{"current_steps": 1, "total_steps": 1626, "loss": 1.9595, "learning_rate": 1.8404907975460125e-07, "epoch": 0.0018433179723502304, "percentage": 0.06, "elapsed_time": "0:00:25", "remaining_time": "11:22:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 2, "total_steps": 1626, "loss": 1.9238, "learning_rate": 3.680981595092025e-07, "epoch": 0.003686635944700461, "percentage": 0.12, "elapsed_time": "0:00:49", "remaining_time": "11:15:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 3, "total_steps": 1626, "loss": 1.9764, "learning_rate": 5.521472392638038e-07, "epoch": 0.005529953917050691, "percentage": 0.18, "elapsed_time": "0:01:14", "remaining_time": "11:14:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 4, "total_steps": 1626, "loss": 1.9161, "learning_rate": 7.36196319018405e-07, "epoch": 0.007373271889400922, "percentage": 0.25, "elapsed_time": "0:01:39", "remaining_time": "11:13:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 5, "total_steps": 1626, "loss": 1.9629, "learning_rate": 9.202453987730061e-07, "epoch": 0.009216589861751152, "percentage": 0.31, "elapsed_time": "0:02:04", "remaining_time": "11:13:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 6, "total_steps": 1626, "loss": 1.9158, "learning_rate": 1.1042944785276075e-06, "epoch": 0.011059907834101382, "percentage": 0.37, "elapsed_time": "0:02:29", "remaining_time": "11:12:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 7, "total_steps": 1626, "loss": 1.9572, "learning_rate": 1.2883435582822088e-06, "epoch": 0.012903225806451613, "percentage": 0.43, "elapsed_time": "0:02:54", "remaining_time": "11:12:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 8, "total_steps": 1626, "loss": 1.9453, "learning_rate": 1.47239263803681e-06, "epoch": 0.014746543778801843, "percentage": 0.49, "elapsed_time": "0:03:19", "remaining_time": "11:11:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 9, "total_steps": 1626, "loss": 1.9377, "learning_rate": 1.656441717791411e-06, "epoch": 0.016589861751152075, "percentage": 0.55, "elapsed_time": "0:03:44", "remaining_time": "11:11:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 10, "total_steps": 1626, "loss": 1.9312, "learning_rate": 1.8404907975460122e-06, "epoch": 0.018433179723502304, "percentage": 0.62, "elapsed_time": "0:04:09", "remaining_time": "11:10:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 11, "total_steps": 1626, "loss": 1.9273, "learning_rate": 2.0245398773006137e-06, "epoch": 0.020276497695852536, "percentage": 0.68, "elapsed_time": "0:04:33", "remaining_time": "11:10:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 12, "total_steps": 1626, "loss": 1.8951, "learning_rate": 2.208588957055215e-06, "epoch": 0.022119815668202765, "percentage": 0.74, "elapsed_time": "0:04:58", "remaining_time": "11:09:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 13, "total_steps": 1626, "loss": 1.9054, "learning_rate": 2.392638036809816e-06, "epoch": 0.023963133640552997, "percentage": 0.8, "elapsed_time": "0:05:23", "remaining_time": "11:09:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 14, "total_steps": 1626, "loss": 1.9343, "learning_rate": 2.5766871165644175e-06, "epoch": 0.025806451612903226, "percentage": 0.86, "elapsed_time": "0:05:48", "remaining_time": "11:09:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 15, "total_steps": 1626, "loss": 1.8964, "learning_rate": 2.7607361963190186e-06, "epoch": 0.027649769585253458, "percentage": 0.92, "elapsed_time": "0:06:13", "remaining_time": "11:08:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 16, "total_steps": 1626, "loss": 1.9385, "learning_rate": 2.94478527607362e-06, "epoch": 0.029493087557603687, "percentage": 0.98, "elapsed_time": "0:06:38", "remaining_time": "11:08:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 17, "total_steps": 1626, "loss": 1.9145, "learning_rate": 3.1288343558282206e-06, "epoch": 0.03133640552995392, "percentage": 1.05, "elapsed_time": "0:07:03", "remaining_time": "11:07:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 18, "total_steps": 1626, "loss": 1.9392, "learning_rate": 3.312883435582822e-06, "epoch": 0.03317972350230415, "percentage": 1.11, "elapsed_time": "0:07:30", "remaining_time": "11:10:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 19, "total_steps": 1626, "loss": 1.8919, "learning_rate": 3.496932515337423e-06, "epoch": 0.035023041474654376, "percentage": 1.17, "elapsed_time": "0:07:54", "remaining_time": "11:09:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 20, "total_steps": 1626, "loss": 1.8735, "learning_rate": 3.6809815950920245e-06, "epoch": 0.03686635944700461, "percentage": 1.23, "elapsed_time": "0:08:19", "remaining_time": "11:09:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 21, "total_steps": 1626, "loss": 1.9463, "learning_rate": 3.865030674846626e-06, "epoch": 0.03870967741935484, "percentage": 1.29, "elapsed_time": "0:08:44", "remaining_time": "11:08:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 22, "total_steps": 1626, "loss": 1.8726, "learning_rate": 4.049079754601227e-06, "epoch": 0.04055299539170507, "percentage": 1.35, "elapsed_time": "0:09:09", "remaining_time": "11:08:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 23, "total_steps": 1626, "loss": 1.8418, "learning_rate": 4.233128834355828e-06, "epoch": 0.0423963133640553, "percentage": 1.41, "elapsed_time": "0:09:34", "remaining_time": "11:07:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 24, "total_steps": 1626, "loss": 1.8251, "learning_rate": 4.41717791411043e-06, "epoch": 0.04423963133640553, "percentage": 1.48, "elapsed_time": "0:09:59", "remaining_time": "11:07:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 25, "total_steps": 1626, "loss": 1.7802, "learning_rate": 4.601226993865031e-06, "epoch": 0.04608294930875576, "percentage": 1.54, "elapsed_time": "0:10:24", "remaining_time": "11:06:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 26, "total_steps": 1626, "loss": 1.8777, "learning_rate": 4.785276073619632e-06, "epoch": 0.047926267281105994, "percentage": 1.6, "elapsed_time": "0:10:49", "remaining_time": "11:06:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 27, "total_steps": 1626, "loss": 1.8371, "learning_rate": 4.969325153374233e-06, "epoch": 0.04976958525345622, "percentage": 1.66, "elapsed_time": "0:11:14", "remaining_time": "11:05:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 28, "total_steps": 1626, "loss": 1.9045, "learning_rate": 5.153374233128835e-06, "epoch": 0.05161290322580645, "percentage": 1.72, "elapsed_time": "0:11:39", "remaining_time": "11:05:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 29, "total_steps": 1626, "loss": 1.8053, "learning_rate": 5.337423312883436e-06, "epoch": 0.053456221198156684, "percentage": 1.78, "elapsed_time": "0:12:04", "remaining_time": "11:04:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 30, "total_steps": 1626, "loss": 1.8451, "learning_rate": 5.521472392638037e-06, "epoch": 0.055299539170506916, "percentage": 1.85, "elapsed_time": "0:12:29", "remaining_time": "11:04:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 31, "total_steps": 1626, "loss": 1.8552, "learning_rate": 5.7055214723926385e-06, "epoch": 0.05714285714285714, "percentage": 1.91, "elapsed_time": "0:12:54", "remaining_time": "11:03:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 32, "total_steps": 1626, "loss": 1.8164, "learning_rate": 5.88957055214724e-06, "epoch": 0.05898617511520737, "percentage": 1.97, "elapsed_time": "0:13:19", "remaining_time": "11:03:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 33, "total_steps": 1626, "loss": 1.7819, "learning_rate": 6.0736196319018406e-06, "epoch": 0.060829493087557605, "percentage": 2.03, "elapsed_time": "0:13:44", "remaining_time": "11:02:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 34, "total_steps": 1626, "loss": 1.8147, "learning_rate": 6.257668711656441e-06, "epoch": 0.06267281105990784, "percentage": 2.09, "elapsed_time": "0:14:08", "remaining_time": "11:02:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 35, "total_steps": 1626, "loss": 1.7534, "learning_rate": 6.4417177914110434e-06, "epoch": 0.06451612903225806, "percentage": 2.15, "elapsed_time": "0:14:33", "remaining_time": "11:01:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 36, "total_steps": 1626, "loss": 1.7973, "learning_rate": 6.625766871165644e-06, "epoch": 0.0663594470046083, "percentage": 2.21, "elapsed_time": "0:14:58", "remaining_time": "11:01:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 37, "total_steps": 1626, "loss": 1.8, "learning_rate": 6.8098159509202454e-06, "epoch": 0.06820276497695853, "percentage": 2.28, "elapsed_time": "0:15:23", "remaining_time": "11:01:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 38, "total_steps": 1626, "loss": 1.713, "learning_rate": 6.993865030674846e-06, "epoch": 0.07004608294930875, "percentage": 2.34, "elapsed_time": "0:15:48", "remaining_time": "11:00:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 39, "total_steps": 1626, "loss": 1.7656, "learning_rate": 7.177914110429448e-06, "epoch": 0.07188940092165899, "percentage": 2.4, "elapsed_time": "0:16:13", "remaining_time": "11:00:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 40, "total_steps": 1626, "loss": 1.7899, "learning_rate": 7.361963190184049e-06, "epoch": 0.07373271889400922, "percentage": 2.46, "elapsed_time": "0:16:38", "remaining_time": "10:59:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 41, "total_steps": 1626, "loss": 1.7247, "learning_rate": 7.54601226993865e-06, "epoch": 0.07557603686635944, "percentage": 2.52, "elapsed_time": "0:17:03", "remaining_time": "10:59:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 42, "total_steps": 1626, "loss": 1.7437, "learning_rate": 7.730061349693252e-06, "epoch": 0.07741935483870968, "percentage": 2.58, "elapsed_time": "0:17:28", "remaining_time": "10:58:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 43, "total_steps": 1626, "loss": 1.7758, "learning_rate": 7.914110429447852e-06, "epoch": 0.0792626728110599, "percentage": 2.64, "elapsed_time": "0:17:53", "remaining_time": "10:58:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 44, "total_steps": 1626, "loss": 1.7264, "learning_rate": 8.098159509202455e-06, "epoch": 0.08110599078341015, "percentage": 2.71, "elapsed_time": "0:18:18", "remaining_time": "10:57:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 45, "total_steps": 1626, "loss": 1.6925, "learning_rate": 8.282208588957055e-06, "epoch": 0.08294930875576037, "percentage": 2.77, "elapsed_time": "0:18:42", "remaining_time": "10:57:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 46, "total_steps": 1626, "loss": 1.7767, "learning_rate": 8.466257668711656e-06, "epoch": 0.0847926267281106, "percentage": 2.83, "elapsed_time": "0:19:07", "remaining_time": "10:57:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 47, "total_steps": 1626, "loss": 1.8833, "learning_rate": 8.650306748466258e-06, "epoch": 0.08663594470046083, "percentage": 2.89, "elapsed_time": "0:19:32", "remaining_time": "10:56:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 48, "total_steps": 1626, "loss": 1.7341, "learning_rate": 8.83435582822086e-06, "epoch": 0.08847926267281106, "percentage": 2.95, "elapsed_time": "0:19:57", "remaining_time": "10:56:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 49, "total_steps": 1626, "loss": 1.7423, "learning_rate": 9.01840490797546e-06, "epoch": 0.09032258064516129, "percentage": 3.01, "elapsed_time": "0:20:22", "remaining_time": "10:55:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 50, "total_steps": 1626, "loss": 1.7198, "learning_rate": 9.202453987730062e-06, "epoch": 0.09216589861751152, "percentage": 3.08, "elapsed_time": "0:20:47", "remaining_time": "10:55:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 51, "total_steps": 1626, "loss": 1.7294, "learning_rate": 9.386503067484664e-06, "epoch": 0.09400921658986175, "percentage": 3.14, "elapsed_time": "0:21:12", "remaining_time": "10:55:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 52, "total_steps": 1626, "loss": 1.7277, "learning_rate": 9.570552147239264e-06, "epoch": 0.09585253456221199, "percentage": 3.2, "elapsed_time": "0:21:38", "remaining_time": "10:55:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 53, "total_steps": 1626, "loss": 1.7979, "learning_rate": 9.754601226993865e-06, "epoch": 0.09769585253456221, "percentage": 3.26, "elapsed_time": "0:22:03", "remaining_time": "10:54:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 54, "total_steps": 1626, "loss": 1.7392, "learning_rate": 9.938650306748466e-06, "epoch": 0.09953917050691244, "percentage": 3.32, "elapsed_time": "0:22:28", "remaining_time": "10:54:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 55, "total_steps": 1626, "loss": 1.6929, "learning_rate": 1.0122699386503068e-05, "epoch": 0.10138248847926268, "percentage": 3.38, "elapsed_time": "0:22:53", "remaining_time": "10:53:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 56, "total_steps": 1626, "loss": 1.7455, "learning_rate": 1.030674846625767e-05, "epoch": 0.1032258064516129, "percentage": 3.44, "elapsed_time": "0:23:18", "remaining_time": "10:53:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 57, "total_steps": 1626, "loss": 1.7015, "learning_rate": 1.0490797546012269e-05, "epoch": 0.10506912442396313, "percentage": 3.51, "elapsed_time": "0:23:43", "remaining_time": "10:52:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 58, "total_steps": 1626, "loss": 1.702, "learning_rate": 1.0674846625766871e-05, "epoch": 0.10691244239631337, "percentage": 3.57, "elapsed_time": "0:24:07", "remaining_time": "10:52:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 59, "total_steps": 1626, "loss": 1.7593, "learning_rate": 1.0858895705521474e-05, "epoch": 0.10875576036866359, "percentage": 3.63, "elapsed_time": "0:24:32", "remaining_time": "10:51:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 60, "total_steps": 1626, "loss": 1.7446, "learning_rate": 1.1042944785276074e-05, "epoch": 0.11059907834101383, "percentage": 3.69, "elapsed_time": "0:24:57", "remaining_time": "10:51:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 61, "total_steps": 1626, "loss": 1.7666, "learning_rate": 1.1226993865030675e-05, "epoch": 0.11244239631336406, "percentage": 3.75, "elapsed_time": "0:25:22", "remaining_time": "10:51:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 62, "total_steps": 1626, "loss": 1.7226, "learning_rate": 1.1411042944785277e-05, "epoch": 0.11428571428571428, "percentage": 3.81, "elapsed_time": "0:25:47", "remaining_time": "10:50:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 63, "total_steps": 1626, "loss": 1.7503, "learning_rate": 1.1595092024539878e-05, "epoch": 0.11612903225806452, "percentage": 3.87, "elapsed_time": "0:26:12", "remaining_time": "10:50:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 64, "total_steps": 1626, "loss": 1.7478, "learning_rate": 1.177914110429448e-05, "epoch": 0.11797235023041475, "percentage": 3.94, "elapsed_time": "0:26:37", "remaining_time": "10:49:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 65, "total_steps": 1626, "loss": 1.779, "learning_rate": 1.1963190184049079e-05, "epoch": 0.11981566820276497, "percentage": 4.0, "elapsed_time": "0:27:02", "remaining_time": "10:49:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 66, "total_steps": 1626, "loss": 1.6816, "learning_rate": 1.2147239263803681e-05, "epoch": 0.12165898617511521, "percentage": 4.06, "elapsed_time": "0:27:27", "remaining_time": "10:49:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 67, "total_steps": 1626, "loss": 1.7439, "learning_rate": 1.2331288343558283e-05, "epoch": 0.12350230414746544, "percentage": 4.12, "elapsed_time": "0:27:52", "remaining_time": "10:48:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 68, "total_steps": 1626, "loss": 1.6918, "learning_rate": 1.2515337423312882e-05, "epoch": 0.12534562211981568, "percentage": 4.18, "elapsed_time": "0:28:17", "remaining_time": "10:48:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 69, "total_steps": 1626, "loss": 1.7043, "learning_rate": 1.2699386503067485e-05, "epoch": 0.1271889400921659, "percentage": 4.24, "elapsed_time": "0:28:42", "remaining_time": "10:47:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 70, "total_steps": 1626, "loss": 1.7501, "learning_rate": 1.2883435582822087e-05, "epoch": 0.12903225806451613, "percentage": 4.31, "elapsed_time": "0:29:07", "remaining_time": "10:47:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 71, "total_steps": 1626, "loss": 1.7396, "learning_rate": 1.3067484662576687e-05, "epoch": 0.13087557603686636, "percentage": 4.37, "elapsed_time": "0:29:32", "remaining_time": "10:47:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 72, "total_steps": 1626, "loss": 1.7276, "learning_rate": 1.3251533742331288e-05, "epoch": 0.1327188940092166, "percentage": 4.43, "elapsed_time": "0:29:57", "remaining_time": "10:46:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 73, "total_steps": 1626, "loss": 1.7103, "learning_rate": 1.343558282208589e-05, "epoch": 0.13456221198156681, "percentage": 4.49, "elapsed_time": "0:30:22", "remaining_time": "10:46:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 74, "total_steps": 1626, "loss": 1.7418, "learning_rate": 1.3619631901840491e-05, "epoch": 0.13640552995391705, "percentage": 4.55, "elapsed_time": "0:30:48", "remaining_time": "10:45:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 75, "total_steps": 1626, "loss": 1.7143, "learning_rate": 1.3803680981595093e-05, "epoch": 0.1382488479262673, "percentage": 4.61, "elapsed_time": "0:31:12", "remaining_time": "10:45:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 76, "total_steps": 1626, "loss": 1.7034, "learning_rate": 1.3987730061349692e-05, "epoch": 0.1400921658986175, "percentage": 4.67, "elapsed_time": "0:31:37", "remaining_time": "10:45:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 77, "total_steps": 1626, "loss": 1.726, "learning_rate": 1.4171779141104294e-05, "epoch": 0.14193548387096774, "percentage": 4.74, "elapsed_time": "0:32:02", "remaining_time": "10:44:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 78, "total_steps": 1626, "loss": 1.7184, "learning_rate": 1.4355828220858897e-05, "epoch": 0.14377880184331798, "percentage": 4.8, "elapsed_time": "0:32:27", "remaining_time": "10:44:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 79, "total_steps": 1626, "loss": 1.7506, "learning_rate": 1.4539877300613497e-05, "epoch": 0.1456221198156682, "percentage": 4.86, "elapsed_time": "0:32:52", "remaining_time": "10:43:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 80, "total_steps": 1626, "loss": 1.667, "learning_rate": 1.4723926380368098e-05, "epoch": 0.14746543778801843, "percentage": 4.92, "elapsed_time": "0:33:17", "remaining_time": "10:43:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 81, "total_steps": 1626, "loss": 1.7629, "learning_rate": 1.49079754601227e-05, "epoch": 0.14930875576036867, "percentage": 4.98, "elapsed_time": "0:33:42", "remaining_time": "10:42:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 82, "total_steps": 1626, "loss": 1.7055, "learning_rate": 1.50920245398773e-05, "epoch": 0.15115207373271888, "percentage": 5.04, "elapsed_time": "0:34:07", "remaining_time": "10:42:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 83, "total_steps": 1626, "loss": 1.7149, "learning_rate": 1.52760736196319e-05, "epoch": 0.15299539170506912, "percentage": 5.1, "elapsed_time": "0:34:31", "remaining_time": "10:41:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 84, "total_steps": 1626, "loss": 1.702, "learning_rate": 1.5460122699386504e-05, "epoch": 0.15483870967741936, "percentage": 5.17, "elapsed_time": "0:34:56", "remaining_time": "10:41:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 85, "total_steps": 1626, "loss": 1.7771, "learning_rate": 1.5644171779141104e-05, "epoch": 0.15668202764976957, "percentage": 5.23, "elapsed_time": "0:35:21", "remaining_time": "10:41:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 86, "total_steps": 1626, "loss": 1.704, "learning_rate": 1.5828220858895705e-05, "epoch": 0.1585253456221198, "percentage": 5.29, "elapsed_time": "0:35:46", "remaining_time": "10:40:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 87, "total_steps": 1626, "loss": 1.7032, "learning_rate": 1.601226993865031e-05, "epoch": 0.16036866359447005, "percentage": 5.35, "elapsed_time": "0:36:11", "remaining_time": "10:40:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 88, "total_steps": 1626, "loss": 1.7504, "learning_rate": 1.619631901840491e-05, "epoch": 0.1622119815668203, "percentage": 5.41, "elapsed_time": "0:36:36", "remaining_time": "10:39:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 89, "total_steps": 1626, "loss": 1.6755, "learning_rate": 1.638036809815951e-05, "epoch": 0.1640552995391705, "percentage": 5.47, "elapsed_time": "0:37:01", "remaining_time": "10:39:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 90, "total_steps": 1626, "loss": 1.6542, "learning_rate": 1.656441717791411e-05, "epoch": 0.16589861751152074, "percentage": 5.54, "elapsed_time": "0:37:26", "remaining_time": "10:39:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 91, "total_steps": 1626, "loss": 1.7041, "learning_rate": 1.674846625766871e-05, "epoch": 0.16774193548387098, "percentage": 5.6, "elapsed_time": "0:37:51", "remaining_time": "10:38:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 92, "total_steps": 1626, "loss": 1.664, "learning_rate": 1.693251533742331e-05, "epoch": 0.1695852534562212, "percentage": 5.66, "elapsed_time": "0:38:16", "remaining_time": "10:38:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 93, "total_steps": 1626, "loss": 1.674, "learning_rate": 1.7116564417177916e-05, "epoch": 0.17142857142857143, "percentage": 5.72, "elapsed_time": "0:38:41", "remaining_time": "10:37:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 94, "total_steps": 1626, "loss": 1.6702, "learning_rate": 1.7300613496932516e-05, "epoch": 0.17327188940092167, "percentage": 5.78, "elapsed_time": "0:39:06", "remaining_time": "10:37:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 95, "total_steps": 1626, "loss": 1.6675, "learning_rate": 1.7484662576687117e-05, "epoch": 0.17511520737327188, "percentage": 5.84, "elapsed_time": "0:39:31", "remaining_time": "10:36:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 96, "total_steps": 1626, "loss": 1.735, "learning_rate": 1.766871165644172e-05, "epoch": 0.17695852534562212, "percentage": 5.9, "elapsed_time": "0:39:56", "remaining_time": "10:36:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 97, "total_steps": 1626, "loss": 1.7476, "learning_rate": 1.785276073619632e-05, "epoch": 0.17880184331797236, "percentage": 5.97, "elapsed_time": "0:40:22", "remaining_time": "10:36:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 98, "total_steps": 1626, "loss": 1.7693, "learning_rate": 1.803680981595092e-05, "epoch": 0.18064516129032257, "percentage": 6.03, "elapsed_time": "0:40:47", "remaining_time": "10:35:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 99, "total_steps": 1626, "loss": 1.6862, "learning_rate": 1.8220858895705523e-05, "epoch": 0.1824884792626728, "percentage": 6.09, "elapsed_time": "0:41:11", "remaining_time": "10:35:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 100, "total_steps": 1626, "loss": 1.713, "learning_rate": 1.8404907975460123e-05, "epoch": 0.18433179723502305, "percentage": 6.15, "elapsed_time": "0:41:36", "remaining_time": "10:35:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 101, "total_steps": 1626, "loss": 1.6564, "learning_rate": 1.8588957055214724e-05, "epoch": 0.18617511520737326, "percentage": 6.21, "elapsed_time": "0:42:01", "remaining_time": "10:34:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 102, "total_steps": 1626, "loss": 1.7286, "learning_rate": 1.8773006134969328e-05, "epoch": 0.1880184331797235, "percentage": 6.27, "elapsed_time": "0:42:26", "remaining_time": "10:34:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 103, "total_steps": 1626, "loss": 1.6485, "learning_rate": 1.8957055214723928e-05, "epoch": 0.18986175115207374, "percentage": 6.33, "elapsed_time": "0:42:51", "remaining_time": "10:33:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 104, "total_steps": 1626, "loss": 1.7372, "learning_rate": 1.914110429447853e-05, "epoch": 0.19170506912442398, "percentage": 6.4, "elapsed_time": "0:43:16", "remaining_time": "10:33:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 105, "total_steps": 1626, "loss": 1.6868, "learning_rate": 1.9325153374233126e-05, "epoch": 0.1935483870967742, "percentage": 6.46, "elapsed_time": "0:43:41", "remaining_time": "10:32:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 106, "total_steps": 1626, "loss": 1.7132, "learning_rate": 1.950920245398773e-05, "epoch": 0.19539170506912443, "percentage": 6.52, "elapsed_time": "0:44:06", "remaining_time": "10:32:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 107, "total_steps": 1626, "loss": 1.6949, "learning_rate": 1.969325153374233e-05, "epoch": 0.19723502304147467, "percentage": 6.58, "elapsed_time": "0:44:31", "remaining_time": "10:32:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 108, "total_steps": 1626, "loss": 1.6948, "learning_rate": 1.987730061349693e-05, "epoch": 0.19907834101382488, "percentage": 6.64, "elapsed_time": "0:44:56", "remaining_time": "10:31:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 109, "total_steps": 1626, "loss": 1.7014, "learning_rate": 2.0061349693251535e-05, "epoch": 0.20092165898617512, "percentage": 6.7, "elapsed_time": "0:45:21", "remaining_time": "10:31:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 110, "total_steps": 1626, "loss": 1.709, "learning_rate": 2.0245398773006136e-05, "epoch": 0.20276497695852536, "percentage": 6.77, "elapsed_time": "0:45:46", "remaining_time": "10:30:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 111, "total_steps": 1626, "loss": 1.6834, "learning_rate": 2.0429447852760736e-05, "epoch": 0.20460829493087557, "percentage": 6.83, "elapsed_time": "0:46:11", "remaining_time": "10:30:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 112, "total_steps": 1626, "loss": 1.5777, "learning_rate": 2.061349693251534e-05, "epoch": 0.2064516129032258, "percentage": 6.89, "elapsed_time": "0:46:36", "remaining_time": "10:30:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 113, "total_steps": 1626, "loss": 1.6934, "learning_rate": 2.0797546012269938e-05, "epoch": 0.20829493087557605, "percentage": 6.95, "elapsed_time": "0:47:01", "remaining_time": "10:29:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 114, "total_steps": 1626, "loss": 1.6717, "learning_rate": 2.0981595092024538e-05, "epoch": 0.21013824884792626, "percentage": 7.01, "elapsed_time": "0:47:26", "remaining_time": "10:29:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 115, "total_steps": 1626, "loss": 1.6857, "learning_rate": 2.1165644171779142e-05, "epoch": 0.2119815668202765, "percentage": 7.07, "elapsed_time": "0:47:51", "remaining_time": "10:28:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 116, "total_steps": 1626, "loss": 1.6959, "learning_rate": 2.1349693251533743e-05, "epoch": 0.21382488479262673, "percentage": 7.13, "elapsed_time": "0:48:16", "remaining_time": "10:28:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 117, "total_steps": 1626, "loss": 1.6764, "learning_rate": 2.1533742331288343e-05, "epoch": 0.21566820276497695, "percentage": 7.2, "elapsed_time": "0:48:41", "remaining_time": "10:27:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 118, "total_steps": 1626, "loss": 1.6252, "learning_rate": 2.1717791411042947e-05, "epoch": 0.21751152073732719, "percentage": 7.26, "elapsed_time": "0:49:05", "remaining_time": "10:27:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 119, "total_steps": 1626, "loss": 1.6692, "learning_rate": 2.1901840490797548e-05, "epoch": 0.21935483870967742, "percentage": 7.32, "elapsed_time": "0:49:30", "remaining_time": "10:27:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 120, "total_steps": 1626, "loss": 1.6462, "learning_rate": 2.208588957055215e-05, "epoch": 0.22119815668202766, "percentage": 7.38, "elapsed_time": "0:49:55", "remaining_time": "10:26:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 121, "total_steps": 1626, "loss": 1.7658, "learning_rate": 2.226993865030675e-05, "epoch": 0.22304147465437787, "percentage": 7.44, "elapsed_time": "0:50:20", "remaining_time": "10:26:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 122, "total_steps": 1626, "loss": 1.6979, "learning_rate": 2.245398773006135e-05, "epoch": 0.2248847926267281, "percentage": 7.5, "elapsed_time": "0:50:45", "remaining_time": "10:25:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 123, "total_steps": 1626, "loss": 1.692, "learning_rate": 2.263803680981595e-05, "epoch": 0.22672811059907835, "percentage": 7.56, "elapsed_time": "0:51:10", "remaining_time": "10:25:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 124, "total_steps": 1626, "loss": 1.6947, "learning_rate": 2.2822085889570554e-05, "epoch": 0.22857142857142856, "percentage": 7.63, "elapsed_time": "0:51:35", "remaining_time": "10:24:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 125, "total_steps": 1626, "loss": 1.7041, "learning_rate": 2.3006134969325155e-05, "epoch": 0.2304147465437788, "percentage": 7.69, "elapsed_time": "0:52:00", "remaining_time": "10:24:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 126, "total_steps": 1626, "loss": 1.7073, "learning_rate": 2.3190184049079755e-05, "epoch": 0.23225806451612904, "percentage": 7.75, "elapsed_time": "0:52:25", "remaining_time": "10:24:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 127, "total_steps": 1626, "loss": 1.6824, "learning_rate": 2.337423312883436e-05, "epoch": 0.23410138248847925, "percentage": 7.81, "elapsed_time": "0:52:49", "remaining_time": "10:23:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 128, "total_steps": 1626, "loss": 1.7052, "learning_rate": 2.355828220858896e-05, "epoch": 0.2359447004608295, "percentage": 7.87, "elapsed_time": "0:53:14", "remaining_time": "10:23:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 129, "total_steps": 1626, "loss": 1.6765, "learning_rate": 2.3742331288343557e-05, "epoch": 0.23778801843317973, "percentage": 7.93, "elapsed_time": "0:53:39", "remaining_time": "10:22:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 130, "total_steps": 1626, "loss": 1.6804, "learning_rate": 2.3926380368098158e-05, "epoch": 0.23963133640552994, "percentage": 8.0, "elapsed_time": "0:54:04", "remaining_time": "10:22:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 131, "total_steps": 1626, "loss": 1.709, "learning_rate": 2.411042944785276e-05, "epoch": 0.24147465437788018, "percentage": 8.06, "elapsed_time": "0:54:29", "remaining_time": "10:21:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 132, "total_steps": 1626, "loss": 1.6391, "learning_rate": 2.4294478527607362e-05, "epoch": 0.24331797235023042, "percentage": 8.12, "elapsed_time": "0:54:55", "remaining_time": "10:21:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 133, "total_steps": 1626, "loss": 1.6555, "learning_rate": 2.4478527607361963e-05, "epoch": 0.24516129032258063, "percentage": 8.18, "elapsed_time": "0:55:20", "remaining_time": "10:21:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 134, "total_steps": 1626, "loss": 1.7266, "learning_rate": 2.4662576687116567e-05, "epoch": 0.24700460829493087, "percentage": 8.24, "elapsed_time": "0:55:44", "remaining_time": "10:20:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 135, "total_steps": 1626, "loss": 1.7161, "learning_rate": 2.4846625766871167e-05, "epoch": 0.2488479262672811, "percentage": 8.3, "elapsed_time": "0:56:09", "remaining_time": "10:20:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 136, "total_steps": 1626, "loss": 1.641, "learning_rate": 2.5030674846625765e-05, "epoch": 0.25069124423963135, "percentage": 8.36, "elapsed_time": "0:56:34", "remaining_time": "10:19:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 137, "total_steps": 1626, "loss": 1.7422, "learning_rate": 2.521472392638037e-05, "epoch": 0.25253456221198156, "percentage": 8.43, "elapsed_time": "0:56:59", "remaining_time": "10:19:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 138, "total_steps": 1626, "loss": 1.7261, "learning_rate": 2.539877300613497e-05, "epoch": 0.2543778801843318, "percentage": 8.49, "elapsed_time": "0:57:24", "remaining_time": "10:19:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 139, "total_steps": 1626, "loss": 1.7018, "learning_rate": 2.558282208588957e-05, "epoch": 0.25622119815668204, "percentage": 8.55, "elapsed_time": "0:57:49", "remaining_time": "10:18:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 140, "total_steps": 1626, "loss": 1.6838, "learning_rate": 2.5766871165644174e-05, "epoch": 0.25806451612903225, "percentage": 8.61, "elapsed_time": "0:58:14", "remaining_time": "10:18:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 141, "total_steps": 1626, "loss": 1.7003, "learning_rate": 2.5950920245398774e-05, "epoch": 0.25990783410138246, "percentage": 8.67, "elapsed_time": "0:58:39", "remaining_time": "10:17:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 142, "total_steps": 1626, "loss": 1.6799, "learning_rate": 2.6134969325153375e-05, "epoch": 0.26175115207373273, "percentage": 8.73, "elapsed_time": "0:59:04", "remaining_time": "10:17:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 143, "total_steps": 1626, "loss": 1.6357, "learning_rate": 2.631901840490798e-05, "epoch": 0.26359447004608294, "percentage": 8.79, "elapsed_time": "0:59:29", "remaining_time": "10:16:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 144, "total_steps": 1626, "loss": 1.6062, "learning_rate": 2.6503067484662576e-05, "epoch": 0.2654377880184332, "percentage": 8.86, "elapsed_time": "0:59:54", "remaining_time": "10:16:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 145, "total_steps": 1626, "loss": 1.7424, "learning_rate": 2.6687116564417177e-05, "epoch": 0.2672811059907834, "percentage": 8.92, "elapsed_time": "1:00:19", "remaining_time": "10:16:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 146, "total_steps": 1626, "loss": 1.7195, "learning_rate": 2.687116564417178e-05, "epoch": 0.26912442396313363, "percentage": 8.98, "elapsed_time": "1:00:43", "remaining_time": "10:15:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 147, "total_steps": 1626, "loss": 1.6467, "learning_rate": 2.705521472392638e-05, "epoch": 0.2709677419354839, "percentage": 9.04, "elapsed_time": "1:01:08", "remaining_time": "10:15:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 148, "total_steps": 1626, "loss": 1.6234, "learning_rate": 2.7239263803680982e-05, "epoch": 0.2728110599078341, "percentage": 9.1, "elapsed_time": "1:01:33", "remaining_time": "10:14:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 149, "total_steps": 1626, "loss": 1.6945, "learning_rate": 2.7423312883435586e-05, "epoch": 0.2746543778801843, "percentage": 9.16, "elapsed_time": "1:01:58", "remaining_time": "10:14:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 150, "total_steps": 1626, "loss": 1.6172, "learning_rate": 2.7607361963190186e-05, "epoch": 0.2764976958525346, "percentage": 9.23, "elapsed_time": "1:02:23", "remaining_time": "10:13:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 151, "total_steps": 1626, "loss": 1.6771, "learning_rate": 2.7791411042944787e-05, "epoch": 0.2783410138248848, "percentage": 9.29, "elapsed_time": "1:02:48", "remaining_time": "10:13:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 152, "total_steps": 1626, "loss": 1.6522, "learning_rate": 2.7975460122699384e-05, "epoch": 0.280184331797235, "percentage": 9.35, "elapsed_time": "1:03:13", "remaining_time": "10:13:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 153, "total_steps": 1626, "loss": 1.6456, "learning_rate": 2.8159509202453988e-05, "epoch": 0.2820276497695853, "percentage": 9.41, "elapsed_time": "1:03:38", "remaining_time": "10:12:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 154, "total_steps": 1626, "loss": 1.6521, "learning_rate": 2.834355828220859e-05, "epoch": 0.2838709677419355, "percentage": 9.47, "elapsed_time": "1:04:03", "remaining_time": "10:12:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 155, "total_steps": 1626, "loss": 1.6517, "learning_rate": 2.852760736196319e-05, "epoch": 0.2857142857142857, "percentage": 9.53, "elapsed_time": "1:04:28", "remaining_time": "10:11:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 156, "total_steps": 1626, "loss": 1.6422, "learning_rate": 2.8711656441717793e-05, "epoch": 0.28755760368663597, "percentage": 9.59, "elapsed_time": "1:04:53", "remaining_time": "10:11:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 157, "total_steps": 1626, "loss": 1.6693, "learning_rate": 2.8895705521472394e-05, "epoch": 0.2894009216589862, "percentage": 9.66, "elapsed_time": "1:05:18", "remaining_time": "10:11:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 158, "total_steps": 1626, "loss": 1.7079, "learning_rate": 2.9079754601226994e-05, "epoch": 0.2912442396313364, "percentage": 9.72, "elapsed_time": "1:05:43", "remaining_time": "10:10:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 159, "total_steps": 1626, "loss": 1.7135, "learning_rate": 2.92638036809816e-05, "epoch": 0.29308755760368665, "percentage": 9.78, "elapsed_time": "1:06:08", "remaining_time": "10:10:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 160, "total_steps": 1626, "loss": 1.6375, "learning_rate": 2.9447852760736196e-05, "epoch": 0.29493087557603687, "percentage": 9.84, "elapsed_time": "1:06:33", "remaining_time": "10:09:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 161, "total_steps": 1626, "loss": 1.6542, "learning_rate": 2.9631901840490796e-05, "epoch": 0.2967741935483871, "percentage": 9.9, "elapsed_time": "1:06:57", "remaining_time": "10:09:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 162, "total_steps": 1626, "loss": 1.6308, "learning_rate": 2.98159509202454e-05, "epoch": 0.29861751152073734, "percentage": 9.96, "elapsed_time": "1:07:22", "remaining_time": "10:08:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 163, "total_steps": 1626, "loss": 1.7211, "learning_rate": 3e-05, "epoch": 0.30046082949308756, "percentage": 10.02, "elapsed_time": "1:07:48", "remaining_time": "10:08:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 164, "total_steps": 1626, "loss": 1.6273, "learning_rate": 2.9999965416241516e-05, "epoch": 0.30230414746543777, "percentage": 10.09, "elapsed_time": "1:08:13", "remaining_time": "10:08:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 165, "total_steps": 1626, "loss": 1.7136, "learning_rate": 2.999986166512553e-05, "epoch": 0.30414746543778803, "percentage": 10.15, "elapsed_time": "1:08:40", "remaining_time": "10:08:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 166, "total_steps": 1626, "loss": 1.6912, "learning_rate": 2.9999688747130467e-05, "epoch": 0.30599078341013825, "percentage": 10.21, "elapsed_time": "1:09:05", "remaining_time": "10:07:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 167, "total_steps": 1626, "loss": 1.6703, "learning_rate": 2.999944666305367e-05, "epoch": 0.30783410138248846, "percentage": 10.27, "elapsed_time": "1:09:29", "remaining_time": "10:07:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 168, "total_steps": 1626, "loss": 1.5595, "learning_rate": 2.999913541401143e-05, "epoch": 0.3096774193548387, "percentage": 10.33, "elapsed_time": "1:09:54", "remaining_time": "10:06:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 169, "total_steps": 1626, "loss": 1.6433, "learning_rate": 2.9998755001438975e-05, "epoch": 0.31152073732718893, "percentage": 10.39, "elapsed_time": "1:10:19", "remaining_time": "10:06:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 170, "total_steps": 1626, "loss": 1.6257, "learning_rate": 2.999830542709045e-05, "epoch": 0.31336405529953915, "percentage": 10.46, "elapsed_time": "1:10:44", "remaining_time": "10:05:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 171, "total_steps": 1626, "loss": 1.6341, "learning_rate": 2.9997786693038913e-05, "epoch": 0.3152073732718894, "percentage": 10.52, "elapsed_time": "1:11:09", "remaining_time": "10:05:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 172, "total_steps": 1626, "loss": 1.646, "learning_rate": 2.9997198801676335e-05, "epoch": 0.3170506912442396, "percentage": 10.58, "elapsed_time": "1:11:34", "remaining_time": "10:05:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 173, "total_steps": 1626, "loss": 1.6753, "learning_rate": 2.9996541755713585e-05, "epoch": 0.31889400921658984, "percentage": 10.64, "elapsed_time": "1:12:00", "remaining_time": "10:04:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 174, "total_steps": 1626, "loss": 1.6883, "learning_rate": 2.999581555818041e-05, "epoch": 0.3207373271889401, "percentage": 10.7, "elapsed_time": "1:12:25", "remaining_time": "10:04:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 175, "total_steps": 1626, "loss": 1.656, "learning_rate": 2.9995020212425432e-05, "epoch": 0.3225806451612903, "percentage": 10.76, "elapsed_time": "1:12:50", "remaining_time": "10:03:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 176, "total_steps": 1626, "loss": 1.725, "learning_rate": 2.9994155722116118e-05, "epoch": 0.3244239631336406, "percentage": 10.82, "elapsed_time": "1:13:15", "remaining_time": "10:03:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 177, "total_steps": 1626, "loss": 1.7542, "learning_rate": 2.999322209123878e-05, "epoch": 0.3262672811059908, "percentage": 10.89, "elapsed_time": "1:13:39", "remaining_time": "10:03:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 178, "total_steps": 1626, "loss": 1.6049, "learning_rate": 2.9992219324098545e-05, "epoch": 0.328110599078341, "percentage": 