} |
| {"current_steps": 530, "total_steps": 5360, "loss": 8.897, "lr": 4.934701492537314e-05, "epoch": 0.9888059701492538, "percentage": 9.89, "elapsed_time": "0:00:52", "remaining_time": "0:07:55", "throughput": 2896.64, "total_tokens": 151264} |
| {"current_steps": 535, "total_steps": 5360, "loss": 8.9279, "lr": 4.98134328358209e-05, "epoch": 0.9981343283582089, "percentage": 9.98, "elapsed_time": "0:00:52", "remaining_time": "0:07:54", "throughput": 2898.4, "total_tokens": 152608} |
| {"current_steps": 536, "total_steps": 5360, "eval_loss": 8.663278579711914, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:55", "remaining_time": "0:08:18", "throughput": 2757.64, "total_tokens": 152672} |
| {"current_steps": 540, "total_steps": 5360, "loss": 8.8564, "lr": 4.999995228691131e-05, "epoch": 1.007462686567164, "percentage": 10.07, "elapsed_time": "0:00:56", "remaining_time": "0:08:28", "throughput": 2699.3, "total_tokens": 153760} |
| {"current_steps": 545, "total_steps": 5360, "loss": 8.3945, "lr": 4.999966070758437e-05, "epoch": 1.0167910447761195, "percentage": 10.17, "elapsed_time": "0:00:57", "remaining_time": "0:08:27", "throughput": 2701.98, "total_tokens": 155104} |
| {"current_steps": 550, "total_steps": 5360, "loss": 8.5309, "lr": 4.999910405928983e-05, "epoch": 1.0261194029850746, "percentage": 10.26, "elapsed_time": "0:00:57", "remaining_time": "0:08:25", "throughput": 2704.06, "total_tokens": 156416} |
| {"current_steps": 555, "total_steps": 5360, "loss": 9.1396, "lr": 4.9998282347929784e-05, "epoch": 1.0354477611940298, "percentage": 10.35, "elapsed_time": "0:00:58", "remaining_time": "0:08:24", "throughput": 2708.17, "total_tokens": 157888} |
| {"current_steps": 560, "total_steps": 5360, "loss": 8.6982, "lr": 4.999719558221674e-05, "epoch": 1.044776119402985, "percentage": 10.45, "elapsed_time": "0:00:58", "remaining_time": "0:08:23", "throughput": 2712.45, "total_tokens": 159392} |
| {"current_steps": 565, "total_steps": 5360, "loss": 8.8241, "lr": 4.999584377367359e-05, "epoch": 1.0541044776119404, "percentage": 10.54, "elapsed_time": "0:00:59", "remaining_time": "0:08:22", "throughput": 2715.94, "total_tokens": 160864} |
| {"current_steps": 570, "total_steps": 5360, "loss": 8.7151, "lr": 4.9994226936633415e-05, "epoch": 1.0634328358208955, "percentage": 10.63, "elapsed_time": "0:00:59", "remaining_time": "0:08:21", "throughput": 2718.34, "total_tokens": 162240} |
| {"current_steps": 575, "total_steps": 5360, "loss": 8.3339, "lr": 4.999234508823938e-05, "epoch": 1.0727611940298507, "percentage": 10.73, "elapsed_time": "0:01:00", "remaining_time": "0:08:20", "throughput": 2721.01, "total_tokens": 163616} |
| {"current_steps": 580, "total_steps": 5360, "loss": 8.4545, "lr": 4.999019824844455e-05, "epoch": 1.0820895522388059, "percentage": 10.82, "elapsed_time": "0:01:00", "remaining_time": "0:08:19", "throughput": 2725.08, "total_tokens": 165152} |
| {"current_steps": 585, "total_steps": 5360, "loss": 8.2728, "lr": 4.998778644001165e-05, "epoch": 1.0914179104477613, "percentage": 10.91, "elapsed_time": "0:01:01", "remaining_time": "0:08:18", "throughput": 2728.23, "total_tokens": 166560} |
| {"current_steps": 590, "total_steps": 5360, "loss": 8.3721, "lr": 4.9985109688512854e-05, "epoch": 1.1007462686567164, "percentage": 11.01, "elapsed_time": "0:01:01", "remaining_time": "0:08:17", "throughput": 2730.66, "total_tokens": 167904} |
| {"current_steps": 595, "total_steps": 5360, "loss": 8.427, "lr": 4.998216802232949e-05, "epoch": 1.1100746268656716, "percentage": 11.1, "elapsed_time": "0:01:01", "remaining_time": "0:08:15", "throughput": 2733.35, "total_tokens": 169280} |
| {"current_steps": 600, "total_steps": 5360, "loss": 8.3741, "lr": 4.9978961472651774e-05, "epoch": 1.1194029850746268, "percentage": 11.19, "elapsed_time": "0:01:02", "remaining_time": "0:08:14", "throughput": 2736.02, "total_tokens": 170656} |
| {"current_steps": 605, "total_steps": 5360, "loss": 7.8491, "lr": 4.997549007347842e-05, "epoch": 1.1287313432835822, "percentage": 11.29, "elapsed_time": "0:01:02", "remaining_time": "0:08:14", "throughput": 2741.97, "total_tokens": 172352} |
| {"current_steps": 610, "total_steps": 5360, "loss": 8.19, "lr": 4.9971753861616354e-05, "epoch": 1.1380597014925373, "percentage": 11.38, "elapsed_time": "0:01:03", "remaining_time": "0:08:13", "throughput": 2746.53, "total_tokens": 173888} |
| {"current_steps": 615, "total_steps": 5360, "loss": 8.3163, "lr": 4.9967752876680254e-05, "epoch": 1.1473880597014925, "percentage": 11.47, "elapsed_time": "0:01:03", "remaining_time": "0:08:11", "throughput": 2746.28, "total_tokens": 175040} |
| {"current_steps": 620, "total_steps": 5360, "loss": 8.0931, "lr": 4.996348716109217e-05, "epoch": 1.1567164179104479, "percentage": 11.57, "elapsed_time": "0:01:04", "remaining_time": "0:08:10", "throughput": 2748.79, "total_tokens": 176480} |
| {"current_steps": 625, "total_steps": 5360, "loss": 8.4488, "lr": 4.9958956760081085e-05, "epoch": 1.166044776119403, "percentage": 11.66, "elapsed_time": "0:01:04", "remaining_time": "0:08:09", "throughput": 2752.53, "total_tokens": 177952} |
| {"current_steps": 630, "total_steps": 5360, "loss": 8.8229, "lr": 4.995416172168239e-05, "epoch": 1.1753731343283582, "percentage": 11.75, "elapsed_time": "0:01:05", "remaining_time": "0:08:09", "throughput": 2756.44, "total_tokens": 179552} |
| {"current_steps": 635, "total_steps": 5360, "loss": 8.6877, "lr": 4.994910209673741e-05, "epoch": 1.1847014925373134, "percentage": 11.85, "elapsed_time": "0:01:05", "remaining_time": "0:08:08", "throughput": 2761.01, "total_tokens": 181120} |
| {"current_steps": 640, "total_steps": 5360, "loss": 8.4657, "lr": 4.9943777938892855e-05, "epoch": 1.1940298507462686, "percentage": 11.94, "elapsed_time": "0:01:06", "remaining_time": "0:08:07", "throughput": 2763.86, "total_tokens": 182560} |
| {"current_steps": 645, "total_steps": 5360, "loss": 8.4572, "lr": 4.993818930460026e-05, "epoch": 1.203358208955224, "percentage": 12.03, "elapsed_time": "0:01:06", "remaining_time": "0:08:06", "throughput": 2766.72, "total_tokens": 184064} |
| {"current_steps": 650, "total_steps": 5360, "loss": 8.3868, "lr": 4.9932336253115354e-05, "epoch": 1.212686567164179, "percentage": 12.13, "elapsed_time": "0:01:06", "remaining_time": "0:08:05", "throughput": 2771.0, "total_tokens": 185600} |
| {"current_steps": 655, "total_steps": 5360, "loss": 8.0466, "lr": 4.9926218846497486e-05, "epoch": 1.2220149253731343, "percentage": 12.22, "elapsed_time": "0:01:07", "remaining_time": "0:08:04", "throughput": 2771.9, "total_tokens": 186848} |
| {"current_steps": 660, "total_steps": 5360, "loss": 8.3877, "lr": 4.991983714960892e-05, "epoch": 1.2313432835820897, "percentage": 12.31, "elapsed_time": "0:01:07", "remaining_time": "0:08:03", "throughput": 2774.18, "total_tokens": 188224} |
| {"current_steps": 665, "total_steps": 5360, "loss": 8.5721, "lr": 4.9913191230114156e-05, "epoch": 1.2406716417910448, "percentage": 12.41, "elapsed_time": "0:01:08", "remaining_time": "0:08:02", "throughput": 2777.39, "total_tokens": 189696} |
| {"current_steps": 670, "total_steps": 5360, "loss": 8.2866, "lr": 4.990628115847924e-05, "epoch": 1.25, "percentage": 12.5, "elapsed_time": "0:01:08", "remaining_time": "0:08:01", "throughput": 2781.84, "total_tokens": 191360} |
| {"current_steps": 675, "total_steps": 5360, "loss": 8.2224, "lr": 4.9899107007971004e-05, "epoch": 1.2593283582089552, "percentage": 12.59, "elapsed_time": "0:01:09", "remaining_time": "0:08:00", "throughput": 2784.71, "total_tokens": 192800} |
| {"current_steps": 680, "total_steps": 5360, "loss": 7.8275, "lr": 4.989166885465624e-05, "epoch": 1.2686567164179103, "percentage": 12.69, "elapsed_time": "0:01:09", "remaining_time": "0:07:59", "throughput": 2786.91, "total_tokens": 194208} |
| {"current_steps": 685, "total_steps": 5360, "loss": 8.2978, "lr": 4.988396677740097e-05, "epoch": 1.2779850746268657, "percentage": 12.78, "elapsed_time": "0:01:10", "remaining_time": "0:07:58", "throughput": 2788.42, "total_tokens": 195552} |
| {"current_steps": 690, "total_steps": 5360, "loss": 7.9729, "lr": 4.9876000857869583e-05, "epoch": 1.287313432835821, "percentage": 12.87, "elapsed_time": "0:01:10", "remaining_time": "0:07:57", "throughput": 2789.2, "total_tokens": 196832} |
| {"current_steps": 695, "total_steps": 5360, "loss": 7.5958, "lr": 4.986777118052393e-05, "epoch": 1.296641791044776, "percentage": 12.97, "elapsed_time": "0:01:11", "remaining_time": "0:07:56", "throughput": 2790.25, "total_tokens": 198112} |
| {"current_steps": 700, "total_steps": 5360, "loss": 7.7611, "lr": 4.9859277832622494e-05, "epoch": 1.3059701492537314, "percentage": 13.06, "elapsed_time": "0:01:11", "remaining_time": "0:07:55", "throughput": 2794.16, "total_tokens": 199680} |
| {"current_steps": 705, "total_steps": 5360, "loss": 7.8067, "lr": 4.98505209042194e-05, "epoch": 1.3152985074626866, "percentage": 13.15, "elapsed_time": "0:01:11", "remaining_time": "0:07:54", "throughput": 2795.19, "total_tokens": 200960} |
| {"current_steps": 710, "total_steps": 5360, "loss": 7.676, "lr": 4.9841500488163526e-05, "epoch": 1.3246268656716418, "percentage": 13.25, "elapsed_time": "0:01:12", "remaining_time": "0:07:53", "throughput": 2796.88, "total_tokens": 202368} |
| {"current_steps": 715, "total_steps": 5360, "loss": 8.1728, "lr": 4.983221668009744e-05, "epoch": 1.333955223880597, "percentage": 13.34, "elapsed_time": "0:01:12", "remaining_time": "0:07:52", "throughput": 2798.76, "total_tokens": 203744} |
| {"current_steps": 720, "total_steps": 5360, "loss": 7.9879, "lr": 4.982266957845648e-05, "epoch": 1.3432835820895521, "percentage": 13.43, "elapsed_time": "0:01:13", "remaining_time": "0:07:51", "throughput": 2800.07, "total_tokens": 205056} |
| {"current_steps": 725, "total_steps": 5360, "loss": 7.8765, "lr": 4.981285928446762e-05, "epoch": 1.3526119402985075, "percentage": 13.53, "elapsed_time": "0:01:13", "remaining_time": "0:07:50", "throughput": 2802.09, "total_tokens": 206432} |
| {"current_steps": 730, "total_steps": 5360, "loss": 7.9381, "lr": 4.9802785902148455e-05, "epoch": 1.3619402985074627, "percentage": 13.62, "elapsed_time": "0:01:14", "remaining_time": "0:07:50", "throughput": 2802.86, "total_tokens": 207712} |
| {"current_steps": 735, "total_steps": 5360, "loss": 7.9643, "lr": 4.979244953830608e-05, "epoch": 1.3712686567164178, "percentage": 13.71, "elapsed_time": "0:01:14", "remaining_time": "0:07:49", "throughput": 2803.75, "total_tokens": 208992} |
| {"current_steps": 740, "total_steps": 5360, "loss": 7.8442, "lr": 4.9781850302535945e-05, "epoch": 1.3805970149253732, "percentage": 13.81, "elapsed_time": "0:01:14", "remaining_time": "0:07:48", "throughput": 2805.85, "total_tokens": 210400} |
| {"current_steps": 745, "total_steps": 5360, "loss": 7.8334, "lr": 4.9770988307220736e-05, "epoch": 1.3899253731343284, "percentage": 13.9, "elapsed_time": "0:01:15", "remaining_time": "0:07:47", "throughput": 2808.45, "total_tokens": 211936} |
| {"current_steps": 750, "total_steps": 5360, "loss": 7.5606, "lr": 4.97598636675291e-05, "epoch": 1.3992537313432836, "percentage": 13.99, "elapsed_time": "0:01:15", "remaining_time": "0:07:46", "throughput": 2811.07, "total_tokens": 213376} |
| {"current_steps": 755, "total_steps": 5360, "loss": 7.6396, "lr": 4.974847650141453e-05, "epoch": 1.4085820895522387, "percentage": 14.09, "elapsed_time": "0:01:16", "remaining_time": "0:07:45", "throughput": 2813.31, "total_tokens": 214784} |
| {"current_steps": 760, "total_steps": 5360, "loss": 7.4207, "lr": 4.973682692961403e-05, "epoch": 1.417910447761194, "percentage": 14.18, "elapsed_time": "0:01:16", "remaining_time": "0:07:44", "throughput": 2815.72, "total_tokens": 216224} |
| {"current_steps": 765, "total_steps": 5360, "loss": 8.1997, "lr": 4.972491507564688e-05, "epoch": 1.4272388059701493, "percentage": 14.27, "elapsed_time": "0:01:17", "remaining_time": "0:07:43", "throughput": 2817.33, "total_tokens": 217600} |
| {"current_steps": 770, "total_steps": 5360, "loss": 7.9907, "lr": 4.971274106581331e-05, "epoch": 1.4365671641791045, "percentage": 14.37, "elapsed_time": "0:01:17", "remaining_time": "0:07:43", "throughput": 2819.83, "total_tokens": 219040} |
| {"current_steps": 775, "total_steps": 5360, "loss": 8.4593, "lr": 4.970030502919315e-05, "epoch": 1.4458955223880596, "percentage": 14.46, "elapsed_time": "0:01:18", "remaining_time": "0:07:42", "throughput": 2822.15, "total_tokens": 220480} |
| {"current_steps": 780, "total_steps": 5360, "loss": 7.1874, "lr": 4.9687607097644495e-05, "epoch": 1.455223880597015, "percentage": 14.55, "elapsed_time": "0:01:18", "remaining_time": "0:07:41", "throughput": 2826.25, "total_tokens": 222208} |
| {"current_steps": 785, "total_steps": 5360, "loss": 7.7768, "lr": 4.967464740580227e-05, "epoch": 1.4645522388059702, "percentage": 14.65, "elapsed_time": "0:01:19", "remaining_time": "0:07:40", "throughput": 2827.93, "total_tokens": 223648} |
| {"current_steps": 790, "total_steps": 5360, "loss": 7.8255, "lr": 4.9661426091076834e-05, "epoch": 1.4738805970149254, "percentage": 14.74, "elapsed_time": "0:01:19", "remaining_time": "0:07:40", "throughput": 2830.09, "total_tokens": 225152} |
| {"current_steps": 795, "total_steps": 5360, "loss": 7.9542, "lr": 4.9647943293652486e-05, "epoch": 1.4832089552238805, "percentage": 14.83, "elapsed_time": "0:01:20", "remaining_time": "0:07:39", "throughput": 2831.59, "total_tokens": 226528} |
| {"current_steps": 800, "total_steps": 5360, "loss": 7.7268, "lr": 4.963419915648603e-05, "epoch": 1.4925373134328357, "percentage": 14.93, "elapsed_time": "0:01:20", "remaining_time": "0:07:38", "throughput": 2833.57, "total_tokens": 228000} |
| {"current_steps": 804, "total_steps": 5360, "eval_loss": 7.69692325592041, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:01:23", "remaining_time": "0:07:52", "throughput": 2749.52, "total_tokens": 229344} |
| {"current_steps": 805, "total_steps": 5360, "loss": 7.6279, "lr": 4.962019382530521e-05, "epoch": 1.501865671641791, "percentage": 15.02, "elapsed_time": "0:01:24", "remaining_time": "0:07:58", "throughput": 2713.92, "total_tokens": 229600} |
| {"current_steps": 810, "total_steps": 5360, "loss": 7.3638, "lr": 4.960592744860717e-05, "epoch": 1.5111940298507462, "percentage": 15.11, "elapsed_time": "0:01:25", "remaining_time": "0:07:57", "throughput": 2714.89, "total_tokens": 230912} |
| {"current_steps": 815, "total_steps": 5360, "loss": 7.3002, "lr": 4.9591400177656935e-05, "epoch": 1.5205223880597014, "percentage": 15.21, "elapsed_time": "0:01:25", "remaining_time": "0:07:56", "throughput": 2716.52, "total_tokens": 232256} |
| {"current_steps": 820, "total_steps": 5360, "loss": 7.7275, "lr": 4.957661216648573e-05, "epoch": 1.5298507462686568, "percentage": 15.3, "elapsed_time": "0:01:25", "remaining_time": "0:07:55", "throughput": 2719.2, "total_tokens": 233728} |
| {"current_steps": 825, "total_steps": 5360, "loss": 7.736, "lr": 4.95615635718894e-05, "epoch": 1.539179104477612, "percentage": 15.39, "elapsed_time": "0:01:26", "remaining_time": "0:07:54", "throughput": 2720.73, "total_tokens": 235072} |
| {"current_steps": 830, "total_steps": 5360, "loss": 7.2555, "lr": 4.954625455342674e-05, "epoch": 1.5485074626865671, "percentage": 15.49, "elapsed_time": "0:01:26", "remaining_time": "0:07:54", "throughput": 2723.24, "total_tokens": 236512} |
| {"current_steps": 835, "total_steps": 5360, "loss": 7.5543, "lr": 4.953068527341777e-05, "epoch": 1.5578358208955225, "percentage": 15.58, "elapsed_time": "0:01:27", "remaining_time": "0:07:53", "throughput": 2725.9, "total_tokens": 237952} |
| {"current_steps": 840, "total_steps": 5360, "loss": 8.1271, "lr": 4.9514855896942046e-05, "epoch": 1.5671641791044775, "percentage": 15.67, "elapsed_time": "0:01:27", "remaining_time": "0:07:52", "throughput": 2727.83, "total_tokens": 239328} |
| {"current_steps": 845, "total_steps": 5360, "loss": 7.4141, "lr": 4.949876659183692e-05, "epoch": 1.5764925373134329, "percentage": 15.76, "elapsed_time": "0:01:28", "remaining_time": "0:07:51", "throughput": 2730.09, "total_tokens": 240736} |
| {"current_steps": 850, "total_steps": 5360, "loss": 7.4536, "lr": 4.948241752869571e-05, "epoch": 1.585820895522388, "percentage": 15.86, "elapsed_time": "0:01:28", "remaining_time": "0:07:50", "throughput": 2730.85, "total_tokens": 241984} |
| {"current_steps": 855, "total_steps": 5360, "loss": 7.8676, "lr": 4.946580888086595e-05, "epoch": 1.5951492537313432, "percentage": 15.95, "elapsed_time": "0:01:29", "remaining_time": "0:07:49", "throughput": 2732.17, "total_tokens": 243296} |
| {"current_steps": 860, "total_steps": 5360, "loss": 6.9482, "lr": 4.9448940824447515e-05, "epoch": 1.6044776119402986, "percentage": 16.04, "elapsed_time": "0:01:29", "remaining_time": "0:07:48", "throughput": 2735.9, "total_tokens": 244960} |
| {"current_steps": 865, "total_steps": 5360, "loss": 7.5292, "lr": 4.943181353829076e-05, "epoch": 1.6138059701492538, "percentage": 16.14, "elapsed_time": "0:01:29", "remaining_time": "0:07:47", "throughput": 2737.52, "total_tokens": 246304} |
| {"current_steps": 870, "total_steps": 5360, "loss": 7.6678, "lr": 4.941442720399464e-05, "epoch": 1.623134328358209, "percentage": 16.23, "elapsed_time": "0:01:30", "remaining_time": "0:07:46", "throughput": 2739.29, "total_tokens": 247680} |
| {"current_steps": 875, "total_steps": 5360, "loss": 7.4366, "lr": 4.939678200590475e-05, "epoch": 1.6324626865671643, "percentage": 16.32, "elapsed_time": "0:01:30", "remaining_time": "0:07:45", "throughput": 2742.04, "total_tokens": 249152} |
| {"current_steps": 880, "total_steps": 5360, "loss": 7.3552, "lr": 4.937887813111142e-05, "epoch": 1.6417910447761193, "percentage": 16.42, "elapsed_time": "0:01:31", "remaining_time": "0:07:44", "throughput": 2743.33, "total_tokens": 250496} |
| {"current_steps": 885, "total_steps": 5360, "loss": 7.7847, "lr": 4.936071576944769e-05, "epoch": 1.6511194029850746, "percentage": 16.51, "elapsed_time": "0:01:31", "remaining_time": "0:07:43", "throughput": 2745.12, "total_tokens": 251872} |
| {"current_steps": 890, "total_steps": 5360, "loss": 7.0814, "lr": 4.93422951134873e-05, "epoch": 1.6604477611940298, "percentage": 16.6, "elapsed_time": "0:01:32", "remaining_time": "0:07:43", "throughput": 2748.47, "total_tokens": 253440} |
| {"current_steps": 895, "total_steps": 5360, "loss": 6.8777, "lr": 4.932361635854268e-05, "epoch": 1.669776119402985, "percentage": 16.7, "elapsed_time": "0:01:32", "remaining_time": "0:07:42", "throughput": 2749.49, "total_tokens": 254720} |
| {"current_steps": 900, "total_steps": 5360, "loss": 7.3267, "lr": 4.9304679702662854e-05, "epoch": 1.6791044776119404, "percentage": 16.79, "elapsed_time": "0:01:33", "remaining_time": "0:07:41", "throughput": 2752.54, "total_tokens": 256320} |
| {"current_steps": 905, "total_steps": 5360, "loss": 7.6562, "lr": 4.9285485346631334e-05, "epoch": 1.6884328358208955, "percentage": 16.88, "elapsed_time": "0:01:33", "remaining_time": "0:07:40", "throughput": 2753.53, "total_tokens": 257600} |
| {"current_steps": 910, "total_steps": 5360, "loss": 7.3446, "lr": 4.9266033493964e-05, "epoch": 1.6977611940298507, "percentage": 16.98, "elapsed_time": "0:01:33", "remaining_time": "0:07:39", "throughput": 2755.54, "total_tokens": 259008} |
| {"current_steps": 915, "total_steps": 5360, "loss": 7.2013, "lr": 4.924632435090696e-05, "epoch": 1.707089552238806, "percentage": 17.07, "elapsed_time": "0:01:34", "remaining_time": "0:07:38", "throughput": 2757.62, "total_tokens": 260448} |
| {"current_steps": 920, "total_steps": 5360, "loss": 7.7115, "lr": 4.922635812643434e-05, "epoch": 1.716417910447761, "percentage": 17.16, "elapsed_time": "0:01:34", "remaining_time": "0:07:37", "throughput": 2759.66, "total_tokens": 261888} |
| {"current_steps": 925, "total_steps": 5360, "loss": 7.2164, "lr": 4.920613503224608e-05, "epoch": 1.7257462686567164, "percentage": 17.26, "elapsed_time": "0:01:35", "remaining_time": "0:07:37", "throughput": 2761.61, "total_tokens": 263328} |
| {"current_steps": 930, "total_steps": 5360, "loss": 7.544, "lr": 4.9185655282765655e-05, "epoch": 1.7350746268656716, "percentage": 17.35, "elapsed_time": "0:01:35", "remaining_time": "0:07:36", "throughput": 2764.36, "total_tokens": 264832} |
| {"current_steps": 935, "total_steps": 5360, "loss": 6.8825, "lr": 4.916491909513787e-05, "epoch": 1.7444029850746268, "percentage": 17.44, "elapsed_time": "0:01:36", "remaining_time": "0:07:35", "throughput": 2766.79, "total_tokens": 266368} |
| {"current_steps": 940, "total_steps": 5360, "loss": 7.6216, "lr": 4.914392668922651e-05, "epoch": 1.7537313432835822, "percentage": 17.54, "elapsed_time": "0:01:36", "remaining_time": "0:07:34", "throughput": 2769.74, "total_tokens": 267904} |
| {"current_steps": 945, "total_steps": 5360, "loss": 7.3775, "lr": 4.912267828761199e-05, "epoch": 1.7630597014925373, "percentage": 17.63, "elapsed_time": "0:01:37", "remaining_time": "0:07:34", "throughput": 2772.96, "total_tokens": 269504} |
| {"current_steps": 950, "total_steps": 5360, "loss": 6.7441, "lr": 4.910117411558906e-05, "epoch": 1.7723880597014925, "percentage": 17.72, "elapsed_time": "0:01:37", "remaining_time": "0:07:33", "throughput": 2774.82, "total_tokens": 270912} |
| {"current_steps": 955, "total_steps": 5360, "loss": 7.2112, "lr": 4.907941440116436e-05, "epoch": 1.7817164179104479, "percentage": 17.82, "elapsed_time": "0:01:38", "remaining_time": "0:07:32", "throughput": 2777.0, "total_tokens": 272384} |
| {"current_steps": 960, "total_steps": 5360, "loss": 7.2948, "lr": 4.905739937505401e-05, "epoch": 1.7910447761194028, "percentage": 17.91, "elapsed_time": "0:01:38", "remaining_time": "0:07:31", "throughput": 2778.48, "total_tokens": 273760} |
| {"current_steps": 965, "total_steps": 5360, "loss": 7.2113, "lr": 4.9035129270681196e-05, "epoch": 1.8003731343283582, "percentage": 18.0, "elapsed_time": "0:01:38", "remaining_time": "0:07:30", "throughput": 2782.12, "total_tokens": 275424} |
| {"current_steps": 970, "total_steps": 5360, "loss": 7.6151, "lr": 4.901260432417367e-05, "epoch": 1.8097014925373134, "percentage": 18.1, "elapsed_time": "0:01:39", "remaining_time": "0:07:30", "throughput": 2783.98, "total_tokens": 276832} |
| {"current_steps": 975, "total_steps": 5360, "loss": 7.7834, "lr": 4.8989824774361236e-05, "epoch": 1.8190298507462686, "percentage": 18.19, "elapsed_time": "0:01:39", "remaining_time": "0:07:29", "throughput": 2786.32, "total_tokens": 278336} |
| {"current_steps": 980, "total_steps": 5360, "loss": 7.1615, "lr": 4.896679086277325e-05, "epoch": 1.828358208955224, "percentage": 18.28, "elapsed_time": "0:01:40", "remaining_time": "0:07:28", "throughput": 2787.82, "total_tokens": 279712} |
| {"current_steps": 985, "total_steps": 5360, "loss": 7.066, "lr": 4.8943502833636026e-05, "epoch": 1.837686567164179, "percentage": 18.38, "elapsed_time": "0:01:40", "remaining_time": "0:07:27", "throughput": 2789.64, "total_tokens": 281152} |
| {"current_steps": 990, "total_steps": 5360, "loss": 7.5003, "lr": 4.891996093387028e-05, "epoch": 1.8470149253731343, "percentage": 18.47, "elapsed_time": "0:01:41", "remaining_time": "0:07:26", "throughput": 2791.34, "total_tokens": 282560} |
| {"current_steps": 995, "total_steps": 5360, "loss": 6.7303, "lr": 4.889616541308847e-05, "epoch": 1.8563432835820897, "percentage": 18.56, "elapsed_time": "0:01:41", "remaining_time": "0:07:26", "throughput": 2792.98, "total_tokens": 283968} |
| {"current_steps": 1000, "total_steps": 5360, "loss": 6.7719, "lr": 4.8872116523592196e-05, "epoch": 1.8656716417910446, "percentage": 18.66, "elapsed_time": "0:01:42", "remaining_time": "0:07:25", "throughput": 2795.25, "total_tokens": 285440} |
| {"current_steps": 1005, "total_steps": 5360, "loss": 6.4091, "lr": 4.8847814520369475e-05, "epoch": 1.875, "percentage": 18.75, "elapsed_time": "0:01:42", "remaining_time": "0:07:24", "throughput": 2797.62, "total_tokens": 286944} |
| {"current_steps": 1010, "total_steps": 5360, "loss": 7.0659, "lr": 4.8823259661092104e-05, "epoch": 1.8843283582089554, "percentage": 18.84, "elapsed_time": "0:01:43", "remaining_time": "0:07:23", "throughput": 2798.8, "total_tokens": 288320} |
| {"current_steps": 1015, "total_steps": 5360, "loss": 6.9223, "lr": 4.879845220611284e-05, "epoch": 1.8936567164179103, "percentage": 18.94, "elapsed_time": "0:01:43", "remaining_time": "0:07:22", "throughput": 2799.24, "total_tokens": 289568} |
| {"current_steps": 1020, "total_steps": 5360, "loss": 7.5876, "lr": 4.877339241846273e-05, "epoch": 1.9029850746268657, "percentage": 19.03, "elapsed_time": "0:01:43", "remaining_time": "0:07:22", "throughput": 2800.91, "total_tokens": 290976} |
| {"current_steps": 1025, "total_steps": 5360, "loss": 7.4811, "lr": 4.874808056384825e-05, "epoch": 1.912313432835821, "percentage": 19.12, "elapsed_time": "0:01:44", "remaining_time": "0:07:21", "throughput": 2804.03, "total_tokens": 292576} |
| {"current_steps": 1030, "total_steps": 5360, "loss": 7.0982, "lr": 4.872251691064854e-05, "epoch": 1.921641791044776, "percentage": 19.22, "elapsed_time": "0:01:44", "remaining_time": "0:07:20", "throughput": 2805.43, "total_tokens": 293952} |
| {"current_steps": 1035, "total_steps": 5360, "loss": 7.4047, "lr": 4.869670172991252e-05, "epoch": 1.9309701492537314, "percentage": 19.31, "elapsed_time": "0:01:45", "remaining_time": "0:07:19", "throughput": 2807.74, "total_tokens": 295488} |
| {"current_steps": 1040, "total_steps": 5360, "loss": 7.268, "lr": 4.8670635295356035e-05, "epoch": 1.9402985074626866, "percentage": 19.4, "elapsed_time": "0:01:45", "remaining_time": "0:07:18", "throughput": 2808.18, "total_tokens": 296768} |
| {"current_steps": 1045, "total_steps": 5360, "loss": 6.7933, "lr": 4.8644317883358956e-05, "epoch": 1.9496268656716418, "percentage": 19.5, "elapsed_time": "0:01:46", "remaining_time": "0:07:18", "throughput": 2810.1, "total_tokens": 298240} |
| {"current_steps": 1050, "total_steps": 5360, "loss": 7.4257, "lr": 4.861774977296223e-05, "epoch": 1.9589552238805972, "percentage": 19.59, "elapsed_time": "0:01:46", "remaining_time": "0:07:17", "throughput": 2812.12, "total_tokens": 299712} |
| {"current_steps": 1055, "total_steps": 5360, "loss": 7.252, "lr": 4.8590931245864954e-05, "epoch": 1.9682835820895521, "percentage": 19.68, "elapsed_time": "0:01:46", "remaining_time": "0:07:16", "throughput": 2811.83, "total_tokens": 300864} |
| {"current_steps": 1060, "total_steps": 5360, "loss": 6.9777, "lr": 4.856386258642135e-05, "epoch": 1.9776119402985075, "percentage": 19.78, "elapsed_time": "0:01:47", "remaining_time": "0:07:15", "throughput": 2813.74, "total_tokens": 302336} |
| {"current_steps": 1065, "total_steps": 5360, "loss": 7.1512, "lr": 4.8536544081637787e-05, "epoch": 1.9869402985074627, "percentage": 19.87, "elapsed_time": "0:01:47", "remaining_time": "0:07:15", "throughput": 2814.11, "total_tokens": 303584} |
| {"current_steps": 1070, "total_steps": 5360, "loss": 7.3138, "lr": 4.8508976021169705e-05, "epoch": 1.9962686567164178, "percentage": 19.96, "elapsed_time": "0:01:48", "remaining_time": "0:07:14", "throughput": 2815.54, "total_tokens": 304960} |
| {"current_steps": 1072, "total_steps": 5360, "eval_loss": 7.15101957321167, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:01:51", "remaining_time": "0:07:25", "throughput": 2741.88, "total_tokens": 305288} |
| {"current_steps": 1075, "total_steps": 5360, "loss": 7.529, "lr": 4.8481158697318564e-05, "epoch": 2.0055970149253732, "percentage": 20.06, "elapsed_time": "0:01:52", "remaining_time": "0:07:29", "throughput": 2715.04, "total_tokens": 306152} |
| {"current_steps": 1080, "total_steps": 5360, "loss": 7.797, "lr": 4.845309240502874e-05, "epoch": 2.014925373134328, "percentage": 20.15, "elapsed_time": "0:01:53", "remaining_time": "0:07:28", "throughput": 2716.12, "total_tokens": 307464} |
| {"current_steps": 1085, "total_steps": 5360, "loss": 7.5253, "lr": 4.8424777441884405e-05, "epoch": 2.0242537313432836, "percentage": 20.24, "elapsed_time": "0:01:53", "remaining_time": "0:07:27", "throughput": 2718.32, "total_tokens": 308968} |
| {"current_steps": 1090, "total_steps": 5360, "loss": 7.4095, "lr": 4.839621410810634e-05, "epoch": 2.033582089552239, "percentage": 20.34, "elapsed_time": "0:01:54", "remaining_time": "0:07:27", "throughput": 2720.46, "total_tokens": 310440} |
| {"current_steps": 1095, "total_steps": 5360, "loss": 7.2855, "lr": 4.8367402706548805e-05, "epoch": 2.042910447761194, "percentage": 20.43, "elapsed_time": "0:01:54", "remaining_time": "0:07:26", "throughput": 2723.22, "total_tokens": 312008} |
| {"current_steps": 1100, "total_steps": 5360, "loss": 7.0683, "lr": 4.8338343542696275e-05, "epoch": 2.0522388059701493, "percentage": 20.52, "elapsed_time": "0:01:55", "remaining_time": "0:07:25", "throughput": 2724.86, "total_tokens": 313416} |
| {"current_steps": 1105, "total_steps": 5360, "loss": 6.9105, "lr": 4.830903692466024e-05, "epoch": 2.0615671641791047, "percentage": 20.62, "elapsed_time": "0:01:55", "remaining_time": "0:07:24", "throughput": 2725.76, "total_tokens": 314728} |
| {"current_steps": 1110, "total_steps": 5360, "loss": 7.605, "lr": 4.82794831631759e-05, "epoch": 2.0708955223880596, "percentage": 20.71, "elapsed_time": "0:01:55", "remaining_time": "0:07:23", "throughput": 2727.0, "total_tokens": 316072} |
| {"current_steps": 1115, "total_steps": 5360, "loss": 7.245, "lr": 4.8249682571598945e-05, "epoch": 2.080223880597015, "percentage": 20.8, "elapsed_time": "0:01:56", "remaining_time": "0:07:22", "throughput": 2727.99, "total_tokens": 317384} |
| {"current_steps": 1120, "total_steps": 5360, "loss": 7.04, "lr": 4.821963546590211e-05, "epoch": 2.08955223880597, "percentage": 20.9, "elapsed_time": "0:01:56", "remaining_time": "0:07:22", "throughput": 2729.1, "total_tokens": 318696} |
| {"current_steps": 1125, "total_steps": 5360, "loss": 6.7811, "lr": 4.8189342164671944e-05, "epoch": 2.0988805970149254, "percentage": 20.99, "elapsed_time": "0:01:57", "remaining_time": "0:07:21", "throughput": 2730.15, "total_tokens": 320008} |
| {"current_steps": 1130, "total_steps": 5360, "loss": 7.008, "lr": 4.815880298910537e-05, "epoch": 2.1082089552238807, "percentage": 21.08, "elapsed_time": "0:01:57", "remaining_time": "0:07:20", "throughput": 2732.12, "total_tokens": 321480} |
