diff --git "a/logs/train.jsonl" "b/logs/train.jsonl"
--- "a/logs/train.jsonl"
+++ "b/logs/train.jsonl"
@@ -1,2603 +1,102 @@
-{"ts": "2025-12-26T18:17:26", "event": "train_log", "step": 2, "epoch": 0.0008438818565400844, "progress_pct": 0.01, "epoch_pct": 0.01, "eta": "31:09:53", "max_grad_norm": 1.0, "loss": 1.6941628456115723, "grad_norm": 0.5386583805084229, "learning_rate": 1.7574692442882248e-07}
-{"ts": "2025-12-26T18:17:42", "event": "train_log", "step": 4, "epoch": 0.0016877637130801688, "progress_pct": 0.03, "epoch_pct": 0.03, "eta": "31:14:54", "max_grad_norm": 1.0, "loss": 1.7132279872894287, "grad_norm": 0.5477277636528015, "learning_rate": 5.272407732864675e-07}
-{"ts": "2025-12-26T18:17:57", "event": "train_log", "step": 6, "epoch": 0.002531645569620253, "progress_pct": 0.04, "epoch_pct": 0.04, "eta": "31:02:32", "max_grad_norm": 1.0, "loss": 1.641180396080017, "grad_norm": 0.5390765070915222, "learning_rate": 8.787346221441126e-07}
-{"ts": "2025-12-26T18:18:13", "event": "train_log", "step": 8, "epoch": 0.0033755274261603376, "progress_pct": 0.06, "epoch_pct": 0.06, "eta": "31:07:59", "max_grad_norm": 1.0, "loss": 1.5616240501403809, "grad_norm": 0.5023683905601501, "learning_rate": 1.2302284710017575e-06}
-{"ts": "2025-12-26T18:18:31", "event": "train_log", "step": 10, "epoch": 0.004219409282700422, "progress_pct": 0.07, "epoch_pct": 0.07, "eta": "31:44:10", "max_grad_norm": 1.0, "loss": 1.572033405303955, "grad_norm": 0.4899154603481293, "learning_rate": 1.5817223198594026e-06}
-{"ts": "2025-12-26T18:18:47", "event": "train_log", "step": 12, "epoch": 0.005063291139240506, "progress_pct": 0.08, "epoch_pct": 0.08, "eta": "31:44:10", "max_grad_norm": 1.0, "loss": 1.6242921352386475, "grad_norm": 0.5239788293838501, "learning_rate": 1.9332161687170474e-06}
-{"ts": "2025-12-26T18:19:03", "event": "train_log", "step": 14, "epoch": 0.00590717299578059, "progress_pct": 0.1, "epoch_pct": 0.1, "eta": "31:40:24", "max_grad_norm": 1.0, "loss": 1.6800041198730469, "grad_norm": 0.5172926783561707, "learning_rate": 2.2847100175746925e-06}
-{"ts": "2025-12-26T18:19:20", "event": "train_log", "step": 16, "epoch": 0.006751054852320675, "progress_pct": 0.11, "epoch_pct": 0.11, "eta": "31:54:47", "max_grad_norm": 1.0, "loss": 1.6450834274291992, "grad_norm": 0.5539224743843079, "learning_rate": 2.6362038664323376e-06}
-{"ts": "2025-12-26T18:19:35", "event": "train_log", "step": 18, "epoch": 0.007594936708860759, "progress_pct": 0.13, "epoch_pct": 0.13, "eta": "31:50:46", "max_grad_norm": 1.0, "loss": 1.6673263311386108, "grad_norm": 0.5255337953567505, "learning_rate": 2.9876977152899827e-06}
-{"ts": "2025-12-26T18:19:51", "event": "train_log", "step": 20, "epoch": 0.008438818565400843, "progress_pct": 0.14, "epoch_pct": 0.14, "eta": "31:40:51", "max_grad_norm": 1.0, "loss": 1.531802773475647, "grad_norm": 0.5074548721313477, "learning_rate": 3.3391915641476277e-06}
-{"ts": "2025-12-26T18:20:06", "event": "train_log", "step": 22, "epoch": 0.009282700421940928, "progress_pct": 0.15, "epoch_pct": 0.15, "eta": "31:30:04", "max_grad_norm": 1.0, "loss": 1.599354863166809, "grad_norm": 0.4160279333591461, "learning_rate": 3.6906854130052724e-06}
-{"ts": "2025-12-26T18:20:22", "event": "train_log", "step": 24, "epoch": 0.010126582278481013, "progress_pct": 0.17, "epoch_pct": 0.17, "eta": "31:26:56", "max_grad_norm": 1.0, "loss": 1.6700962781906128, "grad_norm": 0.5716474652290344, "learning_rate": 4.0421792618629174e-06}
-{"ts": "2025-12-26T18:20:38", "event": "train_log", "step": 26, "epoch": 0.010970464135021098, "progress_pct": 0.18, "epoch_pct": 0.18, "eta": "31:27:18", "max_grad_norm": 1.0, "loss": 1.66217839717865, "grad_norm": 0.5148899555206299, "learning_rate": 4.3936731107205625e-06}
-{"ts": "2025-12-26T18:20:53", "event": "train_log", "step": 28, "epoch": 0.01181434599156118, "progress_pct": 0.2, "epoch_pct": 0.2, "eta": "31:18:25", "max_grad_norm": 1.0, "loss": 1.6692266464233398, "grad_norm": 0.575722336769104, "learning_rate": 4.7451669595782076e-06}
-{"ts": "2025-12-26T18:21:07", "event": "train_log", "step": 30, "epoch": 0.012658227848101266, "progress_pct": 0.21, "epoch_pct": 0.21, "eta": "31:10:37", "max_grad_norm": 1.0, "loss": 1.5518689155578613, "grad_norm": 0.5345953106880188, "learning_rate": 5.096660808435853e-06}
-{"ts": "2025-12-26T18:21:22", "event": "train_log", "step": 32, "epoch": 0.01350210970464135, "progress_pct": 0.23, "epoch_pct": 0.23, "eta": "31:03:45", "max_grad_norm": 1.0, "loss": 1.5930007696151733, "grad_norm": 0.4462043344974518, "learning_rate": 5.448154657293498e-06}
-{"ts": "2025-12-26T18:21:37", "event": "train_log", "step": 34, "epoch": 0.014345991561181435, "progress_pct": 0.24, "epoch_pct": 0.24, "eta": "30:55:24", "max_grad_norm": 1.0, "loss": 1.6069684028625488, "grad_norm": 0.5119605660438538, "learning_rate": 5.799648506151143e-06}
-{"ts": "2025-12-26T18:21:52", "event": "train_log", "step": 36, "epoch": 0.015189873417721518, "progress_pct": 0.25, "epoch_pct": 0.25, "eta": "30:50:57", "max_grad_norm": 1.0, "loss": 1.5838109254837036, "grad_norm": 0.5328608751296997, "learning_rate": 6.151142355008788e-06}
-{"ts": "2025-12-26T18:22:07", "event": "train_log", "step": 38, "epoch": 0.016033755274261603, "progress_pct": 0.27, "epoch_pct": 0.27, "eta": "30:48:40", "max_grad_norm": 1.0, "loss": 1.608130931854248, "grad_norm": 0.5065920352935791, "learning_rate": 6.502636203866433e-06}
-{"ts": "2025-12-26T18:22:23", "event": "train_log", "step": 40, "epoch": 0.016877637130801686, "progress_pct": 0.28, "epoch_pct": 0.28, "eta": "30:48:19", "max_grad_norm": 1.0, "loss": 1.5942182540893555, "grad_norm": 0.4479359984397888, "learning_rate": 6.854130052724078e-06}
-{"ts": "2025-12-26T18:22:37", "event": "train_log", "step": 42, "epoch": 0.017721518987341773, "progress_pct": 0.3, "epoch_pct": 0.3, "eta": "30:41:16", "max_grad_norm": 1.0, "loss": 1.6441553831100464, "grad_norm": 0.42844903469085693, "learning_rate": 7.205623901581722e-06}
-{"ts": "2025-12-26T18:22:52", "event": "train_log", "step": 44, "epoch": 0.018565400843881856, "progress_pct": 0.31, "epoch_pct": 0.31, "eta": "30:36:38", "max_grad_norm": 1.0, "loss": 1.6068111658096313, "grad_norm": 0.476630836725235, "learning_rate": 7.557117750439367e-06}
-{"ts": "2025-12-26T18:23:07", "event": "train_log", "step": 46, "epoch": 0.019409282700421943, "progress_pct": 0.32, "epoch_pct": 0.32, "eta": "30:29:59", "max_grad_norm": 1.0, "loss": 1.6618021726608276, "grad_norm": 0.4532654881477356, "learning_rate": 7.908611599297012e-06}
-{"ts": "2025-12-26T18:23:22", "event": "train_log", "step": 48, "epoch": 0.020253164556962026, "progress_pct": 0.34, "epoch_pct": 0.34, "eta": "30:27:44", "max_grad_norm": 1.0, "loss": 1.4730033874511719, "grad_norm": 0.3701118230819702, "learning_rate": 8.260105448154657e-06}
-{"ts": "2025-12-26T18:23:37", "event": "train_log", "step": 50, "epoch": 0.02109704641350211, "progress_pct": 0.35, "epoch_pct": 0.35, "eta": "30:26:49", "max_grad_norm": 1.0, "loss": 1.4828267097473145, "grad_norm": 0.38471561670303345, "learning_rate": 8.611599297012302e-06}
-{"ts": "2025-12-26T18:23:52", "event": "train_log", "step": 52, "epoch": 0.021940928270042195, "progress_pct": 0.37, "epoch_pct": 0.37, "eta": "30:23:44", "max_grad_norm": 1.0, "loss": 1.3877452611923218, "grad_norm": 0.3602336347103119, "learning_rate": 8.963093145869948e-06}
-{"ts": "2025-12-26T18:24:06", "event": "train_log", "step": 54, "epoch": 0.02278481012658228, "progress_pct": 0.38, "epoch_pct": 0.38, "eta": "30:16:46", "max_grad_norm": 1.0, "loss": 1.49052894115448, "grad_norm": 0.40318572521209717, "learning_rate": 9.314586994727593e-06}
-{"ts": "2025-12-26T18:24:21", "event": "train_log", "step": 56, "epoch": 0.02362869198312236, "progress_pct": 0.39, "epoch_pct": 0.39, "eta": "30:15:39", "max_grad_norm": 1.0, "loss": 1.4912524223327637, "grad_norm": 0.3223826587200165, "learning_rate": 9.666080843585238e-06}
-{"ts": "2025-12-26T18:24:35", "event": "train_log", "step": 58, "epoch": 0.024472573839662448, "progress_pct": 0.41, "epoch_pct": 0.41, "eta": "30:12:10", "max_grad_norm": 1.0, "loss": 1.526674509048462, "grad_norm": 0.3873065114021301, "learning_rate": 1.0017574692442883e-05}
-{"ts": "2025-12-26T18:24:50", "event": "train_log", "step": 60, "epoch": 0.02531645569620253, "progress_pct": 0.42, "epoch_pct": 0.42, "eta": "30:08:52", "max_grad_norm": 1.0, "loss": 1.4480271339416504, "grad_norm": 0.410159707069397, "learning_rate": 1.0369068541300528e-05}
-{"ts": "2025-12-26T18:25:05", "event": "train_log", "step": 62, "epoch": 0.026160337552742614, "progress_pct": 0.44, "epoch_pct": 0.44, "eta": "30:07:18", "max_grad_norm": 1.0, "loss": 1.4222990274429321, "grad_norm": 0.3632003962993622, "learning_rate": 1.0720562390158173e-05}
-{"ts": "2025-12-26T18:25:20", "event": "train_log", "step": 64, "epoch": 0.0270042194092827, "progress_pct": 0.45, "epoch_pct": 0.45, "eta": "30:05:16", "max_grad_norm": 1.0, "loss": 1.387171745300293, "grad_norm": 0.33118435740470886, "learning_rate": 1.1072056239015818e-05}
-{"ts": "2025-12-26T18:25:34", "event": "train_log", "step": 66, "epoch": 0.027848101265822784, "progress_pct": 0.46, "epoch_pct": 0.46, "eta": "30:02:30", "max_grad_norm": 1.0, "loss": 1.3523777723312378, "grad_norm": 0.3301764726638794, "learning_rate": 1.1423550087873463e-05}
-{"ts": "2025-12-26T18:25:50", "event": "train_log", "step": 68, "epoch": 0.02869198312236287, "progress_pct": 0.48, "epoch_pct": 0.48, "eta": "30:02:26", "max_grad_norm": 1.0, "loss": 1.4515162706375122, "grad_norm": 0.34342435002326965, "learning_rate": 1.1775043936731108e-05}
-{"ts": "2025-12-26T18:26:05", "event": "train_log", "step": 70, "epoch": 0.029535864978902954, "progress_pct": 0.49, "epoch_pct": 0.49, "eta": "30:02:54", "max_grad_norm": 1.0, "loss": 1.3509243726730347, "grad_norm": 0.3243122100830078, "learning_rate": 1.2126537785588753e-05}
-{"ts": "2025-12-26T18:26:19", "event": "train_log", "step": 72, "epoch": 0.030379746835443037, "progress_pct": 0.51, "epoch_pct": 0.51, "eta": "29:57:27", "max_grad_norm": 1.0, "loss": 1.4936245679855347, "grad_norm": 0.3450150787830353, "learning_rate": 1.2478031634446398e-05}
-{"ts": "2025-12-26T18:26:34", "event": "train_log", "step": 74, "epoch": 0.031223628691983123, "progress_pct": 0.52, "epoch_pct": 0.52, "eta": "29:57:49", "max_grad_norm": 1.0, "loss": 1.3419109582901, "grad_norm": 0.38912028074264526, "learning_rate": 1.2829525483304042e-05}
-{"ts": "2025-12-26T18:26:49", "event": "train_log", "step": 76, "epoch": 0.032067510548523206, "progress_pct": 0.53, "epoch_pct": 0.53, "eta": "29:56:09", "max_grad_norm": 1.0, "loss": 1.4284154176712036, "grad_norm": 0.3019310235977173, "learning_rate": 1.3181019332161687e-05}
-{"ts": "2025-12-26T18:27:04", "event": "train_log", "step": 78, "epoch": 0.03291139240506329, "progress_pct": 0.55, "epoch_pct": 0.55, "eta": "29:53:57", "max_grad_norm": 1.0, "loss": 1.4256561994552612, "grad_norm": 0.37803682684898376, "learning_rate": 1.3532513181019332e-05}
-{"ts": "2025-12-26T18:27:19", "event": "train_log", "step": 80, "epoch": 0.03375527426160337, "progress_pct": 0.56, "epoch_pct": 0.56, "eta": "29:52:20", "max_grad_norm": 1.0, "loss": 1.3256909847259521, "grad_norm": 0.34191736578941345, "learning_rate": 1.3884007029876977e-05}
-{"ts": "2025-12-26T18:27:34", "event": "train_log", "step": 82, "epoch": 0.03459915611814346, "progress_pct": 0.58, "epoch_pct": 0.58, "eta": "29:52:58", "max_grad_norm": 1.0, "loss": 1.2710685729980469, "grad_norm": 0.35242700576782227, "learning_rate": 1.4235500878734624e-05}
-{"ts": "2025-12-26T18:27:50", "event": "train_log", "step": 84, "epoch": 0.035443037974683546, "progress_pct": 0.59, "epoch_pct": 0.59, "eta": "29:53:41", "max_grad_norm": 1.0, "loss": 1.253411889076233, "grad_norm": 0.38094228506088257, "learning_rate": 1.4586994727592269e-05}
-{"ts": "2025-12-26T18:28:05", "event": "train_log", "step": 86, "epoch": 0.036286919831223625, "progress_pct": 0.6, "epoch_pct": 0.6, "eta": "29:54:14", "max_grad_norm": 1.0, "loss": 1.3064342737197876, "grad_norm": 0.36837366223335266, "learning_rate": 1.4938488576449914e-05}
-{"ts": "2025-12-26T18:28:20", "event": "train_log", "step": 88, "epoch": 0.03713080168776371, "progress_pct": 0.62, "epoch_pct": 0.62, "eta": "29:52:02", "max_grad_norm": 1.0, "loss": 1.293562412261963, "grad_norm": 0.3443569242954254, "learning_rate": 1.5289982425307557e-05}
-{"ts": "2025-12-26T18:28:35", "event": "train_log", "step": 90, "epoch": 0.0379746835443038, "progress_pct": 0.63, "epoch_pct": 0.63, "eta": "29:50:57", "max_grad_norm": 1.0, "loss": 1.3382648229599, "grad_norm": 0.3799338936805725, "learning_rate": 1.5641476274165202e-05}
-{"ts": "2025-12-26T18:28:49", "event": "train_log", "step": 92, "epoch": 0.038818565400843885, "progress_pct": 0.65, "epoch_pct": 0.65, "eta": "29:49:38", "max_grad_norm": 1.0, "loss": 1.3925724029541016, "grad_norm": 0.40501922369003296, "learning_rate": 1.599297012302285e-05}
-{"ts": "2025-12-26T18:29:04", "event": "train_log", "step": 94, "epoch": 0.039662447257383965, "progress_pct": 0.66, "epoch_pct": 0.66, "eta": "29:46:49", "max_grad_norm": 1.0, "loss": 1.357171893119812, "grad_norm": 0.4419630467891693, "learning_rate": 1.6344463971880492e-05}
-{"ts": "2025-12-26T18:29:18", "event": "train_log", "step": 96, "epoch": 0.04050632911392405, "progress_pct": 0.68, "epoch_pct": 0.68, "eta": "29:45:24", "max_grad_norm": 1.0, "loss": 1.3029985427856445, "grad_norm": 0.3619817793369293, "learning_rate": 1.6695957820738137e-05}
-{"ts": "2025-12-26T18:29:32", "event": "train_log", "step": 98, "epoch": 0.04135021097046414, "progress_pct": 0.69, "epoch_pct": 0.69, "eta": "29:42:16", "max_grad_norm": 1.0, "loss": 1.3498191833496094, "grad_norm": 0.4851357340812683, "learning_rate": 1.7047451669595782e-05}
-{"ts": "2025-12-26T18:29:48", "event": "train_log", "step": 100, "epoch": 0.04219409282700422, "progress_pct": 0.7, "epoch_pct": 0.7, "eta": "29:42:35", "max_grad_norm": 1.0, "loss": 1.185287356376648, "grad_norm": 0.418658584356308, "learning_rate": 1.7398945518453427e-05}
-{"ts": "2025-12-26T18:41:10", "event": "train_log", "step": 100, "epoch": 0.04219409282700422, "progress_pct": 0.7, "epoch_pct": 0.7, "eta": "56:28:01", "max_grad_norm": 1.0, "eval_loss": 1.2979938983917236, "eval_runtime": 682.1979, "eval_samples_per_second": 3.089, "eval_steps_per_second": 3.089}
-{"ts": "2025-12-26T18:41:25", "event": "train_log", "step": 102, "epoch": 0.043037974683544304, "progress_pct": 0.72, "epoch_pct": 0.72, "eta": "55:56:35", "max_grad_norm": 1.0, "loss": 1.2217272520065308, "grad_norm": 0.4464418888092041, "learning_rate": 1.7750439367311073e-05}
-{"ts": "2025-12-26T18:41:41", "event": "train_log", "step": 104, "epoch": 0.04388185654008439, "progress_pct": 0.73, "epoch_pct": 0.73, "eta": "55:27:29", "max_grad_norm": 1.0, "loss": 1.2052050828933716, "grad_norm": 0.4706237316131592, "learning_rate": 1.8101933216168718e-05}
-{"ts": "2025-12-26T18:41:55", "event": "train_log", "step": 106, "epoch": 0.04472573839662447, "progress_pct": 0.75, "epoch_pct": 0.75, "eta": "54:55:49", "max_grad_norm": 1.0, "loss": 1.221343994140625, "grad_norm": 0.46394404768943787, "learning_rate": 1.8453427065026363e-05}
-{"ts": "2025-12-26T18:42:11", "event": "train_log", "step": 108, "epoch": 0.04556962025316456, "progress_pct": 0.76, "epoch_pct": 0.76, "eta": "54:27:45", "max_grad_norm": 1.0, "loss": 1.2387475967407227, "grad_norm": 0.4726889431476593, "learning_rate": 1.8804920913884008e-05}
-{"ts": "2025-12-26T18:42:26", "event": "train_log", "step": 110, "epoch": 0.046413502109704644, "progress_pct": 0.77, "epoch_pct": 0.77, "eta": "54:01:37", "max_grad_norm": 1.0, "loss": 1.2851309776306152, "grad_norm": 0.42130985856056213, "learning_rate": 1.9156414762741653e-05}
-{"ts": "2025-12-26T18:42:43", "event": "train_log", "step": 112, "epoch": 0.04725738396624472, "progress_pct": 0.79, "epoch_pct": 0.79, "eta": "53:37:09", "max_grad_norm": 1.0, "loss": 1.2753145694732666, "grad_norm": 0.4504576623439789, "learning_rate": 1.9507908611599298e-05}
-{"ts": "2025-12-26T18:42:59", "event": "train_log", "step": 114, "epoch": 0.04810126582278481, "progress_pct": 0.8, "epoch_pct": 0.8, "eta": "53:13:19", "max_grad_norm": 1.0, "loss": 1.2427717447280884, "grad_norm": 0.396085262298584, "learning_rate": 1.9859402460456943e-05}
-{"ts": "2025-12-26T18:43:14", "event": "train_log", "step": 116, "epoch": 0.048945147679324896, "progress_pct": 0.82, "epoch_pct": 0.82, "eta": "52:49:08", "max_grad_norm": 1.0, "loss": 1.2943825721740723, "grad_norm": 0.5106491446495056, "learning_rate": 2.0210896309314588e-05}
-{"ts": "2025-12-26T18:43:29", "event": "train_log", "step": 118, "epoch": 0.049789029535864976, "progress_pct": 0.83, "epoch_pct": 0.83, "eta": "52:25:12", "max_grad_norm": 1.0, "loss": 1.263301134109497, "grad_norm": 0.42351317405700684, "learning_rate": 2.0562390158172233e-05}
-{"ts": "2025-12-26T18:43:44", "event": "train_log", "step": 120, "epoch": 0.05063291139240506, "progress_pct": 0.84, "epoch_pct": 0.84, "eta": "52:01:59", "max_grad_norm": 1.0, "loss": 1.2647849321365356, "grad_norm": 0.4403539299964905, "learning_rate": 2.0913884007029878e-05}
-{"ts": "2025-12-26T18:43:59", "event": "train_log", "step": 122, "epoch": 0.05147679324894515, "progress_pct": 0.86, "epoch_pct": 0.86, "eta": "51:38:39", "max_grad_norm": 1.0, "loss": 1.2351393699645996, "grad_norm": 0.5260752439498901, "learning_rate": 2.1265377855887523e-05}
-{"ts": "2025-12-26T18:44:16", "event": "train_log", "step": 124, "epoch": 0.05232067510548523, "progress_pct": 0.87, "epoch_pct": 0.87, "eta": "51:20:15", "max_grad_norm": 1.0, "loss": 1.0384471416473389, "grad_norm": 0.44978851079940796, "learning_rate": 2.1616871704745168e-05}
-{"ts": "2025-12-26T18:44:33", "event": "train_log", "step": 126, "epoch": 0.053164556962025315, "progress_pct": 0.89, "epoch_pct": 0.89, "eta": "51:02:43", "max_grad_norm": 1.0, "loss": 1.1518068313598633, "grad_norm": 0.47732362151145935, "learning_rate": 2.1968365553602813e-05}
-{"ts": "2025-12-26T18:44:48", "event": "train_log", "step": 128, "epoch": 0.0540084388185654, "progress_pct": 0.9, "epoch_pct": 0.9, "eta": "50:41:43", "max_grad_norm": 1.0, "loss": 1.2264912128448486, "grad_norm": 0.5473551750183105, "learning_rate": 2.231985940246046e-05}
-{"ts": "2025-12-26T18:45:03", "event": "train_log", "step": 130, "epoch": 0.05485232067510549, "progress_pct": 0.91, "epoch_pct": 0.91, "eta": "50:21:17", "max_grad_norm": 1.0, "loss": 1.1615246534347534, "grad_norm": 0.4473855197429657, "learning_rate": 2.2671353251318103e-05}
-{"ts": "2025-12-26T18:45:19", "event": "train_log", "step": 132, "epoch": 0.05569620253164557, "progress_pct": 0.93, "epoch_pct": 0.93, "eta": "50:03:15", "max_grad_norm": 1.0, "loss": 1.1334880590438843, "grad_norm": 0.5980377197265625, "learning_rate": 2.302284710017575e-05}
-{"ts": "2025-12-26T18:45:35", "event": "train_log", "step": 134, "epoch": 0.056540084388185655, "progress_pct": 0.94, "epoch_pct": 0.94, "eta": "49:46:01", "max_grad_norm": 1.0, "loss": 1.1546804904937744, "grad_norm": 0.5987792015075684, "learning_rate": 2.3374340949033394e-05}
-{"ts": "2025-12-26T18:45:50", "event": "train_log", "step": 136, "epoch": 0.05738396624472574, "progress_pct": 0.96, "epoch_pct": 0.96, "eta": "49:29:14", "max_grad_norm": 1.0, "loss": 1.194953441619873, "grad_norm": 0.45355498790740967, "learning_rate": 2.372583479789104e-05}
-{"ts": "2025-12-26T18:46:07", "event": "train_log", "step": 138, "epoch": 0.05822784810126582, "progress_pct": 0.97, "epoch_pct": 0.97, "eta": "49:13:04", "max_grad_norm": 1.0, "loss": 1.1067466735839844, "grad_norm": 0.5373698472976685, "learning_rate": 2.4077328646748684e-05}
-{"ts": "2025-12-26T18:46:22", "event": "train_log", "step": 140, "epoch": 0.05907172995780591, "progress_pct": 0.98, "epoch_pct": 0.98, "eta": "48:55:54", "max_grad_norm": 1.0, "loss": 1.188468098640442, "grad_norm": 0.48734328150749207, "learning_rate": 2.442882249560633e-05}
-{"ts": "2025-12-26T18:46:38", "event": "train_log", "step": 142, "epoch": 0.059915611814345994, "progress_pct": 1.0, "epoch_pct": 1.0, "eta": "48:40:36", "max_grad_norm": 1.0, "loss": 1.1624362468719482, "grad_norm": 0.4692173898220062, "learning_rate": 2.478031634446397e-05}
-{"ts": "2025-12-26T18:46:54", "event": "train_log", "step": 144, "epoch": 0.060759493670886074, "progress_pct": 1.01, "epoch_pct": 1.01, "eta": "48:26:30", "max_grad_norm": 1.0, "loss": 1.0978907346725464, "grad_norm": 0.532554030418396, "learning_rate": 2.513181019332162e-05}
-{"ts": "2025-12-26T18:47:09", "event": "train_log", "step": 146, "epoch": 0.06160337552742616, "progress_pct": 1.03, "epoch_pct": 1.03, "eta": "48:09:34", "max_grad_norm": 1.0, "loss": 1.2030781507492065, "grad_norm": 0.5853802561759949, "learning_rate": 2.5483304042179264e-05}
-{"ts": "2025-12-26T18:47:25", "event": "train_log", "step": 148, "epoch": 0.06244725738396625, "progress_pct": 1.04, "epoch_pct": 1.04, "eta": "47:55:44", "max_grad_norm": 1.0, "loss": 1.082366943359375, "grad_norm": 0.5061611533164978, "learning_rate": 2.583479789103691e-05}
-{"ts": "2025-12-26T18:47:41", "event": "train_log", "step": 150, "epoch": 0.06329113924050633, "progress_pct": 1.05, "epoch_pct": 1.05, "eta": "47:42:57", "max_grad_norm": 1.0, "loss": 1.10564386844635, "grad_norm": 0.49426141381263733, "learning_rate": 2.6186291739894554e-05}
-{"ts": "2025-12-26T18:47:57", "event": "train_log", "step": 152, "epoch": 0.06413502109704641, "progress_pct": 1.07, "epoch_pct": 1.07, "eta": "47:28:55", "max_grad_norm": 1.0, "loss": 1.1992807388305664, "grad_norm": 0.5846618413925171, "learning_rate": 2.6537785588752196e-05}
-{"ts": "2025-12-26T18:48:12", "event": "train_log", "step": 154, "epoch": 0.06497890295358649, "progress_pct": 1.08, "epoch_pct": 1.08, "eta": "47:14:42", "max_grad_norm": 1.0, "loss": 1.1757566928863525, "grad_norm": 0.5517552495002747, "learning_rate": 2.6889279437609844e-05}
-{"ts": "2025-12-26T18:48:28", "event": "train_log", "step": 156, "epoch": 0.06582278481012659, "progress_pct": 1.1, "epoch_pct": 1.1, "eta": "47:01:26", "max_grad_norm": 1.0, "loss": 1.0548783540725708, "grad_norm": 0.5667305588722229, "learning_rate": 2.7240773286467486e-05}
-{"ts": "2025-12-26T18:48:44", "event": "train_log", "step": 158, "epoch": 0.06666666666666667, "progress_pct": 1.11, "epoch_pct": 1.11, "eta": "46:49:16", "max_grad_norm": 1.0, "loss": 1.184364914894104, "grad_norm": 0.6760414242744446, "learning_rate": 2.7592267135325134e-05}
-{"ts": "2025-12-26T18:48:59", "event": "train_log", "step": 160, "epoch": 0.06751054852320675, "progress_pct": 1.13, "epoch_pct": 1.13, "eta": "46:36:11", "max_grad_norm": 1.0, "loss": 1.1945042610168457, "grad_norm": 0.5261430740356445, "learning_rate": 2.7943760984182776e-05}
-{"ts": "2025-12-26T18:49:14", "event": "train_log", "step": 162, "epoch": 0.06835443037974684, "progress_pct": 1.14, "epoch_pct": 1.14, "eta": "46:22:52", "max_grad_norm": 1.0, "loss": 1.2021973133087158, "grad_norm": 0.6155015230178833, "learning_rate": 2.8295254833040425e-05}
-{"ts": "2025-12-26T18:49:30", "event": "train_log", "step": 164, "epoch": 0.06919831223628692, "progress_pct": 1.15, "epoch_pct": 1.15, "eta": "46:10:34", "max_grad_norm": 1.0, "loss": 1.144123911857605, "grad_norm": 0.6131619215011597, "learning_rate": 2.8646748681898066e-05}
-{"ts": "2025-12-26T18:49:46", "event": "train_log", "step": 166, "epoch": 0.070042194092827, "progress_pct": 1.17, "epoch_pct": 1.17, "eta": "46:00:05", "max_grad_norm": 1.0, "loss": 1.1329256296157837, "grad_norm": 0.5749185681343079, "learning_rate": 2.8998242530755715e-05}
-{"ts": "2025-12-26T18:50:03", "event": "train_log", "step": 168, "epoch": 0.07088607594936709, "progress_pct": 1.18, "epoch_pct": 1.18, "eta": "45:49:46", "max_grad_norm": 1.0, "loss": 1.0892387628555298, "grad_norm": 0.5243118405342102, "learning_rate": 2.9349736379613356e-05}
-{"ts": "2025-12-26T18:50:17", "event": "train_log", "step": 170, "epoch": 0.07172995780590717, "progress_pct": 1.2, "epoch_pct": 1.2, "eta": "45:37:02", "max_grad_norm": 1.0, "loss": 1.163260817527771, "grad_norm": 0.7190104722976685, "learning_rate": 2.9701230228471005e-05}
-{"ts": "2025-12-26T18:50:33", "event": "train_log", "step": 172, "epoch": 0.07257383966244725, "progress_pct": 1.21, "epoch_pct": 1.21, "eta": "45:25:46", "max_grad_norm": 1.0, "loss": 1.0880777835845947, "grad_norm": 0.5486982464790344, "learning_rate": 3.0052724077328647e-05}
-{"ts": "2025-12-26T18:50:49", "event": "train_log", "step": 174, "epoch": 0.07341772151898734, "progress_pct": 1.22, "epoch_pct": 1.22, "eta": "45:16:37", "max_grad_norm": 1.0, "loss": 1.0433368682861328, "grad_norm": 0.5020889043807983, "learning_rate": 3.0404217926186295e-05}
-{"ts": "2025-12-26T18:51:05", "event": "train_log", "step": 176, "epoch": 0.07426160337552742, "progress_pct": 1.24, "epoch_pct": 1.24, "eta": "45:05:47", "max_grad_norm": 1.0, "loss": 1.0528991222381592, "grad_norm": 0.47329774498939514, "learning_rate": 3.075571177504394e-05}
-{"ts": "2025-12-26T18:51:20", "event": "train_log", "step": 178, "epoch": 0.0751054852320675, "progress_pct": 1.25, "epoch_pct": 1.25, "eta": "44:55:26", "max_grad_norm": 1.0, "loss": 1.1627811193466187, "grad_norm": 0.6635547876358032, "learning_rate": 3.110720562390158e-05}
-{"ts": "2025-12-26T18:51:36", "event": "train_log", "step": 180, "epoch": 0.0759493670886076, "progress_pct": 1.27, "epoch_pct": 1.27, "eta": "44:45:10", "max_grad_norm": 1.0, "loss": 1.084869384765625, "grad_norm": 0.5624618530273438, "learning_rate": 3.145869947275923e-05}
-{"ts": "2025-12-26T18:51:51", "event": "train_log", "step": 182, "epoch": 0.07679324894514768, "progress_pct": 1.28, "epoch_pct": 1.28, "eta": "44:34:28", "max_grad_norm": 1.0, "loss": 1.2227671146392822, "grad_norm": 0.6029536724090576, "learning_rate": 3.181019332161687e-05}
-{"ts": "2025-12-26T18:52:05", "event": "train_log", "step": 184, "epoch": 0.07763713080168777, "progress_pct": 1.29, "epoch_pct": 1.29, "eta": "44:23:43", "max_grad_norm": 1.0, "loss": 1.0955452919006348, "grad_norm": 0.930959939956665, "learning_rate": 3.216168717047452e-05}
-{"ts": "2025-12-26T18:52:21", "event": "train_log", "step": 186, "epoch": 0.07848101265822785, "progress_pct": 1.31, "epoch_pct": 1.31, "eta": "44:14:24", "max_grad_norm": 1.0, "loss": 1.0640798807144165, "grad_norm": 0.5326952338218689, "learning_rate": 3.251318101933216e-05}
-{"ts": "2025-12-26T18:52:36", "event": "train_log", "step": 188, "epoch": 0.07932489451476793, "progress_pct": 1.32, "epoch_pct": 1.32, "eta": "44:04:53", "max_grad_norm": 1.0, "loss": 1.0700589418411255, "grad_norm": 0.5484727621078491, "learning_rate": 3.286467486818981e-05}
-{"ts": "2025-12-26T18:52:51", "event": "train_log", "step": 190, "epoch": 0.08016877637130802, "progress_pct": 1.34, "epoch_pct": 1.34, "eta": "43:54:36", "max_grad_norm": 1.0, "loss": 1.1593081951141357, "grad_norm": 0.605273425579071, "learning_rate": 3.3216168717047456e-05}
-{"ts": "2025-12-26T18:53:05", "event": "train_log", "step": 192, "epoch": 0.0810126582278481, "progress_pct": 1.35, "epoch_pct": 1.35, "eta": "43:44:25", "max_grad_norm": 1.0, "loss": 1.1617076396942139, "grad_norm": 0.5704394578933716, "learning_rate": 3.35676625659051e-05}
-{"ts": "2025-12-26T18:53:21", "event": "train_log", "step": 194, "epoch": 0.08185654008438818, "progress_pct": 1.36, "epoch_pct": 1.36, "eta": "43:35:18", "max_grad_norm": 1.0, "loss": 1.1346839666366577, "grad_norm": 0.5929452180862427, "learning_rate": 3.3919156414762746e-05}
-{"ts": "2025-12-26T18:53:35", "event": "train_log", "step": 196, "epoch": 0.08270042194092828, "progress_pct": 1.38, "epoch_pct": 1.38, "eta": "43:25:58", "max_grad_norm": 1.0, "loss": 1.0934710502624512, "grad_norm": 0.5624077916145325, "learning_rate": 3.427065026362039e-05}
-{"ts": "2025-12-26T18:53:50", "event": "train_log", "step": 198, "epoch": 0.08354430379746836, "progress_pct": 1.39, "epoch_pct": 1.39, "eta": "43:16:01", "max_grad_norm": 1.0, "loss": 1.1810534000396729, "grad_norm": 0.6717425584793091, "learning_rate": 3.4622144112478036e-05}
-{"ts": "2025-12-26T18:54:05", "event": "train_log", "step": 200, "epoch": 0.08438818565400844, "progress_pct": 1.41, "epoch_pct": 1.41, "eta": "43:07:42", "max_grad_norm": 1.0, "loss": 1.1525514125823975, "grad_norm": 0.5120199918746948, "learning_rate": 3.4973637961335674e-05}
-{"ts": "2025-12-26T19:05:13", "event": "train_log", "step": 200, "epoch": 0.08438818565400844, "progress_pct": 1.41, "epoch_pct": 1.41, "eta": "56:08:25", "max_grad_norm": 1.0, "eval_loss": 1.142486810684204, "eval_runtime": 668.2356, "eval_samples_per_second": 3.153, "eval_steps_per_second": 3.153}
-{"ts": "2025-12-26T19:05:29", "event": "train_log", "step": 202, "epoch": 0.08523206751054853, "progress_pct": 1.42, "epoch_pct": 1.42, "eta": "55:52:50", "max_grad_norm": 1.0, "loss": 1.0243735313415527, "grad_norm": 0.5144487023353577, "learning_rate": 3.5325131810193326e-05}
-{"ts": "2025-12-26T19:05:44", "event": "train_log", "step": 204, "epoch": 0.08607594936708861, "progress_pct": 1.43, "epoch_pct": 1.43, "eta": "55:36:55", "max_grad_norm": 1.0, "loss": 1.118743896484375, "grad_norm": 0.6325069069862366, "learning_rate": 3.5676625659050964e-05}
-{"ts": "2025-12-26T19:06:00", "event": "train_log", "step": 206, "epoch": 0.08691983122362869, "progress_pct": 1.45, "epoch_pct": 1.45, "eta": "55:21:52", "max_grad_norm": 1.0, "loss": 1.0380504131317139, "grad_norm": 0.5501633882522583, "learning_rate": 3.6028119507908616e-05}
-{"ts": "2025-12-26T19:06:16", "event": "train_log", "step": 208, "epoch": 0.08776371308016878, "progress_pct": 1.46, "epoch_pct": 1.46, "eta": "55:07:35", "max_grad_norm": 1.0, "loss": 0.9837555885314941, "grad_norm": 0.6133899688720703, "learning_rate": 3.6379613356766254e-05}
-{"ts": "2025-12-26T19:06:31", "event": "train_log", "step": 210, "epoch": 0.08860759493670886, "progress_pct": 1.48, "epoch_pct": 1.48, "eta": "54:52:41", "max_grad_norm": 1.0, "loss": 1.090720295906067, "grad_norm": 0.5799810886383057, "learning_rate": 3.6731107205623906e-05}
-{"ts": "2025-12-26T19:06:47", "event": "train_log", "step": 212, "epoch": 0.08945147679324894, "progress_pct": 1.49, "epoch_pct": 1.49, "eta": "54:37:49", "max_grad_norm": 1.0, "loss": 1.120232343673706, "grad_norm": 0.6039511561393738, "learning_rate": 3.7082601054481544e-05}
-{"ts": "2025-12-26T19:07:01", "event": "train_log", "step": 214, "epoch": 0.09029535864978903, "progress_pct": 1.5, "epoch_pct": 1.5, "eta": "54:22:58", "max_grad_norm": 1.0, "loss": 1.096949815750122, "grad_norm": 0.5983024835586548, "learning_rate": 3.7434094903339196e-05}
-{"ts": "2025-12-26T19:07:17", "event": "train_log", "step": 216, "epoch": 0.09113924050632911, "progress_pct": 1.52, "epoch_pct": 1.52, "eta": "54:09:30", "max_grad_norm": 1.0, "loss": 1.1226298809051514, "grad_norm": 0.5641079545021057, "learning_rate": 3.7785588752196835e-05}
-{"ts": "2025-12-26T19:07:33", "event": "train_log", "step": 218, "epoch": 0.0919831223628692, "progress_pct": 1.53, "epoch_pct": 1.53, "eta": "53:55:26", "max_grad_norm": 1.0, "loss": 1.1260643005371094, "grad_norm": 0.655717134475708, "learning_rate": 3.8137082601054486e-05}
-{"ts": "2025-12-26T19:07:48", "event": "train_log", "step": 220, "epoch": 0.09282700421940929, "progress_pct": 1.55, "epoch_pct": 1.55, "eta": "53:42:00", "max_grad_norm": 1.0, "loss": 1.0777709484100342, "grad_norm": 0.6111898422241211, "learning_rate": 3.848857644991213e-05}
-{"ts": "2025-12-26T19:08:04", "event": "train_log", "step": 222, "epoch": 0.09367088607594937, "progress_pct": 1.56, "epoch_pct": 1.56, "eta": "53:29:16", "max_grad_norm": 1.0, "loss": 1.10588800907135, "grad_norm": 0.6821302771568298, "learning_rate": 3.884007029876977e-05}
-{"ts": "2025-12-26T19:08:19", "event": "train_log", "step": 224, "epoch": 0.09451476793248945, "progress_pct": 1.58, "epoch_pct": 1.58, "eta": "53:16:02", "max_grad_norm": 1.0, "loss": 1.1498671770095825, "grad_norm": 0.693175733089447, "learning_rate": 3.919156414762742e-05}
-{"ts": "2025-12-26T19:08:35", "event": "train_log", "step": 226, "epoch": 0.09535864978902954, "progress_pct": 1.59, "epoch_pct": 1.59, "eta": "53:03:34", "max_grad_norm": 1.0, "loss": 1.0587562322616577, "grad_norm": 0.5288166403770447, "learning_rate": 3.954305799648506e-05}
-{"ts": "2025-12-26T19:08:50", "event": "train_log", "step": 228, "epoch": 0.09620253164556962, "progress_pct": 1.6, "epoch_pct": 1.6, "eta": "52:50:35", "max_grad_norm": 1.0, "loss": 1.1107512712478638, "grad_norm": 0.6882867813110352, "learning_rate": 3.989455184534271e-05}
-{"ts": "2025-12-26T19:09:07", "event": "train_log", "step": 230, "epoch": 0.0970464135021097, "progress_pct": 1.62, "epoch_pct": 1.62, "eta": "52:40:01", "max_grad_norm": 1.0, "loss": 1.020510196685791, "grad_norm": 0.5834154486656189, "learning_rate": 4.024604569420035e-05}
-{"ts": "2025-12-26T19:09:22", "event": "train_log", "step": 232, "epoch": 0.09789029535864979, "progress_pct": 1.63, "epoch_pct": 1.63, "eta": "52:27:27", "max_grad_norm": 1.0, "loss": 1.0642449855804443, "grad_norm": 0.7157064080238342, "learning_rate": 4.0597539543058e-05}
-{"ts": "2025-12-26T19:09:39", "event": "train_log", "step": 234, "epoch": 0.09873417721518987, "progress_pct": 1.65, "epoch_pct": 1.65, "eta": "52:16:19", "max_grad_norm": 1.0, "loss": 1.0359872579574585, "grad_norm": 0.6530708074569702, "learning_rate": 4.094903339191564e-05}
-{"ts": "2025-12-26T19:09:53", "event": "train_log", "step": 236, "epoch": 0.09957805907172995, "progress_pct": 1.66, "epoch_pct": 1.66, "eta": "52:03:41", "max_grad_norm": 1.0, "loss": 1.050504446029663, "grad_norm": 0.6329686045646667, "learning_rate": 4.130052724077329e-05}
-{"ts": "2025-12-26T19:10:08", "event": "train_log", "step": 238, "epoch": 0.10042194092827005, "progress_pct": 1.67, "epoch_pct": 1.67, "eta": "51:51:35", "max_grad_norm": 1.0, "loss": 1.2621175050735474, "grad_norm": 0.6597026586532593, "learning_rate": 4.165202108963093e-05}
-{"ts": "2025-12-26T19:10:24", "event": "train_log", "step": 240, "epoch": 0.10126582278481013, "progress_pct": 1.69, "epoch_pct": 1.69, "eta": "51:41:04", "max_grad_norm": 1.0, "loss": 1.1218310594558716, "grad_norm": 0.6195225119590759, "learning_rate": 4.200351493848858e-05}
-{"ts": "2025-12-26T19:10:40", "event": "train_log", "step": 242, "epoch": 0.1021097046413502, "progress_pct": 1.7, "epoch_pct": 1.7, "eta": "51:29:35", "max_grad_norm": 1.0, "loss": 1.1250728368759155, "grad_norm": 0.6764137744903564, "learning_rate": 4.235500878734622e-05}
-{"ts": "2025-12-26T19:10:56", "event": "train_log", "step": 244, "epoch": 0.1029535864978903, "progress_pct": 1.72, "epoch_pct": 1.72, "eta": "51:19:19", "max_grad_norm": 1.0, "loss": 1.028212308883667, "grad_norm": 0.552363395690918, "learning_rate": 4.270650263620387e-05}
-{"ts": "2025-12-26T19:11:12", "event": "train_log", "step": 246, "epoch": 0.10379746835443038, "progress_pct": 1.73, "epoch_pct": 1.73, "eta": "51:09:20", "max_grad_norm": 1.0, "loss": 1.0425450801849365, "grad_norm": 0.5620495676994324, "learning_rate": 4.305799648506151e-05}
-{"ts": "2025-12-26T19:11:27", "event": "train_log", "step": 248, "epoch": 0.10464135021097046, "progress_pct": 1.74, "epoch_pct": 1.74, "eta": "50:57:59", "max_grad_norm": 1.0, "loss": 1.144278883934021, "grad_norm": 0.6860032081604004, "learning_rate": 4.3409490333919156e-05}
-{"ts": "2025-12-26T19:11:41", "event": "train_log", "step": 250, "epoch": 0.10548523206751055, "progress_pct": 1.76, "epoch_pct": 1.76, "eta": "50:46:30", "max_grad_norm": 1.0, "loss": 1.1223982572555542, "grad_norm": 0.6033259034156799, "learning_rate": 4.37609841827768e-05}
-{"ts": "2025-12-26T19:11:57", "event": "train_log", "step": 252, "epoch": 0.10632911392405063, "progress_pct": 1.77, "epoch_pct": 1.77, "eta": "50:36:22", "max_grad_norm": 1.0, "loss": 1.1609960794448853, "grad_norm": 0.6292146444320679, "learning_rate": 4.4112478031634446e-05}
-{"ts": "2025-12-26T19:12:12", "event": "train_log", "step": 254, "epoch": 0.10717299578059072, "progress_pct": 1.79, "epoch_pct": 1.79, "eta": "50:25:56", "max_grad_norm": 1.0, "loss": 1.063547968864441, "grad_norm": 0.7982883453369141, "learning_rate": 4.44639718804921e-05}
-{"ts": "2025-12-26T19:12:27", "event": "train_log", "step": 256, "epoch": 0.1080168776371308, "progress_pct": 1.8, "epoch_pct": 1.8, "eta": "50:14:56", "max_grad_norm": 1.0, "loss": 1.0719804763793945, "grad_norm": 0.7719110250473022, "learning_rate": 4.4815465729349736e-05}
-{"ts": "2025-12-26T19:12:43", "event": "train_log", "step": 258, "epoch": 0.10886075949367088, "progress_pct": 1.81, "epoch_pct": 1.81, "eta": "50:05:41", "max_grad_norm": 1.0, "loss": 1.0778400897979736, "grad_norm": 0.6101011633872986, "learning_rate": 4.516695957820739e-05}
-{"ts": "2025-12-26T19:12:58", "event": "train_log", "step": 260, "epoch": 0.10970464135021098, "progress_pct": 1.83, "epoch_pct": 1.83, "eta": "49:55:27", "max_grad_norm": 1.0, "loss": 1.2129558324813843, "grad_norm": 0.7300994396209717, "learning_rate": 4.5518453427065026e-05}
-{"ts": "2025-12-26T19:13:13", "event": "train_log", "step": 262, "epoch": 0.11054852320675106, "progress_pct": 1.84, "epoch_pct": 1.84, "eta": "49:45:54", "max_grad_norm": 1.0, "loss": 1.221714735031128, "grad_norm": 0.8348747491836548, "learning_rate": 4.586994727592268e-05}
-{"ts": "2025-12-26T19:13:28", "event": "train_log", "step": 264, "epoch": 0.11139240506329114, "progress_pct": 1.86, "epoch_pct": 1.86, "eta": "49:36:28", "max_grad_norm": 1.0, "loss": 1.0187978744506836, "grad_norm": 0.5445612072944641, "learning_rate": 4.6221441124780316e-05}
-{"ts": "2025-12-26T19:13:45", "event": "train_log", "step": 266, "epoch": 0.11223628691983123, "progress_pct": 1.87, "epoch_pct": 1.87, "eta": "49:28:20", "max_grad_norm": 1.0, "loss": 1.096561312675476, "grad_norm": 0.6230319738388062, "learning_rate": 4.657293497363797e-05}
-{"ts": "2025-12-26T19:14:02", "event": "train_log", "step": 268, "epoch": 0.11308016877637131, "progress_pct": 1.88, "epoch_pct": 1.88, "eta": "49:20:11", "max_grad_norm": 1.0, "loss": 1.089842438697815, "grad_norm": 0.6231237649917603, "learning_rate": 4.6924428822495606e-05}
-{"ts": "2025-12-26T19:14:16", "event": "train_log", "step": 270, "epoch": 0.11392405063291139, "progress_pct": 1.9, "epoch_pct": 1.9, "eta": "49:10:11", "max_grad_norm": 1.0, "loss": 1.0696645975112915, "grad_norm": 0.7178627252578735, "learning_rate": 4.727592267135325e-05}
-{"ts": "2025-12-26T19:14:32", "event": "train_log", "step": 272, "epoch": 0.11476793248945148, "progress_pct": 1.91, "epoch_pct": 1.91, "eta": "49:01:48", "max_grad_norm": 1.0, "loss": 1.0511361360549927, "grad_norm": 0.6895854473114014, "learning_rate": 4.7627416520210896e-05}
-{"ts": "2025-12-26T19:14:48", "event": "train_log", "step": 274, "epoch": 0.11561181434599156, "progress_pct": 1.93, "epoch_pct": 1.93, "eta": "48:53:38", "max_grad_norm": 1.0, "loss": 1.1373958587646484, "grad_norm": 0.6046878695487976, "learning_rate": 4.797891036906854e-05}
-{"ts": "2025-12-26T19:15:04", "event": "train_log", "step": 276, "epoch": 0.11645569620253164, "progress_pct": 1.94, "epoch_pct": 1.94, "eta": "48:44:50", "max_grad_norm": 1.0, "loss": 1.0734186172485352, "grad_norm": 0.6524552702903748, "learning_rate": 4.833040421792619e-05}
-{"ts": "2025-12-26T19:15:19", "event": "train_log", "step": 278, "epoch": 0.11729957805907174, "progress_pct": 1.95, "epoch_pct": 1.95, "eta": "48:36:17", "max_grad_norm": 1.0, "loss": 1.123913049697876, "grad_norm": 0.6331019997596741, "learning_rate": 4.868189806678383e-05}
-{"ts": "2025-12-26T19:15:34", "event": "train_log", "step": 280, "epoch": 0.11814345991561181, "progress_pct": 1.97, "epoch_pct": 1.97, "eta": "48:27:43", "max_grad_norm": 1.0, "loss": 1.0635710954666138, "grad_norm": 0.5919018983840942, "learning_rate": 4.903339191564148e-05}
-{"ts": "2025-12-26T19:15:52", "event": "train_log", "step": 282, "epoch": 0.1189873417721519, "progress_pct": 1.98, "epoch_pct": 1.98, "eta": "48:20:49", "max_grad_norm": 1.0, "loss": 1.0429247617721558, "grad_norm": 0.6067633032798767, "learning_rate": 4.938488576449912e-05}
-{"ts": "2025-12-26T19:16:07", "event": "train_log", "step": 284, "epoch": 0.11983122362869199, "progress_pct": 2.0, "epoch_pct": 2.0, "eta": "48:12:20", "max_grad_norm": 1.0, "loss": 1.1397464275360107, "grad_norm": 0.6583750247955322, "learning_rate": 4.9736379613356774e-05}
-{"ts": "2025-12-26T19:16:23", "event": "train_log", "step": 286, "epoch": 0.12067510548523207, "progress_pct": 2.01, "epoch_pct": 2.01, "eta": "48:04:38", "max_grad_norm": 1.0, "loss": 1.0590803623199463, "grad_norm": 0.6200069785118103, "learning_rate": 5.008787346221442e-05}
-{"ts": "2025-12-26T19:16:38", "event": "train_log", "step": 288, "epoch": 0.12151898734177215, "progress_pct": 2.03, "epoch_pct": 2.03, "eta": "47:56:39", "max_grad_norm": 1.0, "loss": 1.1318789720535278, "grad_norm": 0.6798665523529053, "learning_rate": 5.0439367311072064e-05}
-{"ts": "2025-12-26T19:16:55", "event": "train_log", "step": 290, "epoch": 0.12236286919831224, "progress_pct": 2.04, "epoch_pct": 2.04, "eta": "47:49:56", "max_grad_norm": 1.0, "loss": 1.0934956073760986, "grad_norm": 0.7508794069290161, "learning_rate": 5.07908611599297e-05}
-{"ts": "2025-12-26T19:17:10", "event": "train_log", "step": 292, "epoch": 0.12320675105485232, "progress_pct": 2.05, "epoch_pct": 2.05, "eta": "47:42:06", "max_grad_norm": 1.0, "loss": 1.163407802581787, "grad_norm": 0.6901452541351318, "learning_rate": 5.114235500878735e-05}
-{"ts": "2025-12-26T19:17:25", "event": "train_log", "step": 294, "epoch": 0.1240506329113924, "progress_pct": 2.07, "epoch_pct": 2.07, "eta": "47:34:06", "max_grad_norm": 1.0, "loss": 1.09059476852417, "grad_norm": 0.6423285603523254, "learning_rate": 5.1493848857644985e-05}
-{"ts": "2025-12-26T19:17:42", "event": "train_log", "step": 296, "epoch": 0.1248945147679325, "progress_pct": 2.08, "epoch_pct": 2.08, "eta": "47:27:04", "max_grad_norm": 1.0, "loss": 1.0690211057662964, "grad_norm": 0.6839275360107422, "learning_rate": 5.1845342706502644e-05}
-{"ts": "2025-12-26T19:17:58", "event": "train_log", "step": 298, "epoch": 0.1257383966244726, "progress_pct": 2.1, "epoch_pct": 2.1, "eta": "47:20:03", "max_grad_norm": 1.0, "loss": 0.982322096824646, "grad_norm": 0.6350128054618835, "learning_rate": 5.219683655536028e-05}
-{"ts": "2025-12-26T19:18:12", "event": "train_log", "step": 300, "epoch": 0.12658227848101267, "progress_pct": 2.11, "epoch_pct": 2.11, "eta": "47:12:00", "max_grad_norm": 1.0, "loss": 1.1132930517196655, "grad_norm": 0.7136530876159668, "learning_rate": 5.254833040421793e-05}
-{"ts": "2025-12-26T19:29:29", "event": "train_log", "step": 300, "epoch": 0.12658227848101267, "progress_pct": 2.11, "epoch_pct": 2.11, "eta": "55:55:36", "max_grad_norm": 1.0, "eval_loss": 1.0952109098434448, "eval_runtime": 677.0652, "eval_samples_per_second": 3.112, "eval_steps_per_second": 3.112}
-{"ts": "2025-12-26T19:29:45", "event": "train_log", "step": 302, "epoch": 0.12742616033755275, "progress_pct": 2.12, "epoch_pct": 2.12, "eta": "55:44:49", "max_grad_norm": 1.0, "loss": 0.973595917224884, "grad_norm": 0.7339721322059631, "learning_rate": 5.289982425307557e-05}
-{"ts": "2025-12-26T19:30:00", "event": "train_log", "step": 304, "epoch": 0.12827004219409283, "progress_pct": 2.14, "epoch_pct": 2.14, "eta": "55:33:54", "max_grad_norm": 1.0, "loss": 0.9819849729537964, "grad_norm": 0.5941481590270996, "learning_rate": 5.3251318101933224e-05}
-{"ts": "2025-12-26T19:30:15", "event": "train_log", "step": 306, "epoch": 0.1291139240506329, "progress_pct": 2.15, "epoch_pct": 2.15, "eta": "55:23:03", "max_grad_norm": 1.0, "loss": 1.0315470695495605, "grad_norm": 0.7153938412666321, "learning_rate": 5.360281195079086e-05}
-{"ts": "2025-12-26T19:30:31", "event": "train_log", "step": 308, "epoch": 0.12995780590717299, "progress_pct": 2.17, "epoch_pct": 2.17, "eta": "55:13:01", "max_grad_norm": 1.0, "loss": 0.9492001533508301, "grad_norm": 0.5167180299758911, "learning_rate": 5.395430579964851e-05}
-{"ts": "2025-12-26T19:30:46", "event": "train_log", "step": 310, "epoch": 0.1308016877637131, "progress_pct": 2.18, "epoch_pct": 2.18, "eta": "55:02:21", "max_grad_norm": 1.0, "loss": 1.0156209468841553, "grad_norm": 0.6055944561958313, "learning_rate": 5.430579964850615e-05}
-{"ts": "2025-12-26T19:31:00", "event": "train_log", "step": 312, "epoch": 0.13164556962025317, "progress_pct": 2.19, "epoch_pct": 2.19, "eta": "54:51:12", "max_grad_norm": 1.0, "loss": 1.1791651248931885, "grad_norm": 0.7662386298179626, "learning_rate": 5.4657293497363805e-05}
-{"ts": "2025-12-26T19:31:16", "event": "train_log", "step": 314, "epoch": 0.13248945147679325, "progress_pct": 2.21, "epoch_pct": 2.21, "eta": "54:41:26", "max_grad_norm": 1.0, "loss": 1.0009297132492065, "grad_norm": 0.6065546274185181, "learning_rate": 5.500878734622145e-05}
-{"ts": "2025-12-26T19:31:31", "event": "train_log", "step": 316, "epoch": 0.13333333333333333, "progress_pct": 2.22, "epoch_pct": 2.22, "eta": "54:31:32", "max_grad_norm": 1.0, "loss": 1.0208244323730469, "grad_norm": 0.604225754737854, "learning_rate": 5.536028119507909e-05}
-{"ts": "2025-12-26T19:31:47", "event": "train_log", "step": 318, "epoch": 0.1341772151898734, "progress_pct": 2.24, "epoch_pct": 2.24, "eta": "54:21:35", "max_grad_norm": 1.0, "loss": 0.9968416690826416, "grad_norm": 0.6186763048171997, "learning_rate": 5.571177504393673e-05}
-{"ts": "2025-12-26T19:32:02", "event": "train_log", "step": 320, "epoch": 0.1350210970464135, "progress_pct": 2.25, "epoch_pct": 2.25, "eta": "54:11:46", "max_grad_norm": 1.0, "loss": 0.9540256857872009, "grad_norm": 0.7100363969802856, "learning_rate": 5.606326889279437e-05}
-{"ts": "2025-12-26T19:32:16", "event": "train_log", "step": 322, "epoch": 0.1358649789029536, "progress_pct": 2.26, "epoch_pct": 2.26, "eta": "54:01:33", "max_grad_norm": 1.0, "loss": 1.0631953477859497, "grad_norm": 0.6979711055755615, "learning_rate": 5.641476274165203e-05}
-{"ts": "2025-12-26T19:32:32", "event": "train_log", "step": 324, "epoch": 0.13670886075949368, "progress_pct": 2.28, "epoch_pct": 2.28, "eta": "53:52:08", "max_grad_norm": 1.0, "loss": 1.0170501470565796, "grad_norm": 0.6237109303474426, "learning_rate": 5.676625659050967e-05}
-{"ts": "2025-12-26T19:32:48", "event": "train_log", "step": 326, "epoch": 0.13755274261603376, "progress_pct": 2.29, "epoch_pct": 2.29, "eta": "53:43:14", "max_grad_norm": 1.0, "loss": 1.0715603828430176, "grad_norm": 0.6525548696517944, "learning_rate": 5.711775043936731e-05}
-{"ts": "2025-12-26T19:33:03", "event": "train_log", "step": 328, "epoch": 0.13839662447257384, "progress_pct": 2.31, "epoch_pct": 2.31, "eta": "53:33:47", "max_grad_norm": 1.0, "loss": 1.0111541748046875, "grad_norm": 0.6869221329689026, "learning_rate": 5.746924428822495e-05}
-{"ts": "2025-12-26T19:33:18", "event": "train_log", "step": 330, "epoch": 0.13924050632911392, "progress_pct": 2.32, "epoch_pct": 2.32, "eta": "53:24:42", "max_grad_norm": 1.0, "loss": 1.0311682224273682, "grad_norm": 0.553188145160675, "learning_rate": 5.782073813708261e-05}
-{"ts": "2025-12-26T19:33:33", "event": "train_log", "step": 332, "epoch": 0.140084388185654, "progress_pct": 2.33, "epoch_pct": 2.33, "eta": "53:15:19", "max_grad_norm": 1.0, "loss": 1.0213634967803955, "grad_norm": 0.6760852932929993, "learning_rate": 5.817223198594025e-05}
-{"ts": "2025-12-26T19:33:49", "event": "train_log", "step": 334, "epoch": 0.1409282700421941, "progress_pct": 2.35, "epoch_pct": 2.35, "eta": "53:06:28", "max_grad_norm": 1.0, "loss": 0.9748594164848328, "grad_norm": 0.5907419919967651, "learning_rate": 5.8523725834797894e-05}
-{"ts": "2025-12-26T19:34:03", "event": "train_log", "step": 336, "epoch": 0.14177215189873418, "progress_pct": 2.36, "epoch_pct": 2.36, "eta": "52:56:30", "max_grad_norm": 1.0, "loss": 1.05863356590271, "grad_norm": 0.7044920921325684, "learning_rate": 5.887521968365554e-05}
-{"ts": "2025-12-26T19:34:17", "event": "train_log", "step": 338, "epoch": 0.14261603375527426, "progress_pct": 2.38, "epoch_pct": 2.38, "eta": "52:47:06", "max_grad_norm": 1.0, "loss": 1.1341127157211304, "grad_norm": 0.679073691368103, "learning_rate": 5.922671353251318e-05}
-{"ts": "2025-12-26T19:34:32", "event": "train_log", "step": 340, "epoch": 0.14345991561181434, "progress_pct": 2.39, "epoch_pct": 2.39, "eta": "52:38:12", "max_grad_norm": 1.0, "loss": 0.9540836215019226, "grad_norm": 0.7676237225532532, "learning_rate": 5.957820738137083e-05}
-{"ts": "2025-12-26T19:34:47", "event": "train_log", "step": 342, "epoch": 0.14430379746835442, "progress_pct": 2.41, "epoch_pct": 2.41, "eta": "52:29:26", "max_grad_norm": 1.0, "loss": 1.0585911273956299, "grad_norm": 0.6313899755477905, "learning_rate": 5.9929701230228474e-05}
-{"ts": "2025-12-26T19:35:02", "event": "train_log", "step": 344, "epoch": 0.1451476793248945, "progress_pct": 2.42, "epoch_pct": 2.42, "eta": "52:20:40", "max_grad_norm": 1.0, "loss": 1.0760118961334229, "grad_norm": 0.7123099565505981, "learning_rate": 6.028119507908612e-05}
-{"ts": "2025-12-26T19:35:17", "event": "train_log", "step": 346, "epoch": 0.1459915611814346, "progress_pct": 2.43, "epoch_pct": 2.43, "eta": "52:12:28", "max_grad_norm": 1.0, "loss": 1.036866307258606, "grad_norm": 0.585935652256012, "learning_rate": 6.063268892794376e-05}
-{"ts": "2025-12-26T19:35:32", "event": "train_log", "step": 348, "epoch": 0.1468354430379747, "progress_pct": 2.45, "epoch_pct": 2.45, "eta": "52:03:40", "max_grad_norm": 1.0, "loss": 1.0242938995361328, "grad_norm": 0.5643263459205627, "learning_rate": 6.0984182776801416e-05}
-{"ts": "2025-12-26T19:35:47", "event": "train_log", "step": 350, "epoch": 0.14767932489451477, "progress_pct": 2.46, "epoch_pct": 2.46, "eta": "51:55:02", "max_grad_norm": 1.0, "loss": 1.0497376918792725, "grad_norm": 0.626761794090271, "learning_rate": 6.133567662565906e-05}
-{"ts": "2025-12-26T19:36:03", "event": "train_log", "step": 352, "epoch": 0.14852320675105485, "progress_pct": 2.48, "epoch_pct": 2.48, "eta": "51:47:28", "max_grad_norm": 1.0, "loss": 0.9811885356903076, "grad_norm": 0.5106956958770752, "learning_rate": 6.16871704745167e-05}
-{"ts": "2025-12-26T19:36:19", "event": "train_log", "step": 354, "epoch": 0.14936708860759493, "progress_pct": 2.49, "epoch_pct": 2.49, "eta": "51:40:08", "max_grad_norm": 1.0, "loss": 1.0715330839157104, "grad_norm": 0.6948089003562927, "learning_rate": 6.203866432337434e-05}
-{"ts": "2025-12-26T19:36:35", "event": "train_log", "step": 356, "epoch": 0.150210970464135, "progress_pct": 2.5, "epoch_pct": 2.5, "eta": "51:32:27", "max_grad_norm": 1.0, "loss": 1.0405226945877075, "grad_norm": 0.699713945388794, "learning_rate": 6.239015817223199e-05}
-{"ts": "2025-12-26T19:36:51", "event": "train_log", "step": 358, "epoch": 0.15105485232067511, "progress_pct": 2.52, "epoch_pct": 2.52, "eta": "51:25:30", "max_grad_norm": 1.0, "loss": 1.0490930080413818, "grad_norm": 0.6437667012214661, "learning_rate": 6.274165202108964e-05}
-{"ts": "2025-12-26T19:37:07", "event": "train_log", "step": 360, "epoch": 0.1518987341772152, "progress_pct": 2.53, "epoch_pct": 2.53, "eta": "51:17:47", "max_grad_norm": 1.0, "loss": 0.9267548322677612, "grad_norm": 0.6952699422836304, "learning_rate": 6.309314586994728e-05}
-{"ts": "2025-12-26T19:37:22", "event": "train_log", "step": 362, "epoch": 0.15274261603375527, "progress_pct": 2.55, "epoch_pct": 2.55, "eta": "51:10:08", "max_grad_norm": 1.0, "loss": 1.0427420139312744, "grad_norm": 0.6713186502456665, "learning_rate": 6.344463971880492e-05}
-{"ts": "2025-12-26T19:37:38", "event": "train_log", "step": 364, "epoch": 0.15358649789029535, "progress_pct": 2.56, "epoch_pct": 2.56, "eta": "51:02:50", "max_grad_norm": 1.0, "loss": 1.048950433731079, "grad_norm": 0.6750379800796509, "learning_rate": 6.379613356766257e-05}
-{"ts": "2025-12-26T19:37:54", "event": "train_log", "step": 366, "epoch": 0.15443037974683543, "progress_pct": 2.57, "epoch_pct": 2.57, "eta": "50:55:57", "max_grad_norm": 1.0, "loss": 1.0156004428863525, "grad_norm": 0.6053379774093628, "learning_rate": 6.414762741652022e-05}
-{"ts": "2025-12-26T19:38:10", "event": "train_log", "step": 368, "epoch": 0.15527426160337554, "progress_pct": 2.59, "epoch_pct": 2.59, "eta": "50:48:36", "max_grad_norm": 1.0, "loss": 1.0020819902420044, "grad_norm": 0.8063633441925049, "learning_rate": 6.449912126537786e-05}
-{"ts": "2025-12-26T19:38:26", "event": "train_log", "step": 370, "epoch": 0.15611814345991562, "progress_pct": 2.6, "epoch_pct": 2.6, "eta": "50:41:51", "max_grad_norm": 1.0, "loss": 1.055633783340454, "grad_norm": 0.8027494549751282, "learning_rate": 6.48506151142355e-05}
-{"ts": "2025-12-26T19:38:42", "event": "train_log", "step": 372, "epoch": 0.1569620253164557, "progress_pct": 2.62, "epoch_pct": 2.62, "eta": "50:35:05", "max_grad_norm": 1.0, "loss": 1.0149940252304077, "grad_norm": 0.6580121517181396, "learning_rate": 6.520210896309315e-05}
-{"ts": "2025-12-26T19:38:58", "event": "train_log", "step": 374, "epoch": 0.15780590717299578, "progress_pct": 2.63, "epoch_pct": 2.63, "eta": "50:28:07", "max_grad_norm": 1.0, "loss": 0.9769611954689026, "grad_norm": 0.6561233997344971, "learning_rate": 6.55536028119508e-05}
-{"ts": "2025-12-26T19:39:16", "event": "train_log", "step": 376, "epoch": 0.15864978902953586, "progress_pct": 2.64, "epoch_pct": 2.64, "eta": "50:22:50", "max_grad_norm": 1.0, "loss": 0.9099349975585938, "grad_norm": 0.6444346308708191, "learning_rate": 6.590509666080844e-05}
-{"ts": "2025-12-26T19:39:32", "event": "train_log", "step": 378, "epoch": 0.15949367088607594, "progress_pct": 2.66, "epoch_pct": 2.66, "eta": "50:16:06", "max_grad_norm": 1.0, "loss": 1.0797548294067383, "grad_norm": 0.5879359245300293, "learning_rate": 6.625659050966608e-05}
-{"ts": "2025-12-26T19:39:47", "event": "train_log", "step": 380, "epoch": 0.16033755274261605, "progress_pct": 2.67, "epoch_pct": 2.67, "eta": "50:08:50", "max_grad_norm": 1.0, "loss": 1.0336791276931763, "grad_norm": 0.6994144916534424, "learning_rate": 6.660808435852373e-05}
-{"ts": "2025-12-26T19:40:03", "event": "train_log", "step": 382, "epoch": 0.16118143459915613, "progress_pct": 2.69, "epoch_pct": 2.69, "eta": "50:02:10", "max_grad_norm": 1.0, "loss": 1.018118143081665, "grad_norm": 0.6128669381141663, "learning_rate": 6.695957820738138e-05}
-{"ts": "2025-12-26T19:40:18", "event": "train_log", "step": 384, "epoch": 0.1620253164556962, "progress_pct": 2.7, "epoch_pct": 2.7, "eta": "49:55:31", "max_grad_norm": 1.0, "loss": 1.1405497789382935, "grad_norm": 1.0237540006637573, "learning_rate": 6.731107205623902e-05}
-{"ts": "2025-12-26T19:40:35", "event": "train_log", "step": 386, "epoch": 0.16286919831223629, "progress_pct": 2.71, "epoch_pct": 2.71, "eta": "49:49:24", "max_grad_norm": 1.0, "loss": 1.0314189195632935, "grad_norm": 0.6091578006744385, "learning_rate": 6.766256590509666e-05}
-{"ts": "2025-12-26T19:40:52", "event": "train_log", "step": 388, "epoch": 0.16371308016877636, "progress_pct": 2.73, "epoch_pct": 2.73, "eta": "49:43:57", "max_grad_norm": 1.0, "loss": 0.9564052820205688, "grad_norm": 0.5916037559509277, "learning_rate": 6.801405975395431e-05}
-{"ts": "2025-12-26T19:41:08", "event": "train_log", "step": 390, "epoch": 0.16455696202531644, "progress_pct": 2.74, "epoch_pct": 2.74, "eta": "49:37:22", "max_grad_norm": 1.0, "loss": 1.0023859739303589, "grad_norm": 0.771653950214386, "learning_rate": 6.836555360281195e-05}
-{"ts": "2025-12-26T19:41:23", "event": "train_log", "step": 392, "epoch": 0.16540084388185655, "progress_pct": 2.76, "epoch_pct": 2.76, "eta": "49:30:32", "max_grad_norm": 1.0, "loss": 1.07024085521698, "grad_norm": 0.654658317565918, "learning_rate": 6.87170474516696e-05}
-{"ts": "2025-12-26T19:41:38", "event": "train_log", "step": 394, "epoch": 0.16624472573839663, "progress_pct": 2.77, "epoch_pct": 2.77, "eta": "49:23:51", "max_grad_norm": 1.0, "loss": 1.0552500486373901, "grad_norm": 0.6611968874931335, "learning_rate": 6.906854130052724e-05}
-{"ts": "2025-12-26T19:41:53", "event": "train_log", "step": 396, "epoch": 0.1670886075949367, "progress_pct": 2.78, "epoch_pct": 2.78, "eta": "49:17:24", "max_grad_norm": 1.0, "loss": 1.0562875270843506, "grad_norm": 0.6955893039703369, "learning_rate": 6.942003514938489e-05}
-{"ts": "2025-12-26T19:42:08", "event": "train_log", "step": 398, "epoch": 0.1679324894514768, "progress_pct": 2.8, "epoch_pct": 2.8, "eta": "49:10:51", "max_grad_norm": 1.0, "loss": 0.9850592017173767, "grad_norm": 0.6666058301925659, "learning_rate": 6.977152899824253e-05}
-{"ts": "2025-12-26T19:42:24", "event": "train_log", "step": 400, "epoch": 0.16877637130801687, "progress_pct": 2.81, "epoch_pct": 2.81, "eta": "49:04:38", "max_grad_norm": 1.0, "loss": 1.0077755451202393, "grad_norm": 0.6131711006164551, "learning_rate": 7.012302284710018e-05}
-{"ts": "2025-12-26T19:53:55", "event": "train_log", "step": 400, "epoch": 0.16877637130801687, "progress_pct": 2.81, "epoch_pct": 2.81, "eta": "55:42:32", "max_grad_norm": 1.0, "eval_loss": 1.0625108480453491, "eval_runtime": 691.0068, "eval_samples_per_second": 3.049, "eval_steps_per_second": 3.049}
-{"ts": "2025-12-26T19:54:10", "event": "train_log", "step": 402, "epoch": 0.16962025316455695, "progress_pct": 2.83, "epoch_pct": 2.83, "eta": "55:33:53", "max_grad_norm": 1.0, "loss": 1.1012427806854248, "grad_norm": 0.6286499500274658, "learning_rate": 7.047451669595783e-05}
-{"ts": "2025-12-26T19:54:25", "event": "train_log", "step": 404, "epoch": 0.17046413502109706, "progress_pct": 2.84, "epoch_pct": 2.84, "eta": "55:25:32", "max_grad_norm": 1.0, "loss": 1.0379719734191895, "grad_norm": 0.6639351844787598, "learning_rate": 7.082601054481547e-05}
-{"ts": "2025-12-26T19:54:40", "event": "train_log", "step": 406, "epoch": 0.17130801687763714, "progress_pct": 2.86, "epoch_pct": 2.86, "eta": "55:17:01", "max_grad_norm": 1.0, "loss": 1.031856656074524, "grad_norm": 0.750401496887207, "learning_rate": 7.117750439367311e-05}
-{"ts": "2025-12-26T19:54:53", "event": "train_log", "step": 408, "epoch": 0.17215189873417722, "progress_pct": 2.87, "epoch_pct": 2.87, "eta": "55:08:10", "max_grad_norm": 1.0, "loss": 1.0493193864822388, "grad_norm": 0.8084847331047058, "learning_rate": 7.152899824253075e-05}
-{"ts": "2025-12-26T19:55:09", "event": "train_log", "step": 410, "epoch": 0.1729957805907173, "progress_pct": 2.88, "epoch_pct": 2.88, "eta": "55:00:00", "max_grad_norm": 1.0, "loss": 1.1012418270111084, "grad_norm": 0.7448462247848511, "learning_rate": 7.188049209138841e-05}
-{"ts": "2025-12-26T19:55:24", "event": "train_log", "step": 412, "epoch": 0.17383966244725738, "progress_pct": 2.9, "epoch_pct": 2.9, "eta": "54:52:18", "max_grad_norm": 1.0, "loss": 0.9926692247390747, "grad_norm": 0.5841867923736572, "learning_rate": 7.223198594024605e-05}
-{"ts": "2025-12-26T19:55:39", "event": "train_log", "step": 414, "epoch": 0.17468354430379746, "progress_pct": 2.91, "epoch_pct": 2.91, "eta": "54:44:09", "max_grad_norm": 1.0, "loss": 1.0588877201080322, "grad_norm": 0.7125606536865234, "learning_rate": 7.258347978910369e-05}
-{"ts": "2025-12-26T19:55:54", "event": "train_log", "step": 416, "epoch": 0.17552742616033756, "progress_pct": 2.93, "epoch_pct": 2.93, "eta": "54:36:25", "max_grad_norm": 1.0, "loss": 1.038270354270935, "grad_norm": 0.5750942230224609, "learning_rate": 7.293497363796134e-05}
-{"ts": "2025-12-26T19:56:10", "event": "train_log", "step": 418, "epoch": 0.17637130801687764, "progress_pct": 2.94, "epoch_pct": 2.94, "eta": "54:28:45", "max_grad_norm": 1.0, "loss": 0.9843021035194397, "grad_norm": 0.565444827079773, "learning_rate": 7.328646748681899e-05}
-{"ts": "2025-12-26T19:56:25", "event": "train_log", "step": 420, "epoch": 0.17721518987341772, "progress_pct": 2.95, "epoch_pct": 2.95, "eta": "54:21:02", "max_grad_norm": 1.0, "loss": 1.0731632709503174, "grad_norm": 0.5825693011283875, "learning_rate": 7.363796133567663e-05}
-{"ts": "2025-12-26T19:56:40", "event": "train_log", "step": 422, "epoch": 0.1780590717299578, "progress_pct": 2.97, "epoch_pct": 2.97, "eta": "54:13:08", "max_grad_norm": 1.0, "loss": 1.0061273574829102, "grad_norm": 0.6267391443252563, "learning_rate": 7.398945518453427e-05}
-{"ts": "2025-12-26T19:56:54", "event": "train_log", "step": 424, "epoch": 0.17890295358649788, "progress_pct": 2.98, "epoch_pct": 2.98, "eta": "54:05:00", "max_grad_norm": 1.0, "loss": 1.0461612939834595, "grad_norm": 0.6621372103691101, "learning_rate": 7.434094903339192e-05}
-{"ts": "2025-12-26T19:57:09", "event": "train_log", "step": 426, "epoch": 0.17974683544303796, "progress_pct": 3.0, "epoch_pct": 3.0, "eta": "53:57:21", "max_grad_norm": 1.0, "loss": 0.9789207577705383, "grad_norm": 0.6635435223579407, "learning_rate": 7.469244288224957e-05}
-{"ts": "2025-12-26T19:57:23", "event": "train_log", "step": 428, "epoch": 0.18059071729957807, "progress_pct": 3.01, "epoch_pct": 3.01, "eta": "53:49:30", "max_grad_norm": 1.0, "loss": 1.0527069568634033, "grad_norm": 0.6342346668243408, "learning_rate": 7.504393673110721e-05}
-{"ts": "2025-12-26T19:57:39", "event": "train_log", "step": 430, "epoch": 0.18143459915611815, "progress_pct": 3.02, "epoch_pct": 3.02, "eta": "53:42:34", "max_grad_norm": 1.0, "loss": 0.9708702564239502, "grad_norm": 0.6762149930000305, "learning_rate": 7.539543057996485e-05}
-{"ts": "2025-12-26T19:57:54", "event": "train_log", "step": 432, "epoch": 0.18227848101265823, "progress_pct": 3.04, "epoch_pct": 3.04, "eta": "53:35:00", "max_grad_norm": 1.0, "loss": 1.0509834289550781, "grad_norm": 0.7073282599449158, "learning_rate": 7.57469244288225e-05}
-{"ts": "2025-12-26T19:58:09", "event": "train_log", "step": 434, "epoch": 0.1831223628691983, "progress_pct": 3.05, "epoch_pct": 3.05, "eta": "53:27:34", "max_grad_norm": 1.0, "loss": 1.0128819942474365, "grad_norm": 0.6917856931686401, "learning_rate": 7.609841827768014e-05}
-{"ts": "2025-12-26T19:58:25", "event": "train_log", "step": 436, "epoch": 0.1839662447257384, "progress_pct": 3.07, "epoch_pct": 3.07, "eta": "53:21:04", "max_grad_norm": 1.0, "loss": 0.989395797252655, "grad_norm": 0.5574942231178284, "learning_rate": 7.644991212653779e-05}
-{"ts": "2025-12-26T19:58:41", "event": "train_log", "step": 438, "epoch": 0.1848101265822785, "progress_pct": 3.08, "epoch_pct": 3.08, "eta": "53:14:12", "max_grad_norm": 1.0, "loss": 0.9846042990684509, "grad_norm": 0.640765905380249, "learning_rate": 7.680140597539543e-05}
-{"ts": "2025-12-26T19:58:56", "event": "train_log", "step": 440, "epoch": 0.18565400843881857, "progress_pct": 3.09, "epoch_pct": 3.09, "eta": "53:06:51", "max_grad_norm": 1.0, "loss": 1.0344442129135132, "grad_norm": 0.6699127554893494, "learning_rate": 7.715289982425308e-05}
-{"ts": "2025-12-26T19:59:11", "event": "train_log", "step": 442, "epoch": 0.18649789029535865, "progress_pct": 3.11, "epoch_pct": 3.11, "eta": "53:00:08", "max_grad_norm": 1.0, "loss": 1.0179373025894165, "grad_norm": 0.6164930462837219, "learning_rate": 7.750439367311072e-05}
-{"ts": "2025-12-26T19:59:26", "event": "train_log", "step": 444, "epoch": 0.18734177215189873, "progress_pct": 3.12, "epoch_pct": 3.12, "eta": "52:53:05", "max_grad_norm": 1.0, "loss": 1.0518895387649536, "grad_norm": 0.6880720853805542, "learning_rate": 7.785588752196837e-05}
-{"ts": "2025-12-26T19:59:41", "event": "train_log", "step": 446, "epoch": 0.1881856540084388, "progress_pct": 3.14, "epoch_pct": 3.14, "eta": "52:45:49", "max_grad_norm": 1.0, "loss": 1.0442606210708618, "grad_norm": 0.6501413583755493, "learning_rate": 7.820738137082601e-05}
-{"ts": "2025-12-26T19:59:55", "event": "train_log", "step": 448, "epoch": 0.1890295358649789, "progress_pct": 3.15, "epoch_pct": 3.15, "eta": "52:38:48", "max_grad_norm": 1.0, "loss": 0.9828442335128784, "grad_norm": 0.6076085567474365, "learning_rate": 7.855887521968366e-05}
-{"ts": "2025-12-26T20:00:10", "event": "train_log", "step": 450, "epoch": 0.189873417721519, "progress_pct": 3.16, "epoch_pct": 3.16, "eta": "52:31:43", "max_grad_norm": 1.0, "loss": 1.0573710203170776, "grad_norm": 0.6418202519416809, "learning_rate": 7.89103690685413e-05}
-{"ts": "2025-12-26T20:00:25", "event": "train_log", "step": 452, "epoch": 0.19071729957805908, "progress_pct": 3.18, "epoch_pct": 3.18, "eta": "52:24:44", "max_grad_norm": 1.0, "loss": 1.0216103792190552, "grad_norm": 0.7055076360702515, "learning_rate": 7.926186291739895e-05}
-{"ts": "2025-12-26T20:00:39", "event": "train_log", "step": 454, "epoch": 0.19156118143459916, "progress_pct": 3.19, "epoch_pct": 3.19, "eta": "52:17:54", "max_grad_norm": 1.0, "loss": 0.9837722778320312, "grad_norm": 0.5668330192565918, "learning_rate": 7.961335676625659e-05}
-{"ts": "2025-12-26T20:00:54", "event": "train_log", "step": 456, "epoch": 0.19240506329113924, "progress_pct": 3.21, "epoch_pct": 3.21, "eta": "52:10:53", "max_grad_norm": 1.0, "loss": 1.0003894567489624, "grad_norm": 0.6419380307197571, "learning_rate": 7.996485061511424e-05}
-{"ts": "2025-12-26T20:01:09", "event": "train_log", "step": 458, "epoch": 0.19324894514767932, "progress_pct": 3.22, "epoch_pct": 3.22, "eta": "52:04:16", "max_grad_norm": 1.0, "loss": 1.0609031915664673, "grad_norm": 0.5949198007583618, "learning_rate": 8.031634446397188e-05}
-{"ts": "2025-12-26T20:01:24", "event": "train_log", "step": 460, "epoch": 0.1940928270042194, "progress_pct": 3.23, "epoch_pct": 3.23, "eta": "51:57:39", "max_grad_norm": 1.0, "loss": 1.0543403625488281, "grad_norm": 0.7032039761543274, "learning_rate": 8.066783831282952e-05}
-{"ts": "2025-12-26T20:01:39", "event": "train_log", "step": 462, "epoch": 0.1949367088607595, "progress_pct": 3.25, "epoch_pct": 3.25, "eta": "51:51:20", "max_grad_norm": 1.0, "loss": 0.9819303154945374, "grad_norm": 0.5775868892669678, "learning_rate": 8.101933216168718e-05}
-{"ts": "2025-12-26T20:01:55", "event": "train_log", "step": 464, "epoch": 0.19578059071729959, "progress_pct": 3.26, "epoch_pct": 3.26, "eta": "51:45:12", "max_grad_norm": 1.0, "loss": 1.0542067289352417, "grad_norm": 0.9301062226295471, "learning_rate": 8.137082601054482e-05}
-{"ts": "2025-12-26T20:02:10", "event": "train_log", "step": 466, "epoch": 0.19662447257383966, "progress_pct": 3.28, "epoch_pct": 3.28, "eta": "51:38:58", "max_grad_norm": 1.0, "loss": 0.9966341257095337, "grad_norm": 0.6193217039108276, "learning_rate": 8.172231985940246e-05}
-{"ts": "2025-12-26T20:02:25", "event": "train_log", "step": 468, "epoch": 0.19746835443037974, "progress_pct": 3.29, "epoch_pct": 3.29, "eta": "51:32:35", "max_grad_norm": 1.0, "loss": 1.0474121570587158, "grad_norm": 0.6286146640777588, "learning_rate": 8.20738137082601e-05}
-{"ts": "2025-12-26T20:02:40", "event": "train_log", "step": 470, "epoch": 0.19831223628691982, "progress_pct": 3.31, "epoch_pct": 3.31, "eta": "51:26:23", "max_grad_norm": 1.0, "loss": 0.9549239277839661, "grad_norm": 0.7418972253799438, "learning_rate": 8.242530755711776e-05}
-{"ts": "2025-12-26T20:02:56", "event": "train_log", "step": 472, "epoch": 0.1991561181434599, "progress_pct": 3.32, "epoch_pct": 3.32, "eta": "51:20:28", "max_grad_norm": 1.0, "loss": 1.0191338062286377, "grad_norm": 0.6122808456420898, "learning_rate": 8.27768014059754e-05}
-{"ts": "2025-12-26T20:03:11", "event": "train_log", "step": 474, "epoch": 0.2, "progress_pct": 3.33, "epoch_pct": 3.33, "eta": "51:14:22", "max_grad_norm": 1.0, "loss": 1.0987539291381836, "grad_norm": 0.6375362277030945, "learning_rate": 8.312829525483304e-05}
-{"ts": "2025-12-26T20:03:26", "event": "train_log", "step": 476, "epoch": 0.2008438818565401, "progress_pct": 3.35, "epoch_pct": 3.35, "eta": "51:08:04", "max_grad_norm": 1.0, "loss": 1.0369136333465576, "grad_norm": 0.6459513306617737, "learning_rate": 8.347978910369068e-05}
-{"ts": "2025-12-26T20:03:41", "event": "train_log", "step": 478, "epoch": 0.20168776371308017, "progress_pct": 3.36, "epoch_pct": 3.36, "eta": "51:02:13", "max_grad_norm": 1.0, "loss": 1.0582096576690674, "grad_norm": 0.7029640674591064, "learning_rate": 8.383128295254833e-05}
-{"ts": "2025-12-26T20:03:56", "event": "train_log", "step": 480, "epoch": 0.20253164556962025, "progress_pct": 3.38, "epoch_pct": 3.38, "eta": "50:56:07", "max_grad_norm": 1.0, "loss": 1.022916316986084, "grad_norm": 0.6345387697219849, "learning_rate": 8.418277680140598e-05}
-{"ts": "2025-12-26T20:04:11", "event": "train_log", "step": 482, "epoch": 0.20337552742616033, "progress_pct": 3.39, "epoch_pct": 3.39, "eta": "50:50:12", "max_grad_norm": 1.0, "loss": 0.973024308681488, "grad_norm": 0.5764590501785278, "learning_rate": 8.453427065026362e-05}
-{"ts": "2025-12-26T20:04:26", "event": "train_log", "step": 484, "epoch": 0.2042194092827004, "progress_pct": 3.4, "epoch_pct": 3.4, "eta": "50:44:12", "max_grad_norm": 1.0, "loss": 1.0292812585830688, "grad_norm": 0.5884482860565186, "learning_rate": 8.488576449912127e-05}
-{"ts": "2025-12-26T20:04:41", "event": "train_log", "step": 486, "epoch": 0.20506329113924052, "progress_pct": 3.42, "epoch_pct": 3.42, "eta": "50:38:27", "max_grad_norm": 1.0, "loss": 1.0083447694778442, "grad_norm": 0.616357147693634, "learning_rate": 8.523725834797891e-05}
-{"ts": "2025-12-26T20:04:56", "event": "train_log", "step": 488, "epoch": 0.2059071729957806, "progress_pct": 3.43, "epoch_pct": 3.43, "eta": "50:32:38", "max_grad_norm": 1.0, "loss": 0.9936985373497009, "grad_norm": 0.7671196460723877, "learning_rate": 8.558875219683656e-05}
-{"ts": "2025-12-26T20:05:11", "event": "train_log", "step": 490, "epoch": 0.20675105485232068, "progress_pct": 3.45, "epoch_pct": 3.45, "eta": "50:26:41", "max_grad_norm": 1.0, "loss": 1.051513910293579, "grad_norm": 0.6197299957275391, "learning_rate": 8.59402460456942e-05}
-{"ts": "2025-12-26T20:05:26", "event": "train_log", "step": 492, "epoch": 0.20759493670886076, "progress_pct": 3.46, "epoch_pct": 3.46, "eta": "50:20:53", "max_grad_norm": 1.0, "loss": 0.9474978446960449, "grad_norm": 0.6912890672683716, "learning_rate": 8.629173989455185e-05}
-{"ts": "2025-12-26T20:05:41", "event": "train_log", "step": 494, "epoch": 0.20843881856540084, "progress_pct": 3.47, "epoch_pct": 3.47, "eta": "50:15:02", "max_grad_norm": 1.0, "loss": 1.0671660900115967, "grad_norm": 0.6941592693328857, "learning_rate": 8.664323374340949e-05}
-{"ts": "2025-12-26T20:05:56", "event": "train_log", "step": 496, "epoch": 0.20928270042194091, "progress_pct": 3.49, "epoch_pct": 3.49, "eta": "50:09:32", "max_grad_norm": 1.0, "loss": 1.0020159482955933, "grad_norm": 0.5889528393745422, "learning_rate": 8.699472759226714e-05}
-{"ts": "2025-12-26T20:06:12", "event": "train_log", "step": 498, "epoch": 0.21012658227848102, "progress_pct": 3.5, "epoch_pct": 3.5, "eta": "50:04:05", "max_grad_norm": 1.0, "loss": 1.0165860652923584, "grad_norm": 0.6478549838066101, "learning_rate": 8.734622144112478e-05}
-{"ts": "2025-12-26T20:06:28", "event": "train_log", "step": 500, "epoch": 0.2109704641350211, "progress_pct": 3.52, "epoch_pct": 3.52, "eta": "49:58:53", "max_grad_norm": 1.0, "loss": 0.8798263072967529, "grad_norm": 0.6018255949020386, "learning_rate": 8.769771528998243e-05}
-{"ts": "2025-12-26T20:18:00", "event": "train_log", "step": 500, "epoch": 0.2109704641350211, "progress_pct": 3.52, "epoch_pct": 3.52, "eta": "55:15:34", "max_grad_norm": 1.0, "eval_loss": 1.042096495628357, "eval_runtime": 692.4361, "eval_samples_per_second": 3.043, "eval_steps_per_second": 3.043}
-{"ts": "2025-12-26T20:18:16", "event": "train_log", "step": 502, "epoch": 0.21181434599156118, "progress_pct": 3.53, "epoch_pct": 3.53, "eta": "55:09:15", "max_grad_norm": 1.0, "loss": 1.092096209526062, "grad_norm": 0.578990638256073, "learning_rate": 8.804920913884007e-05}
-{"ts": "2025-12-26T20:18:32", "event": "train_log", "step": 504, "epoch": 0.21265822784810126, "progress_pct": 3.54, "epoch_pct": 3.54, "eta": "55:02:40", "max_grad_norm": 1.0, "loss": 1.0413451194763184, "grad_norm": 0.6597883701324463, "learning_rate": 8.840070298769771e-05}
-{"ts": "2025-12-26T20:18:48", "event": "train_log", "step": 506, "epoch": 0.21350210970464134, "progress_pct": 3.56, "epoch_pct": 3.56, "eta": "54:56:20", "max_grad_norm": 1.0, "loss": 1.0073142051696777, "grad_norm": 0.6660305261611938, "learning_rate": 8.875219683655536e-05}
-{"ts": "2025-12-26T20:19:03", "event": "train_log", "step": 508, "epoch": 0.21434599156118145, "progress_pct": 3.57, "epoch_pct": 3.57, "eta": "54:49:52", "max_grad_norm": 1.0, "loss": 1.0319768190383911, "grad_norm": 0.6283115148544312, "learning_rate": 8.910369068541301e-05}
-{"ts": "2025-12-26T20:19:20", "event": "train_log", "step": 510, "epoch": 0.21518987341772153, "progress_pct": 3.59, "epoch_pct": 3.59, "eta": "54:44:05", "max_grad_norm": 1.0, "loss": 1.0046353340148926, "grad_norm": 0.6257343292236328, "learning_rate": 8.945518453427065e-05}
-{"ts": "2025-12-26T20:19:36", "event": "train_log", "step": 512, "epoch": 0.2160337552742616, "progress_pct": 3.6, "epoch_pct": 3.6, "eta": "54:37:47", "max_grad_norm": 1.0, "loss": 0.9169099926948547, "grad_norm": 0.5530875325202942, "learning_rate": 8.980667838312829e-05}
-{"ts": "2025-12-26T20:19:52", "event": "train_log", "step": 514, "epoch": 0.2168776371308017, "progress_pct": 3.61, "epoch_pct": 3.61, "eta": "54:31:36", "max_grad_norm": 1.0, "loss": 0.9081505537033081, "grad_norm": 0.5369633436203003, "learning_rate": 9.015817223198594e-05}
-{"ts": "2025-12-26T20:20:07", "event": "train_log", "step": 516, "epoch": 0.21772151898734177, "progress_pct": 3.63, "epoch_pct": 3.63, "eta": "54:25:10", "max_grad_norm": 1.0, "loss": 0.9165045022964478, "grad_norm": 0.6618232131004333, "learning_rate": 9.05096660808436e-05}
-{"ts": "2025-12-26T20:20:22", "event": "train_log", "step": 518, "epoch": 0.21856540084388185, "progress_pct": 3.64, "epoch_pct": 3.64, "eta": "54:18:59", "max_grad_norm": 1.0, "loss": 0.91348797082901, "grad_norm": 0.600666344165802, "learning_rate": 9.086115992970123e-05}
-{"ts": "2025-12-26T20:20:38", "event": "train_log", "step": 520, "epoch": 0.21940928270042195, "progress_pct": 3.66, "epoch_pct": 3.66, "eta": "54:12:36", "max_grad_norm": 1.0, "loss": 1.006508469581604, "grad_norm": 0.5919831991195679, "learning_rate": 9.121265377855887e-05}
-{"ts": "2025-12-26T20:20:53", "event": "train_log", "step": 522, "epoch": 0.22025316455696203, "progress_pct": 3.67, "epoch_pct": 3.67, "eta": "54:06:25", "max_grad_norm": 1.0, "loss": 1.0013236999511719, "grad_norm": 0.688058614730835, "learning_rate": 9.156414762741654e-05}
-{"ts": "2025-12-26T20:21:09", "event": "train_log", "step": 524, "epoch": 0.2210970464135021, "progress_pct": 3.68, "epoch_pct": 3.68, "eta": "54:00:23", "max_grad_norm": 1.0, "loss": 1.0909923315048218, "grad_norm": 0.6721227765083313, "learning_rate": 9.191564147627418e-05}
-{"ts": "2025-12-26T20:21:25", "event": "train_log", "step": 526, "epoch": 0.2219409282700422, "progress_pct": 3.7, "epoch_pct": 3.7, "eta": "53:54:36", "max_grad_norm": 1.0, "loss": 1.0117096900939941, "grad_norm": 0.5987313389778137, "learning_rate": 9.226713532513181e-05}
-{"ts": "2025-12-26T20:21:40", "event": "train_log", "step": 528, "epoch": 0.22278481012658227, "progress_pct": 3.71, "epoch_pct": 3.71, "eta": "53:48:39", "max_grad_norm": 1.0, "loss": 1.0153647661209106, "grad_norm": 0.6191489696502686, "learning_rate": 9.261862917398945e-05}
-{"ts": "2025-12-26T20:21:56", "event": "train_log", "step": 530, "epoch": 0.22362869198312235, "progress_pct": 3.73, "epoch_pct": 3.73, "eta": "53:42:46", "max_grad_norm": 1.0, "loss": 0.9649755954742432, "grad_norm": 0.6821563243865967, "learning_rate": 9.29701230228471e-05}
-{"ts": "2025-12-26T20:22:12", "event": "train_log", "step": 532, "epoch": 0.22447257383966246, "progress_pct": 3.74, "epoch_pct": 3.74, "eta": "53:36:44", "max_grad_norm": 1.0, "loss": 0.8673232197761536, "grad_norm": 1.760398268699646, "learning_rate": 9.332161687170476e-05}
-{"ts": "2025-12-26T20:22:27", "event": "train_log", "step": 534, "epoch": 0.22531645569620254, "progress_pct": 3.76, "epoch_pct": 3.76, "eta": "53:30:57", "max_grad_norm": 1.0, "loss": 0.9942440986633301, "grad_norm": 0.6670058369636536, "learning_rate": 9.36731107205624e-05}
-{"ts": "2025-12-26T20:22:42", "event": "train_log", "step": 536, "epoch": 0.22616033755274262, "progress_pct": 3.77, "epoch_pct": 3.77, "eta": "53:24:51", "max_grad_norm": 1.0, "loss": 1.0364389419555664, "grad_norm": 0.7345916032791138, "learning_rate": 9.402460456942003e-05}
-{"ts": "2025-12-26T20:22:57", "event": "train_log", "step": 538, "epoch": 0.2270042194092827, "progress_pct": 3.78, "epoch_pct": 3.78, "eta": "53:18:50", "max_grad_norm": 1.0, "loss": 0.9314924478530884, "grad_norm": 0.5946128964424133, "learning_rate": 9.437609841827768e-05}
-{"ts": "2025-12-26T20:23:12", "event": "train_log", "step": 540, "epoch": 0.22784810126582278, "progress_pct": 3.8, "epoch_pct": 3.8, "eta": "53:12:58", "max_grad_norm": 1.0, "loss": 1.0694862604141235, "grad_norm": 0.5800848603248596, "learning_rate": 9.472759226713534e-05}
-{"ts": "2025-12-26T20:23:27", "event": "train_log", "step": 542, "epoch": 0.22869198312236286, "progress_pct": 3.81, "epoch_pct": 3.81, "eta": "53:06:38", "max_grad_norm": 1.0, "loss": 1.03531014919281, "grad_norm": 0.6712192893028259, "learning_rate": 9.507908611599297e-05}
-{"ts": "2025-12-26T20:23:42", "event": "train_log", "step": 544, "epoch": 0.22953586497890296, "progress_pct": 3.83, "epoch_pct": 3.83, "eta": "53:01:02", "max_grad_norm": 1.0, "loss": 0.9795235991477966, "grad_norm": 0.5641416311264038, "learning_rate": 9.543057996485063e-05}
-{"ts": "2025-12-26T20:23:58", "event": "train_log", "step": 546, "epoch": 0.23037974683544304, "progress_pct": 3.84, "epoch_pct": 3.84, "eta": "52:55:25", "max_grad_norm": 1.0, "loss": 0.9641494750976562, "grad_norm": 0.50412517786026, "learning_rate": 9.578207381370826e-05}
-{"ts": "2025-12-26T20:24:13", "event": "train_log", "step": 548, "epoch": 0.23122362869198312, "progress_pct": 3.85, "epoch_pct": 3.85, "eta": "52:49:35", "max_grad_norm": 1.0, "loss": 0.9375281929969788, "grad_norm": 0.579118549823761, "learning_rate": 9.61335676625659e-05}
-{"ts": "2025-12-26T20:24:28", "event": "train_log", "step": 550, "epoch": 0.2320675105485232, "progress_pct": 3.87, "epoch_pct": 3.87, "eta": "52:43:58", "max_grad_norm": 1.0, "loss": 0.9414046406745911, "grad_norm": 0.5888341665267944, "learning_rate": 9.648506151142355e-05}
-{"ts": "2025-12-26T20:24:43", "event": "train_log", "step": 552, "epoch": 0.23291139240506328, "progress_pct": 3.88, "epoch_pct": 3.88, "eta": "52:38:11", "max_grad_norm": 1.0, "loss": 0.9005617499351501, "grad_norm": 0.5595056414604187, "learning_rate": 9.68365553602812e-05}
-{"ts": "2025-12-26T20:24:58", "event": "train_log", "step": 554, "epoch": 0.23375527426160336, "progress_pct": 3.9, "epoch_pct": 3.9, "eta": "52:32:28", "max_grad_norm": 1.0, "loss": 1.0283968448638916, "grad_norm": 0.6605326533317566, "learning_rate": 9.718804920913884e-05}
-{"ts": "2025-12-26T20:25:14", "event": "train_log", "step": 556, "epoch": 0.23459915611814347, "progress_pct": 3.91, "epoch_pct": 3.91, "eta": "52:27:16", "max_grad_norm": 1.0, "loss": 1.0058249235153198, "grad_norm": 0.5657313466072083, "learning_rate": 9.753954305799648e-05}
-{"ts": "2025-12-26T20:25:30", "event": "train_log", "step": 558, "epoch": 0.23544303797468355, "progress_pct": 3.92, "epoch_pct": 3.92, "eta": "52:21:57", "max_grad_norm": 1.0, "loss": 0.9835494756698608, "grad_norm": 0.5433364510536194, "learning_rate": 9.789103690685413e-05}
-{"ts": "2025-12-26T20:25:44", "event": "train_log", "step": 560, "epoch": 0.23628691983122363, "progress_pct": 3.94, "epoch_pct": 3.94, "eta": "52:16:10", "max_grad_norm": 1.0, "loss": 1.054532527923584, "grad_norm": 0.6129802465438843, "learning_rate": 9.824253075571179e-05}
-{"ts": "2025-12-26T20:25:59", "event": "train_log", "step": 562, "epoch": 0.2371308016877637, "progress_pct": 3.95, "epoch_pct": 3.95, "eta": "52:10:39", "max_grad_norm": 1.0, "loss": 1.0240973234176636, "grad_norm": 0.6496239304542542, "learning_rate": 9.859402460456942e-05}
-{"ts": "2025-12-26T20:26:14", "event": "train_log", "step": 564, "epoch": 0.2379746835443038, "progress_pct": 3.97, "epoch_pct": 3.97, "eta": "52:04:58", "max_grad_norm": 1.0, "loss": 1.0229179859161377, "grad_norm": 0.6380873918533325, "learning_rate": 9.894551845342706e-05}
-{"ts": "2025-12-26T20:26:29", "event": "train_log", "step": 566, "epoch": 0.23881856540084387, "progress_pct": 3.98, "epoch_pct": 3.98, "eta": "51:59:24", "max_grad_norm": 1.0, "loss": 1.0111570358276367, "grad_norm": 0.6151993870735168, "learning_rate": 9.929701230228471e-05}
-{"ts": "2025-12-26T20:26:43", "event": "train_log", "step": 568, "epoch": 0.23966244725738398, "progress_pct": 3.99, "epoch_pct": 3.99, "eta": "51:53:51", "max_grad_norm": 1.0, "loss": 0.9450829029083252, "grad_norm": 0.5727584958076477, "learning_rate": 9.964850615114237e-05}
-{"ts": "2025-12-26T20:26:58", "event": "train_log", "step": 570, "epoch": 0.24050632911392406, "progress_pct": 4.01, "epoch_pct": 4.01, "eta": "51:48:12", "max_grad_norm": 1.0, "loss": 0.9800319075584412, "grad_norm": 0.6620725989341736, "learning_rate": 0.0001}
-{"ts": "2025-12-26T20:27:12", "event": "train_log", "step": 572, "epoch": 0.24135021097046414, "progress_pct": 4.02, "epoch_pct": 4.02, "eta": "51:42:42", "max_grad_norm": 1.0, "loss": 0.9757438898086548, "grad_norm": 0.6151163578033447, "learning_rate": 0.00010035149384885764}
-{"ts": "2025-12-26T20:27:27", "event": "train_log", "step": 574, "epoch": 0.24219409282700421, "progress_pct": 4.04, "epoch_pct": 4.04, "eta": "51:37:25", "max_grad_norm": 1.0, "loss": 0.9104921817779541, "grad_norm": 0.5672140717506409, "learning_rate": 0.0001007029876977153}
-{"ts": "2025-12-26T20:27:43", "event": "train_log", "step": 576, "epoch": 0.2430379746835443, "progress_pct": 4.05, "epoch_pct": 4.05, "eta": "51:32:22", "max_grad_norm": 1.0, "loss": 1.1027376651763916, "grad_norm": 0.5697256326675415, "learning_rate": 0.00010105448154657293}
-{"ts": "2025-12-26T20:27:58", "event": "train_log", "step": 578, "epoch": 0.2438818565400844, "progress_pct": 4.06, "epoch_pct": 4.06, "eta": "51:27:07", "max_grad_norm": 1.0, "loss": 1.0055404901504517, "grad_norm": 0.5590381622314453, "learning_rate": 0.00010140597539543057}
-{"ts": "2025-12-26T20:28:13", "event": "train_log", "step": 580, "epoch": 0.24472573839662448, "progress_pct": 4.08, "epoch_pct": 4.08, "eta": "51:21:54", "max_grad_norm": 1.0, "loss": 1.020835518836975, "grad_norm": 0.5518567562103271, "learning_rate": 0.00010175746924428824}
-{"ts": "2025-12-26T20:28:28", "event": "train_log", "step": 582, "epoch": 0.24556962025316456, "progress_pct": 4.09, "epoch_pct": 4.09, "eta": "51:16:45", "max_grad_norm": 1.0, "loss": 0.9528344869613647, "grad_norm": 0.6338496208190918, "learning_rate": 0.00010210896309314588}
-{"ts": "2025-12-26T20:28:42", "event": "train_log", "step": 584, "epoch": 0.24641350210970464, "progress_pct": 4.11, "epoch_pct": 4.11, "eta": "51:11:14", "max_grad_norm": 1.0, "loss": 1.0088670253753662, "grad_norm": 0.6497329473495483, "learning_rate": 0.00010246045694200353}
-{"ts": "2025-12-26T20:28:58", "event": "train_log", "step": 586, "epoch": 0.24725738396624472, "progress_pct": 4.12, "epoch_pct": 4.12, "eta": "51:06:18", "max_grad_norm": 1.0, "loss": 0.9961200952529907, "grad_norm": 0.49888095259666443, "learning_rate": 0.00010281195079086117}
-{"ts": "2025-12-26T20:29:12", "event": "train_log", "step": 588, "epoch": 0.2481012658227848, "progress_pct": 4.14, "epoch_pct": 4.14, "eta": "51:01:08", "max_grad_norm": 1.0, "loss": 0.9635610580444336, "grad_norm": 0.5680158734321594, "learning_rate": 0.0001031634446397188}
-{"ts": "2025-12-26T20:29:27", "event": "train_log", "step": 590, "epoch": 0.2489451476793249, "progress_pct": 4.15, "epoch_pct": 4.15, "eta": "50:55:56", "max_grad_norm": 1.0, "loss": 0.9392287135124207, "grad_norm": 0.658168375492096, "learning_rate": 0.00010351493848857646}
-{"ts": "2025-12-26T20:29:42", "event": "train_log", "step": 592, "epoch": 0.249789029535865, "progress_pct": 4.16, "epoch_pct": 4.16, "eta": "50:50:55", "max_grad_norm": 1.0, "loss": 0.9600516557693481, "grad_norm": 0.618262767791748, "learning_rate": 0.0001038664323374341}
-{"ts": "2025-12-26T20:29:56", "event": "train_log", "step": 594, "epoch": 0.25063291139240507, "progress_pct": 4.18, "epoch_pct": 4.18, "eta": "50:45:40", "max_grad_norm": 1.0, "loss": 1.005476713180542, "grad_norm": 0.6003909111022949, "learning_rate": 0.00010421792618629173}
-{"ts": "2025-12-26T20:30:11", "event": "train_log", "step": 596, "epoch": 0.2514767932489452, "progress_pct": 4.19, "epoch_pct": 4.19, "eta": "50:40:42", "max_grad_norm": 1.0, "loss": 0.9523017406463623, "grad_norm": 0.5437078475952148, "learning_rate": 0.00010456942003514938}
-{"ts": "2025-12-26T20:30:27", "event": "train_log", "step": 598, "epoch": 0.2523206751054852, "progress_pct": 4.21, "epoch_pct": 4.21, "eta": "50:35:58", "max_grad_norm": 1.0, "loss": 0.9526668787002563, "grad_norm": 0.5524541735649109, "learning_rate": 0.00010492091388400705}
-{"ts": "2025-12-26T20:30:42", "event": "train_log", "step": 600, "epoch": 0.25316455696202533, "progress_pct": 4.22, "epoch_pct": 4.22, "eta": "50:31:16", "max_grad_norm": 1.0, "loss": 1.019660472869873, "grad_norm": 0.679504930973053, "learning_rate": 0.00010527240773286469}
-{"ts": "2025-12-26T20:42:00", "event": "train_log", "step": 600, "epoch": 0.25316455696202533, "progress_pct": 4.22, "epoch_pct": 4.22, "eta": "54:47:45", "max_grad_norm": 1.0, "eval_loss": 1.0193854570388794, "eval_runtime": 677.9523, "eval_samples_per_second": 3.108, "eval_steps_per_second": 3.108}
-{"ts": "2025-12-26T20:42:16", "event": "train_log", "step": 602, "epoch": 0.2540084388185654, "progress_pct": 4.23, "epoch_pct": 4.23, "eta": "54:42:19", "max_grad_norm": 1.0, "loss": 0.9910882711410522, "grad_norm": 0.5646136999130249, "learning_rate": 0.00010562390158172233}
-{"ts": "2025-12-26T20:42:33", "event": "train_log", "step": 604, "epoch": 0.2548523206751055, "progress_pct": 4.25, "epoch_pct": 4.25, "eta": "54:37:11", "max_grad_norm": 1.0, "loss": 0.9616432785987854, "grad_norm": 0.5238093137741089, "learning_rate": 0.00010597539543057998}
-{"ts": "2025-12-26T20:42:47", "event": "train_log", "step": 606, "epoch": 0.25569620253164554, "progress_pct": 4.26, "epoch_pct": 4.26, "eta": "54:31:19", "max_grad_norm": 1.0, "loss": 1.0078275203704834, "grad_norm": 0.7483857274055481, "learning_rate": 0.00010632688927943762}
-{"ts": "2025-12-26T20:43:03", "event": "train_log", "step": 608, "epoch": 0.25654008438818565, "progress_pct": 4.28, "epoch_pct": 4.28, "eta": "54:26:10", "max_grad_norm": 1.0, "loss": 0.9827103018760681, "grad_norm": 0.578948974609375, "learning_rate": 0.00010667838312829525}
-{"ts": "2025-12-26T20:43:20", "event": "train_log", "step": 610, "epoch": 0.25738396624472576, "progress_pct": 4.29, "epoch_pct": 4.29, "eta": "54:21:03", "max_grad_norm": 1.0, "loss": 1.0423277616500854, "grad_norm": 0.5525906085968018, "learning_rate": 0.00010702987697715289}
-{"ts": "2025-12-26T20:43:36", "event": "train_log", "step": 612, "epoch": 0.2582278481012658, "progress_pct": 4.3, "epoch_pct": 4.3, "eta": "54:15:54", "max_grad_norm": 1.0, "loss": 0.9561693072319031, "grad_norm": 0.6721326112747192, "learning_rate": 0.00010738137082601054}
-{"ts": "2025-12-26T20:43:51", "event": "train_log", "step": 614, "epoch": 0.2590717299578059, "progress_pct": 4.32, "epoch_pct": 4.32, "eta": "54:10:30", "max_grad_norm": 1.0, "loss": 0.9602992534637451, "grad_norm": 0.5701051354408264, "learning_rate": 0.00010773286467486821}
-{"ts": "2025-12-26T20:44:06", "event": "train_log", "step": 616, "epoch": 0.25991561181434597, "progress_pct": 4.33, "epoch_pct": 4.33, "eta": "54:04:48", "max_grad_norm": 1.0, "loss": 1.1422650814056396, "grad_norm": 0.6349860429763794, "learning_rate": 0.00010808435852372585}
-{"ts": "2025-12-26T20:44:21", "event": "train_log", "step": 618, "epoch": 0.2607594936708861, "progress_pct": 4.35, "epoch_pct": 4.35, "eta": "53:59:30", "max_grad_norm": 1.0, "loss": 0.9762773513793945, "grad_norm": 0.5496085286140442, "learning_rate": 0.00010843585237258349}
-{"ts": "2025-12-26T20:44:37", "event": "train_log", "step": 620, "epoch": 0.2616033755274262, "progress_pct": 4.36, "epoch_pct": 4.36, "eta": "53:54:10", "max_grad_norm": 1.0, "loss": 1.0133616924285889, "grad_norm": 0.6080722808837891, "learning_rate": 0.00010878734622144114}
-{"ts": "2025-12-26T20:44:53", "event": "train_log", "step": 622, "epoch": 0.26244725738396624, "progress_pct": 4.37, "epoch_pct": 4.37, "eta": "53:49:12", "max_grad_norm": 1.0, "loss": 0.9385587573051453, "grad_norm": 0.5450218915939331, "learning_rate": 0.00010913884007029878}
-{"ts": "2025-12-26T20:45:10", "event": "train_log", "step": 624, "epoch": 0.26329113924050634, "progress_pct": 4.39, "epoch_pct": 4.39, "eta": "53:44:42", "max_grad_norm": 1.0, "loss": 0.9359989762306213, "grad_norm": 0.592106819152832, "learning_rate": 0.00010949033391915641}
-{"ts": "2025-12-26T20:45:25", "event": "train_log", "step": 626, "epoch": 0.2641350210970464, "progress_pct": 4.4, "epoch_pct": 4.4, "eta": "53:39:18", "max_grad_norm": 1.0, "loss": 1.0266027450561523, "grad_norm": 0.6449427604675293, "learning_rate": 0.00010984182776801407}
-{"ts": "2025-12-26T20:45:41", "event": "train_log", "step": 628, "epoch": 0.2649789029535865, "progress_pct": 4.42, "epoch_pct": 4.42, "eta": "53:34:30", "max_grad_norm": 1.0, "loss": 0.9303187131881714, "grad_norm": 0.538299560546875, "learning_rate": 0.0001101933216168717}
-{"ts": "2025-12-26T20:45:57", "event": "train_log", "step": 630, "epoch": 0.26582278481012656, "progress_pct": 4.43, "epoch_pct": 4.43, "eta": "53:29:35", "max_grad_norm": 1.0, "loss": 0.9368857145309448, "grad_norm": 0.546316921710968, "learning_rate": 0.00011054481546572934}
-{"ts": "2025-12-26T20:46:13", "event": "train_log", "step": 632, "epoch": 0.26666666666666666, "progress_pct": 4.44, "epoch_pct": 4.44, "eta": "53:24:21", "max_grad_norm": 1.0, "loss": 0.9573145508766174, "grad_norm": 0.5818730592727661, "learning_rate": 0.00011089630931458701}
-{"ts": "2025-12-26T20:46:28", "event": "train_log", "step": 634, "epoch": 0.26751054852320677, "progress_pct": 4.46, "epoch_pct": 4.46, "eta": "53:19:26", "max_grad_norm": 1.0, "loss": 0.9345449805259705, "grad_norm": 0.5958262085914612, "learning_rate": 0.00011124780316344465}
-{"ts": "2025-12-26T20:46:43", "event": "train_log", "step": 636, "epoch": 0.2683544303797468, "progress_pct": 4.47, "epoch_pct": 4.47, "eta": "53:14:04", "max_grad_norm": 1.0, "loss": 1.0906590223312378, "grad_norm": 0.6259077787399292, "learning_rate": 0.0001115992970123023}
-{"ts": "2025-12-26T20:46:58", "event": "train_log", "step": 638, "epoch": 0.26919831223628693, "progress_pct": 4.49, "epoch_pct": 4.49, "eta": "53:09:05", "max_grad_norm": 1.0, "loss": 1.0757447481155396, "grad_norm": 0.589672863483429, "learning_rate": 0.00011195079086115994}
-{"ts": "2025-12-26T20:47:14", "event": "train_log", "step": 640, "epoch": 0.270042194092827, "progress_pct": 4.5, "epoch_pct": 4.5, "eta": "53:04:07", "max_grad_norm": 1.0, "loss": 0.9310855269432068, "grad_norm": 0.5714080333709717, "learning_rate": 0.00011230228471001758}
-{"ts": "2025-12-26T20:47:29", "event": "train_log", "step": 642, "epoch": 0.2708860759493671, "progress_pct": 4.51, "epoch_pct": 4.51, "eta": "52:59:05", "max_grad_norm": 1.0, "loss": 0.9276360273361206, "grad_norm": 0.45342639088630676, "learning_rate": 0.00011265377855887523}
-{"ts": "2025-12-26T20:47:44", "event": "train_log", "step": 644, "epoch": 0.2717299578059072, "progress_pct": 4.53, "epoch_pct": 4.53, "eta": "52:54:02", "max_grad_norm": 1.0, "loss": 1.084719181060791, "grad_norm": 0.6386750340461731, "learning_rate": 0.00011300527240773287}
-{"ts": "2025-12-26T20:48:01", "event": "train_log", "step": 646, "epoch": 0.27257383966244725, "progress_pct": 4.54, "epoch_pct": 4.54, "eta": "52:49:30", "max_grad_norm": 1.0, "loss": 0.9763918519020081, "grad_norm": 0.6446163654327393, "learning_rate": 0.0001133567662565905}
-{"ts": "2025-12-26T20:48:15", "event": "train_log", "step": 648, "epoch": 0.27341772151898736, "progress_pct": 4.56, "epoch_pct": 4.56, "eta": "52:44:16", "max_grad_norm": 1.0, "loss": 0.9517921805381775, "grad_norm": 0.5925686359405518, "learning_rate": 0.00011370826010544816}
-{"ts": "2025-12-26T20:48:31", "event": "train_log", "step": 650, "epoch": 0.2742616033755274, "progress_pct": 4.57, "epoch_pct": 4.57, "eta": "52:39:42", "max_grad_norm": 1.0, "loss": 1.0587927103042603, "grad_norm": 0.5399773716926575, "learning_rate": 0.00011405975395430582}
-{"ts": "2025-12-26T20:48:46", "event": "train_log", "step": 652, "epoch": 0.2751054852320675, "progress_pct": 4.59, "epoch_pct": 4.59, "eta": "52:34:44", "max_grad_norm": 1.0, "loss": 0.883341908454895, "grad_norm": 0.5872456431388855, "learning_rate": 0.00011441124780316346}
-{"ts": "2025-12-26T20:49:04", "event": "train_log", "step": 654, "epoch": 0.2759493670886076, "progress_pct": 4.6, "epoch_pct": 4.6, "eta": "52:30:39", "max_grad_norm": 1.0, "loss": 1.0306891202926636, "grad_norm": 0.5574564337730408, "learning_rate": 0.0001147627416520211}
-{"ts": "2025-12-26T20:49:21", "event": "train_log", "step": 656, "epoch": 0.2767932489451477, "progress_pct": 4.61, "epoch_pct": 4.61, "eta": "52:26:30", "max_grad_norm": 1.0, "loss": 0.8814032077789307, "grad_norm": 0.47789013385772705, "learning_rate": 0.00011511423550087874}
-{"ts": "2025-12-26T20:49:36", "event": "train_log", "step": 658, "epoch": 0.2776371308016878, "progress_pct": 4.63, "epoch_pct": 4.63, "eta": "52:21:51", "max_grad_norm": 1.0, "loss": 0.9460552334785461, "grad_norm": 0.5565530061721802, "learning_rate": 0.00011546572934973639}
-{"ts": "2025-12-26T20:49:51", "event": "train_log", "step": 660, "epoch": 0.27848101265822783, "progress_pct": 4.64, "epoch_pct": 4.64, "eta": "52:17:00", "max_grad_norm": 1.0, "loss": 0.9475110769271851, "grad_norm": 0.5299761295318604, "learning_rate": 0.00011581722319859403}
-{"ts": "2025-12-26T20:50:07", "event": "train_log", "step": 662, "epoch": 0.27932489451476794, "progress_pct": 4.66, "epoch_pct": 4.66, "eta": "52:12:15", "max_grad_norm": 1.0, "loss": 1.0630913972854614, "grad_norm": 0.6503344178199768, "learning_rate": 0.00011616871704745166}
-{"ts": "2025-12-26T20:50:23", "event": "train_log", "step": 664, "epoch": 0.280168776371308, "progress_pct": 4.67, "epoch_pct": 4.67, "eta": "52:07:53", "max_grad_norm": 1.0, "loss": 0.9389138221740723, "grad_norm": 0.5794585943222046, "learning_rate": 0.00011652021089630932}
-{"ts": "2025-12-26T20:50:39", "event": "train_log", "step": 666, "epoch": 0.2810126582278481, "progress_pct": 4.68, "epoch_pct": 4.68, "eta": "52:03:31", "max_grad_norm": 1.0, "loss": 0.8934136033058167, "grad_norm": 0.5762867331504822, "learning_rate": 0.00011687170474516695}
-{"ts": "2025-12-26T20:50:55", "event": "train_log", "step": 668, "epoch": 0.2818565400843882, "progress_pct": 4.7, "epoch_pct": 4.7, "eta": "51:59:04", "max_grad_norm": 1.0, "loss": 1.1072614192962646, "grad_norm": 0.6565435528755188, "learning_rate": 0.00011722319859402462}
-{"ts": "2025-12-26T20:51:10", "event": "train_log", "step": 670, "epoch": 0.28270042194092826, "progress_pct": 4.71, "epoch_pct": 4.71, "eta": "51:54:16", "max_grad_norm": 1.0, "loss": 1.0501434803009033, "grad_norm": 0.5819830298423767, "learning_rate": 0.00011757469244288226}
-{"ts": "2025-12-26T20:51:25", "event": "train_log", "step": 672, "epoch": 0.28354430379746837, "progress_pct": 4.73, "epoch_pct": 4.73, "eta": "51:49:35", "max_grad_norm": 1.0, "loss": 0.9880793690681458, "grad_norm": 0.6071487069129944, "learning_rate": 0.00011792618629173991}
-{"ts": "2025-12-26T20:51:40", "event": "train_log", "step": 674, "epoch": 0.2843881856540084, "progress_pct": 4.74, "epoch_pct": 4.74, "eta": "51:44:55", "max_grad_norm": 1.0, "loss": 0.9670693874359131, "grad_norm": 0.5765058398246765, "learning_rate": 0.00011827768014059755}
-{"ts": "2025-12-26T20:51:55", "event": "train_log", "step": 676, "epoch": 0.2852320675105485, "progress_pct": 4.75, "epoch_pct": 4.75, "eta": "51:40:28", "max_grad_norm": 1.0, "loss": 0.9602360725402832, "grad_norm": 0.5245351791381836, "learning_rate": 0.00011862917398945519}
-{"ts": "2025-12-26T20:52:10", "event": "train_log", "step": 678, "epoch": 0.28607594936708863, "progress_pct": 4.77, "epoch_pct": 4.77, "eta": "51:35:46", "max_grad_norm": 1.0, "loss": 0.9684560894966125, "grad_norm": 0.6189922094345093, "learning_rate": 0.00011898066783831282}
-{"ts": "2025-12-26T20:52:27", "event": "train_log", "step": 680, "epoch": 0.2869198312236287, "progress_pct": 4.78, "epoch_pct": 4.78, "eta": "51:31:50", "max_grad_norm": 1.0, "loss": 0.9465792775154114, "grad_norm": 0.6138690710067749, "learning_rate": 0.00011933216168717048}
-{"ts": "2025-12-26T20:52:45", "event": "train_log", "step": 682, "epoch": 0.2877637130801688, "progress_pct": 4.8, "epoch_pct": 4.8, "eta": "51:28:15", "max_grad_norm": 1.0, "loss": 0.8495944738388062, "grad_norm": 0.5371595621109009, "learning_rate": 0.00011968365553602812}