10.95, "elapsed_time": "1:14:04", "remaining_time": "10:02:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 179, "total_steps": 1626, "loss": 1.637, "learning_rate": 2.9991147425319346e-05, "epoch": 0.32995391705069127, "percentage": 11.01, "elapsed_time": "1:14:29", "remaining_time": "10:02:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 180, "total_steps": 1626, "loss": 1.7051, "learning_rate": 2.9990006399843884e-05, "epoch": 0.3317972350230415, "percentage": 11.07, "elapsed_time": "1:14:54", "remaining_time": "10:01:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 181, "total_steps": 1626, "loss": 1.7094, "learning_rate": 2.998879625293362e-05, "epoch": 0.3336405529953917, "percentage": 11.13, "elapsed_time": "1:15:19", "remaining_time": "10:01:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 182, "total_steps": 1626, "loss": 1.6021, "learning_rate": 2.9987516990168743e-05, "epoch": 0.33548387096774196, "percentage": 11.19, "elapsed_time": "1:15:44", "remaining_time": "10:00:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 183, "total_steps": 1626, "loss": 1.6267, "learning_rate": 2.9986168617448153e-05, "epoch": 0.33732718894009217, "percentage": 11.25, "elapsed_time": "1:16:09", "remaining_time": "10:00:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 184, "total_steps": 1626, "loss": 1.662, "learning_rate": 2.9984751140989417e-05, "epoch": 0.3391705069124424, "percentage": 11.32, "elapsed_time": "1:16:34", "remaining_time": "10:00:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 185, "total_steps": 1626, "loss": 1.6909, "learning_rate": 2.9983264567328756e-05, "epoch": 0.34101382488479265, "percentage": 11.38, "elapsed_time": "1:16:59", "remaining_time": "9:59:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 186, "total_steps": 1626, "loss": 1.6502, "learning_rate": 2.9981708903321017e-05, "epoch": 0.34285714285714286, "percentage": 11.44, "elapsed_time": "1:17:24", "remaining_time": "9:59:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 187, "total_steps": 1626, "loss": 1.6409, "learning_rate": 2.9980084156139625e-05, "epoch": 0.34470046082949307, "percentage": 11.5, "elapsed_time": "1:17:49", "remaining_time": "9:58:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 188, "total_steps": 1626, "loss": 1.6765, "learning_rate": 2.9978390333276565e-05, "epoch": 0.34654377880184334, "percentage": 11.56, "elapsed_time": "1:18:13", "remaining_time": "9:58:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 189, "total_steps": 1626, "loss": 1.7486, "learning_rate": 2.9976627442542325e-05, "epoch": 0.34838709677419355, "percentage": 11.62, "elapsed_time": "1:18:38", "remaining_time": "9:57:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 190, "total_steps": 1626, "loss": 1.6863, "learning_rate": 2.997479549206591e-05, "epoch": 0.35023041474654376, "percentage": 11.69, "elapsed_time": "1:19:03", "remaining_time": "9:57:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 191, "total_steps": 1626, "loss": 1.6223, "learning_rate": 2.9972894490294738e-05, "epoch": 0.35207373271889403, "percentage": 11.75, "elapsed_time": "1:19:28", "remaining_time": "9:57:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 192, "total_steps": 1626, "loss": 1.7044, "learning_rate": 2.9970924445994645e-05, "epoch": 0.35391705069124424, "percentage": 11.81, "elapsed_time": "1:19:53", "remaining_time": "9:56:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 193, "total_steps": 1626, "loss": 1.6907, "learning_rate": 2.9968885368249847e-05, "epoch": 0.35576036866359445, "percentage": 11.87, "elapsed_time": "1:20:18", "remaining_time": "9:56:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 194, "total_steps": 1626, "loss": 1.7002, "learning_rate": 2.9966777266462863e-05, "epoch": 0.3576036866359447, "percentage": 11.93, "elapsed_time": "1:20:43", "remaining_time": "9:55:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 195, "total_steps": 1626, "loss": 1.639, "learning_rate": 2.9964600150354512e-05, "epoch": 0.35944700460829493, "percentage": 11.99, "elapsed_time": "1:21:09", "remaining_time": "9:55:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 196, "total_steps": 1626, "loss": 1.679, "learning_rate": 2.9962354029963835e-05, "epoch": 0.36129032258064514, "percentage": 12.05, "elapsed_time": "1:21:33", "remaining_time": "9:55:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 197, "total_steps": 1626, "loss": 1.7343, "learning_rate": 2.9960038915648076e-05, "epoch": 0.3631336405529954, "percentage": 12.12, "elapsed_time": "1:21:58", "remaining_time": "9:54:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 198, "total_steps": 1626, "loss": 1.6759, "learning_rate": 2.9957654818082615e-05, "epoch": 0.3649769585253456, "percentage": 12.18, "elapsed_time": "1:22:23", "remaining_time": "9:54:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 199, "total_steps": 1626, "loss": 1.7189, "learning_rate": 2.9955201748260923e-05, "epoch": 0.36682027649769583, "percentage": 12.24, "elapsed_time": "1:22:48", "remaining_time": "9:53:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 200, "total_steps": 1626, "loss": 1.6882, "learning_rate": 2.9952679717494516e-05, "epoch": 0.3686635944700461, "percentage": 12.3, "elapsed_time": "1:23:13", "remaining_time": "9:53:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 201, "total_steps": 1626, "loss": 1.6536, "learning_rate": 2.9950088737412898e-05, "epoch": 0.3705069124423963, "percentage": 12.36, "elapsed_time": "1:23:48", "remaining_time": "9:54:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 202, "total_steps": 1626, "loss": 1.6957, "learning_rate": 2.9947428819963526e-05, "epoch": 0.3723502304147465, "percentage": 12.42, "elapsed_time": "1:24:13", "remaining_time": "9:53:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 203, "total_steps": 1626, "loss": 1.6434, "learning_rate": 2.994469997741171e-05, "epoch": 0.3741935483870968, "percentage": 12.48, "elapsed_time": "1:24:38", "remaining_time": "9:53:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 204, "total_steps": 1626, "loss": 1.6897, "learning_rate": 2.994190222234061e-05, "epoch": 0.376036866359447, "percentage": 12.55, "elapsed_time": "1:25:02", "remaining_time": "9:52:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 205, "total_steps": 1626, "loss": 1.6727, "learning_rate": 2.9939035567651146e-05, "epoch": 0.3778801843317972, "percentage": 12.61, "elapsed_time": "1:25:27", "remaining_time": "9:52:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 206, "total_steps": 1626, "loss": 1.6824, "learning_rate": 2.9936100026561933e-05, "epoch": 0.3797235023041475, "percentage": 12.67, "elapsed_time": "1:25:52", "remaining_time": "9:51:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 207, "total_steps": 1626, "loss": 1.6703, "learning_rate": 2.9933095612609253e-05, "epoch": 0.3815668202764977, "percentage": 12.73, "elapsed_time": "1:26:17", "remaining_time": "9:51:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 208, "total_steps": 1626, "loss": 1.7284, "learning_rate": 2.993002233964696e-05, "epoch": 0.38341013824884795, "percentage": 12.79, "elapsed_time": "1:26:42", "remaining_time": "9:51:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 209, "total_steps": 1626, "loss": 1.6617, "learning_rate": 2.9926880221846435e-05, "epoch": 0.38525345622119817, "percentage": 12.85, "elapsed_time": "1:27:07", "remaining_time": "9:50:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 210, "total_steps": 1626, "loss": 1.5947, "learning_rate": 2.9923669273696506e-05, "epoch": 0.3870967741935484, "percentage": 12.92, "elapsed_time": "1:27:32", "remaining_time": "9:50:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 211, "total_steps": 1626, "loss": 1.6403, "learning_rate": 2.9920389510003395e-05, "epoch": 0.38894009216589864, "percentage": 12.98, "elapsed_time": "1:27:57", "remaining_time": "9:49:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 212, "total_steps": 1626, "loss": 1.7241, "learning_rate": 2.9917040945890638e-05, "epoch": 0.39078341013824885, "percentage": 13.04, "elapsed_time": "1:28:22", "remaining_time": "9:49:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 213, "total_steps": 1626, "loss": 1.6997, "learning_rate": 2.9913623596799032e-05, "epoch": 0.39262672811059907, "percentage": 13.1, "elapsed_time": "1:28:47", "remaining_time": "9:48:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 214, "total_steps": 1626, "loss": 1.6451, "learning_rate": 2.9910137478486545e-05, "epoch": 0.39447004608294933, "percentage": 13.16, "elapsed_time": "1:29:12", "remaining_time": "9:48:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 215, "total_steps": 1626, "loss": 1.6784, "learning_rate": 2.990658260702826e-05, "epoch": 0.39631336405529954, "percentage": 13.22, "elapsed_time": "1:29:36", "remaining_time": "9:48:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 216, "total_steps": 1626, "loss": 1.7088, "learning_rate": 2.9902958998816274e-05, "epoch": 0.39815668202764976, "percentage": 13.28, "elapsed_time": "1:30:01", "remaining_time": "9:47:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 217, "total_steps": 1626, "loss": 1.6855, "learning_rate": 2.989926667055966e-05, "epoch": 0.4, "percentage": 13.35, "elapsed_time": "1:30:27", "remaining_time": "9:47:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 218, "total_steps": 1626, "loss": 1.6437, "learning_rate": 2.989550563928436e-05, "epoch": 0.40184331797235023, "percentage": 13.41, "elapsed_time": "1:30:52", "remaining_time": "9:46:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 219, "total_steps": 1626, "loss": 1.6708, "learning_rate": 2.9891675922333125e-05, "epoch": 0.40368663594470044, "percentage": 13.47, "elapsed_time": "1:31:17", "remaining_time": "9:46:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 220, "total_steps": 1626, "loss": 1.6655, "learning_rate": 2.9887777537365416e-05, "epoch": 0.4055299539170507, "percentage": 13.53, "elapsed_time": "1:31:42", "remaining_time": "9:46:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 221, "total_steps": 1626, "loss": 1.6737, "learning_rate": 2.9883810502357346e-05, "epoch": 0.4073732718894009, "percentage": 13.59, "elapsed_time": "1:32:07", "remaining_time": "9:45:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 222, "total_steps": 1626, "loss": 1.6562, "learning_rate": 2.9879774835601574e-05, "epoch": 0.40921658986175113, "percentage": 13.65, "elapsed_time": "1:32:32", "remaining_time": "9:45:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 223, "total_steps": 1626, "loss": 1.696, "learning_rate": 2.987567055570724e-05, "epoch": 0.4110599078341014, "percentage": 13.71, "elapsed_time": "1:32:57", "remaining_time": "9:44:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 224, "total_steps": 1626, "loss": 1.5771, "learning_rate": 2.987149768159987e-05, "epoch": 0.4129032258064516, "percentage": 13.78, "elapsed_time": "1:33:22", "remaining_time": "9:44:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 225, "total_steps": 1626, "loss": 1.7274, "learning_rate": 2.986725623252128e-05, "epoch": 0.4147465437788018, "percentage": 13.84, "elapsed_time": "1:33:47", "remaining_time": "9:43:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 226, "total_steps": 1626, "loss": 1.6277, "learning_rate": 2.9862946228029507e-05, "epoch": 0.4165898617511521, "percentage": 13.9, "elapsed_time": "1:34:12", "remaining_time": "9:43:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 227, "total_steps": 1626, "loss": 1.6161, "learning_rate": 2.9858567687998702e-05, "epoch": 0.4184331797235023, "percentage": 13.96, "elapsed_time": "1:34:36", "remaining_time": "9:43:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 228, "total_steps": 1626, "loss": 1.6358, "learning_rate": 2.9854120632619053e-05, "epoch": 0.4202764976958525, "percentage": 14.02, "elapsed_time": "1:35:01", "remaining_time": "9:42:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 229, "total_steps": 1626, "loss": 1.7176, "learning_rate": 2.9849605082396678e-05, "epoch": 0.4221198156682028, "percentage": 14.08, "elapsed_time": "1:35:27", "remaining_time": "9:42:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 230, "total_steps": 1626, "loss": 1.6292, "learning_rate": 2.9845021058153532e-05, "epoch": 0.423963133640553, "percentage": 14.15, "elapsed_time": "1:35:52", "remaining_time": "9:41:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 231, "total_steps": 1626, "loss": 1.6453, "learning_rate": 2.984036858102732e-05, "epoch": 0.4258064516129032, "percentage": 14.21, "elapsed_time": "1:36:17", "remaining_time": "9:41:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 232, "total_steps": 1626, "loss": 1.7311, "learning_rate": 2.98356476724714e-05, "epoch": 0.42764976958525347, "percentage": 14.27, "elapsed_time": "1:36:41", "remaining_time": "9:41:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 233, "total_steps": 1626, "loss": 1.632, "learning_rate": 2.9830858354254672e-05, "epoch": 0.4294930875576037, "percentage": 14.33, "elapsed_time": "1:37:06", "remaining_time": "9:40:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 234, "total_steps": 1626, "loss": 1.6307, "learning_rate": 2.9826000648461484e-05, "epoch": 0.4313364055299539, "percentage": 14.39, "elapsed_time": "1:37:31", "remaining_time": "9:40:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 235, "total_steps": 1626, "loss": 1.6314, "learning_rate": 2.982107457749153e-05, "epoch": 0.43317972350230416, "percentage": 14.45, "elapsed_time": "1:37:56", "remaining_time": "9:39:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 236, "total_steps": 1626, "loss": 1.6417, "learning_rate": 2.9816080164059758e-05, "epoch": 0.43502304147465437, "percentage": 14.51, "elapsed_time": "1:38:21", "remaining_time": "9:39:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 237, "total_steps": 1626, "loss": 1.5736, "learning_rate": 2.981101743119624e-05, "epoch": 0.4368663594470046, "percentage": 14.58, "elapsed_time": "1:38:46", "remaining_time": "9:38:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 238, "total_steps": 1626, "loss": 1.6921, "learning_rate": 2.9805886402246084e-05, "epoch": 0.43870967741935485, "percentage": 14.64, "elapsed_time": "1:39:11", "remaining_time": "9:38:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 239, "total_steps": 1626, "loss": 1.642, "learning_rate": 2.9800687100869334e-05, "epoch": 0.44055299539170506, "percentage": 14.7, "elapsed_time": "1:39:36", "remaining_time": "9:38:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 240, "total_steps": 1626, "loss": 1.6786, "learning_rate": 2.9795419551040836e-05, "epoch": 0.4423963133640553, "percentage": 14.76, "elapsed_time": "1:40:01", "remaining_time": "9:37:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 241, "total_steps": 1626, "loss": 1.6565, "learning_rate": 2.9790083777050148e-05, "epoch": 0.44423963133640554, "percentage": 14.82, "elapsed_time": "1:40:26", "remaining_time": "9:37:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 242, "total_steps": 1626, "loss": 1.7311, "learning_rate": 2.9784679803501416e-05, "epoch": 0.44608294930875575, "percentage": 14.88, "elapsed_time": "1:40:51", "remaining_time": "9:36:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 243, "total_steps": 1626, "loss": 1.6551, "learning_rate": 2.977920765531327e-05, "epoch": 0.447926267281106, "percentage": 14.94, "elapsed_time": "1:41:16", "remaining_time": "9:36:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 244, "total_steps": 1626, "loss": 1.6495, "learning_rate": 2.9773667357718706e-05, "epoch": 0.4497695852534562, "percentage": 15.01, "elapsed_time": "1:41:41", "remaining_time": "9:35:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 245, "total_steps": 1626, "loss": 1.6847, "learning_rate": 2.9768058936264967e-05, "epoch": 0.45161290322580644, "percentage": 15.07, "elapsed_time": "1:42:06", "remaining_time": "9:35:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 246, "total_steps": 1626, "loss": 1.642, "learning_rate": 2.976238241681342e-05, "epoch": 0.4534562211981567, "percentage": 15.13, "elapsed_time": "1:42:31", "remaining_time": "9:35:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 247, "total_steps": 1626, "loss": 1.5912, "learning_rate": 2.9756637825539453e-05, "epoch": 0.4552995391705069, "percentage": 15.19, "elapsed_time": "1:42:56", "remaining_time": "9:34:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 248, "total_steps": 1626, "loss": 1.6017, "learning_rate": 2.9750825188932334e-05, "epoch": 0.45714285714285713, "percentage": 15.25, "elapsed_time": "1:43:21", "remaining_time": "9:34:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 249, "total_steps": 1626, "loss": 1.6603, "learning_rate": 2.9744944533795112e-05, "epoch": 0.4589861751152074, "percentage": 15.31, "elapsed_time": "1:43:46", "remaining_time": "9:33:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 250, "total_steps": 1626, "loss": 1.6234, "learning_rate": 2.973899588724448e-05, "epoch": 0.4608294930875576, "percentage": 15.38, "elapsed_time": "1:44:10", "remaining_time": "9:33:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 251, "total_steps": 1626, "loss": 1.6411, "learning_rate": 2.973297927671063e-05, "epoch": 0.4626728110599078, "percentage": 15.44, "elapsed_time": "1:44:36", "remaining_time": "9:33:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 252, "total_steps": 1626, "loss": 1.6307, "learning_rate": 2.9726894729937177e-05, "epoch": 0.4645161290322581, "percentage": 15.5, "elapsed_time": "1:45:01", "remaining_time": "9:32:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 253, "total_steps": 1626, "loss": 1.6697, "learning_rate": 2.972074227498098e-05, "epoch": 0.4663594470046083, "percentage": 15.56, "elapsed_time": "1:45:26", "remaining_time": "9:32:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 254, "total_steps": 1626, "loss": 1.6441, "learning_rate": 2.971452194021204e-05, "epoch": 0.4682027649769585, "percentage": 15.62, "elapsed_time": "1:45:51", "remaining_time": "9:31:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 255, "total_steps": 1626, "loss": 1.6774, "learning_rate": 2.9708233754313365e-05, "epoch": 0.4700460829493088, "percentage": 15.68, "elapsed_time": "1:46:16", "remaining_time": "9:31:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 256, "total_steps": 1626, "loss": 1.693, "learning_rate": 2.9701877746280843e-05, "epoch": 0.471889400921659, "percentage": 15.74, "elapsed_time": "1:46:41", "remaining_time": "9:30:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 257, "total_steps": 1626, "loss": 1.6944, "learning_rate": 2.9695453945423087e-05, "epoch": 0.4737327188940092, "percentage": 15.81, "elapsed_time": "1:47:06", "remaining_time": "9:30:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 258, "total_steps": 1626, "loss": 1.6628, "learning_rate": 2.9688962381361317e-05, "epoch": 0.47557603686635946, "percentage": 15.87, "elapsed_time": "1:47:31", "remaining_time": "9:30:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 259, "total_steps": 1626, "loss": 1.6312, "learning_rate": 2.968240308402923e-05, "epoch": 0.4774193548387097, "percentage": 15.93, "elapsed_time": "1:47:56", "remaining_time": "9:29:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 260, "total_steps": 1626, "loss": 1.6166, "learning_rate": 2.967577608367285e-05, "epoch": 0.4792626728110599, "percentage": 15.99, "elapsed_time": "1:48:21", "remaining_time": "9:29:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 261, "total_steps": 1626, "loss": 1.5918, "learning_rate": 2.9669081410850378e-05, "epoch": 0.48110599078341015, "percentage": 16.05, "elapsed_time": "1:48:46", "remaining_time": "9:28:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 262, "total_steps": 1626, "loss": 1.6475, "learning_rate": 2.966231909643208e-05, "epoch": 0.48294930875576036, "percentage": 16.11, "elapsed_time": "1:49:11", "remaining_time": "9:28:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 263, "total_steps": 1626, "loss": 1.6218, "learning_rate": 2.9655489171600118e-05, "epoch": 0.4847926267281106, "percentage": 16.17, "elapsed_time": "1:49:36", "remaining_time": "9:28:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 264, "total_steps": 1626, "loss": 1.7007, "learning_rate": 2.9648591667848428e-05, "epoch": 0.48663594470046084, "percentage": 16.24, "elapsed_time": "1:50:00", "remaining_time": "9:27:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 265, "total_steps": 1626, "loss": 1.6758, "learning_rate": 2.9641626616982555e-05, "epoch": 0.48847926267281105, "percentage": 16.3, "elapsed_time": "1:50:25", "remaining_time": "9:27:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 266, "total_steps": 1626, "loss": 1.6889, "learning_rate": 2.9634594051119515e-05, "epoch": 0.49032258064516127, "percentage": 16.36, "elapsed_time": "1:50:50", "remaining_time": "9:26:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 267, "total_steps": 1626, "loss": 1.7099, "learning_rate": 2.9627494002687653e-05, "epoch": 0.49216589861751153, "percentage": 16.42, "elapsed_time": "1:51:15", "remaining_time": "9:26:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 268, "total_steps": 1626, "loss": 1.6494, "learning_rate": 2.9620326504426476e-05, "epoch": 0.49400921658986174, "percentage": 16.48, "elapsed_time": "1:51:40", "remaining_time": "9:25:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 269, "total_steps": 1626, "loss": 1.6435, "learning_rate": 2.9613091589386526e-05, "epoch": 0.49585253456221196, "percentage": 16.54, "elapsed_time": "1:52:05", "remaining_time": "9:25:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 270, "total_steps": 1626, "loss": 1.6588, "learning_rate": 2.9605789290929214e-05, "epoch": 0.4976958525345622, "percentage": 16.61, "elapsed_time": "1:52:30", "remaining_time": "9:25:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 271, "total_steps": 1626, "loss": 1.6463, "learning_rate": 2.9598419642726655e-05, "epoch": 0.49953917050691243, "percentage": 16.67, "elapsed_time": "1:52:55", "remaining_time": "9:24:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 272, "total_steps": 1626, "loss": 1.6022, "learning_rate": 2.9590982678761544e-05, "epoch": 0.5013824884792627, "percentage": 16.73, "elapsed_time": "1:53:21", "remaining_time": "9:24:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 273, "total_steps": 1626, "loss": 1.6602, "learning_rate": 2.958347843332696e-05, "epoch": 0.5032258064516129, "percentage": 16.79, "elapsed_time": "1:53:46", "remaining_time": "9:23:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 274, "total_steps": 1626, "loss": 1.6223, "learning_rate": 2.957590694102624e-05, "epoch": 0.5050691244239631, "percentage": 16.85, "elapsed_time": "1:54:11", "remaining_time": "9:23:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 275, "total_steps": 1626, "loss": 1.6716, "learning_rate": 2.9568268236772816e-05, "epoch": 0.5069124423963134, "percentage": 16.91, "elapsed_time": "1:54:36", "remaining_time": "9:23:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 276, "total_steps": 1626, "loss": 1.6326, "learning_rate": 2.956056235579002e-05, "epoch": 0.5087557603686635, "percentage": 16.97, "elapsed_time": "1:55:01", "remaining_time": "9:22:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 277, "total_steps": 1626, "loss": 1.6584, "learning_rate": 2.955278933361097e-05, "epoch": 0.5105990783410138, "percentage": 17.04, "elapsed_time": "1:55:26", "remaining_time": "9:22:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 278, "total_steps": 1626, "loss": 1.6457, "learning_rate": 2.9544949206078372e-05, "epoch": 0.5124423963133641, "percentage": 17.1, "elapsed_time": "1:55:51", "remaining_time": "9:21:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 279, "total_steps": 1626, "loss": 1.6027, "learning_rate": 2.9537042009344376e-05, "epoch": 0.5142857142857142, "percentage": 17.16, "elapsed_time": "1:56:15", "remaining_time": "9:21:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 280, "total_steps": 1626, "loss": 1.6157, "learning_rate": 2.9529067779870385e-05, "epoch": 0.5161290322580645, "percentage": 17.22, "elapsed_time": "1:56:40", "remaining_time": "9:20:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 281, "total_steps": 1626, "loss": 1.6148, "learning_rate": 2.952102655442692e-05, "epoch": 0.5179723502304148, "percentage": 17.28, "elapsed_time": "1:57:05", "remaining_time": "9:20:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 282, "total_steps": 1626, "loss": 1.6785, "learning_rate": 2.9512918370093407e-05, "epoch": 0.5198156682027649, "percentage": 17.34, "elapsed_time": "1:57:30", "remaining_time": "9:20:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 283, "total_steps": 1626, "loss": 1.5828, "learning_rate": 2.950474326425805e-05, "epoch": 0.5216589861751152, "percentage": 17.4, "elapsed_time": "1:57:55", "remaining_time": "9:19:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 284, "total_steps": 1626, "loss": 1.6606, "learning_rate": 2.949650127461764e-05, "epoch": 0.5235023041474655, "percentage": 17.47, "elapsed_time": "1:58:20", "remaining_time": "9:19:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 285, "total_steps": 1626, "loss": 1.7019, "learning_rate": 2.948819243917737e-05, "epoch": 0.5253456221198156, "percentage": 17.53, "elapsed_time": "1:58:45", "remaining_time": "9:18:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 286, "total_steps": 1626, "loss": 1.7214, "learning_rate": 2.947981679625067e-05, "epoch": 0.5271889400921659, "percentage": 17.59, "elapsed_time": "1:59:10", "remaining_time": "9:18:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 287, "total_steps": 1626, "loss": 1.6599, "learning_rate": 2.947137438445904e-05, "epoch": 0.5290322580645161, "percentage": 17.65, "elapsed_time": "1:59:35", "remaining_time": "9:17:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 288, "total_steps": 1626, "loss": 1.6602, "learning_rate": 2.9462865242731856e-05, "epoch": 0.5308755760368664, "percentage": 17.71, "elapsed_time": "2:00:00", "remaining_time": "9:17:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 289, "total_steps": 1626, "loss": 1.5909, "learning_rate": 2.9454289410306202e-05, "epoch": 0.5327188940092166, "percentage": 17.77, "elapsed_time": "2:00:25", "remaining_time": "9:17:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 290, "total_steps": 1626, "loss": 1.7039, "learning_rate": 2.944564692672667e-05, "epoch": 0.5345622119815668, "percentage": 17.84, "elapsed_time": "2:00:50", "remaining_time": "9:16:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 291, "total_steps": 1626, "loss": 1.6789, "learning_rate": 2.9436937831845217e-05, "epoch": 0.5364055299539171, "percentage": 17.9, "elapsed_time": "2:01:14", "remaining_time": "9:16:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 292, "total_steps": 1626, "loss": 1.6341, "learning_rate": 2.942816216582093e-05, "epoch": 0.5382488479262673, "percentage": 17.96, "elapsed_time": "2:01:39", "remaining_time": "9:15:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 293, "total_steps": 1626, "loss": 1.5926, "learning_rate": 2.9419319969119875e-05, "epoch": 0.5400921658986175, "percentage": 18.02, "elapsed_time": "2:02:04", "remaining_time": "9:15:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 294, "total_steps": 1626, "loss": 1.6507, "learning_rate": 2.9410411282514913e-05, "epoch": 0.5419354838709678, "percentage": 18.08, "elapsed_time": "2:02:29", "remaining_time": "9:14:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 295, "total_steps": 1626, "loss": 1.6504, "learning_rate": 2.940143614708549e-05, "epoch": 0.543778801843318, "percentage": 18.14, "elapsed_time": "2:02:54", "remaining_time": "9:14:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 296, "total_steps": 1626, "loss": 1.6762, "learning_rate": 2.939239460421746e-05, "epoch": 0.5456221198156682, "percentage": 18.2, "elapsed_time": "2:03:19", "remaining_time": "9:14:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 297, "total_steps": 1626, "loss": 1.6301, "learning_rate": 2.93832866956029e-05, "epoch": 0.5474654377880185, "percentage": 18.27, "elapsed_time": "2:03:44", "remaining_time": "9:13:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 298, "total_steps": 1626, "loss": 1.7101, "learning_rate": 2.9374112463239896e-05, "epoch": 0.5493087557603686, "percentage": 18.33, "elapsed_time": "2:04:09", "remaining_time": "9:13:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 299, "total_steps": 1626, "loss": 1.6871, "learning_rate": 2.9364871949432378e-05, "epoch": 0.5511520737327189, "percentage": 18.39, "elapsed_time": "2:04:34", "remaining_time": "9:12:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 300, "total_steps": 1626, "loss": 1.7028, "learning_rate": 2.9355565196789906e-05, "epoch": 0.5529953917050692, "percentage": 18.45, "elapsed_time": "2:04:59", "remaining_time": "9:12:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 301, "total_steps": 1626, "loss": 1.6229, "learning_rate": 2.9346192248227476e-05, "epoch": 0.5548387096774193, "percentage": 18.51, "elapsed_time": "2:05:24", "remaining_time": "9:12:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 302, "total_steps": 1626, "loss": 1.666, "learning_rate": 2.9336753146965327e-05, "epoch": 0.5566820276497696, "percentage": 18.57, "elapsed_time": "2:05:49", "remaining_time": "9:11:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 303, "total_steps": 1626, "loss": 1.5925, "learning_rate": 2.9327247936528742e-05, "epoch": 0.5585253456221199, "percentage": 18.63, "elapsed_time": "2:06:13", "remaining_time": "9:11:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 304, "total_steps": 1626, "loss": 1.6605, "learning_rate": 2.9317676660747837e-05, "epoch": 0.56036866359447, "percentage": 18.7, "elapsed_time": "2:06:38", "remaining_time": "9:10:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 305, "total_steps": 1626, "loss": 1.6371, "learning_rate": 2.9308039363757372e-05, "epoch": 0.5622119815668203, "percentage": 18.76, "elapsed_time": "2:07:03", "remaining_time": "9:10:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 306, "total_steps": 1626, "loss": 1.7176, "learning_rate": 2.9298336089996538e-05, "epoch": 0.5640552995391706, "percentage": 18.82, "elapsed_time": "2:07:28", "remaining_time": "9:09:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 307, "total_steps": 1626, "loss": 1.6378, "learning_rate": 2.9288566884208766e-05, "epoch": 0.5658986175115207, "percentage": 18.88, "elapsed_time": "2:07:53", "remaining_time": "9:09:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 308, "total_steps": 1626, "loss": 1.6313, "learning_rate": 2.9278731791441497e-05, "epoch": 0.567741935483871, "percentage": 18.94, "elapsed_time": "2:08:18", "remaining_time": "9:09:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 309, "total_steps": 1626, "loss": 1.6114, "learning_rate": 2.9268830857045997e-05, "epoch": 0.5695852534562212, "percentage": 19.0, "elapsed_time": "2:08:43", "remaining_time": "9:08:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 310, "total_steps": 1626, "loss": 1.6438, "learning_rate": 2.9258864126677132e-05, "epoch": 0.5714285714285714, "percentage": 19.07, "elapsed_time": "2:09:08", "remaining_time": "9:08:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 311, "total_steps": 1626, "loss": 1.6521, "learning_rate": 2.9248831646293174e-05, "epoch": 0.5732718894009217, "percentage": 19.13, "elapsed_time": "2:09:33", "remaining_time": "9:07:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 312, "total_steps": 1626, "loss": 1.6399, "learning_rate": 2.9238733462155564e-05, "epoch": 0.5751152073732719, "percentage": 19.19, "elapsed_time": "2:09:57", "remaining_time": "9:07:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 313, "total_steps": 1626, "loss": 1.6316, "learning_rate": 2.9228569620828735e-05, "epoch": 0.5769585253456221, "percentage": 19.25, "elapsed_time": "2:10:22", "remaining_time": "9:06:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 314, "total_steps": 1626, "loss": 1.5787, "learning_rate": 2.921834016917986e-05, "epoch": 0.5788018433179724, "percentage": 19.31, "elapsed_time": "2:10:47", "remaining_time": "9:06:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 315, "total_steps": 1626, "loss": 1.6223, "learning_rate": 2.920804515437865e-05, "epoch": 0.5806451612903226, "percentage": 19.37, "elapsed_time": "2:11:12", "remaining_time": "9:06:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 316, "total_steps": 1626, "loss": 1.6368, "learning_rate": 2.9197684623897157e-05, "epoch": 0.5824884792626728, "percentage": 19.43, "elapsed_time": "2:11:37", "remaining_time": "9:05:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 317, "total_steps": 1626, "loss": 1.6855, "learning_rate": 2.9187258625509518e-05, "epoch": 0.584331797235023, "percentage": 19.5, "elapsed_time": "2:12:02", "remaining_time": "9:05:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 318, "total_steps": 1626, "loss": 1.6448, "learning_rate": 2.917676720729177e-05, "epoch": 0.5861751152073733, "percentage": 19.56, "elapsed_time": "2:12:27", "remaining_time": "9:04:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 319, "total_steps": 1626, "loss": 1.6295, "learning_rate": 2.916621041762159e-05, "epoch": 0.5880184331797235, "percentage": 19.62, "elapsed_time": "2:12:52", "remaining_time": "9:04:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 320, "total_steps": 1626, "loss": 1.5738, "learning_rate": 2.9155588305178113e-05, "epoch": 0.5898617511520737, "percentage": 19.68, "elapsed_time": "2:13:17", "remaining_time": "9:04:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 321, "total_steps": 1626, "loss": 1.6247, "learning_rate": 2.9144900918941687e-05, "epoch": 0.591705069124424, "percentage": 19.74, "elapsed_time": "2:13:42", "remaining_time": "9:03:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 322, "total_steps": 1626, "loss": 1.7135, "learning_rate": 2.9134148308193637e-05, "epoch": 0.5935483870967742, "percentage": 19.8, "elapsed_time": "2:14:07", "remaining_time": "9:03:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 323, "total_steps": 1626, "loss": 1.6522, "learning_rate": 2.9123330522516053e-05, "epoch": 0.5953917050691244, "percentage": 19.86, "elapsed_time": "2:14:32", "remaining_time": "9:02:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 324, "total_steps": 1626, "loss": 1.6347, "learning_rate": 2.9112447611791563e-05, "epoch": 0.5972350230414747, "percentage": 19.93, "elapsed_time": "2:14:57", "remaining_time": "9:02:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 325, "total_steps": 1626, "loss": 1.6071, "learning_rate": 2.9101499626203102e-05, "epoch": 0.5990783410138248, "percentage": 19.99, "elapsed_time": "2:15:21", "remaining_time": "9:01:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 326, "total_steps": 1626, "loss": 1.6191, "learning_rate": 2.9090486616233654e-05, "epoch": 0.6009216589861751, "percentage": 20.05, "elapsed_time": "2:15:47", "remaining_time": "9:01:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 327, "total_steps": 1626, "loss": 1.6427, "learning_rate": 2.907940863266607e-05, "epoch": 0.6027649769585254, "percentage": 20.11, "elapsed_time": "2:16:12", "remaining_time": "9:01:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 328, "total_steps": 1626, "loss": 1.5825, "learning_rate": 2.906826572658278e-05, "epoch": 0.6046082949308755, "percentage": 20.17, "elapsed_time": "2:16:37", "remaining_time": "9:00:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 329, "total_steps": 1626, "loss": 1.6189, "learning_rate": 2.9057057949365602e-05, "epoch": 0.6064516129032258, "percentage": 20.23, "elapsed_time": "2:17:02", "remaining_time": "9:00:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 330, "total_steps": 1626, "loss": 1.6485, "learning_rate": 2.904578535269547e-05, "epoch": 0.6082949308755761, "percentage": 20.3, "elapsed_time": "2:17:27", "remaining_time": "8:59:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 331, "total_steps": 1626, "loss": 1.6874, "learning_rate": 2.9034447988552227e-05, "epoch": 0.6101382488479262, "percentage": 20.36, "elapsed_time": "2:17:52", "remaining_time": "8:59:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 332, "total_steps": 1626, "loss": 1.6805, "learning_rate": 2.902304590921435e-05, "epoch": 0.6119815668202765, "percentage": 20.42, "elapsed_time": "2:18:17", "remaining_time": "8:58:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 333, "total_steps": 1626, "loss": 1.6611, "learning_rate": 2.9011579167258756e-05, "epoch": 0.6138248847926268, "percentage": 20.48, "elapsed_time": "2:18:41", "remaining_time": "8:58:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 334, "total_steps": 1626, "loss": 1.5686, "learning_rate": 2.90000478155605e-05, "epoch": 0.6156682027649769, "percentage": 20.54, "elapsed_time": "2:19:06", "remaining_time": "8:58:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 335, "total_steps": 1626, "loss": 1.6636, "learning_rate": 2.8988451907292594e-05, "epoch": 0.6175115207373272, "percentage": 20.6, "elapsed_time": "2:19:31", "remaining_time": "8:57:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 336, "total_steps": 1626, "loss": 1.7131, "learning_rate": 2.8976791495925704e-05, "epoch": 0.6193548387096774, "percentage": 20.66, "elapsed_time": "2:19:56", "remaining_time": "8:57:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 337, "total_steps": 1626, "loss": 1.6664, "learning_rate": 2.896506663522795e-05, "epoch": 0.6211981566820276, "percentage": 20.73, "elapsed_time": "2:20:21", "remaining_time": "8:56:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 338, "total_steps": 1626, "loss": 1.6567, "learning_rate": 2.8953277379264633e-05, "epoch": 0.6230414746543779, "percentage": 20.79, "elapsed_time": "2:20:46", "remaining_time": "8:56:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 339, "total_steps": 1626, "loss": 1.6504, "learning_rate": 2.8941423782397987e-05, "epoch": 0.6248847926267281, "percentage": 20.85, "elapsed_time": "2:21:11", "remaining_time": "8:56:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 340, "total_steps": 1626, "loss": 1.6381, "learning_rate": 2.892950589928694e-05, "epoch": 0.6267281105990783, "percentage": 20.91, "elapsed_time": "2:21:37", "remaining_time": "8:55:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 341, "total_steps": 1626, "loss": 1.6845, "learning_rate": 2.8917523784886846e-05, "epoch": 0.6285714285714286, "percentage": 20.97, "elapsed_time": "2:22:02", "remaining_time": "8:55:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 342, "total_steps": 1626, "loss": 1.6751, "learning_rate": 2.890547749444925e-05, "epoch": 0.6304147465437788, "percentage": 21.03, "elapsed_time": "2:22:27", "remaining_time": "8:54:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 343, "total_steps": 1626, "loss": 1.6247, "learning_rate": 2.8893367083521616e-05, "epoch": 0.632258064516129, "percentage": 21.09, "elapsed_time": "2:22:51", "remaining_time": "8:54:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 344, "total_steps": 1626, "loss": 1.6086, "learning_rate": 2.888119260794708e-05, "epoch": 0.6341013824884792, "percentage": 21.16, "elapsed_time": "2:23:16", "remaining_time": "8:53:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 345, "total_steps": 1626, "loss": 1.653, "learning_rate": 2.8868954123864194e-05, "epoch": 0.6359447004608295, "percentage": 21.22, "elapsed_time": "2:23:41", "remaining_time": "8:53:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 346, "total_steps": 1626, "loss": 1.6432, "learning_rate": 2.885665168770666e-05, "epoch": 0.6377880184331797, "percentage": 21.28, "elapsed_time": "2:24:06", "remaining_time": "8:53:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 347, "total_steps": 1626, "loss": 1.6346, "learning_rate": 2.8844285356203074e-05, "epoch": 0.6396313364055299, "percentage": 21.34, "elapsed_time": "2:24:31", "remaining_time": "8:52:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 348, "total_steps": 1626, "loss": 1.6907, "learning_rate": 2.8831855186376672e-05, "epoch": 0.6414746543778802, "percentage": 21.4, "elapsed_time": "2:24:56", "remaining_time": "8:52:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 349, "total_steps": 1626, "loss": 1.699, "learning_rate": 2.8819361235545047e-05, "epoch": 0.6433179723502304, "percentage": 21.46, "elapsed_time": "2:25:21", "remaining_time": "8:51:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 350, "total_steps": 1626, "loss": 1.6464, "learning_rate": 2.8806803561319903e-05, "epoch": 0.6451612903225806, "percentage": 21.53, "elapsed_time": "2:25:46", "remaining_time": "8:51:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 351, "total_steps": 1626, "loss": 1.5384, "learning_rate": 2.8794182221606784e-05, "epoch": 0.6470046082949309, "percentage": 21.59, "elapsed_time": "2:26:11", "remaining_time": "8:51:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 352, "total_steps": 1626, "loss": 1.571, "learning_rate": 2.878149727460481e-05, "epoch": 0.6488479262672812, "percentage": 21.65, "elapsed_time": "2:26:36", "remaining_time": "8:50:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 353, "total_steps": 1626, "loss": 1.5831, "learning_rate": 2.876874877880639e-05, "epoch": 0.6506912442396313, "percentage": 21.71, "elapsed_time": "2:27:01", "remaining_time": "8:50:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 354, "total_steps": 1626, "loss": 1.6923, "learning_rate": 2.8755936792996987e-05, "epoch": 0.6525345622119816, "percentage": 21.77, "elapsed_time": "2:27:25", "remaining_time": "8:49:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 355, "total_steps": 1626, "loss": 1.6356, "learning_rate": 2.8743061376254813e-05, "epoch": 0.6543778801843319, "percentage": 21.83, "elapsed_time": "2:27:50", "remaining_time": "8:49:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 356, "total_steps": 1626, "loss": 1.6479, "learning_rate": 