| {"current_steps": 1135, "total_steps": 5360, "loss": 6.7962, "lr": 4.8128018263006305e-05, "epoch": 2.1175373134328357, "percentage": 21.18, "elapsed_time": "0:01:58", "remaining_time": "0:07:19", "throughput": 2734.56, "total_tokens": 323016} |
| {"current_steps": 1140, "total_steps": 5360, "loss": 7.0804, "lr": 4.8096988312782174e-05, "epoch": 2.126865671641791, "percentage": 21.27, "elapsed_time": "0:01:58", "remaining_time": "0:07:18", "throughput": 2736.41, "total_tokens": 324456} |
| {"current_steps": 1145, "total_steps": 5360, "loss": 7.6275, "lr": 4.806571346744053e-05, "epoch": 2.1361940298507465, "percentage": 21.36, "elapsed_time": "0:01:59", "remaining_time": "0:07:18", "throughput": 2739.18, "total_tokens": 326120} |
| {"current_steps": 1150, "total_steps": 5360, "loss": 7.8758, "lr": 4.803419405858553e-05, "epoch": 2.1455223880597014, "percentage": 21.46, "elapsed_time": "0:01:59", "remaining_time": "0:07:17", "throughput": 2741.38, "total_tokens": 327624} |
| {"current_steps": 1155, "total_steps": 5360, "loss": 6.8095, "lr": 4.8002430420414356e-05, "epoch": 2.154850746268657, "percentage": 21.55, "elapsed_time": "0:01:59", "remaining_time": "0:07:16", "throughput": 2743.8, "total_tokens": 329160} |
| {"current_steps": 1160, "total_steps": 5360, "loss": 7.3275, "lr": 4.79704228897138e-05, "epoch": 2.1641791044776117, "percentage": 21.64, "elapsed_time": "0:02:00", "remaining_time": "0:07:15", "throughput": 2744.73, "total_tokens": 330472} |
| {"current_steps": 1165, "total_steps": 5360, "loss": 7.1853, "lr": 4.79381718058566e-05, "epoch": 2.173507462686567, "percentage": 21.74, "elapsed_time": "0:02:00", "remaining_time": "0:07:15", "throughput": 2747.05, "total_tokens": 332008} |
| {"current_steps": 1170, "total_steps": 5360, "loss": 6.2736, "lr": 4.790567751079783e-05, "epoch": 2.1828358208955225, "percentage": 21.83, "elapsed_time": "0:02:01", "remaining_time": "0:07:14", "throughput": 2748.43, "total_tokens": 333384} |
| {"current_steps": 1175, "total_steps": 5360, "loss": 7.0594, "lr": 4.787294034907135e-05, "epoch": 2.1921641791044775, "percentage": 21.92, "elapsed_time": "0:02:01", "remaining_time": "0:07:13", "throughput": 2749.32, "total_tokens": 334696} |
| {"current_steps": 1180, "total_steps": 5360, "loss": 7.1676, "lr": 4.78399606677861e-05, "epoch": 2.201492537313433, "percentage": 22.01, "elapsed_time": "0:02:02", "remaining_time": "0:07:12", "throughput": 2751.14, "total_tokens": 336232} |
| {"current_steps": 1185, "total_steps": 5360, "loss": 7.1117, "lr": 4.780673881662242e-05, "epoch": 2.2108208955223883, "percentage": 22.11, "elapsed_time": "0:02:02", "remaining_time": "0:07:12", "throughput": 2751.91, "total_tokens": 337512} |
| {"current_steps": 1190, "total_steps": 5360, "loss": 6.5368, "lr": 4.777327514782837e-05, "epoch": 2.220149253731343, "percentage": 22.2, "elapsed_time": "0:02:03", "remaining_time": "0:07:11", "throughput": 2754.44, "total_tokens": 339080} |
| {"current_steps": 1195, "total_steps": 5360, "loss": 6.9429, "lr": 4.773957001621597e-05, "epoch": 2.2294776119402986, "percentage": 22.29, "elapsed_time": "0:02:03", "remaining_time": "0:07:10", "throughput": 2755.6, "total_tokens": 340456} |
| {"current_steps": 1200, "total_steps": 5360, "loss": 6.9668, "lr": 4.7705623779157435e-05, "epoch": 2.2388059701492535, "percentage": 22.39, "elapsed_time": "0:02:03", "remaining_time": "0:07:09", "throughput": 2757.04, "total_tokens": 341864} |
| {"current_steps": 1205, "total_steps": 5360, "loss": 6.8569, "lr": 4.7671436796581426e-05, "epoch": 2.248134328358209, "percentage": 22.48, "elapsed_time": "0:02:04", "remaining_time": "0:07:09", "throughput": 2758.37, "total_tokens": 343240} |
| {"current_steps": 1210, "total_steps": 5360, "loss": 6.3704, "lr": 4.7637009430969194e-05, "epoch": 2.2574626865671643, "percentage": 22.57, "elapsed_time": "0:02:04", "remaining_time": "0:07:08", "throughput": 2760.78, "total_tokens": 344808} |
| {"current_steps": 1215, "total_steps": 5360, "loss": 6.6781, "lr": 4.760234204735072e-05, "epoch": 2.2667910447761193, "percentage": 22.67, "elapsed_time": "0:02:05", "remaining_time": "0:07:07", "throughput": 2761.88, "total_tokens": 346152} |
| {"current_steps": 1220, "total_steps": 5360, "loss": 7.1345, "lr": 4.756743501330091e-05, "epoch": 2.2761194029850746, "percentage": 22.76, "elapsed_time": "0:02:05", "remaining_time": "0:07:06", "throughput": 2763.33, "total_tokens": 347528} |
| {"current_steps": 1225, "total_steps": 5360, "loss": 7.5046, "lr": 4.753228869893566e-05, "epoch": 2.28544776119403, "percentage": 22.85, "elapsed_time": "0:02:06", "remaining_time": "0:07:05", "throughput": 2763.75, "total_tokens": 348776} |
| {"current_steps": 1230, "total_steps": 5360, "loss": 6.8257, "lr": 4.7496903476907885e-05, "epoch": 2.294776119402985, "percentage": 22.95, "elapsed_time": "0:02:06", "remaining_time": "0:07:05", "throughput": 2764.58, "total_tokens": 350088} |
| {"current_steps": 1235, "total_steps": 5360, "loss": 7.0531, "lr": 4.746127972240367e-05, "epoch": 2.3041044776119404, "percentage": 23.04, "elapsed_time": "0:02:07", "remaining_time": "0:07:04", "throughput": 2766.29, "total_tokens": 351528} |
| {"current_steps": 1240, "total_steps": 5360, "loss": 6.8511, "lr": 4.742541781313822e-05, "epoch": 2.3134328358208958, "percentage": 23.13, "elapsed_time": "0:02:07", "remaining_time": "0:07:03", "throughput": 2767.18, "total_tokens": 352840} |
| {"current_steps": 1245, "total_steps": 5360, "loss": 6.6784, "lr": 4.738931812935186e-05, "epoch": 2.3227611940298507, "percentage": 23.23, "elapsed_time": "0:02:07", "remaining_time": "0:07:02", "throughput": 2767.99, "total_tokens": 354152} |
| {"current_steps": 1250, "total_steps": 5360, "loss": 6.7425, "lr": 4.735298105380601e-05, "epoch": 2.332089552238806, "percentage": 23.32, "elapsed_time": "0:02:08", "remaining_time": "0:07:02", "throughput": 2769.05, "total_tokens": 355496} |
| {"current_steps": 1255, "total_steps": 5360, "loss": 7.2814, "lr": 4.7316406971779145e-05, "epoch": 2.341417910447761, "percentage": 23.41, "elapsed_time": "0:02:08", "remaining_time": "0:07:01", "throughput": 2771.47, "total_tokens": 357096} |
| {"current_steps": 1260, "total_steps": 5360, "loss": 6.8146, "lr": 4.7279596271062716e-05, "epoch": 2.3507462686567164, "percentage": 23.51, "elapsed_time": "0:02:09", "remaining_time": "0:07:00", "throughput": 2771.87, "total_tokens": 358312} |
| {"current_steps": 1265, "total_steps": 5360, "loss": 7.5862, "lr": 4.724254934195697e-05, "epoch": 2.360074626865672, "percentage": 23.6, "elapsed_time": "0:02:09", "remaining_time": "0:06:59", "throughput": 2773.08, "total_tokens": 359752} |
| {"current_steps": 1270, "total_steps": 5360, "loss": 6.7293, "lr": 4.720526657726691e-05, "epoch": 2.3694029850746268, "percentage": 23.69, "elapsed_time": "0:02:10", "remaining_time": "0:06:59", "throughput": 2774.29, "total_tokens": 361128} |
| {"current_steps": 1275, "total_steps": 5360, "loss": 7.019, "lr": 4.716774837229804e-05, "epoch": 2.378731343283582, "percentage": 23.79, "elapsed_time": "0:02:10", "remaining_time": "0:06:58", "throughput": 2775.65, "total_tokens": 362600} |
| {"current_steps": 1280, "total_steps": 5360, "loss": 6.5359, "lr": 4.712999512485225e-05, "epoch": 2.388059701492537, "percentage": 23.88, "elapsed_time": "0:02:11", "remaining_time": "0:06:57", "throughput": 2777.44, "total_tokens": 364072} |
| {"current_steps": 1285, "total_steps": 5360, "loss": 6.6359, "lr": 4.709200723522353e-05, "epoch": 2.3973880597014925, "percentage": 23.97, "elapsed_time": "0:02:11", "remaining_time": "0:06:57", "throughput": 2779.4, "total_tokens": 365576} |
| {"current_steps": 1290, "total_steps": 5360, "loss": 7.2102, "lr": 4.7053785106193793e-05, "epoch": 2.406716417910448, "percentage": 24.07, "elapsed_time": "0:02:11", "remaining_time": "0:06:56", "throughput": 2782.13, "total_tokens": 367208} |
| {"current_steps": 1295, "total_steps": 5360, "loss": 7.1793, "lr": 4.701532914302853e-05, "epoch": 2.416044776119403, "percentage": 24.16, "elapsed_time": "0:02:12", "remaining_time": "0:06:55", "throughput": 2783.48, "total_tokens": 368680} |
| {"current_steps": 1300, "total_steps": 5360, "loss": 7.2568, "lr": 4.697663975347258e-05, "epoch": 2.425373134328358, "percentage": 24.25, "elapsed_time": "0:02:12", "remaining_time": "0:06:55", "throughput": 2786.27, "total_tokens": 370408} |
| {"current_steps": 1305, "total_steps": 5360, "loss": 6.9625, "lr": 4.693771734774578e-05, "epoch": 2.4347014925373136, "percentage": 24.35, "elapsed_time": "0:02:13", "remaining_time": "0:06:54", "throughput": 2787.41, "total_tokens": 371784} |
| {"current_steps": 1310, "total_steps": 5360, "loss": 6.4715, "lr": 4.6898562338538606e-05, "epoch": 2.4440298507462686, "percentage": 24.44, "elapsed_time": "0:02:13", "remaining_time": "0:06:53", "throughput": 2788.91, "total_tokens": 373256} |
| {"current_steps": 1315, "total_steps": 5360, "loss": 6.8562, "lr": 4.6859175141007796e-05, "epoch": 2.453358208955224, "percentage": 24.53, "elapsed_time": "0:02:14", "remaining_time": "0:06:53", "throughput": 2790.8, "total_tokens": 374760} |
| {"current_steps": 1320, "total_steps": 5360, "loss": 6.7238, "lr": 4.6819556172771974e-05, "epoch": 2.4626865671641793, "percentage": 24.63, "elapsed_time": "0:02:14", "remaining_time": "0:06:52", "throughput": 2792.71, "total_tokens": 376360} |
| {"current_steps": 1325, "total_steps": 5360, "loss": 6.3232, "lr": 4.6779705853907205e-05, "epoch": 2.4720149253731343, "percentage": 24.72, "elapsed_time": "0:02:15", "remaining_time": "0:06:51", "throughput": 2794.67, "total_tokens": 377960} |
| {"current_steps": 1330, "total_steps": 5360, "loss": 6.797, "lr": 4.673962460694254e-05, "epoch": 2.4813432835820897, "percentage": 24.81, "elapsed_time": "0:02:15", "remaining_time": "0:06:51", "throughput": 2795.04, "total_tokens": 379208} |
| {"current_steps": 1335, "total_steps": 5360, "loss": 6.7893, "lr": 4.669931285685553e-05, "epoch": 2.4906716417910446, "percentage": 24.91, "elapsed_time": "0:02:16", "remaining_time": "0:06:50", "throughput": 2796.94, "total_tokens": 380744} |
| {"current_steps": 1340, "total_steps": 5360, "loss": 6.8308, "lr": 4.6658771031067734e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:02:16", "remaining_time": "0:06:49", "throughput": 2797.92, "total_tokens": 382120} |
| {"current_steps": 1340, "total_steps": 5360, "eval_loss": 6.847332954406738, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:02:19", "remaining_time": "0:06:57", "throughput": 2746.16, "total_tokens": 382120} |
| {"current_steps": 1345, "total_steps": 5360, "loss": 6.9646, "lr": 4.6617999559440187e-05, "epoch": 2.5093283582089554, "percentage": 25.09, "elapsed_time": "0:02:20", "remaining_time": "0:06:59", "throughput": 2726.43, "total_tokens": 383400} |
| {"current_steps": 1350, "total_steps": 5360, "loss": 6.5551, "lr": 4.657699887426884e-05, "epoch": 2.5186567164179103, "percentage": 25.19, "elapsed_time": "0:02:21", "remaining_time": "0:06:59", "throughput": 2726.97, "total_tokens": 384680} |
| {"current_steps": 1355, "total_steps": 5360, "loss": 6.7656, "lr": 4.653576941027995e-05, "epoch": 2.5279850746268657, "percentage": 25.28, "elapsed_time": "0:02:21", "remaining_time": "0:06:58", "throughput": 2727.59, "total_tokens": 385992} |
| {"current_steps": 1360, "total_steps": 5360, "loss": 6.3868, "lr": 4.649431160462552e-05, "epoch": 2.5373134328358207, "percentage": 25.37, "elapsed_time": "0:02:21", "remaining_time": "0:06:57", "throughput": 2728.55, "total_tokens": 387368} |
| {"current_steps": 1365, "total_steps": 5360, "loss": 6.2019, "lr": 4.645262589687861e-05, "epoch": 2.546641791044776, "percentage": 25.47, "elapsed_time": "0:02:22", "remaining_time": "0:06:56", "throughput": 2729.8, "total_tokens": 388776} |
| {"current_steps": 1370, "total_steps": 5360, "loss": 6.7456, "lr": 4.6410712729028734e-05, "epoch": 2.5559701492537314, "percentage": 25.56, "elapsed_time": "0:02:22", "remaining_time": "0:06:56", "throughput": 2732.33, "total_tokens": 390440} |
| {"current_steps": 1375, "total_steps": 5360, "loss": 6.3728, "lr": 4.636857254547712e-05, "epoch": 2.5652985074626864, "percentage": 25.65, "elapsed_time": "0:02:23", "remaining_time": "0:06:55", "throughput": 2733.0, "total_tokens": 391720} |
| {"current_steps": 1380, "total_steps": 5360, "loss": 6.7978, "lr": 4.632620579303203e-05, "epoch": 2.574626865671642, "percentage": 25.75, "elapsed_time": "0:02:23", "remaining_time": "0:06:54", "throughput": 2733.82, "total_tokens": 393032} |
| {"current_steps": 1385, "total_steps": 5360, "loss": 6.2146, "lr": 4.628361292090403e-05, "epoch": 2.583955223880597, "percentage": 25.84, "elapsed_time": "0:02:24", "remaining_time": "0:06:53", "throughput": 2734.45, "total_tokens": 394312} |
| {"current_steps": 1390, "total_steps": 5360, "loss": 6.4358, "lr": 4.624079438070117e-05, "epoch": 2.593283582089552, "percentage": 25.93, "elapsed_time": "0:02:24", "remaining_time": "0:06:53", "throughput": 2735.45, "total_tokens": 395656} |
| {"current_steps": 1395, "total_steps": 5360, "loss": 6.744, "lr": 4.6197750626424277e-05, "epoch": 2.6026119402985075, "percentage": 26.03, "elapsed_time": "0:02:25", "remaining_time": "0:06:52", "throughput": 2737.56, "total_tokens": 397288} |
| {"current_steps": 1400, "total_steps": 5360, "loss": 6.8124, "lr": 4.615448211446208e-05, "epoch": 2.611940298507463, "percentage": 26.12, "elapsed_time": "0:02:25", "remaining_time": "0:06:51", "throughput": 2738.42, "total_tokens": 398600} |
| {"current_steps": 1405, "total_steps": 5360, "loss": 6.621, "lr": 4.6110989303586396e-05, "epoch": 2.621268656716418, "percentage": 26.21, "elapsed_time": "0:02:26", "remaining_time": "0:06:51", "throughput": 2740.54, "total_tokens": 400168} |
| {"current_steps": 1410, "total_steps": 5360, "loss": 7.0945, "lr": 4.606727265494727e-05, "epoch": 2.6305970149253732, "percentage": 26.31, "elapsed_time": "0:02:26", "remaining_time": "0:06:50", "throughput": 2741.68, "total_tokens": 401544} |
| {"current_steps": 1415, "total_steps": 5360, "loss": 6.5069, "lr": 4.602333263206806e-05, "epoch": 2.6399253731343286, "percentage": 26.4, "elapsed_time": "0:02:26", "remaining_time": "0:06:49", "throughput": 2743.11, "total_tokens": 402984} |
| {"current_steps": 1420, "total_steps": 5360, "loss": 7.1347, "lr": 4.597916970084056e-05, "epoch": 2.6492537313432836, "percentage": 26.49, "elapsed_time": "0:02:27", "remaining_time": "0:06:48", "throughput": 2744.06, "total_tokens": 404328} |
| {"current_steps": 1425, "total_steps": 5360, "loss": 6.0565, "lr": 4.593478432952002e-05, "epoch": 2.658582089552239, "percentage": 26.59, "elapsed_time": "0:02:27", "remaining_time": "0:06:48", "throughput": 2744.72, "total_tokens": 405608} |
| {"current_steps": 1430, "total_steps": 5360, "loss": 6.3487, "lr": 4.5890176988720205e-05, "epoch": 2.667910447761194, "percentage": 26.68, "elapsed_time": "0:02:28", "remaining_time": "0:06:47", "throughput": 2746.64, "total_tokens": 407208} |
| {"current_steps": 1435, "total_steps": 5360, "loss": 6.8202, "lr": 4.584534815140842e-05, "epoch": 2.6772388059701493, "percentage": 26.77, "elapsed_time": "0:02:28", "remaining_time": "0:06:46", "throughput": 2748.4, "total_tokens": 408776} |
| {"current_steps": 1440, "total_steps": 5360, "loss": 6.1282, "lr": 4.5800298292900446e-05, "epoch": 2.6865671641791042, "percentage": 26.87, "elapsed_time": "0:02:29", "remaining_time": "0:06:46", "throughput": 2749.34, "total_tokens": 410120} |
| {"current_steps": 1445, "total_steps": 5360, "loss": 6.467, "lr": 4.575502789085555e-05, "epoch": 2.6958955223880596, "percentage": 26.96, "elapsed_time": "0:02:29", "remaining_time": "0:06:45", "throughput": 2751.05, "total_tokens": 411624} |
| {"current_steps": 1450, "total_steps": 5360, "loss": 6.3529, "lr": 4.57095374252714e-05, "epoch": 2.705223880597015, "percentage": 27.05, "elapsed_time": "0:02:30", "remaining_time": "0:06:44", "throughput": 2752.64, "total_tokens": 413096} |
| {"current_steps": 1455, "total_steps": 5360, "loss": 6.9861, "lr": 4.5663827378478975e-05, "epoch": 2.71455223880597, "percentage": 27.15, "elapsed_time": "0:02:30", "remaining_time": "0:06:43", "throughput": 2753.62, "total_tokens": 414472} |
| {"current_steps": 1460, "total_steps": 5360, "loss": 7.2706, "lr": 4.561789823513743e-05, "epoch": 2.7238805970149254, "percentage": 27.24, "elapsed_time": "0:02:30", "remaining_time": "0:06:43", "throughput": 2755.86, "total_tokens": 416072} |
| {"current_steps": 1465, "total_steps": 5360, "loss": 6.7473, "lr": 4.5571750482229016e-05, "epoch": 2.7332089552238807, "percentage": 27.33, "elapsed_time": "0:02:31", "remaining_time": "0:06:42", "throughput": 2757.63, "total_tokens": 417640} |
| {"current_steps": 1470, "total_steps": 5360, "loss": 6.9012, "lr": 4.552538460905386e-05, "epoch": 2.7425373134328357, "percentage": 27.43, "elapsed_time": "0:02:31", "remaining_time": "0:06:41", "throughput": 2758.8, "total_tokens": 419048} |
| {"current_steps": 1475, "total_steps": 5360, "loss": 6.3489, "lr": 4.54788011072248e-05, "epoch": 2.751865671641791, "percentage": 27.52, "elapsed_time": "0:02:32", "remaining_time": "0:06:41", "throughput": 2760.25, "total_tokens": 420520} |
| {"current_steps": 1480, "total_steps": 5360, "loss": 6.5353, "lr": 4.543200047066216e-05, "epoch": 2.7611940298507465, "percentage": 27.61, "elapsed_time": "0:02:32", "remaining_time": "0:06:40", "throughput": 2761.59, "total_tokens": 421960} |
| {"current_steps": 1485, "total_steps": 5360, "loss": 6.489, "lr": 4.538498319558854e-05, "epoch": 2.7705223880597014, "percentage": 27.71, "elapsed_time": "0:02:33", "remaining_time": "0:06:39", "throughput": 2762.38, "total_tokens": 423304} |
| {"current_steps": 1490, "total_steps": 5360, "loss": 6.8703, "lr": 4.5337749780523526e-05, "epoch": 2.779850746268657, "percentage": 27.8, "elapsed_time": "0:02:33", "remaining_time": "0:06:39", "throughput": 2762.78, "total_tokens": 424552} |
| {"current_steps": 1495, "total_steps": 5360, "loss": 6.516, "lr": 4.5290300726278415e-05, "epoch": 2.789179104477612, "percentage": 27.89, "elapsed_time": "0:02:34", "remaining_time": "0:06:38", "throughput": 2763.67, "total_tokens": 425896} |
| {"current_steps": 1500, "total_steps": 5360, "loss": 6.2462, "lr": 4.5242636535950913e-05, "epoch": 2.798507462686567, "percentage": 27.99, "elapsed_time": "0:02:34", "remaining_time": "0:06:37", "throughput": 2764.42, "total_tokens": 427208} |
| {"current_steps": 1505, "total_steps": 5360, "loss": 6.361, "lr": 4.519475771491978e-05, "epoch": 2.8078358208955225, "percentage": 28.08, "elapsed_time": "0:02:34", "remaining_time": "0:06:36", "throughput": 2764.44, "total_tokens": 428392} |
| {"current_steps": 1510, "total_steps": 5360, "loss": 7.0662, "lr": 4.5146664770839495e-05, "epoch": 2.8171641791044775, "percentage": 28.17, "elapsed_time": "0:02:35", "remaining_time": "0:06:36", "throughput": 2766.28, "total_tokens": 429928} |
| {"current_steps": 1515, "total_steps": 5360, "loss": 7.1708, "lr": 4.5098358213634876e-05, "epoch": 2.826492537313433, "percentage": 28.26, "elapsed_time": "0:02:35", "remaining_time": "0:06:35", "throughput": 2767.81, "total_tokens": 431464} |
| {"current_steps": 1520, "total_steps": 5360, "loss": 6.8913, "lr": 4.504983855549562e-05, "epoch": 2.835820895522388, "percentage": 28.36, "elapsed_time": "0:02:36", "remaining_time": "0:06:34", "throughput": 2769.42, "total_tokens": 432968} |
| {"current_steps": 1525, "total_steps": 5360, "loss": 7.1544, "lr": 4.5001106310870946e-05, "epoch": 2.845149253731343, "percentage": 28.45, "elapsed_time": "0:02:36", "remaining_time": "0:06:34", "throughput": 2771.0, "total_tokens": 434472} |
| {"current_steps": 1530, "total_steps": 5360, "loss": 6.3892, "lr": 4.49521619964641e-05, "epoch": 2.8544776119402986, "percentage": 28.54, "elapsed_time": "0:02:37", "remaining_time": "0:06:33", "throughput": 2772.45, "total_tokens": 435944} |
| {"current_steps": 1535, "total_steps": 5360, "loss": 6.9862, "lr": 4.4903006131226874e-05, "epoch": 2.8638059701492535, "percentage": 28.64, "elapsed_time": "0:02:37", "remaining_time": "0:06:33", "throughput": 2774.47, "total_tokens": 437608} |
| {"current_steps": 1540, "total_steps": 5360, "loss": 7.2509, "lr": 4.485363923635413e-05, "epoch": 2.873134328358209, "percentage": 28.73, "elapsed_time": "0:02:38", "remaining_time": "0:06:32", "throughput": 2776.03, "total_tokens": 439176} |
| {"current_steps": 1545, "total_steps": 5360, "loss": 6.3681, "lr": 4.480406183527823e-05, "epoch": 2.8824626865671643, "percentage": 28.82, "elapsed_time": "0:02:38", "remaining_time": "0:06:31", "throughput": 2776.81, "total_tokens": 440520} |
| {"current_steps": 1550, "total_steps": 5360, "loss": 6.1798, "lr": 4.475427445366355e-05, "epoch": 2.8917910447761193, "percentage": 28.92, "elapsed_time": "0:02:39", "remaining_time": "0:06:31", "throughput": 2777.8, "total_tokens": 441896} |
| {"current_steps": 1555, "total_steps": 5360, "loss": 7.0098, "lr": 4.4704277619400834e-05, "epoch": 2.9011194029850746, "percentage": 29.01, "elapsed_time": "0:02:39", "remaining_time": "0:06:30", "throughput": 2778.2, "total_tokens": 443176} |
| {"current_steps": 1560, "total_steps": 5360, "loss": 6.9893, "lr": 4.4654071862601654e-05, "epoch": 2.91044776119403, "percentage": 29.1, "elapsed_time": "0:02:39", "remaining_time": "0:06:29", "throughput": 2779.39, "total_tokens": 444680} |
| {"current_steps": 1565, "total_steps": 5360, "loss": 6.3998, "lr": 4.460365771559275e-05, "epoch": 2.919776119402985, "percentage": 29.2, "elapsed_time": "0:02:40", "remaining_time": "0:06:29", "throughput": 2780.22, "total_tokens": 446024} |
| {"current_steps": 1570, "total_steps": 5360, "loss": 6.3063, "lr": 4.455303571291042e-05, "epoch": 2.9291044776119404, "percentage": 29.29, "elapsed_time": "0:02:40", "remaining_time": "0:06:28", "throughput": 2782.04, "total_tokens": 447656} |
| {"current_steps": 1575, "total_steps": 5360, "loss": 6.7395, "lr": 4.4502206391294824e-05, "epoch": 2.9384328358208958, "percentage": 29.38, "elapsed_time": "0:02:41", "remaining_time": "0:06:27", "throughput": 2782.39, "total_tokens": 448904} |
| {"current_steps": 1580, "total_steps": 5360, "loss": 6.6092, "lr": 4.445117028968431e-05, "epoch": 2.9477611940298507, "percentage": 29.48, "elapsed_time": "0:02:41", "remaining_time": "0:06:27", "throughput": 2782.94, "total_tokens": 450216} |
| {"current_steps": 1585, "total_steps": 5360, "loss": 6.4942, "lr": 4.439992794920969e-05, "epoch": 2.957089552238806, "percentage": 29.57, "elapsed_time": "0:02:42", "remaining_time": "0:06:26", "throughput": 2783.83, "total_tokens": 451592} |
| {"current_steps": 1590, "total_steps": 5360, "loss": 6.6325, "lr": 4.434847991318851e-05, "epoch": 2.966417910447761, "percentage": 29.66, "elapsed_time": "0:02:42", "remaining_time": "0:06:25", "throughput": 2785.05, "total_tokens": 453032} |
| {"current_steps": 1595, "total_steps": 5360, "loss": 6.5674, "lr": 4.4296826727119296e-05, "epoch": 2.9757462686567164, "percentage": 29.76, "elapsed_time": "0:02:43", "remaining_time": "0:06:25", "throughput": 2785.97, "total_tokens": 454408} |
| {"current_steps": 1600, "total_steps": 5360, "loss": 6.6931, "lr": 4.424496893867573e-05, "epoch": 2.9850746268656714, "percentage": 29.85, "elapsed_time": "0:02:43", "remaining_time": "0:06:24", "throughput": 2787.44, "total_tokens": 455912} |
| {"current_steps": 1605, "total_steps": 5360, "loss": 6.5213, "lr": 4.419290709770091e-05, "epoch": 2.9944029850746268, "percentage": 29.94, "elapsed_time": "0:02:43", "remaining_time": "0:06:23", "throughput": 2788.29, "total_tokens": 457256} |
| {"current_steps": 1608, "total_steps": 5360, "eval_loss": 6.66015625, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:02:46", "remaining_time": "0:06:29", "throughput": 2743.82, "total_tokens": 457952} |
| {"current_steps": 1610, "total_steps": 5360, "loss": 6.3029, "lr": 4.414064175620146e-05, "epoch": 3.003731343283582, "percentage": 30.04, "elapsed_time": "0:02:48", "remaining_time": "0:06:31", "throughput": 2725.05, "total_tokens": 458464} |
| {"current_steps": 1615, "total_steps": 5360, "loss": 7.0312, "lr": 4.408817346834169e-05, "epoch": 3.013059701492537, "percentage": 30.13, "elapsed_time": "0:02:48", "remaining_time": "0:06:31", "throughput": 2726.07, "total_tokens": 459872} |
| {"current_steps": 1620, "total_steps": 5360, "loss": 6.9781, "lr": 4.4035502790437764e-05, "epoch": 3.0223880597014925, "percentage": 30.22, "elapsed_time": "0:02:49", "remaining_time": "0:06:30", "throughput": 2727.68, "total_tokens": 461408} |
| {"current_steps": 1625, "total_steps": 5360, "loss": 6.7744, "lr": 4.398263028095175e-05, "epoch": 3.031716417910448, "percentage": 30.32, "elapsed_time": "0:02:49", "remaining_time": "0:06:29", "throughput": 2728.0, "total_tokens": 462624} |
| {"current_steps": 1630, "total_steps": 5360, "loss": 6.8695, "lr": 4.392955650048571e-05, "epoch": 3.041044776119403, "percentage": 30.41, "elapsed_time": "0:02:50", "remaining_time": "0:06:29", "throughput": 2729.24, "total_tokens": 464096} |
| {"current_steps": 1635, "total_steps": 5360, "loss": 6.6582, "lr": 4.387628201177577e-05, "epoch": 3.050373134328358, "percentage": 30.5, "elapsed_time": "0:02:50", "remaining_time": "0:06:28", "throughput": 2730.0, "total_tokens": 465408} |
| {"current_steps": 1640, "total_steps": 5360, "loss": 6.7798, "lr": 4.382280737968614e-05, "epoch": 3.0597014925373136, "percentage": 30.6, "elapsed_time": "0:02:50", "remaining_time": "0:06:27", "throughput": 2731.37, "total_tokens": 466880} |
| {"current_steps": 1645, "total_steps": 5360, "loss": 6.5449, "lr": 4.3769133171203144e-05, "epoch": 3.0690298507462686, "percentage": 30.69, "elapsed_time": "0:02:51", "remaining_time": "0:06:27", "throughput": 2732.79, "total_tokens": 468416} |
| {"current_steps": 1650, "total_steps": 5360, "loss": 6.5721, "lr": 4.371525995542918e-05, "epoch": 3.078358208955224, "percentage": 30.78, "elapsed_time": "0:02:51", "remaining_time": "0:06:26", "throughput": 2734.56, "total_tokens": 469952} |
| {"current_steps": 1655, "total_steps": 5360, "loss": 6.1842, "lr": 4.366118830357672e-05, "epoch": 3.0876865671641793, "percentage": 30.88, "elapsed_time": "0:02:52", "remaining_time": "0:06:25", "throughput": 2735.27, "total_tokens": 471264} |
| {"current_steps": 1660, "total_steps": 5360, "loss": 6.5954, "lr": 4.3606918788962205e-05, "epoch": 3.0970149253731343, "percentage": 30.97, "elapsed_time": "0:02:52", "remaining_time": "0:06:25", "throughput": 2736.24, "total_tokens": 472640} |
| {"current_steps": 1665, "total_steps": 5360, "loss": 6.67, "lr": 4.355245198700003e-05, "epoch": 3.1063432835820897, "percentage": 31.06, "elapsed_time": "0:02:53", "remaining_time": "0:06:24", "throughput": 2737.03, "total_tokens": 473984} |
| {"current_steps": 1670, "total_steps": 5360, "loss": 6.7531, "lr": 4.3497788475196376e-05, "epoch": 3.1156716417910446, "percentage": 31.16, "elapsed_time": "0:02:53", "remaining_time": "0:06:23", "throughput": 2738.52, "total_tokens": 475488} |
| {"current_steps": 1675, "total_steps": 5360, "loss": 6.8457, "lr": 4.3442928833143145e-05, "epoch": 3.125, "percentage": 31.25, "elapsed_time": "0:02:54", "remaining_time": "0:06:22", "throughput": 2739.42, "total_tokens": 476864} |
| {"current_steps": 1680, "total_steps": 5360, "loss": 6.157, "lr": 4.338787364251177e-05, "epoch": 3.1343283582089554, "percentage": 31.34, "elapsed_time": "0:02:54", "remaining_time": "0:06:22", "throughput": 2740.46, "total_tokens": 478272} |
| {"current_steps": 1685, "total_steps": 5360, "loss": 6.3999, "lr": 4.3332623487047084e-05, "epoch": 3.1436567164179103, "percentage": 31.44, "elapsed_time": "0:02:54", "remaining_time": "0:06:21", "throughput": 2741.36, "total_tokens": 479648} |
| {"current_steps": 1690, "total_steps": 5360, "loss": 6.34, "lr": 4.32771789525611e-05, "epoch": 3.1529850746268657, "percentage": 31.53, "elapsed_time": "0:02:55", "remaining_time": "0:06:20", "throughput": 2742.55, "total_tokens": 481152} |
| {"current_steps": 1695, "total_steps": 5360, "loss": 6.6815, "lr": 4.3221540626926824e-05, "epoch": 3.1623134328358207, "percentage": 31.62, "elapsed_time": "0:02:55", "remaining_time": "0:06:20", "throughput": 2743.83, "total_tokens": 482624} |
| {"current_steps": 1700, "total_steps": 5360, "loss": 7.0455, "lr": 4.3165709100071986e-05, "epoch": 3.171641791044776, "percentage": 31.72, "elapsed_time": "0:02:56", "remaining_time": "0:06:19", "throughput": 2744.87, "total_tokens": 484032} |
| {"current_steps": 1705, "total_steps": 5360, "loss": 6.2077, "lr": 4.310968496397284e-05, "epoch": 3.1809701492537314, "percentage": 31.81, "elapsed_time": "0:02:56", "remaining_time": "0:06:18", "throughput": 2745.82, "total_tokens": 485440} |
| {"current_steps": 1710, "total_steps": 5360, "loss": 6.4335, "lr": 4.305346881264785e-05, "epoch": 3.1902985074626864, "percentage": 31.9, "elapsed_time": "0:02:57", "remaining_time": "0:06:18", "throughput": 2746.84, "total_tokens": 486848} |
| {"current_steps": 1715, "total_steps": 5360, "loss": 6.2969, "lr": 4.299706124215138e-05, "epoch": 3.199626865671642, "percentage": 32.0, "elapsed_time": "0:02:57", "remaining_time": "0:06:17", "throughput": 2747.63, "total_tokens": 488192} |
| {"current_steps": 1720, "total_steps": 5360, "loss": 6.4261, "lr": 4.294046285056742e-05, "epoch": 3.208955223880597, "percentage": 32.09, "elapsed_time": "0:02:58", "remaining_time": "0:06:16", "throughput": 2749.13, "total_tokens": 489696} |
| {"current_steps": 1725, "total_steps": 5360, "loss": 6.3899, "lr": 4.288367423800319e-05, "epoch": 3.218283582089552, "percentage": 32.18, "elapsed_time": "0:02:58", "remaining_time": "0:06:16", "throughput": 2749.78, "total_tokens": 491008} |
| {"current_steps": 1730, "total_steps": 5360, "loss": 7.1036, "lr": 4.2826696006582825e-05, "epoch": 3.2276119402985075, "percentage": 32.28, "elapsed_time": "0:02:59", "remaining_time": "0:06:15", "throughput": 2751.52, "total_tokens": 492576} |
| {"current_steps": 1735, "total_steps": 5360, "loss": 6.8823, "lr": 4.276952876044096e-05, "epoch": 3.236940298507463, "percentage": 32.37, "elapsed_time": "0:02:59", "remaining_time": "0:06:14", "throughput": 2751.86, "total_tokens": 493824} |