-{"ts": "2025-12-26T20:53:02", "event": "train_log", "step": 684, "epoch": 0.28860759493670884, "progress_pct": 4.81, "epoch_pct": 4.81, "eta": "51:24:18", "max_grad_norm": 1.0, "loss": 0.9663267135620117, "grad_norm": 0.5549944639205933, "learning_rate": 0.00012003514938488578}
-{"ts": "2025-12-26T20:53:18", "event": "train_log", "step": 686, "epoch": 0.28945147679324895, "progress_pct": 4.82, "epoch_pct": 4.82, "eta": "51:20:19", "max_grad_norm": 1.0, "loss": 0.9736058712005615, "grad_norm": 0.6484189033508301, "learning_rate": 0.00012038664323374342}
-{"ts": "2025-12-26T20:53:33", "event": "train_log", "step": 688, "epoch": 0.290295358649789, "progress_pct": 4.84, "epoch_pct": 4.84, "eta": "51:15:56", "max_grad_norm": 1.0, "loss": 1.0591845512390137, "grad_norm": 0.540351390838623, "learning_rate": 0.00012073813708260107}
-{"ts": "2025-12-26T20:53:49", "event": "train_log", "step": 690, "epoch": 0.2911392405063291, "progress_pct": 4.85, "epoch_pct": 4.85, "eta": "51:11:39", "max_grad_norm": 1.0, "loss": 0.944908618927002, "grad_norm": 0.5657922029495239, "learning_rate": 0.00012108963093145871}
-{"ts": "2025-12-26T20:54:03", "event": "train_log", "step": 692, "epoch": 0.2919831223628692, "progress_pct": 4.87, "epoch_pct": 4.87, "eta": "51:07:00", "max_grad_norm": 1.0, "loss": 1.0018219947814941, "grad_norm": 0.6040505170822144, "learning_rate": 0.00012144112478031635}
-{"ts": "2025-12-26T20:54:19", "event": "train_log", "step": 694, "epoch": 0.29282700421940927, "progress_pct": 4.88, "epoch_pct": 4.88, "eta": "51:02:55", "max_grad_norm": 1.0, "loss": 1.0351502895355225, "grad_norm": 0.5435477495193481, "learning_rate": 0.000121792618629174}
-{"ts": "2025-12-26T20:54:35", "event": "train_log", "step": 696, "epoch": 0.2936708860759494, "progress_pct": 4.89, "epoch_pct": 4.89, "eta": "50:58:37", "max_grad_norm": 1.0, "loss": 0.9935672283172607, "grad_norm": 0.5712518692016602, "learning_rate": 0.00012214411247803164}
-{"ts": "2025-12-26T20:54:49", "event": "train_log", "step": 698, "epoch": 0.29451476793248943, "progress_pct": 4.91, "epoch_pct": 4.91, "eta": "50:54:05", "max_grad_norm": 1.0, "loss": 1.0165108442306519, "grad_norm": 0.6138222813606262, "learning_rate": 0.00012249560632688928}
-{"ts": "2025-12-26T20:55:05", "event": "train_log", "step": 700, "epoch": 0.29535864978902954, "progress_pct": 4.92, "epoch_pct": 4.92, "eta": "50:49:50", "max_grad_norm": 1.0, "loss": 0.9334425926208496, "grad_norm": 0.4495212435722351, "learning_rate": 0.00012284710017574691}
-{"ts": "2025-12-26T21:06:13", "event": "train_log", "step": 700, "epoch": 0.29535864978902954, "progress_pct": 4.92, "epoch_pct": 4.92, "eta": "54:25:04", "max_grad_norm": 1.0, "eval_loss": 0.996929407119751, "eval_runtime": 668.6398, "eval_samples_per_second": 3.151, "eval_steps_per_second": 3.151}
-{"ts": "2025-12-26T21:06:28", "event": "train_log", "step": 702, "epoch": 0.29620253164556964, "progress_pct": 4.94, "epoch_pct": 4.94, "eta": "54:20:05", "max_grad_norm": 1.0, "loss": 1.0516537427902222, "grad_norm": 0.5321539044380188, "learning_rate": 0.00012319859402460458}
-{"ts": "2025-12-26T21:06:43", "event": "train_log", "step": 704, "epoch": 0.2970464135021097, "progress_pct": 4.95, "epoch_pct": 4.95, "eta": "54:15:07", "max_grad_norm": 1.0, "loss": 0.9387198686599731, "grad_norm": 0.5716516971588135, "learning_rate": 0.00012355008787346222}
-{"ts": "2025-12-26T21:06:57", "event": "train_log", "step": 706, "epoch": 0.2978902953586498, "progress_pct": 4.96, "epoch_pct": 4.96, "eta": "54:09:58", "max_grad_norm": 1.0, "loss": 0.99737948179245, "grad_norm": 0.5617920160293579, "learning_rate": 0.00012390158172231988}
-{"ts": "2025-12-26T21:07:12", "event": "train_log", "step": 708, "epoch": 0.29873417721518986, "progress_pct": 4.98, "epoch_pct": 4.98, "eta": "54:04:59", "max_grad_norm": 1.0, "loss": 0.9955025911331177, "grad_norm": 0.4922899007797241, "learning_rate": 0.00012425307557117752}
-{"ts": "2025-12-26T21:07:27", "event": "train_log", "step": 710, "epoch": 0.29957805907172996, "progress_pct": 4.99, "epoch_pct": 4.99, "eta": "54:00:09", "max_grad_norm": 1.0, "loss": 0.9124280214309692, "grad_norm": 0.543501615524292, "learning_rate": 0.00012460456942003516}
-{"ts": "2025-12-26T21:07:43", "event": "train_log", "step": 712, "epoch": 0.30042194092827, "progress_pct": 5.01, "epoch_pct": 5.01, "eta": "53:55:30", "max_grad_norm": 1.0, "loss": 0.9820216298103333, "grad_norm": 0.49590054154396057, "learning_rate": 0.0001249560632688928}
-{"ts": "2025-12-26T21:07:57", "event": "train_log", "step": 714, "epoch": 0.3012658227848101, "progress_pct": 5.02, "epoch_pct": 5.02, "eta": "53:50:31", "max_grad_norm": 1.0, "loss": 1.0152074098587036, "grad_norm": 0.5984305739402771, "learning_rate": 0.00012530755711775044}
-{"ts": "2025-12-26T21:08:13", "event": "train_log", "step": 716, "epoch": 0.30210970464135023, "progress_pct": 5.04, "epoch_pct": 5.04, "eta": "53:46:08", "max_grad_norm": 1.0, "loss": 1.0577725172042847, "grad_norm": 0.9343504905700684, "learning_rate": 0.00012565905096660807}
-{"ts": "2025-12-26T21:08:29", "event": "train_log", "step": 718, "epoch": 0.3029535864978903, "progress_pct": 5.05, "epoch_pct": 5.05, "eta": "53:41:40", "max_grad_norm": 1.0, "loss": 0.9830358028411865, "grad_norm": 0.5118702054023743, "learning_rate": 0.0001260105448154657}
-{"ts": "2025-12-26T21:08:46", "event": "train_log", "step": 720, "epoch": 0.3037974683544304, "progress_pct": 5.06, "epoch_pct": 5.06, "eta": "53:37:36", "max_grad_norm": 1.0, "loss": 0.9466043710708618, "grad_norm": 0.4940392076969147, "learning_rate": 0.00012636203866432338}
-{"ts": "2025-12-26T21:09:01", "event": "train_log", "step": 722, "epoch": 0.30464135021097044, "progress_pct": 5.08, "epoch_pct": 5.08, "eta": "53:32:47", "max_grad_norm": 1.0, "loss": 1.015270709991455, "grad_norm": 0.5965693593025208, "learning_rate": 0.00012671353251318104}
-{"ts": "2025-12-26T21:09:18", "event": "train_log", "step": 724, "epoch": 0.30548523206751055, "progress_pct": 5.09, "epoch_pct": 5.09, "eta": "53:28:39", "max_grad_norm": 1.0, "loss": 0.9703927636146545, "grad_norm": 0.5020529627799988, "learning_rate": 0.00012706502636203868}
-{"ts": "2025-12-26T21:09:33", "event": "train_log", "step": 726, "epoch": 0.30632911392405066, "progress_pct": 5.11, "epoch_pct": 5.11, "eta": "53:23:58", "max_grad_norm": 1.0, "loss": 1.0255526304244995, "grad_norm": 0.6067010164260864, "learning_rate": 0.00012741652021089632}
-{"ts": "2025-12-26T21:09:48", "event": "train_log", "step": 728, "epoch": 0.3071729957805907, "progress_pct": 5.12, "epoch_pct": 5.12, "eta": "53:19:18", "max_grad_norm": 1.0, "loss": 0.9335633516311646, "grad_norm": 0.5931884050369263, "learning_rate": 0.00012776801405975396}
-{"ts": "2025-12-26T21:10:03", "event": "train_log", "step": 730, "epoch": 0.3080168776371308, "progress_pct": 5.13, "epoch_pct": 5.13, "eta": "53:14:39", "max_grad_norm": 1.0, "loss": 1.0921578407287598, "grad_norm": 0.5938752293586731, "learning_rate": 0.0001281195079086116}
-{"ts": "2025-12-26T21:10:19", "event": "train_log", "step": 732, "epoch": 0.30886075949367087, "progress_pct": 5.15, "epoch_pct": 5.15, "eta": "53:10:26", "max_grad_norm": 1.0, "loss": 0.963066041469574, "grad_norm": 0.49728086590766907, "learning_rate": 0.00012847100175746923}
-{"ts": "2025-12-26T21:10:34", "event": "train_log", "step": 734, "epoch": 0.309704641350211, "progress_pct": 5.16, "epoch_pct": 5.16, "eta": "53:05:50", "max_grad_norm": 1.0, "loss": 0.9513075351715088, "grad_norm": 0.5452080965042114, "learning_rate": 0.0001288224956063269}
-{"ts": "2025-12-26T21:10:50", "event": "train_log", "step": 736, "epoch": 0.3105485232067511, "progress_pct": 5.18, "epoch_pct": 5.18, "eta": "53:01:38", "max_grad_norm": 1.0, "loss": 0.8576077222824097, "grad_norm": 0.5497731566429138, "learning_rate": 0.00012917398945518454}
-{"ts": "2025-12-26T21:11:04", "event": "train_log", "step": 738, "epoch": 0.31139240506329113, "progress_pct": 5.19, "epoch_pct": 5.19, "eta": "52:56:46", "max_grad_norm": 1.0, "loss": 0.9542577862739563, "grad_norm": 0.5580397248268127, "learning_rate": 0.0001295254833040422}
-{"ts": "2025-12-26T21:11:18", "event": "train_log", "step": 740, "epoch": 0.31223628691983124, "progress_pct": 5.2, "epoch_pct": 5.2, "eta": "52:52:06", "max_grad_norm": 1.0, "loss": 0.8992732167243958, "grad_norm": 0.5890427827835083, "learning_rate": 0.00012987697715289984}
-{"ts": "2025-12-26T21:11:33", "event": "train_log", "step": 742, "epoch": 0.3130801687763713, "progress_pct": 5.22, "epoch_pct": 5.22, "eta": "52:47:38", "max_grad_norm": 1.0, "loss": 1.0322896242141724, "grad_norm": 0.5942965745925903, "learning_rate": 0.00013022847100175748}
-{"ts": "2025-12-26T21:11:49", "event": "train_log", "step": 744, "epoch": 0.3139240506329114, "progress_pct": 5.23, "epoch_pct": 5.23, "eta": "52:43:20", "max_grad_norm": 1.0, "loss": 0.9217103719711304, "grad_norm": 0.6341713070869446, "learning_rate": 0.00013057996485061512}
-{"ts": "2025-12-26T21:12:04", "event": "train_log", "step": 746, "epoch": 0.31476793248945145, "progress_pct": 5.25, "epoch_pct": 5.25, "eta": "52:38:57", "max_grad_norm": 1.0, "loss": 0.951789915561676, "grad_norm": 0.5294105410575867, "learning_rate": 0.00013093145869947276}
-{"ts": "2025-12-26T21:12:19", "event": "train_log", "step": 748, "epoch": 0.31561181434599156, "progress_pct": 5.26, "epoch_pct": 5.26, "eta": "52:34:32", "max_grad_norm": 1.0, "loss": 0.9459875226020813, "grad_norm": 0.6372058391571045, "learning_rate": 0.0001312829525483304}
-{"ts": "2025-12-26T21:12:34", "event": "train_log", "step": 750, "epoch": 0.31645569620253167, "progress_pct": 5.27, "epoch_pct": 5.27, "eta": "52:30:09", "max_grad_norm": 1.0, "loss": 0.9626097679138184, "grad_norm": 0.5979796648025513, "learning_rate": 0.00013163444639718806}
-{"ts": "2025-12-26T21:12:50", "event": "train_log", "step": 752, "epoch": 0.3172995780590717, "progress_pct": 5.29, "epoch_pct": 5.29, "eta": "52:26:08", "max_grad_norm": 1.0, "loss": 1.0261781215667725, "grad_norm": 0.5682399868965149, "learning_rate": 0.0001319859402460457}
-{"ts": "2025-12-26T21:13:06", "event": "train_log", "step": 754, "epoch": 0.3181434599156118, "progress_pct": 5.3, "epoch_pct": 5.3, "eta": "52:22:05", "max_grad_norm": 1.0, "loss": 0.9319828152656555, "grad_norm": 0.5349125266075134, "learning_rate": 0.00013233743409490336}
-{"ts": "2025-12-26T21:13:22", "event": "train_log", "step": 756, "epoch": 0.3189873417721519, "progress_pct": 5.32, "epoch_pct": 5.32, "eta": "52:17:54", "max_grad_norm": 1.0, "loss": 0.9216550588607788, "grad_norm": 0.6093934178352356, "learning_rate": 0.000132688927943761}
-{"ts": "2025-12-26T21:13:37", "event": "train_log", "step": 758, "epoch": 0.319831223628692, "progress_pct": 5.33, "epoch_pct": 5.33, "eta": "52:13:46", "max_grad_norm": 1.0, "loss": 0.901739776134491, "grad_norm": 0.5188612341880798, "learning_rate": 0.00013304042179261864}
-{"ts": "2025-12-26T21:13:52", "event": "train_log", "step": 760, "epoch": 0.3206751054852321, "progress_pct": 5.34, "epoch_pct": 5.34, "eta": "52:09:30", "max_grad_norm": 1.0, "loss": 1.0362589359283447, "grad_norm": 0.5877130627632141, "learning_rate": 0.00013339191564147628}
-{"ts": "2025-12-26T21:14:08", "event": "train_log", "step": 762, "epoch": 0.32151898734177214, "progress_pct": 5.36, "epoch_pct": 5.36, "eta": "52:05:22", "max_grad_norm": 1.0, "loss": 0.8787116408348083, "grad_norm": 0.5542771816253662, "learning_rate": 0.00013374340949033392}
-{"ts": "2025-12-26T21:14:24", "event": "train_log", "step": 764, "epoch": 0.32236286919831225, "progress_pct": 5.37, "epoch_pct": 5.37, "eta": "52:01:24", "max_grad_norm": 1.0, "loss": 0.9237037301063538, "grad_norm": 0.5084902048110962, "learning_rate": 0.00013409490333919156}
-{"ts": "2025-12-26T21:14:40", "event": "train_log", "step": 766, "epoch": 0.3232067510548523, "progress_pct": 5.39, "epoch_pct": 5.39, "eta": "51:57:27", "max_grad_norm": 1.0, "loss": 1.0150731801986694, "grad_norm": 0.5461528301239014, "learning_rate": 0.00013444639718804922}
-{"ts": "2025-12-26T21:14:56", "event": "train_log", "step": 768, "epoch": 0.3240506329113924, "progress_pct": 5.4, "epoch_pct": 5.4, "eta": "51:53:36", "max_grad_norm": 1.0, "loss": 0.8985214829444885, "grad_norm": 0.53483647108078, "learning_rate": 0.00013479789103690686}
-{"ts": "2025-12-26T21:15:11", "event": "train_log", "step": 770, "epoch": 0.32489451476793246, "progress_pct": 5.41, "epoch_pct": 5.41, "eta": "51:49:35", "max_grad_norm": 1.0, "loss": 1.0225775241851807, "grad_norm": 0.5580531358718872, "learning_rate": 0.0001351493848857645}
-{"ts": "2025-12-26T21:15:27", "event": "train_log", "step": 772, "epoch": 0.32573839662447257, "progress_pct": 5.43, "epoch_pct": 5.43, "eta": "51:45:42", "max_grad_norm": 1.0, "loss": 0.9571293592453003, "grad_norm": 0.5203377604484558, "learning_rate": 0.00013550087873462216}
-{"ts": "2025-12-26T21:15:43", "event": "train_log", "step": 774, "epoch": 0.3265822784810127, "progress_pct": 5.44, "epoch_pct": 5.44, "eta": "51:41:44", "max_grad_norm": 1.0, "loss": 1.0468909740447998, "grad_norm": 0.5049671530723572, "learning_rate": 0.0001358523725834798}
-{"ts": "2025-12-26T21:16:00", "event": "train_log", "step": 776, "epoch": 0.32742616033755273, "progress_pct": 5.46, "epoch_pct": 5.46, "eta": "51:38:13", "max_grad_norm": 1.0, "loss": 0.7743215560913086, "grad_norm": 0.4723063111305237, "learning_rate": 0.00013620386643233744}
-{"ts": "2025-12-26T21:16:16", "event": "train_log", "step": 778, "epoch": 0.32827004219409284, "progress_pct": 5.47, "epoch_pct": 5.47, "eta": "51:34:17", "max_grad_norm": 1.0, "loss": 1.021510362625122, "grad_norm": 0.6310980916023254, "learning_rate": 0.00013655536028119508}
-{"ts": "2025-12-26T21:16:31", "event": "train_log", "step": 780, "epoch": 0.3291139240506329, "progress_pct": 5.49, "epoch_pct": 5.49, "eta": "51:30:25", "max_grad_norm": 1.0, "loss": 0.9134382605552673, "grad_norm": 0.47066664695739746, "learning_rate": 0.00013690685413005274}
-{"ts": "2025-12-26T21:16:47", "event": "train_log", "step": 782, "epoch": 0.329957805907173, "progress_pct": 5.5, "epoch_pct": 5.5, "eta": "51:26:32", "max_grad_norm": 1.0, "loss": 0.9797834753990173, "grad_norm": 0.5725092887878418, "learning_rate": 0.00013725834797891038}
-{"ts": "2025-12-26T21:17:04", "event": "train_log", "step": 784, "epoch": 0.3308016877637131, "progress_pct": 5.51, "epoch_pct": 5.51, "eta": "51:23:03", "max_grad_norm": 1.0, "loss": 0.9372621178627014, "grad_norm": 0.5139563083648682, "learning_rate": 0.00013760984182776802}
-{"ts": "2025-12-26T21:17:19", "event": "train_log", "step": 786, "epoch": 0.33164556962025316, "progress_pct": 5.53, "epoch_pct": 5.53, "eta": "51:18:56", "max_grad_norm": 1.0, "loss": 0.9528245329856873, "grad_norm": 0.5275821685791016, "learning_rate": 0.00013796133567662566}
-{"ts": "2025-12-26T21:17:34", "event": "train_log", "step": 788, "epoch": 0.33248945147679326, "progress_pct": 5.54, "epoch_pct": 5.54, "eta": "51:14:59", "max_grad_norm": 1.0, "loss": 0.9750176072120667, "grad_norm": 0.5702582001686096, "learning_rate": 0.0001383128295254833}
-{"ts": "2025-12-26T21:17:49", "event": "train_log", "step": 790, "epoch": 0.3333333333333333, "progress_pct": 5.56, "epoch_pct": 5.56, "eta": "51:11:03", "max_grad_norm": 1.0, "loss": 0.9412306547164917, "grad_norm": 0.5281293392181396, "learning_rate": 0.00013866432337434096}
-{"ts": "2025-12-26T21:18:05", "event": "train_log", "step": 792, "epoch": 0.3341772151898734, "progress_pct": 5.57, "epoch_pct": 5.57, "eta": "51:07:18", "max_grad_norm": 1.0, "loss": 0.997580885887146, "grad_norm": 0.5578986406326294, "learning_rate": 0.0001390158172231986}
-{"ts": "2025-12-26T21:18:21", "event": "train_log", "step": 794, "epoch": 0.33502109704641353, "progress_pct": 5.58, "epoch_pct": 5.58, "eta": "51:03:36", "max_grad_norm": 1.0, "loss": 0.9082320928573608, "grad_norm": 0.50461345911026, "learning_rate": 0.00013936731107205624}
-{"ts": "2025-12-26T21:18:36", "event": "train_log", "step": 796, "epoch": 0.3358649789029536, "progress_pct": 5.6, "epoch_pct": 5.6, "eta": "50:59:41", "max_grad_norm": 1.0, "loss": 1.0082844495773315, "grad_norm": 0.5258530378341675, "learning_rate": 0.0001397188049209139}
-{"ts": "2025-12-26T21:18:50", "event": "train_log", "step": 798, "epoch": 0.3367088607594937, "progress_pct": 5.61, "epoch_pct": 5.61, "eta": "50:55:38", "max_grad_norm": 1.0, "loss": 0.9729003310203552, "grad_norm": 0.5548169016838074, "learning_rate": 0.00014007029876977154}
-{"ts": "2025-12-26T21:19:06", "event": "train_log", "step": 800, "epoch": 0.33755274261603374, "progress_pct": 5.63, "epoch_pct": 5.63, "eta": "50:51:55", "max_grad_norm": 1.0, "loss": 0.9099526405334473, "grad_norm": 0.48601076006889343, "learning_rate": 0.00014042179261862918}
-{"ts": "2025-12-26T21:30:25", "event": "train_log", "step": 800, "epoch": 0.33755274261603374, "progress_pct": 5.63, "epoch_pct": 5.63, "eta": "54:01:42", "max_grad_norm": 1.0, "eval_loss": 0.9800403714179993, "eval_runtime": 678.8306, "eval_samples_per_second": 3.104, "eval_steps_per_second": 3.104}
-{"ts": "2025-12-26T21:30:40", "event": "train_log", "step": 802, "epoch": 0.33839662447257385, "progress_pct": 5.64, "epoch_pct": 5.64, "eta": "53:57:18", "max_grad_norm": 1.0, "loss": 0.8610644936561584, "grad_norm": 0.5413158535957336, "learning_rate": 0.00014077328646748682}
-{"ts": "2025-12-26T21:30:55", "event": "train_log", "step": 804, "epoch": 0.3392405063291139, "progress_pct": 5.65, "epoch_pct": 5.65, "eta": "53:53:04", "max_grad_norm": 1.0, "loss": 0.9584825038909912, "grad_norm": 0.5147035717964172, "learning_rate": 0.00014112478031634446}
-{"ts": "2025-12-26T21:31:10", "event": "train_log", "step": 806, "epoch": 0.340084388185654, "progress_pct": 5.67, "epoch_pct": 5.67, "eta": "53:48:43", "max_grad_norm": 1.0, "loss": 1.0142558813095093, "grad_norm": 0.5931771397590637, "learning_rate": 0.0001414762741652021}
-{"ts": "2025-12-26T21:31:25", "event": "train_log", "step": 808, "epoch": 0.3409282700421941, "progress_pct": 5.68, "epoch_pct": 5.68, "eta": "53:44:25", "max_grad_norm": 1.0, "loss": 1.0078763961791992, "grad_norm": 0.5178377032279968, "learning_rate": 0.00014182776801405976}
-{"ts": "2025-12-26T21:31:41", "event": "train_log", "step": 810, "epoch": 0.34177215189873417, "progress_pct": 5.7, "epoch_pct": 5.7, "eta": "53:40:22", "max_grad_norm": 1.0, "loss": 0.9107215404510498, "grad_norm": 0.5453237295150757, "learning_rate": 0.0001421792618629174}
-{"ts": "2025-12-26T21:31:56", "event": "train_log", "step": 812, "epoch": 0.3426160337552743, "progress_pct": 5.71, "epoch_pct": 5.71, "eta": "53:35:55", "max_grad_norm": 1.0, "loss": 0.9981362819671631, "grad_norm": 0.5886152982711792, "learning_rate": 0.00014253075571177506}
-{"ts": "2025-12-26T21:32:11", "event": "train_log", "step": 814, "epoch": 0.3434599156118143, "progress_pct": 5.72, "epoch_pct": 5.72, "eta": "53:31:45", "max_grad_norm": 1.0, "loss": 0.9636131525039673, "grad_norm": 0.48040178418159485, "learning_rate": 0.0001428822495606327}
-{"ts": "2025-12-26T21:32:26", "event": "train_log", "step": 816, "epoch": 0.34430379746835443, "progress_pct": 5.74, "epoch_pct": 5.74, "eta": "53:27:21", "max_grad_norm": 1.0, "loss": 0.9590586423873901, "grad_norm": 0.5011753439903259, "learning_rate": 0.00014323374340949034}
-{"ts": "2025-12-26T21:32:40", "event": "train_log", "step": 818, "epoch": 0.34514767932489454, "progress_pct": 5.75, "epoch_pct": 5.75, "eta": "53:23:00", "max_grad_norm": 1.0, "loss": 0.978246808052063, "grad_norm": 0.57858806848526, "learning_rate": 0.00014358523725834798}
-{"ts": "2025-12-26T21:32:56", "event": "train_log", "step": 820, "epoch": 0.3459915611814346, "progress_pct": 5.77, "epoch_pct": 5.77, "eta": "53:19:00", "max_grad_norm": 1.0, "loss": 0.8549934029579163, "grad_norm": 0.46092939376831055, "learning_rate": 0.00014393673110720562}
-{"ts": "2025-12-26T21:33:11", "event": "train_log", "step": 822, "epoch": 0.3468354430379747, "progress_pct": 5.78, "epoch_pct": 5.78, "eta": "53:14:47", "max_grad_norm": 1.0, "loss": 0.9771265387535095, "grad_norm": 0.5756489038467407, "learning_rate": 0.00014428822495606326}
-{"ts": "2025-12-26T21:33:26", "event": "train_log", "step": 824, "epoch": 0.34767932489451475, "progress_pct": 5.79, "epoch_pct": 5.79, "eta": "53:10:41", "max_grad_norm": 1.0, "loss": 0.8739748001098633, "grad_norm": 0.5501731634140015, "learning_rate": 0.00014463971880492092}
-{"ts": "2025-12-26T21:33:40", "event": "train_log", "step": 826, "epoch": 0.34852320675105486, "progress_pct": 5.81, "epoch_pct": 5.81, "eta": "53:06:23", "max_grad_norm": 1.0, "loss": 0.9129468202590942, "grad_norm": 0.5451868176460266, "learning_rate": 0.0001449912126537786}
-{"ts": "2025-12-26T21:33:56", "event": "train_log", "step": 828, "epoch": 0.3493670886075949, "progress_pct": 5.82, "epoch_pct": 5.82, "eta": "53:02:18", "max_grad_norm": 1.0, "loss": 0.9196704030036926, "grad_norm": 0.4624619781970978, "learning_rate": 0.00014534270650263623}
-{"ts": "2025-12-26T21:34:10", "event": "train_log", "step": 830, "epoch": 0.350210970464135, "progress_pct": 5.84, "epoch_pct": 5.84, "eta": "52:58:07", "max_grad_norm": 1.0, "loss": 0.9976527690887451, "grad_norm": 0.520878791809082, "learning_rate": 0.00014569420035149386}
-{"ts": "2025-12-26T21:34:26", "event": "train_log", "step": 832, "epoch": 0.3510548523206751, "progress_pct": 5.85, "epoch_pct": 5.85, "eta": "52:54:12", "max_grad_norm": 1.0, "loss": 0.7753443717956543, "grad_norm": 0.4469171464443207, "learning_rate": 0.0001460456942003515}
-{"ts": "2025-12-26T21:34:40", "event": "train_log", "step": 834, "epoch": 0.3518987341772152, "progress_pct": 5.86, "epoch_pct": 5.86, "eta": "52:49:58", "max_grad_norm": 1.0, "loss": 0.9584846496582031, "grad_norm": 0.5105249881744385, "learning_rate": 0.00014639718804920914}
-{"ts": "2025-12-26T21:34:57", "event": "train_log", "step": 836, "epoch": 0.3527426160337553, "progress_pct": 5.88, "epoch_pct": 5.88, "eta": "52:46:15", "max_grad_norm": 1.0, "loss": 0.9013500213623047, "grad_norm": 0.5043913125991821, "learning_rate": 0.00014674868189806678}
-{"ts": "2025-12-26T21:35:11", "event": "train_log", "step": 838, "epoch": 0.35358649789029534, "progress_pct": 5.89, "epoch_pct": 5.89, "eta": "52:41:58", "max_grad_norm": 1.0, "loss": 0.9775562286376953, "grad_norm": 0.575850784778595, "learning_rate": 0.00014710017574692442}
-{"ts": "2025-12-26T21:35:25", "event": "train_log", "step": 840, "epoch": 0.35443037974683544, "progress_pct": 5.91, "epoch_pct": 5.91, "eta": "52:37:44", "max_grad_norm": 1.0, "loss": 0.9278940558433533, "grad_norm": 0.5128876566886902, "learning_rate": 0.00014745166959578208}
-{"ts": "2025-12-26T21:35:40", "event": "train_log", "step": 842, "epoch": 0.35527426160337555, "progress_pct": 5.92, "epoch_pct": 5.92, "eta": "52:33:47", "max_grad_norm": 1.0, "loss": 1.0091488361358643, "grad_norm": 0.5757885575294495, "learning_rate": 0.00014780316344463975}
-{"ts": "2025-12-26T21:35:55", "event": "train_log", "step": 844, "epoch": 0.3561181434599156, "progress_pct": 5.94, "epoch_pct": 5.94, "eta": "52:29:53", "max_grad_norm": 1.0, "loss": 0.9286836981773376, "grad_norm": 0.500934898853302, "learning_rate": 0.00014815465729349739}
-{"ts": "2025-12-26T21:36:10", "event": "train_log", "step": 846, "epoch": 0.3569620253164557, "progress_pct": 5.95, "epoch_pct": 5.95, "eta": "52:25:58", "max_grad_norm": 1.0, "loss": 0.9484171867370605, "grad_norm": 0.5220686197280884, "learning_rate": 0.00014850615114235502}
-{"ts": "2025-12-26T21:36:26", "event": "train_log", "step": 848, "epoch": 0.35780590717299576, "progress_pct": 5.96, "epoch_pct": 5.96, "eta": "52:22:05", "max_grad_norm": 1.0, "loss": 1.0556397438049316, "grad_norm": 0.5494697690010071, "learning_rate": 0.00014885764499121266}
-{"ts": "2025-12-26T21:36:41", "event": "train_log", "step": 850, "epoch": 0.35864978902953587, "progress_pct": 5.98, "epoch_pct": 5.98, "eta": "52:18:16", "max_grad_norm": 1.0, "loss": 0.933089017868042, "grad_norm": 0.46633943915367126, "learning_rate": 0.0001492091388400703}
-{"ts": "2025-12-26T21:36:56", "event": "train_log", "step": 852, "epoch": 0.3594936708860759, "progress_pct": 5.99, "epoch_pct": 5.99, "eta": "52:14:19", "max_grad_norm": 1.0, "loss": 1.0016963481903076, "grad_norm": 0.4864962697029114, "learning_rate": 0.00014956063268892794}
-{"ts": "2025-12-26T21:37:10", "event": "train_log", "step": 854, "epoch": 0.36033755274261603, "progress_pct": 6.01, "epoch_pct": 6.01, "eta": "52:10:17", "max_grad_norm": 1.0, "loss": 0.9085348844528198, "grad_norm": 0.5032764673233032, "learning_rate": 0.0001499121265377856}
-{"ts": "2025-12-26T21:37:25", "event": "train_log", "step": 856, "epoch": 0.36118143459915614, "progress_pct": 6.02, "epoch_pct": 6.02, "eta": "52:06:22", "max_grad_norm": 1.0, "loss": 0.923502504825592, "grad_norm": 0.5424998998641968, "learning_rate": 0.00015026362038664324}
-{"ts": "2025-12-26T21:37:40", "event": "train_log", "step": 858, "epoch": 0.3620253164556962, "progress_pct": 6.03, "epoch_pct": 6.03, "eta": "52:02:28", "max_grad_norm": 1.0, "loss": 0.919174313545227, "grad_norm": 0.5181655287742615, "learning_rate": 0.00015061511423550088}
-{"ts": "2025-12-26T21:37:56", "event": "train_log", "step": 860, "epoch": 0.3628691983122363, "progress_pct": 6.05, "epoch_pct": 6.05, "eta": "51:58:46", "max_grad_norm": 1.0, "loss": 0.851981520652771, "grad_norm": 0.5129443407058716, "learning_rate": 0.00015096660808435855}
-{"ts": "2025-12-26T21:38:11", "event": "train_log", "step": 862, "epoch": 0.36371308016877635, "progress_pct": 6.06, "epoch_pct": 6.06, "eta": "51:55:02", "max_grad_norm": 1.0, "loss": 0.8633858561515808, "grad_norm": 0.49540698528289795, "learning_rate": 0.00015131810193321618}
-{"ts": "2025-12-26T21:38:26", "event": "train_log", "step": 864, "epoch": 0.36455696202531646, "progress_pct": 6.08, "epoch_pct": 6.08, "eta": "51:51:17", "max_grad_norm": 1.0, "loss": 0.9473677277565002, "grad_norm": 0.4706701934337616, "learning_rate": 0.00015166959578207382}
-{"ts": "2025-12-26T21:38:41", "event": "train_log", "step": 866, "epoch": 0.36540084388185656, "progress_pct": 6.09, "epoch_pct": 6.09, "eta": "51:47:31", "max_grad_norm": 1.0, "loss": 0.942383885383606, "grad_norm": 0.587704598903656, "learning_rate": 0.00015202108963093146}
-{"ts": "2025-12-26T21:38:58", "event": "train_log", "step": 868, "epoch": 0.3662447257383966, "progress_pct": 6.1, "epoch_pct": 6.1, "eta": "51:44:02", "max_grad_norm": 1.0, "loss": 0.9811251163482666, "grad_norm": 0.5851273536682129, "learning_rate": 0.0001523725834797891}
-{"ts": "2025-12-26T21:39:13", "event": "train_log", "step": 870, "epoch": 0.3670886075949367, "progress_pct": 6.12, "epoch_pct": 6.12, "eta": "51:40:24", "max_grad_norm": 1.0, "loss": 0.8151084184646606, "grad_norm": 0.46357613801956177, "learning_rate": 0.00015272407732864676}
-{"ts": "2025-12-26T21:39:30", "event": "train_log", "step": 872, "epoch": 0.3679324894514768, "progress_pct": 6.13, "epoch_pct": 6.13, "eta": "51:37:04", "max_grad_norm": 1.0, "loss": 0.9023333191871643, "grad_norm": 0.47250670194625854, "learning_rate": 0.0001530755711775044}
-{"ts": "2025-12-26T21:39:45", "event": "train_log", "step": 874, "epoch": 0.3687763713080169, "progress_pct": 6.15, "epoch_pct": 6.15, "eta": "51:33:29", "max_grad_norm": 1.0, "loss": 0.8758499622344971, "grad_norm": 0.47510042786598206, "learning_rate": 0.00015342706502636204}
-{"ts": "2025-12-26T21:40:00", "event": "train_log", "step": 876, "epoch": 0.369620253164557, "progress_pct": 6.16, "epoch_pct": 6.16, "eta": "51:29:37", "max_grad_norm": 1.0, "loss": 0.9837421774864197, "grad_norm": 0.5687124729156494, "learning_rate": 0.00015377855887521968}
-{"ts": "2025-12-26T21:40:15", "event": "train_log", "step": 878, "epoch": 0.37046413502109704, "progress_pct": 6.17, "epoch_pct": 6.17, "eta": "51:25:57", "max_grad_norm": 1.0, "loss": 0.9084216356277466, "grad_norm": 0.49064236879348755, "learning_rate": 0.00015413005272407735}
-{"ts": "2025-12-26T21:40:31", "event": "train_log", "step": 880, "epoch": 0.37130801687763715, "progress_pct": 6.19, "epoch_pct": 6.19, "eta": "51:22:31", "max_grad_norm": 1.0, "loss": 0.8425542712211609, "grad_norm": 0.5288164615631104, "learning_rate": 0.00015448154657293498}
-{"ts": "2025-12-26T21:40:46", "event": "train_log", "step": 882, "epoch": 0.3721518987341772, "progress_pct": 6.2, "epoch_pct": 6.2, "eta": "51:18:48", "max_grad_norm": 1.0, "loss": 1.006197452545166, "grad_norm": 0.5446951985359192, "learning_rate": 0.00015483304042179262}
-{"ts": "2025-12-26T21:41:02", "event": "train_log", "step": 884, "epoch": 0.3729957805907173, "progress_pct": 6.22, "epoch_pct": 6.22, "eta": "51:15:32", "max_grad_norm": 1.0, "loss": 0.9779444932937622, "grad_norm": 0.46872642636299133, "learning_rate": 0.00015518453427065026}
-{"ts": "2025-12-26T21:41:19", "event": "train_log", "step": 886, "epoch": 0.37383966244725736, "progress_pct": 6.23, "epoch_pct": 6.23, "eta": "51:12:13", "max_grad_norm": 1.0, "loss": 0.9099963307380676, "grad_norm": 0.4852714240550995, "learning_rate": 0.00015553602811950793}
-{"ts": "2025-12-26T21:41:35", "event": "train_log", "step": 888, "epoch": 0.37468354430379747, "progress_pct": 6.24, "epoch_pct": 6.24, "eta": "51:08:57", "max_grad_norm": 1.0, "loss": 0.9730570316314697, "grad_norm": 0.5219841003417969, "learning_rate": 0.00015588752196836556}
-{"ts": "2025-12-26T21:41:50", "event": "train_log", "step": 890, "epoch": 0.3755274261603376, "progress_pct": 6.26, "epoch_pct": 6.26, "eta": "51:05:18", "max_grad_norm": 1.0, "loss": 0.9304586052894592, "grad_norm": 0.5258626341819763, "learning_rate": 0.0001562390158172232}
-{"ts": "2025-12-26T21:42:07", "event": "train_log", "step": 892, "epoch": 0.3763713080168776, "progress_pct": 6.27, "epoch_pct": 6.27, "eta": "51:02:19", "max_grad_norm": 1.0, "loss": 0.8680716156959534, "grad_norm": 0.4266716241836548, "learning_rate": 0.00015659050966608084}
-{"ts": "2025-12-26T21:42:23", "event": "train_log", "step": 894, "epoch": 0.37721518987341773, "progress_pct": 6.29, "epoch_pct": 6.29, "eta": "50:59:00", "max_grad_norm": 1.0, "loss": 0.8428018093109131, "grad_norm": 0.46361327171325684, "learning_rate": 0.0001569420035149385}
-{"ts": "2025-12-26T21:42:39", "event": "train_log", "step": 896, "epoch": 0.3780590717299578, "progress_pct": 6.3, "epoch_pct": 6.3, "eta": "50:55:40", "max_grad_norm": 1.0, "loss": 0.8465750217437744, "grad_norm": 0.5313687920570374, "learning_rate": 0.00015729349736379614}
-{"ts": "2025-12-26T21:42:54", "event": "train_log", "step": 898, "epoch": 0.3789029535864979, "progress_pct": 6.32, "epoch_pct": 6.32, "eta": "50:52:08", "max_grad_norm": 1.0, "loss": 0.9120327234268188, "grad_norm": 0.47166210412979126, "learning_rate": 0.00015764499121265378}
-{"ts": "2025-12-26T21:43:10", "event": "train_log", "step": 900, "epoch": 0.379746835443038, "progress_pct": 6.33, "epoch_pct": 6.33, "eta": "50:48:52", "max_grad_norm": 1.0, "loss": 0.8950425982475281, "grad_norm": 0.4647318720817566, "learning_rate": 0.00015799648506151145}
-{"ts": "2025-12-26T21:54:42", "event": "train_log", "step": 900, "epoch": 0.379746835443038, "progress_pct": 6.33, "epoch_pct": 6.33, "eta": "53:39:30", "max_grad_norm": 1.0, "eval_loss": 0.9643027186393738, "eval_runtime": 691.7929, "eval_samples_per_second": 3.046, "eval_steps_per_second": 3.046}
-{"ts": "2025-12-26T21:54:57", "event": "train_log", "step": 902, "epoch": 0.38059071729957805, "progress_pct": 6.34, "epoch_pct": 6.34, "eta": "53:35:36", "max_grad_norm": 1.0, "loss": 0.908163845539093, "grad_norm": 0.5445119738578796, "learning_rate": 0.00015834797891036909}
-{"ts": "2025-12-26T21:55:13", "event": "train_log", "step": 904, "epoch": 0.38143459915611816, "progress_pct": 6.36, "epoch_pct": 6.36, "eta": "53:31:48", "max_grad_norm": 1.0, "loss": 0.8945821523666382, "grad_norm": 0.4311858117580414, "learning_rate": 0.00015869947275922672}
-{"ts": "2025-12-26T21:55:27", "event": "train_log", "step": 906, "epoch": 0.3822784810126582, "progress_pct": 6.37, "epoch_pct": 6.37, "eta": "53:27:41", "max_grad_norm": 1.0, "loss": 0.9478458762168884, "grad_norm": 0.5590984225273132, "learning_rate": 0.00015905096660808436}
-{"ts": "2025-12-26T21:55:41", "event": "train_log", "step": 908, "epoch": 0.3831223628691983, "progress_pct": 6.39, "epoch_pct": 6.39, "eta": "53:23:40", "max_grad_norm": 1.0, "loss": 0.9259957671165466, "grad_norm": 0.5470241904258728, "learning_rate": 0.000159402460456942}
-{"ts": "2025-12-26T21:55:56", "event": "train_log", "step": 910, "epoch": 0.38396624472573837, "progress_pct": 6.4, "epoch_pct": 6.4, "eta": "53:19:46", "max_grad_norm": 1.0, "loss": 0.8824930787086487, "grad_norm": 0.5498791337013245, "learning_rate": 0.00015975395430579964}
-{"ts": "2025-12-26T21:56:12", "event": "train_log", "step": 912, "epoch": 0.3848101265822785, "progress_pct": 6.41, "epoch_pct": 6.41, "eta": "53:16:04", "max_grad_norm": 1.0, "loss": 0.8842340707778931, "grad_norm": 0.4779198467731476, "learning_rate": 0.0001601054481546573}
-{"ts": "2025-12-26T21:56:27", "event": "train_log", "step": 914, "epoch": 0.3856540084388186, "progress_pct": 6.43, "epoch_pct": 6.43, "eta": "53:12:23", "max_grad_norm": 1.0, "loss": 0.92950040102005, "grad_norm": 0.5390620827674866, "learning_rate": 0.00016045694200351494}
-{"ts": "2025-12-26T21:56:42", "event": "train_log", "step": 916, "epoch": 0.38649789029535864, "progress_pct": 6.44, "epoch_pct": 6.44, "eta": "53:08:24", "max_grad_norm": 1.0, "loss": 0.8420897126197815, "grad_norm": 0.505519688129425, "learning_rate": 0.0001608084358523726}
-{"ts": "2025-12-26T21:56:57", "event": "train_log", "step": 918, "epoch": 0.38734177215189874, "progress_pct": 6.46, "epoch_pct": 6.46, "eta": "53:04:38", "max_grad_norm": 1.0, "loss": 0.8256624341011047, "grad_norm": 0.4463907778263092, "learning_rate": 0.00016115992970123025}
-{"ts": "2025-12-26T21:57:12", "event": "train_log", "step": 920, "epoch": 0.3881856540084388, "progress_pct": 6.47, "epoch_pct": 6.47, "eta": "53:00:53", "max_grad_norm": 1.0, "loss": 0.8701168298721313, "grad_norm": 0.5321422219276428, "learning_rate": 0.00016151142355008788}
-{"ts": "2025-12-26T21:57:27", "event": "train_log", "step": 922, "epoch": 0.3890295358649789, "progress_pct": 6.48, "epoch_pct": 6.48, "eta": "52:57:05", "max_grad_norm": 1.0, "loss": 0.9019309878349304, "grad_norm": 0.4343073070049286, "learning_rate": 0.00016186291739894552}
-{"ts": "2025-12-26T21:57:42", "event": "train_log", "step": 924, "epoch": 0.389873417721519, "progress_pct": 6.5, "epoch_pct": 6.5, "eta": "52:53:23", "max_grad_norm": 1.0, "loss": 0.8560551404953003, "grad_norm": 0.5311984419822693, "learning_rate": 0.00016221441124780316}
-{"ts": "2025-12-26T21:57:56", "event": "train_log", "step": 926, "epoch": 0.39071729957805906, "progress_pct": 6.51, "epoch_pct": 6.51, "eta": "52:49:26", "max_grad_norm": 1.0, "loss": 0.9700050354003906, "grad_norm": 0.588691771030426, "learning_rate": 0.0001625659050966608}
-{"ts": "2025-12-26T21:58:10", "event": "train_log", "step": 928, "epoch": 0.39156118143459917, "progress_pct": 6.53, "epoch_pct": 6.53, "eta": "52:45:28", "max_grad_norm": 1.0, "loss": 1.043768048286438, "grad_norm": 0.5425586104393005, "learning_rate": 0.00016291739894551844}
-{"ts": "2025-12-26T21:58:25", "event": "train_log", "step": 930, "epoch": 0.3924050632911392, "progress_pct": 6.54, "epoch_pct": 6.54, "eta": "52:41:36", "max_grad_norm": 1.0, "loss": 0.9501712918281555, "grad_norm": 0.5228736996650696, "learning_rate": 0.0001632688927943761}
-{"ts": "2025-12-26T21:58:40", "event": "train_log", "step": 932, "epoch": 0.39324894514767933, "progress_pct": 6.55, "epoch_pct": 6.55, "eta": "52:37:56", "max_grad_norm": 1.0, "loss": 0.9223058223724365, "grad_norm": 0.48960360884666443, "learning_rate": 0.00016362038664323377}
-{"ts": "2025-12-26T21:58:55", "event": "train_log", "step": 934, "epoch": 0.39409282700421944, "progress_pct": 6.57, "epoch_pct": 6.57, "eta": "52:34:22", "max_grad_norm": 1.0, "loss": 0.9692960977554321, "grad_norm": 0.45204755663871765, "learning_rate": 0.0001639718804920914}
-{"ts": "2025-12-26T21:59:10", "event": "train_log", "step": 936, "epoch": 0.3949367088607595, "progress_pct": 6.58, "epoch_pct": 6.58, "eta": "52:30:37", "max_grad_norm": 1.0, "loss": 0.9467466473579407, "grad_norm": 0.5299274921417236, "learning_rate": 0.00016432337434094905}
-{"ts": "2025-12-26T21:59:25", "event": "train_log", "step": 938, "epoch": 0.3957805907172996, "progress_pct": 6.6, "epoch_pct": 6.6, "eta": "52:26:58", "max_grad_norm": 1.0, "loss": 0.9118053317070007, "grad_norm": 0.5607715249061584, "learning_rate": 0.00016467486818980668}
-{"ts": "2025-12-26T21:59:39", "event": "train_log", "step": 940, "epoch": 0.39662447257383965, "progress_pct": 6.61, "epoch_pct": 6.61, "eta": "52:23:10", "max_grad_norm": 1.0, "loss": 0.9131460189819336, "grad_norm": 0.5271831154823303, "learning_rate": 0.00016502636203866432}
-{"ts": "2025-12-26T21:59:55", "event": "train_log", "step": 942, "epoch": 0.39746835443037976, "progress_pct": 6.62, "epoch_pct": 6.62, "eta": "52:19:40", "max_grad_norm": 1.0, "loss": 0.9358300566673279, "grad_norm": 0.5075286030769348, "learning_rate": 0.00016537785588752196}
-{"ts": "2025-12-26T22:00:10", "event": "train_log", "step": 944, "epoch": 0.3983122362869198, "progress_pct": 6.64, "epoch_pct": 6.64, "eta": "52:16:02", "max_grad_norm": 1.0, "loss": 0.8908210396766663, "grad_norm": 0.515731155872345, "learning_rate": 0.00016572934973637963}
-{"ts": "2025-12-26T22:00:24", "event": "train_log", "step": 946, "epoch": 0.3991561181434599, "progress_pct": 6.65, "epoch_pct": 6.65, "eta": "52:12:24", "max_grad_norm": 1.0, "loss": 0.9775290489196777, "grad_norm": 0.4856977164745331, "learning_rate": 0.00016608084358523726}
-{"ts": "2025-12-26T22:00:39", "event": "train_log", "step": 948, "epoch": 0.4, "progress_pct": 6.67, "epoch_pct": 6.67, "eta": "52:08:42", "max_grad_norm": 1.0, "loss": 0.8957490921020508, "grad_norm": 0.48846355080604553, "learning_rate": 0.00016643233743409493}
-{"ts": "2025-12-26T22:00:54", "event": "train_log", "step": 950, "epoch": 0.4008438818565401, "progress_pct": 6.68, "epoch_pct": 6.68, "eta": "52:05:14", "max_grad_norm": 1.0, "loss": 0.9036174416542053, "grad_norm": 0.42990800738334656, "learning_rate": 0.00016678383128295257}
-{"ts": "2025-12-26T22:01:09", "event": "train_log", "step": 952, "epoch": 0.4016877637130802, "progress_pct": 6.69, "epoch_pct": 6.69, "eta": "52:01:39", "max_grad_norm": 1.0, "loss": 0.991032600402832, "grad_norm": 0.49552062153816223, "learning_rate": 0.0001671353251318102}
-{"ts": "2025-12-26T22:01:24", "event": "train_log", "step": 954, "epoch": 0.40253164556962023, "progress_pct": 6.71, "epoch_pct": 6.71, "eta": "51:58:06", "max_grad_norm": 1.0, "loss": 0.823063313961029, "grad_norm": 0.4565040171146393, "learning_rate": 0.00016748681898066784}
-{"ts": "2025-12-26T22:01:39", "event": "train_log", "step": 956, "epoch": 0.40337552742616034, "progress_pct": 6.72, "epoch_pct": 6.72, "eta": "51:54:35", "max_grad_norm": 1.0, "loss": 0.8785063624382019, "grad_norm": 0.4290153682231903, "learning_rate": 0.00016783831282952548}
-{"ts": "2025-12-26T22:01:54", "event": "train_log", "step": 958, "epoch": 0.40421940928270045, "progress_pct": 6.74, "epoch_pct": 6.74, "eta": "51:51:01", "max_grad_norm": 1.0, "loss": 0.8763971924781799, "grad_norm": 0.5419702529907227, "learning_rate": 0.00016818980667838312}
-{"ts": "2025-12-26T22:02:09", "event": "train_log", "step": 960, "epoch": 0.4050632911392405, "progress_pct": 6.75, "epoch_pct": 6.75, "eta": "51:47:34", "max_grad_norm": 1.0, "loss": 0.9470553398132324, "grad_norm": 0.5177501440048218, "learning_rate": 0.00016854130052724079}
-{"ts": "2025-12-26T22:02:24", "event": "train_log", "step": 962, "epoch": 0.4059071729957806, "progress_pct": 6.77, "epoch_pct": 6.77, "eta": "51:44:07", "max_grad_norm": 1.0, "loss": 0.9235025644302368, "grad_norm": 0.539725661277771, "learning_rate": 0.00016889279437609842}
-{"ts": "2025-12-26T22:02:38", "event": "train_log", "step": 964, "epoch": 0.40675105485232066, "progress_pct": 6.78, "epoch_pct": 6.78, "eta": "51:40:25", "max_grad_norm": 1.0, "loss": 1.0248996019363403, "grad_norm": 0.5324983596801758, "learning_rate": 0.0001692442882249561}
-{"ts": "2025-12-26T22:02:54", "event": "train_log", "step": 966, "epoch": 0.40759493670886077, "progress_pct": 6.79, "epoch_pct": 6.79, "eta": "51:37:07", "max_grad_norm": 1.0, "loss": 0.9076873660087585, "grad_norm": 0.4936407506465912, "learning_rate": 0.00016959578207381373}
-{"ts": "2025-12-26T22:03:09", "event": "train_log", "step": 968, "epoch": 0.4084388185654008, "progress_pct": 6.81, "epoch_pct": 6.81, "eta": "51:33:42", "max_grad_norm": 1.0, "loss": 0.9162673950195312, "grad_norm": 0.4960501194000244, "learning_rate": 0.00016994727592267137}
-{"ts": "2025-12-26T22:03:24", "event": "train_log", "step": 970, "epoch": 0.4092827004219409, "progress_pct": 6.82, "epoch_pct": 6.82, "eta": "51:30:15", "max_grad_norm": 1.0, "loss": 0.904100775718689, "grad_norm": 0.45093682408332825, "learning_rate": 0.000170298769771529}
-{"ts": "2025-12-26T22:03:39", "event": "train_log", "step": 972, "epoch": 0.41012658227848103, "progress_pct": 6.84, "epoch_pct": 6.84, "eta": "51:26:56", "max_grad_norm": 1.0, "loss": 0.8633337020874023, "grad_norm": 0.4560275077819824, "learning_rate": 0.00017065026362038664}
-{"ts": "2025-12-26T22:03:54", "event": "train_log", "step": 974, "epoch": 0.4109704641350211, "progress_pct": 6.85, "epoch_pct": 6.85, "eta": "51:23:30", "max_grad_norm": 1.0, "loss": 0.8454209566116333, "grad_norm": 0.44885000586509705, "learning_rate": 0.00017100175746924428}
-{"ts": "2025-12-26T22:04:10", "event": "train_log", "step": 976, "epoch": 0.4118143459915612, "progress_pct": 6.86, "epoch_pct": 6.86, "eta": "51:20:11", "max_grad_norm": 1.0, "loss": 0.824730396270752, "grad_norm": 0.47251659631729126, "learning_rate": 0.00017135325131810195}
-{"ts": "2025-12-26T22:04:25", "event": "train_log", "step": 978, "epoch": 0.41265822784810124, "progress_pct": 6.88, "epoch_pct": 6.88, "eta": "51:16:48", "max_grad_norm": 1.0, "loss": 0.9496501684188843, "grad_norm": 0.6597666144371033, "learning_rate": 0.00017170474516695959}
-{"ts": "2025-12-26T22:04:40", "event": "train_log", "step": 980, "epoch": 0.41350210970464135, "progress_pct": 6.89, "epoch_pct": 6.89, "eta": "51:13:28", "max_grad_norm": 1.0, "loss": 0.9419087171554565, "grad_norm": 0.39806297421455383, "learning_rate": 0.00017205623901581722}
-{"ts": "2025-12-26T22:04:55", "event": "train_log", "step": 982, "epoch": 0.41434599156118146, "progress_pct": 6.91, "epoch_pct": 6.91, "eta": "51:10:04", "max_grad_norm": 1.0, "loss": 0.9182976484298706, "grad_norm": 0.48231109976768494, "learning_rate": 0.0001724077328646749}
-{"ts": "2025-12-26T22:05:09", "event": "train_log", "step": 984, "epoch": 0.4151898734177215, "progress_pct": 6.92, "epoch_pct": 6.92, "eta": "51:06:38", "max_grad_norm": 1.0, "loss": 0.9386967420578003, "grad_norm": 0.5438776612281799, "learning_rate": 0.00017275922671353253}
-{"ts": "2025-12-26T22:05:24", "event": "train_log", "step": 986, "epoch": 0.4160337552742616, "progress_pct": 6.93, "epoch_pct": 6.93, "eta": "51:03:21", "max_grad_norm": 1.0, "loss": 0.897849440574646, "grad_norm": 0.4959667921066284, "learning_rate": 0.00017311072056239017}
-{"ts": "2025-12-26T22:05:39", "event": "train_log", "step": 988, "epoch": 0.41687763713080167, "progress_pct": 6.95, "epoch_pct": 6.95, "eta": "51:00:03", "max_grad_norm": 1.0, "loss": 0.8776953816413879, "grad_norm": 0.43533357977867126, "learning_rate": 0.0001734622144112478}
-{"ts": "2025-12-26T22:05:55", "event": "train_log", "step": 990, "epoch": 0.4177215189873418, "progress_pct": 6.96, "epoch_pct": 6.96, "eta": "50:56:52", "max_grad_norm": 1.0, "loss": 0.9162989854812622, "grad_norm": 0.47513946890830994, "learning_rate": 0.00017381370826010547}
-{"ts": "2025-12-26T22:06:10", "event": "train_log", "step": 992, "epoch": 0.41856540084388183, "progress_pct": 6.98, "epoch_pct": 6.98, "eta": "50:53:35", "max_grad_norm": 1.0, "loss": 0.9482660889625549, "grad_norm": 0.4907188415527344, "learning_rate": 0.0001741652021089631}
-{"ts": "2025-12-26T22:06:25", "event": "train_log", "step": 994, "epoch": 0.41940928270042194, "progress_pct": 6.99, "epoch_pct": 6.99, "eta": "50:50:13", "max_grad_norm": 1.0, "loss": 0.8812930583953857, "grad_norm": 0.44499966502189636, "learning_rate": 0.00017451669595782075}
-{"ts": "2025-12-26T22:06:39", "event": "train_log", "step": 996, "epoch": 0.42025316455696204, "progress_pct": 7.0, "epoch_pct": 7.0, "eta": "50:46:55", "max_grad_norm": 1.0, "loss": 0.9439874887466431, "grad_norm": 0.4535730481147766, "learning_rate": 0.00017486818980667838}
-{"ts": "2025-12-26T22:06:54", "event": "train_log", "step": 998, "epoch": 0.4210970464135021, "progress_pct": 7.02, "epoch_pct": 7.02, "eta": "50:43:37", "max_grad_norm": 1.0, "loss": 0.8818395137786865, "grad_norm": 0.5240745544433594, "learning_rate": 0.00017521968365553602}
-{"ts": "2025-12-26T22:07:10", "event": "train_log", "step": 1000, "epoch": 0.4219409282700422, "progress_pct": 7.03, "epoch_pct": 7.03, "eta": "50:40:27", "max_grad_norm": 1.0, "loss": 0.886186957359314, "grad_norm": 0.5301211476325989, "learning_rate": 0.0001755711775043937}
-{"ts": "2025-12-26T22:18:39", "event": "train_log", "step": 1000, "epoch": 0.4219409282700422, "progress_pct": 7.03, "epoch_pct": 7.03, "eta": "53:12:22", "max_grad_norm": 1.0, "eval_loss": 0.9487298727035522, "eval_runtime": 689.4288, "eval_samples_per_second": 3.056, "eval_steps_per_second": 3.056}
-{"ts": "2025-12-26T22:18:56", "event": "train_log", "step": 1002, "epoch": 0.42278481012658226, "progress_pct": 7.05, "epoch_pct": 7.05, "eta": "53:09:18", "max_grad_norm": 1.0, "loss": 0.8814021348953247, "grad_norm": 0.47876957058906555, "learning_rate": 0.00017592267135325133}
-{"ts": "2025-12-26T22:19:13", "event": "train_log", "step": 1004, "epoch": 0.42362869198312236, "progress_pct": 7.06, "epoch_pct": 7.06, "eta": "53:06:07", "max_grad_norm": 1.0, "loss": 0.8295068740844727, "grad_norm": 0.4929780960083008, "learning_rate": 0.00017627416520210896}
-{"ts": "2025-12-26T22:19:30", "event": "train_log", "step": 1006, "epoch": 0.42447257383966247, "progress_pct": 7.07, "epoch_pct": 7.07, "eta": "53:03:03", "max_grad_norm": 1.0, "loss": 0.8364827036857605, "grad_norm": 0.41888436675071716, "learning_rate": 0.00017662565905096663}
-{"ts": "2025-12-26T22:19:46", "event": "train_log", "step": 1008, "epoch": 0.4253164556962025, "progress_pct": 7.09, "epoch_pct": 7.09, "eta": "52:59:39", "max_grad_norm": 1.0, "loss": 1.0167189836502075, "grad_norm": 0.5175151824951172, "learning_rate": 0.00017697715289982427}
-{"ts": "2025-12-26T22:20:01", "event": "train_log", "step": 1010, "epoch": 0.42616033755274263, "progress_pct": 7.1, "epoch_pct": 7.1, "eta": "52:56:17", "max_grad_norm": 1.0, "loss": 0.8460752964019775, "grad_norm": 0.4815356135368347, "learning_rate": 0.0001773286467486819}
-{"ts": "2025-12-26T22:20:16", "event": "train_log", "step": 1012, "epoch": 0.4270042194092827, "progress_pct": 7.12, "epoch_pct": 7.12, "eta": "52:52:48", "max_grad_norm": 1.0, "loss": 0.8595574498176575, "grad_norm": 0.5210875272750854, "learning_rate": 0.00017768014059753954}
-{"ts": "2025-12-26T22:20:32", "event": "train_log", "step": 1014, "epoch": 0.4278481012658228, "progress_pct": 7.13, "epoch_pct": 7.13, "eta": "52:49:35", "max_grad_norm": 1.0, "loss": 0.8764723539352417, "grad_norm": 0.4400486946105957, "learning_rate": 0.00017803163444639718}
-{"ts": "2025-12-26T22:20:48", "event": "train_log", "step": 1016, "epoch": 0.4286919831223629, "progress_pct": 7.14, "epoch_pct": 7.14, "eta": "52:46:12", "max_grad_norm": 1.0, "loss": 0.9706798791885376, "grad_norm": 0.5282127857208252, "learning_rate": 0.00017838312829525482}
-{"ts": "2025-12-26T22:21:04", "event": "train_log", "step": 1018, "epoch": 0.42953586497890295, "progress_pct": 7.16, "epoch_pct": 7.16, "eta": "52:42:56", "max_grad_norm": 1.0, "loss": 0.8912002444267273, "grad_norm": 0.47523441910743713, "learning_rate": 0.00017873462214411249}
-{"ts": "2025-12-26T22:21:19", "event": "train_log", "step": 1020, "epoch": 0.43037974683544306, "progress_pct": 7.17, "epoch_pct": 7.17, "eta": "52:39:37", "max_grad_norm": 1.0, "loss": 0.8835636973381042, "grad_norm": 0.49640706181526184, "learning_rate": 0.00017908611599297012}
-{"ts": "2025-12-26T22:21:35", "event": "train_log", "step": 1022, "epoch": 0.4312236286919831, "progress_pct": 7.19, "epoch_pct": 7.19, "eta": "52:36:18", "max_grad_norm": 1.0, "loss": 0.8711735606193542, "grad_norm": 0.5253039002418518, "learning_rate": 0.0001794376098418278}
-{"ts": "2025-12-26T22:21:50", "event": "train_log", "step": 1024, "epoch": 0.4320675105485232, "progress_pct": 7.2, "epoch_pct": 7.2, "eta": "52:32:59", "max_grad_norm": 1.0, "loss": 0.9064869284629822, "grad_norm": 0.49285009503364563, "learning_rate": 0.00017978910369068543}
-{"ts": "2025-12-26T22:22:05", "event": "train_log", "step": 1026, "epoch": 0.43291139240506327, "progress_pct": 7.22, "epoch_pct": 7.22, "eta": "52:29:36", "max_grad_norm": 1.0, "loss": 0.8993359208106995, "grad_norm": 0.48758041858673096, "learning_rate": 0.00018014059753954307}
-{"ts": "2025-12-26T22:22:20", "event": "train_log", "step": 1028, "epoch": 0.4337552742616034, "progress_pct": 7.23, "epoch_pct": 7.23, "eta": "52:26:09", "max_grad_norm": 1.0, "loss": 0.8747937679290771, "grad_norm": 0.4815461039543152, "learning_rate": 0.0001804920913884007}
-{"ts": "2025-12-26T22:22:35", "event": "train_log", "step": 1030, "epoch": 0.4345991561181435, "progress_pct": 7.24, "epoch_pct": 7.24, "eta": "52:22:49", "max_grad_norm": 1.0, "loss": 0.8879084587097168, "grad_norm": 0.4930349886417389, "learning_rate": 0.00018084358523725834}
-{"ts": "2025-12-26T22:22:51", "event": "train_log", "step": 1032, "epoch": 0.43544303797468353, "progress_pct": 7.26, "epoch_pct": 7.26, "eta": "52:19:29", "max_grad_norm": 1.0, "loss": 1.0023083686828613, "grad_norm": 0.49303027987480164, "learning_rate": 0.00018119507908611598}
-{"ts": "2025-12-26T22:23:06", "event": "train_log", "step": 1034, "epoch": 0.43628691983122364, "progress_pct": 7.27, "epoch_pct": 7.27, "eta": "52:16:17", "max_grad_norm": 1.0, "loss": 0.938680112361908, "grad_norm": 0.5312249064445496, "learning_rate": 0.00018154657293497365}
-{"ts": "2025-12-26T22:23:23", "event": "train_log", "step": 1036, "epoch": 0.4371308016877637, "progress_pct": 7.29, "epoch_pct": 7.29, "eta": "52:13:13", "max_grad_norm": 1.0, "loss": 0.854195773601532, "grad_norm": 0.5174582004547119, "learning_rate": 0.0001818980667838313}
-{"ts": "2025-12-26T22:23:38", "event": "train_log", "step": 1038, "epoch": 0.4379746835443038, "progress_pct": 7.3, "epoch_pct": 7.3, "eta": "52:09:54", "max_grad_norm": 1.0, "loss": 0.9059375524520874, "grad_norm": 0.5452545881271362, "learning_rate": 0.00018224956063268895}
-{"ts": "2025-12-26T22:23:54", "event": "train_log", "step": 1040, "epoch": 0.4388185654008439, "progress_pct": 7.31, "epoch_pct": 7.31, "eta": "52:06:46", "max_grad_norm": 1.0, "loss": 0.9708920121192932, "grad_norm": 0.5480839014053345, "learning_rate": 0.0001826010544815466}
-{"ts": "2025-12-26T22:24:10", "event": "train_log", "step": 1042, "epoch": 0.43966244725738396, "progress_pct": 7.33, "epoch_pct": 7.33, "eta": "52:03:46", "max_grad_norm": 1.0, "loss": 0.8561046123504639, "grad_norm": 0.44693151116371155, "learning_rate": 0.00018295254833040423}
-{"ts": "2025-12-26T22:24:27", "event": "train_log", "step": 1044, "epoch": 0.44050632911392407, "progress_pct": 7.34, "epoch_pct": 7.34, "eta": "52:00:46", "max_grad_norm": 1.0, "loss": 0.8811968564987183, "grad_norm": 0.4024234116077423, "learning_rate": 0.00018330404217926187}
-{"ts": "2025-12-26T22:24:42", "event": "train_log", "step": 1046, "epoch": 0.4413502109704641, "progress_pct": 7.36, "epoch_pct": 7.36, "eta": "51:57:36", "max_grad_norm": 1.0, "loss": 0.978068470954895, "grad_norm": 0.5586408376693726, "learning_rate": 0.0001836555360281195}
-{"ts": "2025-12-26T22:24:58", "event": "train_log", "step": 1048, "epoch": 0.4421940928270042, "progress_pct": 7.37, "epoch_pct": 7.37, "eta": "51:54:26", "max_grad_norm": 1.0, "loss": 0.8640981316566467, "grad_norm": 0.4918624758720398, "learning_rate": 0.00018400702987697714}
-{"ts": "2025-12-26T22:25:14", "event": "train_log", "step": 1050, "epoch": 0.4430379746835443, "progress_pct": 7.38, "epoch_pct": 7.38, "eta": "51:51:27", "max_grad_norm": 1.0, "loss": 0.9077964425086975, "grad_norm": 0.4335230588912964, "learning_rate": 0.0001843585237258348}
-{"ts": "2025-12-26T22:25:30", "event": "train_log", "step": 1052, "epoch": 0.4438818565400844, "progress_pct": 7.4, "epoch_pct": 7.4, "eta": "51:48:21", "max_grad_norm": 1.0, "loss": 0.960682213306427, "grad_norm": 0.5275123715400696, "learning_rate": 0.00018471001757469247}
-{"ts": "2025-12-26T22:25:45", "event": "train_log", "step": 1054, "epoch": 0.4447257383966245, "progress_pct": 7.41, "epoch_pct": 7.41, "eta": "51:45:04", "max_grad_norm": 1.0, "loss": 0.8549577593803406, "grad_norm": 0.5144415497779846, "learning_rate": 0.0001850615114235501}
-{"ts": "2025-12-26T22:25:59", "event": "train_log", "step": 1056, "epoch": 0.44556962025316454, "progress_pct": 7.43, "epoch_pct": 7.43, "eta": "51:41:39", "max_grad_norm": 1.0, "loss": 0.9320827126502991, "grad_norm": 0.5166662931442261, "learning_rate": 0.00018541300527240775}
-{"ts": "2025-12-26T22:26:13", "event": "train_log", "step": 1058, "epoch": 0.44641350210970465, "progress_pct": 7.44, "epoch_pct": 7.44, "eta": "51:38:16", "max_grad_norm": 1.0, "loss": 0.9632431864738464, "grad_norm": 0.5011980533599854, "learning_rate": 0.0001857644991212654}
-{"ts": "2025-12-26T22:26:28", "event": "train_log", "step": 1060, "epoch": 0.4472573839662447, "progress_pct": 7.45, "epoch_pct": 7.45, "eta": "51:34:58", "max_grad_norm": 1.0, "loss": 0.9442946910858154, "grad_norm": 0.49312469363212585, "learning_rate": 0.00018611599297012303}
-{"ts": "2025-12-26T22:26:42", "event": "train_log", "step": 1062, "epoch": 0.4481012658227848, "progress_pct": 7.47, "epoch_pct": 7.47, "eta": "51:31:39", "max_grad_norm": 1.0, "loss": 0.952802300453186, "grad_norm": 0.49958568811416626, "learning_rate": 0.00018646748681898066}
-{"ts": "2025-12-26T22:26:57", "event": "train_log", "step": 1064, "epoch": 0.4489451476793249, "progress_pct": 7.48, "epoch_pct": 7.48, "eta": "51:28:21", "max_grad_norm": 1.0, "loss": 0.9630650877952576, "grad_norm": 0.49827462434768677, "learning_rate": 0.00018681898066783833}
-{"ts": "2025-12-26T22:27:11", "event": "train_log", "step": 1066, "epoch": 0.44978902953586497, "progress_pct": 7.5, "epoch_pct": 7.5, "eta": "51:24:58", "max_grad_norm": 1.0, "loss": 0.9081395268440247, "grad_norm": 0.523980438709259, "learning_rate": 0.00018717047451669597}
-{"ts": "2025-12-26T22:27:26", "event": "train_log", "step": 1068, "epoch": 0.4506329113924051, "progress_pct": 7.51, "epoch_pct": 7.51, "eta": "51:21:57", "max_grad_norm": 1.0, "loss": 0.9398958683013916, "grad_norm": 0.5108568668365479, "learning_rate": 0.0001875219683655536}
-{"ts": "2025-12-26T22:27:41", "event": "train_log", "step": 1070, "epoch": 0.45147679324894513, "progress_pct": 7.52, "epoch_pct": 7.52, "eta": "51:18:43", "max_grad_norm": 1.0, "loss": 0.93592768907547, "grad_norm": 0.4453965127468109, "learning_rate": 0.00018787346221441127}
-{"ts": "2025-12-26T22:27:55", "event": "train_log", "step": 1072, "epoch": 0.45232067510548524, "progress_pct": 7.54, "epoch_pct": 7.54, "eta": "51:15:29", "max_grad_norm": 1.0, "loss": 0.8879633545875549, "grad_norm": 0.4675683081150055, "learning_rate": 0.0001882249560632689}
-{"ts": "2025-12-26T22:28:11", "event": "train_log", "step": 1074, "epoch": 0.4531645569620253, "progress_pct": 7.55, "epoch_pct": 7.55, "eta": "51:12:22", "max_grad_norm": 1.0, "loss": 0.9966004490852356, "grad_norm": 0.47398847341537476, "learning_rate": 0.00018857644991212655}
-{"ts": "2025-12-26T22:28:25", "event": "train_log", "step": 1076, "epoch": 0.4540084388185654, "progress_pct": 7.57, "epoch_pct": 7.57, "eta": "51:09:13", "max_grad_norm": 1.0, "loss": 0.9184179902076721, "grad_norm": 0.46053192019462585, "learning_rate": 0.0001889279437609842}
-{"ts": "2025-12-26T22:28:40", "event": "train_log", "step": 1078, "epoch": 0.4548523206751055, "progress_pct": 7.58, "epoch_pct": 7.58, "eta": "51:06:06", "max_grad_norm": 1.0, "loss": 0.9434974193572998, "grad_norm": 0.5601398348808289, "learning_rate": 0.00018927943760984182}
-{"ts": "2025-12-26T22:28:55", "event": "train_log", "step": 1080, "epoch": 0.45569620253164556, "progress_pct": 7.59, "epoch_pct": 7.59, "eta": "51:02:54", "max_grad_norm": 1.0, "loss": 0.9522465467453003, "grad_norm": 0.48422637581825256, "learning_rate": 0.0001896309314586995}
-{"ts": "2025-12-26T22:29:09", "event": "train_log", "step": 1082, "epoch": 0.45654008438818566, "progress_pct": 7.61, "epoch_pct": 7.61, "eta": "50:59:42", "max_grad_norm": 1.0, "loss": 0.9315434694290161, "grad_norm": 0.46280911564826965, "learning_rate": 0.00018998242530755713}
-{"ts": "2025-12-26T22:29:25", "event": "train_log", "step": 1084, "epoch": 0.4573839662447257, "progress_pct": 7.62, "epoch_pct": 7.62, "eta": "50:56:41", "max_grad_norm": 1.0, "loss": 0.8165783286094666, "grad_norm": 0.4658683240413666, "learning_rate": 0.00019033391915641477}
-{"ts": "2025-12-26T22:29:40", "event": "train_log", "step": 1086, "epoch": 0.4582278481012658, "progress_pct": 7.64, "epoch_pct": 7.64, "eta": "50:53:37", "max_grad_norm": 1.0, "loss": 0.8024274110794067, "grad_norm": 0.4192182123661041, "learning_rate": 0.0001906854130052724}
-{"ts": "2025-12-26T22:29:56", "event": "train_log", "step": 1088, "epoch": 0.45907172995780593, "progress_pct": 7.65, "epoch_pct": 7.65, "eta": "50:50:52", "max_grad_norm": 1.0, "loss": 0.8620653748512268, "grad_norm": 0.4178735613822937, "learning_rate": 0.00019103690685413007}
-{"ts": "2025-12-26T22:30:11", "event": "train_log", "step": 1090, "epoch": 0.459915611814346, "progress_pct": 7.67, "epoch_pct": 7.67, "eta": "50:47:46", "max_grad_norm": 1.0, "loss": 0.9121530055999756, "grad_norm": 0.4488574266433716, "learning_rate": 0.0001913884007029877}
-{"ts": "2025-12-26T22:30:25", "event": "train_log", "step": 1092, "epoch": 0.4607594936708861, "progress_pct": 7.68, "epoch_pct": 7.68, "eta": "50:44:34", "max_grad_norm": 1.0, "loss": 0.9496700763702393, "grad_norm": 0.5164965987205505, "learning_rate": 0.00019173989455184535}
-{"ts": "2025-12-26T22:30:40", "event": "train_log", "step": 1094, "epoch": 0.46160337552742614, "progress_pct": 7.69, "epoch_pct": 7.69, "eta": "50:41:34", "max_grad_norm": 1.0, "loss": 0.8757708668708801, "grad_norm": 0.41563132405281067, "learning_rate": 0.00019209138840070299}
-{"ts": "2025-12-26T22:30:56", "event": "train_log", "step": 1096, "epoch": 0.46244725738396625, "progress_pct": 7.71, "epoch_pct": 7.71, "eta": "50:38:35", "max_grad_norm": 1.0, "loss": 0.8406533002853394, "grad_norm": 2.3222429752349854, "learning_rate": 0.00019244288224956065}
-{"ts": "2025-12-26T22:31:10", "event": "train_log", "step": 1098, "epoch": 0.46329113924050636, "progress_pct": 7.72, "epoch_pct": 7.72, "eta": "50:35:33", "max_grad_norm": 1.0, "loss": 0.9459465742111206, "grad_norm": 0.4813845157623291, "learning_rate": 0.0001927943760984183}
-{"ts": "2025-12-26T22:31:24", "event": "train_log", "step": 1100, "epoch": 0.4641350210970464, "progress_pct": 7.74, "epoch_pct": 7.74, "eta": "50:32:13", "max_grad_norm": 1.0, "loss": 0.9376904368400574, "grad_norm": 0.6233882308006287, "learning_rate": 0.00019314586994727593}
-{"ts": "2025-12-26T22:42:41", "event": "train_log", "step": 1100, "epoch": 0.4641350210970464, "progress_pct": 7.74, "epoch_pct": 7.74, "eta": "52:46:47", "max_grad_norm": 1.0, "eval_loss": 0.9357889294624329, "eval_runtime": 676.9573, "eval_samples_per_second": 3.112, "eval_steps_per_second": 3.112}
-{"ts": "2025-12-26T22:42:57", "event": "train_log", "step": 1102, "epoch": 0.4649789029535865, "progress_pct": 7.75, "epoch_pct": 7.75, "eta": "52:43:45", "max_grad_norm": 1.0, "loss": 0.8998825550079346, "grad_norm": 0.5125579237937927, "learning_rate": 0.00019349736379613357}
-{"ts": "2025-12-26T22:43:13", "event": "train_log", "step": 1104, "epoch": 0.46582278481012657, "progress_pct": 7.76, "epoch_pct": 7.76, "eta": "52:40:41", "max_grad_norm": 1.0, "loss": 0.9213768839836121, "grad_norm": 0.4534320831298828, "learning_rate": 0.00019384885764499123}
-{"ts": "2025-12-26T22:43:29", "event": "train_log", "step": 1106, "epoch": 0.4666666666666667, "progress_pct": 7.78, "epoch_pct": 7.78, "eta": "52:37:39", "max_grad_norm": 1.0, "loss": 0.9739661812782288, "grad_norm": 0.4715143144130707, "learning_rate": 0.00019420035149384887}
-{"ts": "2025-12-26T22:43:43", "event": "train_log", "step": 1108, "epoch": 0.4675105485232067, "progress_pct": 7.79, "epoch_pct": 7.79, "eta": "52:34:20", "max_grad_norm": 1.0, "loss": 0.9113216400146484, "grad_norm": 0.45529672503471375, "learning_rate": 0.0001945518453427065}
-{"ts": "2025-12-26T22:43:58", "event": "train_log", "step": 1110, "epoch": 0.46835443037974683, "progress_pct": 7.81, "epoch_pct": 7.81, "eta": "52:31:08", "max_grad_norm": 1.0, "loss": 0.92528235912323, "grad_norm": 0.48199015855789185, "learning_rate": 0.00019490333919156417}
-{"ts": "2025-12-26T22:44:14", "event": "train_log", "step": 1112, "epoch": 0.46919831223628694, "progress_pct": 7.82, "epoch_pct": 7.82, "eta": "52:28:02", "max_grad_norm": 1.0, "loss": 0.8612716197967529, "grad_norm": 0.4425188899040222, "learning_rate": 0.0001952548330404218}
-{"ts": "2025-12-26T22:44:33", "event": "train_log", "step": 1114, "epoch": 0.470042194092827, "progress_pct": 7.83, "epoch_pct": 7.83, "eta": "52:25:38", "max_grad_norm": 1.0, "loss": 0.8901699185371399, "grad_norm": 0.4311593770980835, "learning_rate": 0.00019560632688927945}
-{"ts": "2025-12-26T22:44:48", "event": "train_log", "step": 1116, "epoch": 0.4708860759493671, "progress_pct": 7.85, "epoch_pct": 7.85, "eta": "52:22:27", "max_grad_norm": 1.0, "loss": 0.9271994829177856, "grad_norm": 0.497806578874588, "learning_rate": 0.0001959578207381371}
-{"ts": "2025-12-26T22:45:04", "event": "train_log", "step": 1118, "epoch": 0.47172995780590715, "progress_pct": 7.86, "epoch_pct": 7.86, "eta": "52:19:34", "max_grad_norm": 1.0, "loss": 0.8740925788879395, "grad_norm": 0.47149473428726196, "learning_rate": 0.00019630931458699473}
-{"ts": "2025-12-26T22:45:20", "event": "train_log", "step": 1120, "epoch": 0.47257383966244726, "progress_pct": 7.88, "epoch_pct": 7.88, "eta": "52:16:38", "max_grad_norm": 1.0, "loss": 0.9190115928649902, "grad_norm": 0.5029966235160828, "learning_rate": 0.00019666080843585236}
-{"ts": "2025-12-26T22:45:36", "event": "train_log", "step": 1122, "epoch": 0.47341772151898737, "progress_pct": 7.89, "epoch_pct": 7.89, "eta": "52:13:34", "max_grad_norm": 1.0, "loss": 1.0043057203292847, "grad_norm": 0.47972601652145386, "learning_rate": 0.00019701230228471003}
-{"ts": "2025-12-26T22:45:52", "event": "train_log", "step": 1124, "epoch": 0.4742616033755274, "progress_pct": 7.9, "epoch_pct": 7.9, "eta": "52:10:36", "max_grad_norm": 1.0, "loss": 0.9472925066947937, "grad_norm": 0.45096471905708313, "learning_rate": 0.00019736379613356767}
-{"ts": "2025-12-26T22:46:07", "event": "train_log", "step": 1126, "epoch": 0.4751054852320675, "progress_pct": 7.92, "epoch_pct": 7.92, "eta": "52:07:33", "max_grad_norm": 1.0, "loss": 0.8043124079704285, "grad_norm": 0.459852933883667, "learning_rate": 0.00019771528998242533}
-{"ts": "2025-12-26T22:46:23", "event": "train_log", "step": 1128, "epoch": 0.4759493670886076, "progress_pct": 7.93, "epoch_pct": 7.93, "eta": "52:04:34", "max_grad_norm": 1.0, "loss": 0.9662142395973206, "grad_norm": 0.5313422679901123, "learning_rate": 0.00019806678383128297}
-{"ts": "2025-12-26T22:46:39", "event": "train_log", "step": 1130, "epoch": 0.4767932489451477, "progress_pct": 7.95, "epoch_pct": 7.95, "eta": "52:01:39", "max_grad_norm": 1.0, "loss": 0.8691151738166809, "grad_norm": 0.43474531173706055, "learning_rate": 0.0001984182776801406}
-{"ts": "2025-12-26T22:46:55", "event": "train_log", "step": 1132, "epoch": 0.47763713080168774, "progress_pct": 7.96, "epoch_pct": 7.96, "eta": "51:58:43", "max_grad_norm": 1.0, "loss": 0.9024254083633423, "grad_norm": 0.5232312083244324, "learning_rate": 0.00019876977152899825}
-{"ts": "2025-12-26T22:47:12", "event": "train_log", "step": 1134, "epoch": 0.47848101265822784, "progress_pct": 7.97, "epoch_pct": 7.97, "eta": "51:56:07", "max_grad_norm": 1.0, "loss": 0.8996873497962952, "grad_norm": 0.47671905159950256, "learning_rate": 0.0001991212653778559}
-{"ts": "2025-12-26T22:47:28", "event": "train_log", "step": 1136, "epoch": 0.47932489451476795, "progress_pct": 7.99, "epoch_pct": 7.99, "eta": "51:53:07", "max_grad_norm": 1.0, "loss": 0.8336917757987976, "grad_norm": 0.42289480566978455, "learning_rate": 0.00019947275922671353}
-{"ts": "2025-12-26T22:47:43", "event": "train_log", "step": 1138, "epoch": 0.480168776371308, "progress_pct": 8.0, "epoch_pct": 8.0, "eta": "51:50:03", "max_grad_norm": 1.0, "loss": 0.8943206071853638, "grad_norm": 0.4700844883918762, "learning_rate": 0.0001998242530755712}
-{"ts": "2025-12-26T22:47:59", "event": "train_log", "step": 1140, "epoch": 0.4810126582278481, "progress_pct": 8.02, "epoch_pct": 8.02, "eta": "51:47:11", "max_grad_norm": 1.0, "loss": 0.9340365529060364, "grad_norm": 0.5341399312019348, "learning_rate": 0.00019999999711649004}
-{"ts": "2025-12-26T22:48:14", "event": "train_log", "step": 1142, "epoch": 0.48185654008438816, "progress_pct": 8.03, "epoch_pct": 8.03, "eta": "51:44:14", "max_grad_norm": 1.0, "loss": 0.8241778016090393, "grad_norm": 0.46169522404670715, "learning_rate": 0.00019999997404841123}
-{"ts": "2025-12-26T22:48:28", "event": "train_log", "step": 1144, "epoch": 0.48270042194092827, "progress_pct": 8.05, "epoch_pct": 8.05, "eta": "51:40:52", "max_grad_norm": 1.0, "loss": 1.0096158981323242, "grad_norm": 0.5475223064422607, "learning_rate": 0.00019999992791225896}
-{"ts": "2025-12-26T22:48:44", "event": "train_log", "step": 1146, "epoch": 0.4835443037974684, "progress_pct": 8.06, "epoch_pct": 8.06, "eta": "51:38:04", "max_grad_norm": 1.0, "loss": 0.9650378227233887, "grad_norm": 0.524641215801239, "learning_rate": 0.00019999985870804385}
-{"ts": "2025-12-26T22:49:00", "event": "train_log", "step": 1148, "epoch": 0.48438818565400843, "progress_pct": 8.07, "epoch_pct": 8.07, "eta": "51:35:11", "max_grad_norm": 1.0, "loss": 0.9003009796142578, "grad_norm": 0.4326174855232239, "learning_rate": 0.00019999976643578186}
-{"ts": "2025-12-26T22:49:14", "event": "train_log", "step": 1150, "epoch": 0.48523206751054854, "progress_pct": 8.09, "epoch_pct": 8.09, "eta": "51:32:06", "max_grad_norm": 1.0, "loss": 0.9793432950973511, "grad_norm": 0.49034059047698975, "learning_rate": 0.0001999996510954943}
-{"ts": "2025-12-26T22:49:29", "event": "train_log", "step": 1152, "epoch": 0.4860759493670886, "progress_pct": 8.1, "epoch_pct": 8.1, "eta": "51:29:06", "max_grad_norm": 1.0, "loss": 0.8793007731437683, "grad_norm": 0.4760092496871948, "learning_rate": 0.00019999951268720776}
-{"ts": "2025-12-26T22:49:44", "event": "train_log", "step": 1154, "epoch": 0.4869198312236287, "progress_pct": 8.12, "epoch_pct": 8.12, "eta": "51:26:05", "max_grad_norm": 1.0, "loss": 0.888630747795105, "grad_norm": 0.44606879353523254, "learning_rate": 0.00019999935121095417}
-{"ts": "2025-12-26T22:49:59", "event": "train_log", "step": 1156, "epoch": 0.4877637130801688, "progress_pct": 8.13, "epoch_pct": 8.13, "eta": "51:23:09", "max_grad_norm": 1.0, "loss": 0.9660000801086426, "grad_norm": 0.5030332207679749, "learning_rate": 0.0001999991666667708}
-{"ts": "2025-12-26T22:50:14", "event": "train_log", "step": 1158, "epoch": 0.48860759493670886, "progress_pct": 8.14, "epoch_pct": 8.14, "eta": "51:20:04", "max_grad_norm": 1.0, "loss": 0.824654757976532, "grad_norm": 0.4295555055141449, "learning_rate": 0.00019999895905470014}
-{"ts": "2025-12-26T22:50:31", "event": "train_log", "step": 1160, "epoch": 0.48945147679324896, "progress_pct": 8.16, "epoch_pct": 8.16, "eta": "51:17:31", "max_grad_norm": 1.0, "loss": 0.8159562349319458, "grad_norm": 0.392167866230011, "learning_rate": 0.0001999987283747902}
-{"ts": "2025-12-26T22:50:46", "event": "train_log", "step": 1162, "epoch": 0.490295358649789, "progress_pct": 8.17, "epoch_pct": 8.17, "eta": "51:14:33", "max_grad_norm": 1.0, "loss": 0.9630686044692993, "grad_norm": 0.484611839056015, "learning_rate": 0.00019999847462709412}
-{"ts": "2025-12-26T22:51:03", "event": "train_log", "step": 1164, "epoch": 0.4911392405063291, "progress_pct": 8.19, "epoch_pct": 8.19, "eta": "51:11:53", "max_grad_norm": 1.0, "loss": 0.8396129608154297, "grad_norm": 0.45891445875167847, "learning_rate": 0.00019999819781167042}
-{"ts": "2025-12-26T22:51:19", "event": "train_log", "step": 1166, "epoch": 0.4919831223628692, "progress_pct": 8.2, "epoch_pct": 8.2, "eta": "51:09:17", "max_grad_norm": 1.0, "loss": 0.8194513916969299, "grad_norm": 0.5553452968597412, "learning_rate": 0.00019999789792858304}
-{"ts": "2025-12-26T22:51:35", "event": "train_log", "step": 1168, "epoch": 0.4928270042194093, "progress_pct": 8.21, "epoch_pct": 8.21, "eta": "51:06:31", "max_grad_norm": 1.0, "loss": 0.9268721342086792, "grad_norm": 0.38998672366142273, "learning_rate": 0.00019999757497790106}
-{"ts": "2025-12-26T22:51:50", "event": "train_log", "step": 1170, "epoch": 0.4936708860759494, "progress_pct": 8.23, "epoch_pct": 8.23, "eta": "51:03:38", "max_grad_norm": 1.0, "loss": 0.9204684495925903, "grad_norm": 0.45445355772972107, "learning_rate": 0.00019999722895969904}
-{"ts": "2025-12-26T22:52:05", "event": "train_log", "step": 1172, "epoch": 0.49451476793248944, "progress_pct": 8.24, "epoch_pct": 8.24, "eta": "51:00:41", "max_grad_norm": 1.0, "loss": 0.9270301461219788, "grad_norm": 0.484225332736969, "learning_rate": 0.00019999685987405678}
-{"ts": "2025-12-26T22:52:21", "event": "train_log", "step": 1174, "epoch": 0.49535864978902955, "progress_pct": 8.26, "epoch_pct": 8.26, "eta": "50:57:56", "max_grad_norm": 1.0, "loss": 0.8782645463943481, "grad_norm": 0.45215415954589844, "learning_rate": 0.00019999646772105942}
-{"ts": "2025-12-26T22:52:38", "event": "train_log", "step": 1176, "epoch": 0.4962025316455696, "progress_pct": 8.27, "epoch_pct": 8.27, "eta": "50:55:21", "max_grad_norm": 1.0, "loss": 0.873112678527832, "grad_norm": 0.41578832268714905, "learning_rate": 0.00019999605250079744}
-{"ts": "2025-12-26T22:52:55", "event": "train_log", "step": 1178, "epoch": 0.4970464135021097, "progress_pct": 8.28, "epoch_pct": 8.28, "eta": "50:52:47", "max_grad_norm": 1.0, "loss": 0.9593189358711243, "grad_norm": 0.4632788300514221, "learning_rate": 0.0001999956142133666}
-{"ts": "2025-12-26T22:53:10", "event": "train_log", "step": 1180, "epoch": 0.4978902953586498, "progress_pct": 8.3, "epoch_pct": 8.3, "eta": "50:49:58", "max_grad_norm": 1.0, "loss": 0.9215621948242188, "grad_norm": 0.5007622838020325, "learning_rate": 0.000199995152858868}
-{"ts": "2025-12-26T22:53:24", "event": "train_log", "step": 1182, "epoch": 0.49873417721518987, "progress_pct": 8.31, "epoch_pct": 8.31, "eta": "50:46:55", "max_grad_norm": 1.0, "loss": 0.8964219689369202, "grad_norm": 0.5201935768127441, "learning_rate": 0.0001999946684374081}
-{"ts": "2025-12-26T22:53:38", "event": "train_log", "step": 1184, "epoch": 0.49957805907173, "progress_pct": 8.33, "epoch_pct": 8.33, "eta": "50:43:54", "max_grad_norm": 1.0, "loss": 0.8528663516044617, "grad_norm": 0.5053967237472534, "learning_rate": 0.0001999941609490986}
-{"ts": "2025-12-26T22:53:54", "event": "train_log", "step": 1186, "epoch": 0.5004219409282701, "progress_pct": 8.34, "epoch_pct": 8.34, "eta": "50:41:18", "max_grad_norm": 1.0, "loss": 0.8214734792709351, "grad_norm": 0.44397974014282227, "learning_rate": 0.0001999936303940566}
-{"ts": "2025-12-26T22:54:10", "event": "train_log", "step": 1188, "epoch": 0.5012658227848101, "progress_pct": 8.35, "epoch_pct": 8.35, "eta": "50:38:29", "max_grad_norm": 1.0, "loss": 0.8882166743278503, "grad_norm": 0.4563101530075073, "learning_rate": 0.0001999930767724045}
-{"ts": "2025-12-26T22:54:25", "event": "train_log", "step": 1190, "epoch": 0.5021097046413502, "progress_pct": 8.37, "epoch_pct": 8.37, "eta": "50:35:43", "max_grad_norm": 1.0, "loss": 0.8882588148117065, "grad_norm": 0.4666728675365448, "learning_rate": 0.00019999250008426997}
-{"ts": "2025-12-26T22:54:41", "event": "train_log", "step": 1192, "epoch": 0.5029535864978903, "progress_pct": 8.38, "epoch_pct": 8.38, "eta": "50:33:07", "max_grad_norm": 1.0, "loss": 0.8353691697120667, "grad_norm": 0.4423629939556122, "learning_rate": 0.00019999190032978607}
-{"ts": "2025-12-26T22:54:58", "event": "train_log", "step": 1194, "epoch": 0.5037974683544304, "progress_pct": 8.4, "epoch_pct": 8.4, "eta": "50:30:39", "max_grad_norm": 1.0, "loss": 0.8721219301223755, "grad_norm": 0.4514595866203308, "learning_rate": 0.00019999127750909118}
-{"ts": "2025-12-26T22:55:13", "event": "train_log", "step": 1196, "epoch": 0.5046413502109705, "progress_pct": 8.41, "epoch_pct": 8.41, "eta": "50:27:54", "max_grad_norm": 1.0, "loss": 0.902795135974884, "grad_norm": 0.48469996452331543, "learning_rate": 0.00019999063162232886}
-{"ts": "2025-12-26T22:55:29", "event": "train_log", "step": 1198, "epoch": 0.5054852320675105, "progress_pct": 8.42, "epoch_pct": 8.42, "eta": "50:25:15", "max_grad_norm": 1.0, "loss": 0.8843175768852234, "grad_norm": 0.4931983947753906, "learning_rate": 0.00019998996266964823}
-{"ts": "2025-12-26T22:55:45", "event": "train_log", "step": 1200, "epoch": 0.5063291139240507, "progress_pct": 8.44, "epoch_pct": 8.44, "eta": "50:22:33", "max_grad_norm": 1.0, "loss": 0.9179208278656006, "grad_norm": 0.507408082485199, "learning_rate": 0.00019998927065120357}
-{"ts": "2025-12-26T23:06:55", "event": "train_log", "step": 1200, "epoch": 0.5063291139240507, "progress_pct": 8.44, "epoch_pct": 8.44, "eta": "52:23:40", "max_grad_norm": 1.0, "eval_loss": 0.9224098324775696, "eval_runtime": 669.7542, "eval_samples_per_second": 3.146, "eval_steps_per_second": 3.146}
-{"ts": "2025-12-26T23:07:09", "event": "train_log", "step": 1202, "epoch": 0.5071729957805907, "progress_pct": 8.45, "epoch_pct": 8.45, "eta": "52:20:34", "max_grad_norm": 1.0, "loss": 0.9078981876373291, "grad_norm": 0.4024188220500946, "learning_rate": 0.00019998855556715447}
-{"ts": "2025-12-26T23:07:24", "event": "train_log", "step": 1204, "epoch": 0.5080168776371308, "progress_pct": 8.47, "epoch_pct": 8.47, "eta": "52:17:36", "max_grad_norm": 1.0, "loss": 0.8089252710342407, "grad_norm": 0.6558667421340942, "learning_rate": 0.00019998781741766594}
-{"ts": "2025-12-26T23:07:38", "event": "train_log", "step": 1206, "epoch": 0.5088607594936709, "progress_pct": 8.48, "epoch_pct": 8.48, "eta": "52:14:29", "max_grad_norm": 1.0, "loss": 0.9316248297691345, "grad_norm": 0.45128145813941956, "learning_rate": 0.00019998705620290823}
-{"ts": "2025-12-26T23:07:53", "event": "train_log", "step": 1208, "epoch": 0.509704641350211, "progress_pct": 8.5, "epoch_pct": 8.5, "eta": "52:11:31", "max_grad_norm": 1.0, "loss": 0.9047867655754089, "grad_norm": 0.4733511507511139, "learning_rate": 0.00019998627192305694}
-{"ts": "2025-12-26T23:08:09", "event": "train_log", "step": 1210, "epoch": 0.510548523206751, "progress_pct": 8.51, "epoch_pct": 8.51, "eta": "52:08:34", "max_grad_norm": 1.0, "loss": 0.8507166504859924, "grad_norm": 0.4026021659374237, "learning_rate": 0.00019998546457829298}
-{"ts": "2025-12-26T23:08:23", "event": "train_log", "step": 1212, "epoch": 0.5113924050632911, "progress_pct": 8.52, "epoch_pct": 8.52, "eta": "52:05:33", "max_grad_norm": 1.0, "loss": 0.8490090370178223, "grad_norm": 0.43416184186935425, "learning_rate": 0.00019998463416880262}
-{"ts": "2025-12-26T23:08:41", "event": "train_log", "step": 1214, "epoch": 0.5122362869198313, "progress_pct": 8.54, "epoch_pct": 8.54, "eta": "52:03:01", "max_grad_norm": 1.0, "loss": 0.7730492949485779, "grad_norm": 0.3678364157676697, "learning_rate": 0.0001999837806947774}
-{"ts": "2025-12-26T23:08:55", "event": "train_log", "step": 1216, "epoch": 0.5130801687763713, "progress_pct": 8.55, "epoch_pct": 8.55, "eta": "51:59:55", "max_grad_norm": 1.0, "loss": 0.9625269174575806, "grad_norm": 0.49042677879333496, "learning_rate": 0.00019998290415641415}
-{"ts": "2025-12-26T23:09:09", "event": "train_log", "step": 1218, "epoch": 0.5139240506329114, "progress_pct": 8.57, "epoch_pct": 8.57, "eta": "51:56:54", "max_grad_norm": 1.0, "loss": 0.8961732983589172, "grad_norm": 0.4576701819896698, "learning_rate": 0.00019998200455391516}
-{"ts": "2025-12-26T23:09:24", "event": "train_log", "step": 1220, "epoch": 0.5147679324894515, "progress_pct": 8.58, "epoch_pct": 8.58, "eta": "51:53:54", "max_grad_norm": 1.0, "loss": 0.8508996367454529, "grad_norm": 0.4465518593788147, "learning_rate": 0.00019998108188748793}
-{"ts": "2025-12-26T23:09:38", "event": "train_log", "step": 1222, "epoch": 0.5156118143459916, "progress_pct": 8.59, "epoch_pct": 8.59, "eta": "51:50:52", "max_grad_norm": 1.0, "loss": 0.8664930462837219, "grad_norm": 0.4267960488796234, "learning_rate": 0.00019998013615734524}
-{"ts": "2025-12-26T23:09:54", "event": "train_log", "step": 1224, "epoch": 0.5164556962025316, "progress_pct": 8.61, "epoch_pct": 8.61, "eta": "51:48:10", "max_grad_norm": 1.0, "loss": 0.8841317892074585, "grad_norm": 0.39936602115631104, "learning_rate": 0.0001999791673637053}
-{"ts": "2025-12-26T23:10:09", "event": "train_log", "step": 1226, "epoch": 0.5172995780590718, "progress_pct": 8.62, "epoch_pct": 8.62, "eta": "51:45:16", "max_grad_norm": 1.0, "loss": 0.8601276874542236, "grad_norm": 0.4442414343357086, "learning_rate": 0.0001999781755067916}
-{"ts": "2025-12-26T23:10:25", "event": "train_log", "step": 1228, "epoch": 0.5181434599156118, "progress_pct": 8.64, "epoch_pct": 8.64, "eta": "51:42:32", "max_grad_norm": 1.0, "loss": 0.8377046585083008, "grad_norm": 0.4397028088569641, "learning_rate": 0.00019997716058683292}
-{"ts": "2025-12-26T23:10:41", "event": "train_log", "step": 1230, "epoch": 0.5189873417721519, "progress_pct": 8.65, "epoch_pct": 8.65, "eta": "51:39:42", "max_grad_norm": 1.0, "loss": 0.9853615164756775, "grad_norm": 0.5327648520469666, "learning_rate": 0.0001999761226040634}
-{"ts": "2025-12-26T23:10:57", "event": "train_log", "step": 1232, "epoch": 0.5198312236286919, "progress_pct": 8.66, "epoch_pct": 8.66, "eta": "51:37:10", "max_grad_norm": 1.0, "loss": 0.9235715866088867, "grad_norm": 0.40931421518325806, "learning_rate": 0.00019997506155872244}
-{"ts": "2025-12-26T23:11:13", "event": "train_log", "step": 1234, "epoch": 0.5206751054852321, "progress_pct": 8.68, "epoch_pct": 8.68, "eta": "51:34:23", "max_grad_norm": 1.0, "loss": 0.868396520614624, "grad_norm": 0.4599161148071289, "learning_rate": 0.00019997397745105487}
-{"ts": "2025-12-26T23:11:28", "event": "train_log", "step": 1236, "epoch": 0.5215189873417722, "progress_pct": 8.69, "epoch_pct": 8.69, "eta": "51:31:36", "max_grad_norm": 1.0, "loss": 0.9946733117103577, "grad_norm": 0.4813833236694336, "learning_rate": 0.0001999728702813107}
-{"ts": "2025-12-26T23:11:44", "event": "train_log", "step": 1238, "epoch": 0.5223628691983122, "progress_pct": 8.71, "epoch_pct": 8.71, "eta": "51:28:52", "max_grad_norm": 1.0, "loss": 0.8608635067939758, "grad_norm": 0.43518269062042236, "learning_rate": 0.00019997174004974543}
-{"ts": "2025-12-26T23:12:00", "event": "train_log", "step": 1240, "epoch": 0.5232067510548524, "progress_pct": 8.72, "epoch_pct": 8.72, "eta": "51:26:15", "max_grad_norm": 1.0, "loss": 0.819354772567749, "grad_norm": 0.45646214485168457, "learning_rate": 0.0001999705867566197}
-{"ts": "2025-12-26T23:12:16", "event": "train_log", "step": 1242, "epoch": 0.5240506329113924, "progress_pct": 8.73, "epoch_pct": 8.73, "eta": "51:23:35", "max_grad_norm": 1.0, "loss": 0.8934658765792847, "grad_norm": 0.46834197640419006, "learning_rate": 0.00019996941040219954}
-{"ts": "2025-12-26T23:12:33", "event": "train_log", "step": 1244, "epoch": 0.5248945147679325, "progress_pct": 8.75, "epoch_pct": 8.75, "eta": "51:20:59", "max_grad_norm": 1.0, "loss": 0.8624778985977173, "grad_norm": 0.46065032482147217, "learning_rate": 0.0001999682109867564}
-{"ts": "2025-12-26T23:12:48", "event": "train_log", "step": 1246, "epoch": 0.5257383966244725, "progress_pct": 8.76, "epoch_pct": 8.76, "eta": "51:18:12", "max_grad_norm": 1.0, "loss": 0.8540882468223572, "grad_norm": 0.4506741166114807, "learning_rate": 0.00019996698851056688}
-{"ts": "2025-12-26T23:13:03", "event": "train_log", "step": 1248, "epoch": 0.5265822784810127, "progress_pct": 8.78, "epoch_pct": 8.78, "eta": "51:15:30", "max_grad_norm": 1.0, "loss": 0.9003006219863892, "grad_norm": 0.4550519287586212, "learning_rate": 0.00019996574297391302}
-{"ts": "2025-12-26T23:13:19", "event": "train_log", "step": 1250, "epoch": 0.5274261603375527, "progress_pct": 8.79, "epoch_pct": 8.79, "eta": "51:12:47", "max_grad_norm": 1.0, "loss": 0.8490248918533325, "grad_norm": 0.4097813367843628, "learning_rate": 0.00019996447437708214}
-{"ts": "2025-12-26T23:13:35", "event": "train_log", "step": 1252, "epoch": 0.5282700421940928, "progress_pct": 8.8, "epoch_pct": 8.8, "eta": "51:10:10", "max_grad_norm": 1.0, "loss": 0.9204569458961487, "grad_norm": 0.4375711679458618, "learning_rate": 0.00019996318272036688}
-{"ts": "2025-12-26T23:13:51", "event": "train_log", "step": 1254, "epoch": 0.529113924050633, "progress_pct": 8.82, "epoch_pct": 8.82, "eta": "51:07:35", "max_grad_norm": 1.0, "loss": 0.8831789493560791, "grad_norm": 0.4335198998451233, "learning_rate": 0.00019996186800406518}
-{"ts": "2025-12-26T23:14:06", "event": "train_log", "step": 1256, "epoch": 0.529957805907173, "progress_pct": 8.83, "epoch_pct": 8.83, "eta": "51:04:53", "max_grad_norm": 1.0, "loss": 0.8578064441680908, "grad_norm": 0.4840933084487915, "learning_rate": 0.00019996053022848035}
-{"ts": "2025-12-26T23:14:21", "event": "train_log", "step": 1258, "epoch": 0.5308016877637131, "progress_pct": 8.85, "epoch_pct": 8.85, "eta": "51:02:04", "max_grad_norm": 1.0, "loss": 0.9235416650772095, "grad_norm": 0.48911216855049133, "learning_rate": 0.00019995916939392097}
-{"ts": "2025-12-26T23:14:38", "event": "train_log", "step": 1260, "epoch": 0.5316455696202531, "progress_pct": 8.86, "epoch_pct": 8.86, "eta": "50:59:42", "max_grad_norm": 1.0, "loss": 0.7897764444351196, "grad_norm": 0.41106730699539185, "learning_rate": 0.00019995778550070098}
-{"ts": "2025-12-26T23:14:56", "event": "train_log", "step": 1262, "epoch": 0.5324894514767933, "progress_pct": 8.87, "epoch_pct": 8.87, "eta": "50:57:18", "max_grad_norm": 1.0, "loss": 0.9392989873886108, "grad_norm": 0.42233356833457947, "learning_rate": 0.00019995637854913957}
-{"ts": "2025-12-26T23:15:12", "event": "train_log", "step": 1264, "epoch": 0.5333333333333333, "progress_pct": 8.89, "epoch_pct": 8.89, "eta": "50:54:49", "max_grad_norm": 1.0, "loss": 0.9130091667175293, "grad_norm": 0.39145180583000183, "learning_rate": 0.0001999549485395613}
-{"ts": "2025-12-26T23:15:28", "event": "train_log", "step": 1266, "epoch": 0.5341772151898734, "progress_pct": 8.9, "epoch_pct": 8.9, "eta": "50:52:17", "max_grad_norm": 1.0, "loss": 0.9690561890602112, "grad_norm": 0.42780739068984985, "learning_rate": 0.00019995349547229614}
-{"ts": "2025-12-26T23:15:44", "event": "train_log", "step": 1268, "epoch": 0.5350210970464135, "progress_pct": 8.92, "epoch_pct": 8.92, "eta": "50:49:37", "max_grad_norm": 1.0, "loss": 0.9990131258964539, "grad_norm": 0.4823327362537384, "learning_rate": 0.0001999520193476792}
-{"ts": "2025-12-26T23:15:58", "event": "train_log", "step": 1270, "epoch": 0.5358649789029536, "progress_pct": 8.93, "epoch_pct": 8.93, "eta": "50:46:50", "max_grad_norm": 1.0, "loss": 0.8343052864074707, "grad_norm": 0.4669715166091919, "learning_rate": 0.00019995052016605097}
-{"ts": "2025-12-26T23:16:14", "event": "train_log", "step": 1272, "epoch": 0.5367088607594936, "progress_pct": 8.95, "epoch_pct": 8.95, "eta": "50:44:11", "max_grad_norm": 1.0, "loss": 0.9605970978736877, "grad_norm": 0.4024743437767029, "learning_rate": 0.0001999489979277574}
-{"ts": "2025-12-26T23:16:30", "event": "train_log", "step": 1274, "epoch": 0.5375527426160338, "progress_pct": 8.96, "epoch_pct": 8.96, "eta": "50:41:44", "max_grad_norm": 1.0, "loss": 0.8164438009262085, "grad_norm": 0.42063432931900024, "learning_rate": 0.0001999474526331495}
-{"ts": "2025-12-26T23:16:46", "event": "train_log", "step": 1276, "epoch": 0.5383966244725739, "progress_pct": 8.97, "epoch_pct": 8.97, "eta": "50:39:10", "max_grad_norm": 1.0, "loss": 0.879767656326294, "grad_norm": 0.47953495383262634, "learning_rate": 0.00019994588428258383}
-{"ts": "2025-12-26T23:17:02", "event": "train_log", "step": 1278, "epoch": 0.5392405063291139, "progress_pct": 8.99, "epoch_pct": 8.99, "eta": "50:36:40", "max_grad_norm": 1.0, "loss": 0.7658726572990417, "grad_norm": 0.39668557047843933, "learning_rate": 0.00019994429287642214}
-{"ts": "2025-12-26T23:17:18", "event": "train_log", "step": 1280, "epoch": 0.540084388185654, "progress_pct": 9.0, "epoch_pct": 9.0, "eta": "50:34:06", "max_grad_norm": 1.0, "loss": 0.9477384686470032, "grad_norm": 0.5136121511459351, "learning_rate": 0.00019994267841503155}
-{"ts": "2025-12-26T23:17:36", "event": "train_log", "step": 1282, "epoch": 0.5409282700421941, "progress_pct": 9.02, "epoch_pct": 9.02, "eta": "50:32:00", "max_grad_norm": 1.0, "loss": 0.7883896827697754, "grad_norm": 0.4039286673069, "learning_rate": 0.00019994104089878452}
-{"ts": "2025-12-26T23:17:52", "event": "train_log", "step": 1284, "epoch": 0.5417721518987342, "progress_pct": 9.03, "epoch_pct": 9.03, "eta": "50:29:27", "max_grad_norm": 1.0, "loss": 0.8526129126548767, "grad_norm": 0.4425487816333771, "learning_rate": 0.0001999393803280587}
-{"ts": "2025-12-26T23:18:09", "event": "train_log", "step": 1286, "epoch": 0.5426160337552742, "progress_pct": 9.04, "epoch_pct": 9.04, "eta": "50:27:06", "max_grad_norm": 1.0, "loss": 0.8694683909416199, "grad_norm": 0.4544559121131897, "learning_rate": 0.00019993769670323725}
-{"ts": "2025-12-26T23:18:28", "event": "train_log", "step": 1288, "epoch": 0.5434599156118144, "progress_pct": 9.06, "epoch_pct": 9.06, "eta": "50:25:06", "max_grad_norm": 1.0, "loss": 0.8211527466773987, "grad_norm": 0.42872917652130127, "learning_rate": 0.0001999359900247085}
-{"ts": "2025-12-26T23:18:44", "event": "train_log", "step": 1290, "epoch": 0.5443037974683544, "progress_pct": 9.07, "epoch_pct": 9.07, "eta": "50:22:40", "max_grad_norm": 1.0, "loss": 0.7967932224273682, "grad_norm": 0.41549673676490784, "learning_rate": 0.00019993426029286617}
-{"ts": "2025-12-26T23:19:00", "event": "train_log", "step": 1292, "epoch": 0.5451476793248945, "progress_pct": 9.09, "epoch_pct": 9.09, "eta": "50:20:13", "max_grad_norm": 1.0, "loss": 0.8291563987731934, "grad_norm": 0.42888355255126953, "learning_rate": 0.00019993250750810926}
-{"ts": "2025-12-26T23:19:16", "event": "train_log", "step": 1294, "epoch": 0.5459915611814345, "progress_pct": 9.1, "epoch_pct": 9.1, "eta": "50:17:39", "max_grad_norm": 1.0, "loss": 0.8787803649902344, "grad_norm": 0.44985485076904297, "learning_rate": 0.0001999307316708421}
-{"ts": "2025-12-26T23:19:31", "event": "train_log", "step": 1296, "epoch": 0.5468354430379747, "progress_pct": 9.11, "epoch_pct": 9.11, "eta": "50:15:05", "max_grad_norm": 1.0, "loss": 0.8375519514083862, "grad_norm": 0.43326008319854736, "learning_rate": 0.00019992893278147436}
-{"ts": "2025-12-26T23:19:48", "event": "train_log", "step": 1298, "epoch": 0.5476793248945148, "progress_pct": 9.13, "epoch_pct": 9.13, "eta": "50:12:47", "max_grad_norm": 1.0, "loss": 0.8538051247596741, "grad_norm": 0.406556099653244, "learning_rate": 0.00019992711084042096}
-{"ts": "2025-12-26T23:20:04", "event": "train_log", "step": 1300, "epoch": 0.5485232067510548, "progress_pct": 9.14, "epoch_pct": 9.14, "eta": "50:10:17", "max_grad_norm": 1.0, "loss": 0.9722132086753845, "grad_norm": 0.46090877056121826, "learning_rate": 0.00019992526584810226}
-{"ts": "2025-12-26T23:31:25", "event": "train_log", "step": 1300, "epoch": 0.5485232067510548, "progress_pct": 9.14, "epoch_pct": 9.14, "eta": "52:03:03", "max_grad_norm": 1.0, "eval_loss": 0.9068717360496521, "eval_runtime": 680.7718, "eval_samples_per_second": 3.095, "eval_steps_per_second": 3.095}
-{"ts": "2025-12-26T23:31:39", "event": "train_log", "step": 1302, "epoch": 0.549367088607595, "progress_pct": 9.16, "epoch_pct": 9.16, "eta": "52:00:15", "max_grad_norm": 1.0, "loss": 0.8474152684211731, "grad_norm": 0.44932207465171814, "learning_rate": 0.00019992339780494382}
-{"ts": "2025-12-26T23:31:54", "event": "train_log", "step": 1304, "epoch": 0.550210970464135, "progress_pct": 9.17, "epoch_pct": 9.17, "eta": "51:57:26", "max_grad_norm": 1.0, "loss": 0.8440775871276855, "grad_norm": 0.5185276865959167, "learning_rate": 0.0001999215067113766}
-{"ts": "2025-12-26T23:32:10", "event": "train_log", "step": 1306, "epoch": 0.5510548523206751, "progress_pct": 9.18, "epoch_pct": 9.18, "eta": "51:54:42", "max_grad_norm": 1.0, "loss": 0.8848010897636414, "grad_norm": 0.43811365962028503, "learning_rate": 0.0001999195925678368}
-{"ts": "2025-12-26T23:32:25", "event": "train_log", "step": 1308, "epoch": 0.5518987341772152, "progress_pct": 9.2, "epoch_pct": 9.2, "eta": "51:51:54", "max_grad_norm": 1.0, "loss": 0.8265100121498108, "grad_norm": 0.4861660301685333, "learning_rate": 0.00019991765537476596}
-{"ts": "2025-12-26T23:32:39", "event": "train_log", "step": 1310, "epoch": 0.5527426160337553, "progress_pct": 9.21, "epoch_pct": 9.21, "eta": "51:49:03", "max_grad_norm": 1.0, "loss": 0.9327963590621948, "grad_norm": 0.5068721771240234, "learning_rate": 0.000199915695132611}
-{"ts": "2025-12-26T23:32:54", "event": "train_log", "step": 1312, "epoch": 0.5535864978902953, "progress_pct": 9.23, "epoch_pct": 9.23, "eta": "51:46:20", "max_grad_norm": 1.0, "loss": 0.9315155744552612, "grad_norm": 0.4902805685997009, "learning_rate": 0.0001999137118418241}
-{"ts": "2025-12-26T23:33:09", "event": "train_log", "step": 1314, "epoch": 0.5544303797468354, "progress_pct": 9.24, "epoch_pct": 9.24, "eta": "51:43:33", "max_grad_norm": 1.0, "loss": 0.9344852566719055, "grad_norm": 0.4530964493751526, "learning_rate": 0.00019991170550286272}
-{"ts": "2025-12-26T23:33:24", "event": "train_log", "step": 1316, "epoch": 0.5552742616033756, "progress_pct": 9.25, "epoch_pct": 9.25, "eta": "51:40:48", "max_grad_norm": 1.0, "loss": 0.8326173424720764, "grad_norm": 0.4106673300266266, "learning_rate": 0.00019990967611618974}
-{"ts": "2025-12-26T23:33:40", "event": "train_log", "step": 1318, "epoch": 0.5561181434599156, "progress_pct": 9.27, "epoch_pct": 9.27, "eta": "51:38:09", "max_grad_norm": 1.0, "loss": 0.8934909105300903, "grad_norm": 0.4439711570739746, "learning_rate": 0.0001999076236822733}
-{"ts": "2025-12-26T23:33:55", "event": "train_log", "step": 1320, "epoch": 0.5569620253164557, "progress_pct": 9.28, "epoch_pct": 9.28, "eta": "51:35:33", "max_grad_norm": 1.0, "loss": 0.6691107153892517, "grad_norm": 0.40245553851127625, "learning_rate": 0.0001999055482015868}
-{"ts": "2025-12-26T23:34:10", "event": "train_log", "step": 1322, "epoch": 0.5578059071729958, "progress_pct": 9.3, "epoch_pct": 9.3, "eta": "51:32:47", "max_grad_norm": 1.0, "loss": 0.8560307621955872, "grad_norm": 0.43904435634613037, "learning_rate": 0.0001999034496746091}
-{"ts": "2025-12-26T23:34:24", "event": "train_log", "step": 1324, "epoch": 0.5586497890295359, "progress_pct": 9.31, "epoch_pct": 9.31, "eta": "51:29:54", "max_grad_norm": 1.0, "loss": 0.9024442434310913, "grad_norm": 0.5131705403327942, "learning_rate": 0.00019990132810182422}
-{"ts": "2025-12-26T23:34:39", "event": "train_log", "step": 1326, "epoch": 0.5594936708860759, "progress_pct": 9.32, "epoch_pct": 9.32, "eta": "51:27:10", "max_grad_norm": 1.0, "loss": 0.8675428628921509, "grad_norm": 0.4539531171321869, "learning_rate": 0.00019989918348372156}
-{"ts": "2025-12-26T23:34:54", "event": "train_log", "step": 1328, "epoch": 0.560337552742616, "progress_pct": 9.34, "epoch_pct": 9.34, "eta": "51:24:27", "max_grad_norm": 1.0, "loss": 0.8853429555892944, "grad_norm": 0.44469985365867615, "learning_rate": 0.00019989701582079591}
-{"ts": "2025-12-26T23:35:08", "event": "train_log", "step": 1330, "epoch": 0.5611814345991561, "progress_pct": 9.35, "epoch_pct": 9.35, "eta": "51:21:37", "max_grad_norm": 1.0, "loss": 0.9675378799438477, "grad_norm": 0.4485546946525574, "learning_rate": 0.00019989482511354725}
-{"ts": "2025-12-26T23:35:23", "event": "train_log", "step": 1332, "epoch": 0.5620253164556962, "progress_pct": 9.37, "epoch_pct": 9.37, "eta": "51:18:52", "max_grad_norm": 1.0, "loss": 0.8256655335426331, "grad_norm": 0.43316468596458435, "learning_rate": 0.00019989261136248097}
-{"ts": "2025-12-26T23:35:38", "event": "train_log", "step": 1334, "epoch": 0.5628691983122363, "progress_pct": 9.38, "epoch_pct": 9.38, "eta": "51:16:17", "max_grad_norm": 1.0, "loss": 0.7727690935134888, "grad_norm": 0.4315780699253082, "learning_rate": 0.00019989037456810772}
-{"ts": "2025-12-26T23:35:53", "event": "train_log", "step": 1336, "epoch": 0.5637130801687764, "progress_pct": 9.4, "epoch_pct": 9.4, "eta": "51:13:34", "max_grad_norm": 1.0, "loss": 0.9240618348121643, "grad_norm": 0.45147502422332764, "learning_rate": 0.00019988811473094348}
-{"ts": "2025-12-26T23:36:08", "event": "train_log", "step": 1338, "epoch": 0.5645569620253165, "progress_pct": 9.41, "epoch_pct": 9.41, "eta": "51:10:57", "max_grad_norm": 1.0, "loss": 0.8005949258804321, "grad_norm": 0.4606908857822418, "learning_rate": 0.00019988583185150957}
-{"ts": "2025-12-26T23:36:23", "event": "train_log", "step": 1340, "epoch": 0.5654008438818565, "progress_pct": 9.42, "epoch_pct": 9.42, "eta": "51:08:12", "max_grad_norm": 1.0, "loss": 0.9042718410491943, "grad_norm": 0.48932451009750366, "learning_rate": 0.00019988352593033255}
-{"ts": "2025-12-26T23:36:37", "event": "train_log", "step": 1342, "epoch": 0.5662447257383966, "progress_pct": 9.44, "epoch_pct": 9.44, "eta": "51:05:23", "max_grad_norm": 1.0, "loss": 0.8724613785743713, "grad_norm": 0.46022218465805054, "learning_rate": 0.00019988119696794443}
-{"ts": "2025-12-26T23:36:52", "event": "train_log", "step": 1344, "epoch": 0.5670886075949367, "progress_pct": 9.45, "epoch_pct": 9.45, "eta": "51:02:44", "max_grad_norm": 1.0, "loss": 0.8653066158294678, "grad_norm": 0.4414621889591217, "learning_rate": 0.00019987884496488242}
-{"ts": "2025-12-26T23:37:06", "event": "train_log", "step": 1346, "epoch": 0.5679324894514768, "progress_pct": 9.47, "epoch_pct": 9.47, "eta": "51:00:04", "max_grad_norm": 1.0, "loss": 0.8843849301338196, "grad_norm": 0.4490342140197754, "learning_rate": 0.0001998764699216891}
-{"ts": "2025-12-26T23:37:22", "event": "train_log", "step": 1348, "epoch": 0.5687763713080168, "progress_pct": 9.48, "epoch_pct": 9.48, "eta": "50:57:30", "max_grad_norm": 1.0, "loss": 0.8385393023490906, "grad_norm": 0.47690069675445557, "learning_rate": 0.00019987407183891232}
-{"ts": "2025-12-26T23:37:37", "event": "train_log", "step": 1350, "epoch": 0.569620253164557, "progress_pct": 9.49, "epoch_pct": 9.49, "eta": "50:54:52", "max_grad_norm": 1.0, "loss": 0.77492755651474, "grad_norm": 0.41409361362457275, "learning_rate": 0.00019987165071710527}
-{"ts": "2025-12-26T23:37:52", "event": "train_log", "step": 1352, "epoch": 0.570464135021097, "progress_pct": 9.51, "epoch_pct": 9.51, "eta": "50:52:19", "max_grad_norm": 1.0, "loss": 0.8368680477142334, "grad_norm": 0.4151647984981537, "learning_rate": 0.0001998692065568265}
-{"ts": "2025-12-26T23:38:08", "event": "train_log", "step": 1354, "epoch": 0.5713080168776371, "progress_pct": 9.52, "epoch_pct": 9.52, "eta": "50:49:53", "max_grad_norm": 1.0, "loss": 0.833220362663269, "grad_norm": 0.4105067849159241, "learning_rate": 0.0001998667393586398}
-{"ts": "2025-12-26T23:38:24", "event": "train_log", "step": 1356, "epoch": 0.5721518987341773, "progress_pct": 9.54, "epoch_pct": 9.54, "eta": "50:47:24", "max_grad_norm": 1.0, "loss": 0.8041552305221558, "grad_norm": 0.44701820611953735, "learning_rate": 0.0001998642491231143}
-{"ts": "2025-12-26T23:38:39", "event": "train_log", "step": 1358, "epoch": 0.5729957805907173, "progress_pct": 9.55, "epoch_pct": 9.55, "eta": "50:44:48", "max_grad_norm": 1.0, "loss": 0.9052709937095642, "grad_norm": 0.4621582329273224, "learning_rate": 0.00019986173585082444}
-{"ts": "2025-12-26T23:38:53", "event": "train_log", "step": 1360, "epoch": 0.5738396624472574, "progress_pct": 9.56, "epoch_pct": 9.56, "eta": "50:42:04", "max_grad_norm": 1.0, "loss": 0.8036054372787476, "grad_norm": 0.4934713840484619, "learning_rate": 0.00019985919954235005}
-{"ts": "2025-12-26T23:39:09", "event": "train_log", "step": 1362, "epoch": 0.5746835443037974, "progress_pct": 9.58, "epoch_pct": 9.58, "eta": "50:39:38", "max_grad_norm": 1.0, "loss": 0.8340095281600952, "grad_norm": 0.4557384252548218, "learning_rate": 0.0001998566401982761}