2.873012258795057e-05, "epoch": 0.656221198156682, "percentage": 21.89, "elapsed_time": "2:28:15", "remaining_time": "8:48:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 357, "total_steps": 1626, "loss": 1.629, "learning_rate": 2.8717120487747193e-05, "epoch": 0.6580645161290323, "percentage": 21.96, "elapsed_time": "2:28:40", "remaining_time": "8:48:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 358, "total_steps": 1626, "loss": 1.5984, "learning_rate": 2.870405513559954e-05, "epoch": 0.6599078341013825, "percentage": 22.02, "elapsed_time": "2:29:05", "remaining_time": "8:48:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 359, "total_steps": 1626, "loss": 1.5927, "learning_rate": 2.8690926591754142e-05, "epoch": 0.6617511520737327, "percentage": 22.08, "elapsed_time": "2:29:30", "remaining_time": "8:47:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 360, "total_steps": 1626, "loss": 1.6457, "learning_rate": 2.8677734916748927e-05, "epoch": 0.663594470046083, "percentage": 22.14, "elapsed_time": "2:29:55", "remaining_time": "8:47:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 361, "total_steps": 1626, "loss": 1.6161, "learning_rate": 2.866448017141291e-05, "epoch": 0.6654377880184332, "percentage": 22.2, "elapsed_time": "2:30:20", "remaining_time": "8:46:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 362, "total_steps": 1626, "loss": 1.6897, "learning_rate": 2.865116241686595e-05, "epoch": 0.6672811059907834, "percentage": 22.26, "elapsed_time": "2:30:45", "remaining_time": "8:46:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 363, "total_steps": 1626, "loss": 1.6293, "learning_rate": 2.863778171451845e-05, "epoch": 0.6691244239631337, "percentage": 22.32, "elapsed_time": "2:31:11", "remaining_time": "8:46:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 364, "total_steps": 1626, "loss": 1.6143, "learning_rate": 2.8624338126071073e-05, "epoch": 0.6709677419354839, "percentage": 22.39, "elapsed_time": "2:31:36", "remaining_time": "8:45:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 365, "total_steps": 1626, "loss": 1.5878, "learning_rate": 2.861083171351446e-05, "epoch": 0.6728110599078341, "percentage": 22.45, "elapsed_time": "2:32:00", "remaining_time": "8:45:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 366, "total_steps": 1626, "loss": 1.6939, "learning_rate": 2.8597262539128947e-05, "epoch": 0.6746543778801843, "percentage": 22.51, "elapsed_time": "2:32:25", "remaining_time": "8:44:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 367, "total_steps": 1626, "loss": 1.66, "learning_rate": 2.858363066548427e-05, "epoch": 0.6764976958525346, "percentage": 22.57, "elapsed_time": "2:32:50", "remaining_time": "8:44:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 368, "total_steps": 1626, "loss": 1.6183, "learning_rate": 2.856993615543929e-05, "epoch": 0.6783410138248848, "percentage": 22.63, "elapsed_time": "2:33:15", "remaining_time": "8:43:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 369, "total_steps": 1626, "loss": 1.6187, "learning_rate": 2.8556179072141693e-05, "epoch": 0.680184331797235, "percentage": 22.69, "elapsed_time": "2:33:40", "remaining_time": "8:43:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 370, "total_steps": 1626, "loss": 1.5613, "learning_rate": 2.8542359479027693e-05, "epoch": 0.6820276497695853, "percentage": 22.76, "elapsed_time": "2:34:05", "remaining_time": "8:43:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 371, "total_steps": 1626, "loss": 1.6317, "learning_rate": 2.8528477439821753e-05, "epoch": 0.6838709677419355, "percentage": 22.82, "elapsed_time": "2:34:30", "remaining_time": "8:42:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 372, "total_steps": 1626, "loss": 1.6531, "learning_rate": 2.8514533018536286e-05, "epoch": 0.6857142857142857, "percentage": 22.88, "elapsed_time": "2:34:55", "remaining_time": "8:42:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 373, "total_steps": 1626, "loss": 1.6045, "learning_rate": 2.8500526279471362e-05, "epoch": 0.687557603686636, "percentage": 22.94, "elapsed_time": "2:35:20", "remaining_time": "8:41:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 374, "total_steps": 1626, "loss": 1.6746, "learning_rate": 2.8486457287214403e-05, "epoch": 0.6894009216589861, "percentage": 23.0, "elapsed_time": "2:35:45", "remaining_time": "8:41:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 375, "total_steps": 1626, "loss": 1.6882, "learning_rate": 2.8472326106639896e-05, "epoch": 0.6912442396313364, "percentage": 23.06, "elapsed_time": "2:36:10", "remaining_time": "8:40:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 376, "total_steps": 1626, "loss": 1.5905, "learning_rate": 2.8458132802909075e-05, "epoch": 0.6930875576036867, "percentage": 23.12, "elapsed_time": "2:36:35", "remaining_time": "8:40:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 377, "total_steps": 1626, "loss": 1.6351, "learning_rate": 2.8443877441469653e-05, "epoch": 0.6949308755760368, "percentage": 23.19, "elapsed_time": "2:37:00", "remaining_time": "8:40:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 378, "total_steps": 1626, "loss": 1.6291, "learning_rate": 2.8429560088055502e-05, "epoch": 0.6967741935483871, "percentage": 23.25, "elapsed_time": "2:37:24", "remaining_time": "8:39:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 379, "total_steps": 1626, "loss": 1.6113, "learning_rate": 2.8415180808686326e-05, "epoch": 0.6986175115207374, "percentage": 23.31, "elapsed_time": "2:37:49", "remaining_time": "8:39:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 380, "total_steps": 1626, "loss": 1.6397, "learning_rate": 2.84007396696674e-05, "epoch": 0.7004608294930875, "percentage": 23.37, "elapsed_time": "2:38:14", "remaining_time": "8:38:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 381, "total_steps": 1626, "loss": 1.6255, "learning_rate": 2.8386236737589244e-05, "epoch": 0.7023041474654378, "percentage": 23.43, "elapsed_time": "2:38:39", "remaining_time": "8:38:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 382, "total_steps": 1626, "loss": 1.5909, "learning_rate": 2.8371672079327304e-05, "epoch": 0.7041474654377881, "percentage": 23.49, "elapsed_time": "2:39:04", "remaining_time": "8:38:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 383, "total_steps": 1626, "loss": 1.668, "learning_rate": 2.835704576204167e-05, "epoch": 0.7059907834101382, "percentage": 23.55, "elapsed_time": "2:39:29", "remaining_time": "8:37:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 384, "total_steps": 1626, "loss": 1.655, "learning_rate": 2.8342357853176742e-05, "epoch": 0.7078341013824885, "percentage": 23.62, "elapsed_time": "2:39:54", "remaining_time": "8:37:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 385, "total_steps": 1626, "loss": 1.6606, "learning_rate": 2.8327608420460933e-05, "epoch": 0.7096774193548387, "percentage": 23.68, "elapsed_time": "2:40:19", "remaining_time": "8:36:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 386, "total_steps": 1626, "loss": 1.6487, "learning_rate": 2.8312797531906346e-05, "epoch": 0.7115207373271889, "percentage": 23.74, "elapsed_time": "2:40:44", "remaining_time": "8:36:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 387, "total_steps": 1626, "loss": 1.5784, "learning_rate": 2.8297925255808484e-05, "epoch": 0.7133640552995392, "percentage": 23.8, "elapsed_time": "2:41:09", "remaining_time": "8:35:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 388, "total_steps": 1626, "loss": 1.5551, "learning_rate": 2.82829916607459e-05, "epoch": 0.7152073732718894, "percentage": 23.86, "elapsed_time": "2:41:34", "remaining_time": "8:35:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 389, "total_steps": 1626, "loss": 1.6242, "learning_rate": 2.826799681557991e-05, "epoch": 0.7170506912442396, "percentage": 23.92, "elapsed_time": "2:41:59", "remaining_time": "8:35:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 390, "total_steps": 1626, "loss": 1.6404, "learning_rate": 2.8252940789454268e-05, "epoch": 0.7188940092165899, "percentage": 23.99, "elapsed_time": "2:42:25", "remaining_time": "8:34:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 391, "total_steps": 1626, "loss": 1.7135, "learning_rate": 2.823782365179482e-05, "epoch": 0.7207373271889401, "percentage": 24.05, "elapsed_time": "2:42:50", "remaining_time": "8:34:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 392, "total_steps": 1626, "loss": 1.6472, "learning_rate": 2.822264547230924e-05, "epoch": 0.7225806451612903, "percentage": 24.11, "elapsed_time": "2:43:15", "remaining_time": "8:33:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 393, "total_steps": 1626, "loss": 1.5996, "learning_rate": 2.820740632098665e-05, "epoch": 0.7244239631336405, "percentage": 24.17, "elapsed_time": "2:43:40", "remaining_time": "8:33:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 394, "total_steps": 1626, "loss": 1.6192, "learning_rate": 2.8192106268097336e-05, "epoch": 0.7262672811059908, "percentage": 24.23, "elapsed_time": "2:44:04", "remaining_time": "8:33:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 395, "total_steps": 1626, "loss": 1.6183, "learning_rate": 2.8176745384192417e-05, "epoch": 0.728110599078341, "percentage": 24.29, "elapsed_time": "2:44:29", "remaining_time": "8:32:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 396, "total_steps": 1626, "loss": 1.6092, "learning_rate": 2.8161323740103495e-05, "epoch": 0.7299539170506912, "percentage": 24.35, "elapsed_time": "2:44:54", "remaining_time": "8:32:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 397, "total_steps": 1626, "loss": 1.6938, "learning_rate": 2.814584140694237e-05, "epoch": 0.7317972350230415, "percentage": 24.42, "elapsed_time": "2:45:19", "remaining_time": "8:31:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 398, "total_steps": 1626, "loss": 1.6665, "learning_rate": 2.8130298456100667e-05, "epoch": 0.7336405529953917, "percentage": 24.48, "elapsed_time": "2:45:44", "remaining_time": "8:31:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 399, "total_steps": 1626, "loss": 1.6464, "learning_rate": 2.811469495924955e-05, "epoch": 0.7354838709677419, "percentage": 24.54, "elapsed_time": "2:46:09", "remaining_time": "8:30:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 400, "total_steps": 1626, "loss": 1.5455, "learning_rate": 2.8099030988339353e-05, "epoch": 0.7373271889400922, "percentage": 24.6, "elapsed_time": "2:46:34", "remaining_time": "8:30:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 401, "total_steps": 1626, "loss": 1.6348, "learning_rate": 2.8083306615599283e-05, "epoch": 0.7391705069124423, "percentage": 24.66, "elapsed_time": "2:47:09", "remaining_time": "8:30:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 402, "total_steps": 1626, "loss": 1.6365, "learning_rate": 2.8067521913537047e-05, "epoch": 0.7410138248847926, "percentage": 24.72, "elapsed_time": "2:47:33", "remaining_time": "8:30:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 403, "total_steps": 1626, "loss": 1.6348, "learning_rate": 2.8051676954938574e-05, "epoch": 0.7428571428571429, "percentage": 24.78, "elapsed_time": "2:47:58", "remaining_time": "8:29:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 404, "total_steps": 1626, "loss": 1.6384, "learning_rate": 2.8035771812867613e-05, "epoch": 0.744700460829493, "percentage": 24.85, "elapsed_time": "2:48:23", "remaining_time": "8:29:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 405, "total_steps": 1626, "loss": 1.6978, "learning_rate": 2.801980656066545e-05, "epoch": 0.7465437788018433, "percentage": 24.91, "elapsed_time": "2:48:48", "remaining_time": "8:28:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 406, "total_steps": 1626, "loss": 1.6924, "learning_rate": 2.8003781271950535e-05, "epoch": 0.7483870967741936, "percentage": 24.97, "elapsed_time": "2:49:13", "remaining_time": "8:28:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 407, "total_steps": 1626, "loss": 1.5734, "learning_rate": 2.7987696020618163e-05, "epoch": 0.7502304147465437, "percentage": 25.03, "elapsed_time": "2:49:38", "remaining_time": "8:28:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 408, "total_steps": 1626, "loss": 1.6261, "learning_rate": 2.7971550880840138e-05, "epoch": 0.752073732718894, "percentage": 25.09, "elapsed_time": "2:50:03", "remaining_time": "8:27:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 409, "total_steps": 1626, "loss": 1.6264, "learning_rate": 2.79553459270644e-05, "epoch": 0.7539170506912443, "percentage": 25.15, "elapsed_time": "2:50:28", "remaining_time": "8:27:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 410, "total_steps": 1626, "loss": 1.6432, "learning_rate": 2.7939081234014708e-05, "epoch": 0.7557603686635944, "percentage": 25.22, "elapsed_time": "2:50:53", "remaining_time": "8:26:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 411, "total_steps": 1626, "loss": 1.6903, "learning_rate": 2.7922756876690298e-05, "epoch": 0.7576036866359447, "percentage": 25.28, "elapsed_time": "2:51:18", "remaining_time": "8:26:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 412, "total_steps": 1626, "loss": 1.6626, "learning_rate": 2.790637293036552e-05, "epoch": 0.759447004608295, "percentage": 25.34, "elapsed_time": "2:51:43", "remaining_time": "8:25:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 413, "total_steps": 1626, "loss": 1.6489, "learning_rate": 2.7889929470589494e-05, "epoch": 0.7612903225806451, "percentage": 25.4, "elapsed_time": "2:52:08", "remaining_time": "8:25:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 414, "total_steps": 1626, "loss": 1.664, "learning_rate": 2.7873426573185777e-05, "epoch": 0.7631336405529954, "percentage": 25.46, "elapsed_time": "2:52:33", "remaining_time": "8:25:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 415, "total_steps": 1626, "loss": 1.6475, "learning_rate": 2.7856864314251994e-05, "epoch": 0.7649769585253456, "percentage": 25.52, "elapsed_time": "2:52:58", "remaining_time": "8:24:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 416, "total_steps": 1626, "loss": 1.6332, "learning_rate": 2.78402427701595e-05, "epoch": 0.7668202764976959, "percentage": 25.58, "elapsed_time": "2:53:23", "remaining_time": "8:24:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 417, "total_steps": 1626, "loss": 1.6633, "learning_rate": 2.782356201755303e-05, "epoch": 0.7686635944700461, "percentage": 25.65, "elapsed_time": "2:53:48", "remaining_time": "8:23:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 418, "total_steps": 1626, "loss": 1.6281, "learning_rate": 2.780682213335033e-05, "epoch": 0.7705069124423963, "percentage": 25.71, "elapsed_time": "2:54:12", "remaining_time": "8:23:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 419, "total_steps": 1626, "loss": 1.6733, "learning_rate": 2.7790023194741812e-05, "epoch": 0.7723502304147466, "percentage": 25.77, "elapsed_time": "2:54:37", "remaining_time": "8:23:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 420, "total_steps": 1626, "loss": 1.6269, "learning_rate": 2.7773165279190206e-05, "epoch": 0.7741935483870968, "percentage": 25.83, "elapsed_time": "2:55:03", "remaining_time": "8:22:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 421, "total_steps": 1626, "loss": 1.6292, "learning_rate": 2.7756248464430186e-05, "epoch": 0.776036866359447, "percentage": 25.89, "elapsed_time": "2:55:28", "remaining_time": "8:22:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 422, "total_steps": 1626, "loss": 1.6159, "learning_rate": 2.7739272828468022e-05, "epoch": 0.7778801843317973, "percentage": 25.95, "elapsed_time": "2:55:53", "remaining_time": "8:21:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 423, "total_steps": 1626, "loss": 1.6183, "learning_rate": 2.7722238449581227e-05, "epoch": 0.7797235023041474, "percentage": 26.01, "elapsed_time": "2:56:18", "remaining_time": "8:21:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 424, "total_steps": 1626, "loss": 1.7191, "learning_rate": 2.7705145406318167e-05, "epoch": 0.7815668202764977, "percentage": 26.08, "elapsed_time": "2:56:42", "remaining_time": "8:20:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 425, "total_steps": 1626, "loss": 1.5733, "learning_rate": 2.7687993777497747e-05, "epoch": 0.783410138248848, "percentage": 26.14, "elapsed_time": "2:57:07", "remaining_time": "8:20:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 426, "total_steps": 1626, "loss": 1.6225, "learning_rate": 2.7670783642208996e-05, "epoch": 0.7852534562211981, "percentage": 26.2, "elapsed_time": "2:57:32", "remaining_time": "8:20:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 427, "total_steps": 1626, "loss": 1.6964, "learning_rate": 2.7653515079810744e-05, "epoch": 0.7870967741935484, "percentage": 26.26, "elapsed_time": "2:57:57", "remaining_time": "8:19:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 428, "total_steps": 1626, "loss": 1.6728, "learning_rate": 2.7636188169931217e-05, "epoch": 0.7889400921658987, "percentage": 26.32, "elapsed_time": "2:58:22", "remaining_time": "8:19:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 429, "total_steps": 1626, "loss": 1.6971, "learning_rate": 2.7618802992467718e-05, "epoch": 0.7907834101382488, "percentage": 26.38, "elapsed_time": "2:58:47", "remaining_time": "8:18:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 430, "total_steps": 1626, "loss": 1.6763, "learning_rate": 2.760135962758621e-05, "epoch": 0.7926267281105991, "percentage": 26.45, "elapsed_time": "2:59:12", "remaining_time": "8:18:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 431, "total_steps": 1626, "loss": 1.6291, "learning_rate": 2.7583858155720977e-05, "epoch": 0.7944700460829494, "percentage": 26.51, "elapsed_time": "2:59:37", "remaining_time": "8:18:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 432, "total_steps": 1626, "loss": 1.6718, "learning_rate": 2.756629865757424e-05, "epoch": 0.7963133640552995, "percentage": 26.57, "elapsed_time": "3:00:02", "remaining_time": "8:17:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 433, "total_steps": 1626, "loss": 1.5723, "learning_rate": 2.7548681214115798e-05, "epoch": 0.7981566820276498, "percentage": 26.63, "elapsed_time": "3:00:27", "remaining_time": "8:17:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 434, "total_steps": 1626, "loss": 1.6833, "learning_rate": 2.7531005906582628e-05, "epoch": 0.8, "percentage": 26.69, "elapsed_time": "3:00:52", "remaining_time": "8:16:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 435, "total_steps": 1626, "loss": 1.6166, "learning_rate": 2.7513272816478554e-05, "epoch": 0.8018433179723502, "percentage": 26.75, "elapsed_time": "3:01:17", "remaining_time": "8:16:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 436, "total_steps": 1626, "loss": 1.6716, "learning_rate": 2.7495482025573817e-05, "epoch": 0.8036866359447005, "percentage": 26.81, "elapsed_time": "3:01:42", "remaining_time": "8:15:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 437, "total_steps": 1626, "loss": 1.6573, "learning_rate": 2.7477633615904744e-05, "epoch": 0.8055299539170507, "percentage": 26.88, "elapsed_time": "3:02:06", "remaining_time": "8:15:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 438, "total_steps": 1626, "loss": 1.6609, "learning_rate": 2.7459727669773344e-05, "epoch": 0.8073732718894009, "percentage": 26.94, "elapsed_time": "3:02:31", "remaining_time": "8:15:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 439, "total_steps": 1626, "loss": 1.6401, "learning_rate": 2.7441764269746946e-05, "epoch": 0.8092165898617512, "percentage": 27.0, "elapsed_time": "3:02:56", "remaining_time": "8:14:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 440, "total_steps": 1626, "loss": 1.6313, "learning_rate": 2.7423743498657794e-05, "epoch": 0.8110599078341014, "percentage": 27.06, "elapsed_time": "3:03:21", "remaining_time": "8:14:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 441, "total_steps": 1626, "loss": 1.729, "learning_rate": 2.7405665439602695e-05, "epoch": 0.8129032258064516, "percentage": 27.12, "elapsed_time": "3:03:46", "remaining_time": "8:13:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 442, "total_steps": 1626, "loss": 1.6436, "learning_rate": 2.7387530175942604e-05, "epoch": 0.8147465437788018, "percentage": 27.18, "elapsed_time": "3:04:11", "remaining_time": "8:13:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 443, "total_steps": 1626, "loss": 1.6492, "learning_rate": 2.7369337791302272e-05, "epoch": 0.8165898617511521, "percentage": 27.24, "elapsed_time": "3:04:36", "remaining_time": "8:12:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 444, "total_steps": 1626, "loss": 1.6683, "learning_rate": 2.7351088369569833e-05, "epoch": 0.8184331797235023, "percentage": 27.31, "elapsed_time": "3:05:01", "remaining_time": "8:12:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 445, "total_steps": 1626, "loss": 1.6595, "learning_rate": 2.7332781994896438e-05, "epoch": 0.8202764976958525, "percentage": 27.37, "elapsed_time": "3:05:26", "remaining_time": "8:12:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 446, "total_steps": 1626, "loss": 1.6208, "learning_rate": 2.7314418751695845e-05, "epoch": 0.8221198156682028, "percentage": 27.43, "elapsed_time": "3:05:51", "remaining_time": "8:11:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 447, "total_steps": 1626, "loss": 1.6085, "learning_rate": 2.7295998724644058e-05, "epoch": 0.823963133640553, "percentage": 27.49, "elapsed_time": "3:06:16", "remaining_time": "8:11:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 448, "total_steps": 1626, "loss": 1.6348, "learning_rate": 2.7277521998678904e-05, "epoch": 0.8258064516129032, "percentage": 27.55, "elapsed_time": "3:06:41", "remaining_time": "8:10:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 449, "total_steps": 1626, "loss": 1.6787, "learning_rate": 2.725898865899967e-05, "epoch": 0.8276497695852535, "percentage": 27.61, "elapsed_time": "3:07:06", "remaining_time": "8:10:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 450, "total_steps": 1626, "loss": 1.6271, "learning_rate": 2.72403987910667e-05, "epoch": 0.8294930875576036, "percentage": 27.68, "elapsed_time": "3:07:31", "remaining_time": "8:10:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 451, "total_steps": 1626, "loss": 1.6035, "learning_rate": 2.722175248060099e-05, "epoch": 0.8313364055299539, "percentage": 27.74, "elapsed_time": "3:07:56", "remaining_time": "8:09:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 452, "total_steps": 1626, "loss": 1.5928, "learning_rate": 2.7203049813583803e-05, "epoch": 0.8331797235023042, "percentage": 27.8, "elapsed_time": "3:08:21", "remaining_time": "8:09:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 453, "total_steps": 1626, "loss": 1.6073, "learning_rate": 2.7184290876256278e-05, "epoch": 0.8350230414746543, "percentage": 27.86, "elapsed_time": "3:08:46", "remaining_time": "8:08:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 454, "total_steps": 1626, "loss": 1.6385, "learning_rate": 2.716547575511903e-05, "epoch": 0.8368663594470046, "percentage": 27.92, "elapsed_time": "3:09:11", "remaining_time": "8:08:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 455, "total_steps": 1626, "loss": 1.6921, "learning_rate": 2.714660453693173e-05, "epoch": 0.8387096774193549, "percentage": 27.98, "elapsed_time": "3:09:36", "remaining_time": "8:07:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 456, "total_steps": 1626, "loss": 1.6651, "learning_rate": 2.7127677308712733e-05, "epoch": 0.840552995391705, "percentage": 28.04, "elapsed_time": "3:10:01", "remaining_time": "8:07:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 457, "total_steps": 1626, "loss": 1.5813, "learning_rate": 2.710869415773867e-05, "epoch": 0.8423963133640553, "percentage": 28.11, "elapsed_time": "3:10:26", "remaining_time": "8:07:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 458, "total_steps": 1626, "loss": 1.6971, "learning_rate": 2.7089655171544026e-05, "epoch": 0.8442396313364056, "percentage": 28.17, "elapsed_time": "3:10:51", "remaining_time": "8:06:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 459, "total_steps": 1626, "loss": 1.6268, "learning_rate": 2.707056043792077e-05, "epoch": 0.8460829493087557, "percentage": 28.23, "elapsed_time": "3:11:16", "remaining_time": "8:06:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 460, "total_steps": 1626, "loss": 1.6883, "learning_rate": 2.705141004491792e-05, "epoch": 0.847926267281106, "percentage": 28.29, "elapsed_time": "3:11:40", "remaining_time": "8:05:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 461, "total_steps": 1626, "loss": 1.6409, "learning_rate": 2.703220408084115e-05, "epoch": 0.8497695852534562, "percentage": 28.35, "elapsed_time": "3:12:05", "remaining_time": "8:05:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 462, "total_steps": 1626, "loss": 1.5454, "learning_rate": 2.7012942634252384e-05, "epoch": 0.8516129032258064, "percentage": 28.41, "elapsed_time": "3:12:30", "remaining_time": "8:05:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 463, "total_steps": 1626, "loss": 1.6845, "learning_rate": 2.6993625793969383e-05, "epoch": 0.8534562211981567, "percentage": 28.47, "elapsed_time": "3:12:55", "remaining_time": "8:04:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 464, "total_steps": 1626, "loss": 1.6339, "learning_rate": 2.697425364906534e-05, "epoch": 0.8552995391705069, "percentage": 28.54, "elapsed_time": "3:13:20", "remaining_time": "8:04:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 465, "total_steps": 1626, "loss": 1.6226, "learning_rate": 2.6954826288868463e-05, "epoch": 0.8571428571428571, "percentage": 28.6, "elapsed_time": "3:13:45", "remaining_time": "8:03:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 466, "total_steps": 1626, "loss": 1.5902, "learning_rate": 2.693534380296158e-05, "epoch": 0.8589861751152074, "percentage": 28.66, "elapsed_time": "3:14:10", "remaining_time": "8:03:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 467, "total_steps": 1626, "loss": 1.6444, "learning_rate": 2.6915806281181688e-05, "epoch": 0.8608294930875576, "percentage": 28.72, "elapsed_time": "3:14:35", "remaining_time": "8:02:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 468, "total_steps": 1626, "loss": 1.631, "learning_rate": 2.6896213813619592e-05, "epoch": 0.8626728110599078, "percentage": 28.78, "elapsed_time": "3:15:00", "remaining_time": "8:02:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 469, "total_steps": 1626, "loss": 1.5984, "learning_rate": 2.6876566490619437e-05, "epoch": 0.864516129032258, "percentage": 28.84, "elapsed_time": "3:15:25", "remaining_time": "8:02:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 470, "total_steps": 1626, "loss": 1.6318, "learning_rate": 2.685686440277833e-05, "epoch": 0.8663594470046083, "percentage": 28.91, "elapsed_time": "3:15:50", "remaining_time": "8:01:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 471, "total_steps": 1626, "loss": 1.6931, "learning_rate": 2.6837107640945904e-05, "epoch": 0.8682027649769585, "percentage": 28.97, "elapsed_time": "3:16:14", "remaining_time": "8:01:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 472, "total_steps": 1626, "loss": 1.5986, "learning_rate": 2.681729629622391e-05, "epoch": 0.8700460829493087, "percentage": 29.03, "elapsed_time": "3:16:39", "remaining_time": "8:00:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 473, "total_steps": 1626, "loss": 1.6511, "learning_rate": 2.6797430459965766e-05, "epoch": 0.871889400921659, "percentage": 29.09, "elapsed_time": "3:17:04", "remaining_time": "8:00:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 474, "total_steps": 1626, "loss": 1.6248, "learning_rate": 2.6777510223776187e-05, "epoch": 0.8737327188940092, "percentage": 29.15, "elapsed_time": "3:17:30", "remaining_time": "8:00:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 475, "total_steps": 1626, "loss": 1.6032, "learning_rate": 2.6757535679510727e-05, "epoch": 0.8755760368663594, "percentage": 29.21, "elapsed_time": "3:17:55", "remaining_time": "7:59:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 476, "total_steps": 1626, "loss": 1.6658, "learning_rate": 2.6737506919275363e-05, "epoch": 0.8774193548387097, "percentage": 29.27, "elapsed_time": "3:18:20", "remaining_time": "7:59:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 477, "total_steps": 1626, "loss": 1.6324, "learning_rate": 2.6717424035426054e-05, "epoch": 0.8792626728110599, "percentage": 29.34, "elapsed_time": "3:18:44", "remaining_time": "7:58:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 478, "total_steps": 1626, "loss": 1.6608, "learning_rate": 2.6697287120568364e-05, "epoch": 0.8811059907834101, "percentage": 29.4, "elapsed_time": "3:19:09", "remaining_time": "7:58:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 479, "total_steps": 1626, "loss": 1.5962, "learning_rate": 2.6677096267556984e-05, "epoch": 0.8829493087557604, "percentage": 29.46, "elapsed_time": "3:19:34", "remaining_time": "7:57:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 480, "total_steps": 1626, "loss": 1.6496, "learning_rate": 2.6656851569495316e-05, "epoch": 0.8847926267281107, "percentage": 29.52, "elapsed_time": "3:19:59", "remaining_time": "7:57:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 481, "total_steps": 1626, "loss": 1.6164, "learning_rate": 2.6636553119735066e-05, "epoch": 0.8866359447004608, "percentage": 29.58, "elapsed_time": "3:20:24", "remaining_time": "7:57:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 482, "total_steps": 1626, "loss": 1.6317, "learning_rate": 2.6616201011875792e-05, "epoch": 0.8884792626728111, "percentage": 29.64, "elapsed_time": "3:20:49", "remaining_time": "7:56:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 483, "total_steps": 1626, "loss": 1.6076, "learning_rate": 2.6595795339764478e-05, "epoch": 0.8903225806451613, "percentage": 29.7, "elapsed_time": "3:21:14", "remaining_time": "7:56:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 484, "total_steps": 1626, "loss": 1.6106, "learning_rate": 2.6575336197495098e-05, "epoch": 0.8921658986175115, "percentage": 29.77, "elapsed_time": "3:21:39", "remaining_time": "7:55:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 485, "total_steps": 1626, "loss": 1.6597, "learning_rate": 2.6554823679408195e-05, "epoch": 0.8940092165898618, "percentage": 29.83, "elapsed_time": "3:22:04", "remaining_time": "7:55:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 486, "total_steps": 1626, "loss": 1.5526, "learning_rate": 2.653425788009043e-05, "epoch": 0.895852534562212, "percentage": 29.89, "elapsed_time": "3:22:28", "remaining_time": "7:54:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 487, "total_steps": 1626, "loss": 1.687, "learning_rate": 2.6513638894374158e-05, "epoch": 0.8976958525345622, "percentage": 29.95, "elapsed_time": "3:22:53", "remaining_time": "7:54:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 488, "total_steps": 1626, "loss": 1.619, "learning_rate": 2.6492966817336977e-05, "epoch": 0.8995391705069125, "percentage": 30.01, "elapsed_time": "3:23:18", "remaining_time": "7:54:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 489, "total_steps": 1626, "loss": 1.5945, "learning_rate": 2.6472241744301304e-05, "epoch": 0.9013824884792627, "percentage": 30.07, "elapsed_time": "3:23:43", "remaining_time": "7:53:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 490, "total_steps": 1626, "loss": 1.5934, "learning_rate": 2.645146377083393e-05, "epoch": 0.9032258064516129, "percentage": 30.14, "elapsed_time": "3:24:08", "remaining_time": "7:53:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 491, "total_steps": 1626, "loss": 1.6376, "learning_rate": 2.6430632992745577e-05, "epoch": 0.9050691244239631, "percentage": 30.2, "elapsed_time": "3:24:33", "remaining_time": "7:52:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 492, "total_steps": 1626, "loss": 1.6398, "learning_rate": 2.6409749506090456e-05, "epoch": 0.9069124423963134, "percentage": 30.26, "elapsed_time": "3:24:58", "remaining_time": "7:52:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 493, "total_steps": 1626, "loss": 1.7085, "learning_rate": 2.638881340716583e-05, "epoch": 0.9087557603686636, "percentage": 30.32, "elapsed_time": "3:25:22", "remaining_time": "7:52:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 494, "total_steps": 1626, "loss": 1.663, "learning_rate": 2.6367824792511565e-05, "epoch": 0.9105990783410138, "percentage": 30.38, "elapsed_time": "3:25:47", "remaining_time": "7:51:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 495, "total_steps": 1626, "loss": 1.6809, "learning_rate": 2.6346783758909683e-05, "epoch": 0.9124423963133641, "percentage": 30.44, "elapsed_time": "3:26:12", "remaining_time": "7:51:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 496, "total_steps": 1626, "loss": 1.6235, "learning_rate": 2.632569040338392e-05, "epoch": 0.9142857142857143, "percentage": 30.5, "elapsed_time": "3:26:38", "remaining_time": "7:50:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 497, "total_steps": 1626, "loss": 1.6263, "learning_rate": 2.6304544823199282e-05, "epoch": 0.9161290322580645, "percentage": 30.57, "elapsed_time": "3:27:03", "remaining_time": "7:50:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 498, "total_steps": 1626, "loss": 1.6395, "learning_rate": 2.6283347115861586e-05, "epoch": 0.9179723502304148, "percentage": 30.63, "elapsed_time": "3:27:27", "remaining_time": "7:49:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 499, "total_steps": 1626, "loss": 1.6613, "learning_rate": 2.6262097379117015e-05, "epoch": 0.919815668202765, "percentage": 30.69, "elapsed_time": "3:27:52", "remaining_time": "7:49:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 500, "total_steps": 1626, "loss": 1.6483, "learning_rate": 2.624079571095167e-05, "epoch": 0.9216589861751152, "percentage": 30.75, "elapsed_time": "3:28:17", "remaining_time": "7:49:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 501, "total_steps": 1626, "loss": 1.6918, "learning_rate": 2.6219442209591123e-05, "epoch": 0.9235023041474655, "percentage": 30.81, "elapsed_time": "3:28:42", "remaining_time": "7:48:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 502, "total_steps": 1626, "loss": 1.6222, "learning_rate": 2.619803697349994e-05, "epoch": 0.9253456221198156, "percentage": 30.87, "elapsed_time": "3:29:07", "remaining_time": "7:48:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 503, "total_steps": 1626, "loss": 1.6017, "learning_rate": 2.6176580101381273e-05, "epoch": 0.9271889400921659, "percentage": 30.93, "elapsed_time": "3:29:32", "remaining_time": "7:47:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 504, "total_steps": 1626, "loss": 1.6117, "learning_rate": 2.6155071692176348e-05, "epoch": 0.9290322580645162, "percentage": 31.0, "elapsed_time": "3:29:57", "remaining_time": "7:47:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 505, "total_steps": 1626, "loss": 1.6483, "learning_rate": 2.613351184506405e-05, "epoch": 0.9308755760368663, "percentage": 31.06, "elapsed_time": "3:30:22", "remaining_time": "7:46:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 506, "total_steps": 1626, "loss": 1.63, "learning_rate": 2.6111900659460455e-05, "epoch": 0.9327188940092166, "percentage": 31.12, "elapsed_time": "3:30:47", "remaining_time": "7:46:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 507, "total_steps": 1626, "loss": 1.617, "learning_rate": 2.6090238235018365e-05, "epoch": 0.9345622119815669, "percentage": 31.18, "elapsed_time": "3:31:12", "remaining_time": "7:46:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 508, "total_steps": 1626, "loss": 1.6671, "learning_rate": 2.6068524671626856e-05, "epoch": 0.936405529953917, "percentage": 31.24, "elapsed_time": "3:31:36", "remaining_time": "7:45:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 509, "total_steps": 1626, "loss": 1.6101, "learning_rate": 2.6046760069410806e-05, "epoch": 0.9382488479262673, "percentage": 31.3, "elapsed_time": "3:32:01", "remaining_time": "7:45:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 510, "total_steps": 1626, "loss": 1.5903, "learning_rate": 2.6024944528730453e-05, "epoch": 0.9400921658986175, "percentage": 31.37, "elapsed_time": "3:32:26", "remaining_time": "7:44:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 511, "total_steps": 1626, "loss": 1.6722, "learning_rate": 2.6003078150180922e-05, "epoch": 0.9419354838709677, "percentage": 31.43, "elapsed_time": "3:32:51", "remaining_time": "7:44:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 512, "total_steps": 1626, "loss": 1.6232, "learning_rate": 2.598116103459174e-05, "epoch": 0.943778801843318, "percentage": 31.49, "elapsed_time": "3:33:16", "remaining_time": "7:44:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 513, "total_steps": 1626, "loss": 1.5969, "learning_rate": 2.595919328302641e-05, "epoch": 0.9456221198156682, "percentage": 31.55, "elapsed_time": "3:33:41", "remaining_time": "7:43:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 514, "total_steps": 1626, "loss": 1.5817, "learning_rate": 2.5937174996781927e-05, "epoch": 0.9474654377880184, "percentage": 31.61, "elapsed_time": "3:34:06", "remaining_time": "7:43:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 515, "total_steps": 1626, "loss": 1.5845, "learning_rate": 2.5915106277388293e-05, "epoch": 0.9493087557603687, "percentage": 31.67, "elapsed_time": "3:34:31", "remaining_time": "7:42:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 516, "total_steps": 1626, "loss": 1.6227, "learning_rate": 2.5892987226608082e-05, "epoch": 0.9511520737327189, "percentage": 31.73, "elapsed_time": "3:34:56", "remaining_time": "7:42:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 517, "total_steps": 1626, "loss": 1.5853, "learning_rate": 2.5870817946435953e-05, "epoch": 0.9529953917050691, "percentage": 31.8, "elapsed_time": "3:35:20", "remaining_time": "7:41:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 518, "total_steps": 1626, "loss": 1.6514, "learning_rate": 2.5848598539098164e-05, "epoch": 0.9548387096774194, "percentage": 31.86, "elapsed_time": "3:35:45", "remaining_time": "7:41:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 519, "total_steps": 1626, "loss": 1.603, "learning_rate": 2.5826329107052144e-05, "epoch": 0.9566820276497696, "percentage": 31.92, "elapsed_time": "3:36:10", "remaining_time": "7:41:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 520, "total_steps": 1626, "loss": 1.6073, "learning_rate": 2.5804009752985975e-05, "epoch": 0.9585253456221198, "percentage": 31.98, "elapsed_time": "3:36:35", "remaining_time": "7:40:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 521, "total_steps": 1626, "loss": 1.6337, "learning_rate": 2.5781640579817946e-05, "epoch": 0.96036866359447, "percentage": 32.04, "elapsed_time": "3:37:01", "remaining_time": "7:40:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 522, "total_steps": 1626, "loss": 1.6345, "learning_rate": 2.5759221690696062e-05, "epoch": 0.9622119815668203, "percentage": 32.1, "elapsed_time": "3:37:26", "remaining_time": "7:39:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 523, "total_steps": 1626, "loss": 1.6471, "learning_rate": 2.573675318899759e-05, "epoch": 0.9640552995391705, "percentage": 32.16, "elapsed_time": "3:37:51", "remaining_time": "7:39:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 524, "total_steps": 1626, "loss": 1.6632, "learning_rate": 2.5714235178328554e-05, "epoch": 0.9658986175115207, "percentage": 32.23, "elapsed_time": "3:38:16", "remaining_time": "7:39:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 525, "total_steps": 1626, "loss": 1.6133, "learning_rate": 2.5691667762523284e-05, "epoch": 0.967741935483871, "percentage": 32.29, "elapsed_time": "3:38:41", "remaining_time": "7:38:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 526, "total_steps": 1626, "loss": 1.628, "learning_rate": 2.566905104564393e-05, "epoch": 0.9695852534562212, "percentage": 32.35, "elapsed_time": "3:39:05", "remaining_time": "7:38:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 527, "total_steps": 1626, "loss": 1.5717, "learning_rate": 2.564638513197995e-05, "epoch": 0.9714285714285714, "percentage": 32.41, "elapsed_time": "3:39:30", "remaining_time": "7:37:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 528, "total_steps": 1626, "loss": 1.6104, "learning_rate": 2.562367012604769e-05, "epoch": 0.9732718894009217, "percentage": 32.47, "elapsed_time": "3:39:55", "remaining_time": "7:37:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 529, "total_steps": 1626, "loss": 1.6325, "learning_rate": 2.5600906132589846e-05, "epoch": 0.9751152073732718, "percentage": 32.53, "elapsed_time": "3:40:20", "remaining_time": "7:36:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 530, "total_steps": 1626, "loss": 1.605, "learning_rate": 2.557809325657501e-05, "epoch": 0.9769585253456221, "percentage": 32.6, "elapsed_time": "3:40:45", "remaining_time": "7:36:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 531, "total_steps": 1626, "loss": 1.6302, "learning_rate": 2.555523160319719e-05, "epoch": 0.9788018433179724, "percentage": 32.66, "elapsed_time": "3:41:10", "remaining_time": "7:36:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 532, "total_steps": 1626, "loss": 1.6813, "learning_rate": 2.5532321277875305e-05, "epoch": 0.9806451612903225, "percentage": 32.72, "elapsed_time": "3:41:35", "remaining_time": "7:35:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 533, "total_steps": 1626, "loss": 1.6166, "learning_rate": 2.5509362386252702e-05, "epoch": 0.9824884792626728, "percentage": 32.78, "elapsed_time": "3:42:00", "remaining_time": "7:35:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 534, "total_steps": 1626, "loss": 