| {"current_steps": 1740, "total_steps": 5360, "loss": 7.2438, "lr": 4.2712173105716346e-05, "epoch": 3.246268656716418, "percentage": 32.46, "elapsed_time": "0:02:59", "remaining_time": "0:06:14", "throughput": 2752.89, "total_tokens": 495200} |
| {"current_steps": 1745, "total_steps": 5360, "loss": 6.7313, "lr": 4.265462965054539e-05, "epoch": 3.2555970149253732, "percentage": 32.56, "elapsed_time": "0:03:00", "remaining_time": "0:06:13", "throughput": 2753.72, "total_tokens": 496576} |
| {"current_steps": 1750, "total_steps": 5360, "loss": 6.3991, "lr": 4.259689900505576e-05, "epoch": 3.264925373134328, "percentage": 32.65, "elapsed_time": "0:03:00", "remaining_time": "0:06:12", "throughput": 2755.02, "total_tokens": 498112} |
| {"current_steps": 1755, "total_steps": 5360, "loss": 6.7519, "lr": 4.253898178135985e-05, "epoch": 3.2742537313432836, "percentage": 32.74, "elapsed_time": "0:03:01", "remaining_time": "0:06:12", "throughput": 2756.23, "total_tokens": 499552} |
| {"current_steps": 1760, "total_steps": 5360, "loss": 6.9308, "lr": 4.2480878593548344e-05, "epoch": 3.283582089552239, "percentage": 32.84, "elapsed_time": "0:03:01", "remaining_time": "0:06:11", "throughput": 2757.23, "total_tokens": 500960} |
| {"current_steps": 1765, "total_steps": 5360, "loss": 6.0125, "lr": 4.24225900576837e-05, "epoch": 3.292910447761194, "percentage": 32.93, "elapsed_time": "0:03:02", "remaining_time": "0:06:10", "throughput": 2757.52, "total_tokens": 502208} |
| {"current_steps": 1770, "total_steps": 5360, "loss": 5.9982, "lr": 4.236411679179357e-05, "epoch": 3.3022388059701493, "percentage": 33.02, "elapsed_time": "0:03:02", "remaining_time": "0:06:10", "throughput": 2759.08, "total_tokens": 503808} |
| {"current_steps": 1775, "total_steps": 5360, "loss": 6.1401, "lr": 4.230545941586431e-05, "epoch": 3.3115671641791042, "percentage": 33.12, "elapsed_time": "0:03:03", "remaining_time": "0:06:09", "throughput": 2760.23, "total_tokens": 505248} |
| {"current_steps": 1780, "total_steps": 5360, "loss": 6.5042, "lr": 4.224661855183435e-05, "epoch": 3.3208955223880596, "percentage": 33.21, "elapsed_time": "0:03:03", "remaining_time": "0:06:09", "throughput": 2762.45, "total_tokens": 507072} |
| {"current_steps": 1785, "total_steps": 5360, "loss": 7.3425, "lr": 4.218759482358765e-05, "epoch": 3.330223880597015, "percentage": 33.3, "elapsed_time": "0:03:04", "remaining_time": "0:06:08", "throughput": 2763.75, "total_tokens": 508576} |
| {"current_steps": 1790, "total_steps": 5360, "loss": 6.2476, "lr": 4.212838885694705e-05, "epoch": 3.33955223880597, "percentage": 33.4, "elapsed_time": "0:03:04", "remaining_time": "0:06:07", "throughput": 2764.24, "total_tokens": 509824} |
| {"current_steps": 1795, "total_steps": 5360, "loss": 5.6183, "lr": 4.206900127966764e-05, "epoch": 3.3488805970149254, "percentage": 33.49, "elapsed_time": "0:03:04", "remaining_time": "0:06:07", "throughput": 2765.93, "total_tokens": 511392} |
| {"current_steps": 1800, "total_steps": 5360, "loss": 6.7416, "lr": 4.200943272143013e-05, "epoch": 3.3582089552238807, "percentage": 33.58, "elapsed_time": "0:03:05", "remaining_time": "0:06:06", "throughput": 2766.38, "total_tokens": 512672} |
| {"current_steps": 1805, "total_steps": 5360, "loss": 6.9277, "lr": 4.194968381383414e-05, "epoch": 3.3675373134328357, "percentage": 33.68, "elapsed_time": "0:03:05", "remaining_time": "0:06:05", "throughput": 2767.6, "total_tokens": 514144} |
| {"current_steps": 1810, "total_steps": 5360, "loss": 6.4683, "lr": 4.188975519039151e-05, "epoch": 3.376865671641791, "percentage": 33.77, "elapsed_time": "0:03:06", "remaining_time": "0:06:05", "throughput": 2768.6, "total_tokens": 515584} |
| {"current_steps": 1815, "total_steps": 5360, "loss": 6.5091, "lr": 4.1829647486519596e-05, "epoch": 3.3861940298507465, "percentage": 33.86, "elapsed_time": "0:03:06", "remaining_time": "0:06:04", "throughput": 2769.31, "total_tokens": 516928} |
| {"current_steps": 1820, "total_steps": 5360, "loss": 6.495, "lr": 4.176936133953454e-05, "epoch": 3.3955223880597014, "percentage": 33.96, "elapsed_time": "0:03:07", "remaining_time": "0:06:03", "throughput": 2770.36, "total_tokens": 518432} |
| {"current_steps": 1825, "total_steps": 5360, "loss": 6.0773, "lr": 4.170889738864448e-05, "epoch": 3.404850746268657, "percentage": 34.05, "elapsed_time": "0:03:07", "remaining_time": "0:06:03", "throughput": 2771.6, "total_tokens": 519904} |
| {"current_steps": 1830, "total_steps": 5360, "loss": 6.6777, "lr": 4.16482562749428e-05, "epoch": 3.4141791044776117, "percentage": 34.14, "elapsed_time": "0:03:08", "remaining_time": "0:06:02", "throughput": 2773.23, "total_tokens": 521472} |
| {"current_steps": 1835, "total_steps": 5360, "loss": 6.1763, "lr": 4.158743864140131e-05, "epoch": 3.423507462686567, "percentage": 34.24, "elapsed_time": "0:03:08", "remaining_time": "0:06:02", "throughput": 2774.01, "total_tokens": 522848} |
| {"current_steps": 1840, "total_steps": 5360, "loss": 6.407, "lr": 4.152644513286348e-05, "epoch": 3.4328358208955225, "percentage": 34.33, "elapsed_time": "0:03:08", "remaining_time": "0:06:01", "throughput": 2774.54, "total_tokens": 524160} |
| {"current_steps": 1845, "total_steps": 5360, "loss": 6.5662, "lr": 4.146527639603751e-05, "epoch": 3.4421641791044775, "percentage": 34.42, "elapsed_time": "0:03:09", "remaining_time": "0:06:00", "throughput": 2775.2, "total_tokens": 525504} |
| {"current_steps": 1850, "total_steps": 5360, "loss": 6.1601, "lr": 4.1403933079489585e-05, "epoch": 3.451492537313433, "percentage": 34.51, "elapsed_time": "0:03:09", "remaining_time": "0:06:00", "throughput": 2775.7, "total_tokens": 526816} |
| {"current_steps": 1855, "total_steps": 5360, "loss": 6.4124, "lr": 4.1342415833636904e-05, "epoch": 3.4608208955223883, "percentage": 34.61, "elapsed_time": "0:03:10", "remaining_time": "0:05:59", "throughput": 2776.62, "total_tokens": 528224} |
| {"current_steps": 1860, "total_steps": 5360, "loss": 5.9867, "lr": 4.128072531074084e-05, "epoch": 3.470149253731343, "percentage": 34.7, "elapsed_time": "0:03:10", "remaining_time": "0:05:58", "throughput": 2777.04, "total_tokens": 529504} |
| {"current_steps": 1865, "total_steps": 5360, "loss": 6.4769, "lr": 4.121886216489998e-05, "epoch": 3.4794776119402986, "percentage": 34.79, "elapsed_time": "0:03:11", "remaining_time": "0:05:58", "throughput": 2778.64, "total_tokens": 531072} |
| {"current_steps": 1870, "total_steps": 5360, "loss": 6.6296, "lr": 4.115682705204326e-05, "epoch": 3.4888059701492535, "percentage": 34.89, "elapsed_time": "0:03:11", "remaining_time": "0:05:57", "throughput": 2780.75, "total_tokens": 532832} |
| {"current_steps": 1875, "total_steps": 5360, "loss": 6.1458, "lr": 4.109462062992293e-05, "epoch": 3.498134328358209, "percentage": 34.98, "elapsed_time": "0:03:12", "remaining_time": "0:05:57", "throughput": 2781.54, "total_tokens": 534272} |
| {"current_steps": 1876, "total_steps": 5360, "eval_loss": 6.530898094177246, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:03:14", "remaining_time": "0:06:01", "throughput": 2745.36, "total_tokens": 534688} |
| {"current_steps": 1880, "total_steps": 5360, "loss": 6.7196, "lr": 4.103224355810761e-05, "epoch": 3.5074626865671643, "percentage": 35.07, "elapsed_time": "0:03:16", "remaining_time": "0:06:02", "throughput": 2733.01, "total_tokens": 535872} |
| {"current_steps": 1885, "total_steps": 5360, "loss": 6.6623, "lr": 4.096969649797534e-05, "epoch": 3.5167910447761193, "percentage": 35.17, "elapsed_time": "0:03:16", "remaining_time": "0:06:02", "throughput": 2734.38, "total_tokens": 537376} |
| {"current_steps": 1890, "total_steps": 5360, "loss": 5.9926, "lr": 4.0906980112706494e-05, "epoch": 3.5261194029850746, "percentage": 35.26, "elapsed_time": "0:03:16", "remaining_time": "0:06:01", "throughput": 2735.67, "total_tokens": 538880} |
| {"current_steps": 1895, "total_steps": 5360, "loss": 6.4891, "lr": 4.08440950672768e-05, "epoch": 3.53544776119403, "percentage": 35.35, "elapsed_time": "0:03:17", "remaining_time": "0:06:01", "throughput": 2737.06, "total_tokens": 540512} |
| {"current_steps": 1900, "total_steps": 5360, "loss": 6.9897, "lr": 4.078104202845027e-05, "epoch": 3.544776119402985, "percentage": 35.45, "elapsed_time": "0:03:17", "remaining_time": "0:06:00", "throughput": 2737.97, "total_tokens": 541920} |
| {"current_steps": 1905, "total_steps": 5360, "loss": 6.0652, "lr": 4.071782166477213e-05, "epoch": 3.5541044776119404, "percentage": 35.54, "elapsed_time": "0:03:18", "remaining_time": "0:05:59", "throughput": 2738.81, "total_tokens": 543328} |
| {"current_steps": 1910, "total_steps": 5360, "loss": 6.3105, "lr": 4.065443464656174e-05, "epoch": 3.5634328358208958, "percentage": 35.63, "elapsed_time": "0:03:18", "remaining_time": "0:05:59", "throughput": 2739.95, "total_tokens": 544800} |
| {"current_steps": 1915, "total_steps": 5360, "loss": 6.2764, "lr": 4.0590881645905475e-05, "epoch": 3.5727611940298507, "percentage": 35.73, "elapsed_time": "0:03:19", "remaining_time": "0:05:58", "throughput": 2740.91, "total_tokens": 546208} |
| {"current_steps": 1920, "total_steps": 5360, "loss": 6.4578, "lr": 4.052716333664963e-05, "epoch": 3.582089552238806, "percentage": 35.82, "elapsed_time": "0:03:19", "remaining_time": "0:05:57", "throughput": 2741.84, "total_tokens": 547616} |
| {"current_steps": 1925, "total_steps": 5360, "loss": 6.3317, "lr": 4.046328039439321e-05, "epoch": 3.591417910447761, "percentage": 35.91, "elapsed_time": "0:03:20", "remaining_time": "0:05:57", "throughput": 2742.98, "total_tokens": 549088} |
| {"current_steps": 1930, "total_steps": 5360, "loss": 6.5272, "lr": 4.039923349648084e-05, "epoch": 3.6007462686567164, "percentage": 36.01, "elapsed_time": "0:03:20", "remaining_time": "0:05:56", "throughput": 2743.8, "total_tokens": 550464} |
| {"current_steps": 1935, "total_steps": 5360, "loss": 5.8427, "lr": 4.0335023321995545e-05, "epoch": 3.6100746268656714, "percentage": 36.1, "elapsed_time": "0:03:21", "remaining_time": "0:05:55", "throughput": 2745.18, "total_tokens": 552032} |
| {"current_steps": 1940, "total_steps": 5360, "loss": 6.3749, "lr": 4.0270650551751546e-05, "epoch": 3.6194029850746268, "percentage": 36.19, "elapsed_time": "0:03:21", "remaining_time": "0:05:55", "throughput": 2745.7, "total_tokens": 553344} |
| {"current_steps": 1945, "total_steps": 5360, "loss": 6.5775, "lr": 4.020611586828705e-05, "epoch": 3.628731343283582, "percentage": 36.29, "elapsed_time": "0:03:21", "remaining_time": "0:05:54", "throughput": 2746.02, "total_tokens": 554592} |
| {"current_steps": 1950, "total_steps": 5360, "loss": 6.7602, "lr": 4.0141419955857044e-05, "epoch": 3.638059701492537, "percentage": 36.38, "elapsed_time": "0:03:22", "remaining_time": "0:05:53", "throughput": 2747.17, "total_tokens": 556064} |
| {"current_steps": 1955, "total_steps": 5360, "loss": 5.6166, "lr": 4.007656350042595e-05, "epoch": 3.6473880597014925, "percentage": 36.47, "elapsed_time": "0:03:22", "remaining_time": "0:05:53", "throughput": 2748.29, "total_tokens": 557536} |
| {"current_steps": 1960, "total_steps": 5360, "loss": 6.717, "lr": 4.001154718966048e-05, "epoch": 3.656716417910448, "percentage": 36.57, "elapsed_time": "0:03:23", "remaining_time": "0:05:52", "throughput": 2749.33, "total_tokens": 558976} |
| {"current_steps": 1965, "total_steps": 5360, "loss": 5.7437, "lr": 3.994637171292223e-05, "epoch": 3.666044776119403, "percentage": 36.66, "elapsed_time": "0:03:23", "remaining_time": "0:05:52", "throughput": 2749.56, "total_tokens": 560192} |
| {"current_steps": 1970, "total_steps": 5360, "loss": 6.5671, "lr": 3.988103776126042e-05, "epoch": 3.675373134328358, "percentage": 36.75, "elapsed_time": "0:03:24", "remaining_time": "0:05:51", "throughput": 2750.03, "total_tokens": 561472} |
| {"current_steps": 1975, "total_steps": 5360, "loss": 6.267, "lr": 3.9815546027404603e-05, "epoch": 3.6847014925373136, "percentage": 36.85, "elapsed_time": "0:03:24", "remaining_time": "0:05:50", "throughput": 2751.07, "total_tokens": 562912} |
| {"current_steps": 1980, "total_steps": 5360, "loss": 6.494, "lr": 3.974989720575724e-05, "epoch": 3.6940298507462686, "percentage": 36.94, "elapsed_time": "0:03:25", "remaining_time": "0:05:50", "throughput": 2751.87, "total_tokens": 564288} |
| {"current_steps": 1985, "total_steps": 5360, "loss": 6.3349, "lr": 3.9684091992386393e-05, "epoch": 3.703358208955224, "percentage": 37.03, "elapsed_time": "0:03:25", "remaining_time": "0:05:49", "throughput": 2752.67, "total_tokens": 565664} |
| {"current_steps": 1990, "total_steps": 5360, "loss": 6.595, "lr": 3.961813108501833e-05, "epoch": 3.7126865671641793, "percentage": 37.13, "elapsed_time": "0:03:25", "remaining_time": "0:05:48", "throughput": 2753.45, "total_tokens": 567040} |
| {"current_steps": 1995, "total_steps": 5360, "loss": 6.1501, "lr": 3.9552015183030136e-05, "epoch": 3.7220149253731343, "percentage": 37.22, "elapsed_time": "0:03:26", "remaining_time": "0:05:48", "throughput": 2753.85, "total_tokens": 568320} |
| {"current_steps": 2000, "total_steps": 5360, "loss": 6.5023, "lr": 3.9485744987442266e-05, "epoch": 3.7313432835820897, "percentage": 37.31, "elapsed_time": "0:03:26", "remaining_time": "0:05:47", "throughput": 2754.53, "total_tokens": 569696} |
| {"current_steps": 2005, "total_steps": 5360, "loss": 6.8004, "lr": 3.9419321200911155e-05, "epoch": 3.7406716417910446, "percentage": 37.41, "elapsed_time": "0:03:27", "remaining_time": "0:05:46", "throughput": 2756.09, "total_tokens": 571296} |
| {"current_steps": 2010, "total_steps": 5360, "loss": 6.9846, "lr": 3.9352744527721754e-05, "epoch": 3.75, "percentage": 37.5, "elapsed_time": "0:03:27", "remaining_time": "0:05:46", "throughput": 2757.17, "total_tokens": 572768} |
| {"current_steps": 2015, "total_steps": 5360, "loss": 6.1147, "lr": 3.928601567378003e-05, "epoch": 3.7593283582089554, "percentage": 37.59, "elapsed_time": "0:03:28", "remaining_time": "0:05:45", "throughput": 2757.66, "total_tokens": 574080} |
| {"current_steps": 2020, "total_steps": 5360, "loss": 6.2397, "lr": 3.921913534660552e-05, "epoch": 3.7686567164179103, "percentage": 37.69, "elapsed_time": "0:03:28", "remaining_time": "0:05:44", "throughput": 2758.24, "total_tokens": 575456} |
| {"current_steps": 2025, "total_steps": 5360, "loss": 6.8914, "lr": 3.915210425532383e-05, "epoch": 3.7779850746268657, "percentage": 37.78, "elapsed_time": "0:03:29", "remaining_time": "0:05:44", "throughput": 2759.06, "total_tokens": 576864} |
| {"current_steps": 2030, "total_steps": 5360, "loss": 6.6493, "lr": 3.908492311065909e-05, "epoch": 3.7873134328358207, "percentage": 37.87, "elapsed_time": "0:03:29", "remaining_time": "0:05:43", "throughput": 2759.98, "total_tokens": 578304} |
| {"current_steps": 2035, "total_steps": 5360, "loss": 6.654, "lr": 3.901759262492643e-05, "epoch": 3.796641791044776, "percentage": 37.97, "elapsed_time": "0:03:29", "remaining_time": "0:05:43", "throughput": 2760.9, "total_tokens": 579744} |
| {"current_steps": 2040, "total_steps": 5360, "loss": 6.6757, "lr": 3.895011351202443e-05, "epoch": 3.8059701492537314, "percentage": 38.06, "elapsed_time": "0:03:30", "remaining_time": "0:05:42", "throughput": 2761.31, "total_tokens": 581088} |
| {"current_steps": 2045, "total_steps": 5360, "loss": 6.9096, "lr": 3.888248648742756e-05, "epoch": 3.8152985074626864, "percentage": 38.15, "elapsed_time": "0:03:30", "remaining_time": "0:05:41", "throughput": 2762.25, "total_tokens": 582560} |
| {"current_steps": 2050, "total_steps": 5360, "loss": 6.2226, "lr": 3.881471226817858e-05, "epoch": 3.824626865671642, "percentage": 38.25, "elapsed_time": "0:03:31", "remaining_time": "0:05:41", "throughput": 2763.25, "total_tokens": 584000} |
| {"current_steps": 2055, "total_steps": 5360, "loss": 6.2206, "lr": 3.874679157288092e-05, "epoch": 3.833955223880597, "percentage": 38.34, "elapsed_time": "0:03:31", "remaining_time": "0:05:40", "throughput": 2763.66, "total_tokens": 585248} |
| {"current_steps": 2060, "total_steps": 5360, "loss": 6.6818, "lr": 3.86787251216911e-05, "epoch": 3.843283582089552, "percentage": 38.43, "elapsed_time": "0:03:32", "remaining_time": "0:05:39", "throughput": 2764.78, "total_tokens": 586720} |
| {"current_steps": 2065, "total_steps": 5360, "loss": 6.701, "lr": 3.8610513636311073e-05, "epoch": 3.8526119402985075, "percentage": 38.53, "elapsed_time": "0:03:32", "remaining_time": "0:05:39", "throughput": 2766.18, "total_tokens": 588352} |
| {"current_steps": 2070, "total_steps": 5360, "loss": 6.5315, "lr": 3.854215783998058e-05, "epoch": 3.861940298507463, "percentage": 38.62, "elapsed_time": "0:03:33", "remaining_time": "0:05:38", "throughput": 2766.6, "total_tokens": 589632} |
| {"current_steps": 2075, "total_steps": 5360, "loss": 5.8164, "lr": 3.8473658457469466e-05, "epoch": 3.871268656716418, "percentage": 38.71, "elapsed_time": "0:03:33", "remaining_time": "0:05:38", "throughput": 2767.57, "total_tokens": 591072} |
| {"current_steps": 2080, "total_steps": 5360, "loss": 6.5248, "lr": 3.840501621507003e-05, "epoch": 3.8805970149253732, "percentage": 38.81, "elapsed_time": "0:03:34", "remaining_time": "0:05:37", "throughput": 2768.43, "total_tokens": 592544} |
| {"current_steps": 2085, "total_steps": 5360, "loss": 6.2466, "lr": 3.833623184058926e-05, "epoch": 3.8899253731343286, "percentage": 38.9, "elapsed_time": "0:03:34", "remaining_time": "0:05:36", "throughput": 2769.79, "total_tokens": 594112} |
| {"current_steps": 2090, "total_steps": 5360, "loss": 6.3241, "lr": 3.826730606334119e-05, "epoch": 3.8992537313432836, "percentage": 38.99, "elapsed_time": "0:03:34", "remaining_time": "0:05:36", "throughput": 2771.12, "total_tokens": 595744} |
| {"current_steps": 2095, "total_steps": 5360, "loss": 6.4945, "lr": 3.819823961413912e-05, "epoch": 3.908582089552239, "percentage": 39.09, "elapsed_time": "0:03:35", "remaining_time": "0:05:35", "throughput": 2771.8, "total_tokens": 597184} |
| {"current_steps": 2100, "total_steps": 5360, "loss": 6.8721, "lr": 3.812903322528789e-05, "epoch": 3.917910447761194, "percentage": 39.18, "elapsed_time": "0:03:35", "remaining_time": "0:05:35", "throughput": 2773.36, "total_tokens": 598816} |
| {"current_steps": 2105, "total_steps": 5360, "loss": 6.3736, "lr": 3.805968763057609e-05, "epoch": 3.9272388059701493, "percentage": 39.27, "elapsed_time": "0:03:36", "remaining_time": "0:05:34", "throughput": 2773.99, "total_tokens": 600192} |
| {"current_steps": 2110, "total_steps": 5360, "loss": 6.1833, "lr": 3.7990203565268314e-05, "epoch": 3.9365671641791042, "percentage": 39.37, "elapsed_time": "0:03:36", "remaining_time": "0:05:33", "throughput": 2774.33, "total_tokens": 601472} |
| {"current_steps": 2115, "total_steps": 5360, "loss": 6.2474, "lr": 3.792058176609734e-05, "epoch": 3.9458955223880596, "percentage": 39.46, "elapsed_time": "0:03:37", "remaining_time": "0:05:33", "throughput": 2775.12, "total_tokens": 602880} |
| {"current_steps": 2120, "total_steps": 5360, "loss": 6.5263, "lr": 3.785082297125631e-05, "epoch": 3.955223880597015, "percentage": 39.55, "elapsed_time": "0:03:37", "remaining_time": "0:05:32", "throughput": 2776.32, "total_tokens": 604416} |
| {"current_steps": 2125, "total_steps": 5360, "loss": 6.5571, "lr": 3.7780927920390964e-05, "epoch": 3.96455223880597, "percentage": 39.65, "elapsed_time": "0:03:38", "remaining_time": "0:05:32", "throughput": 2776.62, "total_tokens": 605696} |
| {"current_steps": 2130, "total_steps": 5360, "loss": 6.8228, "lr": 3.771089735459168e-05, "epoch": 3.9738805970149254, "percentage": 39.74, "elapsed_time": "0:03:38", "remaining_time": "0:05:31", "throughput": 2777.19, "total_tokens": 607040} |
| {"current_steps": 2135, "total_steps": 5360, "loss": 6.2469, "lr": 3.7640732016385745e-05, "epoch": 3.9832089552238807, "percentage": 39.83, "elapsed_time": "0:03:39", "remaining_time": "0:05:30", "throughput": 2778.42, "total_tokens": 608608} |
| {"current_steps": 2140, "total_steps": 5360, "loss": 6.4748, "lr": 3.757043264972941e-05, "epoch": 3.9925373134328357, "percentage": 39.93, "elapsed_time": "0:03:39", "remaining_time": "0:05:30", "throughput": 2779.2, "total_tokens": 609984} |
| {"current_steps": 2144, "total_steps": 5360, "eval_loss": 6.432187080383301, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:03:42", "remaining_time": "0:05:33", "throughput": 2745.93, "total_tokens": 610944} |
| {"current_steps": 2145, "total_steps": 5360, "loss": 5.8664, "lr": 3.7500000000000003e-05, "epoch": 4.001865671641791, "percentage": 40.02, "elapsed_time": "0:03:43", "remaining_time": "0:05:35", "throughput": 2731.3, "total_tokens": 611200} |
| {"current_steps": 2150, "total_steps": 5360, "loss": 6.1699, "lr": 3.742943481398805e-05, "epoch": 4.0111940298507465, "percentage": 40.11, "elapsed_time": "0:03:44", "remaining_time": "0:05:34", "throughput": 2731.79, "total_tokens": 612512} |
| {"current_steps": 2155, "total_steps": 5360, "loss": 6.1006, "lr": 3.7358737839889356e-05, "epoch": 4.020522388059701, "percentage": 40.21, "elapsed_time": "0:03:44", "remaining_time": "0:05:34", "throughput": 2732.64, "total_tokens": 613920} |
| {"current_steps": 2160, "total_steps": 5360, "loss": 6.1764, "lr": 3.728790982729705e-05, "epoch": 4.029850746268656, "percentage": 40.3, "elapsed_time": "0:03:45", "remaining_time": "0:05:33", "throughput": 2733.14, "total_tokens": 615264} |
| {"current_steps": 2165, "total_steps": 5360, "loss": 6.2364, "lr": 3.721695152719364e-05, "epoch": 4.039179104477612, "percentage": 40.39, "elapsed_time": "0:03:45", "remaining_time": "0:05:32", "throughput": 2733.47, "total_tokens": 616576} |
| {"current_steps": 2170, "total_steps": 5360, "loss": 6.1802, "lr": 3.7145863691943076e-05, "epoch": 4.048507462686567, "percentage": 40.49, "elapsed_time": "0:03:46", "remaining_time": "0:05:32", "throughput": 2734.2, "total_tokens": 617984} |
| {"current_steps": 2175, "total_steps": 5360, "loss": 6.2227, "lr": 3.707464707528275e-05, "epoch": 4.057835820895522, "percentage": 40.58, "elapsed_time": "0:03:46", "remaining_time": "0:05:31", "throughput": 2735.27, "total_tokens": 619520} |
| {"current_steps": 2180, "total_steps": 5360, "loss": 6.4914, "lr": 3.700330243231552e-05, "epoch": 4.067164179104478, "percentage": 40.67, "elapsed_time": "0:03:46", "remaining_time": "0:05:31", "throughput": 2735.93, "total_tokens": 620864} |
| {"current_steps": 2185, "total_steps": 5360, "loss": 6.3576, "lr": 3.6931830519501685e-05, "epoch": 4.076492537313433, "percentage": 40.76, "elapsed_time": "0:03:47", "remaining_time": "0:05:30", "throughput": 2736.77, "total_tokens": 622272} |
| {"current_steps": 2190, "total_steps": 5360, "loss": 5.6246, "lr": 3.686023209465096e-05, "epoch": 4.085820895522388, "percentage": 40.86, "elapsed_time": "0:03:47", "remaining_time": "0:05:29", "throughput": 2737.88, "total_tokens": 623840} |
| {"current_steps": 2195, "total_steps": 5360, "loss": 6.6165, "lr": 3.678850791691448e-05, "epoch": 4.095149253731344, "percentage": 40.95, "elapsed_time": "0:03:48", "remaining_time": "0:05:29", "throughput": 2738.65, "total_tokens": 625216} |
| {"current_steps": 2200, "total_steps": 5360, "loss": 6.4202, "lr": 3.671665874677673e-05, "epoch": 4.104477611940299, "percentage": 41.04, "elapsed_time": "0:03:48", "remaining_time": "0:05:28", "throughput": 2739.34, "total_tokens": 626592} |
| {"current_steps": 2205, "total_steps": 5360, "loss": 6.526, "lr": 3.664468534604745e-05, "epoch": 4.1138059701492535, "percentage": 41.14, "elapsed_time": "0:03:49", "remaining_time": "0:05:27", "throughput": 2740.01, "total_tokens": 627968} |
| {"current_steps": 2210, "total_steps": 5360, "loss": 6.0054, "lr": 3.65725884778536e-05, "epoch": 4.123134328358209, "percentage": 41.23, "elapsed_time": "0:03:49", "remaining_time": "0:05:27", "throughput": 2740.52, "total_tokens": 629248} |
| {"current_steps": 2215, "total_steps": 5360, "loss": 5.8631, "lr": 3.650036890663124e-05, "epoch": 4.132462686567164, "percentage": 41.32, "elapsed_time": "0:03:50", "remaining_time": "0:05:26", "throughput": 2742.25, "total_tokens": 631040} |
| {"current_steps": 2220, "total_steps": 5360, "loss": 6.5582, "lr": 3.642802739811747e-05, "epoch": 4.141791044776119, "percentage": 41.42, "elapsed_time": "0:03:50", "remaining_time": "0:05:26", "throughput": 2742.61, "total_tokens": 632320} |
| {"current_steps": 2225, "total_steps": 5360, "loss": 6.6937, "lr": 3.635556471934224e-05, "epoch": 4.151119402985074, "percentage": 41.51, "elapsed_time": "0:03:51", "remaining_time": "0:05:25", "throughput": 2743.43, "total_tokens": 633792} |
| {"current_steps": 2230, "total_steps": 5360, "loss": 6.5748, "lr": 3.628298163862029e-05, "epoch": 4.16044776119403, "percentage": 41.6, "elapsed_time": "0:03:51", "remaining_time": "0:05:24", "throughput": 2744.56, "total_tokens": 635328} |
| {"current_steps": 2235, "total_steps": 5360, "loss": 6.0516, "lr": 3.621027892554295e-05, "epoch": 4.169776119402985, "percentage": 41.7, "elapsed_time": "0:03:51", "remaining_time": "0:05:24", "throughput": 2745.65, "total_tokens": 636864} |
| {"current_steps": 2240, "total_steps": 5360, "loss": 5.9094, "lr": 3.613745735096999e-05, "epoch": 4.17910447761194, "percentage": 41.79, "elapsed_time": "0:03:52", "remaining_time": "0:05:23", "throughput": 2745.86, "total_tokens": 638112} |
| {"current_steps": 2245, "total_steps": 5360, "loss": 6.2744, "lr": 3.606451768702151e-05, "epoch": 4.188432835820896, "percentage": 41.88, "elapsed_time": "0:03:52", "remaining_time": "0:05:23", "throughput": 2746.3, "total_tokens": 639456} |
| {"current_steps": 2250, "total_steps": 5360, "loss": 6.1296, "lr": 3.599146070706964e-05, "epoch": 4.197761194029851, "percentage": 41.98, "elapsed_time": "0:03:53", "remaining_time": "0:05:22", "throughput": 2746.54, "total_tokens": 640736} |
| {"current_steps": 2255, "total_steps": 5360, "loss": 6.0515, "lr": 3.5918287185730414e-05, "epoch": 4.207089552238806, "percentage": 42.07, "elapsed_time": "0:03:53", "remaining_time": "0:05:21", "throughput": 2747.24, "total_tokens": 642208} |
| {"current_steps": 2260, "total_steps": 5360, "loss": 6.505, "lr": 3.5844997898855566e-05, "epoch": 4.2164179104477615, "percentage": 42.16, "elapsed_time": "0:03:54", "remaining_time": "0:05:21", "throughput": 2747.93, "total_tokens": 643616} |
| {"current_steps": 2265, "total_steps": 5360, "loss": 6.9843, "lr": 3.5771593623524265e-05, "epoch": 4.225746268656716, "percentage": 42.26, "elapsed_time": "0:03:54", "remaining_time": "0:05:20", "throughput": 2748.58, "total_tokens": 645024} |
| {"current_steps": 2270, "total_steps": 5360, "loss": 6.3727, "lr": 3.569807513803488e-05, "epoch": 4.235074626865671, "percentage": 42.35, "elapsed_time": "0:03:55", "remaining_time": "0:05:20", "throughput": 2749.41, "total_tokens": 646464} |
| {"current_steps": 2275, "total_steps": 5360, "loss": 6.8002, "lr": 3.5624443221896776e-05, "epoch": 4.244402985074627, "percentage": 42.44, "elapsed_time": "0:03:55", "remaining_time": "0:05:19", "throughput": 2750.46, "total_tokens": 647968} |
| {"current_steps": 2280, "total_steps": 5360, "loss": 6.6819, "lr": 3.555069865582197e-05, "epoch": 4.253731343283582, "percentage": 42.54, "elapsed_time": "0:03:56", "remaining_time": "0:05:18", "throughput": 2750.95, "total_tokens": 649312} |
| {"current_steps": 2285, "total_steps": 5360, "loss": 6.133, "lr": 3.547684222171692e-05, "epoch": 4.263059701492537, "percentage": 42.63, "elapsed_time": "0:03:56", "remaining_time": "0:05:18", "throughput": 2751.41, "total_tokens": 650656} |
| {"current_steps": 2290, "total_steps": 5360, "loss": 6.7494, "lr": 3.54028747026742e-05, "epoch": 4.272388059701493, "percentage": 42.72, "elapsed_time": "0:03:56", "remaining_time": "0:05:17", "throughput": 2752.0, "total_tokens": 652032} |
| {"current_steps": 2295, "total_steps": 5360, "loss": 7.0372, "lr": 3.532879688296421e-05, "epoch": 4.281716417910448, "percentage": 42.82, "elapsed_time": "0:03:57", "remaining_time": "0:05:17", "throughput": 2752.93, "total_tokens": 653504} |
| {"current_steps": 2300, "total_steps": 5360, "loss": 6.6207, "lr": 3.5254609548026865e-05, "epoch": 4.291044776119403, "percentage": 42.91, "elapsed_time": "0:03:57", "remaining_time": "0:05:16", "throughput": 2753.56, "total_tokens": 654912} |
| {"current_steps": 2305, "total_steps": 5360, "loss": 7.1731, "lr": 3.518031348446324e-05, "epoch": 4.300373134328359, "percentage": 43.0, "elapsed_time": "0:03:58", "remaining_time": "0:05:15", "throughput": 2754.13, "total_tokens": 656256} |
| {"current_steps": 2310, "total_steps": 5360, "loss": 6.5055, "lr": 3.5105909480027276e-05, "epoch": 4.309701492537314, "percentage": 43.1, "elapsed_time": "0:03:58", "remaining_time": "0:05:15", "throughput": 2755.26, "total_tokens": 657792} |
| {"current_steps": 2315, "total_steps": 5360, "loss": 5.8665, "lr": 3.5031398323617366e-05, "epoch": 4.3190298507462686, "percentage": 43.19, "elapsed_time": "0:03:59", "remaining_time": "0:05:14", "throughput": 2755.9, "total_tokens": 659264} |
| {"current_steps": 2320, "total_steps": 5360, "loss": 6.0873, "lr": 3.4956780805268066e-05, "epoch": 4.3283582089552235, "percentage": 43.28, "elapsed_time": "0:03:59", "remaining_time": "0:05:14", "throughput": 2756.51, "total_tokens": 660640} |
| {"current_steps": 2325, "total_steps": 5360, "loss": 6.3679, "lr": 3.4882057716141635e-05, "epoch": 4.337686567164179, "percentage": 43.38, "elapsed_time": "0:04:00", "remaining_time": "0:05:13", "throughput": 2757.09, "total_tokens": 662016} |
| {"current_steps": 2330, "total_steps": 5360, "loss": 6.804, "lr": 3.480722984851972e-05, "epoch": 4.347014925373134, "percentage": 43.47, "elapsed_time": "0:04:00", "remaining_time": "0:05:12", "throughput": 2757.43, "total_tokens": 663392} |
| {"current_steps": 2335, "total_steps": 5360, "loss": 5.9175, "lr": 3.473229799579492e-05, "epoch": 4.356343283582089, "percentage": 43.56, "elapsed_time": "0:04:01", "remaining_time": "0:05:12", "throughput": 2758.23, "total_tokens": 664928} |
| {"current_steps": 2340, "total_steps": 5360, "loss": 6.4613, "lr": 3.465726295246236e-05, "epoch": 4.365671641791045, "percentage": 43.66, "elapsed_time": "0:04:01", "remaining_time": "0:05:11", "throughput": 2758.43, "total_tokens": 666176} |
| {"current_steps": 2345, "total_steps": 5360, "loss": 6.4258, "lr": 3.45821255141113e-05, "epoch": 4.375, "percentage": 43.75, "elapsed_time": "0:04:01", "remaining_time": "0:05:11", "throughput": 2759.05, "total_tokens": 667552} |