-{"ts": "2025-12-26T23:39:24", "event": "train_log", "step": 1364, "epoch": 0.5755274261603376, "progress_pct": 9.59, "epoch_pct": 9.59, "eta": "50:37:04", "max_grad_norm": 1.0, "loss": 0.8703633546829224, "grad_norm": 0.5048403739929199, "learning_rate": 0.00019985405781919305}
-{"ts": "2025-12-26T23:39:39", "event": "train_log", "step": 1366, "epoch": 0.5763713080168776, "progress_pct": 9.61, "epoch_pct": 9.61, "eta": "50:34:28", "max_grad_norm": 1.0, "loss": 0.9115830659866333, "grad_norm": 0.4707714319229126, "learning_rate": 0.0001998514524056966}
-{"ts": "2025-12-26T23:39:54", "event": "train_log", "step": 1368, "epoch": 0.5772151898734177, "progress_pct": 9.62, "epoch_pct": 9.62, "eta": "50:31:56", "max_grad_norm": 1.0, "loss": 0.8603149056434631, "grad_norm": 0.4502186179161072, "learning_rate": 0.00019984882395838777}
-{"ts": "2025-12-26T23:40:10", "event": "train_log", "step": 1370, "epoch": 0.5780590717299579, "progress_pct": 9.63, "epoch_pct": 9.63, "eta": "50:29:33", "max_grad_norm": 1.0, "loss": 0.7482197284698486, "grad_norm": 0.4229136109352112, "learning_rate": 0.00019984617247787288}
-{"ts": "2025-12-26T23:40:25", "event": "train_log", "step": 1372, "epoch": 0.5789029535864979, "progress_pct": 9.65, "epoch_pct": 9.65, "eta": "50:26:57", "max_grad_norm": 1.0, "loss": 0.9071239233016968, "grad_norm": 0.49208030104637146, "learning_rate": 0.0001998434979647636}
-{"ts": "2025-12-26T23:40:39", "event": "train_log", "step": 1374, "epoch": 0.579746835443038, "progress_pct": 9.66, "epoch_pct": 9.66, "eta": "50:24:20", "max_grad_norm": 1.0, "loss": 0.9370644092559814, "grad_norm": 0.47393161058425903, "learning_rate": 0.00019984080041967687}
-{"ts": "2025-12-26T23:40:54", "event": "train_log", "step": 1376, "epoch": 0.580590717299578, "progress_pct": 9.68, "epoch_pct": 9.68, "eta": "50:21:46", "max_grad_norm": 1.0, "loss": 0.8536180257797241, "grad_norm": 0.4483324885368347, "learning_rate": 0.00019983807984323492}
-{"ts": "2025-12-26T23:41:09", "event": "train_log", "step": 1378, "epoch": 0.5814345991561182, "progress_pct": 9.69, "epoch_pct": 9.69, "eta": "50:19:16", "max_grad_norm": 1.0, "loss": 0.7360405325889587, "grad_norm": 0.4163796007633209, "learning_rate": 0.00019983533623606543}
-{"ts": "2025-12-26T23:41:25", "event": "train_log", "step": 1380, "epoch": 0.5822784810126582, "progress_pct": 9.7, "epoch_pct": 9.7, "eta": "50:16:56", "max_grad_norm": 1.0, "loss": 0.8162824511528015, "grad_norm": 0.44147446751594543, "learning_rate": 0.00019983256959880122}
-{"ts": "2025-12-26T23:41:41", "event": "train_log", "step": 1382, "epoch": 0.5831223628691983, "progress_pct": 9.72, "epoch_pct": 9.72, "eta": "50:14:36", "max_grad_norm": 1.0, "loss": 0.9169327616691589, "grad_norm": 0.44443491101264954, "learning_rate": 0.0001998297799320805}
-{"ts": "2025-12-26T23:41:58", "event": "train_log", "step": 1384, "epoch": 0.5839662447257384, "progress_pct": 9.73, "epoch_pct": 9.73, "eta": "50:12:18", "max_grad_norm": 1.0, "loss": 0.8875693678855896, "grad_norm": 0.4641949236392975, "learning_rate": 0.00019982696723654686}
-{"ts": "2025-12-26T23:42:15", "event": "train_log", "step": 1386, "epoch": 0.5848101265822785, "progress_pct": 9.75, "epoch_pct": 9.75, "eta": "50:10:13", "max_grad_norm": 1.0, "loss": 0.7747344970703125, "grad_norm": 0.4327974319458008, "learning_rate": 0.00019982413151284906}
-{"ts": "2025-12-26T23:42:32", "event": "train_log", "step": 1388, "epoch": 0.5856540084388185, "progress_pct": 9.76, "epoch_pct": 9.76, "eta": "50:07:54", "max_grad_norm": 1.0, "loss": 0.8490481972694397, "grad_norm": 0.44200772047042847, "learning_rate": 0.0001998212727616413}
-{"ts": "2025-12-26T23:42:47", "event": "train_log", "step": 1390, "epoch": 0.5864978902953587, "progress_pct": 9.77, "epoch_pct": 9.77, "eta": "50:05:32", "max_grad_norm": 1.0, "loss": 0.8014808297157288, "grad_norm": 0.39084959030151367, "learning_rate": 0.000199818390983583}
-{"ts": "2025-12-26T23:43:03", "event": "train_log", "step": 1392, "epoch": 0.5873417721518988, "progress_pct": 9.79, "epoch_pct": 9.79, "eta": "50:03:11", "max_grad_norm": 1.0, "loss": 0.8650928139686584, "grad_norm": 0.3691277801990509, "learning_rate": 0.00019981548617933897}
-{"ts": "2025-12-26T23:43:20", "event": "train_log", "step": 1394, "epoch": 0.5881856540084388, "progress_pct": 9.8, "epoch_pct": 9.8, "eta": "50:00:54", "max_grad_norm": 1.0, "loss": 0.7713267803192139, "grad_norm": 0.480002760887146, "learning_rate": 0.00019981255834957925}
-{"ts": "2025-12-26T23:43:35", "event": "train_log", "step": 1396, "epoch": 0.5890295358649789, "progress_pct": 9.82, "epoch_pct": 9.82, "eta": "49:58:27", "max_grad_norm": 1.0, "loss": 0.9053656458854675, "grad_norm": 0.4397226572036743, "learning_rate": 0.00019980960749497927}
-{"ts": "2025-12-26T23:43:51", "event": "train_log", "step": 1398, "epoch": 0.589873417721519, "progress_pct": 9.83, "epoch_pct": 9.83, "eta": "49:56:12", "max_grad_norm": 1.0, "loss": 0.8737669587135315, "grad_norm": 0.4263727366924286, "learning_rate": 0.00019980663361621973}
-{"ts": "2025-12-26T23:44:06", "event": "train_log", "step": 1400, "epoch": 0.5907172995780591, "progress_pct": 9.85, "epoch_pct": 9.85, "eta": "49:53:45", "max_grad_norm": 1.0, "loss": 0.9396650791168213, "grad_norm": 0.4468817710876465, "learning_rate": 0.0001998036367139866}
-{"ts": "2025-12-26T23:55:39", "event": "train_log", "step": 1400, "epoch": 0.5907172995780591, "progress_pct": 9.85, "epoch_pct": 9.85, "eta": "51:39:29", "max_grad_norm": 1.0, "eval_loss": 0.8971880674362183, "eval_runtime": 692.8046, "eval_samples_per_second": 3.041, "eval_steps_per_second": 3.041}
-{"ts": "2025-12-26T23:55:55", "event": "train_log", "step": 1402, "epoch": 0.5915611814345991, "progress_pct": 9.86, "epoch_pct": 9.86, "eta": "51:36:59", "max_grad_norm": 1.0, "loss": 0.926134467124939, "grad_norm": 0.4128144383430481, "learning_rate": 0.00019980061678897127}
-{"ts": "2025-12-26T23:56:11", "event": "train_log", "step": 1404, "epoch": 0.5924050632911393, "progress_pct": 9.87, "epoch_pct": 9.87, "eta": "51:34:34", "max_grad_norm": 1.0, "loss": 0.826360285282135, "grad_norm": 0.45524629950523376, "learning_rate": 0.00019979757384187035}
-{"ts": "2025-12-26T23:56:26", "event": "train_log", "step": 1406, "epoch": 0.5932489451476793, "progress_pct": 9.89, "epoch_pct": 9.89, "eta": "51:32:01", "max_grad_norm": 1.0, "loss": 0.8147702813148499, "grad_norm": 0.42521336674690247, "learning_rate": 0.0001997945078733858}
-{"ts": "2025-12-26T23:56:42", "event": "train_log", "step": 1408, "epoch": 0.5940928270042194, "progress_pct": 9.9, "epoch_pct": 9.9, "eta": "51:29:32", "max_grad_norm": 1.0, "loss": 0.7711596488952637, "grad_norm": 0.4172525107860565, "learning_rate": 0.00019979141888422489}
-{"ts": "2025-12-26T23:56:57", "event": "train_log", "step": 1410, "epoch": 0.5949367088607594, "progress_pct": 9.92, "epoch_pct": 9.92, "eta": "51:26:58", "max_grad_norm": 1.0, "loss": 0.7875980138778687, "grad_norm": 0.46193623542785645, "learning_rate": 0.00019978830687510013}
-{"ts": "2025-12-26T23:57:13", "event": "train_log", "step": 1412, "epoch": 0.5957805907172996, "progress_pct": 9.93, "epoch_pct": 9.93, "eta": "51:24:26", "max_grad_norm": 1.0, "loss": 0.8590195178985596, "grad_norm": 0.4455825686454773, "learning_rate": 0.00019978517184672946}
-{"ts": "2025-12-26T23:57:27", "event": "train_log", "step": 1414, "epoch": 0.5966244725738397, "progress_pct": 9.94, "epoch_pct": 9.94, "eta": "51:21:45", "max_grad_norm": 1.0, "loss": 0.9318227767944336, "grad_norm": 0.4266505539417267, "learning_rate": 0.00019978201379983608}
-{"ts": "2025-12-26T23:57:42", "event": "train_log", "step": 1416, "epoch": 0.5974683544303797, "progress_pct": 9.96, "epoch_pct": 9.96, "eta": "51:19:14", "max_grad_norm": 1.0, "loss": 0.8644474744796753, "grad_norm": 0.42627251148223877, "learning_rate": 0.00019977883273514843}
-{"ts": "2025-12-26T23:57:58", "event": "train_log", "step": 1418, "epoch": 0.5983122362869199, "progress_pct": 9.97, "epoch_pct": 9.97, "eta": "51:16:47", "max_grad_norm": 1.0, "loss": 0.7760446071624756, "grad_norm": 0.393873393535614, "learning_rate": 0.00019977562865340038}
-{"ts": "2025-12-26T23:58:14", "event": "train_log", "step": 1420, "epoch": 0.5991561181434599, "progress_pct": 9.99, "epoch_pct": 9.99, "eta": "51:14:18", "max_grad_norm": 1.0, "loss": 0.8071584701538086, "grad_norm": 0.44334208965301514, "learning_rate": 0.000199772401555331}
-{"ts": "2025-12-26T23:58:28", "event": "train_log", "step": 1422, "epoch": 0.6, "progress_pct": 10.0, "epoch_pct": 10.0, "eta": "51:11:43", "max_grad_norm": 1.0, "loss": 0.9076889753341675, "grad_norm": 0.39390063285827637, "learning_rate": 0.0001997691514416848}
-{"ts": "2025-12-26T23:58:43", "event": "train_log", "step": 1424, "epoch": 0.60084388185654, "progress_pct": 10.01, "epoch_pct": 10.01, "eta": "51:09:08", "max_grad_norm": 1.0, "loss": 0.8534318804740906, "grad_norm": 0.46753421425819397, "learning_rate": 0.00019976587831321144}
-{"ts": "2025-12-26T23:58:57", "event": "train_log", "step": 1426, "epoch": 0.6016877637130802, "progress_pct": 10.03, "epoch_pct": 10.03, "eta": "51:06:29", "max_grad_norm": 1.0, "loss": 0.9049596190452576, "grad_norm": 0.4840681254863739, "learning_rate": 0.00019976258217066598}
-{"ts": "2025-12-26T23:59:12", "event": "train_log", "step": 1428, "epoch": 0.6025316455696202, "progress_pct": 10.04, "epoch_pct": 10.04, "eta": "51:03:54", "max_grad_norm": 1.0, "loss": 0.8520918488502502, "grad_norm": 0.4740557372570038, "learning_rate": 0.00019975926301480878}
-{"ts": "2025-12-26T23:59:27", "event": "train_log", "step": 1430, "epoch": 0.6033755274261603, "progress_pct": 10.06, "epoch_pct": 10.06, "eta": "51:01:21", "max_grad_norm": 1.0, "loss": 0.8221305012702942, "grad_norm": 0.46498584747314453, "learning_rate": 0.00019975592084640553}
-{"ts": "2025-12-26T23:59:42", "event": "train_log", "step": 1432, "epoch": 0.6042194092827005, "progress_pct": 10.07, "epoch_pct": 10.07, "eta": "50:58:52", "max_grad_norm": 1.0, "loss": 0.8132198452949524, "grad_norm": 0.40885692834854126, "learning_rate": 0.0001997525556662272}
-{"ts": "2025-12-26T23:59:57", "event": "train_log", "step": 1434, "epoch": 0.6050632911392405, "progress_pct": 10.08, "epoch_pct": 10.08, "eta": "50:56:19", "max_grad_norm": 1.0, "loss": 0.870534360408783, "grad_norm": 0.4375821053981781, "learning_rate": 0.00019974916747505006}
-{"ts": "2025-12-27T00:00:12", "event": "train_log", "step": 1436, "epoch": 0.6059071729957806, "progress_pct": 10.1, "epoch_pct": 10.1, "eta": "50:53:46", "max_grad_norm": 1.0, "loss": 0.8825759291648865, "grad_norm": 0.4780935049057007, "learning_rate": 0.00019974575627365569}
-{"ts": "2025-12-27T00:00:27", "event": "train_log", "step": 1438, "epoch": 0.6067510548523207, "progress_pct": 10.11, "epoch_pct": 10.11, "eta": "50:51:15", "max_grad_norm": 1.0, "loss": 0.8187641501426697, "grad_norm": 0.4623970687389374, "learning_rate": 0.00019974232206283098}
-{"ts": "2025-12-27T00:00:42", "event": "train_log", "step": 1440, "epoch": 0.6075949367088608, "progress_pct": 10.13, "epoch_pct": 10.13, "eta": "50:48:47", "max_grad_norm": 1.0, "loss": 0.8569821119308472, "grad_norm": 0.42172595858573914, "learning_rate": 0.0001997388648433682}
-{"ts": "2025-12-27T00:00:56", "event": "train_log", "step": 1442, "epoch": 0.6084388185654008, "progress_pct": 10.14, "epoch_pct": 10.14, "eta": "50:46:13", "max_grad_norm": 1.0, "loss": 0.9173614382743835, "grad_norm": 0.49386659264564514, "learning_rate": 0.0001997353846160648}
-{"ts": "2025-12-27T00:01:11", "event": "train_log", "step": 1444, "epoch": 0.6092827004219409, "progress_pct": 10.15, "epoch_pct": 10.15, "eta": "50:43:46", "max_grad_norm": 1.0, "loss": 0.9444975256919861, "grad_norm": 0.47122615575790405, "learning_rate": 0.00019973188138172363}
-{"ts": "2025-12-27T00:01:26", "event": "train_log", "step": 1446, "epoch": 0.610126582278481, "progress_pct": 10.17, "epoch_pct": 10.17, "eta": "50:41:13", "max_grad_norm": 1.0, "loss": 0.9537245631217957, "grad_norm": 0.4831530451774597, "learning_rate": 0.0001997283551411528}
-{"ts": "2025-12-27T00:01:42", "event": "train_log", "step": 1448, "epoch": 0.6109704641350211, "progress_pct": 10.18, "epoch_pct": 10.18, "eta": "50:38:53", "max_grad_norm": 1.0, "loss": 0.8481367230415344, "grad_norm": 0.44460317492485046, "learning_rate": 0.0001997248058951658}
-{"ts": "2025-12-27T00:01:57", "event": "train_log", "step": 1450, "epoch": 0.6118143459915611, "progress_pct": 10.2, "epoch_pct": 10.2, "eta": "50:36:23", "max_grad_norm": 1.0, "loss": 0.8572371006011963, "grad_norm": 0.4315263628959656, "learning_rate": 0.00019972123364458128}
-{"ts": "2025-12-27T00:02:12", "event": "train_log", "step": 1452, "epoch": 0.6126582278481013, "progress_pct": 10.21, "epoch_pct": 10.21, "eta": "50:33:58", "max_grad_norm": 1.0, "loss": 0.762590765953064, "grad_norm": 0.38559582829475403, "learning_rate": 0.00019971763839022336}
-{"ts": "2025-12-27T00:02:27", "event": "train_log", "step": 1454, "epoch": 0.6135021097046414, "progress_pct": 10.23, "epoch_pct": 10.23, "eta": "50:31:35", "max_grad_norm": 1.0, "loss": 0.7879500389099121, "grad_norm": 0.3820290267467499, "learning_rate": 0.00019971402013292138}
-{"ts": "2025-12-27T00:02:42", "event": "train_log", "step": 1456, "epoch": 0.6143459915611814, "progress_pct": 10.24, "epoch_pct": 10.24, "eta": "50:29:07", "max_grad_norm": 1.0, "loss": 0.8696863055229187, "grad_norm": 0.42509570717811584, "learning_rate": 0.00019971037887351}
-{"ts": "2025-12-27T00:02:57", "event": "train_log", "step": 1458, "epoch": 0.6151898734177215, "progress_pct": 10.25, "epoch_pct": 10.25, "eta": "50:26:34", "max_grad_norm": 1.0, "loss": 0.8425862789154053, "grad_norm": 0.46750548481941223, "learning_rate": 0.00019970671461282916}
-{"ts": "2025-12-27T00:03:12", "event": "train_log", "step": 1460, "epoch": 0.6160337552742616, "progress_pct": 10.27, "epoch_pct": 10.27, "eta": "50:24:12", "max_grad_norm": 1.0, "loss": 0.8028931021690369, "grad_norm": 0.3937121033668518, "learning_rate": 0.0001997030273517242}
-{"ts": "2025-12-27T00:03:27", "event": "train_log", "step": 1462, "epoch": 0.6168776371308017, "progress_pct": 10.28, "epoch_pct": 10.28, "eta": "50:21:46", "max_grad_norm": 1.0, "loss": 0.8662509918212891, "grad_norm": 0.4361220896244049, "learning_rate": 0.00019969931709104565}
-{"ts": "2025-12-27T00:03:41", "event": "train_log", "step": 1464, "epoch": 0.6177215189873417, "progress_pct": 10.3, "epoch_pct": 10.3, "eta": "50:19:13", "max_grad_norm": 1.0, "loss": 0.8962596654891968, "grad_norm": 0.4737963378429413, "learning_rate": 0.00019969558383164943}
-{"ts": "2025-12-27T00:03:57", "event": "train_log", "step": 1466, "epoch": 0.6185654008438819, "progress_pct": 10.31, "epoch_pct": 10.31, "eta": "50:16:54", "max_grad_norm": 1.0, "loss": 0.8630867600440979, "grad_norm": 0.3952867388725281, "learning_rate": 0.00019969182757439668}
-{"ts": "2025-12-27T00:04:12", "event": "train_log", "step": 1468, "epoch": 0.619409282700422, "progress_pct": 10.32, "epoch_pct": 10.32, "eta": "50:14:32", "max_grad_norm": 1.0, "loss": 0.8759240508079529, "grad_norm": 0.41688743233680725, "learning_rate": 0.00019968804832015393}
-{"ts": "2025-12-27T00:04:26", "event": "train_log", "step": 1470, "epoch": 0.620253164556962, "progress_pct": 10.34, "epoch_pct": 10.34, "eta": "50:12:03", "max_grad_norm": 1.0, "loss": 0.8459385633468628, "grad_norm": 0.4599224627017975, "learning_rate": 0.00019968424606979298}
-{"ts": "2025-12-27T00:04:41", "event": "train_log", "step": 1472, "epoch": 0.6210970464135022, "progress_pct": 10.35, "epoch_pct": 10.35, "eta": "50:09:36", "max_grad_norm": 1.0, "loss": 0.8844659328460693, "grad_norm": 0.5476765632629395, "learning_rate": 0.00019968042082419094}
-{"ts": "2025-12-27T00:04:56", "event": "train_log", "step": 1474, "epoch": 0.6219409282700422, "progress_pct": 10.37, "epoch_pct": 10.37, "eta": "50:07:12", "max_grad_norm": 1.0, "loss": 0.860946536064148, "grad_norm": 0.46202269196510315, "learning_rate": 0.00019967657258423022}
-{"ts": "2025-12-27T00:05:12", "event": "train_log", "step": 1476, "epoch": 0.6227848101265823, "progress_pct": 10.38, "epoch_pct": 10.38, "eta": "50:04:53", "max_grad_norm": 1.0, "loss": 0.7587860822677612, "grad_norm": 0.39446666836738586, "learning_rate": 0.00019967270135079853}
-{"ts": "2025-12-27T00:05:27", "event": "train_log", "step": 1478, "epoch": 0.6236286919831223, "progress_pct": 10.39, "epoch_pct": 10.39, "eta": "50:02:33", "max_grad_norm": 1.0, "loss": 0.9143000245094299, "grad_norm": 0.4500375986099243, "learning_rate": 0.0001996688071247889}
-{"ts": "2025-12-27T00:05:42", "event": "train_log", "step": 1480, "epoch": 0.6244725738396625, "progress_pct": 10.41, "epoch_pct": 10.41, "eta": "50:00:13", "max_grad_norm": 1.0, "loss": 0.7865519523620605, "grad_norm": 0.4203545153141022, "learning_rate": 0.0001996648899070996}
-{"ts": "2025-12-27T00:05:56", "event": "train_log", "step": 1482, "epoch": 0.6253164556962025, "progress_pct": 10.42, "epoch_pct": 10.42, "eta": "49:57:42", "max_grad_norm": 1.0, "loss": 0.9192912578582764, "grad_norm": 0.45623889565467834, "learning_rate": 0.00019966094969863432}
-{"ts": "2025-12-27T00:06:11", "event": "train_log", "step": 1484, "epoch": 0.6261603375527426, "progress_pct": 10.44, "epoch_pct": 10.44, "eta": "49:55:22", "max_grad_norm": 1.0, "loss": 0.8459161520004272, "grad_norm": 0.4139637053012848, "learning_rate": 0.00019965698650030195}
-{"ts": "2025-12-27T00:06:26", "event": "train_log", "step": 1486, "epoch": 0.6270042194092827, "progress_pct": 10.45, "epoch_pct": 10.45, "eta": "49:52:56", "max_grad_norm": 1.0, "loss": 0.8159077763557434, "grad_norm": 0.4410824179649353, "learning_rate": 0.00019965300031301678}
-{"ts": "2025-12-27T00:06:41", "event": "train_log", "step": 1488, "epoch": 0.6278481012658228, "progress_pct": 10.46, "epoch_pct": 10.46, "eta": "49:50:34", "max_grad_norm": 1.0, "loss": 0.884467363357544, "grad_norm": 0.43821197748184204, "learning_rate": 0.00019964899113769828}
-{"ts": "2025-12-27T00:06:55", "event": "train_log", "step": 1490, "epoch": 0.6286919831223629, "progress_pct": 10.48, "epoch_pct": 10.48, "eta": "49:48:06", "max_grad_norm": 1.0, "loss": 0.8693601489067078, "grad_norm": 0.4692091643810272, "learning_rate": 0.00019964495897527133}
-{"ts": "2025-12-27T00:07:10", "event": "train_log", "step": 1492, "epoch": 0.6295358649789029, "progress_pct": 10.49, "epoch_pct": 10.49, "eta": "49:45:43", "max_grad_norm": 1.0, "loss": 0.8897743225097656, "grad_norm": 0.40715447068214417, "learning_rate": 0.00019964090382666608}
-{"ts": "2025-12-27T00:07:25", "event": "train_log", "step": 1494, "epoch": 0.6303797468354431, "progress_pct": 10.51, "epoch_pct": 10.51, "eta": "49:43:25", "max_grad_norm": 1.0, "loss": 0.8274733424186707, "grad_norm": 0.4123334586620331, "learning_rate": 0.0001996368256928179}
-{"ts": "2025-12-27T00:07:40", "event": "train_log", "step": 1496, "epoch": 0.6312236286919831, "progress_pct": 10.52, "epoch_pct": 10.52, "eta": "49:41:03", "max_grad_norm": 1.0, "loss": 0.8158749938011169, "grad_norm": 0.44347211718559265, "learning_rate": 0.00019963272457466767}
-{"ts": "2025-12-27T00:07:54", "event": "train_log", "step": 1498, "epoch": 0.6320675105485232, "progress_pct": 10.53, "epoch_pct": 10.53, "eta": "49:38:40", "max_grad_norm": 1.0, "loss": 0.8439569473266602, "grad_norm": 0.4700329601764679, "learning_rate": 0.00019962860047316135}
-{"ts": "2025-12-27T00:08:09", "event": "train_log", "step": 1500, "epoch": 0.6329113924050633, "progress_pct": 10.55, "epoch_pct": 10.55, "eta": "49:36:19", "max_grad_norm": 1.0, "loss": 0.8316822648048401, "grad_norm": 0.46415844559669495, "learning_rate": 0.00019962445338925027}
-{"ts": "2025-12-27T00:19:35", "event": "train_log", "step": 1500, "epoch": 0.6329113924050633, "progress_pct": 10.55, "epoch_pct": 10.55, "eta": "51:13:18", "max_grad_norm": 1.0, "eval_loss": 0.887488842010498, "eval_runtime": 686.2804, "eval_samples_per_second": 3.07, "eval_steps_per_second": 3.07}
-{"ts": "2025-12-27T00:19:52", "event": "train_log", "step": 1502, "epoch": 0.6337552742616034, "progress_pct": 10.56, "epoch_pct": 10.56, "eta": "51:11:03", "max_grad_norm": 1.0, "loss": 0.9121994972229004, "grad_norm": 0.44183167815208435, "learning_rate": 0.0001996202833238911}
-{"ts": "2025-12-27T00:20:08", "event": "train_log", "step": 1504, "epoch": 0.6345991561181434, "progress_pct": 10.58, "epoch_pct": 10.58, "eta": "51:08:43", "max_grad_norm": 1.0, "loss": 0.9160211086273193, "grad_norm": 0.4279208779335022, "learning_rate": 0.00019961609027804587}
-{"ts": "2025-12-27T00:20:22", "event": "train_log", "step": 1506, "epoch": 0.6354430379746835, "progress_pct": 10.59, "epoch_pct": 10.59, "eta": "51:06:13", "max_grad_norm": 1.0, "loss": 0.861677348613739, "grad_norm": 0.3967169523239136, "learning_rate": 0.00019961187425268176}
-{"ts": "2025-12-27T00:20:38", "event": "train_log", "step": 1508, "epoch": 0.6362869198312237, "progress_pct": 10.6, "epoch_pct": 10.6, "eta": "51:03:57", "max_grad_norm": 1.0, "loss": 0.8478423357009888, "grad_norm": 0.4796451926231384, "learning_rate": 0.0001996076352487713}
-{"ts": "2025-12-27T00:20:55", "event": "train_log", "step": 1510, "epoch": 0.6371308016877637, "progress_pct": 10.62, "epoch_pct": 10.62, "eta": "51:01:45", "max_grad_norm": 1.0, "loss": 0.8739159107208252, "grad_norm": 0.3861426115036011, "learning_rate": 0.00019960337326729245}
-{"ts": "2025-12-27T00:21:12", "event": "train_log", "step": 1512, "epoch": 0.6379746835443038, "progress_pct": 10.63, "epoch_pct": 10.63, "eta": "50:59:31", "max_grad_norm": 1.0, "loss": 0.7693920731544495, "grad_norm": 0.4567820429801941, "learning_rate": 0.00019959908830922824}
-{"ts": "2025-12-27T00:21:27", "event": "train_log", "step": 1514, "epoch": 0.6388185654008439, "progress_pct": 10.65, "epoch_pct": 10.65, "eta": "50:57:13", "max_grad_norm": 1.0, "loss": 0.8482301831245422, "grad_norm": 0.4457108676433563, "learning_rate": 0.00019959478037556724}
-{"ts": "2025-12-27T00:21:43", "event": "train_log", "step": 1516, "epoch": 0.639662447257384, "progress_pct": 10.66, "epoch_pct": 10.66, "eta": "50:54:57", "max_grad_norm": 1.0, "loss": 0.8626812696456909, "grad_norm": 0.43918928503990173, "learning_rate": 0.00019959044946730314}
-{"ts": "2025-12-27T00:22:01", "event": "train_log", "step": 1518, "epoch": 0.640506329113924, "progress_pct": 10.68, "epoch_pct": 10.68, "eta": "50:52:51", "max_grad_norm": 1.0, "loss": 0.8342230916023254, "grad_norm": 0.4095900058746338, "learning_rate": 0.00019958609558543504}
-{"ts": "2025-12-27T00:22:17", "event": "train_log", "step": 1520, "epoch": 0.6413502109704642, "progress_pct": 10.69, "epoch_pct": 10.69, "eta": "50:50:34", "max_grad_norm": 1.0, "loss": 0.8794118165969849, "grad_norm": 0.4181270897388458, "learning_rate": 0.00019958171873096724}
-{"ts": "2025-12-27T00:22:32", "event": "train_log", "step": 1522, "epoch": 0.6421940928270042, "progress_pct": 10.7, "epoch_pct": 10.7, "eta": "50:48:15", "max_grad_norm": 1.0, "loss": 0.7787677049636841, "grad_norm": 0.4750959277153015, "learning_rate": 0.00019957731890490947}
-{"ts": "2025-12-27T00:22:47", "event": "train_log", "step": 1524, "epoch": 0.6430379746835443, "progress_pct": 10.72, "epoch_pct": 10.72, "eta": "50:45:53", "max_grad_norm": 1.0, "loss": 0.9084368348121643, "grad_norm": 0.5129296779632568, "learning_rate": 0.00019957289610827663}
-{"ts": "2025-12-27T00:23:03", "event": "train_log", "step": 1526, "epoch": 0.6438818565400843, "progress_pct": 10.73, "epoch_pct": 10.73, "eta": "50:43:31", "max_grad_norm": 1.0, "loss": 0.9066952466964722, "grad_norm": 0.4829029142856598, "learning_rate": 0.000199568450342089}
-{"ts": "2025-12-27T00:23:18", "event": "train_log", "step": 1528, "epoch": 0.6447257383966245, "progress_pct": 10.75, "epoch_pct": 10.75, "eta": "50:41:13", "max_grad_norm": 1.0, "loss": 0.8127874732017517, "grad_norm": 0.4225057363510132, "learning_rate": 0.00019956398160737214}
-{"ts": "2025-12-27T00:23:33", "event": "train_log", "step": 1530, "epoch": 0.6455696202531646, "progress_pct": 10.76, "epoch_pct": 10.76, "eta": "50:38:51", "max_grad_norm": 1.0, "loss": 0.8781921863555908, "grad_norm": 0.4231826364994049, "learning_rate": 0.00019955948990515684}
-{"ts": "2025-12-27T00:23:48", "event": "train_log", "step": 1532, "epoch": 0.6464135021097046, "progress_pct": 10.77, "epoch_pct": 10.77, "eta": "50:36:29", "max_grad_norm": 1.0, "loss": 0.8136996626853943, "grad_norm": 0.4436216950416565, "learning_rate": 0.00019955497523647933}
-{"ts": "2025-12-27T00:24:05", "event": "train_log", "step": 1534, "epoch": 0.6472573839662448, "progress_pct": 10.79, "epoch_pct": 10.79, "eta": "50:34:17", "max_grad_norm": 1.0, "loss": 0.8003877401351929, "grad_norm": 0.4018244743347168, "learning_rate": 0.00019955043760238098}
-{"ts": "2025-12-27T00:24:22", "event": "train_log", "step": 1536, "epoch": 0.6481012658227848, "progress_pct": 10.8, "epoch_pct": 10.8, "eta": "50:32:17", "max_grad_norm": 1.0, "loss": 0.8996267914772034, "grad_norm": 0.40024611353874207, "learning_rate": 0.0001995458770039086}
-{"ts": "2025-12-27T00:24:39", "event": "train_log", "step": 1538, "epoch": 0.6489451476793249, "progress_pct": 10.82, "epoch_pct": 10.82, "eta": "50:30:05", "max_grad_norm": 1.0, "loss": 0.8610522150993347, "grad_norm": 0.42845702171325684, "learning_rate": 0.00019954129344211424}
-{"ts": "2025-12-27T00:24:55", "event": "train_log", "step": 1540, "epoch": 0.6497890295358649, "progress_pct": 10.83, "epoch_pct": 10.83, "eta": "50:27:56", "max_grad_norm": 1.0, "loss": 0.8991837501525879, "grad_norm": 0.4258182644844055, "learning_rate": 0.00019953668691805517}
-{"ts": "2025-12-27T00:25:10", "event": "train_log", "step": 1542, "epoch": 0.6506329113924051, "progress_pct": 10.84, "epoch_pct": 10.84, "eta": "50:25:34", "max_grad_norm": 1.0, "loss": 0.8150189518928528, "grad_norm": 0.4483257830142975, "learning_rate": 0.0001995320574327941}
-{"ts": "2025-12-27T00:25:25", "event": "train_log", "step": 1544, "epoch": 0.6514767932489451, "progress_pct": 10.86, "epoch_pct": 10.86, "eta": "50:23:15", "max_grad_norm": 1.0, "loss": 0.8572840690612793, "grad_norm": 0.4320627748966217, "learning_rate": 0.0001995274049873989}
-{"ts": "2025-12-27T00:25:42", "event": "train_log", "step": 1546, "epoch": 0.6523206751054852, "progress_pct": 10.87, "epoch_pct": 10.87, "eta": "50:21:12", "max_grad_norm": 1.0, "loss": 0.7766129374504089, "grad_norm": 0.39950594305992126, "learning_rate": 0.00019952272958294288}
-{"ts": "2025-12-27T00:25:58", "event": "train_log", "step": 1548, "epoch": 0.6531645569620254, "progress_pct": 10.89, "epoch_pct": 10.89, "eta": "50:18:58", "max_grad_norm": 1.0, "loss": 0.9032199382781982, "grad_norm": 0.4130117893218994, "learning_rate": 0.00019951803122050446}
-{"ts": "2025-12-27T00:26:13", "event": "train_log", "step": 1550, "epoch": 0.6540084388185654, "progress_pct": 10.9, "epoch_pct": 10.9, "eta": "50:16:35", "max_grad_norm": 1.0, "loss": 0.8361048102378845, "grad_norm": 0.4436919391155243, "learning_rate": 0.00019951330990116754}
-{"ts": "2025-12-27T00:26:29", "event": "train_log", "step": 1552, "epoch": 0.6548523206751055, "progress_pct": 10.91, "epoch_pct": 10.91, "eta": "50:14:26", "max_grad_norm": 1.0, "loss": 0.8661768436431885, "grad_norm": 0.4229227900505066, "learning_rate": 0.00019950856562602121}
-{"ts": "2025-12-27T00:26:44", "event": "train_log", "step": 1554, "epoch": 0.6556962025316456, "progress_pct": 10.93, "epoch_pct": 10.93, "eta": "50:12:13", "max_grad_norm": 1.0, "loss": 0.9737826585769653, "grad_norm": 0.4839727580547333, "learning_rate": 0.00019950379839615988}
-{"ts": "2025-12-27T00:27:01", "event": "train_log", "step": 1556, "epoch": 0.6565400843881857, "progress_pct": 10.94, "epoch_pct": 10.94, "eta": "50:10:04", "max_grad_norm": 1.0, "loss": 0.7542453408241272, "grad_norm": 0.3859386742115021, "learning_rate": 0.00019949900821268328}
-{"ts": "2025-12-27T00:27:18", "event": "train_log", "step": 1558, "epoch": 0.6573839662447257, "progress_pct": 10.96, "epoch_pct": 10.96, "eta": "50:08:02", "max_grad_norm": 1.0, "loss": 0.9226290583610535, "grad_norm": 0.39643988013267517, "learning_rate": 0.0001994941950766964}
-{"ts": "2025-12-27T00:27:32", "event": "train_log", "step": 1560, "epoch": 0.6582278481012658, "progress_pct": 10.97, "epoch_pct": 10.97, "eta": "50:05:42", "max_grad_norm": 1.0, "loss": 0.8375602960586548, "grad_norm": 0.4261355400085449, "learning_rate": 0.00019948935898930954}
-{"ts": "2025-12-27T00:27:49", "event": "train_log", "step": 1562, "epoch": 0.6590717299578059, "progress_pct": 10.98, "epoch_pct": 10.98, "eta": "50:03:35", "max_grad_norm": 1.0, "loss": 0.7847310304641724, "grad_norm": 0.445931077003479, "learning_rate": 0.00019948449995163826}
-{"ts": "2025-12-27T00:28:04", "event": "train_log", "step": 1564, "epoch": 0.659915611814346, "progress_pct": 11.0, "epoch_pct": 11.0, "eta": "50:01:16", "max_grad_norm": 1.0, "loss": 0.851150631904602, "grad_norm": 0.4680459797382355, "learning_rate": 0.00019947961796480353}
-{"ts": "2025-12-27T00:28:19", "event": "train_log", "step": 1566, "epoch": 0.660759493670886, "progress_pct": 11.01, "epoch_pct": 11.01, "eta": "49:59:00", "max_grad_norm": 1.0, "loss": 0.8259562253952026, "grad_norm": 0.6826074719429016, "learning_rate": 0.00019947471302993143}
-{"ts": "2025-12-27T00:28:33", "event": "train_log", "step": 1568, "epoch": 0.6616033755274262, "progress_pct": 11.03, "epoch_pct": 11.03, "eta": "49:56:37", "max_grad_norm": 1.0, "loss": 0.879021406173706, "grad_norm": 0.47369205951690674, "learning_rate": 0.00019946978514815352}
-{"ts": "2025-12-27T00:28:47", "event": "train_log", "step": 1570, "epoch": 0.6624472573839663, "progress_pct": 11.04, "epoch_pct": 11.04, "eta": "49:54:14", "max_grad_norm": 1.0, "loss": 0.9296056032180786, "grad_norm": 0.41111937165260315, "learning_rate": 0.0001994648343206065}
-{"ts": "2025-12-27T00:29:02", "event": "train_log", "step": 1572, "epoch": 0.6632911392405063, "progress_pct": 11.05, "epoch_pct": 11.05, "eta": "49:51:58", "max_grad_norm": 1.0, "loss": 0.873822808265686, "grad_norm": 0.4297783076763153, "learning_rate": 0.00019945986054843248}
-{"ts": "2025-12-27T00:29:17", "event": "train_log", "step": 1574, "epoch": 0.6641350210970464, "progress_pct": 11.07, "epoch_pct": 11.07, "eta": "49:49:39", "max_grad_norm": 1.0, "loss": 0.937151312828064, "grad_norm": 0.48124316334724426, "learning_rate": 0.00019945486383277878}
-{"ts": "2025-12-27T00:29:32", "event": "train_log", "step": 1576, "epoch": 0.6649789029535865, "progress_pct": 11.08, "epoch_pct": 11.08, "eta": "49:47:21", "max_grad_norm": 1.0, "loss": 0.8398929834365845, "grad_norm": 0.4048190116882324, "learning_rate": 0.00019944984417479805}
-{"ts": "2025-12-27T00:29:47", "event": "train_log", "step": 1578, "epoch": 0.6658227848101266, "progress_pct": 11.1, "epoch_pct": 11.1, "eta": "49:45:09", "max_grad_norm": 1.0, "loss": 0.8269520998001099, "grad_norm": 0.4023774266242981, "learning_rate": 0.00019944480157564826}
-{"ts": "2025-12-27T00:30:02", "event": "train_log", "step": 1580, "epoch": 0.6666666666666666, "progress_pct": 11.11, "epoch_pct": 11.11, "eta": "49:42:52", "max_grad_norm": 1.0, "loss": 0.8237608671188354, "grad_norm": 0.3784184157848358, "learning_rate": 0.00019943973603649262}
-{"ts": "2025-12-27T00:30:17", "event": "train_log", "step": 1582, "epoch": 0.6675105485232068, "progress_pct": 11.13, "epoch_pct": 11.13, "eta": "49:40:36", "max_grad_norm": 1.0, "loss": 0.8469099998474121, "grad_norm": 0.4448573887348175, "learning_rate": 0.00019943464755849965}
-{"ts": "2025-12-27T00:30:32", "event": "train_log", "step": 1584, "epoch": 0.6683544303797468, "progress_pct": 11.14, "epoch_pct": 11.14, "eta": "49:38:23", "max_grad_norm": 1.0, "loss": 0.8630822896957397, "grad_norm": 0.4690774083137512, "learning_rate": 0.00019942953614284317}
-{"ts": "2025-12-27T00:30:47", "event": "train_log", "step": 1586, "epoch": 0.6691983122362869, "progress_pct": 11.15, "epoch_pct": 11.15, "eta": "49:36:07", "max_grad_norm": 1.0, "loss": 0.8904082179069519, "grad_norm": 0.43670853972435, "learning_rate": 0.00019942440179070227}
-{"ts": "2025-12-27T00:31:02", "event": "train_log", "step": 1588, "epoch": 0.6700421940928271, "progress_pct": 11.17, "epoch_pct": 11.17, "eta": "49:33:56", "max_grad_norm": 1.0, "loss": 0.8355640172958374, "grad_norm": 0.4236849844455719, "learning_rate": 0.00019941924450326138}
-{"ts": "2025-12-27T00:31:16", "event": "train_log", "step": 1590, "epoch": 0.6708860759493671, "progress_pct": 11.18, "epoch_pct": 11.18, "eta": "49:31:36", "max_grad_norm": 1.0, "loss": 0.8898435831069946, "grad_norm": 0.48624539375305176, "learning_rate": 0.00019941406428171013}
-{"ts": "2025-12-27T00:31:30", "event": "train_log", "step": 1592, "epoch": 0.6717299578059072, "progress_pct": 11.2, "epoch_pct": 11.2, "eta": "49:29:16", "max_grad_norm": 1.0, "loss": 0.9000012278556824, "grad_norm": 0.4453780949115753, "learning_rate": 0.00019940886112724355}
-{"ts": "2025-12-27T00:31:45", "event": "train_log", "step": 1594, "epoch": 0.6725738396624472, "progress_pct": 11.21, "epoch_pct": 11.21, "eta": "49:27:00", "max_grad_norm": 1.0, "loss": 0.8171058893203735, "grad_norm": 0.4417199194431305, "learning_rate": 0.00019940363504106193}
-{"ts": "2025-12-27T00:31:59", "event": "train_log", "step": 1596, "epoch": 0.6734177215189874, "progress_pct": 11.22, "epoch_pct": 11.22, "eta": "49:24:43", "max_grad_norm": 1.0, "loss": 0.8703798055648804, "grad_norm": 0.45055362582206726, "learning_rate": 0.00019939838602437074}
-{"ts": "2025-12-27T00:32:14", "event": "train_log", "step": 1598, "epoch": 0.6742616033755274, "progress_pct": 11.24, "epoch_pct": 11.24, "eta": "49:22:27", "max_grad_norm": 1.0, "loss": 0.8677281737327576, "grad_norm": 0.42316532135009766, "learning_rate": 0.00019939311407838088}
-{"ts": "2025-12-27T00:32:29", "event": "train_log", "step": 1600, "epoch": 0.6751054852320675, "progress_pct": 11.25, "epoch_pct": 11.25, "eta": "49:20:19", "max_grad_norm": 1.0, "loss": 0.7314013242721558, "grad_norm": 0.3935781717300415, "learning_rate": 0.0001993878192043085}
-{"ts": "2025-12-27T00:43:47", "event": "train_log", "step": 1600, "epoch": 0.6751054852320675, "progress_pct": 11.25, "epoch_pct": 11.25, "eta": "50:49:27", "max_grad_norm": 1.0, "eval_loss": 0.8769772052764893, "eval_runtime": 677.9338, "eval_samples_per_second": 3.108, "eval_steps_per_second": 3.108}
-{"ts": "2025-12-27T00:44:03", "event": "train_log", "step": 1602, "epoch": 0.6759493670886076, "progress_pct": 11.27, "epoch_pct": 11.27, "eta": "50:47:17", "max_grad_norm": 1.0, "loss": 0.8075380325317383, "grad_norm": 0.4197012186050415, "learning_rate": 0.000199382501403375}
-{"ts": "2025-12-27T00:44:20", "event": "train_log", "step": 1604, "epoch": 0.6767932489451477, "progress_pct": 11.28, "epoch_pct": 11.28, "eta": "50:45:10", "max_grad_norm": 1.0, "loss": 0.7885794639587402, "grad_norm": 0.45227327942848206, "learning_rate": 0.00019937716067680713}
-{"ts": "2025-12-27T00:44:35", "event": "train_log", "step": 1606, "epoch": 0.6776371308016877, "progress_pct": 11.29, "epoch_pct": 11.29, "eta": "50:42:55", "max_grad_norm": 1.0, "loss": 0.868261992931366, "grad_norm": 0.45660385489463806, "learning_rate": 0.00019937179702583682}
-{"ts": "2025-12-27T00:44:51", "event": "train_log", "step": 1608, "epoch": 0.6784810126582278, "progress_pct": 11.31, "epoch_pct": 11.31, "eta": "50:40:44", "max_grad_norm": 1.0, "loss": 0.8306655287742615, "grad_norm": 0.3955288231372833, "learning_rate": 0.00019936641045170144}
-{"ts": "2025-12-27T00:45:07", "event": "train_log", "step": 1610, "epoch": 0.679324894514768, "progress_pct": 11.32, "epoch_pct": 11.32, "eta": "50:38:31", "max_grad_norm": 1.0, "loss": 0.7505315542221069, "grad_norm": 0.3651324510574341, "learning_rate": 0.00019936100095564353}
-{"ts": "2025-12-27T00:45:23", "event": "train_log", "step": 1612, "epoch": 0.680168776371308, "progress_pct": 11.34, "epoch_pct": 11.34, "eta": "50:36:19", "max_grad_norm": 1.0, "loss": 0.8792756795883179, "grad_norm": 0.4240955412387848, "learning_rate": 0.00019935556853891096}
-{"ts": "2025-12-27T00:45:40", "event": "train_log", "step": 1614, "epoch": 0.6810126582278481, "progress_pct": 11.35, "epoch_pct": 11.35, "eta": "50:34:20", "max_grad_norm": 1.0, "loss": 0.7328272461891174, "grad_norm": 0.4142507314682007, "learning_rate": 0.00019935011320275687}
-{"ts": "2025-12-27T00:45:54", "event": "train_log", "step": 1616, "epoch": 0.6818565400843882, "progress_pct": 11.36, "epoch_pct": 11.36, "eta": "50:31:57", "max_grad_norm": 1.0, "loss": 0.8414849042892456, "grad_norm": 0.48339322209358215, "learning_rate": 0.00019934463494843975}
-{"ts": "2025-12-27T00:46:09", "event": "train_log", "step": 1618, "epoch": 0.6827004219409283, "progress_pct": 11.38, "epoch_pct": 11.38, "eta": "50:29:41", "max_grad_norm": 1.0, "loss": 0.8588716983795166, "grad_norm": 0.4312443435192108, "learning_rate": 0.00019933913377722328}
-{"ts": "2025-12-27T00:46:24", "event": "train_log", "step": 1620, "epoch": 0.6835443037974683, "progress_pct": 11.39, "epoch_pct": 11.39, "eta": "50:27:24", "max_grad_norm": 1.0, "loss": 0.846511960029602, "grad_norm": 0.43849512934684753, "learning_rate": 0.0001993336096903765}
-{"ts": "2025-12-27T00:46:40", "event": "train_log", "step": 1622, "epoch": 0.6843881856540084, "progress_pct": 11.41, "epoch_pct": 11.41, "eta": "50:25:12", "max_grad_norm": 1.0, "loss": 0.9352323412895203, "grad_norm": 0.45767566561698914, "learning_rate": 0.0001993280626891737}
-{"ts": "2025-12-27T00:46:55", "event": "train_log", "step": 1624, "epoch": 0.6852320675105485, "progress_pct": 11.42, "epoch_pct": 11.42, "eta": "50:22:55", "max_grad_norm": 1.0, "loss": 0.8884757161140442, "grad_norm": 0.438412606716156, "learning_rate": 0.00019932249277489444}
-{"ts": "2025-12-27T00:47:10", "event": "train_log", "step": 1626, "epoch": 0.6860759493670886, "progress_pct": 11.43, "epoch_pct": 11.43, "eta": "50:20:41", "max_grad_norm": 1.0, "loss": 0.7739649415016174, "grad_norm": 0.45893922448158264, "learning_rate": 0.0001993168999488237}
-{"ts": "2025-12-27T00:47:26", "event": "train_log", "step": 1628, "epoch": 0.6869198312236287, "progress_pct": 11.45, "epoch_pct": 11.45, "eta": "50:18:32", "max_grad_norm": 1.0, "loss": 0.7948258519172668, "grad_norm": 0.38631772994995117, "learning_rate": 0.0001993112842122515}
-{"ts": "2025-12-27T00:47:42", "event": "train_log", "step": 1630, "epoch": 0.6877637130801688, "progress_pct": 11.46, "epoch_pct": 11.46, "eta": "50:16:27", "max_grad_norm": 1.0, "loss": 0.750511884689331, "grad_norm": 0.3824027180671692, "learning_rate": 0.00019930564556647334}
-{"ts": "2025-12-27T00:47:57", "event": "train_log", "step": 1632, "epoch": 0.6886075949367089, "progress_pct": 11.48, "epoch_pct": 11.48, "eta": "50:14:09", "max_grad_norm": 1.0, "loss": 0.9006738662719727, "grad_norm": 0.3980776071548462, "learning_rate": 0.00019929998401278996}
-{"ts": "2025-12-27T00:48:12", "event": "train_log", "step": 1634, "epoch": 0.6894514767932489, "progress_pct": 11.49, "epoch_pct": 11.49, "eta": "50:11:56", "max_grad_norm": 1.0, "loss": 0.6996869444847107, "grad_norm": 0.41419896483421326, "learning_rate": 0.00019929429955250734}
-{"ts": "2025-12-27T00:48:28", "event": "train_log", "step": 1636, "epoch": 0.6902953586497891, "progress_pct": 11.5, "epoch_pct": 11.5, "eta": "50:09:49", "max_grad_norm": 1.0, "loss": 0.8523393273353577, "grad_norm": 0.43783676624298096, "learning_rate": 0.00019928859218693682}
-{"ts": "2025-12-27T00:48:44", "event": "train_log", "step": 1638, "epoch": 0.6911392405063291, "progress_pct": 11.52, "epoch_pct": 11.52, "eta": "50:07:46", "max_grad_norm": 1.0, "loss": 0.8885987401008606, "grad_norm": 0.4378126561641693, "learning_rate": 0.00019928286191739497}
-{"ts": "2025-12-27T00:49:00", "event": "train_log", "step": 1640, "epoch": 0.6919831223628692, "progress_pct": 11.53, "epoch_pct": 11.53, "eta": "50:05:35", "max_grad_norm": 1.0, "loss": 0.8563809990882874, "grad_norm": 0.4276133179664612, "learning_rate": 0.00019927710874520363}
-{"ts": "2025-12-27T00:49:15", "event": "train_log", "step": 1642, "epoch": 0.6928270042194092, "progress_pct": 11.55, "epoch_pct": 11.55, "eta": "50:03:22", "max_grad_norm": 1.0, "loss": 0.854114294052124, "grad_norm": 0.4600282311439514, "learning_rate": 0.00019927133267168992}
-{"ts": "2025-12-27T00:49:29", "event": "train_log", "step": 1644, "epoch": 0.6936708860759494, "progress_pct": 11.56, "epoch_pct": 11.56, "eta": "50:01:05", "max_grad_norm": 1.0, "loss": 0.8557889461517334, "grad_norm": 0.5058461427688599, "learning_rate": 0.00019926553369818635}
-{"ts": "2025-12-27T00:49:44", "event": "train_log", "step": 1646, "epoch": 0.6945147679324895, "progress_pct": 11.58, "epoch_pct": 11.58, "eta": "49:58:54", "max_grad_norm": 1.0, "loss": 0.8622767925262451, "grad_norm": 0.4947412312030792, "learning_rate": 0.00019925971182603057}
-{"ts": "2025-12-27T00:50:01", "event": "train_log", "step": 1648, "epoch": 0.6953586497890295, "progress_pct": 11.59, "epoch_pct": 11.59, "eta": "49:56:50", "max_grad_norm": 1.0, "loss": 0.7836558818817139, "grad_norm": 0.42555496096611023, "learning_rate": 0.00019925386705656558}
-{"ts": "2025-12-27T00:50:16", "event": "train_log", "step": 1650, "epoch": 0.6962025316455697, "progress_pct": 11.6, "epoch_pct": 11.6, "eta": "49:54:44", "max_grad_norm": 1.0, "loss": 0.7877846956253052, "grad_norm": 0.47560831904411316, "learning_rate": 0.00019924799939113967}
-{"ts": "2025-12-27T00:50:33", "event": "train_log", "step": 1652, "epoch": 0.6970464135021097, "progress_pct": 11.62, "epoch_pct": 11.62, "eta": "49:52:41", "max_grad_norm": 1.0, "loss": 0.775681734085083, "grad_norm": 0.391702264547348, "learning_rate": 0.0001992421088311064}
-{"ts": "2025-12-27T00:50:49", "event": "train_log", "step": 1654, "epoch": 0.6978902953586498, "progress_pct": 11.63, "epoch_pct": 11.63, "eta": "49:50:42", "max_grad_norm": 1.0, "loss": 0.8809882402420044, "grad_norm": 0.463679701089859, "learning_rate": 0.0001992361953778246}
-{"ts": "2025-12-27T00:51:06", "event": "train_log", "step": 1656, "epoch": 0.6987341772151898, "progress_pct": 11.65, "epoch_pct": 11.65, "eta": "49:48:43", "max_grad_norm": 1.0, "loss": 0.8513299226760864, "grad_norm": 0.44096484780311584, "learning_rate": 0.00019923025903265836}
-{"ts": "2025-12-27T00:51:22", "event": "train_log", "step": 1658, "epoch": 0.69957805907173, "progress_pct": 11.66, "epoch_pct": 11.66, "eta": "49:46:39", "max_grad_norm": 1.0, "loss": 0.8309667706489563, "grad_norm": 0.47818854451179504, "learning_rate": 0.0001992242997969772}
-{"ts": "2025-12-27T00:51:37", "event": "train_log", "step": 1660, "epoch": 0.70042194092827, "progress_pct": 11.67, "epoch_pct": 11.67, "eta": "49:44:29", "max_grad_norm": 1.0, "loss": 0.8817558884620667, "grad_norm": 0.4192790985107422, "learning_rate": 0.00019921831767215565}
-{"ts": "2025-12-27T00:51:54", "event": "train_log", "step": 1662, "epoch": 0.7012658227848101, "progress_pct": 11.69, "epoch_pct": 11.69, "eta": "49:42:31", "max_grad_norm": 1.0, "loss": 0.8315755724906921, "grad_norm": 0.45285239815711975, "learning_rate": 0.00019921231265957373}
-{"ts": "2025-12-27T00:52:10", "event": "train_log", "step": 1664, "epoch": 0.7021097046413503, "progress_pct": 11.7, "epoch_pct": 11.7, "eta": "49:40:30", "max_grad_norm": 1.0, "loss": 0.8698058724403381, "grad_norm": 0.47118625044822693, "learning_rate": 0.00019920628476061673}
-{"ts": "2025-12-27T00:52:26", "event": "train_log", "step": 1666, "epoch": 0.7029535864978903, "progress_pct": 11.72, "epoch_pct": 11.72, "eta": "49:38:25", "max_grad_norm": 1.0, "loss": 0.953620970249176, "grad_norm": 0.4769238829612732, "learning_rate": 0.0001992002339766751}
-{"ts": "2025-12-27T00:52:41", "event": "train_log", "step": 1668, "epoch": 0.7037974683544304, "progress_pct": 11.73, "epoch_pct": 11.73, "eta": "49:36:21", "max_grad_norm": 1.0, "loss": 0.8536615371704102, "grad_norm": 0.39397355914115906, "learning_rate": 0.00019919416030914468}
-{"ts": "2025-12-27T00:52:59", "event": "train_log", "step": 1670, "epoch": 0.7046413502109705, "progress_pct": 11.74, "epoch_pct": 11.74, "eta": "49:34:31", "max_grad_norm": 1.0, "loss": 0.8159828782081604, "grad_norm": 0.3659648299217224, "learning_rate": 0.00019918806375942655}
-{"ts": "2025-12-27T00:53:14", "event": "train_log", "step": 1672, "epoch": 0.7054852320675106, "progress_pct": 11.76, "epoch_pct": 11.76, "eta": "49:32:25", "max_grad_norm": 1.0, "loss": 0.782463550567627, "grad_norm": 0.4381789565086365, "learning_rate": 0.00019918194432892703}
-{"ts": "2025-12-27T00:53:29", "event": "train_log", "step": 1674, "epoch": 0.7063291139240506, "progress_pct": 11.77, "epoch_pct": 11.77, "eta": "49:30:15", "max_grad_norm": 1.0, "loss": 0.9314272999763489, "grad_norm": 0.44745752215385437, "learning_rate": 0.00019917580201905778}
-{"ts": "2025-12-27T00:53:46", "event": "train_log", "step": 1676, "epoch": 0.7071729957805907, "progress_pct": 11.79, "epoch_pct": 11.79, "eta": "49:28:20", "max_grad_norm": 1.0, "loss": 0.860816240310669, "grad_norm": 0.4515164792537689, "learning_rate": 0.00019916963683123574}
-{"ts": "2025-12-27T00:54:02", "event": "train_log", "step": 1678, "epoch": 0.7080168776371308, "progress_pct": 11.8, "epoch_pct": 11.8, "eta": "49:26:16", "max_grad_norm": 1.0, "loss": 0.8008456826210022, "grad_norm": 0.42735886573791504, "learning_rate": 0.00019916344876688303}
-{"ts": "2025-12-27T00:54:15", "event": "train_log", "step": 1680, "epoch": 0.7088607594936709, "progress_pct": 11.81, "epoch_pct": 11.81, "eta": "49:23:57", "max_grad_norm": 1.0, "loss": 0.7796595096588135, "grad_norm": 0.418275386095047, "learning_rate": 0.00019915723782742718}
-{"ts": "2025-12-27T00:54:30", "event": "train_log", "step": 1682, "epoch": 0.7097046413502109, "progress_pct": 11.83, "epoch_pct": 11.83, "eta": "49:21:49", "max_grad_norm": 1.0, "loss": 0.9006506204605103, "grad_norm": 0.44347989559173584, "learning_rate": 0.00019915100401430089}
-{"ts": "2025-12-27T00:54:47", "event": "train_log", "step": 1684, "epoch": 0.7105485232067511, "progress_pct": 11.84, "epoch_pct": 11.84, "eta": "49:19:51", "max_grad_norm": 1.0, "loss": 0.7750146985054016, "grad_norm": 0.3932702839374542, "learning_rate": 0.00019914474732894225}
-{"ts": "2025-12-27T00:55:02", "event": "train_log", "step": 1686, "epoch": 0.7113924050632912, "progress_pct": 11.86, "epoch_pct": 11.86, "eta": "49:17:44", "max_grad_norm": 1.0, "loss": 0.7508097290992737, "grad_norm": 0.4810502231121063, "learning_rate": 0.00019913846777279447}
-{"ts": "2025-12-27T00:55:16", "event": "train_log", "step": 1688, "epoch": 0.7122362869198312, "progress_pct": 11.87, "epoch_pct": 11.87, "eta": "49:15:36", "max_grad_norm": 1.0, "loss": 0.7926796078681946, "grad_norm": 0.4166778028011322, "learning_rate": 0.00019913216534730622}
-{"ts": "2025-12-27T00:55:32", "event": "train_log", "step": 1690, "epoch": 0.7130801687763713, "progress_pct": 11.88, "epoch_pct": 11.88, "eta": "49:13:33", "max_grad_norm": 1.0, "loss": 0.8363928198814392, "grad_norm": 0.47900474071502686, "learning_rate": 0.00019912584005393123}
-{"ts": "2025-12-27T00:55:49", "event": "train_log", "step": 1692, "epoch": 0.7139240506329114, "progress_pct": 11.9, "epoch_pct": 11.9, "eta": "49:11:39", "max_grad_norm": 1.0, "loss": 0.8649623990058899, "grad_norm": 0.435143381357193, "learning_rate": 0.00019911949189412872}
-{"ts": "2025-12-27T00:56:05", "event": "train_log", "step": 1694, "epoch": 0.7147679324894515, "progress_pct": 11.91, "epoch_pct": 11.91, "eta": "49:09:44", "max_grad_norm": 1.0, "loss": 0.8196499943733215, "grad_norm": 0.4070208966732025, "learning_rate": 0.00019911312086936305}
-{"ts": "2025-12-27T00:56:21", "event": "train_log", "step": 1696, "epoch": 0.7156118143459915, "progress_pct": 11.93, "epoch_pct": 11.93, "eta": "49:07:45", "max_grad_norm": 1.0, "loss": 0.9157413840293884, "grad_norm": 0.4717724621295929, "learning_rate": 0.0001991067269811039}
-{"ts": "2025-12-27T00:56:36", "event": "train_log", "step": 1698, "epoch": 0.7164556962025317, "progress_pct": 11.94, "epoch_pct": 11.94, "eta": "49:05:37", "max_grad_norm": 1.0, "loss": 0.7880456447601318, "grad_norm": 0.3942880928516388, "learning_rate": 0.0001991003102308262}
-{"ts": "2025-12-27T00:56:52", "event": "train_log", "step": 1700, "epoch": 0.7172995780590717, "progress_pct": 11.95, "epoch_pct": 11.95, "eta": "49:03:40", "max_grad_norm": 1.0, "loss": 0.8088646531105042, "grad_norm": 0.4037776589393616, "learning_rate": 0.0001990938706200102}
-{"ts": "2025-12-27T01:08:03", "event": "train_log", "step": 1700, "epoch": 0.7172995780590717, "progress_pct": 11.95, "epoch_pct": 11.95, "eta": "50:25:57", "max_grad_norm": 1.0, "eval_loss": 0.8708170056343079, "eval_runtime": 670.3019, "eval_samples_per_second": 3.143, "eval_steps_per_second": 3.143}
-{"ts": "2025-12-27T01:08:17", "event": "train_log", "step": 1702, "epoch": 0.7181434599156118, "progress_pct": 11.97, "epoch_pct": 11.97, "eta": "50:23:38", "max_grad_norm": 1.0, "loss": 0.8740324378013611, "grad_norm": 0.4443536400794983, "learning_rate": 0.0001990874081501414}
-{"ts": "2025-12-27T01:08:32", "event": "train_log", "step": 1704, "epoch": 0.7189873417721518, "progress_pct": 11.98, "epoch_pct": 11.98, "eta": "50:21:26", "max_grad_norm": 1.0, "loss": 0.8305023908615112, "grad_norm": 0.45089733600616455, "learning_rate": 0.00019908092282271053}
-{"ts": "2025-12-27T01:08:47", "event": "train_log", "step": 1706, "epoch": 0.719831223628692, "progress_pct": 12.0, "epoch_pct": 12.0, "eta": "50:19:21", "max_grad_norm": 1.0, "loss": 0.7718394994735718, "grad_norm": 0.3903036415576935, "learning_rate": 0.00019907441463921366}
-{"ts": "2025-12-27T01:09:02", "event": "train_log", "step": 1708, "epoch": 0.7206751054852321, "progress_pct": 12.01, "epoch_pct": 12.01, "eta": "50:17:10", "max_grad_norm": 1.0, "loss": 0.843289315700531, "grad_norm": 0.42990729212760925, "learning_rate": 0.00019906788360115208}
-{"ts": "2025-12-27T01:09:17", "event": "train_log", "step": 1710, "epoch": 0.7215189873417721, "progress_pct": 12.03, "epoch_pct": 12.03, "eta": "50:14:56", "max_grad_norm": 1.0, "loss": 0.8332282900810242, "grad_norm": 0.4287833571434021, "learning_rate": 0.0001990613297100324}
-{"ts": "2025-12-27T01:09:32", "event": "train_log", "step": 1712, "epoch": 0.7223628691983123, "progress_pct": 12.04, "epoch_pct": 12.04, "eta": "50:12:43", "max_grad_norm": 1.0, "loss": 0.784180223941803, "grad_norm": 0.4557269513607025, "learning_rate": 0.00019905475296736646}
-{"ts": "2025-12-27T01:09:47", "event": "train_log", "step": 1714, "epoch": 0.7232067510548523, "progress_pct": 12.05, "epoch_pct": 12.05, "eta": "50:10:39", "max_grad_norm": 1.0, "loss": 0.7807716131210327, "grad_norm": 0.4001525640487671, "learning_rate": 0.0001990481533746714}
-{"ts": "2025-12-27T01:10:03", "event": "train_log", "step": 1716, "epoch": 0.7240506329113924, "progress_pct": 12.07, "epoch_pct": 12.07, "eta": "50:08:29", "max_grad_norm": 1.0, "loss": 0.7936414480209351, "grad_norm": 0.5208709836006165, "learning_rate": 0.0001990415309334696}
-{"ts": "2025-12-27T01:10:18", "event": "train_log", "step": 1718, "epoch": 0.7248945147679325, "progress_pct": 12.08, "epoch_pct": 12.08, "eta": "50:06:24", "max_grad_norm": 1.0, "loss": 0.7964845895767212, "grad_norm": 0.46469953656196594, "learning_rate": 0.00019903488564528875}
-{"ts": "2025-12-27T01:10:34", "event": "train_log", "step": 1720, "epoch": 0.7257383966244726, "progress_pct": 12.1, "epoch_pct": 12.1, "eta": "50:04:17", "max_grad_norm": 1.0, "loss": 0.8302215337753296, "grad_norm": 0.405773401260376, "learning_rate": 0.00019902821751166178}
-{"ts": "2025-12-27T01:10:49", "event": "train_log", "step": 1722, "epoch": 0.7265822784810126, "progress_pct": 12.11, "epoch_pct": 12.11, "eta": "50:02:10", "max_grad_norm": 1.0, "loss": 0.8486512899398804, "grad_norm": 0.3874973654747009, "learning_rate": 0.00019902152653412692}
-{"ts": "2025-12-27T01:11:03", "event": "train_log", "step": 1724, "epoch": 0.7274261603375527, "progress_pct": 12.12, "epoch_pct": 12.12, "eta": "49:59:57", "max_grad_norm": 1.0, "loss": 0.837841272354126, "grad_norm": 0.46865755319595337, "learning_rate": 0.00019901481271422758}
-{"ts": "2025-12-27T01:11:19", "event": "train_log", "step": 1726, "epoch": 0.7282700421940929, "progress_pct": 12.14, "epoch_pct": 12.14, "eta": "49:57:51", "max_grad_norm": 1.0, "loss": 0.7640942335128784, "grad_norm": 0.4139123558998108, "learning_rate": 0.0001990080760535126}
-{"ts": "2025-12-27T01:11:33", "event": "train_log", "step": 1728, "epoch": 0.7291139240506329, "progress_pct": 12.15, "epoch_pct": 12.15, "eta": "49:55:34", "max_grad_norm": 1.0, "loss": 0.8236244320869446, "grad_norm": 0.5003024935722351, "learning_rate": 0.000199001316553536}
-{"ts": "2025-12-27T01:11:47", "event": "train_log", "step": 1730, "epoch": 0.729957805907173, "progress_pct": 12.17, "epoch_pct": 12.17, "eta": "49:53:23", "max_grad_norm": 1.0, "loss": 0.7792612314224243, "grad_norm": 0.38495776057243347, "learning_rate": 0.00019899453421585696}
-{"ts": "2025-12-27T01:12:03", "event": "train_log", "step": 1732, "epoch": 0.7308016877637131, "progress_pct": 12.18, "epoch_pct": 12.18, "eta": "49:51:19", "max_grad_norm": 1.0, "loss": 0.7733872532844543, "grad_norm": 0.4462733268737793, "learning_rate": 0.00019898772904204014}
-{"ts": "2025-12-27T01:12:18", "event": "train_log", "step": 1734, "epoch": 0.7316455696202532, "progress_pct": 12.19, "epoch_pct": 12.19, "eta": "49:49:13", "max_grad_norm": 1.0, "loss": 0.8933147192001343, "grad_norm": 0.398248553276062, "learning_rate": 0.00019898090103365532}
-{"ts": "2025-12-27T01:12:33", "event": "train_log", "step": 1736, "epoch": 0.7324894514767932, "progress_pct": 12.21, "epoch_pct": 12.21, "eta": "49:47:06", "max_grad_norm": 1.0, "loss": 0.8198356628417969, "grad_norm": 0.4231175482273102, "learning_rate": 0.00019897405019227756}
-{"ts": "2025-12-27T01:12:48", "event": "train_log", "step": 1738, "epoch": 0.7333333333333333, "progress_pct": 12.22, "epoch_pct": 12.22, "eta": "49:45:00", "max_grad_norm": 1.0, "loss": 0.8266391158103943, "grad_norm": 0.43639084696769714, "learning_rate": 0.0001989671765194873}
-{"ts": "2025-12-27T01:13:05", "event": "train_log", "step": 1740, "epoch": 0.7341772151898734, "progress_pct": 12.24, "epoch_pct": 12.24, "eta": "49:43:03", "max_grad_norm": 1.0, "loss": 0.7839997410774231, "grad_norm": 0.4235835671424866, "learning_rate": 0.00019896028001687008}
-{"ts": "2025-12-27T01:13:21", "event": "train_log", "step": 1742, "epoch": 0.7350210970464135, "progress_pct": 12.25, "epoch_pct": 12.25, "eta": "49:41:05", "max_grad_norm": 1.0, "loss": 0.7153518199920654, "grad_norm": 0.4033111035823822, "learning_rate": 0.00019895336068601687}
-{"ts": "2025-12-27T01:13:36", "event": "train_log", "step": 1744, "epoch": 0.7358649789029535, "progress_pct": 12.26, "epoch_pct": 12.26, "eta": "49:38:57", "max_grad_norm": 1.0, "loss": 0.9079289436340332, "grad_norm": 0.44281265139579773, "learning_rate": 0.00019894641852852377}
-{"ts": "2025-12-27T01:13:51", "event": "train_log", "step": 1746, "epoch": 0.7367088607594937, "progress_pct": 12.28, "epoch_pct": 12.28, "eta": "49:36:52", "max_grad_norm": 1.0, "loss": 0.8645254373550415, "grad_norm": 0.4882747232913971, "learning_rate": 0.0001989394535459922}
-{"ts": "2025-12-27T01:14:08", "event": "train_log", "step": 1748, "epoch": 0.7375527426160338, "progress_pct": 12.29, "epoch_pct": 12.29, "eta": "49:35:01", "max_grad_norm": 1.0, "loss": 0.8134214878082275, "grad_norm": 0.34858641028404236, "learning_rate": 0.00019893246574002887}
-{"ts": "2025-12-27T01:14:24", "event": "train_log", "step": 1750, "epoch": 0.7383966244725738, "progress_pct": 12.31, "epoch_pct": 12.31, "eta": "49:33:01", "max_grad_norm": 1.0, "loss": 0.8142663240432739, "grad_norm": 0.4273303747177124, "learning_rate": 0.00019892545511224574}
-{"ts": "2025-12-27T01:14:38", "event": "train_log", "step": 1752, "epoch": 0.739240506329114, "progress_pct": 12.32, "epoch_pct": 12.32, "eta": "49:30:52", "max_grad_norm": 1.0, "loss": 0.7957643866539001, "grad_norm": 0.4289957284927368, "learning_rate": 0.00019891842166426004}
-{"ts": "2025-12-27T01:14:54", "event": "train_log", "step": 1754, "epoch": 0.740084388185654, "progress_pct": 12.33, "epoch_pct": 12.33, "eta": "49:28:50", "max_grad_norm": 1.0, "loss": 0.9000363945960999, "grad_norm": 0.4812224805355072, "learning_rate": 0.00019891136539769416}
-{"ts": "2025-12-27T01:15:09", "event": "train_log", "step": 1756, "epoch": 0.7409282700421941, "progress_pct": 12.35, "epoch_pct": 12.35, "eta": "49:26:51", "max_grad_norm": 1.0, "loss": 0.7719792723655701, "grad_norm": 0.4078022837638855, "learning_rate": 0.00019890428631417595}
-{"ts": "2025-12-27T01:15:25", "event": "train_log", "step": 1758, "epoch": 0.7417721518987341, "progress_pct": 12.36, "epoch_pct": 12.36, "eta": "49:24:49", "max_grad_norm": 1.0, "loss": 0.7681847214698792, "grad_norm": 0.40169858932495117, "learning_rate": 0.00019889718441533838}
-{"ts": "2025-12-27T01:15:42", "event": "train_log", "step": 1760, "epoch": 0.7426160337552743, "progress_pct": 12.38, "epoch_pct": 12.38, "eta": "49:22:58", "max_grad_norm": 1.0, "loss": 0.7536827325820923, "grad_norm": 0.3713594377040863, "learning_rate": 0.00019889005970281972}
-{"ts": "2025-12-27T01:15:56", "event": "train_log", "step": 1762, "epoch": 0.7434599156118143, "progress_pct": 12.39, "epoch_pct": 12.39, "eta": "49:20:52", "max_grad_norm": 1.0, "loss": 0.9000160694122314, "grad_norm": 0.4183627665042877, "learning_rate": 0.0001988829121782635}
-{"ts": "2025-12-27T01:16:12", "event": "train_log", "step": 1764, "epoch": 0.7443037974683544, "progress_pct": 12.41, "epoch_pct": 12.41, "eta": "49:18:51", "max_grad_norm": 1.0, "loss": 0.8047307133674622, "grad_norm": 0.4241594672203064, "learning_rate": 0.00019887574184331851}
-{"ts": "2025-12-27T01:16:27", "event": "train_log", "step": 1766, "epoch": 0.7451476793248946, "progress_pct": 12.42, "epoch_pct": 12.42, "eta": "49:16:51", "max_grad_norm": 1.0, "loss": 0.8932583928108215, "grad_norm": 0.4249233603477478, "learning_rate": 0.00019886854869963883}
-{"ts": "2025-12-27T01:16:45", "event": "train_log", "step": 1768, "epoch": 0.7459915611814346, "progress_pct": 12.43, "epoch_pct": 12.43, "eta": "49:15:07", "max_grad_norm": 1.0, "loss": 0.7684977054595947, "grad_norm": 0.35815340280532837, "learning_rate": 0.00019886133274888378}
-{"ts": "2025-12-27T01:17:00", "event": "train_log", "step": 1770, "epoch": 0.7468354430379747, "progress_pct": 12.45, "epoch_pct": 12.45, "eta": "49:13:05", "max_grad_norm": 1.0, "loss": 0.8644338250160217, "grad_norm": 0.41035401821136475, "learning_rate": 0.00019885409399271795}
-{"ts": "2025-12-27T01:17:16", "event": "train_log", "step": 1772, "epoch": 0.7476793248945147, "progress_pct": 12.46, "epoch_pct": 12.46, "eta": "49:11:07", "max_grad_norm": 1.0, "loss": 0.8035860657691956, "grad_norm": 0.5450286269187927, "learning_rate": 0.00019884683243281116}
-{"ts": "2025-12-27T01:17:31", "event": "train_log", "step": 1774, "epoch": 0.7485232067510549, "progress_pct": 12.48, "epoch_pct": 12.48, "eta": "49:09:03", "max_grad_norm": 1.0, "loss": 0.8861207962036133, "grad_norm": 0.5280999541282654, "learning_rate": 0.0001988395480708385}
-{"ts": "2025-12-27T01:17:47", "event": "train_log", "step": 1776, "epoch": 0.7493670886075949, "progress_pct": 12.49, "epoch_pct": 12.49, "eta": "49:07:05", "max_grad_norm": 1.0, "loss": 0.7506847977638245, "grad_norm": 0.42665231227874756, "learning_rate": 0.00019883224090848036}
-{"ts": "2025-12-27T01:18:04", "event": "train_log", "step": 1778, "epoch": 0.750210970464135, "progress_pct": 12.5, "epoch_pct": 12.5, "eta": "49:05:22", "max_grad_norm": 1.0, "loss": 0.7662046551704407, "grad_norm": 0.39029282331466675, "learning_rate": 0.00019882491094742232}
-{"ts": "2025-12-27T01:18:21", "event": "train_log", "step": 1780, "epoch": 0.7510548523206751, "progress_pct": 12.52, "epoch_pct": 12.52, "eta": "49:03:34", "max_grad_norm": 1.0, "loss": 0.7590143084526062, "grad_norm": 0.43870019912719727, "learning_rate": 0.00019881755818935534}
-{"ts": "2025-12-27T01:18:36", "event": "train_log", "step": 1782, "epoch": 0.7518987341772152, "progress_pct": 12.53, "epoch_pct": 12.53, "eta": "49:01:32", "max_grad_norm": 1.0, "loss": 0.9340365529060364, "grad_norm": 0.4195050001144409, "learning_rate": 0.0001988101826359755}
-{"ts": "2025-12-27T01:18:51", "event": "train_log", "step": 1784, "epoch": 0.7527426160337553, "progress_pct": 12.55, "epoch_pct": 12.55, "eta": "48:59:28", "max_grad_norm": 1.0, "loss": 0.7969209551811218, "grad_norm": 0.4236123263835907, "learning_rate": 0.0001988027842889842}
-{"ts": "2025-12-27T01:19:06", "event": "train_log", "step": 1786, "epoch": 0.7535864978902953, "progress_pct": 12.56, "epoch_pct": 12.56, "eta": "48:57:27", "max_grad_norm": 1.0, "loss": 0.7892382144927979, "grad_norm": 0.4274357259273529, "learning_rate": 0.00019879536315008808}
-{"ts": "2025-12-27T01:19:22", "event": "train_log", "step": 1788, "epoch": 0.7544303797468355, "progress_pct": 12.57, "epoch_pct": 12.57, "eta": "48:55:31", "max_grad_norm": 1.0, "loss": 0.8752562403678894, "grad_norm": 0.4622916579246521, "learning_rate": 0.00019878791922099912}
-{"ts": "2025-12-27T01:19:38", "event": "train_log", "step": 1790, "epoch": 0.7552742616033755, "progress_pct": 12.59, "epoch_pct": 12.59, "eta": "48:53:37", "max_grad_norm": 1.0, "loss": 0.813011884689331, "grad_norm": 0.3648734986782074, "learning_rate": 0.00019878045250343445}
-{"ts": "2025-12-27T01:19:53", "event": "train_log", "step": 1792, "epoch": 0.7561181434599156, "progress_pct": 12.6, "epoch_pct": 12.6, "eta": "48:51:39", "max_grad_norm": 1.0, "loss": 0.7310198545455933, "grad_norm": 0.41361239552497864, "learning_rate": 0.00019877296299911648}
-{"ts": "2025-12-27T01:20:09", "event": "train_log", "step": 1794, "epoch": 0.7569620253164557, "progress_pct": 12.62, "epoch_pct": 12.62, "eta": "48:49:44", "max_grad_norm": 1.0, "loss": 0.858386754989624, "grad_norm": 0.4113222062587738, "learning_rate": 0.00019876545070977294}
-{"ts": "2025-12-27T01:20:25", "event": "train_log", "step": 1796, "epoch": 0.7578059071729958, "progress_pct": 12.63, "epoch_pct": 12.63, "eta": "48:47:48", "max_grad_norm": 1.0, "loss": 0.8377325534820557, "grad_norm": 0.4295370876789093, "learning_rate": 0.00019875791563713676}
-{"ts": "2025-12-27T01:20:40", "event": "train_log", "step": 1798, "epoch": 0.7586497890295358, "progress_pct": 12.64, "epoch_pct": 12.64, "eta": "48:45:54", "max_grad_norm": 1.0, "loss": 0.9139418005943298, "grad_norm": 0.4227522015571594, "learning_rate": 0.0001987503577829461}
-{"ts": "2025-12-27T01:20:57", "event": "train_log", "step": 1800, "epoch": 0.759493670886076, "progress_pct": 12.66, "epoch_pct": 12.66, "eta": "48:44:02", "max_grad_norm": 1.0, "loss": 0.6994872689247131, "grad_norm": 0.3638151288032532, "learning_rate": 0.00019874277714894442}
-{"ts": "2025-12-27T01:32:23", "event": "train_log", "step": 1800, "epoch": 0.759493670886076, "progress_pct": 12.66, "epoch_pct": 12.66, "eta": "50:02:59", "max_grad_norm": 1.0, "eval_loss": 0.8625519275665283, "eval_runtime": 686.4271, "eval_samples_per_second": 3.07, "eval_steps_per_second": 3.07}
-{"ts": "2025-12-27T01:32:38", "event": "train_log", "step": 1802, "epoch": 0.760337552742616, "progress_pct": 12.67, "epoch_pct": 12.67, "eta": "50:00:51", "max_grad_norm": 1.0, "loss": 0.8681167960166931, "grad_norm": 0.46954411268234253, "learning_rate": 0.00019873517373688047}
-{"ts": "2025-12-27T01:32:52", "event": "train_log", "step": 1804, "epoch": 0.7611814345991561, "progress_pct": 12.69, "epoch_pct": 12.69, "eta": "49:58:42", "max_grad_norm": 1.0, "loss": 0.7420852184295654, "grad_norm": 0.41958674788475037, "learning_rate": 0.00019872754754850819}
-{"ts": "2025-12-27T01:33:07", "event": "train_log", "step": 1806, "epoch": 0.7620253164556962, "progress_pct": 12.7, "epoch_pct": 12.7, "eta": "49:56:37", "max_grad_norm": 1.0, "loss": 0.8018608093261719, "grad_norm": 0.431226521730423, "learning_rate": 0.00019871989858558678}
-{"ts": "2025-12-27T01:33:22", "event": "train_log", "step": 1808, "epoch": 0.7628691983122363, "progress_pct": 12.71, "epoch_pct": 12.71, "eta": "49:54:32", "max_grad_norm": 1.0, "loss": 0.8793904781341553, "grad_norm": 0.45129454135894775, "learning_rate": 0.0001987122268498807}
-{"ts": "2025-12-27T01:33:36", "event": "train_log", "step": 1810, "epoch": 0.7637130801687764, "progress_pct": 12.73, "epoch_pct": 12.73, "eta": "49:52:21", "max_grad_norm": 1.0, "loss": 0.8416730761528015, "grad_norm": 0.44278961420059204, "learning_rate": 0.00019870453234315972}
-{"ts": "2025-12-27T01:33:51", "event": "train_log", "step": 1812, "epoch": 0.7645569620253164, "progress_pct": 12.74, "epoch_pct": 12.74, "eta": "49:50:15", "max_grad_norm": 1.0, "loss": 0.8225743174552917, "grad_norm": 0.4689098000526428, "learning_rate": 0.00019869681506719876}
-{"ts": "2025-12-27T01:34:05", "event": "train_log", "step": 1814, "epoch": 0.7654008438818566, "progress_pct": 12.76, "epoch_pct": 12.76, "eta": "49:48:05", "max_grad_norm": 1.0, "loss": 0.7871913313865662, "grad_norm": 0.4413386881351471, "learning_rate": 0.00019868907502377806}
-{"ts": "2025-12-27T01:34:20", "event": "train_log", "step": 1816, "epoch": 0.7662447257383966, "progress_pct": 12.77, "epoch_pct": 12.77, "eta": "49:46:00", "max_grad_norm": 1.0, "loss": 0.8616237044334412, "grad_norm": 0.48395273089408875, "learning_rate": 0.00019868131221468315}
-{"ts": "2025-12-27T01:34:36", "event": "train_log", "step": 1818, "epoch": 0.7670886075949367, "progress_pct": 12.78, "epoch_pct": 12.78, "eta": "49:44:01", "max_grad_norm": 1.0, "loss": 0.7243452668190002, "grad_norm": 0.370263934135437, "learning_rate": 0.0001986735266417047}
-{"ts": "2025-12-27T01:34:51", "event": "train_log", "step": 1820, "epoch": 0.7679324894514767, "progress_pct": 12.8, "epoch_pct": 12.8, "eta": "49:41:57", "max_grad_norm": 1.0, "loss": 0.8623812198638916, "grad_norm": 0.4522445797920227, "learning_rate": 0.00019866571830663875}
-{"ts": "2025-12-27T01:35:06", "event": "train_log", "step": 1822, "epoch": 0.7687763713080169, "progress_pct": 12.81, "epoch_pct": 12.81, "eta": "49:39:56", "max_grad_norm": 1.0, "loss": 0.776618480682373, "grad_norm": 0.43821004033088684, "learning_rate": 0.00019865788721128643}
-{"ts": "2025-12-27T01:35:21", "event": "train_log", "step": 1824, "epoch": 0.769620253164557, "progress_pct": 12.83, "epoch_pct": 12.83, "eta": "49:37:55", "max_grad_norm": 1.0, "loss": 0.8722774982452393, "grad_norm": 0.3825650215148926, "learning_rate": 0.00019865003335745436}
-{"ts": "2025-12-27T01:35:36", "event": "train_log", "step": 1826, "epoch": 0.770464135021097, "progress_pct": 12.84, "epoch_pct": 12.84, "eta": "49:35:51", "max_grad_norm": 1.0, "loss": 0.907802939414978, "grad_norm": 0.43684205412864685, "learning_rate": 0.00019864215674695416}
-{"ts": "2025-12-27T01:35:51", "event": "train_log", "step": 1828, "epoch": 0.7713080168776372, "progress_pct": 12.86, "epoch_pct": 12.86, "eta": "49:33:49", "max_grad_norm": 1.0, "loss": 0.8505539298057556, "grad_norm": 0.4128975570201874, "learning_rate": 0.00019863425738160287}
-{"ts": "2025-12-27T01:36:06", "event": "train_log", "step": 1830, "epoch": 0.7721518987341772, "progress_pct": 12.87, "epoch_pct": 12.87, "eta": "49:31:46", "max_grad_norm": 1.0, "loss": 0.83274906873703, "grad_norm": 0.4254065454006195, "learning_rate": 0.0001986263352632227}
-{"ts": "2025-12-27T01:36:21", "event": "train_log", "step": 1832, "epoch": 0.7729957805907173, "progress_pct": 12.88, "epoch_pct": 12.88, "eta": "49:29:42", "max_grad_norm": 1.0, "loss": 0.8172078728675842, "grad_norm": 0.4137375056743622, "learning_rate": 0.00019861839039364118}
-{"ts": "2025-12-27T01:36:35", "event": "train_log", "step": 1834, "epoch": 0.7738396624472574, "progress_pct": 12.9, "epoch_pct": 12.9, "eta": "49:27:34", "max_grad_norm": 1.0, "loss": 0.8610842227935791, "grad_norm": 0.4387703239917755, "learning_rate": 0.00019861042277469096}
-{"ts": "2025-12-27T01:36:50", "event": "train_log", "step": 1836, "epoch": 0.7746835443037975, "progress_pct": 12.91, "epoch_pct": 12.91, "eta": "49:25:32", "max_grad_norm": 1.0, "loss": 0.7961188554763794, "grad_norm": 0.398952454328537, "learning_rate": 0.00019860243240821005}
-{"ts": "2025-12-27T01:37:05", "event": "train_log", "step": 1838, "epoch": 0.7755274261603375, "progress_pct": 12.93, "epoch_pct": 12.93, "eta": "49:23:32", "max_grad_norm": 1.0, "loss": 0.8078321218490601, "grad_norm": 0.4079921543598175, "learning_rate": 0.0001985944192960417}
-{"ts": "2025-12-27T01:37:19", "event": "train_log", "step": 1840, "epoch": 0.7763713080168776, "progress_pct": 12.94, "epoch_pct": 12.94, "eta": "49:21:27", "max_grad_norm": 1.0, "loss": 0.8743909001350403, "grad_norm": 0.4701489508152008, "learning_rate": 0.00019858638344003433}
-{"ts": "2025-12-27T01:37:34", "event": "train_log", "step": 1842, "epoch": 0.7772151898734178, "progress_pct": 12.95, "epoch_pct": 12.95, "eta": "49:19:25", "max_grad_norm": 1.0, "loss": 0.7681707143783569, "grad_norm": 0.5391269326210022, "learning_rate": 0.00019857832484204173}
-{"ts": "2025-12-27T01:37:50", "event": "train_log", "step": 1844, "epoch": 0.7780590717299578, "progress_pct": 12.97, "epoch_pct": 12.97, "eta": "49:17:30", "max_grad_norm": 1.0, "loss": 0.7817525863647461, "grad_norm": 0.36250734329223633, "learning_rate": 0.00019857024350392277}
-{"ts": "2025-12-27T01:38:05", "event": "train_log", "step": 1846, "epoch": 0.7789029535864979, "progress_pct": 12.98, "epoch_pct": 12.98, "eta": "49:15:29", "max_grad_norm": 1.0, "loss": 0.7614551782608032, "grad_norm": 0.41237136721611023, "learning_rate": 0.00019856213942754175}
-{"ts": "2025-12-27T01:38:20", "event": "train_log", "step": 1848, "epoch": 0.779746835443038, "progress_pct": 13.0, "epoch_pct": 13.0, "eta": "49:13:31", "max_grad_norm": 1.0, "loss": 0.7492313981056213, "grad_norm": 0.3968869745731354, "learning_rate": 0.00019855401261476807}
-{"ts": "2025-12-27T01:38:35", "event": "train_log", "step": 1850, "epoch": 0.7805907172995781, "progress_pct": 13.01, "epoch_pct": 13.01, "eta": "49:11:29", "max_grad_norm": 1.0, "loss": 0.8615695238113403, "grad_norm": 0.441476434469223, "learning_rate": 0.00019854586306747646}
-{"ts": "2025-12-27T01:38:49", "event": "train_log", "step": 1852, "epoch": 0.7814345991561181, "progress_pct": 13.02, "epoch_pct": 13.02, "eta": "49:09:26", "max_grad_norm": 1.0, "loss": 0.8416724801063538, "grad_norm": 0.4486154317855835, "learning_rate": 0.00019853769078754686}
-{"ts": "2025-12-27T01:39:04", "event": "train_log", "step": 1854, "epoch": 0.7822784810126582, "progress_pct": 13.04, "epoch_pct": 13.04, "eta": "49:07:24", "max_grad_norm": 1.0, "loss": 0.8987806439399719, "grad_norm": 0.45148879289627075, "learning_rate": 0.0001985294957768644}
-{"ts": "2025-12-27T01:39:20", "event": "train_log", "step": 1856, "epoch": 0.7831223628691983, "progress_pct": 13.05, "epoch_pct": 13.05, "eta": "49:05:32", "max_grad_norm": 1.0, "loss": 0.7597590088844299, "grad_norm": 0.39330095052719116, "learning_rate": 0.0001985212780373196}
-{"ts": "2025-12-27T01:39:35", "event": "train_log", "step": 1858, "epoch": 0.7839662447257384, "progress_pct": 13.07, "epoch_pct": 13.07, "eta": "49:03:30", "max_grad_norm": 1.0, "loss": 0.8429927229881287, "grad_norm": 0.4260408580303192, "learning_rate": 0.00019851303757080808}
-{"ts": "2025-12-27T01:39:50", "event": "train_log", "step": 1860, "epoch": 0.7848101265822784, "progress_pct": 13.08, "epoch_pct": 13.08, "eta": "49:01:34", "max_grad_norm": 1.0, "loss": 0.7443564534187317, "grad_norm": 0.37519171833992004, "learning_rate": 0.00019850477437923075}
-{"ts": "2025-12-27T01:40:04", "event": "train_log", "step": 1862, "epoch": 0.7856540084388186, "progress_pct": 13.09, "epoch_pct": 13.09, "eta": "48:59:28", "max_grad_norm": 1.0, "loss": 0.934238612651825, "grad_norm": 0.4991084337234497, "learning_rate": 0.00019849648846449383}
-{"ts": "2025-12-27T01:40:19", "event": "train_log", "step": 1864, "epoch": 0.7864978902953587, "progress_pct": 13.11, "epoch_pct": 13.11, "eta": "48:57:27", "max_grad_norm": 1.0, "loss": 0.8938905000686646, "grad_norm": 0.4711335003376007, "learning_rate": 0.00019848817982850867}
-{"ts": "2025-12-27T01:40:34", "event": "train_log", "step": 1866, "epoch": 0.7873417721518987, "progress_pct": 13.12, "epoch_pct": 13.12, "eta": "48:55:31", "max_grad_norm": 1.0, "loss": 0.8745643496513367, "grad_norm": 0.4145370423793793, "learning_rate": 0.00019847984847319193}
-{"ts": "2025-12-27T01:40:49", "event": "train_log", "step": 1868, "epoch": 0.7881856540084389, "progress_pct": 13.14, "epoch_pct": 13.14, "eta": "48:53:36", "max_grad_norm": 1.0, "loss": 0.7178786396980286, "grad_norm": 0.3444044888019562, "learning_rate": 0.00019847149440046548}
-{"ts": "2025-12-27T01:41:04", "event": "train_log", "step": 1870, "epoch": 0.7890295358649789, "progress_pct": 13.15, "epoch_pct": 13.15, "eta": "48:51:38", "max_grad_norm": 1.0, "loss": 0.9114303588867188, "grad_norm": 0.34632962942123413, "learning_rate": 0.00019846311761225646}
-{"ts": "2025-12-27T01:41:20", "event": "train_log", "step": 1872, "epoch": 0.789873417721519, "progress_pct": 13.16, "epoch_pct": 13.16, "eta": "48:49:43", "max_grad_norm": 1.0, "loss": 0.836281955242157, "grad_norm": 0.38630741834640503, "learning_rate": 0.0001984547181104972}
-{"ts": "2025-12-27T01:41:35", "event": "train_log", "step": 1874, "epoch": 0.790717299578059, "progress_pct": 13.18, "epoch_pct": 13.18, "eta": "48:47:46", "max_grad_norm": 1.0, "loss": 0.8247858881950378, "grad_norm": 0.40947434306144714, "learning_rate": 0.00019844629589712534}
-{"ts": "2025-12-27T01:41:49", "event": "train_log", "step": 1876, "epoch": 0.7915611814345992, "progress_pct": 13.19, "epoch_pct": 13.19, "eta": "48:45:48", "max_grad_norm": 1.0, "loss": 0.8446351289749146, "grad_norm": 0.45878684520721436, "learning_rate": 0.00019843785097408372}
-{"ts": "2025-12-27T01:42:05", "event": "train_log", "step": 1878, "epoch": 0.7924050632911392, "progress_pct": 13.21, "epoch_pct": 13.21, "eta": "48:43:54", "max_grad_norm": 1.0, "loss": 0.8567686676979065, "grad_norm": 0.37202852964401245, "learning_rate": 0.0001984293833433204}
-{"ts": "2025-12-27T01:42:21", "event": "train_log", "step": 1880, "epoch": 0.7932489451476793, "progress_pct": 13.22, "epoch_pct": 13.22, "eta": "48:42:03", "max_grad_norm": 1.0, "loss": 0.8134047985076904, "grad_norm": 0.3839069902896881, "learning_rate": 0.00019842089300678876}
-{"ts": "2025-12-27T01:42:35", "event": "train_log", "step": 1882, "epoch": 0.7940928270042195, "progress_pct": 13.23, "epoch_pct": 13.23, "eta": "48:40:05", "max_grad_norm": 1.0, "loss": 0.8670110106468201, "grad_norm": 0.4018687605857849, "learning_rate": 0.00019841237996644727}
-{"ts": "2025-12-27T01:42:51", "event": "train_log", "step": 1884, "epoch": 0.7949367088607595, "progress_pct": 13.25, "epoch_pct": 13.25, "eta": "48:38:11", "max_grad_norm": 1.0, "loss": 0.7975355386734009, "grad_norm": 0.372089684009552, "learning_rate": 0.0001984038442242598}
-{"ts": "2025-12-27T01:43:05", "event": "train_log", "step": 1886, "epoch": 0.7957805907172996, "progress_pct": 13.26, "epoch_pct": 13.26, "eta": "48:36:12", "max_grad_norm": 1.0, "loss": 0.8755611777305603, "grad_norm": 0.4492705166339874, "learning_rate": 0.0001983952857821953}
-{"ts": "2025-12-27T01:43:20", "event": "train_log", "step": 1888, "epoch": 0.7966244725738396, "progress_pct": 13.28, "epoch_pct": 13.28, "eta": "48:34:17", "max_grad_norm": 1.0, "loss": 0.8680241107940674, "grad_norm": 0.451054185628891, "learning_rate": 0.00019838670464222813}
-{"ts": "2025-12-27T01:43:35", "event": "train_log", "step": 1890, "epoch": 0.7974683544303798, "progress_pct": 13.29, "epoch_pct": 13.29, "eta": "48:32:20", "max_grad_norm": 1.0, "loss": 0.7990990877151489, "grad_norm": 0.4036900997161865, "learning_rate": 0.00019837810080633773}
-{"ts": "2025-12-27T01:43:50", "event": "train_log", "step": 1892, "epoch": 0.7983122362869198, "progress_pct": 13.31, "epoch_pct": 13.31, "eta": "48:30:22", "max_grad_norm": 1.0, "loss": 0.8598953485488892, "grad_norm": 0.46125802397727966, "learning_rate": 0.0001983694742765089}
-{"ts": "2025-12-27T01:44:06", "event": "train_log", "step": 1894, "epoch": 0.7991561181434599, "progress_pct": 13.32, "epoch_pct": 13.32, "eta": "48:28:36", "max_grad_norm": 1.0, "loss": 0.7707474827766418, "grad_norm": 0.4458785951137543, "learning_rate": 0.00019836082505473153}
-{"ts": "2025-12-27T01:44:22", "event": "train_log", "step": 1896, "epoch": 0.8, "progress_pct": 13.33, "epoch_pct": 13.33, "eta": "48:26:44", "max_grad_norm": 1.0, "loss": 0.8069534301757812, "grad_norm": 0.44501590728759766, "learning_rate": 0.0001983521531430009}
-{"ts": "2025-12-27T01:44:38", "event": "train_log", "step": 1898, "epoch": 0.8008438818565401, "progress_pct": 13.35, "epoch_pct": 13.35, "eta": "48:24:56", "max_grad_norm": 1.0, "loss": 0.862334668636322, "grad_norm": 0.400771826505661, "learning_rate": 0.0001983434585433174}
-{"ts": "2025-12-27T01:44:52", "event": "train_log", "step": 1900, "epoch": 0.8016877637130801, "progress_pct": 13.36, "epoch_pct": 13.36, "eta": "48:22:56", "max_grad_norm": 1.0, "loss": 0.8125433325767517, "grad_norm": 0.39193347096443176, "learning_rate": 0.00019833474125768676}
-{"ts": "2025-12-27T01:56:20", "event": "train_log", "step": 1900, "epoch": 0.8016877637130801, "progress_pct": 13.36, "epoch_pct": 13.36, "eta": "49:37:21", "max_grad_norm": 1.0, "eval_loss": 0.8546335697174072, "eval_runtime": 688.5301, "eval_samples_per_second": 3.06, "eval_steps_per_second": 3.06}
-{"ts": "2025-12-27T01:56:36", "event": "train_log", "step": 1902, "epoch": 0.8025316455696202, "progress_pct": 13.38, "epoch_pct": 13.38, "eta": "49:35:25", "max_grad_norm": 1.0, "loss": 0.8246012330055237, "grad_norm": 0.441129207611084, "learning_rate": 0.00019832600128811986}
-{"ts": "2025-12-27T01:56:51", "event": "train_log", "step": 1904, "epoch": 0.8033755274261604, "progress_pct": 13.39, "epoch_pct": 13.39, "eta": "49:33:24", "max_grad_norm": 1.0, "loss": 0.8387641310691833, "grad_norm": 0.4089467227458954, "learning_rate": 0.00019831723863663285}
-{"ts": "2025-12-27T01:57:06", "event": "train_log", "step": 1906, "epoch": 0.8042194092827004, "progress_pct": 13.4, "epoch_pct": 13.4, "eta": "49:31:29", "max_grad_norm": 1.0, "loss": 0.7891429662704468, "grad_norm": 0.4871654510498047, "learning_rate": 0.0001983084533052471}
-{"ts": "2025-12-27T01:57:22", "event": "train_log", "step": 1908, "epoch": 0.8050632911392405, "progress_pct": 13.42, "epoch_pct": 13.42, "eta": "49:29:35", "max_grad_norm": 1.0, "loss": 0.8008774518966675, "grad_norm": 0.40085604786872864, "learning_rate": 0.00019829964529598923}
-{"ts": "2025-12-27T01:57:38", "event": "train_log", "step": 1910, "epoch": 0.8059071729957806, "progress_pct": 13.43, "epoch_pct": 13.43, "eta": "49:27:39", "max_grad_norm": 1.0, "loss": 0.7921834588050842, "grad_norm": 0.38775014877319336, "learning_rate": 0.00019829081461089109}
-{"ts": "2025-12-27T01:57:55", "event": "train_log", "step": 1912, "epoch": 0.8067510548523207, "progress_pct": 13.45, "epoch_pct": 13.45, "eta": "49:25:57", "max_grad_norm": 1.0, "loss": 0.7752519845962524, "grad_norm": 0.37830594182014465, "learning_rate": 0.0001982819612519897}
-{"ts": "2025-12-27T01:58:11", "event": "train_log", "step": 1914, "epoch": 0.8075949367088607, "progress_pct": 13.46, "epoch_pct": 13.46, "eta": "49:24:03", "max_grad_norm": 1.0, "loss": 0.7958255410194397, "grad_norm": 0.41137194633483887, "learning_rate": 0.0001982730852213274}
-{"ts": "2025-12-27T01:58:26", "event": "train_log", "step": 1916, "epoch": 0.8084388185654009, "progress_pct": 13.47, "epoch_pct": 13.47, "eta": "49:22:03", "max_grad_norm": 1.0, "loss": 0.8177281618118286, "grad_norm": 0.4871830940246582, "learning_rate": 0.0001982641865209517}
-{"ts": "2025-12-27T01:58:43", "event": "train_log", "step": 1918, "epoch": 0.809282700421941, "progress_pct": 13.49, "epoch_pct": 13.49, "eta": "49:20:18", "max_grad_norm": 1.0, "loss": 0.7726616859436035, "grad_norm": 0.4157388210296631, "learning_rate": 0.0001982552651529154}
-{"ts": "2025-12-27T01:59:00", "event": "train_log", "step": 1920, "epoch": 0.810126582278481, "progress_pct": 13.5, "epoch_pct": 13.5, "eta": "49:18:35", "max_grad_norm": 1.0, "loss": 0.6601400375366211, "grad_norm": 0.32338014245033264, "learning_rate": 0.00019824632111927645}
-{"ts": "2025-12-27T01:59:15", "event": "train_log", "step": 1922, "epoch": 0.810970464135021, "progress_pct": 13.52, "epoch_pct": 13.52, "eta": "49:16:36", "max_grad_norm": 1.0, "loss": 0.7866622805595398, "grad_norm": 0.4642949104309082, "learning_rate": 0.00019823735442209804}
-{"ts": "2025-12-27T01:59:32", "event": "train_log", "step": 1924, "epoch": 0.8118143459915612, "progress_pct": 13.53, "epoch_pct": 13.53, "eta": "49:14:52", "max_grad_norm": 1.0, "loss": 0.7857986092567444, "grad_norm": 0.43558797240257263, "learning_rate": 0.00019822836506344865}
-{"ts": "2025-12-27T01:59:47", "event": "train_log", "step": 1926, "epoch": 0.8126582278481013, "progress_pct": 13.54, "epoch_pct": 13.54, "eta": "49:12:59", "max_grad_norm": 1.0, "loss": 0.8407763838768005, "grad_norm": 0.3996953070163727, "learning_rate": 0.000198219353045402}
-{"ts": "2025-12-27T02:00:02", "event": "train_log", "step": 1928, "epoch": 0.8135021097046413, "progress_pct": 13.56, "epoch_pct": 13.56, "eta": "49:11:00", "max_grad_norm": 1.0, "loss": 0.8433752655982971, "grad_norm": 0.4415414333343506, "learning_rate": 0.00019821031837003686}
-{"ts": "2025-12-27T02:00:19", "event": "train_log", "step": 1930, "epoch": 0.8143459915611815, "progress_pct": 13.57, "epoch_pct": 13.57, "eta": "49:09:13", "max_grad_norm": 1.0, "loss": 0.6941158175468445, "grad_norm": 0.37329310178756714, "learning_rate": 0.00019820126103943752}
-{"ts": "2025-12-27T02:00:33", "event": "train_log", "step": 1932, "epoch": 0.8151898734177215, "progress_pct": 13.59, "epoch_pct": 13.59, "eta": "49:07:15", "max_grad_norm": 1.0, "loss": 0.775604248046875, "grad_norm": 0.4482601284980774, "learning_rate": 0.00019819218105569323}
-{"ts": "2025-12-27T02:00:49", "event": "train_log", "step": 1934, "epoch": 0.8160337552742616, "progress_pct": 13.6, "epoch_pct": 13.6, "eta": "49:05:22", "max_grad_norm": 1.0, "loss": 0.8496418595314026, "grad_norm": 0.426194429397583, "learning_rate": 0.00019818307842089854}
-{"ts": "2025-12-27T02:01:04", "event": "train_log", "step": 1936, "epoch": 0.8168776371308016, "progress_pct": 13.61, "epoch_pct": 13.61, "eta": "49:03:26", "max_grad_norm": 1.0, "loss": 0.7767958045005798, "grad_norm": 0.42379093170166016, "learning_rate": 0.00019817395313715335}
-{"ts": "2025-12-27T02:01:19", "event": "train_log", "step": 1938, "epoch": 0.8177215189873418, "progress_pct": 13.63, "epoch_pct": 13.63, "eta": "49:01:32", "max_grad_norm": 1.0, "loss": 0.7347666025161743, "grad_norm": 0.4149782061576843, "learning_rate": 0.0001981648052065626}
-{"ts": "2025-12-27T02:01:34", "event": "train_log", "step": 1940, "epoch": 0.8185654008438819, "progress_pct": 13.64, "epoch_pct": 13.64, "eta": "48:59:35", "max_grad_norm": 1.0, "loss": 0.7839647531509399, "grad_norm": 0.3927431106567383, "learning_rate": 0.0001981556346312366}
-{"ts": "2025-12-27T02:01:49", "event": "train_log", "step": 1942, "epoch": 0.8194092827004219, "progress_pct": 13.66, "epoch_pct": 13.66, "eta": "48:57:38", "max_grad_norm": 1.0, "loss": 0.8870531916618347, "grad_norm": 0.4483136236667633, "learning_rate": 0.00019814644141329083}
-{"ts": "2025-12-27T02:02:03", "event": "train_log", "step": 1944, "epoch": 0.8202531645569621, "progress_pct": 13.67, "epoch_pct": 13.67, "eta": "48:55:36", "max_grad_norm": 1.0, "loss": 0.8646620512008667, "grad_norm": 0.4400147497653961, "learning_rate": 0.00019813722555484594}
-{"ts": "2025-12-27T02:02:17", "event": "train_log", "step": 1946, "epoch": 0.8210970464135021, "progress_pct": 13.68, "epoch_pct": 13.68, "eta": "48:53:38", "max_grad_norm": 1.0, "loss": 0.9576541781425476, "grad_norm": 0.469971626996994, "learning_rate": 0.00019812798705802785}
-{"ts": "2025-12-27T02:02:32", "event": "train_log", "step": 1948, "epoch": 0.8219409282700422, "progress_pct": 13.7, "epoch_pct": 13.7, "eta": "48:51:44", "max_grad_norm": 1.0, "loss": 0.7956477403640747, "grad_norm": 0.388113409280777, "learning_rate": 0.00019811872592496776}
-{"ts": "2025-12-27T02:02:48", "event": "train_log", "step": 1950, "epoch": 0.8227848101265823, "progress_pct": 13.71, "epoch_pct": 13.71, "eta": "48:49:55", "max_grad_norm": 1.0, "loss": 0.8440352082252502, "grad_norm": 0.4271424114704132, "learning_rate": 0.00019810944215780201}
-{"ts": "2025-12-27T02:03:03", "event": "train_log", "step": 1952, "epoch": 0.8236286919831224, "progress_pct": 13.73, "epoch_pct": 13.73, "eta": "48:47:58", "max_grad_norm": 1.0, "loss": 0.8589065074920654, "grad_norm": 0.4097966253757477, "learning_rate": 0.00019810013575867217}
-{"ts": "2025-12-27T02:03:17", "event": "train_log", "step": 1954, "epoch": 0.8244725738396624, "progress_pct": 13.74, "epoch_pct": 13.74, "eta": "48:46:00", "max_grad_norm": 1.0, "loss": 0.8606626987457275, "grad_norm": 0.41550710797309875, "learning_rate": 0.00019809080672972504}
-{"ts": "2025-12-27T02:03:33", "event": "train_log", "step": 1956, "epoch": 0.8253164556962025, "progress_pct": 13.76, "epoch_pct": 13.76, "eta": "48:44:08", "max_grad_norm": 1.0, "loss": 0.7582436800003052, "grad_norm": 0.3680916130542755, "learning_rate": 0.0001980814550731127}
-{"ts": "2025-12-27T02:03:48", "event": "train_log", "step": 1958, "epoch": 0.8261603375527427, "progress_pct": 13.77, "epoch_pct": 13.77, "eta": "48:42:14", "max_grad_norm": 1.0, "loss": 0.8345186710357666, "grad_norm": 0.573297917842865, "learning_rate": 0.00019807208079099234}
-{"ts": "2025-12-27T02:04:02", "event": "train_log", "step": 1960, "epoch": 0.8270042194092827, "progress_pct": 13.78, "epoch_pct": 13.78, "eta": "48:40:16", "max_grad_norm": 1.0, "loss": 0.889683723449707, "grad_norm": 0.43631303310394287, "learning_rate": 0.00019806268388552646}
-{"ts": "2025-12-27T02:04:17", "event": "train_log", "step": 1962, "epoch": 0.8278481012658228, "progress_pct": 13.8, "epoch_pct": 13.8, "eta": "48:38:21", "max_grad_norm": 1.0, "loss": 0.8092973232269287, "grad_norm": 0.442531019449234, "learning_rate": 0.00019805326435888275}
-{"ts": "2025-12-27T02:04:31", "event": "train_log", "step": 1964, "epoch": 0.8286919831223629, "progress_pct": 13.81, "epoch_pct": 13.81, "eta": "48:36:24", "max_grad_norm": 1.0, "loss": 0.8919535279273987, "grad_norm": 0.45020824670791626, "learning_rate": 0.0001980438222132341}
-{"ts": "2025-12-27T02:04:46", "event": "train_log", "step": 1966, "epoch": 0.829535864978903, "progress_pct": 13.83, "epoch_pct": 13.83, "eta": "48:34:29", "max_grad_norm": 1.0, "loss": 0.7652381658554077, "grad_norm": 0.43131786584854126, "learning_rate": 0.0001980343574507586}
-{"ts": "2025-12-27T02:05:01", "event": "train_log", "step": 1968, "epoch": 0.830379746835443, "progress_pct": 13.84, "epoch_pct": 13.84, "eta": "48:32:37", "max_grad_norm": 1.0, "loss": 0.8512389659881592, "grad_norm": 0.4461326599121094, "learning_rate": 0.00019802487007363967}
-{"ts": "2025-12-27T02:05:16", "event": "train_log", "step": 1970, "epoch": 0.8312236286919831, "progress_pct": 13.85, "epoch_pct": 13.85, "eta": "48:30:45", "max_grad_norm": 1.0, "loss": 0.8681327700614929, "grad_norm": 0.4676894247531891, "learning_rate": 0.0001980153600840658}
-{"ts": "2025-12-27T02:05:32", "event": "train_log", "step": 1972, "epoch": 0.8320675105485232, "progress_pct": 13.87, "epoch_pct": 13.87, "eta": "48:28:56", "max_grad_norm": 1.0, "loss": 0.7476955652236938, "grad_norm": 0.38376888632774353, "learning_rate": 0.00019800582748423075}
-{"ts": "2025-12-27T02:05:47", "event": "train_log", "step": 1974, "epoch": 0.8329113924050633, "progress_pct": 13.88, "epoch_pct": 13.88, "eta": "48:27:05", "max_grad_norm": 1.0, "loss": 0.814192533493042, "grad_norm": 0.37173229455947876, "learning_rate": 0.00019799627227633354}
-{"ts": "2025-12-27T02:06:02", "event": "train_log", "step": 1976, "epoch": 0.8337552742616033, "progress_pct": 13.9, "epoch_pct": 13.9, "eta": "48:25:13", "max_grad_norm": 1.0, "loss": 0.7668994069099426, "grad_norm": 0.4345237910747528, "learning_rate": 0.00019798669446257844}
-{"ts": "2025-12-27T02:06:17", "event": "train_log", "step": 1978, "epoch": 0.8345991561181435, "progress_pct": 13.91, "epoch_pct": 13.91, "eta": "48:23:21", "max_grad_norm": 1.0, "loss": 0.8321775197982788, "grad_norm": 0.45872583985328674, "learning_rate": 0.0001979770940451747}
-{"ts": "2025-12-27T02:06:31", "event": "train_log", "step": 1980, "epoch": 0.8354430379746836, "progress_pct": 13.92, "epoch_pct": 13.92, "eta": "48:21:27", "max_grad_norm": 1.0, "loss": 0.7824342250823975, "grad_norm": 0.40618205070495605, "learning_rate": 0.0001979674710263371}
-{"ts": "2025-12-27T02:06:47", "event": "train_log", "step": 1982, "epoch": 0.8362869198312236, "progress_pct": 13.94, "epoch_pct": 13.94, "eta": "48:19:37", "max_grad_norm": 1.0, "loss": 0.8752480745315552, "grad_norm": 0.38377392292022705, "learning_rate": 0.00019795782540828544}
-{"ts": "2025-12-27T02:07:02", "event": "train_log", "step": 1984, "epoch": 0.8371308016877637, "progress_pct": 13.95, "epoch_pct": 13.95, "eta": "48:17:50", "max_grad_norm": 1.0, "loss": 0.66700679063797, "grad_norm": 0.36340072751045227, "learning_rate": 0.00019794815719324476}
-{"ts": "2025-12-27T02:07:17", "event": "train_log", "step": 1986, "epoch": 0.8379746835443038, "progress_pct": 13.97, "epoch_pct": 13.97, "eta": "48:15:55", "max_grad_norm": 1.0, "loss": 0.8582209944725037, "grad_norm": 0.4638384282588959, "learning_rate": 0.00019793846638344536}
-{"ts": "2025-12-27T02:07:32", "event": "train_log", "step": 1988, "epoch": 0.8388185654008439, "progress_pct": 13.98, "epoch_pct": 13.98, "eta": "48:14:04", "max_grad_norm": 1.0, "loss": 0.7724968791007996, "grad_norm": 0.38364699482917786, "learning_rate": 0.00019792875298112268}
-{"ts": "2025-12-27T02:07:47", "event": "train_log", "step": 1990, "epoch": 0.8396624472573839, "progress_pct": 13.99, "epoch_pct": 13.99, "eta": "48:12:13", "max_grad_norm": 1.0, "loss": 0.8542404174804688, "grad_norm": 0.439730703830719, "learning_rate": 0.00019791901698851749}
-{"ts": "2025-12-27T02:08:01", "event": "train_log", "step": 1992, "epoch": 0.8405063291139241, "progress_pct": 14.01, "epoch_pct": 14.01, "eta": "48:10:21", "max_grad_norm": 1.0, "loss": 0.8424296975135803, "grad_norm": 0.4622722566127777, "learning_rate": 0.00019790925840787563}
-{"ts": "2025-12-27T02:08:16", "event": "train_log", "step": 1994, "epoch": 0.8413502109704641, "progress_pct": 14.02, "epoch_pct": 14.02, "eta": "48:08:29", "max_grad_norm": 1.0, "loss": 0.8400710225105286, "grad_norm": 0.4491989314556122, "learning_rate": 0.0001978994772414482}
-{"ts": "2025-12-27T02:08:31", "event": "train_log", "step": 1996, "epoch": 0.8421940928270042, "progress_pct": 14.04, "epoch_pct": 14.04, "eta": "48:06:41", "max_grad_norm": 1.0, "loss": 0.7265452146530151, "grad_norm": 0.372295081615448, "learning_rate": 0.0001978896734914916}
-{"ts": "2025-12-27T02:08:46", "event": "train_log", "step": 1998, "epoch": 0.8430379746835444, "progress_pct": 14.05, "epoch_pct": 14.05, "eta": "48:04:49", "max_grad_norm": 1.0, "loss": 0.8458228707313538, "grad_norm": 0.4328666925430298, "learning_rate": 0.00019787984716026732}
-{"ts": "2025-12-27T02:09:01", "event": "train_log", "step": 2000, "epoch": 0.8438818565400844, "progress_pct": 14.06, "epoch_pct": 14.06, "eta": "48:02:57", "max_grad_norm": 1.0, "loss": 0.8517491817474365, "grad_norm": 0.42246317863464355, "learning_rate": 0.00019786999825004216}
-{"ts": "2025-12-27T02:20:26", "event": "train_log", "step": 2000, "epoch": 0.8438818565400844, "progress_pct": 14.06, "epoch_pct": 14.06, "eta": "49:12:44", "max_grad_norm": 1.0, "eval_loss": 0.8460908532142639, "eval_runtime": 685.2518, "eval_samples_per_second": 3.075, "eval_steps_per_second": 3.075}
-{"ts": "2025-12-27T02:20:44", "event": "train_log", "step": 2002, "epoch": 0.8447257383966245, "progress_pct": 14.08, "epoch_pct": 14.08, "eta": "49:11:05", "max_grad_norm": 1.0, "loss": 0.8045481443405151, "grad_norm": 0.3927323818206787, "learning_rate": 0.00019786012676308802}
-{"ts": "2025-12-27T02:20:59", "event": "train_log", "step": 2004, "epoch": 0.8455696202531645, "progress_pct": 14.09, "epoch_pct": 14.09, "eta": "49:09:17", "max_grad_norm": 1.0, "loss": 0.7509838938713074, "grad_norm": 0.38189369440078735, "learning_rate": 0.00019785023270168202}
-{"ts": "2025-12-27T02:21:15", "event": "train_log", "step": 2006, "epoch": 0.8464135021097047, "progress_pct": 14.11, "epoch_pct": 14.11, "eta": "49:07:27", "max_grad_norm": 1.0, "loss": 0.7730163335800171, "grad_norm": 0.40383535623550415, "learning_rate": 0.00019784031606810663}
-{"ts": "2025-12-27T02:21:31", "event": "train_log", "step": 2008, "epoch": 0.8472573839662447, "progress_pct": 14.12, "epoch_pct": 14.12, "eta": "49:05:37", "max_grad_norm": 1.0, "loss": 0.7096828818321228, "grad_norm": 0.3665419816970825, "learning_rate": 0.00019783037686464935}
-{"ts": "2025-12-27T02:21:47", "event": "train_log", "step": 2010, "epoch": 0.8481012658227848, "progress_pct": 14.14, "epoch_pct": 14.14, "eta": "49:03:50", "max_grad_norm": 1.0, "loss": 0.8186401128768921, "grad_norm": 0.36623379588127136, "learning_rate": 0.00019782041509360302}
-{"ts": "2025-12-27T02:22:03", "event": "train_log", "step": 2012, "epoch": 0.8489451476793249, "progress_pct": 14.15, "epoch_pct": 14.15, "eta": "49:02:01", "max_grad_norm": 1.0, "loss": 0.8502879738807678, "grad_norm": 0.477255642414093, "learning_rate": 0.0001978104307572656}
-{"ts": "2025-12-27T02:22:19", "event": "train_log", "step": 2014, "epoch": 0.849789029535865, "progress_pct": 14.16, "epoch_pct": 14.16, "eta": "49:00:14", "max_grad_norm": 1.0, "loss": 0.9010884761810303, "grad_norm": 0.44456636905670166, "learning_rate": 0.00019780042385794032}
-{"ts": "2025-12-27T02:22:34", "event": "train_log", "step": 2016, "epoch": 0.850632911392405, "progress_pct": 14.18, "epoch_pct": 14.18, "eta": "48:58:23", "max_grad_norm": 1.0, "loss": 0.774183452129364, "grad_norm": 0.42378175258636475, "learning_rate": 0.00019779039439793552}
-{"ts": "2025-12-27T02:22:49", "event": "train_log", "step": 2018, "epoch": 0.8514767932489451, "progress_pct": 14.19, "epoch_pct": 14.19, "eta": "48:56:32", "max_grad_norm": 1.0, "loss": 0.8487694263458252, "grad_norm": 0.43021997809410095, "learning_rate": 0.00019778034237956482}
-{"ts": "2025-12-27T02:23:06", "event": "train_log", "step": 2020, "epoch": 0.8523206751054853, "progress_pct": 14.21, "epoch_pct": 14.21, "eta": "48:54:47", "max_grad_norm": 1.0, "loss": 0.8004868030548096, "grad_norm": 0.38188812136650085, "learning_rate": 0.00019777026780514704}
-{"ts": "2025-12-27T02:23:21", "event": "train_log", "step": 2022, "epoch": 0.8531645569620253, "progress_pct": 14.22, "epoch_pct": 14.22, "eta": "48:52:57", "max_grad_norm": 1.0, "loss": 0.7680953145027161, "grad_norm": 0.3684130609035492, "learning_rate": 0.0001977601706770062}
-{"ts": "2025-12-27T02:23:37", "event": "train_log", "step": 2024, "epoch": 0.8540084388185654, "progress_pct": 14.23, "epoch_pct": 14.23, "eta": "48:51:11", "max_grad_norm": 1.0, "loss": 0.8990264534950256, "grad_norm": 0.444844514131546, "learning_rate": 0.00019775005099747153}
-{"ts": "2025-12-27T02:23:54", "event": "train_log", "step": 2026, "epoch": 0.8548523206751055, "progress_pct": 14.25, "epoch_pct": 14.25, "eta": "48:49:31", "max_grad_norm": 1.0, "loss": 0.7676048874855042, "grad_norm": 0.3432365655899048, "learning_rate": 0.00019773990876887737}
-{"ts": "2025-12-27T02:24:10", "event": "train_log", "step": 2028, "epoch": 0.8556962025316456, "progress_pct": 14.26, "epoch_pct": 14.26, "eta": "48:47:41", "max_grad_norm": 1.0, "loss": 0.8546769618988037, "grad_norm": 0.3728618025779724, "learning_rate": 0.00019772974399356343}
-{"ts": "2025-12-27T02:24:26", "event": "train_log", "step": 2030, "epoch": 0.8565400843881856, "progress_pct": 14.28, "epoch_pct": 14.28, "eta": "48:46:01", "max_grad_norm": 1.0, "loss": 0.8009977340698242, "grad_norm": 0.42767980694770813, "learning_rate": 0.00019771955667387449}
-{"ts": "2025-12-27T02:24:42", "event": "train_log", "step": 2032, "epoch": 0.8573839662447258, "progress_pct": 14.29, "epoch_pct": 14.29, "eta": "48:44:15", "max_grad_norm": 1.0, "loss": 0.8424299955368042, "grad_norm": 0.4125710129737854, "learning_rate": 0.00019770934681216055}
-{"ts": "2025-12-27T02:24:58", "event": "train_log", "step": 2034, "epoch": 0.8582278481012658, "progress_pct": 14.3, "epoch_pct": 14.3, "eta": "48:42:29", "max_grad_norm": 1.0, "loss": 0.7940502762794495, "grad_norm": 0.4399266839027405, "learning_rate": 0.00019769911441077685}
-{"ts": "2025-12-27T02:25:15", "event": "train_log", "step": 2036, "epoch": 0.8590717299578059, "progress_pct": 14.32, "epoch_pct": 14.32, "eta": "48:40:49", "max_grad_norm": 1.0, "loss": 0.9424314498901367, "grad_norm": 0.41797709465026855, "learning_rate": 0.0001976888594720838}