1.669, "learning_rate": 2.5486355034196686e-05, "epoch": 0.9843317972350231, "percentage": 32.84, "elapsed_time": "3:42:24", "remaining_time": "7:34:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 535, "total_steps": 1626, "loss": 1.6714, "learning_rate": 2.5463299327798015e-05, "epoch": 0.9861751152073732, "percentage": 32.9, "elapsed_time": "3:42:49", "remaining_time": "7:34:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 536, "total_steps": 1626, "loss": 1.6314, "learning_rate": 2.544019537337043e-05, "epoch": 0.9880184331797235, "percentage": 32.96, "elapsed_time": "3:43:14", "remaining_time": "7:33:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 537, "total_steps": 1626, "loss": 1.6458, "learning_rate": 2.541704327745013e-05, "epoch": 0.9898617511520738, "percentage": 33.03, "elapsed_time": "3:43:39", "remaining_time": "7:33:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 538, "total_steps": 1626, "loss": 1.6564, "learning_rate": 2.539384314679532e-05, "epoch": 0.9917050691244239, "percentage": 33.09, "elapsed_time": "3:44:04", "remaining_time": "7:33:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 539, "total_steps": 1626, "loss": 1.6071, "learning_rate": 2.5370595088385696e-05, "epoch": 0.9935483870967742, "percentage": 33.15, "elapsed_time": "3:44:29", "remaining_time": "7:32:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 540, "total_steps": 1626, "loss": 1.611, "learning_rate": 2.5347299209421955e-05, "epoch": 0.9953917050691244, "percentage": 33.21, "elapsed_time": "3:44:54", "remaining_time": "7:32:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 541, "total_steps": 1626, "loss": 1.6311, "learning_rate": 2.53239556173253e-05, "epoch": 0.9972350230414746, "percentage": 33.27, "elapsed_time": "3:45:19", "remaining_time": "7:31:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 542, "total_steps": 1626, "loss": 1.5659, "learning_rate": 2.530056441973696e-05, "epoch": 0.9990783410138249, "percentage": 33.33, "elapsed_time": "3:45:44", "remaining_time": "7:31:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 543, "total_steps": 1626, "loss": 1.6523, "learning_rate": 2.5277125724517665e-05, "epoch": 1.0009216589861751, "percentage": 33.39, "elapsed_time": "3:46:09", "remaining_time": "7:31:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 544, "total_steps": 1626, "loss": 1.655, "learning_rate": 2.525363963974717e-05, "epoch": 1.0027649769585254, "percentage": 33.46, "elapsed_time": "3:46:36", "remaining_time": "7:30:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 545, "total_steps": 1626, "loss": 1.5368, "learning_rate": 2.523010627372376e-05, "epoch": 1.0046082949308757, "percentage": 33.52, "elapsed_time": "3:47:01", "remaining_time": "7:30:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 546, "total_steps": 1626, "loss": 1.6131, "learning_rate": 2.520652573496373e-05, "epoch": 1.0064516129032257, "percentage": 33.58, "elapsed_time": "3:47:26", "remaining_time": "7:29:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 547, "total_steps": 1626, "loss": 1.6299, "learning_rate": 2.51828981322009e-05, "epoch": 1.008294930875576, "percentage": 33.64, "elapsed_time": "3:47:51", "remaining_time": "7:29:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 548, "total_steps": 1626, "loss": 1.6282, "learning_rate": 2.5159223574386117e-05, "epoch": 1.0101382488479262, "percentage": 33.7, "elapsed_time": "3:48:16", "remaining_time": "7:29:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 549, "total_steps": 1626, "loss": 1.6306, "learning_rate": 2.513550217068673e-05, "epoch": 1.0119815668202765, "percentage": 33.76, "elapsed_time": "3:48:40", "remaining_time": "7:28:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 550, "total_steps": 1626, "loss": 1.6022, "learning_rate": 2.5111734030486127e-05, "epoch": 1.0138248847926268, "percentage": 33.83, "elapsed_time": "3:49:05", "remaining_time": "7:28:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 551, "total_steps": 1626, "loss": 1.6113, "learning_rate": 2.508791926338317e-05, "epoch": 1.015668202764977, "percentage": 33.89, "elapsed_time": "3:49:30", "remaining_time": "7:27:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 552, "total_steps": 1626, "loss": 1.6101, "learning_rate": 2.5064057979191766e-05, "epoch": 1.017511520737327, "percentage": 33.95, "elapsed_time": "3:49:55", "remaining_time": "7:27:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 553, "total_steps": 1626, "loss": 1.611, "learning_rate": 2.5040150287940286e-05, "epoch": 1.0193548387096774, "percentage": 34.01, "elapsed_time": "3:50:20", "remaining_time": "7:26:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 554, "total_steps": 1626, "loss": 1.6068, "learning_rate": 2.5016196299871115e-05, "epoch": 1.0211981566820276, "percentage": 34.07, "elapsed_time": "3:50:45", "remaining_time": "7:26:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 555, "total_steps": 1626, "loss": 1.6466, "learning_rate": 2.49921961254401e-05, "epoch": 1.023041474654378, "percentage": 34.13, "elapsed_time": "3:51:10", "remaining_time": "7:26:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 556, "total_steps": 1626, "loss": 1.651, "learning_rate": 2.496814987531609e-05, "epoch": 1.0248847926267282, "percentage": 34.19, "elapsed_time": "3:51:35", "remaining_time": "7:25:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 557, "total_steps": 1626, "loss": 1.6455, "learning_rate": 2.4944057660380363e-05, "epoch": 1.0267281105990784, "percentage": 34.26, "elapsed_time": "3:52:00", "remaining_time": "7:25:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 558, "total_steps": 1626, "loss": 1.6231, "learning_rate": 2.4919919591726175e-05, "epoch": 1.0285714285714285, "percentage": 34.32, "elapsed_time": "3:52:25", "remaining_time": "7:24:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 559, "total_steps": 1626, "loss": 1.6258, "learning_rate": 2.489573578065821e-05, "epoch": 1.0304147465437787, "percentage": 34.38, "elapsed_time": "3:52:50", "remaining_time": "7:24:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 560, "total_steps": 1626, "loss": 1.5856, "learning_rate": 2.487150633869207e-05, "epoch": 1.032258064516129, "percentage": 34.44, "elapsed_time": "3:53:15", "remaining_time": "7:24:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 561, "total_steps": 1626, "loss": 1.5899, "learning_rate": 2.484723137755379e-05, "epoch": 1.0341013824884793, "percentage": 34.5, "elapsed_time": "3:53:39", "remaining_time": "7:23:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 562, "total_steps": 1626, "loss": 1.7224, "learning_rate": 2.482291100917928e-05, "epoch": 1.0359447004608295, "percentage": 34.56, "elapsed_time": "3:54:04", "remaining_time": "7:23:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 563, "total_steps": 1626, "loss": 1.6187, "learning_rate": 2.4798545345713837e-05, "epoch": 1.0377880184331798, "percentage": 34.62, "elapsed_time": "3:54:29", "remaining_time": "7:22:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 564, "total_steps": 1626, "loss": 1.7049, "learning_rate": 2.4774134499511636e-05, "epoch": 1.0396313364055298, "percentage": 34.69, "elapsed_time": "3:54:54", "remaining_time": "7:22:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 565, "total_steps": 1626, "loss": 1.5474, "learning_rate": 2.4749678583135175e-05, "epoch": 1.0414746543778801, "percentage": 34.75, "elapsed_time": "3:55:20", "remaining_time": "7:21:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 566, "total_steps": 1626, "loss": 1.623, "learning_rate": 2.472517770935479e-05, "epoch": 1.0433179723502304, "percentage": 34.81, "elapsed_time": "3:55:44", "remaining_time": "7:21:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 567, "total_steps": 1626, "loss": 1.5814, "learning_rate": 2.4700631991148126e-05, "epoch": 1.0451612903225806, "percentage": 34.87, "elapsed_time": "3:56:09", "remaining_time": "7:21:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 568, "total_steps": 1626, "loss": 1.644, "learning_rate": 2.46760415416996e-05, "epoch": 1.047004608294931, "percentage": 34.93, "elapsed_time": "3:56:34", "remaining_time": "7:20:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 569, "total_steps": 1626, "loss": 1.6133, "learning_rate": 2.465140647439991e-05, "epoch": 1.0488479262672812, "percentage": 34.99, "elapsed_time": "3:56:59", "remaining_time": "7:20:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 570, "total_steps": 1626, "loss": 1.6963, "learning_rate": 2.4626726902845477e-05, "epoch": 1.0506912442396312, "percentage": 35.06, "elapsed_time": "3:57:24", "remaining_time": "7:19:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 571, "total_steps": 1626, "loss": 1.5626, "learning_rate": 2.4602002940837948e-05, "epoch": 1.0525345622119815, "percentage": 35.12, "elapsed_time": "3:57:49", "remaining_time": "7:19:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 572, "total_steps": 1626, "loss": 1.5422, "learning_rate": 2.4577234702383666e-05, "epoch": 1.0543778801843318, "percentage": 35.18, "elapsed_time": "3:58:14", "remaining_time": "7:18:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 573, "total_steps": 1626, "loss": 1.5826, "learning_rate": 2.4552422301693128e-05, "epoch": 1.056221198156682, "percentage": 35.24, "elapsed_time": "3:58:38", "remaining_time": "7:18:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 574, "total_steps": 1626, "loss": 1.596, "learning_rate": 2.452756585318048e-05, "epoch": 1.0580645161290323, "percentage": 35.3, "elapsed_time": "3:59:03", "remaining_time": "7:18:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 575, "total_steps": 1626, "loss": 1.6028, "learning_rate": 2.4502665471462983e-05, "epoch": 1.0599078341013826, "percentage": 35.36, "elapsed_time": "3:59:28", "remaining_time": "7:17:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 576, "total_steps": 1626, "loss": 1.5927, "learning_rate": 2.447772127136046e-05, "epoch": 1.0617511520737328, "percentage": 35.42, "elapsed_time": "3:59:53", "remaining_time": "7:17:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 577, "total_steps": 1626, "loss": 1.5879, "learning_rate": 2.4452733367894816e-05, "epoch": 1.0635944700460829, "percentage": 35.49, "elapsed_time": "4:00:18", "remaining_time": "7:16:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 578, "total_steps": 1626, "loss": 1.5583, "learning_rate": 2.4427701876289465e-05, "epoch": 1.0654377880184331, "percentage": 35.55, "elapsed_time": "4:00:43", "remaining_time": "7:16:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 579, "total_steps": 1626, "loss": 1.6205, "learning_rate": 2.440262691196881e-05, "epoch": 1.0672811059907834, "percentage": 35.61, "elapsed_time": "4:01:08", "remaining_time": "7:16:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 580, "total_steps": 1626, "loss": 1.6112, "learning_rate": 2.437750859055773e-05, "epoch": 1.0691244239631337, "percentage": 35.67, "elapsed_time": "4:01:33", "remaining_time": "7:15:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 581, "total_steps": 1626, "loss": 1.6036, "learning_rate": 2.4352347027881003e-05, "epoch": 1.070967741935484, "percentage": 35.73, "elapsed_time": "4:01:58", "remaining_time": "7:15:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 582, "total_steps": 1626, "loss": 1.6073, "learning_rate": 2.4327142339962827e-05, "epoch": 1.072811059907834, "percentage": 35.79, "elapsed_time": "4:02:23", "remaining_time": "7:14:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 583, "total_steps": 1626, "loss": 1.6312, "learning_rate": 2.430189464302625e-05, "epoch": 1.0746543778801843, "percentage": 35.85, "elapsed_time": "4:02:48", "remaining_time": "7:14:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 584, "total_steps": 1626, "loss": 1.6042, "learning_rate": 2.4276604053492636e-05, "epoch": 1.0764976958525345, "percentage": 35.92, "elapsed_time": "4:03:13", "remaining_time": "7:13:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 585, "total_steps": 1626, "loss": 1.586, "learning_rate": 2.425127068798113e-05, "epoch": 1.0783410138248848, "percentage": 35.98, "elapsed_time": "4:03:38", "remaining_time": "7:13:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 586, "total_steps": 1626, "loss": 1.6629, "learning_rate": 2.422589466330814e-05, "epoch": 1.080184331797235, "percentage": 36.04, "elapsed_time": "4:04:03", "remaining_time": "7:13:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 587, "total_steps": 1626, "loss": 1.5843, "learning_rate": 2.4200476096486774e-05, "epoch": 1.0820276497695853, "percentage": 36.1, "elapsed_time": "4:04:28", "remaining_time": "7:12:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 588, "total_steps": 1626, "loss": 1.6378, "learning_rate": 2.4175015104726306e-05, "epoch": 1.0838709677419356, "percentage": 36.16, "elapsed_time": "4:04:53", "remaining_time": "7:12:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 589, "total_steps": 1626, "loss": 1.7082, "learning_rate": 2.414951180543164e-05, "epoch": 1.0857142857142856, "percentage": 36.22, "elapsed_time": "4:05:18", "remaining_time": "7:11:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 590, "total_steps": 1626, "loss": 1.5482, "learning_rate": 2.4123966316202768e-05, "epoch": 1.087557603686636, "percentage": 36.29, "elapsed_time": "4:05:43", "remaining_time": "7:11:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 591, "total_steps": 1626, "loss": 1.6042, "learning_rate": 2.4098378754834227e-05, "epoch": 1.0894009216589862, "percentage": 36.35, "elapsed_time": "4:06:08", "remaining_time": "7:11:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 592, "total_steps": 1626, "loss": 1.5839, "learning_rate": 2.4072749239314565e-05, "epoch": 1.0912442396313364, "percentage": 36.41, "elapsed_time": "4:06:32", "remaining_time": "7:10:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 593, "total_steps": 1626, "loss": 1.5705, "learning_rate": 2.4047077887825765e-05, "epoch": 1.0930875576036867, "percentage": 36.47, "elapsed_time": "4:06:57", "remaining_time": "7:10:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 594, "total_steps": 1626, "loss": 1.6325, "learning_rate": 2.402136481874275e-05, "epoch": 1.094930875576037, "percentage": 36.53, "elapsed_time": "4:07:22", "remaining_time": "7:09:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 595, "total_steps": 1626, "loss": 1.5755, "learning_rate": 2.399561015063278e-05, "epoch": 1.096774193548387, "percentage": 36.59, "elapsed_time": "4:07:47", "remaining_time": "7:09:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 596, "total_steps": 1626, "loss": 1.6258, "learning_rate": 2.3969814002254965e-05, "epoch": 1.0986175115207373, "percentage": 36.65, "elapsed_time": "4:08:12", "remaining_time": "7:08:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 597, "total_steps": 1626, "loss": 1.6046, "learning_rate": 2.3943976492559675e-05, "epoch": 1.1004608294930875, "percentage": 36.72, "elapsed_time": "4:08:37", "remaining_time": "7:08:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 598, "total_steps": 1626, "loss": 1.6198, "learning_rate": 2.3918097740687987e-05, "epoch": 1.1023041474654378, "percentage": 36.78, "elapsed_time": "4:09:02", "remaining_time": "7:08:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 599, "total_steps": 1626, "loss": 1.5345, "learning_rate": 2.3892177865971183e-05, "epoch": 1.104147465437788, "percentage": 36.84, "elapsed_time": "4:09:27", "remaining_time": "7:07:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 600, "total_steps": 1626, "loss": 1.6041, "learning_rate": 2.386621698793015e-05, "epoch": 1.1059907834101383, "percentage": 36.9, "elapsed_time": "4:09:52", "remaining_time": "7:07:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 601, "total_steps": 1626, "loss": 1.5975, "learning_rate": 2.3840215226274847e-05, "epoch": 1.1078341013824884, "percentage": 36.96, "elapsed_time": "4:10:27", "remaining_time": "7:07:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 602, "total_steps": 1626, "loss": 1.6021, "learning_rate": 2.3814172700903775e-05, "epoch": 1.1096774193548387, "percentage": 37.02, "elapsed_time": "4:10:52", "remaining_time": "7:06:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 603, "total_steps": 1626, "loss": 1.5317, "learning_rate": 2.3788089531903372e-05, "epoch": 1.111520737327189, "percentage": 37.08, "elapsed_time": "4:11:17", "remaining_time": "7:06:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 604, "total_steps": 1626, "loss": 1.5867, "learning_rate": 2.3761965839547515e-05, "epoch": 1.1133640552995392, "percentage": 37.15, "elapsed_time": "4:11:42", "remaining_time": "7:05:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 605, "total_steps": 1626, "loss": 1.6256, "learning_rate": 2.3735801744296934e-05, "epoch": 1.1152073732718895, "percentage": 37.21, "elapsed_time": "4:12:07", "remaining_time": "7:05:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 606, "total_steps": 1626, "loss": 1.6208, "learning_rate": 2.3709597366798662e-05, "epoch": 1.1170506912442397, "percentage": 37.27, "elapsed_time": "4:12:32", "remaining_time": "7:05:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 607, "total_steps": 1626, "loss": 1.6535, "learning_rate": 2.3683352827885472e-05, "epoch": 1.1188940092165898, "percentage": 37.33, "elapsed_time": "4:12:57", "remaining_time": "7:04:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 608, "total_steps": 1626, "loss": 1.606, "learning_rate": 2.365706824857535e-05, "epoch": 1.12073732718894, "percentage": 37.39, "elapsed_time": "4:13:22", "remaining_time": "7:04:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 609, "total_steps": 1626, "loss": 1.5968, "learning_rate": 2.3630743750070892e-05, "epoch": 1.1225806451612903, "percentage": 37.45, "elapsed_time": "4:13:47", "remaining_time": "7:03:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 610, "total_steps": 1626, "loss": 1.6303, "learning_rate": 2.360437945375878e-05, "epoch": 1.1244239631336406, "percentage": 37.52, "elapsed_time": "4:14:12", "remaining_time": "7:03:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 611, "total_steps": 1626, "loss": 1.6004, "learning_rate": 2.3577975481209214e-05, "epoch": 1.1262672811059908, "percentage": 37.58, "elapsed_time": "4:14:37", "remaining_time": "7:02:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 612, "total_steps": 1626, "loss": 1.6507, "learning_rate": 2.3551531954175335e-05, "epoch": 1.128110599078341, "percentage": 37.64, "elapsed_time": "4:15:02", "remaining_time": "7:02:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 613, "total_steps": 1626, "loss": 1.5314, "learning_rate": 2.3525048994592684e-05, "epoch": 1.1299539170506911, "percentage": 37.7, "elapsed_time": "4:15:27", "remaining_time": "7:02:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 614, "total_steps": 1626, "loss": 1.5997, "learning_rate": 2.3498526724578637e-05, "epoch": 1.1317972350230414, "percentage": 37.76, "elapsed_time": "4:15:51", "remaining_time": "7:01:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 615, "total_steps": 1626, "loss": 1.6192, "learning_rate": 2.3471965266431824e-05, "epoch": 1.1336405529953917, "percentage": 37.82, "elapsed_time": "4:16:16", "remaining_time": "7:01:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 616, "total_steps": 1626, "loss": 1.5632, "learning_rate": 2.3445364742631592e-05, "epoch": 1.135483870967742, "percentage": 37.88, "elapsed_time": "4:16:41", "remaining_time": "7:00:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 617, "total_steps": 1626, "loss": 1.6104, "learning_rate": 2.3418725275837413e-05, "epoch": 1.1373271889400922, "percentage": 37.95, "elapsed_time": "4:17:06", "remaining_time": "7:00:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 618, "total_steps": 1626, "loss": 1.5942, "learning_rate": 2.3392046988888345e-05, "epoch": 1.1391705069124425, "percentage": 38.01, "elapsed_time": "4:17:31", "remaining_time": "7:00:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 619, "total_steps": 1626, "loss": 1.6284, "learning_rate": 2.3365330004802443e-05, "epoch": 1.1410138248847925, "percentage": 38.07, "elapsed_time": "4:17:56", "remaining_time": "6:59:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 620, "total_steps": 1626, "loss": 1.5903, "learning_rate": 2.33385744467762e-05, "epoch": 1.1428571428571428, "percentage": 38.13, "elapsed_time": "4:18:21", "remaining_time": "6:59:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 621, "total_steps": 1626, "loss": 1.6339, "learning_rate": 2.331178043818399e-05, "epoch": 1.144700460829493, "percentage": 38.19, "elapsed_time": "4:18:46", "remaining_time": "6:58:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 622, "total_steps": 1626, "loss": 1.5174, "learning_rate": 2.328494810257748e-05, "epoch": 1.1465437788018433, "percentage": 38.25, "elapsed_time": "4:19:11", "remaining_time": "6:58:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 623, "total_steps": 1626, "loss": 1.6126, "learning_rate": 2.3258077563685072e-05, "epoch": 1.1483870967741936, "percentage": 38.31, "elapsed_time": "4:19:36", "remaining_time": "6:57:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 624, "total_steps": 1626, "loss": 1.5872, "learning_rate": 2.3231168945411326e-05, "epoch": 1.1502304147465439, "percentage": 38.38, "elapsed_time": "4:20:01", "remaining_time": "6:57:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 625, "total_steps": 1626, "loss": 1.6007, "learning_rate": 2.320422237183641e-05, "epoch": 1.1520737327188941, "percentage": 38.44, "elapsed_time": "4:20:26", "remaining_time": "6:57:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 626, "total_steps": 1626, "loss": 1.5988, "learning_rate": 2.317723796721547e-05, "epoch": 1.1539170506912442, "percentage": 38.5, "elapsed_time": "4:20:51", "remaining_time": "6:56:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 627, "total_steps": 1626, "loss": 1.5385, "learning_rate": 2.315021585597815e-05, "epoch": 1.1557603686635944, "percentage": 38.56, "elapsed_time": "4:21:16", "remaining_time": "6:56:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 628, "total_steps": 1626, "loss": 1.6156, "learning_rate": 2.3123156162727923e-05, "epoch": 1.1576036866359447, "percentage": 38.62, "elapsed_time": "4:21:41", "remaining_time": "6:55:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 629, "total_steps": 1626, "loss": 1.5353, "learning_rate": 2.3096059012241583e-05, "epoch": 1.159447004608295, "percentage": 38.68, "elapsed_time": "4:22:06", "remaining_time": "6:55:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 630, "total_steps": 1626, "loss": 1.6577, "learning_rate": 2.3068924529468638e-05, "epoch": 1.1612903225806452, "percentage": 38.75, "elapsed_time": "4:22:31", "remaining_time": "6:55:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 631, "total_steps": 1626, "loss": 1.6112, "learning_rate": 2.3041752839530735e-05, "epoch": 1.1631336405529953, "percentage": 38.81, "elapsed_time": "4:22:56", "remaining_time": "6:54:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 632, "total_steps": 1626, "loss": 1.5268, "learning_rate": 2.3014544067721096e-05, "epoch": 1.1649769585253456, "percentage": 38.87, "elapsed_time": "4:23:21", "remaining_time": "6:54:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 633, "total_steps": 1626, "loss": 1.5635, "learning_rate": 2.298729833950394e-05, "epoch": 1.1668202764976958, "percentage": 38.93, "elapsed_time": "4:23:46", "remaining_time": "6:53:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 634, "total_steps": 1626, "loss": 1.6243, "learning_rate": 2.2960015780513893e-05, "epoch": 1.168663594470046, "percentage": 38.99, "elapsed_time": "4:24:11", "remaining_time": "6:53:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 635, "total_steps": 1626, "loss": 1.5647, "learning_rate": 2.2932696516555396e-05, "epoch": 1.1705069124423964, "percentage": 39.05, "elapsed_time": "4:24:36", "remaining_time": "6:52:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 636, "total_steps": 1626, "loss": 1.5705, "learning_rate": 2.2905340673602184e-05, "epoch": 1.1723502304147466, "percentage": 39.11, "elapsed_time": "4:25:00", "remaining_time": "6:52:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 637, "total_steps": 1626, "loss": 1.6524, "learning_rate": 2.287794837779662e-05, "epoch": 1.1741935483870969, "percentage": 39.18, "elapsed_time": "4:25:25", "remaining_time": "6:52:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 638, "total_steps": 1626, "loss": 1.57, "learning_rate": 2.2850519755449183e-05, "epoch": 1.176036866359447, "percentage": 39.24, "elapsed_time": "4:25:50", "remaining_time": "6:51:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 639, "total_steps": 1626, "loss": 1.6409, "learning_rate": 2.282305493303785e-05, "epoch": 1.1778801843317972, "percentage": 39.3, "elapsed_time": "4:26:18", "remaining_time": "6:51:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 640, "total_steps": 1626, "loss": 1.6925, "learning_rate": 2.2795554037207528e-05, "epoch": 1.1797235023041475, "percentage": 39.36, "elapsed_time": "4:26:42", "remaining_time": "6:50:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 641, "total_steps": 1626, "loss": 1.5796, "learning_rate": 2.2768017194769466e-05, "epoch": 1.1815668202764977, "percentage": 39.42, "elapsed_time": "4:27:07", "remaining_time": "6:50:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 642, "total_steps": 1626, "loss": 1.6039, "learning_rate": 2.2740444532700657e-05, "epoch": 1.183410138248848, "percentage": 39.48, "elapsed_time": "4:27:32", "remaining_time": "6:50:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 643, "total_steps": 1626, "loss": 1.6457, "learning_rate": 2.271283617814328e-05, "epoch": 1.185253456221198, "percentage": 39.54, "elapsed_time": "4:27:57", "remaining_time": "6:49:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 644, "total_steps": 1626, "loss": 1.5728, "learning_rate": 2.268519225840409e-05, "epoch": 1.1870967741935483, "percentage": 39.61, "elapsed_time": "4:28:22", "remaining_time": "6:49:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 645, "total_steps": 1626, "loss": 1.617, "learning_rate": 2.2657512900953832e-05, "epoch": 1.1889400921658986, "percentage": 39.67, "elapsed_time": "4:28:47", "remaining_time": "6:48:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 646, "total_steps": 1626, "loss": 1.6127, "learning_rate": 2.2629798233426677e-05, "epoch": 1.1907834101382488, "percentage": 39.73, "elapsed_time": "4:29:12", "remaining_time": "6:48:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 647, "total_steps": 1626, "loss": 1.5747, "learning_rate": 2.26020483836196e-05, "epoch": 1.192626728110599, "percentage": 39.79, "elapsed_time": "4:29:37", "remaining_time": "6:47:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 648, "total_steps": 1626, "loss": 1.6335, "learning_rate": 2.2574263479491816e-05, "epoch": 1.1944700460829494, "percentage": 39.85, "elapsed_time": "4:30:02", "remaining_time": "6:47:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 649, "total_steps": 1626, "loss": 1.5749, "learning_rate": 2.2546443649164186e-05, "epoch": 1.1963133640552996, "percentage": 39.91, "elapsed_time": "4:30:27", "remaining_time": "6:47:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 650, "total_steps": 1626, "loss": 1.6022, "learning_rate": 2.2518589020918612e-05, "epoch": 1.1981566820276497, "percentage": 39.98, "elapsed_time": "4:30:52", "remaining_time": "6:46:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 651, "total_steps": 1626, "loss": 1.6034, "learning_rate": 2.2490699723197454e-05, "epoch": 1.2, "percentage": 40.04, "elapsed_time": "4:31:17", "remaining_time": "6:46:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 652, "total_steps": 1626, "loss": 1.6301, "learning_rate": 2.2462775884602954e-05, "epoch": 1.2018433179723502, "percentage": 40.1, "elapsed_time": "4:31:42", "remaining_time": "6:45:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 653, "total_steps": 1626, "loss": 1.5741, "learning_rate": 2.243481763389661e-05, "epoch": 1.2036866359447005, "percentage": 40.16, "elapsed_time": "4:32:07", "remaining_time": "6:45:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 654, "total_steps": 1626, "loss": 1.5861, "learning_rate": 2.24068250999986e-05, "epoch": 1.2055299539170508, "percentage": 40.22, "elapsed_time": "4:32:32", "remaining_time": "6:45:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 655, "total_steps": 1626, "loss": 1.6016, "learning_rate": 2.2378798411987218e-05, "epoch": 1.2073732718894008, "percentage": 40.28, "elapsed_time": "4:32:56", "remaining_time": "6:44:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 656, "total_steps": 1626, "loss": 1.6194, "learning_rate": 2.2350737699098203e-05, "epoch": 1.209216589861751, "percentage": 40.34, "elapsed_time": "4:33:21", "remaining_time": "6:44:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 657, "total_steps": 1626, "loss": 1.6285, "learning_rate": 2.2322643090724218e-05, "epoch": 1.2110599078341013, "percentage": 40.41, "elapsed_time": "4:33:46", "remaining_time": "6:43:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 658, "total_steps": 1626, "loss": 1.6217, "learning_rate": 2.229451471641422e-05, "epoch": 1.2129032258064516, "percentage": 40.47, "elapsed_time": "4:34:11", "remaining_time": "6:43:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 659, "total_steps": 1626, "loss": 1.5244, "learning_rate": 2.226635270587286e-05, "epoch": 1.2147465437788019, "percentage": 40.53, "elapsed_time": "4:34:36", "remaining_time": "6:42:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 660, "total_steps": 1626, "loss": 1.5988, "learning_rate": 2.2238157188959893e-05, "epoch": 1.2165898617511521, "percentage": 40.59, "elapsed_time": "4:35:01", "remaining_time": "6:42:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 661, "total_steps": 1626, "loss": 1.6695, "learning_rate": 2.2209928295689582e-05, "epoch": 1.2184331797235024, "percentage": 40.65, "elapsed_time": "4:35:26", "remaining_time": "6:42:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 662, "total_steps": 1626, "loss": 1.5763, "learning_rate": 2.2181666156230082e-05, "epoch": 1.2202764976958524, "percentage": 40.71, "elapsed_time": "4:35:51", "remaining_time": "6:41:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 663, "total_steps": 1626, "loss": 1.5866, "learning_rate": 2.2153370900902872e-05, "epoch": 1.2221198156682027, "percentage": 40.77, "elapsed_time": "4:36:16", "remaining_time": "6:41:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 664, "total_steps": 1626, "loss": 1.555, "learning_rate": 2.2125042660182115e-05, "epoch": 1.223963133640553, "percentage": 40.84, "elapsed_time": "4:36:40", "remaining_time": "6:40:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 665, "total_steps": 1626, "loss": 1.6108, "learning_rate": 2.2096681564694087e-05, "epoch": 1.2258064516129032, "percentage": 40.9, "elapsed_time": "4:37:05", "remaining_time": "6:40:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 666, "total_steps": 1626, "loss": 1.6178, "learning_rate": 2.2068287745216552e-05, "epoch": 1.2276497695852535, "percentage": 40.96, "elapsed_time": "4:37:30", "remaining_time": "6:40:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 667, "total_steps": 1626, "loss": 1.5851, "learning_rate": 2.203986133267818e-05, "epoch": 1.2294930875576038, "percentage": 41.02, "elapsed_time": "4:37:56", "remaining_time": "6:39:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 668, "total_steps": 1626, "loss": 1.657, "learning_rate": 2.2011402458157935e-05, "epoch": 1.2313364055299538, "percentage": 41.08, "elapsed_time": "4:38:21", "remaining_time": "6:39:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 669, "total_steps": 1626, "loss": 1.5385, "learning_rate": 2.198291125288445e-05, "epoch": 1.233179723502304, "percentage": 41.14, "elapsed_time": "4:38:45", "remaining_time": "6:38:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 670, "total_steps": 1626, "loss": 1.5856, "learning_rate": 2.1954387848235455e-05, "epoch": 1.2350230414746544, "percentage": 41.21, "elapsed_time": "4:39:10", "remaining_time": "6:38:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 671, "total_steps": 1626, "loss": 1.587, "learning_rate": 2.1925832375737168e-05, "epoch": 1.2368663594470046, "percentage": 41.27, "elapsed_time": "4:39:35", "remaining_time": "6:37:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 672, "total_steps": 1626, "loss": 1.6016, "learning_rate": 2.1897244967063653e-05, "epoch": 1.238709677419355, "percentage": 41.33, "elapsed_time": "4:40:00", "remaining_time": "6:37:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 673, "total_steps": 1626, "loss": 1.5758, "learning_rate": 2.1868625754036256e-05, "epoch": 1.2405529953917052, "percentage": 41.39, "elapsed_time": "4:40:25", "remaining_time": "6:37:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 674, "total_steps": 1626, "loss": 1.5834, "learning_rate": 2.1839974868622956e-05, "epoch": 1.2423963133640552, "percentage": 41.45, "elapsed_time": "4:40:50", "remaining_time": "6:36:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 675, "total_steps": 1626, "loss": 1.5689, "learning_rate": 2.1811292442937808e-05, "epoch": 1.2442396313364055, "percentage": 41.51, "elapsed_time": "4:41:15", "remaining_time": "6:36:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 676, "total_steps": 1626, "loss": 1.5531, "learning_rate": 2.1782578609240286e-05, "epoch": 1.2460829493087557, "percentage": 41.57, "elapsed_time": "4:41:40", "remaining_time": "6:35:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 677, "total_steps": 1626, "loss": 1.5728, "learning_rate": 2.1753833499934694e-05, "epoch": 1.247926267281106, "percentage": 41.64, "elapsed_time": "4:42:05", "remaining_time": "6:35:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 678, "total_steps": 1626, "loss": 1.5917, "learning_rate": 2.1725057247569552e-05, "epoch": 1.2497695852534563, "percentage": 41.7, "elapsed_time": "4:42:30", "remaining_time": "6:35:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 679, "total_steps": 1626, "loss": 1.6209, "learning_rate": 2.1696249984836993e-05, "epoch": 1.2516129032258063, "percentage": 41.76, "elapsed_time": "4:42:55", "remaining_time": "6:34:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 680, "total_steps": 1626, "loss": 1.6489, "learning_rate": 2.166741184457214e-05, "epoch": 1.2534562211981566, "percentage": 41.82, "elapsed_time": "4:43:20", "remaining_time": "6:34:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 681, "total_steps": 1626, "loss": 1.5935, "learning_rate": 2.1638542959752485e-05, "epoch": 1.2552995391705069, "percentage": 41.88, "elapsed_time": "4:43:45", "remaining_time": "6:33:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 682, "total_steps": 1626, "loss": 1.6304, "learning_rate": 2.160964346349731e-05, "epoch": 1.2571428571428571, "percentage": 41.94, "elapsed_time": "4:44:10", "remaining_time": "6:33:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 683, "total_steps": 1626, "loss": 1.6311, "learning_rate": 2.1580713489067043e-05, "epoch": 1.2589861751152074, "percentage": 42.0, "elapsed_time": "4:44:34", "remaining_time": "6:32:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 684, "total_steps": 1626, "loss": 1.6682, "learning_rate": 2.155175316986265e-05, "epoch": 1.2608294930875577, "percentage": 42.07, "elapsed_time": "4:44:59", "remaining_time": "6:32:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 685, "total_steps": 1626, "loss": 1.5798, "learning_rate": 2.1522762639425012e-05, "epoch": 1.262672811059908, "percentage": 42.13, "elapsed_time": "4:45:24", "remaining_time": "6:32:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 686, "total_steps": 1626, "loss": 1.5585, "learning_rate": 2.1493742031434343e-05, "epoch": 1.2645161290322582, "percentage": 42.19, "elapsed_time": "4:45:49", "remaining_time": "6:31:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 687, "total_steps": 1626, "loss": 1.5789, "learning_rate": 2.1464691479709534e-05, "epoch": 1.2663594470046082, "percentage": 42.25, "elapsed_time": "4:46:14", "remaining_time": "6:31:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 688, "total_steps": 1626, "loss": 1.564, "learning_rate": 2.1435611118207546e-05, "epoch": 1.2682027649769585, "percentage": 42.31, "elapsed_time": "4:46:39", "remaining_time": "6:30:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 689, "total_steps": 1626, "loss": 1.5709, "learning_rate": 2.140650108102281e-05, "epoch": 1.2700460829493088, "percentage": 42.37, "elapsed_time": "4:47:04", "remaining_time": "6:30:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 690, "total_steps": 1626, "loss": 1.6146, "learning_rate": 2.137736150238659e-05, "epoch": 1.271889400921659, "percentage": 42.44, "elapsed_time": "4:47:29", "remaining_time": "6:29:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 691, "total_steps": 1626, "loss": 1.6126, "learning_rate": 2.1348192516666376e-05, "epoch": 1.2737327188940093, "percentage": 42.5, "elapsed_time": "4:47:54", "remaining_time": "6:29:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 692, "total_steps": 1626, "loss": 1.5817, "learning_rate": 2.1318994258365253e-05, "epoch": 1.2755760368663593, "percentage": 42.56, "elapsed_time": "4:48:19", "remaining_time": "6:29:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 693, "total_steps": 1626, "loss": 1.5634, "learning_rate": 2.128976686212129e-05, "epoch": 1.2774193548387096, "percentage": 42.62, "elapsed_time": "4:48:44", "remaining_time": "6:28:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 694, "total_steps": 1626, "loss": 1.6467, "learning_rate": 2.1260510462706914e-05, "epoch": 1.2792626728110599, "percentage": 42.68, "elapsed_time": "4:49:09", "remaining_time": "6:28:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 695, "total_steps": 1626, "loss": 1.5887, "learning_rate": 2.12312251950283e-05, "epoch": 1.2811059907834101, "percentage": 42.74, "elapsed_time": "4:49:34", "remaining_time": "6:27:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 696, "total_steps": 1626, "loss": 1.6167, "learning_rate": 2.120191119412472e-05, "epoch": 1.2829493087557604, "percentage": 42.8, "elapsed_time": "4:49:59", "remaining_time": "6:27:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 697, "total_steps": 1626, "loss": 1.5946, "learning_rate": 2.117256859516795e-05, "epoch": 1.2847926267281107, "percentage": 42.87, "elapsed_time": "4:50:24", "remaining_time": "6:27:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 698, "total_steps": 1626, "loss": 1.5888, "learning_rate": 2.1143197533461655e-05, "epoch": 1.286635944700461, "percentage": 42.93, "elapsed_time": "4:50:49", "remaining_time": "6:26:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 699, "total_steps": 1626, "loss": 1.5984, "learning_rate": 2.1113798144440712e-05, "epoch": 1.288479262672811, "percentage": 42.99, "elapsed_time": "4:51:14", "remaining_time": "6:26:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 700, "total_steps": 1626, "loss": 1.6601, "learning_rate": 2.108437056367064e-05, "epoch": 1.2903225806451613, "percentage": 43.05, "elapsed_time": "4:51:38", "remaining_time": "6:25:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 701, "total_steps": 1626, "loss": 1.5355, "learning_rate": 2.1054914926846957e-05, "epoch": 1.2921658986175115, "percentage": 43.11, "elapsed_time": "4:52:03", "remaining_time": "6:25:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 702, "total_steps": 1626, "loss": 1.6608, "learning_rate": 2.1025431369794546e-05, "epoch": 1.2940092165898618, "percentage": 43.17, "elapsed_time": "4:52:28", "remaining_time": "6:24:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 703, "total_steps": 1626, "loss": 1.6063, "learning_rate": 2.0995920028467027e-05, "epoch": 1.295852534562212, "percentage": 43.23, "elapsed_time": "4:52:53", "remaining_time": "6:24:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 704, "total_steps": 1626, "loss": 1.5948, "learning_rate": 2.096638103894616e-05, "epoch": 1.297695852534562, "percentage": 43.3, "elapsed_time": "4:53:18", "remaining_time": "6:24:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 705, "total_steps": 1626, "loss": 1.5953, "learning_rate": 2.0936814537441173e-05, "epoch": 1.2995391705069124, "percentage": 43.36, "elapsed_time": "4:53:43", "remaining_time": "6:23:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 706, "total_steps": 1626, "loss": 1.5376, "learning_rate": 2.0907220660288166e-05, "epoch": 1.3013824884792626, "percentage": 43.42, "elapsed_time": "4:54:08", "remaining_time": "6:23:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 707, "total_steps": 1626, "loss": 1.6224, "learning_rate": 2.087759954394948e-05, "epoch": 1.303225806451613, "percentage": 43.48, "elapsed_time": "4:54:33", "remaining_time": "6:22:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 708, "total_steps": 1626, "loss": 1.6294, "learning_rate": 2.084795132501304e-05, "epoch": 1.3050691244239632, "percentage": 43.54, "elapsed_time": "4:54:58", "remaining_time": "6:22:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 709, "total_steps": 1626, "loss": 1.5813, "learning_rate": 2.081827614019177e-05, "epoch": 1.3069124423963134, "percentage": 43.6, "elapsed_time": "4:55:23", "remaining_time": "6:22:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 710, "total_steps": 1626, "loss": 1.596, "learning_rate": 2.0788574126322928e-05, "epoch": 1.3087557603686637, "percentage": 43.67, "elapsed_time": "4:55:47", "remaining_time": "6:21:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 711, "total_steps": 1626, "loss": 1.5958, "learning_rate": 2.0758845420367474e-05, "epoch": 1.3105990783410137, "percentage": 43.73, "elapsed_time": "4:56:12", "remaining_time": "6:21:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 712, "total_steps": 1626, "loss": 