| {"current_steps": 2350, "total_steps": 5360, "loss": 6.3671, "lr": 3.450688647741668e-05, "epoch": 4.384328358208955, "percentage": 43.84, "elapsed_time": "0:04:02", "remaining_time": "0:05:10", "throughput": 2760.08, "total_tokens": 669056} |
| {"current_steps": 2355, "total_steps": 5360, "loss": 6.2882, "lr": 3.443154664013067e-05, "epoch": 4.393656716417911, "percentage": 43.94, "elapsed_time": "0:04:02", "remaining_time": "0:05:09", "throughput": 2761.25, "total_tokens": 670592} |
| {"current_steps": 2360, "total_steps": 5360, "loss": 6.6846, "lr": 3.4356106801074245e-05, "epoch": 4.402985074626866, "percentage": 44.03, "elapsed_time": "0:04:03", "remaining_time": "0:05:09", "throughput": 2762.2, "total_tokens": 672096} |
| {"current_steps": 2365, "total_steps": 5360, "loss": 7.0621, "lr": 3.4280567760128656e-05, "epoch": 4.412313432835821, "percentage": 44.12, "elapsed_time": "0:04:03", "remaining_time": "0:05:08", "throughput": 2763.01, "total_tokens": 673568} |
| {"current_steps": 2370, "total_steps": 5360, "loss": 6.1608, "lr": 3.4204930318227016e-05, "epoch": 4.4216417910447765, "percentage": 44.22, "elapsed_time": "0:04:04", "remaining_time": "0:05:08", "throughput": 2763.69, "total_tokens": 674976} |
| {"current_steps": 2375, "total_steps": 5360, "loss": 6.4338, "lr": 3.4129195277345724e-05, "epoch": 4.4309701492537314, "percentage": 44.31, "elapsed_time": "0:04:04", "remaining_time": "0:05:07", "throughput": 2764.04, "total_tokens": 676288} |
| {"current_steps": 2380, "total_steps": 5360, "loss": 6.3068, "lr": 3.405336344049607e-05, "epoch": 4.440298507462686, "percentage": 44.4, "elapsed_time": "0:04:05", "remaining_time": "0:05:06", "throughput": 2765.18, "total_tokens": 677888} |
| {"current_steps": 2385, "total_steps": 5360, "loss": 6.3268, "lr": 3.397743561171562e-05, "epoch": 4.449626865671641, "percentage": 44.5, "elapsed_time": "0:04:05", "remaining_time": "0:05:06", "throughput": 2765.76, "total_tokens": 679328} |
| {"current_steps": 2390, "total_steps": 5360, "loss": 6.2514, "lr": 3.390141259605975e-05, "epoch": 4.458955223880597, "percentage": 44.59, "elapsed_time": "0:04:06", "remaining_time": "0:05:05", "throughput": 2766.38, "total_tokens": 680736} |
| {"current_steps": 2395, "total_steps": 5360, "loss": 6.6166, "lr": 3.3825295199593084e-05, "epoch": 4.468283582089552, "percentage": 44.68, "elapsed_time": "0:04:06", "remaining_time": "0:05:05", "throughput": 2767.56, "total_tokens": 682304} |
| {"current_steps": 2400, "total_steps": 5360, "loss": 6.3584, "lr": 3.3749084229380976e-05, "epoch": 4.477611940298507, "percentage": 44.78, "elapsed_time": "0:04:06", "remaining_time": "0:05:04", "throughput": 2768.97, "total_tokens": 683936} |
| {"current_steps": 2405, "total_steps": 5360, "loss": 6.4258, "lr": 3.367278049348093e-05, "epoch": 4.486940298507463, "percentage": 44.87, "elapsed_time": "0:04:07", "remaining_time": "0:05:04", "throughput": 2769.57, "total_tokens": 685312} |
| {"current_steps": 2410, "total_steps": 5360, "loss": 6.0796, "lr": 3.3596384800934e-05, "epoch": 4.496268656716418, "percentage": 44.96, "elapsed_time": "0:04:07", "remaining_time": "0:05:03", "throughput": 2770.24, "total_tokens": 686752} |
| {"current_steps": 2412, "total_steps": 5360, "eval_loss": 6.357021808624268, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:04:10", "remaining_time": "0:05:06", "throughput": 2741.67, "total_tokens": 687328} |
| {"current_steps": 2415, "total_steps": 5360, "loss": 6.05, "lr": 3.351989796175628e-05, "epoch": 4.505597014925373, "percentage": 45.06, "elapsed_time": "0:04:12", "remaining_time": "0:05:07", "throughput": 2730.35, "total_tokens": 688096} |
| {"current_steps": 2420, "total_steps": 5360, "loss": 6.0463, "lr": 3.3443320786930275e-05, "epoch": 4.514925373134329, "percentage": 45.15, "elapsed_time": "0:04:12", "remaining_time": "0:05:06", "throughput": 2731.43, "total_tokens": 689664} |
| {"current_steps": 2425, "total_steps": 5360, "loss": 5.9086, "lr": 3.3366654088396326e-05, "epoch": 4.524253731343284, "percentage": 45.24, "elapsed_time": "0:04:12", "remaining_time": "0:05:06", "throughput": 2731.64, "total_tokens": 690912} |
| {"current_steps": 2430, "total_steps": 5360, "loss": 5.9177, "lr": 3.328989867904396e-05, "epoch": 4.5335820895522385, "percentage": 45.34, "elapsed_time": "0:04:13", "remaining_time": "0:05:05", "throughput": 2732.23, "total_tokens": 692320} |
| {"current_steps": 2435, "total_steps": 5360, "loss": 5.967, "lr": 3.3213055372703305e-05, "epoch": 4.542910447761194, "percentage": 45.43, "elapsed_time": "0:04:13", "remaining_time": "0:05:04", "throughput": 2732.3, "total_tokens": 693568} |
| {"current_steps": 2440, "total_steps": 5360, "loss": 6.7199, "lr": 3.313612498413646e-05, "epoch": 4.552238805970149, "percentage": 45.52, "elapsed_time": "0:04:14", "remaining_time": "0:05:04", "throughput": 2733.53, "total_tokens": 695168} |
| {"current_steps": 2445, "total_steps": 5360, "loss": 5.6648, "lr": 3.305910832902884e-05, "epoch": 4.561567164179104, "percentage": 45.62, "elapsed_time": "0:04:14", "remaining_time": "0:05:03", "throughput": 2733.68, "total_tokens": 696384} |
| {"current_steps": 2450, "total_steps": 5360, "loss": 6.0214, "lr": 3.298200622398054e-05, "epoch": 4.57089552238806, "percentage": 45.71, "elapsed_time": "0:04:15", "remaining_time": "0:05:03", "throughput": 2734.39, "total_tokens": 697792} |
| {"current_steps": 2455, "total_steps": 5360, "loss": 6.3854, "lr": 3.290481948649767e-05, "epoch": 4.580223880597015, "percentage": 45.8, "elapsed_time": "0:04:15", "remaining_time": "0:05:02", "throughput": 2735.21, "total_tokens": 699232} |
| {"current_steps": 2460, "total_steps": 5360, "loss": 5.8858, "lr": 3.282754893498369e-05, "epoch": 4.58955223880597, "percentage": 45.9, "elapsed_time": "0:04:16", "remaining_time": "0:05:01", "throughput": 2736.12, "total_tokens": 700704} |
| {"current_steps": 2465, "total_steps": 5360, "loss": 6.2053, "lr": 3.275019538873071e-05, "epoch": 4.598880597014926, "percentage": 45.99, "elapsed_time": "0:04:16", "remaining_time": "0:05:01", "throughput": 2736.57, "total_tokens": 702016} |
| {"current_steps": 2470, "total_steps": 5360, "loss": 6.2383, "lr": 3.267275966791088e-05, "epoch": 4.608208955223881, "percentage": 46.08, "elapsed_time": "0:04:16", "remaining_time": "0:05:00", "throughput": 2737.4, "total_tokens": 703456} |
| {"current_steps": 2475, "total_steps": 5360, "loss": 6.4459, "lr": 3.259524259356759e-05, "epoch": 4.617537313432836, "percentage": 46.18, "elapsed_time": "0:04:17", "remaining_time": "0:05:00", "throughput": 2738.24, "total_tokens": 704896} |
| {"current_steps": 2480, "total_steps": 5360, "loss": 6.5718, "lr": 3.251764498760683e-05, "epoch": 4.6268656716417915, "percentage": 46.27, "elapsed_time": "0:04:17", "remaining_time": "0:04:59", "throughput": 2738.86, "total_tokens": 706272} |
| {"current_steps": 2485, "total_steps": 5360, "loss": 6.808, "lr": 3.243996767278846e-05, "epoch": 4.6361940298507465, "percentage": 46.36, "elapsed_time": "0:04:18", "remaining_time": "0:04:58", "throughput": 2739.76, "total_tokens": 707744} |
| {"current_steps": 2490, "total_steps": 5360, "loss": 6.5115, "lr": 3.2362211472717484e-05, "epoch": 4.645522388059701, "percentage": 46.46, "elapsed_time": "0:04:18", "remaining_time": "0:04:58", "throughput": 2740.46, "total_tokens": 709120} |
| {"current_steps": 2495, "total_steps": 5360, "loss": 5.607, "lr": 3.228437721183531e-05, "epoch": 4.654850746268656, "percentage": 46.55, "elapsed_time": "0:04:19", "remaining_time": "0:04:57", "throughput": 2741.25, "total_tokens": 710592} |
| {"current_steps": 2500, "total_steps": 5360, "loss": 6.2247, "lr": 3.220646571541105e-05, "epoch": 4.664179104477612, "percentage": 46.64, "elapsed_time": "0:04:19", "remaining_time": "0:04:57", "throughput": 2741.91, "total_tokens": 712000} |
| {"current_steps": 2505, "total_steps": 5360, "loss": 6.4959, "lr": 3.2128477809532684e-05, "epoch": 4.673507462686567, "percentage": 46.74, "elapsed_time": "0:04:20", "remaining_time": "0:04:56", "throughput": 2742.71, "total_tokens": 713408} |
| {"current_steps": 2510, "total_steps": 5360, "loss": 6.466, "lr": 3.2050414321098385e-05, "epoch": 4.682835820895522, "percentage": 46.83, "elapsed_time": "0:04:20", "remaining_time": "0:04:55", "throughput": 2743.12, "total_tokens": 714688} |
| {"current_steps": 2515, "total_steps": 5360, "loss": 6.6022, "lr": 3.197227607780774e-05, "epoch": 4.692164179104478, "percentage": 46.92, "elapsed_time": "0:04:20", "remaining_time": "0:04:55", "throughput": 2743.94, "total_tokens": 716128} |
| {"current_steps": 2520, "total_steps": 5360, "loss": 6.836, "lr": 3.1894063908152916e-05, "epoch": 4.701492537313433, "percentage": 47.01, "elapsed_time": "0:04:21", "remaining_time": "0:04:54", "throughput": 2744.71, "total_tokens": 717632} |
| {"current_steps": 2525, "total_steps": 5360, "loss": 5.9339, "lr": 3.181577864140992e-05, "epoch": 4.710820895522388, "percentage": 47.11, "elapsed_time": "0:04:21", "remaining_time": "0:04:54", "throughput": 2745.97, "total_tokens": 719264} |
| {"current_steps": 2530, "total_steps": 5360, "loss": 5.8009, "lr": 3.173742110762984e-05, "epoch": 4.720149253731344, "percentage": 47.2, "elapsed_time": "0:04:22", "remaining_time": "0:04:53", "throughput": 2747.2, "total_tokens": 720832} |
| {"current_steps": 2535, "total_steps": 5360, "loss": 6.2572, "lr": 3.165899213762995e-05, "epoch": 4.729477611940299, "percentage": 47.29, "elapsed_time": "0:04:22", "remaining_time": "0:04:52", "throughput": 2747.94, "total_tokens": 722240} |
| {"current_steps": 2540, "total_steps": 5360, "loss": 6.5728, "lr": 3.158049256298499e-05, "epoch": 4.7388059701492535, "percentage": 47.39, "elapsed_time": "0:04:23", "remaining_time": "0:04:52", "throughput": 2748.36, "total_tokens": 723552} |
| {"current_steps": 2545, "total_steps": 5360, "loss": 6.0845, "lr": 3.15019232160183e-05, "epoch": 4.7481343283582085, "percentage": 47.48, "elapsed_time": "0:04:23", "remaining_time": "0:04:51", "throughput": 2748.79, "total_tokens": 724864} |
| {"current_steps": 2550, "total_steps": 5360, "loss": 5.9881, "lr": 3.142328492979301e-05, "epoch": 4.757462686567164, "percentage": 47.57, "elapsed_time": "0:04:24", "remaining_time": "0:04:51", "throughput": 2749.19, "total_tokens": 726176} |
| {"current_steps": 2555, "total_steps": 5360, "loss": 6.3026, "lr": 3.134457853810322e-05, "epoch": 4.766791044776119, "percentage": 47.67, "elapsed_time": "0:04:24", "remaining_time": "0:04:50", "throughput": 2750.14, "total_tokens": 727680} |
| {"current_steps": 2560, "total_steps": 5360, "loss": 6.149, "lr": 3.126580487546513e-05, "epoch": 4.776119402985074, "percentage": 47.76, "elapsed_time": "0:04:25", "remaining_time": "0:04:49", "throughput": 2750.62, "total_tokens": 729024} |
| {"current_steps": 2565, "total_steps": 5360, "loss": 6.2203, "lr": 3.1186964777108215e-05, "epoch": 4.78544776119403, "percentage": 47.85, "elapsed_time": "0:04:25", "remaining_time": "0:04:49", "throughput": 2750.97, "total_tokens": 730304} |
| {"current_steps": 2570, "total_steps": 5360, "loss": 6.4271, "lr": 3.110805907896637e-05, "epoch": 4.794776119402985, "percentage": 47.95, "elapsed_time": "0:04:25", "remaining_time": "0:04:48", "throughput": 2751.79, "total_tokens": 731776} |
| {"current_steps": 2575, "total_steps": 5360, "loss": 5.6447, "lr": 3.1029088617669e-05, "epoch": 4.80410447761194, "percentage": 48.04, "elapsed_time": "0:04:26", "remaining_time": "0:04:48", "throughput": 2752.36, "total_tokens": 733152} |
| {"current_steps": 2580, "total_steps": 5360, "loss": 6.4536, "lr": 3.0950054230532235e-05, "epoch": 4.813432835820896, "percentage": 48.13, "elapsed_time": "0:04:26", "remaining_time": "0:04:47", "throughput": 2752.71, "total_tokens": 734432} |
| {"current_steps": 2585, "total_steps": 5360, "loss": 6.2467, "lr": 3.0870956755549976e-05, "epoch": 4.822761194029851, "percentage": 48.23, "elapsed_time": "0:04:27", "remaining_time": "0:04:46", "throughput": 2753.27, "total_tokens": 735808} |
| {"current_steps": 2590, "total_steps": 5360, "loss": 6.329, "lr": 3.079179703138505e-05, "epoch": 4.832089552238806, "percentage": 48.32, "elapsed_time": "0:04:27", "remaining_time": "0:04:46", "throughput": 2753.57, "total_tokens": 737088} |
| {"current_steps": 2595, "total_steps": 5360, "loss": 6.1552, "lr": 3.0712575897360304e-05, "epoch": 4.8414179104477615, "percentage": 48.41, "elapsed_time": "0:04:28", "remaining_time": "0:04:45", "throughput": 2754.35, "total_tokens": 738528} |
| {"current_steps": 2600, "total_steps": 5360, "loss": 6.5962, "lr": 3.0633294193449695e-05, "epoch": 4.850746268656716, "percentage": 48.51, "elapsed_time": "0:04:28", "remaining_time": "0:04:45", "throughput": 2755.4, "total_tokens": 740128} |
| {"current_steps": 2605, "total_steps": 5360, "loss": 5.7478, "lr": 3.0553952760269426e-05, "epoch": 4.860074626865671, "percentage": 48.6, "elapsed_time": "0:04:29", "remaining_time": "0:04:44", "throughput": 2756.77, "total_tokens": 741760} |
| {"current_steps": 2610, "total_steps": 5360, "loss": 6.2444, "lr": 3.0474552439068978e-05, "epoch": 4.869402985074627, "percentage": 48.69, "elapsed_time": "0:04:29", "remaining_time": "0:04:43", "throughput": 2757.36, "total_tokens": 743136} |
| {"current_steps": 2615, "total_steps": 5360, "loss": 5.913, "lr": 3.039509407172222e-05, "epoch": 4.878731343283582, "percentage": 48.79, "elapsed_time": "0:04:29", "remaining_time": "0:04:43", "throughput": 2757.61, "total_tokens": 744384} |
| {"current_steps": 2620, "total_steps": 5360, "loss": 6.4635, "lr": 3.0315578500718476e-05, "epoch": 4.888059701492537, "percentage": 48.88, "elapsed_time": "0:04:30", "remaining_time": "0:04:42", "throughput": 2758.54, "total_tokens": 745888} |
| {"current_steps": 2625, "total_steps": 5360, "loss": 6.0929, "lr": 3.0236006569153617e-05, "epoch": 4.897388059701493, "percentage": 48.97, "elapsed_time": "0:04:30", "remaining_time": "0:04:42", "throughput": 2759.42, "total_tokens": 747360} |
| {"current_steps": 2630, "total_steps": 5360, "loss": 6.0556, "lr": 3.0156379120721068e-05, "epoch": 4.906716417910448, "percentage": 49.07, "elapsed_time": "0:04:31", "remaining_time": "0:04:41", "throughput": 2759.55, "total_tokens": 748576} |
| {"current_steps": 2635, "total_steps": 5360, "loss": 5.938, "lr": 3.0076696999702913e-05, "epoch": 4.916044776119403, "percentage": 49.16, "elapsed_time": "0:04:31", "remaining_time": "0:04:40", "throughput": 2759.68, "total_tokens": 749792} |
| {"current_steps": 2640, "total_steps": 5360, "loss": 6.3418, "lr": 2.9996961050960932e-05, "epoch": 4.925373134328359, "percentage": 49.25, "elapsed_time": "0:04:32", "remaining_time": "0:04:40", "throughput": 2760.34, "total_tokens": 751200} |
| {"current_steps": 2645, "total_steps": 5360, "loss": 5.9282, "lr": 2.9917172119927606e-05, "epoch": 4.934701492537314, "percentage": 49.35, "elapsed_time": "0:04:32", "remaining_time": "0:04:39", "throughput": 2761.09, "total_tokens": 752608} |
| {"current_steps": 2650, "total_steps": 5360, "loss": 6.3392, "lr": 2.9837331052597224e-05, "epoch": 4.9440298507462686, "percentage": 49.44, "elapsed_time": "0:04:33", "remaining_time": "0:04:39", "throughput": 2762.08, "total_tokens": 754144} |
| {"current_steps": 2655, "total_steps": 5360, "loss": 6.6677, "lr": 2.9757438695516816e-05, "epoch": 4.9533582089552235, "percentage": 49.53, "elapsed_time": "0:04:33", "remaining_time": "0:04:38", "throughput": 2762.83, "total_tokens": 755584} |
| {"current_steps": 2660, "total_steps": 5360, "loss": 5.873, "lr": 2.9677495895777286e-05, "epoch": 4.962686567164179, "percentage": 49.63, "elapsed_time": "0:04:33", "remaining_time": "0:04:38", "throughput": 2763.97, "total_tokens": 757152} |
| {"current_steps": 2665, "total_steps": 5360, "loss": 6.7788, "lr": 2.9597503501004343e-05, "epoch": 4.972014925373134, "percentage": 49.72, "elapsed_time": "0:04:34", "remaining_time": "0:04:37", "throughput": 2764.48, "total_tokens": 758528} |
| {"current_steps": 2670, "total_steps": 5360, "loss": 6.1211, "lr": 2.9517462359349553e-05, "epoch": 4.981343283582089, "percentage": 49.81, "elapsed_time": "0:04:34", "remaining_time": "0:04:36", "throughput": 2765.01, "total_tokens": 759904} |
| {"current_steps": 2675, "total_steps": 5360, "loss": 6.3025, "lr": 2.943737331948136e-05, "epoch": 4.990671641791045, "percentage": 49.91, "elapsed_time": "0:04:35", "remaining_time": "0:04:36", "throughput": 2765.8, "total_tokens": 761344} |
| {"current_steps": 2680, "total_steps": 5360, "loss": 6.3133, "lr": 2.9357237230576045e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:04:35", "remaining_time": "0:04:35", "throughput": 2764.72, "total_tokens": 762440} |
| {"current_steps": 2680, "total_steps": 5360, "eval_loss": 6.3077392578125, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:04:38", "remaining_time": "0:04:38", "throughput": 2739.08, "total_tokens": 762440} |
| {"current_steps": 2685, "total_steps": 5360, "loss": 6.1517, "lr": 2.927705494230875e-05, "epoch": 5.009328358208955, "percentage": 50.09, "elapsed_time": "0:04:39", "remaining_time": "0:04:38", "throughput": 2728.24, "total_tokens": 763656} |
| {"current_steps": 2690, "total_steps": 5360, "loss": 6.0177, "lr": 2.9196827304844483e-05, "epoch": 5.018656716417911, "percentage": 50.19, "elapsed_time": "0:04:40", "remaining_time": "0:04:38", "throughput": 2728.66, "total_tokens": 764968} |
| {"current_steps": 2695, "total_steps": 5360, "loss": 6.0259, "lr": 2.911655516882905e-05, "epoch": 5.027985074626866, "percentage": 50.28, "elapsed_time": "0:04:40", "remaining_time": "0:04:37", "throughput": 2729.5, "total_tokens": 766440} |
| {"current_steps": 2700, "total_steps": 5360, "loss": 5.963, "lr": 2.9036239385380098e-05, "epoch": 5.037313432835821, "percentage": 50.37, "elapsed_time": "0:04:41", "remaining_time": "0:04:37", "throughput": 2729.94, "total_tokens": 767784} |
| {"current_steps": 2705, "total_steps": 5360, "loss": 5.9648, "lr": 2.8955880806078068e-05, "epoch": 5.0466417910447765, "percentage": 50.47, "elapsed_time": "0:04:41", "remaining_time": "0:04:36", "throughput": 2730.42, "total_tokens": 769128} |
| {"current_steps": 2710, "total_steps": 5360, "loss": 5.6471, "lr": 2.8875480282957133e-05, "epoch": 5.0559701492537314, "percentage": 50.56, "elapsed_time": "0:04:42", "remaining_time": "0:04:35", "throughput": 2731.1, "total_tokens": 770536} |
| {"current_steps": 2715, "total_steps": 5360, "loss": 6.2019, "lr": 2.8795038668496222e-05, "epoch": 5.065298507462686, "percentage": 50.65, "elapsed_time": "0:04:42", "remaining_time": "0:04:35", "throughput": 2731.99, "total_tokens": 772040} |
| {"current_steps": 2720, "total_steps": 5360, "loss": 6.6323, "lr": 2.8714556815609926e-05, "epoch": 5.074626865671641, "percentage": 50.75, "elapsed_time": "0:04:43", "remaining_time": "0:04:34", "throughput": 2732.71, "total_tokens": 773480} |
| {"current_steps": 2725, "total_steps": 5360, "loss": 5.851, "lr": 2.8634035577639505e-05, "epoch": 5.083955223880597, "percentage": 50.84, "elapsed_time": "0:04:43", "remaining_time": "0:04:34", "throughput": 2733.41, "total_tokens": 774888} |
| {"current_steps": 2730, "total_steps": 5360, "loss": 5.7735, "lr": 2.8553475808343798e-05, "epoch": 5.093283582089552, "percentage": 50.93, "elapsed_time": "0:04:43", "remaining_time": "0:04:33", "throughput": 2734.04, "total_tokens": 776296} |
| {"current_steps": 2735, "total_steps": 5360, "loss": 5.9805, "lr": 2.847287836189019e-05, "epoch": 5.102611940298507, "percentage": 51.03, "elapsed_time": "0:04:44", "remaining_time": "0:04:32", "throughput": 2735.37, "total_tokens": 777928} |
| {"current_steps": 2740, "total_steps": 5360, "loss": 6.4475, "lr": 2.839224409284556e-05, "epoch": 5.111940298507463, "percentage": 51.12, "elapsed_time": "0:04:44", "remaining_time": "0:04:32", "throughput": 2735.91, "total_tokens": 779304} |
| {"current_steps": 2745, "total_steps": 5360, "loss": 6.3653, "lr": 2.83115738561672e-05, "epoch": 5.121268656716418, "percentage": 51.21, "elapsed_time": "0:04:45", "remaining_time": "0:04:31", "throughput": 2735.93, "total_tokens": 780456} |
| {"current_steps": 2750, "total_steps": 5360, "loss": 6.3319, "lr": 2.8230868507193785e-05, "epoch": 5.130597014925373, "percentage": 51.31, "elapsed_time": "0:04:45", "remaining_time": "0:04:31", "throughput": 2736.42, "total_tokens": 781800} |
| {"current_steps": 2755, "total_steps": 5360, "loss": 5.9545, "lr": 2.8150128901636262e-05, "epoch": 5.139925373134329, "percentage": 51.4, "elapsed_time": "0:04:46", "remaining_time": "0:04:30", "throughput": 2737.0, "total_tokens": 783176} |
| {"current_steps": 2760, "total_steps": 5360, "loss": 6.5791, "lr": 2.8069355895568805e-05, "epoch": 5.149253731343284, "percentage": 51.49, "elapsed_time": "0:04:46", "remaining_time": "0:04:29", "throughput": 2737.37, "total_tokens": 784488} |
| {"current_steps": 2765, "total_steps": 5360, "loss": 6.686, "lr": 2.7988550345419733e-05, "epoch": 5.1585820895522385, "percentage": 51.59, "elapsed_time": "0:04:47", "remaining_time": "0:04:29", "throughput": 2738.06, "total_tokens": 785928} |
| {"current_steps": 2770, "total_steps": 5360, "loss": 6.7563, "lr": 2.790771310796243e-05, "epoch": 5.167910447761194, "percentage": 51.68, "elapsed_time": "0:04:47", "remaining_time": "0:04:28", "throughput": 2738.81, "total_tokens": 787368} |
| {"current_steps": 2775, "total_steps": 5360, "loss": 6.4211, "lr": 2.7826845040306238e-05, "epoch": 5.177238805970149, "percentage": 51.77, "elapsed_time": "0:04:47", "remaining_time": "0:04:28", "throughput": 2739.39, "total_tokens": 788744} |
| {"current_steps": 2780, "total_steps": 5360, "loss": 6.3064, "lr": 2.7745946999887406e-05, "epoch": 5.186567164179104, "percentage": 51.87, "elapsed_time": "0:04:48", "remaining_time": "0:04:27", "throughput": 2740.04, "total_tokens": 790216} |
| {"current_steps": 2785, "total_steps": 5360, "loss": 6.3934, "lr": 2.766501984445999e-05, "epoch": 5.19589552238806, "percentage": 51.96, "elapsed_time": "0:04:48", "remaining_time": "0:04:27", "throughput": 2740.84, "total_tokens": 791656} |
| {"current_steps": 2790, "total_steps": 5360, "loss": 6.2562, "lr": 2.7584064432086716e-05, "epoch": 5.205223880597015, "percentage": 52.05, "elapsed_time": "0:04:49", "remaining_time": "0:04:26", "throughput": 2742.08, "total_tokens": 793288} |
| {"current_steps": 2795, "total_steps": 5360, "loss": 6.7897, "lr": 2.750308162112995e-05, "epoch": 5.21455223880597, "percentage": 52.15, "elapsed_time": "0:04:49", "remaining_time": "0:04:25", "throughput": 2743.31, "total_tokens": 794984} |
| {"current_steps": 2800, "total_steps": 5360, "loss": 5.7294, "lr": 2.7422072270242548e-05, "epoch": 5.223880597014926, "percentage": 52.24, "elapsed_time": "0:04:50", "remaining_time": "0:04:25", "throughput": 2743.75, "total_tokens": 796328} |
| {"current_steps": 2805, "total_steps": 5360, "loss": 6.2595, "lr": 2.7341037238358774e-05, "epoch": 5.233208955223881, "percentage": 52.33, "elapsed_time": "0:04:50", "remaining_time": "0:04:24", "throughput": 2744.26, "total_tokens": 797704} |
| {"current_steps": 2810, "total_steps": 5360, "loss": 5.8314, "lr": 2.7259977384685163e-05, "epoch": 5.242537313432836, "percentage": 52.43, "elapsed_time": "0:04:51", "remaining_time": "0:04:24", "throughput": 2744.59, "total_tokens": 798984} |
| {"current_steps": 2815, "total_steps": 5360, "loss": 6.2151, "lr": 2.717889356869146e-05, "epoch": 5.251865671641791, "percentage": 52.52, "elapsed_time": "0:04:51", "remaining_time": "0:04:23", "throughput": 2745.2, "total_tokens": 800392} |
| {"current_steps": 2820, "total_steps": 5360, "loss": 6.1419, "lr": 2.7097786650101458e-05, "epoch": 5.2611940298507465, "percentage": 52.61, "elapsed_time": "0:04:52", "remaining_time": "0:04:23", "throughput": 2745.95, "total_tokens": 801832} |
| {"current_steps": 2825, "total_steps": 5360, "loss": 5.7732, "lr": 2.7016657488883928e-05, "epoch": 5.270522388059701, "percentage": 52.71, "elapsed_time": "0:04:52", "remaining_time": "0:04:22", "throughput": 2746.59, "total_tokens": 803272} |
| {"current_steps": 2830, "total_steps": 5360, "loss": 6.5791, "lr": 2.693550694524346e-05, "epoch": 5.279850746268656, "percentage": 52.8, "elapsed_time": "0:04:52", "remaining_time": "0:04:21", "throughput": 2747.56, "total_tokens": 804872} |
| {"current_steps": 2835, "total_steps": 5360, "loss": 6.0309, "lr": 2.685433587961136e-05, "epoch": 5.289179104477612, "percentage": 52.89, "elapsed_time": "0:04:53", "remaining_time": "0:04:21", "throughput": 2748.29, "total_tokens": 806312} |
| {"current_steps": 2840, "total_steps": 5360, "loss": 6.2054, "lr": 2.6773145152636536e-05, "epoch": 5.298507462686567, "percentage": 52.99, "elapsed_time": "0:04:53", "remaining_time": "0:04:20", "throughput": 2749.36, "total_tokens": 807944} |
| {"current_steps": 2845, "total_steps": 5360, "loss": 6.9317, "lr": 2.6691935625176357e-05, "epoch": 5.307835820895522, "percentage": 53.08, "elapsed_time": "0:04:54", "remaining_time": "0:04:20", "throughput": 2749.91, "total_tokens": 809320} |
| {"current_steps": 2850, "total_steps": 5360, "loss": 6.0374, "lr": 2.6610708158287535e-05, "epoch": 5.317164179104478, "percentage": 53.17, "elapsed_time": "0:04:54", "remaining_time": "0:04:19", "throughput": 2751.13, "total_tokens": 810952} |
| {"current_steps": 2855, "total_steps": 5360, "loss": 6.5508, "lr": 2.6529463613216986e-05, "epoch": 5.326492537313433, "percentage": 53.26, "elapsed_time": "0:04:55", "remaining_time": "0:04:19", "throughput": 2751.54, "total_tokens": 812264} |
| {"current_steps": 2860, "total_steps": 5360, "loss": 6.2744, "lr": 2.644820285139271e-05, "epoch": 5.335820895522388, "percentage": 53.36, "elapsed_time": "0:04:55", "remaining_time": "0:04:18", "throughput": 2752.18, "total_tokens": 813704} |
| {"current_steps": 2865, "total_steps": 5360, "loss": 6.2007, "lr": 2.636692673441465e-05, "epoch": 5.345149253731344, "percentage": 53.45, "elapsed_time": "0:04:56", "remaining_time": "0:04:17", "throughput": 2753.02, "total_tokens": 815272} |
| {"current_steps": 2870, "total_steps": 5360, "loss": 6.3687, "lr": 2.628563612404556e-05, "epoch": 5.354477611940299, "percentage": 53.54, "elapsed_time": "0:04:56", "remaining_time": "0:04:17", "throughput": 2753.89, "total_tokens": 816904} |
| {"current_steps": 2875, "total_steps": 5360, "loss": 6.2943, "lr": 2.6204331882201864e-05, "epoch": 5.3638059701492535, "percentage": 53.64, "elapsed_time": "0:04:57", "remaining_time": "0:04:16", "throughput": 2754.87, "total_tokens": 818440} |
| {"current_steps": 2880, "total_steps": 5360, "loss": 6.4227, "lr": 2.6123014870944517e-05, "epoch": 5.373134328358209, "percentage": 53.73, "elapsed_time": "0:04:57", "remaining_time": "0:04:16", "throughput": 2755.21, "total_tokens": 819752} |
| {"current_steps": 2885, "total_steps": 5360, "loss": 6.314, "lr": 2.6041685952469875e-05, "epoch": 5.382462686567164, "percentage": 53.82, "elapsed_time": "0:04:57", "remaining_time": "0:04:15", "throughput": 2755.24, "total_tokens": 820936} |
| {"current_steps": 2890, "total_steps": 5360, "loss": 6.1103, "lr": 2.596034598910053e-05, "epoch": 5.391791044776119, "percentage": 53.92, "elapsed_time": "0:04:58", "remaining_time": "0:04:15", "throughput": 2756.01, "total_tokens": 822408} |
| {"current_steps": 2895, "total_steps": 5360, "loss": 5.8164, "lr": 2.5878995843276204e-05, "epoch": 5.401119402985074, "percentage": 54.01, "elapsed_time": "0:04:58", "remaining_time": "0:04:14", "throughput": 2756.53, "total_tokens": 823784} |
| {"current_steps": 2900, "total_steps": 5360, "loss": 5.6906, "lr": 2.5797636377544564e-05, "epoch": 5.41044776119403, "percentage": 54.1, "elapsed_time": "0:04:59", "remaining_time": "0:04:13", "throughput": 2756.84, "total_tokens": 825064} |
| {"current_steps": 2905, "total_steps": 5360, "loss": 6.471, "lr": 2.5716268454552095e-05, "epoch": 5.419776119402985, "percentage": 54.2, "elapsed_time": "0:04:59", "remaining_time": "0:04:13", "throughput": 2757.55, "total_tokens": 826600} |
| {"current_steps": 2910, "total_steps": 5360, "loss": 6.076, "lr": 2.563489293703496e-05, "epoch": 5.42910447761194, "percentage": 54.29, "elapsed_time": "0:05:00", "remaining_time": "0:04:12", "throughput": 2758.39, "total_tokens": 828104} |
| {"current_steps": 2915, "total_steps": 5360, "loss": 5.8456, "lr": 2.5553510687809855e-05, "epoch": 5.438432835820896, "percentage": 54.38, "elapsed_time": "0:05:00", "remaining_time": "0:04:12", "throughput": 2759.17, "total_tokens": 829640} |
| {"current_steps": 2920, "total_steps": 5360, "loss": 6.5653, "lr": 2.547212256976484e-05, "epoch": 5.447761194029851, "percentage": 54.48, "elapsed_time": "0:05:01", "remaining_time": "0:04:11", "throughput": 2759.98, "total_tokens": 831112} |
| {"current_steps": 2925, "total_steps": 5360, "loss": 6.372, "lr": 2.5390729445850198e-05, "epoch": 5.457089552238806, "percentage": 54.57, "elapsed_time": "0:05:01", "remaining_time": "0:04:11", "throughput": 2761.01, "total_tokens": 832744} |
| {"current_steps": 2930, "total_steps": 5360, "loss": 6.6638, "lr": 2.53093321790693e-05, "epoch": 5.4664179104477615, "percentage": 54.66, "elapsed_time": "0:05:02", "remaining_time": "0:04:10", "throughput": 2761.88, "total_tokens": 834248} |
| {"current_steps": 2935, "total_steps": 5360, "loss": 6.0771, "lr": 2.5227931632469437e-05, "epoch": 5.475746268656716, "percentage": 54.76, "elapsed_time": "0:05:02", "remaining_time": "0:04:09", "throughput": 2762.77, "total_tokens": 835752} |
| {"current_steps": 2940, "total_steps": 5360, "loss": 6.0065, "lr": 2.5146528669132664e-05, "epoch": 5.485074626865671, "percentage": 54.85, "elapsed_time": "0:05:02", "remaining_time": "0:04:09", "throughput": 2763.15, "total_tokens": 837064} |
| {"current_steps": 2945, "total_steps": 5360, "loss": 5.5232, "lr": 2.506512415216669e-05, "epoch": 5.494402985074627, "percentage": 54.94, "elapsed_time": "0:05:03", "remaining_time": "0:04:08", "throughput": 2763.69, "total_tokens": 838440} |
| {"current_steps": 2948, "total_steps": 5360, "eval_loss": 6.261446952819824, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:05:06", "remaining_time": "0:04:10", "throughput": 2741.53, "total_tokens": 839656} |