-{"ts": "2025-12-27T02:25:31", "event": "train_log", "step": 2038, "epoch": 0.859915611814346, "progress_pct": 14.33, "epoch_pct": 14.33, "eta": "48:39:02", "max_grad_norm": 1.0, "loss": 0.9102896451950073, "grad_norm": 0.5245009660720825, "learning_rate": 0.00019767858199844698}
-{"ts": "2025-12-27T02:25:48", "event": "train_log", "step": 2040, "epoch": 0.8607594936708861, "progress_pct": 14.35, "epoch_pct": 14.35, "eta": "48:37:22", "max_grad_norm": 1.0, "loss": 0.7434720396995544, "grad_norm": 0.4092593193054199, "learning_rate": 0.00019766828199223728}
-{"ts": "2025-12-27T02:26:03", "event": "train_log", "step": 2042, "epoch": 0.8616033755274262, "progress_pct": 14.36, "epoch_pct": 14.36, "eta": "48:35:34", "max_grad_norm": 1.0, "loss": 0.7441987991333008, "grad_norm": 0.40787473320961, "learning_rate": 0.00019765795945583068}
-{"ts": "2025-12-27T02:26:18", "event": "train_log", "step": 2044, "epoch": 0.8624472573839662, "progress_pct": 14.37, "epoch_pct": 14.37, "eta": "48:33:46", "max_grad_norm": 1.0, "loss": 0.8317872881889343, "grad_norm": 0.42438021302223206, "learning_rate": 0.0001976476143916084}
-{"ts": "2025-12-27T02:26:34", "event": "train_log", "step": 2046, "epoch": 0.8632911392405064, "progress_pct": 14.39, "epoch_pct": 14.39, "eta": "48:32:01", "max_grad_norm": 1.0, "loss": 0.764509379863739, "grad_norm": 0.38261914253234863, "learning_rate": 0.00019763724680195682}
-{"ts": "2025-12-27T02:26:50", "event": "train_log", "step": 2048, "epoch": 0.8641350210970464, "progress_pct": 14.4, "epoch_pct": 14.4, "eta": "48:30:16", "max_grad_norm": 1.0, "loss": 0.8666167855262756, "grad_norm": 0.43295741081237793, "learning_rate": 0.00019762685668926758}
-{"ts": "2025-12-27T02:27:06", "event": "train_log", "step": 2050, "epoch": 0.8649789029535865, "progress_pct": 14.42, "epoch_pct": 14.42, "eta": "48:28:32", "max_grad_norm": 1.0, "loss": 0.7606754302978516, "grad_norm": 0.36384403705596924, "learning_rate": 0.00019761644405593743}
-{"ts": "2025-12-27T02:27:21", "event": "train_log", "step": 2052, "epoch": 0.8658227848101265, "progress_pct": 14.43, "epoch_pct": 14.43, "eta": "48:26:41", "max_grad_norm": 1.0, "loss": 0.827495813369751, "grad_norm": 0.4296814501285553, "learning_rate": 0.0001976060089043684}
-{"ts": "2025-12-27T02:27:37", "event": "train_log", "step": 2054, "epoch": 0.8666666666666667, "progress_pct": 14.44, "epoch_pct": 14.44, "eta": "48:24:55", "max_grad_norm": 1.0, "loss": 0.7418577075004578, "grad_norm": 0.3831455111503601, "learning_rate": 0.0001975955512369677}
-{"ts": "2025-12-27T02:27:52", "event": "train_log", "step": 2056, "epoch": 0.8675105485232067, "progress_pct": 14.46, "epoch_pct": 14.46, "eta": "48:23:10", "max_grad_norm": 1.0, "loss": 0.8603045344352722, "grad_norm": 0.44710344076156616, "learning_rate": 0.0001975850710561477}
-{"ts": "2025-12-27T02:28:08", "event": "train_log", "step": 2058, "epoch": 0.8683544303797468, "progress_pct": 14.47, "epoch_pct": 14.47, "eta": "48:21:25", "max_grad_norm": 1.0, "loss": 0.900658905506134, "grad_norm": 0.44012558460235596, "learning_rate": 0.00019757456836432593}
-{"ts": "2025-12-27T02:28:24", "event": "train_log", "step": 2060, "epoch": 0.869198312236287, "progress_pct": 14.49, "epoch_pct": 14.49, "eta": "48:19:39", "max_grad_norm": 1.0, "loss": 0.8416497707366943, "grad_norm": 0.42166298627853394, "learning_rate": 0.0001975640431639252}
-{"ts": "2025-12-27T02:28:39", "event": "train_log", "step": 2062, "epoch": 0.870042194092827, "progress_pct": 14.5, "epoch_pct": 14.5, "eta": "48:17:50", "max_grad_norm": 1.0, "loss": 0.8281066417694092, "grad_norm": 0.40824490785598755, "learning_rate": 0.00019755349545737345}
-{"ts": "2025-12-27T02:28:54", "event": "train_log", "step": 2064, "epoch": 0.8708860759493671, "progress_pct": 14.51, "epoch_pct": 14.51, "eta": "48:16:01", "max_grad_norm": 1.0, "loss": 0.83869469165802, "grad_norm": 0.4272223711013794, "learning_rate": 0.00019754292524710388}
-{"ts": "2025-12-27T02:29:09", "event": "train_log", "step": 2066, "epoch": 0.8717299578059071, "progress_pct": 14.53, "epoch_pct": 14.53, "eta": "48:14:16", "max_grad_norm": 1.0, "loss": 0.8337644934654236, "grad_norm": 0.3732798397541046, "learning_rate": 0.00019753233253555478}
-{"ts": "2025-12-27T02:29:25", "event": "train_log", "step": 2068, "epoch": 0.8725738396624473, "progress_pct": 14.54, "epoch_pct": 14.54, "eta": "48:12:32", "max_grad_norm": 1.0, "loss": 0.7677452564239502, "grad_norm": 0.4048069417476654, "learning_rate": 0.00019752171732516973}
-{"ts": "2025-12-27T02:29:41", "event": "train_log", "step": 2070, "epoch": 0.8734177215189873, "progress_pct": 14.56, "epoch_pct": 14.56, "eta": "48:10:48", "max_grad_norm": 1.0, "loss": 0.8320774435997009, "grad_norm": 0.43628430366516113, "learning_rate": 0.00019751107961839742}
-{"ts": "2025-12-27T02:29:57", "event": "train_log", "step": 2072, "epoch": 0.8742616033755274, "progress_pct": 14.57, "epoch_pct": 14.57, "eta": "48:09:06", "max_grad_norm": 1.0, "loss": 0.8480262160301208, "grad_norm": 0.43674105405807495, "learning_rate": 0.00019750041941769174}
-{"ts": "2025-12-27T02:30:13", "event": "train_log", "step": 2074, "epoch": 0.8751054852320675, "progress_pct": 14.59, "epoch_pct": 14.59, "eta": "48:07:23", "max_grad_norm": 1.0, "loss": 0.7598503828048706, "grad_norm": 0.3678584098815918, "learning_rate": 0.0001974897367255119}
-{"ts": "2025-12-27T02:30:29", "event": "train_log", "step": 2076, "epoch": 0.8759493670886076, "progress_pct": 14.6, "epoch_pct": 14.6, "eta": "48:05:47", "max_grad_norm": 1.0, "loss": 0.7907084822654724, "grad_norm": 0.4316411316394806, "learning_rate": 0.0001974790315443221}
-{"ts": "2025-12-27T02:30:44", "event": "train_log", "step": 2078, "epoch": 0.8767932489451477, "progress_pct": 14.61, "epoch_pct": 14.61, "eta": "48:03:58", "max_grad_norm": 1.0, "loss": 0.8287727236747742, "grad_norm": 0.426465779542923, "learning_rate": 0.00019746830387659182}
-{"ts": "2025-12-27T02:30:59", "event": "train_log", "step": 2080, "epoch": 0.8776371308016878, "progress_pct": 14.63, "epoch_pct": 14.63, "eta": "48:02:08", "max_grad_norm": 1.0, "loss": 0.8464577794075012, "grad_norm": 0.447337806224823, "learning_rate": 0.00019745755372479578}
-{"ts": "2025-12-27T02:31:14", "event": "train_log", "step": 2082, "epoch": 0.8784810126582279, "progress_pct": 14.64, "epoch_pct": 14.64, "eta": "48:00:21", "max_grad_norm": 1.0, "loss": 0.7383086681365967, "grad_norm": 0.37877580523490906, "learning_rate": 0.0001974467810914138}
-{"ts": "2025-12-27T02:31:28", "event": "train_log", "step": 2084, "epoch": 0.8793248945147679, "progress_pct": 14.66, "epoch_pct": 14.66, "eta": "47:58:32", "max_grad_norm": 1.0, "loss": 0.729221522808075, "grad_norm": 0.3914664089679718, "learning_rate": 0.0001974359859789309}
-{"ts": "2025-12-27T02:31:44", "event": "train_log", "step": 2086, "epoch": 0.880168776371308, "progress_pct": 14.67, "epoch_pct": 14.67, "eta": "47:56:50", "max_grad_norm": 1.0, "loss": 0.692332923412323, "grad_norm": 0.39767366647720337, "learning_rate": 0.00019742516838983733}
-{"ts": "2025-12-27T02:31:59", "event": "train_log", "step": 2088, "epoch": 0.8810126582278481, "progress_pct": 14.68, "epoch_pct": 14.68, "eta": "47:55:00", "max_grad_norm": 1.0, "loss": 0.8540068864822388, "grad_norm": 0.4396754205226898, "learning_rate": 0.0001974143283266285}
-{"ts": "2025-12-27T02:32:13", "event": "train_log", "step": 2090, "epoch": 0.8818565400843882, "progress_pct": 14.7, "epoch_pct": 14.7, "eta": "47:53:10", "max_grad_norm": 1.0, "loss": 0.8570998907089233, "grad_norm": 0.4968172609806061, "learning_rate": 0.00019740346579180502}
-{"ts": "2025-12-27T02:32:29", "event": "train_log", "step": 2092, "epoch": 0.8827004219409282, "progress_pct": 14.71, "epoch_pct": 14.71, "eta": "47:51:29", "max_grad_norm": 1.0, "loss": 0.784139096736908, "grad_norm": 0.41686809062957764, "learning_rate": 0.00019739258078787264}
-{"ts": "2025-12-27T02:32:44", "event": "train_log", "step": 2094, "epoch": 0.8835443037974684, "progress_pct": 14.73, "epoch_pct": 14.73, "eta": "47:49:44", "max_grad_norm": 1.0, "loss": 0.8521397113800049, "grad_norm": 0.38788047432899475, "learning_rate": 0.0001973816733173423}
-{"ts": "2025-12-27T02:32:59", "event": "train_log", "step": 2096, "epoch": 0.8843881856540085, "progress_pct": 14.74, "epoch_pct": 14.74, "eta": "47:47:56", "max_grad_norm": 1.0, "loss": 0.8457935452461243, "grad_norm": 0.38369178771972656, "learning_rate": 0.00019737074338273023}
-{"ts": "2025-12-27T02:33:15", "event": "train_log", "step": 2098, "epoch": 0.8852320675105485, "progress_pct": 14.75, "epoch_pct": 14.75, "eta": "47:46:15", "max_grad_norm": 1.0, "loss": 0.7425959706306458, "grad_norm": 0.38869398832321167, "learning_rate": 0.0001973597909865577}
-{"ts": "2025-12-27T02:33:30", "event": "train_log", "step": 2100, "epoch": 0.8860759493670886, "progress_pct": 14.77, "epoch_pct": 14.77, "eta": "47:44:34", "max_grad_norm": 1.0, "loss": 0.7742393016815186, "grad_norm": 0.4067917466163635, "learning_rate": 0.00019734881613135122}
-{"ts": "2025-12-27T02:44:39", "event": "train_log", "step": 2100, "epoch": 0.8860759493670886, "progress_pct": 14.77, "epoch_pct": 14.77, "eta": "48:48:55", "max_grad_norm": 1.0, "eval_loss": 0.8401098847389221, "eval_runtime": 669.1149, "eval_samples_per_second": 3.149, "eval_steps_per_second": 3.149}
-{"ts": "2025-12-27T02:44:54", "event": "train_log", "step": 2102, "epoch": 0.8869198312236287, "progress_pct": 14.78, "epoch_pct": 14.78, "eta": "48:47:04", "max_grad_norm": 1.0, "loss": 0.9099814295768738, "grad_norm": 0.4282098412513733, "learning_rate": 0.00019733781881964242}
-{"ts": "2025-12-27T02:45:09", "event": "train_log", "step": 2104, "epoch": 0.8877637130801688, "progress_pct": 14.8, "epoch_pct": 14.8, "eta": "48:45:15", "max_grad_norm": 1.0, "loss": 0.7458856105804443, "grad_norm": 0.33882173895835876, "learning_rate": 0.00019732679905396826}
-{"ts": "2025-12-27T02:45:26", "event": "train_log", "step": 2106, "epoch": 0.8886075949367088, "progress_pct": 14.81, "epoch_pct": 14.81, "eta": "48:43:37", "max_grad_norm": 1.0, "loss": 0.7829693555831909, "grad_norm": 0.43959516286849976, "learning_rate": 0.00019731575683687078}
-{"ts": "2025-12-27T02:45:41", "event": "train_log", "step": 2108, "epoch": 0.889451476793249, "progress_pct": 14.82, "epoch_pct": 14.82, "eta": "48:41:47", "max_grad_norm": 1.0, "loss": 0.7898997068405151, "grad_norm": 0.40046483278274536, "learning_rate": 0.00019730469217089716}
-{"ts": "2025-12-27T02:45:57", "event": "train_log", "step": 2110, "epoch": 0.890295358649789, "progress_pct": 14.84, "epoch_pct": 14.84, "eta": "48:40:05", "max_grad_norm": 1.0, "loss": 0.7874186635017395, "grad_norm": 0.40572553873062134, "learning_rate": 0.00019729360505859984}
-{"ts": "2025-12-27T02:46:13", "event": "train_log", "step": 2112, "epoch": 0.8911392405063291, "progress_pct": 14.85, "epoch_pct": 14.85, "eta": "48:38:23", "max_grad_norm": 1.0, "loss": 0.8499898910522461, "grad_norm": 0.42086347937583923, "learning_rate": 0.0001972824955025364}
-{"ts": "2025-12-27T02:46:29", "event": "train_log", "step": 2114, "epoch": 0.8919831223628693, "progress_pct": 14.87, "epoch_pct": 14.87, "eta": "48:36:38", "max_grad_norm": 1.0, "loss": 0.7940409779548645, "grad_norm": 0.38845229148864746, "learning_rate": 0.00019727136350526956}
-{"ts": "2025-12-27T02:46:46", "event": "train_log", "step": 2116, "epoch": 0.8928270042194093, "progress_pct": 14.88, "epoch_pct": 14.88, "eta": "48:35:01", "max_grad_norm": 1.0, "loss": 0.8279082775115967, "grad_norm": 0.41575267910957336, "learning_rate": 0.00019726020906936728}
-{"ts": "2025-12-27T02:47:02", "event": "train_log", "step": 2118, "epoch": 0.8936708860759494, "progress_pct": 14.89, "epoch_pct": 14.89, "eta": "48:33:15", "max_grad_norm": 1.0, "loss": 0.8217757940292358, "grad_norm": 0.37615057826042175, "learning_rate": 0.0001972490321974027}
-{"ts": "2025-12-27T02:47:16", "event": "train_log", "step": 2120, "epoch": 0.8945147679324894, "progress_pct": 14.91, "epoch_pct": 14.91, "eta": "48:31:26", "max_grad_norm": 1.0, "loss": 0.7637750506401062, "grad_norm": 0.9318385124206543, "learning_rate": 0.00019723783289195415}
-{"ts": "2025-12-27T02:47:33", "event": "train_log", "step": 2122, "epoch": 0.8953586497890296, "progress_pct": 14.92, "epoch_pct": 14.92, "eta": "48:29:46", "max_grad_norm": 1.0, "loss": 0.8702366948127747, "grad_norm": 0.41948962211608887, "learning_rate": 0.000197226611155605}
-{"ts": "2025-12-27T02:47:49", "event": "train_log", "step": 2124, "epoch": 0.8962025316455696, "progress_pct": 14.94, "epoch_pct": 14.94, "eta": "48:28:06", "max_grad_norm": 1.0, "loss": 0.8146984577178955, "grad_norm": 0.4718417525291443, "learning_rate": 0.00019721536699094392}
-{"ts": "2025-12-27T02:48:04", "event": "train_log", "step": 2126, "epoch": 0.8970464135021097, "progress_pct": 14.95, "epoch_pct": 14.95, "eta": "48:26:20", "max_grad_norm": 1.0, "loss": 0.8646075129508972, "grad_norm": 0.4470657408237457, "learning_rate": 0.00019720410040056474}
-{"ts": "2025-12-27T02:48:20", "event": "train_log", "step": 2128, "epoch": 0.8978902953586498, "progress_pct": 14.96, "epoch_pct": 14.96, "eta": "48:24:34", "max_grad_norm": 1.0, "loss": 0.7925992012023926, "grad_norm": 0.4176540970802307, "learning_rate": 0.00019719281138706643}
-{"ts": "2025-12-27T02:48:35", "event": "train_log", "step": 2130, "epoch": 0.8987341772151899, "progress_pct": 14.98, "epoch_pct": 14.98, "eta": "48:22:51", "max_grad_norm": 1.0, "loss": 0.8142143487930298, "grad_norm": 0.4854719042778015, "learning_rate": 0.00019718149995305315}
-{"ts": "2025-12-27T02:48:53", "event": "train_log", "step": 2132, "epoch": 0.8995780590717299, "progress_pct": 14.99, "epoch_pct": 14.99, "eta": "48:21:18", "max_grad_norm": 1.0, "loss": 0.8050890564918518, "grad_norm": 0.4270440340042114, "learning_rate": 0.00019717016610113427}
-{"ts": "2025-12-27T02:49:09", "event": "train_log", "step": 2134, "epoch": 0.90042194092827, "progress_pct": 15.01, "epoch_pct": 15.01, "eta": "48:19:38", "max_grad_norm": 1.0, "loss": 0.7888354659080505, "grad_norm": 0.37710970640182495, "learning_rate": 0.00019715880983392422}
-{"ts": "2025-12-27T02:49:24", "event": "train_log", "step": 2136, "epoch": 0.9012658227848102, "progress_pct": 15.02, "epoch_pct": 15.02, "eta": "48:17:47", "max_grad_norm": 1.0, "loss": 0.7348225712776184, "grad_norm": 0.4181252717971802, "learning_rate": 0.00019714743115404273}
-{"ts": "2025-12-27T02:49:39", "event": "train_log", "step": 2138, "epoch": 0.9021097046413502, "progress_pct": 15.04, "epoch_pct": 15.04, "eta": "48:16:02", "max_grad_norm": 1.0, "loss": 0.7729623913764954, "grad_norm": 0.4475359618663788, "learning_rate": 0.0001971360300641146}
-{"ts": "2025-12-27T02:49:55", "event": "train_log", "step": 2140, "epoch": 0.9029535864978903, "progress_pct": 15.05, "epoch_pct": 15.05, "eta": "48:14:21", "max_grad_norm": 1.0, "loss": 0.8066384792327881, "grad_norm": 0.4052332937717438, "learning_rate": 0.00019712460656676992}
-{"ts": "2025-12-27T02:50:10", "event": "train_log", "step": 2142, "epoch": 0.9037974683544304, "progress_pct": 15.06, "epoch_pct": 15.06, "eta": "48:12:35", "max_grad_norm": 1.0, "loss": 0.8053154349327087, "grad_norm": 0.4567393362522125, "learning_rate": 0.0001971131606646438}
-{"ts": "2025-12-27T02:50:27", "event": "train_log", "step": 2144, "epoch": 0.9046413502109705, "progress_pct": 15.08, "epoch_pct": 15.08, "eta": "48:11:00", "max_grad_norm": 1.0, "loss": 0.7242560386657715, "grad_norm": 0.4304409325122833, "learning_rate": 0.00019710169236037656}
-{"ts": "2025-12-27T02:50:42", "event": "train_log", "step": 2146, "epoch": 0.9054852320675105, "progress_pct": 15.09, "epoch_pct": 15.09, "eta": "48:09:17", "max_grad_norm": 1.0, "loss": 0.8475301265716553, "grad_norm": 0.4785008132457733, "learning_rate": 0.0001970902016566138}
-{"ts": "2025-12-27T02:50:58", "event": "train_log", "step": 2148, "epoch": 0.9063291139240506, "progress_pct": 15.11, "epoch_pct": 15.11, "eta": "48:07:33", "max_grad_norm": 1.0, "loss": 0.928544282913208, "grad_norm": 0.45226508378982544, "learning_rate": 0.00019707868855600618}
-{"ts": "2025-12-27T02:51:14", "event": "train_log", "step": 2150, "epoch": 0.9071729957805907, "progress_pct": 15.12, "epoch_pct": 15.12, "eta": "48:05:53", "max_grad_norm": 1.0, "loss": 0.8135722875595093, "grad_norm": 0.3794468641281128, "learning_rate": 0.00019706715306120956}
-{"ts": "2025-12-27T02:51:29", "event": "train_log", "step": 2152, "epoch": 0.9080168776371308, "progress_pct": 15.13, "epoch_pct": 15.13, "eta": "48:04:12", "max_grad_norm": 1.0, "loss": 0.7808290719985962, "grad_norm": 0.4005141258239746, "learning_rate": 0.0001970555951748849}
-{"ts": "2025-12-27T02:51:45", "event": "train_log", "step": 2154, "epoch": 0.9088607594936708, "progress_pct": 15.15, "epoch_pct": 15.15, "eta": "48:02:29", "max_grad_norm": 1.0, "loss": 0.8292917013168335, "grad_norm": 0.37929919362068176, "learning_rate": 0.00019704401489969842}
-{"ts": "2025-12-27T02:52:00", "event": "train_log", "step": 2156, "epoch": 0.909704641350211, "progress_pct": 15.16, "epoch_pct": 15.16, "eta": "48:00:45", "max_grad_norm": 1.0, "loss": 0.772884726524353, "grad_norm": 0.4458678066730499, "learning_rate": 0.0001970324122383215}
-{"ts": "2025-12-27T02:52:15", "event": "train_log", "step": 2158, "epoch": 0.9105485232067511, "progress_pct": 15.18, "epoch_pct": 15.18, "eta": "47:59:01", "max_grad_norm": 1.0, "loss": 0.8204470872879028, "grad_norm": 0.41907885670661926, "learning_rate": 0.0001970207871934306}
-{"ts": "2025-12-27T02:52:31", "event": "train_log", "step": 2160, "epoch": 0.9113924050632911, "progress_pct": 15.19, "epoch_pct": 15.19, "eta": "47:57:20", "max_grad_norm": 1.0, "loss": 0.8361451625823975, "grad_norm": 0.40610212087631226, "learning_rate": 0.00019700913976770741}
-{"ts": "2025-12-27T02:52:46", "event": "train_log", "step": 2162, "epoch": 0.9122362869198313, "progress_pct": 15.2, "epoch_pct": 15.2, "eta": "47:55:39", "max_grad_norm": 1.0, "loss": 0.8456075191497803, "grad_norm": 0.4213273227214813, "learning_rate": 0.00019699746996383878}
-{"ts": "2025-12-27T02:53:02", "event": "train_log", "step": 2164, "epoch": 0.9130801687763713, "progress_pct": 15.22, "epoch_pct": 15.22, "eta": "47:53:56", "max_grad_norm": 1.0, "loss": 0.8731603622436523, "grad_norm": 0.49264612793922424, "learning_rate": 0.0001969857777845167}
-{"ts": "2025-12-27T02:53:18", "event": "train_log", "step": 2166, "epoch": 0.9139240506329114, "progress_pct": 15.23, "epoch_pct": 15.23, "eta": "47:52:21", "max_grad_norm": 1.0, "loss": 0.8149666786193848, "grad_norm": 0.42002132534980774, "learning_rate": 0.00019697406323243834}
-{"ts": "2025-12-27T02:53:34", "event": "train_log", "step": 2168, "epoch": 0.9147679324894514, "progress_pct": 15.25, "epoch_pct": 15.25, "eta": "47:50:41", "max_grad_norm": 1.0, "loss": 0.7508546710014343, "grad_norm": 0.37501421570777893, "learning_rate": 0.000196962326310306}
-{"ts": "2025-12-27T02:53:50", "event": "train_log", "step": 2170, "epoch": 0.9156118143459916, "progress_pct": 15.26, "epoch_pct": 15.26, "eta": "47:49:00", "max_grad_norm": 1.0, "loss": 0.830280601978302, "grad_norm": 0.3706159293651581, "learning_rate": 0.00019695056702082717}
-{"ts": "2025-12-27T02:54:07", "event": "train_log", "step": 2172, "epoch": 0.9164556962025316, "progress_pct": 15.27, "epoch_pct": 15.27, "eta": "47:47:27", "max_grad_norm": 1.0, "loss": 0.7297167778015137, "grad_norm": 0.3873467445373535, "learning_rate": 0.00019693878536671452}
-{"ts": "2025-12-27T02:54:22", "event": "train_log", "step": 2174, "epoch": 0.9172995780590717, "progress_pct": 15.29, "epoch_pct": 15.29, "eta": "47:45:47", "max_grad_norm": 1.0, "loss": 0.7924292087554932, "grad_norm": 0.42876651883125305, "learning_rate": 0.00019692698135068582}
-{"ts": "2025-12-27T02:54:38", "event": "train_log", "step": 2176, "epoch": 0.9181434599156119, "progress_pct": 15.3, "epoch_pct": 15.3, "eta": "47:44:05", "max_grad_norm": 1.0, "loss": 0.8098247051239014, "grad_norm": 0.4259159564971924, "learning_rate": 0.00019691515497546406}
-{"ts": "2025-12-27T02:54:54", "event": "train_log", "step": 2178, "epoch": 0.9189873417721519, "progress_pct": 15.32, "epoch_pct": 15.32, "eta": "47:42:29", "max_grad_norm": 1.0, "loss": 0.6789063215255737, "grad_norm": 0.38152721524238586, "learning_rate": 0.00019690330624377728}
-{"ts": "2025-12-27T02:55:11", "event": "train_log", "step": 2180, "epoch": 0.919831223628692, "progress_pct": 15.33, "epoch_pct": 15.33, "eta": "47:40:54", "max_grad_norm": 1.0, "loss": 0.8582620620727539, "grad_norm": 0.4135437607765198, "learning_rate": 0.00019689143515835887}
-{"ts": "2025-12-27T02:55:28", "event": "train_log", "step": 2182, "epoch": 0.920675105485232, "progress_pct": 15.34, "epoch_pct": 15.34, "eta": "47:39:23", "max_grad_norm": 1.0, "loss": 0.8059743642807007, "grad_norm": 0.3818798065185547, "learning_rate": 0.0001968795417219472}
-{"ts": "2025-12-27T02:55:46", "event": "train_log", "step": 2184, "epoch": 0.9215189873417722, "progress_pct": 15.36, "epoch_pct": 15.36, "eta": "47:37:56", "max_grad_norm": 1.0, "loss": 0.7432259917259216, "grad_norm": 0.39021286368370056, "learning_rate": 0.00019686762593728582}
-{"ts": "2025-12-27T02:56:02", "event": "train_log", "step": 2186, "epoch": 0.9223628691983122, "progress_pct": 15.37, "epoch_pct": 15.37, "eta": "47:36:22", "max_grad_norm": 1.0, "loss": 0.7561086416244507, "grad_norm": 0.37864068150520325, "learning_rate": 0.00019685568780712355}
-{"ts": "2025-12-27T02:56:18", "event": "train_log", "step": 2188, "epoch": 0.9232067510548523, "progress_pct": 15.39, "epoch_pct": 15.39, "eta": "47:34:44", "max_grad_norm": 1.0, "loss": 0.7552722692489624, "grad_norm": 0.450847864151001, "learning_rate": 0.00019684372733421425}
-{"ts": "2025-12-27T02:56:34", "event": "train_log", "step": 2190, "epoch": 0.9240506329113924, "progress_pct": 15.4, "epoch_pct": 15.4, "eta": "47:33:07", "max_grad_norm": 1.0, "loss": 0.6905336380004883, "grad_norm": 0.37909507751464844, "learning_rate": 0.00019683174452131695}
-{"ts": "2025-12-27T02:56:49", "event": "train_log", "step": 2192, "epoch": 0.9248945147679325, "progress_pct": 15.41, "epoch_pct": 15.41, "eta": "47:31:28", "max_grad_norm": 1.0, "loss": 0.7710593938827515, "grad_norm": 0.4439173638820648, "learning_rate": 0.0001968197393711959}
-{"ts": "2025-12-27T02:57:05", "event": "train_log", "step": 2194, "epoch": 0.9257383966244725, "progress_pct": 15.43, "epoch_pct": 15.43, "eta": "47:29:48", "max_grad_norm": 1.0, "loss": 0.8212814331054688, "grad_norm": 0.3908376395702362, "learning_rate": 0.00019680771188662044}
-{"ts": "2025-12-27T02:57:21", "event": "train_log", "step": 2196, "epoch": 0.9265822784810127, "progress_pct": 15.44, "epoch_pct": 15.44, "eta": "47:28:11", "max_grad_norm": 1.0, "loss": 0.751355767250061, "grad_norm": 0.3528299033641815, "learning_rate": 0.00019679566207036507}
-{"ts": "2025-12-27T02:57:35", "event": "train_log", "step": 2198, "epoch": 0.9274261603375528, "progress_pct": 15.46, "epoch_pct": 15.46, "eta": "47:26:26", "max_grad_norm": 1.0, "loss": 0.8204057812690735, "grad_norm": 0.4351397156715393, "learning_rate": 0.00019678358992520945}
-{"ts": "2025-12-27T02:57:51", "event": "train_log", "step": 2200, "epoch": 0.9282700421940928, "progress_pct": 15.47, "epoch_pct": 15.47, "eta": "47:24:48", "max_grad_norm": 1.0, "loss": 0.763841450214386, "grad_norm": 0.45566943287849426, "learning_rate": 0.0001967714954539384}
-{"ts": "2025-12-27T03:09:05", "event": "train_log", "step": 2200, "epoch": 0.9282700421940928, "progress_pct": 15.47, "epoch_pct": 15.47, "eta": "48:26:13", "max_grad_norm": 1.0, "eval_loss": 0.8336610198020935, "eval_runtime": 674.5134, "eval_samples_per_second": 3.124, "eval_steps_per_second": 3.124}
-{"ts": "2025-12-27T03:09:20", "event": "train_log", "step": 2202, "epoch": 0.9291139240506329, "progress_pct": 15.49, "epoch_pct": 15.49, "eta": "48:24:27", "max_grad_norm": 1.0, "loss": 0.861711323261261, "grad_norm": 0.4516221284866333, "learning_rate": 0.00019675937865934188}
-{"ts": "2025-12-27T03:09:36", "event": "train_log", "step": 2204, "epoch": 0.929957805907173, "progress_pct": 15.5, "epoch_pct": 15.5, "eta": "48:22:43", "max_grad_norm": 1.0, "loss": 0.8062718510627747, "grad_norm": 0.43421855568885803, "learning_rate": 0.00019674723954421502}
-{"ts": "2025-12-27T03:09:50", "event": "train_log", "step": 2206, "epoch": 0.9308016877637131, "progress_pct": 15.51, "epoch_pct": 15.51, "eta": "48:20:57", "max_grad_norm": 1.0, "loss": 0.8069695234298706, "grad_norm": 0.42442476749420166, "learning_rate": 0.00019673507811135803}
-{"ts": "2025-12-27T03:10:06", "event": "train_log", "step": 2208, "epoch": 0.9316455696202531, "progress_pct": 15.53, "epoch_pct": 15.53, "eta": "48:19:13", "max_grad_norm": 1.0, "loss": 0.7336108684539795, "grad_norm": 0.3976045250892639, "learning_rate": 0.00019672289436357637}
-{"ts": "2025-12-27T03:10:20", "event": "train_log", "step": 2210, "epoch": 0.9324894514767933, "progress_pct": 15.54, "epoch_pct": 15.54, "eta": "48:17:25", "max_grad_norm": 1.0, "loss": 0.7559890151023865, "grad_norm": 0.4131270945072174, "learning_rate": 0.00019671068830368058}
-{"ts": "2025-12-27T03:10:35", "event": "train_log", "step": 2212, "epoch": 0.9333333333333333, "progress_pct": 15.56, "epoch_pct": 15.56, "eta": "48:15:41", "max_grad_norm": 1.0, "loss": 0.8447075486183167, "grad_norm": 0.4599294364452362, "learning_rate": 0.00019669845993448634}
-{"ts": "2025-12-27T03:10:50", "event": "train_log", "step": 2214, "epoch": 0.9341772151898734, "progress_pct": 15.57, "epoch_pct": 15.57, "eta": "48:13:58", "max_grad_norm": 1.0, "loss": 0.8329233527183533, "grad_norm": 0.4291204810142517, "learning_rate": 0.00019668620925881455}
-{"ts": "2025-12-27T03:11:07", "event": "train_log", "step": 2216, "epoch": 0.9350210970464135, "progress_pct": 15.58, "epoch_pct": 15.58, "eta": "48:12:20", "max_grad_norm": 1.0, "loss": 0.749232292175293, "grad_norm": 0.4226539731025696, "learning_rate": 0.00019667393627949116}
-{"ts": "2025-12-27T03:11:22", "event": "train_log", "step": 2218, "epoch": 0.9358649789029536, "progress_pct": 15.6, "epoch_pct": 15.6, "eta": "48:10:38", "max_grad_norm": 1.0, "loss": 0.7470011115074158, "grad_norm": 0.4159580171108246, "learning_rate": 0.00019666164099934732}
-{"ts": "2025-12-27T03:11:37", "event": "train_log", "step": 2220, "epoch": 0.9367088607594937, "progress_pct": 15.61, "epoch_pct": 15.61, "eta": "48:08:51", "max_grad_norm": 1.0, "loss": 0.8094202280044556, "grad_norm": 0.4160766303539276, "learning_rate": 0.00019664932342121935}
-{"ts": "2025-12-27T03:11:52", "event": "train_log", "step": 2222, "epoch": 0.9375527426160337, "progress_pct": 15.63, "epoch_pct": 15.63, "eta": "48:07:10", "max_grad_norm": 1.0, "loss": 0.8398169875144958, "grad_norm": 0.45284298062324524, "learning_rate": 0.00019663698354794863}
-{"ts": "2025-12-27T03:12:07", "event": "train_log", "step": 2224, "epoch": 0.9383966244725739, "progress_pct": 15.64, "epoch_pct": 15.64, "eta": "48:05:24", "max_grad_norm": 1.0, "loss": 0.7652443051338196, "grad_norm": 0.3960540294647217, "learning_rate": 0.00019662462138238178}
-{"ts": "2025-12-27T03:12:21", "event": "train_log", "step": 2226, "epoch": 0.9392405063291139, "progress_pct": 15.65, "epoch_pct": 15.65, "eta": "48:03:39", "max_grad_norm": 1.0, "loss": 0.7909489870071411, "grad_norm": 0.4269275367259979, "learning_rate": 0.00019661223692737047}
-{"ts": "2025-12-27T03:12:37", "event": "train_log", "step": 2228, "epoch": 0.940084388185654, "progress_pct": 15.67, "epoch_pct": 15.67, "eta": "48:02:00", "max_grad_norm": 1.0, "loss": 0.7821935415267944, "grad_norm": 0.38187873363494873, "learning_rate": 0.00019659983018577157}
-{"ts": "2025-12-27T03:12:52", "event": "train_log", "step": 2230, "epoch": 0.9409282700421941, "progress_pct": 15.68, "epoch_pct": 15.68, "eta": "48:00:17", "max_grad_norm": 1.0, "loss": 0.7792721390724182, "grad_norm": 0.45898866653442383, "learning_rate": 0.0001965874011604471}
-{"ts": "2025-12-27T03:13:06", "event": "train_log", "step": 2232, "epoch": 0.9417721518987342, "progress_pct": 15.7, "epoch_pct": 15.7, "eta": "47:58:30", "max_grad_norm": 1.0, "loss": 0.885725200176239, "grad_norm": 0.4740699827671051, "learning_rate": 0.00019657494985426418}
-{"ts": "2025-12-27T03:13:21", "event": "train_log", "step": 2234, "epoch": 0.9426160337552743, "progress_pct": 15.71, "epoch_pct": 15.71, "eta": "47:56:46", "max_grad_norm": 1.0, "loss": 0.7898101806640625, "grad_norm": 0.3912813365459442, "learning_rate": 0.00019656247627009506}
-{"ts": "2025-12-27T03:13:36", "event": "train_log", "step": 2236, "epoch": 0.9434599156118143, "progress_pct": 15.72, "epoch_pct": 15.72, "eta": "47:55:03", "max_grad_norm": 1.0, "loss": 0.8646330833435059, "grad_norm": 0.4552418291568756, "learning_rate": 0.0001965499804108172}
-{"ts": "2025-12-27T03:13:51", "event": "train_log", "step": 2238, "epoch": 0.9443037974683545, "progress_pct": 15.74, "epoch_pct": 15.74, "eta": "47:53:17", "max_grad_norm": 1.0, "loss": 0.8068296313285828, "grad_norm": 0.4178548753261566, "learning_rate": 0.0001965374622793131}
-{"ts": "2025-12-27T03:14:06", "event": "train_log", "step": 2240, "epoch": 0.9451476793248945, "progress_pct": 15.75, "epoch_pct": 15.75, "eta": "47:51:36", "max_grad_norm": 1.0, "loss": 0.7953271865844727, "grad_norm": 0.38649076223373413, "learning_rate": 0.00019652492187847057}
-{"ts": "2025-12-27T03:14:20", "event": "train_log", "step": 2242, "epoch": 0.9459915611814346, "progress_pct": 15.77, "epoch_pct": 15.77, "eta": "47:49:49", "max_grad_norm": 1.0, "loss": 0.8423402309417725, "grad_norm": 0.39785075187683105, "learning_rate": 0.0001965123592111823}
-{"ts": "2025-12-27T03:14:35", "event": "train_log", "step": 2244, "epoch": 0.9468354430379747, "progress_pct": 15.78, "epoch_pct": 15.78, "eta": "47:48:06", "max_grad_norm": 1.0, "loss": 0.8883589506149292, "grad_norm": 0.47455263137817383, "learning_rate": 0.00019649977428034632}
-{"ts": "2025-12-27T03:14:50", "event": "train_log", "step": 2246, "epoch": 0.9476793248945148, "progress_pct": 15.79, "epoch_pct": 15.79, "eta": "47:46:26", "max_grad_norm": 1.0, "loss": 0.7232863903045654, "grad_norm": 0.3866841197013855, "learning_rate": 0.0001964871670888657}
-{"ts": "2025-12-27T03:15:06", "event": "train_log", "step": 2248, "epoch": 0.9485232067510548, "progress_pct": 15.81, "epoch_pct": 15.81, "eta": "47:44:47", "max_grad_norm": 1.0, "loss": 0.7265347838401794, "grad_norm": 0.3950609564781189, "learning_rate": 0.00019647453763964876}
-{"ts": "2025-12-27T03:15:21", "event": "train_log", "step": 2250, "epoch": 0.9493670886075949, "progress_pct": 15.82, "epoch_pct": 15.82, "eta": "47:43:04", "max_grad_norm": 1.0, "loss": 0.8000131249427795, "grad_norm": 0.4315829575061798, "learning_rate": 0.0001964618859356088}
-{"ts": "2025-12-27T03:15:37", "event": "train_log", "step": 2252, "epoch": 0.950210970464135, "progress_pct": 15.84, "epoch_pct": 15.84, "eta": "47:41:30", "max_grad_norm": 1.0, "loss": 0.823086678981781, "grad_norm": 0.403984934091568, "learning_rate": 0.00019644921197966433}
-{"ts": "2025-12-27T03:15:53", "event": "train_log", "step": 2254, "epoch": 0.9510548523206751, "progress_pct": 15.85, "epoch_pct": 15.85, "eta": "47:39:52", "max_grad_norm": 1.0, "loss": 0.8457553386688232, "grad_norm": 0.4311080574989319, "learning_rate": 0.00019643651577473897}
-{"ts": "2025-12-27T03:16:09", "event": "train_log", "step": 2256, "epoch": 0.9518987341772152, "progress_pct": 15.86, "epoch_pct": 15.86, "eta": "47:38:20", "max_grad_norm": 1.0, "loss": 0.7866189479827881, "grad_norm": 0.3884856104850769, "learning_rate": 0.00019642379732376158}
-{"ts": "2025-12-27T03:16:25", "event": "train_log", "step": 2258, "epoch": 0.9527426160337553, "progress_pct": 15.88, "epoch_pct": 15.88, "eta": "47:36:43", "max_grad_norm": 1.0, "loss": 0.7095813751220703, "grad_norm": 0.3384067714214325, "learning_rate": 0.00019641105662966595}
-{"ts": "2025-12-27T03:16:41", "event": "train_log", "step": 2260, "epoch": 0.9535864978902954, "progress_pct": 15.89, "epoch_pct": 15.89, "eta": "47:35:06", "max_grad_norm": 1.0, "loss": 0.8271632194519043, "grad_norm": 0.40426746010780334, "learning_rate": 0.00019639829369539117}
-{"ts": "2025-12-27T03:16:57", "event": "train_log", "step": 2262, "epoch": 0.9544303797468354, "progress_pct": 15.91, "epoch_pct": 15.91, "eta": "47:33:30", "max_grad_norm": 1.0, "loss": 0.8204861283302307, "grad_norm": 0.45495131611824036, "learning_rate": 0.00019638550852388144}
-{"ts": "2025-12-27T03:17:12", "event": "train_log", "step": 2264, "epoch": 0.9552742616033755, "progress_pct": 15.92, "epoch_pct": 15.92, "eta": "47:31:50", "max_grad_norm": 1.0, "loss": 0.884763777256012, "grad_norm": 0.47201067209243774, "learning_rate": 0.00019637270111808598}
-{"ts": "2025-12-27T03:17:27", "event": "train_log", "step": 2266, "epoch": 0.9561181434599156, "progress_pct": 15.94, "epoch_pct": 15.94, "eta": "47:30:13", "max_grad_norm": 1.0, "loss": 0.7630926370620728, "grad_norm": 0.3959396779537201, "learning_rate": 0.0001963598714809592}
-{"ts": "2025-12-27T03:17:43", "event": "train_log", "step": 2268, "epoch": 0.9569620253164557, "progress_pct": 15.95, "epoch_pct": 15.95, "eta": "47:28:36", "max_grad_norm": 1.0, "loss": 0.797870397567749, "grad_norm": 0.4197136461734772, "learning_rate": 0.00019634701961546077}
-{"ts": "2025-12-27T03:17:58", "event": "train_log", "step": 2270, "epoch": 0.9578059071729957, "progress_pct": 15.96, "epoch_pct": 15.96, "eta": "47:26:55", "max_grad_norm": 1.0, "loss": 0.7755846977233887, "grad_norm": 0.381290078163147, "learning_rate": 0.00019633414552455526}
-{"ts": "2025-12-27T03:18:13", "event": "train_log", "step": 2272, "epoch": 0.9586497890295359, "progress_pct": 15.98, "epoch_pct": 15.98, "eta": "47:25:15", "max_grad_norm": 1.0, "loss": 0.7553264498710632, "grad_norm": 0.3868124783039093, "learning_rate": 0.00019632124921121255}
-{"ts": "2025-12-27T03:18:29", "event": "train_log", "step": 2274, "epoch": 0.959493670886076, "progress_pct": 15.99, "epoch_pct": 15.99, "eta": "47:23:39", "max_grad_norm": 1.0, "loss": 0.7792160511016846, "grad_norm": 0.4350631833076477, "learning_rate": 0.00019630833067840747}
-{"ts": "2025-12-27T03:18:44", "event": "train_log", "step": 2276, "epoch": 0.960337552742616, "progress_pct": 16.01, "epoch_pct": 16.01, "eta": "47:22:01", "max_grad_norm": 1.0, "loss": 0.878220796585083, "grad_norm": 0.4717157781124115, "learning_rate": 0.00019629538992912016}
-{"ts": "2025-12-27T03:18:59", "event": "train_log", "step": 2278, "epoch": 0.9611814345991562, "progress_pct": 16.02, "epoch_pct": 16.02, "eta": "47:20:21", "max_grad_norm": 1.0, "loss": 0.8891014456748962, "grad_norm": 0.45545122027397156, "learning_rate": 0.00019628242696633584}
-{"ts": "2025-12-27T03:19:15", "event": "train_log", "step": 2280, "epoch": 0.9620253164556962, "progress_pct": 16.03, "epoch_pct": 16.03, "eta": "47:18:45", "max_grad_norm": 1.0, "loss": 0.8024723529815674, "grad_norm": 0.4421025514602661, "learning_rate": 0.00019626944179304467}
-{"ts": "2025-12-27T03:19:30", "event": "train_log", "step": 2282, "epoch": 0.9628691983122363, "progress_pct": 16.05, "epoch_pct": 16.05, "eta": "47:17:08", "max_grad_norm": 1.0, "loss": 0.8036280274391174, "grad_norm": 0.40385812520980835, "learning_rate": 0.00019625643441224222}
-{"ts": "2025-12-27T03:19:47", "event": "train_log", "step": 2284, "epoch": 0.9637130801687763, "progress_pct": 16.06, "epoch_pct": 16.06, "eta": "47:15:40", "max_grad_norm": 1.0, "loss": 0.8072395324707031, "grad_norm": 0.3866552412509918, "learning_rate": 0.00019624340482692898}
-{"ts": "2025-12-27T03:20:03", "event": "train_log", "step": 2286, "epoch": 0.9645569620253165, "progress_pct": 16.08, "epoch_pct": 16.08, "eta": "47:14:06", "max_grad_norm": 1.0, "loss": 0.8046114444732666, "grad_norm": 0.4113233685493469, "learning_rate": 0.0001962303530401106}
-{"ts": "2025-12-27T03:20:18", "event": "train_log", "step": 2288, "epoch": 0.9654008438818565, "progress_pct": 16.09, "epoch_pct": 16.09, "eta": "47:12:28", "max_grad_norm": 1.0, "loss": 0.8434037566184998, "grad_norm": 0.40720227360725403, "learning_rate": 0.00019621727905479798}
-{"ts": "2025-12-27T03:20:35", "event": "train_log", "step": 2290, "epoch": 0.9662447257383966, "progress_pct": 16.1, "epoch_pct": 16.1, "eta": "47:10:57", "max_grad_norm": 1.0, "loss": 0.7832419276237488, "grad_norm": 0.35759273171424866, "learning_rate": 0.00019620418287400693}
-{"ts": "2025-12-27T03:20:50", "event": "train_log", "step": 2292, "epoch": 0.9670886075949368, "progress_pct": 16.12, "epoch_pct": 16.12, "eta": "47:09:20", "max_grad_norm": 1.0, "loss": 0.7975693345069885, "grad_norm": 0.4170442223548889, "learning_rate": 0.0001961910645007585}
-{"ts": "2025-12-27T03:21:06", "event": "train_log", "step": 2294, "epoch": 0.9679324894514768, "progress_pct": 16.13, "epoch_pct": 16.13, "eta": "47:07:45", "max_grad_norm": 1.0, "loss": 0.8554494976997375, "grad_norm": 0.4126700162887573, "learning_rate": 0.00019617792393807895}
-{"ts": "2025-12-27T03:21:21", "event": "train_log", "step": 2296, "epoch": 0.9687763713080169, "progress_pct": 16.15, "epoch_pct": 16.15, "eta": "47:06:09", "max_grad_norm": 1.0, "loss": 0.824539065361023, "grad_norm": 0.4231695830821991, "learning_rate": 0.00019616476118899942}
-{"ts": "2025-12-27T03:21:37", "event": "train_log", "step": 2298, "epoch": 0.9696202531645569, "progress_pct": 16.16, "epoch_pct": 16.16, "eta": "47:04:35", "max_grad_norm": 1.0, "loss": 0.7008040547370911, "grad_norm": 0.3556209206581116, "learning_rate": 0.0001961515762565564}
-{"ts": "2025-12-27T03:21:53", "event": "train_log", "step": 2300, "epoch": 0.9704641350210971, "progress_pct": 16.17, "epoch_pct": 16.17, "eta": "47:02:59", "max_grad_norm": 1.0, "loss": 0.8192558288574219, "grad_norm": 0.4370400309562683, "learning_rate": 0.00019613836914379132}
-{"ts": "2025-12-27T03:33:21", "event": "train_log", "step": 2300, "epoch": 0.9704641350210971, "progress_pct": 16.17, "epoch_pct": 16.17, "eta": "48:02:28", "max_grad_norm": 1.0, "eval_loss": 0.8281980156898499, "eval_runtime": 688.6136, "eval_samples_per_second": 3.06, "eval_steps_per_second": 3.06}
-{"ts": "2025-12-27T03:33:36", "event": "train_log", "step": 2302, "epoch": 0.9713080168776371, "progress_pct": 16.19, "epoch_pct": 16.19, "eta": "48:00:45", "max_grad_norm": 1.0, "loss": 0.878928005695343, "grad_norm": 0.4207614064216614, "learning_rate": 0.00019612513985375088}
-{"ts": "2025-12-27T03:33:51", "event": "train_log", "step": 2304, "epoch": 0.9721518987341772, "progress_pct": 16.2, "epoch_pct": 16.2, "eta": "47:59:07", "max_grad_norm": 1.0, "loss": 0.736182689666748, "grad_norm": 0.37607815861701965, "learning_rate": 0.0001961118883894868}
-{"ts": "2025-12-27T03:34:06", "event": "train_log", "step": 2306, "epoch": 0.9729957805907173, "progress_pct": 16.22, "epoch_pct": 16.22, "eta": "47:57:24", "max_grad_norm": 1.0, "loss": 0.8403618335723877, "grad_norm": 0.43311476707458496, "learning_rate": 0.00019609861475405592}
-{"ts": "2025-12-27T03:34:21", "event": "train_log", "step": 2308, "epoch": 0.9738396624472574, "progress_pct": 16.23, "epoch_pct": 16.23, "eta": "47:55:44", "max_grad_norm": 1.0, "loss": 0.8414564728736877, "grad_norm": 0.4533176124095917, "learning_rate": 0.00019608531895052021}
-{"ts": "2025-12-27T03:34:37", "event": "train_log", "step": 2310, "epoch": 0.9746835443037974, "progress_pct": 16.24, "epoch_pct": 16.24, "eta": "47:54:04", "max_grad_norm": 1.0, "loss": 0.8105775117874146, "grad_norm": 0.4025697410106659, "learning_rate": 0.00019607200098194677}
-{"ts": "2025-12-27T03:34:51", "event": "train_log", "step": 2312, "epoch": 0.9755274261603376, "progress_pct": 16.26, "epoch_pct": 16.26, "eta": "47:52:22", "max_grad_norm": 1.0, "loss": 0.8053821325302124, "grad_norm": 0.37894198298454285, "learning_rate": 0.00019605866085140784}
-{"ts": "2025-12-27T03:35:06", "event": "train_log", "step": 2314, "epoch": 0.9763713080168777, "progress_pct": 16.27, "epoch_pct": 16.27, "eta": "47:50:41", "max_grad_norm": 1.0, "loss": 0.8092884421348572, "grad_norm": 0.46265891194343567, "learning_rate": 0.0001960452985619807}
-{"ts": "2025-12-27T03:35:21", "event": "train_log", "step": 2316, "epoch": 0.9772151898734177, "progress_pct": 16.29, "epoch_pct": 16.29, "eta": "47:48:59", "max_grad_norm": 1.0, "loss": 0.7456095218658447, "grad_norm": 0.3770054280757904, "learning_rate": 0.0001960319141167477}
-{"ts": "2025-12-27T03:35:35", "event": "train_log", "step": 2318, "epoch": 0.9780590717299578, "progress_pct": 16.3, "epoch_pct": 16.3, "eta": "47:47:15", "max_grad_norm": 1.0, "loss": 0.7739883661270142, "grad_norm": 0.44084450602531433, "learning_rate": 0.0001960185075187965}
-{"ts": "2025-12-27T03:35:51", "event": "train_log", "step": 2320, "epoch": 0.9789029535864979, "progress_pct": 16.32, "epoch_pct": 16.32, "eta": "47:45:37", "max_grad_norm": 1.0, "loss": 0.6961302757263184, "grad_norm": 0.3880341351032257, "learning_rate": 0.00019600507877121965}
-{"ts": "2025-12-27T03:36:05", "event": "train_log", "step": 2322, "epoch": 0.979746835443038, "progress_pct": 16.33, "epoch_pct": 16.33, "eta": "47:43:54", "max_grad_norm": 1.0, "loss": 0.8447984457015991, "grad_norm": 0.468037486076355, "learning_rate": 0.00019599162787711495}
-{"ts": "2025-12-27T03:36:20", "event": "train_log", "step": 2324, "epoch": 0.980590717299578, "progress_pct": 16.34, "epoch_pct": 16.34, "eta": "47:42:14", "max_grad_norm": 1.0, "loss": 0.8155615329742432, "grad_norm": 0.4123631417751312, "learning_rate": 0.00019597815483958527}
-{"ts": "2025-12-27T03:36:35", "event": "train_log", "step": 2326, "epoch": 0.9814345991561182, "progress_pct": 16.36, "epoch_pct": 16.36, "eta": "47:40:34", "max_grad_norm": 1.0, "loss": 0.7990952730178833, "grad_norm": 0.3827875554561615, "learning_rate": 0.00019596465966173853}
-{"ts": "2025-12-27T03:36:50", "event": "train_log", "step": 2328, "epoch": 0.9822784810126582, "progress_pct": 16.37, "epoch_pct": 16.37, "eta": "47:38:52", "max_grad_norm": 1.0, "loss": 0.8899750709533691, "grad_norm": 0.4644222557544708, "learning_rate": 0.00019595114234668788}
-{"ts": "2025-12-27T03:37:04", "event": "train_log", "step": 2330, "epoch": 0.9831223628691983, "progress_pct": 16.39, "epoch_pct": 16.39, "eta": "47:37:10", "max_grad_norm": 1.0, "loss": 0.7863160371780396, "grad_norm": 0.43699249625205994, "learning_rate": 0.00019593760289755144}
-{"ts": "2025-12-27T03:37:19", "event": "train_log", "step": 2332, "epoch": 0.9839662447257383, "progress_pct": 16.4, "epoch_pct": 16.4, "eta": "47:35:27", "max_grad_norm": 1.0, "loss": 0.7960637807846069, "grad_norm": 0.40713244676589966, "learning_rate": 0.00019592404131745254}
-{"ts": "2025-12-27T03:37:34", "event": "train_log", "step": 2334, "epoch": 0.9848101265822785, "progress_pct": 16.41, "epoch_pct": 16.41, "eta": "47:33:52", "max_grad_norm": 1.0, "loss": 0.714144229888916, "grad_norm": 0.37364068627357483, "learning_rate": 0.00019591045760951957}
-{"ts": "2025-12-27T03:37:50", "event": "train_log", "step": 2336, "epoch": 0.9856540084388186, "progress_pct": 16.43, "epoch_pct": 16.43, "eta": "47:32:14", "max_grad_norm": 1.0, "loss": 0.7311791777610779, "grad_norm": 0.4094736576080322, "learning_rate": 0.00019589685177688599}
-{"ts": "2025-12-27T03:38:05", "event": "train_log", "step": 2338, "epoch": 0.9864978902953586, "progress_pct": 16.44, "epoch_pct": 16.44, "eta": "47:30:36", "max_grad_norm": 1.0, "loss": 0.8191342353820801, "grad_norm": 0.4275180697441101, "learning_rate": 0.0001958832238226905}
-{"ts": "2025-12-27T03:38:20", "event": "train_log", "step": 2340, "epoch": 0.9873417721518988, "progress_pct": 16.46, "epoch_pct": 16.46, "eta": "47:28:56", "max_grad_norm": 1.0, "loss": 0.7476106286048889, "grad_norm": 0.4627651274204254, "learning_rate": 0.00019586957375007668}
-{"ts": "2025-12-27T03:38:34", "event": "train_log", "step": 2342, "epoch": 0.9881856540084388, "progress_pct": 16.47, "epoch_pct": 16.47, "eta": "47:27:13", "max_grad_norm": 1.0, "loss": 0.8257967233657837, "grad_norm": 0.44676414132118225, "learning_rate": 0.00019585590156219346}
-{"ts": "2025-12-27T03:38:49", "event": "train_log", "step": 2344, "epoch": 0.9890295358649789, "progress_pct": 16.48, "epoch_pct": 16.48, "eta": "47:25:38", "max_grad_norm": 1.0, "loss": 0.7922079563140869, "grad_norm": 0.40667134523391724, "learning_rate": 0.00019584220726219466}
-{"ts": "2025-12-27T03:39:04", "event": "train_log", "step": 2346, "epoch": 0.9898734177215189, "progress_pct": 16.5, "epoch_pct": 16.5, "eta": "47:23:59", "max_grad_norm": 1.0, "loss": 0.7892434597015381, "grad_norm": 0.40865346789360046, "learning_rate": 0.00019582849085323934}
-{"ts": "2025-12-27T03:39:18", "event": "train_log", "step": 2348, "epoch": 0.9907172995780591, "progress_pct": 16.51, "epoch_pct": 16.51, "eta": "47:22:16", "max_grad_norm": 1.0, "loss": 0.8766644597053528, "grad_norm": 0.43309709429740906, "learning_rate": 0.00019581475233849163}
-{"ts": "2025-12-27T03:39:34", "event": "train_log", "step": 2350, "epoch": 0.9915611814345991, "progress_pct": 16.53, "epoch_pct": 16.53, "eta": "47:20:40", "max_grad_norm": 1.0, "loss": 0.9183312058448792, "grad_norm": 0.41558781266212463, "learning_rate": 0.00019580099172112069}
-{"ts": "2025-12-27T03:39:48", "event": "train_log", "step": 2352, "epoch": 0.9924050632911392, "progress_pct": 16.54, "epoch_pct": 16.54, "eta": "47:18:59", "max_grad_norm": 1.0, "loss": 0.7905668020248413, "grad_norm": 0.432748019695282, "learning_rate": 0.00019578720900430082}
-{"ts": "2025-12-27T03:40:03", "event": "train_log", "step": 2354, "epoch": 0.9932489451476794, "progress_pct": 16.55, "epoch_pct": 16.55, "eta": "47:17:19", "max_grad_norm": 1.0, "loss": 0.8279712200164795, "grad_norm": 0.4116985499858856, "learning_rate": 0.0001957734041912115}
-{"ts": "2025-12-27T03:40:17", "event": "train_log", "step": 2356, "epoch": 0.9940928270042194, "progress_pct": 16.57, "epoch_pct": 16.57, "eta": "47:15:41", "max_grad_norm": 1.0, "loss": 0.7451362609863281, "grad_norm": 0.3927275240421295, "learning_rate": 0.00019575957728503718}
-{"ts": "2025-12-27T03:40:33", "event": "train_log", "step": 2358, "epoch": 0.9949367088607595, "progress_pct": 16.58, "epoch_pct": 16.58, "eta": "47:14:07", "max_grad_norm": 1.0, "loss": 0.6769390106201172, "grad_norm": 0.3389509320259094, "learning_rate": 0.0001957457282889675}
-{"ts": "2025-12-27T03:40:49", "event": "train_log", "step": 2360, "epoch": 0.9957805907172996, "progress_pct": 16.6, "epoch_pct": 16.6, "eta": "47:12:31", "max_grad_norm": 1.0, "loss": 0.7590897083282471, "grad_norm": 0.4220774471759796, "learning_rate": 0.00019573185720619712}
-{"ts": "2025-12-27T03:41:03", "event": "train_log", "step": 2362, "epoch": 0.9966244725738397, "progress_pct": 16.61, "epoch_pct": 16.61, "eta": "47:10:53", "max_grad_norm": 1.0, "loss": 0.8301284313201904, "grad_norm": 0.4299897849559784, "learning_rate": 0.00019571796403992583}
-{"ts": "2025-12-27T03:41:19", "event": "train_log", "step": 2364, "epoch": 0.9974683544303797, "progress_pct": 16.62, "epoch_pct": 16.62, "eta": "47:09:19", "max_grad_norm": 1.0, "loss": 0.8019471764564514, "grad_norm": 0.4031789302825928, "learning_rate": 0.00019570404879335856}
-{"ts": "2025-12-27T03:41:34", "event": "train_log", "step": 2366, "epoch": 0.9983122362869198, "progress_pct": 16.64, "epoch_pct": 16.64, "eta": "47:07:42", "max_grad_norm": 1.0, "loss": 0.7427027821540833, "grad_norm": 0.3957567811012268, "learning_rate": 0.00019569011146970526}
-{"ts": "2025-12-27T03:41:49", "event": "train_log", "step": 2368, "epoch": 0.99915611814346, "progress_pct": 16.65, "epoch_pct": 16.65, "eta": "47:06:04", "max_grad_norm": 1.0, "loss": 0.8221617341041565, "grad_norm": 0.41741347312927246, "learning_rate": 0.000195676152072181}
-{"ts": "2025-12-27T03:42:03", "event": "train_log", "step": 2370, "epoch": 1.0, "progress_pct": 16.67, "epoch_pct": 16.67, "eta": "47:04:25", "max_grad_norm": 1.0, "loss": 0.8143455982208252, "grad_norm": 0.47121551632881165, "learning_rate": 0.00019566217060400595}
-{"ts": "2025-12-27T03:42:18", "event": "train_log", "step": 2372, "epoch": 1.0008438818565402, "progress_pct": 16.68, "epoch_pct": 16.68, "eta": "47:02:48", "max_grad_norm": 1.0, "loss": 0.6971694231033325, "grad_norm": 0.3854716122150421, "learning_rate": 0.0001956481670684054}
-{"ts": "2025-12-27T03:42:33", "event": "train_log", "step": 2374, "epoch": 1.00168776371308, "progress_pct": 16.69, "epoch_pct": 16.69, "eta": "47:01:13", "max_grad_norm": 1.0, "loss": 0.6719155311584473, "grad_norm": 0.4029138386249542, "learning_rate": 0.00019563414146860964}
-{"ts": "2025-12-27T03:42:48", "event": "train_log", "step": 2376, "epoch": 1.0025316455696203, "progress_pct": 16.71, "epoch_pct": 16.71, "eta": "46:59:37", "max_grad_norm": 1.0, "loss": 0.7161872386932373, "grad_norm": 0.40136656165122986, "learning_rate": 0.00019562009380785412}
-{"ts": "2025-12-27T03:43:04", "event": "train_log", "step": 2378, "epoch": 1.0033755274261604, "progress_pct": 16.72, "epoch_pct": 16.72, "eta": "46:58:02", "max_grad_norm": 1.0, "loss": 0.71699059009552, "grad_norm": 0.40685850381851196, "learning_rate": 0.0001956060240893794}
-{"ts": "2025-12-27T03:43:18", "event": "train_log", "step": 2380, "epoch": 1.0042194092827004, "progress_pct": 16.74, "epoch_pct": 16.74, "eta": "46:56:25", "max_grad_norm": 1.0, "loss": 0.8030059337615967, "grad_norm": 0.46153366565704346, "learning_rate": 0.00019559193231643104}
-{"ts": "2025-12-27T03:43:33", "event": "train_log", "step": 2382, "epoch": 1.0050632911392405, "progress_pct": 16.75, "epoch_pct": 16.75, "eta": "46:54:46", "max_grad_norm": 1.0, "loss": 0.7666479349136353, "grad_norm": 0.45048823952674866, "learning_rate": 0.0001955778184922598}
-{"ts": "2025-12-27T03:43:47", "event": "train_log", "step": 2384, "epoch": 1.0059071729957807, "progress_pct": 16.77, "epoch_pct": 16.77, "eta": "46:53:07", "max_grad_norm": 1.0, "loss": 0.7481234073638916, "grad_norm": 0.4260413348674774, "learning_rate": 0.00019556368262012142}
-{"ts": "2025-12-27T03:44:02", "event": "train_log", "step": 2386, "epoch": 1.0067510548523206, "progress_pct": 16.78, "epoch_pct": 16.78, "eta": "46:51:31", "max_grad_norm": 1.0, "loss": 0.7943820953369141, "grad_norm": 0.4819575548171997, "learning_rate": 0.0001955495247032768}
-{"ts": "2025-12-27T03:44:18", "event": "train_log", "step": 2388, "epoch": 1.0075949367088608, "progress_pct": 16.79, "epoch_pct": 16.79, "eta": "46:50:01", "max_grad_norm": 1.0, "loss": 0.6401634812355042, "grad_norm": 0.45789605379104614, "learning_rate": 0.0001955353447449919}
-{"ts": "2025-12-27T03:44:33", "event": "train_log", "step": 2390, "epoch": 1.0084388185654007, "progress_pct": 16.81, "epoch_pct": 16.81, "eta": "46:48:26", "max_grad_norm": 1.0, "loss": 0.7058886885643005, "grad_norm": 0.37019097805023193, "learning_rate": 0.00019552114274853778}
-{"ts": "2025-12-27T03:44:48", "event": "train_log", "step": 2392, "epoch": 1.009282700421941, "progress_pct": 16.82, "epoch_pct": 16.82, "eta": "46:46:48", "max_grad_norm": 1.0, "loss": 0.7631242871284485, "grad_norm": 0.44416263699531555, "learning_rate": 0.0001955069187171905}
-{"ts": "2025-12-27T03:45:02", "event": "train_log", "step": 2394, "epoch": 1.010126582278481, "progress_pct": 16.84, "epoch_pct": 16.84, "eta": "46:45:10", "max_grad_norm": 1.0, "loss": 0.7873892784118652, "grad_norm": 0.4478379786014557, "learning_rate": 0.00019549267265423138}
-{"ts": "2025-12-27T03:45:17", "event": "train_log", "step": 2396, "epoch": 1.010970464135021, "progress_pct": 16.85, "epoch_pct": 16.85, "eta": "46:43:35", "max_grad_norm": 1.0, "loss": 0.7882059216499329, "grad_norm": 0.4596130847930908, "learning_rate": 0.00019547840456294658}
-{"ts": "2025-12-27T03:45:33", "event": "train_log", "step": 2398, "epoch": 1.0118143459915612, "progress_pct": 16.86, "epoch_pct": 16.86, "eta": "46:42:03", "max_grad_norm": 1.0, "loss": 0.6358574628829956, "grad_norm": 0.4062999188899994, "learning_rate": 0.0001954641144466276}
-{"ts": "2025-12-27T03:45:47", "event": "train_log", "step": 2400, "epoch": 1.0126582278481013, "progress_pct": 16.88, "epoch_pct": 16.88, "eta": "46:40:24", "max_grad_norm": 1.0, "loss": 0.7803886532783508, "grad_norm": 0.47627049684524536, "learning_rate": 0.0001954498023085708}
-{"ts": "2025-12-27T03:57:18", "event": "train_log", "step": 2400, "epoch": 1.0126582278481013, "progress_pct": 16.88, "epoch_pct": 16.88, "eta": "47:37:10", "max_grad_norm": 1.0, "eval_loss": 0.8250564932823181, "eval_runtime": 691.5833, "eval_samples_per_second": 3.047, "eval_steps_per_second": 3.047}
-{"ts": "2025-12-27T03:57:35", "event": "train_log", "step": 2402, "epoch": 1.0135021097046413, "progress_pct": 16.89, "epoch_pct": 16.89, "eta": "47:35:41", "max_grad_norm": 1.0, "loss": 0.7394700050354004, "grad_norm": 0.40690696239471436, "learning_rate": 0.00019543546815207777}
-{"ts": "2025-12-27T03:57:50", "event": "train_log", "step": 2404, "epoch": 1.0143459915611814, "progress_pct": 16.91, "epoch_pct": 16.91, "eta": "47:34:04", "max_grad_norm": 1.0, "loss": 0.7096555829048157, "grad_norm": 0.45543980598449707, "learning_rate": 0.0001954211119804551}
-{"ts": "2025-12-27T03:58:06", "event": "train_log", "step": 2406, "epoch": 1.0151898734177216, "progress_pct": 16.92, "epoch_pct": 16.92, "eta": "47:32:29", "max_grad_norm": 1.0, "loss": 0.7961843013763428, "grad_norm": 0.4367314279079437, "learning_rate": 0.00019540673379701454}
-{"ts": "2025-12-27T03:58:21", "event": "train_log", "step": 2408, "epoch": 1.0160337552742615, "progress_pct": 16.93, "epoch_pct": 16.93, "eta": "47:30:51", "max_grad_norm": 1.0, "loss": 0.743843138217926, "grad_norm": 0.4458340108394623, "learning_rate": 0.00019539233360507278}
-{"ts": "2025-12-27T03:58:36", "event": "train_log", "step": 2410, "epoch": 1.0168776371308017, "progress_pct": 16.95, "epoch_pct": 16.95, "eta": "47:29:16", "max_grad_norm": 1.0, "loss": 0.7273756265640259, "grad_norm": 0.3741893470287323, "learning_rate": 0.0001953779114079517}
-{"ts": "2025-12-27T03:58:52", "event": "train_log", "step": 2412, "epoch": 1.0177215189873419, "progress_pct": 16.96, "epoch_pct": 16.96, "eta": "47:27:43", "max_grad_norm": 1.0, "loss": 0.7922506928443909, "grad_norm": 0.4340079426765442, "learning_rate": 0.00019536346720897823}
-{"ts": "2025-12-27T03:59:08", "event": "train_log", "step": 2414, "epoch": 1.0185654008438818, "progress_pct": 16.98, "epoch_pct": 16.98, "eta": "47:26:12", "max_grad_norm": 1.0, "loss": 0.6492037773132324, "grad_norm": 0.4518018662929535, "learning_rate": 0.00019534900101148437}
-{"ts": "2025-12-27T03:59:24", "event": "train_log", "step": 2416, "epoch": 1.019409282700422, "progress_pct": 16.99, "epoch_pct": 16.99, "eta": "47:24:37", "max_grad_norm": 1.0, "loss": 0.7422950863838196, "grad_norm": 0.4160727560520172, "learning_rate": 0.00019533451281880716}
-{"ts": "2025-12-27T03:59:41", "event": "train_log", "step": 2418, "epoch": 1.0202531645569621, "progress_pct": 17.0, "epoch_pct": 17.0, "eta": "47:23:11", "max_grad_norm": 1.0, "loss": 0.6489207148551941, "grad_norm": 0.35953211784362793, "learning_rate": 0.00019532000263428883}
-{"ts": "2025-12-27T03:59:58", "event": "train_log", "step": 2420, "epoch": 1.021097046413502, "progress_pct": 17.02, "epoch_pct": 17.02, "eta": "47:21:43", "max_grad_norm": 1.0, "loss": 0.7449417114257812, "grad_norm": 0.38774433732032776, "learning_rate": 0.0001953054704612765}
-{"ts": "2025-12-27T04:00:13", "event": "train_log", "step": 2422, "epoch": 1.0219409282700422, "progress_pct": 17.03, "epoch_pct": 17.03, "eta": "47:20:09", "max_grad_norm": 1.0, "loss": 0.8481494188308716, "grad_norm": 0.48185858130455017, "learning_rate": 0.0001952909163031225}
-{"ts": "2025-12-27T04:00:29", "event": "train_log", "step": 2424, "epoch": 1.0227848101265822, "progress_pct": 17.05, "epoch_pct": 17.05, "eta": "47:18:34", "max_grad_norm": 1.0, "loss": 0.7442291378974915, "grad_norm": 0.4098491072654724, "learning_rate": 0.00019527634016318425}
-{"ts": "2025-12-27T04:00:45", "event": "train_log", "step": 2426, "epoch": 1.0236286919831223, "progress_pct": 17.06, "epoch_pct": 17.06, "eta": "47:17:02", "max_grad_norm": 1.0, "loss": 0.7564480900764465, "grad_norm": 0.41284480690956116, "learning_rate": 0.00019526174204482412}
-{"ts": "2025-12-27T04:01:00", "event": "train_log", "step": 2428, "epoch": 1.0244725738396625, "progress_pct": 17.07, "epoch_pct": 17.07, "eta": "47:15:28", "max_grad_norm": 1.0, "loss": 0.7234854102134705, "grad_norm": 0.44948479533195496, "learning_rate": 0.00019524712195140965}
-{"ts": "2025-12-27T04:01:15", "event": "train_log", "step": 2430, "epoch": 1.0253164556962024, "progress_pct": 17.09, "epoch_pct": 17.09, "eta": "47:13:52", "max_grad_norm": 1.0, "loss": 0.7638729810714722, "grad_norm": 0.39939233660697937, "learning_rate": 0.0001952324798863134}
-{"ts": "2025-12-27T04:01:31", "event": "train_log", "step": 2432, "epoch": 1.0261603375527426, "progress_pct": 17.1, "epoch_pct": 17.1, "eta": "47:12:22", "max_grad_norm": 1.0, "loss": 0.6922630071640015, "grad_norm": 0.40807482600212097, "learning_rate": 0.00019521781585291298}
-{"ts": "2025-12-27T04:01:46", "event": "train_log", "step": 2434, "epoch": 1.0270042194092828, "progress_pct": 17.12, "epoch_pct": 17.12, "eta": "47:10:47", "max_grad_norm": 1.0, "loss": 0.762996256351471, "grad_norm": 0.45735791325569153, "learning_rate": 0.00019520312985459116}
-{"ts": "2025-12-27T04:02:02", "event": "train_log", "step": 2436, "epoch": 1.0278481012658227, "progress_pct": 17.13, "epoch_pct": 17.13, "eta": "47:09:15", "max_grad_norm": 1.0, "loss": 0.7811596989631653, "grad_norm": 0.4280409812927246, "learning_rate": 0.0001951884218947357}
-{"ts": "2025-12-27T04:02:18", "event": "train_log", "step": 2438, "epoch": 1.0286919831223629, "progress_pct": 17.14, "epoch_pct": 17.14, "eta": "47:07:46", "max_grad_norm": 1.0, "loss": 0.7278305292129517, "grad_norm": 0.41957560181617737, "learning_rate": 0.00019517369197673943}
-{"ts": "2025-12-27T04:02:33", "event": "train_log", "step": 2440, "epoch": 1.029535864978903, "progress_pct": 17.16, "epoch_pct": 17.16, "eta": "47:06:09", "max_grad_norm": 1.0, "loss": 0.807456910610199, "grad_norm": 0.4832586646080017, "learning_rate": 0.00019515894010400028}
-{"ts": "2025-12-27T04:02:48", "event": "train_log", "step": 2442, "epoch": 1.030379746835443, "progress_pct": 17.17, "epoch_pct": 17.17, "eta": "47:04:30", "max_grad_norm": 1.0, "loss": 0.7421302795410156, "grad_norm": 0.46448788046836853, "learning_rate": 0.00019514416627992122}
-{"ts": "2025-12-27T04:03:02", "event": "train_log", "step": 2444, "epoch": 1.0312236286919831, "progress_pct": 17.19, "epoch_pct": 17.19, "eta": "47:02:54", "max_grad_norm": 1.0, "loss": 0.6892213225364685, "grad_norm": 0.41362619400024414, "learning_rate": 0.00019512937050791024}
-{"ts": "2025-12-27T04:03:17", "event": "train_log", "step": 2446, "epoch": 1.0320675105485233, "progress_pct": 17.2, "epoch_pct": 17.2, "eta": "47:01:18", "max_grad_norm": 1.0, "loss": 0.7305331826210022, "grad_norm": 0.4158109128475189, "learning_rate": 0.0001951145527913805}
-{"ts": "2025-12-27T04:03:31", "event": "train_log", "step": 2448, "epoch": 1.0329113924050632, "progress_pct": 17.22, "epoch_pct": 17.22, "eta": "46:59:40", "max_grad_norm": 1.0, "loss": 0.7682753205299377, "grad_norm": 0.4725087881088257, "learning_rate": 0.00019509971313375011}
-{"ts": "2025-12-27T04:03:46", "event": "train_log", "step": 2450, "epoch": 1.0337552742616034, "progress_pct": 17.23, "epoch_pct": 17.23, "eta": "46:58:04", "max_grad_norm": 1.0, "loss": 0.747041642665863, "grad_norm": 0.4341438114643097, "learning_rate": 0.00019508485153844237}
-{"ts": "2025-12-27T04:04:01", "event": "train_log", "step": 2452, "epoch": 1.0345991561181433, "progress_pct": 17.24, "epoch_pct": 17.24, "eta": "46:56:29", "max_grad_norm": 1.0, "loss": 0.7312062382698059, "grad_norm": 0.44515377283096313, "learning_rate": 0.00019506996800888548}
-{"ts": "2025-12-27T04:04:16", "event": "train_log", "step": 2454, "epoch": 1.0354430379746835, "progress_pct": 17.26, "epoch_pct": 17.26, "eta": "46:54:52", "max_grad_norm": 1.0, "loss": 0.7861107587814331, "grad_norm": 0.5313915014266968, "learning_rate": 0.00019505506254851283}
-{"ts": "2025-12-27T04:04:30", "event": "train_log", "step": 2456, "epoch": 1.0362869198312237, "progress_pct": 17.27, "epoch_pct": 17.27, "eta": "46:53:14", "max_grad_norm": 1.0, "loss": 0.8458115458488464, "grad_norm": 0.6094246506690979, "learning_rate": 0.00019504013516076285}
-{"ts": "2025-12-27T04:04:46", "event": "train_log", "step": 2458, "epoch": 1.0371308016877636, "progress_pct": 17.29, "epoch_pct": 17.29, "eta": "46:51:45", "max_grad_norm": 1.0, "loss": 0.6091256141662598, "grad_norm": 0.36419153213500977, "learning_rate": 0.00019502518584907895}
-{"ts": "2025-12-27T04:05:02", "event": "train_log", "step": 2460, "epoch": 1.0379746835443038, "progress_pct": 17.3, "epoch_pct": 17.3, "eta": "46:50:14", "max_grad_norm": 1.0, "loss": 0.6703370809555054, "grad_norm": 0.399271696805954, "learning_rate": 0.00019501021461690966}
-{"ts": "2025-12-27T04:05:17", "event": "train_log", "step": 2462, "epoch": 1.038818565400844, "progress_pct": 17.31, "epoch_pct": 17.31, "eta": "46:48:42", "max_grad_norm": 1.0, "loss": 0.7220943570137024, "grad_norm": 0.38560932874679565, "learning_rate": 0.00019499522146770856}
-{"ts": "2025-12-27T04:05:32", "event": "train_log", "step": 2464, "epoch": 1.0396624472573839, "progress_pct": 17.33, "epoch_pct": 17.33, "eta": "46:47:08", "max_grad_norm": 1.0, "loss": 0.7501406073570251, "grad_norm": 0.44199803471565247, "learning_rate": 0.00019498020640493428}
-{"ts": "2025-12-27T04:05:46", "event": "train_log", "step": 2466, "epoch": 1.040506329113924, "progress_pct": 17.34, "epoch_pct": 17.34, "eta": "46:45:31", "max_grad_norm": 1.0, "loss": 0.7957925796508789, "grad_norm": 0.47394421696662903, "learning_rate": 0.00019496516943205054}
-{"ts": "2025-12-27T04:06:01", "event": "train_log", "step": 2468, "epoch": 1.0413502109704642, "progress_pct": 17.36, "epoch_pct": 17.36, "eta": "46:43:55", "max_grad_norm": 1.0, "loss": 0.7964824438095093, "grad_norm": 0.5274425745010376, "learning_rate": 0.00019495011055252603}
-{"ts": "2025-12-27T04:06:16", "event": "train_log", "step": 2470, "epoch": 1.0421940928270041, "progress_pct": 17.37, "epoch_pct": 17.37, "eta": "46:42:22", "max_grad_norm": 1.0, "loss": 0.7478582262992859, "grad_norm": 0.44004881381988525, "learning_rate": 0.0001949350297698346}
-{"ts": "2025-12-27T04:06:32", "event": "train_log", "step": 2472, "epoch": 1.0430379746835443, "progress_pct": 17.38, "epoch_pct": 17.38, "eta": "46:40:52", "max_grad_norm": 1.0, "loss": 0.738339900970459, "grad_norm": 0.40662670135498047, "learning_rate": 0.000194919927087455}
-{"ts": "2025-12-27T04:06:47", "event": "train_log", "step": 2474, "epoch": 1.0438818565400845, "progress_pct": 17.4, "epoch_pct": 17.4, "eta": "46:39:19", "max_grad_norm": 1.0, "loss": 0.817171037197113, "grad_norm": 0.43934181332588196, "learning_rate": 0.00019490480250887123}
-{"ts": "2025-12-27T04:07:01", "event": "train_log", "step": 2476, "epoch": 1.0447257383966244, "progress_pct": 17.41, "epoch_pct": 17.41, "eta": "46:37:42", "max_grad_norm": 1.0, "loss": 0.7413169145584106, "grad_norm": 0.4111221432685852, "learning_rate": 0.00019488965603757223}
-{"ts": "2025-12-27T04:07:16", "event": "train_log", "step": 2478, "epoch": 1.0455696202531646, "progress_pct": 17.43, "epoch_pct": 17.43, "eta": "46:36:12", "max_grad_norm": 1.0, "loss": 0.7893102169036865, "grad_norm": 0.3770996630191803, "learning_rate": 0.00019487448767705194}
-{"ts": "2025-12-27T04:07:31", "event": "train_log", "step": 2480, "epoch": 1.0464135021097047, "progress_pct": 17.44, "epoch_pct": 17.44, "eta": "46:34:38", "max_grad_norm": 1.0, "loss": 0.7037841081619263, "grad_norm": 0.4524461627006531, "learning_rate": 0.00019485929743080945}
-{"ts": "2025-12-27T04:07:46", "event": "train_log", "step": 2482, "epoch": 1.0472573839662447, "progress_pct": 17.45, "epoch_pct": 17.45, "eta": "46:33:04", "max_grad_norm": 1.0, "loss": 0.7456525564193726, "grad_norm": 0.4232378900051117, "learning_rate": 0.00019484408530234885}
-{"ts": "2025-12-27T04:08:02", "event": "train_log", "step": 2484, "epoch": 1.0481012658227848, "progress_pct": 17.47, "epoch_pct": 17.47, "eta": "46:31:36", "max_grad_norm": 1.0, "loss": 0.7263808250427246, "grad_norm": 0.3842810392379761, "learning_rate": 0.00019482885129517929}
-{"ts": "2025-12-27T04:08:17", "event": "train_log", "step": 2486, "epoch": 1.048945147679325, "progress_pct": 17.48, "epoch_pct": 17.48, "eta": "46:30:03", "max_grad_norm": 1.0, "loss": 0.7101474404335022, "grad_norm": 0.43203726410865784, "learning_rate": 0.00019481359541281495}
-{"ts": "2025-12-27T04:08:32", "event": "train_log", "step": 2488, "epoch": 1.049789029535865, "progress_pct": 17.5, "epoch_pct": 17.5, "eta": "46:28:30", "max_grad_norm": 1.0, "loss": 0.8561921715736389, "grad_norm": 0.46944454312324524, "learning_rate": 0.00019479831765877509}
-{"ts": "2025-12-27T04:08:47", "event": "train_log", "step": 2490, "epoch": 1.0506329113924051, "progress_pct": 17.51, "epoch_pct": 17.51, "eta": "46:26:58", "max_grad_norm": 1.0, "loss": 0.7206679582595825, "grad_norm": 0.4455019533634186, "learning_rate": 0.00019478301803658397}
-{"ts": "2025-12-27T04:09:02", "event": "train_log", "step": 2492, "epoch": 1.051476793248945, "progress_pct": 17.52, "epoch_pct": 17.52, "eta": "46:25:26", "max_grad_norm": 1.0, "loss": 0.7271745800971985, "grad_norm": 0.4253813326358795, "learning_rate": 0.00019476769654977095}
-{"ts": "2025-12-27T04:09:16", "event": "train_log", "step": 2494, "epoch": 1.0523206751054852, "progress_pct": 17.54, "epoch_pct": 17.54, "eta": "46:23:52", "max_grad_norm": 1.0, "loss": 0.7358576059341431, "grad_norm": 0.42758429050445557, "learning_rate": 0.00019475235320187033}
-{"ts": "2025-12-27T04:09:33", "event": "train_log", "step": 2496, "epoch": 1.0531645569620254, "progress_pct": 17.55, "epoch_pct": 17.55, "eta": "46:22:27", "max_grad_norm": 1.0, "loss": 0.6617647409439087, "grad_norm": 0.400634765625, "learning_rate": 0.00019473698799642164}
-{"ts": "2025-12-27T04:09:48", "event": "train_log", "step": 2498, "epoch": 1.0540084388185653, "progress_pct": 17.57, "epoch_pct": 17.57, "eta": "46:20:55", "max_grad_norm": 1.0, "loss": 0.6900970935821533, "grad_norm": 0.4132104814052582, "learning_rate": 0.00019472160093696926}
-{"ts": "2025-12-27T04:10:02", "event": "train_log", "step": 2500, "epoch": 1.0548523206751055, "progress_pct": 17.58, "epoch_pct": 17.58, "eta": "46:19:22", "max_grad_norm": 1.0, "loss": 0.7352861762046814, "grad_norm": 0.5116495490074158, "learning_rate": 0.00019470619202706268}
-{"ts": "2025-12-27T04:21:22", "event": "train_log", "step": 2500, "epoch": 1.0548523206751055, "progress_pct": 17.58, "epoch_pct": 17.58, "eta": "47:12:27", "max_grad_norm": 1.0, "eval_loss": 0.8249453902244568, "eval_runtime": 679.4446, "eval_samples_per_second": 3.101, "eval_steps_per_second": 3.101}
-{"ts": "2025-12-27T04:21:37", "event": "train_log", "step": 2502, "epoch": 1.0556962025316456, "progress_pct": 17.59, "epoch_pct": 17.59, "eta": "47:10:55", "max_grad_norm": 1.0, "loss": 0.7583479881286621, "grad_norm": 0.42822444438934326, "learning_rate": 0.0001946907612702565}
-{"ts": "2025-12-27T04:21:53", "event": "train_log", "step": 2504, "epoch": 1.0565400843881856, "progress_pct": 17.61, "epoch_pct": 17.61, "eta": "47:09:22", "max_grad_norm": 1.0, "loss": 0.777511477470398, "grad_norm": 0.4788980782032013, "learning_rate": 0.00019467530867011025}
-{"ts": "2025-12-27T04:22:09", "event": "train_log", "step": 2506, "epoch": 1.0573839662447257, "progress_pct": 17.62, "epoch_pct": 17.62, "eta": "47:07:52", "max_grad_norm": 1.0, "loss": 0.7452852129936218, "grad_norm": 0.4210498034954071, "learning_rate": 0.00019465983423018856}
-{"ts": "2025-12-27T04:22:24", "event": "train_log", "step": 2508, "epoch": 1.058227848101266, "progress_pct": 17.64, "epoch_pct": 17.64, "eta": "47:06:19", "max_grad_norm": 1.0, "loss": 0.7540958523750305, "grad_norm": 0.43219906091690063, "learning_rate": 0.0001946443379540611}
-{"ts": "2025-12-27T04:22:39", "event": "train_log", "step": 2510, "epoch": 1.0590717299578059, "progress_pct": 17.65, "epoch_pct": 17.65, "eta": "47:04:47", "max_grad_norm": 1.0, "loss": 0.7175624966621399, "grad_norm": 0.4361002445220947, "learning_rate": 0.00019462881984530253}
-{"ts": "2025-12-27T04:22:55", "event": "train_log", "step": 2512, "epoch": 1.059915611814346, "progress_pct": 17.67, "epoch_pct": 17.67, "eta": "47:03:15", "max_grad_norm": 1.0, "loss": 0.7342076301574707, "grad_norm": 0.4575091600418091, "learning_rate": 0.00019461327990749264}
-{"ts": "2025-12-27T04:23:10", "event": "train_log", "step": 2514, "epoch": 1.0607594936708862, "progress_pct": 17.68, "epoch_pct": 17.68, "eta": "47:01:43", "max_grad_norm": 1.0, "loss": 0.8255488872528076, "grad_norm": 0.4823324978351593, "learning_rate": 0.00019459771814421615}
-{"ts": "2025-12-27T04:23:26", "event": "train_log", "step": 2516, "epoch": 1.0616033755274261, "progress_pct": 17.69, "epoch_pct": 17.69, "eta": "47:00:12", "max_grad_norm": 1.0, "loss": 0.6624729633331299, "grad_norm": 0.41693785786628723, "learning_rate": 0.00019458213455906284}
-{"ts": "2025-12-27T04:23:41", "event": "train_log", "step": 2518, "epoch": 1.0624472573839663, "progress_pct": 17.71, "epoch_pct": 17.71, "eta": "46:58:41", "max_grad_norm": 1.0, "loss": 0.8224266767501831, "grad_norm": 0.41319167613983154, "learning_rate": 0.00019456652915562762}
-{"ts": "2025-12-27T04:23:57", "event": "train_log", "step": 2520, "epoch": 1.0632911392405062, "progress_pct": 17.72, "epoch_pct": 17.72, "eta": "46:57:11", "max_grad_norm": 1.0, "loss": 0.7582900524139404, "grad_norm": 0.4405190050601959, "learning_rate": 0.00019455090193751023}
-{"ts": "2025-12-27T04:24:13", "event": "train_log", "step": 2522, "epoch": 1.0641350210970464, "progress_pct": 17.74, "epoch_pct": 17.74, "eta": "46:55:40", "max_grad_norm": 1.0, "loss": 0.7948101162910461, "grad_norm": 0.4564387798309326, "learning_rate": 0.0001945352529083157}
-{"ts": "2025-12-27T04:24:28", "event": "train_log", "step": 2524, "epoch": 1.0649789029535865, "progress_pct": 17.75, "epoch_pct": 17.75, "eta": "46:54:09", "max_grad_norm": 1.0, "loss": 0.7670508027076721, "grad_norm": 0.4247225224971771, "learning_rate": 0.00019451958207165394}
-{"ts": "2025-12-27T04:24:43", "event": "train_log", "step": 2526, "epoch": 1.0658227848101265, "progress_pct": 17.76, "epoch_pct": 17.76, "eta": "46:52:37", "max_grad_norm": 1.0, "loss": 0.7753698229789734, "grad_norm": 0.42070862650871277, "learning_rate": 0.00019450388943113983}
-{"ts": "2025-12-27T04:24:59", "event": "train_log", "step": 2528, "epoch": 1.0666666666666667, "progress_pct": 17.78, "epoch_pct": 17.78, "eta": "46:51:09", "max_grad_norm": 1.0, "loss": 0.710904598236084, "grad_norm": 0.3729179799556732, "learning_rate": 0.00019448817499039342}
-{"ts": "2025-12-27T04:25:16", "event": "train_log", "step": 2530, "epoch": 1.0675105485232068, "progress_pct": 17.79, "epoch_pct": 17.79, "eta": "46:49:44", "max_grad_norm": 1.0, "loss": 0.7000213265419006, "grad_norm": 0.40901753306388855, "learning_rate": 0.0001944724387530397}
-{"ts": "2025-12-27T04:25:32", "event": "train_log", "step": 2532, "epoch": 1.0683544303797468, "progress_pct": 17.81, "epoch_pct": 17.81, "eta": "46:48:14", "max_grad_norm": 1.0, "loss": 0.7374410629272461, "grad_norm": 0.4481421113014221, "learning_rate": 0.00019445668072270877}
-{"ts": "2025-12-27T04:25:47", "event": "train_log", "step": 2534, "epoch": 1.069198312236287, "progress_pct": 17.82, "epoch_pct": 17.82, "eta": "46:46:43", "max_grad_norm": 1.0, "loss": 0.746309220790863, "grad_norm": 0.4839915335178375, "learning_rate": 0.00019444090090303567}
-{"ts": "2025-12-27T04:26:03", "event": "train_log", "step": 2536, "epoch": 1.070042194092827, "progress_pct": 17.83, "epoch_pct": 17.83, "eta": "46:45:14", "max_grad_norm": 1.0, "loss": 0.7448083162307739, "grad_norm": 0.4982132613658905, "learning_rate": 0.00019442509929766048}
-{"ts": "2025-12-27T04:26:19", "event": "train_log", "step": 2538, "epoch": 1.070886075949367, "progress_pct": 17.85, "epoch_pct": 17.85, "eta": "46:43:48", "max_grad_norm": 1.0, "loss": 0.7052555680274963, "grad_norm": 0.3987475037574768, "learning_rate": 0.00019440927591022838}
-{"ts": "2025-12-27T04:26:34", "event": "train_log", "step": 2540, "epoch": 1.0717299578059072, "progress_pct": 17.86, "epoch_pct": 17.86, "eta": "46:42:17", "max_grad_norm": 1.0, "loss": 0.7090281248092651, "grad_norm": 0.4089896082878113, "learning_rate": 0.00019439343074438944}
-{"ts": "2025-12-27T04:26:50", "event": "train_log", "step": 2542, "epoch": 1.0725738396624473, "progress_pct": 17.88, "epoch_pct": 17.88, "eta": "46:40:47", "max_grad_norm": 1.0, "loss": 0.7530601024627686, "grad_norm": 0.3703136146068573, "learning_rate": 0.00019437756380379895}
-{"ts": "2025-12-27T04:27:05", "event": "train_log", "step": 2544, "epoch": 1.0734177215189873, "progress_pct": 17.89, "epoch_pct": 17.89, "eta": "46:39:15", "max_grad_norm": 1.0, "loss": 0.7597941160202026, "grad_norm": 0.4015701413154602, "learning_rate": 0.00019436167509211702}
-{"ts": "2025-12-27T04:27:23", "event": "train_log", "step": 2546, "epoch": 1.0742616033755275, "progress_pct": 17.9, "epoch_pct": 17.9, "eta": "46:37:56", "max_grad_norm": 1.0, "loss": 0.7168124318122864, "grad_norm": 0.3915148675441742, "learning_rate": 0.00019434576461300888}
-{"ts": "2025-12-27T04:27:38", "event": "train_log", "step": 2548, "epoch": 1.0751054852320676, "progress_pct": 17.92, "epoch_pct": 17.92, "eta": "46:36:28", "max_grad_norm": 1.0, "loss": 0.7762725949287415, "grad_norm": 0.44643113017082214, "learning_rate": 0.00019432983237014482}
-{"ts": "2025-12-27T04:27:54", "event": "train_log", "step": 2550, "epoch": 1.0759493670886076, "progress_pct": 17.93, "epoch_pct": 17.93, "eta": "46:34:59", "max_grad_norm": 1.0, "loss": 0.7879725098609924, "grad_norm": 0.46874719858169556, "learning_rate": 0.00019431387836720004}
-{"ts": "2025-12-27T04:28:10", "event": "train_log", "step": 2552, "epoch": 1.0767932489451477, "progress_pct": 17.95, "epoch_pct": 17.95, "eta": "46:33:32", "max_grad_norm": 1.0, "loss": 0.7351391315460205, "grad_norm": 0.4143001437187195, "learning_rate": 0.00019429790260785487}
-{"ts": "2025-12-27T04:28:27", "event": "train_log", "step": 2554, "epoch": 1.0776371308016879, "progress_pct": 17.96, "epoch_pct": 17.96, "eta": "46:32:09", "max_grad_norm": 1.0, "loss": 0.86613929271698, "grad_norm": 0.4569888412952423, "learning_rate": 0.0001942819050957946}
-{"ts": "2025-12-27T04:28:43", "event": "train_log", "step": 2556, "epoch": 1.0784810126582278, "progress_pct": 17.97, "epoch_pct": 17.97, "eta": "46:30:44", "max_grad_norm": 1.0, "loss": 0.7122719287872314, "grad_norm": 0.41729897260665894, "learning_rate": 0.00019426588583470954}
-{"ts": "2025-12-27T04:28:59", "event": "train_log", "step": 2558, "epoch": 1.079324894514768, "progress_pct": 17.99, "epoch_pct": 17.99, "eta": "46:29:18", "max_grad_norm": 1.0, "loss": 0.6605332493782043, "grad_norm": 0.42295604944229126, "learning_rate": 0.000194249844828295}
-{"ts": "2025-12-27T04:29:14", "event": "train_log", "step": 2560, "epoch": 1.080168776371308, "progress_pct": 18.0, "epoch_pct": 18.0, "eta": "46:27:43", "max_grad_norm": 1.0, "loss": 0.7839207649230957, "grad_norm": 0.45787641406059265, "learning_rate": 0.00019423378208025137}
-{"ts": "2025-12-27T04:29:29", "event": "train_log", "step": 2562, "epoch": 1.081012658227848, "progress_pct": 18.02, "epoch_pct": 18.02, "eta": "46:26:15", "max_grad_norm": 1.0, "loss": 0.7557987570762634, "grad_norm": 0.43370622396469116, "learning_rate": 0.00019421769759428404}
-{"ts": "2025-12-27T04:29:45", "event": "train_log", "step": 2564, "epoch": 1.0818565400843883, "progress_pct": 18.03, "epoch_pct": 18.03, "eta": "46:24:46", "max_grad_norm": 1.0, "loss": 0.7349345088005066, "grad_norm": 0.4371975362300873, "learning_rate": 0.00019420159137410335}
-{"ts": "2025-12-27T04:30:01", "event": "train_log", "step": 2566, "epoch": 1.0827004219409282, "progress_pct": 18.05, "epoch_pct": 18.05, "eta": "46:23:22", "max_grad_norm": 1.0, "loss": 0.7024962902069092, "grad_norm": 0.468730628490448, "learning_rate": 0.0001941854634234247}
-{"ts": "2025-12-27T04:30:18", "event": "train_log", "step": 2568, "epoch": 1.0835443037974684, "progress_pct": 18.06, "epoch_pct": 18.06, "eta": "46:22:00", "max_grad_norm": 1.0, "loss": 0.6981064081192017, "grad_norm": 0.4257284998893738, "learning_rate": 0.0001941693137459685}
-{"ts": "2025-12-27T04:30:34", "event": "train_log", "step": 2570, "epoch": 1.0843881856540085, "progress_pct": 18.07, "epoch_pct": 18.07, "eta": "46:20:32", "max_grad_norm": 1.0, "loss": 0.7899637818336487, "grad_norm": 0.4322902262210846, "learning_rate": 0.00019415314234546015}
-{"ts": "2025-12-27T04:30:49", "event": "train_log", "step": 2572, "epoch": 1.0852320675105485, "progress_pct": 18.09, "epoch_pct": 18.09, "eta": "46:19:02", "max_grad_norm": 1.0, "loss": 0.7964152693748474, "grad_norm": 0.44384217262268066, "learning_rate": 0.00019413694922563014}
-{"ts": "2025-12-27T04:31:05", "event": "train_log", "step": 2574, "epoch": 1.0860759493670886, "progress_pct": 18.1, "epoch_pct": 18.1, "eta": "46:17:36", "max_grad_norm": 1.0, "loss": 0.7902941107749939, "grad_norm": 0.47391360998153687, "learning_rate": 0.0001941207343902139}
-{"ts": "2025-12-27T04:31:20", "event": "train_log", "step": 2576, "epoch": 1.0869198312236288, "progress_pct": 18.12, "epoch_pct": 18.12, "eta": "46:16:08", "max_grad_norm": 1.0, "loss": 0.7818595170974731, "grad_norm": 0.4575883746147156, "learning_rate": 0.00019410449784295182}
-{"ts": "2025-12-27T04:31:36", "event": "train_log", "step": 2578, "epoch": 1.0877637130801687, "progress_pct": 18.13, "epoch_pct": 18.13, "eta": "46:14:40", "max_grad_norm": 1.0, "loss": 0.7516021728515625, "grad_norm": 0.41236087679862976, "learning_rate": 0.0001940882395875894}
-{"ts": "2025-12-27T04:31:53", "event": "train_log", "step": 2580, "epoch": 1.0886075949367089, "progress_pct": 18.14, "epoch_pct": 18.14, "eta": "46:13:21", "max_grad_norm": 1.0, "loss": 0.6870401501655579, "grad_norm": 0.3817494213581085, "learning_rate": 0.0001940719596278771}
-{"ts": "2025-12-27T04:32:08", "event": "train_log", "step": 2582, "epoch": 1.0894514767932488, "progress_pct": 18.16, "epoch_pct": 18.16, "eta": "46:11:52", "max_grad_norm": 1.0, "loss": 0.7437341809272766, "grad_norm": 0.4630168378353119, "learning_rate": 0.00019405565796757043}
-{"ts": "2025-12-27T04:32:24", "event": "train_log", "step": 2584, "epoch": 1.090295358649789, "progress_pct": 18.17, "epoch_pct": 18.17, "eta": "46:10:26", "max_grad_norm": 1.0, "loss": 0.7101680040359497, "grad_norm": 0.4063820540904999, "learning_rate": 0.00019403933461042982}
-{"ts": "2025-12-27T04:32:39", "event": "train_log", "step": 2586, "epoch": 1.0911392405063292, "progress_pct": 18.19, "epoch_pct": 18.19, "eta": "46:08:58", "max_grad_norm": 1.0, "loss": 0.6894780397415161, "grad_norm": 0.44423359632492065, "learning_rate": 0.0001940229895602208}
-{"ts": "2025-12-27T04:32:55", "event": "train_log", "step": 2588, "epoch": 1.091983122362869, "progress_pct": 18.2, "epoch_pct": 18.2, "eta": "46:07:31", "max_grad_norm": 1.0, "loss": 0.7277120351791382, "grad_norm": 0.4267353117465973, "learning_rate": 0.0001940066228207138}
-{"ts": "2025-12-27T04:33:12", "event": "train_log", "step": 2590, "epoch": 1.0928270042194093, "progress_pct": 18.21, "epoch_pct": 18.21, "eta": "46:06:12", "max_grad_norm": 1.0, "loss": 0.6512353420257568, "grad_norm": 0.44747647643089294, "learning_rate": 0.00019399023439568434}
-{"ts": "2025-12-27T04:33:27", "event": "train_log", "step": 2592, "epoch": 1.0936708860759494, "progress_pct": 18.23, "epoch_pct": 18.23, "eta": "46:04:41", "max_grad_norm": 1.0, "loss": 0.7850068807601929, "grad_norm": 0.4557100832462311, "learning_rate": 0.00019397382428891296}
-{"ts": "2025-12-27T04:33:42", "event": "train_log", "step": 2594, "epoch": 1.0945147679324894, "progress_pct": 18.24, "epoch_pct": 18.24, "eta": "46:03:12", "max_grad_norm": 1.0, "loss": 0.786868691444397, "grad_norm": 0.44980114698410034, "learning_rate": 0.0001939573925041851}
-{"ts": "2025-12-27T04:33:57", "event": "train_log", "step": 2596, "epoch": 1.0953586497890295, "progress_pct": 18.26, "epoch_pct": 18.26, "eta": "46:01:42", "max_grad_norm": 1.0, "loss": 0.8260899186134338, "grad_norm": 0.45374399423599243, "learning_rate": 0.00019394093904529126}
-{"ts": "2025-12-27T04:34:11", "event": "train_log", "step": 2598, "epoch": 1.0962025316455697, "progress_pct": 18.27, "epoch_pct": 18.27, "eta": "46:00:10", "max_grad_norm": 1.0, "loss": 0.7056689262390137, "grad_norm": 0.40681353211402893, "learning_rate": 0.00019392446391602695}
-{"ts": "2025-12-27T04:34:26", "event": "train_log", "step": 2600, "epoch": 1.0970464135021096, "progress_pct": 18.28, "epoch_pct": 18.28, "eta": "45:58:42", "max_grad_norm": 1.0, "loss": 0.7557252645492554, "grad_norm": 0.39278075098991394, "learning_rate": 0.0001939079671201927}
-{"ts": "2025-12-27T04:45:36", "event": "train_log", "step": 2600, "epoch": 1.0970464135021096, "progress_pct": 18.28, "epoch_pct": 18.28, "eta": "46:48:37", "max_grad_norm": 1.0, "eval_loss": 0.8211485743522644, "eval_runtime": 670.2276, "eval_samples_per_second": 3.144, "eval_steps_per_second": 3.144}
-{"ts": "2025-12-27T04:45:51", "event": "train_log", "step": 2602, "epoch": 1.0978902953586498, "progress_pct": 18.3, "epoch_pct": 18.3, "eta": "46:47:03", "max_grad_norm": 1.0, "loss": 0.7139819264411926, "grad_norm": 0.4261230230331421, "learning_rate": 0.00019389144866159398}
-{"ts": "2025-12-27T04:46:06", "event": "train_log", "step": 2604, "epoch": 1.09873417721519, "progress_pct": 18.31, "epoch_pct": 18.31, "eta": "46:45:31", "max_grad_norm": 1.0, "loss": 0.7274705767631531, "grad_norm": 0.4664439558982849, "learning_rate": 0.0001938749085440412}
-{"ts": "2025-12-27T04:46:20", "event": "train_log", "step": 2606, "epoch": 1.09957805907173, "progress_pct": 18.33, "epoch_pct": 18.33, "eta": "46:43:58", "max_grad_norm": 1.0, "loss": 0.7547051906585693, "grad_norm": 0.46306154131889343, "learning_rate": 0.00019385834677134998}
-{"ts": "2025-12-27T04:46:35", "event": "train_log", "step": 2608, "epoch": 1.10042194092827, "progress_pct": 18.34, "epoch_pct": 18.34, "eta": "46:42:27", "max_grad_norm": 1.0, "loss": 0.6942694187164307, "grad_norm": 0.39753687381744385, "learning_rate": 0.00019384176334734073}
-{"ts": "2025-12-27T04:46:50", "event": "train_log", "step": 2610, "epoch": 1.1012658227848102, "progress_pct": 18.35, "epoch_pct": 18.35, "eta": "46:40:54", "max_grad_norm": 1.0, "loss": 0.7161701321601868, "grad_norm": 0.4556522071361542, "learning_rate": 0.00019382515827583898}
-{"ts": "2025-12-27T04:47:06", "event": "train_log", "step": 2612, "epoch": 1.1021097046413502, "progress_pct": 18.37, "epoch_pct": 18.37, "eta": "46:39:29", "max_grad_norm": 1.0, "loss": 0.7165710926055908, "grad_norm": 0.3863290250301361, "learning_rate": 0.0001938085315606751}
-{"ts": "2025-12-27T04:47:21", "event": "train_log", "step": 2614, "epoch": 1.1029535864978903, "progress_pct": 18.38, "epoch_pct": 18.38, "eta": "46:37:58", "max_grad_norm": 1.0, "loss": 0.8080679774284363, "grad_norm": 0.49601292610168457, "learning_rate": 0.00019379188320568466}
-{"ts": "2025-12-27T04:47:37", "event": "train_log", "step": 2616, "epoch": 1.1037974683544305, "progress_pct": 18.4, "epoch_pct": 18.4, "eta": "46:36:31", "max_grad_norm": 1.0, "loss": 0.7032502889633179, "grad_norm": 0.4498465955257416, "learning_rate": 0.00019377521321470805}
-{"ts": "2025-12-27T04:47:54", "event": "train_log", "step": 2618, "epoch": 1.1046413502109704, "progress_pct": 18.41, "epoch_pct": 18.41, "eta": "46:35:11", "max_grad_norm": 1.0, "loss": 0.7076731324195862, "grad_norm": 0.4537963569164276, "learning_rate": 0.00019375852159159073}
-{"ts": "2025-12-27T04:48:12", "event": "train_log", "step": 2620, "epoch": 1.1054852320675106, "progress_pct": 18.42, "epoch_pct": 18.42, "eta": "46:33:50", "max_grad_norm": 1.0, "loss": 0.7020825743675232, "grad_norm": 0.4042968153953552, "learning_rate": 0.0001937418083401832}
-{"ts": "2025-12-27T04:48:27", "event": "train_log", "step": 2622, "epoch": 1.1063291139240505, "progress_pct": 18.44, "epoch_pct": 18.44, "eta": "46:32:20", "max_grad_norm": 1.0, "loss": 0.7222874760627747, "grad_norm": 0.44306516647338867, "learning_rate": 0.00019372507346434076}
-{"ts": "2025-12-27T04:48:44", "event": "train_log", "step": 2624, "epoch": 1.1071729957805907, "progress_pct": 18.45, "epoch_pct": 18.45, "eta": "46:30:58", "max_grad_norm": 1.0, "loss": 0.6136211156845093, "grad_norm": 0.3792516887187958, "learning_rate": 0.00019370831696792392}
-{"ts": "2025-12-27T04:49:00", "event": "train_log", "step": 2626, "epoch": 1.1080168776371309, "progress_pct": 18.47, "epoch_pct": 18.47, "eta": "46:29:33", "max_grad_norm": 1.0, "loss": 0.7358977198600769, "grad_norm": 0.46655353903770447, "learning_rate": 0.00019369153885479806}
-{"ts": "2025-12-27T04:49:15", "event": "train_log", "step": 2628, "epoch": 1.1088607594936708, "progress_pct": 18.48, "epoch_pct": 18.48, "eta": "46:28:05", "max_grad_norm": 1.0, "loss": 0.7484551072120667, "grad_norm": 0.4416999816894531, "learning_rate": 0.0001936747391288336}
-{"ts": "2025-12-27T04:49:30", "event": "train_log", "step": 2630, "epoch": 1.109704641350211, "progress_pct": 18.5, "epoch_pct": 18.5, "eta": "46:26:35", "max_grad_norm": 1.0, "loss": 0.6874802708625793, "grad_norm": 0.4620150327682495, "learning_rate": 0.00019365791779390584}
-{"ts": "2025-12-27T04:49:46", "event": "train_log", "step": 2632, "epoch": 1.1105485232067511, "progress_pct": 18.51, "epoch_pct": 18.51, "eta": "46:25:09", "max_grad_norm": 1.0, "loss": 0.7168865203857422, "grad_norm": 0.4357883334159851, "learning_rate": 0.00019364107485389518}
-{"ts": "2025-12-27T04:50:01", "event": "train_log", "step": 2634, "epoch": 1.111392405063291, "progress_pct": 18.52, "epoch_pct": 18.52, "eta": "46:23:41", "max_grad_norm": 1.0, "loss": 0.7533737421035767, "grad_norm": 0.4581143856048584, "learning_rate": 0.00019362421031268699}
-{"ts": "2025-12-27T04:50:17", "event": "train_log", "step": 2636, "epoch": 1.1122362869198312, "progress_pct": 18.54, "epoch_pct": 18.54, "eta": "46:22:13", "max_grad_norm": 1.0, "loss": 0.8245398998260498, "grad_norm": 0.46408653259277344, "learning_rate": 0.00019360732417417152}
-{"ts": "2025-12-27T04:50:32", "event": "train_log", "step": 2638, "epoch": 1.1130801687763714, "progress_pct": 18.55, "epoch_pct": 18.55, "eta": "46:20:45", "max_grad_norm": 1.0, "loss": 0.7095663547515869, "grad_norm": 0.4639282524585724, "learning_rate": 0.00019359041644224415}
-{"ts": "2025-12-27T04:50:49", "event": "train_log", "step": 2640, "epoch": 1.1139240506329113, "progress_pct": 18.57, "epoch_pct": 18.57, "eta": "46:19:22", "max_grad_norm": 1.0, "loss": 0.7030285596847534, "grad_norm": 0.4598273038864136, "learning_rate": 0.00019357348712080517}
-{"ts": "2025-12-27T04:51:04", "event": "train_log", "step": 2642, "epoch": 1.1147679324894515, "progress_pct": 18.58, "epoch_pct": 18.58, "eta": "46:17:55", "max_grad_norm": 1.0, "loss": 0.7158969640731812, "grad_norm": 0.42993804812431335, "learning_rate": 0.00019355653621375978}
-{"ts": "2025-12-27T04:51:22", "event": "train_log", "step": 2644, "epoch": 1.1156118143459917, "progress_pct": 18.59, "epoch_pct": 18.59, "eta": "46:16:38", "max_grad_norm": 1.0, "loss": 0.6800820231437683, "grad_norm": 0.36132168769836426, "learning_rate": 0.0001935395637250183}
-{"ts": "2025-12-27T04:51:37", "event": "train_log", "step": 2646, "epoch": 1.1164556962025316, "progress_pct": 18.61, "epoch_pct": 18.61, "eta": "46:15:09", "max_grad_norm": 1.0, "loss": 0.694972813129425, "grad_norm": 0.5004428029060364, "learning_rate": 0.00019352256965849592}
-{"ts": "2025-12-27T04:51:54", "event": "train_log", "step": 2648, "epoch": 1.1172995780590718, "progress_pct": 18.62, "epoch_pct": 18.62, "eta": "46:13:48", "max_grad_norm": 1.0, "loss": 0.7164262533187866, "grad_norm": 0.43715354800224304, "learning_rate": 0.00019350555401811286}
-{"ts": "2025-12-27T04:52:09", "event": "train_log", "step": 2650, "epoch": 1.1181434599156117, "progress_pct": 18.64, "epoch_pct": 18.64, "eta": "46:12:20", "max_grad_norm": 1.0, "loss": 0.7026737928390503, "grad_norm": 0.42316755652427673, "learning_rate": 0.00019348851680779433}
-{"ts": "2025-12-27T04:52:25", "event": "train_log", "step": 2652, "epoch": 1.1189873417721519, "progress_pct": 18.65, "epoch_pct": 18.65, "eta": "46:10:58", "max_grad_norm": 1.0, "loss": 0.6774232387542725, "grad_norm": 0.35848063230514526, "learning_rate": 0.0001934714580314704}
-{"ts": "2025-12-27T04:52:41", "event": "train_log", "step": 2654, "epoch": 1.119831223628692, "progress_pct": 18.66, "epoch_pct": 18.66, "eta": "46:09:34", "max_grad_norm": 1.0, "loss": 0.7789244055747986, "grad_norm": 0.46613892912864685, "learning_rate": 0.00019345437769307627}
-{"ts": "2025-12-27T04:52:57", "event": "train_log", "step": 2656, "epoch": 1.120675105485232, "progress_pct": 18.68, "epoch_pct": 18.68, "eta": "46:08:09", "max_grad_norm": 1.0, "loss": 0.8647177815437317, "grad_norm": 0.4298146367073059, "learning_rate": 0.00019343727579655204}
-{"ts": "2025-12-27T04:53:14", "event": "train_log", "step": 2658, "epoch": 1.1215189873417721, "progress_pct": 18.69, "epoch_pct": 18.69, "eta": "46:06:47", "max_grad_norm": 1.0, "loss": 0.6949124336242676, "grad_norm": 0.4638161361217499, "learning_rate": 0.00019342015234584276}
-{"ts": "2025-12-27T04:53:28", "event": "train_log", "step": 2660, "epoch": 1.1223628691983123, "progress_pct": 18.71, "epoch_pct": 18.71, "eta": "46:05:15", "max_grad_norm": 1.0, "loss": 0.6677125096321106, "grad_norm": 0.4079605042934418, "learning_rate": 0.00019340300734489854}
-{"ts": "2025-12-27T04:53:43", "event": "train_log", "step": 2662, "epoch": 1.1232067510548522, "progress_pct": 18.72, "epoch_pct": 18.72, "eta": "46:03:46", "max_grad_norm": 1.0, "loss": 0.7521067261695862, "grad_norm": 0.46079063415527344, "learning_rate": 0.00019338584079767434}
-{"ts": "2025-12-27T04:53:58", "event": "train_log", "step": 2664, "epoch": 1.1240506329113924, "progress_pct": 18.73, "epoch_pct": 18.73, "eta": "46:02:20", "max_grad_norm": 1.0, "loss": 0.6829184889793396, "grad_norm": 0.3935202956199646, "learning_rate": 0.0001933686527081302}
-{"ts": "2025-12-27T04:54:14", "event": "train_log", "step": 2666, "epoch": 1.1248945147679326, "progress_pct": 18.75, "epoch_pct": 18.75, "eta": "46:00:53", "max_grad_norm": 1.0, "loss": 0.7122842669487, "grad_norm": 0.45696479082107544, "learning_rate": 0.000193351443080231}
-{"ts": "2025-12-27T04:54:30", "event": "train_log", "step": 2668, "epoch": 1.1257383966244725, "progress_pct": 18.76, "epoch_pct": 18.76, "eta": "45:59:30", "max_grad_norm": 1.0, "loss": 0.7316977977752686, "grad_norm": 0.4078282415866852, "learning_rate": 0.0001933342119179468}
-{"ts": "2025-12-27T04:54:45", "event": "train_log", "step": 2670, "epoch": 1.1265822784810127, "progress_pct": 18.78, "epoch_pct": 18.78, "eta": "45:58:02", "max_grad_norm": 1.0, "loss": 0.7323395013809204, "grad_norm": 0.4282447099685669, "learning_rate": 0.0001933169592252524}
-{"ts": "2025-12-27T04:55:01", "event": "train_log", "step": 2672, "epoch": 1.1274261603375528, "progress_pct": 18.79, "epoch_pct": 18.79, "eta": "45:56:41", "max_grad_norm": 1.0, "loss": 0.7177348732948303, "grad_norm": 0.46398648619651794, "learning_rate": 0.00019329968500612766}
-{"ts": "2025-12-27T04:55:17", "event": "train_log", "step": 2674, "epoch": 1.1282700421940928, "progress_pct": 18.8, "epoch_pct": 18.8, "eta": "45:55:16", "max_grad_norm": 1.0, "loss": 0.7957183122634888, "grad_norm": 0.4560202658176422, "learning_rate": 0.0001932823892645575}
-{"ts": "2025-12-27T04:55:33", "event": "train_log", "step": 2676, "epoch": 1.129113924050633, "progress_pct": 18.82, "epoch_pct": 18.82, "eta": "45:53:53", "max_grad_norm": 1.0, "loss": 0.762060284614563, "grad_norm": 0.4790743887424469, "learning_rate": 0.00019326507200453162}
-{"ts": "2025-12-27T04:55:48", "event": "train_log", "step": 2678, "epoch": 1.129957805907173, "progress_pct": 18.83, "epoch_pct": 18.83, "eta": "45:52:29", "max_grad_norm": 1.0, "loss": 0.7227895259857178, "grad_norm": 0.46524202823638916, "learning_rate": 0.00019324773323004484}
-{"ts": "2025-12-27T04:56:04", "event": "train_log", "step": 2680, "epoch": 1.130801687763713, "progress_pct": 18.85, "epoch_pct": 18.85, "eta": "45:51:04", "max_grad_norm": 1.0, "loss": 0.6968042254447937, "grad_norm": 0.47912222146987915, "learning_rate": 0.00019323037294509683}
-{"ts": "2025-12-27T04:56:19", "event": "train_log", "step": 2682, "epoch": 1.1316455696202532, "progress_pct": 18.86, "epoch_pct": 18.86, "eta": "45:49:37", "max_grad_norm": 1.0, "loss": 0.6682016253471375, "grad_norm": 0.4412849247455597, "learning_rate": 0.00019321299115369233}
-{"ts": "2025-12-27T04:56:34", "event": "train_log", "step": 2684, "epoch": 1.1324894514767934, "progress_pct": 18.87, "epoch_pct": 18.87, "eta": "45:48:09", "max_grad_norm": 1.0, "loss": 0.7287812829017639, "grad_norm": 0.4138370752334595, "learning_rate": 0.00019319558785984095}
-{"ts": "2025-12-27T04:56:50", "event": "train_log", "step": 2686, "epoch": 1.1333333333333333, "progress_pct": 18.89, "epoch_pct": 18.89, "eta": "45:46:46", "max_grad_norm": 1.0, "loss": 0.6547526121139526, "grad_norm": 0.391170859336853, "learning_rate": 0.00019317816306755733}
-{"ts": "2025-12-27T04:57:06", "event": "train_log", "step": 2688, "epoch": 1.1341772151898735, "progress_pct": 18.9, "epoch_pct": 18.9, "eta": "45:45:23", "max_grad_norm": 1.0, "loss": 0.6942042708396912, "grad_norm": 0.45472806692123413, "learning_rate": 0.00019316071678086098}
-{"ts": "2025-12-27T04:57:23", "event": "train_log", "step": 2690, "epoch": 1.1350210970464134, "progress_pct": 18.92, "epoch_pct": 18.92, "eta": "45:44:07", "max_grad_norm": 1.0, "loss": 0.7417841553688049, "grad_norm": 0.40321481227874756, "learning_rate": 0.00019314324900377648}
-{"ts": "2025-12-27T04:57:39", "event": "train_log", "step": 2692, "epoch": 1.1358649789029536, "progress_pct": 18.93, "epoch_pct": 18.93, "eta": "45:42:46", "max_grad_norm": 1.0, "loss": 0.7780525088310242, "grad_norm": 0.3806784152984619, "learning_rate": 0.00019312575974033327}
-{"ts": "2025-12-27T04:57:55", "event": "train_log", "step": 2694, "epoch": 1.1367088607594937, "progress_pct": 18.95, "epoch_pct": 18.95, "eta": "45:41:21", "max_grad_norm": 1.0, "loss": 0.661472499370575, "grad_norm": 0.43763765692710876, "learning_rate": 0.0001931082489945658}
-{"ts": "2025-12-27T04:58:10", "event": "train_log", "step": 2696, "epoch": 1.1375527426160337, "progress_pct": 18.96, "epoch_pct": 18.96, "eta": "45:39:55", "max_grad_norm": 1.0, "loss": 0.7443127632141113, "grad_norm": 0.45410826802253723, "learning_rate": 0.00019309071677051348}
-{"ts": "2025-12-27T04:58:26", "event": "train_log", "step": 2698, "epoch": 1.1383966244725738, "progress_pct": 18.97, "epoch_pct": 18.97, "eta": "45:38:33", "max_grad_norm": 1.0, "loss": 0.744393527507782, "grad_norm": 0.47907447814941406, "learning_rate": 0.00019307316307222062}
-{"ts": "2025-12-27T04:58:41", "event": "train_log", "step": 2700, "epoch": 1.139240506329114, "progress_pct": 18.99, "epoch_pct": 18.99, "eta": "45:37:09", "max_grad_norm": 1.0, "loss": 0.7042794227600098, "grad_norm": 0.41723814606666565, "learning_rate": 0.00019305558790373654}
-{"ts": "2025-12-27T05:10:00", "event": "train_log", "step": 2700, "epoch": 1.139240506329114, "progress_pct": 18.99, "epoch_pct": 18.99, "eta": "46:25:23", "max_grad_norm": 1.0, "eval_loss": 0.8155058026313782, "eval_runtime": 678.284, "eval_samples_per_second": 3.106, "eval_steps_per_second": 3.106}
-{"ts": "2025-12-27T05:10:15", "event": "train_log", "step": 2702, "epoch": 1.140084388185654, "progress_pct": 19.0, "epoch_pct": 19.0, "eta": "46:23:54", "max_grad_norm": 1.0, "loss": 0.6715745329856873, "grad_norm": 0.3863268196582794, "learning_rate": 0.0001930379912691155}
-{"ts": "2025-12-27T05:10:30", "event": "train_log", "step": 2704, "epoch": 1.140928270042194, "progress_pct": 19.02, "epoch_pct": 19.02, "eta": "46:22:26", "max_grad_norm": 1.0, "loss": 0.6959030628204346, "grad_norm": 0.49994897842407227, "learning_rate": 0.00019302037317241673}
-{"ts": "2025-12-27T05:10:45", "event": "train_log", "step": 2706, "epoch": 1.1417721518987343, "progress_pct": 19.03, "epoch_pct": 19.03, "eta": "46:20:59", "max_grad_norm": 1.0, "loss": 0.6534222364425659, "grad_norm": 0.46377572417259216, "learning_rate": 0.00019300273361770432}
-{"ts": "2025-12-27T05:11:01", "event": "train_log", "step": 2708, "epoch": 1.1426160337552742, "progress_pct": 19.04, "epoch_pct": 19.04, "eta": "46:19:33", "max_grad_norm": 1.0, "loss": 0.6750475764274597, "grad_norm": 0.3841579556465149, "learning_rate": 0.00019298507260904745}