1.5696, "learning_rate": 2.0729090159409467e-05, "epoch": 1.312442396313364, "percentage": 43.79, "elapsed_time": "4:56:37", "remaining_time": "6:20:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 713, "total_steps": 1626, "loss": 1.5669, "learning_rate": 2.0699308480655397e-05, "epoch": 1.3142857142857143, "percentage": 43.85, "elapsed_time": "4:57:02", "remaining_time": "6:20:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 714, "total_steps": 1626, "loss": 1.6061, "learning_rate": 2.06695005214336e-05, "epoch": 1.3161290322580645, "percentage": 43.91, "elapsed_time": "4:57:27", "remaining_time": "6:19:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 715, "total_steps": 1626, "loss": 1.6457, "learning_rate": 2.0639666419193565e-05, "epoch": 1.3179723502304148, "percentage": 43.97, "elapsed_time": "4:57:52", "remaining_time": "6:19:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 716, "total_steps": 1626, "loss": 1.6045, "learning_rate": 2.0609806311505345e-05, "epoch": 1.3198156682027649, "percentage": 44.03, "elapsed_time": "4:58:17", "remaining_time": "6:19:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 717, "total_steps": 1626, "loss": 1.6246, "learning_rate": 2.057992033605891e-05, "epoch": 1.3216589861751151, "percentage": 44.1, "elapsed_time": "4:58:42", "remaining_time": "6:18:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 718, "total_steps": 1626, "loss": 1.6577, "learning_rate": 2.0550008630663507e-05, "epoch": 1.3235023041474654, "percentage": 44.16, "elapsed_time": "4:59:07", "remaining_time": "6:18:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 719, "total_steps": 1626, "loss": 1.6668, "learning_rate": 2.0520071333247025e-05, "epoch": 1.3253456221198157, "percentage": 44.22, "elapsed_time": "4:59:31", "remaining_time": "6:17:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 720, "total_steps": 1626, "loss": 1.6636, "learning_rate": 2.049010858185537e-05, "epoch": 1.327188940092166, "percentage": 44.28, "elapsed_time": "4:59:56", "remaining_time": "6:17:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 721, "total_steps": 1626, "loss": 1.5561, "learning_rate": 2.0460120514651814e-05, "epoch": 1.3290322580645162, "percentage": 44.34, "elapsed_time": "5:00:21", "remaining_time": "6:17:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 722, "total_steps": 1626, "loss": 1.5208, "learning_rate": 2.0430107269916368e-05, "epoch": 1.3308755760368665, "percentage": 44.4, "elapsed_time": "5:00:46", "remaining_time": "6:16:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 723, "total_steps": 1626, "loss": 1.6206, "learning_rate": 2.0400068986045142e-05, "epoch": 1.3327188940092167, "percentage": 44.46, "elapsed_time": "5:01:11", "remaining_time": "6:16:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 724, "total_steps": 1626, "loss": 1.6127, "learning_rate": 2.03700058015497e-05, "epoch": 1.3345622119815668, "percentage": 44.53, "elapsed_time": "5:01:36", "remaining_time": "6:15:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 725, "total_steps": 1626, "loss": 1.5904, "learning_rate": 2.0339917855056428e-05, "epoch": 1.336405529953917, "percentage": 44.59, "elapsed_time": "5:02:01", "remaining_time": "6:15:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 726, "total_steps": 1626, "loss": 1.5929, "learning_rate": 2.0309805285305905e-05, "epoch": 1.3382488479262673, "percentage": 44.65, "elapsed_time": "5:02:26", "remaining_time": "6:14:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 727, "total_steps": 1626, "loss": 1.5806, "learning_rate": 2.0279668231152233e-05, "epoch": 1.3400921658986176, "percentage": 44.71, "elapsed_time": "5:02:51", "remaining_time": "6:14:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 728, "total_steps": 1626, "loss": 1.6097, "learning_rate": 2.024950683156243e-05, "epoch": 1.3419354838709676, "percentage": 44.77, "elapsed_time": "5:03:16", "remaining_time": "6:14:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 729, "total_steps": 1626, "loss": 1.5724, "learning_rate": 2.021932122561577e-05, "epoch": 1.3437788018433179, "percentage": 44.83, "elapsed_time": "5:03:41", "remaining_time": "6:13:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 730, "total_steps": 1626, "loss": 1.6343, "learning_rate": 2.0189111552503142e-05, "epoch": 1.3456221198156681, "percentage": 44.9, "elapsed_time": "5:04:06", "remaining_time": "6:13:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 731, "total_steps": 1626, "loss": 1.609, "learning_rate": 2.015887795152643e-05, "epoch": 1.3474654377880184, "percentage": 44.96, "elapsed_time": "5:04:31", "remaining_time": "6:12:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 732, "total_steps": 1626, "loss": 1.634, "learning_rate": 2.0128620562097834e-05, "epoch": 1.3493087557603687, "percentage": 45.02, "elapsed_time": "5:04:56", "remaining_time": "6:12:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 733, "total_steps": 1626, "loss": 1.6915, "learning_rate": 2.009833952373925e-05, "epoch": 1.351152073732719, "percentage": 45.08, "elapsed_time": "5:05:21", "remaining_time": "6:12:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 734, "total_steps": 1626, "loss": 1.5641, "learning_rate": 2.0068034976081637e-05, "epoch": 1.3529953917050692, "percentage": 45.14, "elapsed_time": "5:05:46", "remaining_time": "6:11:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 735, "total_steps": 1626, "loss": 1.5901, "learning_rate": 2.0037707058864343e-05, "epoch": 1.3548387096774195, "percentage": 45.2, "elapsed_time": "5:06:11", "remaining_time": "6:11:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 736, "total_steps": 1626, "loss": 1.5878, "learning_rate": 2.0007355911934473e-05, "epoch": 1.3566820276497695, "percentage": 45.26, "elapsed_time": "5:06:35", "remaining_time": "6:10:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 737, "total_steps": 1626, "loss": 1.6212, "learning_rate": 1.997698167524628e-05, "epoch": 1.3585253456221198, "percentage": 45.33, "elapsed_time": "5:07:00", "remaining_time": "6:10:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 738, "total_steps": 1626, "loss": 1.5909, "learning_rate": 1.9946584488860454e-05, "epoch": 1.36036866359447, "percentage": 45.39, "elapsed_time": "5:07:25", "remaining_time": "6:09:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 739, "total_steps": 1626, "loss": 1.6337, "learning_rate": 1.9916164492943518e-05, "epoch": 1.3622119815668203, "percentage": 45.45, "elapsed_time": "5:07:50", "remaining_time": "6:09:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 740, "total_steps": 1626, "loss": 1.674, "learning_rate": 1.9885721827767185e-05, "epoch": 1.3640552995391704, "percentage": 45.51, "elapsed_time": "5:08:15", "remaining_time": "6:09:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 741, "total_steps": 1626, "loss": 1.6264, "learning_rate": 1.9855256633707692e-05, "epoch": 1.3658986175115206, "percentage": 45.57, "elapsed_time": "5:08:40", "remaining_time": "6:08:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 742, "total_steps": 1626, "loss": 1.6138, "learning_rate": 1.9824769051245157e-05, "epoch": 1.367741935483871, "percentage": 45.63, "elapsed_time": "5:09:05", "remaining_time": "6:08:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 743, "total_steps": 1626, "loss": 1.6153, "learning_rate": 1.979425922096294e-05, "epoch": 1.3695852534562212, "percentage": 45.69, "elapsed_time": "5:09:30", "remaining_time": "6:07:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 744, "total_steps": 1626, "loss": 1.6308, "learning_rate": 1.976372728354699e-05, "epoch": 1.3714285714285714, "percentage": 45.76, "elapsed_time": "5:09:55", "remaining_time": "6:07:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 745, "total_steps": 1626, "loss": 1.5748, "learning_rate": 1.9733173379785188e-05, "epoch": 1.3732718894009217, "percentage": 45.82, "elapsed_time": "5:10:20", "remaining_time": "6:06:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 746, "total_steps": 1626, "loss": 1.5993, "learning_rate": 1.9702597650566723e-05, "epoch": 1.375115207373272, "percentage": 45.88, "elapsed_time": "5:10:45", "remaining_time": "6:06:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 747, "total_steps": 1626, "loss": 1.6467, "learning_rate": 1.9672000236881397e-05, "epoch": 1.3769585253456222, "percentage": 45.94, "elapsed_time": "5:11:09", "remaining_time": "6:06:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 748, "total_steps": 1626, "loss": 1.6643, "learning_rate": 1.9641381279819028e-05, "epoch": 1.3788018433179723, "percentage": 46.0, "elapsed_time": "5:11:34", "remaining_time": "6:05:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 749, "total_steps": 1626, "loss": 1.6006, "learning_rate": 1.9610740920568764e-05, "epoch": 1.3806451612903226, "percentage": 46.06, "elapsed_time": "5:11:59", "remaining_time": "6:05:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 750, "total_steps": 1626, "loss": 1.654, "learning_rate": 1.9580079300418444e-05, "epoch": 1.3824884792626728, "percentage": 46.13, "elapsed_time": "5:12:25", "remaining_time": "6:04:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 751, "total_steps": 1626, "loss": 1.6131, "learning_rate": 1.954939656075394e-05, "epoch": 1.384331797235023, "percentage": 46.19, "elapsed_time": "5:12:50", "remaining_time": "6:04:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 752, "total_steps": 1626, "loss": 1.6203, "learning_rate": 1.9518692843058514e-05, "epoch": 1.3861751152073734, "percentage": 46.25, "elapsed_time": "5:13:15", "remaining_time": "6:04:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 753, "total_steps": 1626, "loss": 1.6011, "learning_rate": 1.9487968288912164e-05, "epoch": 1.3880184331797234, "percentage": 46.31, "elapsed_time": "5:13:40", "remaining_time": "6:03:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 754, "total_steps": 1626, "loss": 1.5475, "learning_rate": 1.9457223039990963e-05, "epoch": 1.3898617511520737, "percentage": 46.37, "elapsed_time": "5:14:05", "remaining_time": "6:03:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 755, "total_steps": 1626, "loss": 1.6335, "learning_rate": 1.942645723806641e-05, "epoch": 1.391705069124424, "percentage": 46.43, "elapsed_time": "5:14:30", "remaining_time": "6:02:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 756, "total_steps": 1626, "loss": 1.5606, "learning_rate": 1.9395671025004777e-05, "epoch": 1.3935483870967742, "percentage": 46.49, "elapsed_time": "5:14:55", "remaining_time": "6:02:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 757, "total_steps": 1626, "loss": 1.555, "learning_rate": 1.936486454276647e-05, "epoch": 1.3953917050691245, "percentage": 46.56, "elapsed_time": "5:15:19", "remaining_time": "6:01:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 758, "total_steps": 1626, "loss": 1.5385, "learning_rate": 1.9334037933405337e-05, "epoch": 1.3972350230414747, "percentage": 46.62, "elapsed_time": "5:15:44", "remaining_time": "6:01:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 759, "total_steps": 1626, "loss": 1.6211, "learning_rate": 1.9303191339068048e-05, "epoch": 1.399078341013825, "percentage": 46.68, "elapsed_time": "5:16:09", "remaining_time": "6:01:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 760, "total_steps": 1626, "loss": 1.6319, "learning_rate": 1.9272324901993436e-05, "epoch": 1.400921658986175, "percentage": 46.74, "elapsed_time": "5:16:34", "remaining_time": "6:00:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 761, "total_steps": 1626, "loss": 1.6263, "learning_rate": 1.9241438764511805e-05, "epoch": 1.4027649769585253, "percentage": 46.8, "elapsed_time": "5:16:59", "remaining_time": "6:00:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 762, "total_steps": 1626, "loss": 1.613, "learning_rate": 1.9210533069044334e-05, "epoch": 1.4046082949308756, "percentage": 46.86, "elapsed_time": "5:17:24", "remaining_time": "5:59:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 763, "total_steps": 1626, "loss": 1.5789, "learning_rate": 1.9179607958102356e-05, "epoch": 1.4064516129032258, "percentage": 46.92, "elapsed_time": "5:17:49", "remaining_time": "5:59:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 764, "total_steps": 1626, "loss": 1.5297, "learning_rate": 1.9148663574286757e-05, "epoch": 1.4082949308755761, "percentage": 46.99, "elapsed_time": "5:18:14", "remaining_time": "5:59:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 765, "total_steps": 1626, "loss": 1.5977, "learning_rate": 1.911770006028728e-05, "epoch": 1.4101382488479262, "percentage": 47.05, "elapsed_time": "5:18:39", "remaining_time": "5:58:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 766, "total_steps": 1626, "loss": 1.6296, "learning_rate": 1.908671755888188e-05, "epoch": 1.4119815668202764, "percentage": 47.11, "elapsed_time": "5:19:03", "remaining_time": "5:58:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 767, "total_steps": 1626, "loss": 1.6149, "learning_rate": 1.9055716212936075e-05, "epoch": 1.4138248847926267, "percentage": 47.17, "elapsed_time": "5:19:28", "remaining_time": "5:57:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 768, "total_steps": 1626, "loss": 1.6513, "learning_rate": 1.9024696165402272e-05, "epoch": 1.415668202764977, "percentage": 47.23, "elapsed_time": "5:19:53", "remaining_time": "5:57:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 769, "total_steps": 1626, "loss": 1.5963, "learning_rate": 1.899365755931911e-05, "epoch": 1.4175115207373272, "percentage": 47.29, "elapsed_time": "5:20:18", "remaining_time": "5:56:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 770, "total_steps": 1626, "loss": 1.536, "learning_rate": 1.8962600537810824e-05, "epoch": 1.4193548387096775, "percentage": 47.36, "elapsed_time": "5:20:43", "remaining_time": "5:56:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 771, "total_steps": 1626, "loss": 1.6214, "learning_rate": 1.893152524408653e-05, "epoch": 1.4211981566820278, "percentage": 47.42, "elapsed_time": "5:21:09", "remaining_time": "5:56:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 772, "total_steps": 1626, "loss": 1.6478, "learning_rate": 1.8900431821439644e-05, "epoch": 1.4230414746543778, "percentage": 47.48, "elapsed_time": "5:21:34", "remaining_time": "5:55:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 773, "total_steps": 1626, "loss": 1.5832, "learning_rate": 1.886932041324714e-05, "epoch": 1.424884792626728, "percentage": 47.54, "elapsed_time": "5:21:59", "remaining_time": "5:55:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 774, "total_steps": 1626, "loss": 1.5696, "learning_rate": 1.883819116296895e-05, "epoch": 1.4267281105990783, "percentage": 47.6, "elapsed_time": "5:22:24", "remaining_time": "5:54:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 775, "total_steps": 1626, "loss": 1.606, "learning_rate": 1.880704421414726e-05, "epoch": 1.4285714285714286, "percentage": 47.66, "elapsed_time": "5:22:49", "remaining_time": "5:54:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 776, "total_steps": 1626, "loss": 1.6557, "learning_rate": 1.8775879710405893e-05, "epoch": 1.4304147465437789, "percentage": 47.72, "elapsed_time": "5:23:14", "remaining_time": "5:54:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 777, "total_steps": 1626, "loss": 1.5447, "learning_rate": 1.8744697795449588e-05, "epoch": 1.432258064516129, "percentage": 47.79, "elapsed_time": "5:23:39", "remaining_time": "5:53:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 778, "total_steps": 1626, "loss": 1.5635, "learning_rate": 1.8713498613063403e-05, "epoch": 1.4341013824884792, "percentage": 47.85, "elapsed_time": "5:24:04", "remaining_time": "5:53:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 779, "total_steps": 1626, "loss": 1.6066, "learning_rate": 1.8682282307111988e-05, "epoch": 1.4359447004608294, "percentage": 47.91, "elapsed_time": "5:24:29", "remaining_time": "5:52:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 780, "total_steps": 1626, "loss": 1.5669, "learning_rate": 1.865104902153898e-05, "epoch": 1.4377880184331797, "percentage": 47.97, "elapsed_time": "5:24:54", "remaining_time": "5:52:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 781, "total_steps": 1626, "loss": 1.6059, "learning_rate": 1.8619798900366298e-05, "epoch": 1.43963133640553, "percentage": 48.03, "elapsed_time": "5:25:19", "remaining_time": "5:51:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 782, "total_steps": 1626, "loss": 1.5776, "learning_rate": 1.8588532087693485e-05, "epoch": 1.4414746543778802, "percentage": 48.09, "elapsed_time": "5:25:44", "remaining_time": "5:51:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 783, "total_steps": 1626, "loss": 1.6362, "learning_rate": 1.8557248727697068e-05, "epoch": 1.4433179723502305, "percentage": 48.15, "elapsed_time": "5:26:09", "remaining_time": "5:51:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 784, "total_steps": 1626, "loss": 1.5876, "learning_rate": 1.852594896462987e-05, "epoch": 1.4451612903225808, "percentage": 48.22, "elapsed_time": "5:26:34", "remaining_time": "5:50:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 785, "total_steps": 1626, "loss": 1.5707, "learning_rate": 1.849463294282035e-05, "epoch": 1.4470046082949308, "percentage": 48.28, "elapsed_time": "5:26:58", "remaining_time": "5:50:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 786, "total_steps": 1626, "loss": 1.5538, "learning_rate": 1.8463300806671936e-05, "epoch": 1.448847926267281, "percentage": 48.34, "elapsed_time": "5:27:23", "remaining_time": "5:49:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 787, "total_steps": 1626, "loss": 1.6236, "learning_rate": 1.8431952700662375e-05, "epoch": 1.4506912442396314, "percentage": 48.4, "elapsed_time": "5:27:48", "remaining_time": "5:49:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 788, "total_steps": 1626, "loss": 1.6436, "learning_rate": 1.840058876934303e-05, "epoch": 1.4525345622119816, "percentage": 48.46, "elapsed_time": "5:28:13", "remaining_time": "5:49:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 789, "total_steps": 1626, "loss": 1.49, "learning_rate": 1.8369209157338262e-05, "epoch": 1.4543778801843317, "percentage": 48.52, "elapsed_time": "5:28:38", "remaining_time": "5:48:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 790, "total_steps": 1626, "loss": 1.592, "learning_rate": 1.8337814009344716e-05, "epoch": 1.456221198156682, "percentage": 48.59, "elapsed_time": "5:29:03", "remaining_time": "5:48:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 791, "total_steps": 1626, "loss": 1.5771, "learning_rate": 1.83064034701307e-05, "epoch": 1.4580645161290322, "percentage": 48.65, "elapsed_time": "5:29:29", "remaining_time": "5:47:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 792, "total_steps": 1626, "loss": 1.5751, "learning_rate": 1.8274977684535478e-05, "epoch": 1.4599078341013825, "percentage": 48.71, "elapsed_time": "5:29:54", "remaining_time": "5:47:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 793, "total_steps": 1626, "loss": 1.5485, "learning_rate": 1.824353679746861e-05, "epoch": 1.4617511520737327, "percentage": 48.77, "elapsed_time": "5:30:19", "remaining_time": "5:46:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 794, "total_steps": 1626, "loss": 1.5738, "learning_rate": 1.821208095390931e-05, "epoch": 1.463594470046083, "percentage": 48.83, "elapsed_time": "5:30:44", "remaining_time": "5:46:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 795, "total_steps": 1626, "loss": 1.6364, "learning_rate": 1.8180610298905758e-05, "epoch": 1.4654377880184333, "percentage": 48.89, "elapsed_time": "5:31:09", "remaining_time": "5:46:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 796, "total_steps": 1626, "loss": 1.6, "learning_rate": 1.8149124977574417e-05, "epoch": 1.4672811059907835, "percentage": 48.95, "elapsed_time": "5:31:34", "remaining_time": "5:45:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 797, "total_steps": 1626, "loss": 1.6686, "learning_rate": 1.8117625135099386e-05, "epoch": 1.4691244239631336, "percentage": 49.02, "elapsed_time": "5:31:58", "remaining_time": "5:45:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 798, "total_steps": 1626, "loss": 1.6131, "learning_rate": 1.8086110916731724e-05, "epoch": 1.4709677419354839, "percentage": 49.08, "elapsed_time": "5:32:23", "remaining_time": "5:44:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 799, "total_steps": 1626, "loss": 1.5867, "learning_rate": 1.805458246778878e-05, "epoch": 1.4728110599078341, "percentage": 49.14, "elapsed_time": "5:32:48", "remaining_time": "5:44:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 800, "total_steps": 1626, "loss": 1.5557, "learning_rate": 1.802303993365353e-05, "epoch": 1.4746543778801844, "percentage": 49.2, "elapsed_time": "5:33:13", "remaining_time": "5:44:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 801, "total_steps": 1626, "loss": 1.6668, "learning_rate": 1.7991483459773887e-05, "epoch": 1.4764976958525344, "percentage": 49.26, "elapsed_time": "5:33:48", "remaining_time": "5:43:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 802, "total_steps": 1626, "loss": 1.6072, "learning_rate": 1.795991319166204e-05, "epoch": 1.4783410138248847, "percentage": 49.32, "elapsed_time": "5:34:13", "remaining_time": "5:43:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 803, "total_steps": 1626, "loss": 1.5957, "learning_rate": 1.79283292748938e-05, "epoch": 1.480184331797235, "percentage": 49.38, "elapsed_time": "5:34:38", "remaining_time": "5:42:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 804, "total_steps": 1626, "loss": 1.5923, "learning_rate": 1.7896731855107908e-05, "epoch": 1.4820276497695852, "percentage": 49.45, "elapsed_time": "5:35:03", "remaining_time": "5:42:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 805, "total_steps": 1626, "loss": 1.5798, "learning_rate": 1.7865121078005365e-05, "epoch": 1.4838709677419355, "percentage": 49.51, "elapsed_time": "5:35:28", "remaining_time": "5:42:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 806, "total_steps": 1626, "loss": 1.6172, "learning_rate": 1.7833497089348772e-05, "epoch": 1.4857142857142858, "percentage": 49.57, "elapsed_time": "5:35:53", "remaining_time": "5:41:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 807, "total_steps": 1626, "loss": 1.6114, "learning_rate": 1.780186003496164e-05, "epoch": 1.487557603686636, "percentage": 49.63, "elapsed_time": "5:36:18", "remaining_time": "5:41:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 808, "total_steps": 1626, "loss": 1.5757, "learning_rate": 1.7770210060727748e-05, "epoch": 1.4894009216589863, "percentage": 49.69, "elapsed_time": "5:36:44", "remaining_time": "5:40:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 809, "total_steps": 1626, "loss": 1.6085, "learning_rate": 1.7738547312590426e-05, "epoch": 1.4912442396313363, "percentage": 49.75, "elapsed_time": "5:37:08", "remaining_time": "5:40:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 810, "total_steps": 1626, "loss": 1.6032, "learning_rate": 1.770687193655192e-05, "epoch": 1.4930875576036866, "percentage": 49.82, "elapsed_time": "5:37:33", "remaining_time": "5:40:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 811, "total_steps": 1626, "loss": 1.6087, "learning_rate": 1.7675184078672714e-05, "epoch": 1.4949308755760369, "percentage": 49.88, "elapsed_time": "5:37:58", "remaining_time": "5:39:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 812, "total_steps": 1626, "loss": 1.6077, "learning_rate": 1.7643483885070827e-05, "epoch": 1.4967741935483871, "percentage": 49.94, "elapsed_time": "5:38:23", "remaining_time": "5:39:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 813, "total_steps": 1626, "loss": 1.6598, "learning_rate": 1.7611771501921174e-05, "epoch": 1.4986175115207372, "percentage": 50.0, "elapsed_time": "5:38:48", "remaining_time": "5:38:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 814, "total_steps": 1626, "loss": 1.6591, "learning_rate": 1.7580047075454877e-05, "epoch": 1.5004608294930875, "percentage": 50.06, "elapsed_time": "5:39:13", "remaining_time": "5:38:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 815, "total_steps": 1626, "loss": 1.5475, "learning_rate": 1.7548310751958588e-05, "epoch": 1.5023041474654377, "percentage": 50.12, "elapsed_time": "5:39:38", "remaining_time": "5:37:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 816, "total_steps": 1626, "loss": 1.6011, "learning_rate": 1.751656267777382e-05, "epoch": 1.504147465437788, "percentage": 50.18, "elapsed_time": "5:40:03", "remaining_time": "5:37:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 817, "total_steps": 1626, "loss": 1.6321, "learning_rate": 1.748480299929627e-05, "epoch": 1.5059907834101383, "percentage": 50.25, "elapsed_time": "5:40:28", "remaining_time": "5:37:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 818, "total_steps": 1626, "loss": 1.5943, "learning_rate": 1.7453031862975146e-05, "epoch": 1.5078341013824885, "percentage": 50.31, "elapsed_time": "5:40:52", "remaining_time": "5:36:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 819, "total_steps": 1626, "loss": 1.5845, "learning_rate": 1.742124941531249e-05, "epoch": 1.5096774193548388, "percentage": 50.37, "elapsed_time": "5:41:17", "remaining_time": "5:36:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 820, "total_steps": 1626, "loss": 1.6024, "learning_rate": 1.73894558028625e-05, "epoch": 1.511520737327189, "percentage": 50.43, "elapsed_time": "5:41:42", "remaining_time": "5:35:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 821, "total_steps": 1626, "loss": 1.5477, "learning_rate": 1.7357651172230852e-05, "epoch": 1.5133640552995393, "percentage": 50.49, "elapsed_time": "5:42:07", "remaining_time": "5:35:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 822, "total_steps": 1626, "loss": 1.6505, "learning_rate": 1.7325835670074044e-05, "epoch": 1.5152073732718894, "percentage": 50.55, "elapsed_time": "5:42:32", "remaining_time": "5:35:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 823, "total_steps": 1626, "loss": 1.5482, "learning_rate": 1.729400944309869e-05, "epoch": 1.5170506912442396, "percentage": 50.62, "elapsed_time": "5:42:57", "remaining_time": "5:34:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 824, "total_steps": 1626, "loss": 1.6243, "learning_rate": 1.7262172638060865e-05, "epoch": 1.51889400921659, "percentage": 50.68, "elapsed_time": "5:43:22", "remaining_time": "5:34:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 825, "total_steps": 1626, "loss": 1.5902, "learning_rate": 1.7230325401765415e-05, "epoch": 1.52073732718894, "percentage": 50.74, "elapsed_time": "5:43:47", "remaining_time": "5:33:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 826, "total_steps": 1626, "loss": 1.6411, "learning_rate": 1.7198467881065292e-05, "epoch": 1.5225806451612902, "percentage": 50.8, "elapsed_time": "5:44:12", "remaining_time": "5:33:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 827, "total_steps": 1626, "loss": 1.6384, "learning_rate": 1.7166600222860876e-05, "epoch": 1.5244239631336405, "percentage": 50.86, "elapsed_time": "5:44:36", "remaining_time": "5:32:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 828, "total_steps": 1626, "loss": 1.5762, "learning_rate": 1.713472257409928e-05, "epoch": 1.5262672811059907, "percentage": 50.92, "elapsed_time": "5:45:01", "remaining_time": "5:32:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 829, "total_steps": 1626, "loss": 1.6238, "learning_rate": 1.7102835081773686e-05, "epoch": 1.528110599078341, "percentage": 50.98, "elapsed_time": "5:45:26", "remaining_time": "5:32:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 830, "total_steps": 1626, "loss": 1.6545, "learning_rate": 1.707093789292269e-05, "epoch": 1.5299539170506913, "percentage": 51.05, "elapsed_time": "5:45:51", "remaining_time": "5:31:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 831, "total_steps": 1626, "loss": 1.5693, "learning_rate": 1.7039031154629567e-05, "epoch": 1.5317972350230415, "percentage": 51.11, "elapsed_time": "5:46:16", "remaining_time": "5:31:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 832, "total_steps": 1626, "loss": 1.5427, "learning_rate": 1.700711501402164e-05, "epoch": 1.5336405529953918, "percentage": 51.17, "elapsed_time": "5:46:41", "remaining_time": "5:30:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 833, "total_steps": 1626, "loss": 1.6024, "learning_rate": 1.6975189618269592e-05, "epoch": 1.535483870967742, "percentage": 51.23, "elapsed_time": "5:47:06", "remaining_time": "5:30:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 834, "total_steps": 1626, "loss": 1.5581, "learning_rate": 1.6943255114586788e-05, "epoch": 1.5373271889400921, "percentage": 51.29, "elapsed_time": "5:47:31", "remaining_time": "5:30:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 835, "total_steps": 1626, "loss": 1.5769, "learning_rate": 1.6911311650228574e-05, "epoch": 1.5391705069124424, "percentage": 51.35, "elapsed_time": "5:47:56", "remaining_time": "5:29:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 836, "total_steps": 1626, "loss": 1.5915, "learning_rate": 1.687935937249163e-05, "epoch": 1.5410138248847927, "percentage": 51.41, "elapsed_time": "5:48:21", "remaining_time": "5:29:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 837, "total_steps": 1626, "loss": 1.5609, "learning_rate": 1.6847398428713256e-05, "epoch": 1.5428571428571427, "percentage": 51.48, "elapsed_time": "5:48:46", "remaining_time": "5:28:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 838, "total_steps": 1626, "loss": 1.6441, "learning_rate": 1.681542896627075e-05, "epoch": 1.544700460829493, "percentage": 51.54, "elapsed_time": "5:49:11", "remaining_time": "5:28:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 839, "total_steps": 1626, "loss": 1.6269, "learning_rate": 1.678345113258065e-05, "epoch": 1.5465437788018432, "percentage": 51.6, "elapsed_time": "5:49:36", "remaining_time": "5:27:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 840, "total_steps": 1626, "loss": 1.5342, "learning_rate": 1.6751465075098115e-05, "epoch": 1.5483870967741935, "percentage": 51.66, "elapsed_time": "5:50:01", "remaining_time": "5:27:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 841, "total_steps": 1626, "loss": 1.6072, "learning_rate": 1.6719470941316228e-05, "epoch": 1.5502304147465438, "percentage": 51.72, "elapsed_time": "5:50:25", "remaining_time": "5:27:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 842, "total_steps": 1626, "loss": 1.5937, "learning_rate": 1.668746887876531e-05, "epoch": 1.552073732718894, "percentage": 51.78, "elapsed_time": "5:50:50", "remaining_time": "5:26:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 843, "total_steps": 1626, "loss": 1.5874, "learning_rate": 1.6655459035012237e-05, "epoch": 1.5539170506912443, "percentage": 51.85, "elapsed_time": "5:51:15", "remaining_time": "5:26:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 844, "total_steps": 1626, "loss": 1.5788, "learning_rate": 1.662344155765977e-05, "epoch": 1.5557603686635946, "percentage": 51.91, "elapsed_time": "5:51:40", "remaining_time": "5:25:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 845, "total_steps": 1626, "loss": 1.6263, "learning_rate": 1.659141659434587e-05, "epoch": 1.5576036866359448, "percentage": 51.97, "elapsed_time": "5:52:05", "remaining_time": "5:25:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 846, "total_steps": 1626, "loss": 1.6164, "learning_rate": 1.655938429274302e-05, "epoch": 1.5594470046082949, "percentage": 52.03, "elapsed_time": "5:52:30", "remaining_time": "5:25:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 847, "total_steps": 1626, "loss": 1.5735, "learning_rate": 1.6527344800557534e-05, "epoch": 1.5612903225806452, "percentage": 52.09, "elapsed_time": "5:52:55", "remaining_time": "5:24:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 848, "total_steps": 1626, "loss": 1.6258, "learning_rate": 1.6495298265528883e-05, "epoch": 1.5631336405529954, "percentage": 52.15, "elapsed_time": "5:53:20", "remaining_time": "5:24:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 849, "total_steps": 1626, "loss": 1.6568, "learning_rate": 1.646324483542902e-05, "epoch": 1.5649769585253455, "percentage": 52.21, "elapsed_time": "5:53:45", "remaining_time": "5:23:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 850, "total_steps": 1626, "loss": 1.6342, "learning_rate": 1.64311846580617e-05, "epoch": 1.5668202764976957, "percentage": 52.28, "elapsed_time": "5:54:10", "remaining_time": "5:23:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 851, "total_steps": 1626, "loss": 1.665, "learning_rate": 1.639911788126177e-05, "epoch": 1.568663594470046, "percentage": 52.34, "elapsed_time": "5:54:34", "remaining_time": "5:22:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 852, "total_steps": 1626, "loss": 1.5696, "learning_rate": 1.6367044652894515e-05, "epoch": 1.5705069124423963, "percentage": 52.4, "elapsed_time": "5:54:59", "remaining_time": "5:22:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 853, "total_steps": 1626, "loss": 1.6489, "learning_rate": 1.6334965120854986e-05, "epoch": 1.5723502304147465, "percentage": 52.46, "elapsed_time": "5:55:24", "remaining_time": "5:22:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 854, "total_steps": 1626, "loss": 1.6067, "learning_rate": 1.6302879433067274e-05, "epoch": 1.5741935483870968, "percentage": 52.52, "elapsed_time": "5:55:49", "remaining_time": "5:21:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 855, "total_steps": 1626, "loss": 1.636, "learning_rate": 1.6270787737483877e-05, "epoch": 1.576036866359447, "percentage": 52.58, "elapsed_time": "5:56:14", "remaining_time": "5:21:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 856, "total_steps": 1626, "loss": 1.5383, "learning_rate": 1.623869018208499e-05, "epoch": 1.5778801843317973, "percentage": 52.64, "elapsed_time": "5:56:39", "remaining_time": "5:20:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 857, "total_steps": 1626, "loss": 1.5959, "learning_rate": 1.6206586914877816e-05, "epoch": 1.5797235023041476, "percentage": 52.71, "elapsed_time": "5:57:04", "remaining_time": "5:20:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 858, "total_steps": 1626, "loss": 1.5877, "learning_rate": 1.6174478083895922e-05, "epoch": 1.5815668202764976, "percentage": 52.77, "elapsed_time": "5:57:28", "remaining_time": "5:19:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 859, "total_steps": 1626, "loss": 1.6763, "learning_rate": 1.6142363837198504e-05, "epoch": 1.583410138248848, "percentage": 52.83, "elapsed_time": "5:57:53", "remaining_time": "5:19:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 860, "total_steps": 1626, "loss": 1.6154, "learning_rate": 1.6110244322869746e-05, "epoch": 1.5852534562211982, "percentage": 52.89, "elapsed_time": "5:58:18", "remaining_time": "5:19:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 861, "total_steps": 1626, "loss": 1.5919, "learning_rate": 1.607811968901812e-05, "epoch": 1.5870967741935482, "percentage": 52.95, "elapsed_time": "5:58:43", "remaining_time": "5:18:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 862, "total_steps": 1626, "loss": 1.6255, "learning_rate": 1.6045990083775703e-05, "epoch": 1.5889400921658985, "percentage": 53.01, "elapsed_time": "5:59:08", "remaining_time": "5:18:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 863, "total_steps": 1626, "loss": 1.6017, "learning_rate": 1.6013855655297498e-05, "epoch": 1.5907834101382488, "percentage": 53.08, "elapsed_time": "5:59:33", "remaining_time": "5:17:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 864, "total_steps": 1626, "loss": 1.5115, "learning_rate": 1.5981716551760735e-05, "epoch": 1.592626728110599, "percentage": 53.14, "elapsed_time": "5:59:58", "remaining_time": "5:17:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 865, "total_steps": 1626, "loss": 1.573, "learning_rate": 1.5949572921364226e-05, "epoch": 1.5944700460829493, "percentage": 53.2, "elapsed_time": "6:00:23", "remaining_time": "5:17:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 866, "total_steps": 1626, "loss": 1.6024, "learning_rate": 1.5917424912327644e-05, "epoch": 1.5963133640552996, "percentage": 53.26, "elapsed_time": "6:00:47", "remaining_time": "5:16:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 867, "total_steps": 1626, "loss": 1.6263, "learning_rate": 1.5885272672890842e-05, "epoch": 1.5981566820276498, "percentage": 53.32, "elapsed_time": "6:01:12", "remaining_time": "5:16:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 868, "total_steps": 1626, "loss": 1.6032, "learning_rate": 1.58531163513132e-05, "epoch": 1.6, "percentage": 53.38, "elapsed_time": "6:01:37", "remaining_time": "5:15:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 869, "total_steps": 1626, "loss": 1.6096, "learning_rate": 1.5820956095872914e-05, "epoch": 1.6018433179723504, "percentage": 53.44, "elapsed_time": "6:02:02", "remaining_time": "5:15:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 870, "total_steps": 1626, "loss": 1.5589, "learning_rate": 1.5788792054866314e-05, "epoch": 1.6036866359447006, "percentage": 53.51, "elapsed_time": "6:02:27", "remaining_time": "5:14:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 871, "total_steps": 1626, "loss": 1.5585, "learning_rate": 1.5756624376607193e-05, "epoch": 1.6055299539170507, "percentage": 53.57, "elapsed_time": "6:02:52", "remaining_time": "5:14:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 872, "total_steps": 1626, "loss": 1.578, "learning_rate": 1.5724453209426108e-05, "epoch": 1.607373271889401, "percentage": 53.63, "elapsed_time": "6:03:17", "remaining_time": "5:14:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 873, "total_steps": 1626, "loss": 1.6011, "learning_rate": 1.5692278701669712e-05, "epoch": 1.6092165898617512, "percentage": 53.69, "elapsed_time": "6:03:42", "remaining_time": "5:13:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 874, "total_steps": 1626, "loss": 1.571, "learning_rate": 1.566010100170007e-05, "epoch": 1.6110599078341012, "percentage": 53.75, "elapsed_time": "6:04:07", "remaining_time": "5:13:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 875, "total_steps": 1626, "loss": 1.5961, "learning_rate": 1.5627920257893934e-05, "epoch": 1.6129032258064515, "percentage": 53.81, "elapsed_time": "6:04:32", "remaining_time": "5:12:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 876, "total_steps": 1626, "loss": 1.6229, "learning_rate": 1.5595736618642126e-05, "epoch": 1.6147465437788018, "percentage": 53.87, "elapsed_time": "6:04:57", "remaining_time": "5:12:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 877, "total_steps": 1626, "loss": 1.5469, "learning_rate": 1.5563550232348813e-05, "epoch": 1.616589861751152, "percentage": 53.94, "elapsed_time": "6:05:22", "remaining_time": "5:12:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 878, "total_steps": 1626, "loss": 1.591, "learning_rate": 1.553136124743081e-05, "epoch": 1.6184331797235023, "percentage": 54.0, "elapsed_time": "6:05:46", "remaining_time": "5:11:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 879, "total_steps": 1626, "loss": 1.5349, "learning_rate": 1.5499169812316937e-05, "epoch": 1.6202764976958526, "percentage": 54.06, "elapsed_time": "6:06:11", "remaining_time": "5:11:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 880, "total_steps": 1626, "loss": 1.5831, "learning_rate": 1.5466976075447295e-05, "epoch": 1.6221198156682028, "percentage": 54.12, "elapsed_time": "6:06:36", "remaining_time": "5:10:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 881, "total_steps": 1626, "loss": 1.5148, "learning_rate": 1.5434780185272616e-05, "epoch": 1.6239631336405531, "percentage": 54.18, "elapsed_time": "6:07:01", "remaining_time": "5:10:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 882, "total_steps": 1626, "loss": 1.57, "learning_rate": 1.5402582290253547e-05, "epoch": 1.6258064516129034, "percentage": 54.24, "elapsed_time": "6:07:26", "remaining_time": "5:09:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 883, "total_steps": 1626, "loss": 1.5688, "learning_rate": 1.537038253885998e-05, "epoch": 1.6276497695852534, "percentage": 54.31, "elapsed_time": "6:07:51", "remaining_time": "5:09:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 884, "total_steps": 1626, "loss": 1.5723, "learning_rate": 1.533818107957038e-05, "epoch": 1.6294930875576037, "percentage": 54.37, "elapsed_time": "6:08:16", "remaining_time": "5:09:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 885, "total_steps": 1626, "loss": 1.6315, "learning_rate": 1.5305978060871083e-05, "epoch": 1.631336405529954, "percentage": 54.43, "elapsed_time": "6:08:40", "remaining_time": "5:08:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 886, "total_steps": 1626, "loss": 1.632, "learning_rate": 1.5273773631255602e-05, "epoch": 1.633179723502304, "percentage": 54.49, "elapsed_time": "6:09:05", "remaining_time": "5:08:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 887, "total_steps": 1626, "loss": 1.546, "learning_rate": 1.524156793922396e-05, "epoch": 1.6350230414746543, "percentage": 54.55, "elapsed_time": "6:09:30", "remaining_time": "5:07:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 888, "total_steps": 1626, "loss": 1.574, "learning_rate": 1.5209361133282022e-05, "epoch": 1.6368663594470045, "percentage": 54.61, "elapsed_time": "6:09:55", "remaining_time": "5:07:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 889, "total_steps": 1626, "loss": 1.6679, "learning_rate": 1.517715336194077e-05, "epoch": 1.6387096774193548, "percentage": 54.67, "elapsed_time": "6:10:20", "remaining_time": "5:07:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 890, "total_steps": 1626, "loss": 