| {"current_steps": 2950, "total_steps": 5360, "loss": 6.3547, "lr": 2.4983718944695672e-05, "epoch": 5.503731343283582, "percentage": 55.04, "elapsed_time": "0:05:07", "remaining_time": "0:04:11", "throughput": 2733.14, "total_tokens": 840232} |
| {"current_steps": 2955, "total_steps": 5360, "loss": 6.0888, "lr": 2.49023139098511e-05, "epoch": 5.513059701492537, "percentage": 55.13, "elapsed_time": "0:05:07", "remaining_time": "0:04:10", "throughput": 2733.55, "total_tokens": 841576} |
| {"current_steps": 2960, "total_steps": 5360, "loss": 6.4842, "lr": 2.4820909910762628e-05, "epoch": 5.522388059701493, "percentage": 55.22, "elapsed_time": "0:05:08", "remaining_time": "0:04:09", "throughput": 2734.19, "total_tokens": 842984} |
| {"current_steps": 2965, "total_steps": 5360, "loss": 6.1522, "lr": 2.473950781054893e-05, "epoch": 5.531716417910448, "percentage": 55.32, "elapsed_time": "0:05:08", "remaining_time": "0:04:09", "throughput": 2734.36, "total_tokens": 844232} |
| {"current_steps": 2970, "total_steps": 5360, "loss": 6.2037, "lr": 2.4658108472308545e-05, "epoch": 5.541044776119403, "percentage": 55.41, "elapsed_time": "0:05:09", "remaining_time": "0:04:08", "throughput": 2734.76, "total_tokens": 845576} |
| {"current_steps": 2975, "total_steps": 5360, "loss": 5.5291, "lr": 2.4576712759110728e-05, "epoch": 5.550373134328359, "percentage": 55.5, "elapsed_time": "0:05:09", "remaining_time": "0:04:08", "throughput": 2735.37, "total_tokens": 846984} |
| {"current_steps": 2980, "total_steps": 5360, "loss": 6.5366, "lr": 2.4495321533986297e-05, "epoch": 5.559701492537314, "percentage": 55.6, "elapsed_time": "0:05:10", "remaining_time": "0:04:07", "throughput": 2735.82, "total_tokens": 848328} |
| {"current_steps": 2985, "total_steps": 5360, "loss": 5.6366, "lr": 2.441393565991849e-05, "epoch": 5.5690298507462686, "percentage": 55.69, "elapsed_time": "0:05:10", "remaining_time": "0:04:07", "throughput": 2736.53, "total_tokens": 849800} |
| {"current_steps": 2990, "total_steps": 5360, "loss": 6.0048, "lr": 2.43325559998338e-05, "epoch": 5.5783582089552235, "percentage": 55.78, "elapsed_time": "0:05:10", "remaining_time": "0:04:06", "throughput": 2737.1, "total_tokens": 851176} |
| {"current_steps": 2995, "total_steps": 5360, "loss": 6.3708, "lr": 2.425118341659284e-05, "epoch": 5.587686567164179, "percentage": 55.88, "elapsed_time": "0:05:11", "remaining_time": "0:04:05", "throughput": 2738.05, "total_tokens": 852776} |
| {"current_steps": 3000, "total_steps": 5360, "loss": 6.4106, "lr": 2.416981877298118e-05, "epoch": 5.597014925373134, "percentage": 55.97, "elapsed_time": "0:05:11", "remaining_time": "0:04:05", "throughput": 2738.64, "total_tokens": 854184} |
| {"current_steps": 3005, "total_steps": 5360, "loss": 6.1106, "lr": 2.4088462931700214e-05, "epoch": 5.606343283582089, "percentage": 56.06, "elapsed_time": "0:05:12", "remaining_time": "0:04:04", "throughput": 2739.02, "total_tokens": 855496} |
| {"current_steps": 3010, "total_steps": 5360, "loss": 6.4924, "lr": 2.4007116755357995e-05, "epoch": 5.615671641791045, "percentage": 56.16, "elapsed_time": "0:05:12", "remaining_time": "0:04:04", "throughput": 2739.48, "total_tokens": 856840} |
| {"current_steps": 3015, "total_steps": 5360, "loss": 6.0096, "lr": 2.392578110646012e-05, "epoch": 5.625, "percentage": 56.25, "elapsed_time": "0:05:13", "remaining_time": "0:04:03", "throughput": 2739.98, "total_tokens": 858184} |
| {"current_steps": 3020, "total_steps": 5360, "loss": 6.6961, "lr": 2.384445684740055e-05, "epoch": 5.634328358208955, "percentage": 56.34, "elapsed_time": "0:05:13", "remaining_time": "0:04:03", "throughput": 2740.63, "total_tokens": 859624} |
| {"current_steps": 3025, "total_steps": 5360, "loss": 6.0794, "lr": 2.376314484045248e-05, "epoch": 5.643656716417911, "percentage": 56.44, "elapsed_time": "0:05:14", "remaining_time": "0:04:02", "throughput": 2741.01, "total_tokens": 860968} |
| {"current_steps": 3030, "total_steps": 5360, "loss": 6.0095, "lr": 2.3681845947759206e-05, "epoch": 5.652985074626866, "percentage": 56.53, "elapsed_time": "0:05:14", "remaining_time": "0:04:01", "throughput": 2741.86, "total_tokens": 862472} |
| {"current_steps": 3035, "total_steps": 5360, "loss": 6.6307, "lr": 2.3600561031324958e-05, "epoch": 5.662313432835821, "percentage": 56.62, "elapsed_time": "0:05:15", "remaining_time": "0:04:01", "throughput": 2742.41, "total_tokens": 863880} |
| {"current_steps": 3040, "total_steps": 5360, "loss": 6.6959, "lr": 2.3519290953005784e-05, "epoch": 5.6716417910447765, "percentage": 56.72, "elapsed_time": "0:05:15", "remaining_time": "0:04:00", "throughput": 2743.05, "total_tokens": 865288} |
| {"current_steps": 3045, "total_steps": 5360, "loss": 6.4052, "lr": 2.3438036574500432e-05, "epoch": 5.6809701492537314, "percentage": 56.81, "elapsed_time": "0:05:15", "remaining_time": "0:04:00", "throughput": 2743.97, "total_tokens": 866824} |
| {"current_steps": 3050, "total_steps": 5360, "loss": 6.1437, "lr": 2.3356798757341155e-05, "epoch": 5.690298507462686, "percentage": 56.9, "elapsed_time": "0:05:16", "remaining_time": "0:03:59", "throughput": 2744.27, "total_tokens": 868104} |
| {"current_steps": 3055, "total_steps": 5360, "loss": 6.6104, "lr": 2.327557836288461e-05, "epoch": 5.699626865671641, "percentage": 57.0, "elapsed_time": "0:05:16", "remaining_time": "0:03:59", "throughput": 2744.85, "total_tokens": 869512} |
| {"current_steps": 3060, "total_steps": 5360, "loss": 6.2532, "lr": 2.3194376252302723e-05, "epoch": 5.708955223880597, "percentage": 57.09, "elapsed_time": "0:05:17", "remaining_time": "0:03:58", "throughput": 2745.75, "total_tokens": 871048} |
| {"current_steps": 3065, "total_steps": 5360, "loss": 6.4148, "lr": 2.311319328657358e-05, "epoch": 5.718283582089552, "percentage": 57.18, "elapsed_time": "0:05:17", "remaining_time": "0:03:57", "throughput": 2746.26, "total_tokens": 872424} |
| {"current_steps": 3070, "total_steps": 5360, "loss": 6.8183, "lr": 2.3032030326472235e-05, "epoch": 5.727611940298507, "percentage": 57.28, "elapsed_time": "0:05:18", "remaining_time": "0:03:57", "throughput": 2747.26, "total_tokens": 873992} |
| {"current_steps": 3075, "total_steps": 5360, "loss": 6.1796, "lr": 2.2950888232561672e-05, "epoch": 5.736940298507463, "percentage": 57.37, "elapsed_time": "0:05:18", "remaining_time": "0:03:56", "throughput": 2747.79, "total_tokens": 875368} |
| {"current_steps": 3080, "total_steps": 5360, "loss": 6.403, "lr": 2.2869767865183612e-05, "epoch": 5.746268656716418, "percentage": 57.46, "elapsed_time": "0:05:19", "remaining_time": "0:03:56", "throughput": 2748.46, "total_tokens": 876808} |
| {"current_steps": 3085, "total_steps": 5360, "loss": 6.5861, "lr": 2.2788670084449394e-05, "epoch": 5.755597014925373, "percentage": 57.56, "elapsed_time": "0:05:19", "remaining_time": "0:03:55", "throughput": 2748.83, "total_tokens": 878152} |
| {"current_steps": 3090, "total_steps": 5360, "loss": 6.1444, "lr": 2.2707595750230894e-05, "epoch": 5.764925373134329, "percentage": 57.65, "elapsed_time": "0:05:19", "remaining_time": "0:03:55", "throughput": 2749.2, "total_tokens": 879496} |
| {"current_steps": 3095, "total_steps": 5360, "loss": 5.9159, "lr": 2.2626545722151384e-05, "epoch": 5.774253731343284, "percentage": 57.74, "elapsed_time": "0:05:20", "remaining_time": "0:03:54", "throughput": 2749.78, "total_tokens": 880904} |
| {"current_steps": 3100, "total_steps": 5360, "loss": 6.0135, "lr": 2.254552085957641e-05, "epoch": 5.7835820895522385, "percentage": 57.84, "elapsed_time": "0:05:20", "remaining_time": "0:03:53", "throughput": 2750.03, "total_tokens": 882152} |
| {"current_steps": 3105, "total_steps": 5360, "loss": 6.0739, "lr": 2.246452202160471e-05, "epoch": 5.792910447761194, "percentage": 57.93, "elapsed_time": "0:05:21", "remaining_time": "0:03:53", "throughput": 2750.26, "total_tokens": 883400} |
| {"current_steps": 3110, "total_steps": 5360, "loss": 5.5673, "lr": 2.2383550067059063e-05, "epoch": 5.802238805970149, "percentage": 58.02, "elapsed_time": "0:05:21", "remaining_time": "0:03:52", "throughput": 2751.08, "total_tokens": 884968} |
| {"current_steps": 3115, "total_steps": 5360, "loss": 5.7823, "lr": 2.2302605854477228e-05, "epoch": 5.811567164179104, "percentage": 58.12, "elapsed_time": "0:05:22", "remaining_time": "0:03:52", "throughput": 2751.51, "total_tokens": 886312} |
| {"current_steps": 3120, "total_steps": 5360, "loss": 5.9224, "lr": 2.22216902421028e-05, "epoch": 5.82089552238806, "percentage": 58.21, "elapsed_time": "0:05:22", "remaining_time": "0:03:51", "throughput": 2752.13, "total_tokens": 887752} |
| {"current_steps": 3125, "total_steps": 5360, "loss": 6.0152, "lr": 2.2140804087876132e-05, "epoch": 5.830223880597015, "percentage": 58.3, "elapsed_time": "0:05:23", "remaining_time": "0:03:51", "throughput": 2752.56, "total_tokens": 889096} |
| {"current_steps": 3130, "total_steps": 5360, "loss": 5.6847, "lr": 2.2059948249425243e-05, "epoch": 5.83955223880597, "percentage": 58.4, "elapsed_time": "0:05:23", "remaining_time": "0:03:50", "throughput": 2752.93, "total_tokens": 890408} |
| {"current_steps": 3135, "total_steps": 5360, "loss": 6.2443, "lr": 2.197912358405672e-05, "epoch": 5.848880597014926, "percentage": 58.49, "elapsed_time": "0:05:23", "remaining_time": "0:03:49", "throughput": 2753.83, "total_tokens": 892072} |
| {"current_steps": 3140, "total_steps": 5360, "loss": 6.5642, "lr": 2.189833094874661e-05, "epoch": 5.858208955223881, "percentage": 58.58, "elapsed_time": "0:05:24", "remaining_time": "0:03:49", "throughput": 2754.56, "total_tokens": 893608} |
| {"current_steps": 3145, "total_steps": 5360, "loss": 6.7222, "lr": 2.1817571200131358e-05, "epoch": 5.867537313432836, "percentage": 58.68, "elapsed_time": "0:05:24", "remaining_time": "0:03:48", "throughput": 2754.88, "total_tokens": 894920} |
| {"current_steps": 3150, "total_steps": 5360, "loss": 5.7076, "lr": 2.173684519449872e-05, "epoch": 5.8768656716417915, "percentage": 58.77, "elapsed_time": "0:05:25", "remaining_time": "0:03:48", "throughput": 2755.47, "total_tokens": 896328} |
| {"current_steps": 3155, "total_steps": 5360, "loss": 5.7822, "lr": 2.1656153787778645e-05, "epoch": 5.8861940298507465, "percentage": 58.86, "elapsed_time": "0:05:25", "remaining_time": "0:03:47", "throughput": 2756.43, "total_tokens": 897896} |
| {"current_steps": 3160, "total_steps": 5360, "loss": 5.8496, "lr": 2.157549783553429e-05, "epoch": 5.895522388059701, "percentage": 58.96, "elapsed_time": "0:05:26", "remaining_time": "0:03:47", "throughput": 2756.95, "total_tokens": 899272} |
| {"current_steps": 3165, "total_steps": 5360, "loss": 6.2368, "lr": 2.1494878192952855e-05, "epoch": 5.904850746268656, "percentage": 59.05, "elapsed_time": "0:05:26", "remaining_time": "0:03:46", "throughput": 2757.33, "total_tokens": 900584} |
| {"current_steps": 3170, "total_steps": 5360, "loss": 6.3732, "lr": 2.141429571483655e-05, "epoch": 5.914179104477612, "percentage": 59.14, "elapsed_time": "0:05:27", "remaining_time": "0:03:45", "throughput": 2757.93, "total_tokens": 901992} |
| {"current_steps": 3175, "total_steps": 5360, "loss": 5.8465, "lr": 2.1333751255593552e-05, "epoch": 5.923507462686567, "percentage": 59.24, "elapsed_time": "0:05:27", "remaining_time": "0:03:45", "throughput": 2758.25, "total_tokens": 903304} |
| {"current_steps": 3180, "total_steps": 5360, "loss": 6.3578, "lr": 2.1253245669228905e-05, "epoch": 5.932835820895522, "percentage": 59.33, "elapsed_time": "0:05:27", "remaining_time": "0:03:44", "throughput": 2758.82, "total_tokens": 904712} |
| {"current_steps": 3185, "total_steps": 5360, "loss": 5.9194, "lr": 2.1172779809335496e-05, "epoch": 5.942164179104478, "percentage": 59.42, "elapsed_time": "0:05:28", "remaining_time": "0:03:44", "throughput": 2759.4, "total_tokens": 906120} |
| {"current_steps": 3190, "total_steps": 5360, "loss": 5.8607, "lr": 2.109235452908502e-05, "epoch": 5.951492537313433, "percentage": 59.51, "elapsed_time": "0:05:28", "remaining_time": "0:03:43", "throughput": 2759.77, "total_tokens": 907464} |
| {"current_steps": 3195, "total_steps": 5360, "loss": 6.1528, "lr": 2.101197068121888e-05, "epoch": 5.960820895522388, "percentage": 59.61, "elapsed_time": "0:05:29", "remaining_time": "0:03:43", "throughput": 2760.63, "total_tokens": 909000} |
| {"current_steps": 3200, "total_steps": 5360, "loss": 5.9187, "lr": 2.0931629118039185e-05, "epoch": 5.970149253731344, "percentage": 59.7, "elapsed_time": "0:05:29", "remaining_time": "0:03:42", "throughput": 2760.87, "total_tokens": 910280} |
| {"current_steps": 3205, "total_steps": 5360, "loss": 6.3052, "lr": 2.0851330691399713e-05, "epoch": 5.979477611940299, "percentage": 59.79, "elapsed_time": "0:05:30", "remaining_time": "0:03:41", "throughput": 2761.73, "total_tokens": 911816} |
| {"current_steps": 3210, "total_steps": 5360, "loss": 6.3172, "lr": 2.0771076252696846e-05, "epoch": 5.9888059701492535, "percentage": 59.89, "elapsed_time": "0:05:30", "remaining_time": "0:03:41", "throughput": 2762.35, "total_tokens": 913320} |
| {"current_steps": 3215, "total_steps": 5360, "loss": 5.3684, "lr": 2.0690866652860584e-05, "epoch": 5.9981343283582085, "percentage": 59.98, "elapsed_time": "0:05:31", "remaining_time": "0:03:40", "throughput": 2763.09, "total_tokens": 914856} |
| {"current_steps": 3216, "total_steps": 5360, "eval_loss": 6.22491979598999, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:05:33", "remaining_time": "0:03:42", "throughput": 2740.72, "total_tokens": 914920} |
| {"current_steps": 3220, "total_steps": 5360, "loss": 5.8152, "lr": 2.0610702742345517e-05, "epoch": 6.007462686567164, "percentage": 60.07, "elapsed_time": "0:05:35", "remaining_time": "0:03:42", "throughput": 2731.04, "total_tokens": 916136} |
| {"current_steps": 3225, "total_steps": 5360, "loss": 5.1948, "lr": 2.053058537112177e-05, "epoch": 6.016791044776119, "percentage": 60.17, "elapsed_time": "0:05:35", "remaining_time": "0:03:42", "throughput": 2731.63, "total_tokens": 917544} |
| {"current_steps": 3230, "total_steps": 5360, "loss": 6.3608, "lr": 2.0450515388666022e-05, "epoch": 6.026119402985074, "percentage": 60.26, "elapsed_time": "0:05:36", "remaining_time": "0:03:41", "throughput": 2732.48, "total_tokens": 919080} |
| {"current_steps": 3235, "total_steps": 5360, "loss": 5.5958, "lr": 2.0370493643952507e-05, "epoch": 6.03544776119403, "percentage": 60.35, "elapsed_time": "0:05:36", "remaining_time": "0:03:41", "throughput": 2733.51, "total_tokens": 920840} |
| {"current_steps": 3240, "total_steps": 5360, "loss": 6.1229, "lr": 2.0290520985443985e-05, "epoch": 6.044776119402985, "percentage": 60.45, "elapsed_time": "0:05:37", "remaining_time": "0:03:40", "throughput": 2734.06, "total_tokens": 922248} |
| {"current_steps": 3245, "total_steps": 5360, "loss": 6.1346, "lr": 2.0210598261082765e-05, "epoch": 6.05410447761194, "percentage": 60.54, "elapsed_time": "0:05:37", "remaining_time": "0:03:40", "throughput": 2735.09, "total_tokens": 923912} |
| {"current_steps": 3250, "total_steps": 5360, "loss": 6.4707, "lr": 2.013072631828171e-05, "epoch": 6.063432835820896, "percentage": 60.63, "elapsed_time": "0:05:38", "remaining_time": "0:03:39", "throughput": 2735.71, "total_tokens": 925352} |
| {"current_steps": 3255, "total_steps": 5360, "loss": 6.3204, "lr": 2.005090600391526e-05, "epoch": 6.072761194029851, "percentage": 60.73, "elapsed_time": "0:05:38", "remaining_time": "0:03:39", "throughput": 2736.47, "total_tokens": 926856} |
| {"current_steps": 3260, "total_steps": 5360, "loss": 6.3356, "lr": 1.9971138164310422e-05, "epoch": 6.082089552238806, "percentage": 60.82, "elapsed_time": "0:05:39", "remaining_time": "0:03:38", "throughput": 2736.78, "total_tokens": 928168} |
| {"current_steps": 3265, "total_steps": 5360, "loss": 6.8347, "lr": 1.9891423645237834e-05, "epoch": 6.0914179104477615, "percentage": 60.91, "elapsed_time": "0:05:39", "remaining_time": "0:03:37", "throughput": 2737.3, "total_tokens": 929544} |
| {"current_steps": 3270, "total_steps": 5360, "loss": 6.2436, "lr": 1.9811763291902774e-05, "epoch": 6.100746268656716, "percentage": 61.01, "elapsed_time": "0:05:40", "remaining_time": "0:03:37", "throughput": 2737.5, "total_tokens": 930792} |
| {"current_steps": 3275, "total_steps": 5360, "loss": 5.7265, "lr": 1.9732157948936204e-05, "epoch": 6.110074626865671, "percentage": 61.1, "elapsed_time": "0:05:40", "remaining_time": "0:03:36", "throughput": 2737.74, "total_tokens": 932072} |
| {"current_steps": 3280, "total_steps": 5360, "loss": 6.2326, "lr": 1.9652608460385843e-05, "epoch": 6.119402985074627, "percentage": 61.19, "elapsed_time": "0:05:40", "remaining_time": "0:03:36", "throughput": 2738.15, "total_tokens": 933384} |
| {"current_steps": 3285, "total_steps": 5360, "loss": 6.2225, "lr": 1.957311566970716e-05, "epoch": 6.128731343283582, "percentage": 61.29, "elapsed_time": "0:05:41", "remaining_time": "0:03:35", "throughput": 2738.94, "total_tokens": 934888} |
| {"current_steps": 3290, "total_steps": 5360, "loss": 6.1285, "lr": 1.949368041975447e-05, "epoch": 6.138059701492537, "percentage": 61.38, "elapsed_time": "0:05:41", "remaining_time": "0:03:35", "throughput": 2739.5, "total_tokens": 936328} |
| {"current_steps": 3295, "total_steps": 5360, "loss": 6.3063, "lr": 1.9414303552771997e-05, "epoch": 6.147388059701493, "percentage": 61.47, "elapsed_time": "0:05:42", "remaining_time": "0:03:34", "throughput": 2740.17, "total_tokens": 937864} |
| {"current_steps": 3300, "total_steps": 5360, "loss": 6.1906, "lr": 1.9334985910384923e-05, "epoch": 6.156716417910448, "percentage": 61.57, "elapsed_time": "0:05:42", "remaining_time": "0:03:33", "throughput": 2741.18, "total_tokens": 939464} |
| {"current_steps": 3305, "total_steps": 5360, "loss": 6.5144, "lr": 1.9255728333590475e-05, "epoch": 6.166044776119403, "percentage": 61.66, "elapsed_time": "0:05:43", "remaining_time": "0:03:33", "throughput": 2741.81, "total_tokens": 940968} |
| {"current_steps": 3310, "total_steps": 5360, "loss": 6.1677, "lr": 1.9176531662749044e-05, "epoch": 6.175373134328359, "percentage": 61.75, "elapsed_time": "0:05:43", "remaining_time": "0:03:32", "throughput": 2741.85, "total_tokens": 942152} |
| {"current_steps": 3315, "total_steps": 5360, "loss": 6.4936, "lr": 1.9097396737575206e-05, "epoch": 6.184701492537314, "percentage": 61.85, "elapsed_time": "0:05:44", "remaining_time": "0:03:32", "throughput": 2742.6, "total_tokens": 943720} |
| {"current_steps": 3320, "total_steps": 5360, "loss": 6.0559, "lr": 1.9018324397128866e-05, "epoch": 6.1940298507462686, "percentage": 61.94, "elapsed_time": "0:05:44", "remaining_time": "0:03:31", "throughput": 2742.68, "total_tokens": 944904} |
| {"current_steps": 3325, "total_steps": 5360, "loss": 6.0315, "lr": 1.893931547980635e-05, "epoch": 6.2033582089552235, "percentage": 62.03, "elapsed_time": "0:05:44", "remaining_time": "0:03:31", "throughput": 2743.27, "total_tokens": 946344} |
| {"current_steps": 3330, "total_steps": 5360, "loss": 6.5622, "lr": 1.8860370823331513e-05, "epoch": 6.212686567164179, "percentage": 62.13, "elapsed_time": "0:05:45", "remaining_time": "0:03:30", "throughput": 2743.91, "total_tokens": 947816} |
| {"current_steps": 3335, "total_steps": 5360, "loss": 5.7034, "lr": 1.878149126474685e-05, "epoch": 6.222014925373134, "percentage": 62.22, "elapsed_time": "0:05:45", "remaining_time": "0:03:30", "throughput": 2744.55, "total_tokens": 949320} |
| {"current_steps": 3340, "total_steps": 5360, "loss": 6.2352, "lr": 1.870267764040465e-05, "epoch": 6.231343283582089, "percentage": 62.31, "elapsed_time": "0:05:46", "remaining_time": "0:03:29", "throughput": 2744.96, "total_tokens": 950664} |
| {"current_steps": 3345, "total_steps": 5360, "loss": 6.1331, "lr": 1.8623930785958092e-05, "epoch": 6.240671641791045, "percentage": 62.41, "elapsed_time": "0:05:46", "remaining_time": "0:03:28", "throughput": 2745.94, "total_tokens": 952328} |
| {"current_steps": 3350, "total_steps": 5360, "loss": 6.0583, "lr": 1.8545251536352402e-05, "epoch": 6.25, "percentage": 62.5, "elapsed_time": "0:05:47", "remaining_time": "0:03:28", "throughput": 2746.51, "total_tokens": 953736} |
| {"current_steps": 3355, "total_steps": 5360, "loss": 6.2618, "lr": 1.8466640725816e-05, "epoch": 6.259328358208955, "percentage": 62.59, "elapsed_time": "0:05:47", "remaining_time": "0:03:27", "throughput": 2747.39, "total_tokens": 955272} |
| {"current_steps": 3360, "total_steps": 5360, "loss": 5.9719, "lr": 1.838809918785166e-05, "epoch": 6.268656716417911, "percentage": 62.69, "elapsed_time": "0:05:48", "remaining_time": "0:03:27", "throughput": 2748.21, "total_tokens": 956808} |
| {"current_steps": 3365, "total_steps": 5360, "loss": 6.1851, "lr": 1.8309627755227643e-05, "epoch": 6.277985074626866, "percentage": 62.78, "elapsed_time": "0:05:48", "remaining_time": "0:03:26", "throughput": 2748.63, "total_tokens": 958152} |
| {"current_steps": 3370, "total_steps": 5360, "loss": 5.8786, "lr": 1.8231227259968926e-05, "epoch": 6.287313432835821, "percentage": 62.87, "elapsed_time": "0:05:49", "remaining_time": "0:03:26", "throughput": 2749.14, "total_tokens": 959560} |
| {"current_steps": 3375, "total_steps": 5360, "loss": 5.6246, "lr": 1.8152898533348317e-05, "epoch": 6.2966417910447765, "percentage": 62.97, "elapsed_time": "0:05:49", "remaining_time": "0:03:25", "throughput": 2749.24, "total_tokens": 960776} |
| {"current_steps": 3380, "total_steps": 5360, "loss": 6.6206, "lr": 1.8074642405877673e-05, "epoch": 6.3059701492537314, "percentage": 63.06, "elapsed_time": "0:05:49", "remaining_time": "0:03:24", "throughput": 2749.99, "total_tokens": 962280} |
| {"current_steps": 3385, "total_steps": 5360, "loss": 6.4849, "lr": 1.799645970729909e-05, "epoch": 6.315298507462686, "percentage": 63.15, "elapsed_time": "0:05:50", "remaining_time": "0:03:24", "throughput": 2750.69, "total_tokens": 963752} |
| {"current_steps": 3390, "total_steps": 5360, "loss": 6.4516, "lr": 1.7918351266576112e-05, "epoch": 6.324626865671641, "percentage": 63.25, "elapsed_time": "0:05:50", "remaining_time": "0:03:23", "throughput": 2751.08, "total_tokens": 965096} |
| {"current_steps": 3395, "total_steps": 5360, "loss": 5.5782, "lr": 1.784031791188492e-05, "epoch": 6.333955223880597, "percentage": 63.34, "elapsed_time": "0:05:51", "remaining_time": "0:03:23", "throughput": 2751.83, "total_tokens": 966600} |
| {"current_steps": 3400, "total_steps": 5360, "loss": 5.7395, "lr": 1.776236047060558e-05, "epoch": 6.343283582089552, "percentage": 63.43, "elapsed_time": "0:05:51", "remaining_time": "0:03:22", "throughput": 2752.29, "total_tokens": 967976} |
| {"current_steps": 3405, "total_steps": 5360, "loss": 5.9395, "lr": 1.768447976931326e-05, "epoch": 6.352611940298507, "percentage": 63.53, "elapsed_time": "0:05:52", "remaining_time": "0:03:22", "throughput": 2752.55, "total_tokens": 969256} |
| {"current_steps": 3410, "total_steps": 5360, "loss": 6.3237, "lr": 1.760667663376943e-05, "epoch": 6.361940298507463, "percentage": 63.62, "elapsed_time": "0:05:52", "remaining_time": "0:03:21", "throughput": 2753.14, "total_tokens": 970696} |
| {"current_steps": 3415, "total_steps": 5360, "loss": 6.1189, "lr": 1.7528951888913177e-05, "epoch": 6.371268656716418, "percentage": 63.71, "elapsed_time": "0:05:53", "remaining_time": "0:03:21", "throughput": 2753.57, "total_tokens": 972072} |
| {"current_steps": 3420, "total_steps": 5360, "loss": 5.9715, "lr": 1.7451306358852386e-05, "epoch": 6.380597014925373, "percentage": 63.81, "elapsed_time": "0:05:53", "remaining_time": "0:03:20", "throughput": 2754.51, "total_tokens": 973736} |
| {"current_steps": 3425, "total_steps": 5360, "loss": 6.1186, "lr": 1.737374086685504e-05, "epoch": 6.389925373134329, "percentage": 63.9, "elapsed_time": "0:05:53", "remaining_time": "0:03:19", "throughput": 2755.01, "total_tokens": 975144} |
| {"current_steps": 3430, "total_steps": 5360, "loss": 6.0654, "lr": 1.729625623534053e-05, "epoch": 6.399253731343284, "percentage": 63.99, "elapsed_time": "0:05:54", "remaining_time": "0:03:19", "throughput": 2755.86, "total_tokens": 976712} |
| {"current_steps": 3435, "total_steps": 5360, "loss": 6.1522, "lr": 1.721885328587083e-05, "epoch": 6.4085820895522385, "percentage": 64.09, "elapsed_time": "0:05:54", "remaining_time": "0:03:18", "throughput": 2756.32, "total_tokens": 978088} |
| {"current_steps": 3440, "total_steps": 5360, "loss": 6.0852, "lr": 1.714153283914189e-05, "epoch": 6.417910447761194, "percentage": 64.18, "elapsed_time": "0:05:55", "remaining_time": "0:03:18", "throughput": 2756.94, "total_tokens": 979560} |
| {"current_steps": 3445, "total_steps": 5360, "loss": 6.0977, "lr": 1.706429571497486e-05, "epoch": 6.427238805970149, "percentage": 64.27, "elapsed_time": "0:05:55", "remaining_time": "0:03:17", "throughput": 2757.5, "total_tokens": 981000} |
| {"current_steps": 3450, "total_steps": 5360, "loss": 5.745, "lr": 1.698714273230746e-05, "epoch": 6.436567164179104, "percentage": 64.37, "elapsed_time": "0:05:56", "remaining_time": "0:03:17", "throughput": 2758.24, "total_tokens": 982568} |
| {"current_steps": 3455, "total_steps": 5360, "loss": 6.1179, "lr": 1.6910074709185235e-05, "epoch": 6.44589552238806, "percentage": 64.46, "elapsed_time": "0:05:56", "remaining_time": "0:03:16", "throughput": 2758.76, "total_tokens": 984040} |
| {"current_steps": 3460, "total_steps": 5360, "loss": 6.3443, "lr": 1.6833092462752942e-05, "epoch": 6.455223880597015, "percentage": 64.55, "elapsed_time": "0:05:57", "remaining_time": "0:03:16", "throughput": 2759.14, "total_tokens": 985384} |
| {"current_steps": 3465, "total_steps": 5360, "loss": 5.5857, "lr": 1.6756196809245838e-05, "epoch": 6.46455223880597, "percentage": 64.65, "elapsed_time": "0:05:57", "remaining_time": "0:03:15", "throughput": 2759.44, "total_tokens": 986696} |
| {"current_steps": 3470, "total_steps": 5360, "loss": 6.0145, "lr": 1.667938856398105e-05, "epoch": 6.473880597014926, "percentage": 64.74, "elapsed_time": "0:05:58", "remaining_time": "0:03:15", "throughput": 2760.01, "total_tokens": 988136} |
| {"current_steps": 3475, "total_steps": 5360, "loss": 6.17, "lr": 1.6602668541348916e-05, "epoch": 6.483208955223881, "percentage": 64.83, "elapsed_time": "0:05:58", "remaining_time": "0:03:14", "throughput": 2760.68, "total_tokens": 989608} |
| {"current_steps": 3480, "total_steps": 5360, "loss": 5.9655, "lr": 1.6526037554804367e-05, "epoch": 6.492537313432836, "percentage": 64.93, "elapsed_time": "0:05:58", "remaining_time": "0:03:13", "throughput": 2761.13, "total_tokens": 990984} |
| {"current_steps": 3484, "total_steps": 5360, "eval_loss": 6.200956344604492, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:06:01", "remaining_time": "0:03:14", "throughput": 2741.9, "total_tokens": 992104} |
| {"current_steps": 3485, "total_steps": 5360, "loss": 5.4054, "lr": 1.6449496416858284e-05, "epoch": 6.5018656716417915, "percentage": 65.02, "elapsed_time": "0:06:03", "remaining_time": "0:03:15", "throughput": 2733.23, "total_tokens": 992360} |
| {"current_steps": 3490, "total_steps": 5360, "loss": 6.5438, "lr": 1.637304593906891e-05, "epoch": 6.5111940298507465, "percentage": 65.11, "elapsed_time": "0:06:03", "remaining_time": "0:03:14", "throughput": 2733.71, "total_tokens": 993864} |
| {"current_steps": 3495, "total_steps": 5360, "loss": 5.9384, "lr": 1.6296686932033203e-05, "epoch": 6.520522388059701, "percentage": 65.21, "elapsed_time": "0:06:04", "remaining_time": "0:03:14", "throughput": 2733.98, "total_tokens": 995176} |
| {"current_steps": 3500, "total_steps": 5360, "loss": 5.8669, "lr": 1.6220420205378282e-05, "epoch": 6.529850746268656, "percentage": 65.3, "elapsed_time": "0:06:04", "remaining_time": "0:03:13", "throughput": 2734.71, "total_tokens": 996680} |
| {"current_steps": 3505, "total_steps": 5360, "loss": 6.4108, "lr": 1.614424656775283e-05, "epoch": 6.539179104477612, "percentage": 65.39, "elapsed_time": "0:06:04", "remaining_time": "0:03:13", "throughput": 2735.06, "total_tokens": 998024} |
| {"current_steps": 3510, "total_steps": 5360, "loss": 6.0936, "lr": 1.6068166826818492e-05, "epoch": 6.548507462686567, "percentage": 65.49, "elapsed_time": "0:06:05", "remaining_time": "0:03:12", "throughput": 2735.44, "total_tokens": 999432} |
| {"current_steps": 3515, "total_steps": 5360, "loss": 6.0611, "lr": 1.5992181789241353e-05, "epoch": 6.557835820895522, "percentage": 65.58, "elapsed_time": "0:06:05", "remaining_time": "0:03:12", "throughput": 2735.67, "total_tokens": 1000712} |
| {"current_steps": 3520, "total_steps": 5360, "loss": 6.1056, "lr": 1.591629226068338e-05, "epoch": 6.567164179104478, "percentage": 65.67, "elapsed_time": "0:06:06", "remaining_time": "0:03:11", "throughput": 2736.08, "total_tokens": 1002056} |
| {"current_steps": 3525, "total_steps": 5360, "loss": 5.8667, "lr": 1.5840499045793843e-05, "epoch": 6.576492537313433, "percentage": 65.76, "elapsed_time": "0:06:06", "remaining_time": "0:03:10", "throughput": 2736.56, "total_tokens": 1003464} |
| {"current_steps": 3530, "total_steps": 5360, "loss": 5.888, "lr": 1.5764802948200825e-05, "epoch": 6.585820895522388, "percentage": 65.86, "elapsed_time": "0:06:07", "remaining_time": "0:03:10", "throughput": 2736.95, "total_tokens": 1004808} |
| {"current_steps": 3535, "total_steps": 5360, "loss": 6.055, "lr": 1.5689204770502666e-05, "epoch": 6.595149253731344, "percentage": 65.95, "elapsed_time": "0:06:07", "remaining_time": "0:03:09", "throughput": 2737.27, "total_tokens": 1006120} |
| {"current_steps": 3540, "total_steps": 5360, "loss": 6.5947, "lr": 1.5613705314259492e-05, "epoch": 6.604477611940299, "percentage": 66.04, "elapsed_time": "0:06:08", "remaining_time": "0:03:09", "throughput": 2737.98, "total_tokens": 1007624} |
| {"current_steps": 3545, "total_steps": 5360, "loss": 6.248, "lr": 1.553830537998466e-05, "epoch": 6.6138059701492535, "percentage": 66.14, "elapsed_time": "0:06:08", "remaining_time": "0:03:08", "throughput": 2738.46, "total_tokens": 1009000} |
| {"current_steps": 3550, "total_steps": 5360, "loss": 6.6569, "lr": 1.5463005767136356e-05, "epoch": 6.6231343283582085, "percentage": 66.23, "elapsed_time": "0:06:08", "remaining_time": "0:03:08", "throughput": 2738.88, "total_tokens": 1010376} |