-{"ts": "2025-12-27T05:11:15", "event": "train_log", "step": 2710, "epoch": 1.1434599156118144, "progress_pct": 19.06, "epoch_pct": 19.06, "eta": "46:18:03", "max_grad_norm": 1.0, "loss": 0.7714900374412537, "grad_norm": 0.4171544313430786, "learning_rate": 0.00019296739015052015}
-{"ts": "2025-12-27T05:11:31", "event": "train_log", "step": 2712, "epoch": 1.1443037974683543, "progress_pct": 19.07, "epoch_pct": 19.07, "eta": "46:16:37", "max_grad_norm": 1.0, "loss": 0.7281306982040405, "grad_norm": 0.44384199380874634, "learning_rate": 0.00019294968624620137}
-{"ts": "2025-12-27T05:11:46", "event": "train_log", "step": 2714, "epoch": 1.1451476793248945, "progress_pct": 19.09, "epoch_pct": 19.09, "eta": "46:15:08", "max_grad_norm": 1.0, "loss": 0.7407262325286865, "grad_norm": 0.43345192074775696, "learning_rate": 0.00019293196090017513}
-{"ts": "2025-12-27T05:12:01", "event": "train_log", "step": 2716, "epoch": 1.1459915611814346, "progress_pct": 19.1, "epoch_pct": 19.1, "eta": "46:13:40", "max_grad_norm": 1.0, "loss": 0.6794347167015076, "grad_norm": 0.3897020220756531, "learning_rate": 0.00019291421411653034}
-{"ts": "2025-12-27T05:12:16", "event": "train_log", "step": 2718, "epoch": 1.1468354430379746, "progress_pct": 19.11, "epoch_pct": 19.11, "eta": "46:12:12", "max_grad_norm": 1.0, "loss": 0.7026289105415344, "grad_norm": 0.4289143681526184, "learning_rate": 0.00019289644589936075}
-{"ts": "2025-12-27T05:12:30", "event": "train_log", "step": 2720, "epoch": 1.1476793248945147, "progress_pct": 19.13, "epoch_pct": 19.13, "eta": "46:10:42", "max_grad_norm": 1.0, "loss": 0.7613762617111206, "grad_norm": 0.4783557057380676, "learning_rate": 0.0001928786562527652}
-{"ts": "2025-12-27T05:12:46", "event": "train_log", "step": 2722, "epoch": 1.148523206751055, "progress_pct": 19.14, "epoch_pct": 19.14, "eta": "46:09:18", "max_grad_norm": 1.0, "loss": 0.7123059630393982, "grad_norm": 0.4152112901210785, "learning_rate": 0.00019286084518084745}
-{"ts": "2025-12-27T05:13:01", "event": "train_log", "step": 2724, "epoch": 1.1493670886075948, "progress_pct": 19.16, "epoch_pct": 19.16, "eta": "46:07:49", "max_grad_norm": 1.0, "loss": 0.7198041677474976, "grad_norm": 0.4204908013343811, "learning_rate": 0.0001928430126877161}
-{"ts": "2025-12-27T05:13:16", "event": "train_log", "step": 2726, "epoch": 1.150210970464135, "progress_pct": 19.17, "epoch_pct": 19.17, "eta": "46:06:25", "max_grad_norm": 1.0, "loss": 0.6859839558601379, "grad_norm": 0.41333863139152527, "learning_rate": 0.00019282515877748485}
-{"ts": "2025-12-27T05:13:32", "event": "train_log", "step": 2728, "epoch": 1.1510548523206752, "progress_pct": 19.18, "epoch_pct": 19.18, "eta": "46:04:58", "max_grad_norm": 1.0, "loss": 0.7185758948326111, "grad_norm": 0.4041498005390167, "learning_rate": 0.00019280728345427218}
-{"ts": "2025-12-27T05:13:47", "event": "train_log", "step": 2730, "epoch": 1.1518987341772151, "progress_pct": 19.2, "epoch_pct": 19.2, "eta": "46:03:31", "max_grad_norm": 1.0, "loss": 0.7899971008300781, "grad_norm": 0.4487358629703522, "learning_rate": 0.00019278938672220167}
-{"ts": "2025-12-27T05:14:03", "event": "train_log", "step": 2732, "epoch": 1.1527426160337553, "progress_pct": 19.21, "epoch_pct": 19.21, "eta": "46:02:09", "max_grad_norm": 1.0, "loss": 0.6266586780548096, "grad_norm": 0.3510114252567291, "learning_rate": 0.00019277146858540166}
-{"ts": "2025-12-27T05:14:17", "event": "train_log", "step": 2734, "epoch": 1.1535864978902954, "progress_pct": 19.23, "epoch_pct": 19.23, "eta": "46:00:38", "max_grad_norm": 1.0, "loss": 0.7450110912322998, "grad_norm": 0.4295555055141449, "learning_rate": 0.00019275352904800553}
-{"ts": "2025-12-27T05:14:32", "event": "train_log", "step": 2736, "epoch": 1.1544303797468354, "progress_pct": 19.24, "epoch_pct": 19.24, "eta": "45:59:10", "max_grad_norm": 1.0, "loss": 0.6875549554824829, "grad_norm": 0.40629687905311584, "learning_rate": 0.00019273556811415165}
-{"ts": "2025-12-27T05:14:46", "event": "train_log", "step": 2738, "epoch": 1.1552742616033755, "progress_pct": 19.25, "epoch_pct": 19.25, "eta": "45:57:42", "max_grad_norm": 1.0, "loss": 0.8141522407531738, "grad_norm": 0.4243362247943878, "learning_rate": 0.00019271758578798322}
-{"ts": "2025-12-27T05:15:02", "event": "train_log", "step": 2740, "epoch": 1.1561181434599157, "progress_pct": 19.27, "epoch_pct": 19.27, "eta": "45:56:18", "max_grad_norm": 1.0, "loss": 0.6905186176300049, "grad_norm": 0.483306884765625, "learning_rate": 0.00019269958207364843}
-{"ts": "2025-12-27T05:15:17", "event": "train_log", "step": 2742, "epoch": 1.1569620253164556, "progress_pct": 19.28, "epoch_pct": 19.28, "eta": "45:54:53", "max_grad_norm": 1.0, "loss": 0.6709047555923462, "grad_norm": 0.4303925335407257, "learning_rate": 0.00019268155697530037}
-{"ts": "2025-12-27T05:15:32", "event": "train_log", "step": 2744, "epoch": 1.1578059071729958, "progress_pct": 19.3, "epoch_pct": 19.3, "eta": "45:53:24", "max_grad_norm": 1.0, "loss": 0.7107465863227844, "grad_norm": 0.4533381760120392, "learning_rate": 0.0001926635104970971}
-{"ts": "2025-12-27T05:15:46", "event": "train_log", "step": 2746, "epoch": 1.158649789029536, "progress_pct": 19.31, "epoch_pct": 19.31, "eta": "45:51:55", "max_grad_norm": 1.0, "loss": 0.8043986558914185, "grad_norm": 0.4823286533355713, "learning_rate": 0.0001926454426432016}
-{"ts": "2025-12-27T05:16:01", "event": "train_log", "step": 2748, "epoch": 1.159493670886076, "progress_pct": 19.32, "epoch_pct": 19.32, "eta": "45:50:26", "max_grad_norm": 1.0, "loss": 0.7812165021896362, "grad_norm": 0.3892867863178253, "learning_rate": 0.00019262735341778179}
-{"ts": "2025-12-27T05:16:15", "event": "train_log", "step": 2750, "epoch": 1.160337552742616, "progress_pct": 19.34, "epoch_pct": 19.34, "eta": "45:48:56", "max_grad_norm": 1.0, "loss": 0.7141886353492737, "grad_norm": 0.46737003326416016, "learning_rate": 0.00019260924282501045}
-{"ts": "2025-12-27T05:16:29", "event": "train_log", "step": 2752, "epoch": 1.1611814345991562, "progress_pct": 19.35, "epoch_pct": 19.35, "eta": "45:47:28", "max_grad_norm": 1.0, "loss": 0.7528460621833801, "grad_norm": 0.4335328936576843, "learning_rate": 0.0001925911108690654}
-{"ts": "2025-12-27T05:16:44", "event": "train_log", "step": 2754, "epoch": 1.1620253164556962, "progress_pct": 19.37, "epoch_pct": 19.37, "eta": "45:46:03", "max_grad_norm": 1.0, "loss": 0.7817611694335938, "grad_norm": 0.3792484700679779, "learning_rate": 0.00019257295755412932}
-{"ts": "2025-12-27T05:17:00", "event": "train_log", "step": 2756, "epoch": 1.1628691983122363, "progress_pct": 19.38, "epoch_pct": 19.38, "eta": "45:44:38", "max_grad_norm": 1.0, "loss": 0.6904958486557007, "grad_norm": 0.41246429085731506, "learning_rate": 0.00019255478288438983}
-{"ts": "2025-12-27T05:17:14", "event": "train_log", "step": 2758, "epoch": 1.1637130801687763, "progress_pct": 19.4, "epoch_pct": 19.4, "eta": "45:43:12", "max_grad_norm": 1.0, "loss": 0.7571630477905273, "grad_norm": 0.44368481636047363, "learning_rate": 0.00019253658686403948}
-{"ts": "2025-12-27T05:17:30", "event": "train_log", "step": 2760, "epoch": 1.1645569620253164, "progress_pct": 19.41, "epoch_pct": 19.41, "eta": "45:41:47", "max_grad_norm": 1.0, "loss": 0.6747061014175415, "grad_norm": 0.40121781826019287, "learning_rate": 0.00019251836949727574}
-{"ts": "2025-12-27T05:17:44", "event": "train_log", "step": 2762, "epoch": 1.1654008438818566, "progress_pct": 19.42, "epoch_pct": 19.42, "eta": "45:40:19", "max_grad_norm": 1.0, "loss": 0.7722339034080505, "grad_norm": 0.4660188853740692, "learning_rate": 0.000192500130788301}
-{"ts": "2025-12-27T05:17:59", "event": "train_log", "step": 2764, "epoch": 1.1662447257383965, "progress_pct": 19.44, "epoch_pct": 19.44, "eta": "45:38:54", "max_grad_norm": 1.0, "loss": 0.8081457018852234, "grad_norm": 0.41693782806396484, "learning_rate": 0.0001924818707413226}
-{"ts": "2025-12-27T05:18:14", "event": "train_log", "step": 2766, "epoch": 1.1670886075949367, "progress_pct": 19.45, "epoch_pct": 19.45, "eta": "45:37:28", "max_grad_norm": 1.0, "loss": 0.7745853066444397, "grad_norm": 0.4274570345878601, "learning_rate": 0.00019246358936055274}
-{"ts": "2025-12-27T05:18:29", "event": "train_log", "step": 2768, "epoch": 1.1679324894514769, "progress_pct": 19.47, "epoch_pct": 19.47, "eta": "45:36:04", "max_grad_norm": 1.0, "loss": 0.7918146252632141, "grad_norm": 0.4385969638824463, "learning_rate": 0.00019244528665020863}
-{"ts": "2025-12-27T05:18:45", "event": "train_log", "step": 2770, "epoch": 1.1687763713080168, "progress_pct": 19.48, "epoch_pct": 19.48, "eta": "45:34:42", "max_grad_norm": 1.0, "loss": 0.7382830381393433, "grad_norm": 0.42832866311073303, "learning_rate": 0.00019242696261451234}
-{"ts": "2025-12-27T05:19:02", "event": "train_log", "step": 2772, "epoch": 1.169620253164557, "progress_pct": 19.49, "epoch_pct": 19.49, "eta": "45:33:25", "max_grad_norm": 1.0, "loss": 0.7501721978187561, "grad_norm": 0.44177982211112976, "learning_rate": 0.00019240861725769085}
-{"ts": "2025-12-27T05:19:19", "event": "train_log", "step": 2774, "epoch": 1.1704641350210971, "progress_pct": 19.51, "epoch_pct": 19.51, "eta": "45:32:06", "max_grad_norm": 1.0, "loss": 0.6495388150215149, "grad_norm": 0.4193457365036011, "learning_rate": 0.00019239025058397611}
-{"ts": "2025-12-27T05:19:34", "event": "train_log", "step": 2776, "epoch": 1.171308016877637, "progress_pct": 19.52, "epoch_pct": 19.52, "eta": "45:30:42", "max_grad_norm": 1.0, "loss": 0.8291991353034973, "grad_norm": 0.5145925283432007, "learning_rate": 0.000192371862597605}
-{"ts": "2025-12-27T05:19:51", "event": "train_log", "step": 2778, "epoch": 1.1721518987341772, "progress_pct": 19.54, "epoch_pct": 19.54, "eta": "45:29:25", "max_grad_norm": 1.0, "loss": 0.7491340637207031, "grad_norm": 0.40911251306533813, "learning_rate": 0.00019235345330281914}
-{"ts": "2025-12-27T05:20:07", "event": "train_log", "step": 2780, "epoch": 1.1729957805907172, "progress_pct": 19.55, "epoch_pct": 19.55, "eta": "45:28:07", "max_grad_norm": 1.0, "loss": 0.6315004825592041, "grad_norm": 0.3920276165008545, "learning_rate": 0.0001923350227038653}
-{"ts": "2025-12-27T05:20:23", "event": "train_log", "step": 2782, "epoch": 1.1738396624472573, "progress_pct": 19.56, "epoch_pct": 19.56, "eta": "45:26:44", "max_grad_norm": 1.0, "loss": 0.7538990378379822, "grad_norm": 0.442303329706192, "learning_rate": 0.0001923165708049951}
-{"ts": "2025-12-27T05:20:39", "event": "train_log", "step": 2784, "epoch": 1.1746835443037975, "progress_pct": 19.58, "epoch_pct": 19.58, "eta": "45:25:26", "max_grad_norm": 1.0, "loss": 0.7440794110298157, "grad_norm": 0.4693523049354553, "learning_rate": 0.00019229809761046497}
-{"ts": "2025-12-27T05:20:55", "event": "train_log", "step": 2786, "epoch": 1.1755274261603375, "progress_pct": 19.59, "epoch_pct": 19.59, "eta": "45:24:06", "max_grad_norm": 1.0, "loss": 0.7342568635940552, "grad_norm": 0.4948059618473053, "learning_rate": 0.0001922796031245363}
-{"ts": "2025-12-27T05:21:13", "event": "train_log", "step": 2788, "epoch": 1.1763713080168776, "progress_pct": 19.61, "epoch_pct": 19.61, "eta": "45:22:52", "max_grad_norm": 1.0, "loss": 0.6969661116600037, "grad_norm": 0.3900465965270996, "learning_rate": 0.00019226108735147547}
-{"ts": "2025-12-27T05:21:29", "event": "train_log", "step": 2790, "epoch": 1.1772151898734178, "progress_pct": 19.62, "epoch_pct": 19.62, "eta": "45:21:34", "max_grad_norm": 1.0, "loss": 0.7097541689872742, "grad_norm": 0.36153602600097656, "learning_rate": 0.00019224255029555372}
-{"ts": "2025-12-27T05:21:46", "event": "train_log", "step": 2792, "epoch": 1.1780590717299577, "progress_pct": 19.63, "epoch_pct": 19.63, "eta": "45:20:16", "max_grad_norm": 1.0, "loss": 0.8141831755638123, "grad_norm": 0.41168832778930664, "learning_rate": 0.00019222399196104715}
-{"ts": "2025-12-27T05:22:02", "event": "train_log", "step": 2794, "epoch": 1.1789029535864979, "progress_pct": 19.65, "epoch_pct": 19.65, "eta": "45:18:56", "max_grad_norm": 1.0, "loss": 0.7458863258361816, "grad_norm": 0.4542821943759918, "learning_rate": 0.0001922054123522368}
-{"ts": "2025-12-27T05:22:17", "event": "train_log", "step": 2796, "epoch": 1.179746835443038, "progress_pct": 19.66, "epoch_pct": 19.66, "eta": "45:17:34", "max_grad_norm": 1.0, "loss": 0.6535642147064209, "grad_norm": 0.4026047885417938, "learning_rate": 0.0001921868114734087}
-{"ts": "2025-12-27T05:22:34", "event": "train_log", "step": 2798, "epoch": 1.180590717299578, "progress_pct": 19.68, "epoch_pct": 19.68, "eta": "45:16:16", "max_grad_norm": 1.0, "loss": 0.6248135566711426, "grad_norm": 0.4417034387588501, "learning_rate": 0.0001921681893288537}
-{"ts": "2025-12-27T05:22:50", "event": "train_log", "step": 2800, "epoch": 1.1814345991561181, "progress_pct": 19.69, "epoch_pct": 19.69, "eta": "45:14:59", "max_grad_norm": 1.0, "loss": 0.6777785420417786, "grad_norm": 0.45027074217796326, "learning_rate": 0.00019214954592286748}
-{"ts": "2025-12-27T05:34:19", "event": "train_log", "step": 2800, "epoch": 1.1814345991561181, "progress_pct": 19.69, "epoch_pct": 19.69, "eta": "46:01:47", "max_grad_norm": 1.0, "eval_loss": 0.8124309182167053, "eval_runtime": 688.4759, "eval_samples_per_second": 3.06, "eval_steps_per_second": 3.06}
-{"ts": "2025-12-27T05:34:35", "event": "train_log", "step": 2802, "epoch": 1.1822784810126583, "progress_pct": 19.7, "epoch_pct": 19.7, "eta": "46:00:24", "max_grad_norm": 1.0, "loss": 0.6460301876068115, "grad_norm": 0.406865656375885, "learning_rate": 0.00019213088125975082}
-{"ts": "2025-12-27T05:34:49", "event": "train_log", "step": 2804, "epoch": 1.1831223628691983, "progress_pct": 19.72, "epoch_pct": 19.72, "eta": "45:58:53", "max_grad_norm": 1.0, "loss": 0.7292830944061279, "grad_norm": 0.5052749514579773, "learning_rate": 0.00019211219534380928}
-{"ts": "2025-12-27T05:35:03", "event": "train_log", "step": 2806, "epoch": 1.1839662447257384, "progress_pct": 19.73, "epoch_pct": 19.73, "eta": "45:57:26", "max_grad_norm": 1.0, "loss": 0.7399409413337708, "grad_norm": 0.4028380513191223, "learning_rate": 0.00019209348817935328}
-{"ts": "2025-12-27T05:35:19", "event": "train_log", "step": 2808, "epoch": 1.1848101265822786, "progress_pct": 19.75, "epoch_pct": 19.75, "eta": "45:56:03", "max_grad_norm": 1.0, "loss": 0.6885398030281067, "grad_norm": 0.4522664248943329, "learning_rate": 0.00019207475977069826}
-{"ts": "2025-12-27T05:35:34", "event": "train_log", "step": 2810, "epoch": 1.1856540084388185, "progress_pct": 19.76, "epoch_pct": 19.76, "eta": "45:54:38", "max_grad_norm": 1.0, "loss": 0.6962382197380066, "grad_norm": 0.419546514749527, "learning_rate": 0.0001920560101221645}
-{"ts": "2025-12-27T05:35:49", "event": "train_log", "step": 2812, "epoch": 1.1864978902953587, "progress_pct": 19.77, "epoch_pct": 19.77, "eta": "45:53:11", "max_grad_norm": 1.0, "loss": 0.7380965352058411, "grad_norm": 0.48912352323532104, "learning_rate": 0.00019203723923807715}
-{"ts": "2025-12-27T05:36:03", "event": "train_log", "step": 2814, "epoch": 1.1873417721518988, "progress_pct": 19.79, "epoch_pct": 19.79, "eta": "45:51:43", "max_grad_norm": 1.0, "loss": 0.755382776260376, "grad_norm": 0.40905487537384033, "learning_rate": 0.00019201844712276635}
-{"ts": "2025-12-27T05:36:18", "event": "train_log", "step": 2816, "epoch": 1.1881856540084388, "progress_pct": 19.8, "epoch_pct": 19.8, "eta": "45:50:18", "max_grad_norm": 1.0, "loss": 0.7066168189048767, "grad_norm": 0.385623037815094, "learning_rate": 0.000191999633780567}
-{"ts": "2025-12-27T05:36:33", "event": "train_log", "step": 2818, "epoch": 1.189029535864979, "progress_pct": 19.82, "epoch_pct": 19.82, "eta": "45:48:53", "max_grad_norm": 1.0, "loss": 0.7172947525978088, "grad_norm": 0.4488723576068878, "learning_rate": 0.00019198079921581908}
-{"ts": "2025-12-27T05:36:48", "event": "train_log", "step": 2820, "epoch": 1.189873417721519, "progress_pct": 19.83, "epoch_pct": 19.83, "eta": "45:47:28", "max_grad_norm": 1.0, "loss": 0.6714195013046265, "grad_norm": 0.385277658700943, "learning_rate": 0.00019196194343286727}
-{"ts": "2025-12-27T05:37:03", "event": "train_log", "step": 2822, "epoch": 1.190717299578059, "progress_pct": 19.85, "epoch_pct": 19.85, "eta": "45:46:03", "max_grad_norm": 1.0, "loss": 0.7076966166496277, "grad_norm": 0.4280855655670166, "learning_rate": 0.00019194306643606127}
-{"ts": "2025-12-27T05:37:18", "event": "train_log", "step": 2824, "epoch": 1.1915611814345992, "progress_pct": 19.86, "epoch_pct": 19.86, "eta": "45:44:35", "max_grad_norm": 1.0, "loss": 0.7926747798919678, "grad_norm": 0.4626067578792572, "learning_rate": 0.00019192416822975567}
-{"ts": "2025-12-27T05:37:33", "event": "train_log", "step": 2826, "epoch": 1.1924050632911392, "progress_pct": 19.87, "epoch_pct": 19.87, "eta": "45:43:09", "max_grad_norm": 1.0, "loss": 0.7654290199279785, "grad_norm": 0.3994208574295044, "learning_rate": 0.00019190524881830987}
-{"ts": "2025-12-27T05:37:47", "event": "train_log", "step": 2828, "epoch": 1.1932489451476793, "progress_pct": 19.89, "epoch_pct": 19.89, "eta": "45:41:43", "max_grad_norm": 1.0, "loss": 0.7857998609542847, "grad_norm": 0.47346508502960205, "learning_rate": 0.00019188630820608825}
-{"ts": "2025-12-27T05:38:02", "event": "train_log", "step": 2830, "epoch": 1.1940928270042195, "progress_pct": 19.9, "epoch_pct": 19.9, "eta": "45:40:17", "max_grad_norm": 1.0, "loss": 0.7603738903999329, "grad_norm": 0.446077823638916, "learning_rate": 0.00019186734639746003}
-{"ts": "2025-12-27T05:38:17", "event": "train_log", "step": 2832, "epoch": 1.1949367088607594, "progress_pct": 19.92, "epoch_pct": 19.92, "eta": "45:38:54", "max_grad_norm": 1.0, "loss": 0.790582537651062, "grad_norm": 0.41503727436065674, "learning_rate": 0.00019184836339679936}
-{"ts": "2025-12-27T05:38:32", "event": "train_log", "step": 2834, "epoch": 1.1957805907172996, "progress_pct": 19.93, "epoch_pct": 19.93, "eta": "45:37:30", "max_grad_norm": 1.0, "loss": 0.7229864597320557, "grad_norm": 0.43651700019836426, "learning_rate": 0.00019182935920848522}
-{"ts": "2025-12-27T05:38:47", "event": "train_log", "step": 2836, "epoch": 1.1966244725738397, "progress_pct": 19.94, "epoch_pct": 19.94, "eta": "45:36:03", "max_grad_norm": 1.0, "loss": 0.7817287445068359, "grad_norm": 0.4409031867980957, "learning_rate": 0.00019181033383690153}
-{"ts": "2025-12-27T05:39:02", "event": "train_log", "step": 2838, "epoch": 1.1974683544303797, "progress_pct": 19.96, "epoch_pct": 19.96, "eta": "45:34:40", "max_grad_norm": 1.0, "loss": 0.6342297792434692, "grad_norm": 0.3562015891075134, "learning_rate": 0.0001917912872864371}
-{"ts": "2025-12-27T05:39:17", "event": "train_log", "step": 2840, "epoch": 1.1983122362869199, "progress_pct": 19.97, "epoch_pct": 19.97, "eta": "45:33:15", "max_grad_norm": 1.0, "loss": 0.7065272927284241, "grad_norm": 0.4767192602157593, "learning_rate": 0.00019177221956148555}
-{"ts": "2025-12-27T05:39:33", "event": "train_log", "step": 2842, "epoch": 1.1991561181434598, "progress_pct": 19.99, "epoch_pct": 19.99, "eta": "45:31:54", "max_grad_norm": 1.0, "loss": 0.777110755443573, "grad_norm": 0.45131945610046387, "learning_rate": 0.00019175313066644546}
-{"ts": "2025-12-27T05:39:48", "event": "train_log", "step": 2844, "epoch": 1.2, "progress_pct": 20.0, "epoch_pct": 20.0, "eta": "45:30:30", "max_grad_norm": 1.0, "loss": 0.7456457018852234, "grad_norm": 0.47566652297973633, "learning_rate": 0.00019173402060572027}
-{"ts": "2025-12-27T05:40:02", "event": "train_log", "step": 2846, "epoch": 1.2008438818565401, "progress_pct": 20.01, "epoch_pct": 20.01, "eta": "45:29:03", "max_grad_norm": 1.0, "loss": 0.8041547536849976, "grad_norm": 0.48909857869148254, "learning_rate": 0.00019171488938371834}
-{"ts": "2025-12-27T05:40:17", "event": "train_log", "step": 2848, "epoch": 1.20168776371308, "progress_pct": 20.03, "epoch_pct": 20.03, "eta": "45:27:40", "max_grad_norm": 1.0, "loss": 0.6786676049232483, "grad_norm": 0.436591774225235, "learning_rate": 0.00019169573700485284}
-{"ts": "2025-12-27T05:40:32", "event": "train_log", "step": 2850, "epoch": 1.2025316455696202, "progress_pct": 20.04, "epoch_pct": 20.04, "eta": "45:26:14", "max_grad_norm": 1.0, "loss": 0.7661880850791931, "grad_norm": 0.44230160117149353, "learning_rate": 0.00019167656347354183}
-{"ts": "2025-12-27T05:40:46", "event": "train_log", "step": 2852, "epoch": 1.2033755274261604, "progress_pct": 20.06, "epoch_pct": 20.06, "eta": "45:24:49", "max_grad_norm": 1.0, "loss": 0.7369645833969116, "grad_norm": 0.4844048321247101, "learning_rate": 0.00019165736879420836}
-{"ts": "2025-12-27T05:41:01", "event": "train_log", "step": 2854, "epoch": 1.2042194092827003, "progress_pct": 20.07, "epoch_pct": 20.07, "eta": "45:23:23", "max_grad_norm": 1.0, "loss": 0.7776681184768677, "grad_norm": 0.4272955060005188, "learning_rate": 0.0001916381529712802}
-{"ts": "2025-12-27T05:41:15", "event": "train_log", "step": 2856, "epoch": 1.2050632911392405, "progress_pct": 20.08, "epoch_pct": 20.08, "eta": "45:21:57", "max_grad_norm": 1.0, "loss": 0.8019667267799377, "grad_norm": 0.42392730712890625, "learning_rate": 0.00019161891600919008}
-{"ts": "2025-12-27T05:41:29", "event": "train_log", "step": 2858, "epoch": 1.2059071729957807, "progress_pct": 20.1, "epoch_pct": 20.1, "eta": "45:20:31", "max_grad_norm": 1.0, "loss": 0.7811952233314514, "grad_norm": 0.4528326988220215, "learning_rate": 0.00019159965791237565}
-{"ts": "2025-12-27T05:41:45", "event": "train_log", "step": 2860, "epoch": 1.2067510548523206, "progress_pct": 20.11, "epoch_pct": 20.11, "eta": "45:19:09", "max_grad_norm": 1.0, "loss": 0.7244279980659485, "grad_norm": 0.42840948700904846, "learning_rate": 0.00019158037868527932}
-{"ts": "2025-12-27T05:42:00", "event": "train_log", "step": 2862, "epoch": 1.2075949367088608, "progress_pct": 20.13, "epoch_pct": 20.13, "eta": "45:17:45", "max_grad_norm": 1.0, "loss": 0.7675760984420776, "grad_norm": 0.4291226863861084, "learning_rate": 0.00019156107833234845}
-{"ts": "2025-12-27T05:42:14", "event": "train_log", "step": 2864, "epoch": 1.208438818565401, "progress_pct": 20.14, "epoch_pct": 20.14, "eta": "45:16:21", "max_grad_norm": 1.0, "loss": 0.7071483135223389, "grad_norm": 0.4455093443393707, "learning_rate": 0.00019154175685803527}
-{"ts": "2025-12-27T05:42:29", "event": "train_log", "step": 2866, "epoch": 1.2092827004219409, "progress_pct": 20.15, "epoch_pct": 20.15, "eta": "45:14:58", "max_grad_norm": 1.0, "loss": 0.7554603815078735, "grad_norm": 0.41356268525123596, "learning_rate": 0.00019152241426679688}
-{"ts": "2025-12-27T05:42:44", "event": "train_log", "step": 2868, "epoch": 1.210126582278481, "progress_pct": 20.17, "epoch_pct": 20.17, "eta": "45:13:35", "max_grad_norm": 1.0, "loss": 0.7198356986045837, "grad_norm": 0.43875646591186523, "learning_rate": 0.00019150305056309525}
-{"ts": "2025-12-27T05:42:59", "event": "train_log", "step": 2870, "epoch": 1.2109704641350212, "progress_pct": 20.18, "epoch_pct": 20.18, "eta": "45:12:11", "max_grad_norm": 1.0, "loss": 0.7393195629119873, "grad_norm": 0.454356849193573, "learning_rate": 0.0001914836657513972}
-{"ts": "2025-12-27T05:43:14", "event": "train_log", "step": 2872, "epoch": 1.2118143459915611, "progress_pct": 20.2, "epoch_pct": 20.2, "eta": "45:10:48", "max_grad_norm": 1.0, "loss": 0.7277671694755554, "grad_norm": 0.37668535113334656, "learning_rate": 0.00019146425983617444}
-{"ts": "2025-12-27T05:43:30", "event": "train_log", "step": 2874, "epoch": 1.2126582278481013, "progress_pct": 20.21, "epoch_pct": 20.21, "eta": "45:09:28", "max_grad_norm": 1.0, "loss": 0.6783158183097839, "grad_norm": 0.37869662046432495, "learning_rate": 0.00019144483282190354}
-{"ts": "2025-12-27T05:43:46", "event": "train_log", "step": 2876, "epoch": 1.2135021097046415, "progress_pct": 20.23, "epoch_pct": 20.23, "eta": "45:08:10", "max_grad_norm": 1.0, "loss": 0.7024772763252258, "grad_norm": 0.4333525002002716, "learning_rate": 0.00019142538471306596}
-{"ts": "2025-12-27T05:44:00", "event": "train_log", "step": 2878, "epoch": 1.2143459915611814, "progress_pct": 20.24, "epoch_pct": 20.24, "eta": "45:06:46", "max_grad_norm": 1.0, "loss": 0.7387984395027161, "grad_norm": 0.4693842828273773, "learning_rate": 0.00019140591551414796}
-{"ts": "2025-12-27T05:44:16", "event": "train_log", "step": 2880, "epoch": 1.2151898734177216, "progress_pct": 20.25, "epoch_pct": 20.25, "eta": "45:05:24", "max_grad_norm": 1.0, "loss": 0.7597174644470215, "grad_norm": 0.432640939950943, "learning_rate": 0.00019138642522964074}
-{"ts": "2025-12-27T05:44:30", "event": "train_log", "step": 2882, "epoch": 1.2160337552742617, "progress_pct": 20.27, "epoch_pct": 20.27, "eta": "45:03:59", "max_grad_norm": 1.0, "loss": 0.7884587049484253, "grad_norm": 0.432477205991745, "learning_rate": 0.00019136691386404032}
-{"ts": "2025-12-27T05:44:46", "event": "train_log", "step": 2884, "epoch": 1.2168776371308017, "progress_pct": 20.28, "epoch_pct": 20.28, "eta": "45:02:40", "max_grad_norm": 1.0, "loss": 0.6873269081115723, "grad_norm": 0.39305904507637024, "learning_rate": 0.00019134738142184763}
-{"ts": "2025-12-27T05:45:01", "event": "train_log", "step": 2886, "epoch": 1.2177215189873418, "progress_pct": 20.3, "epoch_pct": 20.3, "eta": "45:01:18", "max_grad_norm": 1.0, "loss": 0.6523491144180298, "grad_norm": 0.4485352635383606, "learning_rate": 0.00019132782790756838}
-{"ts": "2025-12-27T05:45:15", "event": "train_log", "step": 2888, "epoch": 1.2185654008438818, "progress_pct": 20.31, "epoch_pct": 20.31, "eta": "44:59:54", "max_grad_norm": 1.0, "loss": 0.7383941411972046, "grad_norm": 0.4480868875980377, "learning_rate": 0.00019130825332571322}
-{"ts": "2025-12-27T05:45:30", "event": "train_log", "step": 2890, "epoch": 1.219409282700422, "progress_pct": 20.32, "epoch_pct": 20.32, "eta": "44:58:33", "max_grad_norm": 1.0, "loss": 0.7391335964202881, "grad_norm": 0.44085049629211426, "learning_rate": 0.00019128865768079764}
-{"ts": "2025-12-27T05:45:45", "event": "train_log", "step": 2892, "epoch": 1.220253164556962, "progress_pct": 20.34, "epoch_pct": 20.34, "eta": "44:57:10", "max_grad_norm": 1.0, "loss": 0.7282017469406128, "grad_norm": 0.4621105492115021, "learning_rate": 0.00019126904097734198}
-{"ts": "2025-12-27T05:46:01", "event": "train_log", "step": 2894, "epoch": 1.221097046413502, "progress_pct": 20.35, "epoch_pct": 20.35, "eta": "44:55:51", "max_grad_norm": 1.0, "loss": 0.7554038763046265, "grad_norm": 0.41478198766708374, "learning_rate": 0.00019124940321987136}
-{"ts": "2025-12-27T05:46:15", "event": "train_log", "step": 2896, "epoch": 1.2219409282700422, "progress_pct": 20.37, "epoch_pct": 20.37, "eta": "44:54:28", "max_grad_norm": 1.0, "loss": 0.6826799511909485, "grad_norm": 0.4143751263618469, "learning_rate": 0.00019122974441291595}
-{"ts": "2025-12-27T05:46:31", "event": "train_log", "step": 2898, "epoch": 1.2227848101265824, "progress_pct": 20.38, "epoch_pct": 20.38, "eta": "44:53:08", "max_grad_norm": 1.0, "loss": 0.751000702381134, "grad_norm": 0.45392894744873047, "learning_rate": 0.00019121006456101057}
-{"ts": "2025-12-27T05:46:45", "event": "train_log", "step": 2900, "epoch": 1.2236286919831223, "progress_pct": 20.39, "epoch_pct": 20.39, "eta": "44:51:45", "max_grad_norm": 1.0, "loss": 0.7598516941070557, "grad_norm": 0.46946296095848083, "learning_rate": 0.00019119036366869506}
-{"ts": "2025-12-27T05:58:11", "event": "train_log", "step": 2900, "epoch": 1.2236286919831223, "progress_pct": 20.39, "epoch_pct": 20.39, "eta": "45:36:22", "max_grad_norm": 1.0, "eval_loss": 0.8077136278152466, "eval_runtime": 685.6042, "eval_samples_per_second": 3.073, "eval_steps_per_second": 3.073}
-{"ts": "2025-12-27T05:58:26", "event": "train_log", "step": 2902, "epoch": 1.2244725738396625, "progress_pct": 20.41, "epoch_pct": 20.41, "eta": "45:34:58", "max_grad_norm": 1.0, "loss": 0.7518358826637268, "grad_norm": 0.4316656291484833, "learning_rate": 0.00019117064174051395}
-{"ts": "2025-12-27T05:58:42", "event": "train_log", "step": 2904, "epoch": 1.2253164556962026, "progress_pct": 20.42, "epoch_pct": 20.42, "eta": "45:33:37", "max_grad_norm": 1.0, "loss": 0.7308215498924255, "grad_norm": 0.47737377882003784, "learning_rate": 0.0001911508987810168}
-{"ts": "2025-12-27T05:58:57", "event": "train_log", "step": 2906, "epoch": 1.2261603375527426, "progress_pct": 20.44, "epoch_pct": 20.44, "eta": "45:32:17", "max_grad_norm": 1.0, "loss": 0.6996226906776428, "grad_norm": 0.40906062722206116, "learning_rate": 0.00019113113479475783}
-{"ts": "2025-12-27T05:59:13", "event": "train_log", "step": 2908, "epoch": 1.2270042194092827, "progress_pct": 20.45, "epoch_pct": 20.45, "eta": "45:30:54", "max_grad_norm": 1.0, "loss": 0.8364415168762207, "grad_norm": 0.517085075378418, "learning_rate": 0.00019111134978629633}
-{"ts": "2025-12-27T05:59:28", "event": "train_log", "step": 2910, "epoch": 1.2278481012658227, "progress_pct": 20.46, "epoch_pct": 20.46, "eta": "45:29:33", "max_grad_norm": 1.0, "loss": 0.722011923789978, "grad_norm": 0.425581693649292, "learning_rate": 0.00019109154376019624}
-{"ts": "2025-12-27T05:59:43", "event": "train_log", "step": 2912, "epoch": 1.2286919831223628, "progress_pct": 20.48, "epoch_pct": 20.48, "eta": "45:28:09", "max_grad_norm": 1.0, "loss": 0.7586172223091125, "grad_norm": 0.4651593565940857, "learning_rate": 0.00019107171672102643}
-{"ts": "2025-12-27T05:59:58", "event": "train_log", "step": 2914, "epoch": 1.229535864978903, "progress_pct": 20.49, "epoch_pct": 20.49, "eta": "45:26:46", "max_grad_norm": 1.0, "loss": 0.7387955188751221, "grad_norm": 0.4578891396522522, "learning_rate": 0.00019105186867336067}
-{"ts": "2025-12-27T06:00:14", "event": "train_log", "step": 2916, "epoch": 1.230379746835443, "progress_pct": 20.51, "epoch_pct": 20.51, "eta": "45:25:26", "max_grad_norm": 1.0, "loss": 0.8036285638809204, "grad_norm": 0.4312961995601654, "learning_rate": 0.00019103199962177748}
-{"ts": "2025-12-27T06:00:29", "event": "train_log", "step": 2918, "epoch": 1.231223628691983, "progress_pct": 20.52, "epoch_pct": 20.52, "eta": "45:24:06", "max_grad_norm": 1.0, "loss": 0.7356550097465515, "grad_norm": 0.4355425536632538, "learning_rate": 0.00019101210957086026}
-{"ts": "2025-12-27T06:00:45", "event": "train_log", "step": 2920, "epoch": 1.2320675105485233, "progress_pct": 20.53, "epoch_pct": 20.53, "eta": "45:22:44", "max_grad_norm": 1.0, "loss": 0.6730139255523682, "grad_norm": 0.424675852060318, "learning_rate": 0.00019099219852519733}
-{"ts": "2025-12-27T06:01:01", "event": "train_log", "step": 2922, "epoch": 1.2329113924050632, "progress_pct": 20.55, "epoch_pct": 20.55, "eta": "45:21:25", "max_grad_norm": 1.0, "loss": 0.6983892321586609, "grad_norm": 0.41102367639541626, "learning_rate": 0.0001909722664893817}
-{"ts": "2025-12-27T06:01:17", "event": "train_log", "step": 2924, "epoch": 1.2337552742616034, "progress_pct": 20.56, "epoch_pct": 20.56, "eta": "45:20:08", "max_grad_norm": 1.0, "loss": 0.6297144889831543, "grad_norm": 0.4088250398635864, "learning_rate": 0.00019095231346801132}
-{"ts": "2025-12-27T06:01:33", "event": "train_log", "step": 2926, "epoch": 1.2345991561181435, "progress_pct": 20.58, "epoch_pct": 20.58, "eta": "45:18:50", "max_grad_norm": 1.0, "loss": 0.7035690546035767, "grad_norm": 0.3685890734195709, "learning_rate": 0.00019093233946568906}
-{"ts": "2025-12-27T06:01:50", "event": "train_log", "step": 2928, "epoch": 1.2354430379746835, "progress_pct": 20.59, "epoch_pct": 20.59, "eta": "45:17:33", "max_grad_norm": 1.0, "loss": 0.820853054523468, "grad_norm": 0.39438629150390625, "learning_rate": 0.0001909123444870224}
-{"ts": "2025-12-27T06:02:04", "event": "train_log", "step": 2930, "epoch": 1.2362869198312236, "progress_pct": 20.6, "epoch_pct": 20.6, "eta": "45:16:09", "max_grad_norm": 1.0, "loss": 0.7884082794189453, "grad_norm": 0.5041676163673401, "learning_rate": 0.00019089232853662392}
-{"ts": "2025-12-27T06:02:19", "event": "train_log", "step": 2932, "epoch": 1.2371308016877638, "progress_pct": 20.62, "epoch_pct": 20.62, "eta": "45:14:47", "max_grad_norm": 1.0, "loss": 0.773978590965271, "grad_norm": 0.40592801570892334, "learning_rate": 0.00019087229161911086}
-{"ts": "2025-12-27T06:02:35", "event": "train_log", "step": 2934, "epoch": 1.2379746835443037, "progress_pct": 20.63, "epoch_pct": 20.63, "eta": "45:13:29", "max_grad_norm": 1.0, "loss": 0.6742141842842102, "grad_norm": 0.41828030347824097, "learning_rate": 0.00019085223373910536}
-{"ts": "2025-12-27T06:02:50", "event": "train_log", "step": 2936, "epoch": 1.238818565400844, "progress_pct": 20.65, "epoch_pct": 20.65, "eta": "45:12:05", "max_grad_norm": 1.0, "loss": 0.7106125950813293, "grad_norm": 0.39984026551246643, "learning_rate": 0.0001908321549012344}
-{"ts": "2025-12-27T06:03:05", "event": "train_log", "step": 2938, "epoch": 1.239662447257384, "progress_pct": 20.66, "epoch_pct": 20.66, "eta": "45:10:42", "max_grad_norm": 1.0, "loss": 0.7390915751457214, "grad_norm": 0.4841296970844269, "learning_rate": 0.00019081205511012973}
-{"ts": "2025-12-27T06:03:21", "event": "train_log", "step": 2940, "epoch": 1.240506329113924, "progress_pct": 20.68, "epoch_pct": 20.68, "eta": "45:09:27", "max_grad_norm": 1.0, "loss": 0.6527198553085327, "grad_norm": 0.39837637543678284, "learning_rate": 0.00019079193437042806}
-{"ts": "2025-12-27T06:03:37", "event": "train_log", "step": 2942, "epoch": 1.2413502109704642, "progress_pct": 20.69, "epoch_pct": 20.69, "eta": "45:08:07", "max_grad_norm": 1.0, "loss": 0.6939712762832642, "grad_norm": 0.40916863083839417, "learning_rate": 0.0001907717926867708}
-{"ts": "2025-12-27T06:03:52", "event": "train_log", "step": 2944, "epoch": 1.2421940928270043, "progress_pct": 20.7, "epoch_pct": 20.7, "eta": "45:06:46", "max_grad_norm": 1.0, "loss": 0.7566131353378296, "grad_norm": 0.4329306483268738, "learning_rate": 0.0001907516300638043}
-{"ts": "2025-12-27T06:04:08", "event": "train_log", "step": 2946, "epoch": 1.2430379746835443, "progress_pct": 20.72, "epoch_pct": 20.72, "eta": "45:05:26", "max_grad_norm": 1.0, "loss": 0.7893748879432678, "grad_norm": 0.47983601689338684, "learning_rate": 0.00019073144650617963}
-{"ts": "2025-12-27T06:04:23", "event": "train_log", "step": 2948, "epoch": 1.2438818565400844, "progress_pct": 20.73, "epoch_pct": 20.73, "eta": "45:04:07", "max_grad_norm": 1.0, "loss": 0.8259525299072266, "grad_norm": 0.4368246793746948, "learning_rate": 0.0001907112420185528}
-{"ts": "2025-12-27T06:04:38", "event": "train_log", "step": 2950, "epoch": 1.2447257383966246, "progress_pct": 20.75, "epoch_pct": 20.75, "eta": "45:02:45", "max_grad_norm": 1.0, "loss": 0.734692394733429, "grad_norm": 0.41272372007369995, "learning_rate": 0.0001906910166055846}
-{"ts": "2025-12-27T06:04:53", "event": "train_log", "step": 2952, "epoch": 1.2455696202531645, "progress_pct": 20.76, "epoch_pct": 20.76, "eta": "45:01:23", "max_grad_norm": 1.0, "loss": 0.7091750502586365, "grad_norm": 0.36929839849472046, "learning_rate": 0.00019067077027194057}
-{"ts": "2025-12-27T06:05:08", "event": "train_log", "step": 2954, "epoch": 1.2464135021097047, "progress_pct": 20.77, "epoch_pct": 20.77, "eta": "45:00:01", "max_grad_norm": 1.0, "loss": 0.6960210204124451, "grad_norm": 0.4395252466201782, "learning_rate": 0.00019065050302229125}
-{"ts": "2025-12-27T06:05:22", "event": "train_log", "step": 2956, "epoch": 1.2472573839662446, "progress_pct": 20.79, "epoch_pct": 20.79, "eta": "44:58:36", "max_grad_norm": 1.0, "loss": 0.7817115187644958, "grad_norm": 0.46784868836402893, "learning_rate": 0.00019063021486131186}
-{"ts": "2025-12-27T06:05:37", "event": "train_log", "step": 2958, "epoch": 1.2481012658227848, "progress_pct": 20.8, "epoch_pct": 20.8, "eta": "44:57:14", "max_grad_norm": 1.0, "loss": 0.7933676242828369, "grad_norm": 0.4191588759422302, "learning_rate": 0.00019060990579368244}
-{"ts": "2025-12-27T06:05:51", "event": "train_log", "step": 2960, "epoch": 1.248945147679325, "progress_pct": 20.82, "epoch_pct": 20.82, "eta": "44:55:53", "max_grad_norm": 1.0, "loss": 0.6856688857078552, "grad_norm": 0.3967524468898773, "learning_rate": 0.000190589575824088}
-{"ts": "2025-12-27T06:06:07", "event": "train_log", "step": 2962, "epoch": 1.249789029535865, "progress_pct": 20.83, "epoch_pct": 20.83, "eta": "44:54:33", "max_grad_norm": 1.0, "loss": 0.6783818602561951, "grad_norm": 0.40346091985702515, "learning_rate": 0.0001905692249572182}
-{"ts": "2025-12-27T06:06:22", "event": "train_log", "step": 2964, "epoch": 1.250632911392405, "progress_pct": 20.84, "epoch_pct": 20.84, "eta": "44:53:14", "max_grad_norm": 1.0, "loss": 0.6997019052505493, "grad_norm": 0.38349980115890503, "learning_rate": 0.0001905488531977676}
-{"ts": "2025-12-27T06:06:37", "event": "train_log", "step": 2966, "epoch": 1.2514767932489452, "progress_pct": 20.86, "epoch_pct": 20.86, "eta": "44:51:54", "max_grad_norm": 1.0, "loss": 0.6978800892829895, "grad_norm": 0.44021397829055786, "learning_rate": 0.0001905284605504356}
-{"ts": "2025-12-27T06:06:53", "event": "train_log", "step": 2968, "epoch": 1.2523206751054852, "progress_pct": 20.87, "epoch_pct": 20.87, "eta": "44:50:34", "max_grad_norm": 1.0, "loss": 0.7007693648338318, "grad_norm": 0.47491583228111267, "learning_rate": 0.0001905080470199264}
-{"ts": "2025-12-27T06:07:08", "event": "train_log", "step": 2970, "epoch": 1.2531645569620253, "progress_pct": 20.89, "epoch_pct": 20.89, "eta": "44:49:15", "max_grad_norm": 1.0, "loss": 0.7258896231651306, "grad_norm": 0.4011451005935669, "learning_rate": 0.00019048761261094898}
-{"ts": "2025-12-27T06:07:23", "event": "train_log", "step": 2972, "epoch": 1.2540084388185653, "progress_pct": 20.9, "epoch_pct": 20.9, "eta": "44:47:54", "max_grad_norm": 1.0, "loss": 0.6746299266815186, "grad_norm": 0.44206640124320984, "learning_rate": 0.0001904671573282172}
-{"ts": "2025-12-27T06:07:38", "event": "train_log", "step": 2974, "epoch": 1.2548523206751054, "progress_pct": 20.91, "epoch_pct": 20.91, "eta": "44:46:36", "max_grad_norm": 1.0, "loss": 0.7638527154922485, "grad_norm": 0.4532456696033478, "learning_rate": 0.00019044668117644965}
-{"ts": "2025-12-27T06:07:53", "event": "train_log", "step": 2976, "epoch": 1.2556962025316456, "progress_pct": 20.93, "epoch_pct": 20.93, "eta": "44:45:13", "max_grad_norm": 1.0, "loss": 0.659598171710968, "grad_norm": 0.44301095604896545, "learning_rate": 0.00019042618416036984}
-{"ts": "2025-12-27T06:08:08", "event": "train_log", "step": 2978, "epoch": 1.2565400843881855, "progress_pct": 20.94, "epoch_pct": 20.94, "eta": "44:43:52", "max_grad_norm": 1.0, "loss": 0.7132709622383118, "grad_norm": 0.37427952885627747, "learning_rate": 0.00019040566628470597}
-{"ts": "2025-12-27T06:08:22", "event": "train_log", "step": 2980, "epoch": 1.2573839662447257, "progress_pct": 20.96, "epoch_pct": 20.96, "eta": "44:42:30", "max_grad_norm": 1.0, "loss": 0.8163022398948669, "grad_norm": 0.4195408821105957, "learning_rate": 0.0001903851275541912}
-{"ts": "2025-12-27T06:08:37", "event": "train_log", "step": 2982, "epoch": 1.2582278481012659, "progress_pct": 20.97, "epoch_pct": 20.97, "eta": "44:41:10", "max_grad_norm": 1.0, "loss": 0.7481505870819092, "grad_norm": 0.3951880633831024, "learning_rate": 0.00019036456797356336}
-{"ts": "2025-12-27T06:08:53", "event": "train_log", "step": 2984, "epoch": 1.2590717299578058, "progress_pct": 20.98, "epoch_pct": 20.98, "eta": "44:39:53", "max_grad_norm": 1.0, "loss": 0.750126838684082, "grad_norm": 0.4239100217819214, "learning_rate": 0.00019034398754756522}
-{"ts": "2025-12-27T06:09:08", "event": "train_log", "step": 2986, "epoch": 1.259915611814346, "progress_pct": 21.0, "epoch_pct": 21.0, "eta": "44:38:32", "max_grad_norm": 1.0, "loss": 0.746433436870575, "grad_norm": 0.4209354817867279, "learning_rate": 0.0001903233862809442}
-{"ts": "2025-12-27T06:09:22", "event": "train_log", "step": 2988, "epoch": 1.2607594936708861, "progress_pct": 21.01, "epoch_pct": 21.01, "eta": "44:37:12", "max_grad_norm": 1.0, "loss": 0.7104454040527344, "grad_norm": 0.4188138544559479, "learning_rate": 0.00019030276417845266}
-{"ts": "2025-12-27T06:09:38", "event": "train_log", "step": 2990, "epoch": 1.261603375527426, "progress_pct": 21.03, "epoch_pct": 21.03, "eta": "44:35:52", "max_grad_norm": 1.0, "loss": 0.650738000869751, "grad_norm": 0.4531371593475342, "learning_rate": 0.00019028212124484772}
-{"ts": "2025-12-27T06:09:53", "event": "train_log", "step": 2992, "epoch": 1.2624472573839662, "progress_pct": 21.04, "epoch_pct": 21.04, "eta": "44:34:35", "max_grad_norm": 1.0, "loss": 0.6870551109313965, "grad_norm": 0.4672204256057739, "learning_rate": 0.00019026145748489133}
-{"ts": "2025-12-27T06:10:08", "event": "train_log", "step": 2994, "epoch": 1.2632911392405064, "progress_pct": 21.05, "epoch_pct": 21.05, "eta": "44:33:16", "max_grad_norm": 1.0, "loss": 0.6879403591156006, "grad_norm": 0.40681278705596924, "learning_rate": 0.00019024077290335018}
-{"ts": "2025-12-27T06:10:23", "event": "train_log", "step": 2996, "epoch": 1.2641350210970463, "progress_pct": 21.07, "epoch_pct": 21.07, "eta": "44:31:56", "max_grad_norm": 1.0, "loss": 0.6886372566223145, "grad_norm": 0.4491691291332245, "learning_rate": 0.00019022006750499585}
-{"ts": "2025-12-27T06:10:38", "event": "train_log", "step": 2998, "epoch": 1.2649789029535865, "progress_pct": 21.08, "epoch_pct": 21.08, "eta": "44:30:36", "max_grad_norm": 1.0, "loss": 0.7199324369430542, "grad_norm": 0.4144807457923889, "learning_rate": 0.0001901993412946046}
-{"ts": "2025-12-27T06:10:53", "event": "train_log", "step": 3000, "epoch": 1.2658227848101267, "progress_pct": 21.1, "epoch_pct": 21.1, "eta": "44:29:16", "max_grad_norm": 1.0, "loss": 0.7105490565299988, "grad_norm": 0.40370482206344604, "learning_rate": 0.0001901785942769577}
-{"ts": "2025-12-27T06:22:11", "event": "train_log", "step": 3000, "epoch": 1.2658227848101267, "progress_pct": 21.1, "epoch_pct": 21.1, "eta": "45:11:34", "max_grad_norm": 1.0, "eval_loss": 0.8033165335655212, "eval_runtime": 678.7554, "eval_samples_per_second": 3.104, "eval_steps_per_second": 3.104}
-{"ts": "2025-12-27T06:22:28", "event": "train_log", "step": 3002, "epoch": 1.2666666666666666, "progress_pct": 21.11, "epoch_pct": 21.11, "eta": "45:10:18", "max_grad_norm": 1.0, "loss": 0.7385403513908386, "grad_norm": 0.42637890577316284, "learning_rate": 0.00019015782645684097}
-{"ts": "2025-12-27T06:22:45", "event": "train_log", "step": 3004, "epoch": 1.2675105485232068, "progress_pct": 21.13, "epoch_pct": 21.13, "eta": "45:09:04", "max_grad_norm": 1.0, "loss": 0.6395129561424255, "grad_norm": 0.3709809482097626, "learning_rate": 0.00019013703783904518}
-{"ts": "2025-12-27T06:23:00", "event": "train_log", "step": 3006, "epoch": 1.268354430379747, "progress_pct": 21.14, "epoch_pct": 21.14, "eta": "45:07:45", "max_grad_norm": 1.0, "loss": 0.7123657464981079, "grad_norm": 0.4642501175403595, "learning_rate": 0.00019011622842836592}
-{"ts": "2025-12-27T06:23:15", "event": "train_log", "step": 3008, "epoch": 1.2691983122362869, "progress_pct": 21.15, "epoch_pct": 21.15, "eta": "45:06:23", "max_grad_norm": 1.0, "loss": 0.744048535823822, "grad_norm": 0.4553911089897156, "learning_rate": 0.00019009539822960342}
-{"ts": "2025-12-27T06:23:31", "event": "train_log", "step": 3010, "epoch": 1.270042194092827, "progress_pct": 21.17, "epoch_pct": 21.17, "eta": "45:05:07", "max_grad_norm": 1.0, "loss": 0.7181914448738098, "grad_norm": 0.39334386587142944, "learning_rate": 0.0001900745472475629}
-{"ts": "2025-12-27T06:23:47", "event": "train_log", "step": 3012, "epoch": 1.2708860759493672, "progress_pct": 21.18, "epoch_pct": 21.18, "eta": "45:03:50", "max_grad_norm": 1.0, "loss": 0.7238107919692993, "grad_norm": 0.40902766585350037, "learning_rate": 0.00019005367548705426}
-{"ts": "2025-12-27T06:24:03", "event": "train_log", "step": 3014, "epoch": 1.2717299578059071, "progress_pct": 21.2, "epoch_pct": 21.2, "eta": "45:02:30", "max_grad_norm": 1.0, "loss": 0.7479744553565979, "grad_norm": 0.48296019434928894, "learning_rate": 0.00019003278295289216}
-{"ts": "2025-12-27T06:24:18", "event": "train_log", "step": 3016, "epoch": 1.2725738396624473, "progress_pct": 21.21, "epoch_pct": 21.21, "eta": "45:01:11", "max_grad_norm": 1.0, "loss": 0.829924464225769, "grad_norm": 0.4807029962539673, "learning_rate": 0.00019001186964989617}
-{"ts": "2025-12-27T06:24:34", "event": "train_log", "step": 3018, "epoch": 1.2734177215189875, "progress_pct": 21.22, "epoch_pct": 21.22, "eta": "44:59:52", "max_grad_norm": 1.0, "loss": 0.7204707264900208, "grad_norm": 0.4239083528518677, "learning_rate": 0.00018999093558289055}
-{"ts": "2025-12-27T06:24:50", "event": "train_log", "step": 3020, "epoch": 1.2742616033755274, "progress_pct": 21.24, "epoch_pct": 21.24, "eta": "44:58:36", "max_grad_norm": 1.0, "loss": 0.7668164968490601, "grad_norm": 0.4687928259372711, "learning_rate": 0.0001899699807567044}
-{"ts": "2025-12-27T06:25:06", "event": "train_log", "step": 3022, "epoch": 1.2751054852320676, "progress_pct": 21.25, "epoch_pct": 21.25, "eta": "44:57:19", "max_grad_norm": 1.0, "loss": 0.766342043876648, "grad_norm": 0.41724732518196106, "learning_rate": 0.0001899490051761716}
-{"ts": "2025-12-27T06:25:22", "event": "train_log", "step": 3024, "epoch": 1.2759493670886077, "progress_pct": 21.27, "epoch_pct": 21.27, "eta": "44:56:02", "max_grad_norm": 1.0, "loss": 0.6595507860183716, "grad_norm": 0.4131613075733185, "learning_rate": 0.00018992800884613082}
-{"ts": "2025-12-27T06:25:38", "event": "train_log", "step": 3026, "epoch": 1.2767932489451477, "progress_pct": 21.28, "epoch_pct": 21.28, "eta": "44:54:47", "max_grad_norm": 1.0, "loss": 0.7419850826263428, "grad_norm": 0.4156053364276886, "learning_rate": 0.00018990699177142548}
-{"ts": "2025-12-27T06:25:56", "event": "train_log", "step": 3028, "epoch": 1.2776371308016878, "progress_pct": 21.29, "epoch_pct": 21.29, "eta": "44:53:37", "max_grad_norm": 1.0, "loss": 0.67264324426651, "grad_norm": 0.41845977306365967, "learning_rate": 0.00018988595395690388}
-{"ts": "2025-12-27T06:26:12", "event": "train_log", "step": 3030, "epoch": 1.2784810126582278, "progress_pct": 21.31, "epoch_pct": 21.31, "eta": "44:52:21", "max_grad_norm": 1.0, "loss": 0.6269281506538391, "grad_norm": 0.3826757073402405, "learning_rate": 0.00018986489540741893}
-{"ts": "2025-12-27T06:26:28", "event": "train_log", "step": 3032, "epoch": 1.279324894514768, "progress_pct": 21.32, "epoch_pct": 21.32, "eta": "44:51:05", "max_grad_norm": 1.0, "loss": 0.71211177110672, "grad_norm": 0.4531428813934326, "learning_rate": 0.00018984381612782854}
-{"ts": "2025-12-27T06:26:42", "event": "train_log", "step": 3034, "epoch": 1.2801687763713079, "progress_pct": 21.34, "epoch_pct": 21.34, "eta": "44:49:43", "max_grad_norm": 1.0, "loss": 0.635804295539856, "grad_norm": 0.3747255802154541, "learning_rate": 0.00018982271612299524}
-{"ts": "2025-12-27T06:26:59", "event": "train_log", "step": 3036, "epoch": 1.281012658227848, "progress_pct": 21.35, "epoch_pct": 21.35, "eta": "44:48:30", "max_grad_norm": 1.0, "loss": 0.7269464731216431, "grad_norm": 0.4079552888870239, "learning_rate": 0.00018980159539778638}
-{"ts": "2025-12-27T06:27:15", "event": "train_log", "step": 3038, "epoch": 1.2818565400843882, "progress_pct": 21.36, "epoch_pct": 21.36, "eta": "44:47:13", "max_grad_norm": 1.0, "loss": 0.7737077474594116, "grad_norm": 0.4193854033946991, "learning_rate": 0.00018978045395707418}
-{"ts": "2025-12-27T06:27:31", "event": "train_log", "step": 3040, "epoch": 1.2827004219409281, "progress_pct": 21.38, "epoch_pct": 21.38, "eta": "44:45:55", "max_grad_norm": 1.0, "loss": 0.7458174824714661, "grad_norm": 0.4182516038417816, "learning_rate": 0.0001897592918057355}
-{"ts": "2025-12-27T06:27:46", "event": "train_log", "step": 3042, "epoch": 1.2835443037974683, "progress_pct": 21.39, "epoch_pct": 21.39, "eta": "44:44:36", "max_grad_norm": 1.0, "loss": 0.6565808057785034, "grad_norm": 0.43343567848205566, "learning_rate": 0.00018973810894865205}
-{"ts": "2025-12-27T06:28:02", "event": "train_log", "step": 3044, "epoch": 1.2843881856540085, "progress_pct": 21.41, "epoch_pct": 21.41, "eta": "44:43:21", "max_grad_norm": 1.0, "loss": 0.736944317817688, "grad_norm": 0.4294503331184387, "learning_rate": 0.00018971690539071033}
-{"ts": "2025-12-27T06:28:18", "event": "train_log", "step": 3046, "epoch": 1.2852320675105484, "progress_pct": 21.42, "epoch_pct": 21.42, "eta": "44:42:06", "max_grad_norm": 1.0, "loss": 0.6921742558479309, "grad_norm": 0.41330763697624207, "learning_rate": 0.0001896956811368016}
-{"ts": "2025-12-27T06:28:33", "event": "train_log", "step": 3048, "epoch": 1.2860759493670886, "progress_pct": 21.43, "epoch_pct": 21.43, "eta": "44:40:47", "max_grad_norm": 1.0, "loss": 0.7004357576370239, "grad_norm": 0.44992703199386597, "learning_rate": 0.0001896744361918218}
-{"ts": "2025-12-27T06:28:50", "event": "train_log", "step": 3050, "epoch": 1.2869198312236287, "progress_pct": 21.45, "epoch_pct": 21.45, "eta": "44:39:35", "max_grad_norm": 1.0, "loss": 0.6767720580101013, "grad_norm": 0.43748870491981506, "learning_rate": 0.0001896531705606719}
-{"ts": "2025-12-27T06:29:06", "event": "train_log", "step": 3052, "epoch": 1.2877637130801687, "progress_pct": 21.46, "epoch_pct": 21.46, "eta": "44:38:18", "max_grad_norm": 1.0, "loss": 0.7596892714500427, "grad_norm": 0.47581973671913147, "learning_rate": 0.0001896318842482573}
-{"ts": "2025-12-27T06:29:22", "event": "train_log", "step": 3054, "epoch": 1.2886075949367088, "progress_pct": 21.48, "epoch_pct": 21.48, "eta": "44:37:02", "max_grad_norm": 1.0, "loss": 0.7650044560432434, "grad_norm": 0.45806005597114563, "learning_rate": 0.00018961057725948844}
-{"ts": "2025-12-27T06:29:36", "event": "train_log", "step": 3056, "epoch": 1.289451476793249, "progress_pct": 21.49, "epoch_pct": 21.49, "eta": "44:35:41", "max_grad_norm": 1.0, "loss": 0.6654610633850098, "grad_norm": 0.4291481375694275, "learning_rate": 0.00018958924959928042}
-{"ts": "2025-12-27T06:29:52", "event": "train_log", "step": 3058, "epoch": 1.290295358649789, "progress_pct": 21.5, "epoch_pct": 21.5, "eta": "44:34:26", "max_grad_norm": 1.0, "loss": 0.7079797387123108, "grad_norm": 0.42454418540000916, "learning_rate": 0.00018956790127255309}
-{"ts": "2025-12-27T06:30:07", "event": "train_log", "step": 3060, "epoch": 1.2911392405063291, "progress_pct": 21.52, "epoch_pct": 21.52, "eta": "44:33:07", "max_grad_norm": 1.0, "loss": 0.7724313735961914, "grad_norm": 0.46820637583732605, "learning_rate": 0.00018954653228423114}
-{"ts": "2025-12-27T06:30:23", "event": "train_log", "step": 3062, "epoch": 1.2919831223628693, "progress_pct": 21.53, "epoch_pct": 21.53, "eta": "44:31:52", "max_grad_norm": 1.0, "loss": 0.7746338248252869, "grad_norm": 0.4440016746520996, "learning_rate": 0.00018952514263924396}
-{"ts": "2025-12-27T06:30:39", "event": "train_log", "step": 3064, "epoch": 1.2928270042194092, "progress_pct": 21.55, "epoch_pct": 21.55, "eta": "44:30:36", "max_grad_norm": 1.0, "loss": 0.7570929527282715, "grad_norm": 0.4296419620513916, "learning_rate": 0.00018950373234252572}
-{"ts": "2025-12-27T06:30:55", "event": "train_log", "step": 3066, "epoch": 1.2936708860759494, "progress_pct": 21.56, "epoch_pct": 21.56, "eta": "44:29:20", "max_grad_norm": 1.0, "loss": 0.7274802923202515, "grad_norm": 0.428780734539032, "learning_rate": 0.0001894823013990154}
-{"ts": "2025-12-27T06:31:10", "event": "train_log", "step": 3068, "epoch": 1.2945147679324895, "progress_pct": 21.58, "epoch_pct": 21.58, "eta": "44:28:02", "max_grad_norm": 1.0, "loss": 0.6595024466514587, "grad_norm": 0.4111585021018982, "learning_rate": 0.0001894608498136567}
-{"ts": "2025-12-27T06:31:25", "event": "train_log", "step": 3070, "epoch": 1.2953586497890295, "progress_pct": 21.59, "epoch_pct": 21.59, "eta": "44:26:43", "max_grad_norm": 1.0, "loss": 0.7316440939903259, "grad_norm": 0.4373013973236084, "learning_rate": 0.00018943937759139802}
-{"ts": "2025-12-27T06:31:40", "event": "train_log", "step": 3072, "epoch": 1.2962025316455696, "progress_pct": 21.6, "epoch_pct": 21.6, "eta": "44:25:26", "max_grad_norm": 1.0, "loss": 0.7072293162345886, "grad_norm": 0.37705400586128235, "learning_rate": 0.0001894178847371927}
-{"ts": "2025-12-27T06:31:56", "event": "train_log", "step": 3074, "epoch": 1.2970464135021098, "progress_pct": 21.62, "epoch_pct": 21.62, "eta": "44:24:09", "max_grad_norm": 1.0, "loss": 0.7218101024627686, "grad_norm": 0.4171125888824463, "learning_rate": 0.00018939637125599864}
-{"ts": "2025-12-27T06:32:11", "event": "train_log", "step": 3076, "epoch": 1.2978902953586497, "progress_pct": 21.63, "epoch_pct": 21.63, "eta": "44:22:53", "max_grad_norm": 1.0, "loss": 0.725140392780304, "grad_norm": 0.4264235198497772, "learning_rate": 0.00018937483715277865}
-{"ts": "2025-12-27T06:32:27", "event": "train_log", "step": 3078, "epoch": 1.29873417721519, "progress_pct": 21.65, "epoch_pct": 21.65, "eta": "44:21:38", "max_grad_norm": 1.0, "loss": 0.7423256635665894, "grad_norm": 0.4251643121242523, "learning_rate": 0.0001893532824325002}
-{"ts": "2025-12-27T06:32:44", "event": "train_log", "step": 3080, "epoch": 1.29957805907173, "progress_pct": 21.66, "epoch_pct": 21.66, "eta": "44:20:26", "max_grad_norm": 1.0, "loss": 0.7058811187744141, "grad_norm": 0.43096452951431274, "learning_rate": 0.00018933170710013554}
-{"ts": "2025-12-27T06:33:00", "event": "train_log", "step": 3082, "epoch": 1.30042194092827, "progress_pct": 21.67, "epoch_pct": 21.67, "eta": "44:19:13", "max_grad_norm": 1.0, "loss": 0.7334373593330383, "grad_norm": 0.466804176568985, "learning_rate": 0.00018931011116066172}
-{"ts": "2025-12-27T06:33:18", "event": "train_log", "step": 3084, "epoch": 1.3012658227848102, "progress_pct": 21.69, "epoch_pct": 21.69, "eta": "44:18:03", "max_grad_norm": 1.0, "loss": 0.6033462285995483, "grad_norm": 0.36896654963493347, "learning_rate": 0.00018928849461906047}
-{"ts": "2025-12-27T06:33:34", "event": "train_log", "step": 3086, "epoch": 1.3021097046413503, "progress_pct": 21.7, "epoch_pct": 21.7, "eta": "44:16:50", "max_grad_norm": 1.0, "loss": 0.690375566482544, "grad_norm": 0.42875027656555176, "learning_rate": 0.00018926685748031833}
-{"ts": "2025-12-27T06:33:49", "event": "train_log", "step": 3088, "epoch": 1.3029535864978903, "progress_pct": 21.72, "epoch_pct": 21.72, "eta": "44:15:32", "max_grad_norm": 1.0, "loss": 0.7468435168266296, "grad_norm": 0.4041171967983246, "learning_rate": 0.00018924519974942658}
-{"ts": "2025-12-27T06:34:04", "event": "train_log", "step": 3090, "epoch": 1.3037974683544304, "progress_pct": 21.73, "epoch_pct": 21.73, "eta": "44:14:13", "max_grad_norm": 1.0, "loss": 0.7574344873428345, "grad_norm": 0.4704097807407379, "learning_rate": 0.00018922352143138126}
-{"ts": "2025-12-27T06:34:19", "event": "train_log", "step": 3092, "epoch": 1.3046413502109704, "progress_pct": 21.74, "epoch_pct": 21.74, "eta": "44:12:58", "max_grad_norm": 1.0, "loss": 0.756452739238739, "grad_norm": 0.4391418397426605, "learning_rate": 0.0001892018225311831}
-{"ts": "2025-12-27T06:34:34", "event": "train_log", "step": 3094, "epoch": 1.3054852320675105, "progress_pct": 21.76, "epoch_pct": 21.76, "eta": "44:11:42", "max_grad_norm": 1.0, "loss": 0.6620991230010986, "grad_norm": 0.42684388160705566, "learning_rate": 0.0001891801030538376}
-{"ts": "2025-12-27T06:34:50", "event": "train_log", "step": 3096, "epoch": 1.3063291139240507, "progress_pct": 21.77, "epoch_pct": 21.77, "eta": "44:10:27", "max_grad_norm": 1.0, "loss": 0.7764125466346741, "grad_norm": 0.4972277283668518, "learning_rate": 0.00018915836300435507}
-{"ts": "2025-12-27T06:35:06", "event": "train_log", "step": 3098, "epoch": 1.3071729957805907, "progress_pct": 21.79, "epoch_pct": 21.79, "eta": "44:09:14", "max_grad_norm": 1.0, "loss": 0.6557663083076477, "grad_norm": 0.3905445337295532, "learning_rate": 0.00018913660238775053}
-{"ts": "2025-12-27T06:35:21", "event": "train_log", "step": 3100, "epoch": 1.3080168776371308, "progress_pct": 21.8, "epoch_pct": 21.8, "eta": "44:07:56", "max_grad_norm": 1.0, "loss": 0.6746718883514404, "grad_norm": 0.4553062319755554, "learning_rate": 0.0001891148212090437}
-{"ts": "2025-12-27T06:46:29", "event": "train_log", "step": 3100, "epoch": 1.3080168776371308, "progress_pct": 21.8, "epoch_pct": 21.8, "eta": "44:47:53", "max_grad_norm": 1.0, "eval_loss": 0.8010181784629822, "eval_runtime": 668.1688, "eval_samples_per_second": 3.153, "eval_steps_per_second": 3.153}
-{"ts": "2025-12-27T06:46:45", "event": "train_log", "step": 3102, "epoch": 1.3088607594936708, "progress_pct": 21.81, "epoch_pct": 21.81, "eta": "44:46:35", "max_grad_norm": 1.0, "loss": 0.7916419506072998, "grad_norm": 0.4254429340362549, "learning_rate": 0.00018909301947325915}
-{"ts": "2025-12-27T06:46:59", "event": "train_log", "step": 3104, "epoch": 1.309704641350211, "progress_pct": 21.83, "epoch_pct": 21.83, "eta": "44:45:13", "max_grad_norm": 1.0, "loss": 0.883936882019043, "grad_norm": 0.6118508577346802, "learning_rate": 0.00018907119718542602}
-{"ts": "2025-12-27T06:47:14", "event": "train_log", "step": 3106, "epoch": 1.310548523206751, "progress_pct": 21.84, "epoch_pct": 21.84, "eta": "44:43:54", "max_grad_norm": 1.0, "loss": 0.7145928740501404, "grad_norm": 0.43206971883773804, "learning_rate": 0.00018904935435057837}
-{"ts": "2025-12-27T06:47:30", "event": "train_log", "step": 3108, "epoch": 1.311392405063291, "progress_pct": 21.86, "epoch_pct": 21.86, "eta": "44:42:37", "max_grad_norm": 1.0, "loss": 0.7442842125892639, "grad_norm": 0.39657703042030334, "learning_rate": 0.0001890274909737549}
-{"ts": "2025-12-27T06:47:45", "event": "train_log", "step": 3110, "epoch": 1.3122362869198312, "progress_pct": 21.87, "epoch_pct": 21.87, "eta": "44:41:20", "max_grad_norm": 1.0, "loss": 0.6815276145935059, "grad_norm": 0.4087927043437958, "learning_rate": 0.00018900560705999904}
-{"ts": "2025-12-27T06:48:00", "event": "train_log", "step": 3112, "epoch": 1.3130801687763713, "progress_pct": 21.88, "epoch_pct": 21.88, "eta": "44:39:59", "max_grad_norm": 1.0, "loss": 0.8153640627861023, "grad_norm": 0.430259108543396, "learning_rate": 0.00018898370261435904}
-{"ts": "2025-12-27T06:48:14", "event": "train_log", "step": 3114, "epoch": 1.3139240506329113, "progress_pct": 21.9, "epoch_pct": 21.9, "eta": "44:38:38", "max_grad_norm": 1.0, "loss": 0.7828266024589539, "grad_norm": 0.47486868500709534, "learning_rate": 0.0001889617776418878}
-{"ts": "2025-12-27T06:48:29", "event": "train_log", "step": 3116, "epoch": 1.3147679324894515, "progress_pct": 21.91, "epoch_pct": 21.91, "eta": "44:37:19", "max_grad_norm": 1.0, "loss": 0.7849065661430359, "grad_norm": 0.4929087162017822, "learning_rate": 0.000188939832147643}
-{"ts": "2025-12-27T06:48:44", "event": "train_log", "step": 3118, "epoch": 1.3156118143459916, "progress_pct": 21.93, "epoch_pct": 21.93, "eta": "44:36:03", "max_grad_norm": 1.0, "loss": 0.7262985706329346, "grad_norm": 0.39038679003715515, "learning_rate": 0.00018891786613668704}
-{"ts": "2025-12-27T06:48:59", "event": "train_log", "step": 3120, "epoch": 1.3164556962025316, "progress_pct": 21.94, "epoch_pct": 21.94, "eta": "44:34:42", "max_grad_norm": 1.0, "loss": 0.8121856451034546, "grad_norm": 0.4827214479446411, "learning_rate": 0.0001888958796140871}
-{"ts": "2025-12-27T06:49:13", "event": "train_log", "step": 3122, "epoch": 1.3172995780590717, "progress_pct": 21.95, "epoch_pct": 21.95, "eta": "44:33:22", "max_grad_norm": 1.0, "loss": 0.7165566086769104, "grad_norm": 0.47739601135253906, "learning_rate": 0.000188873872584915}
-{"ts": "2025-12-27T06:49:28", "event": "train_log", "step": 3124, "epoch": 1.3181434599156119, "progress_pct": 21.97, "epoch_pct": 21.97, "eta": "44:32:01", "max_grad_norm": 1.0, "loss": 0.6698412299156189, "grad_norm": 0.4274037778377533, "learning_rate": 0.0001888518450542473}
-{"ts": "2025-12-27T06:49:44", "event": "train_log", "step": 3126, "epoch": 1.3189873417721518, "progress_pct": 21.98, "epoch_pct": 21.98, "eta": "44:30:50", "max_grad_norm": 1.0, "loss": 0.7271128296852112, "grad_norm": 0.44825276732444763, "learning_rate": 0.00018882979702716544}
-{"ts": "2025-12-27T06:50:01", "event": "train_log", "step": 3128, "epoch": 1.319831223628692, "progress_pct": 22.0, "epoch_pct": 22.0, "eta": "44:29:38", "max_grad_norm": 1.0, "loss": 0.7924301624298096, "grad_norm": 0.42956918478012085, "learning_rate": 0.00018880772850875537}
-{"ts": "2025-12-27T06:50:16", "event": "train_log", "step": 3130, "epoch": 1.3206751054852321, "progress_pct": 22.01, "epoch_pct": 22.01, "eta": "44:28:21", "max_grad_norm": 1.0, "loss": 0.7846497893333435, "grad_norm": 0.4848136305809021, "learning_rate": 0.00018878563950410792}
-{"ts": "2025-12-27T06:50:32", "event": "train_log", "step": 3132, "epoch": 1.321518987341772, "progress_pct": 22.03, "epoch_pct": 22.03, "eta": "44:27:04", "max_grad_norm": 1.0, "loss": 0.7262214422225952, "grad_norm": 0.46651726961135864, "learning_rate": 0.00018876353001831864}
-{"ts": "2025-12-27T06:50:47", "event": "train_log", "step": 3134, "epoch": 1.3223628691983123, "progress_pct": 22.04, "epoch_pct": 22.04, "eta": "44:25:46", "max_grad_norm": 1.0, "loss": 0.7640091180801392, "grad_norm": 0.44598284363746643, "learning_rate": 0.0001887414000564877}
-{"ts": "2025-12-27T06:51:03", "event": "train_log", "step": 3136, "epoch": 1.3232067510548524, "progress_pct": 22.05, "epoch_pct": 22.05, "eta": "44:24:33", "max_grad_norm": 1.0, "loss": 0.6960080862045288, "grad_norm": 0.43744903802871704, "learning_rate": 0.00018871924962372006}
-{"ts": "2025-12-27T06:51:17", "event": "train_log", "step": 3138, "epoch": 1.3240506329113924, "progress_pct": 22.07, "epoch_pct": 22.07, "eta": "44:23:13", "max_grad_norm": 1.0, "loss": 0.7121244072914124, "grad_norm": 0.4737822413444519, "learning_rate": 0.00018869707872512544}
-{"ts": "2025-12-27T06:51:33", "event": "train_log", "step": 3140, "epoch": 1.3248945147679325, "progress_pct": 22.08, "epoch_pct": 22.08, "eta": "44:21:58", "max_grad_norm": 1.0, "loss": 0.713148295879364, "grad_norm": 0.44452038407325745, "learning_rate": 0.00018867488736581817}
-{"ts": "2025-12-27T06:51:48", "event": "train_log", "step": 3142, "epoch": 1.3257383966244727, "progress_pct": 22.1, "epoch_pct": 22.1, "eta": "44:20:40", "max_grad_norm": 1.0, "loss": 0.6904974579811096, "grad_norm": 0.47142693400382996, "learning_rate": 0.0001886526755509175}
-{"ts": "2025-12-27T06:52:05", "event": "train_log", "step": 3144, "epoch": 1.3265822784810126, "progress_pct": 22.11, "epoch_pct": 22.11, "eta": "44:19:27", "max_grad_norm": 1.0, "loss": 0.7319386005401611, "grad_norm": 0.40572887659072876, "learning_rate": 0.00018863044328554712}
-{"ts": "2025-12-27T06:52:20", "event": "train_log", "step": 3146, "epoch": 1.3274261603375528, "progress_pct": 22.12, "epoch_pct": 22.12, "eta": "44:18:12", "max_grad_norm": 1.0, "loss": 0.7268120646476746, "grad_norm": 0.44173532724380493, "learning_rate": 0.00018860819057483566}
-{"ts": "2025-12-27T06:52:36", "event": "train_log", "step": 3148, "epoch": 1.328270042194093, "progress_pct": 22.14, "epoch_pct": 22.14, "eta": "44:16:57", "max_grad_norm": 1.0, "loss": 0.7129524946212769, "grad_norm": 0.43025046586990356, "learning_rate": 0.00018858591742391642}
-{"ts": "2025-12-27T06:52:52", "event": "train_log", "step": 3150, "epoch": 1.3291139240506329, "progress_pct": 22.15, "epoch_pct": 22.15, "eta": "44:15:43", "max_grad_norm": 1.0, "loss": 0.6917402148246765, "grad_norm": 0.41418036818504333, "learning_rate": 0.00018856362383792732}
-{"ts": "2025-12-27T06:53:08", "event": "train_log", "step": 3152, "epoch": 1.329957805907173, "progress_pct": 22.17, "epoch_pct": 22.17, "eta": "44:14:29", "max_grad_norm": 1.0, "loss": 0.7653918862342834, "grad_norm": 0.46275854110717773, "learning_rate": 0.00018854130982201111}
-{"ts": "2025-12-27T06:53:25", "event": "train_log", "step": 3154, "epoch": 1.3308016877637132, "progress_pct": 22.18, "epoch_pct": 22.18, "eta": "44:13:20", "max_grad_norm": 1.0, "loss": 0.7311477065086365, "grad_norm": 0.38927653431892395, "learning_rate": 0.0001885189753813152}
-{"ts": "2025-12-27T06:53:41", "event": "train_log", "step": 3156, "epoch": 1.3316455696202532, "progress_pct": 22.19, "epoch_pct": 22.19, "eta": "44:12:05", "max_grad_norm": 1.0, "loss": 0.7978816628456116, "grad_norm": 0.44294974207878113, "learning_rate": 0.0001884966205209917}
-{"ts": "2025-12-27T06:53:57", "event": "train_log", "step": 3158, "epoch": 1.3324894514767933, "progress_pct": 22.21, "epoch_pct": 22.21, "eta": "44:10:53", "max_grad_norm": 1.0, "loss": 0.7497738599777222, "grad_norm": 0.3772844970226288, "learning_rate": 0.00018847424524619745}
-{"ts": "2025-12-27T06:54:13", "event": "train_log", "step": 3160, "epoch": 1.3333333333333333, "progress_pct": 22.22, "epoch_pct": 22.22, "eta": "44:09:38", "max_grad_norm": 1.0, "loss": 0.712806761264801, "grad_norm": 0.4538787603378296, "learning_rate": 0.000188451849562094}
-{"ts": "2025-12-27T06:54:28", "event": "train_log", "step": 3162, "epoch": 1.3341772151898734, "progress_pct": 22.24, "epoch_pct": 22.24, "eta": "44:08:23", "max_grad_norm": 1.0, "loss": 0.7282580137252808, "grad_norm": 0.4194336533546448, "learning_rate": 0.00018842943347384763}
-{"ts": "2025-12-27T06:54:44", "event": "train_log", "step": 3164, "epoch": 1.3350210970464136, "progress_pct": 22.25, "epoch_pct": 22.25, "eta": "44:07:08", "max_grad_norm": 1.0, "loss": 0.797752320766449, "grad_norm": 0.4186438024044037, "learning_rate": 0.00018840699698662925}
-{"ts": "2025-12-27T06:54:59", "event": "train_log", "step": 3166, "epoch": 1.3358649789029535, "progress_pct": 22.26, "epoch_pct": 22.26, "eta": "44:05:51", "max_grad_norm": 1.0, "loss": 0.8175379633903503, "grad_norm": 0.47711506485939026, "learning_rate": 0.00018838454010561457}
-{"ts": "2025-12-27T06:55:14", "event": "train_log", "step": 3168, "epoch": 1.3367088607594937, "progress_pct": 22.28, "epoch_pct": 22.28, "eta": "44:04:37", "max_grad_norm": 1.0, "loss": 0.659176766872406, "grad_norm": 0.4380176067352295, "learning_rate": 0.00018836206283598394}
-{"ts": "2025-12-27T06:55:32", "event": "train_log", "step": 3170, "epoch": 1.3375527426160336, "progress_pct": 22.29, "epoch_pct": 22.29, "eta": "44:03:29", "max_grad_norm": 1.0, "loss": 0.732314944267273, "grad_norm": 0.4505249559879303, "learning_rate": 0.00018833956518292245}
-{"ts": "2025-12-27T06:55:47", "event": "train_log", "step": 3172, "epoch": 1.3383966244725738, "progress_pct": 22.31, "epoch_pct": 22.31, "eta": "44:02:15", "max_grad_norm": 1.0, "loss": 0.6791377067565918, "grad_norm": 0.3832913935184479, "learning_rate": 0.00018831704715161984}
-{"ts": "2025-12-27T06:56:03", "event": "train_log", "step": 3174, "epoch": 1.339240506329114, "progress_pct": 22.32, "epoch_pct": 22.32, "eta": "44:00:59", "max_grad_norm": 1.0, "loss": 0.7395796775817871, "grad_norm": 0.42996498942375183, "learning_rate": 0.00018829450874727064}
-{"ts": "2025-12-27T06:56:21", "event": "train_log", "step": 3176, "epoch": 1.340084388185654, "progress_pct": 22.33, "epoch_pct": 22.33, "eta": "43:59:53", "max_grad_norm": 1.0, "loss": 0.6893631219863892, "grad_norm": 0.3926190435886383, "learning_rate": 0.000188271949975074}
-{"ts": "2025-12-27T06:56:37", "event": "train_log", "step": 3178, "epoch": 1.340928270042194, "progress_pct": 22.35, "epoch_pct": 22.35, "eta": "43:58:42", "max_grad_norm": 1.0, "loss": 0.6708382964134216, "grad_norm": 0.4353938102722168, "learning_rate": 0.0001882493708402338}
-{"ts": "2025-12-27T06:56:52", "event": "train_log", "step": 3180, "epoch": 1.3417721518987342, "progress_pct": 22.36, "epoch_pct": 22.36, "eta": "43:57:27", "max_grad_norm": 1.0, "loss": 0.8447695374488831, "grad_norm": 0.43043214082717896, "learning_rate": 0.0001882267713479586}
-{"ts": "2025-12-27T06:57:08", "event": "train_log", "step": 3182, "epoch": 1.3426160337552742, "progress_pct": 22.38, "epoch_pct": 22.38, "eta": "43:56:15", "max_grad_norm": 1.0, "loss": 0.7081091403961182, "grad_norm": 0.40693536400794983, "learning_rate": 0.00018820415150346163}
-{"ts": "2025-12-27T06:57:24", "event": "train_log", "step": 3184, "epoch": 1.3434599156118143, "progress_pct": 22.39, "epoch_pct": 22.39, "eta": "43:55:01", "max_grad_norm": 1.0, "loss": 0.6822336316108704, "grad_norm": 0.45037057995796204, "learning_rate": 0.00018818151131196097}
-{"ts": "2025-12-27T06:57:40", "event": "train_log", "step": 3186, "epoch": 1.3443037974683545, "progress_pct": 22.41, "epoch_pct": 22.41, "eta": "43:53:49", "max_grad_norm": 1.0, "loss": 0.6316909790039062, "grad_norm": 0.3731948137283325, "learning_rate": 0.00018815885077867915}
-{"ts": "2025-12-27T06:57:56", "event": "train_log", "step": 3188, "epoch": 1.3451476793248944, "progress_pct": 22.42, "epoch_pct": 22.42, "eta": "43:52:34", "max_grad_norm": 1.0, "loss": 0.7452375292778015, "grad_norm": 0.4248095750808716, "learning_rate": 0.00018813616990884363}
-{"ts": "2025-12-27T06:58:12", "event": "train_log", "step": 3190, "epoch": 1.3459915611814346, "progress_pct": 22.43, "epoch_pct": 22.43, "eta": "43:51:25", "max_grad_norm": 1.0, "loss": 0.6493782997131348, "grad_norm": 0.39229142665863037, "learning_rate": 0.00018811346870768638}
-{"ts": "2025-12-27T06:58:28", "event": "train_log", "step": 3192, "epoch": 1.3468354430379748, "progress_pct": 22.45, "epoch_pct": 22.45, "eta": "43:50:11", "max_grad_norm": 1.0, "loss": 0.735163688659668, "grad_norm": 0.45015549659729004, "learning_rate": 0.00018809074718044414}
-{"ts": "2025-12-27T06:58:44", "event": "train_log", "step": 3194, "epoch": 1.3476793248945147, "progress_pct": 22.46, "epoch_pct": 22.46, "eta": "43:49:01", "max_grad_norm": 1.0, "loss": 0.6656006574630737, "grad_norm": 0.39756354689598083, "learning_rate": 0.00018806800533235836}
-{"ts": "2025-12-27T06:59:00", "event": "train_log", "step": 3196, "epoch": 1.3485232067510549, "progress_pct": 22.48, "epoch_pct": 22.48, "eta": "43:47:48", "max_grad_norm": 1.0, "loss": 0.7040987014770508, "grad_norm": 0.4410010576248169, "learning_rate": 0.0001880452431686751}
-{"ts": "2025-12-27T06:59:16", "event": "train_log", "step": 3198, "epoch": 1.349367088607595, "progress_pct": 22.49, "epoch_pct": 22.49, "eta": "43:46:36", "max_grad_norm": 1.0, "loss": 0.7722331285476685, "grad_norm": 0.48144352436065674, "learning_rate": 0.0001880224606946452}
-{"ts": "2025-12-27T06:59:33", "event": "train_log", "step": 3200, "epoch": 1.350210970464135, "progress_pct": 22.5, "epoch_pct": 22.5, "eta": "43:45:27", "max_grad_norm": 1.0, "loss": 0.6681689023971558, "grad_norm": 0.38644957542419434, "learning_rate": 0.00018799965791552414}
-{"ts": "2025-12-27T07:10:54", "event": "train_log", "step": 3200, "epoch": 1.350210970464135, "progress_pct": 22.5, "epoch_pct": 22.5, "eta": "44:24:33", "max_grad_norm": 1.0, "eval_loss": 0.797160804271698, "eval_runtime": 680.976, "eval_samples_per_second": 3.094, "eval_steps_per_second": 3.094}
-{"ts": "2025-12-27T07:11:09", "event": "train_log", "step": 3202, "epoch": 1.3510548523206751, "progress_pct": 22.52, "epoch_pct": 22.52, "eta": "44:23:15", "max_grad_norm": 1.0, "loss": 0.6995527744293213, "grad_norm": 0.4471014440059662, "learning_rate": 0.00018797683483657201}
-{"ts": "2025-12-27T07:11:25", "event": "train_log", "step": 3204, "epoch": 1.3518987341772153, "progress_pct": 22.53, "epoch_pct": 22.53, "eta": "44:22:00", "max_grad_norm": 1.0, "loss": 0.659622848033905, "grad_norm": 0.4065002202987671, "learning_rate": 0.00018795399146305378}
-{"ts": "2025-12-27T07:11:39", "event": "train_log", "step": 3206, "epoch": 1.3527426160337552, "progress_pct": 22.55, "epoch_pct": 22.55, "eta": "44:20:40", "max_grad_norm": 1.0, "loss": 0.7927116751670837, "grad_norm": 0.4787910580635071, "learning_rate": 0.00018793112780023888}
-{"ts": "2025-12-27T07:11:54", "event": "train_log", "step": 3208, "epoch": 1.3535864978902954, "progress_pct": 22.56, "epoch_pct": 22.56, "eta": "44:19:23", "max_grad_norm": 1.0, "loss": 0.6738835573196411, "grad_norm": 0.43351876735687256, "learning_rate": 0.0001879082438534015}
-{"ts": "2025-12-27T07:12:09", "event": "train_log", "step": 3210, "epoch": 1.3544303797468356, "progress_pct": 22.57, "epoch_pct": 22.57, "eta": "44:18:06", "max_grad_norm": 1.0, "loss": 0.7785354852676392, "grad_norm": 0.4275745749473572, "learning_rate": 0.00018788533962782063}
-{"ts": "2025-12-27T07:12:24", "event": "train_log", "step": 3212, "epoch": 1.3552742616033755, "progress_pct": 22.59, "epoch_pct": 22.59, "eta": "44:16:49", "max_grad_norm": 1.0, "loss": 0.7325424551963806, "grad_norm": 0.4506145119667053, "learning_rate": 0.00018786241512877975}
-{"ts": "2025-12-27T07:12:39", "event": "train_log", "step": 3214, "epoch": 1.3561181434599157, "progress_pct": 22.6, "epoch_pct": 22.6, "eta": "44:15:31", "max_grad_norm": 1.0, "loss": 0.6898744702339172, "grad_norm": 0.42040735483169556, "learning_rate": 0.00018783947036156713}
-{"ts": "2025-12-27T07:12:54", "event": "train_log", "step": 3216, "epoch": 1.3569620253164558, "progress_pct": 22.62, "epoch_pct": 22.62, "eta": "44:14:15", "max_grad_norm": 1.0, "loss": 0.7498815655708313, "grad_norm": 0.4650438129901886, "learning_rate": 0.0001878165053314757}
-{"ts": "2025-12-27T07:13:09", "event": "train_log", "step": 3218, "epoch": 1.3578059071729958, "progress_pct": 22.63, "epoch_pct": 22.63, "eta": "44:13:00", "max_grad_norm": 1.0, "loss": 0.6891883611679077, "grad_norm": 0.4194130599498749, "learning_rate": 0.000187793520043803}
-{"ts": "2025-12-27T07:13:24", "event": "train_log", "step": 3220, "epoch": 1.358649789029536, "progress_pct": 22.64, "epoch_pct": 22.64, "eta": "44:11:44", "max_grad_norm": 1.0, "loss": 0.753805935382843, "grad_norm": 0.4447539746761322, "learning_rate": 0.0001877705145038514}
-{"ts": "2025-12-27T07:13:40", "event": "train_log", "step": 3222, "epoch": 1.3594936708860759, "progress_pct": 22.66, "epoch_pct": 22.66, "eta": "44:10:28", "max_grad_norm": 1.0, "loss": 0.6476293802261353, "grad_norm": 0.4047110974788666, "learning_rate": 0.00018774748871692773}
-{"ts": "2025-12-27T07:13:55", "event": "train_log", "step": 3224, "epoch": 1.360337552742616, "progress_pct": 22.67, "epoch_pct": 22.67, "eta": "44:09:12", "max_grad_norm": 1.0, "loss": 0.6765931844711304, "grad_norm": 0.39818957448005676, "learning_rate": 0.00018772444268834364}
-{"ts": "2025-12-27T07:14:10", "event": "train_log", "step": 3226, "epoch": 1.3611814345991562, "progress_pct": 22.69, "epoch_pct": 22.69, "eta": "44:07:55", "max_grad_norm": 1.0, "loss": 0.7360382676124573, "grad_norm": 0.41843733191490173, "learning_rate": 0.0001877013764234154}
-{"ts": "2025-12-27T07:14:24", "event": "train_log", "step": 3228, "epoch": 1.3620253164556961, "progress_pct": 22.7, "epoch_pct": 22.7, "eta": "44:06:39", "max_grad_norm": 1.0, "loss": 0.7149524688720703, "grad_norm": 0.41397789120674133, "learning_rate": 0.00018767828992746394}
-{"ts": "2025-12-27T07:14:39", "event": "train_log", "step": 3230, "epoch": 1.3628691983122363, "progress_pct": 22.71, "epoch_pct": 22.71, "eta": "44:05:23", "max_grad_norm": 1.0, "loss": 0.6932925581932068, "grad_norm": 0.43585047125816345, "learning_rate": 0.00018765518320581492}
-{"ts": "2025-12-27T07:14:55", "event": "train_log", "step": 3232, "epoch": 1.3637130801687762, "progress_pct": 22.73, "epoch_pct": 22.73, "eta": "44:04:09", "max_grad_norm": 1.0, "loss": 0.6561182141304016, "grad_norm": 0.3651057481765747, "learning_rate": 0.00018763205626379857}
-{"ts": "2025-12-27T07:15:10", "event": "train_log", "step": 3234, "epoch": 1.3645569620253164, "progress_pct": 22.74, "epoch_pct": 22.74, "eta": "44:02:52", "max_grad_norm": 1.0, "loss": 0.7436831593513489, "grad_norm": 0.44937077164649963, "learning_rate": 0.00018760890910674984}
-{"ts": "2025-12-27T07:15:24", "event": "train_log", "step": 3236, "epoch": 1.3654008438818566, "progress_pct": 22.76, "epoch_pct": 22.76, "eta": "44:01:32", "max_grad_norm": 1.0, "loss": 0.7849522233009338, "grad_norm": 0.5045920014381409, "learning_rate": 0.00018758574174000832}
-{"ts": "2025-12-27T07:15:38", "event": "train_log", "step": 3238, "epoch": 1.3662447257383965, "progress_pct": 22.77, "epoch_pct": 22.77, "eta": "44:00:13", "max_grad_norm": 1.0, "loss": 0.7501618266105652, "grad_norm": 0.4625580906867981, "learning_rate": 0.00018756255416891833}
-{"ts": "2025-12-27T07:15:53", "event": "train_log", "step": 3240, "epoch": 1.3670886075949367, "progress_pct": 22.78, "epoch_pct": 22.78, "eta": "43:58:57", "max_grad_norm": 1.0, "loss": 0.7656083106994629, "grad_norm": 0.3721269369125366, "learning_rate": 0.00018753934639882875}
-{"ts": "2025-12-27T07:16:07", "event": "train_log", "step": 3242, "epoch": 1.3679324894514768, "progress_pct": 22.8, "epoch_pct": 22.8, "eta": "43:57:40", "max_grad_norm": 1.0, "loss": 0.7816168069839478, "grad_norm": 0.41721680760383606, "learning_rate": 0.00018751611843509318}
-{"ts": "2025-12-27T07:16:22", "event": "train_log", "step": 3244, "epoch": 1.3687763713080168, "progress_pct": 22.81, "epoch_pct": 22.81, "eta": "43:56:25", "max_grad_norm": 1.0, "loss": 0.7002755403518677, "grad_norm": 0.8452199101448059, "learning_rate": 0.00018749287028306988}
-{"ts": "2025-12-27T07:16:37", "event": "train_log", "step": 3246, "epoch": 1.369620253164557, "progress_pct": 22.83, "epoch_pct": 22.83, "eta": "43:55:07", "max_grad_norm": 1.0, "loss": 0.7358270883560181, "grad_norm": 0.4320507347583771, "learning_rate": 0.00018746960194812172}
-{"ts": "2025-12-27T07:16:52", "event": "train_log", "step": 3248, "epoch": 1.370464135021097, "progress_pct": 22.84, "epoch_pct": 22.84, "eta": "43:53:53", "max_grad_norm": 1.0, "loss": 0.6528644561767578, "grad_norm": 0.43323323130607605, "learning_rate": 0.00018744631343561627}
-{"ts": "2025-12-27T07:17:07", "event": "train_log", "step": 3250, "epoch": 1.371308016877637, "progress_pct": 22.86, "epoch_pct": 22.86, "eta": "43:52:35", "max_grad_norm": 1.0, "loss": 0.7317517995834351, "grad_norm": 0.41487041115760803, "learning_rate": 0.0001874230047509258}
-{"ts": "2025-12-27T07:17:20", "event": "train_log", "step": 3252, "epoch": 1.3721518987341772, "progress_pct": 22.87, "epoch_pct": 22.87, "eta": "43:51:15", "max_grad_norm": 1.0, "loss": 0.8236643671989441, "grad_norm": 0.5085384249687195, "learning_rate": 0.00018739967589942707}
-{"ts": "2025-12-27T07:17:35", "event": "train_log", "step": 3254, "epoch": 1.3729957805907174, "progress_pct": 22.88, "epoch_pct": 22.88, "eta": "43:50:00", "max_grad_norm": 1.0, "loss": 0.730254054069519, "grad_norm": 0.4126952290534973, "learning_rate": 0.00018737632688650168}
-{"ts": "2025-12-27T07:17:50", "event": "train_log", "step": 3256, "epoch": 1.3738396624472573, "progress_pct": 22.9, "epoch_pct": 22.9, "eta": "43:48:43", "max_grad_norm": 1.0, "loss": 0.7637890577316284, "grad_norm": 0.5272142291069031, "learning_rate": 0.00018735295771753573}
-{"ts": "2025-12-27T07:18:04", "event": "train_log", "step": 3258, "epoch": 1.3746835443037975, "progress_pct": 22.91, "epoch_pct": 22.91, "eta": "43:47:25", "max_grad_norm": 1.0, "loss": 0.7906988263130188, "grad_norm": 0.4319530725479126, "learning_rate": 0.00018732956839792012}
-{"ts": "2025-12-27T07:18:19", "event": "train_log", "step": 3260, "epoch": 1.3755274261603376, "progress_pct": 22.93, "epoch_pct": 22.93, "eta": "43:46:10", "max_grad_norm": 1.0, "loss": 0.7261547446250916, "grad_norm": 0.4393143355846405, "learning_rate": 0.00018730615893305025}
-{"ts": "2025-12-27T07:18:34", "event": "train_log", "step": 3262, "epoch": 1.3763713080168776, "progress_pct": 22.94, "epoch_pct": 22.94, "eta": "43:44:55", "max_grad_norm": 1.0, "loss": 0.6857497692108154, "grad_norm": 0.4161636233329773, "learning_rate": 0.00018728272932832632}
-{"ts": "2025-12-27T07:18:48", "event": "train_log", "step": 3264, "epoch": 1.3772151898734177, "progress_pct": 22.95, "epoch_pct": 22.95, "eta": "43:43:37", "max_grad_norm": 1.0, "loss": 0.7488857507705688, "grad_norm": 0.48862120509147644, "learning_rate": 0.00018725927958915297}
-{"ts": "2025-12-27T07:19:03", "event": "train_log", "step": 3266, "epoch": 1.378059071729958, "progress_pct": 22.97, "epoch_pct": 22.97, "eta": "43:42:22", "max_grad_norm": 1.0, "loss": 0.7257721424102783, "grad_norm": 0.4422304928302765, "learning_rate": 0.0001872358097209397}
-{"ts": "2025-12-27T07:19:17", "event": "train_log", "step": 3268, "epoch": 1.3789029535864978, "progress_pct": 22.98, "epoch_pct": 22.98, "eta": "43:41:06", "max_grad_norm": 1.0, "loss": 0.746697187423706, "grad_norm": 0.4577067494392395, "learning_rate": 0.00018721231972910048}
-{"ts": "2025-12-27T07:19:32", "event": "train_log", "step": 3270, "epoch": 1.379746835443038, "progress_pct": 23.0, "epoch_pct": 23.0, "eta": "43:39:51", "max_grad_norm": 1.0, "loss": 0.768519401550293, "grad_norm": 0.42382001876831055, "learning_rate": 0.00018718880961905406}
-{"ts": "2025-12-27T07:19:47", "event": "train_log", "step": 3272, "epoch": 1.3805907172995782, "progress_pct": 23.01, "epoch_pct": 23.01, "eta": "43:38:36", "max_grad_norm": 1.0, "loss": 0.7426102757453918, "grad_norm": 0.43368014693260193, "learning_rate": 0.00018716527939622378}
-{"ts": "2025-12-27T07:20:03", "event": "train_log", "step": 3274, "epoch": 1.381434599156118, "progress_pct": 23.02, "epoch_pct": 23.02, "eta": "43:37:23", "max_grad_norm": 1.0, "loss": 0.7104197144508362, "grad_norm": 0.3777220547199249, "learning_rate": 0.00018714172906603757}
-{"ts": "2025-12-27T07:20:17", "event": "train_log", "step": 3276, "epoch": 1.3822784810126583, "progress_pct": 23.04, "epoch_pct": 23.04, "eta": "43:36:08", "max_grad_norm": 1.0, "loss": 0.7502968907356262, "grad_norm": 0.46071696281433105, "learning_rate": 0.00018711815863392802}
-{"ts": "2025-12-27T07:20:33", "event": "train_log", "step": 3278, "epoch": 1.3831223628691984, "progress_pct": 23.05, "epoch_pct": 23.05, "eta": "43:34:56", "max_grad_norm": 1.0, "loss": 0.6400540471076965, "grad_norm": 0.42510855197906494, "learning_rate": 0.00018709456810533245}
-{"ts": "2025-12-27T07:20:50", "event": "train_log", "step": 3280, "epoch": 1.3839662447257384, "progress_pct": 23.07, "epoch_pct": 23.07, "eta": "43:33:49", "max_grad_norm": 1.0, "loss": 0.6648687720298767, "grad_norm": 0.4217228293418884, "learning_rate": 0.00018707095748569268}
-{"ts": "2025-12-27T07:21:07", "event": "train_log", "step": 3282, "epoch": 1.3848101265822785, "progress_pct": 23.08, "epoch_pct": 23.08, "eta": "43:32:39", "max_grad_norm": 1.0, "loss": 0.7176171541213989, "grad_norm": 0.48267799615859985, "learning_rate": 0.00018704732678045526}
-{"ts": "2025-12-27T07:21:21", "event": "train_log", "step": 3284, "epoch": 1.3856540084388187, "progress_pct": 23.09, "epoch_pct": 23.09, "eta": "43:31:24", "max_grad_norm": 1.0, "loss": 0.8402457237243652, "grad_norm": 0.47114965319633484, "learning_rate": 0.00018702367599507134}
-{"ts": "2025-12-27T07:21:37", "event": "train_log", "step": 3286, "epoch": 1.3864978902953586, "progress_pct": 23.11, "epoch_pct": 23.11, "eta": "43:30:13", "max_grad_norm": 1.0, "loss": 0.8130836486816406, "grad_norm": 0.5054492354393005, "learning_rate": 0.00018700000513499667}
-{"ts": "2025-12-27T07:21:54", "event": "train_log", "step": 3288, "epoch": 1.3873417721518988, "progress_pct": 23.12, "epoch_pct": 23.12, "eta": "43:29:06", "max_grad_norm": 1.0, "loss": 0.6432579755783081, "grad_norm": 0.39435645937919617, "learning_rate": 0.00018697631420569168}
-{"ts": "2025-12-27T07:22:11", "event": "train_log", "step": 3290, "epoch": 1.3881856540084387, "progress_pct": 23.14, "epoch_pct": 23.14, "eta": "43:27:57", "max_grad_norm": 1.0, "loss": 0.6921643614768982, "grad_norm": 0.3997228443622589, "learning_rate": 0.00018695260321262142}
-{"ts": "2025-12-27T07:22:27", "event": "train_log", "step": 3292, "epoch": 1.389029535864979, "progress_pct": 23.15, "epoch_pct": 23.15, "eta": "43:26:46", "max_grad_norm": 1.0, "loss": 0.7162153124809265, "grad_norm": 0.37304237484931946, "learning_rate": 0.00018692887216125557}
-{"ts": "2025-12-27T07:22:43", "event": "train_log", "step": 3294, "epoch": 1.389873417721519, "progress_pct": 23.16, "epoch_pct": 23.16, "eta": "43:25:38", "max_grad_norm": 1.0, "loss": 0.7194803953170776, "grad_norm": 0.7997981309890747, "learning_rate": 0.00018690512105706838}
-{"ts": "2025-12-27T07:22:58", "event": "train_log", "step": 3296, "epoch": 1.390717299578059, "progress_pct": 23.18, "epoch_pct": 23.18, "eta": "43:24:23", "max_grad_norm": 1.0, "loss": 0.6888322830200195, "grad_norm": 0.41268959641456604, "learning_rate": 0.00018688134990553883}
-{"ts": "2025-12-27T07:23:14", "event": "train_log", "step": 3298, "epoch": 1.3915611814345992, "progress_pct": 23.19, "epoch_pct": 23.19, "eta": "43:23:13", "max_grad_norm": 1.0, "loss": 0.7387221455574036, "grad_norm": 0.4485826790332794, "learning_rate": 0.00018685755871215043}
-{"ts": "2025-12-27T07:23:29", "event": "train_log", "step": 3300, "epoch": 1.3924050632911391, "progress_pct": 23.21, "epoch_pct": 23.21, "eta": "43:21:58", "max_grad_norm": 1.0, "loss": 0.8061952590942383, "grad_norm": 0.47835296392440796, "learning_rate": 0.0001868337474823914}
-{"ts": "2025-12-27T07:35:01", "event": "train_log", "step": 3300, "epoch": 1.3924050632911391, "progress_pct": 23.21, "epoch_pct": 23.21, "eta": "44:00:10", "max_grad_norm": 1.0, "eval_loss": 0.795619547367096, "eval_runtime": 692.7157, "eval_samples_per_second": 3.042, "eval_steps_per_second": 3.042}
-{"ts": "2025-12-27T07:35:18", "event": "train_log", "step": 3302, "epoch": 1.3932489451476793, "progress_pct": 23.22, "epoch_pct": 23.22, "eta": "43:58:58", "max_grad_norm": 1.0, "loss": 0.7317537069320679, "grad_norm": 0.4024396240711212, "learning_rate": 0.00018680991622175446}
-{"ts": "2025-12-27T07:35:34", "event": "train_log", "step": 3304, "epoch": 1.3940928270042194, "progress_pct": 23.23, "epoch_pct": 23.23, "eta": "43:57:47", "max_grad_norm": 1.0, "loss": 0.7470992207527161, "grad_norm": 0.4526490271091461, "learning_rate": 0.00018678606493573708}
-{"ts": "2025-12-27T07:35:50", "event": "train_log", "step": 3306, "epoch": 1.3949367088607594, "progress_pct": 23.25, "epoch_pct": 23.25, "eta": "43:56:34", "max_grad_norm": 1.0, "loss": 0.7627943754196167, "grad_norm": 0.5055129528045654, "learning_rate": 0.00018676219362984126}
-{"ts": "2025-12-27T07:36:05", "event": "train_log", "step": 3308, "epoch": 1.3957805907172995, "progress_pct": 23.26, "epoch_pct": 23.26, "eta": "43:55:21", "max_grad_norm": 1.0, "loss": 0.684033989906311, "grad_norm": 0.4030216634273529, "learning_rate": 0.0001867383023095737}
-{"ts": "2025-12-27T07:36:21", "event": "train_log", "step": 3310, "epoch": 1.3966244725738397, "progress_pct": 23.28, "epoch_pct": 23.28, "eta": "43:54:09", "max_grad_norm": 1.0, "loss": 0.7366722822189331, "grad_norm": 0.4353308379650116, "learning_rate": 0.0001867143909804456}
-{"ts": "2025-12-27T07:36:37", "event": "train_log", "step": 3312, "epoch": 1.3974683544303796, "progress_pct": 23.29, "epoch_pct": 23.29, "eta": "43:52:57", "max_grad_norm": 1.0, "loss": 0.8050951957702637, "grad_norm": 0.5360553860664368, "learning_rate": 0.0001866904596479729}
-{"ts": "2025-12-27T07:36:51", "event": "train_log", "step": 3314, "epoch": 1.3983122362869198, "progress_pct": 23.31, "epoch_pct": 23.31, "eta": "43:51:40", "max_grad_norm": 1.0, "loss": 0.7227963805198669, "grad_norm": 0.46081677079200745, "learning_rate": 0.00018666650831767608}
-{"ts": "2025-12-27T07:37:05", "event": "train_log", "step": 3316, "epoch": 1.39915611814346, "progress_pct": 23.32, "epoch_pct": 23.32, "eta": "43:50:22", "max_grad_norm": 1.0, "loss": 0.714216411113739, "grad_norm": 0.4325845539569855, "learning_rate": 0.00018664253699508029}
-{"ts": "2025-12-27T07:37:21", "event": "train_log", "step": 3318, "epoch": 1.4, "progress_pct": 23.33, "epoch_pct": 23.33, "eta": "43:49:08", "max_grad_norm": 1.0, "loss": 0.7378593683242798, "grad_norm": 0.4373100996017456, "learning_rate": 0.0001866185456857152}
-{"ts": "2025-12-27T07:37:35", "event": "train_log", "step": 3320, "epoch": 1.40084388185654, "progress_pct": 23.35, "epoch_pct": 23.35, "eta": "43:47:53", "max_grad_norm": 1.0, "loss": 0.7565981149673462, "grad_norm": 0.43221279978752136, "learning_rate": 0.00018659453439511512}
-{"ts": "2025-12-27T07:37:51", "event": "train_log", "step": 3322, "epoch": 1.4016877637130802, "progress_pct": 23.36, "epoch_pct": 23.36, "eta": "43:46:40", "max_grad_norm": 1.0, "loss": 0.6409488916397095, "grad_norm": 0.3938370943069458, "learning_rate": 0.00018657050312881904}
-{"ts": "2025-12-27T07:38:06", "event": "train_log", "step": 3324, "epoch": 1.4025316455696202, "progress_pct": 23.38, "epoch_pct": 23.38, "eta": "43:45:24", "max_grad_norm": 1.0, "loss": 0.6911652088165283, "grad_norm": 0.43609440326690674, "learning_rate": 0.00018654645189237055}
-{"ts": "2025-12-27T07:38:20", "event": "train_log", "step": 3326, "epoch": 1.4033755274261603, "progress_pct": 23.39, "epoch_pct": 23.39, "eta": "43:44:08", "max_grad_norm": 1.0, "loss": 0.7275710701942444, "grad_norm": 0.4526350200176239, "learning_rate": 0.00018652238069131774}
-{"ts": "2025-12-27T07:38:35", "event": "train_log", "step": 3328, "epoch": 1.4042194092827005, "progress_pct": 23.4, "epoch_pct": 23.4, "eta": "43:42:54", "max_grad_norm": 1.0, "loss": 0.6466895341873169, "grad_norm": 0.3990516662597656, "learning_rate": 0.0001864982895312134}
-{"ts": "2025-12-27T07:38:51", "event": "train_log", "step": 3330, "epoch": 1.4050632911392404, "progress_pct": 23.42, "epoch_pct": 23.42, "eta": "43:41:41", "max_grad_norm": 1.0, "loss": 0.6520540714263916, "grad_norm": 0.44321122765541077, "learning_rate": 0.0001864741784176149}
-{"ts": "2025-12-27T07:39:05", "event": "train_log", "step": 3332, "epoch": 1.4059071729957806, "progress_pct": 23.43, "epoch_pct": 23.43, "eta": "43:40:25", "max_grad_norm": 1.0, "loss": 0.7289671301841736, "grad_norm": 0.44733941555023193, "learning_rate": 0.0001864500473560842}
-{"ts": "2025-12-27T07:39:19", "event": "train_log", "step": 3334, "epoch": 1.4067510548523208, "progress_pct": 23.45, "epoch_pct": 23.45, "eta": "43:39:09", "max_grad_norm": 1.0, "loss": 0.7664391398429871, "grad_norm": 0.4569414556026459, "learning_rate": 0.00018642589635218789}
-{"ts": "2025-12-27T07:39:35", "event": "train_log", "step": 3336, "epoch": 1.4075949367088607, "progress_pct": 23.46, "epoch_pct": 23.46, "eta": "43:37:55", "max_grad_norm": 1.0, "loss": 0.7747462391853333, "grad_norm": 0.4172186851501465, "learning_rate": 0.00018640172541149709}
-{"ts": "2025-12-27T07:39:49", "event": "train_log", "step": 3338, "epoch": 1.4084388185654009, "progress_pct": 23.47, "epoch_pct": 23.47, "eta": "43:36:39", "max_grad_norm": 1.0, "loss": 0.8337607383728027, "grad_norm": 0.4540993869304657, "learning_rate": 0.0001863775345395877}
-{"ts": "2025-12-27T07:40:04", "event": "train_log", "step": 3340, "epoch": 1.409282700421941, "progress_pct": 23.49, "epoch_pct": 23.49, "eta": "43:35:26", "max_grad_norm": 1.0, "loss": 0.6851577758789062, "grad_norm": 0.4306154251098633, "learning_rate": 0.00018635332374203993}
-{"ts": "2025-12-27T07:40:18", "event": "train_log", "step": 3342, "epoch": 1.410126582278481, "progress_pct": 23.5, "epoch_pct": 23.5, "eta": "43:34:09", "max_grad_norm": 1.0, "loss": 0.6841398477554321, "grad_norm": 0.45615455508232117, "learning_rate": 0.00018632909302443884}
-{"ts": "2025-12-27T07:40:34", "event": "train_log", "step": 3344, "epoch": 1.4109704641350211, "progress_pct": 23.52, "epoch_pct": 23.52, "eta": "43:32:59", "max_grad_norm": 1.0, "loss": 0.6672312021255493, "grad_norm": 0.35296666622161865, "learning_rate": 0.00018630484239237397}
-{"ts": "2025-12-27T07:40:48", "event": "train_log", "step": 3346, "epoch": 1.4118143459915613, "progress_pct": 23.53, "epoch_pct": 23.53, "eta": "43:31:42", "max_grad_norm": 1.0, "loss": 0.7027004361152649, "grad_norm": 0.4424770176410675, "learning_rate": 0.00018628057185143945}
-{"ts": "2025-12-27T07:41:04", "event": "train_log", "step": 3348, "epoch": 1.4126582278481012, "progress_pct": 23.54, "epoch_pct": 23.54, "eta": "43:30:29", "max_grad_norm": 1.0, "loss": 0.7397928237915039, "grad_norm": 0.429817259311676, "learning_rate": 0.0001862562814072341}
-{"ts": "2025-12-27T07:41:19", "event": "train_log", "step": 3350, "epoch": 1.4135021097046414, "progress_pct": 23.56, "epoch_pct": 23.56, "eta": "43:29:16", "max_grad_norm": 1.0, "loss": 0.8009215593338013, "grad_norm": 0.4720051884651184, "learning_rate": 0.00018623197106536118}
-{"ts": "2025-12-27T07:41:34", "event": "train_log", "step": 3352, "epoch": 1.4143459915611816, "progress_pct": 23.57, "epoch_pct": 23.57, "eta": "43:28:03", "max_grad_norm": 1.0, "loss": 0.6875046491622925, "grad_norm": 0.42197802662849426, "learning_rate": 0.0001862076408314287}
-{"ts": "2025-12-27T07:41:50", "event": "train_log", "step": 3354, "epoch": 1.4151898734177215, "progress_pct": 23.59, "epoch_pct": 23.59, "eta": "43:26:52", "max_grad_norm": 1.0, "loss": 0.7202261090278625, "grad_norm": 0.3674047589302063, "learning_rate": 0.00018618329071104907}
-{"ts": "2025-12-27T07:42:04", "event": "train_log", "step": 3356, "epoch": 1.4160337552742617, "progress_pct": 23.6, "epoch_pct": 23.6, "eta": "43:25:36", "max_grad_norm": 1.0, "loss": 0.6981248259544373, "grad_norm": 0.42327889800071716, "learning_rate": 0.0001861589207098395}
-{"ts": "2025-12-27T07:42:20", "event": "train_log", "step": 3358, "epoch": 1.4168776371308016, "progress_pct": 23.61, "epoch_pct": 23.61, "eta": "43:24:26", "max_grad_norm": 1.0, "loss": 0.7081356048583984, "grad_norm": 0.40644150972366333, "learning_rate": 0.00018613453083342162}
-{"ts": "2025-12-27T07:42:35", "event": "train_log", "step": 3360, "epoch": 1.4177215189873418, "progress_pct": 23.63, "epoch_pct": 23.63, "eta": "43:23:14", "max_grad_norm": 1.0, "loss": 0.6420091986656189, "grad_norm": 0.3948482275009155, "learning_rate": 0.00018611012108742168}
-{"ts": "2025-12-27T07:42:49", "event": "train_log", "step": 3362, "epoch": 1.4185654008438817, "progress_pct": 23.64, "epoch_pct": 23.64, "eta": "43:21:57", "max_grad_norm": 1.0, "loss": 0.7662023305892944, "grad_norm": 0.44622674584388733, "learning_rate": 0.00018608569147747064}
-{"ts": "2025-12-27T07:43:04", "event": "train_log", "step": 3364, "epoch": 1.4194092827004219, "progress_pct": 23.66, "epoch_pct": 23.66, "eta": "43:20:43", "max_grad_norm": 1.0, "loss": 0.7243877649307251, "grad_norm": 0.39772045612335205, "learning_rate": 0.00018606124200920386}
-{"ts": "2025-12-27T07:43:19", "event": "train_log", "step": 3366, "epoch": 1.420253164556962, "progress_pct": 23.67, "epoch_pct": 23.67, "eta": "43:19:29", "max_grad_norm": 1.0, "loss": 0.7399296164512634, "grad_norm": 0.4284326136112213, "learning_rate": 0.00018603677268826138}
-{"ts": "2025-12-27T07:43:34", "event": "train_log", "step": 3368, "epoch": 1.421097046413502, "progress_pct": 23.68, "epoch_pct": 23.68, "eta": "43:18:17", "max_grad_norm": 1.0, "loss": 0.6978716850280762, "grad_norm": 0.3749450445175171, "learning_rate": 0.0001860122835202878}
-{"ts": "2025-12-27T07:43:48", "event": "train_log", "step": 3370, "epoch": 1.4219409282700421, "progress_pct": 23.7, "epoch_pct": 23.7, "eta": "43:17:02", "max_grad_norm": 1.0, "loss": 0.7733059525489807, "grad_norm": 0.46721795201301575, "learning_rate": 0.00018598777451093234}
-{"ts": "2025-12-27T07:44:04", "event": "train_log", "step": 3372, "epoch": 1.4227848101265823, "progress_pct": 23.71, "epoch_pct": 23.71, "eta": "43:15:51", "max_grad_norm": 1.0, "loss": 0.6721867918968201, "grad_norm": 0.39606085419654846, "learning_rate": 0.0001859632456658487}
-{"ts": "2025-12-27T07:44:19", "event": "train_log", "step": 3374, "epoch": 1.4236286919831223, "progress_pct": 23.73, "epoch_pct": 23.73, "eta": "43:14:38", "max_grad_norm": 1.0, "loss": 0.715825080871582, "grad_norm": 0.3879879117012024, "learning_rate": 0.00018593869699069527}
-{"ts": "2025-12-27T07:44:35", "event": "train_log", "step": 3376, "epoch": 1.4244725738396624, "progress_pct": 23.74, "epoch_pct": 23.74, "eta": "43:13:27", "max_grad_norm": 1.0, "loss": 0.6226941347122192, "grad_norm": 0.3641676902770996, "learning_rate": 0.0001859141284911349}
-{"ts": "2025-12-27T07:44:49", "event": "train_log", "step": 3378, "epoch": 1.4253164556962026, "progress_pct": 23.76, "epoch_pct": 23.76, "eta": "43:12:14", "max_grad_norm": 1.0, "loss": 0.7972121238708496, "grad_norm": 0.4612879753112793, "learning_rate": 0.0001858895401728351}
-{"ts": "2025-12-27T07:45:04", "event": "train_log", "step": 3380, "epoch": 1.4261603375527425, "progress_pct": 23.77, "epoch_pct": 23.77, "eta": "43:11:00", "max_grad_norm": 1.0, "loss": 0.6663658022880554, "grad_norm": 0.4406103193759918, "learning_rate": 0.00018586493204146795}
-{"ts": "2025-12-27T07:45:20", "event": "train_log", "step": 3382, "epoch": 1.4270042194092827, "progress_pct": 23.78, "epoch_pct": 23.78, "eta": "43:09:49", "max_grad_norm": 1.0, "loss": 0.6867321133613586, "grad_norm": 0.420205295085907, "learning_rate": 0.00018584030410271}
-{"ts": "2025-12-27T07:45:35", "event": "train_log", "step": 3384, "epoch": 1.4278481012658228, "progress_pct": 23.8, "epoch_pct": 23.8, "eta": "43:08:39", "max_grad_norm": 1.0, "loss": 0.66688072681427, "grad_norm": 0.4499560594558716, "learning_rate": 0.00018581565636224253}