1.5074, "learning_rate": 1.5144944773715635e-05, "epoch": 1.640552995391705, "percentage": 54.74, "elapsed_time": "6:10:45", "remaining_time": "5:06:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 891, "total_steps": 1626, "loss": 1.5874, "learning_rate": 1.511273551712583e-05, "epoch": 1.6423963133640553, "percentage": 54.8, "elapsed_time": "6:11:11", "remaining_time": "5:06:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 892, "total_steps": 1626, "loss": 1.5366, "learning_rate": 1.5080525740693635e-05, "epoch": 1.6442396313364056, "percentage": 54.86, "elapsed_time": "6:11:35", "remaining_time": "5:05:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 893, "total_steps": 1626, "loss": 1.6149, "learning_rate": 1.5048315592943743e-05, "epoch": 1.6460829493087559, "percentage": 54.92, "elapsed_time": "6:12:00", "remaining_time": "5:05:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 894, "total_steps": 1626, "loss": 1.574, "learning_rate": 1.5016105222402546e-05, "epoch": 1.6479262672811061, "percentage": 54.98, "elapsed_time": "6:12:25", "remaining_time": "5:04:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 895, "total_steps": 1626, "loss": 1.6566, "learning_rate": 1.4983894777597461e-05, "epoch": 1.6497695852534562, "percentage": 55.04, "elapsed_time": "6:12:50", "remaining_time": "5:04:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 896, "total_steps": 1626, "loss": 1.5382, "learning_rate": 1.495168440705626e-05, "epoch": 1.6516129032258065, "percentage": 55.1, "elapsed_time": "6:13:16", "remaining_time": "5:04:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 897, "total_steps": 1626, "loss": 1.5384, "learning_rate": 1.4919474259306362e-05, "epoch": 1.6534562211981567, "percentage": 55.17, "elapsed_time": "6:13:41", "remaining_time": "5:03:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 898, "total_steps": 1626, "loss": 1.5575, "learning_rate": 1.4887264482874173e-05, "epoch": 1.6552995391705068, "percentage": 55.23, "elapsed_time": "6:14:06", "remaining_time": "5:03:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 899, "total_steps": 1626, "loss": 1.5714, "learning_rate": 1.4855055226284367e-05, "epoch": 1.657142857142857, "percentage": 55.29, "elapsed_time": "6:14:30", "remaining_time": "5:02:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 900, "total_steps": 1626, "loss": 1.5896, "learning_rate": 1.4822846638059234e-05, "epoch": 1.6589861751152073, "percentage": 55.35, "elapsed_time": "6:14:55", "remaining_time": "5:02:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 901, "total_steps": 1626, "loss": 1.6283, "learning_rate": 1.4790638866717984e-05, "epoch": 1.6608294930875576, "percentage": 55.41, "elapsed_time": "6:15:20", "remaining_time": "5:02:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 902, "total_steps": 1626, "loss": 1.5921, "learning_rate": 1.4758432060776044e-05, "epoch": 1.6626728110599078, "percentage": 55.47, "elapsed_time": "6:15:45", "remaining_time": "5:01:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 903, "total_steps": 1626, "loss": 1.595, "learning_rate": 1.4726226368744404e-05, "epoch": 1.664516129032258, "percentage": 55.54, "elapsed_time": "6:16:10", "remaining_time": "5:01:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 904, "total_steps": 1626, "loss": 1.589, "learning_rate": 1.4694021939128925e-05, "epoch": 1.6663594470046084, "percentage": 55.6, "elapsed_time": "6:16:35", "remaining_time": "5:00:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 905, "total_steps": 1626, "loss": 1.6052, "learning_rate": 1.466181892042962e-05, "epoch": 1.6682027649769586, "percentage": 55.66, "elapsed_time": "6:17:00", "remaining_time": "5:00:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 906, "total_steps": 1626, "loss": 1.6106, "learning_rate": 1.462961746114002e-05, "epoch": 1.670046082949309, "percentage": 55.72, "elapsed_time": "6:17:24", "remaining_time": "4:59:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 907, "total_steps": 1626, "loss": 1.6252, "learning_rate": 1.4597417709746454e-05, "epoch": 1.671889400921659, "percentage": 55.78, "elapsed_time": "6:17:49", "remaining_time": "4:59:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 908, "total_steps": 1626, "loss": 1.5807, "learning_rate": 1.4565219814727388e-05, "epoch": 1.6737327188940092, "percentage": 55.84, "elapsed_time": "6:18:14", "remaining_time": "4:59:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 909, "total_steps": 1626, "loss": 1.5701, "learning_rate": 1.4533023924552706e-05, "epoch": 1.6755760368663595, "percentage": 55.9, "elapsed_time": "6:18:39", "remaining_time": "4:58:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 910, "total_steps": 1626, "loss": 1.6027, "learning_rate": 1.4500830187683066e-05, "epoch": 1.6774193548387095, "percentage": 55.97, "elapsed_time": "6:19:04", "remaining_time": "4:58:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 911, "total_steps": 1626, "loss": 1.6226, "learning_rate": 1.4468638752569193e-05, "epoch": 1.6792626728110598, "percentage": 56.03, "elapsed_time": "6:19:29", "remaining_time": "4:57:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 912, "total_steps": 1626, "loss": 1.5525, "learning_rate": 1.4436449767651191e-05, "epoch": 1.68110599078341, "percentage": 56.09, "elapsed_time": "6:19:54", "remaining_time": "4:57:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 913, "total_steps": 1626, "loss": 1.5962, "learning_rate": 1.4404263381357873e-05, "epoch": 1.6829493087557603, "percentage": 56.15, "elapsed_time": "6:20:19", "remaining_time": "4:57:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 914, "total_steps": 1626, "loss": 1.5739, "learning_rate": 1.437207974210607e-05, "epoch": 1.6847926267281106, "percentage": 56.21, "elapsed_time": "6:20:44", "remaining_time": "4:56:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 915, "total_steps": 1626, "loss": 1.6128, "learning_rate": 1.4339898998299936e-05, "epoch": 1.6866359447004609, "percentage": 56.27, "elapsed_time": "6:21:08", "remaining_time": "4:56:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 916, "total_steps": 1626, "loss": 1.5863, "learning_rate": 1.4307721298330284e-05, "epoch": 1.6884792626728111, "percentage": 56.33, "elapsed_time": "6:21:33", "remaining_time": "4:55:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 917, "total_steps": 1626, "loss": 1.5724, "learning_rate": 1.4275546790573895e-05, "epoch": 1.6903225806451614, "percentage": 56.4, "elapsed_time": "6:21:58", "remaining_time": "4:55:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 918, "total_steps": 1626, "loss": 1.5473, "learning_rate": 1.4243375623392808e-05, "epoch": 1.6921658986175117, "percentage": 56.46, "elapsed_time": "6:22:23", "remaining_time": "4:54:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 919, "total_steps": 1626, "loss": 1.6016, "learning_rate": 1.4211207945133685e-05, "epoch": 1.6940092165898617, "percentage": 56.52, "elapsed_time": "6:22:48", "remaining_time": "4:54:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 920, "total_steps": 1626, "loss": 1.5635, "learning_rate": 1.417904390412709e-05, "epoch": 1.695852534562212, "percentage": 56.58, "elapsed_time": "6:23:13", "remaining_time": "4:54:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 921, "total_steps": 1626, "loss": 1.5302, "learning_rate": 1.41468836486868e-05, "epoch": 1.6976958525345622, "percentage": 56.64, "elapsed_time": "6:23:38", "remaining_time": "4:53:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 922, "total_steps": 1626, "loss": 1.5837, "learning_rate": 1.411472732710916e-05, "epoch": 1.6995391705069123, "percentage": 56.7, "elapsed_time": "6:24:03", "remaining_time": "4:53:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 923, "total_steps": 1626, "loss": 1.6095, "learning_rate": 1.4082575087672363e-05, "epoch": 1.7013824884792625, "percentage": 56.77, "elapsed_time": "6:24:28", "remaining_time": "4:52:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 924, "total_steps": 1626, "loss": 1.5882, "learning_rate": 1.4050427078635777e-05, "epoch": 1.7032258064516128, "percentage": 56.83, "elapsed_time": "6:24:53", "remaining_time": "4:52:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 925, "total_steps": 1626, "loss": 1.5997, "learning_rate": 1.4018283448239266e-05, "epoch": 1.705069124423963, "percentage": 56.89, "elapsed_time": "6:25:18", "remaining_time": "4:51:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 926, "total_steps": 1626, "loss": 1.5694, "learning_rate": 1.398614434470251e-05, "epoch": 1.7069124423963133, "percentage": 56.95, "elapsed_time": "6:25:42", "remaining_time": "4:51:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 927, "total_steps": 1626, "loss": 1.6191, "learning_rate": 1.3954009916224299e-05, "epoch": 1.7087557603686636, "percentage": 57.01, "elapsed_time": "6:26:07", "remaining_time": "4:51:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 928, "total_steps": 1626, "loss": 1.5921, "learning_rate": 1.3921880310981878e-05, "epoch": 1.7105990783410139, "percentage": 57.07, "elapsed_time": "6:26:32", "remaining_time": "4:50:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 929, "total_steps": 1626, "loss": 1.6333, "learning_rate": 1.3889755677130253e-05, "epoch": 1.7124423963133641, "percentage": 57.13, "elapsed_time": "6:26:57", "remaining_time": "4:50:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 930, "total_steps": 1626, "loss": 1.6297, "learning_rate": 1.3857636162801499e-05, "epoch": 1.7142857142857144, "percentage": 57.2, "elapsed_time": "6:27:22", "remaining_time": "4:49:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 931, "total_steps": 1626, "loss": 1.5691, "learning_rate": 1.3825521916104082e-05, "epoch": 1.7161290322580647, "percentage": 57.26, "elapsed_time": "6:27:47", "remaining_time": "4:49:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 932, "total_steps": 1626, "loss": 1.6432, "learning_rate": 1.3793413085122183e-05, "epoch": 1.7179723502304147, "percentage": 57.32, "elapsed_time": "6:28:12", "remaining_time": "4:49:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 933, "total_steps": 1626, "loss": 1.6167, "learning_rate": 1.3761309817915017e-05, "epoch": 1.719815668202765, "percentage": 57.38, "elapsed_time": "6:28:37", "remaining_time": "4:48:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 934, "total_steps": 1626, "loss": 1.6157, "learning_rate": 1.3729212262516124e-05, "epoch": 1.7216589861751153, "percentage": 57.44, "elapsed_time": "6:29:02", "remaining_time": "4:48:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 935, "total_steps": 1626, "loss": 1.5703, "learning_rate": 1.3697120566932727e-05, "epoch": 1.7235023041474653, "percentage": 57.5, "elapsed_time": "6:29:29", "remaining_time": "4:47:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 936, "total_steps": 1626, "loss": 1.6183, "learning_rate": 1.3665034879145022e-05, "epoch": 1.7253456221198156, "percentage": 57.56, "elapsed_time": "6:29:54", "remaining_time": "4:47:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 937, "total_steps": 1626, "loss": 1.6312, "learning_rate": 1.3632955347105487e-05, "epoch": 1.7271889400921658, "percentage": 57.63, "elapsed_time": "6:30:19", "remaining_time": "4:47:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 938, "total_steps": 1626, "loss": 1.6336, "learning_rate": 1.3600882118738232e-05, "epoch": 1.729032258064516, "percentage": 57.69, "elapsed_time": "6:30:43", "remaining_time": "4:46:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 939, "total_steps": 1626, "loss": 1.6183, "learning_rate": 1.3568815341938303e-05, "epoch": 1.7308755760368664, "percentage": 57.75, "elapsed_time": "6:31:08", "remaining_time": "4:46:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 940, "total_steps": 1626, "loss": 1.6386, "learning_rate": 1.3536755164570977e-05, "epoch": 1.7327188940092166, "percentage": 57.81, "elapsed_time": "6:31:34", "remaining_time": "4:45:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 941, "total_steps": 1626, "loss": 1.5957, "learning_rate": 1.3504701734471117e-05, "epoch": 1.734562211981567, "percentage": 57.87, "elapsed_time": "6:31:59", "remaining_time": "4:45:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 942, "total_steps": 1626, "loss": 1.5977, "learning_rate": 1.3472655199442473e-05, "epoch": 1.7364055299539172, "percentage": 57.93, "elapsed_time": "6:32:23", "remaining_time": "4:44:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 943, "total_steps": 1626, "loss": 1.5497, "learning_rate": 1.3440615707256984e-05, "epoch": 1.7382488479262674, "percentage": 58.0, "elapsed_time": "6:32:48", "remaining_time": "4:44:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 944, "total_steps": 1626, "loss": 1.5602, "learning_rate": 1.340858340565413e-05, "epoch": 1.7400921658986175, "percentage": 58.06, "elapsed_time": "6:33:13", "remaining_time": "4:44:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 945, "total_steps": 1626, "loss": 1.5655, "learning_rate": 1.3376558442340233e-05, "epoch": 1.7419354838709677, "percentage": 58.12, "elapsed_time": "6:33:38", "remaining_time": "4:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 946, "total_steps": 1626, "loss": 1.5792, "learning_rate": 1.3344540964987766e-05, "epoch": 1.743778801843318, "percentage": 58.18, "elapsed_time": "6:34:03", "remaining_time": "4:43:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 947, "total_steps": 1626, "loss": 1.6535, "learning_rate": 1.331253112123469e-05, "epoch": 1.745622119815668, "percentage": 58.24, "elapsed_time": "6:34:28", "remaining_time": "4:42:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 948, "total_steps": 1626, "loss": 1.5837, "learning_rate": 1.3280529058683778e-05, "epoch": 1.7474654377880183, "percentage": 58.3, "elapsed_time": "6:34:53", "remaining_time": "4:42:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 949, "total_steps": 1626, "loss": 1.5671, "learning_rate": 1.3248534924901887e-05, "epoch": 1.7493087557603686, "percentage": 58.36, "elapsed_time": "6:35:17", "remaining_time": "4:41:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 950, "total_steps": 1626, "loss": 1.6098, "learning_rate": 1.3216548867419352e-05, "epoch": 1.7511520737327189, "percentage": 58.43, "elapsed_time": "6:35:42", "remaining_time": "4:41:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 951, "total_steps": 1626, "loss": 1.5503, "learning_rate": 1.3184571033729253e-05, "epoch": 1.7529953917050691, "percentage": 58.49, "elapsed_time": "6:36:07", "remaining_time": "4:41:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 952, "total_steps": 1626, "loss": 1.5739, "learning_rate": 1.3152601571286746e-05, "epoch": 1.7548387096774194, "percentage": 58.55, "elapsed_time": "6:36:32", "remaining_time": "4:40:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 953, "total_steps": 1626, "loss": 1.5847, "learning_rate": 1.3120640627508376e-05, "epoch": 1.7566820276497697, "percentage": 58.61, "elapsed_time": "6:36:57", "remaining_time": "4:40:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 954, "total_steps": 1626, "loss": 1.6444, "learning_rate": 1.3088688349771425e-05, "epoch": 1.75852534562212, "percentage": 58.67, "elapsed_time": "6:37:22", "remaining_time": "4:39:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 955, "total_steps": 1626, "loss": 1.603, "learning_rate": 1.3056744885413216e-05, "epoch": 1.7603686635944702, "percentage": 58.73, "elapsed_time": "6:37:47", "remaining_time": "4:39:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 956, "total_steps": 1626, "loss": 1.6084, "learning_rate": 1.3024810381730409e-05, "epoch": 1.7622119815668202, "percentage": 58.79, "elapsed_time": "6:38:12", "remaining_time": "4:39:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 957, "total_steps": 1626, "loss": 1.6451, "learning_rate": 1.2992884985978363e-05, "epoch": 1.7640552995391705, "percentage": 58.86, "elapsed_time": "6:38:37", "remaining_time": "4:38:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 958, "total_steps": 1626, "loss": 1.5732, "learning_rate": 1.2960968845370443e-05, "epoch": 1.7658986175115208, "percentage": 58.92, "elapsed_time": "6:39:02", "remaining_time": "4:38:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 959, "total_steps": 1626, "loss": 1.5397, "learning_rate": 1.2929062107077315e-05, "epoch": 1.7677419354838708, "percentage": 58.98, "elapsed_time": "6:39:26", "remaining_time": "4:37:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 960, "total_steps": 1626, "loss": 1.552, "learning_rate": 1.2897164918226311e-05, "epoch": 1.769585253456221, "percentage": 59.04, "elapsed_time": "6:39:51", "remaining_time": "4:37:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 961, "total_steps": 1626, "loss": 1.5747, "learning_rate": 1.2865277425900725e-05, "epoch": 1.7714285714285714, "percentage": 59.1, "elapsed_time": "6:40:16", "remaining_time": "4:36:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 962, "total_steps": 1626, "loss": 1.5018, "learning_rate": 1.2833399777139128e-05, "epoch": 1.7732718894009216, "percentage": 59.16, "elapsed_time": "6:40:41", "remaining_time": "4:36:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 963, "total_steps": 1626, "loss": 1.5727, "learning_rate": 1.2801532118934708e-05, "epoch": 1.7751152073732719, "percentage": 59.23, "elapsed_time": "6:41:06", "remaining_time": "4:36:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 964, "total_steps": 1626, "loss": 1.5706, "learning_rate": 1.276967459823459e-05, "epoch": 1.7769585253456222, "percentage": 59.29, "elapsed_time": "6:41:31", "remaining_time": "4:35:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 965, "total_steps": 1626, "loss": 1.6598, "learning_rate": 1.273782736193914e-05, "epoch": 1.7788018433179724, "percentage": 59.35, "elapsed_time": "6:41:56", "remaining_time": "4:35:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 966, "total_steps": 1626, "loss": 1.584, "learning_rate": 1.2705990556901311e-05, "epoch": 1.7806451612903227, "percentage": 59.41, "elapsed_time": "6:42:20", "remaining_time": "4:34:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 967, "total_steps": 1626, "loss": 1.5988, "learning_rate": 1.2674164329925961e-05, "epoch": 1.782488479262673, "percentage": 59.47, "elapsed_time": "6:42:45", "remaining_time": "4:34:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 968, "total_steps": 1626, "loss": 1.5834, "learning_rate": 1.2642348827769152e-05, "epoch": 1.784331797235023, "percentage": 59.53, "elapsed_time": "6:43:10", "remaining_time": "4:34:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 969, "total_steps": 1626, "loss": 1.5643, "learning_rate": 1.2610544197137502e-05, "epoch": 1.7861751152073733, "percentage": 59.59, "elapsed_time": "6:43:35", "remaining_time": "4:33:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 970, "total_steps": 1626, "loss": 1.6284, "learning_rate": 1.257875058468751e-05, "epoch": 1.7880184331797235, "percentage": 59.66, "elapsed_time": "6:44:00", "remaining_time": "4:33:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 971, "total_steps": 1626, "loss": 1.6223, "learning_rate": 1.2546968137024856e-05, "epoch": 1.7898617511520736, "percentage": 59.72, "elapsed_time": "6:44:25", "remaining_time": "4:32:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 972, "total_steps": 1626, "loss": 1.5396, "learning_rate": 1.251519700070373e-05, "epoch": 1.7917050691244238, "percentage": 59.78, "elapsed_time": "6:44:50", "remaining_time": "4:32:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 973, "total_steps": 1626, "loss": 1.5131, "learning_rate": 1.2483437322226178e-05, "epoch": 1.793548387096774, "percentage": 59.84, "elapsed_time": "6:45:14", "remaining_time": "4:31:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 974, "total_steps": 1626, "loss": 1.6107, "learning_rate": 1.2451689248041416e-05, "epoch": 1.7953917050691244, "percentage": 59.9, "elapsed_time": "6:45:39", "remaining_time": "4:31:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 975, "total_steps": 1626, "loss": 1.5571, "learning_rate": 1.2419952924545125e-05, "epoch": 1.7972350230414746, "percentage": 59.96, "elapsed_time": "6:46:04", "remaining_time": "4:31:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 976, "total_steps": 1626, "loss": 1.6405, "learning_rate": 1.2388228498078827e-05, "epoch": 1.799078341013825, "percentage": 60.02, "elapsed_time": "6:46:29", "remaining_time": "4:30:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 977, "total_steps": 1626, "loss": 1.6042, "learning_rate": 1.2356516114929176e-05, "epoch": 1.8009216589861752, "percentage": 60.09, "elapsed_time": "6:46:54", "remaining_time": "4:30:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 978, "total_steps": 1626, "loss": 1.6023, "learning_rate": 1.2324815921327288e-05, "epoch": 1.8027649769585254, "percentage": 60.15, "elapsed_time": "6:47:19", "remaining_time": "4:29:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 979, "total_steps": 1626, "loss": 1.5884, "learning_rate": 1.2293128063448078e-05, "epoch": 1.8046082949308757, "percentage": 60.21, "elapsed_time": "6:47:44", "remaining_time": "4:29:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 980, "total_steps": 1626, "loss": 1.603, "learning_rate": 1.2261452687409576e-05, "epoch": 1.8064516129032258, "percentage": 60.27, "elapsed_time": "6:48:09", "remaining_time": "4:29:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 981, "total_steps": 1626, "loss": 1.5548, "learning_rate": 1.2229789939272253e-05, "epoch": 1.808294930875576, "percentage": 60.33, "elapsed_time": "6:48:33", "remaining_time": "4:28:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 982, "total_steps": 1626, "loss": 1.6292, "learning_rate": 1.2198139965038356e-05, "epoch": 1.8101382488479263, "percentage": 60.39, "elapsed_time": "6:48:59", "remaining_time": "4:28:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 983, "total_steps": 1626, "loss": 1.6037, "learning_rate": 1.2166502910651232e-05, "epoch": 1.8119815668202763, "percentage": 60.46, "elapsed_time": "6:49:24", "remaining_time": "4:27:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 984, "total_steps": 1626, "loss": 1.5707, "learning_rate": 1.2134878921994634e-05, "epoch": 1.8138248847926266, "percentage": 60.52, "elapsed_time": "6:49:49", "remaining_time": "4:27:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 985, "total_steps": 1626, "loss": 1.5857, "learning_rate": 1.210326814489209e-05, "epoch": 1.8156682027649769, "percentage": 60.58, "elapsed_time": "6:50:14", "remaining_time": "4:26:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 986, "total_steps": 1626, "loss": 1.533, "learning_rate": 1.2071670725106203e-05, "epoch": 1.8175115207373271, "percentage": 60.64, "elapsed_time": "6:50:39", "remaining_time": "4:26:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 987, "total_steps": 1626, "loss": 1.5974, "learning_rate": 1.2040086808337965e-05, "epoch": 1.8193548387096774, "percentage": 60.7, "elapsed_time": "6:51:03", "remaining_time": "4:26:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 988, "total_steps": 1626, "loss": 1.5904, "learning_rate": 1.2008516540226115e-05, "epoch": 1.8211981566820277, "percentage": 60.76, "elapsed_time": "6:51:28", "remaining_time": "4:25:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 989, "total_steps": 1626, "loss": 1.5456, "learning_rate": 1.1976960066346474e-05, "epoch": 1.823041474654378, "percentage": 60.82, "elapsed_time": "6:51:53", "remaining_time": "4:25:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 990, "total_steps": 1626, "loss": 1.5873, "learning_rate": 1.194541753221122e-05, "epoch": 1.8248847926267282, "percentage": 60.89, "elapsed_time": "6:52:18", "remaining_time": "4:24:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 991, "total_steps": 1626, "loss": 1.517, "learning_rate": 1.1913889083268278e-05, "epoch": 1.8267281105990785, "percentage": 60.95, "elapsed_time": "6:52:43", "remaining_time": "4:24:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 992, "total_steps": 1626, "loss": 1.5257, "learning_rate": 1.1882374864900616e-05, "epoch": 1.8285714285714287, "percentage": 61.01, "elapsed_time": "6:53:08", "remaining_time": "4:24:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 993, "total_steps": 1626, "loss": 1.5693, "learning_rate": 1.1850875022425587e-05, "epoch": 1.8304147465437788, "percentage": 61.07, "elapsed_time": "6:53:33", "remaining_time": "4:23:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 994, "total_steps": 1626, "loss": 1.5939, "learning_rate": 1.1819389701094241e-05, "epoch": 1.832258064516129, "percentage": 61.13, "elapsed_time": "6:53:58", "remaining_time": "4:23:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 995, "total_steps": 1626, "loss": 1.501, "learning_rate": 1.1787919046090686e-05, "epoch": 1.8341013824884793, "percentage": 61.19, "elapsed_time": "6:54:23", "remaining_time": "4:22:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 996, "total_steps": 1626, "loss": 1.6314, "learning_rate": 1.1756463202531392e-05, "epoch": 1.8359447004608294, "percentage": 61.25, "elapsed_time": "6:54:48", "remaining_time": "4:22:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 997, "total_steps": 1626, "loss": 1.5555, "learning_rate": 1.1725022315464528e-05, "epoch": 1.8377880184331796, "percentage": 61.32, "elapsed_time": "6:55:12", "remaining_time": "4:21:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 998, "total_steps": 1626, "loss": 1.6408, "learning_rate": 1.16935965298693e-05, "epoch": 1.83963133640553, "percentage": 61.38, "elapsed_time": "6:55:37", "remaining_time": "4:21:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 999, "total_steps": 1626, "loss": 1.5627, "learning_rate": 1.1662185990655285e-05, "epoch": 1.8414746543778802, "percentage": 61.44, "elapsed_time": "6:56:02", "remaining_time": "4:21:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1000, "total_steps": 1626, "loss": 1.5737, "learning_rate": 1.1630790842661742e-05, "epoch": 1.8433179723502304, "percentage": 61.5, "elapsed_time": "6:56:27", "remaining_time": "4:20:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1001, "total_steps": 1626, "loss": 1.6198, "learning_rate": 1.1599411230656971e-05, "epoch": 1.8451612903225807, "percentage": 61.56, "elapsed_time": "6:57:02", "remaining_time": "4:20:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1002, "total_steps": 1626, "loss": 1.5751, "learning_rate": 1.1568047299337632e-05, "epoch": 1.847004608294931, "percentage": 61.62, "elapsed_time": "6:57:27", "remaining_time": "4:19:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1003, "total_steps": 1626, "loss": 1.5722, "learning_rate": 1.1536699193328063e-05, "epoch": 1.8488479262672812, "percentage": 61.69, "elapsed_time": "6:57:52", "remaining_time": "4:19:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1004, "total_steps": 1626, "loss": 1.6136, "learning_rate": 1.1505367057179648e-05, "epoch": 1.8506912442396315, "percentage": 61.75, "elapsed_time": "6:58:17", "remaining_time": "4:19:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1005, "total_steps": 1626, "loss": 1.5622, "learning_rate": 1.1474051035370133e-05, "epoch": 1.8525345622119815, "percentage": 61.81, "elapsed_time": "6:58:42", "remaining_time": "4:18:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1006, "total_steps": 1626, "loss": 1.5597, "learning_rate": 1.1442751272302933e-05, "epoch": 1.8543778801843318, "percentage": 61.87, "elapsed_time": "6:59:07", "remaining_time": "4:18:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1007, "total_steps": 1626, "loss": 1.5493, "learning_rate": 1.1411467912306518e-05, "epoch": 1.856221198156682, "percentage": 61.93, "elapsed_time": "6:59:32", "remaining_time": "4:17:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1008, "total_steps": 1626, "loss": 1.5411, "learning_rate": 1.138020109963371e-05, "epoch": 1.8580645161290321, "percentage": 61.99, "elapsed_time": "6:59:57", "remaining_time": "4:17:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1009, "total_steps": 1626, "loss": 1.6137, "learning_rate": 1.1348950978461023e-05, "epoch": 1.8599078341013824, "percentage": 62.05, "elapsed_time": "7:00:22", "remaining_time": "4:17:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1010, "total_steps": 1626, "loss": 1.59, "learning_rate": 1.1317717692888014e-05, "epoch": 1.8617511520737327, "percentage": 62.12, "elapsed_time": "7:00:47", "remaining_time": "4:16:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1011, "total_steps": 1626, "loss": 1.5858, "learning_rate": 1.1286501386936606e-05, "epoch": 1.863594470046083, "percentage": 62.18, "elapsed_time": "7:01:11", "remaining_time": "4:16:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1012, "total_steps": 1626, "loss": 1.5399, "learning_rate": 1.1255302204550414e-05, "epoch": 1.8654377880184332, "percentage": 62.24, "elapsed_time": "7:01:36", "remaining_time": "4:15:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1013, "total_steps": 1626, "loss": 1.5987, "learning_rate": 1.1224120289594111e-05, "epoch": 1.8672811059907835, "percentage": 62.3, "elapsed_time": "7:02:01", "remaining_time": "4:15:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1014, "total_steps": 1626, "loss": 1.6218, "learning_rate": 1.119295578585274e-05, "epoch": 1.8691244239631337, "percentage": 62.36, "elapsed_time": "7:02:26", "remaining_time": "4:14:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1015, "total_steps": 1626, "loss": 1.5151, "learning_rate": 1.1161808837031056e-05, "epoch": 1.870967741935484, "percentage": 62.42, "elapsed_time": "7:02:51", "remaining_time": "4:14:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1016, "total_steps": 1626, "loss": 1.5683, "learning_rate": 1.1130679586752861e-05, "epoch": 1.8728110599078343, "percentage": 62.48, "elapsed_time": "7:03:16", "remaining_time": "4:14:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1017, "total_steps": 1626, "loss": 1.6067, "learning_rate": 1.1099568178560356e-05, "epoch": 1.8746543778801843, "percentage": 62.55, "elapsed_time": "7:03:40", "remaining_time": "4:13:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1018, "total_steps": 1626, "loss": 1.6124, "learning_rate": 1.1068474755913473e-05, "epoch": 1.8764976958525346, "percentage": 62.61, "elapsed_time": "7:04:06", "remaining_time": "4:13:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1019, "total_steps": 1626, "loss": 1.6175, "learning_rate": 1.1037399462189178e-05, "epoch": 1.8783410138248848, "percentage": 62.67, "elapsed_time": "7:04:31", "remaining_time": "4:12:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1020, "total_steps": 1626, "loss": 1.5625, "learning_rate": 1.1006342440680885e-05, "epoch": 1.8801843317972349, "percentage": 62.73, "elapsed_time": "7:04:56", "remaining_time": "4:12:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1021, "total_steps": 1626, "loss": 1.5548, "learning_rate": 1.0975303834597734e-05, "epoch": 1.8820276497695851, "percentage": 62.79, "elapsed_time": "7:05:20", "remaining_time": "4:12:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1022, "total_steps": 1626, "loss": 1.5778, "learning_rate": 1.0944283787063929e-05, "epoch": 1.8838709677419354, "percentage": 62.85, "elapsed_time": "7:05:45", "remaining_time": "4:11:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1023, "total_steps": 1626, "loss": 1.6363, "learning_rate": 1.0913282441118123e-05, "epoch": 1.8857142857142857, "percentage": 62.92, "elapsed_time": "7:06:10", "remaining_time": "4:11:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1024, "total_steps": 1626, "loss": 1.6048, "learning_rate": 1.0882299939712727e-05, "epoch": 1.887557603686636, "percentage": 62.98, "elapsed_time": "7:06:35", "remaining_time": "4:10:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1025, "total_steps": 1626, "loss": 1.6136, "learning_rate": 1.0851336425713248e-05, "epoch": 1.8894009216589862, "percentage": 63.04, "elapsed_time": "7:07:00", "remaining_time": "4:10:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1026, "total_steps": 1626, "loss": 1.5434, "learning_rate": 1.0820392041897647e-05, "epoch": 1.8912442396313365, "percentage": 63.1, "elapsed_time": "7:07:25", "remaining_time": "4:09:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1027, "total_steps": 1626, "loss": 1.6315, "learning_rate": 1.0789466930955672e-05, "epoch": 1.8930875576036867, "percentage": 63.16, "elapsed_time": "7:07:50", "remaining_time": "4:09:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1028, "total_steps": 1626, "loss": 1.5834, "learning_rate": 1.0758561235488196e-05, "epoch": 1.894930875576037, "percentage": 63.22, "elapsed_time": "7:08:15", "remaining_time": "4:09:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1029, "total_steps": 1626, "loss": 1.5912, "learning_rate": 1.0727675098006568e-05, "epoch": 1.896774193548387, "percentage": 63.28, "elapsed_time": "7:08:40", "remaining_time": "4:08:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1030, "total_steps": 1626, "loss": 1.5692, "learning_rate": 1.0696808660931953e-05, "epoch": 1.8986175115207373, "percentage": 63.35, "elapsed_time": "7:09:05", "remaining_time": "4:08:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1031, "total_steps": 1626, "loss": 1.5915, "learning_rate": 1.0665962066594666e-05, "epoch": 1.9004608294930876, "percentage": 63.41, "elapsed_time": "7:09:30", "remaining_time": "4:07:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1032, "total_steps": 1626, "loss": 1.575, "learning_rate": 1.0635135457233533e-05, "epoch": 1.9023041474654376, "percentage": 63.47, "elapsed_time": "7:09:54", "remaining_time": "4:07:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1033, "total_steps": 1626, "loss": 1.5779, "learning_rate": 1.0604328974995229e-05, "epoch": 1.904147465437788, "percentage": 63.53, "elapsed_time": "7:10:20", "remaining_time": "4:07:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1034, "total_steps": 1626, "loss": 1.5594, "learning_rate": 1.0573542761933596e-05, "epoch": 1.9059907834101382, "percentage": 63.59, "elapsed_time": "7:10:45", "remaining_time": "4:06:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1035, "total_steps": 1626, "loss": 1.5894, "learning_rate": 1.054277696000904e-05, "epoch": 1.9078341013824884, "percentage": 63.65, "elapsed_time": "7:11:09", "remaining_time": "4:06:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1036, "total_steps": 1626, "loss": 1.6442, "learning_rate": 1.0512031711087835e-05, "epoch": 1.9096774193548387, "percentage": 63.71, "elapsed_time": "7:11:34", "remaining_time": "4:05:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1037, "total_steps": 1626, "loss": 1.6298, "learning_rate": 1.048130715694149e-05, "epoch": 1.911520737327189, "percentage": 63.78, "elapsed_time": "7:11:59", "remaining_time": "4:05:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1038, "total_steps": 1626, "loss": 1.6536, "learning_rate": 1.0450603439246063e-05, "epoch": 1.9133640552995392, "percentage": 63.84, "elapsed_time": "7:12:25", "remaining_time": "4:04:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1039, "total_steps": 1626, "loss": 1.5612, "learning_rate": 1.0419920699581556e-05, "epoch": 1.9152073732718895, "percentage": 63.9, "elapsed_time": "7:12:49", "remaining_time": "4:04:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1040, "total_steps": 1626, "loss": 1.4936, "learning_rate": 1.038925907943124e-05, "epoch": 1.9170506912442398, "percentage": 63.96, "elapsed_time": "7:13:14", "remaining_time": "4:04:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1041, "total_steps": 1626, "loss": 1.7092, "learning_rate": 1.0358618720180975e-05, "epoch": 1.9188940092165898, "percentage": 64.02, "elapsed_time": "7:13:39", "remaining_time": "4:03:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1042, "total_steps": 1626, "loss": 1.5919, "learning_rate": 1.0327999763118607e-05, "epoch": 1.92073732718894, "percentage": 64.08, "elapsed_time": "7:14:04", "remaining_time": "4:03:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1043, "total_steps": 1626, "loss": 1.5795, "learning_rate": 1.0297402349433286e-05, "epoch": 1.9225806451612903, "percentage": 64.15, "elapsed_time": "7:14:30", "remaining_time": "4:02:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1044, "total_steps": 1626, "loss": 1.5867, "learning_rate": 1.0266826620214813e-05, "epoch": 1.9244239631336404, "percentage": 64.21, "elapsed_time": "7:14:55", "remaining_time": "4:02:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1045, "total_steps": 1626, "loss": 1.5676, "learning_rate": 1.0236272716453012e-05, "epoch": 1.9262672811059907, "percentage": 64.27, "elapsed_time": "7:15:19", "remaining_time": "4:02:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1046, "total_steps": 1626, "loss": 1.6077, "learning_rate": 1.0205740779037065e-05, "epoch": 1.928110599078341, "percentage": 64.33, "elapsed_time": "7:15:44", "remaining_time": "4:01:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1047, "total_steps": 1626, "loss": 1.5721, "learning_rate": 1.0175230948754846e-05, "epoch": 1.9299539170506912, "percentage": 64.39, "elapsed_time": "7:16:09", "remaining_time": "4:01:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1048, "total_steps": 1626, "loss": 1.5684, "learning_rate": 1.014474336629231e-05, "epoch": 1.9317972350230415, "percentage": 64.45, "elapsed_time": "7:16:34", "remaining_time": "4:00:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1049, "total_steps": 1626, "loss": 1.5567, "learning_rate": 1.011427817223282e-05, "epoch": 1.9336405529953917, "percentage": 64.51, "elapsed_time": "7:16:59", "remaining_time": "4:00:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1050, "total_steps": 1626, "loss": 1.6219, "learning_rate": 1.0083835507056483e-05, "epoch": 1.935483870967742, "percentage": 64.58, "elapsed_time": "7:17:24", "remaining_time": "3:59:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1051, "total_steps": 1626, "loss": 1.608, "learning_rate": 1.0053415511139547e-05, "epoch": 1.9373271889400923, "percentage": 64.64, "elapsed_time": "7:17:49", "remaining_time": "3:59:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1052, "total_steps": 1626, "loss": 1.6128, "learning_rate": 1.0023018324753726e-05, "epoch": 1.9391705069124425, "percentage": 64.7, "elapsed_time": "7:18:14", "remaining_time": "3:59:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1053, "total_steps": 1626, "loss": 1.626, "learning_rate": 9.992644088065528e-06, "epoch": 1.9410138248847926, "percentage": 64.76, "elapsed_time": "7:18:39", "remaining_time": "3:58:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1054, "total_steps": 1626, "loss": 1.5861, "learning_rate": 9.96229294113566e-06, "epoch": 1.9428571428571428, "percentage": 64.82, "elapsed_time": "7:19:04", "remaining_time": "3:58:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1055, "total_steps": 1626, "loss": 1.6247, "learning_rate": 9.931965023918369e-06, "epoch": 1.944700460829493, "percentage": 64.88, "elapsed_time": "7:19:28", "remaining_time": "3:57:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1056, "total_steps": 1626, "loss": 1.6123, "learning_rate": 9.901660476260752e-06, "epoch": 1.9465437788018434, "percentage": 64.94, "elapsed_time": "7:19:53", "remaining_time": "3:57:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1057, "total_steps": 1626, "loss": 1.6035, "learning_rate": 9.87137943790217e-06, "epoch": 1.9483870967741934, "percentage": 65.01, "elapsed_time": "7:20:18", "remaining_time": "3:57:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1058, "total_steps": 1626, "loss": 1.5866, "learning_rate": 9.84112204847357e-06, "epoch": 1.9502304147465437, "percentage": 65.07, "elapsed_time": "7:20:43", "remaining_time": "3:56:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1059, "total_steps": 1626, "loss": 1.5301, "learning_rate": 9.810888447496859e-06, "epoch": 1.952073732718894, "percentage": 65.13, "elapsed_time": "7:21:08", "remaining_time": "3:56:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1060, "total_steps": 1626, "loss": 1.5863, "learning_rate": 9.780678774384235e-06, "epoch": 1.9539170506912442, "percentage": 65.19, "elapsed_time": "7:21:33", "remaining_time": "3:55:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1061, "total_steps": 1626, "loss": 1.5563, "learning_rate": 9.750493168437574e-06, "epoch": 1.9557603686635945, "percentage": 65.25, "elapsed_time": "7:21:58", "remaining_time": "3:55:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1062, "total_steps": 1626, "loss": 1.6323, "learning_rate": 9.720331768847773e-06, "epoch": 1.9576036866359448, "percentage": 65.31, "elapsed_time": "7:22:23", "remaining_time": "3:54:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1063, "total_steps": 1626, "loss": 1.5633, "learning_rate": 9.690194714694101e-06, "epoch": 1.959447004608295, "percentage": 65.38, "elapsed_time": "7:22:47", "remaining_time": "3:54:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1064, "total_steps": 1626, "loss": 1.6879, "learning_rate": 9.660082144943571e-06, "epoch": 1.9612903225806453, "percentage": 65.44, "elapsed_time": "7:23:12", "remaining_time": "3:54:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1065, "total_steps": 1626, "loss": 1.5623, "learning_rate": 9.629994198450305e-06, "epoch": 1.9631336405529956, "percentage": 65.5, "elapsed_time": "7:23:37", "remaining_time": "3:53:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1066, "total_steps": 1626, "loss": 1.5979, "learning_rate": 9.599931013954858e-06, "epoch": 1.9649769585253456, "percentage": 65.56, "elapsed_time": "7:24:02", "remaining_time": "3:53:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1067, "total_steps": 1626, "loss": 1.6626, "learning_rate": 9.569892730083631e-06, "epoch": 1.9668202764976959, "percentage": 65.62, "elapsed_time": "7:24:27", "remaining_time": "3:52:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1068, "total_steps": 