| {"current_steps": 3555, "total_steps": 5360, "loss": 6.4636, "lr": 1.5387807274109038e-05, "epoch": 6.632462686567164, "percentage": 66.32, "elapsed_time": "0:06:09", "remaining_time": "0:03:07", "throughput": 2739.44, "total_tokens": 1011816} |
| {"current_steps": 3560, "total_steps": 5360, "loss": 6.2983, "lr": 1.531271069822499e-05, "epoch": 6.641791044776119, "percentage": 66.42, "elapsed_time": "0:06:09", "remaining_time": "0:03:06", "throughput": 2740.36, "total_tokens": 1013416} |
| {"current_steps": 3565, "total_steps": 5360, "loss": 5.957, "lr": 1.5237716835725906e-05, "epoch": 6.651119402985074, "percentage": 66.51, "elapsed_time": "0:06:10", "remaining_time": "0:03:06", "throughput": 2740.72, "total_tokens": 1014728} |
| {"current_steps": 3570, "total_steps": 5360, "loss": 5.8537, "lr": 1.5162826481764398e-05, "epoch": 6.66044776119403, "percentage": 66.6, "elapsed_time": "0:06:10", "remaining_time": "0:03:05", "throughput": 2741.21, "total_tokens": 1016136} |
| {"current_steps": 3575, "total_steps": 5360, "loss": 6.2042, "lr": 1.5088040430395589e-05, "epoch": 6.669776119402985, "percentage": 66.7, "elapsed_time": "0:06:11", "remaining_time": "0:03:05", "throughput": 2741.48, "total_tokens": 1017416} |
| {"current_steps": 3580, "total_steps": 5360, "loss": 6.421, "lr": 1.5013359474568712e-05, "epoch": 6.67910447761194, "percentage": 66.79, "elapsed_time": "0:06:11", "remaining_time": "0:03:04", "throughput": 2742.3, "total_tokens": 1019048} |
| {"current_steps": 3585, "total_steps": 5360, "loss": 6.5384, "lr": 1.493878440611866e-05, "epoch": 6.688432835820896, "percentage": 66.88, "elapsed_time": "0:06:12", "remaining_time": "0:03:04", "throughput": 2743.02, "total_tokens": 1020552} |
| {"current_steps": 3590, "total_steps": 5360, "loss": 6.6356, "lr": 1.4864316015757623e-05, "epoch": 6.697761194029851, "percentage": 66.98, "elapsed_time": "0:06:12", "remaining_time": "0:03:03", "throughput": 2743.41, "total_tokens": 1021896} |
| {"current_steps": 3595, "total_steps": 5360, "loss": 6.4283, "lr": 1.478995509306669e-05, "epoch": 6.707089552238806, "percentage": 67.07, "elapsed_time": "0:06:12", "remaining_time": "0:03:03", "throughput": 2743.76, "total_tokens": 1023240} |
| {"current_steps": 3600, "total_steps": 5360, "loss": 5.6127, "lr": 1.4715702426487482e-05, "epoch": 6.7164179104477615, "percentage": 67.16, "elapsed_time": "0:06:13", "remaining_time": "0:03:02", "throughput": 2744.41, "total_tokens": 1024712} |
| {"current_steps": 3605, "total_steps": 5360, "loss": 6.131, "lr": 1.4641558803313781e-05, "epoch": 6.725746268656716, "percentage": 67.26, "elapsed_time": "0:06:13", "remaining_time": "0:03:01", "throughput": 2745.17, "total_tokens": 1026216} |
| {"current_steps": 3610, "total_steps": 5360, "loss": 6.1017, "lr": 1.4567525009683219e-05, "epoch": 6.735074626865671, "percentage": 67.35, "elapsed_time": "0:06:14", "remaining_time": "0:03:01", "throughput": 2745.56, "total_tokens": 1027592} |
| {"current_steps": 3615, "total_steps": 5360, "loss": 5.7326, "lr": 1.4493601830568887e-05, "epoch": 6.744402985074627, "percentage": 67.44, "elapsed_time": "0:06:14", "remaining_time": "0:03:00", "throughput": 2746.21, "total_tokens": 1029064} |
| {"current_steps": 3620, "total_steps": 5360, "loss": 6.5532, "lr": 1.4419790049771068e-05, "epoch": 6.753731343283582, "percentage": 67.54, "elapsed_time": "0:06:15", "remaining_time": "0:03:00", "throughput": 2746.89, "total_tokens": 1030632} |
| {"current_steps": 3625, "total_steps": 5360, "loss": 6.0863, "lr": 1.434609044990886e-05, "epoch": 6.763059701492537, "percentage": 67.63, "elapsed_time": "0:06:15", "remaining_time": "0:02:59", "throughput": 2747.34, "total_tokens": 1032072} |
| {"current_steps": 3630, "total_steps": 5360, "loss": 6.4396, "lr": 1.4272503812411974e-05, "epoch": 6.772388059701493, "percentage": 67.72, "elapsed_time": "0:06:16", "remaining_time": "0:02:59", "throughput": 2747.86, "total_tokens": 1033480} |
| {"current_steps": 3635, "total_steps": 5360, "loss": 6.4214, "lr": 1.4199030917512329e-05, "epoch": 6.781716417910448, "percentage": 67.82, "elapsed_time": "0:06:16", "remaining_time": "0:02:58", "throughput": 2748.18, "total_tokens": 1034792} |
| {"current_steps": 3640, "total_steps": 5360, "loss": 6.6049, "lr": 1.412567254423589e-05, "epoch": 6.791044776119403, "percentage": 67.91, "elapsed_time": "0:06:16", "remaining_time": "0:02:58", "throughput": 2748.69, "total_tokens": 1036200} |
| {"current_steps": 3645, "total_steps": 5360, "loss": 6.6506, "lr": 1.4052429470394352e-05, "epoch": 6.800373134328359, "percentage": 68.0, "elapsed_time": "0:06:17", "remaining_time": "0:02:57", "throughput": 2749.2, "total_tokens": 1037608} |
| {"current_steps": 3650, "total_steps": 5360, "loss": 6.4012, "lr": 1.3979302472576868e-05, "epoch": 6.809701492537314, "percentage": 68.1, "elapsed_time": "0:06:17", "remaining_time": "0:02:57", "throughput": 2749.52, "total_tokens": 1038952} |
| {"current_steps": 3655, "total_steps": 5360, "loss": 6.1017, "lr": 1.3906292326141904e-05, "epoch": 6.8190298507462686, "percentage": 68.19, "elapsed_time": "0:06:18", "remaining_time": "0:02:56", "throughput": 2750.31, "total_tokens": 1040584} |
| {"current_steps": 3660, "total_steps": 5360, "loss": 6.2408, "lr": 1.3833399805208904e-05, "epoch": 6.8283582089552235, "percentage": 68.28, "elapsed_time": "0:06:18", "remaining_time": "0:02:55", "throughput": 2750.72, "total_tokens": 1041960} |
| {"current_steps": 3665, "total_steps": 5360, "loss": 5.5561, "lr": 1.376062568265018e-05, "epoch": 6.837686567164179, "percentage": 68.38, "elapsed_time": "0:06:19", "remaining_time": "0:02:55", "throughput": 2751.17, "total_tokens": 1043336} |
| {"current_steps": 3670, "total_steps": 5360, "loss": 6.2007, "lr": 1.3687970730082678e-05, "epoch": 6.847014925373134, "percentage": 68.47, "elapsed_time": "0:06:19", "remaining_time": "0:02:54", "throughput": 2751.62, "total_tokens": 1044712} |
| {"current_steps": 3675, "total_steps": 5360, "loss": 5.9179, "lr": 1.361543571785976e-05, "epoch": 6.856343283582089, "percentage": 68.56, "elapsed_time": "0:06:20", "remaining_time": "0:02:54", "throughput": 2752.11, "total_tokens": 1046120} |
| {"current_steps": 3680, "total_steps": 5360, "loss": 6.482, "lr": 1.3543021415063117e-05, "epoch": 6.865671641791045, "percentage": 68.66, "elapsed_time": "0:06:20", "remaining_time": "0:02:53", "throughput": 2752.72, "total_tokens": 1047592} |
| {"current_steps": 3685, "total_steps": 5360, "loss": 5.4138, "lr": 1.347072858949453e-05, "epoch": 6.875, "percentage": 68.75, "elapsed_time": "0:06:21", "remaining_time": "0:02:53", "throughput": 2753.11, "total_tokens": 1048936} |
| {"current_steps": 3690, "total_steps": 5360, "loss": 6.5698, "lr": 1.3398558007667806e-05, "epoch": 6.884328358208955, "percentage": 68.84, "elapsed_time": "0:06:21", "remaining_time": "0:02:52", "throughput": 2753.64, "total_tokens": 1050376} |
| {"current_steps": 3695, "total_steps": 5360, "loss": 5.5196, "lr": 1.3326510434800566e-05, "epoch": 6.893656716417911, "percentage": 68.94, "elapsed_time": "0:06:21", "remaining_time": "0:02:52", "throughput": 2754.17, "total_tokens": 1051816} |
| {"current_steps": 3700, "total_steps": 5360, "loss": 5.9008, "lr": 1.3254586634806249e-05, "epoch": 6.902985074626866, "percentage": 69.03, "elapsed_time": "0:06:22", "remaining_time": "0:02:51", "throughput": 2754.46, "total_tokens": 1053128} |
| {"current_steps": 3705, "total_steps": 5360, "loss": 6.6612, "lr": 1.3182787370285865e-05, "epoch": 6.912313432835821, "percentage": 69.12, "elapsed_time": "0:06:22", "remaining_time": "0:02:50", "throughput": 2754.76, "total_tokens": 1054440} |
| {"current_steps": 3710, "total_steps": 5360, "loss": 5.8695, "lr": 1.3111113402520053e-05, "epoch": 6.9216417910447765, "percentage": 69.22, "elapsed_time": "0:06:23", "remaining_time": "0:02:50", "throughput": 2755.2, "total_tokens": 1055816} |
| {"current_steps": 3715, "total_steps": 5360, "loss": 6.0544, "lr": 1.3039565491460882e-05, "epoch": 6.9309701492537314, "percentage": 69.31, "elapsed_time": "0:06:23", "remaining_time": "0:02:49", "throughput": 2755.81, "total_tokens": 1057288} |
| {"current_steps": 3720, "total_steps": 5360, "loss": 5.9799, "lr": 1.2968144395723914e-05, "epoch": 6.940298507462686, "percentage": 69.4, "elapsed_time": "0:06:24", "remaining_time": "0:02:49", "throughput": 2756.63, "total_tokens": 1058888} |
| {"current_steps": 3725, "total_steps": 5360, "loss": 6.2505, "lr": 1.289685087258004e-05, "epoch": 6.949626865671641, "percentage": 69.5, "elapsed_time": "0:06:24", "remaining_time": "0:02:48", "throughput": 2757.14, "total_tokens": 1060296} |
| {"current_steps": 3730, "total_steps": 5360, "loss": 5.6764, "lr": 1.2825685677947563e-05, "epoch": 6.958955223880597, "percentage": 69.59, "elapsed_time": "0:06:25", "remaining_time": "0:02:48", "throughput": 2757.49, "total_tokens": 1061640} |
| {"current_steps": 3735, "total_steps": 5360, "loss": 5.4387, "lr": 1.2754649566384114e-05, "epoch": 6.968283582089552, "percentage": 69.68, "elapsed_time": "0:06:25", "remaining_time": "0:02:47", "throughput": 2757.61, "total_tokens": 1062888} |
| {"current_steps": 3740, "total_steps": 5360, "loss": 6.3835, "lr": 1.2683743291078649e-05, "epoch": 6.977611940298507, "percentage": 69.78, "elapsed_time": "0:06:25", "remaining_time": "0:02:47", "throughput": 2758.01, "total_tokens": 1064328} |
| {"current_steps": 3745, "total_steps": 5360, "loss": 5.9752, "lr": 1.2612967603843512e-05, "epoch": 6.986940298507463, "percentage": 69.87, "elapsed_time": "0:06:26", "remaining_time": "0:02:46", "throughput": 2758.86, "total_tokens": 1065928} |
| {"current_steps": 3750, "total_steps": 5360, "loss": 6.3153, "lr": 1.2542323255106408e-05, "epoch": 6.996268656716418, "percentage": 69.96, "elapsed_time": "0:06:26", "remaining_time": "0:02:46", "throughput": 2759.04, "total_tokens": 1067176} |
| {"current_steps": 3752, "total_steps": 5360, "eval_loss": 6.178179740905762, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:06:29", "remaining_time": "0:02:46", "throughput": 2740.06, "total_tokens": 1067520} |
| {"current_steps": 3755, "total_steps": 5360, "loss": 5.9444, "lr": 1.24718109939025e-05, "epoch": 7.005597014925373, "percentage": 70.06, "elapsed_time": "0:06:30", "remaining_time": "0:02:47", "throughput": 2732.0, "total_tokens": 1068192} |
| {"current_steps": 3760, "total_steps": 5360, "loss": 6.1903, "lr": 1.2401431567866425e-05, "epoch": 7.014925373134329, "percentage": 70.15, "elapsed_time": "0:06:31", "remaining_time": "0:02:46", "throughput": 2732.44, "total_tokens": 1069600} |
| {"current_steps": 3765, "total_steps": 5360, "loss": 5.4235, "lr": 1.233118572322437e-05, "epoch": 7.024253731343284, "percentage": 70.24, "elapsed_time": "0:06:31", "remaining_time": "0:02:46", "throughput": 2732.66, "total_tokens": 1070880} |
| {"current_steps": 3770, "total_steps": 5360, "loss": 5.953, "lr": 1.22610742047862e-05, "epoch": 7.0335820895522385, "percentage": 70.34, "elapsed_time": "0:06:32", "remaining_time": "0:02:45", "throughput": 2733.35, "total_tokens": 1072416} |
| {"current_steps": 3775, "total_steps": 5360, "loss": 6.5618, "lr": 1.21910977559375e-05, "epoch": 7.042910447761194, "percentage": 70.43, "elapsed_time": "0:06:32", "remaining_time": "0:02:44", "throughput": 2733.78, "total_tokens": 1073824} |
| {"current_steps": 3780, "total_steps": 5360, "loss": 6.1063, "lr": 1.212125711863176e-05, "epoch": 7.052238805970149, "percentage": 70.52, "elapsed_time": "0:06:33", "remaining_time": "0:02:44", "throughput": 2733.78, "total_tokens": 1074976} |
| {"current_steps": 3785, "total_steps": 5360, "loss": 5.7972, "lr": 1.2051553033382425e-05, "epoch": 7.061567164179104, "percentage": 70.62, "elapsed_time": "0:06:33", "remaining_time": "0:02:43", "throughput": 2734.23, "total_tokens": 1076416} |
| {"current_steps": 3790, "total_steps": 5360, "loss": 5.831, "lr": 1.1981986239255164e-05, "epoch": 7.07089552238806, "percentage": 70.71, "elapsed_time": "0:06:34", "remaining_time": "0:02:43", "throughput": 2734.79, "total_tokens": 1077920} |
| {"current_steps": 3795, "total_steps": 5360, "loss": 5.5865, "lr": 1.1912557473859895e-05, "epoch": 7.080223880597015, "percentage": 70.8, "elapsed_time": "0:06:34", "remaining_time": "0:02:42", "throughput": 2735.86, "total_tokens": 1079776} |
| {"current_steps": 3800, "total_steps": 5360, "loss": 6.3899, "lr": 1.1843267473343048e-05, "epoch": 7.08955223880597, "percentage": 70.9, "elapsed_time": "0:06:35", "remaining_time": "0:02:42", "throughput": 2736.15, "total_tokens": 1081088} |
| {"current_steps": 3805, "total_steps": 5360, "loss": 6.194, "lr": 1.177411697237977e-05, "epoch": 7.098880597014926, "percentage": 70.99, "elapsed_time": "0:06:35", "remaining_time": "0:02:41", "throughput": 2736.91, "total_tokens": 1082624} |
| {"current_steps": 3810, "total_steps": 5360, "loss": 6.7915, "lr": 1.1705106704166069e-05, "epoch": 7.108208955223881, "percentage": 71.08, "elapsed_time": "0:06:36", "remaining_time": "0:02:41", "throughput": 2737.31, "total_tokens": 1084000} |
| {"current_steps": 3815, "total_steps": 5360, "loss": 6.0824, "lr": 1.1636237400411107e-05, "epoch": 7.117537313432836, "percentage": 71.18, "elapsed_time": "0:06:36", "remaining_time": "0:02:40", "throughput": 2737.97, "total_tokens": 1085504} |
| {"current_steps": 3820, "total_steps": 5360, "loss": 6.0044, "lr": 1.1567509791329401e-05, "epoch": 7.126865671641791, "percentage": 71.27, "elapsed_time": "0:06:36", "remaining_time": "0:02:40", "throughput": 2738.34, "total_tokens": 1086848} |
| {"current_steps": 3825, "total_steps": 5360, "loss": 6.3117, "lr": 1.1498924605633111e-05, "epoch": 7.1361940298507465, "percentage": 71.36, "elapsed_time": "0:06:37", "remaining_time": "0:02:39", "throughput": 2738.66, "total_tokens": 1088160} |
| {"current_steps": 3830, "total_steps": 5360, "loss": 6.0298, "lr": 1.1430482570524253e-05, "epoch": 7.145522388059701, "percentage": 71.46, "elapsed_time": "0:06:37", "remaining_time": "0:02:38", "throughput": 2739.14, "total_tokens": 1089568} |
| {"current_steps": 3835, "total_steps": 5360, "loss": 5.9721, "lr": 1.136218441168709e-05, "epoch": 7.154850746268656, "percentage": 71.55, "elapsed_time": "0:06:38", "remaining_time": "0:02:38", "throughput": 2739.2, "total_tokens": 1090752} |
| {"current_steps": 3840, "total_steps": 5360, "loss": 5.8658, "lr": 1.1294030853280321e-05, "epoch": 7.164179104477612, "percentage": 71.64, "elapsed_time": "0:06:38", "remaining_time": "0:02:37", "throughput": 2739.62, "total_tokens": 1092128} |
| {"current_steps": 3845, "total_steps": 5360, "loss": 6.0109, "lr": 1.12260226179295e-05, "epoch": 7.173507462686567, "percentage": 71.74, "elapsed_time": "0:06:39", "remaining_time": "0:02:37", "throughput": 2739.79, "total_tokens": 1093376} |
| {"current_steps": 3850, "total_steps": 5360, "loss": 5.887, "lr": 1.115816042671933e-05, "epoch": 7.182835820895522, "percentage": 71.83, "elapsed_time": "0:06:39", "remaining_time": "0:02:36", "throughput": 2740.42, "total_tokens": 1094848} |
| {"current_steps": 3855, "total_steps": 5360, "loss": 6.0866, "lr": 1.1090444999186e-05, "epoch": 7.192164179104478, "percentage": 71.92, "elapsed_time": "0:06:39", "remaining_time": "0:02:36", "throughput": 2740.96, "total_tokens": 1096352} |
| {"current_steps": 3860, "total_steps": 5360, "loss": 6.0945, "lr": 1.102287705330961e-05, "epoch": 7.201492537313433, "percentage": 72.01, "elapsed_time": "0:06:40", "remaining_time": "0:02:35", "throughput": 2741.53, "total_tokens": 1097824} |
| {"current_steps": 3865, "total_steps": 5360, "loss": 6.4308, "lr": 1.095545730550649e-05, "epoch": 7.210820895522388, "percentage": 72.11, "elapsed_time": "0:06:40", "remaining_time": "0:02:35", "throughput": 2741.81, "total_tokens": 1099136} |
| {"current_steps": 3870, "total_steps": 5360, "loss": 5.7004, "lr": 1.0888186470621675e-05, "epoch": 7.220149253731344, "percentage": 72.2, "elapsed_time": "0:06:41", "remaining_time": "0:02:34", "throughput": 2742.18, "total_tokens": 1100512} |
| {"current_steps": 3875, "total_steps": 5360, "loss": 6.2317, "lr": 1.0821065261921262e-05, "epoch": 7.229477611940299, "percentage": 72.29, "elapsed_time": "0:06:41", "remaining_time": "0:02:33", "throughput": 2742.5, "total_tokens": 1101856} |
| {"current_steps": 3880, "total_steps": 5360, "loss": 5.8558, "lr": 1.0754094391084896e-05, "epoch": 7.2388059701492535, "percentage": 72.39, "elapsed_time": "0:06:42", "remaining_time": "0:02:33", "throughput": 2742.95, "total_tokens": 1103264} |
| {"current_steps": 3885, "total_steps": 5360, "loss": 6.0049, "lr": 1.0687274568198208e-05, "epoch": 7.248134328358209, "percentage": 72.48, "elapsed_time": "0:06:42", "remaining_time": "0:02:32", "throughput": 2743.56, "total_tokens": 1104736} |
| {"current_steps": 3890, "total_steps": 5360, "loss": 5.9316, "lr": 1.0620606501745251e-05, "epoch": 7.257462686567164, "percentage": 72.57, "elapsed_time": "0:06:43", "remaining_time": "0:02:32", "throughput": 2744.26, "total_tokens": 1106336} |
| {"current_steps": 3895, "total_steps": 5360, "loss": 5.6941, "lr": 1.0554090898601062e-05, "epoch": 7.266791044776119, "percentage": 72.67, "elapsed_time": "0:06:43", "remaining_time": "0:02:31", "throughput": 2744.76, "total_tokens": 1107808} |
| {"current_steps": 3900, "total_steps": 5360, "loss": 6.6189, "lr": 1.0487728464024086e-05, "epoch": 7.276119402985074, "percentage": 72.76, "elapsed_time": "0:06:44", "remaining_time": "0:02:31", "throughput": 2745.15, "total_tokens": 1109184} |
| {"current_steps": 3905, "total_steps": 5360, "loss": 6.732, "lr": 1.0421519901648758e-05, "epoch": 7.28544776119403, "percentage": 72.85, "elapsed_time": "0:06:44", "remaining_time": "0:02:30", "throughput": 2745.87, "total_tokens": 1110720} |
| {"current_steps": 3910, "total_steps": 5360, "loss": 5.4294, "lr": 1.0355465913478019e-05, "epoch": 7.294776119402985, "percentage": 72.95, "elapsed_time": "0:06:44", "remaining_time": "0:02:30", "throughput": 2746.25, "total_tokens": 1112096} |
| {"current_steps": 3915, "total_steps": 5360, "loss": 5.931, "lr": 1.0289567199875878e-05, "epoch": 7.30410447761194, "percentage": 73.04, "elapsed_time": "0:06:45", "remaining_time": "0:02:29", "throughput": 2746.52, "total_tokens": 1113408} |
| {"current_steps": 3920, "total_steps": 5360, "loss": 6.1846, "lr": 1.0223824459559971e-05, "epoch": 7.313432835820896, "percentage": 73.13, "elapsed_time": "0:06:45", "remaining_time": "0:02:29", "throughput": 2746.92, "total_tokens": 1114784} |
| {"current_steps": 3925, "total_steps": 5360, "loss": 6.5178, "lr": 1.0158238389594164e-05, "epoch": 7.322761194029851, "percentage": 73.23, "elapsed_time": "0:06:46", "remaining_time": "0:02:28", "throughput": 2747.73, "total_tokens": 1116416} |
| {"current_steps": 3930, "total_steps": 5360, "loss": 6.2234, "lr": 1.009280968538118e-05, "epoch": 7.332089552238806, "percentage": 73.32, "elapsed_time": "0:06:46", "remaining_time": "0:02:28", "throughput": 2748.18, "total_tokens": 1117824} |
| {"current_steps": 3935, "total_steps": 5360, "loss": 6.1671, "lr": 1.0027539040655173e-05, "epoch": 7.3414179104477615, "percentage": 73.41, "elapsed_time": "0:06:47", "remaining_time": "0:02:27", "throughput": 2748.46, "total_tokens": 1119136} |
| {"current_steps": 3940, "total_steps": 5360, "loss": 5.7908, "lr": 9.962427147474474e-06, "epoch": 7.350746268656716, "percentage": 73.51, "elapsed_time": "0:06:47", "remaining_time": "0:02:26", "throughput": 2748.84, "total_tokens": 1120480} |
| {"current_steps": 3945, "total_steps": 5360, "loss": 6.0781, "lr": 9.89747469621411e-06, "epoch": 7.360074626865671, "percentage": 73.6, "elapsed_time": "0:06:48", "remaining_time": "0:02:26", "throughput": 2749.19, "total_tokens": 1121856} |
| {"current_steps": 3950, "total_steps": 5360, "loss": 6.1132, "lr": 9.832682375558614e-06, "epoch": 7.369402985074627, "percentage": 73.69, "elapsed_time": "0:06:48", "remaining_time": "0:02:25", "throughput": 2749.39, "total_tokens": 1123136} |
| {"current_steps": 3955, "total_steps": 5360, "loss": 6.3012, "lr": 9.768050872494638e-06, "epoch": 7.378731343283582, "percentage": 73.79, "elapsed_time": "0:06:48", "remaining_time": "0:02:25", "throughput": 2749.71, "total_tokens": 1124480} |
| {"current_steps": 3960, "total_steps": 5360, "loss": 6.2296, "lr": 9.70358087230373e-06, "epoch": 7.388059701492537, "percentage": 73.88, "elapsed_time": "0:06:49", "remaining_time": "0:02:24", "throughput": 2750.1, "total_tokens": 1125856} |
| {"current_steps": 3965, "total_steps": 5360, "loss": 6.0967, "lr": 9.639273058555004e-06, "epoch": 7.397388059701493, "percentage": 73.97, "elapsed_time": "0:06:49", "remaining_time": "0:02:24", "throughput": 2750.58, "total_tokens": 1127264} |
| {"current_steps": 3970, "total_steps": 5360, "loss": 6.4853, "lr": 9.575128113097952e-06, "epoch": 7.406716417910448, "percentage": 74.07, "elapsed_time": "0:06:50", "remaining_time": "0:02:23", "throughput": 2750.9, "total_tokens": 1128640} |
| {"current_steps": 3975, "total_steps": 5360, "loss": 6.4158, "lr": 9.5111467160552e-06, "epoch": 7.416044776119403, "percentage": 74.16, "elapsed_time": "0:06:50", "remaining_time": "0:02:23", "throughput": 2751.24, "total_tokens": 1129984} |
| {"current_steps": 3980, "total_steps": 5360, "loss": 6.0877, "lr": 9.447329545815246e-06, "epoch": 7.425373134328359, "percentage": 74.25, "elapsed_time": "0:06:51", "remaining_time": "0:02:22", "throughput": 2751.84, "total_tokens": 1131552} |
| {"current_steps": 3985, "total_steps": 5360, "loss": 6.1683, "lr": 9.383677279025347e-06, "epoch": 7.434701492537314, "percentage": 74.35, "elapsed_time": "0:06:51", "remaining_time": "0:02:22", "throughput": 2752.26, "total_tokens": 1132928} |
| {"current_steps": 3990, "total_steps": 5360, "loss": 5.8752, "lr": 9.320190590584273e-06, "epoch": 7.4440298507462686, "percentage": 74.44, "elapsed_time": "0:06:52", "remaining_time": "0:02:21", "throughput": 2752.6, "total_tokens": 1134336} |
| {"current_steps": 3995, "total_steps": 5360, "loss": 5.8536, "lr": 9.256870153635208e-06, "epoch": 7.4533582089552235, "percentage": 74.53, "elapsed_time": "0:06:52", "remaining_time": "0:02:20", "throughput": 2753.26, "total_tokens": 1135840} |
| {"current_steps": 4000, "total_steps": 5360, "loss": 5.8271, "lr": 9.193716639558587e-06, "epoch": 7.462686567164179, "percentage": 74.63, "elapsed_time": "0:06:52", "remaining_time": "0:02:20", "throughput": 2753.62, "total_tokens": 1137216} |
| {"current_steps": 4005, "total_steps": 5360, "loss": 6.065, "lr": 9.130730717964948e-06, "epoch": 7.472014925373134, "percentage": 74.72, "elapsed_time": "0:06:53", "remaining_time": "0:02:19", "throughput": 2753.88, "total_tokens": 1138528} |
| {"current_steps": 4010, "total_steps": 5360, "loss": 6.6618, "lr": 9.067913056687899e-06, "epoch": 7.481343283582089, "percentage": 74.81, "elapsed_time": "0:06:53", "remaining_time": "0:02:19", "throughput": 2754.22, "total_tokens": 1139872} |
| {"current_steps": 4015, "total_steps": 5360, "loss": 6.6422, "lr": 9.005264321776974e-06, "epoch": 7.490671641791045, "percentage": 74.91, "elapsed_time": "0:06:54", "remaining_time": "0:02:18", "throughput": 2754.9, "total_tokens": 1141408} |
| {"current_steps": 4020, "total_steps": 5360, "loss": 6.4198, "lr": 8.942785177490617e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:06:54", "remaining_time": "0:02:18", "throughput": 2755.51, "total_tokens": 1142912} |
| {"current_steps": 4020, "total_steps": 5360, "eval_loss": 6.164480686187744, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:06:57", "remaining_time": "0:02:19", "throughput": 2738.5, "total_tokens": 1142912} |
| {"current_steps": 4025, "total_steps": 5360, "loss": 5.6221, "lr": 8.880476286289091e-06, "epoch": 7.509328358208955, "percentage": 75.09, "elapsed_time": "0:06:58", "remaining_time": "0:02:18", "throughput": 2732.45, "total_tokens": 1144256} |
| {"current_steps": 4030, "total_steps": 5360, "loss": 5.5548, "lr": 8.818338308827529e-06, "epoch": 7.518656716417911, "percentage": 75.19, "elapsed_time": "0:06:59", "remaining_time": "0:02:18", "throughput": 2732.74, "total_tokens": 1145568} |
| {"current_steps": 4035, "total_steps": 5360, "loss": 6.2794, "lr": 8.75637190394884e-06, "epoch": 7.527985074626866, "percentage": 75.28, "elapsed_time": "0:06:59", "remaining_time": "0:02:17", "throughput": 2733.2, "total_tokens": 1147008} |
| {"current_steps": 4040, "total_steps": 5360, "loss": 5.8641, "lr": 8.69457772867677e-06, "epoch": 7.537313432835821, "percentage": 75.37, "elapsed_time": "0:07:00", "remaining_time": "0:02:17", "throughput": 2733.52, "total_tokens": 1148416} |
| {"current_steps": 4045, "total_steps": 5360, "loss": 6.2364, "lr": 8.632956438208961e-06, "epoch": 7.5466417910447765, "percentage": 75.47, "elapsed_time": "0:07:00", "remaining_time": "0:02:16", "throughput": 2734.04, "total_tokens": 1149888} |
| {"current_steps": 4050, "total_steps": 5360, "loss": 5.519, "lr": 8.571508685909931e-06, "epoch": 7.5559701492537314, "percentage": 75.56, "elapsed_time": "0:07:01", "remaining_time": "0:02:16", "throughput": 2734.61, "total_tokens": 1151360} |
| {"current_steps": 4055, "total_steps": 5360, "loss": 6.4117, "lr": 8.510235123304227e-06, "epoch": 7.565298507462686, "percentage": 75.65, "elapsed_time": "0:07:01", "remaining_time": "0:02:15", "throughput": 2735.15, "total_tokens": 1152800} |
| {"current_steps": 4060, "total_steps": 5360, "loss": 5.8707, "lr": 8.449136400069464e-06, "epoch": 7.574626865671641, "percentage": 75.75, "elapsed_time": "0:07:01", "remaining_time": "0:02:15", "throughput": 2735.66, "total_tokens": 1154272} |
| {"current_steps": 4065, "total_steps": 5360, "loss": 6.2107, "lr": 8.38821316402946e-06, "epoch": 7.583955223880597, "percentage": 75.84, "elapsed_time": "0:07:02", "remaining_time": "0:02:14", "throughput": 2735.99, "total_tokens": 1155584} |
| {"current_steps": 4070, "total_steps": 5360, "loss": 6.3887, "lr": 8.327466061147337e-06, "epoch": 7.593283582089552, "percentage": 75.93, "elapsed_time": "0:07:02", "remaining_time": "0:02:14", "throughput": 2736.71, "total_tokens": 1157152} |
| {"current_steps": 4075, "total_steps": 5360, "loss": 6.1544, "lr": 8.266895735518729e-06, "epoch": 7.602611940298507, "percentage": 76.03, "elapsed_time": "0:07:03", "remaining_time": "0:02:13", "throughput": 2736.96, "total_tokens": 1158432} |
| {"current_steps": 4080, "total_steps": 5360, "loss": 5.8934, "lr": 8.20650282936488e-06, "epoch": 7.611940298507463, "percentage": 76.12, "elapsed_time": "0:07:03", "remaining_time": "0:02:12", "throughput": 2737.78, "total_tokens": 1160032} |
| {"current_steps": 4085, "total_steps": 5360, "loss": 5.6975, "lr": 8.146287983025903e-06, "epoch": 7.621268656716418, "percentage": 76.21, "elapsed_time": "0:07:04", "remaining_time": "0:02:12", "throughput": 2738.42, "total_tokens": 1161536} |
| {"current_steps": 4090, "total_steps": 5360, "loss": 6.0205, "lr": 8.086251834953953e-06, "epoch": 7.630597014925373, "percentage": 76.31, "elapsed_time": "0:07:04", "remaining_time": "0:02:11", "throughput": 2738.98, "total_tokens": 1163072} |
| {"current_steps": 4095, "total_steps": 5360, "loss": 6.2374, "lr": 8.02639502170645e-06, "epoch": 7.639925373134329, "percentage": 76.4, "elapsed_time": "0:07:05", "remaining_time": "0:02:11", "throughput": 2739.26, "total_tokens": 1164384} |
| {"current_steps": 4100, "total_steps": 5360, "loss": 6.2528, "lr": 7.966718177939366e-06, "epoch": 7.649253731343284, "percentage": 76.49, "elapsed_time": "0:07:05", "remaining_time": "0:02:10", "throughput": 2739.58, "total_tokens": 1165728} |
| {"current_steps": 4105, "total_steps": 5360, "loss": 6.3124, "lr": 7.907221936400453e-06, "epoch": 7.6585820895522385, "percentage": 76.59, "elapsed_time": "0:07:05", "remaining_time": "0:02:10", "throughput": 2740.26, "total_tokens": 1167264} |
| {"current_steps": 4110, "total_steps": 5360, "loss": 6.0519, "lr": 7.847906927922574e-06, "epoch": 7.667910447761194, "percentage": 76.68, "elapsed_time": "0:07:06", "remaining_time": "0:02:09", "throughput": 2740.82, "total_tokens": 1168800} |
| {"current_steps": 4115, "total_steps": 5360, "loss": 6.3352, "lr": 7.788773781416974e-06, "epoch": 7.677238805970149, "percentage": 76.77, "elapsed_time": "0:07:06", "remaining_time": "0:02:09", "throughput": 2741.33, "total_tokens": 1170240} |
| {"current_steps": 4120, "total_steps": 5360, "loss": 5.5979, "lr": 7.729823123866656e-06, "epoch": 7.686567164179104, "percentage": 76.87, "elapsed_time": "0:07:07", "remaining_time": "0:02:08", "throughput": 2742.15, "total_tokens": 1171936} |
| {"current_steps": 4125, "total_steps": 5360, "loss": 6.1621, "lr": 7.671055580319706e-06, "epoch": 7.69589552238806, "percentage": 76.96, "elapsed_time": "0:07:07", "remaining_time": "0:02:08", "throughput": 2742.39, "total_tokens": 1173216} |
| {"current_steps": 4130, "total_steps": 5360, "loss": 6.2407, "lr": 7.612471773882651e-06, "epoch": 7.705223880597015, "percentage": 77.05, "elapsed_time": "0:07:08", "remaining_time": "0:02:07", "throughput": 2742.64, "total_tokens": 1174496} |
| {"current_steps": 4135, "total_steps": 5360, "loss": 5.7773, "lr": 7.554072325713896e-06, "epoch": 7.71455223880597, "percentage": 77.15, "elapsed_time": "0:07:08", "remaining_time": "0:02:07", "throughput": 2743.28, "total_tokens": 1176032} |
| {"current_steps": 4140, "total_steps": 5360, "loss": 5.7109, "lr": 7.495857855017091e-06, "epoch": 7.723880597014926, "percentage": 77.24, "elapsed_time": "0:07:09", "remaining_time": "0:02:06", "throughput": 2743.82, "total_tokens": 1177472} |
| {"current_steps": 4145, "total_steps": 5360, "loss": 6.2057, "lr": 7.437828979034606e-06, "epoch": 7.733208955223881, "percentage": 77.33, "elapsed_time": "0:07:09", "remaining_time": "0:02:05", "throughput": 2744.41, "total_tokens": 1178976} |
| {"current_steps": 4150, "total_steps": 5360, "loss": 5.5216, "lr": 7.379986313040959e-06, "epoch": 7.742537313432836, "percentage": 77.43, "elapsed_time": "0:07:10", "remaining_time": "0:02:05", "throughput": 2744.96, "total_tokens": 1180448} |
| {"current_steps": 4155, "total_steps": 5360, "loss": 5.5106, "lr": 7.3223304703363135e-06, "epoch": 7.7518656716417915, "percentage": 77.52, "elapsed_time": "0:07:10", "remaining_time": "0:02:04", "throughput": 2745.29, "total_tokens": 1181888} |