-{"ts": "2025-12-27T07:45:51", "event": "train_log", "step": 3386, "epoch": 1.4286919831223628, "progress_pct": 23.81, "epoch_pct": 23.81, "eta": "43:07:28", "max_grad_norm": 1.0, "loss": 0.6714702844619751, "grad_norm": 0.42507919669151306, "learning_rate": 0.00018579098882575123}
-{"ts": "2025-12-27T07:46:06", "event": "train_log", "step": 3388, "epoch": 1.429535864978903, "progress_pct": 23.83, "epoch_pct": 23.83, "eta": "43:06:17", "max_grad_norm": 1.0, "loss": 0.7219351530075073, "grad_norm": 0.43856513500213623, "learning_rate": 0.0001857663014989265}
-{"ts": "2025-12-27T07:46:21", "event": "train_log", "step": 3390, "epoch": 1.4303797468354431, "progress_pct": 23.84, "epoch_pct": 23.84, "eta": "43:05:05", "max_grad_norm": 1.0, "loss": 0.7157991528511047, "grad_norm": 0.5167419910430908, "learning_rate": 0.00018574159438746314}
-{"ts": "2025-12-27T07:46:36", "event": "train_log", "step": 3392, "epoch": 1.431223628691983, "progress_pct": 23.85, "epoch_pct": 23.85, "eta": "43:03:53", "max_grad_norm": 1.0, "loss": 0.7509840726852417, "grad_norm": 0.4443167746067047, "learning_rate": 0.00018571686749706067}
-{"ts": "2025-12-27T07:46:51", "event": "train_log", "step": 3394, "epoch": 1.4320675105485232, "progress_pct": 23.87, "epoch_pct": 23.87, "eta": "43:02:41", "max_grad_norm": 1.0, "loss": 0.756000816822052, "grad_norm": 0.41321757435798645, "learning_rate": 0.0001856921208334231}
-{"ts": "2025-12-27T07:47:06", "event": "train_log", "step": 3396, "epoch": 1.4329113924050634, "progress_pct": 23.88, "epoch_pct": 23.88, "eta": "43:01:29", "max_grad_norm": 1.0, "loss": 0.7047854065895081, "grad_norm": 0.4094153046607971, "learning_rate": 0.000185667354402259}
-{"ts": "2025-12-27T07:47:21", "event": "train_log", "step": 3398, "epoch": 1.4337552742616033, "progress_pct": 23.9, "epoch_pct": 23.9, "eta": "43:00:16", "max_grad_norm": 1.0, "loss": 0.7620865106582642, "grad_norm": 0.4248482286930084, "learning_rate": 0.0001856425682092815}
-{"ts": "2025-12-27T07:47:35", "event": "train_log", "step": 3400, "epoch": 1.4345991561181435, "progress_pct": 23.91, "epoch_pct": 23.91, "eta": "42:59:01", "max_grad_norm": 1.0, "loss": 0.7441845536231995, "grad_norm": 0.4190550148487091, "learning_rate": 0.0001856177622602083}
-{"ts": "2025-12-27T07:59:01", "event": "train_log", "step": 3400, "epoch": 1.4345991561181435, "progress_pct": 23.91, "epoch_pct": 23.91, "eta": "43:35:25", "max_grad_norm": 1.0, "eval_loss": 0.7917885780334473, "eval_runtime": 686.1689, "eval_samples_per_second": 3.071, "eval_steps_per_second": 3.071}
-{"ts": "2025-12-27T07:59:17", "event": "train_log", "step": 3402, "epoch": 1.4354430379746836, "progress_pct": 23.92, "epoch_pct": 23.92, "eta": "43:34:13", "max_grad_norm": 1.0, "loss": 0.7123498916625977, "grad_norm": 0.45602327585220337, "learning_rate": 0.00018559293656076166}
-{"ts": "2025-12-27T07:59:32", "event": "train_log", "step": 3404, "epoch": 1.4362869198312236, "progress_pct": 23.94, "epoch_pct": 23.94, "eta": "43:33:00", "max_grad_norm": 1.0, "loss": 0.7096527814865112, "grad_norm": 0.5209269523620605, "learning_rate": 0.00018556809111666843}
-{"ts": "2025-12-27T07:59:48", "event": "train_log", "step": 3406, "epoch": 1.4371308016877637, "progress_pct": 23.95, "epoch_pct": 23.95, "eta": "43:31:49", "max_grad_norm": 1.0, "loss": 0.7116838693618774, "grad_norm": 0.44521182775497437, "learning_rate": 0.00018554322593365995}
-{"ts": "2025-12-27T08:00:02", "event": "train_log", "step": 3408, "epoch": 1.437974683544304, "progress_pct": 23.97, "epoch_pct": 23.97, "eta": "43:30:34", "max_grad_norm": 1.0, "loss": 0.7756352424621582, "grad_norm": 0.44571003317832947, "learning_rate": 0.00018551834101747212}
-{"ts": "2025-12-27T08:00:18", "event": "train_log", "step": 3410, "epoch": 1.4388185654008439, "progress_pct": 23.98, "epoch_pct": 23.98, "eta": "43:29:23", "max_grad_norm": 1.0, "loss": 0.689633309841156, "grad_norm": 0.4030776023864746, "learning_rate": 0.00018549343637384543}
-{"ts": "2025-12-27T08:00:34", "event": "train_log", "step": 3412, "epoch": 1.439662447257384, "progress_pct": 23.99, "epoch_pct": 23.99, "eta": "43:28:14", "max_grad_norm": 1.0, "loss": 0.7173827290534973, "grad_norm": 0.4025530517101288, "learning_rate": 0.0001854685120085249}
-{"ts": "2025-12-27T08:00:50", "event": "train_log", "step": 3414, "epoch": 1.4405063291139242, "progress_pct": 24.01, "epoch_pct": 24.01, "eta": "43:27:04", "max_grad_norm": 1.0, "loss": 0.7212072610855103, "grad_norm": 0.4376870095729828, "learning_rate": 0.0001854435679272601}
-{"ts": "2025-12-27T08:01:05", "event": "train_log", "step": 3416, "epoch": 1.4413502109704641, "progress_pct": 24.02, "epoch_pct": 24.02, "eta": "43:25:50", "max_grad_norm": 1.0, "loss": 0.8260660171508789, "grad_norm": 0.4469084143638611, "learning_rate": 0.00018541860413580515}
-{"ts": "2025-12-27T08:01:21", "event": "train_log", "step": 3418, "epoch": 1.4421940928270043, "progress_pct": 24.04, "epoch_pct": 24.04, "eta": "43:24:40", "max_grad_norm": 1.0, "loss": 0.764930248260498, "grad_norm": 0.48033684492111206, "learning_rate": 0.00018539362063991872}
-{"ts": "2025-12-27T08:01:37", "event": "train_log", "step": 3420, "epoch": 1.4430379746835442, "progress_pct": 24.05, "epoch_pct": 24.05, "eta": "43:23:30", "max_grad_norm": 1.0, "loss": 0.7436494827270508, "grad_norm": 0.4428006708621979, "learning_rate": 0.00018536861744536403}
-{"ts": "2025-12-27T08:01:53", "event": "train_log", "step": 3422, "epoch": 1.4438818565400844, "progress_pct": 24.06, "epoch_pct": 24.06, "eta": "43:22:21", "max_grad_norm": 1.0, "loss": 0.7695552706718445, "grad_norm": 0.41812989115715027, "learning_rate": 0.00018534359455790885}
-{"ts": "2025-12-27T08:02:09", "event": "train_log", "step": 3424, "epoch": 1.4447257383966245, "progress_pct": 24.08, "epoch_pct": 24.08, "eta": "43:21:10", "max_grad_norm": 1.0, "loss": 0.7430856823921204, "grad_norm": 0.4243115186691284, "learning_rate": 0.00018531855198332544}
-{"ts": "2025-12-27T08:02:23", "event": "train_log", "step": 3426, "epoch": 1.4455696202531645, "progress_pct": 24.09, "epoch_pct": 24.09, "eta": "43:19:56", "max_grad_norm": 1.0, "loss": 0.7015851140022278, "grad_norm": 0.44387027621269226, "learning_rate": 0.00018529348972739067}
-{"ts": "2025-12-27T08:02:38", "event": "train_log", "step": 3428, "epoch": 1.4464135021097047, "progress_pct": 24.11, "epoch_pct": 24.11, "eta": "43:18:41", "max_grad_norm": 1.0, "loss": 0.7073075771331787, "grad_norm": 0.5105122923851013, "learning_rate": 0.0001852684077958859}
-{"ts": "2025-12-27T08:02:53", "event": "train_log", "step": 3430, "epoch": 1.4472573839662446, "progress_pct": 24.12, "epoch_pct": 24.12, "eta": "43:17:32", "max_grad_norm": 1.0, "loss": 0.7478930950164795, "grad_norm": 0.40193185210227966, "learning_rate": 0.00018524330619459708}
-{"ts": "2025-12-27T08:03:08", "event": "train_log", "step": 3432, "epoch": 1.4481012658227848, "progress_pct": 24.14, "epoch_pct": 24.14, "eta": "43:16:18", "max_grad_norm": 1.0, "loss": 0.6987152099609375, "grad_norm": 0.47935256361961365, "learning_rate": 0.00018521818492931463}
-{"ts": "2025-12-27T08:03:23", "event": "train_log", "step": 3434, "epoch": 1.448945147679325, "progress_pct": 24.15, "epoch_pct": 24.15, "eta": "43:15:06", "max_grad_norm": 1.0, "loss": 0.6677015423774719, "grad_norm": 0.42298686504364014, "learning_rate": 0.00018519304400583356}
-{"ts": "2025-12-27T08:03:39", "event": "train_log", "step": 3436, "epoch": 1.4497890295358649, "progress_pct": 24.16, "epoch_pct": 24.16, "eta": "43:13:55", "max_grad_norm": 1.0, "loss": 0.5727065205574036, "grad_norm": 0.37220221757888794, "learning_rate": 0.0001851678834299534}
-{"ts": "2025-12-27T08:03:55", "event": "train_log", "step": 3438, "epoch": 1.450632911392405, "progress_pct": 24.18, "epoch_pct": 24.18, "eta": "43:12:45", "max_grad_norm": 1.0, "loss": 0.7245276570320129, "grad_norm": 0.4990854561328888, "learning_rate": 0.00018514270320747823}
-{"ts": "2025-12-27T08:04:11", "event": "train_log", "step": 3440, "epoch": 1.4514767932489452, "progress_pct": 24.19, "epoch_pct": 24.19, "eta": "43:11:38", "max_grad_norm": 1.0, "loss": 0.5907649993896484, "grad_norm": 0.4366965889930725, "learning_rate": 0.00018511750334421665}
-{"ts": "2025-12-27T08:04:26", "event": "train_log", "step": 3442, "epoch": 1.4523206751054851, "progress_pct": 24.21, "epoch_pct": 24.21, "eta": "43:10:25", "max_grad_norm": 1.0, "loss": 0.6898093223571777, "grad_norm": 0.4355267286300659, "learning_rate": 0.00018509228384598172}
-{"ts": "2025-12-27T08:04:43", "event": "train_log", "step": 3444, "epoch": 1.4531645569620253, "progress_pct": 24.22, "epoch_pct": 24.22, "eta": "43:09:19", "max_grad_norm": 1.0, "loss": 0.6242932081222534, "grad_norm": 0.4055832028388977, "learning_rate": 0.00018506704471859116}
-{"ts": "2025-12-27T08:04:58", "event": "train_log", "step": 3446, "epoch": 1.4540084388185655, "progress_pct": 24.23, "epoch_pct": 24.23, "eta": "43:08:07", "max_grad_norm": 1.0, "loss": 0.7214970588684082, "grad_norm": 0.42599600553512573, "learning_rate": 0.00018504178596786712}
-{"ts": "2025-12-27T08:05:14", "event": "train_log", "step": 3448, "epoch": 1.4548523206751054, "progress_pct": 24.25, "epoch_pct": 24.25, "eta": "43:06:59", "max_grad_norm": 1.0, "loss": 0.7120789885520935, "grad_norm": 0.41228237748146057, "learning_rate": 0.0001850165075996363}
-{"ts": "2025-12-27T08:05:30", "event": "train_log", "step": 3450, "epoch": 1.4556962025316456, "progress_pct": 24.26, "epoch_pct": 24.26, "eta": "43:05:48", "max_grad_norm": 1.0, "loss": 0.7376183867454529, "grad_norm": 0.4529595375061035, "learning_rate": 0.00018499120961972996}
-{"ts": "2025-12-27T08:05:44", "event": "train_log", "step": 3452, "epoch": 1.4565400843881857, "progress_pct": 24.28, "epoch_pct": 24.28, "eta": "43:04:35", "max_grad_norm": 1.0, "loss": 0.7321018576622009, "grad_norm": 0.4260895550251007, "learning_rate": 0.00018496589203398386}
-{"ts": "2025-12-27T08:05:58", "event": "train_log", "step": 3454, "epoch": 1.4573839662447257, "progress_pct": 24.29, "epoch_pct": 24.29, "eta": "43:03:20", "max_grad_norm": 1.0, "loss": 0.7099342346191406, "grad_norm": 0.46325981616973877, "learning_rate": 0.00018494055484823824}
-{"ts": "2025-12-27T08:06:14", "event": "train_log", "step": 3456, "epoch": 1.4582278481012658, "progress_pct": 24.3, "epoch_pct": 24.3, "eta": "43:02:10", "max_grad_norm": 1.0, "loss": 0.6663834452629089, "grad_norm": 0.43322354555130005, "learning_rate": 0.00018491519806833795}
-{"ts": "2025-12-27T08:06:30", "event": "train_log", "step": 3458, "epoch": 1.459071729957806, "progress_pct": 24.32, "epoch_pct": 24.32, "eta": "43:01:03", "max_grad_norm": 1.0, "loss": 0.6634764671325684, "grad_norm": 0.421683132648468, "learning_rate": 0.0001848898217001323}
-{"ts": "2025-12-27T08:06:46", "event": "train_log", "step": 3460, "epoch": 1.459915611814346, "progress_pct": 24.33, "epoch_pct": 24.33, "eta": "42:59:53", "max_grad_norm": 1.0, "loss": 0.697095513343811, "grad_norm": 0.44365957379341125, "learning_rate": 0.00018486442574947511}
-{"ts": "2025-12-27T08:07:01", "event": "train_log", "step": 3462, "epoch": 1.460759493670886, "progress_pct": 24.35, "epoch_pct": 24.35, "eta": "42:58:43", "max_grad_norm": 1.0, "loss": 0.8009715676307678, "grad_norm": 0.4892813265323639, "learning_rate": 0.00018483901022222474}
-{"ts": "2025-12-27T08:07:17", "event": "train_log", "step": 3464, "epoch": 1.4616033755274263, "progress_pct": 24.36, "epoch_pct": 24.36, "eta": "42:57:33", "max_grad_norm": 1.0, "loss": 0.631499707698822, "grad_norm": 0.4230288863182068, "learning_rate": 0.00018481357512424408}
-{"ts": "2025-12-27T08:07:32", "event": "train_log", "step": 3466, "epoch": 1.4624472573839662, "progress_pct": 24.37, "epoch_pct": 24.37, "eta": "42:56:21", "max_grad_norm": 1.0, "loss": 0.8045525550842285, "grad_norm": 0.49490758776664734, "learning_rate": 0.00018478812046140056}
-{"ts": "2025-12-27T08:07:47", "event": "train_log", "step": 3468, "epoch": 1.4632911392405064, "progress_pct": 24.39, "epoch_pct": 24.39, "eta": "42:55:10", "max_grad_norm": 1.0, "loss": 0.7299133539199829, "grad_norm": 0.5035375952720642, "learning_rate": 0.00018476264623956597}
-{"ts": "2025-12-27T08:08:02", "event": "train_log", "step": 3470, "epoch": 1.4641350210970465, "progress_pct": 24.4, "epoch_pct": 24.4, "eta": "42:53:58", "max_grad_norm": 1.0, "loss": 0.7313228845596313, "grad_norm": 0.45048409700393677, "learning_rate": 0.00018473715246461684}
-{"ts": "2025-12-27T08:08:16", "event": "train_log", "step": 3472, "epoch": 1.4649789029535865, "progress_pct": 24.42, "epoch_pct": 24.42, "eta": "42:52:46", "max_grad_norm": 1.0, "loss": 0.7515901923179626, "grad_norm": 0.41414541006088257, "learning_rate": 0.00018471163914243405}
-{"ts": "2025-12-27T08:08:31", "event": "train_log", "step": 3474, "epoch": 1.4658227848101266, "progress_pct": 24.43, "epoch_pct": 24.43, "eta": "42:51:35", "max_grad_norm": 1.0, "loss": 0.7425532341003418, "grad_norm": 0.4440646767616272, "learning_rate": 0.00018468610627890298}
-{"ts": "2025-12-27T08:08:46", "event": "train_log", "step": 3476, "epoch": 1.4666666666666668, "progress_pct": 24.44, "epoch_pct": 24.44, "eta": "42:50:23", "max_grad_norm": 1.0, "loss": 0.7509122490882874, "grad_norm": 0.4749740660190582, "learning_rate": 0.00018466055387991362}
-{"ts": "2025-12-27T08:09:00", "event": "train_log", "step": 3478, "epoch": 1.4675105485232067, "progress_pct": 24.46, "epoch_pct": 24.46, "eta": "42:49:10", "max_grad_norm": 1.0, "loss": 0.7395774126052856, "grad_norm": 0.498951256275177, "learning_rate": 0.00018463498195136046}
-{"ts": "2025-12-27T08:09:15", "event": "train_log", "step": 3480, "epoch": 1.4683544303797469, "progress_pct": 24.47, "epoch_pct": 24.47, "eta": "42:47:58", "max_grad_norm": 1.0, "loss": 0.7860153317451477, "grad_norm": 0.45996859669685364, "learning_rate": 0.00018460939049914237}
-{"ts": "2025-12-27T08:09:30", "event": "train_log", "step": 3482, "epoch": 1.469198312236287, "progress_pct": 24.49, "epoch_pct": 24.49, "eta": "42:46:47", "max_grad_norm": 1.0, "loss": 0.8193565607070923, "grad_norm": 0.5989604592323303, "learning_rate": 0.0001845837795291629}
-{"ts": "2025-12-27T08:09:45", "event": "train_log", "step": 3484, "epoch": 1.470042194092827, "progress_pct": 24.5, "epoch_pct": 24.5, "eta": "42:45:35", "max_grad_norm": 1.0, "loss": 0.6569210290908813, "grad_norm": 0.3903721272945404, "learning_rate": 0.0001845581490473299}
-{"ts": "2025-12-27T08:09:59", "event": "train_log", "step": 3486, "epoch": 1.4708860759493672, "progress_pct": 24.51, "epoch_pct": 24.51, "eta": "42:44:24", "max_grad_norm": 1.0, "loss": 0.7226642370223999, "grad_norm": 0.4316142201423645, "learning_rate": 0.00018453249905955592}
-{"ts": "2025-12-27T08:10:14", "event": "train_log", "step": 3488, "epoch": 1.471729957805907, "progress_pct": 24.53, "epoch_pct": 24.53, "eta": "42:43:11", "max_grad_norm": 1.0, "loss": 0.8134398460388184, "grad_norm": 0.4447585344314575, "learning_rate": 0.00018450682957175786}
-{"ts": "2025-12-27T08:10:29", "event": "train_log", "step": 3490, "epoch": 1.4725738396624473, "progress_pct": 24.54, "epoch_pct": 24.54, "eta": "42:41:59", "max_grad_norm": 1.0, "loss": 0.7668985724449158, "grad_norm": 0.42515450716018677, "learning_rate": 0.0001844811405898572}
-{"ts": "2025-12-27T08:10:43", "event": "train_log", "step": 3492, "epoch": 1.4734177215189874, "progress_pct": 24.56, "epoch_pct": 24.56, "eta": "42:40:49", "max_grad_norm": 1.0, "loss": 0.7289790511131287, "grad_norm": 0.39883363246917725, "learning_rate": 0.0001844554321197799}
-{"ts": "2025-12-27T08:10:58", "event": "train_log", "step": 3494, "epoch": 1.4742616033755274, "progress_pct": 24.57, "epoch_pct": 24.57, "eta": "42:39:36", "max_grad_norm": 1.0, "loss": 0.7611824870109558, "grad_norm": 0.4419080317020416, "learning_rate": 0.00018442970416745645}
-{"ts": "2025-12-27T08:11:13", "event": "train_log", "step": 3496, "epoch": 1.4751054852320675, "progress_pct": 24.59, "epoch_pct": 24.59, "eta": "42:38:27", "max_grad_norm": 1.0, "loss": 0.6926230788230896, "grad_norm": 0.37460315227508545, "learning_rate": 0.0001844039567388217}
-{"ts": "2025-12-27T08:11:28", "event": "train_log", "step": 3498, "epoch": 1.4759493670886075, "progress_pct": 24.6, "epoch_pct": 24.6, "eta": "42:37:17", "max_grad_norm": 1.0, "loss": 0.7889325618743896, "grad_norm": 0.47706854343414307, "learning_rate": 0.00018437818983981513}
-{"ts": "2025-12-27T08:11:43", "event": "train_log", "step": 3500, "epoch": 1.4767932489451476, "progress_pct": 24.61, "epoch_pct": 24.61, "eta": "42:36:05", "max_grad_norm": 1.0, "loss": 0.7231656312942505, "grad_norm": 0.449028879404068, "learning_rate": 0.00018435240347638074}
-{"ts": "2025-12-27T08:22:55", "event": "train_log", "step": 3500, "epoch": 1.4767932489451476, "progress_pct": 24.61, "epoch_pct": 24.61, "eta": "43:10:24", "max_grad_norm": 1.0, "eval_loss": 0.7902651429176331, "eval_runtime": 672.312, "eval_samples_per_second": 3.134, "eval_steps_per_second": 3.134}
-{"ts": "2025-12-27T08:23:12", "event": "train_log", "step": 3502, "epoch": 1.4776371308016878, "progress_pct": 24.63, "epoch_pct": 24.63, "eta": "43:09:17", "max_grad_norm": 1.0, "loss": 0.7464927434921265, "grad_norm": 0.44085755944252014, "learning_rate": 0.00018432659765446686}
-{"ts": "2025-12-27T08:23:25", "event": "train_log", "step": 3504, "epoch": 1.4784810126582277, "progress_pct": 24.64, "epoch_pct": 24.64, "eta": "43:08:01", "max_grad_norm": 1.0, "loss": 0.7312393188476562, "grad_norm": 0.4243546724319458, "learning_rate": 0.0001843007723800264}
-{"ts": "2025-12-27T08:23:42", "event": "train_log", "step": 3506, "epoch": 1.479324894514768, "progress_pct": 24.66, "epoch_pct": 24.66, "eta": "43:06:54", "max_grad_norm": 1.0, "loss": 0.7169944643974304, "grad_norm": 0.4437529444694519, "learning_rate": 0.00018427492765901677}
-{"ts": "2025-12-27T08:23:57", "event": "train_log", "step": 3508, "epoch": 1.480168776371308, "progress_pct": 24.67, "epoch_pct": 24.67, "eta": "43:05:43", "max_grad_norm": 1.0, "loss": 0.6169725060462952, "grad_norm": 0.3639313280582428, "learning_rate": 0.0001842490634973999}
-{"ts": "2025-12-27T08:24:13", "event": "train_log", "step": 3510, "epoch": 1.481012658227848, "progress_pct": 24.68, "epoch_pct": 24.68, "eta": "43:04:33", "max_grad_norm": 1.0, "loss": 0.7034649848937988, "grad_norm": 0.4452592730522156, "learning_rate": 0.0001842231799011421}
-{"ts": "2025-12-27T08:24:27", "event": "train_log", "step": 3512, "epoch": 1.4818565400843882, "progress_pct": 24.7, "epoch_pct": 24.7, "eta": "43:03:19", "max_grad_norm": 1.0, "loss": 0.7535615563392639, "grad_norm": 0.5229591131210327, "learning_rate": 0.00018419727687621421}
-{"ts": "2025-12-27T08:24:43", "event": "train_log", "step": 3514, "epoch": 1.4827004219409283, "progress_pct": 24.71, "epoch_pct": 24.71, "eta": "43:02:11", "max_grad_norm": 1.0, "loss": 0.6858918070793152, "grad_norm": 0.40748512744903564, "learning_rate": 0.00018417135442859163}
-{"ts": "2025-12-27T08:24:58", "event": "train_log", "step": 3516, "epoch": 1.4835443037974683, "progress_pct": 24.73, "epoch_pct": 24.73, "eta": "43:01:01", "max_grad_norm": 1.0, "loss": 0.7120109796524048, "grad_norm": 0.4532773792743683, "learning_rate": 0.0001841454125642541}
-{"ts": "2025-12-27T08:25:13", "event": "train_log", "step": 3518, "epoch": 1.4843881856540084, "progress_pct": 24.74, "epoch_pct": 24.74, "eta": "42:59:50", "max_grad_norm": 1.0, "loss": 0.6837015748023987, "grad_norm": 0.4281020760536194, "learning_rate": 0.00018411945128918593}
-{"ts": "2025-12-27T08:25:29", "event": "train_log", "step": 3520, "epoch": 1.4852320675105486, "progress_pct": 24.75, "epoch_pct": 24.75, "eta": "42:58:41", "max_grad_norm": 1.0, "loss": 0.6639618873596191, "grad_norm": 0.4891088306903839, "learning_rate": 0.0001840934706093759}
-{"ts": "2025-12-27T08:25:44", "event": "train_log", "step": 3522, "epoch": 1.4860759493670885, "progress_pct": 24.77, "epoch_pct": 24.77, "eta": "42:57:30", "max_grad_norm": 1.0, "loss": 0.693483829498291, "grad_norm": 0.44358906149864197, "learning_rate": 0.00018406747053081724}
-{"ts": "2025-12-27T08:26:01", "event": "train_log", "step": 3524, "epoch": 1.4869198312236287, "progress_pct": 24.78, "epoch_pct": 24.78, "eta": "42:56:23", "max_grad_norm": 1.0, "loss": 0.7046290636062622, "grad_norm": 0.40134626626968384, "learning_rate": 0.00018404145105950767}
-{"ts": "2025-12-27T08:26:17", "event": "train_log", "step": 3526, "epoch": 1.4877637130801689, "progress_pct": 24.8, "epoch_pct": 24.8, "eta": "42:55:16", "max_grad_norm": 1.0, "loss": 0.6991957426071167, "grad_norm": 0.4601934552192688, "learning_rate": 0.0001840154122014494}
-{"ts": "2025-12-27T08:26:33", "event": "train_log", "step": 3528, "epoch": 1.4886075949367088, "progress_pct": 24.81, "epoch_pct": 24.81, "eta": "42:54:09", "max_grad_norm": 1.0, "loss": 0.667023241519928, "grad_norm": 0.39107242226600647, "learning_rate": 0.00018398935396264906}
-{"ts": "2025-12-27T08:26:50", "event": "train_log", "step": 3530, "epoch": 1.489451476793249, "progress_pct": 24.82, "epoch_pct": 24.82, "eta": "42:53:03", "max_grad_norm": 1.0, "loss": 0.7187332510948181, "grad_norm": 0.4498196542263031, "learning_rate": 0.00018396327634911784}
-{"ts": "2025-12-27T08:27:06", "event": "train_log", "step": 3532, "epoch": 1.4902953586497891, "progress_pct": 24.84, "epoch_pct": 24.84, "eta": "42:51:55", "max_grad_norm": 1.0, "loss": 0.6854014992713928, "grad_norm": 0.41769179701805115, "learning_rate": 0.0001839371793668713}
-{"ts": "2025-12-27T08:27:21", "event": "train_log", "step": 3534, "epoch": 1.491139240506329, "progress_pct": 24.85, "epoch_pct": 24.85, "eta": "42:50:44", "max_grad_norm": 1.0, "loss": 0.6643120050430298, "grad_norm": 0.40170612931251526, "learning_rate": 0.0001839110630219295}
-{"ts": "2025-12-27T08:27:36", "event": "train_log", "step": 3536, "epoch": 1.4919831223628692, "progress_pct": 24.87, "epoch_pct": 24.87, "eta": "42:49:33", "max_grad_norm": 1.0, "loss": 0.6822295188903809, "grad_norm": 0.43697425723075867, "learning_rate": 0.00018388492732031701}
-{"ts": "2025-12-27T08:27:52", "event": "train_log", "step": 3538, "epoch": 1.4928270042194094, "progress_pct": 24.88, "epoch_pct": 24.88, "eta": "42:48:25", "max_grad_norm": 1.0, "loss": 0.7500558495521545, "grad_norm": 0.4400080442428589, "learning_rate": 0.00018385877226806288}
-{"ts": "2025-12-27T08:28:08", "event": "train_log", "step": 3540, "epoch": 1.4936708860759493, "progress_pct": 24.89, "epoch_pct": 24.89, "eta": "42:47:19", "max_grad_norm": 1.0, "loss": 0.7742161750793457, "grad_norm": 0.5162575244903564, "learning_rate": 0.00018383259787120048}
-{"ts": "2025-12-27T08:28:24", "event": "train_log", "step": 3542, "epoch": 1.4945147679324895, "progress_pct": 24.91, "epoch_pct": 24.91, "eta": "42:46:11", "max_grad_norm": 1.0, "loss": 0.7334147095680237, "grad_norm": 0.4234789311885834, "learning_rate": 0.0001838064041357678}
-{"ts": "2025-12-27T08:28:41", "event": "train_log", "step": 3544, "epoch": 1.4953586497890297, "progress_pct": 24.92, "epoch_pct": 24.92, "eta": "42:45:05", "max_grad_norm": 1.0, "loss": 0.691303014755249, "grad_norm": 0.40562525391578674, "learning_rate": 0.0001837801910678072}
-{"ts": "2025-12-27T08:28:55", "event": "train_log", "step": 3546, "epoch": 1.4962025316455696, "progress_pct": 24.94, "epoch_pct": 24.94, "eta": "42:43:54", "max_grad_norm": 1.0, "loss": 0.6478174328804016, "grad_norm": 0.3651523292064667, "learning_rate": 0.00018375395867336556}
-{"ts": "2025-12-27T08:29:11", "event": "train_log", "step": 3548, "epoch": 1.4970464135021098, "progress_pct": 24.95, "epoch_pct": 24.95, "eta": "42:42:46", "max_grad_norm": 1.0, "loss": 0.6800187826156616, "grad_norm": 0.45428016781806946, "learning_rate": 0.00018372770695849417}
-{"ts": "2025-12-27T08:29:29", "event": "train_log", "step": 3550, "epoch": 1.49789029535865, "progress_pct": 24.96, "epoch_pct": 24.96, "eta": "42:41:43", "max_grad_norm": 1.0, "loss": 0.7386951446533203, "grad_norm": 0.4258574843406677, "learning_rate": 0.00018370143592924882}
-{"ts": "2025-12-27T08:29:43", "event": "train_log", "step": 3552, "epoch": 1.4987341772151899, "progress_pct": 24.98, "epoch_pct": 24.98, "eta": "42:40:31", "max_grad_norm": 1.0, "loss": 0.757290780544281, "grad_norm": 0.4260908365249634, "learning_rate": 0.00018367514559168972}
-{"ts": "2025-12-27T08:29:58", "event": "train_log", "step": 3554, "epoch": 1.49957805907173, "progress_pct": 24.99, "epoch_pct": 24.99, "eta": "42:39:22", "max_grad_norm": 1.0, "loss": 0.7254101037979126, "grad_norm": 0.4037017226219177, "learning_rate": 0.00018364883595188152}
-{"ts": "2025-12-27T08:30:13", "event": "train_log", "step": 3556, "epoch": 1.5004219409282702, "progress_pct": 25.01, "epoch_pct": 25.01, "eta": "42:38:11", "max_grad_norm": 1.0, "loss": 0.7342239618301392, "grad_norm": 0.4212391674518585, "learning_rate": 0.0001836225070158934}
-{"ts": "2025-12-27T08:30:28", "event": "train_log", "step": 3558, "epoch": 1.5012658227848101, "progress_pct": 25.02, "epoch_pct": 25.02, "eta": "42:36:59", "max_grad_norm": 1.0, "loss": 0.7147436738014221, "grad_norm": 0.4902292490005493, "learning_rate": 0.0001835961587897989}
-{"ts": "2025-12-27T08:30:44", "event": "train_log", "step": 3560, "epoch": 1.50210970464135, "progress_pct": 25.04, "epoch_pct": 25.04, "eta": "42:35:53", "max_grad_norm": 1.0, "loss": 0.7473883628845215, "grad_norm": 0.39230459928512573, "learning_rate": 0.00018356979127967605}
-{"ts": "2025-12-27T08:31:00", "event": "train_log", "step": 3562, "epoch": 1.5029535864978905, "progress_pct": 25.05, "epoch_pct": 25.05, "eta": "42:34:45", "max_grad_norm": 1.0, "loss": 0.7026845812797546, "grad_norm": 0.4203200340270996, "learning_rate": 0.00018354340449160735}
-{"ts": "2025-12-27T08:31:15", "event": "train_log", "step": 3564, "epoch": 1.5037974683544304, "progress_pct": 25.06, "epoch_pct": 25.06, "eta": "42:33:37", "max_grad_norm": 1.0, "loss": 0.7426526546478271, "grad_norm": 0.44363775849342346, "learning_rate": 0.00018351699843167972}
-{"ts": "2025-12-27T08:31:32", "event": "train_log", "step": 3566, "epoch": 1.5046413502109703, "progress_pct": 25.08, "epoch_pct": 25.08, "eta": "42:32:32", "max_grad_norm": 1.0, "loss": 0.6800932884216309, "grad_norm": 0.4479754865169525, "learning_rate": 0.0001834905731059845}
-{"ts": "2025-12-27T08:31:49", "event": "train_log", "step": 3568, "epoch": 1.5054852320675105, "progress_pct": 25.09, "epoch_pct": 25.09, "eta": "42:31:28", "max_grad_norm": 1.0, "loss": 0.6681315898895264, "grad_norm": 0.43898341059684753, "learning_rate": 0.0001834641285206176}
-{"ts": "2025-12-27T08:32:03", "event": "train_log", "step": 3570, "epoch": 1.5063291139240507, "progress_pct": 25.11, "epoch_pct": 25.11, "eta": "42:30:16", "max_grad_norm": 1.0, "loss": 0.7319603562355042, "grad_norm": 0.44789746403694153, "learning_rate": 0.00018343766468167916}
-{"ts": "2025-12-27T08:32:20", "event": "train_log", "step": 3572, "epoch": 1.5071729957805906, "progress_pct": 25.12, "epoch_pct": 25.12, "eta": "42:29:11", "max_grad_norm": 1.0, "loss": 0.7205765843391418, "grad_norm": 0.44450023770332336, "learning_rate": 0.00018341118159527392}
-{"ts": "2025-12-27T08:32:36", "event": "train_log", "step": 3574, "epoch": 1.5080168776371308, "progress_pct": 25.13, "epoch_pct": 25.13, "eta": "42:28:05", "max_grad_norm": 1.0, "loss": 0.8053180575370789, "grad_norm": 0.4461601674556732, "learning_rate": 0.00018338467926751103}
-{"ts": "2025-12-27T08:32:51", "event": "train_log", "step": 3576, "epoch": 1.508860759493671, "progress_pct": 25.15, "epoch_pct": 25.15, "eta": "42:26:57", "max_grad_norm": 1.0, "loss": 0.6944835186004639, "grad_norm": 0.415216863155365, "learning_rate": 0.00018335815770450408}
-{"ts": "2025-12-27T08:33:07", "event": "train_log", "step": 3578, "epoch": 1.5097046413502109, "progress_pct": 25.16, "epoch_pct": 25.16, "eta": "42:25:48", "max_grad_norm": 1.0, "loss": 0.7333522439002991, "grad_norm": 0.48354068398475647, "learning_rate": 0.00018333161691237105}
-{"ts": "2025-12-27T08:33:23", "event": "train_log", "step": 3580, "epoch": 1.510548523206751, "progress_pct": 25.18, "epoch_pct": 25.18, "eta": "42:24:43", "max_grad_norm": 1.0, "loss": 0.7036639451980591, "grad_norm": 0.44450995326042175, "learning_rate": 0.00018330505689723446}
-{"ts": "2025-12-27T08:33:39", "event": "train_log", "step": 3582, "epoch": 1.5113924050632912, "progress_pct": 25.19, "epoch_pct": 25.19, "eta": "42:23:36", "max_grad_norm": 1.0, "loss": 0.6589286923408508, "grad_norm": 0.355945348739624, "learning_rate": 0.00018327847766522111}
-{"ts": "2025-12-27T08:33:54", "event": "train_log", "step": 3584, "epoch": 1.5122362869198311, "progress_pct": 25.2, "epoch_pct": 25.2, "eta": "42:22:27", "max_grad_norm": 1.0, "loss": 0.7284913063049316, "grad_norm": 0.4532116651535034, "learning_rate": 0.00018325187922246236}
-{"ts": "2025-12-27T08:34:09", "event": "train_log", "step": 3586, "epoch": 1.5130801687763713, "progress_pct": 25.22, "epoch_pct": 25.22, "eta": "42:21:18", "max_grad_norm": 1.0, "loss": 0.7253853678703308, "grad_norm": 0.45910802483558655, "learning_rate": 0.00018322526157509396}
-{"ts": "2025-12-27T08:34:27", "event": "train_log", "step": 3588, "epoch": 1.5139240506329115, "progress_pct": 25.23, "epoch_pct": 25.23, "eta": "42:20:16", "max_grad_norm": 1.0, "loss": 0.7626010179519653, "grad_norm": 0.4729263186454773, "learning_rate": 0.0001831986247292561}
-{"ts": "2025-12-27T08:34:43", "event": "train_log", "step": 3590, "epoch": 1.5147679324894514, "progress_pct": 25.25, "epoch_pct": 25.25, "eta": "42:19:11", "max_grad_norm": 1.0, "loss": 0.705466091632843, "grad_norm": 0.42071840167045593, "learning_rate": 0.00018317196869109336}
-{"ts": "2025-12-27T08:34:59", "event": "train_log", "step": 3592, "epoch": 1.5156118143459916, "progress_pct": 25.26, "epoch_pct": 25.26, "eta": "42:18:07", "max_grad_norm": 1.0, "loss": 0.6900550723075867, "grad_norm": 0.40275856852531433, "learning_rate": 0.00018314529346675479}
-{"ts": "2025-12-27T08:35:15", "event": "train_log", "step": 3594, "epoch": 1.5164556962025317, "progress_pct": 25.27, "epoch_pct": 25.27, "eta": "42:16:59", "max_grad_norm": 1.0, "loss": 0.6951512694358826, "grad_norm": 0.43557414412498474, "learning_rate": 0.00018311859906239387}
-{"ts": "2025-12-27T08:35:30", "event": "train_log", "step": 3596, "epoch": 1.5172995780590717, "progress_pct": 25.29, "epoch_pct": 25.29, "eta": "42:15:51", "max_grad_norm": 1.0, "loss": 0.7453750967979431, "grad_norm": 0.4007355570793152, "learning_rate": 0.00018309188548416844}
-{"ts": "2025-12-27T08:35:46", "event": "train_log", "step": 3598, "epoch": 1.5181434599156118, "progress_pct": 25.3, "epoch_pct": 25.3, "eta": "42:14:46", "max_grad_norm": 1.0, "loss": 0.7549434900283813, "grad_norm": 0.4686451256275177, "learning_rate": 0.00018306515273824086}
-{"ts": "2025-12-27T08:36:01", "event": "train_log", "step": 3600, "epoch": 1.518987341772152, "progress_pct": 25.32, "epoch_pct": 25.32, "eta": "42:13:35", "max_grad_norm": 1.0, "loss": 0.7708864212036133, "grad_norm": 0.47308704257011414, "learning_rate": 0.0001830384008307778}
-{"ts": "2025-12-27T08:47:16", "event": "train_log", "step": 3600, "epoch": 1.518987341772152, "progress_pct": 25.32, "epoch_pct": 25.32, "eta": "42:46:47", "max_grad_norm": 1.0, "eval_loss": 0.785450279712677, "eval_runtime": 675.2312, "eval_samples_per_second": 3.12, "eval_steps_per_second": 3.12}
-{"ts": "2025-12-27T08:47:32", "event": "train_log", "step": 3602, "epoch": 1.519831223628692, "progress_pct": 25.33, "epoch_pct": 25.33, "eta": "42:45:39", "max_grad_norm": 1.0, "loss": 0.7501338124275208, "grad_norm": 0.4343389570713043, "learning_rate": 0.0001830116297679505}
-{"ts": "2025-12-27T08:47:46", "event": "train_log", "step": 3604, "epoch": 1.520675105485232, "progress_pct": 25.34, "epoch_pct": 25.34, "eta": "42:44:28", "max_grad_norm": 1.0, "loss": 0.7358015179634094, "grad_norm": 0.4971345067024231, "learning_rate": 0.00018298483955593445}
-{"ts": "2025-12-27T08:48:01", "event": "train_log", "step": 3606, "epoch": 1.5215189873417723, "progress_pct": 25.36, "epoch_pct": 25.36, "eta": "42:43:17", "max_grad_norm": 1.0, "loss": 0.7972728610038757, "grad_norm": 0.42013493180274963, "learning_rate": 0.0001829580302009097}
-{"ts": "2025-12-27T08:48:17", "event": "train_log", "step": 3608, "epoch": 1.5223628691983122, "progress_pct": 25.37, "epoch_pct": 25.37, "eta": "42:42:08", "max_grad_norm": 1.0, "loss": 0.5908644199371338, "grad_norm": 0.44829806685447693, "learning_rate": 0.00018293120170906062}
-{"ts": "2025-12-27T08:48:31", "event": "train_log", "step": 3610, "epoch": 1.5232067510548524, "progress_pct": 25.39, "epoch_pct": 25.39, "eta": "42:40:56", "max_grad_norm": 1.0, "loss": 0.7872797846794128, "grad_norm": 0.47412917017936707, "learning_rate": 0.000182904354086576}
-{"ts": "2025-12-27T08:48:46", "event": "train_log", "step": 3612, "epoch": 1.5240506329113925, "progress_pct": 25.4, "epoch_pct": 25.4, "eta": "42:39:46", "max_grad_norm": 1.0, "loss": 0.7327616214752197, "grad_norm": 0.4224211275577545, "learning_rate": 0.0001828774873396491}
-{"ts": "2025-12-27T08:49:01", "event": "train_log", "step": 3614, "epoch": 1.5248945147679325, "progress_pct": 25.41, "epoch_pct": 25.41, "eta": "42:38:37", "max_grad_norm": 1.0, "loss": 0.6649892330169678, "grad_norm": 0.4055147171020508, "learning_rate": 0.00018285060147447756}
-{"ts": "2025-12-27T08:49:17", "event": "train_log", "step": 3616, "epoch": 1.5257383966244724, "progress_pct": 25.43, "epoch_pct": 25.43, "eta": "42:37:28", "max_grad_norm": 1.0, "loss": 0.6939427852630615, "grad_norm": 0.4058035910129547, "learning_rate": 0.00018282369649726346}
-{"ts": "2025-12-27T08:49:32", "event": "train_log", "step": 3618, "epoch": 1.5265822784810128, "progress_pct": 25.44, "epoch_pct": 25.44, "eta": "42:36:18", "max_grad_norm": 1.0, "loss": 0.6351069211959839, "grad_norm": 0.4192068874835968, "learning_rate": 0.00018279677241421325}
-{"ts": "2025-12-27T08:49:46", "event": "train_log", "step": 3620, "epoch": 1.5274261603375527, "progress_pct": 25.46, "epoch_pct": 25.46, "eta": "42:35:08", "max_grad_norm": 1.0, "loss": 0.6963213682174683, "grad_norm": 0.4659916162490845, "learning_rate": 0.00018276982923153776}
-{"ts": "2025-12-27T08:50:00", "event": "train_log", "step": 3622, "epoch": 1.5282700421940927, "progress_pct": 25.47, "epoch_pct": 25.47, "eta": "42:33:55", "max_grad_norm": 1.0, "loss": 0.7463255524635315, "grad_norm": 0.4993051290512085, "learning_rate": 0.00018274286695545229}
-{"ts": "2025-12-27T08:50:15", "event": "train_log", "step": 3624, "epoch": 1.529113924050633, "progress_pct": 25.49, "epoch_pct": 25.49, "eta": "42:32:45", "max_grad_norm": 1.0, "loss": 0.6566499471664429, "grad_norm": 0.39232251048088074, "learning_rate": 0.00018271588559217654}
-{"ts": "2025-12-27T08:50:30", "event": "train_log", "step": 3626, "epoch": 1.529957805907173, "progress_pct": 25.5, "epoch_pct": 25.5, "eta": "42:31:34", "max_grad_norm": 1.0, "loss": 0.7695494890213013, "grad_norm": 0.4482063353061676, "learning_rate": 0.00018268888514793457}
-{"ts": "2025-12-27T08:50:45", "event": "train_log", "step": 3628, "epoch": 1.530801687763713, "progress_pct": 25.51, "epoch_pct": 25.51, "eta": "42:30:25", "max_grad_norm": 1.0, "loss": 0.7357239723205566, "grad_norm": 0.4000336825847626, "learning_rate": 0.00018266186562895483}
-{"ts": "2025-12-27T08:51:00", "event": "train_log", "step": 3630, "epoch": 1.5316455696202531, "progress_pct": 25.53, "epoch_pct": 25.53, "eta": "42:29:15", "max_grad_norm": 1.0, "loss": 0.7234170436859131, "grad_norm": 0.4220462441444397, "learning_rate": 0.0001826348270414703}
-{"ts": "2025-12-27T08:51:14", "event": "train_log", "step": 3632, "epoch": 1.5324894514767933, "progress_pct": 25.54, "epoch_pct": 25.54, "eta": "42:28:03", "max_grad_norm": 1.0, "loss": 0.7864061594009399, "grad_norm": 0.4787490665912628, "learning_rate": 0.00018260776939171814}
-{"ts": "2025-12-27T08:51:29", "event": "train_log", "step": 3634, "epoch": 1.5333333333333332, "progress_pct": 25.56, "epoch_pct": 25.56, "eta": "42:26:56", "max_grad_norm": 1.0, "loss": 0.670537531375885, "grad_norm": 0.3670683205127716, "learning_rate": 0.00018258069268594013}
-{"ts": "2025-12-27T08:51:45", "event": "train_log", "step": 3636, "epoch": 1.5341772151898734, "progress_pct": 25.57, "epoch_pct": 25.57, "eta": "42:25:48", "max_grad_norm": 1.0, "loss": 0.7535691261291504, "grad_norm": 0.41599538922309875, "learning_rate": 0.0001825535969303823}
-{"ts": "2025-12-27T08:51:59", "event": "train_log", "step": 3638, "epoch": 1.5350210970464135, "progress_pct": 25.58, "epoch_pct": 25.58, "eta": "42:24:36", "max_grad_norm": 1.0, "loss": 0.7553712725639343, "grad_norm": 0.5033245086669922, "learning_rate": 0.00018252648213129514}
-{"ts": "2025-12-27T08:52:15", "event": "train_log", "step": 3640, "epoch": 1.5358649789029535, "progress_pct": 25.6, "epoch_pct": 25.6, "eta": "42:23:30", "max_grad_norm": 1.0, "loss": 0.7149441242218018, "grad_norm": 0.4235823452472687, "learning_rate": 0.0001824993482949335}
-{"ts": "2025-12-27T08:52:30", "event": "train_log", "step": 3642, "epoch": 1.5367088607594936, "progress_pct": 25.61, "epoch_pct": 25.61, "eta": "42:22:22", "max_grad_norm": 1.0, "loss": 0.735568642616272, "grad_norm": 0.37993329763412476, "learning_rate": 0.00018247219542755664}
-{"ts": "2025-12-27T08:52:46", "event": "train_log", "step": 3644, "epoch": 1.5375527426160338, "progress_pct": 25.63, "epoch_pct": 25.63, "eta": "42:21:14", "max_grad_norm": 1.0, "loss": 0.693510115146637, "grad_norm": 0.39534425735473633, "learning_rate": 0.00018244502353542818}
-{"ts": "2025-12-27T08:53:01", "event": "train_log", "step": 3646, "epoch": 1.5383966244725737, "progress_pct": 25.64, "epoch_pct": 25.64, "eta": "42:20:05", "max_grad_norm": 1.0, "loss": 0.7261984348297119, "grad_norm": 0.45447441935539246, "learning_rate": 0.00018241783262481622}
-{"ts": "2025-12-27T08:53:18", "event": "train_log", "step": 3648, "epoch": 1.539240506329114, "progress_pct": 25.65, "epoch_pct": 25.65, "eta": "42:19:02", "max_grad_norm": 1.0, "loss": 0.7518824338912964, "grad_norm": 0.4131409823894501, "learning_rate": 0.0001823906227019931}
-{"ts": "2025-12-27T08:53:33", "event": "train_log", "step": 3650, "epoch": 1.540084388185654, "progress_pct": 25.67, "epoch_pct": 25.67, "eta": "42:17:54", "max_grad_norm": 1.0, "loss": 0.7650659680366516, "grad_norm": 0.46603885293006897, "learning_rate": 0.00018236339377323567}
-{"ts": "2025-12-27T08:53:51", "event": "train_log", "step": 3652, "epoch": 1.540928270042194, "progress_pct": 25.68, "epoch_pct": 25.68, "eta": "42:16:53", "max_grad_norm": 1.0, "loss": 0.6436064839363098, "grad_norm": 0.3998747766017914, "learning_rate": 0.00018233614584482513}
-{"ts": "2025-12-27T08:54:07", "event": "train_log", "step": 3654, "epoch": 1.5417721518987342, "progress_pct": 25.7, "epoch_pct": 25.7, "eta": "42:15:47", "max_grad_norm": 1.0, "loss": 0.7068451642990112, "grad_norm": 0.4314839839935303, "learning_rate": 0.00018230887892304703}
-{"ts": "2025-12-27T08:54:22", "event": "train_log", "step": 3656, "epoch": 1.5426160337552743, "progress_pct": 25.71, "epoch_pct": 25.71, "eta": "42:14:38", "max_grad_norm": 1.0, "loss": 0.7342977523803711, "grad_norm": 0.4324610233306885, "learning_rate": 0.0001822815930141913}
-{"ts": "2025-12-27T08:54:38", "event": "train_log", "step": 3658, "epoch": 1.5434599156118143, "progress_pct": 25.72, "epoch_pct": 25.72, "eta": "42:13:32", "max_grad_norm": 1.0, "loss": 0.6482785940170288, "grad_norm": 0.4385458827018738, "learning_rate": 0.0001822542881245524}
-{"ts": "2025-12-27T08:54:54", "event": "train_log", "step": 3660, "epoch": 1.5443037974683544, "progress_pct": 25.74, "epoch_pct": 25.74, "eta": "42:12:27", "max_grad_norm": 1.0, "loss": 0.6319621205329895, "grad_norm": 0.3736587166786194, "learning_rate": 0.0001822269642604289}
-{"ts": "2025-12-27T08:55:08", "event": "train_log", "step": 3662, "epoch": 1.5451476793248946, "progress_pct": 25.75, "epoch_pct": 25.75, "eta": "42:11:17", "max_grad_norm": 1.0, "loss": 0.6603307723999023, "grad_norm": 0.42113035917282104, "learning_rate": 0.00018219962142812393}
-{"ts": "2025-12-27T08:55:24", "event": "train_log", "step": 3664, "epoch": 1.5459915611814345, "progress_pct": 25.77, "epoch_pct": 25.77, "eta": "42:10:09", "max_grad_norm": 1.0, "loss": 0.6874772906303406, "grad_norm": 0.422158420085907, "learning_rate": 0.00018217225963394496}
-{"ts": "2025-12-27T08:55:40", "event": "train_log", "step": 3666, "epoch": 1.5468354430379747, "progress_pct": 25.78, "epoch_pct": 25.78, "eta": "42:09:06", "max_grad_norm": 1.0, "loss": 0.7231854796409607, "grad_norm": 0.42724940180778503, "learning_rate": 0.00018214487888420388}
-{"ts": "2025-12-27T08:55:58", "event": "train_log", "step": 3668, "epoch": 1.5476793248945149, "progress_pct": 25.79, "epoch_pct": 25.79, "eta": "42:08:06", "max_grad_norm": 1.0, "loss": 0.6418231129646301, "grad_norm": 0.3747844398021698, "learning_rate": 0.00018211747918521685}
-{"ts": "2025-12-27T08:56:15", "event": "train_log", "step": 3670, "epoch": 1.5485232067510548, "progress_pct": 25.81, "epoch_pct": 25.81, "eta": "42:07:03", "max_grad_norm": 1.0, "loss": 0.7019823789596558, "grad_norm": 0.37007269263267517, "learning_rate": 0.00018209006054330446}
-{"ts": "2025-12-27T08:56:30", "event": "train_log", "step": 3672, "epoch": 1.549367088607595, "progress_pct": 25.82, "epoch_pct": 25.82, "eta": "42:05:55", "max_grad_norm": 1.0, "loss": 0.6632764339447021, "grad_norm": 0.409701943397522, "learning_rate": 0.00018206262296479168}
-{"ts": "2025-12-27T08:56:45", "event": "train_log", "step": 3674, "epoch": 1.5502109704641351, "progress_pct": 25.84, "epoch_pct": 25.84, "eta": "42:04:47", "max_grad_norm": 1.0, "loss": 0.7327075600624084, "grad_norm": 0.49566221237182617, "learning_rate": 0.00018203516645600782}
-{"ts": "2025-12-27T08:57:01", "event": "train_log", "step": 3676, "epoch": 1.551054852320675, "progress_pct": 25.85, "epoch_pct": 25.85, "eta": "42:03:42", "max_grad_norm": 1.0, "loss": 0.6535149812698364, "grad_norm": 0.4549940526485443, "learning_rate": 0.0001820076910232866}
-{"ts": "2025-12-27T08:57:16", "event": "train_log", "step": 3678, "epoch": 1.5518987341772152, "progress_pct": 25.86, "epoch_pct": 25.86, "eta": "42:02:35", "max_grad_norm": 1.0, "loss": 0.7761320471763611, "grad_norm": 0.42619478702545166, "learning_rate": 0.000181980196672966}
-{"ts": "2025-12-27T08:57:31", "event": "train_log", "step": 3680, "epoch": 1.5527426160337554, "progress_pct": 25.88, "epoch_pct": 25.88, "eta": "42:01:26", "max_grad_norm": 1.0, "loss": 0.6728626489639282, "grad_norm": 0.4332887828350067, "learning_rate": 0.00018195268341138852}
-{"ts": "2025-12-27T08:57:47", "event": "train_log", "step": 3682, "epoch": 1.5535864978902953, "progress_pct": 25.89, "epoch_pct": 25.89, "eta": "42:00:19", "max_grad_norm": 1.0, "loss": 0.7369232177734375, "grad_norm": 0.4972975552082062, "learning_rate": 0.0001819251512449009}
-{"ts": "2025-12-27T08:58:03", "event": "train_log", "step": 3684, "epoch": 1.5544303797468353, "progress_pct": 25.91, "epoch_pct": 25.91, "eta": "41:59:15", "max_grad_norm": 1.0, "loss": 0.6703663468360901, "grad_norm": 0.3619556725025177, "learning_rate": 0.00018189760017985428}
-{"ts": "2025-12-27T08:58:19", "event": "train_log", "step": 3686, "epoch": 1.5552742616033757, "progress_pct": 25.92, "epoch_pct": 25.92, "eta": "41:58:11", "max_grad_norm": 1.0, "loss": 0.7183756828308105, "grad_norm": 0.46435829997062683, "learning_rate": 0.00018187003022260417}
-{"ts": "2025-12-27T08:58:36", "event": "train_log", "step": 3688, "epoch": 1.5561181434599156, "progress_pct": 25.94, "epoch_pct": 25.94, "eta": "41:57:08", "max_grad_norm": 1.0, "loss": 0.680042564868927, "grad_norm": 0.4605063498020172, "learning_rate": 0.00018184244137951045}
-{"ts": "2025-12-27T08:58:52", "event": "train_log", "step": 3690, "epoch": 1.5569620253164556, "progress_pct": 25.95, "epoch_pct": 25.95, "eta": "41:56:02", "max_grad_norm": 1.0, "loss": 0.679821789264679, "grad_norm": 0.4023124873638153, "learning_rate": 0.00018181483365693732}
-{"ts": "2025-12-27T08:59:07", "event": "train_log", "step": 3692, "epoch": 1.557805907172996, "progress_pct": 25.96, "epoch_pct": 25.96, "eta": "41:54:55", "max_grad_norm": 1.0, "loss": 0.7408921718597412, "grad_norm": 0.459499716758728, "learning_rate": 0.00018178720706125333}
-{"ts": "2025-12-27T08:59:22", "event": "train_log", "step": 3694, "epoch": 1.5586497890295359, "progress_pct": 25.98, "epoch_pct": 25.98, "eta": "41:53:48", "max_grad_norm": 1.0, "loss": 0.6926741003990173, "grad_norm": 0.4397135078907013, "learning_rate": 0.00018175956159883146}
-{"ts": "2025-12-27T08:59:38", "event": "train_log", "step": 3696, "epoch": 1.5594936708860758, "progress_pct": 25.99, "epoch_pct": 25.99, "eta": "41:52:43", "max_grad_norm": 1.0, "loss": 0.752724826335907, "grad_norm": 0.4476170837879181, "learning_rate": 0.0001817318972760489}
-{"ts": "2025-12-27T08:59:53", "event": "train_log", "step": 3698, "epoch": 1.560337552742616, "progress_pct": 26.01, "epoch_pct": 26.01, "eta": "41:51:36", "max_grad_norm": 1.0, "loss": 0.7217722535133362, "grad_norm": 0.43684154748916626, "learning_rate": 0.00018170421409928735}
-{"ts": "2025-12-27T09:00:10", "event": "train_log", "step": 3700, "epoch": 1.5611814345991561, "progress_pct": 26.02, "epoch_pct": 26.02, "eta": "41:50:33", "max_grad_norm": 1.0, "loss": 0.7264936566352844, "grad_norm": 0.4118131995201111, "learning_rate": 0.00018167651207493278}
-{"ts": "2025-12-27T09:11:38", "event": "train_log", "step": 3700, "epoch": 1.5611814345991561, "progress_pct": 26.02, "epoch_pct": 26.02, "eta": "42:23:09", "max_grad_norm": 1.0, "eval_loss": 0.7854447960853577, "eval_runtime": 687.7907, "eval_samples_per_second": 3.063, "eval_steps_per_second": 3.063}
-{"ts": "2025-12-27T09:11:53", "event": "train_log", "step": 3702, "epoch": 1.562025316455696, "progress_pct": 26.03, "epoch_pct": 26.03, "eta": "42:22:00", "max_grad_norm": 1.0, "loss": 0.701478123664856, "grad_norm": 0.40639030933380127, "learning_rate": 0.0001816487912093755}
-{"ts": "2025-12-27T09:12:08", "event": "train_log", "step": 3704, "epoch": 1.5628691983122363, "progress_pct": 26.05, "epoch_pct": 26.05, "eta": "42:20:52", "max_grad_norm": 1.0, "loss": 0.696711003780365, "grad_norm": 0.4205699563026428, "learning_rate": 0.00018162105150901017}
-{"ts": "2025-12-27T09:12:22", "event": "train_log", "step": 3706, "epoch": 1.5637130801687764, "progress_pct": 26.06, "epoch_pct": 26.06, "eta": "42:19:41", "max_grad_norm": 1.0, "loss": 0.7130293250083923, "grad_norm": 0.46437183022499084, "learning_rate": 0.0001815932929802358}
-{"ts": "2025-12-27T09:12:36", "event": "train_log", "step": 3708, "epoch": 1.5645569620253164, "progress_pct": 26.08, "epoch_pct": 26.08, "eta": "42:18:30", "max_grad_norm": 1.0, "loss": 0.7180310487747192, "grad_norm": 0.4413023591041565, "learning_rate": 0.0001815655156294558}
-{"ts": "2025-12-27T09:12:51", "event": "train_log", "step": 3710, "epoch": 1.5654008438818565, "progress_pct": 26.09, "epoch_pct": 26.09, "eta": "42:17:22", "max_grad_norm": 1.0, "loss": 0.6883325576782227, "grad_norm": 0.3964478075504303, "learning_rate": 0.00018153771946307783}
-{"ts": "2025-12-27T09:13:08", "event": "train_log", "step": 3712, "epoch": 1.5662447257383967, "progress_pct": 26.1, "epoch_pct": 26.1, "eta": "42:16:18", "max_grad_norm": 1.0, "loss": 0.6683162450790405, "grad_norm": 0.34486109018325806, "learning_rate": 0.00018150990448751394}
-{"ts": "2025-12-27T09:13:23", "event": "train_log", "step": 3714, "epoch": 1.5670886075949366, "progress_pct": 26.12, "epoch_pct": 26.12, "eta": "42:15:09", "max_grad_norm": 1.0, "loss": 0.6969789862632751, "grad_norm": 0.4209035336971283, "learning_rate": 0.00018148207070918052}
-{"ts": "2025-12-27T09:13:38", "event": "train_log", "step": 3716, "epoch": 1.5679324894514768, "progress_pct": 26.13, "epoch_pct": 26.13, "eta": "42:14:00", "max_grad_norm": 1.0, "loss": 0.714320182800293, "grad_norm": 0.41674816608428955, "learning_rate": 0.00018145421813449829}
-{"ts": "2025-12-27T09:13:53", "event": "train_log", "step": 3718, "epoch": 1.568776371308017, "progress_pct": 26.15, "epoch_pct": 26.15, "eta": "42:12:53", "max_grad_norm": 1.0, "loss": 0.7125279307365417, "grad_norm": 0.4365934729576111, "learning_rate": 0.00018142634676989228}
-{"ts": "2025-12-27T09:14:08", "event": "train_log", "step": 3720, "epoch": 1.5696202531645569, "progress_pct": 26.16, "epoch_pct": 26.16, "eta": "42:11:44", "max_grad_norm": 1.0, "loss": 0.6787398457527161, "grad_norm": 0.43599721789360046, "learning_rate": 0.00018139845662179188}
-{"ts": "2025-12-27T09:14:24", "event": "train_log", "step": 3722, "epoch": 1.570464135021097, "progress_pct": 26.17, "epoch_pct": 26.17, "eta": "42:10:38", "max_grad_norm": 1.0, "loss": 0.6401328444480896, "grad_norm": 0.36320003867149353, "learning_rate": 0.0001813705476966308}
-{"ts": "2025-12-27T09:14:39", "event": "train_log", "step": 3724, "epoch": 1.5713080168776372, "progress_pct": 26.19, "epoch_pct": 26.19, "eta": "42:09:31", "max_grad_norm": 1.0, "loss": 0.6875129342079163, "grad_norm": 0.43504419922828674, "learning_rate": 0.00018134262000084718}
-{"ts": "2025-12-27T09:14:54", "event": "train_log", "step": 3726, "epoch": 1.5721518987341772, "progress_pct": 26.2, "epoch_pct": 26.2, "eta": "42:08:23", "max_grad_norm": 1.0, "loss": 0.6903918385505676, "grad_norm": 0.476723313331604, "learning_rate": 0.00018131467354088332}
-{"ts": "2025-12-27T09:15:09", "event": "train_log", "step": 3728, "epoch": 1.5729957805907173, "progress_pct": 26.22, "epoch_pct": 26.22, "eta": "42:07:15", "max_grad_norm": 1.0, "loss": 0.690018892288208, "grad_norm": 0.4465550184249878, "learning_rate": 0.00018128670832318592}
-{"ts": "2025-12-27T09:15:24", "event": "train_log", "step": 3730, "epoch": 1.5738396624472575, "progress_pct": 26.23, "epoch_pct": 26.23, "eta": "42:06:07", "max_grad_norm": 1.0, "loss": 0.6912158727645874, "grad_norm": 0.43816477060317993, "learning_rate": 0.0001812587243542061}
-{"ts": "2025-12-27T09:15:39", "event": "train_log", "step": 3732, "epoch": 1.5746835443037974, "progress_pct": 26.24, "epoch_pct": 26.24, "eta": "42:04:59", "max_grad_norm": 1.0, "loss": 0.7415492534637451, "grad_norm": 0.40546250343322754, "learning_rate": 0.00018123072164039913}
-{"ts": "2025-12-27T09:15:54", "event": "train_log", "step": 3734, "epoch": 1.5755274261603376, "progress_pct": 26.26, "epoch_pct": 26.26, "eta": "42:03:52", "max_grad_norm": 1.0, "loss": 0.7664727568626404, "grad_norm": 0.4253178536891937, "learning_rate": 0.00018120270018822477}
-{"ts": "2025-12-27T09:16:08", "event": "train_log", "step": 3736, "epoch": 1.5763713080168777, "progress_pct": 26.27, "epoch_pct": 26.27, "eta": "42:02:41", "max_grad_norm": 1.0, "loss": 0.782779335975647, "grad_norm": 0.503524661064148, "learning_rate": 0.000181174660004147}
-{"ts": "2025-12-27T09:16:22", "event": "train_log", "step": 3738, "epoch": 1.5772151898734177, "progress_pct": 26.29, "epoch_pct": 26.29, "eta": "42:01:29", "max_grad_norm": 1.0, "loss": 0.806460976600647, "grad_norm": 0.5260395407676697, "learning_rate": 0.00018114660109463414}
-{"ts": "2025-12-27T09:16:37", "event": "train_log", "step": 3740, "epoch": 1.5780590717299579, "progress_pct": 26.3, "epoch_pct": 26.3, "eta": "42:00:23", "max_grad_norm": 1.0, "loss": 0.6859704852104187, "grad_norm": 0.3641359806060791, "learning_rate": 0.0001811185234661589}
-{"ts": "2025-12-27T09:16:52", "event": "train_log", "step": 3742, "epoch": 1.578902953586498, "progress_pct": 26.32, "epoch_pct": 26.32, "eta": "41:59:14", "max_grad_norm": 1.0, "loss": 0.7798553109169006, "grad_norm": 0.4468916058540344, "learning_rate": 0.00018109042712519818}
-{"ts": "2025-12-27T09:17:07", "event": "train_log", "step": 3744, "epoch": 1.579746835443038, "progress_pct": 26.33, "epoch_pct": 26.33, "eta": "41:58:06", "max_grad_norm": 1.0, "loss": 0.7086471915245056, "grad_norm": 0.4078207015991211, "learning_rate": 0.00018106231207823327}
-{"ts": "2025-12-27T09:17:23", "event": "train_log", "step": 3746, "epoch": 1.580590717299578, "progress_pct": 26.34, "epoch_pct": 26.34, "eta": "41:57:03", "max_grad_norm": 1.0, "loss": 0.6669760346412659, "grad_norm": 0.39144742488861084, "learning_rate": 0.00018103417833174981}
-{"ts": "2025-12-27T09:17:38", "event": "train_log", "step": 3748, "epoch": 1.5814345991561183, "progress_pct": 26.36, "epoch_pct": 26.36, "eta": "41:55:54", "max_grad_norm": 1.0, "loss": 0.7296954989433289, "grad_norm": 0.4366845190525055, "learning_rate": 0.0001810060258922377}
-{"ts": "2025-12-27T09:17:53", "event": "train_log", "step": 3750, "epoch": 1.5822784810126582, "progress_pct": 26.37, "epoch_pct": 26.37, "eta": "41:54:46", "max_grad_norm": 1.0, "loss": 0.7663856148719788, "grad_norm": 0.46795082092285156, "learning_rate": 0.00018097785476619118}
-{"ts": "2025-12-27T09:18:08", "event": "train_log", "step": 3752, "epoch": 1.5831223628691982, "progress_pct": 26.39, "epoch_pct": 26.39, "eta": "41:53:39", "max_grad_norm": 1.0, "loss": 0.7105234861373901, "grad_norm": 0.40331873297691345, "learning_rate": 0.00018094966496010878}
-{"ts": "2025-12-27T09:18:24", "event": "train_log", "step": 3754, "epoch": 1.5839662447257385, "progress_pct": 26.4, "epoch_pct": 26.4, "eta": "41:52:34", "max_grad_norm": 1.0, "loss": 0.666635274887085, "grad_norm": 0.38210469484329224, "learning_rate": 0.00018092145648049334}
-{"ts": "2025-12-27T09:18:38", "event": "train_log", "step": 3756, "epoch": 1.5848101265822785, "progress_pct": 26.41, "epoch_pct": 26.41, "eta": "41:51:24", "max_grad_norm": 1.0, "loss": 0.7287175059318542, "grad_norm": 0.45946040749549866, "learning_rate": 0.000180893229333852}
-{"ts": "2025-12-27T09:18:53", "event": "train_log", "step": 3758, "epoch": 1.5856540084388184, "progress_pct": 26.43, "epoch_pct": 26.43, "eta": "41:50:18", "max_grad_norm": 1.0, "loss": 0.7145618796348572, "grad_norm": 0.4035777747631073, "learning_rate": 0.00018086498352669624}
-{"ts": "2025-12-27T09:19:07", "event": "train_log", "step": 3760, "epoch": 1.5864978902953588, "progress_pct": 26.44, "epoch_pct": 26.44, "eta": "41:49:08", "max_grad_norm": 1.0, "loss": 0.6550979018211365, "grad_norm": 0.42843320965766907, "learning_rate": 0.0001808367190655418}
-{"ts": "2025-12-27T09:19:23", "event": "train_log", "step": 3762, "epoch": 1.5873417721518988, "progress_pct": 26.46, "epoch_pct": 26.46, "eta": "41:48:03", "max_grad_norm": 1.0, "loss": 0.7040430307388306, "grad_norm": 0.4016468822956085, "learning_rate": 0.0001808084359569088}
-{"ts": "2025-12-27T09:19:37", "event": "train_log", "step": 3764, "epoch": 1.5881856540084387, "progress_pct": 26.47, "epoch_pct": 26.47, "eta": "41:46:52", "max_grad_norm": 1.0, "loss": 0.7523179054260254, "grad_norm": 0.4126848578453064, "learning_rate": 0.00018078013420732157}
-{"ts": "2025-12-27T09:19:51", "event": "train_log", "step": 3766, "epoch": 1.5890295358649789, "progress_pct": 26.48, "epoch_pct": 26.48, "eta": "41:45:45", "max_grad_norm": 1.0, "loss": 0.7497967481613159, "grad_norm": 0.45878592133522034, "learning_rate": 0.00018075181382330878}
-{"ts": "2025-12-27T09:20:06", "event": "train_log", "step": 3768, "epoch": 1.589873417721519, "progress_pct": 26.5, "epoch_pct": 26.5, "eta": "41:44:37", "max_grad_norm": 1.0, "loss": 0.7694459557533264, "grad_norm": 0.44179272651672363, "learning_rate": 0.00018072347481140345}
-{"ts": "2025-12-27T09:20:21", "event": "train_log", "step": 3770, "epoch": 1.590717299578059, "progress_pct": 26.51, "epoch_pct": 26.51, "eta": "41:43:31", "max_grad_norm": 1.0, "loss": 0.6766634583473206, "grad_norm": 0.3706412613391876, "learning_rate": 0.00018069511717814276}
-{"ts": "2025-12-27T09:20:36", "event": "train_log", "step": 3772, "epoch": 1.5915611814345991, "progress_pct": 26.53, "epoch_pct": 26.53, "eta": "41:42:24", "max_grad_norm": 1.0, "loss": 0.6394028067588806, "grad_norm": 0.40555453300476074, "learning_rate": 0.0001806667409300683}
-{"ts": "2025-12-27T09:20:52", "event": "train_log", "step": 3774, "epoch": 1.5924050632911393, "progress_pct": 26.54, "epoch_pct": 26.54, "eta": "41:41:19", "max_grad_norm": 1.0, "loss": 0.6775637865066528, "grad_norm": 0.3752219080924988, "learning_rate": 0.000180638346073726}
-{"ts": "2025-12-27T09:21:08", "event": "train_log", "step": 3776, "epoch": 1.5932489451476792, "progress_pct": 26.55, "epoch_pct": 26.55, "eta": "41:40:16", "max_grad_norm": 1.0, "loss": 0.7200632095336914, "grad_norm": 0.40960127115249634, "learning_rate": 0.00018060993261566593}
-{"ts": "2025-12-27T09:21:23", "event": "train_log", "step": 3778, "epoch": 1.5940928270042194, "progress_pct": 26.57, "epoch_pct": 26.57, "eta": "41:39:09", "max_grad_norm": 1.0, "loss": 0.7314276695251465, "grad_norm": 0.4215535521507263, "learning_rate": 0.00018058150056244254}
-{"ts": "2025-12-27T09:21:38", "event": "train_log", "step": 3780, "epoch": 1.5949367088607596, "progress_pct": 26.58, "epoch_pct": 26.58, "eta": "41:38:02", "max_grad_norm": 1.0, "loss": 0.7954897284507751, "grad_norm": 0.42734605073928833, "learning_rate": 0.00018055304992061456}
-{"ts": "2025-12-27T09:21:54", "event": "train_log", "step": 3782, "epoch": 1.5957805907172995, "progress_pct": 26.6, "epoch_pct": 26.6, "eta": "41:36:57", "max_grad_norm": 1.0, "loss": 0.6552245020866394, "grad_norm": 0.3980397582054138, "learning_rate": 0.00018052458069674505}
-{"ts": "2025-12-27T09:22:07", "event": "train_log", "step": 3784, "epoch": 1.5966244725738397, "progress_pct": 26.61, "epoch_pct": 26.61, "eta": "41:35:48", "max_grad_norm": 1.0, "loss": 0.7638092041015625, "grad_norm": 0.44602933526039124, "learning_rate": 0.00018049609289740124}
-{"ts": "2025-12-27T09:22:23", "event": "train_log", "step": 3786, "epoch": 1.5974683544303798, "progress_pct": 26.62, "epoch_pct": 26.62, "eta": "41:34:43", "max_grad_norm": 1.0, "loss": 0.6886481046676636, "grad_norm": 0.43835216760635376, "learning_rate": 0.00018046758652915474}
-{"ts": "2025-12-27T09:22:39", "event": "train_log", "step": 3788, "epoch": 1.5983122362869198, "progress_pct": 26.64, "epoch_pct": 26.64, "eta": "41:33:39", "max_grad_norm": 1.0, "loss": 0.6726123690605164, "grad_norm": 0.38229402899742126, "learning_rate": 0.00018043906159858147}
-{"ts": "2025-12-27T09:22:54", "event": "train_log", "step": 3790, "epoch": 1.59915611814346, "progress_pct": 26.65, "epoch_pct": 26.65, "eta": "41:32:32", "max_grad_norm": 1.0, "loss": 0.7416896224021912, "grad_norm": 0.43049392104148865, "learning_rate": 0.00018041051811226155}
-{"ts": "2025-12-27T09:23:10", "event": "train_log", "step": 3792, "epoch": 1.6, "progress_pct": 26.67, "epoch_pct": 26.67, "eta": "41:31:28", "max_grad_norm": 1.0, "loss": 0.682691752910614, "grad_norm": 0.4027816951274872, "learning_rate": 0.00018038195607677943}
-{"ts": "2025-12-27T09:23:25", "event": "train_log", "step": 3794, "epoch": 1.60084388185654, "progress_pct": 26.68, "epoch_pct": 26.68, "eta": "41:30:21", "max_grad_norm": 1.0, "loss": 0.7199558615684509, "grad_norm": 0.4143599569797516, "learning_rate": 0.00018035337549872376}
-{"ts": "2025-12-27T09:23:40", "event": "train_log", "step": 3796, "epoch": 1.6016877637130802, "progress_pct": 26.69, "epoch_pct": 26.69, "eta": "41:29:16", "max_grad_norm": 1.0, "loss": 0.6586267948150635, "grad_norm": 0.41221415996551514, "learning_rate": 0.00018032477638468762}
-{"ts": "2025-12-27T09:23:56", "event": "train_log", "step": 3798, "epoch": 1.6025316455696204, "progress_pct": 26.71, "epoch_pct": 26.71, "eta": "41:28:15", "max_grad_norm": 1.0, "loss": 0.7579189538955688, "grad_norm": 0.40655994415283203, "learning_rate": 0.0001802961587412682}
-{"ts": "2025-12-27T09:24:12", "event": "train_log", "step": 3800, "epoch": 1.6033755274261603, "progress_pct": 26.72, "epoch_pct": 26.72, "eta": "41:27:09", "max_grad_norm": 1.0, "loss": 0.7246071100234985, "grad_norm": 0.4163990914821625, "learning_rate": 0.00018026752257506708}
-{"ts": "2025-12-27T09:35:44", "event": "train_log", "step": 3800, "epoch": 1.6033755274261603, "progress_pct": 26.72, "epoch_pct": 26.72, "eta": "41:58:48", "max_grad_norm": 1.0, "eval_loss": 0.778353214263916, "eval_runtime": 692.5522, "eval_samples_per_second": 3.042, "eval_steps_per_second": 3.042}
-{"ts": "2025-12-27T09:36:01", "event": "train_log", "step": 3802, "epoch": 1.6042194092827005, "progress_pct": 26.74, "epoch_pct": 26.74, "eta": "41:57:47", "max_grad_norm": 1.0, "loss": 0.7114223837852478, "grad_norm": 0.378628671169281, "learning_rate": 0.0001802388678926901}
-{"ts": "2025-12-27T09:36:16", "event": "train_log", "step": 3804, "epoch": 1.6050632911392406, "progress_pct": 26.75, "epoch_pct": 26.75, "eta": "41:56:37", "max_grad_norm": 1.0, "loss": 0.7519527077674866, "grad_norm": 0.5050750374794006, "learning_rate": 0.0001802101947007473}
-{"ts": "2025-12-27T09:36:30", "event": "train_log", "step": 3806, "epoch": 1.6059071729957806, "progress_pct": 26.77, "epoch_pct": 26.77, "eta": "41:55:27", "max_grad_norm": 1.0, "loss": 0.7553771138191223, "grad_norm": 0.5003950595855713, "learning_rate": 0.00018018150300585305}
-{"ts": "2025-12-27T09:36:45", "event": "train_log", "step": 3808, "epoch": 1.6067510548523207, "progress_pct": 26.78, "epoch_pct": 26.78, "eta": "41:54:20", "max_grad_norm": 1.0, "loss": 0.6584326028823853, "grad_norm": 0.3851728141307831, "learning_rate": 0.00018015279281462595}
-{"ts": "2025-12-27T09:37:01", "event": "train_log", "step": 3810, "epoch": 1.6075949367088609, "progress_pct": 26.79, "epoch_pct": 26.79, "eta": "41:53:17", "max_grad_norm": 1.0, "loss": 0.7215287089347839, "grad_norm": 0.41256240010261536, "learning_rate": 0.00018012406413368893}
-{"ts": "2025-12-27T09:37:17", "event": "train_log", "step": 3812, "epoch": 1.6084388185654008, "progress_pct": 26.81, "epoch_pct": 26.81, "eta": "41:52:13", "max_grad_norm": 1.0, "loss": 0.7753872275352478, "grad_norm": 0.41479718685150146, "learning_rate": 0.00018009531696966912}
-{"ts": "2025-12-27T09:37:32", "event": "train_log", "step": 3814, "epoch": 1.6092827004219408, "progress_pct": 26.82, "epoch_pct": 26.82, "eta": "41:51:04", "max_grad_norm": 1.0, "loss": 0.6984832882881165, "grad_norm": 0.398509681224823, "learning_rate": 0.00018006655132919797}
-{"ts": "2025-12-27T09:37:47", "event": "train_log", "step": 3816, "epoch": 1.6101265822784812, "progress_pct": 26.84, "epoch_pct": 26.84, "eta": "41:49:57", "max_grad_norm": 1.0, "loss": 0.8117644786834717, "grad_norm": 0.42210307717323303, "learning_rate": 0.0001800377672189111}
-{"ts": "2025-12-27T09:38:03", "event": "train_log", "step": 3818, "epoch": 1.610970464135021, "progress_pct": 26.85, "epoch_pct": 26.85, "eta": "41:48:54", "max_grad_norm": 1.0, "loss": 0.6302977204322815, "grad_norm": 0.3714556396007538, "learning_rate": 0.0001800089646454485}
-{"ts": "2025-12-27T09:38:18", "event": "train_log", "step": 3820, "epoch": 1.611814345991561, "progress_pct": 26.86, "epoch_pct": 26.86, "eta": "41:47:48", "max_grad_norm": 1.0, "loss": 0.7327325940132141, "grad_norm": 0.4478890299797058, "learning_rate": 0.00017998014361545438}
-{"ts": "2025-12-27T09:38:34", "event": "train_log", "step": 3822, "epoch": 1.6126582278481014, "progress_pct": 26.88, "epoch_pct": 26.88, "eta": "41:46:43", "max_grad_norm": 1.0, "loss": 0.6877713203430176, "grad_norm": 0.43516477942466736, "learning_rate": 0.00017995130413557713}
-{"ts": "2025-12-27T09:38:50", "event": "train_log", "step": 3824, "epoch": 1.6135021097046414, "progress_pct": 26.89, "epoch_pct": 26.89, "eta": "41:45:39", "max_grad_norm": 1.0, "loss": 0.6797093152999878, "grad_norm": 0.42912542819976807, "learning_rate": 0.0001799224462124695}
-{"ts": "2025-12-27T09:39:06", "event": "train_log", "step": 3826, "epoch": 1.6143459915611813, "progress_pct": 26.91, "epoch_pct": 26.91, "eta": "41:44:36", "max_grad_norm": 1.0, "loss": 0.7402470111846924, "grad_norm": 0.40646228194236755, "learning_rate": 0.00017989356985278853}
-{"ts": "2025-12-27T09:39:22", "event": "train_log", "step": 3828, "epoch": 1.6151898734177215, "progress_pct": 26.92, "epoch_pct": 26.92, "eta": "41:43:31", "max_grad_norm": 1.0, "loss": 0.6698583364486694, "grad_norm": 0.42576655745506287, "learning_rate": 0.00017986467506319535}
-{"ts": "2025-12-27T09:39:37", "event": "train_log", "step": 3830, "epoch": 1.6160337552742616, "progress_pct": 26.93, "epoch_pct": 26.93, "eta": "41:42:25", "max_grad_norm": 1.0, "loss": 0.6736086010932922, "grad_norm": 0.4298654794692993, "learning_rate": 0.0001798357618503555}
-{"ts": "2025-12-27T09:39:52", "event": "train_log", "step": 3832, "epoch": 1.6168776371308016, "progress_pct": 26.95, "epoch_pct": 26.95, "eta": "41:41:18", "max_grad_norm": 1.0, "loss": 0.7724249958992004, "grad_norm": 0.4205976128578186, "learning_rate": 0.0001798068302209386}
-{"ts": "2025-12-27T09:40:07", "event": "train_log", "step": 3834, "epoch": 1.6177215189873417, "progress_pct": 26.96, "epoch_pct": 26.96, "eta": "41:40:11", "max_grad_norm": 1.0, "loss": 0.6468521952629089, "grad_norm": 0.39669108390808105, "learning_rate": 0.00017977788018161872}
-{"ts": "2025-12-27T09:40:21", "event": "train_log", "step": 3836, "epoch": 1.618565400843882, "progress_pct": 26.98, "epoch_pct": 26.98, "eta": "41:39:02", "max_grad_norm": 1.0, "loss": 0.7086918950080872, "grad_norm": 0.428551584482193, "learning_rate": 0.00017974891173907405}
-{"ts": "2025-12-27T09:40:36", "event": "train_log", "step": 3838, "epoch": 1.6194092827004218, "progress_pct": 26.99, "epoch_pct": 26.99, "eta": "41:37:56", "max_grad_norm": 1.0, "loss": 0.6483711004257202, "grad_norm": 0.43773409724235535, "learning_rate": 0.00017971992489998703}
-{"ts": "2025-12-27T09:40:52", "event": "train_log", "step": 3840, "epoch": 1.620253164556962, "progress_pct": 27.0, "epoch_pct": 27.0, "eta": "41:36:51", "max_grad_norm": 1.0, "loss": 0.6947301030158997, "grad_norm": 0.40540891885757446, "learning_rate": 0.00017969091967104438}
-{"ts": "2025-12-27T09:41:08", "event": "train_log", "step": 3842, "epoch": 1.6210970464135022, "progress_pct": 27.02, "epoch_pct": 27.02, "eta": "41:35:48", "max_grad_norm": 1.0, "loss": 0.667517900466919, "grad_norm": 0.3685019016265869, "learning_rate": 0.00017966189605893708}
-{"ts": "2025-12-27T09:41:23", "event": "train_log", "step": 3844, "epoch": 1.621940928270042, "progress_pct": 27.03, "epoch_pct": 27.03, "eta": "41:34:41", "max_grad_norm": 1.0, "loss": 0.6957448124885559, "grad_norm": 0.44813284277915955, "learning_rate": 0.0001796328540703603}
-{"ts": "2025-12-27T09:41:38", "event": "train_log", "step": 3846, "epoch": 1.6227848101265823, "progress_pct": 27.05, "epoch_pct": 27.05, "eta": "41:33:34", "max_grad_norm": 1.0, "loss": 0.7735851407051086, "grad_norm": 0.4524349868297577, "learning_rate": 0.00017960379371201345}
-{"ts": "2025-12-27T09:41:54", "event": "train_log", "step": 3848, "epoch": 1.6236286919831224, "progress_pct": 27.06, "epoch_pct": 27.06, "eta": "41:32:31", "max_grad_norm": 1.0, "loss": 0.7052056193351746, "grad_norm": 0.42349138855934143, "learning_rate": 0.0001795747149906002}
-{"ts": "2025-12-27T09:42:08", "event": "train_log", "step": 3850, "epoch": 1.6244725738396624, "progress_pct": 27.07, "epoch_pct": 27.07, "eta": "41:31:23", "max_grad_norm": 1.0, "loss": 0.7402311563491821, "grad_norm": 0.47317537665367126, "learning_rate": 0.0001795456179128285}
-{"ts": "2025-12-27T09:42:23", "event": "train_log", "step": 3852, "epoch": 1.6253164556962025, "progress_pct": 27.09, "epoch_pct": 27.09, "eta": "41:30:18", "max_grad_norm": 1.0, "loss": 0.6743243932723999, "grad_norm": 0.38915711641311646, "learning_rate": 0.0001795165024854104}
-{"ts": "2025-12-27T09:42:38", "event": "train_log", "step": 3854, "epoch": 1.6261603375527427, "progress_pct": 27.1, "epoch_pct": 27.1, "eta": "41:29:11", "max_grad_norm": 1.0, "loss": 0.6983860731124878, "grad_norm": 0.4430672526359558, "learning_rate": 0.00017948736871506235}
-{"ts": "2025-12-27T09:42:53", "event": "train_log", "step": 3856, "epoch": 1.6270042194092826, "progress_pct": 27.12, "epoch_pct": 27.12, "eta": "41:28:04", "max_grad_norm": 1.0, "loss": 0.8012514710426331, "grad_norm": 0.44286689162254333, "learning_rate": 0.00017945821660850494}
-{"ts": "2025-12-27T09:43:07", "event": "train_log", "step": 3858, "epoch": 1.6278481012658228, "progress_pct": 27.13, "epoch_pct": 27.13, "eta": "41:26:57", "max_grad_norm": 1.0, "loss": 0.8064966201782227, "grad_norm": 0.43364086747169495, "learning_rate": 0.00017942904617246295}
-{"ts": "2025-12-27T09:43:22", "event": "train_log", "step": 3860, "epoch": 1.628691983122363, "progress_pct": 27.14, "epoch_pct": 27.14, "eta": "41:25:52", "max_grad_norm": 1.0, "loss": 0.7069969177246094, "grad_norm": 0.45848122239112854, "learning_rate": 0.00017939985741366547}
-{"ts": "2025-12-27T09:43:38", "event": "train_log", "step": 3862, "epoch": 1.629535864978903, "progress_pct": 27.16, "epoch_pct": 27.16, "eta": "41:24:47", "max_grad_norm": 1.0, "loss": 0.6722052097320557, "grad_norm": 0.4199717044830322, "learning_rate": 0.0001793706503388458}
-{"ts": "2025-12-27T09:43:53", "event": "train_log", "step": 3864, "epoch": 1.630379746835443, "progress_pct": 27.17, "epoch_pct": 27.17, "eta": "41:23:42", "max_grad_norm": 1.0, "loss": 0.663442075252533, "grad_norm": 0.3820365071296692, "learning_rate": 0.00017934142495474142}
-{"ts": "2025-12-27T09:44:09", "event": "train_log", "step": 3866, "epoch": 1.6312236286919832, "progress_pct": 27.19, "epoch_pct": 27.19, "eta": "41:22:39", "max_grad_norm": 1.0, "loss": 0.70677250623703, "grad_norm": 0.4470944106578827, "learning_rate": 0.00017931218126809412}
-{"ts": "2025-12-27T09:44:24", "event": "train_log", "step": 3868, "epoch": 1.6320675105485232, "progress_pct": 27.2, "epoch_pct": 27.2, "eta": "41:21:33", "max_grad_norm": 1.0, "loss": 0.7125341892242432, "grad_norm": 0.3941600024700165, "learning_rate": 0.0001792829192856498}
-{"ts": "2025-12-27T09:44:39", "event": "train_log", "step": 3870, "epoch": 1.6329113924050633, "progress_pct": 27.22, "epoch_pct": 27.22, "eta": "41:20:27", "max_grad_norm": 1.0, "loss": 0.7245699763298035, "grad_norm": 0.44924396276474, "learning_rate": 0.00017925363901415863}
-{"ts": "2025-12-27T09:44:54", "event": "train_log", "step": 3872, "epoch": 1.6337552742616035, "progress_pct": 27.23, "epoch_pct": 27.23, "eta": "41:19:23", "max_grad_norm": 1.0, "loss": 0.6977120637893677, "grad_norm": 0.4070027470588684, "learning_rate": 0.00017922434046037508}
-{"ts": "2025-12-27T09:45:09", "event": "train_log", "step": 3874, "epoch": 1.6345991561181434, "progress_pct": 27.24, "epoch_pct": 27.24, "eta": "41:18:16", "max_grad_norm": 1.0, "loss": 0.7631482481956482, "grad_norm": 0.45040908455848694, "learning_rate": 0.00017919502363105772}
-{"ts": "2025-12-27T09:45:25", "event": "train_log", "step": 3876, "epoch": 1.6354430379746834, "progress_pct": 27.26, "epoch_pct": 27.26, "eta": "41:17:13", "max_grad_norm": 1.0, "loss": 0.6656452417373657, "grad_norm": 0.4083724617958069, "learning_rate": 0.00017916568853296934}
-{"ts": "2025-12-27T09:45:42", "event": "train_log", "step": 3878, "epoch": 1.6362869198312238, "progress_pct": 27.27, "epoch_pct": 27.27, "eta": "41:16:13", "max_grad_norm": 1.0, "loss": 0.6302213072776794, "grad_norm": 0.3762308359146118, "learning_rate": 0.00017913633517287704}
-{"ts": "2025-12-27T09:45:57", "event": "train_log", "step": 3880, "epoch": 1.6371308016877637, "progress_pct": 27.29, "epoch_pct": 27.29, "eta": "41:15:10", "max_grad_norm": 1.0, "loss": 0.7119566202163696, "grad_norm": 0.36366912722587585, "learning_rate": 0.00017910696355755205}
-{"ts": "2025-12-27T09:46:12", "event": "train_log", "step": 3882, "epoch": 1.6379746835443036, "progress_pct": 27.3, "epoch_pct": 27.3, "eta": "41:14:04", "max_grad_norm": 1.0, "loss": 0.7271678447723389, "grad_norm": 0.43168532848358154, "learning_rate": 0.00017907757369376985}
-{"ts": "2025-12-27T09:46:27", "event": "train_log", "step": 3884, "epoch": 1.638818565400844, "progress_pct": 27.31, "epoch_pct": 27.31, "eta": "41:12:59", "max_grad_norm": 1.0, "loss": 0.6340095400810242, "grad_norm": 0.37720009684562683, "learning_rate": 0.00017904816558831014}
-{"ts": "2025-12-27T09:46:43", "event": "train_log", "step": 3886, "epoch": 1.639662447257384, "progress_pct": 27.33, "epoch_pct": 27.33, "eta": "41:11:55", "max_grad_norm": 1.0, "loss": 0.6910572052001953, "grad_norm": 0.36539995670318604, "learning_rate": 0.00017901873924795677}
-{"ts": "2025-12-27T09:46:57", "event": "train_log", "step": 3888, "epoch": 1.640506329113924, "progress_pct": 27.34, "epoch_pct": 27.34, "eta": "41:10:48", "max_grad_norm": 1.0, "loss": 0.7570282220840454, "grad_norm": 0.42437905073165894, "learning_rate": 0.00017898929467949782}
-{"ts": "2025-12-27T09:47:11", "event": "train_log", "step": 3890, "epoch": 1.6413502109704643, "progress_pct": 27.36, "epoch_pct": 27.36, "eta": "41:09:41", "max_grad_norm": 1.0, "loss": 0.7835264205932617, "grad_norm": 0.43482181429862976, "learning_rate": 0.00017895983188972558}
-{"ts": "2025-12-27T09:47:26", "event": "train_log", "step": 3892, "epoch": 1.6421940928270042, "progress_pct": 27.37, "epoch_pct": 27.37, "eta": "41:08:36", "max_grad_norm": 1.0, "loss": 0.7058968544006348, "grad_norm": 0.40460237860679626, "learning_rate": 0.00017893035088543662}
-{"ts": "2025-12-27T09:47:42", "event": "train_log", "step": 3894, "epoch": 1.6430379746835442, "progress_pct": 27.38, "epoch_pct": 27.38, "eta": "41:07:34", "max_grad_norm": 1.0, "loss": 0.723969042301178, "grad_norm": 0.39779701828956604, "learning_rate": 0.00017890085167343158}
-{"ts": "2025-12-27T09:47:58", "event": "train_log", "step": 3896, "epoch": 1.6438818565400843, "progress_pct": 27.4, "epoch_pct": 27.4, "eta": "41:06:30", "max_grad_norm": 1.0, "loss": 0.7773922681808472, "grad_norm": 0.46131494641304016, "learning_rate": 0.00017887133426051536}
-{"ts": "2025-12-27T09:48:12", "event": "train_log", "step": 3898, "epoch": 1.6447257383966245, "progress_pct": 27.41, "epoch_pct": 27.41, "eta": "41:05:23", "max_grad_norm": 1.0, "loss": 0.7742162942886353, "grad_norm": 0.48412877321243286, "learning_rate": 0.0001788417986534971}
-{"ts": "2025-12-27T09:48:27", "event": "train_log", "step": 3900, "epoch": 1.6455696202531644, "progress_pct": 27.43, "epoch_pct": 27.43, "eta": "41:04:18", "max_grad_norm": 1.0, "loss": 0.6674869656562805, "grad_norm": 0.40083935856819153, "learning_rate": 0.00017881224485919006}
-{"ts": "2025-12-27T09:59:49", "event": "train_log", "step": 3900, "epoch": 1.6455696202531644, "progress_pct": 27.43, "epoch_pct": 27.43, "eta": "41:34:23", "max_grad_norm": 1.0, "eval_loss": 0.7763351202011108, "eval_runtime": 682.0824, "eval_samples_per_second": 3.089, "eval_steps_per_second": 3.089}
-{"ts": "2025-12-27T10:00:05", "event": "train_log", "step": 3902, "epoch": 1.6464135021097046, "progress_pct": 27.44, "epoch_pct": 27.44, "eta": "41:33:19", "max_grad_norm": 1.0, "loss": 0.6777821183204651, "grad_norm": 0.3944476842880249, "learning_rate": 0.00017878267288441176}
-{"ts": "2025-12-27T10:00:21", "event": "train_log", "step": 3904, "epoch": 1.6472573839662448, "progress_pct": 27.45, "epoch_pct": 27.45, "eta": "41:32:15", "max_grad_norm": 1.0, "loss": 0.7398322224617004, "grad_norm": 0.44863224029541016, "learning_rate": 0.0001787530827359839}
-{"ts": "2025-12-27T10:00:36", "event": "train_log", "step": 3906, "epoch": 1.6481012658227847, "progress_pct": 27.47, "epoch_pct": 27.47, "eta": "41:31:10", "max_grad_norm": 1.0, "loss": 0.7203068733215332, "grad_norm": 0.4665529131889343, "learning_rate": 0.00017872347442073232}
-{"ts": "2025-12-27T10:00:52", "event": "train_log", "step": 3908, "epoch": 1.6489451476793249, "progress_pct": 27.48, "epoch_pct": 27.48, "eta": "41:30:07", "max_grad_norm": 1.0, "loss": 0.6232115030288696, "grad_norm": 0.3603050410747528, "learning_rate": 0.00017869384794548708}
-{"ts": "2025-12-27T10:01:08", "event": "train_log", "step": 3910, "epoch": 1.649789029535865, "progress_pct": 27.5, "epoch_pct": 27.5, "eta": "41:29:04", "max_grad_norm": 1.0, "loss": 0.6120040416717529, "grad_norm": 0.3545325696468353, "learning_rate": 0.0001786642033170825}
-{"ts": "2025-12-27T10:01:23", "event": "train_log", "step": 3912, "epoch": 1.650632911392405, "progress_pct": 27.51, "epoch_pct": 27.51, "eta": "41:27:58", "max_grad_norm": 1.0, "loss": 0.7285997867584229, "grad_norm": 0.3947487473487854, "learning_rate": 0.00017863454054235697}
-{"ts": "2025-12-27T10:01:41", "event": "train_log", "step": 3914, "epoch": 1.6514767932489451, "progress_pct": 27.52, "epoch_pct": 27.52, "eta": "41:27:01", "max_grad_norm": 1.0, "loss": 0.6486109495162964, "grad_norm": 0.33153054118156433, "learning_rate": 0.00017860485962815312}
-{"ts": "2025-12-27T10:01:57", "event": "train_log", "step": 3916, "epoch": 1.6523206751054853, "progress_pct": 27.54, "epoch_pct": 27.54, "eta": "41:25:56", "max_grad_norm": 1.0, "loss": 0.6870376467704773, "grad_norm": 0.3886185884475708, "learning_rate": 0.00017857516058131782}
-{"ts": "2025-12-27T10:02:12", "event": "train_log", "step": 3918, "epoch": 1.6531645569620252, "progress_pct": 27.55, "epoch_pct": 27.55, "eta": "41:24:52", "max_grad_norm": 1.0, "loss": 0.7351298928260803, "grad_norm": 0.46399059891700745, "learning_rate": 0.00017854544340870201}
-{"ts": "2025-12-27T10:02:27", "event": "train_log", "step": 3920, "epoch": 1.6540084388185654, "progress_pct": 27.57, "epoch_pct": 27.57, "eta": "41:23:47", "max_grad_norm": 1.0, "loss": 0.7283915281295776, "grad_norm": 0.49280229210853577, "learning_rate": 0.00017851570811716093}
-{"ts": "2025-12-27T10:02:42", "event": "train_log", "step": 3922, "epoch": 1.6548523206751056, "progress_pct": 27.58, "epoch_pct": 27.58, "eta": "41:22:41", "max_grad_norm": 1.0, "loss": 0.7436906099319458, "grad_norm": 0.41570642590522766, "learning_rate": 0.00017848595471355388}
-{"ts": "2025-12-27T10:02:57", "event": "train_log", "step": 3924, "epoch": 1.6556962025316455, "progress_pct": 27.59, "epoch_pct": 27.59, "eta": "41:21:35", "max_grad_norm": 1.0, "loss": 0.7427505254745483, "grad_norm": 0.44591766595840454, "learning_rate": 0.00017845618320474444}
-{"ts": "2025-12-27T10:03:13", "event": "train_log", "step": 3926, "epoch": 1.6565400843881857, "progress_pct": 27.61, "epoch_pct": 27.61, "eta": "41:20:32", "max_grad_norm": 1.0, "loss": 0.7642725706100464, "grad_norm": 0.4804318845272064, "learning_rate": 0.00017842639359760032}
-{"ts": "2025-12-27T10:03:29", "event": "train_log", "step": 3928, "epoch": 1.6573839662447258, "progress_pct": 27.62, "epoch_pct": 27.62, "eta": "41:19:29", "max_grad_norm": 1.0, "loss": 0.7097790837287903, "grad_norm": 0.4164349138736725, "learning_rate": 0.00017839658589899343}
-{"ts": "2025-12-27T10:03:43", "event": "train_log", "step": 3930, "epoch": 1.6582278481012658, "progress_pct": 27.64, "epoch_pct": 27.64, "eta": "41:18:22", "max_grad_norm": 1.0, "loss": 0.8346033096313477, "grad_norm": 0.5307883620262146, "learning_rate": 0.00017836676011579976}
-{"ts": "2025-12-27T10:03:59", "event": "train_log", "step": 3932, "epoch": 1.659071729957806, "progress_pct": 27.65, "epoch_pct": 27.65, "eta": "41:17:20", "max_grad_norm": 1.0, "loss": 0.6327160596847534, "grad_norm": 0.37231504917144775, "learning_rate": 0.0001783369162548996}
-{"ts": "2025-12-27T10:04:14", "event": "train_log", "step": 3934, "epoch": 1.659915611814346, "progress_pct": 27.67, "epoch_pct": 27.67, "eta": "41:16:14", "max_grad_norm": 1.0, "loss": 0.6441237330436707, "grad_norm": 0.4178757965564728, "learning_rate": 0.00017830705432317738}
-{"ts": "2025-12-27T10:04:30", "event": "train_log", "step": 3936, "epoch": 1.660759493670886, "progress_pct": 27.68, "epoch_pct": 27.68, "eta": "41:15:12", "max_grad_norm": 1.0, "loss": 0.7267951369285583, "grad_norm": 0.42698073387145996, "learning_rate": 0.00017827717432752162}
-{"ts": "2025-12-27T10:04:46", "event": "train_log", "step": 3938, "epoch": 1.6616033755274262, "progress_pct": 27.69, "epoch_pct": 27.69, "eta": "41:14:09", "max_grad_norm": 1.0, "loss": 0.7248380780220032, "grad_norm": 0.48763108253479004, "learning_rate": 0.0001782472762748251}
-{"ts": "2025-12-27T10:05:03", "event": "train_log", "step": 3940, "epoch": 1.6624472573839664, "progress_pct": 27.71, "epoch_pct": 27.71, "eta": "41:13:07", "max_grad_norm": 1.0, "loss": 0.6665275692939758, "grad_norm": 0.38882505893707275, "learning_rate": 0.0001782173601719847}
-{"ts": "2025-12-27T10:05:18", "event": "train_log", "step": 3942, "epoch": 1.6632911392405063, "progress_pct": 27.72, "epoch_pct": 27.72, "eta": "41:12:03", "max_grad_norm": 1.0, "loss": 0.8017846941947937, "grad_norm": 0.4684160649776459, "learning_rate": 0.0001781874260259015}
-{"ts": "2025-12-27T10:05:33", "event": "train_log", "step": 3944, "epoch": 1.6641350210970463, "progress_pct": 27.74, "epoch_pct": 27.74, "eta": "41:10:59", "max_grad_norm": 1.0, "loss": 0.6810902953147888, "grad_norm": 0.4200204908847809, "learning_rate": 0.00017815747384348075}
-{"ts": "2025-12-27T10:05:48", "event": "train_log", "step": 3946, "epoch": 1.6649789029535866, "progress_pct": 27.75, "epoch_pct": 27.75, "eta": "41:09:55", "max_grad_norm": 1.0, "loss": 0.714082658290863, "grad_norm": 0.45843279361724854, "learning_rate": 0.0001781275036316318}
-{"ts": "2025-12-27T10:06:03", "event": "train_log", "step": 3948, "epoch": 1.6658227848101266, "progress_pct": 27.76, "epoch_pct": 27.76, "eta": "41:08:50", "max_grad_norm": 1.0, "loss": 0.842085599899292, "grad_norm": 0.522654116153717, "learning_rate": 0.00017809751539726824}
-{"ts": "2025-12-27T10:06:19", "event": "train_log", "step": 3950, "epoch": 1.6666666666666665, "progress_pct": 27.78, "epoch_pct": 27.78, "eta": "41:07:46", "max_grad_norm": 1.0, "loss": 0.6917972564697266, "grad_norm": 0.43468809127807617, "learning_rate": 0.00017806750914730777}
-{"ts": "2025-12-27T10:06:35", "event": "train_log", "step": 3952, "epoch": 1.667510548523207, "progress_pct": 27.79, "epoch_pct": 27.79, "eta": "41:06:43", "max_grad_norm": 1.0, "loss": 0.6676424741744995, "grad_norm": 0.4071558117866516, "learning_rate": 0.00017803748488867224}
-{"ts": "2025-12-27T10:06:51", "event": "train_log", "step": 3954, "epoch": 1.6683544303797468, "progress_pct": 27.81, "epoch_pct": 27.81, "eta": "41:05:42", "max_grad_norm": 1.0, "loss": 0.7563748359680176, "grad_norm": 0.4478702247142792, "learning_rate": 0.00017800744262828772}
-{"ts": "2025-12-27T10:07:07", "event": "train_log", "step": 3956, "epoch": 1.6691983122362868, "progress_pct": 27.82, "epoch_pct": 27.82, "eta": "41:04:39", "max_grad_norm": 1.0, "loss": 0.685714066028595, "grad_norm": 0.42986053228378296, "learning_rate": 0.00017797738237308432}
-{"ts": "2025-12-27T10:07:23", "event": "train_log", "step": 3958, "epoch": 1.6700421940928272, "progress_pct": 27.83, "epoch_pct": 27.83, "eta": "41:03:37", "max_grad_norm": 1.0, "loss": 0.7753605842590332, "grad_norm": 0.4410569667816162, "learning_rate": 0.0001779473041299964}
-{"ts": "2025-12-27T10:07:37", "event": "train_log", "step": 3960, "epoch": 1.6708860759493671, "progress_pct": 27.85, "epoch_pct": 27.85, "eta": "41:02:32", "max_grad_norm": 1.0, "loss": 0.7826018333435059, "grad_norm": 0.44055965542793274, "learning_rate": 0.00017791720790596242}
-{"ts": "2025-12-27T10:07:53", "event": "train_log", "step": 3962, "epoch": 1.671729957805907, "progress_pct": 27.86, "epoch_pct": 27.86, "eta": "41:01:29", "max_grad_norm": 1.0, "loss": 0.7012629508972168, "grad_norm": 0.4660222828388214, "learning_rate": 0.00017788709370792502}
-{"ts": "2025-12-27T10:08:10", "event": "train_log", "step": 3964, "epoch": 1.6725738396624472, "progress_pct": 27.88, "epoch_pct": 27.88, "eta": "41:00:30", "max_grad_norm": 1.0, "loss": 0.6647007465362549, "grad_norm": 0.3655732274055481, "learning_rate": 0.00017785696154283093}
-{"ts": "2025-12-27T10:08:26", "event": "train_log", "step": 3966, "epoch": 1.6734177215189874, "progress_pct": 27.89, "epoch_pct": 27.89, "eta": "40:59:27", "max_grad_norm": 1.0, "loss": 0.7238346338272095, "grad_norm": 0.45735979080200195, "learning_rate": 0.0001778268114176311}
-{"ts": "2025-12-27T10:08:42", "event": "train_log", "step": 3968, "epoch": 1.6742616033755273, "progress_pct": 27.9, "epoch_pct": 27.9, "eta": "40:58:25", "max_grad_norm": 1.0, "loss": 0.7595300078392029, "grad_norm": 0.4894043207168579, "learning_rate": 0.00017779664333928053}
-{"ts": "2025-12-27T10:09:00", "event": "train_log", "step": 3970, "epoch": 1.6751054852320675, "progress_pct": 27.92, "epoch_pct": 27.92, "eta": "40:57:28", "max_grad_norm": 1.0, "loss": 0.6534504294395447, "grad_norm": 0.3613647222518921, "learning_rate": 0.00017776645731473848}
-{"ts": "2025-12-27T10:09:15", "event": "train_log", "step": 3972, "epoch": 1.6759493670886076, "progress_pct": 27.93, "epoch_pct": 27.93, "eta": "40:56:24", "max_grad_norm": 1.0, "loss": 0.7699148058891296, "grad_norm": 0.4402320683002472, "learning_rate": 0.00017773625335096828}
-{"ts": "2025-12-27T10:09:31", "event": "train_log", "step": 3974, "epoch": 1.6767932489451476, "progress_pct": 27.95, "epoch_pct": 27.95, "eta": "40:55:24", "max_grad_norm": 1.0, "loss": 0.771800696849823, "grad_norm": 0.4391469955444336, "learning_rate": 0.0001777060314549374}
-{"ts": "2025-12-27T10:09:47", "event": "train_log", "step": 3976, "epoch": 1.6776371308016877, "progress_pct": 27.96, "epoch_pct": 27.96, "eta": "40:54:22", "max_grad_norm": 1.0, "loss": 0.6957393884658813, "grad_norm": 0.41348180174827576, "learning_rate": 0.00017767579163361735}
-{"ts": "2025-12-27T10:10:03", "event": "train_log", "step": 3978, "epoch": 1.678481012658228, "progress_pct": 27.97, "epoch_pct": 27.97, "eta": "40:53:21", "max_grad_norm": 1.0, "loss": 0.6666664481163025, "grad_norm": 0.4115046560764313, "learning_rate": 0.00017764553389398407}
-{"ts": "2025-12-27T10:10:18", "event": "train_log", "step": 3980, "epoch": 1.6793248945147679, "progress_pct": 27.99, "epoch_pct": 27.99, "eta": "40:52:16", "max_grad_norm": 1.0, "loss": 0.7364352345466614, "grad_norm": 0.44647306203842163, "learning_rate": 0.00017761525824301725}
-{"ts": "2025-12-27T10:10:33", "event": "train_log", "step": 3982, "epoch": 1.680168776371308, "progress_pct": 28.0, "epoch_pct": 28.0, "eta": "40:51:12", "max_grad_norm": 1.0, "loss": 0.7229774594306946, "grad_norm": 0.424234002828598, "learning_rate": 0.00017758496468770103}
-{"ts": "2025-12-27T10:10:48", "event": "train_log", "step": 3984, "epoch": 1.6810126582278482, "progress_pct": 28.02, "epoch_pct": 28.02, "eta": "40:50:07", "max_grad_norm": 1.0, "loss": 0.6992678642272949, "grad_norm": 0.4850127696990967, "learning_rate": 0.00017755465323502346}
-{"ts": "2025-12-27T10:11:02", "event": "train_log", "step": 3986, "epoch": 1.6818565400843881, "progress_pct": 28.03, "epoch_pct": 28.03, "eta": "40:49:01", "max_grad_norm": 1.0, "loss": 0.6957634091377258, "grad_norm": 0.44637173414230347, "learning_rate": 0.00017752432389197688}
-{"ts": "2025-12-27T10:11:16", "event": "train_log", "step": 3988, "epoch": 1.6827004219409283, "progress_pct": 28.05, "epoch_pct": 28.05, "eta": "40:47:55", "max_grad_norm": 1.0, "loss": 0.6842859983444214, "grad_norm": 0.477393239736557, "learning_rate": 0.00017749397666555768}
-{"ts": "2025-12-27T10:11:32", "event": "train_log", "step": 3990, "epoch": 1.6835443037974684, "progress_pct": 28.06, "epoch_pct": 28.06, "eta": "40:46:54", "max_grad_norm": 1.0, "loss": 0.6478199362754822, "grad_norm": 0.3634146451950073, "learning_rate": 0.00017746361156276632}
-{"ts": "2025-12-27T10:11:47", "event": "train_log", "step": 3992, "epoch": 1.6843881856540084, "progress_pct": 28.07, "epoch_pct": 28.07, "eta": "40:45:50", "max_grad_norm": 1.0, "loss": 0.7166973352432251, "grad_norm": 0.4806389808654785, "learning_rate": 0.00017743322859060752}
-{"ts": "2025-12-27T10:12:02", "event": "train_log", "step": 3994, "epoch": 1.6852320675105485, "progress_pct": 28.09, "epoch_pct": 28.09, "eta": "40:44:47", "max_grad_norm": 1.0, "loss": 0.6624643206596375, "grad_norm": 0.4273380935192108, "learning_rate": 0.00017740282775609}
-{"ts": "2025-12-27T10:12:18", "event": "train_log", "step": 3996, "epoch": 1.6860759493670887, "progress_pct": 28.1, "epoch_pct": 28.1, "eta": "40:43:44", "max_grad_norm": 1.0, "loss": 0.6408489346504211, "grad_norm": 0.4340716600418091, "learning_rate": 0.0001773724090662267}
-{"ts": "2025-12-27T10:12:32", "event": "train_log", "step": 3998, "epoch": 1.6869198312236287, "progress_pct": 28.12, "epoch_pct": 28.12, "eta": "40:42:38", "max_grad_norm": 1.0, "loss": 0.8096797466278076, "grad_norm": 0.50480717420578, "learning_rate": 0.00017734197252803458}
-{"ts": "2025-12-27T10:12:46", "event": "train_log", "step": 4000, "epoch": 1.6877637130801688, "progress_pct": 28.13, "epoch_pct": 28.13, "eta": "40:41:34", "max_grad_norm": 1.0, "loss": 0.6902434825897217, "grad_norm": 0.4549327790737152, "learning_rate": 0.00017731151814853475}
-{"ts": "2025-12-27T10:23:55", "event": "train_log", "step": 4000, "epoch": 1.6877637130801688, "progress_pct": 28.13, "epoch_pct": 28.13, "eta": "41:10:01", "max_grad_norm": 1.0, "eval_loss": 0.7721371650695801, "eval_runtime": 668.395, "eval_samples_per_second": 3.152, "eval_steps_per_second": 3.152}
-{"ts": "2025-12-27T10:24:12", "event": "train_log", "step": 4002, "epoch": 1.688607594936709, "progress_pct": 28.14, "epoch_pct": 28.14, "eta": "41:09:02", "max_grad_norm": 1.0, "loss": 0.6510542035102844, "grad_norm": 0.38909077644348145, "learning_rate": 0.00017728104593475247}
-{"ts": "2025-12-27T10:24:27", "event": "train_log", "step": 4004, "epoch": 1.689451476793249, "progress_pct": 28.16, "epoch_pct": 28.16, "eta": "41:07:56", "max_grad_norm": 1.0, "loss": 0.7331066727638245, "grad_norm": 0.444608598947525, "learning_rate": 0.00017725055589371715}
-{"ts": "2025-12-27T10:24:43", "event": "train_log", "step": 4006, "epoch": 1.690295358649789, "progress_pct": 28.17, "epoch_pct": 28.17, "eta": "41:06:54", "max_grad_norm": 1.0, "loss": 0.5950609445571899, "grad_norm": 0.3364178538322449, "learning_rate": 0.0001772200480324622}
-{"ts": "2025-12-27T10:24:59", "event": "train_log", "step": 4008, "epoch": 1.6911392405063292, "progress_pct": 28.19, "epoch_pct": 28.19, "eta": "41:05:54", "max_grad_norm": 1.0, "loss": 0.7024590969085693, "grad_norm": 0.37264227867126465, "learning_rate": 0.0001771895223580252}
-{"ts": "2025-12-27T10:25:17", "event": "train_log", "step": 4010, "epoch": 1.6919831223628692, "progress_pct": 28.2, "epoch_pct": 28.2, "eta": "41:04:56", "max_grad_norm": 1.0, "loss": 0.6620895266532898, "grad_norm": 0.3576899766921997, "learning_rate": 0.00017715897887744784}
-{"ts": "2025-12-27T10:25:33", "event": "train_log", "step": 4012, "epoch": 1.6928270042194091, "progress_pct": 28.21, "epoch_pct": 28.21, "eta": "41:03:53", "max_grad_norm": 1.0, "loss": 0.6726759076118469, "grad_norm": 0.45855066180229187, "learning_rate": 0.00017712841759777591}
-{"ts": "2025-12-27T10:25:49", "event": "train_log", "step": 4014, "epoch": 1.6936708860759495, "progress_pct": 28.23, "epoch_pct": 28.23, "eta": "41:02:52", "max_grad_norm": 1.0, "loss": 0.6550953984260559, "grad_norm": 0.44610634446144104, "learning_rate": 0.00017709783852605933}
-{"ts": "2025-12-27T10:26:05", "event": "train_log", "step": 4016, "epoch": 1.6945147679324895, "progress_pct": 28.24, "epoch_pct": 28.24, "eta": "41:01:51", "max_grad_norm": 1.0, "loss": 0.7338476777076721, "grad_norm": 0.4262036681175232, "learning_rate": 0.00017706724166935208}
-{"ts": "2025-12-27T10:26:20", "event": "train_log", "step": 4018, "epoch": 1.6953586497890294, "progress_pct": 28.26, "epoch_pct": 28.26, "eta": "41:00:47", "max_grad_norm": 1.0, "loss": 0.6785868406295776, "grad_norm": 0.44584009051322937, "learning_rate": 0.0001770366270347123}
-{"ts": "2025-12-27T10:26:37", "event": "train_log", "step": 4020, "epoch": 1.6962025316455698, "progress_pct": 28.27, "epoch_pct": 28.27, "eta": "40:59:46", "max_grad_norm": 1.0, "loss": 0.7113003134727478, "grad_norm": 0.44828134775161743, "learning_rate": 0.0001770059946292022}
-{"ts": "2025-12-27T10:26:52", "event": "train_log", "step": 4022, "epoch": 1.6970464135021097, "progress_pct": 28.28, "epoch_pct": 28.28, "eta": "40:58:43", "max_grad_norm": 1.0, "loss": 0.6420866847038269, "grad_norm": 0.39716270565986633, "learning_rate": 0.00017697534445988803}
-{"ts": "2025-12-27T10:27:08", "event": "train_log", "step": 4024, "epoch": 1.6978902953586497, "progress_pct": 28.3, "epoch_pct": 28.3, "eta": "40:57:40", "max_grad_norm": 1.0, "loss": 0.8087385892868042, "grad_norm": 0.43546608090400696, "learning_rate": 0.00017694467653384024}
-{"ts": "2025-12-27T10:27:24", "event": "train_log", "step": 4026, "epoch": 1.6987341772151898, "progress_pct": 28.31, "epoch_pct": 28.31, "eta": "40:56:39", "max_grad_norm": 1.0, "loss": 0.6378461718559265, "grad_norm": 0.3698647618293762, "learning_rate": 0.00017691399085813334}
-{"ts": "2025-12-27T10:27:40", "event": "train_log", "step": 4028, "epoch": 1.69957805907173, "progress_pct": 28.33, "epoch_pct": 28.33, "eta": "40:55:37", "max_grad_norm": 1.0, "loss": 0.6504215002059937, "grad_norm": 0.4256688058376312, "learning_rate": 0.0001768832874398459}
-{"ts": "2025-12-27T10:27:55", "event": "train_log", "step": 4030, "epoch": 1.70042194092827, "progress_pct": 28.34, "epoch_pct": 28.34, "eta": "40:54:35", "max_grad_norm": 1.0, "loss": 0.6648795008659363, "grad_norm": 0.4014805555343628, "learning_rate": 0.00017685256628606063}
-{"ts": "2025-12-27T10:28:10", "event": "train_log", "step": 4032, "epoch": 1.70126582278481, "progress_pct": 28.35, "epoch_pct": 28.35, "eta": "40:53:31", "max_grad_norm": 1.0, "loss": 0.6905859112739563, "grad_norm": 0.43924233317375183, "learning_rate": 0.00017682182740386427}
-{"ts": "2025-12-27T10:28:27", "event": "train_log", "step": 4034, "epoch": 1.7021097046413503, "progress_pct": 28.37, "epoch_pct": 28.37, "eta": "40:52:31", "max_grad_norm": 1.0, "loss": 0.7800544500350952, "grad_norm": 0.43565094470977783, "learning_rate": 0.00017679107080034774}
-{"ts": "2025-12-27T10:28:42", "event": "train_log", "step": 4036, "epoch": 1.7029535864978902, "progress_pct": 28.38, "epoch_pct": 28.38, "eta": "40:51:27", "max_grad_norm": 1.0, "loss": 0.7487648725509644, "grad_norm": 0.4681089520454407, "learning_rate": 0.00017676029648260597}
-{"ts": "2025-12-27T10:28:59", "event": "train_log", "step": 4038, "epoch": 1.7037974683544304, "progress_pct": 28.4, "epoch_pct": 28.4, "eta": "40:50:28", "max_grad_norm": 1.0, "loss": 0.7374032735824585, "grad_norm": 0.41400185227394104, "learning_rate": 0.00017672950445773804}
-{"ts": "2025-12-27T10:29:14", "event": "train_log", "step": 4040, "epoch": 1.7046413502109705, "progress_pct": 28.41, "epoch_pct": 28.41, "eta": "40:49:25", "max_grad_norm": 1.0, "loss": 0.7539847493171692, "grad_norm": 0.5120159983634949, "learning_rate": 0.00017669869473284702}
-{"ts": "2025-12-27T10:29:30", "event": "train_log", "step": 4042, "epoch": 1.7054852320675105, "progress_pct": 28.42, "epoch_pct": 28.42, "eta": "40:48:24", "max_grad_norm": 1.0, "loss": 0.7029932737350464, "grad_norm": 0.4043315052986145, "learning_rate": 0.00017666786731504013}
-{"ts": "2025-12-27T10:29:47", "event": "train_log", "step": 4044, "epoch": 1.7063291139240506, "progress_pct": 28.44, "epoch_pct": 28.44, "eta": "40:47:23", "max_grad_norm": 1.0, "loss": 0.6464276313781738, "grad_norm": 0.462801992893219, "learning_rate": 0.00017663702221142874}
-{"ts": "2025-12-27T10:30:01", "event": "train_log", "step": 4046, "epoch": 1.7071729957805908, "progress_pct": 28.45, "epoch_pct": 28.45, "eta": "40:46:19", "max_grad_norm": 1.0, "loss": 0.7646113634109497, "grad_norm": 0.4751932621002197, "learning_rate": 0.00017660615942912813}
-{"ts": "2025-12-27T10:30:16", "event": "train_log", "step": 4048, "epoch": 1.7080168776371307, "progress_pct": 28.47, "epoch_pct": 28.47, "eta": "40:45:14", "max_grad_norm": 1.0, "loss": 0.7191748023033142, "grad_norm": 0.41720855236053467, "learning_rate": 0.0001765752789752578}
-{"ts": "2025-12-27T10:30:31", "event": "train_log", "step": 4050, "epoch": 1.7088607594936709, "progress_pct": 28.48, "epoch_pct": 28.48, "eta": "40:44:11", "max_grad_norm": 1.0, "loss": 0.6946488618850708, "grad_norm": 0.40235280990600586, "learning_rate": 0.00017654438085694128}
-{"ts": "2025-12-27T10:30:46", "event": "train_log", "step": 4052, "epoch": 1.709704641350211, "progress_pct": 28.5, "epoch_pct": 28.5, "eta": "40:43:06", "max_grad_norm": 1.0, "loss": 0.7655195593833923, "grad_norm": 0.4385916292667389, "learning_rate": 0.00017651346508130612}
-{"ts": "2025-12-27T10:31:01", "event": "train_log", "step": 4054, "epoch": 1.710548523206751, "progress_pct": 28.51, "epoch_pct": 28.51, "eta": "40:42:04", "max_grad_norm": 1.0, "loss": 0.7192418575286865, "grad_norm": 0.4192262887954712, "learning_rate": 0.00017648253165548406}
-{"ts": "2025-12-27T10:31:17", "event": "train_log", "step": 4056, "epoch": 1.7113924050632912, "progress_pct": 28.52, "epoch_pct": 28.52, "eta": "40:41:03", "max_grad_norm": 1.0, "loss": 0.6501081585884094, "grad_norm": 0.4348951280117035, "learning_rate": 0.00017645158058661082}
-{"ts": "2025-12-27T10:31:34", "event": "train_log", "step": 4058, "epoch": 1.7122362869198313, "progress_pct": 28.54, "epoch_pct": 28.54, "eta": "40:40:04", "max_grad_norm": 1.0, "loss": 0.741439163684845, "grad_norm": 0.4178772270679474, "learning_rate": 0.0001764206118818262}