1626, "loss": 1.572, "learning_rate": 9.53987948534819e-06, "epoch": 1.9686635944700461, "percentage": 65.68, "elapsed_time": "7:24:52", "remaining_time": "3:52:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1069, "total_steps": 1626, "loss": 1.5863, "learning_rate": 9.509891418144635e-06, "epoch": 1.9705069124423962, "percentage": 65.74, "elapsed_time": "7:25:17", "remaining_time": "3:52:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1070, "total_steps": 1626, "loss": 1.667, "learning_rate": 9.479928666752976e-06, "epoch": 1.9723502304147464, "percentage": 65.81, "elapsed_time": "7:25:42", "remaining_time": "3:51:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1071, "total_steps": 1626, "loss": 1.5255, "learning_rate": 9.449991369336502e-06, "epoch": 1.9741935483870967, "percentage": 65.87, "elapsed_time": "7:26:06", "remaining_time": "3:51:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1072, "total_steps": 1626, "loss": 1.6436, "learning_rate": 9.420079663941096e-06, "epoch": 1.976036866359447, "percentage": 65.93, "elapsed_time": "7:26:31", "remaining_time": "3:50:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1073, "total_steps": 1626, "loss": 1.6202, "learning_rate": 9.390193688494657e-06, "epoch": 1.9778801843317972, "percentage": 65.99, "elapsed_time": "7:26:56", "remaining_time": "3:50:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1074, "total_steps": 1626, "loss": 1.5797, "learning_rate": 9.360333580806439e-06, "epoch": 1.9797235023041475, "percentage": 66.05, "elapsed_time": "7:27:21", "remaining_time": "3:49:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1075, "total_steps": 1626, "loss": 1.535, "learning_rate": 9.330499478566404e-06, "epoch": 1.9815668202764978, "percentage": 66.11, "elapsed_time": "7:27:46", "remaining_time": "3:49:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1076, "total_steps": 1626, "loss": 1.5442, "learning_rate": 9.300691519344602e-06, "epoch": 1.983410138248848, "percentage": 66.17, "elapsed_time": "7:28:11", "remaining_time": "3:49:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1077, "total_steps": 1626, "loss": 1.5763, "learning_rate": 9.270909840590541e-06, "epoch": 1.9852534562211983, "percentage": 66.24, "elapsed_time": "7:28:36", "remaining_time": "3:48:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1078, "total_steps": 1626, "loss": 1.5868, "learning_rate": 9.24115457963253e-06, "epoch": 1.9870967741935484, "percentage": 66.3, "elapsed_time": "7:29:01", "remaining_time": "3:48:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1079, "total_steps": 1626, "loss": 1.5895, "learning_rate": 9.211425873677075e-06, "epoch": 1.9889400921658986, "percentage": 66.36, "elapsed_time": "7:29:27", "remaining_time": "3:47:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1080, "total_steps": 1626, "loss": 1.5867, "learning_rate": 9.181723859808225e-06, "epoch": 1.9907834101382489, "percentage": 66.42, "elapsed_time": "7:29:52", "remaining_time": "3:47:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1081, "total_steps": 1626, "loss": 1.6022, "learning_rate": 9.152048674986959e-06, "epoch": 1.992626728110599, "percentage": 66.48, "elapsed_time": "7:30:17", "remaining_time": "3:47:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1082, "total_steps": 1626, "loss": 1.5695, "learning_rate": 9.122400456050524e-06, "epoch": 1.9944700460829492, "percentage": 66.54, "elapsed_time": "7:30:42", "remaining_time": "3:46:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1083, "total_steps": 1626, "loss": 1.5648, "learning_rate": 9.092779339711833e-06, "epoch": 1.9963133640552995, "percentage": 66.61, "elapsed_time": "7:31:07", "remaining_time": "3:46:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1084, "total_steps": 1626, "loss": 1.5823, "learning_rate": 9.063185462558835e-06, "epoch": 1.9981566820276497, "percentage": 66.67, "elapsed_time": "7:31:32", "remaining_time": "3:45:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1085, "total_steps": 1626, "loss": 1.6445, "learning_rate": 9.033618961053842e-06, "epoch": 2.0, "percentage": 66.73, "elapsed_time": "7:31:57", "remaining_time": "3:45:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1086, "total_steps": 1626, "loss": 1.5811, "learning_rate": 9.004079971532972e-06, "epoch": 2.0018433179723503, "percentage": 66.79, "elapsed_time": "7:32:22", "remaining_time": "3:44:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1087, "total_steps": 1626, "loss": 1.6102, "learning_rate": 8.974568630205462e-06, "epoch": 2.0036866359447005, "percentage": 66.85, "elapsed_time": "7:32:47", "remaining_time": "3:44:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1088, "total_steps": 1626, "loss": 1.5613, "learning_rate": 8.945085073153046e-06, "epoch": 2.005529953917051, "percentage": 66.91, "elapsed_time": "7:33:12", "remaining_time": "3:44:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1089, "total_steps": 1626, "loss": 1.6246, "learning_rate": 8.915629436329362e-06, "epoch": 2.007373271889401, "percentage": 66.97, "elapsed_time": "7:33:37", "remaining_time": "3:43:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1090, "total_steps": 1626, "loss": 1.5279, "learning_rate": 8.886201855559294e-06, "epoch": 2.0092165898617513, "percentage": 67.04, "elapsed_time": "7:34:02", "remaining_time": "3:43:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1091, "total_steps": 1626, "loss": 1.5117, "learning_rate": 8.85680246653835e-06, "epoch": 2.0110599078341016, "percentage": 67.1, "elapsed_time": "7:34:27", "remaining_time": "3:42:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1092, "total_steps": 1626, "loss": 1.528, "learning_rate": 8.827431404832048e-06, "epoch": 2.0129032258064514, "percentage": 67.16, "elapsed_time": "7:34:52", "remaining_time": "3:42:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1093, "total_steps": 1626, "loss": 1.5546, "learning_rate": 8.798088805875286e-06, "epoch": 2.0147465437788017, "percentage": 67.22, "elapsed_time": "7:35:16", "remaining_time": "3:42:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1094, "total_steps": 1626, "loss": 1.5741, "learning_rate": 8.768774804971705e-06, "epoch": 2.016589861751152, "percentage": 67.28, "elapsed_time": "7:35:41", "remaining_time": "3:41:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1095, "total_steps": 1626, "loss": 1.5027, "learning_rate": 8.739489537293087e-06, "epoch": 2.0184331797235022, "percentage": 67.34, "elapsed_time": "7:36:06", "remaining_time": "3:41:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1096, "total_steps": 1626, "loss": 1.5391, "learning_rate": 8.710233137878714e-06, "epoch": 2.0202764976958525, "percentage": 67.4, "elapsed_time": "7:36:32", "remaining_time": "3:40:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1097, "total_steps": 1626, "loss": 1.4878, "learning_rate": 8.681005741634755e-06, "epoch": 2.0221198156682028, "percentage": 67.47, "elapsed_time": "7:36:57", "remaining_time": "3:40:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1098, "total_steps": 1626, "loss": 1.6258, "learning_rate": 8.651807483333627e-06, "epoch": 2.023963133640553, "percentage": 67.53, "elapsed_time": "7:37:22", "remaining_time": "3:39:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1099, "total_steps": 1626, "loss": 1.5711, "learning_rate": 8.622638497613415e-06, "epoch": 2.0258064516129033, "percentage": 67.59, "elapsed_time": "7:37:46", "remaining_time": "3:39:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1100, "total_steps": 1626, "loss": 1.5338, "learning_rate": 8.593498918977196e-06, "epoch": 2.0276497695852536, "percentage": 67.65, "elapsed_time": "7:38:11", "remaining_time": "3:39:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1101, "total_steps": 1626, "loss": 1.5781, "learning_rate": 8.564388881792456e-06, "epoch": 2.029493087557604, "percentage": 67.71, "elapsed_time": "7:38:36", "remaining_time": "3:38:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1102, "total_steps": 1626, "loss": 1.4911, "learning_rate": 8.53530852029047e-06, "epoch": 2.031336405529954, "percentage": 67.77, "elapsed_time": "7:39:01", "remaining_time": "3:38:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1103, "total_steps": 1626, "loss": 1.5759, "learning_rate": 8.506257968565659e-06, "epoch": 2.0331797235023044, "percentage": 67.84, "elapsed_time": "7:39:26", "remaining_time": "3:37:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1104, "total_steps": 1626, "loss": 1.5557, "learning_rate": 8.477237360574984e-06, "epoch": 2.035023041474654, "percentage": 67.9, "elapsed_time": "7:39:51", "remaining_time": "3:37:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1105, "total_steps": 1626, "loss": 1.5667, "learning_rate": 8.448246830137355e-06, "epoch": 2.0368663594470044, "percentage": 67.96, "elapsed_time": "7:40:16", "remaining_time": "3:37:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1106, "total_steps": 1626, "loss": 1.5236, "learning_rate": 8.419286510932961e-06, "epoch": 2.0387096774193547, "percentage": 68.02, "elapsed_time": "7:40:40", "remaining_time": "3:36:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1107, "total_steps": 1626, "loss": 1.5315, "learning_rate": 8.390356536502688e-06, "epoch": 2.040552995391705, "percentage": 68.08, "elapsed_time": "7:41:05", "remaining_time": "3:36:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1108, "total_steps": 1626, "loss": 1.5666, "learning_rate": 8.361457040247518e-06, "epoch": 2.0423963133640552, "percentage": 68.14, "elapsed_time": "7:41:30", "remaining_time": "3:35:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1109, "total_steps": 1626, "loss": 1.5744, "learning_rate": 8.332588155427869e-06, "epoch": 2.0442396313364055, "percentage": 68.2, "elapsed_time": "7:41:55", "remaining_time": "3:35:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1110, "total_steps": 1626, "loss": 1.6014, "learning_rate": 8.303750015163008e-06, "epoch": 2.046082949308756, "percentage": 68.27, "elapsed_time": "7:42:20", "remaining_time": "3:34:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1111, "total_steps": 1626, "loss": 1.5749, "learning_rate": 8.274942752430449e-06, "epoch": 2.047926267281106, "percentage": 68.33, "elapsed_time": "7:42:45", "remaining_time": "3:34:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1112, "total_steps": 1626, "loss": 1.5823, "learning_rate": 8.24616650006531e-06, "epoch": 2.0497695852534563, "percentage": 68.39, "elapsed_time": "7:43:10", "remaining_time": "3:34:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1113, "total_steps": 1626, "loss": 1.5604, "learning_rate": 8.217421390759717e-06, "epoch": 2.0516129032258066, "percentage": 68.45, "elapsed_time": "7:43:35", "remaining_time": "3:33:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1114, "total_steps": 1626, "loss": 1.5849, "learning_rate": 8.188707557062191e-06, "epoch": 2.053456221198157, "percentage": 68.51, "elapsed_time": "7:44:00", "remaining_time": "3:33:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1115, "total_steps": 1626, "loss": 1.6185, "learning_rate": 8.160025131377044e-06, "epoch": 2.055299539170507, "percentage": 68.57, "elapsed_time": "7:44:25", "remaining_time": "3:32:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1116, "total_steps": 1626, "loss": 1.5763, "learning_rate": 8.131374245963753e-06, "epoch": 2.057142857142857, "percentage": 68.63, "elapsed_time": "7:44:50", "remaining_time": "3:32:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1117, "total_steps": 1626, "loss": 1.5421, "learning_rate": 8.102755032936346e-06, "epoch": 2.058986175115207, "percentage": 68.7, "elapsed_time": "7:45:14", "remaining_time": "3:32:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1118, "total_steps": 1626, "loss": 1.5398, "learning_rate": 8.074167624262834e-06, "epoch": 2.0608294930875575, "percentage": 68.76, "elapsed_time": "7:45:39", "remaining_time": "3:31:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1119, "total_steps": 1626, "loss": 1.5596, "learning_rate": 8.045612151764546e-06, "epoch": 2.0626728110599077, "percentage": 68.82, "elapsed_time": "7:46:04", "remaining_time": "3:31:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1120, "total_steps": 1626, "loss": 1.5281, "learning_rate": 8.017088747115554e-06, "epoch": 2.064516129032258, "percentage": 68.88, "elapsed_time": "7:46:29", "remaining_time": "3:30:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1121, "total_steps": 1626, "loss": 1.5766, "learning_rate": 7.98859754184207e-06, "epoch": 2.0663594470046083, "percentage": 68.94, "elapsed_time": "7:46:54", "remaining_time": "3:30:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1122, "total_steps": 1626, "loss": 1.6355, "learning_rate": 7.960138667321822e-06, "epoch": 2.0682027649769585, "percentage": 69.0, "elapsed_time": "7:47:19", "remaining_time": "3:29:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1123, "total_steps": 1626, "loss": 1.6038, "learning_rate": 7.931712254783445e-06, "epoch": 2.070046082949309, "percentage": 69.07, "elapsed_time": "7:47:44", "remaining_time": "3:29:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1124, "total_steps": 1626, "loss": 1.5439, "learning_rate": 7.903318435305914e-06, "epoch": 2.071889400921659, "percentage": 69.13, "elapsed_time": "7:48:09", "remaining_time": "3:29:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1125, "total_steps": 1626, "loss": 1.5385, "learning_rate": 7.874957339817886e-06, "epoch": 2.0737327188940093, "percentage": 69.19, "elapsed_time": "7:48:33", "remaining_time": "3:28:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1126, "total_steps": 1626, "loss": 1.5975, "learning_rate": 7.846629099097127e-06, "epoch": 2.0755760368663596, "percentage": 69.25, "elapsed_time": "7:48:58", "remaining_time": "3:28:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1127, "total_steps": 1626, "loss": 1.5435, "learning_rate": 7.818333843769917e-06, "epoch": 2.07741935483871, "percentage": 69.31, "elapsed_time": "7:49:23", "remaining_time": "3:27:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1128, "total_steps": 1626, "loss": 1.4977, "learning_rate": 7.790071704310422e-06, "epoch": 2.0792626728110597, "percentage": 69.37, "elapsed_time": "7:49:48", "remaining_time": "3:27:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1129, "total_steps": 1626, "loss": 1.5472, "learning_rate": 7.76184281104011e-06, "epoch": 2.08110599078341, "percentage": 69.43, "elapsed_time": "7:50:13", "remaining_time": "3:26:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1130, "total_steps": 1626, "loss": 1.5396, "learning_rate": 7.73364729412714e-06, "epoch": 2.0829493087557602, "percentage": 69.5, "elapsed_time": "7:50:38", "remaining_time": "3:26:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1131, "total_steps": 1626, "loss": 1.5537, "learning_rate": 7.70548528358578e-06, "epoch": 2.0847926267281105, "percentage": 69.56, "elapsed_time": "7:51:03", "remaining_time": "3:26:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1132, "total_steps": 1626, "loss": 1.5174, "learning_rate": 7.677356909275784e-06, "epoch": 2.0866359447004608, "percentage": 69.62, "elapsed_time": "7:51:28", "remaining_time": "3:25:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1133, "total_steps": 1626, "loss": 1.5525, "learning_rate": 7.649262300901796e-06, "epoch": 2.088479262672811, "percentage": 69.68, "elapsed_time": "7:51:52", "remaining_time": "3:25:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1134, "total_steps": 1626, "loss": 1.5841, "learning_rate": 7.621201588012786e-06, "epoch": 2.0903225806451613, "percentage": 69.74, "elapsed_time": "7:52:17", "remaining_time": "3:24:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1135, "total_steps": 1626, "loss": 1.5042, "learning_rate": 7.593174900001398e-06, "epoch": 2.0921658986175116, "percentage": 69.8, "elapsed_time": "7:52:42", "remaining_time": "3:24:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1136, "total_steps": 1626, "loss": 1.5968, "learning_rate": 7.565182366103391e-06, "epoch": 2.094009216589862, "percentage": 69.86, "elapsed_time": "7:53:07", "remaining_time": "3:24:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1137, "total_steps": 1626, "loss": 1.5788, "learning_rate": 7.537224115397048e-06, "epoch": 2.095852534562212, "percentage": 69.93, "elapsed_time": "7:53:32", "remaining_time": "3:23:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1138, "total_steps": 1626, "loss": 1.6213, "learning_rate": 7.5093002768025485e-06, "epoch": 2.0976958525345624, "percentage": 69.99, "elapsed_time": "7:53:57", "remaining_time": "3:23:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1139, "total_steps": 1626, "loss": 1.5571, "learning_rate": 7.481410979081389e-06, "epoch": 2.0995391705069126, "percentage": 70.05, "elapsed_time": "7:54:22", "remaining_time": "3:22:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1140, "total_steps": 1626, "loss": 1.5635, "learning_rate": 7.453556350835821e-06, "epoch": 2.1013824884792625, "percentage": 70.11, "elapsed_time": "7:54:47", "remaining_time": "3:22:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1141, "total_steps": 1626, "loss": 1.5867, "learning_rate": 7.425736520508185e-06, "epoch": 2.1032258064516127, "percentage": 70.17, "elapsed_time": "7:55:12", "remaining_time": "3:21:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1142, "total_steps": 1626, "loss": 1.4974, "learning_rate": 7.397951616380401e-06, "epoch": 2.105069124423963, "percentage": 70.23, "elapsed_time": "7:55:36", "remaining_time": "3:21:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1143, "total_steps": 1626, "loss": 1.5638, "learning_rate": 7.370201766573325e-06, "epoch": 2.1069124423963133, "percentage": 70.3, "elapsed_time": "7:56:01", "remaining_time": "3:21:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1144, "total_steps": 1626, "loss": 1.5507, "learning_rate": 7.342487099046169e-06, "epoch": 2.1087557603686635, "percentage": 70.36, "elapsed_time": "7:56:26", "remaining_time": "3:20:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1145, "total_steps": 1626, "loss": 1.5888, "learning_rate": 7.31480774159591e-06, "epoch": 2.110599078341014, "percentage": 70.42, "elapsed_time": "7:56:51", "remaining_time": "3:20:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1146, "total_steps": 1626, "loss": 1.5648, "learning_rate": 7.287163821856719e-06, "epoch": 2.112442396313364, "percentage": 70.48, "elapsed_time": "7:57:16", "remaining_time": "3:19:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1147, "total_steps": 1626, "loss": 1.6247, "learning_rate": 7.259555467299342e-06, "epoch": 2.1142857142857143, "percentage": 70.54, "elapsed_time": "7:57:41", "remaining_time": "3:19:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1148, "total_steps": 1626, "loss": 1.5349, "learning_rate": 7.231982805230538e-06, "epoch": 2.1161290322580646, "percentage": 70.6, "elapsed_time": "7:58:06", "remaining_time": "3:19:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1149, "total_steps": 1626, "loss": 1.5549, "learning_rate": 7.204445962792471e-06, "epoch": 2.117972350230415, "percentage": 70.66, "elapsed_time": "7:58:31", "remaining_time": "3:18:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1150, "total_steps": 1626, "loss": 1.5853, "learning_rate": 7.176945066962152e-06, "epoch": 2.119815668202765, "percentage": 70.73, "elapsed_time": "7:58:55", "remaining_time": "3:18:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1151, "total_steps": 1626, "loss": 1.5234, "learning_rate": 7.149480244550822e-06, "epoch": 2.1216589861751154, "percentage": 70.79, "elapsed_time": "7:59:20", "remaining_time": "3:17:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1152, "total_steps": 1626, "loss": 1.5817, "learning_rate": 7.12205162220338e-06, "epoch": 2.1235023041474657, "percentage": 70.85, "elapsed_time": "7:59:45", "remaining_time": "3:17:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1153, "total_steps": 1626, "loss": 1.5104, "learning_rate": 7.094659326397818e-06, "epoch": 2.1253456221198155, "percentage": 70.91, "elapsed_time": "8:00:10", "remaining_time": "3:16:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1154, "total_steps": 1626, "loss": 1.5133, "learning_rate": 7.067303483444603e-06, "epoch": 2.1271889400921657, "percentage": 70.97, "elapsed_time": "8:00:35", "remaining_time": "3:16:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1155, "total_steps": 1626, "loss": 1.5857, "learning_rate": 7.039984219486109e-06, "epoch": 2.129032258064516, "percentage": 71.03, "elapsed_time": "8:01:00", "remaining_time": "3:16:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1156, "total_steps": 1626, "loss": 1.5688, "learning_rate": 7.012701660496059e-06, "epoch": 2.1308755760368663, "percentage": 71.09, "elapsed_time": "8:01:25", "remaining_time": "3:15:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1157, "total_steps": 1626, "loss": 1.5684, "learning_rate": 6.985455932278904e-06, "epoch": 2.1327188940092165, "percentage": 71.16, "elapsed_time": "8:01:50", "remaining_time": "3:15:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1158, "total_steps": 1626, "loss": 1.595, "learning_rate": 6.958247160469266e-06, "epoch": 2.134562211981567, "percentage": 71.22, "elapsed_time": "8:02:15", "remaining_time": "3:14:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1159, "total_steps": 1626, "loss": 1.5595, "learning_rate": 6.931075470531371e-06, "epoch": 2.136405529953917, "percentage": 71.28, "elapsed_time": "8:02:39", "remaining_time": "3:14:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1160, "total_steps": 1626, "loss": 1.5561, "learning_rate": 6.9039409877584195e-06, "epoch": 2.1382488479262673, "percentage": 71.34, "elapsed_time": "8:03:04", "remaining_time": "3:14:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1161, "total_steps": 1626, "loss": 1.5711, "learning_rate": 6.876843837272075e-06, "epoch": 2.1400921658986176, "percentage": 71.4, "elapsed_time": "8:03:29", "remaining_time": "3:13:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1162, "total_steps": 1626, "loss": 1.572, "learning_rate": 6.849784144021859e-06, "epoch": 2.141935483870968, "percentage": 71.46, "elapsed_time": "8:03:55", "remaining_time": "3:13:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1163, "total_steps": 1626, "loss": 1.4994, "learning_rate": 6.82276203278453e-06, "epoch": 2.143778801843318, "percentage": 71.53, "elapsed_time": "8:04:20", "remaining_time": "3:12:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1164, "total_steps": 1626, "loss": 1.5317, "learning_rate": 6.795777628163599e-06, "epoch": 2.145622119815668, "percentage": 71.59, "elapsed_time": "8:04:45", "remaining_time": "3:12:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1165, "total_steps": 1626, "loss": 1.568, "learning_rate": 6.7688310545886715e-06, "epoch": 2.1474654377880182, "percentage": 71.65, "elapsed_time": "8:05:10", "remaining_time": "3:11:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1166, "total_steps": 1626, "loss": 1.4829, "learning_rate": 6.741922436314929e-06, "epoch": 2.1493087557603685, "percentage": 71.71, "elapsed_time": "8:05:36", "remaining_time": "3:11:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1167, "total_steps": 1626, "loss": 1.5274, "learning_rate": 6.715051897422523e-06, "epoch": 2.1511520737327188, "percentage": 71.77, "elapsed_time": "8:06:01", "remaining_time": "3:11:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1168, "total_steps": 1626, "loss": 1.556, "learning_rate": 6.688219561816008e-06, "epoch": 2.152995391705069, "percentage": 71.83, "elapsed_time": "8:06:26", "remaining_time": "3:10:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1169, "total_steps": 1626, "loss": 1.5923, "learning_rate": 6.661425553223799e-06, "epoch": 2.1548387096774193, "percentage": 71.89, "elapsed_time": "8:06:51", "remaining_time": "3:10:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1170, "total_steps": 1626, "loss": 1.5599, "learning_rate": 6.634669995197561e-06, "epoch": 2.1566820276497696, "percentage": 71.96, "elapsed_time": "8:07:16", "remaining_time": "3:09:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1171, "total_steps": 1626, "loss": 1.6186, "learning_rate": 6.607953011111655e-06, "epoch": 2.15852534562212, "percentage": 72.02, "elapsed_time": "8:07:41", "remaining_time": "3:09:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1172, "total_steps": 1626, "loss": 1.5157, "learning_rate": 6.581274724162587e-06, "epoch": 2.16036866359447, "percentage": 72.08, "elapsed_time": "8:08:06", "remaining_time": "3:09:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1173, "total_steps": 1626, "loss": 1.5565, "learning_rate": 6.554635257368411e-06, "epoch": 2.1622119815668204, "percentage": 72.14, "elapsed_time": "8:08:31", "remaining_time": "3:08:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1174, "total_steps": 1626, "loss": 1.599, "learning_rate": 6.528034733568174e-06, "epoch": 2.1640552995391706, "percentage": 72.2, "elapsed_time": "8:08:56", "remaining_time": "3:08:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1175, "total_steps": 1626, "loss": 1.5542, "learning_rate": 6.50147327542137e-06, "epoch": 2.165898617511521, "percentage": 72.26, "elapsed_time": "8:09:21", "remaining_time": "3:07:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1176, "total_steps": 1626, "loss": 1.5592, "learning_rate": 6.474951005407317e-06, "epoch": 2.167741935483871, "percentage": 72.32, "elapsed_time": "8:09:46", "remaining_time": "3:07:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1177, "total_steps": 1626, "loss": 1.526, "learning_rate": 6.448468045824664e-06, "epoch": 2.169585253456221, "percentage": 72.39, "elapsed_time": "8:10:11", "remaining_time": "3:06:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1178, "total_steps": 1626, "loss": 1.6018, "learning_rate": 6.4220245187907915e-06, "epoch": 2.1714285714285713, "percentage": 72.45, "elapsed_time": "8:10:36", "remaining_time": "3:06:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1179, "total_steps": 1626, "loss": 1.6524, "learning_rate": 6.395620546241221e-06, "epoch": 2.1732718894009215, "percentage": 72.51, "elapsed_time": "8:11:01", "remaining_time": "3:06:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1180, "total_steps": 1626, "loss": 1.5206, "learning_rate": 6.369256249929112e-06, "epoch": 2.175115207373272, "percentage": 72.57, "elapsed_time": "8:11:26", "remaining_time": "3:05:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1181, "total_steps": 1626, "loss": 1.5366, "learning_rate": 6.342931751424656e-06, "epoch": 2.176958525345622, "percentage": 72.63, "elapsed_time": "8:11:51", "remaining_time": "3:05:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1182, "total_steps": 1626, "loss": 1.5498, "learning_rate": 6.316647172114529e-06, "epoch": 2.1788018433179723, "percentage": 72.69, "elapsed_time": "8:12:16", "remaining_time": "3:04:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1183, "total_steps": 1626, "loss": 1.5518, "learning_rate": 6.2904026332013445e-06, "epoch": 2.1806451612903226, "percentage": 72.76, "elapsed_time": "8:12:41", "remaining_time": "3:04:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1184, "total_steps": 1626, "loss": 1.5568, "learning_rate": 6.264198255703071e-06, "epoch": 2.182488479262673, "percentage": 72.82, "elapsed_time": "8:13:06", "remaining_time": "3:04:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1185, "total_steps": 1626, "loss": 1.5876, "learning_rate": 6.238034160452486e-06, "epoch": 2.184331797235023, "percentage": 72.88, "elapsed_time": "8:13:31", "remaining_time": "3:03:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1186, "total_steps": 1626, "loss": 1.5558, "learning_rate": 6.211910468096631e-06, "epoch": 2.1861751152073734, "percentage": 72.94, "elapsed_time": "8:13:56", "remaining_time": "3:03:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1187, "total_steps": 1626, "loss": 1.5382, "learning_rate": 6.185827299096226e-06, "epoch": 2.1880184331797237, "percentage": 73.0, "elapsed_time": "8:14:21", "remaining_time": "3:02:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1188, "total_steps": 1626, "loss": 1.5488, "learning_rate": 6.1597847737251504e-06, "epoch": 2.189861751152074, "percentage": 73.06, "elapsed_time": "8:14:45", "remaining_time": "3:02:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1189, "total_steps": 1626, "loss": 1.5798, "learning_rate": 6.133783012069853e-06, "epoch": 2.191705069124424, "percentage": 73.12, "elapsed_time": "8:15:10", "remaining_time": "3:01:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1190, "total_steps": 1626, "loss": 1.6048, "learning_rate": 6.1078221340288155e-06, "epoch": 2.193548387096774, "percentage": 73.19, "elapsed_time": "8:15:35", "remaining_time": "3:01:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1191, "total_steps": 1626, "loss": 1.6293, "learning_rate": 6.081902259312013e-06, "epoch": 2.1953917050691243, "percentage": 73.25, "elapsed_time": "8:16:00", "remaining_time": "3:01:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1192, "total_steps": 1626, "loss": 1.5452, "learning_rate": 6.05602350744033e-06, "epoch": 2.1972350230414746, "percentage": 73.31, "elapsed_time": "8:16:25", "remaining_time": "3:00:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1193, "total_steps": 1626, "loss": 1.5874, "learning_rate": 6.030185997745031e-06, "epoch": 2.199078341013825, "percentage": 73.37, "elapsed_time": "8:16:50", "remaining_time": "3:00:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1194, "total_steps": 1626, "loss": 1.5839, "learning_rate": 6.004389849367223e-06, "epoch": 2.200921658986175, "percentage": 73.43, "elapsed_time": "8:17:15", "remaining_time": "2:59:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1195, "total_steps": 1626, "loss": 1.5874, "learning_rate": 5.978635181257254e-06, "epoch": 2.2027649769585254, "percentage": 73.49, "elapsed_time": "8:17:40", "remaining_time": "2:59:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1196, "total_steps": 1626, "loss": 1.5515, "learning_rate": 5.952922112174231e-06, "epoch": 2.2046082949308756, "percentage": 73.55, "elapsed_time": "8:18:04", "remaining_time": "2:59:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1197, "total_steps": 1626, "loss": 1.573, "learning_rate": 5.927250760685441e-06, "epoch": 2.206451612903226, "percentage": 73.62, "elapsed_time": "8:18:29", "remaining_time": "2:58:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1198, "total_steps": 1626, "loss": 1.5727, "learning_rate": 5.901621245165772e-06, "epoch": 2.208294930875576, "percentage": 73.68, "elapsed_time": "8:18:54", "remaining_time": "2:58:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1199, "total_steps": 1626, "loss": 1.5166, "learning_rate": 5.8760336837972355e-06, "epoch": 2.2101382488479264, "percentage": 73.74, "elapsed_time": "8:19:19", "remaining_time": "2:57:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1200, "total_steps": 1626, "loss": 1.4895, "learning_rate": 5.850488194568366e-06, "epoch": 2.2119815668202767, "percentage": 73.8, "elapsed_time": "8:19:44", "remaining_time": "2:57:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1201, "total_steps": 1626, "loss": 1.6212, "learning_rate": 5.824984895273697e-06, "epoch": 2.2138248847926265, "percentage": 73.86, "elapsed_time": "8:20:18", "remaining_time": "2:57:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1202, "total_steps": 1626, "loss": 1.5795, "learning_rate": 5.799523903513228e-06, "epoch": 2.215668202764977, "percentage": 73.92, "elapsed_time": "8:20:43", "remaining_time": "2:56:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1203, "total_steps": 1626, "loss": 1.5421, "learning_rate": 5.774105336691861e-06, "epoch": 2.217511520737327, "percentage": 73.99, "elapsed_time": "8:21:08", "remaining_time": "2:56:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1204, "total_steps": 1626, "loss": 1.5533, "learning_rate": 5.748729312018869e-06, "epoch": 2.2193548387096773, "percentage": 74.05, "elapsed_time": "8:21:33", "remaining_time": "2:55:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1205, "total_steps": 1626, "loss": 1.5814, "learning_rate": 5.723395946507367e-06, "epoch": 2.2211981566820276, "percentage": 74.11, "elapsed_time": "8:21:58", "remaining_time": "2:55:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1206, "total_steps": 1626, "loss": 1.5671, "learning_rate": 5.6981053569737525e-06, "epoch": 2.223041474654378, "percentage": 74.17, "elapsed_time": "8:22:23", "remaining_time": "2:54:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1207, "total_steps": 1626, "loss": 1.6061, "learning_rate": 5.67285766003717e-06, "epoch": 2.224884792626728, "percentage": 74.23, "elapsed_time": "8:22:48", "remaining_time": "2:54:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1208, "total_steps": 1626, "loss": 1.6042, "learning_rate": 5.647652972118998e-06, "epoch": 2.2267281105990784, "percentage": 74.29, "elapsed_time": "8:23:13", "remaining_time": "2:54:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1209, "total_steps": 1626, "loss": 1.4541, "learning_rate": 5.622491409442272e-06, "epoch": 2.2285714285714286, "percentage": 74.35, "elapsed_time": "8:23:37", "remaining_time": "2:53:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1210, "total_steps": 1626, "loss": 1.6308, "learning_rate": 5.597373088031193e-06, "epoch": 2.230414746543779, "percentage": 74.42, "elapsed_time": "8:24:02", "remaining_time": "2:53:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1211, "total_steps": 1626, "loss": 1.5414, "learning_rate": 5.572298123710536e-06, "epoch": 2.232258064516129, "percentage": 74.48, "elapsed_time": "8:24:27", "remaining_time": "2:52:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1212, "total_steps": 1626, "loss": 1.61, "learning_rate": 5.54726663210518e-06, "epoch": 2.2341013824884794, "percentage": 74.54, "elapsed_time": "8:24:52", "remaining_time": "2:52:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1213, "total_steps": 1626, "loss": 1.5563, "learning_rate": 5.522278728639544e-06, "epoch": 2.2359447004608297, "percentage": 74.6, "elapsed_time": "8:25:17", "remaining_time": "2:52:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1214, "total_steps": 1626, "loss": 1.4964, "learning_rate": 5.497334528537022e-06, "epoch": 2.2377880184331795, "percentage": 74.66, "elapsed_time": "8:25:42", "remaining_time": "2:51:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1215, "total_steps": 1626, "loss": 1.5857, "learning_rate": 5.472434146819522e-06, "epoch": 2.23963133640553, "percentage": 74.72, "elapsed_time": "8:26:06", "remaining_time": "2:51:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1216, "total_steps": 1626, "loss": 1.6189, "learning_rate": 5.447577698306876e-06, "epoch": 2.24147465437788, "percentage": 74.78, "elapsed_time": "8:26:31", "remaining_time": "2:50:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1217, "total_steps": 1626, "loss": 1.6145, "learning_rate": 5.422765297616336e-06, "epoch": 2.2433179723502303, "percentage": 74.85, "elapsed_time": "8:26:56", "remaining_time": "2:50:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1218, "total_steps": 1626, "loss": 1.554, "learning_rate": 5.3979970591620555e-06, "epoch": 2.2451612903225806, "percentage": 74.91, "elapsed_time": "8:27:21", "remaining_time": "2:49:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1219, "total_steps": 1626, "loss": 1.5852, "learning_rate": 5.37327309715453e-06, "epoch": 2.247004608294931, "percentage": 74.97, "elapsed_time": "8:27:46", "remaining_time": "2:49:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1220, "total_steps": 1626, "loss": 1.5264, "learning_rate": 5.348593525600093e-06, "epoch": 2.248847926267281, "percentage": 75.03, "elapsed_time": "8:28:11", "remaining_time": "2:49:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1221, "total_steps": 1626, "loss": 1.4948, "learning_rate": 5.323958458300403e-06, "epoch": 2.2506912442396314, "percentage": 75.09, "elapsed_time": "8:28:36", "remaining_time": "2:48:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1222, "total_steps": 1626, "loss": 1.4826, "learning_rate": 5.29936800885188e-06, "epoch": 2.2525345622119817, "percentage": 75.15, "elapsed_time": "8:29:00", "remaining_time": "2:48:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1223, "total_steps": 1626, "loss": 1.5751, "learning_rate": 5.2748222906452105e-06, "epoch": 2.254377880184332, "percentage": 75.22, "elapsed_time": "8:29:25", "remaining_time": "2:47:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1224, "total_steps": 1626, "loss": 1.5187, "learning_rate": 5.250321416864828e-06, "epoch": 2.256221198156682, "percentage": 75.28, "elapsed_time": "8:29:50", "remaining_time": "2:47:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1225, "total_steps": 1626, "loss": 1.5599, "learning_rate": 5.2258655004883696e-06, "epoch": 2.258064516129032, "percentage": 75.34, "elapsed_time": "8:30:15", "remaining_time": "2:47:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1226, "total_steps": 1626, "loss": 1.5331, "learning_rate": 5.201454654286166e-06, "epoch": 2.2599078341013823, "percentage": 75.4, "elapsed_time": "8:30:40", "remaining_time": "2:46:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1227, "total_steps": 1626, "loss": 1.6149, "learning_rate": 5.177088990820725e-06, "epoch": 2.2617511520737326, "percentage": 75.46, "elapsed_time": "8:31:05", "remaining_time": "2:46:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1228, "total_steps": 1626, "loss": 1.5913, "learning_rate": 5.152768622446211e-06, "epoch": 2.263594470046083, "percentage": 75.52, "elapsed_time": "8:31:30", "remaining_time": "2:45:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1229, "total_steps": 1626, "loss": 1.569, "learning_rate": 5.128493661307934e-06, "epoch": 2.265437788018433, "percentage": 75.58, "elapsed_time": "8:31:55", "remaining_time": "2:45:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1230, "total_steps": 1626, "loss": 1.611, "learning_rate": 5.104264219341793e-06, "epoch": 2.2672811059907834, "percentage": 75.65, "elapsed_time": "8:32:20", "remaining_time": "2:44:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1231, "total_steps": 1626, "loss": 1.5826, "learning_rate": 5.080080408273821e-06, "epoch": 2.2691244239631336, "percentage": 75.71, "elapsed_time": "8:32:44", "remaining_time": "2:44:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1232, "total_steps": 1626, "loss": 1.5438, "learning_rate": 5.055942339619639e-06, "epoch": 2.270967741935484, "percentage": 75.77, "elapsed_time": "8:33:09", "remaining_time": "2:44:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1233, "total_steps": 1626, "loss": 1.6009, "learning_rate": 5.031850124683913e-06, "epoch": 2.272811059907834, "percentage": 75.83, "elapsed_time": "8:33:34", "remaining_time": "2:43:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1234, "total_steps": 1626, "loss": 1.5824, "learning_rate": 5.0078038745599e-06, "epoch": 2.2746543778801844, "percentage": 75.89, "elapsed_time": "8:33:59", "remaining_time": "2:43:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1235, "total_steps": 1626, "loss": 1.5522, "learning_rate": 4.983803700128893e-06, "epoch": 2.2764976958525347, "percentage": 75.95, "elapsed_time": "8:34:24", "remaining_time": "2:42:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1236, "total_steps": 1626, "loss": 1.5621, "learning_rate": 4.959849712059716e-06, "epoch": 2.278341013824885, "percentage": 76.01, "elapsed_time": "8:34:49", "remaining_time": "2:42:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1237, "total_steps": 1626, "loss": 1.6181, "learning_rate": 4.935942020808239e-06, "epoch": 2.2801843317972352, "percentage": 76.08, "elapsed_time": "8:35:14", "remaining_time": "2:42:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1238, "total_steps": 1626, "loss": 1.5769, "learning_rate": 4.912080736616833e-06, "epoch": 2.282027649769585, "percentage": 76.14, "elapsed_time": "8:35:38", "remaining_time": "2:41:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1239, "total_steps": 1626, "loss": 1.5911, "learning_rate": 4.888265969513876e-06, "epoch": 2.2838709677419353, "percentage": 76.2, "elapsed_time": "8:36:03", "remaining_time": "2:41:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1240, "total_steps": 1626, "loss": 1.6015, "learning_rate": 4.864497829313269e-06, "epoch": 2.2857142857142856, "percentage": 76.26, "elapsed_time": "8:36:28", "remaining_time": "2:40:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1241, "total_steps": 1626, "loss": 1.561, "learning_rate": 4.840776425613887e-06, "epoch": 2.287557603686636, "percentage": 76.32, "elapsed_time": "8:36:53", "remaining_time": "2:40:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1242, "total_steps": 1626, "loss": 1.5655, "learning_rate": 4.817101867799097e-06, "epoch": 2.289400921658986, "percentage": 76.38, "elapsed_time": "8:37:18", "remaining_time": "2:39:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1243, "total_steps": 1626, "loss": 1.604, "learning_rate": 4.793474265036272e-06, "epoch": 2.2912442396313364, "percentage": 76.45, "elapsed_time": "8:37:43", "remaining_time": "2:39:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1244, "total_steps": 1626, "loss": 1.6451, "learning_rate": 4.769893726276243e-06, "epoch": 2.2930875576036867, "percentage": 76.51, "elapsed_time": "8:38:07", "remaining_time": "2:39:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1245, "total_steps": 1626, "loss": 1.6059, "learning_rate": 4.746360360252834e-06, "epoch": 2.294930875576037, "percentage": 76.57, "elapsed_time": "8:38:32", "remaining_time": "2:38:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1246, "total_steps": 1626, "loss": 1.5981, "learning_rate": 4.722874275482338e-06, "epoch": 2.296774193548387, "percentage": 