| {"current_steps": 4160, "total_steps": 5360, "loss": 6.0824, "lr": 7.264862062239947e-06, "epoch": 7.7611940298507465, "percentage": 77.61, "elapsed_time": "0:07:10", "remaining_time": "0:02:04", "throughput": 2745.98, "total_tokens": 1183456} |
| {"current_steps": 4165, "total_steps": 5360, "loss": 6.2111, "lr": 7.2075816980837814e-06, "epoch": 7.770522388059701, "percentage": 77.71, "elapsed_time": "0:07:11", "remaining_time": "0:02:03", "throughput": 2746.31, "total_tokens": 1184800} |
| {"current_steps": 4170, "total_steps": 5360, "loss": 6.2457, "lr": 7.150489985205952e-06, "epoch": 7.779850746268656, "percentage": 77.8, "elapsed_time": "0:07:11", "remaining_time": "0:02:03", "throughput": 2746.91, "total_tokens": 1186304} |
| {"current_steps": 4175, "total_steps": 5360, "loss": 6.3101, "lr": 7.093587528944326e-06, "epoch": 7.789179104477612, "percentage": 77.89, "elapsed_time": "0:07:12", "remaining_time": "0:02:02", "throughput": 2747.41, "total_tokens": 1187744} |
| {"current_steps": 4180, "total_steps": 5360, "loss": 6.1509, "lr": 7.036874932630117e-06, "epoch": 7.798507462686567, "percentage": 77.99, "elapsed_time": "0:07:12", "remaining_time": "0:02:02", "throughput": 2748.1, "total_tokens": 1189376} |
| {"current_steps": 4185, "total_steps": 5360, "loss": 6.6927, "lr": 6.980352797581438e-06, "epoch": 7.807835820895522, "percentage": 78.08, "elapsed_time": "0:07:13", "remaining_time": "0:02:01", "throughput": 2748.65, "total_tokens": 1190912} |
| {"current_steps": 4190, "total_steps": 5360, "loss": 5.8994, "lr": 6.924021723097004e-06, "epoch": 7.817164179104478, "percentage": 78.17, "elapsed_time": "0:07:13", "remaining_time": "0:02:01", "throughput": 2749.24, "total_tokens": 1192416} |
| {"current_steps": 4195, "total_steps": 5360, "loss": 5.8114, "lr": 6.867882306449694e-06, "epoch": 7.826492537313433, "percentage": 78.26, "elapsed_time": "0:07:14", "remaining_time": "0:02:00", "throughput": 2749.62, "total_tokens": 1193792} |
| {"current_steps": 4200, "total_steps": 5360, "loss": 6.5992, "lr": 6.8119351428802796e-06, "epoch": 7.835820895522388, "percentage": 78.36, "elapsed_time": "0:07:14", "remaining_time": "0:02:00", "throughput": 2750.03, "total_tokens": 1195200} |
| {"current_steps": 4205, "total_steps": 5360, "loss": 6.0213, "lr": 6.756180825591099e-06, "epoch": 7.845149253731344, "percentage": 78.45, "elapsed_time": "0:07:15", "remaining_time": "0:01:59", "throughput": 2750.52, "total_tokens": 1196672} |
| {"current_steps": 4210, "total_steps": 5360, "loss": 6.4122, "lr": 6.700619945739728e-06, "epoch": 7.854477611940299, "percentage": 78.54, "elapsed_time": "0:07:15", "remaining_time": "0:01:58", "throughput": 2751.39, "total_tokens": 1198336} |
| {"current_steps": 4215, "total_steps": 5360, "loss": 5.9713, "lr": 6.645253092432785e-06, "epoch": 7.8638059701492535, "percentage": 78.64, "elapsed_time": "0:07:15", "remaining_time": "0:01:58", "throughput": 2751.77, "total_tokens": 1199712} |
| {"current_steps": 4220, "total_steps": 5360, "loss": 6.1534, "lr": 6.590080852719602e-06, "epoch": 7.8731343283582085, "percentage": 78.73, "elapsed_time": "0:07:16", "remaining_time": "0:01:57", "throughput": 2752.15, "total_tokens": 1201088} |
| {"current_steps": 4225, "total_steps": 5360, "loss": 5.9652, "lr": 6.535103811586085e-06, "epoch": 7.882462686567164, "percentage": 78.82, "elapsed_time": "0:07:16", "remaining_time": "0:01:57", "throughput": 2752.49, "total_tokens": 1202432} |
| {"current_steps": 4230, "total_steps": 5360, "loss": 6.0424, "lr": 6.480322551948426e-06, "epoch": 7.891791044776119, "percentage": 78.92, "elapsed_time": "0:07:17", "remaining_time": "0:01:56", "throughput": 2752.93, "total_tokens": 1203872} |
| {"current_steps": 4235, "total_steps": 5360, "loss": 6.0421, "lr": 6.425737654646993e-06, "epoch": 7.901119402985074, "percentage": 79.01, "elapsed_time": "0:07:17", "remaining_time": "0:01:56", "throughput": 2753.42, "total_tokens": 1205312} |
| {"current_steps": 4240, "total_steps": 5360, "loss": 6.4943, "lr": 6.371349698440149e-06, "epoch": 7.91044776119403, "percentage": 79.1, "elapsed_time": "0:07:18", "remaining_time": "0:01:55", "throughput": 2753.8, "total_tokens": 1206688} |
| {"current_steps": 4245, "total_steps": 5360, "loss": 5.6156, "lr": 6.317159259998073e-06, "epoch": 7.919776119402985, "percentage": 79.2, "elapsed_time": "0:07:18", "remaining_time": "0:01:55", "throughput": 2754.15, "total_tokens": 1208064} |
| {"current_steps": 4250, "total_steps": 5360, "loss": 5.9599, "lr": 6.2631669138967285e-06, "epoch": 7.92910447761194, "percentage": 79.29, "elapsed_time": "0:07:19", "remaining_time": "0:01:54", "throughput": 2754.81, "total_tokens": 1209600} |
| {"current_steps": 4255, "total_steps": 5360, "loss": 6.229, "lr": 6.209373232611682e-06, "epoch": 7.938432835820896, "percentage": 79.38, "elapsed_time": "0:07:19", "remaining_time": "0:01:54", "throughput": 2755.18, "total_tokens": 1210976} |
| {"current_steps": 4260, "total_steps": 5360, "loss": 6.2099, "lr": 6.155778786512109e-06, "epoch": 7.947761194029851, "percentage": 79.48, "elapsed_time": "0:07:19", "remaining_time": "0:01:53", "throughput": 2755.69, "total_tokens": 1212416} |
| {"current_steps": 4265, "total_steps": 5360, "loss": 5.8344, "lr": 6.102384143854698e-06, "epoch": 7.957089552238806, "percentage": 79.57, "elapsed_time": "0:07:20", "remaining_time": "0:01:53", "throughput": 2756.26, "total_tokens": 1213920} |
| {"current_steps": 4270, "total_steps": 5360, "loss": 5.5065, "lr": 6.049189870777652e-06, "epoch": 7.9664179104477615, "percentage": 79.66, "elapsed_time": "0:07:20", "remaining_time": "0:01:52", "throughput": 2756.76, "total_tokens": 1215360} |
| {"current_steps": 4275, "total_steps": 5360, "loss": 6.3202, "lr": 5.996196531294657e-06, "epoch": 7.975746268656716, "percentage": 79.76, "elapsed_time": "0:07:21", "remaining_time": "0:01:52", "throughput": 2757.13, "total_tokens": 1216736} |
| {"current_steps": 4280, "total_steps": 5360, "loss": 6.4767, "lr": 5.943404687288939e-06, "epoch": 7.985074626865671, "percentage": 79.85, "elapsed_time": "0:07:21", "remaining_time": "0:01:51", "throughput": 2757.62, "total_tokens": 1218240} |
| {"current_steps": 4285, "total_steps": 5360, "loss": 5.8816, "lr": 5.890814898507277e-06, "epoch": 7.994402985074627, "percentage": 79.94, "elapsed_time": "0:07:22", "remaining_time": "0:01:50", "throughput": 2757.82, "total_tokens": 1219488} |
| {"current_steps": 4288, "total_steps": 5360, "eval_loss": 6.157891273498535, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:07:25", "remaining_time": "0:01:51", "throughput": 2741.32, "total_tokens": 1220200} |
| {"current_steps": 4290, "total_steps": 5360, "loss": 5.6459, "lr": 5.838427722554057e-06, "epoch": 8.003731343283581, "percentage": 80.04, "elapsed_time": "0:07:26", "remaining_time": "0:01:51", "throughput": 2734.03, "total_tokens": 1220808} |
| {"current_steps": 4295, "total_steps": 5360, "loss": 5.8122, "lr": 5.786243714885442e-06, "epoch": 8.013059701492537, "percentage": 80.13, "elapsed_time": "0:07:26", "remaining_time": "0:01:50", "throughput": 2734.54, "total_tokens": 1222280} |
| {"current_steps": 4300, "total_steps": 5360, "loss": 6.4911, "lr": 5.734263428803352e-06, "epoch": 8.022388059701493, "percentage": 80.22, "elapsed_time": "0:07:27", "remaining_time": "0:01:50", "throughput": 2734.95, "total_tokens": 1223688} |
| {"current_steps": 4305, "total_steps": 5360, "loss": 6.5237, "lr": 5.6824874154497194e-06, "epoch": 8.031716417910447, "percentage": 80.32, "elapsed_time": "0:07:27", "remaining_time": "0:01:49", "throughput": 2735.82, "total_tokens": 1225352} |
| {"current_steps": 4310, "total_steps": 5360, "loss": 5.625, "lr": 5.63091622380055e-06, "epoch": 8.041044776119403, "percentage": 80.41, "elapsed_time": "0:07:28", "remaining_time": "0:01:49", "throughput": 2736.32, "total_tokens": 1226824} |
| {"current_steps": 4315, "total_steps": 5360, "loss": 6.3955, "lr": 5.5795504006601855e-06, "epoch": 8.050373134328359, "percentage": 80.5, "elapsed_time": "0:07:28", "remaining_time": "0:01:48", "throughput": 2736.79, "total_tokens": 1228232} |
| {"current_steps": 4320, "total_steps": 5360, "loss": 5.3909, "lr": 5.528390490655428e-06, "epoch": 8.059701492537313, "percentage": 80.6, "elapsed_time": "0:07:29", "remaining_time": "0:01:48", "throughput": 2737.24, "total_tokens": 1229672} |
| {"current_steps": 4325, "total_steps": 5360, "loss": 6.1, "lr": 5.477437036229833e-06, "epoch": 8.069029850746269, "percentage": 80.69, "elapsed_time": "0:07:29", "remaining_time": "0:01:47", "throughput": 2737.4, "total_tokens": 1230920} |
| {"current_steps": 4330, "total_steps": 5360, "loss": 5.7076, "lr": 5.426690577637913e-06, "epoch": 8.078358208955224, "percentage": 80.78, "elapsed_time": "0:07:30", "remaining_time": "0:01:47", "throughput": 2737.64, "total_tokens": 1232232} |
| {"current_steps": 4335, "total_steps": 5360, "loss": 6.0606, "lr": 5.37615165293942e-06, "epoch": 8.087686567164178, "percentage": 80.88, "elapsed_time": "0:07:30", "remaining_time": "0:01:46", "throughput": 2738.01, "total_tokens": 1233640} |
| {"current_steps": 4340, "total_steps": 5360, "loss": 6.2203, "lr": 5.325820797993661e-06, "epoch": 8.097014925373134, "percentage": 80.97, "elapsed_time": "0:07:31", "remaining_time": "0:01:45", "throughput": 2738.4, "total_tokens": 1235048} |
| {"current_steps": 4345, "total_steps": 5360, "loss": 6.419, "lr": 5.275698546453775e-06, "epoch": 8.10634328358209, "percentage": 81.06, "elapsed_time": "0:07:31", "remaining_time": "0:01:45", "throughput": 2738.96, "total_tokens": 1236552} |
| {"current_steps": 4350, "total_steps": 5360, "loss": 5.5199, "lr": 5.225785429761124e-06, "epoch": 8.115671641791044, "percentage": 81.16, "elapsed_time": "0:07:31", "remaining_time": "0:01:44", "throughput": 2739.24, "total_tokens": 1237896} |
| {"current_steps": 4355, "total_steps": 5360, "loss": 6.2647, "lr": 5.176081977139621e-06, "epoch": 8.125, "percentage": 81.25, "elapsed_time": "0:07:32", "remaining_time": "0:01:44", "throughput": 2739.36, "total_tokens": 1239112} |
| {"current_steps": 4360, "total_steps": 5360, "loss": 5.9782, "lr": 5.12658871559013e-06, "epoch": 8.134328358208956, "percentage": 81.34, "elapsed_time": "0:07:32", "remaining_time": "0:01:43", "throughput": 2740.01, "total_tokens": 1240744} |
| {"current_steps": 4365, "total_steps": 5360, "loss": 6.3084, "lr": 5.077306169884888e-06, "epoch": 8.14365671641791, "percentage": 81.44, "elapsed_time": "0:07:33", "remaining_time": "0:01:43", "throughput": 2740.44, "total_tokens": 1242152} |
| {"current_steps": 4370, "total_steps": 5360, "loss": 6.4504, "lr": 5.0282348625619175e-06, "epoch": 8.152985074626866, "percentage": 81.53, "elapsed_time": "0:07:33", "remaining_time": "0:01:42", "throughput": 2740.74, "total_tokens": 1243496} |
| {"current_steps": 4375, "total_steps": 5360, "loss": 6.322, "lr": 4.979375313919526e-06, "epoch": 8.162313432835822, "percentage": 81.62, "elapsed_time": "0:07:34", "remaining_time": "0:01:42", "throughput": 2741.31, "total_tokens": 1245064} |
| {"current_steps": 4380, "total_steps": 5360, "loss": 5.6682, "lr": 4.930728042010724e-06, "epoch": 8.171641791044776, "percentage": 81.72, "elapsed_time": "0:07:34", "remaining_time": "0:01:41", "throughput": 2741.56, "total_tokens": 1246408} |
| {"current_steps": 4385, "total_steps": 5360, "loss": 5.9767, "lr": 4.882293562637827e-06, "epoch": 8.180970149253731, "percentage": 81.81, "elapsed_time": "0:07:35", "remaining_time": "0:01:41", "throughput": 2741.87, "total_tokens": 1247784} |
| {"current_steps": 4390, "total_steps": 5360, "loss": 5.9875, "lr": 4.834072389346883e-06, "epoch": 8.190298507462687, "percentage": 81.9, "elapsed_time": "0:07:35", "remaining_time": "0:01:40", "throughput": 2742.24, "total_tokens": 1249192} |
| {"current_steps": 4395, "total_steps": 5360, "loss": 6.2637, "lr": 4.78606503342231e-06, "epoch": 8.199626865671641, "percentage": 82.0, "elapsed_time": "0:07:35", "remaining_time": "0:01:40", "throughput": 2742.69, "total_tokens": 1250664} |
| {"current_steps": 4400, "total_steps": 5360, "loss": 5.9832, "lr": 4.738272003881417e-06, "epoch": 8.208955223880597, "percentage": 82.09, "elapsed_time": "0:07:36", "remaining_time": "0:01:39", "throughput": 2743.12, "total_tokens": 1252072} |
| {"current_steps": 4405, "total_steps": 5360, "loss": 5.776, "lr": 4.690693807469035e-06, "epoch": 8.218283582089553, "percentage": 82.18, "elapsed_time": "0:07:36", "remaining_time": "0:01:39", "throughput": 2743.44, "total_tokens": 1253416} |
| {"current_steps": 4410, "total_steps": 5360, "loss": 5.8053, "lr": 4.643330948652155e-06, "epoch": 8.227611940298507, "percentage": 82.28, "elapsed_time": "0:07:37", "remaining_time": "0:01:38", "throughput": 2743.68, "total_tokens": 1254728} |
| {"current_steps": 4415, "total_steps": 5360, "loss": 6.3171, "lr": 4.596183929614559e-06, "epoch": 8.236940298507463, "percentage": 82.37, "elapsed_time": "0:07:37", "remaining_time": "0:01:37", "throughput": 2743.85, "total_tokens": 1255976} |
| {"current_steps": 4420, "total_steps": 5360, "loss": 6.0461, "lr": 4.549253250251498e-06, "epoch": 8.246268656716419, "percentage": 82.46, "elapsed_time": "0:07:38", "remaining_time": "0:01:37", "throughput": 2744.07, "total_tokens": 1257288} |
| {"current_steps": 4425, "total_steps": 5360, "loss": 6.5616, "lr": 4.502539408164386e-06, "epoch": 8.255597014925373, "percentage": 82.56, "elapsed_time": "0:07:38", "remaining_time": "0:01:36", "throughput": 2744.43, "total_tokens": 1258664} |
| {"current_steps": 4430, "total_steps": 5360, "loss": 5.9998, "lr": 4.4560428986555516e-06, "epoch": 8.264925373134329, "percentage": 82.65, "elapsed_time": "0:07:39", "remaining_time": "0:01:36", "throughput": 2744.87, "total_tokens": 1260104} |
| {"current_steps": 4435, "total_steps": 5360, "loss": 6.1062, "lr": 4.409764214722945e-06, "epoch": 8.274253731343283, "percentage": 82.74, "elapsed_time": "0:07:39", "remaining_time": "0:01:35", "throughput": 2745.15, "total_tokens": 1261448} |
| {"current_steps": 4440, "total_steps": 5360, "loss": 5.5596, "lr": 4.363703847054948e-06, "epoch": 8.283582089552239, "percentage": 82.84, "elapsed_time": "0:07:39", "remaining_time": "0:01:35", "throughput": 2745.87, "total_tokens": 1263048} |
| {"current_steps": 4445, "total_steps": 5360, "loss": 6.4068, "lr": 4.317862284025165e-06, "epoch": 8.292910447761194, "percentage": 82.93, "elapsed_time": "0:07:40", "remaining_time": "0:01:34", "throughput": 2746.12, "total_tokens": 1264360} |
| {"current_steps": 4450, "total_steps": 5360, "loss": 6.4016, "lr": 4.272240011687206e-06, "epoch": 8.302238805970148, "percentage": 83.02, "elapsed_time": "0:07:40", "remaining_time": "0:01:34", "throughput": 2746.29, "total_tokens": 1265640} |
| {"current_steps": 4455, "total_steps": 5360, "loss": 6.5845, "lr": 4.226837513769596e-06, "epoch": 8.311567164179104, "percentage": 83.12, "elapsed_time": "0:07:41", "remaining_time": "0:01:33", "throughput": 2746.64, "total_tokens": 1267016} |
| {"current_steps": 4460, "total_steps": 5360, "loss": 5.9948, "lr": 4.181655271670587e-06, "epoch": 8.32089552238806, "percentage": 83.21, "elapsed_time": "0:07:41", "remaining_time": "0:01:33", "throughput": 2747.45, "total_tokens": 1268744} |
| {"current_steps": 4465, "total_steps": 5360, "loss": 6.4208, "lr": 4.1366937644531e-06, "epoch": 8.330223880597014, "percentage": 83.3, "elapsed_time": "0:07:42", "remaining_time": "0:01:32", "throughput": 2747.8, "total_tokens": 1270120} |
| {"current_steps": 4470, "total_steps": 5360, "loss": 6.3729, "lr": 4.091953468839607e-06, "epoch": 8.33955223880597, "percentage": 83.4, "elapsed_time": "0:07:42", "remaining_time": "0:01:32", "throughput": 2748.31, "total_tokens": 1271656} |
| {"current_steps": 4475, "total_steps": 5360, "loss": 6.1454, "lr": 4.047434859207114e-06, "epoch": 8.348880597014926, "percentage": 83.49, "elapsed_time": "0:07:43", "remaining_time": "0:01:31", "throughput": 2748.83, "total_tokens": 1273128} |
| {"current_steps": 4480, "total_steps": 5360, "loss": 5.9514, "lr": 4.003138407582102e-06, "epoch": 8.35820895522388, "percentage": 83.58, "elapsed_time": "0:07:43", "remaining_time": "0:01:31", "throughput": 2749.4, "total_tokens": 1274632} |
| {"current_steps": 4485, "total_steps": 5360, "loss": 6.3528, "lr": 3.959064583635527e-06, "epoch": 8.367537313432836, "percentage": 83.68, "elapsed_time": "0:07:44", "remaining_time": "0:01:30", "throughput": 2749.51, "total_tokens": 1275848} |
| {"current_steps": 4490, "total_steps": 5360, "loss": 6.2285, "lr": 3.9152138546778625e-06, "epoch": 8.376865671641792, "percentage": 83.77, "elapsed_time": "0:07:44", "remaining_time": "0:01:29", "throughput": 2749.87, "total_tokens": 1277224} |
| {"current_steps": 4495, "total_steps": 5360, "loss": 5.8961, "lr": 3.871586685654102e-06, "epoch": 8.386194029850746, "percentage": 83.86, "elapsed_time": "0:07:44", "remaining_time": "0:01:29", "throughput": 2750.02, "total_tokens": 1278504} |
| {"current_steps": 4500, "total_steps": 5360, "loss": 6.0349, "lr": 3.82818353913888e-06, "epoch": 8.395522388059701, "percentage": 83.96, "elapsed_time": "0:07:45", "remaining_time": "0:01:28", "throughput": 2750.2, "total_tokens": 1279784} |
| {"current_steps": 4505, "total_steps": 5360, "loss": 5.5966, "lr": 3.785004875331527e-06, "epoch": 8.404850746268657, "percentage": 84.05, "elapsed_time": "0:07:45", "remaining_time": "0:01:28", "throughput": 2750.63, "total_tokens": 1281256} |
| {"current_steps": 4510, "total_steps": 5360, "loss": 6.1516, "lr": 3.742051152051221e-06, "epoch": 8.414179104477611, "percentage": 84.14, "elapsed_time": "0:07:46", "remaining_time": "0:01:27", "throughput": 2751.21, "total_tokens": 1282792} |
| {"current_steps": 4515, "total_steps": 5360, "loss": 6.2826, "lr": 3.6993228247320877e-06, "epoch": 8.423507462686567, "percentage": 84.24, "elapsed_time": "0:07:46", "remaining_time": "0:01:27", "throughput": 2751.63, "total_tokens": 1284232} |
| {"current_steps": 4520, "total_steps": 5360, "loss": 5.8751, "lr": 3.6568203464184383e-06, "epoch": 8.432835820895523, "percentage": 84.33, "elapsed_time": "0:07:47", "remaining_time": "0:01:26", "throughput": 2751.66, "total_tokens": 1285448} |
| {"current_steps": 4525, "total_steps": 5360, "loss": 6.5124, "lr": 3.614544167759901e-06, "epoch": 8.442164179104477, "percentage": 84.42, "elapsed_time": "0:07:47", "remaining_time": "0:01:26", "throughput": 2751.96, "total_tokens": 1286824} |
| {"current_steps": 4530, "total_steps": 5360, "loss": 5.7768, "lr": 3.5724947370066708e-06, "epoch": 8.451492537313433, "percentage": 84.51, "elapsed_time": "0:07:48", "remaining_time": "0:01:25", "throughput": 2752.18, "total_tokens": 1288136} |
| {"current_steps": 4535, "total_steps": 5360, "loss": 5.7891, "lr": 3.5306725000047918e-06, "epoch": 8.460820895522389, "percentage": 84.61, "elapsed_time": "0:07:48", "remaining_time": "0:01:25", "throughput": 2752.55, "total_tokens": 1289512} |
| {"current_steps": 4540, "total_steps": 5360, "loss": 5.6005, "lr": 3.4890779001913452e-06, "epoch": 8.470149253731343, "percentage": 84.7, "elapsed_time": "0:07:48", "remaining_time": "0:01:24", "throughput": 2753.33, "total_tokens": 1291144} |
| {"current_steps": 4545, "total_steps": 5360, "loss": 6.3989, "lr": 3.4477113785898407e-06, "epoch": 8.479477611940299, "percentage": 84.79, "elapsed_time": "0:07:49", "remaining_time": "0:01:24", "throughput": 2753.93, "total_tokens": 1292680} |
| {"current_steps": 4550, "total_steps": 5360, "loss": 5.6335, "lr": 3.4065733738054606e-06, "epoch": 8.488805970149254, "percentage": 84.89, "elapsed_time": "0:07:49", "remaining_time": "0:01:23", "throughput": 2754.23, "total_tokens": 1294056} |
| {"current_steps": 4555, "total_steps": 5360, "loss": 5.8843, "lr": 3.3656643220204785e-06, "epoch": 8.498134328358208, "percentage": 84.98, "elapsed_time": "0:07:50", "remaining_time": "0:01:23", "throughput": 2754.47, "total_tokens": 1295400} |
| {"current_steps": 4556, "total_steps": 5360, "eval_loss": 6.15064001083374, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:07:52", "remaining_time": "0:01:23", "throughput": 2739.64, "total_tokens": 1295720} |
| {"current_steps": 4560, "total_steps": 5360, "loss": 6.3928, "lr": 3.3249846569895744e-06, "epoch": 8.507462686567164, "percentage": 85.07, "elapsed_time": "0:07:54", "remaining_time": "0:01:23", "throughput": 2734.43, "total_tokens": 1296872} |
| {"current_steps": 4565, "total_steps": 5360, "loss": 6.5311, "lr": 3.284534810035278e-06, "epoch": 8.51679104477612, "percentage": 85.17, "elapsed_time": "0:07:54", "remaining_time": "0:01:22", "throughput": 2734.91, "total_tokens": 1298408} |
| {"current_steps": 4570, "total_steps": 5360, "loss": 6.1849, "lr": 3.2443152100433832e-06, "epoch": 8.526119402985074, "percentage": 85.26, "elapsed_time": "0:07:55", "remaining_time": "0:01:22", "throughput": 2735.36, "total_tokens": 1299848} |
| {"current_steps": 4575, "total_steps": 5360, "loss": 6.3188, "lr": 3.204326283458381e-06, "epoch": 8.53544776119403, "percentage": 85.35, "elapsed_time": "0:07:55", "remaining_time": "0:01:21", "throughput": 2735.69, "total_tokens": 1301224} |
| {"current_steps": 4580, "total_steps": 5360, "loss": 6.3155, "lr": 3.1645684542789765e-06, "epoch": 8.544776119402986, "percentage": 85.45, "elapsed_time": "0:07:56", "remaining_time": "0:01:21", "throughput": 2736.33, "total_tokens": 1302856} |
| {"current_steps": 4585, "total_steps": 5360, "loss": 6.0966, "lr": 3.12504214405355e-06, "epoch": 8.55410447761194, "percentage": 85.54, "elapsed_time": "0:07:56", "remaining_time": "0:01:20", "throughput": 2736.56, "total_tokens": 1304168} |
| {"current_steps": 4590, "total_steps": 5360, "loss": 6.1417, "lr": 3.0857477718757187e-06, "epoch": 8.563432835820896, "percentage": 85.63, "elapsed_time": "0:07:57", "remaining_time": "0:01:20", "throughput": 2737.21, "total_tokens": 1305704} |
| {"current_steps": 4595, "total_steps": 5360, "loss": 6.2247, "lr": 3.0466857543798966e-06, "epoch": 8.572761194029852, "percentage": 85.73, "elapsed_time": "0:07:57", "remaining_time": "0:01:19", "throughput": 2737.57, "total_tokens": 1307080} |
| {"current_steps": 4600, "total_steps": 5360, "loss": 5.7227, "lr": 3.007856505736836e-06, "epoch": 8.582089552238806, "percentage": 85.82, "elapsed_time": "0:07:57", "remaining_time": "0:01:18", "throughput": 2737.66, "total_tokens": 1308296} |
| {"current_steps": 4605, "total_steps": 5360, "loss": 5.766, "lr": 2.969260437649293e-06, "epoch": 8.591417910447761, "percentage": 85.91, "elapsed_time": "0:07:58", "remaining_time": "0:01:18", "throughput": 2738.21, "total_tokens": 1309832} |
| {"current_steps": 4610, "total_steps": 5360, "loss": 6.0528, "lr": 2.9308979593476004e-06, "epoch": 8.600746268656717, "percentage": 86.01, "elapsed_time": "0:07:58", "remaining_time": "0:01:17", "throughput": 2738.84, "total_tokens": 1311368} |
| {"current_steps": 4615, "total_steps": 5360, "loss": 5.7876, "lr": 2.892769477585397e-06, "epoch": 8.610074626865671, "percentage": 86.1, "elapsed_time": "0:07:59", "remaining_time": "0:01:17", "throughput": 2739.05, "total_tokens": 1312680} |
| {"current_steps": 4620, "total_steps": 5360, "loss": 6.2917, "lr": 2.8548753966352426e-06, "epoch": 8.619402985074627, "percentage": 86.19, "elapsed_time": "0:07:59", "remaining_time": "0:01:16", "throughput": 2739.52, "total_tokens": 1314152} |
| {"current_steps": 4625, "total_steps": 5360, "loss": 5.7763, "lr": 2.8172161182844075e-06, "epoch": 8.628731343283581, "percentage": 86.29, "elapsed_time": "0:08:00", "remaining_time": "0:01:16", "throughput": 2739.78, "total_tokens": 1315496} |
| {"current_steps": 4630, "total_steps": 5360, "loss": 5.471, "lr": 2.779792041830537e-06, "epoch": 8.638059701492537, "percentage": 86.38, "elapsed_time": "0:08:00", "remaining_time": "0:01:15", "throughput": 2740.45, "total_tokens": 1317192} |
| {"current_steps": 4635, "total_steps": 5360, "loss": 5.8353, "lr": 2.742603564077478e-06, "epoch": 8.647388059701493, "percentage": 86.47, "elapsed_time": "0:08:01", "remaining_time": "0:01:15", "throughput": 2740.78, "total_tokens": 1318632} |
| {"current_steps": 4640, "total_steps": 5360, "loss": 6.0485, "lr": 2.7056510793310314e-06, "epoch": 8.656716417910447, "percentage": 86.57, "elapsed_time": "0:08:01", "remaining_time": "0:01:14", "throughput": 2741.23, "total_tokens": 1320232} |
| {"current_steps": 4645, "total_steps": 5360, "loss": 5.7388, "lr": 2.6689349793947994e-06, "epoch": 8.666044776119403, "percentage": 86.66, "elapsed_time": "0:08:02", "remaining_time": "0:01:14", "throughput": 2741.79, "total_tokens": 1321768} |
| {"current_steps": 4650, "total_steps": 5360, "loss": 5.8221, "lr": 2.6324556535660045e-06, "epoch": 8.675373134328359, "percentage": 86.75, "elapsed_time": "0:08:02", "remaining_time": "0:01:13", "throughput": 2742.22, "total_tokens": 1323272} |
| {"current_steps": 4655, "total_steps": 5360, "loss": 5.7343, "lr": 2.5962134886313936e-06, "epoch": 8.684701492537313, "percentage": 86.85, "elapsed_time": "0:08:03", "remaining_time": "0:01:13", "throughput": 2742.58, "total_tokens": 1324680} |
| {"current_steps": 4660, "total_steps": 5360, "loss": 6.0207, "lr": 2.5602088688631148e-06, "epoch": 8.694029850746269, "percentage": 86.94, "elapsed_time": "0:08:03", "remaining_time": "0:01:12", "throughput": 2742.81, "total_tokens": 1325992} |
| {"current_steps": 4665, "total_steps": 5360, "loss": 6.0659, "lr": 2.5244421760146355e-06, "epoch": 8.703358208955224, "percentage": 87.03, "elapsed_time": "0:08:03", "remaining_time": "0:01:12", "throughput": 2743.18, "total_tokens": 1327400} |
| {"current_steps": 4670, "total_steps": 5360, "loss": 6.1124, "lr": 2.488913789316724e-06, "epoch": 8.712686567164178, "percentage": 87.13, "elapsed_time": "0:08:04", "remaining_time": "0:01:11", "throughput": 2743.44, "total_tokens": 1328744} |
| {"current_steps": 4675, "total_steps": 5360, "loss": 6.0934, "lr": 2.4536240854733967e-06, "epoch": 8.722014925373134, "percentage": 87.22, "elapsed_time": "0:08:04", "remaining_time": "0:01:11", "throughput": 2744.02, "total_tokens": 1330280} |
| {"current_steps": 4680, "total_steps": 5360, "loss": 5.9329, "lr": 2.4185734386579506e-06, "epoch": 8.73134328358209, "percentage": 87.31, "elapsed_time": "0:08:05", "remaining_time": "0:01:10", "throughput": 2744.41, "total_tokens": 1331784} |
| {"current_steps": 4685, "total_steps": 5360, "loss": 5.8547, "lr": 2.383762220508984e-06, "epoch": 8.740671641791044, "percentage": 87.41, "elapsed_time": "0:08:05", "remaining_time": "0:01:09", "throughput": 2744.67, "total_tokens": 1333128} |
| {"current_steps": 4690, "total_steps": 5360, "loss": 6.4847, "lr": 2.349190800126444e-06, "epoch": 8.75, "percentage": 87.5, "elapsed_time": "0:08:06", "remaining_time": "0:01:09", "throughput": 2745.14, "total_tokens": 1334696} |
| {"current_steps": 4695, "total_steps": 5360, "loss": 6.6503, "lr": 2.3148595440677405e-06, "epoch": 8.759328358208956, "percentage": 87.59, "elapsed_time": "0:08:06", "remaining_time": "0:01:08", "throughput": 2745.65, "total_tokens": 1336264} |
| {"current_steps": 4700, "total_steps": 5360, "loss": 6.4588, "lr": 2.280768816343834e-06, "epoch": 8.76865671641791, "percentage": 87.69, "elapsed_time": "0:08:07", "remaining_time": "0:01:08", "throughput": 2745.9, "total_tokens": 1337608} |
| {"current_steps": 4705, "total_steps": 5360, "loss": 6.0364, "lr": 2.246918978415394e-06, "epoch": 8.777985074626866, "percentage": 87.78, "elapsed_time": "0:08:07", "remaining_time": "0:01:07", "throughput": 2746.41, "total_tokens": 1339144} |
| {"current_steps": 4710, "total_steps": 5360, "loss": 5.9358, "lr": 2.2133103891889438e-06, "epoch": 8.787313432835822, "percentage": 87.87, "elapsed_time": "0:08:08", "remaining_time": "0:01:07", "throughput": 2746.65, "total_tokens": 1340488} |
| {"current_steps": 4715, "total_steps": 5360, "loss": 6.1433, "lr": 2.1799434050131018e-06, "epoch": 8.796641791044776, "percentage": 87.97, "elapsed_time": "0:08:08", "remaining_time": "0:01:06", "throughput": 2747.08, "total_tokens": 1341960} |
| {"current_steps": 4720, "total_steps": 5360, "loss": 6.5289, "lr": 2.1468183796747365e-06, "epoch": 8.805970149253731, "percentage": 88.06, "elapsed_time": "0:08:08", "remaining_time": "0:01:06", "throughput": 2747.83, "total_tokens": 1343624} |
| {"current_steps": 4725, "total_steps": 5360, "loss": 6.0176, "lr": 2.1139356643952666e-06, "epoch": 8.815298507462687, "percentage": 88.15, "elapsed_time": "0:08:09", "remaining_time": "0:01:05", "throughput": 2748.05, "total_tokens": 1344936} |
| {"current_steps": 4730, "total_steps": 5360, "loss": 6.1572, "lr": 2.0812956078269275e-06, "epoch": 8.824626865671641, "percentage": 88.25, "elapsed_time": "0:08:09", "remaining_time": "0:01:05", "throughput": 2748.54, "total_tokens": 1346408} |
| {"current_steps": 4735, "total_steps": 5360, "loss": 5.8598, "lr": 2.0488985560490477e-06, "epoch": 8.833955223880597, "percentage": 88.34, "elapsed_time": "0:08:10", "remaining_time": "0:01:04", "throughput": 2748.82, "total_tokens": 1347784} |
| {"current_steps": 4740, "total_steps": 5360, "loss": 5.6125, "lr": 2.01674485256442e-06, "epoch": 8.843283582089553, "percentage": 88.43, "elapsed_time": "0:08:10", "remaining_time": "0:01:04", "throughput": 2749.07, "total_tokens": 1349128} |
| {"current_steps": 4745, "total_steps": 5360, "loss": 5.9085, "lr": 1.9848348382956293e-06, "epoch": 8.852611940298507, "percentage": 88.53, "elapsed_time": "0:08:11", "remaining_time": "0:01:03", "throughput": 2749.09, "total_tokens": 1350312} |
| {"current_steps": 4750, "total_steps": 5360, "loss": 5.7896, "lr": 1.953168851581452e-06, "epoch": 8.861940298507463, "percentage": 88.62, "elapsed_time": "0:08:11", "remaining_time": "0:01:03", "throughput": 2749.52, "total_tokens": 1351784} |
| {"current_steps": 4755, "total_steps": 5360, "loss": 5.599, "lr": 1.921747228173254e-06, "epoch": 8.871268656716419, "percentage": 88.71, "elapsed_time": "0:08:12", "remaining_time": "0:01:02", "throughput": 2750.12, "total_tokens": 1353416} |
| {"current_steps": 4760, "total_steps": 5360, "loss": 5.8288, "lr": 1.8905703012314563e-06, "epoch": 8.880597014925373, "percentage": 88.81, "elapsed_time": "0:08:12", "remaining_time": "0:01:02", "throughput": 2750.36, "total_tokens": 1354760} |
| {"current_steps": 4765, "total_steps": 5360, "loss": 5.6458, "lr": 1.8596384013219725e-06, "epoch": 8.889925373134329, "percentage": 88.9, "elapsed_time": "0:08:13", "remaining_time": "0:01:01", "throughput": 2750.44, "total_tokens": 1355976} |