-{"ts": "2025-12-27T10:31:49", "event": "train_log", "step": 4060, "epoch": 1.7130801687763713, "progress_pct": 28.55, "epoch_pct": 28.55, "eta": "40:39:01", "max_grad_norm": 1.0, "loss": 0.7087798714637756, "grad_norm": 0.46996670961380005, "learning_rate": 0.00017638962554827414}
-{"ts": "2025-12-27T10:32:05", "event": "train_log", "step": 4062, "epoch": 1.7139240506329114, "progress_pct": 28.57, "epoch_pct": 28.57, "eta": "40:38:00", "max_grad_norm": 1.0, "loss": 0.6716644167900085, "grad_norm": 0.4775761365890503, "learning_rate": 0.00017635862159310253}
-{"ts": "2025-12-27T10:32:21", "event": "train_log", "step": 4064, "epoch": 1.7147679324894516, "progress_pct": 28.58, "epoch_pct": 28.58, "eta": "40:36:58", "max_grad_norm": 1.0, "loss": 0.6630500555038452, "grad_norm": 0.4094069004058838, "learning_rate": 0.00017632760002346345}
-{"ts": "2025-12-27T10:32:36", "event": "train_log", "step": 4066, "epoch": 1.7156118143459915, "progress_pct": 28.59, "epoch_pct": 28.59, "eta": "40:35:56", "max_grad_norm": 1.0, "loss": 0.7678145170211792, "grad_norm": 0.3968847393989563, "learning_rate": 0.0001762965608465129}
-{"ts": "2025-12-27T10:32:52", "event": "train_log", "step": 4068, "epoch": 1.7164556962025317, "progress_pct": 28.61, "epoch_pct": 28.61, "eta": "40:34:54", "max_grad_norm": 1.0, "loss": 0.6981875896453857, "grad_norm": 0.43751946091651917, "learning_rate": 0.0001762655040694111}
-{"ts": "2025-12-27T10:33:06", "event": "train_log", "step": 4070, "epoch": 1.7172995780590719, "progress_pct": 28.62, "epoch_pct": 28.62, "eta": "40:33:50", "max_grad_norm": 1.0, "loss": 0.6919799447059631, "grad_norm": 0.44504284858703613, "learning_rate": 0.00017623442969932218}
-{"ts": "2025-12-27T10:33:23", "event": "train_log", "step": 4072, "epoch": 1.7181434599156118, "progress_pct": 28.64, "epoch_pct": 28.64, "eta": "40:32:52", "max_grad_norm": 1.0, "loss": 0.6310772895812988, "grad_norm": 0.36895114183425903, "learning_rate": 0.00017620333774341447}
-{"ts": "2025-12-27T10:33:38", "event": "train_log", "step": 4074, "epoch": 1.7189873417721517, "progress_pct": 28.65, "epoch_pct": 28.65, "eta": "40:31:49", "max_grad_norm": 1.0, "loss": 0.6954092383384705, "grad_norm": 0.4312762916088104, "learning_rate": 0.00017617222820886022}
-{"ts": "2025-12-27T10:33:54", "event": "train_log", "step": 4076, "epoch": 1.7198312236286921, "progress_pct": 28.66, "epoch_pct": 28.66, "eta": "40:30:48", "max_grad_norm": 1.0, "loss": 0.6973698139190674, "grad_norm": 0.40909886360168457, "learning_rate": 0.00017614110110283587}
-{"ts": "2025-12-27T10:34:10", "event": "train_log", "step": 4078, "epoch": 1.720675105485232, "progress_pct": 28.68, "epoch_pct": 28.68, "eta": "40:29:46", "max_grad_norm": 1.0, "loss": 0.6775513291358948, "grad_norm": 0.43111470341682434, "learning_rate": 0.0001761099564325218}
-{"ts": "2025-12-27T10:34:25", "event": "train_log", "step": 4080, "epoch": 1.721518987341772, "progress_pct": 28.69, "epoch_pct": 28.69, "eta": "40:28:45", "max_grad_norm": 1.0, "loss": 0.6889033913612366, "grad_norm": 0.45573189854621887, "learning_rate": 0.0001760787942051025}
-{"ts": "2025-12-27T10:34:40", "event": "train_log", "step": 4082, "epoch": 1.7223628691983124, "progress_pct": 28.71, "epoch_pct": 28.71, "eta": "40:27:41", "max_grad_norm": 1.0, "loss": 0.6894892454147339, "grad_norm": 0.44934743642807007, "learning_rate": 0.0001760476144277665}
-{"ts": "2025-12-27T10:34:57", "event": "train_log", "step": 4084, "epoch": 1.7232067510548523, "progress_pct": 28.72, "epoch_pct": 28.72, "eta": "40:26:43", "max_grad_norm": 1.0, "loss": 0.6841691732406616, "grad_norm": 0.39716506004333496, "learning_rate": 0.0001760164171077064}
-{"ts": "2025-12-27T10:35:12", "event": "train_log", "step": 4086, "epoch": 1.7240506329113923, "progress_pct": 28.73, "epoch_pct": 28.73, "eta": "40:25:40", "max_grad_norm": 1.0, "loss": 0.7197495102882385, "grad_norm": 0.4486255645751953, "learning_rate": 0.00017598520225211876}
-{"ts": "2025-12-27T10:35:28", "event": "train_log", "step": 4088, "epoch": 1.7248945147679327, "progress_pct": 28.75, "epoch_pct": 28.75, "eta": "40:24:41", "max_grad_norm": 1.0, "loss": 0.7388272881507874, "grad_norm": 0.40130025148391724, "learning_rate": 0.00017595396986820432}
-{"ts": "2025-12-27T10:35:43", "event": "train_log", "step": 4090, "epoch": 1.7257383966244726, "progress_pct": 28.76, "epoch_pct": 28.76, "eta": "40:23:38", "max_grad_norm": 1.0, "loss": 0.7447546720504761, "grad_norm": 0.40419334173202515, "learning_rate": 0.0001759227199631677}
-{"ts": "2025-12-27T10:35:59", "event": "train_log", "step": 4092, "epoch": 1.7265822784810125, "progress_pct": 28.78, "epoch_pct": 28.78, "eta": "40:22:39", "max_grad_norm": 1.0, "loss": 0.6348387598991394, "grad_norm": 0.39778804779052734, "learning_rate": 0.00017589145254421774}
-{"ts": "2025-12-27T10:36:14", "event": "train_log", "step": 4094, "epoch": 1.7274261603375527, "progress_pct": 28.79, "epoch_pct": 28.79, "eta": "40:21:36", "max_grad_norm": 1.0, "loss": 0.6813296675682068, "grad_norm": 0.3934648036956787, "learning_rate": 0.0001758601676185672}
-{"ts": "2025-12-27T10:36:30", "event": "train_log", "step": 4096, "epoch": 1.7282700421940929, "progress_pct": 28.8, "epoch_pct": 28.8, "eta": "40:20:36", "max_grad_norm": 1.0, "loss": 0.6369423270225525, "grad_norm": 0.4080725908279419, "learning_rate": 0.0001758288651934329}
-{"ts": "2025-12-27T10:36:46", "event": "train_log", "step": 4098, "epoch": 1.7291139240506328, "progress_pct": 28.82, "epoch_pct": 28.82, "eta": "40:19:34", "max_grad_norm": 1.0, "loss": 0.6664180159568787, "grad_norm": 0.5186997652053833, "learning_rate": 0.00017579754527603575}
-{"ts": "2025-12-27T10:37:01", "event": "train_log", "step": 4100, "epoch": 1.729957805907173, "progress_pct": 28.83, "epoch_pct": 28.83, "eta": "40:18:33", "max_grad_norm": 1.0, "loss": 0.7181394696235657, "grad_norm": 0.45290765166282654, "learning_rate": 0.0001757662078736006}
-{"ts": "2025-12-27T10:48:15", "event": "train_log", "step": 4100, "epoch": 1.729957805907173, "progress_pct": 28.83, "epoch_pct": 28.83, "eta": "40:46:16", "max_grad_norm": 1.0, "eval_loss": 0.7690847516059875, "eval_runtime": 673.6323, "eval_samples_per_second": 3.128, "eval_steps_per_second": 3.128}
-{"ts": "2025-12-27T10:48:29", "event": "train_log", "step": 4102, "epoch": 1.7308016877637131, "progress_pct": 28.85, "epoch_pct": 28.85, "eta": "40:45:11", "max_grad_norm": 1.0, "loss": 0.6850123405456543, "grad_norm": 0.45677125453948975, "learning_rate": 0.00017573485299335643}
-{"ts": "2025-12-27T10:48:44", "event": "train_log", "step": 4104, "epoch": 1.731645569620253, "progress_pct": 28.86, "epoch_pct": 28.86, "eta": "40:44:07", "max_grad_norm": 1.0, "loss": 0.7225809693336487, "grad_norm": 0.4854084253311157, "learning_rate": 0.0001757034806425362}
-{"ts": "2025-12-27T10:48:59", "event": "train_log", "step": 4106, "epoch": 1.7324894514767932, "progress_pct": 28.87, "epoch_pct": 28.87, "eta": "40:43:02", "max_grad_norm": 1.0, "loss": 0.7303882837295532, "grad_norm": 0.486583411693573, "learning_rate": 0.0001756720908283769}
-{"ts": "2025-12-27T10:49:14", "event": "train_log", "step": 4108, "epoch": 1.7333333333333334, "progress_pct": 28.89, "epoch_pct": 28.89, "eta": "40:42:00", "max_grad_norm": 1.0, "loss": 0.6789878010749817, "grad_norm": 0.4609545171260834, "learning_rate": 0.00017564068355811952}
-{"ts": "2025-12-27T10:49:29", "event": "train_log", "step": 4110, "epoch": 1.7341772151898733, "progress_pct": 28.9, "epoch_pct": 28.9, "eta": "40:40:56", "max_grad_norm": 1.0, "loss": 0.7311062812805176, "grad_norm": 0.3853047788143158, "learning_rate": 0.00017560925883900914}
-{"ts": "2025-12-27T10:49:44", "event": "train_log", "step": 4112, "epoch": 1.7350210970464135, "progress_pct": 28.92, "epoch_pct": 28.92, "eta": "40:39:52", "max_grad_norm": 1.0, "loss": 0.7106070518493652, "grad_norm": 0.41957035660743713, "learning_rate": 0.00017557781667829487}
-{"ts": "2025-12-27T10:49:59", "event": "train_log", "step": 4114, "epoch": 1.7358649789029537, "progress_pct": 28.93, "epoch_pct": 28.93, "eta": "40:38:49", "max_grad_norm": 1.0, "loss": 0.6345783472061157, "grad_norm": 0.37419262528419495, "learning_rate": 0.0001755463570832298}
-{"ts": "2025-12-27T10:50:13", "event": "train_log", "step": 4116, "epoch": 1.7367088607594936, "progress_pct": 28.95, "epoch_pct": 28.95, "eta": "40:37:44", "max_grad_norm": 1.0, "loss": 0.7923876047134399, "grad_norm": 0.5050614476203918, "learning_rate": 0.00017551488006107104}
-{"ts": "2025-12-27T10:50:28", "event": "train_log", "step": 4118, "epoch": 1.7375527426160338, "progress_pct": 28.96, "epoch_pct": 28.96, "eta": "40:36:41", "max_grad_norm": 1.0, "loss": 0.7502455115318298, "grad_norm": 0.49726125597953796, "learning_rate": 0.00017548338561907976}
-{"ts": "2025-12-27T10:50:44", "event": "train_log", "step": 4120, "epoch": 1.738396624472574, "progress_pct": 28.97, "epoch_pct": 28.97, "eta": "40:35:40", "max_grad_norm": 1.0, "loss": 0.6333624720573425, "grad_norm": 0.38956591486930847, "learning_rate": 0.00017545187376452105}
-{"ts": "2025-12-27T10:50:59", "event": "train_log", "step": 4122, "epoch": 1.7392405063291139, "progress_pct": 28.99, "epoch_pct": 28.99, "eta": "40:34:38", "max_grad_norm": 1.0, "loss": 0.6884907484054565, "grad_norm": 0.430318146944046, "learning_rate": 0.0001754203445046642}
-{"ts": "2025-12-27T10:51:15", "event": "train_log", "step": 4124, "epoch": 1.740084388185654, "progress_pct": 29.0, "epoch_pct": 29.0, "eta": "40:33:35", "max_grad_norm": 1.0, "loss": 0.7345985174179077, "grad_norm": 0.39826440811157227, "learning_rate": 0.0001753887978467823}
-{"ts": "2025-12-27T10:51:30", "event": "train_log", "step": 4126, "epoch": 1.7409282700421942, "progress_pct": 29.02, "epoch_pct": 29.02, "eta": "40:32:32", "max_grad_norm": 1.0, "loss": 0.6537752151489258, "grad_norm": 0.4263492822647095, "learning_rate": 0.00017535723379815267}
-{"ts": "2025-12-27T10:51:45", "event": "train_log", "step": 4128, "epoch": 1.7417721518987341, "progress_pct": 29.03, "epoch_pct": 29.03, "eta": "40:31:31", "max_grad_norm": 1.0, "loss": 0.6368000507354736, "grad_norm": 0.4012296199798584, "learning_rate": 0.0001753256523660564}
-{"ts": "2025-12-27T10:52:01", "event": "train_log", "step": 4130, "epoch": 1.7426160337552743, "progress_pct": 29.04, "epoch_pct": 29.04, "eta": "40:30:29", "max_grad_norm": 1.0, "loss": 0.6038334369659424, "grad_norm": 0.3881204426288605, "learning_rate": 0.0001752940535577788}
-{"ts": "2025-12-27T10:52:16", "event": "train_log", "step": 4132, "epoch": 1.7434599156118145, "progress_pct": 29.06, "epoch_pct": 29.06, "eta": "40:29:28", "max_grad_norm": 1.0, "loss": 0.6657052636146545, "grad_norm": 0.38410526514053345, "learning_rate": 0.0001752624373806091}
-{"ts": "2025-12-27T10:52:31", "event": "train_log", "step": 4134, "epoch": 1.7443037974683544, "progress_pct": 29.07, "epoch_pct": 29.07, "eta": "40:28:25", "max_grad_norm": 1.0, "loss": 0.6518114805221558, "grad_norm": 0.3970552980899811, "learning_rate": 0.00017523080384184057}
-{"ts": "2025-12-27T10:52:47", "event": "train_log", "step": 4136, "epoch": 1.7451476793248946, "progress_pct": 29.09, "epoch_pct": 29.09, "eta": "40:27:24", "max_grad_norm": 1.0, "loss": 0.609853208065033, "grad_norm": 0.37542012333869934, "learning_rate": 0.0001751991529487704}
-{"ts": "2025-12-27T10:53:02", "event": "train_log", "step": 4138, "epoch": 1.7459915611814347, "progress_pct": 29.1, "epoch_pct": 29.1, "eta": "40:26:21", "max_grad_norm": 1.0, "loss": 0.7356346845626831, "grad_norm": 0.49812132120132446, "learning_rate": 0.00017516748470869988}
-{"ts": "2025-12-27T10:53:17", "event": "train_log", "step": 4140, "epoch": 1.7468354430379747, "progress_pct": 29.11, "epoch_pct": 29.11, "eta": "40:25:18", "max_grad_norm": 1.0, "loss": 0.7198674082756042, "grad_norm": 0.48197710514068604, "learning_rate": 0.00017513579912893426}
-{"ts": "2025-12-27T10:53:31", "event": "train_log", "step": 4142, "epoch": 1.7476793248945146, "progress_pct": 29.13, "epoch_pct": 29.13, "eta": "40:24:14", "max_grad_norm": 1.0, "loss": 0.6841102242469788, "grad_norm": 0.38266444206237793, "learning_rate": 0.0001751040962167828}
-{"ts": "2025-12-27T10:53:46", "event": "train_log", "step": 4144, "epoch": 1.748523206751055, "progress_pct": 29.14, "epoch_pct": 29.14, "eta": "40:23:12", "max_grad_norm": 1.0, "loss": 0.7348533272743225, "grad_norm": 0.4165695309638977, "learning_rate": 0.0001750723759795587}
-{"ts": "2025-12-27T10:54:01", "event": "train_log", "step": 4146, "epoch": 1.749367088607595, "progress_pct": 29.16, "epoch_pct": 29.16, "eta": "40:22:10", "max_grad_norm": 1.0, "loss": 0.7344526648521423, "grad_norm": 0.4414960443973541, "learning_rate": 0.0001750406384245793}
-{"ts": "2025-12-27T10:54:16", "event": "train_log", "step": 4148, "epoch": 1.7502109704641349, "progress_pct": 29.17, "epoch_pct": 29.17, "eta": "40:21:07", "max_grad_norm": 1.0, "loss": 0.7047654986381531, "grad_norm": 0.4324318468570709, "learning_rate": 0.00017500888355916576}
-{"ts": "2025-12-27T10:54:31", "event": "train_log", "step": 4150, "epoch": 1.7510548523206753, "progress_pct": 29.18, "epoch_pct": 29.18, "eta": "40:20:04", "max_grad_norm": 1.0, "loss": 0.7317671179771423, "grad_norm": 0.44670364260673523, "learning_rate": 0.00017497711139064336}
-{"ts": "2025-12-27T10:54:46", "event": "train_log", "step": 4152, "epoch": 1.7518987341772152, "progress_pct": 29.2, "epoch_pct": 29.2, "eta": "40:19:01", "max_grad_norm": 1.0, "loss": 0.7447407245635986, "grad_norm": 0.43074679374694824, "learning_rate": 0.00017494532192634138}
-{"ts": "2025-12-27T10:55:01", "event": "train_log", "step": 4154, "epoch": 1.7527426160337551, "progress_pct": 29.21, "epoch_pct": 29.21, "eta": "40:17:59", "max_grad_norm": 1.0, "loss": 0.7352449893951416, "grad_norm": 0.43057894706726074, "learning_rate": 0.00017491351517359292}
-{"ts": "2025-12-27T10:55:17", "event": "train_log", "step": 4156, "epoch": 1.7535864978902953, "progress_pct": 29.23, "epoch_pct": 29.23, "eta": "40:16:58", "max_grad_norm": 1.0, "loss": 0.7244091033935547, "grad_norm": 0.49488556385040283, "learning_rate": 0.00017488169113973528}
-{"ts": "2025-12-27T10:55:31", "event": "train_log", "step": 4158, "epoch": 1.7544303797468355, "progress_pct": 29.24, "epoch_pct": 29.24, "eta": "40:15:54", "max_grad_norm": 1.0, "loss": 0.7515795230865479, "grad_norm": 0.4565380811691284, "learning_rate": 0.0001748498498321096}
-{"ts": "2025-12-27T10:55:47", "event": "train_log", "step": 4160, "epoch": 1.7552742616033754, "progress_pct": 29.25, "epoch_pct": 29.25, "eta": "40:14:54", "max_grad_norm": 1.0, "loss": 0.7451042532920837, "grad_norm": 0.45722341537475586, "learning_rate": 0.0001748179912580611}
-{"ts": "2025-12-27T10:56:02", "event": "train_log", "step": 4162, "epoch": 1.7561181434599156, "progress_pct": 29.27, "epoch_pct": 29.27, "eta": "40:13:53", "max_grad_norm": 1.0, "loss": 0.7133217453956604, "grad_norm": 0.47247326374053955, "learning_rate": 0.0001747861154249389}
-{"ts": "2025-12-27T10:56:17", "event": "train_log", "step": 4164, "epoch": 1.7569620253164557, "progress_pct": 29.28, "epoch_pct": 29.28, "eta": "40:12:51", "max_grad_norm": 1.0, "loss": 0.643742561340332, "grad_norm": 0.48307132720947266, "learning_rate": 0.00017475422234009623}
-{"ts": "2025-12-27T10:56:33", "event": "train_log", "step": 4166, "epoch": 1.7578059071729957, "progress_pct": 29.3, "epoch_pct": 29.3, "eta": "40:11:50", "max_grad_norm": 1.0, "loss": 0.7587857842445374, "grad_norm": 0.49163761734962463, "learning_rate": 0.00017472231201089012}
-{"ts": "2025-12-27T10:56:48", "event": "train_log", "step": 4168, "epoch": 1.7586497890295358, "progress_pct": 29.31, "epoch_pct": 29.31, "eta": "40:10:49", "max_grad_norm": 1.0, "loss": 0.6980416774749756, "grad_norm": 0.4726962149143219, "learning_rate": 0.00017469038444468165}
-{"ts": "2025-12-27T10:57:04", "event": "train_log", "step": 4170, "epoch": 1.759493670886076, "progress_pct": 29.32, "epoch_pct": 29.32, "eta": "40:09:48", "max_grad_norm": 1.0, "loss": 0.6929903626441956, "grad_norm": 0.4192392826080322, "learning_rate": 0.00017465843964883598}
-{"ts": "2025-12-27T10:57:19", "event": "train_log", "step": 4172, "epoch": 1.760337552742616, "progress_pct": 29.34, "epoch_pct": 29.34, "eta": "40:08:47", "max_grad_norm": 1.0, "loss": 0.7076222896575928, "grad_norm": 0.43000563979148865, "learning_rate": 0.00017462647763072216}
-{"ts": "2025-12-27T10:57:35", "event": "train_log", "step": 4174, "epoch": 1.761181434599156, "progress_pct": 29.35, "epoch_pct": 29.35, "eta": "40:07:47", "max_grad_norm": 1.0, "loss": 0.7260748147964478, "grad_norm": 0.45402681827545166, "learning_rate": 0.00017459449839771313}
-{"ts": "2025-12-27T10:57:50", "event": "train_log", "step": 4176, "epoch": 1.7620253164556963, "progress_pct": 29.37, "epoch_pct": 29.37, "eta": "40:06:46", "max_grad_norm": 1.0, "loss": 0.6901930570602417, "grad_norm": 0.4077165126800537, "learning_rate": 0.00017456250195718595}
-{"ts": "2025-12-27T10:58:06", "event": "train_log", "step": 4178, "epoch": 1.7628691983122362, "progress_pct": 29.38, "epoch_pct": 29.38, "eta": "40:05:46", "max_grad_norm": 1.0, "loss": 0.7085300087928772, "grad_norm": 0.4167994558811188, "learning_rate": 0.00017453048831652157}
-{"ts": "2025-12-27T10:58:22", "event": "train_log", "step": 4180, "epoch": 1.7637130801687764, "progress_pct": 29.4, "epoch_pct": 29.4, "eta": "40:04:48", "max_grad_norm": 1.0, "loss": 0.7646799087524414, "grad_norm": 0.45262131094932556, "learning_rate": 0.00017449845748310493}
-{"ts": "2025-12-27T10:58:37", "event": "train_log", "step": 4182, "epoch": 1.7645569620253165, "progress_pct": 29.41, "epoch_pct": 29.41, "eta": "40:03:46", "max_grad_norm": 1.0, "loss": 0.7847923040390015, "grad_norm": 0.4639943540096283, "learning_rate": 0.0001744664094643249}
-{"ts": "2025-12-27T10:58:54", "event": "train_log", "step": 4184, "epoch": 1.7654008438818565, "progress_pct": 29.42, "epoch_pct": 29.42, "eta": "40:02:49", "max_grad_norm": 1.0, "loss": 0.7192286252975464, "grad_norm": 0.33605465292930603, "learning_rate": 0.00017443434426757439}
-{"ts": "2025-12-27T10:59:11", "event": "train_log", "step": 4186, "epoch": 1.7662447257383966, "progress_pct": 29.44, "epoch_pct": 29.44, "eta": "40:01:51", "max_grad_norm": 1.0, "loss": 0.6554746627807617, "grad_norm": 0.4036388099193573, "learning_rate": 0.00017440226190025015}
-{"ts": "2025-12-27T10:59:27", "event": "train_log", "step": 4188, "epoch": 1.7670886075949368, "progress_pct": 29.45, "epoch_pct": 29.45, "eta": "40:00:52", "max_grad_norm": 1.0, "loss": 0.6433794498443604, "grad_norm": 0.45648789405822754, "learning_rate": 0.00017437016236975303}
-{"ts": "2025-12-27T10:59:42", "event": "train_log", "step": 4190, "epoch": 1.7679324894514767, "progress_pct": 29.47, "epoch_pct": 29.47, "eta": "39:59:52", "max_grad_norm": 1.0, "loss": 0.6608775854110718, "grad_norm": 0.38929006457328796, "learning_rate": 0.00017433804568348776}
-{"ts": "2025-12-27T11:00:00", "event": "train_log", "step": 4192, "epoch": 1.768776371308017, "progress_pct": 29.48, "epoch_pct": 29.48, "eta": "39:58:56", "max_grad_norm": 1.0, "loss": 0.6470816135406494, "grad_norm": 0.37158843874931335, "learning_rate": 0.00017430591184886308}
-{"ts": "2025-12-27T11:00:16", "event": "train_log", "step": 4194, "epoch": 1.769620253164557, "progress_pct": 29.49, "epoch_pct": 29.49, "eta": "39:57:56", "max_grad_norm": 1.0, "loss": 0.6825124025344849, "grad_norm": 0.39842307567596436, "learning_rate": 0.00017427376087329158}
-{"ts": "2025-12-27T11:00:31", "event": "train_log", "step": 4196, "epoch": 1.770464135021097, "progress_pct": 29.51, "epoch_pct": 29.51, "eta": "39:56:56", "max_grad_norm": 1.0, "loss": 0.7641696333885193, "grad_norm": 0.44220465421676636, "learning_rate": 0.00017424159276418987}
-{"ts": "2025-12-27T11:00:48", "event": "train_log", "step": 4198, "epoch": 1.7713080168776372, "progress_pct": 29.52, "epoch_pct": 29.52, "eta": "39:55:59", "max_grad_norm": 1.0, "loss": 0.7783681154251099, "grad_norm": 0.44530072808265686, "learning_rate": 0.0001742094075289786}
-{"ts": "2025-12-27T11:01:04", "event": "train_log", "step": 4200, "epoch": 1.7721518987341773, "progress_pct": 29.54, "epoch_pct": 29.54, "eta": "39:54:59", "max_grad_norm": 1.0, "loss": 0.6718224883079529, "grad_norm": 0.4497349262237549, "learning_rate": 0.00017417720517508216}
-{"ts": "2025-12-27T11:12:31", "event": "train_log", "step": 4200, "epoch": 1.7721518987341773, "progress_pct": 29.54, "epoch_pct": 29.54, "eta": "40:22:20", "max_grad_norm": 1.0, "eval_loss": 0.7676366567611694, "eval_runtime": 687.9619, "eval_samples_per_second": 3.063, "eval_steps_per_second": 3.063}
-{"ts": "2025-12-27T11:12:47", "event": "train_log", "step": 4202, "epoch": 1.7729957805907173, "progress_pct": 29.55, "epoch_pct": 29.55, "eta": "40:21:19", "max_grad_norm": 1.0, "loss": 0.7050814032554626, "grad_norm": 0.3857066333293915, "learning_rate": 0.00017414498570992914}
-{"ts": "2025-12-27T11:13:01", "event": "train_log", "step": 4204, "epoch": 1.7738396624472574, "progress_pct": 29.56, "epoch_pct": 29.56, "eta": "40:20:16", "max_grad_norm": 1.0, "loss": 0.7222742438316345, "grad_norm": 0.4533625543117523, "learning_rate": 0.00017411274914095188}
-{"ts": "2025-12-27T11:13:16", "event": "train_log", "step": 4206, "epoch": 1.7746835443037976, "progress_pct": 29.58, "epoch_pct": 29.58, "eta": "40:19:13", "max_grad_norm": 1.0, "loss": 0.6434906125068665, "grad_norm": 0.40805840492248535, "learning_rate": 0.00017408049547558676}
-{"ts": "2025-12-27T11:13:31", "event": "train_log", "step": 4208, "epoch": 1.7755274261603375, "progress_pct": 29.59, "epoch_pct": 29.59, "eta": "40:18:11", "max_grad_norm": 1.0, "loss": 0.686283528804779, "grad_norm": 0.5041740536689758, "learning_rate": 0.00017404822472127406}
-{"ts": "2025-12-27T11:13:47", "event": "train_log", "step": 4210, "epoch": 1.7763713080168775, "progress_pct": 29.61, "epoch_pct": 29.61, "eta": "40:17:10", "max_grad_norm": 1.0, "loss": 0.6785043478012085, "grad_norm": 0.41846802830696106, "learning_rate": 0.00017401593688545807}
-{"ts": "2025-12-27T11:14:02", "event": "train_log", "step": 4212, "epoch": 1.7772151898734179, "progress_pct": 29.62, "epoch_pct": 29.62, "eta": "40:16:08", "max_grad_norm": 1.0, "loss": 0.7566665410995483, "grad_norm": 0.4696303606033325, "learning_rate": 0.00017398363197558694}
-{"ts": "2025-12-27T11:14:18", "event": "train_log", "step": 4214, "epoch": 1.7780590717299578, "progress_pct": 29.63, "epoch_pct": 29.63, "eta": "40:15:08", "max_grad_norm": 1.0, "loss": 0.6178455948829651, "grad_norm": 0.3731461763381958, "learning_rate": 0.0001739513099991128}
-{"ts": "2025-12-27T11:14:33", "event": "train_log", "step": 4216, "epoch": 1.7789029535864977, "progress_pct": 29.65, "epoch_pct": 29.65, "eta": "40:14:05", "max_grad_norm": 1.0, "loss": 0.771265983581543, "grad_norm": 0.48098450899124146, "learning_rate": 0.00017391897096349167}
-{"ts": "2025-12-27T11:14:47", "event": "train_log", "step": 4218, "epoch": 1.7797468354430381, "progress_pct": 29.66, "epoch_pct": 29.66, "eta": "40:13:02", "max_grad_norm": 1.0, "loss": 0.6372597813606262, "grad_norm": 0.4164000451564789, "learning_rate": 0.0001738866148761836}
-{"ts": "2025-12-27T11:15:04", "event": "train_log", "step": 4220, "epoch": 1.780590717299578, "progress_pct": 29.68, "epoch_pct": 29.68, "eta": "40:12:03", "max_grad_norm": 1.0, "loss": 0.7213301658630371, "grad_norm": 0.4490415155887604, "learning_rate": 0.00017385424174465251}
-{"ts": "2025-12-27T11:15:18", "event": "train_log", "step": 4222, "epoch": 1.781434599156118, "progress_pct": 29.69, "epoch_pct": 29.69, "eta": "40:11:01", "max_grad_norm": 1.0, "loss": 0.7575726509094238, "grad_norm": 0.44518229365348816, "learning_rate": 0.00017382185157636623}
-{"ts": "2025-12-27T11:15:34", "event": "train_log", "step": 4224, "epoch": 1.7822784810126582, "progress_pct": 29.7, "epoch_pct": 29.7, "eta": "40:10:01", "max_grad_norm": 1.0, "loss": 0.6473780274391174, "grad_norm": 0.34899434447288513, "learning_rate": 0.00017378944437879658}
-{"ts": "2025-12-27T11:15:48", "event": "train_log", "step": 4226, "epoch": 1.7831223628691983, "progress_pct": 29.72, "epoch_pct": 29.72, "eta": "40:08:57", "max_grad_norm": 1.0, "loss": 0.7238336205482483, "grad_norm": 0.4068683087825775, "learning_rate": 0.00017375702015941924}
-{"ts": "2025-12-27T11:16:04", "event": "train_log", "step": 4228, "epoch": 1.7839662447257383, "progress_pct": 29.73, "epoch_pct": 29.73, "eta": "40:07:56", "max_grad_norm": 1.0, "loss": 0.7797979116439819, "grad_norm": 0.4025551974773407, "learning_rate": 0.0001737245789257139}
-{"ts": "2025-12-27T11:16:20", "event": "train_log", "step": 4230, "epoch": 1.7848101265822784, "progress_pct": 29.75, "epoch_pct": 29.75, "eta": "40:06:56", "max_grad_norm": 1.0, "loss": 0.6304885149002075, "grad_norm": 0.35764896869659424, "learning_rate": 0.00017369212068516412}
-{"ts": "2025-12-27T11:16:34", "event": "train_log", "step": 4232, "epoch": 1.7856540084388186, "progress_pct": 29.76, "epoch_pct": 29.76, "eta": "40:05:53", "max_grad_norm": 1.0, "loss": 0.6606637835502625, "grad_norm": 0.43337100744247437, "learning_rate": 0.00017365964544525738}
-{"ts": "2025-12-27T11:16:49", "event": "train_log", "step": 4234, "epoch": 1.7864978902953585, "progress_pct": 29.77, "epoch_pct": 29.77, "eta": "40:04:51", "max_grad_norm": 1.0, "loss": 0.712163507938385, "grad_norm": 0.4630814492702484, "learning_rate": 0.0001736271532134851}
-{"ts": "2025-12-27T11:17:04", "event": "train_log", "step": 4236, "epoch": 1.7873417721518987, "progress_pct": 29.79, "epoch_pct": 29.79, "eta": "40:03:49", "max_grad_norm": 1.0, "loss": 0.6649466753005981, "grad_norm": 0.38714799284935, "learning_rate": 0.00017359464399734255}
-{"ts": "2025-12-27T11:17:19", "event": "train_log", "step": 4238, "epoch": 1.7881856540084389, "progress_pct": 29.8, "epoch_pct": 29.8, "eta": "40:02:48", "max_grad_norm": 1.0, "loss": 0.6223326921463013, "grad_norm": 0.38999977707862854, "learning_rate": 0.0001735621178043291}
-{"ts": "2025-12-27T11:17:34", "event": "train_log", "step": 4240, "epoch": 1.7890295358649788, "progress_pct": 29.82, "epoch_pct": 29.82, "eta": "40:01:46", "max_grad_norm": 1.0, "loss": 0.7207517027854919, "grad_norm": 0.4736211597919464, "learning_rate": 0.00017352957464194786}
-{"ts": "2025-12-27T11:17:49", "event": "train_log", "step": 4242, "epoch": 1.789873417721519, "progress_pct": 29.83, "epoch_pct": 29.83, "eta": "40:00:44", "max_grad_norm": 1.0, "loss": 0.7203661203384399, "grad_norm": 0.423476904630661, "learning_rate": 0.00017349701451770588}
-{"ts": "2025-12-27T11:18:03", "event": "train_log", "step": 4244, "epoch": 1.7907172995780591, "progress_pct": 29.85, "epoch_pct": 29.85, "eta": "39:59:41", "max_grad_norm": 1.0, "loss": 0.709998607635498, "grad_norm": 0.4487479627132416, "learning_rate": 0.0001734644374391142}
-{"ts": "2025-12-27T11:18:17", "event": "train_log", "step": 4246, "epoch": 1.791561181434599, "progress_pct": 29.86, "epoch_pct": 29.86, "eta": "39:58:38", "max_grad_norm": 1.0, "loss": 0.7079582214355469, "grad_norm": 0.43721267580986023, "learning_rate": 0.00017343184341368773}
-{"ts": "2025-12-27T11:18:32", "event": "train_log", "step": 4248, "epoch": 1.7924050632911392, "progress_pct": 29.87, "epoch_pct": 29.87, "eta": "39:57:36", "max_grad_norm": 1.0, "loss": 0.6772971749305725, "grad_norm": 0.426864892244339, "learning_rate": 0.00017339923244894524}
-{"ts": "2025-12-27T11:18:48", "event": "train_log", "step": 4250, "epoch": 1.7932489451476794, "progress_pct": 29.89, "epoch_pct": 29.89, "eta": "39:56:37", "max_grad_norm": 1.0, "loss": 0.6882370710372925, "grad_norm": 0.3580208420753479, "learning_rate": 0.0001733666045524095}
-{"ts": "2025-12-27T11:19:02", "event": "train_log", "step": 4252, "epoch": 1.7940928270042193, "progress_pct": 29.9, "epoch_pct": 29.9, "eta": "39:55:34", "max_grad_norm": 1.0, "loss": 0.7534610629081726, "grad_norm": 0.487248957157135, "learning_rate": 0.00017333395973160714}
-{"ts": "2025-12-27T11:19:17", "event": "train_log", "step": 4254, "epoch": 1.7949367088607595, "progress_pct": 29.92, "epoch_pct": 29.92, "eta": "39:54:32", "max_grad_norm": 1.0, "loss": 0.6897269487380981, "grad_norm": 0.44908860325813293, "learning_rate": 0.00017330129799406866}
-{"ts": "2025-12-27T11:19:33", "event": "train_log", "step": 4256, "epoch": 1.7957805907172997, "progress_pct": 29.93, "epoch_pct": 29.93, "eta": "39:53:32", "max_grad_norm": 1.0, "loss": 0.7081538438796997, "grad_norm": 0.43617817759513855, "learning_rate": 0.00017326861934732852}
-{"ts": "2025-12-27T11:19:48", "event": "train_log", "step": 4258, "epoch": 1.7966244725738396, "progress_pct": 29.94, "epoch_pct": 29.94, "eta": "39:52:31", "max_grad_norm": 1.0, "loss": 0.6852753758430481, "grad_norm": 0.428666353225708, "learning_rate": 0.00017323592379892504}
-{"ts": "2025-12-27T11:20:03", "event": "train_log", "step": 4260, "epoch": 1.7974683544303798, "progress_pct": 29.96, "epoch_pct": 29.96, "eta": "39:51:31", "max_grad_norm": 1.0, "loss": 0.7463182210922241, "grad_norm": 0.4522199034690857, "learning_rate": 0.00017320321135640045}
-{"ts": "2025-12-27T11:20:19", "event": "train_log", "step": 4262, "epoch": 1.79831223628692, "progress_pct": 29.97, "epoch_pct": 29.97, "eta": "39:50:32", "max_grad_norm": 1.0, "loss": 0.6643774509429932, "grad_norm": 0.38632410764694214, "learning_rate": 0.00017317048202730088}
-{"ts": "2025-12-27T11:20:34", "event": "train_log", "step": 4264, "epoch": 1.7991561181434599, "progress_pct": 29.99, "epoch_pct": 29.99, "eta": "39:49:32", "max_grad_norm": 1.0, "loss": 0.6726668477058411, "grad_norm": 0.41171637177467346, "learning_rate": 0.00017313773581917642}
-{"ts": "2025-12-27T11:20:50", "event": "train_log", "step": 4266, "epoch": 1.8, "progress_pct": 30.0, "epoch_pct": 30.0, "eta": "39:48:33", "max_grad_norm": 1.0, "loss": 0.6278629302978516, "grad_norm": 0.398520290851593, "learning_rate": 0.0001731049727395809}
-{"ts": "2025-12-27T11:21:06", "event": "train_log", "step": 4268, "epoch": 1.8008438818565402, "progress_pct": 30.01, "epoch_pct": 30.01, "eta": "39:47:34", "max_grad_norm": 1.0, "loss": 0.5823352336883545, "grad_norm": 0.4000356197357178, "learning_rate": 0.0001730721927960722}
-{"ts": "2025-12-27T11:21:20", "event": "train_log", "step": 4270, "epoch": 1.8016877637130801, "progress_pct": 30.03, "epoch_pct": 30.03, "eta": "39:46:31", "max_grad_norm": 1.0, "loss": 0.7492824196815491, "grad_norm": 0.47376710176467896, "learning_rate": 0.000173039395996212}
-{"ts": "2025-12-27T11:21:35", "event": "train_log", "step": 4272, "epoch": 1.80253164556962, "progress_pct": 30.04, "epoch_pct": 30.04, "eta": "39:45:30", "max_grad_norm": 1.0, "loss": 0.7630324363708496, "grad_norm": 0.4624378979206085, "learning_rate": 0.00017300658234756588}
-{"ts": "2025-12-27T11:21:50", "event": "train_log", "step": 4274, "epoch": 1.8033755274261605, "progress_pct": 30.06, "epoch_pct": 30.06, "eta": "39:44:28", "max_grad_norm": 1.0, "loss": 0.6484803557395935, "grad_norm": 0.4178096354007721, "learning_rate": 0.00017297375185770336}
-{"ts": "2025-12-27T11:22:04", "event": "train_log", "step": 4276, "epoch": 1.8042194092827004, "progress_pct": 30.07, "epoch_pct": 30.07, "eta": "39:43:27", "max_grad_norm": 1.0, "loss": 0.776732325553894, "grad_norm": 0.511215329170227, "learning_rate": 0.00017294090453419774}
-{"ts": "2025-12-27T11:22:19", "event": "train_log", "step": 4278, "epoch": 1.8050632911392404, "progress_pct": 30.08, "epoch_pct": 30.08, "eta": "39:42:24", "max_grad_norm": 1.0, "loss": 0.6801077723503113, "grad_norm": 0.44643548130989075, "learning_rate": 0.00017290804038462633}
-{"ts": "2025-12-27T11:22:33", "event": "train_log", "step": 4280, "epoch": 1.8059071729957807, "progress_pct": 30.1, "epoch_pct": 30.1, "eta": "39:41:22", "max_grad_norm": 1.0, "loss": 0.8024200797080994, "grad_norm": 0.5090142488479614, "learning_rate": 0.0001728751594165702}
-{"ts": "2025-12-27T11:22:47", "event": "train_log", "step": 4282, "epoch": 1.8067510548523207, "progress_pct": 30.11, "epoch_pct": 30.11, "eta": "39:40:19", "max_grad_norm": 1.0, "loss": 0.7810231447219849, "grad_norm": 0.45888981223106384, "learning_rate": 0.00017284226163761436}
-{"ts": "2025-12-27T11:23:02", "event": "train_log", "step": 4284, "epoch": 1.8075949367088606, "progress_pct": 30.13, "epoch_pct": 30.13, "eta": "39:39:19", "max_grad_norm": 1.0, "loss": 0.6768189072608948, "grad_norm": 0.3985820710659027, "learning_rate": 0.0001728093470553478}
-{"ts": "2025-12-27T11:23:18", "event": "train_log", "step": 4286, "epoch": 1.808438818565401, "progress_pct": 30.14, "epoch_pct": 30.14, "eta": "39:38:19", "max_grad_norm": 1.0, "loss": 0.6093943119049072, "grad_norm": 0.3988003730773926, "learning_rate": 0.00017277641567736316}
-{"ts": "2025-12-27T11:23:33", "event": "train_log", "step": 4288, "epoch": 1.809282700421941, "progress_pct": 30.15, "epoch_pct": 30.15, "eta": "39:37:18", "max_grad_norm": 1.0, "loss": 0.6836619973182678, "grad_norm": 0.46131962537765503, "learning_rate": 0.0001727434675112571}
-{"ts": "2025-12-27T11:23:47", "event": "train_log", "step": 4290, "epoch": 1.810126582278481, "progress_pct": 30.17, "epoch_pct": 30.17, "eta": "39:36:17", "max_grad_norm": 1.0, "loss": 0.7144147157669067, "grad_norm": 0.42959487438201904, "learning_rate": 0.0001727105025646302}
-{"ts": "2025-12-27T11:24:02", "event": "train_log", "step": 4292, "epoch": 1.810970464135021, "progress_pct": 30.18, "epoch_pct": 30.18, "eta": "39:35:17", "max_grad_norm": 1.0, "loss": 0.7190625667572021, "grad_norm": 0.4110259413719177, "learning_rate": 0.00017267752084508675}
-{"ts": "2025-12-27T11:24:17", "event": "train_log", "step": 4294, "epoch": 1.8118143459915612, "progress_pct": 30.2, "epoch_pct": 30.2, "eta": "39:34:17", "max_grad_norm": 1.0, "loss": 0.7272495031356812, "grad_norm": 0.4501377046108246, "learning_rate": 0.00017264452236023505}
-{"ts": "2025-12-27T11:24:32", "event": "train_log", "step": 4296, "epoch": 1.8126582278481012, "progress_pct": 30.21, "epoch_pct": 30.21, "eta": "39:33:15", "max_grad_norm": 1.0, "loss": 0.758166491985321, "grad_norm": 0.467817097902298, "learning_rate": 0.0001726115071176872}
-{"ts": "2025-12-27T11:24:47", "event": "train_log", "step": 4298, "epoch": 1.8135021097046413, "progress_pct": 30.23, "epoch_pct": 30.23, "eta": "39:32:15", "max_grad_norm": 1.0, "loss": 0.6712231040000916, "grad_norm": 0.42394939064979553, "learning_rate": 0.0001725784751250592}
-{"ts": "2025-12-27T11:25:02", "event": "train_log", "step": 4300, "epoch": 1.8143459915611815, "progress_pct": 30.24, "epoch_pct": 30.24, "eta": "39:31:15", "max_grad_norm": 1.0, "loss": 0.5999719500541687, "grad_norm": 0.37668925523757935, "learning_rate": 0.00017254542638997088}
-{"ts": "2025-12-27T11:36:30", "event": "train_log", "step": 4300, "epoch": 1.8143459915611815, "progress_pct": 30.24, "epoch_pct": 30.24, "eta": "39:57:43", "max_grad_norm": 1.0, "eval_loss": 0.7672964930534363, "eval_runtime": 688.4249, "eval_samples_per_second": 3.061, "eval_steps_per_second": 3.061}
-{"ts": "2025-12-27T11:36:47", "event": "train_log", "step": 4302, "epoch": 1.8151898734177214, "progress_pct": 30.25, "epoch_pct": 30.25, "eta": "39:56:45", "max_grad_norm": 1.0, "loss": 0.7188607454299927, "grad_norm": 0.44964465498924255, "learning_rate": 0.00017251236092004596}
-{"ts": "2025-12-27T11:37:02", "event": "train_log", "step": 4304, "epoch": 1.8160337552742616, "progress_pct": 30.27, "epoch_pct": 30.27, "eta": "39:55:45", "max_grad_norm": 1.0, "loss": 0.707834005355835, "grad_norm": 0.4108492434024811, "learning_rate": 0.000172479278722912}
-{"ts": "2025-12-27T11:37:18", "event": "train_log", "step": 4306, "epoch": 1.8168776371308017, "progress_pct": 30.28, "epoch_pct": 30.28, "eta": "39:54:45", "max_grad_norm": 1.0, "loss": 0.6915075182914734, "grad_norm": 0.4455305337905884, "learning_rate": 0.00017244617980620043}
-{"ts": "2025-12-27T11:37:35", "event": "train_log", "step": 4308, "epoch": 1.8177215189873417, "progress_pct": 30.3, "epoch_pct": 30.3, "eta": "39:53:48", "max_grad_norm": 1.0, "loss": 0.6591874361038208, "grad_norm": 0.3977123200893402, "learning_rate": 0.00017241306417754655}
-{"ts": "2025-12-27T11:37:49", "event": "train_log", "step": 4310, "epoch": 1.8185654008438819, "progress_pct": 30.31, "epoch_pct": 30.31, "eta": "39:52:45", "max_grad_norm": 1.0, "loss": 0.6254785060882568, "grad_norm": 0.4028434157371521, "learning_rate": 0.00017237993184458946}
-{"ts": "2025-12-27T11:38:05", "event": "train_log", "step": 4312, "epoch": 1.819409282700422, "progress_pct": 30.32, "epoch_pct": 30.32, "eta": "39:51:46", "max_grad_norm": 1.0, "loss": 0.6968662142753601, "grad_norm": 0.41024482250213623, "learning_rate": 0.00017234678281497217}
-{"ts": "2025-12-27T11:38:22", "event": "train_log", "step": 4314, "epoch": 1.820253164556962, "progress_pct": 30.34, "epoch_pct": 30.34, "eta": "39:50:50", "max_grad_norm": 1.0, "loss": 0.6535647511482239, "grad_norm": 0.45941361784935, "learning_rate": 0.00017231361709634153}
-{"ts": "2025-12-27T11:38:38", "event": "train_log", "step": 4316, "epoch": 1.8210970464135021, "progress_pct": 30.35, "epoch_pct": 30.35, "eta": "39:49:52", "max_grad_norm": 1.0, "loss": 0.6378563642501831, "grad_norm": 0.39477071166038513, "learning_rate": 0.00017228043469634825}
-{"ts": "2025-12-27T11:38:54", "event": "train_log", "step": 4318, "epoch": 1.8219409282700423, "progress_pct": 30.37, "epoch_pct": 30.37, "eta": "39:48:53", "max_grad_norm": 1.0, "loss": 0.7021255493164062, "grad_norm": 0.403826504945755, "learning_rate": 0.00017224723562264687}
-{"ts": "2025-12-27T11:39:09", "event": "train_log", "step": 4320, "epoch": 1.8227848101265822, "progress_pct": 30.38, "epoch_pct": 30.38, "eta": "39:47:52", "max_grad_norm": 1.0, "loss": 0.7411118745803833, "grad_norm": 0.4179201126098633, "learning_rate": 0.00017221401988289575}
-{"ts": "2025-12-27T11:39:25", "event": "train_log", "step": 4322, "epoch": 1.8236286919831224, "progress_pct": 30.39, "epoch_pct": 30.39, "eta": "39:46:53", "max_grad_norm": 1.0, "loss": 0.7435210943222046, "grad_norm": 0.4719425141811371, "learning_rate": 0.0001721807874847571}
-{"ts": "2025-12-27T11:39:41", "event": "train_log", "step": 4324, "epoch": 1.8244725738396625, "progress_pct": 30.41, "epoch_pct": 30.41, "eta": "39:45:54", "max_grad_norm": 1.0, "loss": 0.6813794374465942, "grad_norm": 0.39946448802948, "learning_rate": 0.0001721475384358971}
-{"ts": "2025-12-27T11:39:57", "event": "train_log", "step": 4326, "epoch": 1.8253164556962025, "progress_pct": 30.42, "epoch_pct": 30.42, "eta": "39:44:57", "max_grad_norm": 1.0, "loss": 0.6468828320503235, "grad_norm": 0.4367005527019501, "learning_rate": 0.00017211427274398559}
-{"ts": "2025-12-27T11:40:14", "event": "train_log", "step": 4328, "epoch": 1.8261603375527427, "progress_pct": 30.44, "epoch_pct": 30.44, "eta": "39:43:59", "max_grad_norm": 1.0, "loss": 0.6628729701042175, "grad_norm": 0.4078138470649719, "learning_rate": 0.00017208099041669632}
-{"ts": "2025-12-27T11:40:29", "event": "train_log", "step": 4330, "epoch": 1.8270042194092828, "progress_pct": 30.45, "epoch_pct": 30.45, "eta": "39:42:59", "max_grad_norm": 1.0, "loss": 0.7028043866157532, "grad_norm": 0.4141235649585724, "learning_rate": 0.0001720476914617069}
-{"ts": "2025-12-27T11:40:44", "event": "train_log", "step": 4332, "epoch": 1.8278481012658228, "progress_pct": 30.46, "epoch_pct": 30.46, "eta": "39:41:59", "max_grad_norm": 1.0, "loss": 0.6710682511329651, "grad_norm": 0.448733925819397, "learning_rate": 0.00017201437588669878}
-{"ts": "2025-12-27T11:41:00", "event": "train_log", "step": 4334, "epoch": 1.828691983122363, "progress_pct": 30.48, "epoch_pct": 30.48, "eta": "39:41:01", "max_grad_norm": 1.0, "loss": 0.792453408241272, "grad_norm": 0.5084340572357178, "learning_rate": 0.00017198104369935718}
-{"ts": "2025-12-27T11:41:14", "event": "train_log", "step": 4336, "epoch": 1.829535864978903, "progress_pct": 30.49, "epoch_pct": 30.49, "eta": "39:39:58", "max_grad_norm": 1.0, "loss": 0.7536583542823792, "grad_norm": 0.43463611602783203, "learning_rate": 0.00017194769490737124}
-{"ts": "2025-12-27T11:41:30", "event": "train_log", "step": 4338, "epoch": 1.830379746835443, "progress_pct": 30.51, "epoch_pct": 30.51, "eta": "39:39:00", "max_grad_norm": 1.0, "loss": 0.7445555925369263, "grad_norm": 0.46039044857025146, "learning_rate": 0.00017191432951843387}
-{"ts": "2025-12-27T11:41:46", "event": "train_log", "step": 4340, "epoch": 1.831223628691983, "progress_pct": 30.52, "epoch_pct": 30.52, "eta": "39:38:00", "max_grad_norm": 1.0, "loss": 0.7003044486045837, "grad_norm": 0.3894030451774597, "learning_rate": 0.0001718809475402418}
-{"ts": "2025-12-27T11:42:00", "event": "train_log", "step": 4342, "epoch": 1.8320675105485233, "progress_pct": 30.53, "epoch_pct": 30.53, "eta": "39:36:57", "max_grad_norm": 1.0, "loss": 0.6948950886726379, "grad_norm": 0.5851747393608093, "learning_rate": 0.00017184754898049568}
-{"ts": "2025-12-27T11:42:15", "event": "train_log", "step": 4344, "epoch": 1.8329113924050633, "progress_pct": 30.55, "epoch_pct": 30.55, "eta": "39:35:57", "max_grad_norm": 1.0, "loss": 0.675811231136322, "grad_norm": 0.40906789898872375, "learning_rate": 0.00017181413384689982}
-{"ts": "2025-12-27T11:42:30", "event": "train_log", "step": 4346, "epoch": 1.8337552742616032, "progress_pct": 30.56, "epoch_pct": 30.56, "eta": "39:34:57", "max_grad_norm": 1.0, "loss": 0.7422580122947693, "grad_norm": 0.4235765039920807, "learning_rate": 0.0001717807021471625}
-{"ts": "2025-12-27T11:42:45", "event": "train_log", "step": 4348, "epoch": 1.8345991561181436, "progress_pct": 30.58, "epoch_pct": 30.58, "eta": "39:33:58", "max_grad_norm": 1.0, "loss": 0.7014731168746948, "grad_norm": 0.3898368775844574, "learning_rate": 0.0001717472538889958}
-{"ts": "2025-12-27T11:43:00", "event": "train_log", "step": 4350, "epoch": 1.8354430379746836, "progress_pct": 30.59, "epoch_pct": 30.59, "eta": "39:32:57", "max_grad_norm": 1.0, "loss": 0.6952776312828064, "grad_norm": 0.4122314751148224, "learning_rate": 0.00017171378908011553}
-{"ts": "2025-12-27T11:43:15", "event": "train_log", "step": 4352, "epoch": 1.8362869198312235, "progress_pct": 30.6, "epoch_pct": 30.6, "eta": "39:31:56", "max_grad_norm": 1.0, "loss": 0.6758598685264587, "grad_norm": 0.38085612654685974, "learning_rate": 0.00017168030772824144}
-{"ts": "2025-12-27T11:43:29", "event": "train_log", "step": 4354, "epoch": 1.8371308016877637, "progress_pct": 30.62, "epoch_pct": 30.62, "eta": "39:30:54", "max_grad_norm": 1.0, "loss": 0.7139424085617065, "grad_norm": 0.43519729375839233, "learning_rate": 0.00017164680984109695}
-{"ts": "2025-12-27T11:43:44", "event": "train_log", "step": 4356, "epoch": 1.8379746835443038, "progress_pct": 30.63, "epoch_pct": 30.63, "eta": "39:29:54", "max_grad_norm": 1.0, "loss": 0.7125198841094971, "grad_norm": 0.4404325783252716, "learning_rate": 0.0001716132954264095}
-{"ts": "2025-12-27T11:43:59", "event": "train_log", "step": 4358, "epoch": 1.8388185654008438, "progress_pct": 30.65, "epoch_pct": 30.65, "eta": "39:28:53", "max_grad_norm": 1.0, "loss": 0.7011314630508423, "grad_norm": 0.3965512812137604, "learning_rate": 0.00017157976449191012}
-{"ts": "2025-12-27T11:44:13", "event": "train_log", "step": 4360, "epoch": 1.839662447257384, "progress_pct": 30.66, "epoch_pct": 30.66, "eta": "39:27:52", "max_grad_norm": 1.0, "loss": 0.6485645174980164, "grad_norm": 0.4273630976676941, "learning_rate": 0.0001715462170453338}
-{"ts": "2025-12-27T11:44:28", "event": "train_log", "step": 4362, "epoch": 1.840506329113924, "progress_pct": 30.68, "epoch_pct": 30.68, "eta": "39:26:52", "max_grad_norm": 1.0, "loss": 0.6669548153877258, "grad_norm": 0.4639208912849426, "learning_rate": 0.00017151265309441925}
-{"ts": "2025-12-27T11:44:43", "event": "train_log", "step": 4364, "epoch": 1.841350210970464, "progress_pct": 30.69, "epoch_pct": 30.69, "eta": "39:25:52", "max_grad_norm": 1.0, "loss": 0.6276374459266663, "grad_norm": 0.4190906286239624, "learning_rate": 0.00017147907264690907}
-{"ts": "2025-12-27T11:44:59", "event": "train_log", "step": 4366, "epoch": 1.8421940928270042, "progress_pct": 30.7, "epoch_pct": 30.7, "eta": "39:24:53", "max_grad_norm": 1.0, "loss": 0.5975915193557739, "grad_norm": 0.4146515130996704, "learning_rate": 0.00017144547571054962}
-{"ts": "2025-12-27T11:45:14", "event": "train_log", "step": 4368, "epoch": 1.8430379746835444, "progress_pct": 30.72, "epoch_pct": 30.72, "eta": "39:23:53", "max_grad_norm": 1.0, "loss": 0.6536507606506348, "grad_norm": 0.38717755675315857, "learning_rate": 0.00017141186229309105}
-{"ts": "2025-12-27T11:45:29", "event": "train_log", "step": 4370, "epoch": 1.8438818565400843, "progress_pct": 30.73, "epoch_pct": 30.73, "eta": "39:22:54", "max_grad_norm": 1.0, "loss": 0.7078962326049805, "grad_norm": 0.3988541066646576, "learning_rate": 0.00017137823240228735}
-{"ts": "2025-12-27T11:45:44", "event": "train_log", "step": 4372, "epoch": 1.8447257383966245, "progress_pct": 30.75, "epoch_pct": 30.75, "eta": "39:21:54", "max_grad_norm": 1.0, "loss": 0.6795231699943542, "grad_norm": 0.43783870339393616, "learning_rate": 0.00017134458604589628}
-{"ts": "2025-12-27T11:45:59", "event": "train_log", "step": 4374, "epoch": 1.8455696202531646, "progress_pct": 30.76, "epoch_pct": 30.76, "eta": "39:20:53", "max_grad_norm": 1.0, "loss": 0.7030490040779114, "grad_norm": 0.439636766910553, "learning_rate": 0.00017131092323167938}
-{"ts": "2025-12-27T11:46:14", "event": "train_log", "step": 4376, "epoch": 1.8464135021097046, "progress_pct": 30.77, "epoch_pct": 30.77, "eta": "39:19:54", "max_grad_norm": 1.0, "loss": 0.7611671686172485, "grad_norm": 0.4426078498363495, "learning_rate": 0.00017127724396740206}
-{"ts": "2025-12-27T11:46:29", "event": "train_log", "step": 4378, "epoch": 1.8472573839662447, "progress_pct": 30.79, "epoch_pct": 30.79, "eta": "39:18:54", "max_grad_norm": 1.0, "loss": 0.737910270690918, "grad_norm": 0.40058812499046326, "learning_rate": 0.00017124354826083348}
-{"ts": "2025-12-27T11:46:44", "event": "train_log", "step": 4380, "epoch": 1.8481012658227849, "progress_pct": 30.8, "epoch_pct": 30.8, "eta": "39:17:54", "max_grad_norm": 1.0, "loss": 0.683937132358551, "grad_norm": 0.43037283420562744, "learning_rate": 0.00017120983611974654}
-{"ts": "2025-12-27T11:46:58", "event": "train_log", "step": 4382, "epoch": 1.8489451476793248, "progress_pct": 30.82, "epoch_pct": 30.82, "eta": "39:16:54", "max_grad_norm": 1.0, "loss": 0.6987335681915283, "grad_norm": 0.4479113221168518, "learning_rate": 0.00017117610755191807}
-{"ts": "2025-12-27T11:47:14", "event": "train_log", "step": 4384, "epoch": 1.849789029535865, "progress_pct": 30.83, "epoch_pct": 30.83, "eta": "39:15:55", "max_grad_norm": 1.0, "loss": 0.6964257955551147, "grad_norm": 0.4218229651451111, "learning_rate": 0.0001711423625651285}
-{"ts": "2025-12-27T11:47:29", "event": "train_log", "step": 4386, "epoch": 1.8506329113924052, "progress_pct": 30.84, "epoch_pct": 30.84, "eta": "39:14:56", "max_grad_norm": 1.0, "loss": 0.6983811855316162, "grad_norm": 0.397733211517334, "learning_rate": 0.00017110860116716222}
-{"ts": "2025-12-27T11:47:43", "event": "train_log", "step": 4388, "epoch": 1.851476793248945, "progress_pct": 30.86, "epoch_pct": 30.86, "eta": "39:13:55", "max_grad_norm": 1.0, "loss": 0.7579324245452881, "grad_norm": 0.4844493865966797, "learning_rate": 0.00017107482336580735}
-{"ts": "2025-12-27T11:47:58", "event": "train_log", "step": 4390, "epoch": 1.8523206751054853, "progress_pct": 30.87, "epoch_pct": 30.87, "eta": "39:12:54", "max_grad_norm": 1.0, "loss": 0.703558623790741, "grad_norm": 0.4494120478630066, "learning_rate": 0.0001710410291688557}
-{"ts": "2025-12-27T11:48:12", "event": "train_log", "step": 4392, "epoch": 1.8531645569620254, "progress_pct": 30.89, "epoch_pct": 30.89, "eta": "39:11:54", "max_grad_norm": 1.0, "loss": 0.7386981248855591, "grad_norm": 0.4721727967262268, "learning_rate": 0.000171007218584103}
-{"ts": "2025-12-27T11:48:26", "event": "train_log", "step": 4394, "epoch": 1.8540084388185654, "progress_pct": 30.9, "epoch_pct": 30.9, "eta": "39:10:52", "max_grad_norm": 1.0, "loss": 0.7769017219543457, "grad_norm": 0.4816451370716095, "learning_rate": 0.0001709733916193487}
-{"ts": "2025-12-27T11:48:41", "event": "train_log", "step": 4396, "epoch": 1.8548523206751055, "progress_pct": 30.91, "epoch_pct": 30.91, "eta": "39:09:52", "max_grad_norm": 1.0, "loss": 0.7315034866333008, "grad_norm": 0.43638876080513, "learning_rate": 0.00017093954828239602}
-{"ts": "2025-12-27T11:48:57", "event": "train_log", "step": 4398, "epoch": 1.8556962025316457, "progress_pct": 30.93, "epoch_pct": 30.93, "eta": "39:08:54", "max_grad_norm": 1.0, "loss": 0.7289890050888062, "grad_norm": 0.4035055935382843, "learning_rate": 0.000170905688581052}
-{"ts": "2025-12-27T11:49:11", "event": "train_log", "step": 4400, "epoch": 1.8565400843881856, "progress_pct": 30.94, "epoch_pct": 30.94, "eta": "39:07:54", "max_grad_norm": 1.0, "loss": 0.7190408110618591, "grad_norm": 0.44265708327293396, "learning_rate": 0.00017087181252312735}
-{"ts": "2025-12-27T12:00:29", "event": "train_log", "step": 4400, "epoch": 1.8565400843881856, "progress_pct": 30.94, "epoch_pct": 30.94, "eta": "39:33:08", "max_grad_norm": 1.0, "eval_loss": 0.7635221481323242, "eval_runtime": 678.243, "eval_samples_per_second": 3.107, "eval_steps_per_second": 3.107}
-{"ts": "2025-12-27T12:00:47", "event": "train_log", "step": 4402, "epoch": 1.8573839662447258, "progress_pct": 30.96, "epoch_pct": 30.96, "eta": "39:32:14", "max_grad_norm": 1.0, "loss": 0.6318185925483704, "grad_norm": 0.39691466093063354, "learning_rate": 0.0001708379201164367}
-{"ts": "2025-12-27T12:01:03", "event": "train_log", "step": 4404, "epoch": 1.858227848101266, "progress_pct": 30.97, "epoch_pct": 30.97, "eta": "39:31:14", "max_grad_norm": 1.0, "loss": 0.7040913105010986, "grad_norm": 0.47801393270492554, "learning_rate": 0.0001708040113687983}
-{"ts": "2025-12-27T12:01:18", "event": "train_log", "step": 4406, "epoch": 1.859071729957806, "progress_pct": 30.98, "epoch_pct": 30.98, "eta": "39:30:15", "max_grad_norm": 1.0, "loss": 0.7834659218788147, "grad_norm": 0.47457239031791687, "learning_rate": 0.00017077008628803436}
-{"ts": "2025-12-27T12:01:33", "event": "train_log", "step": 4408, "epoch": 1.8599156118143458, "progress_pct": 31.0, "epoch_pct": 31.0, "eta": "39:29:14", "max_grad_norm": 1.0, "loss": 0.7027983665466309, "grad_norm": 0.41362807154655457, "learning_rate": 0.00017073614488197065}
-{"ts": "2025-12-27T12:01:47", "event": "train_log", "step": 4410, "epoch": 1.8607594936708862, "progress_pct": 31.01, "epoch_pct": 31.01, "eta": "39:28:14", "max_grad_norm": 1.0, "loss": 0.7143591642379761, "grad_norm": 0.457927942276001, "learning_rate": 0.0001707021871584368}
-{"ts": "2025-12-27T12:02:03", "event": "train_log", "step": 4412, "epoch": 1.8616033755274262, "progress_pct": 31.03, "epoch_pct": 31.03, "eta": "39:27:16", "max_grad_norm": 1.0, "loss": 0.7328225374221802, "grad_norm": 0.42931967973709106, "learning_rate": 0.00017066821312526625}
-{"ts": "2025-12-27T12:02:18", "event": "train_log", "step": 4414, "epoch": 1.862447257383966, "progress_pct": 31.04, "epoch_pct": 31.04, "eta": "39:26:16", "max_grad_norm": 1.0, "loss": 0.7199252843856812, "grad_norm": 0.3821638524532318, "learning_rate": 0.00017063422279029616}
-{"ts": "2025-12-27T12:02:35", "event": "train_log", "step": 4416, "epoch": 1.8632911392405065, "progress_pct": 31.05, "epoch_pct": 31.05, "eta": "39:25:19", "max_grad_norm": 1.0, "loss": 0.7345157265663147, "grad_norm": 0.3954671621322632, "learning_rate": 0.00017060021616136742}
-{"ts": "2025-12-27T12:02:51", "event": "train_log", "step": 4418, "epoch": 1.8641350210970464, "progress_pct": 31.07, "epoch_pct": 31.07, "eta": "39:24:21", "max_grad_norm": 1.0, "loss": 0.587895393371582, "grad_norm": 0.38824960589408875, "learning_rate": 0.0001705661932463247}
-{"ts": "2025-12-27T12:03:06", "event": "train_log", "step": 4420, "epoch": 1.8649789029535864, "progress_pct": 31.08, "epoch_pct": 31.08, "eta": "39:23:22", "max_grad_norm": 1.0, "loss": 0.7227945327758789, "grad_norm": 0.510923445224762, "learning_rate": 0.00017053215405301648}
-{"ts": "2025-12-27T12:03:23", "event": "train_log", "step": 4422, "epoch": 1.8658227848101265, "progress_pct": 31.1, "epoch_pct": 31.1, "eta": "39:22:27", "max_grad_norm": 1.0, "loss": 0.6605637073516846, "grad_norm": 0.38688936829566956, "learning_rate": 0.0001704980985892949}
-{"ts": "2025-12-27T12:03:37", "event": "train_log", "step": 4424, "epoch": 1.8666666666666667, "progress_pct": 31.11, "epoch_pct": 31.11, "eta": "39:21:24", "max_grad_norm": 1.0, "loss": 0.7581667304039001, "grad_norm": 0.4886745512485504, "learning_rate": 0.0001704640268630159}
-{"ts": "2025-12-27T12:03:53", "event": "train_log", "step": 4426, "epoch": 1.8675105485232066, "progress_pct": 31.13, "epoch_pct": 31.13, "eta": "39:20:27", "max_grad_norm": 1.0, "loss": 0.7051677107810974, "grad_norm": 0.4214446246623993, "learning_rate": 0.0001704299388820392}
-{"ts": "2025-12-27T12:04:09", "event": "train_log", "step": 4428, "epoch": 1.8683544303797468, "progress_pct": 31.14, "epoch_pct": 31.14, "eta": "39:19:29", "max_grad_norm": 1.0, "loss": 0.6489346623420715, "grad_norm": 0.4189293384552002, "learning_rate": 0.00017039583465422824}
-{"ts": "2025-12-27T12:04:24", "event": "train_log", "step": 4430, "epoch": 1.869198312236287, "progress_pct": 31.15, "epoch_pct": 31.15, "eta": "39:18:30", "max_grad_norm": 1.0, "loss": 0.6896629929542542, "grad_norm": 0.4264903962612152, "learning_rate": 0.0001703617141874502}
-{"ts": "2025-12-27T12:04:40", "event": "train_log", "step": 4432, "epoch": 1.870042194092827, "progress_pct": 31.17, "epoch_pct": 31.17, "eta": "39:17:32", "max_grad_norm": 1.0, "loss": 0.7468283772468567, "grad_norm": 0.5351413488388062, "learning_rate": 0.00017032757748957603}
-{"ts": "2025-12-27T12:04:56", "event": "train_log", "step": 4434, "epoch": 1.870886075949367, "progress_pct": 31.18, "epoch_pct": 31.18, "eta": "39:16:35", "max_grad_norm": 1.0, "loss": 0.6029976010322571, "grad_norm": 0.40163540840148926, "learning_rate": 0.00017029342456848035}
-{"ts": "2025-12-27T12:05:11", "event": "train_log", "step": 4436, "epoch": 1.8717299578059072, "progress_pct": 31.2, "epoch_pct": 31.2, "eta": "39:15:37", "max_grad_norm": 1.0, "loss": 0.6891162991523743, "grad_norm": 0.3786795139312744, "learning_rate": 0.0001702592554320417}
-{"ts": "2025-12-27T12:05:27", "event": "train_log", "step": 4438, "epoch": 1.8725738396624472, "progress_pct": 31.21, "epoch_pct": 31.21, "eta": "39:14:37", "max_grad_norm": 1.0, "loss": 0.6189853549003601, "grad_norm": 0.4266849458217621, "learning_rate": 0.00017022507008814214}
-{"ts": "2025-12-27T12:05:41", "event": "train_log", "step": 4440, "epoch": 1.8734177215189873, "progress_pct": 31.22, "epoch_pct": 31.22, "eta": "39:13:36", "max_grad_norm": 1.0, "loss": 0.6858769655227661, "grad_norm": 0.4076935052871704, "learning_rate": 0.0001701908685446676}
-{"ts": "2025-12-27T12:05:57", "event": "train_log", "step": 4442, "epoch": 1.8742616033755275, "progress_pct": 31.24, "epoch_pct": 31.24, "eta": "39:12:39", "max_grad_norm": 1.0, "loss": 0.6650485396385193, "grad_norm": 0.4209558665752411, "learning_rate": 0.00017015665080950774}
-{"ts": "2025-12-27T12:06:14", "event": "train_log", "step": 4444, "epoch": 1.8751054852320674, "progress_pct": 31.25, "epoch_pct": 31.25, "eta": "39:11:44", "max_grad_norm": 1.0, "loss": 0.6887878179550171, "grad_norm": 0.4114036560058594, "learning_rate": 0.0001701224168905559}
-{"ts": "2025-12-27T12:06:30", "event": "train_log", "step": 4446, "epoch": 1.8759493670886076, "progress_pct": 31.27, "epoch_pct": 31.27, "eta": "39:10:46", "max_grad_norm": 1.0, "loss": 0.6950712203979492, "grad_norm": 0.34596455097198486, "learning_rate": 0.00017008816679570926}
-{"ts": "2025-12-27T12:06:46", "event": "train_log", "step": 4448, "epoch": 1.8767932489451478, "progress_pct": 31.28, "epoch_pct": 31.28, "eta": "39:09:50", "max_grad_norm": 1.0, "loss": 0.7360581159591675, "grad_norm": 0.45132747292518616, "learning_rate": 0.0001700539005328686}
-{"ts": "2025-12-27T12:07:03", "event": "train_log", "step": 4450, "epoch": 1.8776371308016877, "progress_pct": 31.29, "epoch_pct": 31.29, "eta": "39:08:55", "max_grad_norm": 1.0, "loss": 0.6672278046607971, "grad_norm": 0.4258243441581726, "learning_rate": 0.00017001961810993846}
-{"ts": "2025-12-27T12:07:18", "event": "train_log", "step": 4452, "epoch": 1.8784810126582279, "progress_pct": 31.31, "epoch_pct": 31.31, "eta": "39:07:55", "max_grad_norm": 1.0, "loss": 0.6740089654922485, "grad_norm": 0.39144474267959595, "learning_rate": 0.0001699853195348272}
-{"ts": "2025-12-27T12:07:33", "event": "train_log", "step": 4454, "epoch": 1.879324894514768, "progress_pct": 31.32, "epoch_pct": 31.32, "eta": "39:06:58", "max_grad_norm": 1.0, "loss": 0.7747141122817993, "grad_norm": 0.42183035612106323, "learning_rate": 0.00016995100481544681}
-{"ts": "2025-12-27T12:07:50", "event": "train_log", "step": 4456, "epoch": 1.880168776371308, "progress_pct": 31.34, "epoch_pct": 31.34, "eta": "39:06:02", "max_grad_norm": 1.0, "loss": 0.7189701199531555, "grad_norm": 0.4110005795955658, "learning_rate": 0.00016991667395971303}
-{"ts": "2025-12-27T12:08:06", "event": "train_log", "step": 4458, "epoch": 1.8810126582278481, "progress_pct": 31.35, "epoch_pct": 31.35, "eta": "39:05:05", "max_grad_norm": 1.0, "loss": 0.6880105137825012, "grad_norm": 0.4073067307472229, "learning_rate": 0.00016988232697554538}
-{"ts": "2025-12-27T12:08:22", "event": "train_log", "step": 4460, "epoch": 1.8818565400843883, "progress_pct": 31.36, "epoch_pct": 31.36, "eta": "39:04:07", "max_grad_norm": 1.0, "loss": 0.6994736790657043, "grad_norm": 0.467443585395813, "learning_rate": 0.00016984796387086698}
-{"ts": "2025-12-27T12:08:37", "event": "train_log", "step": 4462, "epoch": 1.8827004219409282, "progress_pct": 31.38, "epoch_pct": 31.38, "eta": "39:03:08", "max_grad_norm": 1.0, "loss": 0.7389267683029175, "grad_norm": 0.4769018292427063, "learning_rate": 0.00016981358465360482}
-{"ts": "2025-12-27T12:08:53", "event": "train_log", "step": 4464, "epoch": 1.8835443037974684, "progress_pct": 31.39, "epoch_pct": 31.39, "eta": "39:02:13", "max_grad_norm": 1.0, "loss": 0.6375740170478821, "grad_norm": 0.3834097981452942, "learning_rate": 0.00016977918933168938}
-{"ts": "2025-12-27T12:09:09", "event": "train_log", "step": 4466, "epoch": 1.8843881856540086, "progress_pct": 31.41, "epoch_pct": 31.41, "eta": "39:01:15", "max_grad_norm": 1.0, "loss": 0.6845629811286926, "grad_norm": 0.44548940658569336, "learning_rate": 0.00016974477791305517}
-{"ts": "2025-12-27T12:09:24", "event": "train_log", "step": 4468, "epoch": 1.8852320675105485, "progress_pct": 31.42, "epoch_pct": 31.42, "eta": "39:00:16", "max_grad_norm": 1.0, "loss": 0.7307721376419067, "grad_norm": 0.39344266057014465, "learning_rate": 0.00016971035040564016}
-{"ts": "2025-12-27T12:09:40", "event": "train_log", "step": 4470, "epoch": 1.8860759493670884, "progress_pct": 31.43, "epoch_pct": 31.43, "eta": "38:59:20", "max_grad_norm": 1.0, "loss": 0.6733962297439575, "grad_norm": 0.37901216745376587, "learning_rate": 0.0001696759068173861}
-{"ts": "2025-12-27T12:09:55", "event": "train_log", "step": 4472, "epoch": 1.8869198312236288, "progress_pct": 31.45, "epoch_pct": 31.45, "eta": "38:58:21", "max_grad_norm": 1.0, "loss": 0.7294619679450989, "grad_norm": 0.44465333223342896, "learning_rate": 0.00016964144715623852}
-{"ts": "2025-12-27T12:10:11", "event": "train_log", "step": 4474, "epoch": 1.8877637130801688, "progress_pct": 31.46, "epoch_pct": 31.46, "eta": "38:57:24", "max_grad_norm": 1.0, "loss": 0.6537288427352905, "grad_norm": 0.39566636085510254, "learning_rate": 0.00016960697143014657}
-{"ts": "2025-12-27T12:10:27", "event": "train_log", "step": 4476, "epoch": 1.8886075949367087, "progress_pct": 31.48, "epoch_pct": 31.48, "eta": "38:56:28", "max_grad_norm": 1.0, "loss": 0.623903751373291, "grad_norm": 0.4047028124332428, "learning_rate": 0.0001695724796470631}
-{"ts": "2025-12-27T12:10:42", "event": "train_log", "step": 4478, "epoch": 1.889451476793249, "progress_pct": 31.49, "epoch_pct": 31.49, "eta": "38:55:29", "max_grad_norm": 1.0, "loss": 0.661283552646637, "grad_norm": 0.4559679329395294, "learning_rate": 0.00016953797181494475}
-{"ts": "2025-12-27T12:10:59", "event": "train_log", "step": 4480, "epoch": 1.890295358649789, "progress_pct": 31.5, "epoch_pct": 31.5, "eta": "38:54:35", "max_grad_norm": 1.0, "loss": 0.6587702035903931, "grad_norm": 0.3980371952056885, "learning_rate": 0.00016950344794175183}
-{"ts": "2025-12-27T12:11:15", "event": "train_log", "step": 4482, "epoch": 1.891139240506329, "progress_pct": 31.52, "epoch_pct": 31.52, "eta": "38:53:38", "max_grad_norm": 1.0, "loss": 0.7898983955383301, "grad_norm": 0.41418227553367615, "learning_rate": 0.0001694689080354483}
-{"ts": "2025-12-27T12:11:30", "event": "train_log", "step": 4484, "epoch": 1.8919831223628694, "progress_pct": 31.53, "epoch_pct": 31.53, "eta": "38:52:39", "max_grad_norm": 1.0, "loss": 0.6213424205780029, "grad_norm": 0.41184720396995544, "learning_rate": 0.00016943435210400184}
-{"ts": "2025-12-27T12:11:46", "event": "train_log", "step": 4486, "epoch": 1.8928270042194093, "progress_pct": 31.55, "epoch_pct": 31.55, "eta": "38:51:43", "max_grad_norm": 1.0, "loss": 0.6624190807342529, "grad_norm": 0.39218711853027344, "learning_rate": 0.00016939978015538388}
-{"ts": "2025-12-27T12:12:02", "event": "train_log", "step": 4488, "epoch": 1.8936708860759492, "progress_pct": 31.56, "epoch_pct": 31.56, "eta": "38:50:47", "max_grad_norm": 1.0, "loss": 0.7063044309616089, "grad_norm": 0.4875730872154236, "learning_rate": 0.0001693651921975695}
-{"ts": "2025-12-27T12:12:18", "event": "train_log", "step": 4490, "epoch": 1.8945147679324894, "progress_pct": 31.58, "epoch_pct": 31.58, "eta": "38:49:50", "max_grad_norm": 1.0, "loss": 0.6471660137176514, "grad_norm": 0.38058432936668396, "learning_rate": 0.00016933058823853748}
-{"ts": "2025-12-27T12:12:32", "event": "train_log", "step": 4492, "epoch": 1.8953586497890296, "progress_pct": 31.59, "epoch_pct": 31.59, "eta": "38:48:51", "max_grad_norm": 1.0, "loss": 0.7694545388221741, "grad_norm": 0.5368654131889343, "learning_rate": 0.0001692959682862702}
-{"ts": "2025-12-27T12:12:47", "event": "train_log", "step": 4494, "epoch": 1.8962025316455695, "progress_pct": 31.6, "epoch_pct": 31.6, "eta": "38:47:52", "max_grad_norm": 1.0, "loss": 0.700016438961029, "grad_norm": 0.41736599802970886, "learning_rate": 0.00016926133234875396}
-{"ts": "2025-12-27T12:13:02", "event": "train_log", "step": 4496, "epoch": 1.8970464135021097, "progress_pct": 31.62, "epoch_pct": 31.62, "eta": "38:46:53", "max_grad_norm": 1.0, "loss": 0.6926955580711365, "grad_norm": 0.4086865484714508, "learning_rate": 0.0001692266804339785}
-{"ts": "2025-12-27T12:13:17", "event": "train_log", "step": 4498, "epoch": 1.8978902953586498, "progress_pct": 31.63, "epoch_pct": 31.63, "eta": "38:45:55", "max_grad_norm": 1.0, "loss": 0.6776167154312134, "grad_norm": 0.447516530752182, "learning_rate": 0.00016919201254993738}
-{"ts": "2025-12-27T12:13:33", "event": "train_log", "step": 4500, "epoch": 1.8987341772151898, "progress_pct": 31.65, "epoch_pct": 31.65, "eta": "38:44:58", "max_grad_norm": 1.0, "loss": 0.6860454678535461, "grad_norm": 0.43951377272605896, "learning_rate": 0.00016915732870462783}
-{"ts": "2025-12-27T12:24:47", "event": "train_log", "step": 4500, "epoch": 1.8987341772151898, "progress_pct": 31.65, "epoch_pct": 31.65, "eta": "39:09:15", "max_grad_norm": 1.0, "eval_loss": 0.7600579857826233, "eval_runtime": 674.2593, "eval_samples_per_second": 3.125, "eval_steps_per_second": 3.125}
-{"ts": "2025-12-27T12:25:04", "event": "train_log", "step": 4502, "epoch": 1.89957805907173, "progress_pct": 31.66, "epoch_pct": 31.66, "eta": "39:08:19", "max_grad_norm": 1.0, "loss": 0.6525024175643921, "grad_norm": 0.380329966545105, "learning_rate": 0.00016912262890605076}
-{"ts": "2025-12-27T12:25:19", "event": "train_log", "step": 4504, "epoch": 1.90042194092827, "progress_pct": 31.67, "epoch_pct": 31.67, "eta": "39:07:21", "max_grad_norm": 1.0, "loss": 0.6473777294158936, "grad_norm": 0.3461032807826996, "learning_rate": 0.00016908791316221073}
-{"ts": "2025-12-27T12:25:34", "event": "train_log", "step": 4506, "epoch": 1.90126582278481, "progress_pct": 31.69, "epoch_pct": 31.69, "eta": "39:06:21", "max_grad_norm": 1.0, "loss": 0.760007381439209, "grad_norm": 0.47325965762138367, "learning_rate": 0.00016905318148111595}
-{"ts": "2025-12-27T12:25:50", "event": "train_log", "step": 4508, "epoch": 1.9021097046413502, "progress_pct": 31.7, "epoch_pct": 31.7, "eta": "39:05:24", "max_grad_norm": 1.0, "loss": 0.659562349319458, "grad_norm": 0.39158931374549866, "learning_rate": 0.00016901843387077844}
-{"ts": "2025-12-27T12:26:05", "event": "train_log", "step": 4510, "epoch": 1.9029535864978904, "progress_pct": 31.72, "epoch_pct": 31.72, "eta": "39:04:25", "max_grad_norm": 1.0, "loss": 0.5873214602470398, "grad_norm": 0.36785584688186646, "learning_rate": 0.0001689836703392137}
-{"ts": "2025-12-27T12:26:21", "event": "train_log", "step": 4512, "epoch": 1.9037974683544303, "progress_pct": 31.73, "epoch_pct": 31.73, "eta": "39:03:29", "max_grad_norm": 1.0, "loss": 0.6236514449119568, "grad_norm": 0.3843834102153778, "learning_rate": 0.00016894889089444115}
-{"ts": "2025-12-27T12:26:37", "event": "train_log", "step": 4514, "epoch": 1.9046413502109705, "progress_pct": 31.74, "epoch_pct": 31.74, "eta": "39:02:31", "max_grad_norm": 1.0, "loss": 0.7129080891609192, "grad_norm": 0.41675102710723877, "learning_rate": 0.0001689140955444836}
-{"ts": "2025-12-27T12:26:52", "event": "train_log", "step": 4516, "epoch": 1.9054852320675106, "progress_pct": 31.76, "epoch_pct": 31.76, "eta": "39:01:32", "max_grad_norm": 1.0, "loss": 0.7348461747169495, "grad_norm": 0.46025362610816956, "learning_rate": 0.00016887928429736775}
-{"ts": "2025-12-27T12:27:08", "event": "train_log", "step": 4518, "epoch": 1.9063291139240506, "progress_pct": 31.77, "epoch_pct": 31.77, "eta": "39:00:34", "max_grad_norm": 1.0, "loss": 0.6797979474067688, "grad_norm": 0.43589887022972107, "learning_rate": 0.00016884445716112387}
-{"ts": "2025-12-27T12:27:23", "event": "train_log", "step": 4520, "epoch": 1.9071729957805907, "progress_pct": 31.79, "epoch_pct": 31.79, "eta": "38:59:36", "max_grad_norm": 1.0, "loss": 0.6754241585731506, "grad_norm": 0.4301862120628357, "learning_rate": 0.0001688096141437859}
-{"ts": "2025-12-27T12:27:38", "event": "train_log", "step": 4522, "epoch": 1.908016877637131, "progress_pct": 31.8, "epoch_pct": 31.8, "eta": "38:58:39", "max_grad_norm": 1.0, "loss": 0.681866466999054, "grad_norm": 0.41446763277053833, "learning_rate": 0.00016877475525339146}
-{"ts": "2025-12-27T12:27:56", "event": "train_log", "step": 4524, "epoch": 1.9088607594936708, "progress_pct": 31.81, "epoch_pct": 31.81, "eta": "38:57:45", "max_grad_norm": 1.0, "loss": 0.6626620888710022, "grad_norm": 0.4051108658313751, "learning_rate": 0.0001687398804979818}
-{"ts": "2025-12-27T12:28:11", "event": "train_log", "step": 4526, "epoch": 1.909704641350211, "progress_pct": 31.83, "epoch_pct": 31.83, "eta": "38:56:47", "max_grad_norm": 1.0, "loss": 0.6753385066986084, "grad_norm": 0.3896785080432892, "learning_rate": 0.00016870498988560192}
-{"ts": "2025-12-27T12:28:28", "event": "train_log", "step": 4528, "epoch": 1.9105485232067512, "progress_pct": 31.84, "epoch_pct": 31.84, "eta": "38:55:51", "max_grad_norm": 1.0, "loss": 0.6971913576126099, "grad_norm": 0.4307839274406433, "learning_rate": 0.00016867008342430037}
-{"ts": "2025-12-27T12:28:44", "event": "train_log", "step": 4530, "epoch": 1.9113924050632911, "progress_pct": 31.86, "epoch_pct": 31.86, "eta": "38:54:56", "max_grad_norm": 1.0, "loss": 0.7674229145050049, "grad_norm": 0.4120950698852539, "learning_rate": 0.0001686351611221294}
-{"ts": "2025-12-27T12:29:00", "event": "train_log", "step": 4532, "epoch": 1.9122362869198313, "progress_pct": 31.87, "epoch_pct": 31.87, "eta": "38:54:00", "max_grad_norm": 1.0, "loss": 0.7074664235115051, "grad_norm": 0.4321785569190979, "learning_rate": 0.00016860022298714492}
-{"ts": "2025-12-27T12:29:16", "event": "train_log", "step": 4534, "epoch": 1.9130801687763714, "progress_pct": 31.88, "epoch_pct": 31.88, "eta": "38:53:04", "max_grad_norm": 1.0, "loss": 0.6178744435310364, "grad_norm": 0.38313060998916626, "learning_rate": 0.00016856526902740652}
-{"ts": "2025-12-27T12:29:32", "event": "train_log", "step": 4536, "epoch": 1.9139240506329114, "progress_pct": 31.9, "epoch_pct": 31.9, "eta": "38:52:05", "max_grad_norm": 1.0, "loss": 0.7168449759483337, "grad_norm": 0.3940589129924774, "learning_rate": 0.0001685302992509773}
-{"ts": "2025-12-27T12:29:48", "event": "train_log", "step": 4538, "epoch": 1.9147679324894513, "progress_pct": 31.91, "epoch_pct": 31.91, "eta": "38:51:10", "max_grad_norm": 1.0, "loss": 0.6892635226249695, "grad_norm": 0.3719513416290283, "learning_rate": 0.0001684953136659243}
-{"ts": "2025-12-27T12:30:04", "event": "train_log", "step": 4540, "epoch": 1.9156118143459917, "progress_pct": 31.93, "epoch_pct": 31.93, "eta": "38:50:12", "max_grad_norm": 1.0, "loss": 0.7352524399757385, "grad_norm": 0.40150535106658936, "learning_rate": 0.00016846031228031784}
-{"ts": "2025-12-27T12:30:19", "event": "train_log", "step": 4542, "epoch": 1.9164556962025316, "progress_pct": 31.94, "epoch_pct": 31.94, "eta": "38:49:16", "max_grad_norm": 1.0, "loss": 0.6469122767448425, "grad_norm": 0.4212523102760315, "learning_rate": 0.00016842529510223213}
-{"ts": "2025-12-27T12:30:34", "event": "train_log", "step": 4544, "epoch": 1.9172995780590716, "progress_pct": 31.95, "epoch_pct": 31.95, "eta": "38:48:17", "max_grad_norm": 1.0, "loss": 0.6883940696716309, "grad_norm": 0.45365604758262634, "learning_rate": 0.00016839026213974503}
-{"ts": "2025-12-27T12:30:50", "event": "train_log", "step": 4546, "epoch": 1.918143459915612, "progress_pct": 31.97, "epoch_pct": 31.97, "eta": "38:47:20", "max_grad_norm": 1.0, "loss": 0.7378416657447815, "grad_norm": 0.436541885137558, "learning_rate": 0.00016835521340093787}
-{"ts": "2025-12-27T12:31:05", "event": "train_log", "step": 4548, "epoch": 1.918987341772152, "progress_pct": 31.98, "epoch_pct": 31.98, "eta": "38:46:23", "max_grad_norm": 1.0, "loss": 0.7432116270065308, "grad_norm": 0.41461536288261414, "learning_rate": 0.0001683201488938958}
-{"ts": "2025-12-27T12:31:21", "event": "train_log", "step": 4550, "epoch": 1.9198312236286919, "progress_pct": 32.0, "epoch_pct": 32.0, "eta": "38:45:26", "max_grad_norm": 1.0, "loss": 0.6801432967185974, "grad_norm": 0.40218585729599, "learning_rate": 0.00016828506862670746}
-{"ts": "2025-12-27T12:31:36", "event": "train_log", "step": 4552, "epoch": 1.920675105485232, "progress_pct": 32.01, "epoch_pct": 32.01, "eta": "38:44:28", "max_grad_norm": 1.0, "loss": 0.6835547685623169, "grad_norm": 0.3994768559932709, "learning_rate": 0.00016824997260746525}
-{"ts": "2025-12-27T12:31:52", "event": "train_log", "step": 4554, "epoch": 1.9215189873417722, "progress_pct": 32.03, "epoch_pct": 32.03, "eta": "38:43:32", "max_grad_norm": 1.0, "loss": 0.7723629474639893, "grad_norm": 0.460328072309494, "learning_rate": 0.00016821486084426512}
-{"ts": "2025-12-27T12:32:08", "event": "train_log", "step": 4556, "epoch": 1.9223628691983121, "progress_pct": 32.04, "epoch_pct": 32.04, "eta": "38:42:35", "max_grad_norm": 1.0, "loss": 0.7513449192047119, "grad_norm": 0.4739786386489868, "learning_rate": 0.00016817973334520668}
-{"ts": "2025-12-27T12:32:23", "event": "train_log", "step": 4558, "epoch": 1.9232067510548523, "progress_pct": 32.05, "epoch_pct": 32.05, "eta": "38:41:36", "max_grad_norm": 1.0, "loss": 0.7000700235366821, "grad_norm": 0.46618419885635376, "learning_rate": 0.00016814459011839315}
-{"ts": "2025-12-27T12:32:39", "event": "train_log", "step": 4560, "epoch": 1.9240506329113924, "progress_pct": 32.07, "epoch_pct": 32.07, "eta": "38:40:40", "max_grad_norm": 1.0, "loss": 0.6381427049636841, "grad_norm": 0.4187009632587433, "learning_rate": 0.00016810943117193146}
-{"ts": "2025-12-27T12:32:54", "event": "train_log", "step": 4562, "epoch": 1.9248945147679324, "progress_pct": 32.08, "epoch_pct": 32.08, "eta": "38:39:42", "max_grad_norm": 1.0, "loss": 0.7823911309242249, "grad_norm": 0.5057410597801208, "learning_rate": 0.00016807425651393207}
-{"ts": "2025-12-27T12:33:09", "event": "train_log", "step": 4564, "epoch": 1.9257383966244725, "progress_pct": 32.1, "epoch_pct": 32.1, "eta": "38:38:46", "max_grad_norm": 1.0, "loss": 0.7210549712181091, "grad_norm": 0.4235171973705292, "learning_rate": 0.00016803906615250907}
-{"ts": "2025-12-27T12:33:25", "event": "train_log", "step": 4566, "epoch": 1.9265822784810127, "progress_pct": 32.11, "epoch_pct": 32.11, "eta": "38:37:48", "max_grad_norm": 1.0, "loss": 0.794435441493988, "grad_norm": 0.45755431056022644, "learning_rate": 0.00016800386009578025}
-{"ts": "2025-12-27T12:33:40", "event": "train_log", "step": 4568, "epoch": 1.9274261603375527, "progress_pct": 32.12, "epoch_pct": 32.12, "eta": "38:36:51", "max_grad_norm": 1.0, "loss": 0.6490750312805176, "grad_norm": 0.4225042760372162, "learning_rate": 0.0001679686383518669}
-{"ts": "2025-12-27T12:33:56", "event": "train_log", "step": 4570, "epoch": 1.9282700421940928, "progress_pct": 32.14, "epoch_pct": 32.14, "eta": "38:35:55", "max_grad_norm": 1.0, "loss": 0.6976916790008545, "grad_norm": 0.41081616282463074, "learning_rate": 0.00016793340092889408}
-{"ts": "2025-12-27T12:34:12", "event": "train_log", "step": 4572, "epoch": 1.929113924050633, "progress_pct": 32.15, "epoch_pct": 32.15, "eta": "38:34:59", "max_grad_norm": 1.0, "loss": 0.6559295058250427, "grad_norm": 0.42354175448417664, "learning_rate": 0.00016789814783499033}
-{"ts": "2025-12-27T12:34:28", "event": "train_log", "step": 4574, "epoch": 1.929957805907173, "progress_pct": 32.17, "epoch_pct": 32.17, "eta": "38:34:02", "max_grad_norm": 1.0, "loss": 0.7900391817092896, "grad_norm": 0.39702117443084717, "learning_rate": 0.0001678628790782879}
-{"ts": "2025-12-27T12:34:42", "event": "train_log", "step": 4576, "epoch": 1.930801687763713, "progress_pct": 32.18, "epoch_pct": 32.18, "eta": "38:33:03", "max_grad_norm": 1.0, "loss": 0.7020596265792847, "grad_norm": 0.4400629997253418, "learning_rate": 0.00016782759466692256}
-{"ts": "2025-12-27T12:34:57", "event": "train_log", "step": 4578, "epoch": 1.9316455696202532, "progress_pct": 32.19, "epoch_pct": 32.19, "eta": "38:32:05", "max_grad_norm": 1.0, "loss": 0.7107458710670471, "grad_norm": 0.42563396692276, "learning_rate": 0.00016779229460903383}
-{"ts": "2025-12-27T12:35:13", "event": "train_log", "step": 4580, "epoch": 1.9324894514767932, "progress_pct": 32.21, "epoch_pct": 32.21, "eta": "38:31:10", "max_grad_norm": 1.0, "loss": 0.58088618516922, "grad_norm": 0.40650051832199097, "learning_rate": 0.0001677569789127647}
-{"ts": "2025-12-27T12:35:30", "event": "train_log", "step": 4582, "epoch": 1.9333333333333333, "progress_pct": 32.22, "epoch_pct": 32.22, "eta": "38:30:16", "max_grad_norm": 1.0, "loss": 0.6815688610076904, "grad_norm": 0.42461681365966797, "learning_rate": 0.00016772164758626184}
-{"ts": "2025-12-27T12:35:46", "event": "train_log", "step": 4584, "epoch": 1.9341772151898735, "progress_pct": 32.24, "epoch_pct": 32.24, "eta": "38:29:20", "max_grad_norm": 1.0, "loss": 0.6617820262908936, "grad_norm": 0.4248030483722687, "learning_rate": 0.0001676863006376755}
-{"ts": "2025-12-27T12:36:01", "event": "train_log", "step": 4586, "epoch": 1.9350210970464135, "progress_pct": 32.25, "epoch_pct": 32.25, "eta": "38:28:23", "max_grad_norm": 1.0, "loss": 0.7462296485900879, "grad_norm": 0.4336024522781372, "learning_rate": 0.0001676509380751595}
-{"ts": "2025-12-27T12:36:18", "event": "train_log", "step": 4588, "epoch": 1.9358649789029536, "progress_pct": 32.26, "epoch_pct": 32.26, "eta": "38:27:29", "max_grad_norm": 1.0, "loss": 0.7801896333694458, "grad_norm": 0.42542141675949097, "learning_rate": 0.00016761555990687136}
-{"ts": "2025-12-27T12:36:33", "event": "train_log", "step": 4590, "epoch": 1.9367088607594938, "progress_pct": 32.28, "epoch_pct": 32.28, "eta": "38:26:32", "max_grad_norm": 1.0, "loss": 0.7308001518249512, "grad_norm": 0.41240575909614563, "learning_rate": 0.00016758016614097217}
-{"ts": "2025-12-27T12:36:48", "event": "train_log", "step": 4592, "epoch": 1.9375527426160337, "progress_pct": 32.29, "epoch_pct": 32.29, "eta": "38:25:35", "max_grad_norm": 1.0, "loss": 0.7126680016517639, "grad_norm": 0.3811012804508209, "learning_rate": 0.00016754475678562654}
-{"ts": "2025-12-27T12:37:04", "event": "train_log", "step": 4594, "epoch": 1.9383966244725739, "progress_pct": 32.31, "epoch_pct": 32.31, "eta": "38:24:40", "max_grad_norm": 1.0, "loss": 0.679752767086029, "grad_norm": 0.4859951436519623, "learning_rate": 0.00016750933184900272}
-{"ts": "2025-12-27T12:37:20", "event": "train_log", "step": 4596, "epoch": 1.939240506329114, "progress_pct": 32.32, "epoch_pct": 32.32, "eta": "38:23:43", "max_grad_norm": 1.0, "loss": 0.6077587604522705, "grad_norm": 0.36403799057006836, "learning_rate": 0.00016747389133927261}
-{"ts": "2025-12-27T12:37:36", "event": "train_log", "step": 4598, "epoch": 1.940084388185654, "progress_pct": 32.33, "epoch_pct": 32.33, "eta": "38:22:49", "max_grad_norm": 1.0, "loss": 0.6919949650764465, "grad_norm": 0.3960701525211334, "learning_rate": 0.00016743843526461158}
-{"ts": "2025-12-27T12:37:51", "event": "train_log", "step": 4600, "epoch": 1.9409282700421941, "progress_pct": 32.35, "epoch_pct": 32.35, "eta": "38:21:52", "max_grad_norm": 1.0, "loss": 0.728607177734375, "grad_norm": 0.4058634042739868, "learning_rate": 0.00016740296363319877}
-{"ts": "2025-12-27T12:49:10", "event": "train_log", "step": 4600, "epoch": 1.9409282700421941, "progress_pct": 32.35, "epoch_pct": 32.35, "eta": "38:45:32", "max_grad_norm": 1.0, "eval_loss": 0.7585541009902954, "eval_runtime": 679.0866, "eval_samples_per_second": 3.103, "eval_steps_per_second": 3.103}
-{"ts": "2025-12-27T12:49:26", "event": "train_log", "step": 4602, "epoch": 1.9417721518987343, "progress_pct": 32.36, "epoch_pct": 32.36, "eta": "38:44:34", "max_grad_norm": 1.0, "loss": 0.669603168964386, "grad_norm": 0.45107272267341614, "learning_rate": 0.00016736747645321672}
-{"ts": "2025-12-27T12:49:42", "event": "train_log", "step": 4604, "epoch": 1.9426160337552743, "progress_pct": 32.38, "epoch_pct": 32.38, "eta": "38:43:38", "max_grad_norm": 1.0, "loss": 0.6975913643836975, "grad_norm": 0.4244096577167511, "learning_rate": 0.00016733197373285165}
-{"ts": "2025-12-27T12:49:58", "event": "train_log", "step": 4606, "epoch": 1.9434599156118142, "progress_pct": 32.39, "epoch_pct": 32.39, "eta": "38:42:42", "max_grad_norm": 1.0, "loss": 0.5990989804267883, "grad_norm": 0.37567681074142456, "learning_rate": 0.00016729645548029342}
-{"ts": "2025-12-27T12:50:13", "event": "train_log", "step": 4608, "epoch": 1.9443037974683546, "progress_pct": 32.41, "epoch_pct": 32.41, "eta": "38:41:44", "max_grad_norm": 1.0, "loss": 0.723430871963501, "grad_norm": 0.40256237983703613, "learning_rate": 0.00016726092170373533}
-{"ts": "2025-12-27T12:50:27", "event": "train_log", "step": 4610, "epoch": 1.9451476793248945, "progress_pct": 32.42, "epoch_pct": 32.42, "eta": "38:40:44", "max_grad_norm": 1.0, "loss": 0.7460100650787354, "grad_norm": 0.4884983003139496, "learning_rate": 0.0001672253724113744}
-{"ts": "2025-12-27T12:50:43", "event": "train_log", "step": 4612, "epoch": 1.9459915611814345, "progress_pct": 32.43, "epoch_pct": 32.43, "eta": "38:39:48", "max_grad_norm": 1.0, "loss": 0.5577017664909363, "grad_norm": 0.3629630208015442, "learning_rate": 0.0001671898076114111}
-{"ts": "2025-12-27T12:50:57", "event": "train_log", "step": 4614, "epoch": 1.9468354430379748, "progress_pct": 32.45, "epoch_pct": 32.45, "eta": "38:38:49", "max_grad_norm": 1.0, "loss": 0.7394112944602966, "grad_norm": 0.42751777172088623, "learning_rate": 0.00016715422731204967}
-{"ts": "2025-12-27T12:51:13", "event": "train_log", "step": 4616, "epoch": 1.9476793248945148, "progress_pct": 32.46, "epoch_pct": 32.46, "eta": "38:37:51", "max_grad_norm": 1.0, "loss": 0.5905179381370544, "grad_norm": 0.35809609293937683, "learning_rate": 0.00016711863152149765}
-{"ts": "2025-12-27T12:51:28", "event": "train_log", "step": 4618, "epoch": 1.9485232067510547, "progress_pct": 32.48, "epoch_pct": 32.48, "eta": "38:36:55", "max_grad_norm": 1.0, "loss": 0.7035338878631592, "grad_norm": 0.4111083745956421, "learning_rate": 0.0001670830202479664}
-{"ts": "2025-12-27T12:51:43", "event": "train_log", "step": 4620, "epoch": 1.9493670886075949, "progress_pct": 32.49, "epoch_pct": 32.49, "eta": "38:35:55", "max_grad_norm": 1.0, "loss": 0.7048936486244202, "grad_norm": 0.4530862867832184, "learning_rate": 0.0001670473934996707}
-{"ts": "2025-12-27T12:51:57", "event": "train_log", "step": 4622, "epoch": 1.950210970464135, "progress_pct": 32.5, "epoch_pct": 32.5, "eta": "38:34:57", "max_grad_norm": 1.0, "loss": 0.6594944596290588, "grad_norm": 0.41778260469436646, "learning_rate": 0.00016701175128482903}
-{"ts": "2025-12-27T12:52:12", "event": "train_log", "step": 4624, "epoch": 1.951054852320675, "progress_pct": 32.52, "epoch_pct": 32.52, "eta": "38:33:58", "max_grad_norm": 1.0, "loss": 0.6902912259101868, "grad_norm": 0.40512707829475403, "learning_rate": 0.0001669760936116633}
-{"ts": "2025-12-27T12:52:27", "event": "train_log", "step": 4626, "epoch": 1.9518987341772152, "progress_pct": 32.53, "epoch_pct": 32.53, "eta": "38:33:00", "max_grad_norm": 1.0, "loss": 0.7086893320083618, "grad_norm": 0.4226403832435608, "learning_rate": 0.0001669404204883991}
-{"ts": "2025-12-27T12:52:42", "event": "train_log", "step": 4628, "epoch": 1.9527426160337553, "progress_pct": 32.55, "epoch_pct": 32.55, "eta": "38:32:03", "max_grad_norm": 1.0, "loss": 0.6647822856903076, "grad_norm": 0.397930383682251, "learning_rate": 0.00016690473192326549}
-{"ts": "2025-12-27T12:52:56", "event": "train_log", "step": 4630, "epoch": 1.9535864978902953, "progress_pct": 32.56, "epoch_pct": 32.56, "eta": "38:31:04", "max_grad_norm": 1.0, "loss": 0.747227668762207, "grad_norm": 0.3985617458820343, "learning_rate": 0.00016686902792449515}
-{"ts": "2025-12-27T12:53:11", "event": "train_log", "step": 4632, "epoch": 1.9544303797468354, "progress_pct": 32.57, "epoch_pct": 32.57, "eta": "38:30:05", "max_grad_norm": 1.0, "loss": 0.7526347637176514, "grad_norm": 0.4174083173274994, "learning_rate": 0.00016683330850032432}
-{"ts": "2025-12-27T12:53:26", "event": "train_log", "step": 4634, "epoch": 1.9552742616033756, "progress_pct": 32.59, "epoch_pct": 32.59, "eta": "38:29:06", "max_grad_norm": 1.0, "loss": 0.6674112677574158, "grad_norm": 0.425070583820343, "learning_rate": 0.00016679757365899275}
-{"ts": "2025-12-27T12:53:41", "event": "train_log", "step": 4636, "epoch": 1.9561181434599155, "progress_pct": 32.6, "epoch_pct": 32.6, "eta": "38:28:09", "max_grad_norm": 1.0, "loss": 0.6515055298805237, "grad_norm": 0.4049135148525238, "learning_rate": 0.00016676182340874386}
-{"ts": "2025-12-27T12:53:56", "event": "train_log", "step": 4638, "epoch": 1.9569620253164557, "progress_pct": 32.62, "epoch_pct": 32.62, "eta": "38:27:11", "max_grad_norm": 1.0, "loss": 0.645137369632721, "grad_norm": 0.4312315285205841, "learning_rate": 0.00016672605775782447}
-{"ts": "2025-12-27T12:54:10", "event": "train_log", "step": 4640, "epoch": 1.9578059071729959, "progress_pct": 32.63, "epoch_pct": 32.63, "eta": "38:26:13", "max_grad_norm": 1.0, "loss": 0.6519104838371277, "grad_norm": 0.39540281891822815, "learning_rate": 0.00016669027671448503}
-{"ts": "2025-12-27T12:54:25", "event": "train_log", "step": 4642, "epoch": 1.9586497890295358, "progress_pct": 32.64, "epoch_pct": 32.64, "eta": "38:25:14", "max_grad_norm": 1.0, "loss": 0.6815812587738037, "grad_norm": 0.5028185844421387, "learning_rate": 0.00016665448028697961}
-{"ts": "2025-12-27T12:54:39", "event": "train_log", "step": 4644, "epoch": 1.959493670886076, "progress_pct": 32.66, "epoch_pct": 32.66, "eta": "38:24:16", "max_grad_norm": 1.0, "loss": 0.6713913083076477, "grad_norm": 0.4395635724067688, "learning_rate": 0.00016661866848356567}
-{"ts": "2025-12-27T12:54:55", "event": "train_log", "step": 4646, "epoch": 1.9603375527426161, "progress_pct": 32.67, "epoch_pct": 32.67, "eta": "38:23:20", "max_grad_norm": 1.0, "loss": 0.6989195942878723, "grad_norm": 0.42733073234558105, "learning_rate": 0.00016658284131250436}
-{"ts": "2025-12-27T12:55:10", "event": "train_log", "step": 4648, "epoch": 1.961181434599156, "progress_pct": 32.69, "epoch_pct": 32.69, "eta": "38:22:22", "max_grad_norm": 1.0, "loss": 0.6501366496086121, "grad_norm": 0.41415879130363464, "learning_rate": 0.00016654699878206031}
-{"ts": "2025-12-27T12:55:25", "event": "train_log", "step": 4650, "epoch": 1.9620253164556962, "progress_pct": 32.7, "epoch_pct": 32.7, "eta": "38:21:26", "max_grad_norm": 1.0, "loss": 0.6437955498695374, "grad_norm": 0.39072170853614807, "learning_rate": 0.0001665111409005017}
-{"ts": "2025-12-27T12:55:40", "event": "train_log", "step": 4652, "epoch": 1.9628691983122364, "progress_pct": 32.71, "epoch_pct": 32.71, "eta": "38:20:27", "max_grad_norm": 1.0, "loss": 0.6521314382553101, "grad_norm": 0.41802850365638733, "learning_rate": 0.00016647526767610025}
-{"ts": "2025-12-27T12:55:54", "event": "train_log", "step": 4654, "epoch": 1.9637130801687763, "progress_pct": 32.73, "epoch_pct": 32.73, "eta": "38:19:29", "max_grad_norm": 1.0, "loss": 0.7300742864608765, "grad_norm": 0.41475021839141846, "learning_rate": 0.00016643937911713124}
-{"ts": "2025-12-27T12:56:09", "event": "train_log", "step": 4656, "epoch": 1.9645569620253165, "progress_pct": 32.74, "epoch_pct": 32.74, "eta": "38:18:32", "max_grad_norm": 1.0, "loss": 0.6217485070228577, "grad_norm": 0.41763070225715637, "learning_rate": 0.00016640347523187344}
-{"ts": "2025-12-27T12:56:24", "event": "train_log", "step": 4658, "epoch": 1.9654008438818567, "progress_pct": 32.76, "epoch_pct": 32.76, "eta": "38:17:33", "max_grad_norm": 1.0, "loss": 0.7974472641944885, "grad_norm": 0.4488297402858734, "learning_rate": 0.00016636755602860922}
-{"ts": "2025-12-27T12:56:39", "event": "train_log", "step": 4660, "epoch": 1.9662447257383966, "progress_pct": 32.77, "epoch_pct": 32.77, "eta": "38:16:36", "max_grad_norm": 1.0, "loss": 0.728827714920044, "grad_norm": 0.37688007950782776, "learning_rate": 0.00016633162151562445}
-{"ts": "2025-12-27T12:56:53", "event": "train_log", "step": 4662, "epoch": 1.9670886075949368, "progress_pct": 32.78, "epoch_pct": 32.78, "eta": "38:15:38", "max_grad_norm": 1.0, "loss": 0.7563744783401489, "grad_norm": 0.4636184275150299, "learning_rate": 0.0001662956717012085}
-{"ts": "2025-12-27T12:57:08", "event": "train_log", "step": 4664, "epoch": 1.967932489451477, "progress_pct": 32.8, "epoch_pct": 32.8, "eta": "38:14:41", "max_grad_norm": 1.0, "loss": 0.7408145666122437, "grad_norm": 0.432020902633667, "learning_rate": 0.00016625970659365434}
-{"ts": "2025-12-27T12:57:23", "event": "train_log", "step": 4666, "epoch": 1.9687763713080169, "progress_pct": 32.81, "epoch_pct": 32.81, "eta": "38:13:43", "max_grad_norm": 1.0, "loss": 0.6961510181427002, "grad_norm": 0.4098186790943146, "learning_rate": 0.0001662237262012584}
-{"ts": "2025-12-27T12:57:39", "event": "train_log", "step": 4668, "epoch": 1.9696202531645568, "progress_pct": 32.83, "epoch_pct": 32.83, "eta": "38:12:47", "max_grad_norm": 1.0, "loss": 0.6959825754165649, "grad_norm": 0.44124510884284973, "learning_rate": 0.00016618773053232068}
-{"ts": "2025-12-27T12:57:54", "event": "train_log", "step": 4670, "epoch": 1.9704641350210972, "progress_pct": 32.84, "epoch_pct": 32.84, "eta": "38:11:51", "max_grad_norm": 1.0, "loss": 0.6693721413612366, "grad_norm": 0.3729988634586334, "learning_rate": 0.00016615171959514466}
-{"ts": "2025-12-27T12:58:10", "event": "train_log", "step": 4672, "epoch": 1.9713080168776371, "progress_pct": 32.86, "epoch_pct": 32.86, "eta": "38:10:55", "max_grad_norm": 1.0, "loss": 0.6943060159683228, "grad_norm": 0.4506371021270752, "learning_rate": 0.00016611569339803744}
-{"ts": "2025-12-27T12:58:25", "event": "train_log", "step": 4674, "epoch": 1.972151898734177, "progress_pct": 32.87, "epoch_pct": 32.87, "eta": "38:09:59", "max_grad_norm": 1.0, "loss": 0.6915813684463501, "grad_norm": 0.43713298439979553, "learning_rate": 0.00016607965194930947}
-{"ts": "2025-12-27T12:58:41", "event": "train_log", "step": 4676, "epoch": 1.9729957805907175, "progress_pct": 32.88, "epoch_pct": 32.88, "eta": "38:09:04", "max_grad_norm": 1.0, "loss": 0.7430137991905212, "grad_norm": 0.4375544786453247, "learning_rate": 0.00016604359525727492}
-{"ts": "2025-12-27T12:58:56", "event": "train_log", "step": 4678, "epoch": 1.9738396624472574, "progress_pct": 32.9, "epoch_pct": 32.9, "eta": "38:08:08", "max_grad_norm": 1.0, "loss": 0.7260952591896057, "grad_norm": 0.4393104314804077, "learning_rate": 0.00016600752333025134}
-{"ts": "2025-12-27T12:59:11", "event": "train_log", "step": 4680, "epoch": 1.9746835443037973, "progress_pct": 32.91, "epoch_pct": 32.91, "eta": "38:07:10", "max_grad_norm": 1.0, "loss": 0.7350760102272034, "grad_norm": 0.4471568167209625, "learning_rate": 0.00016597143617655982}
-{"ts": "2025-12-27T12:59:27", "event": "train_log", "step": 4682, "epoch": 1.9755274261603377, "progress_pct": 32.93, "epoch_pct": 32.93, "eta": "38:06:15", "max_grad_norm": 1.0, "loss": 0.7295693159103394, "grad_norm": 0.39821380376815796, "learning_rate": 0.00016593533380452499}
-{"ts": "2025-12-27T12:59:41", "event": "train_log", "step": 4684, "epoch": 1.9763713080168777, "progress_pct": 32.94, "epoch_pct": 32.94, "eta": "38:05:18", "max_grad_norm": 1.0, "loss": 0.6461828947067261, "grad_norm": 0.40367990732192993, "learning_rate": 0.00016589921622247493}
-{"ts": "2025-12-27T12:59:57", "event": "train_log", "step": 4686, "epoch": 1.9772151898734176, "progress_pct": 32.95, "epoch_pct": 32.95, "eta": "38:04:22", "max_grad_norm": 1.0, "loss": 0.699313223361969, "grad_norm": 0.4723254442214966, "learning_rate": 0.00016586308343874136}
-{"ts": "2025-12-27T13:00:14", "event": "train_log", "step": 4688, "epoch": 1.9780590717299578, "progress_pct": 32.97, "epoch_pct": 32.97, "eta": "38:03:29", "max_grad_norm": 1.0, "loss": 0.7299131751060486, "grad_norm": 0.45741328597068787, "learning_rate": 0.0001658269354616593}
-{"ts": "2025-12-27T13:00:29", "event": "train_log", "step": 4690, "epoch": 1.978902953586498, "progress_pct": 32.98, "epoch_pct": 32.98, "eta": "38:02:32", "max_grad_norm": 1.0, "loss": 0.7643240690231323, "grad_norm": 0.4011725187301636, "learning_rate": 0.0001657907722995675}
-{"ts": "2025-12-27T13:00:45", "event": "train_log", "step": 4692, "epoch": 1.9797468354430379, "progress_pct": 33.0, "epoch_pct": 33.0, "eta": "38:01:37", "max_grad_norm": 1.0, "loss": 0.6945428848266602, "grad_norm": 0.3904820382595062, "learning_rate": 0.00016575459396080805}
-{"ts": "2025-12-27T13:01:00", "event": "train_log", "step": 4694, "epoch": 1.980590717299578, "progress_pct": 33.01, "epoch_pct": 33.01, "eta": "38:00:42", "max_grad_norm": 1.0, "loss": 0.5986754298210144, "grad_norm": 0.3643582761287689, "learning_rate": 0.00016571840045372663}
-{"ts": "2025-12-27T13:01:17", "event": "train_log", "step": 4696, "epoch": 1.9814345991561182, "progress_pct": 33.02, "epoch_pct": 33.02, "eta": "37:59:49", "max_grad_norm": 1.0, "loss": 0.7462178468704224, "grad_norm": 0.4371087849140167, "learning_rate": 0.00016568219178667235}
-{"ts": "2025-12-27T13:01:32", "event": "train_log", "step": 4698, "epoch": 1.9822784810126581, "progress_pct": 33.04, "epoch_pct": 33.04, "eta": "37:58:53", "max_grad_norm": 1.0, "loss": 0.7553940415382385, "grad_norm": 0.4440254867076874, "learning_rate": 0.0001656459679679979}
-{"ts": "2025-12-27T13:01:48", "event": "train_log", "step": 4700, "epoch": 1.9831223628691983, "progress_pct": 33.05, "epoch_pct": 33.05, "eta": "37:57:59", "max_grad_norm": 1.0, "loss": 0.7119964361190796, "grad_norm": 0.41370099782943726, "learning_rate": 0.00016560972900605937}
-{"ts": "2025-12-27T13:13:19", "event": "train_log", "step": 4700, "epoch": 1.9831223628691983, "progress_pct": 33.05, "epoch_pct": 33.05, "eta": "38:21:17", "max_grad_norm": 1.0, "eval_loss": 0.7582268714904785, "eval_runtime": 690.081, "eval_samples_per_second": 3.053, "eval_steps_per_second": 3.053}
-{"ts": "2025-12-27T13:13:34", "event": "train_log", "step": 4702, "epoch": 1.9839662447257385, "progress_pct": 33.07, "epoch_pct": 33.07, "eta": "38:20:20", "max_grad_norm": 1.0, "loss": 0.6260318160057068, "grad_norm": 0.4408273696899414, "learning_rate": 0.0001655734749092164}
-{"ts": "2025-12-27T13:13:49", "event": "train_log", "step": 4704, "epoch": 1.9848101265822784, "progress_pct": 33.08, "epoch_pct": 33.08, "eta": "38:19:22", "max_grad_norm": 1.0, "loss": 0.7382199168205261, "grad_norm": 0.4697865843772888, "learning_rate": 0.0001655372056858322}
-{"ts": "2025-12-27T13:14:04", "event": "train_log", "step": 4706, "epoch": 1.9856540084388186, "progress_pct": 33.09, "epoch_pct": 33.09, "eta": "38:18:25", "max_grad_norm": 1.0, "loss": 0.7037063241004944, "grad_norm": 0.423520028591156, "learning_rate": 0.00016550092134427327}
-{"ts": "2025-12-27T13:14:20", "event": "train_log", "step": 4708, "epoch": 1.9864978902953587, "progress_pct": 33.11, "epoch_pct": 33.11, "eta": "38:17:29", "max_grad_norm": 1.0, "loss": 0.7173316478729248, "grad_norm": 0.38633009791374207, "learning_rate": 0.00016546462189290974}
-{"ts": "2025-12-27T13:14:35", "event": "train_log", "step": 4710, "epoch": 1.9873417721518987, "progress_pct": 33.12, "epoch_pct": 33.12, "eta": "38:16:33", "max_grad_norm": 1.0, "loss": 0.6884669065475464, "grad_norm": 0.410230815410614, "learning_rate": 0.00016542830734011523}
-{"ts": "2025-12-27T13:14:49", "event": "train_log", "step": 4712, "epoch": 1.9881856540084388, "progress_pct": 33.14, "epoch_pct": 33.14, "eta": "38:15:34", "max_grad_norm": 1.0, "loss": 0.7181811332702637, "grad_norm": 0.4486774802207947, "learning_rate": 0.00016539197769426678}
-{"ts": "2025-12-27T13:15:03", "event": "train_log", "step": 4714, "epoch": 1.989029535864979, "progress_pct": 33.15, "epoch_pct": 33.15, "eta": "38:14:36", "max_grad_norm": 1.0, "loss": 0.7737504243850708, "grad_norm": 0.47757431864738464, "learning_rate": 0.00016535563296374495}
-{"ts": "2025-12-27T13:15:20", "event": "train_log", "step": 4716, "epoch": 1.989873417721519, "progress_pct": 33.16, "epoch_pct": 33.16, "eta": "38:13:42", "max_grad_norm": 1.0, "loss": 0.683630645275116, "grad_norm": 0.40281420946121216, "learning_rate": 0.00016531927315693382}
-{"ts": "2025-12-27T13:15:34", "event": "train_log", "step": 4718, "epoch": 1.990717299578059, "progress_pct": 33.18, "epoch_pct": 33.18, "eta": "38:12:43", "max_grad_norm": 1.0, "loss": 0.7447960376739502, "grad_norm": 0.42349720001220703, "learning_rate": 0.00016528289828222082}
-{"ts": "2025-12-27T13:15:49", "event": "train_log", "step": 4720, "epoch": 1.9915611814345993, "progress_pct": 33.19, "epoch_pct": 33.19, "eta": "38:11:45", "max_grad_norm": 1.0, "loss": 0.6800103783607483, "grad_norm": 0.40754765272140503, "learning_rate": 0.00016524650834799694}
-{"ts": "2025-12-27T13:16:04", "event": "train_log", "step": 4722, "epoch": 1.9924050632911392, "progress_pct": 33.21, "epoch_pct": 33.21, "eta": "38:10:49", "max_grad_norm": 1.0, "loss": 0.6609475612640381, "grad_norm": 0.3766736090183258, "learning_rate": 0.0001652101033626567}
-{"ts": "2025-12-27T13:16:20", "event": "train_log", "step": 4724, "epoch": 1.9932489451476794, "progress_pct": 33.22, "epoch_pct": 33.22, "eta": "38:09:54", "max_grad_norm": 1.0, "loss": 0.6496920585632324, "grad_norm": 0.3600929081439972, "learning_rate": 0.00016517368333459798}
-{"ts": "2025-12-27T13:16:35", "event": "train_log", "step": 4726, "epoch": 1.9940928270042195, "progress_pct": 33.23, "epoch_pct": 33.23, "eta": "38:08:56", "max_grad_norm": 1.0, "loss": 0.6305265426635742, "grad_norm": 0.39590612053871155, "learning_rate": 0.00016513724827222227}
-{"ts": "2025-12-27T13:16:49", "event": "train_log", "step": 4728, "epoch": 1.9949367088607595, "progress_pct": 33.25, "epoch_pct": 33.25, "eta": "38:07:59", "max_grad_norm": 1.0, "loss": 0.712282657623291, "grad_norm": 0.41002732515335083, "learning_rate": 0.00016510079818393426}
-{"ts": "2025-12-27T13:17:05", "event": "train_log", "step": 4730, "epoch": 1.9957805907172996, "progress_pct": 33.26, "epoch_pct": 33.26, "eta": "38:07:03", "max_grad_norm": 1.0, "loss": 0.6974884271621704, "grad_norm": 0.41948413848876953, "learning_rate": 0.00016506433307814246}
-{"ts": "2025-12-27T13:17:20", "event": "train_log", "step": 4732, "epoch": 1.9966244725738398, "progress_pct": 33.28, "epoch_pct": 33.28, "eta": "38:06:05", "max_grad_norm": 1.0, "loss": 0.6844019889831543, "grad_norm": 0.4283764958381653, "learning_rate": 0.00016502785296325858}
-{"ts": "2025-12-27T13:17:34", "event": "train_log", "step": 4734, "epoch": 1.9974683544303797, "progress_pct": 33.29, "epoch_pct": 33.29, "eta": "38:05:07", "max_grad_norm": 1.0, "loss": 0.7453671097755432, "grad_norm": 0.39830246567726135, "learning_rate": 0.0001649913578476979}
-{"ts": "2025-12-27T13:17:49", "event": "train_log", "step": 4736, "epoch": 1.9983122362869197, "progress_pct": 33.31, "epoch_pct": 33.31, "eta": "38:04:10", "max_grad_norm": 1.0, "loss": 0.6571418046951294, "grad_norm": 0.3875660300254822, "learning_rate": 0.00016495484773987917}
-{"ts": "2025-12-27T13:18:04", "event": "train_log", "step": 4738, "epoch": 1.99915611814346, "progress_pct": 33.32, "epoch_pct": 33.32, "eta": "38:03:14", "max_grad_norm": 1.0, "loss": 0.6844568848609924, "grad_norm": 0.379986971616745, "learning_rate": 0.00016491832264822453}
-{"ts": "2025-12-27T13:18:19", "event": "train_log", "step": 4740, "epoch": 2.0, "progress_pct": 33.33, "epoch_pct": 33.33, "eta": "38:02:18", "max_grad_norm": 1.0, "loss": 0.6115277409553528, "grad_norm": 0.38605886697769165, "learning_rate": 0.00016488178258115965}
-{"ts": "2025-12-27T13:18:35", "event": "train_log", "step": 4742, "epoch": 2.00084388185654, "progress_pct": 33.35, "epoch_pct": 33.35, "eta": "38:01:22", "max_grad_norm": 1.0, "loss": 0.6192594170570374, "grad_norm": 0.3991186022758484, "learning_rate": 0.0001648452275471136}
-{"ts": "2025-12-27T13:18:49", "event": "train_log", "step": 4744, "epoch": 2.0016877637130803, "progress_pct": 33.36, "epoch_pct": 33.36, "eta": "38:00:24", "max_grad_norm": 1.0, "loss": 0.6478689312934875, "grad_norm": 0.41378065943717957, "learning_rate": 0.00016480865755451893}
-{"ts": "2025-12-27T13:19:04", "event": "train_log", "step": 4746, "epoch": 2.0025316455696203, "progress_pct": 33.38, "epoch_pct": 33.38, "eta": "37:59:26", "max_grad_norm": 1.0, "loss": 0.6162620186805725, "grad_norm": 0.41938909888267517, "learning_rate": 0.00016477207261181162}
-{"ts": "2025-12-27T13:19:20", "event": "train_log", "step": 4748, "epoch": 2.00337552742616, "progress_pct": 33.39, "epoch_pct": 33.39, "eta": "37:58:33", "max_grad_norm": 1.0, "loss": 0.5328736901283264, "grad_norm": 0.40436387062072754, "learning_rate": 0.00016473547272743115}
-{"ts": "2025-12-27T13:19:35", "event": "train_log", "step": 4750, "epoch": 2.0042194092827006, "progress_pct": 33.4, "epoch_pct": 33.4, "eta": "37:57:36", "max_grad_norm": 1.0, "loss": 0.547049880027771, "grad_norm": 0.4148593544960022, "learning_rate": 0.00016469885790982037}
-{"ts": "2025-12-27T13:19:51", "event": "train_log", "step": 4752, "epoch": 2.0050632911392405, "progress_pct": 33.42, "epoch_pct": 33.42, "eta": "37:56:41", "max_grad_norm": 1.0, "loss": 0.5509368181228638, "grad_norm": 0.42139601707458496, "learning_rate": 0.00016466222816742564}
-{"ts": "2025-12-27T13:20:06", "event": "train_log", "step": 4754, "epoch": 2.0059071729957805, "progress_pct": 33.43, "epoch_pct": 33.43, "eta": "37:55:46", "max_grad_norm": 1.0, "loss": 0.5994526147842407, "grad_norm": 0.4509783089160919, "learning_rate": 0.00016462558350869677}
-{"ts": "2025-12-27T13:20:21", "event": "train_log", "step": 4756, "epoch": 2.006751054852321, "progress_pct": 33.45, "epoch_pct": 33.45, "eta": "37:54:49", "max_grad_norm": 1.0, "loss": 0.6348381638526917, "grad_norm": 0.4232040345668793, "learning_rate": 0.0001645889239420869}
-{"ts": "2025-12-27T13:20:36", "event": "train_log", "step": 4758, "epoch": 2.007594936708861, "progress_pct": 33.46, "epoch_pct": 33.46, "eta": "37:53:53", "max_grad_norm": 1.0, "loss": 0.5487880110740662, "grad_norm": 0.4259628355503082, "learning_rate": 0.00016455224947605274}
-{"ts": "2025-12-27T13:20:51", "event": "train_log", "step": 4760, "epoch": 2.0084388185654007, "progress_pct": 33.47, "epoch_pct": 33.47, "eta": "37:52:56", "max_grad_norm": 1.0, "loss": 0.5468270778656006, "grad_norm": 0.5485594868659973, "learning_rate": 0.0001645155601190544}
-{"ts": "2025-12-27T13:21:06", "event": "train_log", "step": 4762, "epoch": 2.009282700421941, "progress_pct": 33.49, "epoch_pct": 33.49, "eta": "37:51:59", "max_grad_norm": 1.0, "loss": 0.6165785789489746, "grad_norm": 0.4243668019771576, "learning_rate": 0.00016447885587955537}
-{"ts": "2025-12-27T13:21:20", "event": "train_log", "step": 4764, "epoch": 2.010126582278481, "progress_pct": 33.5, "epoch_pct": 33.5, "eta": "37:51:02", "max_grad_norm": 1.0, "loss": 0.5868126749992371, "grad_norm": 0.46513810753822327, "learning_rate": 0.00016444213676602263}
-{"ts": "2025-12-27T13:21:35", "event": "train_log", "step": 4766, "epoch": 2.010970464135021, "progress_pct": 33.52, "epoch_pct": 33.52, "eta": "37:50:06", "max_grad_norm": 1.0, "loss": 0.548373818397522, "grad_norm": 0.4555842876434326, "learning_rate": 0.00016440540278692654}
-{"ts": "2025-12-27T13:21:51", "event": "train_log", "step": 4768, "epoch": 2.0118143459915614, "progress_pct": 33.53, "epoch_pct": 33.53, "eta": "37:49:11", "max_grad_norm": 1.0, "loss": 0.6254384517669678, "grad_norm": 0.4402005672454834, "learning_rate": 0.000164368653950741}
-{"ts": "2025-12-27T13:22:05", "event": "train_log", "step": 4770, "epoch": 2.0126582278481013, "progress_pct": 33.54, "epoch_pct": 33.54, "eta": "37:48:14", "max_grad_norm": 1.0, "loss": 0.6335576772689819, "grad_norm": 0.5100982785224915, "learning_rate": 0.0001643318902659432}
-{"ts": "2025-12-27T13:22:20", "event": "train_log", "step": 4772, "epoch": 2.0135021097046413, "progress_pct": 33.56, "epoch_pct": 33.56, "eta": "37:47:17", "max_grad_norm": 1.0, "loss": 0.6601388454437256, "grad_norm": 0.508076548576355, "learning_rate": 0.0001642951117410138}
-{"ts": "2025-12-27T13:22:36", "event": "train_log", "step": 4774, "epoch": 2.014345991561181, "progress_pct": 33.57, "epoch_pct": 33.57, "eta": "37:46:22", "max_grad_norm": 1.0, "loss": 0.6183612942695618, "grad_norm": 0.47249099612236023, "learning_rate": 0.000164258318384437}
-{"ts": "2025-12-27T13:22:50", "event": "train_log", "step": 4776, "epoch": 2.0151898734177216, "progress_pct": 33.59, "epoch_pct": 33.59, "eta": "37:45:25", "max_grad_norm": 1.0, "loss": 0.6172632575035095, "grad_norm": 0.459249883890152, "learning_rate": 0.00016422151020470022}
-{"ts": "2025-12-27T13:23:05", "event": "train_log", "step": 4778, "epoch": 2.0160337552742615, "progress_pct": 33.6, "epoch_pct": 33.6, "eta": "37:44:28", "max_grad_norm": 1.0, "loss": 0.6392593383789062, "grad_norm": 0.44374513626098633, "learning_rate": 0.00016418468721029442}
-{"ts": "2025-12-27T13:23:19", "event": "train_log", "step": 4780, "epoch": 2.0168776371308015, "progress_pct": 33.61, "epoch_pct": 33.61, "eta": "37:43:31", "max_grad_norm": 1.0, "loss": 0.6331546902656555, "grad_norm": 0.4633971154689789, "learning_rate": 0.000164147849409714}
-{"ts": "2025-12-27T13:23:35", "event": "train_log", "step": 4782, "epoch": 2.017721518987342, "progress_pct": 33.63, "epoch_pct": 33.63, "eta": "37:42:36", "max_grad_norm": 1.0, "loss": 0.5368412137031555, "grad_norm": 0.4080882668495178, "learning_rate": 0.00016411099681145667}
-{"ts": "2025-12-27T13:23:51", "event": "train_log", "step": 4784, "epoch": 2.018565400843882, "progress_pct": 33.64, "epoch_pct": 33.64, "eta": "37:41:42", "max_grad_norm": 1.0, "loss": 0.4763215184211731, "grad_norm": 0.3852706253528595, "learning_rate": 0.00016407412942402366}
-{"ts": "2025-12-27T13:24:06", "event": "train_log", "step": 4786, "epoch": 2.0194092827004217, "progress_pct": 33.66, "epoch_pct": 33.66, "eta": "37:40:46", "max_grad_norm": 1.0, "loss": 0.6510329842567444, "grad_norm": 0.45222651958465576, "learning_rate": 0.00016403724725591958}
-{"ts": "2025-12-27T13:24:21", "event": "train_log", "step": 4788, "epoch": 2.020253164556962, "progress_pct": 33.67, "epoch_pct": 33.67, "eta": "37:39:50", "max_grad_norm": 1.0, "loss": 0.5856698751449585, "grad_norm": 0.4027794897556305, "learning_rate": 0.00016400035031565238}
-{"ts": "2025-12-27T13:24:36", "event": "train_log", "step": 4790, "epoch": 2.021097046413502, "progress_pct": 33.68, "epoch_pct": 33.68, "eta": "37:38:56", "max_grad_norm": 1.0, "loss": 0.5960753560066223, "grad_norm": 0.3780474066734314, "learning_rate": 0.00016396343861173356}
-{"ts": "2025-12-27T13:24:52", "event": "train_log", "step": 4792, "epoch": 2.021940928270042, "progress_pct": 33.7, "epoch_pct": 33.7, "eta": "37:38:02", "max_grad_norm": 1.0, "loss": 0.5696688890457153, "grad_norm": 0.4297144412994385, "learning_rate": 0.00016392651215267785}
-{"ts": "2025-12-27T13:25:07", "event": "train_log", "step": 4794, "epoch": 2.0227848101265824, "progress_pct": 33.71, "epoch_pct": 33.71, "eta": "37:37:06", "max_grad_norm": 1.0, "loss": 0.6610676050186157, "grad_norm": 0.4521540701389313, "learning_rate": 0.00016388957094700356}
-{"ts": "2025-12-27T13:25:22", "event": "train_log", "step": 4796, "epoch": 2.0236286919831223, "progress_pct": 33.73, "epoch_pct": 33.73, "eta": "37:36:11", "max_grad_norm": 1.0, "loss": 0.5387522578239441, "grad_norm": 0.41184982657432556, "learning_rate": 0.00016385261500323224}
-{"ts": "2025-12-27T13:25:37", "event": "train_log", "step": 4798, "epoch": 2.0244725738396623, "progress_pct": 33.74, "epoch_pct": 33.74, "eta": "37:35:13", "max_grad_norm": 1.0, "loss": 0.6614878177642822, "grad_norm": 0.489391565322876, "learning_rate": 0.00016381564432988897}
-{"ts": "2025-12-27T13:25:52", "event": "train_log", "step": 4800, "epoch": 2.0253164556962027, "progress_pct": 33.76, "epoch_pct": 33.76, "eta": "37:34:19", "max_grad_norm": 1.0, "loss": 0.5513694286346436, "grad_norm": 0.3741590678691864, "learning_rate": 0.00016377865893550214}
-{"ts": "2025-12-27T13:37:21", "event": "train_log", "step": 4800, "epoch": 2.0253164556962027, "progress_pct": 33.76, "epoch_pct": 33.76, "eta": "37:56:51", "max_grad_norm": 1.0, "eval_loss": 0.7633068561553955, "eval_runtime": 688.8684, "eval_samples_per_second": 3.059, "eval_steps_per_second": 3.059}
-{"ts": "2025-12-27T13:37:37", "event": "train_log", "step": 4802, "epoch": 2.0261603375527426, "progress_pct": 33.77, "epoch_pct": 33.77, "eta": "37:55:56", "max_grad_norm": 1.0, "loss": 0.5732831358909607, "grad_norm": 0.45757874846458435, "learning_rate": 0.0001637416588286036}
-{"ts": "2025-12-27T13:37:53", "event": "train_log", "step": 4804, "epoch": 2.0270042194092825, "progress_pct": 33.78, "epoch_pct": 33.78, "eta": "37:55:01", "max_grad_norm": 1.0, "loss": 0.5994226932525635, "grad_norm": 0.4009305238723755, "learning_rate": 0.00016370464401772853}
-{"ts": "2025-12-27T13:38:09", "event": "train_log", "step": 4806, "epoch": 2.027848101265823, "progress_pct": 33.8, "epoch_pct": 33.8, "eta": "37:54:08", "max_grad_norm": 1.0, "loss": 0.6229469776153564, "grad_norm": 0.44907137751579285, "learning_rate": 0.0001636676145114156}
-{"ts": "2025-12-27T13:38:26", "event": "train_log", "step": 4808, "epoch": 2.028691983122363, "progress_pct": 33.81, "epoch_pct": 33.81, "eta": "37:53:14", "max_grad_norm": 1.0, "loss": 0.5126086473464966, "grad_norm": 0.4153282344341278, "learning_rate": 0.00016363057031820673}
-{"ts": "2025-12-27T13:38:42", "event": "train_log", "step": 4810, "epoch": 2.029535864978903, "progress_pct": 33.83, "epoch_pct": 33.83, "eta": "37:52:21", "max_grad_norm": 1.0, "loss": 0.5779650211334229, "grad_norm": 0.41859957575798035, "learning_rate": 0.0001635935114466473}
-{"ts": "2025-12-27T13:38:59", "event": "train_log", "step": 4812, "epoch": 2.030379746835443, "progress_pct": 33.84, "epoch_pct": 33.84, "eta": "37:51:27", "max_grad_norm": 1.0, "loss": 0.5561378598213196, "grad_norm": 0.44624394178390503, "learning_rate": 0.00016355643790528617}
-{"ts": "2025-12-27T13:39:14", "event": "train_log", "step": 4814, "epoch": 2.031223628691983, "progress_pct": 33.85, "epoch_pct": 33.85, "eta": "37:50:32", "max_grad_norm": 1.0, "loss": 0.5381612181663513, "grad_norm": 0.44554266333580017, "learning_rate": 0.00016351934970267542}
-{"ts": "2025-12-27T13:39:30", "event": "train_log", "step": 4816, "epoch": 2.032067510548523, "progress_pct": 33.87, "epoch_pct": 33.87, "eta": "37:49:37", "max_grad_norm": 1.0, "loss": 0.6434502601623535, "grad_norm": 0.4529551565647125, "learning_rate": 0.00016348224684737065}
-{"ts": "2025-12-27T13:39:45", "event": "train_log", "step": 4818, "epoch": 2.0329113924050635, "progress_pct": 33.88, "epoch_pct": 33.88, "eta": "37:48:42", "max_grad_norm": 1.0, "loss": 0.6316392421722412, "grad_norm": 0.891188383102417, "learning_rate": 0.00016344512934793066}
-{"ts": "2025-12-27T13:40:02", "event": "train_log", "step": 4820, "epoch": 2.0337552742616034, "progress_pct": 33.9, "epoch_pct": 33.9, "eta": "37:47:50", "max_grad_norm": 1.0, "loss": 0.5569570064544678, "grad_norm": 0.4621472656726837, "learning_rate": 0.00016340799721291783}
-{"ts": "2025-12-27T13:40:19", "event": "train_log", "step": 4822, "epoch": 2.0345991561181433, "progress_pct": 33.91, "epoch_pct": 33.91, "eta": "37:46:56", "max_grad_norm": 1.0, "loss": 0.5403776168823242, "grad_norm": 0.38671162724494934, "learning_rate": 0.00016337085045089786}
-{"ts": "2025-12-27T13:40:34", "event": "train_log", "step": 4824, "epoch": 2.0354430379746837, "progress_pct": 33.92, "epoch_pct": 33.92, "eta": "37:46:01", "max_grad_norm": 1.0, "loss": 0.5629472732543945, "grad_norm": 0.3896256685256958, "learning_rate": 0.00016333368907043972}
-{"ts": "2025-12-27T13:40:49", "event": "train_log", "step": 4826, "epoch": 2.0362869198312237, "progress_pct": 33.94, "epoch_pct": 33.94, "eta": "37:45:06", "max_grad_norm": 1.0, "loss": 0.5740808844566345, "grad_norm": 0.4890784025192261, "learning_rate": 0.00016329651308011583}
-{"ts": "2025-12-27T13:41:05", "event": "train_log", "step": 4828, "epoch": 2.0371308016877636, "progress_pct": 33.95, "epoch_pct": 33.95, "eta": "37:44:11", "max_grad_norm": 1.0, "loss": 0.6362084746360779, "grad_norm": 0.493118554353714, "learning_rate": 0.00016325932248850207}
-{"ts": "2025-12-27T13:41:21", "event": "train_log", "step": 4830, "epoch": 2.037974683544304, "progress_pct": 33.97, "epoch_pct": 33.97, "eta": "37:43:16", "max_grad_norm": 1.0, "loss": 0.5512531399726868, "grad_norm": 0.4112105965614319, "learning_rate": 0.0001632221173041775}
-{"ts": "2025-12-27T13:41:36", "event": "train_log", "step": 4832, "epoch": 2.038818565400844, "progress_pct": 33.98, "epoch_pct": 33.98, "eta": "37:42:21", "max_grad_norm": 1.0, "loss": 0.5507554411888123, "grad_norm": 0.48197677731513977, "learning_rate": 0.00016318489753572464}
-{"ts": "2025-12-27T13:41:52", "event": "train_log", "step": 4834, "epoch": 2.039662447257384, "progress_pct": 33.99, "epoch_pct": 33.99, "eta": "37:41:27", "max_grad_norm": 1.0, "loss": 0.7607873678207397, "grad_norm": 0.5130576491355896, "learning_rate": 0.00016314766319172947}
-{"ts": "2025-12-27T13:42:08", "event": "train_log", "step": 4836, "epoch": 2.0405063291139243, "progress_pct": 34.01, "epoch_pct": 34.01, "eta": "37:40:32", "max_grad_norm": 1.0, "loss": 0.6044831275939941, "grad_norm": 0.4454704523086548, "learning_rate": 0.00016311041428078112}
-{"ts": "2025-12-27T13:42:24", "event": "train_log", "step": 4838, "epoch": 2.041350210970464, "progress_pct": 34.02, "epoch_pct": 34.02, "eta": "37:39:39", "max_grad_norm": 1.0, "loss": 0.587941586971283, "grad_norm": 0.4688933789730072, "learning_rate": 0.00016307315081147227}
-{"ts": "2025-12-27T13:42:39", "event": "train_log", "step": 4840, "epoch": 2.042194092827004, "progress_pct": 34.04, "epoch_pct": 34.04, "eta": "37:38:42", "max_grad_norm": 1.0, "loss": 0.5822482109069824, "grad_norm": 0.45465248823165894, "learning_rate": 0.0001630358727923989}
-{"ts": "2025-12-27T13:42:54", "event": "train_log", "step": 4842, "epoch": 2.043037974683544, "progress_pct": 34.05, "epoch_pct": 34.05, "eta": "37:37:48", "max_grad_norm": 1.0, "loss": 0.584092378616333, "grad_norm": 0.4670163691043854, "learning_rate": 0.00016299858023216028}
-{"ts": "2025-12-27T13:43:11", "event": "train_log", "step": 4844, "epoch": 2.0438818565400845, "progress_pct": 34.06, "epoch_pct": 34.06, "eta": "37:36:56", "max_grad_norm": 1.0, "loss": 0.5876650214195251, "grad_norm": 0.43894922733306885, "learning_rate": 0.0001629612731393591}
-{"ts": "2025-12-27T13:43:26", "event": "train_log", "step": 4846, "epoch": 2.0447257383966244, "progress_pct": 34.08, "epoch_pct": 34.08, "eta": "37:36:00", "max_grad_norm": 1.0, "loss": 0.5628184676170349, "grad_norm": 0.4144253730773926, "learning_rate": 0.0001629239515226014}
-{"ts": "2025-12-27T13:43:42", "event": "train_log", "step": 4848, "epoch": 2.0455696202531644, "progress_pct": 34.09, "epoch_pct": 34.09, "eta": "37:35:06", "max_grad_norm": 1.0, "loss": 0.6156699657440186, "grad_norm": 0.47422146797180176, "learning_rate": 0.0001628866153904966}
-{"ts": "2025-12-27T13:43:59", "event": "train_log", "step": 4850, "epoch": 2.0464135021097047, "progress_pct": 34.11, "epoch_pct": 34.11, "eta": "37:34:14", "max_grad_norm": 1.0, "loss": 0.5761739015579224, "grad_norm": 0.46102508902549744, "learning_rate": 0.00016284926475165735}
-{"ts": "2025-12-27T13:44:14", "event": "train_log", "step": 4852, "epoch": 2.0472573839662447, "progress_pct": 34.12, "epoch_pct": 34.12, "eta": "37:33:17", "max_grad_norm": 1.0, "loss": 0.6326378583908081, "grad_norm": 0.4987565577030182, "learning_rate": 0.00016281189961469977}
-{"ts": "2025-12-27T13:44:28", "event": "train_log", "step": 4854, "epoch": 2.0481012658227846, "progress_pct": 34.14, "epoch_pct": 34.14, "eta": "37:32:21", "max_grad_norm": 1.0, "loss": 0.6072084903717041, "grad_norm": 0.46640047430992126, "learning_rate": 0.0001627745199882433}
-{"ts": "2025-12-27T13:44:43", "event": "train_log", "step": 4856, "epoch": 2.048945147679325, "progress_pct": 34.15, "epoch_pct": 34.15, "eta": "37:31:25", "max_grad_norm": 1.0, "loss": 0.6507929563522339, "grad_norm": 0.5362635254859924, "learning_rate": 0.00016273712588091066}
-{"ts": "2025-12-27T13:44:57", "event": "train_log", "step": 4858, "epoch": 2.049789029535865, "progress_pct": 34.16, "epoch_pct": 34.16, "eta": "37:30:28", "max_grad_norm": 1.0, "loss": 0.6264472007751465, "grad_norm": 0.459285706281662, "learning_rate": 0.00016269971730132796}
-{"ts": "2025-12-27T13:45:11", "event": "train_log", "step": 4860, "epoch": 2.050632911392405, "progress_pct": 34.18, "epoch_pct": 34.18, "eta": "37:29:31", "max_grad_norm": 1.0, "loss": 0.6185184717178345, "grad_norm": 0.4467318058013916, "learning_rate": 0.00016266229425812467}
-{"ts": "2025-12-27T13:45:27", "event": "train_log", "step": 4862, "epoch": 2.0514767932489453, "progress_pct": 34.19, "epoch_pct": 34.19, "eta": "37:28:36", "max_grad_norm": 1.0, "loss": 0.5723293423652649, "grad_norm": 0.4965224266052246, "learning_rate": 0.0001626248567599335}
-{"ts": "2025-12-27T13:45:42", "event": "train_log", "step": 4864, "epoch": 2.052320675105485, "progress_pct": 34.21, "epoch_pct": 34.21, "eta": "37:27:40", "max_grad_norm": 1.0, "loss": 0.578831672668457, "grad_norm": 0.46917736530303955, "learning_rate": 0.0001625874048153907}
-{"ts": "2025-12-27T13:45:56", "event": "train_log", "step": 4866, "epoch": 2.053164556962025, "progress_pct": 34.22, "epoch_pct": 34.22, "eta": "37:26:43", "max_grad_norm": 1.0, "loss": 0.6448227763175964, "grad_norm": 0.498439222574234, "learning_rate": 0.00016254993843313554}
-{"ts": "2025-12-27T13:46:11", "event": "train_log", "step": 4868, "epoch": 2.0540084388185655, "progress_pct": 34.23, "epoch_pct": 34.23, "eta": "37:25:47", "max_grad_norm": 1.0, "loss": 0.6240531802177429, "grad_norm": 0.4801621735095978, "learning_rate": 0.00016251245762181088}
-{"ts": "2025-12-27T13:46:26", "event": "train_log", "step": 4870, "epoch": 2.0548523206751055, "progress_pct": 34.25, "epoch_pct": 34.25, "eta": "37:24:53", "max_grad_norm": 1.0, "loss": 0.4955635070800781, "grad_norm": 0.3652440309524536, "learning_rate": 0.00016247496239006287}
-{"ts": "2025-12-27T13:46:41", "event": "train_log", "step": 4872, "epoch": 2.0556962025316454, "progress_pct": 34.26, "epoch_pct": 34.26, "eta": "37:23:58", "max_grad_norm": 1.0, "loss": 0.6184053421020508, "grad_norm": 0.504094123840332, "learning_rate": 0.00016243745274654084}
-{"ts": "2025-12-27T13:46:56", "event": "train_log", "step": 4874, "epoch": 2.056540084388186, "progress_pct": 34.28, "epoch_pct": 34.28, "eta": "37:23:02", "max_grad_norm": 1.0, "loss": 0.5592952370643616, "grad_norm": 0.4311911463737488, "learning_rate": 0.0001623999286998976}
-{"ts": "2025-12-27T13:47:11", "event": "train_log", "step": 4876, "epoch": 2.0573839662447257, "progress_pct": 34.29, "epoch_pct": 34.29, "eta": "37:22:06", "max_grad_norm": 1.0, "loss": 0.6024063229560852, "grad_norm": 0.5173681974411011, "learning_rate": 0.00016236239025878928}
-{"ts": "2025-12-27T13:47:26", "event": "train_log", "step": 4878, "epoch": 2.0582278481012657, "progress_pct": 34.3, "epoch_pct": 34.3, "eta": "37:21:12", "max_grad_norm": 1.0, "loss": 0.5788836479187012, "grad_norm": 0.41021528840065, "learning_rate": 0.0001623248374318752}
-{"ts": "2025-12-27T13:47:41", "event": "train_log", "step": 4880, "epoch": 2.059071729957806, "progress_pct": 34.32, "epoch_pct": 34.32, "eta": "37:20:16", "max_grad_norm": 1.0, "loss": 0.6215962767601013, "grad_norm": 0.5167528986930847, "learning_rate": 0.00016228727022781807}
-{"ts": "2025-12-27T13:47:55", "event": "train_log", "step": 4882, "epoch": 2.059915611814346, "progress_pct": 34.33, "epoch_pct": 34.33, "eta": "37:19:20", "max_grad_norm": 1.0, "loss": 0.5767302513122559, "grad_norm": 0.5254554152488708, "learning_rate": 0.00016224968865528395}
-{"ts": "2025-12-27T13:48:11", "event": "train_log", "step": 4884, "epoch": 2.060759493670886, "progress_pct": 34.35, "epoch_pct": 34.35, "eta": "37:18:27", "max_grad_norm": 1.0, "loss": 0.5494593381881714, "grad_norm": 0.3826330602169037, "learning_rate": 0.00016221209272294218}
-{"ts": "2025-12-27T13:48:26", "event": "train_log", "step": 4886, "epoch": 2.0616033755274263, "progress_pct": 34.36, "epoch_pct": 34.36, "eta": "37:17:32", "max_grad_norm": 1.0, "loss": 0.5395565032958984, "grad_norm": 0.48100414872169495, "learning_rate": 0.00016217448243946542}
-{"ts": "2025-12-27T13:48:42", "event": "train_log", "step": 4888, "epoch": 2.0624472573839663, "progress_pct": 34.37, "epoch_pct": 34.37, "eta": "37:16:38", "max_grad_norm": 1.0, "loss": 0.5737000107765198, "grad_norm": 0.4237285852432251, "learning_rate": 0.00016213685781352966}
-{"ts": "2025-12-27T13:48:57", "event": "train_log", "step": 4890, "epoch": 2.0632911392405062, "progress_pct": 34.39, "epoch_pct": 34.39, "eta": "37:15:44", "max_grad_norm": 1.0, "loss": 0.6150708794593811, "grad_norm": 0.46409112215042114, "learning_rate": 0.0001620992188538142}
-{"ts": "2025-12-27T13:49:12", "event": "train_log", "step": 4892, "epoch": 2.0641350210970466, "progress_pct": 34.4, "epoch_pct": 34.4, "eta": "37:14:48", "max_grad_norm": 1.0, "loss": 0.5868361592292786, "grad_norm": 0.5053852200508118, "learning_rate": 0.0001620615655690015}
-{"ts": "2025-12-27T13:49:27", "event": "train_log", "step": 4894, "epoch": 2.0649789029535865, "progress_pct": 34.42, "epoch_pct": 34.42, "eta": "37:13:54", "max_grad_norm": 1.0, "loss": 0.543509304523468, "grad_norm": 0.4552644193172455, "learning_rate": 0.00016202389796777763}
-{"ts": "2025-12-27T13:49:42", "event": "train_log", "step": 4896, "epoch": 2.0658227848101265, "progress_pct": 34.43, "epoch_pct": 34.43, "eta": "37:12:59", "max_grad_norm": 1.0, "loss": 0.6006189584732056, "grad_norm": 0.49399474263191223, "learning_rate": 0.00016198621605883164}
-{"ts": "2025-12-27T13:49:58", "event": "train_log", "step": 4898, "epoch": 2.066666666666667, "progress_pct": 34.44, "epoch_pct": 34.44, "eta": "37:12:05", "max_grad_norm": 1.0, "loss": 0.6238788962364197, "grad_norm": 0.4846300184726715, "learning_rate": 0.00016194851985085608}
-{"ts": "2025-12-27T13:50:14", "event": "train_log", "step": 4900, "epoch": 2.067510548523207, "progress_pct": 34.46, "epoch_pct": 34.46, "eta": "37:11:12", "max_grad_norm": 1.0, "loss": 0.5164834856987, "grad_norm": 0.4207721948623657, "learning_rate": 0.00016191080935254673}
-{"ts": "2025-12-27T14:01:30", "event": "train_log", "step": 4900, "epoch": 2.067510548523207, "progress_pct": 34.46, "epoch_pct": 34.46, "eta": "37:32:37", "max_grad_norm": 1.0, "eval_loss": 0.7676681280136108, "eval_runtime": 676.0104, "eval_samples_per_second": 3.117, "eval_steps_per_second": 3.117}
-{"ts": "2025-12-27T14:01:46", "event": "train_log", "step": 4902, "epoch": 2.0683544303797468, "progress_pct": 34.47, "epoch_pct": 34.47, "eta": "37:31:44", "max_grad_norm": 1.0, "loss": 0.6363024115562439, "grad_norm": 0.49213138222694397, "learning_rate": 0.00016187308457260268}
-{"ts": "2025-12-27T14:02:04", "event": "train_log", "step": 4904, "epoch": 2.0691983122362867, "progress_pct": 34.49, "epoch_pct": 34.49, "eta": "37:30:55", "max_grad_norm": 1.0, "loss": 0.5472462177276611, "grad_norm": 0.4619614779949188, "learning_rate": 0.00016183534551972634}
-{"ts": "2025-12-27T14:02:20", "event": "train_log", "step": 4906, "epoch": 2.070042194092827, "progress_pct": 34.5, "epoch_pct": 34.5, "eta": "37:30:02", "max_grad_norm": 1.0, "loss": 0.5588397979736328, "grad_norm": 0.45133984088897705, "learning_rate": 0.00016179759220262335}
-{"ts": "2025-12-27T14:02:35", "event": "train_log", "step": 4908, "epoch": 2.070886075949367, "progress_pct": 34.51, "epoch_pct": 34.51, "eta": "37:29:06", "max_grad_norm": 1.0, "loss": 0.6439877152442932, "grad_norm": 0.43284907937049866, "learning_rate": 0.00016175982463000266}
-{"ts": "2025-12-27T14:02:51", "event": "train_log", "step": 4910, "epoch": 2.071729957805907, "progress_pct": 34.53, "epoch_pct": 34.53, "eta": "37:28:11", "max_grad_norm": 1.0, "loss": 0.5987089276313782, "grad_norm": 0.4439920485019684, "learning_rate": 0.00016172204281057656}
-{"ts": "2025-12-27T14:03:08", "event": "train_log", "step": 4912, "epoch": 2.0725738396624473, "progress_pct": 34.54, "epoch_pct": 34.54, "eta": "37:27:20", "max_grad_norm": 1.0, "loss": 0.53819739818573, "grad_norm": 0.376004695892334, "learning_rate": 0.0001616842467530606}
-{"ts": "2025-12-27T14:03:24", "event": "train_log", "step": 4914, "epoch": 2.0734177215189873, "progress_pct": 34.56, "epoch_pct": 34.56, "eta": "37:26:27", "max_grad_norm": 1.0, "loss": 0.5739918947219849, "grad_norm": 0.42577606439590454, "learning_rate": 0.00016164643646617358}
-{"ts": "2025-12-27T14:03:40", "event": "train_log", "step": 4916, "epoch": 2.0742616033755272, "progress_pct": 34.57, "epoch_pct": 34.57, "eta": "37:25:32", "max_grad_norm": 1.0, "loss": 0.580957293510437, "grad_norm": 0.4607972502708435, "learning_rate": 0.00016160861195863756}
-{"ts": "2025-12-27T14:03:56", "event": "train_log", "step": 4918, "epoch": 2.0751054852320676, "progress_pct": 34.59, "epoch_pct": 34.59, "eta": "37:24:39", "max_grad_norm": 1.0, "loss": 0.6063762903213501, "grad_norm": 0.4114130735397339, "learning_rate": 0.00016157077323917802}
-{"ts": "2025-12-27T14:04:12", "event": "train_log", "step": 4920, "epoch": 2.0759493670886076, "progress_pct": 34.6, "epoch_pct": 34.6, "eta": "37:23:46", "max_grad_norm": 1.0, "loss": 0.5996072292327881, "grad_norm": 0.4415706694126129, "learning_rate": 0.00016153292031652358}
-{"ts": "2025-12-27T14:04:28", "event": "train_log", "step": 4922, "epoch": 2.0767932489451475, "progress_pct": 34.61, "epoch_pct": 34.61, "eta": "37:22:53", "max_grad_norm": 1.0, "loss": 0.6442107558250427, "grad_norm": 0.5539509654045105, "learning_rate": 0.00016149505319940617}
-{"ts": "2025-12-27T14:04:44", "event": "train_log", "step": 4924, "epoch": 2.077637130801688, "progress_pct": 34.63, "epoch_pct": 34.63, "eta": "37:21:58", "max_grad_norm": 1.0, "loss": 0.6175990104675293, "grad_norm": 0.510313868522644, "learning_rate": 0.00016145717189656105}
-{"ts": "2025-12-27T14:05:00", "event": "train_log", "step": 4926, "epoch": 2.078481012658228, "progress_pct": 34.64, "epoch_pct": 34.64, "eta": "37:21:07", "max_grad_norm": 1.0, "loss": 0.6108829975128174, "grad_norm": 0.442271888256073, "learning_rate": 0.00016141927641672666}
-{"ts": "2025-12-27T14:05:16", "event": "train_log", "step": 4928, "epoch": 2.0793248945147678, "progress_pct": 34.66, "epoch_pct": 34.66, "eta": "37:20:13", "max_grad_norm": 1.0, "loss": 0.6193580031394958, "grad_norm": 0.4499345123767853, "learning_rate": 0.00016138136676864477}
-{"ts": "2025-12-27T14:05:33", "event": "train_log", "step": 4930, "epoch": 2.080168776371308, "progress_pct": 34.67, "epoch_pct": 34.67, "eta": "37:19:22", "max_grad_norm": 1.0, "loss": 0.5283842086791992, "grad_norm": 0.36362606287002563, "learning_rate": 0.00016134344296106043}
-{"ts": "2025-12-27T14:05:49", "event": "train_log", "step": 4932, "epoch": 2.081012658227848, "progress_pct": 34.68, "epoch_pct": 34.68, "eta": "37:18:28", "max_grad_norm": 1.0, "loss": 0.5338225960731506, "grad_norm": 0.460282564163208, "learning_rate": 0.00016130550500272195}
-{"ts": "2025-12-27T14:06:05", "event": "train_log", "step": 4934, "epoch": 2.081856540084388, "progress_pct": 34.7, "epoch_pct": 34.7, "eta": "37:17:35", "max_grad_norm": 1.0, "loss": 0.6192039251327515, "grad_norm": 0.4316645860671997, "learning_rate": 0.0001612675529023808}
-{"ts": "2025-12-27T14:06:21", "event": "train_log", "step": 4936, "epoch": 2.0827004219409284, "progress_pct": 34.71, "epoch_pct": 34.71, "eta": "37:16:42", "max_grad_norm": 1.0, "loss": 0.5953296422958374, "grad_norm": 0.4333813488483429, "learning_rate": 0.0001612295866687919}
-{"ts": "2025-12-27T14:06:37", "event": "train_log", "step": 4938, "epoch": 2.0835443037974684, "progress_pct": 34.73, "epoch_pct": 34.73, "eta": "37:15:48", "max_grad_norm": 1.0, "loss": 0.6765958070755005, "grad_norm": 0.560342013835907, "learning_rate": 0.0001611916063107133}
-{"ts": "2025-12-27T14:06:54", "event": "train_log", "step": 4940, "epoch": 2.0843881856540083, "progress_pct": 34.74, "epoch_pct": 34.74, "eta": "37:14:57", "max_grad_norm": 1.0, "loss": 0.5475618243217468, "grad_norm": 0.4263869822025299, "learning_rate": 0.00016115361183690631}
-{"ts": "2025-12-27T14:07:10", "event": "train_log", "step": 4942, "epoch": 2.0852320675105487, "progress_pct": 34.75, "epoch_pct": 34.75, "eta": "37:14:05", "max_grad_norm": 1.0, "loss": 0.570278525352478, "grad_norm": 0.41631078720092773, "learning_rate": 0.00016111560325613553}
-{"ts": "2025-12-27T14:07:27", "event": "train_log", "step": 4944, "epoch": 2.0860759493670886, "progress_pct": 34.77, "epoch_pct": 34.77, "eta": "37:13:12", "max_grad_norm": 1.0, "loss": 0.5691710710525513, "grad_norm": 0.3922317326068878, "learning_rate": 0.00016107758057716884}
-{"ts": "2025-12-27T14:07:42", "event": "train_log", "step": 4946, "epoch": 2.0869198312236286, "progress_pct": 34.78, "epoch_pct": 34.78, "eta": "37:12:19", "max_grad_norm": 1.0, "loss": 0.6014654040336609, "grad_norm": 0.518889307975769, "learning_rate": 0.00016103954380877736}
-{"ts": "2025-12-27T14:07:58", "event": "train_log", "step": 4948, "epoch": 2.087763713080169, "progress_pct": 34.8, "epoch_pct": 34.8, "eta": "37:11:25", "max_grad_norm": 1.0, "loss": 0.6084938049316406, "grad_norm": 0.560624897480011, "learning_rate": 0.00016100149295973537}
-{"ts": "2025-12-27T14:08:14", "event": "train_log", "step": 4950, "epoch": 2.088607594936709, "progress_pct": 34.81, "epoch_pct": 34.81, "eta": "37:10:31", "max_grad_norm": 1.0, "loss": 0.6078231334686279, "grad_norm": 0.46847012639045715, "learning_rate": 0.00016096342803882053}
-{"ts": "2025-12-27T14:08:29", "event": "train_log", "step": 4952, "epoch": 2.089451476793249, "progress_pct": 34.82, "epoch_pct": 34.82, "eta": "37:09:38", "max_grad_norm": 1.0, "loss": 0.5664147734642029, "grad_norm": 0.43910443782806396, "learning_rate": 0.00016092534905481367}
-{"ts": "2025-12-27T14:08:45", "event": "train_log", "step": 4954, "epoch": 2.090295358649789, "progress_pct": 34.84, "epoch_pct": 34.84, "eta": "37:08:45", "max_grad_norm": 1.0, "loss": 0.5793747901916504, "grad_norm": 0.40413206815719604, "learning_rate": 0.00016088725601649887}
-{"ts": "2025-12-27T14:09:01", "event": "train_log", "step": 4956, "epoch": 2.091139240506329, "progress_pct": 34.85, "epoch_pct": 34.85, "eta": "37:07:51", "max_grad_norm": 1.0, "loss": 0.6121629476547241, "grad_norm": 0.47664782404899597, "learning_rate": 0.00016084914893266347}
-{"ts": "2025-12-27T14:09:16", "event": "train_log", "step": 4958, "epoch": 2.091983122362869, "progress_pct": 34.87, "epoch_pct": 34.87, "eta": "37:06:56", "max_grad_norm": 1.0, "loss": 0.6086400747299194, "grad_norm": 0.4575684070587158, "learning_rate": 0.00016081102781209805}
-{"ts": "2025-12-27T14:09:32", "event": "train_log", "step": 4960, "epoch": 2.0928270042194095, "progress_pct": 34.88, "epoch_pct": 34.88, "eta": "37:06:03", "max_grad_norm": 1.0, "loss": 0.5971894860267639, "grad_norm": 0.4286920726299286, "learning_rate": 0.0001607728926635964}
-{"ts": "2025-12-27T14:09:47", "event": "train_log", "step": 4962, "epoch": 2.0936708860759494, "progress_pct": 34.89, "epoch_pct": 34.89, "eta": "37:05:09", "max_grad_norm": 1.0, "loss": 0.6195604801177979, "grad_norm": 0.5314067006111145, "learning_rate": 0.00016073474349595555}
-{"ts": "2025-12-27T14:10:02", "event": "train_log", "step": 4964, "epoch": 2.0945147679324894, "progress_pct": 34.91, "epoch_pct": 34.91, "eta": "37:04:15", "max_grad_norm": 1.0, "loss": 0.6141531467437744, "grad_norm": 0.5221946239471436, "learning_rate": 0.00016069658031797585}
-{"ts": "2025-12-27T14:10:19", "event": "train_log", "step": 4966, "epoch": 2.0953586497890297, "progress_pct": 34.92, "epoch_pct": 34.92, "eta": "37:03:23", "max_grad_norm": 1.0, "loss": 0.6354720592498779, "grad_norm": 0.46874696016311646, "learning_rate": 0.00016065840313846076}
-{"ts": "2025-12-27T14:10:35", "event": "train_log", "step": 4968, "epoch": 2.0962025316455697, "progress_pct": 34.94, "epoch_pct": 34.94, "eta": "37:02:30", "max_grad_norm": 1.0, "loss": 0.5759334564208984, "grad_norm": 0.44518616795539856, "learning_rate": 0.00016062021196621703}
-{"ts": "2025-12-27T14:10:52", "event": "train_log", "step": 4970, "epoch": 2.0970464135021096, "progress_pct": 34.95, "epoch_pct": 34.95, "eta": "37:01:40", "max_grad_norm": 1.0, "loss": 0.5387811064720154, "grad_norm": 0.44092273712158203, "learning_rate": 0.00016058200681005462}
-{"ts": "2025-12-27T14:11:08", "event": "train_log", "step": 4972, "epoch": 2.09789029535865, "progress_pct": 34.96, "epoch_pct": 34.96, "eta": "37:00:47", "max_grad_norm": 1.0, "loss": 0.5712288022041321, "grad_norm": 0.4952426552772522, "learning_rate": 0.00016054378767878678}
-{"ts": "2025-12-27T14:11:25", "event": "train_log", "step": 4974, "epoch": 2.09873417721519, "progress_pct": 34.98, "epoch_pct": 34.98, "eta": "36:59:56", "max_grad_norm": 1.0, "loss": 0.6320934891700745, "grad_norm": 0.4890255331993103, "learning_rate": 0.00016050555458122984}
-{"ts": "2025-12-27T14:11:39", "event": "train_log", "step": 4976, "epoch": 2.09957805907173, "progress_pct": 34.99, "epoch_pct": 34.99, "eta": "36:59:01", "max_grad_norm": 1.0, "loss": 0.6141278147697449, "grad_norm": 0.5182738304138184, "learning_rate": 0.00016046730752620352}
-{"ts": "2025-12-27T14:11:54", "event": "train_log", "step": 4978, "epoch": 2.10042194092827, "progress_pct": 35.01, "epoch_pct": 35.01, "eta": "36:58:06", "max_grad_norm": 1.0, "loss": 0.6079437732696533, "grad_norm": 0.5344594717025757, "learning_rate": 0.00016042904652253064}
-{"ts": "2025-12-27T14:12:10", "event": "train_log", "step": 4980, "epoch": 2.1012658227848102, "progress_pct": 35.02, "epoch_pct": 35.02, "eta": "36:57:13", "max_grad_norm": 1.0, "loss": 0.5634552836418152, "grad_norm": 0.436641126871109, "learning_rate": 0.0001603907715790373}
-{"ts": "2025-12-27T14:12:26", "event": "train_log", "step": 4982, "epoch": 2.10210970464135, "progress_pct": 35.04, "epoch_pct": 35.04, "eta": "36:56:20", "max_grad_norm": 1.0, "loss": 0.5707821846008301, "grad_norm": 0.44045236706733704, "learning_rate": 0.00016035248270455273}
-{"ts": "2025-12-27T14:12:42", "event": "train_log", "step": 4984, "epoch": 2.10295358649789, "progress_pct": 35.05, "epoch_pct": 35.05, "eta": "36:55:28", "max_grad_norm": 1.0, "loss": 0.5635452270507812, "grad_norm": 0.43434852361679077, "learning_rate": 0.00016031417990790953}
-{"ts": "2025-12-27T14:12:57", "event": "train_log", "step": 4986, "epoch": 2.1037974683544305, "progress_pct": 35.06, "epoch_pct": 35.06, "eta": "36:54:33", "max_grad_norm": 1.0, "loss": 0.632486879825592, "grad_norm": 0.5538138747215271, "learning_rate": 0.00016027586319794341}
-{"ts": "2025-12-27T14:13:12", "event": "train_log", "step": 4988, "epoch": 2.1046413502109704, "progress_pct": 35.08, "epoch_pct": 35.08, "eta": "36:53:39", "max_grad_norm": 1.0, "loss": 0.6509168744087219, "grad_norm": 0.5425865054130554, "learning_rate": 0.00016023753258349323}
-{"ts": "2025-12-27T14:13:27", "event": "train_log", "step": 4990, "epoch": 2.1054852320675104, "progress_pct": 35.09, "epoch_pct": 35.09, "eta": "36:52:45", "max_grad_norm": 1.0, "loss": 0.615444540977478, "grad_norm": 0.4603687524795532, "learning_rate": 0.0001601991880734012}
-{"ts": "2025-12-27T14:13:42", "event": "train_log", "step": 4992, "epoch": 2.1063291139240508, "progress_pct": 35.11, "epoch_pct": 35.11, "eta": "36:51:52", "max_grad_norm": 1.0, "loss": 0.684465765953064, "grad_norm": 0.4866391718387604, "learning_rate": 0.0001601608296765126}
-{"ts": "2025-12-27T14:13:57", "event": "train_log", "step": 4994, "epoch": 2.1071729957805907, "progress_pct": 35.12, "epoch_pct": 35.12, "eta": "36:50:57", "max_grad_norm": 1.0, "loss": 0.5981772541999817, "grad_norm": 0.47539305686950684, "learning_rate": 0.000160122457401676}
-{"ts": "2025-12-27T14:14:14", "event": "train_log", "step": 4996, "epoch": 2.1080168776371306, "progress_pct": 35.13, "epoch_pct": 35.13, "eta": "36:50:06", "max_grad_norm": 1.0, "loss": 0.6041272878646851, "grad_norm": 0.4135447144508362, "learning_rate": 0.00016008407125774315}
-{"ts": "2025-12-27T14:14:30", "event": "train_log", "step": 4998, "epoch": 2.108860759493671, "progress_pct": 35.15, "epoch_pct": 35.15, "eta": "36:49:14", "max_grad_norm": 1.0, "loss": 0.6491074562072754, "grad_norm": 0.5324689745903015, "learning_rate": 0.00016004567125356905}
-{"ts": "2025-12-27T14:14:47", "event": "train_log", "step": 5000, "epoch": 2.109704641350211, "progress_pct": 35.16, "epoch_pct": 35.16, "eta": "36:48:24", "max_grad_norm": 1.0, "loss": 0.6178454756736755, "grad_norm": 0.4004698395729065, "learning_rate": 0.00016000725739801172}
-{"ts": "2025-12-27T14:25:57", "event": "train_log", "step": 5000, "epoch": 2.109704641350211, "progress_pct": 35.16, "epoch_pct": 35.16, "eta": "37:08:58", "max_grad_norm": 1.0, "eval_loss": 0.7635271549224854, "eval_runtime": 669.5049, "eval_samples_per_second": 3.147, "eval_steps_per_second": 3.147}
-{"ts": "2025-12-27T14:26:13", "event": "train_log", "step": 5002, "epoch": 2.110548523206751, "progress_pct": 35.18, "epoch_pct": 35.18, "eta": "37:08:07", "max_grad_norm": 1.0, "loss": 0.6120179295539856, "grad_norm": 0.37075328826904297, "learning_rate": 0.00015996882969993262}
-{"ts": "2025-12-27T14:26:29", "event": "train_log", "step": 5004, "epoch": 2.1113924050632913, "progress_pct": 35.19, "epoch_pct": 35.19, "eta": "37:07:12", "max_grad_norm": 1.0, "loss": 0.5534689426422119, "grad_norm": 0.40976548194885254, "learning_rate": 0.0001599303881681962}
-{"ts": "2025-12-27T14:26:43", "event": "train_log", "step": 5006, "epoch": 2.1122362869198312, "progress_pct": 35.2, "epoch_pct": 35.2, "eta": "37:06:17", "max_grad_norm": 1.0, "loss": 0.6165696978569031, "grad_norm": 0.5793944597244263, "learning_rate": 0.00015989193281167022}
-{"ts": "2025-12-27T14:26:59", "event": "train_log", "step": 5008, "epoch": 2.113080168776371, "progress_pct": 35.22, "epoch_pct": 35.22, "eta": "37:05:24", "max_grad_norm": 1.0, "loss": 0.5813543796539307, "grad_norm": 0.501341700553894, "learning_rate": 0.00015985346363922562}
-{"ts": "2025-12-27T14:27:15", "event": "train_log", "step": 5010, "epoch": 2.1139240506329116, "progress_pct": 35.23, "epoch_pct": 35.23, "eta": "37:04:31", "max_grad_norm": 1.0, "loss": 0.6293289661407471, "grad_norm": 0.41892293095588684, "learning_rate": 0.00015981498065973642}
-{"ts": "2025-12-27T14:27:30", "event": "train_log", "step": 5012, "epoch": 2.1147679324894515, "progress_pct": 35.25, "epoch_pct": 35.25, "eta": "37:03:35", "max_grad_norm": 1.0, "loss": 0.621943473815918, "grad_norm": 0.5439590215682983, "learning_rate": 0.00015977648388208}
-{"ts": "2025-12-27T14:27:44", "event": "train_log", "step": 5014, "epoch": 2.1156118143459914, "progress_pct": 35.26, "epoch_pct": 35.26, "eta": "37:02:40", "max_grad_norm": 1.0, "loss": 0.6048483848571777, "grad_norm": 0.4917672276496887, "learning_rate": 0.00015973797331513673}
-{"ts": "2025-12-27T14:27:59", "event": "train_log", "step": 5016, "epoch": 2.116455696202532, "progress_pct": 35.27, "epoch_pct": 35.27, "eta": "37:01:44", "max_grad_norm": 1.0, "loss": 0.5886700749397278, "grad_norm": 0.5026940107345581, "learning_rate": 0.00015969944896779034}
-{"ts": "2025-12-27T14:28:14", "event": "train_log", "step": 5018, "epoch": 2.1172995780590718, "progress_pct": 35.29, "epoch_pct": 35.29, "eta": "37:00:51", "max_grad_norm": 1.0, "loss": 0.6189847588539124, "grad_norm": 0.4289521872997284, "learning_rate": 0.0001596609108489276}
-{"ts": "2025-12-27T14:28:29", "event": "train_log", "step": 5020, "epoch": 2.1181434599156117, "progress_pct": 35.3, "epoch_pct": 35.3, "eta": "36:59:56", "max_grad_norm": 1.0, "loss": 0.6217852830886841, "grad_norm": 0.4428614675998688, "learning_rate": 0.00015962235896743854}
-{"ts": "2025-12-27T14:28:44", "event": "train_log", "step": 5022, "epoch": 2.118987341772152, "progress_pct": 35.32, "epoch_pct": 35.32, "eta": "36:59:01", "max_grad_norm": 1.0, "loss": 0.6325339078903198, "grad_norm": 0.46286383271217346, "learning_rate": 0.00015958379333221636}
-{"ts": "2025-12-27T14:28:59", "event": "train_log", "step": 5024, "epoch": 2.119831223628692, "progress_pct": 35.33, "epoch_pct": 35.33, "eta": "36:58:07", "max_grad_norm": 1.0, "loss": 0.6053416728973389, "grad_norm": 0.4348789155483246, "learning_rate": 0.00015954521395215735}
-{"ts": "2025-12-27T14:29:14", "event": "train_log", "step": 5026, "epoch": 2.120675105485232, "progress_pct": 35.34, "epoch_pct": 35.34, "eta": "36:57:12", "max_grad_norm": 1.0, "loss": 0.5830395817756653, "grad_norm": 0.43629688024520874, "learning_rate": 0.00015950662083616109}
-{"ts": "2025-12-27T14:29:29", "event": "train_log", "step": 5028, "epoch": 2.1215189873417724, "progress_pct": 35.36, "epoch_pct": 35.36, "eta": "36:56:18", "max_grad_norm": 1.0, "loss": 0.6273260116577148, "grad_norm": 0.45533162355422974, "learning_rate": 0.00015946801399313023}
-{"ts": "2025-12-27T14:29:44", "event": "train_log", "step": 5030, "epoch": 2.1223628691983123, "progress_pct": 35.37, "epoch_pct": 35.37, "eta": "36:55:24", "max_grad_norm": 1.0, "loss": 0.6343342661857605, "grad_norm": 0.5445238351821899, "learning_rate": 0.00015942939343197064}
-{"ts": "2025-12-27T14:29:59", "event": "train_log", "step": 5032, "epoch": 2.1232067510548522, "progress_pct": 35.39, "epoch_pct": 35.39, "eta": "36:54:30", "max_grad_norm": 1.0, "loss": 0.6357948780059814, "grad_norm": 0.4698406457901001, "learning_rate": 0.0001593907591615914}
-{"ts": "2025-12-27T14:30:14", "event": "train_log", "step": 5034, "epoch": 2.124050632911392, "progress_pct": 35.4, "epoch_pct": 35.4, "eta": "36:53:35", "max_grad_norm": 1.0, "loss": 0.6478350162506104, "grad_norm": 0.5374915599822998, "learning_rate": 0.0001593521111909046}
-{"ts": "2025-12-27T14:30:30", "event": "train_log", "step": 5036, "epoch": 2.1248945147679326, "progress_pct": 35.41, "epoch_pct": 35.41, "eta": "36:52:42", "max_grad_norm": 1.0, "loss": 0.5516082048416138, "grad_norm": 0.4432879388332367, "learning_rate": 0.00015931344952882563}
-{"ts": "2025-12-27T14:30:45", "event": "train_log", "step": 5038, "epoch": 2.1257383966244725, "progress_pct": 35.43, "epoch_pct": 35.43, "eta": "36:51:48", "max_grad_norm": 1.0, "loss": 0.751211404800415, "grad_norm": 0.5592076778411865, "learning_rate": 0.00015927477418427302}
-{"ts": "2025-12-27T14:31:00", "event": "train_log", "step": 5040, "epoch": 2.1265822784810124, "progress_pct": 35.44, "epoch_pct": 35.44, "eta": "36:50:55", "max_grad_norm": 1.0, "loss": 0.6150388717651367, "grad_norm": 0.47873231768608093, "learning_rate": 0.00015923608516616838}
-{"ts": "2025-12-27T14:31:16", "event": "train_log", "step": 5042, "epoch": 2.127426160337553, "progress_pct": 35.46, "epoch_pct": 35.46, "eta": "36:50:01", "max_grad_norm": 1.0, "loss": 0.6196672320365906, "grad_norm": 0.4760212302207947, "learning_rate": 0.00015919738248343653}
-{"ts": "2025-12-27T14:31:30", "event": "train_log", "step": 5044, "epoch": 2.1282700421940928, "progress_pct": 35.47, "epoch_pct": 35.47, "eta": "36:49:06", "max_grad_norm": 1.0, "loss": 0.6550422310829163, "grad_norm": 0.4995400011539459, "learning_rate": 0.00015915866614500546}
-{"ts": "2025-12-27T14:31:47", "event": "train_log", "step": 5046, "epoch": 2.1291139240506327, "progress_pct": 35.49, "epoch_pct": 35.49, "eta": "36:48:14", "max_grad_norm": 1.0, "loss": 0.6072712540626526, "grad_norm": 0.495466023683548, "learning_rate": 0.00015911993615980627}
-{"ts": "2025-12-27T14:32:01", "event": "train_log", "step": 5048, "epoch": 2.129957805907173, "progress_pct": 35.5, "epoch_pct": 35.5, "eta": "36:47:20", "max_grad_norm": 1.0, "loss": 0.6082064509391785, "grad_norm": 0.4815806448459625, "learning_rate": 0.00015908119253677322}
-{"ts": "2025-12-27T14:32:16", "event": "train_log", "step": 5050, "epoch": 2.130801687763713, "progress_pct": 35.51, "epoch_pct": 35.51, "eta": "36:46:25", "max_grad_norm": 1.0, "loss": 0.5966012477874756, "grad_norm": 0.43178048729896545, "learning_rate": 0.00015904243528484373}
-{"ts": "2025-12-27T14:32:33", "event": "train_log", "step": 5052, "epoch": 2.131645569620253, "progress_pct": 35.53, "epoch_pct": 35.53, "eta": "36:45:34", "max_grad_norm": 1.0, "loss": 0.5763883590698242, "grad_norm": 0.4170011281967163, "learning_rate": 0.00015900366441295836}
-{"ts": "2025-12-27T14:32:47", "event": "train_log", "step": 5054, "epoch": 2.1324894514767934, "progress_pct": 35.54, "epoch_pct": 35.54, "eta": "36:44:40", "max_grad_norm": 1.0, "loss": 0.6827293634414673, "grad_norm": 0.48954638838768005, "learning_rate": 0.0001589648799300608}
-{"ts": "2025-12-27T14:33:04", "event": "train_log", "step": 5056, "epoch": 2.1333333333333333, "progress_pct": 35.56, "epoch_pct": 35.56, "eta": "36:43:48", "max_grad_norm": 1.0, "loss": 0.5683901309967041, "grad_norm": 0.42273828387260437, "learning_rate": 0.00015892608184509788}
-{"ts": "2025-12-27T14:33:19", "event": "train_log", "step": 5058, "epoch": 2.1341772151898732, "progress_pct": 35.57, "epoch_pct": 35.57, "eta": "36:42:55", "max_grad_norm": 1.0, "loss": 0.5256756544113159, "grad_norm": 0.43793967366218567, "learning_rate": 0.00015888727016701956}
-{"ts": "2025-12-27T14:33:34", "event": "train_log", "step": 5060, "epoch": 2.1350210970464136, "progress_pct": 35.58, "epoch_pct": 35.58, "eta": "36:42:01", "max_grad_norm": 1.0, "loss": 0.5872990489006042, "grad_norm": 0.49315446615219116, "learning_rate": 0.000158848444904779}
-{"ts": "2025-12-27T14:33:50", "event": "train_log", "step": 5062, "epoch": 2.1358649789029536, "progress_pct": 35.6, "epoch_pct": 35.6, "eta": "36:41:07", "max_grad_norm": 1.0, "loss": 0.6437247395515442, "grad_norm": 0.47955402731895447, "learning_rate": 0.00015880960606733235}
-{"ts": "2025-12-27T14:34:05", "event": "train_log", "step": 5064, "epoch": 2.1367088607594935, "progress_pct": 35.61, "epoch_pct": 35.61, "eta": "36:40:14", "max_grad_norm": 1.0, "loss": 0.6244118809700012, "grad_norm": 0.49625128507614136, "learning_rate": 0.0001587707536636391}
-{"ts": "2025-12-27T14:34:20", "event": "train_log", "step": 5066, "epoch": 2.137552742616034, "progress_pct": 35.63, "epoch_pct": 35.63, "eta": "36:39:20", "max_grad_norm": 1.0, "loss": 0.6575133800506592, "grad_norm": 0.5150440335273743, "learning_rate": 0.00015873188770266166}
-{"ts": "2025-12-27T14:34:35", "event": "train_log", "step": 5068, "epoch": 2.138396624472574, "progress_pct": 35.64, "epoch_pct": 35.64, "eta": "36:38:27", "max_grad_norm": 1.0, "loss": 0.6086075305938721, "grad_norm": 0.5271725654602051, "learning_rate": 0.0001586930081933657}
-{"ts": "2025-12-27T14:34:51", "event": "train_log", "step": 5070, "epoch": 2.1392405063291138, "progress_pct": 35.65, "epoch_pct": 35.65, "eta": "36:37:34", "max_grad_norm": 1.0, "loss": 0.6213793158531189, "grad_norm": 0.4663483202457428, "learning_rate": 0.00015865411514471997}
-{"ts": "2025-12-27T14:35:06", "event": "train_log", "step": 5072, "epoch": 2.140084388185654, "progress_pct": 35.67, "epoch_pct": 35.67, "eta": "36:36:41", "max_grad_norm": 1.0, "loss": 0.5942427515983582, "grad_norm": 0.44225719571113586, "learning_rate": 0.00015861520856569634}
-{"ts": "2025-12-27T14:35:23", "event": "train_log", "step": 5074, "epoch": 2.140928270042194, "progress_pct": 35.68, "epoch_pct": 35.68, "eta": "36:35:51", "max_grad_norm": 1.0, "loss": 0.5674160122871399, "grad_norm": 0.41664719581604004, "learning_rate": 0.00015857628846526985}
-{"ts": "2025-12-27T14:35:37", "event": "train_log", "step": 5076, "epoch": 2.141772151898734, "progress_pct": 35.7, "epoch_pct": 35.7, "eta": "36:34:56", "max_grad_norm": 1.0, "loss": 0.6162048578262329, "grad_norm": 0.47769808769226074, "learning_rate": 0.00015853735485241857}
-{"ts": "2025-12-27T14:35:53", "event": "train_log", "step": 5078, "epoch": 2.1426160337552744, "progress_pct": 35.71, "epoch_pct": 35.71, "eta": "36:34:04", "max_grad_norm": 1.0, "loss": 0.619512677192688, "grad_norm": 0.46560928225517273, "learning_rate": 0.00015849840773612375}
-{"ts": "2025-12-27T14:36:09", "event": "train_log", "step": 5080, "epoch": 2.1434599156118144, "progress_pct": 35.72, "epoch_pct": 35.72, "eta": "36:33:12", "max_grad_norm": 1.0, "loss": 0.6183180809020996, "grad_norm": 0.4625875949859619, "learning_rate": 0.00015845944712536975}
-{"ts": "2025-12-27T14:36:26", "event": "train_log", "step": 5082, "epoch": 2.1443037974683543, "progress_pct": 35.74, "epoch_pct": 35.74, "eta": "36:32:21", "max_grad_norm": 1.0, "loss": 0.548591673374176, "grad_norm": 0.3870140314102173, "learning_rate": 0.00015842047302914406}
-{"ts": "2025-12-27T14:36:43", "event": "train_log", "step": 5084, "epoch": 2.1451476793248947, "progress_pct": 35.75, "epoch_pct": 35.75, "eta": "36:31:32", "max_grad_norm": 1.0, "loss": 0.6416457295417786, "grad_norm": 0.48335012793540955, "learning_rate": 0.0001583814854564372}
-{"ts": "2025-12-27T14:36:58", "event": "train_log", "step": 5086, "epoch": 2.1459915611814346, "progress_pct": 35.77, "epoch_pct": 35.77, "eta": "36:30:39", "max_grad_norm": 1.0, "loss": 0.6126701235771179, "grad_norm": 0.5226625204086304, "learning_rate": 0.0001583424844162429}
-{"ts": "2025-12-27T14:37:15", "event": "train_log", "step": 5088, "epoch": 2.1468354430379746, "progress_pct": 35.78, "epoch_pct": 35.78, "eta": "36:29:48", "max_grad_norm": 1.0, "loss": 0.6021472215652466, "grad_norm": 0.5319521427154541, "learning_rate": 0.0001583034699175579}
-{"ts": "2025-12-27T14:37:31", "event": "train_log", "step": 5090, "epoch": 2.147679324894515, "progress_pct": 35.79, "epoch_pct": 35.79, "eta": "36:28:57", "max_grad_norm": 1.0, "loss": 0.6050764918327332, "grad_norm": 0.49504420161247253, "learning_rate": 0.00015826444196938218}
-{"ts": "2025-12-27T14:37:47", "event": "train_log", "step": 5092, "epoch": 2.148523206751055, "progress_pct": 35.81, "epoch_pct": 35.81, "eta": "36:28:06", "max_grad_norm": 1.0, "loss": 0.592272162437439, "grad_norm": 0.5531564950942993, "learning_rate": 0.00015822540058071864}
-{"ts": "2025-12-27T14:38:03", "event": "train_log", "step": 5094, "epoch": 2.149367088607595, "progress_pct": 35.82, "epoch_pct": 35.82, "eta": "36:27:14", "max_grad_norm": 1.0, "loss": 0.6607300043106079, "grad_norm": 0.44624611735343933, "learning_rate": 0.00015818634576057346}
-{"ts": "2025-12-27T14:38:20", "event": "train_log", "step": 5096, "epoch": 2.1502109704641352, "progress_pct": 35.84, "epoch_pct": 35.84, "eta": "36:26:23", "max_grad_norm": 1.0, "loss": 0.6294105648994446, "grad_norm": 0.46433159708976746, "learning_rate": 0.00015814727751795578}
-{"ts": "2025-12-27T14:38:35", "event": "train_log", "step": 5098, "epoch": 2.151054852320675, "progress_pct": 35.85, "epoch_pct": 35.85, "eta": "36:25:30", "max_grad_norm": 1.0, "loss": 0.5308064818382263, "grad_norm": 0.46241268515586853, "learning_rate": 0.00015810819586187792}
-{"ts": "2025-12-27T14:38:51", "event": "train_log", "step": 5100, "epoch": 2.151898734177215, "progress_pct": 35.86, "epoch_pct": 35.86, "eta": "36:24:38", "max_grad_norm": 1.0, "loss": 0.6138747930526733, "grad_norm": 0.48821282386779785, "learning_rate": 0.00015806910080135527}
-{"ts": "2025-12-27T14:50:12", "event": "train_log", "step": 5100, "epoch": 2.151898734177215, "progress_pct": 35.86, "epoch_pct": 35.86, "eta": "36:44:57", "max_grad_norm": 1.0, "eval_loss": 0.7654595971107483, "eval_runtime": 681.4966, "eval_samples_per_second": 3.092, "eval_steps_per_second": 3.092}
-{"ts": "2025-12-27T14:50:12", "event": "train_log", "step": 5100, "epoch": 2.151898734177215, "progress_pct": 35.86, "epoch_pct": 35.86, "eta": "36:44:57", "max_grad_norm": 1.0, "train_runtime": 73982.3221, "train_samples_per_second": 1.538, "train_steps_per_second": 0.192, "total_flos": 3.049019256156893e+18, "train_loss": 0.8076860591944526}
-{"ts": "2025-12-27T15:01:27", "event": "train_log", "step": 5100, "epoch": 2.151898734177215, "progress_pct": 35.86, "epoch_pct": 35.86, "eta": "37:05:04", "max_grad_norm": 1.0, "eval_loss": 0.7600579857826233, "eval_runtime": 674.048, "eval_samples_per_second": 3.126, "eval_steps_per_second": 3.126}
+{"ts": "2025-12-27T19:40:44", "event": "train_log", "step": 5, "epoch": 0.02002002002002002, "progress_pct": 1.0, "epoch_pct": 1.0, "eta": "02:23:23", "max_grad_norm": 1.0, "loss": 0.007, "grad_norm": 0.06052486598491669, "learning_rate": 8.000000000000001e-07, "grpo_mean_advantage": -1.3560057254835556e-07, "grpo_std_advantage": 3.0318567496578908e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5922331809997559}
+{"ts": "2025-12-27T19:46:55", "event": "train_log", "step": 5, "epoch": 0.02002002002002002, "progress_pct": 1.0, "epoch_pct": 1.0, "eta": "02:16:53", "max_grad_norm": 1.0, "loss": 0.007, "grad_norm": 0.05460292845964432, "learning_rate": 8.000000000000001e-07, "grpo_mean_advantage": -1.3560057254835556e-07, "grpo_std_advantage": 3.0318567496578908e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5922331809997559}
+{"ts": "2025-12-27T19:48:18", "event": "train_log", "step": 10, "epoch": 0.04004004004004004, "progress_pct": 2.0, "epoch_pct": 2.0, "eta": "02:15:24", "max_grad_norm": 1.0, "loss": 0.0107, "grad_norm": 0.0679207444190979, "learning_rate": 1.8000000000000001e-06, "grpo_mean_advantage": 3.6619603633880615e-06, "grpo_std_advantage": 1.6246918676188216e-05, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5561589002609253}
+{"ts": "2025-12-27T19:49:40", "event": "train_log", "step": 15, "epoch": 0.06006006006006006, "progress_pct": 3.0, "epoch_pct": 3.0, "eta": "02:13:25", "max_grad_norm": 1.0, "loss": 0.007, "grad_norm": 0.05788416787981987, "learning_rate": 2.8000000000000003e-06, "grpo_mean_advantage": -1.0654330395709621e-07, "grpo_std_advantage": 5.399440965447866e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5759152173995972}
+{"ts": "2025-12-27T19:51:01", "event": "train_log", "step": 20, "epoch": 0.08008008008008008, "progress_pct": 4.0, "epoch_pct": 4.0, "eta": "02:11:33", "max_grad_norm": 1.0, "loss": 0.0246, "grad_norm": 0.0746568813920021, "learning_rate": 3.8000000000000005e-06, "grpo_mean_advantage": -5.871057737749652e-07, "grpo_std_advantage": 2.6951597646984737e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5127314329147339}
+{"ts": "2025-12-27T19:52:23", "event": "train_log", "step": 25, "epoch": 0.1001001001001001, "progress_pct": 5.0, "epoch_pct": 5.01, "eta": "02:10:02", "max_grad_norm": 1.0, "loss": 0.0337, "grad_norm": 0.11442846059799194, "learning_rate": 4.800000000000001e-06, "grpo_mean_advantage": 6.370246410369873e-07, "grpo_std_advantage": 2.8908377771585947e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.539706826210022}
+{"ts": "2025-12-27T19:53:48", "event": "train_log", "step": 30, "epoch": 0.12012012012012012, "progress_pct": 6.0, "epoch_pct": 6.01, "eta": "02:09:24", "max_grad_norm": 1.0, "loss": 0.0171, "grad_norm": 0.05778791010379791, "learning_rate": 4.999125183044924e-06, "grpo_mean_advantage": 6.705522359595761e-09, "grpo_std_advantage": 6.189450800775376e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5812538862228394}
+{"ts": "2025-12-27T19:55:13", "event": "train_log", "step": 35, "epoch": 0.14014014014014015, "progress_pct": 7.0, "epoch_pct": 7.01, "eta": "02:08:36", "max_grad_norm": 1.0, "loss": 0.0145, "grad_norm": 0.05819695070385933, "learning_rate": 4.995572288443412e-06, "grpo_mean_advantage": 3.859400692363124e-07, "grpo_std_advantage": 1.6833292875162442e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5909844636917114}
+{"ts": "2025-12-27T19:56:38", "event": "train_log", "step": 40, "epoch": 0.16016016016016016, "progress_pct": 8.0, "epoch_pct": 8.01, "eta": "02:07:30", "max_grad_norm": 1.0, "loss": 0.0196, "grad_norm": 0.07968433201313019, "learning_rate": 4.98929052218411e-06, "grpo_mean_advantage": 2.600252742013254e-07, "grpo_std_advantage": 1.4095899132371414e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5630953907966614}
+{"ts": "2025-12-27T19:58:00", "event": "train_log", "step": 45, "epoch": 0.18018018018018017, "progress_pct": 9.0, "epoch_pct": 9.01, "eta": "02:06:04", "max_grad_norm": 1.0, "loss": 0.0186, "grad_norm": 0.0733402892947197, "learning_rate": 4.980286753286196e-06, "grpo_mean_advantage": -1.2591480924584175e-07, "grpo_std_advantage": 1.0309080380466185e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5604403614997864}
+{"ts": "2025-12-27T19:59:27", "event": "train_log", "step": 50, "epoch": 0.2002002002002002, "progress_pct": 10.0, "epoch_pct": 10.01, "eta": "02:05:12", "max_grad_norm": 1.0, "loss": 0.0286, "grad_norm": 0.07136482000350952, "learning_rate": 4.9685708272387645e-06, "grpo_mean_advantage": -2.808868941883702e-07, "grpo_std_advantage": 1.5696078889959608e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5971035957336426}
+{"ts": "2025-12-27T20:00:53", "event": "train_log", "step": 55, "epoch": 0.22022022022022023, "progress_pct": 11.0, "epoch_pct": 11.01, "eta": "02:04:07", "max_grad_norm": 1.0, "loss": 0.0054, "grad_norm": 0.08851475268602371, "learning_rate": 4.9541555552349404e-06, "grpo_mean_advantage": 2.6822089438383045e-08, "grpo_std_advantage": 3.7878271541558206e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5892971754074097}
+{"ts": "2025-12-27T20:02:17", "event": "train_log", "step": 60, "epoch": 0.24024024024024024, "progress_pct": 12.0, "epoch_pct": 12.01, "eta": "02:02:51", "max_grad_norm": 1.0, "loss": -0.0074, "grad_norm": 0.07778509706258774, "learning_rate": 4.9370567001630155e-06, "grpo_mean_advantage": -5.662441182607836e-08, "grpo_std_advantage": 6.128998393251095e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.564322292804718}
+{"ts": "2025-12-27T20:03:45", "event": "train_log", "step": 65, "epoch": 0.2602602602602603, "progress_pct": 13.0, "epoch_pct": 13.01, "eta": "02:01:55", "max_grad_norm": 1.0, "loss": 0.0145, "grad_norm": 0.08740051090717316, "learning_rate": 4.917292959369968e-06, "grpo_mean_advantage": -1.5944242193199898e-07, "grpo_std_advantage": 1.6374274309782777e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.562497615814209}
+{"ts": "2025-12-27T20:05:10", "event": "train_log", "step": 70, "epoch": 0.2802802802802803, "progress_pct": 14.0, "epoch_pct": 14.01, "eta": "02:00:32", "max_grad_norm": 1.0, "loss": 0.0257, "grad_norm": 0.19070060551166534, "learning_rate": 4.8948859442161876e-06, "grpo_mean_advantage": 1.6838312433264946e-07, "grpo_std_advantage": 8.536571272088622e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5904761552810669}
+{"ts": "2025-12-27T20:06:36", "event": "train_log", "step": 75, "epoch": 0.3003003003003003, "progress_pct": 15.0, "epoch_pct": 15.02, "eta": "01:59:23", "max_grad_norm": 1.0, "loss": 0.0024, "grad_norm": 0.07321271300315857, "learning_rate": 4.869860156443768e-06, "grpo_mean_advantage": 1.1175870895385742e-07, "grpo_std_advantage": 6.451961667153228e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5765624046325684}
+{"ts": "2025-12-27T20:08:03", "event": "train_log", "step": 80, "epoch": 0.3203203203203203, "progress_pct": 16.0, "epoch_pct": 16.02, "eta": "01:58:12", "max_grad_norm": 1.0, "loss": 0.0277, "grad_norm": 0.07126748561859131, "learning_rate": 4.842242961384211e-06, "grpo_mean_advantage": -1.4603138254187797e-07, "grpo_std_advantage": 1.1309343790344428e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5858271718025208}
+{"ts": "2025-12-27T20:09:31", "event": "train_log", "step": 85, "epoch": 0.34034034034034033, "progress_pct": 17.0, "epoch_pct": 17.02, "eta": "01:57:04", "max_grad_norm": 1.0, "loss": 0.0246, "grad_norm": 0.08629189431667328, "learning_rate": 4.812064558034847e-06, "grpo_mean_advantage": -1.817941665649414e-06, "grpo_std_advantage": 1.1141768482048064e-05, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5871662497520447}
+{"ts": "2025-12-27T20:10:55", "event": "train_log", "step": 90, "epoch": 0.36036036036036034, "progress_pct": 18.0, "epoch_pct": 18.02, "eta": "01:55:38", "max_grad_norm": 1.0, "loss": 0.0056, "grad_norm": 0.0998779758810997, "learning_rate": 4.779357946036662e-06, "grpo_mean_advantage": 1.8179416372277046e-07, "grpo_std_advantage": 6.210335072864837e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5330992937088013}
+{"ts": "2025-12-27T20:12:19", "event": "train_log", "step": 95, "epoch": 0.38038038038038036, "progress_pct": 19.0, "epoch_pct": 19.02, "eta": "01:54:09", "max_grad_norm": 1.0, "loss": 0.0053, "grad_norm": 0.10614689439535141, "learning_rate": 4.74415888958968e-06, "grpo_mean_advantage": -2.972781771859445e-07, "grpo_std_advantage": 3.1582342217006953e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5265295505523682}
+{"ts": "2025-12-27T20:13:46", "event": "train_log", "step": 100, "epoch": 0.4004004004004004, "progress_pct": 20.0, "epoch_pct": 20.02, "eta": "01:52:55", "max_grad_norm": 1.0, "loss": 0.0134, "grad_norm": 0.10345634073019028, "learning_rate": 4.706505878345343e-06, "grpo_mean_advantage": -7.033348197182931e-07, "grpo_std_advantage": 4.245831405569334e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5660771131515503}
+{"ts": "2025-12-27T20:15:15", "event": "train_log", "step": 105, "epoch": 0.42042042042042044, "progress_pct": 21.0, "epoch_pct": 21.02, "eta": "01:51:45", "max_grad_norm": 1.0, "loss": 0.0004, "grad_norm": 0.10077933222055435, "learning_rate": 4.666440085318626e-06, "grpo_mean_advantage": 1.1920928955078125e-07, "grpo_std_advantage": 3.2809634831210133e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.57631915807724}
+{"ts": "2025-12-27T20:16:39", "event": "train_log", "step": 110, "epoch": 0.44044044044044045, "progress_pct": 22.0, "epoch_pct": 22.02, "eta": "01:50:19", "max_grad_norm": 1.0, "loss": 0.0033, "grad_norm": 0.09548182785511017, "learning_rate": 4.624005321865968e-06, "grpo_mean_advantage": -4.0978193283081055e-07, "grpo_std_advantage": 6.0397578636184335e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.546563982963562}
+{"ts": "2025-12-27T20:18:01", "event": "train_log", "step": 115, "epoch": 0.46046046046046046, "progress_pct": 23.0, "epoch_pct": 23.02, "eta": "01:48:43", "max_grad_norm": 1.0, "loss": 0.0095, "grad_norm": 0.09417816251516342, "learning_rate": 4.57924798977818e-06, "grpo_mean_advantage": -1.467764434437413e-07, "grpo_std_advantage": 2.2689375782647403e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5519219636917114}
+{"ts": "2025-12-27T20:19:25", "event": "train_log", "step": 120, "epoch": 0.4804804804804805, "progress_pct": 24.0, "epoch_pct": 24.02, "eta": "01:47:18", "max_grad_norm": 1.0, "loss": 0.0006, "grad_norm": 0.10022275149822235, "learning_rate": 4.532217030540781e-06, "grpo_mean_advantage": -5.215406329028838e-09, "grpo_std_advantage": 7.929010621410271e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5490407943725586}
+{"ts": "2025-12-27T20:20:48", "event": "train_log", "step": 125, "epoch": 0.5005005005005005, "progress_pct": 25.0, "epoch_pct": 25.03, "eta": "01:45:46", "max_grad_norm": 1.0, "loss": -0.0046, "grad_norm": 0.14057794213294983, "learning_rate": 4.482963871817195e-06, "grpo_mean_advantage": -5.7369469175228005e-08, "grpo_std_advantage": 1.2823379620385822e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5646580457687378}
+{"ts": "2025-12-27T20:22:09", "event": "train_log", "step": 130, "epoch": 0.5205205205205206, "progress_pct": 26.0, "epoch_pct": 26.03, "eta": "01:44:12", "max_grad_norm": 1.0, "loss": -0.003, "grad_norm": 0.12420658767223358, "learning_rate": 4.4315423712133595e-06, "grpo_mean_advantage": 2.9876827056796174e-07, "grpo_std_advantage": 1.0496698905626545e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.6111599802970886}
+{"ts": "2025-12-27T20:23:32", "event": "train_log", "step": 135, "epoch": 0.5405405405405406, "progress_pct": 27.0, "epoch_pct": 27.03, "eta": "01:42:43", "max_grad_norm": 1.0, "loss": 0.0154, "grad_norm": 0.14342808723449707, "learning_rate": 4.378008757385222e-06, "grpo_mean_advantage": 1.5869736103013565e-07, "grpo_std_advantage": 1.2748531617035042e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5619662404060364}
+{"ts": "2025-12-27T20:24:57", "event": "train_log", "step": 140, "epoch": 0.5605605605605606, "progress_pct": 28.0, "epoch_pct": 28.03, "eta": "01:41:21", "max_grad_norm": 1.0, "loss": -0.0262, "grad_norm": 0.14729444682598114, "learning_rate": 4.322421568553529e-06, "grpo_mean_advantage": 3.0100346748440643e-07, "grpo_std_advantage": 2.4499684059264837e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5795454978942871}
+{"ts": "2025-12-27T20:26:19", "event": "train_log", "step": 145, "epoch": 0.5805805805805806, "progress_pct": 29.0, "epoch_pct": 29.03, "eta": "01:39:51", "max_grad_norm": 1.0, "loss": 0.0018, "grad_norm": 0.15249410271644592, "learning_rate": 4.2648415884931476e-06, "grpo_mean_advantage": -3.233552092751779e-07, "grpo_std_advantage": 1.248456669600273e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5804953575134277}
+{"ts": "2025-12-27T20:27:43", "event": "train_log", "step": 150, "epoch": 0.6006006006006006, "progress_pct": 30.0, "epoch_pct": 30.03, "eta": "01:38:25", "max_grad_norm": 1.0, "loss": -0.017, "grad_norm": 0.1841023564338684, "learning_rate": 4.205331780066892e-06, "grpo_mean_advantage": 3.2261013416245987e-07, "grpo_std_advantage": 1.4773489738217904e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5628539323806763}
+{"ts": "2025-12-27T20:29:07", "event": "train_log", "step": 155, "epoch": 0.6206206206206206, "progress_pct": 31.0, "epoch_pct": 31.03, "eta": "01:37:00", "max_grad_norm": 1.0, "loss": 0.0044, "grad_norm": 0.18597163259983063, "learning_rate": 4.1439572163765615e-06, "grpo_mean_advantage": -2.5331974029541016e-07, "grpo_std_advantage": 1.5092309695319273e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5727725625038147}
+{"ts": "2025-12-27T20:30:30", "event": "train_log", "step": 160, "epoch": 0.6406406406406406, "progress_pct": 32.0, "epoch_pct": 32.03, "eta": "01:35:33", "max_grad_norm": 1.0, "loss": -0.005, "grad_norm": 0.18310388922691345, "learning_rate": 4.0807850096064605e-06, "grpo_mean_advantage": -6.780028627417778e-08, "grpo_std_advantage": 8.550978805033083e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5833909511566162}
+{"ts": "2025-12-27T20:31:51", "event": "train_log", "step": 165, "epoch": 0.6606606606606606, "progress_pct": 33.0, "epoch_pct": 33.03, "eta": "01:34:01", "max_grad_norm": 1.0, "loss": -0.015, "grad_norm": 0.2192923128604889, "learning_rate": 4.015884237637206e-06, "grpo_mean_advantage": -5.587935447692871e-08, "grpo_std_advantage": 3.564579174053506e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5742615461349487}
+{"ts": "2025-12-27T20:33:17", "event": "train_log", "step": 170, "epoch": 0.6806806806806807, "progress_pct": 34.0, "epoch_pct": 34.03, "eta": "01:32:41", "max_grad_norm": 1.0, "loss": -0.0314, "grad_norm": 0.16708803176879883, "learning_rate": 3.949325868510083e-06, "grpo_mean_advantage": -5.327165126800537e-07, "grpo_std_advantage": 2.309018327650847e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5758188962936401}
+{"ts": "2025-12-27T20:34:40", "event": "train_log", "step": 175, "epoch": 0.7007007007007007, "progress_pct": 35.0, "epoch_pct": 35.04, "eta": "01:31:14", "max_grad_norm": 1.0, "loss": -0.0441, "grad_norm": 0.3401262164115906, "learning_rate": 3.881182682824534e-06, "grpo_mean_advantage": 5.863606702405377e-07, "grpo_std_advantage": 2.4449204829579685e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5767683982849121}
+{"ts": "2025-12-27T20:36:09", "event": "train_log", "step": 180, "epoch": 0.7207207207207207, "progress_pct": 36.0, "epoch_pct": 36.04, "eta": "01:29:58", "max_grad_norm": 1.0, "loss": -0.0162, "grad_norm": 0.1931898146867752, "learning_rate": 3.811529194153635e-06, "grpo_mean_advantage": 3.2186508747145126e-07, "grpo_std_advantage": 2.293551688126172e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.586772084236145}
+{"ts": "2025-12-27T20:37:33", "event": "train_log", "step": 185, "epoch": 0.7407407407407407, "progress_pct": 37.0, "epoch_pct": 37.04, "eta": "01:28:33", "max_grad_norm": 1.0, "loss": -0.0386, "grad_norm": 0.2537969648838043, "learning_rate": 3.7404415675646054e-06, "grpo_mean_advantage": -4.470348358154297e-08, "grpo_std_advantage": 3.7067667335577426e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.549396276473999}
+{"ts": "2025-12-27T20:38:56", "event": "train_log", "step": 190, "epoch": 0.7607607607607607, "progress_pct": 38.0, "epoch_pct": 38.04, "eta": "01:27:06", "max_grad_norm": 1.0, "loss": -0.037, "grad_norm": 0.20326584577560425, "learning_rate": 3.667997536333424e-06, "grpo_mean_advantage": -2.1010637851759384e-07, "grpo_std_advantage": 1.1695076409523608e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5798425078392029}
+{"ts": "2025-12-27T20:40:21", "event": "train_log", "step": 195, "epoch": 0.7807807807807807, "progress_pct": 39.0, "epoch_pct": 39.04, "eta": "01:25:43", "max_grad_norm": 1.0, "loss": -0.0292, "grad_norm": 0.25048357248306274, "learning_rate": 3.59427631694463e-06, "grpo_mean_advantage": 1.765787658314366e-07, "grpo_std_advantage": 2.429934738756856e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5584167838096619}
+{"ts": "2025-12-27T20:41:46", "event": "train_log", "step": 200, "epoch": 0.8008008008008008, "progress_pct": 40.0, "epoch_pct": 40.04, "eta": "01:24:20", "max_grad_norm": 1.0, "loss": -0.0454, "grad_norm": 0.2687569260597229, "learning_rate": 3.5193585224692595e-06, "grpo_mean_advantage": 1.6540289493605087e-07, "grpo_std_advantage": 2.6342788714828203e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5676193237304688}
+{"ts": "2025-12-27T20:43:13", "event": "train_log", "step": 205, "epoch": 0.8208208208208209, "progress_pct": 41.0, "epoch_pct": 41.04, "eta": "01:22:59", "max_grad_norm": 1.0, "loss": -0.0423, "grad_norm": 0.22301620244979858, "learning_rate": 3.44332607441564e-06, "grpo_mean_advantage": -1.0944902442133753e-06, "grpo_std_advantage": 5.346942998585291e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5669739842414856}
+{"ts": "2025-12-27T20:44:38", "event": "train_log", "step": 210, "epoch": 0.8408408408408409, "progress_pct": 42.0, "epoch_pct": 42.04, "eta": "01:21:37", "max_grad_norm": 1.0, "loss": -0.0857, "grad_norm": 0.3040211498737335, "learning_rate": 3.3662621131494204e-06, "grpo_mean_advantage": 2.4065374759629776e-07, "grpo_std_advantage": 1.6327536513927043e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5922158360481262}
+{"ts": "2025-12-27T20:46:02", "event": "train_log", "step": 215, "epoch": 0.8608608608608609, "progress_pct": 43.0, "epoch_pct": 43.04, "eta": "01:20:11", "max_grad_norm": 1.0, "loss": -0.0278, "grad_norm": 0.27231141924858093, "learning_rate": 3.2882509069808044e-06, "grpo_mean_advantage": -5.21540641784668e-08, "grpo_std_advantage": 5.847922466273303e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5473950505256653}
+{"ts": "2025-12-27T20:47:28", "event": "train_log", "step": 220, "epoch": 0.8808808808808809, "progress_pct": 44.0, "epoch_pct": 44.04, "eta": "01:18:49", "max_grad_norm": 1.0, "loss": -0.0727, "grad_norm": 0.3571636378765106, "learning_rate": 3.2093777600183873e-06, "grpo_mean_advantage": 6.541609991472797e-07, "grpo_std_advantage": 4.072162937518442e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5880032777786255}
+{"ts": "2025-12-27T20:48:53", "event": "train_log", "step": 225, "epoch": 0.9009009009009009, "progress_pct": 45.0, "epoch_pct": 45.05, "eta": "01:17:25", "max_grad_norm": 1.0, "loss": -0.0464, "grad_norm": 0.306273490190506, "learning_rate": 3.1297289188903705e-06, "grpo_mean_advantage": -1.2218951894737984e-07, "grpo_std_advantage": 4.386006935419573e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5835092663764954}
+{"ts": "2025-12-27T20:50:20", "event": "train_log", "step": 230, "epoch": 0.9209209209209209, "progress_pct": 46.0, "epoch_pct": 46.05, "eta": "01:16:03", "max_grad_norm": 1.0, "loss": -0.0295, "grad_norm": 0.2700377106666565, "learning_rate": 3.049391478435133e-06, "grpo_mean_advantage": 1.7605722177904681e-06, "grpo_std_advantage": 8.007580618141219e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5394966006278992}
+{"ts": "2025-12-27T20:51:41", "event": "train_log", "step": 235, "epoch": 0.9409409409409409, "progress_pct": 47.0, "epoch_pct": 47.05, "eta": "01:14:35", "max_grad_norm": 1.0, "loss": -0.031, "grad_norm": 0.39531761407852173, "learning_rate": 2.9684532864643123e-06, "grpo_mean_advantage": -3.3080578987210174e-07, "grpo_std_advantage": 1.551636614749441e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5687432289123535}
+{"ts": "2025-12-27T20:53:06", "event": "train_log", "step": 240, "epoch": 0.960960960960961, "progress_pct": 48.0, "epoch_pct": 48.05, "eta": "01:13:11", "max_grad_norm": 1.0, "loss": -0.0789, "grad_norm": 0.5987040996551514, "learning_rate": 2.887002847702504e-06, "grpo_mean_advantage": 2.712011450967111e-07, "grpo_std_advantage": 1.4400844747797237e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5550583600997925}
+{"ts": "2025-12-27T20:54:27", "event": "train_log", "step": 245, "epoch": 0.980980980980981, "progress_pct": 49.0, "epoch_pct": 49.05, "eta": "01:11:42", "max_grad_norm": 1.0, "loss": -0.1131, "grad_norm": 0.5680716037750244, "learning_rate": 2.8051292270086506e-06, "grpo_mean_advantage": -3.2857059295565705e-07, "grpo_std_advantage": 2.105091425619321e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.558111310005188}
+{"ts": "2025-12-27T20:55:45", "event": "train_log", "step": 250, "epoch": 1.0, "progress_pct": 50.0, "epoch_pct": 50.0, "eta": "01:10:13", "max_grad_norm": 1.0, "loss": -0.2232, "grad_norm": 0.6204046010971069, "learning_rate": 2.722921951984927e-06, "grpo_mean_advantage": 4.470348358154297e-08, "grpo_std_advantage": 5.315724820320611e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.6196198463439941}
+{"ts": "2025-12-27T20:57:06", "event": "train_log", "step": 255, "epoch": 1.02002002002002, "progress_pct": 51.0, "epoch_pct": 51.0, "eta": "01:08:45", "max_grad_norm": 1.0, "loss": -0.1363, "grad_norm": 0.8389026522636414, "learning_rate": 2.640470915079614e-06, "grpo_mean_advantage": 9.290873776990338e-07, "grpo_std_advantage": 4.219644324621186e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.582168459892273}
+{"ts": "2025-12-27T20:58:26", "event": "train_log", "step": 260, "epoch": 1.04004004004004, "progress_pct": 52.0, "epoch_pct": 52.0, "eta": "01:07:17", "max_grad_norm": 1.0, "loss": -0.1868, "grad_norm": 0.9067686796188354, "learning_rate": 2.557866275291035e-06, "grpo_mean_advantage": 2.533197474008375e-08, "grpo_std_advantage": 1.6600588992332632e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5551307797431946}
+{"ts": "2025-12-27T20:59:48", "event": "train_log", "step": 265, "epoch": 1.06006006006006, "progress_pct": 53.0, "epoch_pct": 53.0, "eta": "01:05:51", "max_grad_norm": 1.0, "loss": -0.1792, "grad_norm": 0.9277902841567993, "learning_rate": 2.4751983595800093e-06, "grpo_mean_advantage": -5.662441182607836e-08, "grpo_std_advantage": 1.0909400316450046e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.535040020942688}
+{"ts": "2025-12-27T21:01:15", "event": "train_log", "step": 270, "epoch": 1.08008008008008, "progress_pct": 54.0, "epoch_pct": 54.0, "eta": "01:04:29", "max_grad_norm": 1.0, "loss": -0.1691, "grad_norm": 1.0715463161468506, "learning_rate": 2.392557564098649e-06, "grpo_mean_advantage": -9.536743306171047e-08, "grpo_std_advantage": 5.838213610331877e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5673571825027466}
+{"ts": "2025-12-27T21:02:37", "event": "train_log", "step": 275, "epoch": 1.1001001001001, "progress_pct": 55.0, "epoch_pct": 55.01, "eta": "01:03:03", "max_grad_norm": 1.0, "loss": -0.1655, "grad_norm": 0.7759184837341309, "learning_rate": 2.3100342553434924e-06, "grpo_mean_advantage": 3.278255533700758e-08, "grpo_std_advantage": 9.317170679423725e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5874732732772827}
+{"ts": "2025-12-27T21:03:59", "event": "train_log", "step": 280, "epoch": 1.12012012012012, "progress_pct": 56.0, "epoch_pct": 56.01, "eta": "01:01:38", "max_grad_norm": 1.0, "loss": -0.1821, "grad_norm": 0.9387398958206177, "learning_rate": 2.2277186713410688e-06, "grpo_mean_advantage": -1.206994113545079e-07, "grpo_std_advantage": 6.201085511747806e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5569106340408325}
+{"ts": "2025-12-27T21:05:19", "event": "train_log", "step": 285, "epoch": 1.14014014014014, "progress_pct": 57.0, "epoch_pct": 57.01, "eta": "01:00:10", "max_grad_norm": 1.0, "loss": -0.2102, "grad_norm": 1.6132302284240723, "learning_rate": 2.1457008229739395e-06, "grpo_mean_advantage": 4.470348358154297e-08, "grpo_std_advantage": 6.115651558502577e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5578873157501221}
+{"ts": "2025-12-27T21:06:43", "event": "train_log", "step": 290, "epoch": 1.16016016016016, "progress_pct": 58.0, "epoch_pct": 58.01, "eta": "00:58:47", "max_grad_norm": 1.0, "loss": -0.2937, "grad_norm": 0.8679026961326599, "learning_rate": 2.0640703955551214e-06, "grpo_mean_advantage": -3.3453108017056365e-07, "grpo_std_advantage": 3.5326345368957845e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5735999345779419}
+{"ts": "2025-12-27T21:08:10", "event": "train_log", "step": 295, "epoch": 1.1801801801801801, "progress_pct": 59.0, "epoch_pct": 59.01, "eta": "00:57:24", "max_grad_norm": 1.0, "loss": -0.2598, "grad_norm": 1.0550166368484497, "learning_rate": 1.9829166507585084e-06, "grpo_mean_advantage": -1.110136480519941e-07, "grpo_std_advantage": 4.731904823529476e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5626259446144104}
+{"ts": "2025-12-27T21:09:34", "event": "train_log", "step": 300, "epoch": 1.2002002002002001, "progress_pct": 60.0, "epoch_pct": 60.01, "eta": "00:56:00", "max_grad_norm": 1.0, "loss": -0.2546, "grad_norm": 1.2819372415542603, "learning_rate": 1.90232832901255e-06, "grpo_mean_advantage": -5.08874677507265e-07, "grpo_std_advantage": 1.840126174101897e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5463050603866577}
+{"ts": "2025-12-27T21:10:59", "event": "train_log", "step": 305, "epoch": 1.2202202202202201, "progress_pct": 61.0, "epoch_pct": 61.01, "eta": "00:54:37", "max_grad_norm": 1.0, "loss": -0.1809, "grad_norm": 1.0188143253326416, "learning_rate": 1.82239355246389e-06, "grpo_mean_advantage": 1.01327898960335e-07, "grpo_std_advantage": 7.798533943059738e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5352144241333008}
+{"ts": "2025-12-27T21:12:25", "event": "train_log", "step": 310, "epoch": 1.2402402402402402, "progress_pct": 62.0, "epoch_pct": 62.01, "eta": "00:53:14", "max_grad_norm": 1.0, "loss": -0.3559, "grad_norm": 2.0709052085876465, "learning_rate": 1.7431997286170923e-06, "grpo_mean_advantage": 1.341104507446289e-07, "grpo_std_advantage": 7.821902840987605e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5547868013381958}
+{"ts": "2025-12-27T21:13:52", "event": "train_log", "step": 315, "epoch": 1.2602602602602602, "progress_pct": 63.0, "epoch_pct": 63.01, "eta": "00:51:52", "max_grad_norm": 1.0, "loss": -0.3874, "grad_norm": 1.8516215085983276, "learning_rate": 1.6648334547558227e-06, "grpo_mean_advantage": 9.015202806494926e-08, "grpo_std_advantage": 1.0693488547985908e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5859472751617432}
+{"ts": "2025-12-27T21:15:21", "event": "train_log", "step": 320, "epoch": 1.2802802802802802, "progress_pct": 64.0, "epoch_pct": 64.01, "eta": "00:50:31", "max_grad_norm": 1.0, "loss": -0.3467, "grad_norm": 1.283104419708252, "learning_rate": 1.5873804232499862e-06, "grpo_mean_advantage": -2.443790378947597e-07, "grpo_std_advantage": 1.183122208203713e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5751550793647766}
+{"ts": "2025-12-27T21:16:47", "event": "train_log", "step": 325, "epoch": 1.3003003003003002, "progress_pct": 65.0, "epoch_pct": 65.02, "eta": "00:49:07", "max_grad_norm": 1.0, "loss": -0.1703, "grad_norm": 1.4108576774597168, "learning_rate": 1.51092532785238e-06, "grpo_mean_advantage": -6.705522537231445e-08, "grpo_std_advantage": 6.109748937888071e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5497723817825317}
+{"ts": "2025-12-27T21:18:13", "event": "train_log", "step": 330, "epoch": 1.3203203203203202, "progress_pct": 66.0, "epoch_pct": 66.02, "eta": "00:47:44", "max_grad_norm": 1.0, "loss": -0.2918, "grad_norm": 1.0421361923217773, "learning_rate": 1.4355517710873184e-06, "grpo_mean_advantage": -1.639127766850379e-08, "grpo_std_advantage": 5.529495297196263e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.55989670753479}
+{"ts": "2025-12-27T21:19:37", "event": "train_log", "step": 335, "epoch": 1.3403403403403402, "progress_pct": 67.0, "epoch_pct": 67.02, "eta": "00:46:20", "max_grad_norm": 1.0, "loss": -0.3069, "grad_norm": 1.3465828895568848, "learning_rate": 1.361342172832502e-06, "grpo_mean_advantage": 4.418194237132411e-07, "grpo_std_advantage": 2.9275292945385445e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5809233784675598}
+{"ts": "2025-12-27T21:20:59", "event": "train_log", "step": 340, "epoch": 1.3603603603603602, "progress_pct": 68.0, "epoch_pct": 68.02, "eta": "00:44:55", "max_grad_norm": 1.0, "loss": -0.5594, "grad_norm": 1.1959459781646729, "learning_rate": 1.2883776801940884e-06, "grpo_mean_advantage": 9.685754776000977e-08, "grpo_std_advantage": 3.754235251562932e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5568087100982666}
+{"ts": "2025-12-27T21:22:27", "event": "train_log", "step": 345, "epoch": 1.3803803803803802, "progress_pct": 69.0, "epoch_pct": 69.02, "eta": "00:43:32", "max_grad_norm": 1.0, "loss": -0.4102, "grad_norm": 1.8967422246932983, "learning_rate": 1.216738078773522e-06, "grpo_mean_advantage": -2.384185791015625e-07, "grpo_std_advantage": 6.821086913078034e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5655568838119507}
+{"ts": "2025-12-27T21:23:49", "event": "train_log", "step": 350, "epoch": 1.4004004004004005, "progress_pct": 70.0, "epoch_pct": 70.02, "eta": "00:42:06", "max_grad_norm": 1.0, "loss": -0.338, "grad_norm": 2.221132755279541, "learning_rate": 1.146501705423155e-06, "grpo_mean_advantage": -8.717179156292332e-08, "grpo_std_advantage": 2.500940354366321e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.6089578866958618}
+{"ts": "2025-12-27T21:25:13", "event": "train_log", "step": 355, "epoch": 1.4204204204204205, "progress_pct": 71.0, "epoch_pct": 71.02, "eta": "00:40:42", "max_grad_norm": 1.0, "loss": -0.4985, "grad_norm": 2.3640377521514893, "learning_rate": 1.0777453625860474e-06, "grpo_mean_advantage": 2.1606683731079102e-07, "grpo_std_advantage": 1.4568390724889468e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.6129671335220337}
+{"ts": "2025-12-27T21:26:36", "event": "train_log", "step": 360, "epoch": 1.4404404404404405, "progress_pct": 72.0, "epoch_pct": 72.02, "eta": "00:39:18", "max_grad_norm": 1.0, "loss": -0.4347, "grad_norm": 1.9084734916687012, "learning_rate": 1.0105442343136184e-06, "grpo_mean_advantage": -3.725290298461914e-09, "grpo_std_advantage": 2.965894054796081e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5562310814857483}
+{"ts": "2025-12-27T21:27:58", "event": "train_log", "step": 365, "epoch": 1.4604604604604605, "progress_pct": 73.0, "epoch_pct": 73.02, "eta": "00:37:52", "max_grad_norm": 1.0, "loss": -0.6217, "grad_norm": 1.6063904762268066, "learning_rate": 9.449718040529987e-07, "grpo_mean_advantage": 4.313886279305734e-07, "grpo_std_advantage": 1.9621948013082147e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5884170532226562}
+{"ts": "2025-12-27T21:29:21", "event": "train_log", "step": 370, "epoch": 1.4804804804804805, "progress_pct": 74.0, "epoch_pct": 74.02, "eta": "00:36:28", "max_grad_norm": 1.0, "loss": -0.5364, "grad_norm": 2.114664077758789, "learning_rate": 8.810997742939531e-07, "grpo_mean_advantage": 2.0489096641540527e-07, "grpo_std_advantage": 1.0235522722723545e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5795440673828125}
+{"ts": "2025-12-27T21:30:45", "event": "train_log", "step": 375, "epoch": 1.5005005005005005, "progress_pct": 75.0, "epoch_pct": 75.03, "eta": "00:35:04", "max_grad_norm": 1.0, "loss": -0.4798, "grad_norm": 1.8450465202331543, "learning_rate": 8.189979881632634e-07, "grpo_mean_advantage": -1.4185905001795618e-06, "grpo_std_advantage": 1.0947338523692451e-05, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5607603788375854}
+{"ts": "2025-12-27T21:32:13", "event": "train_log", "step": 380, "epoch": 1.5205205205205206, "progress_pct": 76.0, "epoch_pct": 76.03, "eta": "00:33:41", "max_grad_norm": 1.0, "loss": -0.4805, "grad_norm": 2.673438787460327, "learning_rate": 7.587343530522945e-07, "grpo_mean_advantage": -1.758337049295733e-07, "grpo_std_advantage": 9.663675655247062e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5381432771682739}
+{"ts": "2025-12-27T21:33:36", "event": "train_log", "step": 385, "epoch": 1.5405405405405406, "progress_pct": 77.0, "epoch_pct": 77.03, "eta": "00:32:16", "max_grad_norm": 1.0, "loss": -0.433, "grad_norm": 2.2263550758361816, "learning_rate": 7.003747663612581e-07, "grpo_mean_advantage": -6.973743325033865e-07, "grpo_std_advantage": 4.341973180999048e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5528443455696106}
+{"ts": "2025-12-27T21:34:59", "event": "train_log", "step": 390, "epoch": 1.5605605605605606, "progress_pct": 78.0, "epoch_pct": 78.03, "eta": "00:30:52", "max_grad_norm": 1.0, "loss": -0.6021, "grad_norm": 2.3657093048095703, "learning_rate": 6.439830434413754e-07, "grpo_mean_advantage": 1.7881394143159923e-08, "grpo_std_advantage": 1.3004198251564958e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.6091476678848267}
+{"ts": "2025-12-27T21:36:21", "event": "train_log", "step": 395, "epoch": 1.5805805805805806, "progress_pct": 79.0, "epoch_pct": 79.03, "eta": "00:29:27", "max_grad_norm": 1.0, "loss": -0.5595, "grad_norm": 1.9847129583358765, "learning_rate": 5.896208478137222e-07, "grpo_mean_advantage": 3.4868716625169327e-07, "grpo_std_advantage": 2.059372718576924e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5397372245788574}
+{"ts": "2025-12-27T21:37:48", "event": "train_log", "step": 400, "epoch": 1.6006006006006006, "progress_pct": 80.0, "epoch_pct": 80.03, "eta": "00:28:03", "max_grad_norm": 1.0, "loss": -0.5592, "grad_norm": 2.922114133834839, "learning_rate": 5.373476237410808e-07, "grpo_mean_advantage": -2.1636485598719446e-06, "grpo_std_advantage": 9.725940799398813e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5873125195503235}
+{"ts": "2025-12-27T21:39:11", "event": "train_log", "step": 405, "epoch": 1.6206206206206206, "progress_pct": 81.0, "epoch_pct": 81.03, "eta": "00:26:39", "max_grad_norm": 1.0, "loss": -0.5623, "grad_norm": 1.8524045944213867, "learning_rate": 4.872205312265074e-07, "grpo_mean_advantage": -5.960464477539063e-08, "grpo_std_advantage": 3.460792754594877e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5601426362991333}
+{"ts": "2025-12-27T21:40:38", "event": "train_log", "step": 410, "epoch": 1.6406406406406406, "progress_pct": 82.0, "epoch_pct": 82.03, "eta": "00:25:15", "max_grad_norm": 1.0, "loss": -0.5943, "grad_norm": 1.7269790172576904, "learning_rate": 4.3929438350970687e-07, "grpo_mean_advantage": 2.6226044269606064e-07, "grpo_std_advantage": 7.928817922220333e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.578656792640686}
+{"ts": "2025-12-27T21:42:02", "event": "train_log", "step": 415, "epoch": 1.6606606606606606, "progress_pct": 83.0, "epoch_pct": 83.03, "eta": "00:23:51", "max_grad_norm": 1.0, "loss": -0.6193, "grad_norm": 2.26530122756958, "learning_rate": 3.936215871295634e-07, "grpo_mean_advantage": 2.3558736756967846e-06, "grpo_std_advantage": 1.4469559573626611e-05, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5885810852050781}
+{"ts": "2025-12-27T21:43:27", "event": "train_log", "step": 420, "epoch": 1.6806806806806807, "progress_pct": 84.0, "epoch_pct": 84.03, "eta": "00:22:27", "max_grad_norm": 1.0, "loss": -0.6934, "grad_norm": 2.6794464588165283, "learning_rate": 3.502520846183577e-07, "grpo_mean_advantage": 1.639127766850379e-08, "grpo_std_advantage": 9.352411325380672e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5805023312568665}
+{"ts": "2025-12-27T21:44:52", "event": "train_log", "step": 425, "epoch": 1.7007007007007007, "progress_pct": 85.0, "epoch_pct": 85.04, "eta": "00:21:03", "max_grad_norm": 1.0, "loss": -0.5126, "grad_norm": 2.100447654724121, "learning_rate": 3.092332998903416e-07, "grpo_mean_advantage": 3.2387674764322583e-06, "grpo_std_advantage": 1.999079904635437e-05, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5655918121337891}
+{"ts": "2025-12-27T21:46:17", "event": "train_log", "step": 430, "epoch": 1.7207207207207207, "progress_pct": 86.0, "epoch_pct": 86.04, "eta": "00:19:39", "max_grad_norm": 1.0, "loss": -0.5446, "grad_norm": 2.1027915477752686, "learning_rate": 2.706100863843822e-07, "grpo_mean_advantage": 3.5464762504489045e-07, "grpo_std_advantage": 1.7663603557593888e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5474504232406616}
+{"ts": "2025-12-27T21:47:43", "event": "train_log", "step": 435, "epoch": 1.7407407407407407, "progress_pct": 87.0, "epoch_pct": 87.04, "eta": "00:18:15", "max_grad_norm": 1.0, "loss": -0.5125, "grad_norm": 2.289045572280884, "learning_rate": 2.3442467801738867e-07, "grpo_mean_advantage": 3.6135315895080566e-07, "grpo_std_advantage": 2.356920958845876e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5874254703521729}
+{"ts": "2025-12-27T21:49:08", "event": "train_log", "step": 440, "epoch": 1.7607607607607607, "progress_pct": 88.0, "epoch_pct": 88.04, "eta": "00:16:51", "max_grad_norm": 1.0, "loss": -0.595, "grad_norm": 2.278038501739502, "learning_rate": 2.007166430021415e-07, "grpo_mean_advantage": 2.7567148563889532e-08, "grpo_std_advantage": 9.97340521280421e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5815118551254272}
+{"ts": "2025-12-27T21:50:35", "event": "train_log", "step": 445, "epoch": 1.7807807807807807, "progress_pct": 89.0, "epoch_pct": 89.04, "eta": "00:15:27", "max_grad_norm": 1.0, "loss": -0.8055, "grad_norm": 2.340942621231079, "learning_rate": 1.6952284058003366e-07, "grpo_mean_advantage": -8.34465012644614e-08, "grpo_std_advantage": 5.558832185670326e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5611211061477661}
+{"ts": "2025-12-27T21:52:06", "event": "train_log", "step": 450, "epoch": 1.800800800800801, "progress_pct": 90.0, "epoch_pct": 90.04, "eta": "00:14:03", "max_grad_norm": 1.0, "loss": -0.8561, "grad_norm": 2.4256298542022705, "learning_rate": 1.4087738071603075e-07, "grpo_mean_advantage": -1.9818544672034477e-07, "grpo_std_advantage": 6.800727305744658e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.590424656867981}
+{"ts": "2025-12-27T21:53:32", "event": "train_log", "step": 455, "epoch": 1.820820820820821, "progress_pct": 91.0, "epoch_pct": 91.04, "eta": "00:12:39", "max_grad_norm": 1.0, "loss": -0.429, "grad_norm": 1.6453255414962769, "learning_rate": 1.1481158679992554e-07, "grpo_mean_advantage": -1.9371508841459217e-08, "grpo_std_advantage": 3.142378943721269e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5670351982116699}
+{"ts": "2025-12-27T21:55:00", "event": "train_log", "step": 460, "epoch": 1.840840840840841, "progress_pct": 92.0, "epoch_pct": 92.04, "eta": "00:11:15", "max_grad_norm": 1.0, "loss": -0.642, "grad_norm": 2.3458049297332764, "learning_rate": 9.135396139467151e-08, "grpo_mean_advantage": 2.3692845729783585e-07, "grpo_std_advantage": 1.682946731307311e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5640432834625244}
+{"ts": "2025-12-27T21:56:27", "event": "train_log", "step": 465, "epoch": 1.860860860860861, "progress_pct": 93.0, "epoch_pct": 93.04, "eta": "00:09:51", "max_grad_norm": 1.0, "loss": -0.583, "grad_norm": 2.730945110321045, "learning_rate": 7.053015506924749e-08, "grpo_mean_advantage": 1.110136480519941e-07, "grpo_std_advantage": 8.930008448260196e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5584251284599304}
+{"ts": "2025-12-27T21:57:50", "event": "train_log", "step": 470, "epoch": 1.880880880880881, "progress_pct": 94.0, "epoch_pct": 94.04, "eta": "00:08:26", "max_grad_norm": 1.0, "loss": -0.5197, "grad_norm": 2.1463465690612793, "learning_rate": 5.236293835013839e-08, "grpo_mean_advantage": 2.5406478698641877e-07, "grpo_std_advantage": 9.93092498902115e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5392154455184937}
+{"ts": "2025-12-27T21:59:15", "event": "train_log", "step": 475, "epoch": 1.900900900900901, "progress_pct": 95.0, "epoch_pct": 95.05, "eta": "00:07:02", "max_grad_norm": 1.0, "loss": -0.5864, "grad_norm": 2.427900791168213, "learning_rate": 3.687217682209837e-08, "grpo_mean_advantage": -8.940697071579962e-09, "grpo_std_advantage": 5.835169645251881e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5686308741569519}
+{"ts": "2025-12-27T22:00:36", "event": "train_log", "step": 480, "epoch": 1.920920920920921, "progress_pct": 96.0, "epoch_pct": 96.05, "eta": "00:05:37", "max_grad_norm": 1.0, "loss": -0.5721, "grad_norm": 2.042795419692993, "learning_rate": 2.4074809405425227e-08, "grpo_mean_advantage": 4.0605664253234863e-07, "grpo_std_advantage": 2.3210795916384086e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5842767357826233}
+{"ts": "2025-12-27T22:01:58", "event": "train_log", "step": 485, "epoch": 1.940940940940941, "progress_pct": 97.0, "epoch_pct": 97.05, "eta": "00:04:13", "max_grad_norm": 1.0, "loss": -0.5944, "grad_norm": 2.800136089324951, "learning_rate": 1.3984829833499636e-08, "grpo_mean_advantage": 1.341104507446289e-07, "grpo_std_advantage": 1.507950400991831e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5495311617851257}
+{"ts": "2025-12-27T22:03:20", "event": "train_log", "step": 490, "epoch": 1.960960960960961, "progress_pct": 98.0, "epoch_pct": 98.05, "eta": "00:02:48", "max_grad_norm": 1.0, "loss": -0.7015, "grad_norm": 2.8475866317749023, "learning_rate": 6.6132713508446075e-09, "grpo_mean_advantage": 2.689659481802664e-07, "grpo_std_advantage": 8.491958851664094e-07, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.549436628818512}
+{"ts": "2025-12-27T22:04:42", "event": "train_log", "step": 495, "epoch": 1.980980980980981, "progress_pct": 99.0, "epoch_pct": 99.05, "eta": "00:01:24", "max_grad_norm": 1.0, "loss": -0.4033, "grad_norm": 2.9422402381896973, "learning_rate": 1.9681946484320645e-09, "grpo_mean_advantage": 8.195638656616211e-08, "grpo_std_advantage": 3.802849732892355e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.544632077217102}
+{"ts": "2025-12-27T22:06:01", "event": "train_log", "step": 500, "epoch": 2.0, "progress_pct": 100.0, "epoch_pct": 100.0, "eta": "00:00:00", "max_grad_norm": 1.0, "loss": -0.6773, "grad_norm": 2.66204833984375, "learning_rate": 5.467904943851077e-11, "grpo_mean_advantage": 7.552536089860951e-07, "grpo_std_advantage": 4.143997102801222e-06, "grpo_mean_kl_div": 0.0, "grpo_mean_group_score": 0.5968535542488098}
+{"ts": "2025-12-27T22:06:03", "event": "train_log", "step": 500, "epoch": 2.0, "progress_pct": 100.0, "epoch_pct": 100.0, "eta": "00:00:00", "max_grad_norm": 1.0, "train_runtime": 8430.3461, "train_samples_per_second": 0.474, "train_steps_per_second": 0.059, "total_flos": 0.0, "train_loss": -0.23323759501613678}