| {"current_steps": 4770, "total_steps": 5360, "loss": 6.052, "lr": 1.8289518564127223e-06, "epoch": 8.899253731343283, "percentage": 88.99, "elapsed_time": "0:08:13", "remaining_time": "0:01:01", "throughput": 2750.83, "total_tokens": 1357416} |
| {"current_steps": 4775, "total_steps": 5360, "loss": 6.4766, "lr": 1.7985109918701643e-06, "epoch": 8.908582089552239, "percentage": 89.09, "elapsed_time": "0:08:13", "remaining_time": "0:01:00", "throughput": 2751.5, "total_tokens": 1359080} |
| {"current_steps": 4780, "total_steps": 5360, "loss": 5.9509, "lr": 1.7683161304558076e-06, "epoch": 8.917910447761194, "percentage": 89.18, "elapsed_time": "0:08:14", "remaining_time": "0:00:59", "throughput": 2751.94, "total_tokens": 1360552} |
| {"current_steps": 4785, "total_steps": 5360, "loss": 6.3764, "lr": 1.738367592322837e-06, "epoch": 8.927238805970148, "percentage": 89.27, "elapsed_time": "0:08:14", "remaining_time": "0:00:59", "throughput": 2752.28, "total_tokens": 1361960} |
| {"current_steps": 4790, "total_steps": 5360, "loss": 6.3492, "lr": 1.708665695012676e-06, "epoch": 8.936567164179104, "percentage": 89.37, "elapsed_time": "0:08:15", "remaining_time": "0:00:58", "throughput": 2752.63, "total_tokens": 1363368} |
| {"current_steps": 4795, "total_steps": 5360, "loss": 6.0071, "lr": 1.6792107534516571e-06, "epoch": 8.94589552238806, "percentage": 89.46, "elapsed_time": "0:08:15", "remaining_time": "0:00:58", "throughput": 2753.05, "total_tokens": 1364840} |
| {"current_steps": 4800, "total_steps": 5360, "loss": 6.1538, "lr": 1.6500030799476513e-06, "epoch": 8.955223880597014, "percentage": 89.55, "elapsed_time": "0:08:16", "remaining_time": "0:00:57", "throughput": 2753.26, "total_tokens": 1366152} |
| {"current_steps": 4805, "total_steps": 5360, "loss": 6.033, "lr": 1.621042984186777e-06, "epoch": 8.96455223880597, "percentage": 89.65, "elapsed_time": "0:08:16", "remaining_time": "0:00:57", "throughput": 2753.55, "total_tokens": 1367528} |
| {"current_steps": 4810, "total_steps": 5360, "loss": 6.1146, "lr": 1.5923307732301136e-06, "epoch": 8.973880597014926, "percentage": 89.74, "elapsed_time": "0:08:17", "remaining_time": "0:00:56", "throughput": 2753.94, "total_tokens": 1368968} |
| {"current_steps": 4815, "total_steps": 5360, "loss": 6.0489, "lr": 1.5638667515104288e-06, "epoch": 8.98320895522388, "percentage": 89.83, "elapsed_time": "0:08:17", "remaining_time": "0:00:56", "throughput": 2754.09, "total_tokens": 1370248} |
| {"current_steps": 4820, "total_steps": 5360, "loss": 6.5707, "lr": 1.5356512208289846e-06, "epoch": 8.992537313432836, "percentage": 89.93, "elapsed_time": "0:08:17", "remaining_time": "0:00:55", "throughput": 2754.26, "total_tokens": 1371496} |
| {"current_steps": 4824, "total_steps": 5360, "eval_loss": 6.147698879241943, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:08:20", "remaining_time": "0:00:55", "throughput": 2739.82, "total_tokens": 1372560} |
| {"current_steps": 4825, "total_steps": 5360, "loss": 6.0195, "lr": 1.5076844803522922e-06, "epoch": 9.001865671641792, "percentage": 90.02, "elapsed_time": "0:08:22", "remaining_time": "0:00:55", "throughput": 2733.12, "total_tokens": 1372784} |
| {"current_steps": 4830, "total_steps": 5360, "loss": 6.2133, "lr": 1.4799668266089834e-06, "epoch": 9.011194029850746, "percentage": 90.11, "elapsed_time": "0:08:22", "remaining_time": "0:00:55", "throughput": 2733.43, "total_tokens": 1374160} |
| {"current_steps": 4835, "total_steps": 5360, "loss": 6.3108, "lr": 1.452498553486642e-06, "epoch": 9.020522388059701, "percentage": 90.21, "elapsed_time": "0:08:23", "remaining_time": "0:00:54", "throughput": 2733.65, "total_tokens": 1375472} |
| {"current_steps": 4840, "total_steps": 5360, "loss": 6.0475, "lr": 1.4252799522286892e-06, "epoch": 9.029850746268657, "percentage": 90.3, "elapsed_time": "0:08:23", "remaining_time": "0:00:54", "throughput": 2734.1, "total_tokens": 1376976} |
| {"current_steps": 4845, "total_steps": 5360, "loss": 6.0916, "lr": 1.398311311431308e-06, "epoch": 9.039179104477611, "percentage": 90.39, "elapsed_time": "0:08:24", "remaining_time": "0:00:53", "throughput": 2734.23, "total_tokens": 1378256} |
| {"current_steps": 4850, "total_steps": 5360, "loss": 5.8887, "lr": 1.3715929170403623e-06, "epoch": 9.048507462686567, "percentage": 90.49, "elapsed_time": "0:08:24", "remaining_time": "0:00:53", "throughput": 2734.82, "total_tokens": 1379856} |
| {"current_steps": 4855, "total_steps": 5360, "loss": 5.3402, "lr": 1.3451250523483976e-06, "epoch": 9.057835820895523, "percentage": 90.58, "elapsed_time": "0:08:25", "remaining_time": "0:00:52", "throughput": 2735.46, "total_tokens": 1381584} |
| {"current_steps": 4860, "total_steps": 5360, "loss": 6.4677, "lr": 1.3189079979915864e-06, "epoch": 9.067164179104477, "percentage": 90.67, "elapsed_time": "0:08:25", "remaining_time": "0:00:52", "throughput": 2735.68, "total_tokens": 1382896} |
| {"current_steps": 4865, "total_steps": 5360, "loss": 6.3469, "lr": 1.2929420319468255e-06, "epoch": 9.076492537313433, "percentage": 90.76, "elapsed_time": "0:08:25", "remaining_time": "0:00:51", "throughput": 2735.95, "total_tokens": 1384240} |
| {"current_steps": 4870, "total_steps": 5360, "loss": 6.7847, "lr": 1.2672274295287057e-06, "epoch": 9.085820895522389, "percentage": 90.86, "elapsed_time": "0:08:26", "remaining_time": "0:00:50", "throughput": 2736.54, "total_tokens": 1385808} |
| {"current_steps": 4875, "total_steps": 5360, "loss": 6.7933, "lr": 1.2417644633866632e-06, "epoch": 9.095149253731343, "percentage": 90.95, "elapsed_time": "0:08:26", "remaining_time": "0:00:50", "throughput": 2737.04, "total_tokens": 1387312} |
| {"current_steps": 4880, "total_steps": 5360, "loss": 5.9755, "lr": 1.2165534035020409e-06, "epoch": 9.104477611940299, "percentage": 91.04, "elapsed_time": "0:08:27", "remaining_time": "0:00:49", "throughput": 2737.31, "total_tokens": 1388688} |
| {"current_steps": 4885, "total_steps": 5360, "loss": 5.6617, "lr": 1.1915945171852572e-06, "epoch": 9.113805970149254, "percentage": 91.14, "elapsed_time": "0:08:27", "remaining_time": "0:00:49", "throughput": 2737.51, "total_tokens": 1390000} |
| {"current_steps": 4890, "total_steps": 5360, "loss": 6.112, "lr": 1.1668880690729467e-06, "epoch": 9.123134328358208, "percentage": 91.23, "elapsed_time": "0:08:28", "remaining_time": "0:00:48", "throughput": 2737.84, "total_tokens": 1391408} |
| {"current_steps": 4895, "total_steps": 5360, "loss": 5.8184, "lr": 1.142434321125177e-06, "epoch": 9.132462686567164, "percentage": 91.32, "elapsed_time": "0:08:28", "remaining_time": "0:00:48", "throughput": 2738.24, "total_tokens": 1392848} |
| {"current_steps": 4900, "total_steps": 5360, "loss": 6.4218, "lr": 1.1182335326226533e-06, "epoch": 9.14179104477612, "percentage": 91.42, "elapsed_time": "0:08:29", "remaining_time": "0:00:47", "throughput": 2738.66, "total_tokens": 1394320} |
| {"current_steps": 4905, "total_steps": 5360, "loss": 6.3468, "lr": 1.0942859601639794e-06, "epoch": 9.151119402985074, "percentage": 91.51, "elapsed_time": "0:08:29", "remaining_time": "0:00:47", "throughput": 2738.68, "total_tokens": 1395504} |
| {"current_steps": 4910, "total_steps": 5360, "loss": 6.2776, "lr": 1.0705918576629364e-06, "epoch": 9.16044776119403, "percentage": 91.6, "elapsed_time": "0:08:30", "remaining_time": "0:00:46", "throughput": 2738.98, "total_tokens": 1396880} |
| {"current_steps": 4915, "total_steps": 5360, "loss": 6.0301, "lr": 1.0471514763457814e-06, "epoch": 9.169776119402986, "percentage": 91.7, "elapsed_time": "0:08:30", "remaining_time": "0:00:46", "throughput": 2738.98, "total_tokens": 1398064} |
| {"current_steps": 4920, "total_steps": 5360, "loss": 5.9416, "lr": 1.023965064748597e-06, "epoch": 9.17910447761194, "percentage": 91.79, "elapsed_time": "0:08:30", "remaining_time": "0:00:45", "throughput": 2739.35, "total_tokens": 1399504} |
| {"current_steps": 4925, "total_steps": 5360, "loss": 5.931, "lr": 1.0010328687146464e-06, "epoch": 9.188432835820896, "percentage": 91.88, "elapsed_time": "0:08:31", "remaining_time": "0:00:45", "throughput": 2739.6, "total_tokens": 1400848} |
| {"current_steps": 4930, "total_steps": 5360, "loss": 5.2613, "lr": 9.783551313917699e-07, "epoch": 9.197761194029852, "percentage": 91.98, "elapsed_time": "0:08:31", "remaining_time": "0:00:44", "throughput": 2739.72, "total_tokens": 1402128} |
| {"current_steps": 4935, "total_steps": 5360, "loss": 5.9859, "lr": 9.559320932298111e-07, "epoch": 9.207089552238806, "percentage": 92.07, "elapsed_time": "0:08:32", "remaining_time": "0:00:44", "throughput": 2740.13, "total_tokens": 1403632} |
| {"current_steps": 4940, "total_steps": 5360, "loss": 5.9936, "lr": 9.337639919780539e-07, "epoch": 9.216417910447761, "percentage": 92.16, "elapsed_time": "0:08:32", "remaining_time": "0:00:43", "throughput": 2740.51, "total_tokens": 1405072} |
| {"current_steps": 4945, "total_steps": 5360, "loss": 6.1751, "lr": 9.118510626827198e-07, "epoch": 9.225746268656717, "percentage": 92.26, "elapsed_time": "0:08:33", "remaining_time": "0:00:43", "throughput": 2740.88, "total_tokens": 1406480} |
| {"current_steps": 4950, "total_steps": 5360, "loss": 5.7156, "lr": 8.901935376844611e-07, "epoch": 9.235074626865671, "percentage": 92.35, "elapsed_time": "0:08:33", "remaining_time": "0:00:42", "throughput": 2741.1, "total_tokens": 1407792} |
| {"current_steps": 4955, "total_steps": 5360, "loss": 5.8181, "lr": 8.687916466159157e-07, "epoch": 9.244402985074627, "percentage": 92.44, "elapsed_time": "0:08:34", "remaining_time": "0:00:42", "throughput": 2741.28, "total_tokens": 1409072} |
| {"current_steps": 4960, "total_steps": 5360, "loss": 5.9283, "lr": 8.476456163992397e-07, "epoch": 9.253731343283581, "percentage": 92.54, "elapsed_time": "0:08:34", "remaining_time": "0:00:41", "throughput": 2741.75, "total_tokens": 1410576} |
| {"current_steps": 4965, "total_steps": 5360, "loss": 5.9073, "lr": 8.267556712437341e-07, "epoch": 9.263059701492537, "percentage": 92.63, "elapsed_time": "0:08:34", "remaining_time": "0:00:40", "throughput": 2741.92, "total_tokens": 1411856} |
| {"current_steps": 4970, "total_steps": 5360, "loss": 5.8621, "lr": 8.061220326434582e-07, "epoch": 9.272388059701493, "percentage": 92.72, "elapsed_time": "0:08:35", "remaining_time": "0:00:40", "throughput": 2742.16, "total_tokens": 1413200} |
| {"current_steps": 4975, "total_steps": 5360, "loss": 5.8104, "lr": 7.857449193748645e-07, "epoch": 9.281716417910447, "percentage": 92.82, "elapsed_time": "0:08:35", "remaining_time": "0:00:39", "throughput": 2742.45, "total_tokens": 1414576} |
| {"current_steps": 4980, "total_steps": 5360, "loss": 5.529, "lr": 7.656245474945034e-07, "epoch": 9.291044776119403, "percentage": 92.91, "elapsed_time": "0:08:36", "remaining_time": "0:00:39", "throughput": 2742.8, "total_tokens": 1415952} |
| {"current_steps": 4985, "total_steps": 5360, "loss": 5.9731, "lr": 7.457611303367196e-07, "epoch": 9.300373134328359, "percentage": 93.0, "elapsed_time": "0:08:36", "remaining_time": "0:00:38", "throughput": 2742.86, "total_tokens": 1417136} |
| {"current_steps": 4990, "total_steps": 5360, "loss": 5.6118, "lr": 7.261548785113925e-07, "epoch": 9.309701492537313, "percentage": 93.1, "elapsed_time": "0:08:37", "remaining_time": "0:00:38", "throughput": 2743.49, "total_tokens": 1418736} |
| {"current_steps": 4995, "total_steps": 5360, "loss": 5.792, "lr": 7.068059999016969e-07, "epoch": 9.319029850746269, "percentage": 93.19, "elapsed_time": "0:08:37", "remaining_time": "0:00:37", "throughput": 2743.85, "total_tokens": 1420144} |
| {"current_steps": 5000, "total_steps": 5360, "loss": 6.6212, "lr": 6.877146996619122e-07, "epoch": 9.328358208955224, "percentage": 93.28, "elapsed_time": "0:08:38", "remaining_time": "0:00:37", "throughput": 2744.22, "total_tokens": 1421552} |
| {"current_steps": 5005, "total_steps": 5360, "loss": 6.3556, "lr": 6.688811802152279e-07, "epoch": 9.337686567164178, "percentage": 93.38, "elapsed_time": "0:08:38", "remaining_time": "0:00:36", "throughput": 2744.68, "total_tokens": 1423024} |
| {"current_steps": 5010, "total_steps": 5360, "loss": 6.0487, "lr": 6.503056412516223e-07, "epoch": 9.347014925373134, "percentage": 93.47, "elapsed_time": "0:08:38", "remaining_time": "0:00:36", "throughput": 2744.68, "total_tokens": 1424208} |
| {"current_steps": 5015, "total_steps": 5360, "loss": 6.3627, "lr": 6.31988279725726e-07, "epoch": 9.35634328358209, "percentage": 93.56, "elapsed_time": "0:08:39", "remaining_time": "0:00:35", "throughput": 2745.08, "total_tokens": 1425648} |
| {"current_steps": 5020, "total_steps": 5360, "loss": 5.7354, "lr": 6.139292898547366e-07, "epoch": 9.365671641791044, "percentage": 93.66, "elapsed_time": "0:08:39", "remaining_time": "0:00:35", "throughput": 2745.24, "total_tokens": 1426896} |
| {"current_steps": 5025, "total_steps": 5360, "loss": 6.1586, "lr": 5.961288631163687e-07, "epoch": 9.375, "percentage": 93.75, "elapsed_time": "0:08:40", "remaining_time": "0:00:34", "throughput": 2745.66, "total_tokens": 1428336} |
| {"current_steps": 5030, "total_steps": 5360, "loss": 5.803, "lr": 5.785871882468069e-07, "epoch": 9.384328358208956, "percentage": 93.84, "elapsed_time": "0:08:40", "remaining_time": "0:00:34", "throughput": 2745.97, "total_tokens": 1429712} |
| {"current_steps": 5035, "total_steps": 5360, "loss": 6.0366, "lr": 5.613044512387283e-07, "epoch": 9.39365671641791, "percentage": 93.94, "elapsed_time": "0:08:41", "remaining_time": "0:00:33", "throughput": 2746.02, "total_tokens": 1430928} |
| {"current_steps": 5040, "total_steps": 5360, "loss": 5.5562, "lr": 5.442808353393059e-07, "epoch": 9.402985074626866, "percentage": 94.03, "elapsed_time": "0:08:41", "remaining_time": "0:00:33", "throughput": 2746.29, "total_tokens": 1432272} |
| {"current_steps": 5045, "total_steps": 5360, "loss": 6.158, "lr": 5.275165210482824e-07, "epoch": 9.412313432835822, "percentage": 94.12, "elapsed_time": "0:08:41", "remaining_time": "0:00:32", "throughput": 2746.52, "total_tokens": 1433616} |
| {"current_steps": 5050, "total_steps": 5360, "loss": 6.1654, "lr": 5.110116861160502e-07, "epoch": 9.421641791044776, "percentage": 94.22, "elapsed_time": "0:08:42", "remaining_time": "0:00:32", "throughput": 2746.97, "total_tokens": 1435216} |
| {"current_steps": 5055, "total_steps": 5360, "loss": 5.7938, "lr": 4.947665055417605e-07, "epoch": 9.430970149253731, "percentage": 94.31, "elapsed_time": "0:08:42", "remaining_time": "0:00:31", "throughput": 2747.03, "total_tokens": 1436432} |
| {"current_steps": 5060, "total_steps": 5360, "loss": 6.2575, "lr": 4.787811515714919e-07, "epoch": 9.440298507462687, "percentage": 94.4, "elapsed_time": "0:08:43", "remaining_time": "0:00:31", "throughput": 2747.29, "total_tokens": 1437808} |
| {"current_steps": 5065, "total_steps": 5360, "loss": 6.0175, "lr": 4.6305579369638475e-07, "epoch": 9.449626865671641, "percentage": 94.5, "elapsed_time": "0:08:43", "remaining_time": "0:00:30", "throughput": 2747.52, "total_tokens": 1439152} |
| {"current_steps": 5070, "total_steps": 5360, "loss": 6.5007, "lr": 4.4759059865088494e-07, "epoch": 9.458955223880597, "percentage": 94.59, "elapsed_time": "0:08:44", "remaining_time": "0:00:29", "throughput": 2748.02, "total_tokens": 1440752} |
| {"current_steps": 5075, "total_steps": 5360, "loss": 6.0571, "lr": 4.323857304109419e-07, "epoch": 9.468283582089553, "percentage": 94.68, "elapsed_time": "0:08:44", "remaining_time": "0:00:29", "throughput": 2748.31, "total_tokens": 1442128} |
| {"current_steps": 5080, "total_steps": 5360, "loss": 6.5857, "lr": 4.1744135019230193e-07, "epoch": 9.477611940298507, "percentage": 94.78, "elapsed_time": "0:08:45", "remaining_time": "0:00:28", "throughput": 2748.83, "total_tokens": 1443728} |
| {"current_steps": 5085, "total_steps": 5360, "loss": 5.8465, "lr": 4.0275761644876787e-07, "epoch": 9.486940298507463, "percentage": 94.87, "elapsed_time": "0:08:45", "remaining_time": "0:00:28", "throughput": 2749.16, "total_tokens": 1445136} |
| {"current_steps": 5090, "total_steps": 5360, "loss": 5.8709, "lr": 3.883346848705338e-07, "epoch": 9.496268656716419, "percentage": 94.96, "elapsed_time": "0:08:46", "remaining_time": "0:00:27", "throughput": 2749.69, "total_tokens": 1446736} |
| {"current_steps": 5092, "total_steps": 5360, "eval_loss": 6.146888256072998, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:08:48", "remaining_time": "0:00:27", "throughput": 2736.45, "total_tokens": 1447376} |
| {"current_steps": 5095, "total_steps": 5360, "loss": 6.6405, "lr": 3.741727083825475e-07, "epoch": 9.505597014925373, "percentage": 95.06, "elapsed_time": "0:08:50", "remaining_time": "0:00:27", "throughput": 2731.11, "total_tokens": 1448112} |
| {"current_steps": 5100, "total_steps": 5360, "loss": 5.934, "lr": 3.6027183714285595e-07, "epoch": 9.514925373134329, "percentage": 95.15, "elapsed_time": "0:08:50", "remaining_time": "0:00:27", "throughput": 2731.71, "total_tokens": 1449744} |
| {"current_steps": 5105, "total_steps": 5360, "loss": 5.9534, "lr": 3.4663221854105423e-07, "epoch": 9.524253731343283, "percentage": 95.24, "elapsed_time": "0:08:51", "remaining_time": "0:00:26", "throughput": 2731.88, "total_tokens": 1451024} |
| {"current_steps": 5110, "total_steps": 5360, "loss": 5.6455, "lr": 3.332539971966836e-07, "epoch": 9.533582089552239, "percentage": 95.34, "elapsed_time": "0:08:51", "remaining_time": "0:00:26", "throughput": 2732.02, "total_tokens": 1452304} |
| {"current_steps": 5115, "total_steps": 5360, "loss": 6.4375, "lr": 3.201373149577247e-07, "epoch": 9.542910447761194, "percentage": 95.43, "elapsed_time": "0:08:52", "remaining_time": "0:00:25", "throughput": 2732.73, "total_tokens": 1453968} |
| {"current_steps": 5120, "total_steps": 5360, "loss": 5.8376, "lr": 3.0728231089907634e-07, "epoch": 9.552238805970148, "percentage": 95.52, "elapsed_time": "0:08:52", "remaining_time": "0:00:24", "throughput": 2733.07, "total_tokens": 1455376} |
| {"current_steps": 5125, "total_steps": 5360, "loss": 5.6522, "lr": 2.946891213211012e-07, "epoch": 9.561567164179104, "percentage": 95.62, "elapsed_time": "0:08:52", "remaining_time": "0:00:24", "throughput": 2733.45, "total_tokens": 1456816} |
| {"current_steps": 5130, "total_steps": 5360, "loss": 6.4457, "lr": 2.823578797481574e-07, "epoch": 9.57089552238806, "percentage": 95.71, "elapsed_time": "0:08:53", "remaining_time": "0:00:23", "throughput": 2733.92, "total_tokens": 1458320} |
| {"current_steps": 5135, "total_steps": 5360, "loss": 5.3658, "lr": 2.7028871692720003e-07, "epoch": 9.580223880597014, "percentage": 95.8, "elapsed_time": "0:08:53", "remaining_time": "0:00:23", "throughput": 2734.15, "total_tokens": 1459632} |
| {"current_steps": 5140, "total_steps": 5360, "loss": 5.9502, "lr": 2.5848176082639007e-07, "epoch": 9.58955223880597, "percentage": 95.9, "elapsed_time": "0:08:54", "remaining_time": "0:00:22", "throughput": 2734.42, "total_tokens": 1461008} |
| {"current_steps": 5145, "total_steps": 5360, "loss": 6.4102, "lr": 2.4693713663372644e-07, "epoch": 9.598880597014926, "percentage": 95.99, "elapsed_time": "0:08:54", "remaining_time": "0:00:22", "throughput": 2734.5, "total_tokens": 1462224} |
| {"current_steps": 5150, "total_steps": 5360, "loss": 6.4049, "lr": 2.3565496675574118e-07, "epoch": 9.60820895522388, "percentage": 96.08, "elapsed_time": "0:08:55", "remaining_time": "0:00:21", "throughput": 2734.9, "total_tokens": 1463664} |
| {"current_steps": 5155, "total_steps": 5360, "loss": 6.2554, "lr": 2.246353708161758e-07, "epoch": 9.617537313432836, "percentage": 96.18, "elapsed_time": "0:08:55", "remaining_time": "0:00:21", "throughput": 2735.37, "total_tokens": 1465168} |
| {"current_steps": 5160, "total_steps": 5360, "loss": 5.9242, "lr": 2.1387846565474045e-07, "epoch": 9.626865671641792, "percentage": 96.27, "elapsed_time": "0:08:56", "remaining_time": "0:00:20", "throughput": 2735.65, "total_tokens": 1466544} |
| {"current_steps": 5165, "total_steps": 5360, "loss": 5.4619, "lr": 2.0338436532584827e-07, "epoch": 9.636194029850746, "percentage": 96.36, "elapsed_time": "0:08:56", "remaining_time": "0:00:20", "throughput": 2736.25, "total_tokens": 1468176} |
| {"current_steps": 5170, "total_steps": 5360, "loss": 6.3981, "lr": 1.9315318109742465e-07, "epoch": 9.645522388059701, "percentage": 96.46, "elapsed_time": "0:08:57", "remaining_time": "0:00:19", "throughput": 2736.71, "total_tokens": 1469680} |
| {"current_steps": 5175, "total_steps": 5360, "loss": 6.2368, "lr": 1.831850214497194e-07, "epoch": 9.654850746268657, "percentage": 96.55, "elapsed_time": "0:08:57", "remaining_time": "0:00:19", "throughput": 2736.96, "total_tokens": 1471024} |
| {"current_steps": 5180, "total_steps": 5360, "loss": 6.3969, "lr": 1.7347999207415478e-07, "epoch": 9.664179104477611, "percentage": 96.64, "elapsed_time": "0:08:57", "remaining_time": "0:00:18", "throughput": 2737.26, "total_tokens": 1472464} |
| {"current_steps": 5185, "total_steps": 5360, "loss": 5.6938, "lr": 1.6403819587221814e-07, "epoch": 9.673507462686567, "percentage": 96.74, "elapsed_time": "0:08:58", "remaining_time": "0:00:18", "throughput": 2737.55, "total_tokens": 1473904} |
| {"current_steps": 5190, "total_steps": 5360, "loss": 6.3233, "lr": 1.5485973295434885e-07, "epoch": 9.682835820895523, "percentage": 96.83, "elapsed_time": "0:08:58", "remaining_time": "0:00:17", "throughput": 2738.0, "total_tokens": 1475408} |
| {"current_steps": 5195, "total_steps": 5360, "loss": 6.5344, "lr": 1.4594470063890308e-07, "epoch": 9.692164179104477, "percentage": 96.92, "elapsed_time": "0:08:59", "remaining_time": "0:00:17", "throughput": 2738.3, "total_tokens": 1476784} |
| {"current_steps": 5200, "total_steps": 5360, "loss": 5.6072, "lr": 1.3729319345109348e-07, "epoch": 9.701492537313433, "percentage": 97.01, "elapsed_time": "0:08:59", "remaining_time": "0:00:16", "throughput": 2738.6, "total_tokens": 1478160} |
| {"current_steps": 5205, "total_steps": 5360, "loss": 6.325, "lr": 1.2890530312200945e-07, "epoch": 9.710820895522389, "percentage": 97.11, "elapsed_time": "0:09:00", "remaining_time": "0:00:16", "throughput": 2738.96, "total_tokens": 1479600} |
| {"current_steps": 5210, "total_steps": 5360, "loss": 6.7264, "lr": 1.207811185876373e-07, "epoch": 9.720149253731343, "percentage": 97.2, "elapsed_time": "0:09:00", "remaining_time": "0:00:15", "throughput": 2739.16, "total_tokens": 1480944} |
| {"current_steps": 5215, "total_steps": 5360, "loss": 6.4153, "lr": 1.1292072598791114e-07, "epoch": 9.729477611940299, "percentage": 97.29, "elapsed_time": "0:09:01", "remaining_time": "0:00:15", "throughput": 2739.61, "total_tokens": 1482448} |
| {"current_steps": 5220, "total_steps": 5360, "loss": 6.253, "lr": 1.0532420866581072e-07, "epoch": 9.738805970149254, "percentage": 97.39, "elapsed_time": "0:09:01", "remaining_time": "0:00:14", "throughput": 2740.05, "total_tokens": 1483920} |
| {"current_steps": 5225, "total_steps": 5360, "loss": 6.2562, "lr": 9.799164716646769e-08, "epoch": 9.748134328358208, "percentage": 97.48, "elapsed_time": "0:09:02", "remaining_time": "0:00:14", "throughput": 2740.24, "total_tokens": 1485232} |
| {"current_steps": 5230, "total_steps": 5360, "loss": 5.9339, "lr": 9.092311923632191e-08, "epoch": 9.757462686567164, "percentage": 97.57, "elapsed_time": "0:09:02", "remaining_time": "0:00:13", "throughput": 2740.56, "total_tokens": 1486640} |
| {"current_steps": 5235, "total_steps": 5360, "loss": 5.9634, "lr": 8.411869982228038e-08, "epoch": 9.76679104477612, "percentage": 97.67, "elapsed_time": "0:09:02", "remaining_time": "0:00:12", "throughput": 2740.93, "total_tokens": 1488080} |
| {"current_steps": 5240, "total_steps": 5360, "loss": 6.3032, "lr": 7.757846107094291e-08, "epoch": 9.776119402985074, "percentage": 97.76, "elapsed_time": "0:09:03", "remaining_time": "0:00:12", "throughput": 2741.18, "total_tokens": 1489456} |
| {"current_steps": 5245, "total_steps": 5360, "loss": 5.7682, "lr": 7.130247232782216e-08, "epoch": 9.78544776119403, "percentage": 97.85, "elapsed_time": "0:09:03", "remaining_time": "0:00:11", "throughput": 2741.58, "total_tokens": 1491024} |
| {"current_steps": 5250, "total_steps": 5360, "loss": 5.2717, "lr": 6.529080013661648e-08, "epoch": 9.794776119402986, "percentage": 97.95, "elapsed_time": "0:09:04", "remaining_time": "0:00:11", "throughput": 2741.93, "total_tokens": 1492432} |
| {"current_steps": 5255, "total_steps": 5360, "loss": 6.1187, "lr": 5.954350823850208e-08, "epoch": 9.80410447761194, "percentage": 98.04, "elapsed_time": "0:09:04", "remaining_time": "0:00:10", "throughput": 2742.47, "total_tokens": 1494064} |
| {"current_steps": 5260, "total_steps": 5360, "loss": 5.6411, "lr": 5.4060657571453064e-08, "epoch": 9.813432835820896, "percentage": 98.13, "elapsed_time": "0:09:05", "remaining_time": "0:00:10", "throughput": 2742.88, "total_tokens": 1495536} |
| {"current_steps": 5265, "total_steps": 5360, "loss": 5.9149, "lr": 4.884230626960307e-08, "epoch": 9.822761194029852, "percentage": 98.23, "elapsed_time": "0:09:05", "remaining_time": "0:00:09", "throughput": 2743.09, "total_tokens": 1496848} |
| {"current_steps": 5270, "total_steps": 5360, "loss": 6.223, "lr": 4.388850966261793e-08, "epoch": 9.832089552238806, "percentage": 98.32, "elapsed_time": "0:09:06", "remaining_time": "0:00:09", "throughput": 2743.44, "total_tokens": 1498352} |
| {"current_steps": 5275, "total_steps": 5360, "loss": 6.0281, "lr": 3.919932027512674e-08, "epoch": 9.841417910447761, "percentage": 98.41, "elapsed_time": "0:09:06", "remaining_time": "0:00:08", "throughput": 2743.82, "total_tokens": 1499824} |
| {"current_steps": 5280, "total_steps": 5360, "loss": 6.8476, "lr": 3.477478782614452e-08, "epoch": 9.850746268656717, "percentage": 98.51, "elapsed_time": "0:09:07", "remaining_time": "0:00:08", "throughput": 2744.28, "total_tokens": 1501328} |
| {"current_steps": 5285, "total_steps": 5360, "loss": 6.3168, "lr": 3.061495922855873e-08, "epoch": 9.860074626865671, "percentage": 98.6, "elapsed_time": "0:09:07", "remaining_time": "0:00:07", "throughput": 2744.49, "total_tokens": 1502640} |
| {"current_steps": 5290, "total_steps": 5360, "loss": 6.3805, "lr": 2.67198785886269e-08, "epoch": 9.869402985074627, "percentage": 98.69, "elapsed_time": "0:09:07", "remaining_time": "0:00:07", "throughput": 2744.94, "total_tokens": 1504144} |
| {"current_steps": 5295, "total_steps": 5360, "loss": 6.0447, "lr": 2.3089587205507578e-08, "epoch": 9.878731343283581, "percentage": 98.79, "elapsed_time": "0:09:08", "remaining_time": "0:00:06", "throughput": 2745.32, "total_tokens": 1505584} |
| {"current_steps": 5300, "total_steps": 5360, "loss": 5.8787, "lr": 1.972412357083009e-08, "epoch": 9.888059701492537, "percentage": 98.88, "elapsed_time": "0:09:08", "remaining_time": "0:00:06", "throughput": 2745.9, "total_tokens": 1507184} |
| {"current_steps": 5305, "total_steps": 5360, "loss": 5.76, "lr": 1.662352336827544e-08, "epoch": 9.897388059701493, "percentage": 98.97, "elapsed_time": "0:09:09", "remaining_time": "0:00:05", "throughput": 2746.31, "total_tokens": 1508656} |
| {"current_steps": 5310, "total_steps": 5360, "loss": 5.9212, "lr": 1.3787819473207176e-08, "epoch": 9.906716417910447, "percentage": 99.07, "elapsed_time": "0:09:09", "remaining_time": "0:00:05", "throughput": 2746.8, "total_tokens": 1510192} |
| {"current_steps": 5315, "total_steps": 5360, "loss": 6.5124, "lr": 1.1217041952313323e-08, "epoch": 9.916044776119403, "percentage": 99.16, "elapsed_time": "0:09:10", "remaining_time": "0:00:04", "throughput": 2747.16, "total_tokens": 1511632} |
| {"current_steps": 5320, "total_steps": 5360, "loss": 6.0284, "lr": 8.91121806330386e-09, "epoch": 9.925373134328359, "percentage": 99.25, "elapsed_time": "0:09:10", "remaining_time": "0:00:04", "throughput": 2747.45, "total_tokens": 1513008} |
| {"current_steps": 5325, "total_steps": 5360, "loss": 6.1722, "lr": 6.870372254602631e-09, "epoch": 9.934701492537313, "percentage": 99.35, "elapsed_time": "0:09:11", "remaining_time": "0:00:03", "throughput": 2747.76, "total_tokens": 1514416} |
| {"current_steps": 5330, "total_steps": 5360, "loss": 6.1963, "lr": 5.09452616509476e-09, "epoch": 9.944029850746269, "percentage": 99.44, "elapsed_time": "0:09:11", "remaining_time": "0:00:03", "throughput": 2748.11, "total_tokens": 1515856} |
| {"current_steps": 5335, "total_steps": 5360, "loss": 5.8672, "lr": 3.58369862391017e-09, "epoch": 9.953358208955224, "percentage": 99.53, "elapsed_time": "0:09:12", "remaining_time": "0:00:02", "throughput": 2748.44, "total_tokens": 1517328} |
| {"current_steps": 5340, "total_steps": 5360, "loss": 5.6686, "lr": 2.3379056502015327e-09, "epoch": 9.962686567164178, "percentage": 99.63, "elapsed_time": "0:09:12", "remaining_time": "0:00:02", "throughput": 2748.75, "total_tokens": 1518800} |
| {"current_steps": 5345, "total_steps": 5360, "loss": 5.7095, "lr": 1.357160452988837e-09, "epoch": 9.972014925373134, "percentage": 99.72, "elapsed_time": "0:09:12", "remaining_time": "0:00:01", "throughput": 2749.07, "total_tokens": 1520208} |
| {"current_steps": 5350, "total_steps": 5360, "loss": 6.2756, "lr": 6.414734310233872e-10, "epoch": 9.98134328358209, "percentage": 99.81, "elapsed_time": "0:09:13", "remaining_time": "0:00:01", "throughput": 2749.38, "total_tokens": 1521616} |
| {"current_steps": 5355, "total_steps": 5360, "loss": 6.6308, "lr": 1.9085217266290312e-10, "epoch": 9.990671641791044, "percentage": 99.91, "elapsed_time": "0:09:13", "remaining_time": "0:00:00", "throughput": 2749.67, "total_tokens": 1522992} |
| {"current_steps": 5360, "total_steps": 5360, "loss": 5.5584, "lr": 5.3014557993558144e-12, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:09:14", "remaining_time": "0:00:00", "throughput": 2749.19, "total_tokens": 1524216} |
| {"current_steps": 5360, "total_steps": 5360, "eval_loss": 6.148874282836914, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:09:17", "remaining_time": "0:00:00", "throughput": 2736.46, "total_tokens": 1524216} |
| {"current_steps": 5360, "total_steps": 5360, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:09:18", "remaining_time": "0:00:00", "throughput": 2731.47, "total_tokens": 1524216} |
|
|