76.63, "elapsed_time": "8:38:57", "remaining_time": "2:38:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1247, "total_steps": 1626, "loss": 1.5291, "learning_rate": 4.699435580263044e-06, "epoch": 2.2986175115207375, "percentage": 76.69, "elapsed_time": "8:39:22", "remaining_time": "2:37:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1248, "total_steps": 1626, "loss": 1.4955, "learning_rate": 4.676044382674702e-06, "epoch": 2.3004608294930877, "percentage": 76.75, "elapsed_time": "8:39:47", "remaining_time": "2:37:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1249, "total_steps": 1626, "loss": 1.5537, "learning_rate": 4.652700790578047e-06, "epoch": 2.3023041474654375, "percentage": 76.81, "elapsed_time": "8:40:12", "remaining_time": "2:37:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1250, "total_steps": 1626, "loss": 1.53, "learning_rate": 4.629404911614306e-06, "epoch": 2.3041474654377883, "percentage": 76.88, "elapsed_time": "8:40:36", "remaining_time": "2:36:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1251, "total_steps": 1626, "loss": 1.5997, "learning_rate": 4.606156853204682e-06, "epoch": 2.305990783410138, "percentage": 76.94, "elapsed_time": "8:41:01", "remaining_time": "2:36:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1252, "total_steps": 1626, "loss": 1.5487, "learning_rate": 4.5829567225498696e-06, "epoch": 2.3078341013824883, "percentage": 77.0, "elapsed_time": "8:41:27", "remaining_time": "2:35:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1253, "total_steps": 1626, "loss": 1.5927, "learning_rate": 4.559804626629574e-06, "epoch": 2.3096774193548386, "percentage": 77.06, "elapsed_time": "8:41:51", "remaining_time": "2:35:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1254, "total_steps": 1626, "loss": 1.5277, "learning_rate": 4.536700672201987e-06, "epoch": 2.311520737327189, "percentage": 77.12, "elapsed_time": "8:42:16", "remaining_time": "2:34:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1255, "total_steps": 1626, "loss": 1.5356, "learning_rate": 4.513644965803316e-06, "epoch": 2.313364055299539, "percentage": 77.18, "elapsed_time": "8:42:41", "remaining_time": "2:34:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1256, "total_steps": 1626, "loss": 1.5588, "learning_rate": 4.490637613747301e-06, "epoch": 2.3152073732718894, "percentage": 77.24, "elapsed_time": "8:43:06", "remaining_time": "2:34:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1257, "total_steps": 1626, "loss": 1.5853, "learning_rate": 4.4676787221247e-06, "epoch": 2.3170506912442397, "percentage": 77.31, "elapsed_time": "8:43:31", "remaining_time": "2:33:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1258, "total_steps": 1626, "loss": 1.5947, "learning_rate": 4.444768396802808e-06, "epoch": 2.31889400921659, "percentage": 77.37, "elapsed_time": "8:43:56", "remaining_time": "2:33:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1259, "total_steps": 1626, "loss": 1.5098, "learning_rate": 4.421906743424989e-06, "epoch": 2.32073732718894, "percentage": 77.43, "elapsed_time": "8:44:21", "remaining_time": "2:32:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1260, "total_steps": 1626, "loss": 1.5564, "learning_rate": 4.39909386741016e-06, "epoch": 2.3225806451612905, "percentage": 77.49, "elapsed_time": "8:44:45", "remaining_time": "2:32:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1261, "total_steps": 1626, "loss": 1.579, "learning_rate": 4.376329873952317e-06, "epoch": 2.3244239631336407, "percentage": 77.55, "elapsed_time": "8:45:10", "remaining_time": "2:32:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1262, "total_steps": 1626, "loss": 1.5967, "learning_rate": 4.353614868020051e-06, "epoch": 2.3262672811059906, "percentage": 77.61, "elapsed_time": "8:45:35", "remaining_time": "2:31:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1263, "total_steps": 1626, "loss": 1.6107, "learning_rate": 4.330948954356076e-06, "epoch": 2.328110599078341, "percentage": 77.68, "elapsed_time": "8:46:00", "remaining_time": "2:31:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1264, "total_steps": 1626, "loss": 1.5283, "learning_rate": 4.308332237476717e-06, "epoch": 2.329953917050691, "percentage": 77.74, "elapsed_time": "8:46:25", "remaining_time": "2:30:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1265, "total_steps": 1626, "loss": 1.5784, "learning_rate": 4.285764821671446e-06, "epoch": 2.3317972350230414, "percentage": 77.8, "elapsed_time": "8:46:50", "remaining_time": "2:30:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1266, "total_steps": 1626, "loss": 1.6278, "learning_rate": 4.263246811002414e-06, "epoch": 2.3336405529953916, "percentage": 77.86, "elapsed_time": "8:47:15", "remaining_time": "2:29:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1267, "total_steps": 1626, "loss": 1.5784, "learning_rate": 4.240778309303942e-06, "epoch": 2.335483870967742, "percentage": 77.92, "elapsed_time": "8:47:40", "remaining_time": "2:29:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1268, "total_steps": 1626, "loss": 1.5651, "learning_rate": 4.218359420182055e-06, "epoch": 2.337327188940092, "percentage": 77.98, "elapsed_time": "8:48:05", "remaining_time": "2:29:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1269, "total_steps": 1626, "loss": 1.5131, "learning_rate": 4.195990247014025e-06, "epoch": 2.3391705069124424, "percentage": 78.04, "elapsed_time": "8:48:31", "remaining_time": "2:28:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1270, "total_steps": 1626, "loss": 1.6161, "learning_rate": 4.173670892947858e-06, "epoch": 2.3410138248847927, "percentage": 78.11, "elapsed_time": "8:48:56", "remaining_time": "2:28:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1271, "total_steps": 1626, "loss": 1.5564, "learning_rate": 4.151401460901833e-06, "epoch": 2.342857142857143, "percentage": 78.17, "elapsed_time": "8:49:21", "remaining_time": "2:27:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1272, "total_steps": 1626, "loss": 1.547, "learning_rate": 4.1291820535640505e-06, "epoch": 2.3447004608294932, "percentage": 78.23, "elapsed_time": "8:49:45", "remaining_time": "2:27:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1273, "total_steps": 1626, "loss": 1.5216, "learning_rate": 4.107012773391918e-06, "epoch": 2.3465437788018435, "percentage": 78.29, "elapsed_time": "8:50:10", "remaining_time": "2:27:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1274, "total_steps": 1626, "loss": 1.551, "learning_rate": 4.084893722611706e-06, "epoch": 2.3483870967741938, "percentage": 78.35, "elapsed_time": "8:50:36", "remaining_time": "2:26:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1275, "total_steps": 1626, "loss": 1.5346, "learning_rate": 4.062825003218075e-06, "epoch": 2.3502304147465436, "percentage": 78.41, "elapsed_time": "8:51:00", "remaining_time": "2:26:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1276, "total_steps": 1626, "loss": 1.5328, "learning_rate": 4.04080671697359e-06, "epoch": 2.352073732718894, "percentage": 78.47, "elapsed_time": "8:51:25", "remaining_time": "2:25:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1277, "total_steps": 1626, "loss": 1.5464, "learning_rate": 4.018838965408259e-06, "epoch": 2.353917050691244, "percentage": 78.54, "elapsed_time": "8:51:50", "remaining_time": "2:25:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1278, "total_steps": 1626, "loss": 1.4875, "learning_rate": 3.99692184981908e-06, "epoch": 2.3557603686635944, "percentage": 78.6, "elapsed_time": "8:52:15", "remaining_time": "2:24:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1279, "total_steps": 1626, "loss": 1.5394, "learning_rate": 3.975055471269545e-06, "epoch": 2.3576036866359447, "percentage": 78.66, "elapsed_time": "8:52:40", "remaining_time": "2:24:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1280, "total_steps": 1626, "loss": 1.6278, "learning_rate": 3.953239930589196e-06, "epoch": 2.359447004608295, "percentage": 78.72, "elapsed_time": "8:53:04", "remaining_time": "2:24:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1281, "total_steps": 1626, "loss": 1.5823, "learning_rate": 3.931475328373145e-06, "epoch": 2.361290322580645, "percentage": 78.78, "elapsed_time": "8:53:29", "remaining_time": "2:23:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1282, "total_steps": 1626, "loss": 1.5393, "learning_rate": 3.909761764981637e-06, "epoch": 2.3631336405529955, "percentage": 78.84, "elapsed_time": "8:53:54", "remaining_time": "2:23:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1283, "total_steps": 1626, "loss": 1.5612, "learning_rate": 3.888099340539548e-06, "epoch": 2.3649769585253457, "percentage": 78.91, "elapsed_time": "8:54:19", "remaining_time": "2:22:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1284, "total_steps": 1626, "loss": 1.5021, "learning_rate": 3.866488154935951e-06, "epoch": 2.366820276497696, "percentage": 78.97, "elapsed_time": "8:54:44", "remaining_time": "2:22:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1285, "total_steps": 1626, "loss": 1.59, "learning_rate": 3.844928307823655e-06, "epoch": 2.3686635944700463, "percentage": 79.03, "elapsed_time": "8:55:08", "remaining_time": "2:22:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1286, "total_steps": 1626, "loss": 1.5734, "learning_rate": 3.823419898618733e-06, "epoch": 2.370506912442396, "percentage": 79.09, "elapsed_time": "8:55:34", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1287, "total_steps": 1626, "loss": 1.5254, "learning_rate": 3.801963026500058e-06, "epoch": 2.3723502304147464, "percentage": 79.15, "elapsed_time": "8:55:59", "remaining_time": "2:21:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1288, "total_steps": 1626, "loss": 1.5835, "learning_rate": 3.7805577904088817e-06, "epoch": 2.3741935483870966, "percentage": 79.21, "elapsed_time": "8:56:23", "remaining_time": "2:20:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1289, "total_steps": 1626, "loss": 1.5936, "learning_rate": 3.7592042890483335e-06, "epoch": 2.376036866359447, "percentage": 79.27, "elapsed_time": "8:56:48", "remaining_time": "2:20:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1290, "total_steps": 1626, "loss": 1.6293, "learning_rate": 3.7379026208829865e-06, "epoch": 2.377880184331797, "percentage": 79.34, "elapsed_time": "8:57:13", "remaining_time": "2:19:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1291, "total_steps": 1626, "loss": 1.5031, "learning_rate": 3.7166528841384197e-06, "epoch": 2.3797235023041474, "percentage": 79.4, "elapsed_time": "8:57:38", "remaining_time": "2:19:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1292, "total_steps": 1626, "loss": 1.552, "learning_rate": 3.695455176800719e-06, "epoch": 2.3815668202764977, "percentage": 79.46, "elapsed_time": "8:58:03", "remaining_time": "2:19:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1293, "total_steps": 1626, "loss": 1.628, "learning_rate": 3.6743095966160773e-06, "epoch": 2.383410138248848, "percentage": 79.52, "elapsed_time": "8:58:28", "remaining_time": "2:18:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1294, "total_steps": 1626, "loss": 1.4956, "learning_rate": 3.6532162410903165e-06, "epoch": 2.385253456221198, "percentage": 79.58, "elapsed_time": "8:58:53", "remaining_time": "2:18:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1295, "total_steps": 1626, "loss": 1.5754, "learning_rate": 3.6321752074884374e-06, "epoch": 2.3870967741935485, "percentage": 79.64, "elapsed_time": "8:59:18", "remaining_time": "2:17:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1296, "total_steps": 1626, "loss": 1.5562, "learning_rate": 3.6111865928341723e-06, "epoch": 2.3889400921658988, "percentage": 79.7, "elapsed_time": "8:59:42", "remaining_time": "2:17:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1297, "total_steps": 1626, "loss": 1.5849, "learning_rate": 3.5902504939095444e-06, "epoch": 2.390783410138249, "percentage": 79.77, "elapsed_time": "9:00:07", "remaining_time": "2:17:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1298, "total_steps": 1626, "loss": 1.6061, "learning_rate": 3.5693670072544253e-06, "epoch": 2.3926267281105993, "percentage": 79.83, "elapsed_time": "9:00:32", "remaining_time": "2:16:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1299, "total_steps": 1626, "loss": 1.5809, "learning_rate": 3.5485362291660727e-06, "epoch": 2.394470046082949, "percentage": 79.89, "elapsed_time": "9:00:58", "remaining_time": "2:16:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1300, "total_steps": 1626, "loss": 1.5568, "learning_rate": 3.527758255698696e-06, "epoch": 2.3963133640552994, "percentage": 79.95, "elapsed_time": "9:01:23", "remaining_time": "2:15:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1301, "total_steps": 1626, "loss": 1.6425, "learning_rate": 3.507033182663026e-06, "epoch": 2.3981566820276496, "percentage": 80.01, "elapsed_time": "9:01:47", "remaining_time": "2:15:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1302, "total_steps": 1626, "loss": 1.5819, "learning_rate": 3.4863611056258456e-06, "epoch": 2.4, "percentage": 80.07, "elapsed_time": "9:02:12", "remaining_time": "2:14:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1303, "total_steps": 1626, "loss": 1.608, "learning_rate": 3.465742119909568e-06, "epoch": 2.40184331797235, "percentage": 80.14, "elapsed_time": "9:02:37", "remaining_time": "2:14:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1304, "total_steps": 1626, "loss": 1.5662, "learning_rate": 3.445176320591806e-06, "epoch": 2.4036866359447004, "percentage": 80.2, "elapsed_time": "9:03:02", "remaining_time": "2:14:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1305, "total_steps": 1626, "loss": 1.5217, "learning_rate": 3.4246638025049043e-06, "epoch": 2.4055299539170507, "percentage": 80.26, "elapsed_time": "9:03:27", "remaining_time": "2:13:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1306, "total_steps": 1626, "loss": 1.593, "learning_rate": 3.4042046602355238e-06, "epoch": 2.407373271889401, "percentage": 80.32, "elapsed_time": "9:03:52", "remaining_time": "2:13:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1307, "total_steps": 1626, "loss": 1.5398, "learning_rate": 3.3837989881242142e-06, "epoch": 2.4092165898617512, "percentage": 80.38, "elapsed_time": "9:04:17", "remaining_time": "2:12:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1308, "total_steps": 1626, "loss": 1.6315, "learning_rate": 3.363446880264937e-06, "epoch": 2.4110599078341015, "percentage": 80.44, "elapsed_time": "9:04:42", "remaining_time": "2:12:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1309, "total_steps": 1626, "loss": 1.5792, "learning_rate": 3.3431484305046838e-06, "epoch": 2.412903225806452, "percentage": 80.5, "elapsed_time": "9:05:07", "remaining_time": "2:12:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1310, "total_steps": 1626, "loss": 1.5373, "learning_rate": 3.3229037324430228e-06, "epoch": 2.4147465437788016, "percentage": 80.57, "elapsed_time": "9:05:32", "remaining_time": "2:11:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1311, "total_steps": 1626, "loss": 1.6078, "learning_rate": 3.3027128794316353e-06, "epoch": 2.4165898617511523, "percentage": 80.63, "elapsed_time": "9:05:56", "remaining_time": "2:11:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1312, "total_steps": 1626, "loss": 1.5733, "learning_rate": 3.282575964573943e-06, "epoch": 2.418433179723502, "percentage": 80.69, "elapsed_time": "9:06:21", "remaining_time": "2:10:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1313, "total_steps": 1626, "loss": 1.5982, "learning_rate": 3.2624930807246443e-06, "epoch": 2.4202764976958524, "percentage": 80.75, "elapsed_time": "9:06:46", "remaining_time": "2:10:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1314, "total_steps": 1626, "loss": 1.5393, "learning_rate": 3.2424643204892734e-06, "epoch": 2.4221198156682027, "percentage": 80.81, "elapsed_time": "9:07:11", "remaining_time": "2:09:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1315, "total_steps": 1626, "loss": 1.5362, "learning_rate": 3.2224897762238143e-06, "epoch": 2.423963133640553, "percentage": 80.87, "elapsed_time": "9:07:36", "remaining_time": "2:09:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1316, "total_steps": 1626, "loss": 1.5838, "learning_rate": 3.2025695400342346e-06, "epoch": 2.425806451612903, "percentage": 80.93, "elapsed_time": "9:08:01", "remaining_time": "2:09:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1317, "total_steps": 1626, "loss": 1.4825, "learning_rate": 3.1827037037760965e-06, "epoch": 2.4276497695852535, "percentage": 81.0, "elapsed_time": "9:08:26", "remaining_time": "2:08:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1318, "total_steps": 1626, "loss": 1.6039, "learning_rate": 3.162892359054098e-06, "epoch": 2.4294930875576037, "percentage": 81.06, "elapsed_time": "9:08:50", "remaining_time": "2:08:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1319, "total_steps": 1626, "loss": 1.568, "learning_rate": 3.1431355972216697e-06, "epoch": 2.431336405529954, "percentage": 81.12, "elapsed_time": "9:09:15", "remaining_time": "2:07:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1320, "total_steps": 1626, "loss": 1.5735, "learning_rate": 3.1234335093805655e-06, "epoch": 2.4331797235023043, "percentage": 81.18, "elapsed_time": "9:09:40", "remaining_time": "2:07:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1321, "total_steps": 1626, "loss": 1.5878, "learning_rate": 3.1037861863804117e-06, "epoch": 2.4350230414746545, "percentage": 81.24, "elapsed_time": "9:10:05", "remaining_time": "2:07:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1322, "total_steps": 1626, "loss": 1.5453, "learning_rate": 3.08419371881831e-06, "epoch": 2.436866359447005, "percentage": 81.3, "elapsed_time": "9:10:30", "remaining_time": "2:06:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1323, "total_steps": 1626, "loss": 1.5695, "learning_rate": 3.0646561970384226e-06, "epoch": 2.4387096774193546, "percentage": 81.37, "elapsed_time": "9:10:55", "remaining_time": "2:06:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1324, "total_steps": 1626, "loss": 1.571, "learning_rate": 3.045173711131537e-06, "epoch": 2.440552995391705, "percentage": 81.43, "elapsed_time": "9:11:19", "remaining_time": "2:05:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1325, "total_steps": 1626, "loss": 1.5779, "learning_rate": 3.02574635093466e-06, "epoch": 2.442396313364055, "percentage": 81.49, "elapsed_time": "9:11:44", "remaining_time": "2:05:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1326, "total_steps": 1626, "loss": 1.5737, "learning_rate": 3.0063742060306227e-06, "epoch": 2.4442396313364054, "percentage": 81.55, "elapsed_time": "9:12:09", "remaining_time": "2:04:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1327, "total_steps": 1626, "loss": 1.6337, "learning_rate": 2.9870573657476196e-06, "epoch": 2.4460829493087557, "percentage": 81.61, "elapsed_time": "9:12:35", "remaining_time": "2:04:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1328, "total_steps": 1626, "loss": 1.5565, "learning_rate": 2.96779591915885e-06, "epoch": 2.447926267281106, "percentage": 81.67, "elapsed_time": "9:13:00", "remaining_time": "2:04:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1329, "total_steps": 1626, "loss": 1.6058, "learning_rate": 2.948589955082085e-06, "epoch": 2.4497695852534562, "percentage": 81.73, "elapsed_time": "9:13:24", "remaining_time": "2:03:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1330, "total_steps": 1626, "loss": 1.5153, "learning_rate": 2.9294395620792306e-06, "epoch": 2.4516129032258065, "percentage": 81.8, "elapsed_time": "9:13:49", "remaining_time": "2:03:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1331, "total_steps": 1626, "loss": 1.5567, "learning_rate": 2.910344828455975e-06, "epoch": 2.4534562211981568, "percentage": 81.86, "elapsed_time": "9:14:14", "remaining_time": "2:02:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1332, "total_steps": 1626, "loss": 1.5801, "learning_rate": 2.8913058422613363e-06, "epoch": 2.455299539170507, "percentage": 81.92, "elapsed_time": "9:14:39", "remaining_time": "2:02:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1333, "total_steps": 1626, "loss": 1.5937, "learning_rate": 2.872322691287268e-06, "epoch": 2.4571428571428573, "percentage": 81.98, "elapsed_time": "9:15:04", "remaining_time": "2:02:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1334, "total_steps": 1626, "loss": 1.6024, "learning_rate": 2.8533954630682728e-06, "epoch": 2.4589861751152076, "percentage": 82.04, "elapsed_time": "9:15:29", "remaining_time": "2:01:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1335, "total_steps": 1626, "loss": 1.6058, "learning_rate": 2.834524244880974e-06, "epoch": 2.460829493087558, "percentage": 82.1, "elapsed_time": "9:15:54", "remaining_time": "2:01:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1336, "total_steps": 1626, "loss": 1.598, "learning_rate": 2.81570912374372e-06, "epoch": 2.4626728110599077, "percentage": 82.16, "elapsed_time": "9:16:18", "remaining_time": "2:00:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1337, "total_steps": 1626, "loss": 1.5603, "learning_rate": 2.796950186416199e-06, "epoch": 2.464516129032258, "percentage": 82.23, "elapsed_time": "9:16:43", "remaining_time": "2:00:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1338, "total_steps": 1626, "loss": 1.5753, "learning_rate": 2.778247519399011e-06, "epoch": 2.466359447004608, "percentage": 82.29, "elapsed_time": "9:17:08", "remaining_time": "1:59:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1339, "total_steps": 1626, "loss": 1.545, "learning_rate": 2.7596012089333015e-06, "epoch": 2.4682027649769585, "percentage": 82.35, "elapsed_time": "9:17:33", "remaining_time": "1:59:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1340, "total_steps": 1626, "loss": 1.5653, "learning_rate": 2.74101134100033e-06, "epoch": 2.4700460829493087, "percentage": 82.41, "elapsed_time": "9:17:58", "remaining_time": "1:59:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1341, "total_steps": 1626, "loss": 1.5775, "learning_rate": 2.7224780013210965e-06, "epoch": 2.471889400921659, "percentage": 82.47, "elapsed_time": "9:18:23", "remaining_time": "1:58:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1342, "total_steps": 1626, "loss": 1.5563, "learning_rate": 2.7040012753559477e-06, "epoch": 2.4737327188940093, "percentage": 82.53, "elapsed_time": "9:18:48", "remaining_time": "1:58:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1343, "total_steps": 1626, "loss": 1.5963, "learning_rate": 2.6855812483041555e-06, "epoch": 2.4755760368663595, "percentage": 82.6, "elapsed_time": "9:19:13", "remaining_time": "1:57:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1344, "total_steps": 1626, "loss": 1.4943, "learning_rate": 2.667218005103562e-06, "epoch": 2.47741935483871, "percentage": 82.66, "elapsed_time": "9:19:37", "remaining_time": "1:57:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1345, "total_steps": 1626, "loss": 1.5842, "learning_rate": 2.6489116304301697e-06, "epoch": 2.47926267281106, "percentage": 82.72, "elapsed_time": "9:20:02", "remaining_time": "1:57:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1346, "total_steps": 1626, "loss": 1.5426, "learning_rate": 2.6306622086977288e-06, "epoch": 2.4811059907834103, "percentage": 82.78, "elapsed_time": "9:20:27", "remaining_time": "1:56:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1347, "total_steps": 1626, "loss": 1.5402, "learning_rate": 2.6124698240573973e-06, "epoch": 2.48294930875576, "percentage": 82.84, "elapsed_time": "9:20:52", "remaining_time": "1:56:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1348, "total_steps": 1626, "loss": 1.5594, "learning_rate": 2.59433456039731e-06, "epoch": 2.4847926267281104, "percentage": 82.9, "elapsed_time": "9:21:17", "remaining_time": "1:55:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1349, "total_steps": 1626, "loss": 1.6267, "learning_rate": 2.576256501342206e-06, "epoch": 2.4866359447004607, "percentage": 82.96, "elapsed_time": "9:21:42", "remaining_time": "1:55:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1350, "total_steps": 1626, "loss": 1.5599, "learning_rate": 2.558235730253057e-06, "epoch": 2.488479262672811, "percentage": 83.03, "elapsed_time": "9:22:07", "remaining_time": "1:54:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1351, "total_steps": 1626, "loss": 1.56, "learning_rate": 2.540272330226658e-06, "epoch": 2.490322580645161, "percentage": 83.09, "elapsed_time": "9:22:31", "remaining_time": "1:54:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1352, "total_steps": 1626, "loss": 1.5663, "learning_rate": 2.5223663840952584e-06, "epoch": 2.4921658986175115, "percentage": 83.15, "elapsed_time": "9:22:56", "remaining_time": "1:54:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1353, "total_steps": 1626, "loss": 1.5397, "learning_rate": 2.5045179744261864e-06, "epoch": 2.4940092165898617, "percentage": 83.21, "elapsed_time": "9:23:21", "remaining_time": "1:53:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1354, "total_steps": 1626, "loss": 1.5689, "learning_rate": 2.486727183521451e-06, "epoch": 2.495852534562212, "percentage": 83.27, "elapsed_time": "9:23:46", "remaining_time": "1:53:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1355, "total_steps": 1626, "loss": 1.561, "learning_rate": 2.46899409341737e-06, "epoch": 2.4976958525345623, "percentage": 83.33, "elapsed_time": "9:24:11", "remaining_time": "1:52:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1356, "total_steps": 1626, "loss": 1.5639, "learning_rate": 2.451318785884205e-06, "epoch": 2.4995391705069125, "percentage": 83.39, "elapsed_time": "9:24:36", "remaining_time": "1:52:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1357, "total_steps": 1626, "loss": 1.5422, "learning_rate": 2.4337013424257604e-06, "epoch": 2.501382488479263, "percentage": 83.46, "elapsed_time": "9:25:00", "remaining_time": "1:52:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1358, "total_steps": 1626, "loss": 1.52, "learning_rate": 2.416141844279023e-06, "epoch": 2.5032258064516126, "percentage": 83.52, "elapsed_time": "9:25:25", "remaining_time": "1:51:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1359, "total_steps": 1626, "loss": 1.5432, "learning_rate": 2.398640372413792e-06, "epoch": 2.5050691244239633, "percentage": 83.58, "elapsed_time": "9:25:50", "remaining_time": "1:51:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1360, "total_steps": 1626, "loss": 1.5505, "learning_rate": 2.38119700753228e-06, "epoch": 2.506912442396313, "percentage": 83.64, "elapsed_time": "9:26:15", "remaining_time": "1:50:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1361, "total_steps": 1626, "loss": 1.5933, "learning_rate": 2.3638118300687842e-06, "epoch": 2.5087557603686634, "percentage": 83.7, "elapsed_time": "9:26:40", "remaining_time": "1:50:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1362, "total_steps": 1626, "loss": 1.5641, "learning_rate": 2.3464849201892596e-06, "epoch": 2.5105990783410137, "percentage": 83.76, "elapsed_time": "9:27:05", "remaining_time": "1:49:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1363, "total_steps": 1626, "loss": 1.5669, "learning_rate": 2.329216357791003e-06, "epoch": 2.512442396313364, "percentage": 83.83, "elapsed_time": "9:27:30", "remaining_time": "1:49:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1364, "total_steps": 1626, "loss": 1.5841, "learning_rate": 2.3120062225022587e-06, "epoch": 2.5142857142857142, "percentage": 83.89, "elapsed_time": "9:27:55", "remaining_time": "1:49:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1365, "total_steps": 1626, "loss": 1.5924, "learning_rate": 2.294854593681834e-06, "epoch": 2.5161290322580645, "percentage": 83.95, "elapsed_time": "9:28:20", "remaining_time": "1:48:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1366, "total_steps": 1626, "loss": 1.5189, "learning_rate": 2.2777615504187787e-06, "epoch": 2.5179723502304148, "percentage": 84.01, "elapsed_time": "9:28:45", "remaining_time": "1:48:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1367, "total_steps": 1626, "loss": 1.6149, "learning_rate": 2.260727171531982e-06, "epoch": 2.519815668202765, "percentage": 84.07, "elapsed_time": "9:29:10", "remaining_time": "1:47:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1368, "total_steps": 1626, "loss": 1.5595, "learning_rate": 2.2437515355698157e-06, "epoch": 2.5216589861751153, "percentage": 84.13, "elapsed_time": "9:29:35", "remaining_time": "1:47:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1369, "total_steps": 1626, "loss": 1.5527, "learning_rate": 2.2268347208097954e-06, "epoch": 2.5235023041474656, "percentage": 84.19, "elapsed_time": "9:30:00", "remaining_time": "1:47:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1370, "total_steps": 1626, "loss": 1.4486, "learning_rate": 2.2099768052581892e-06, "epoch": 2.525345622119816, "percentage": 84.26, "elapsed_time": "9:30:25", "remaining_time": "1:46:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1371, "total_steps": 1626, "loss": 1.5326, "learning_rate": 2.1931778666496704e-06, "epoch": 2.5271889400921657, "percentage": 84.32, "elapsed_time": "9:30:50", "remaining_time": "1:46:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1372, "total_steps": 1626, "loss": 1.5949, "learning_rate": 2.1764379824469704e-06, "epoch": 2.5290322580645164, "percentage": 84.38, "elapsed_time": "9:31:15", "remaining_time": "1:45:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1373, "total_steps": 1626, "loss": 1.5604, "learning_rate": 2.1597572298405e-06, "epoch": 2.530875576036866, "percentage": 84.44, "elapsed_time": "9:31:39", "remaining_time": "1:45:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1374, "total_steps": 1626, "loss": 1.544, "learning_rate": 2.1431356857480076e-06, "epoch": 2.5327188940092165, "percentage": 84.5, "elapsed_time": "9:32:04", "remaining_time": "1:44:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1375, "total_steps": 1626, "loss": 1.5313, "learning_rate": 2.126573426814226e-06, "epoch": 2.5345622119815667, "percentage": 84.56, "elapsed_time": "9:32:29", "remaining_time": "1:44:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1376, "total_steps": 1626, "loss": 1.522, "learning_rate": 2.110070529410508e-06, "epoch": 2.536405529953917, "percentage": 84.62, "elapsed_time": "9:32:54", "remaining_time": "1:44:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1377, "total_steps": 1626, "loss": 1.6378, "learning_rate": 2.093627069634484e-06, "epoch": 2.5382488479262673, "percentage": 84.69, "elapsed_time": "9:33:19", "remaining_time": "1:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1378, "total_steps": 1626, "loss": 1.5337, "learning_rate": 2.0772431233097007e-06, "epoch": 2.5400921658986175, "percentage": 84.75, "elapsed_time": "9:33:44", "remaining_time": "1:43:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1379, "total_steps": 1626, "loss": 1.5457, "learning_rate": 2.060918765985288e-06, "epoch": 2.541935483870968, "percentage": 84.81, "elapsed_time": "9:34:09", "remaining_time": "1:42:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1380, "total_steps": 1626, "loss": 1.5299, "learning_rate": 2.044654072935603e-06, "epoch": 2.543778801843318, "percentage": 84.87, "elapsed_time": "9:34:34", "remaining_time": "1:42:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1381, "total_steps": 1626, "loss": 1.5456, "learning_rate": 2.028449119159862e-06, "epoch": 2.5456221198156683, "percentage": 84.93, "elapsed_time": "9:34:59", "remaining_time": "1:42:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1382, "total_steps": 1626, "loss": 1.5467, "learning_rate": 2.012303979381836e-06, "epoch": 2.5474654377880186, "percentage": 84.99, "elapsed_time": "9:35:24", "remaining_time": "1:41:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1383, "total_steps": 1626, "loss": 1.5974, "learning_rate": 1.9962187280494708e-06, "epoch": 2.549308755760369, "percentage": 85.06, "elapsed_time": "9:35:49", "remaining_time": "1:41:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1384, "total_steps": 1626, "loss": 1.5682, "learning_rate": 1.980193439334554e-06, "epoch": 2.5511520737327187, "percentage": 85.12, "elapsed_time": "9:36:14", "remaining_time": "1:40:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1385, "total_steps": 1626, "loss": 1.5093, "learning_rate": 1.9642281871323896e-06, "epoch": 2.5529953917050694, "percentage": 85.18, "elapsed_time": "9:36:39", "remaining_time": "1:40:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1386, "total_steps": 1626, "loss": 1.5833, "learning_rate": 1.94832304506143e-06, "epoch": 2.554838709677419, "percentage": 85.24, "elapsed_time": "9:37:04", "remaining_time": "1:39:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1387, "total_steps": 1626, "loss": 1.5439, "learning_rate": 1.9324780864629506e-06, "epoch": 2.5566820276497695, "percentage": 85.3, "elapsed_time": "9:37:29", "remaining_time": "1:39:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1388, "total_steps": 1626, "loss": 1.564, "learning_rate": 1.916693384400722e-06, "epoch": 2.5585253456221198, "percentage": 85.36, "elapsed_time": "9:37:54", "remaining_time": "1:39:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1389, "total_steps": 1626, "loss": 1.5753, "learning_rate": 1.9009690116606493e-06, "epoch": 2.56036866359447, "percentage": 85.42, "elapsed_time": "9:38:19", "remaining_time": "1:38:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1390, "total_steps": 1626, "loss": 1.5523, "learning_rate": 1.8853050407504513e-06, "epoch": 2.5622119815668203, "percentage": 85.49, "elapsed_time": "9:38:44", "remaining_time": "1:38:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1391, "total_steps": 1626, "loss": 1.5414, "learning_rate": 1.8697015438993337e-06, "epoch": 2.5640552995391706, "percentage": 85.55, "elapsed_time": "9:39:09", "remaining_time": "1:37:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1392, "total_steps": 1626, "loss": 1.5653, "learning_rate": 1.8541585930576338e-06, "epoch": 2.565898617511521, "percentage": 85.61, "elapsed_time": "9:39:33", "remaining_time": "1:37:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1393, "total_steps": 1626, "loss": 1.5045, "learning_rate": 1.8386762598965073e-06, "epoch": 2.567741935483871, "percentage": 85.67, "elapsed_time": "9:39:58", "remaining_time": "1:37:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1394, "total_steps": 1626, "loss": 1.6125, "learning_rate": 1.8232546158075853e-06, "epoch": 2.5695852534562214, "percentage": 85.73, "elapsed_time": "9:40:23", "remaining_time": "1:36:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1395, "total_steps": 1626, "loss": 1.5814, "learning_rate": 1.8078937319026655e-06, "epoch": 2.571428571428571, "percentage": 85.79, "elapsed_time": "9:40:48", "remaining_time": "1:36:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1396, "total_steps": 1626, "loss": 1.5964, "learning_rate": 1.7925936790133556e-06, "epoch": 2.573271889400922, "percentage": 85.85, "elapsed_time": "9:41:13", "remaining_time": "1:35:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1397, "total_steps": 1626, "loss": 1.5912, "learning_rate": 1.7773545276907639e-06, "epoch": 2.5751152073732717, "percentage": 85.92, "elapsed_time": "9:41:38", "remaining_time": "1:35:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1398, "total_steps": 1626, "loss": 1.5868, "learning_rate": 1.7621763482051827e-06, "epoch": 2.576958525345622, "percentage": 85.98, "elapsed_time": "9:42:02", "remaining_time": "1:34:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1399, "total_steps": 1626, "loss": 1.5747, "learning_rate": 1.747059210545739e-06, "epoch": 2.5788018433179722, "percentage": 86.04, "elapsed_time": "9:42:27", "remaining_time": "1:34:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1400, "total_steps": 1626, "loss": 1.5747, "learning_rate": 1.7320031844200883e-06, "epoch": 2.5806451612903225, "percentage": 86.1, "elapsed_time": "9:42:52", "remaining_time": "1:34:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1401, "total_steps": 1626, "loss": 1.5384, "learning_rate": 1.7170083392540998e-06, "epoch": 2.5824884792626728, "percentage": 86.16, "elapsed_time": "9:43:27", "remaining_time": "1:33:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1402, "total_steps": 1626, "loss": 1.5085, "learning_rate": 1.7020747441915184e-06, "epoch": 2.584331797235023, "percentage": 86.22, "elapsed_time": "9:43:52", "remaining_time": "1:33:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1403, "total_steps": 1626, "loss": 1.6187, "learning_rate": 1.687202468093655e-06, "epoch": 2.5861751152073733, "percentage": 86.29, "elapsed_time": "9:44:17", "remaining_time": "1:32:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1404, "total_steps": 1626, "loss": 1.5834, "learning_rate": 1.6723915795390733e-06, "epoch": 2.5880184331797236, "percentage": 86.35, "elapsed_time": "9:44:42", "remaining_time": "1:32:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1405, "total_steps": 1626, "loss": 1.5716, "learning_rate": 1.6576421468232627e-06, "epoch": 2.589861751152074, "percentage": 86.41, "elapsed_time": "9:45:07", "remaining_time": "1:32:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1406, "total_steps": 1626, "loss": 1.5891, "learning_rate": 1.6429542379583313e-06, "epoch": 2.591705069124424, "percentage": 86.47, "elapsed_time": "9:45:32", "remaining_time": "1:31:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1407, "total_steps": 1626, "loss": 1.6111, "learning_rate": 1.6283279206726964e-06, "epoch": 2.5935483870967744, "percentage": 86.53, "elapsed_time": "9:45:56", "remaining_time": "1:31:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1408, "total_steps": 1626, "loss": 1.5417, "learning_rate": 1.6137632624107602e-06, "epoch": 2.595391705069124, "percentage": 86.59, "elapsed_time": "9:46:21", "remaining_time": "1:30:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1409, "total_steps": 1626, "loss": 1.5703, "learning_rate": 1.5992603303325997e-06, "epoch": 2.597235023041475, "percentage": 86.65, "elapsed_time": "9:46:46", "remaining_time": "1:30:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1410, "total_steps": 1626, "loss": 1.52, "learning_rate": 1.5848191913136757e-06, "epoch": 2.5990783410138247, "percentage": 86.72, "elapsed_time": "9:47:11", "remaining_time": "1:29:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1411, "total_steps": 1626, "loss": 1.5803, "learning_rate": 1.5704399119445007e-06, "epoch": 2.600921658986175, "percentage": 86.78, "elapsed_time": "9:47:36", "remaining_time": "1:29:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1412, "total_steps": 1626, "loss": 1.5631, "learning_rate": 1.5561225585303463e-06, "epoch": 2.6027649769585253, "percentage": 86.84, "elapsed_time": "9:48:01", "remaining_time": "1:29:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1413, "total_steps": 1626, "loss": 1.5197, "learning_rate": 1.5418671970909253e-06, "epoch": 2.6046082949308755, "percentage": 86.9, "elapsed_time": "9:48:26", "remaining_time": "1:28:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1414, "total_steps": 1626, "loss": 1.565, "learning_rate": 1.527673893360108e-06, "epoch": 2.606451612903226, "percentage": 86.96, "elapsed_time": "9:48:51", "remaining_time": "1:28:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1415, "total_steps": 1626, "loss": 1.5228, "learning_rate": 1.5135427127855982e-06, "epoch": 2.608294930875576, "percentage": 87.02, "elapsed_time": "9:49:16", "remaining_time": "1:27:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1416, "total_steps": 1626, "loss": 1.5913, "learning_rate": 1.4994737205286375e-06, "epoch": 2.6101382488479263, "percentage": 87.08, "elapsed_time": "9:49:41", "remaining_time": "1:27:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1417, "total_steps": 1626, "loss": 1.6, "learning_rate": 1.4854669814637145e-06, "epoch": 2.6119815668202766, "percentage": 87.15, "elapsed_time": "9:50:06", "remaining_time": "1:27:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1418, "total_steps": 1626, "loss": 1.5717, "learning_rate": 1.47152256017825e-06, "epoch": 2.613824884792627, "percentage": 87.21, "elapsed_time": "9:50:30", "remaining_time": "1:26:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1419, "total_steps": 1626, "loss": 1.5518, "learning_rate": 1.4576405209723092e-06, "epoch": 2.6156682027649767, "percentage": 87.27, "elapsed_time": "9:50:55", "remaining_time": "1:26:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1420, "total_steps": 1626, "loss": 1.4865, "learning_rate": 1.4438209278583108e-06, "epoch": 2.6175115207373274, "percentage": 87.33, "elapsed_time": "9:51:20", "remaining_time": "1:25:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1421, "total_steps": 1626, "loss": 1.5688, "learning_rate": 1.4300638445607123e-06, "epoch": 2.6193548387096772, "percentage": 87.39, "elapsed_time": "9:51:45", "remaining_time": "1:25:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1422, "total_steps": 1626, "loss": 1.6185, "learning_rate": 1.4163693345157313e-06, "epoch": 2.6211981566820275, "percentage": 87.45, "elapsed_time": "9:52:10", "remaining_time": "1:24:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1423, "total_steps": 1626, "loss": 1.5808, "learning_rate": 1.402737460871057e-06, "epoch": 2.6230414746543778, "percentage": 87.52, "elapsed_time": "9:52:35", "remaining_time": "1:24:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1424, "total_steps": 1626, "loss": 1.538, "learning_rate": 1.3891682864855438e-06, "epoch": 2.624884792626728, "percentage": 87.58, "elapsed_time": "9:53:00", "remaining_time": "1:24:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1425, "total_steps": 1626, "loss": 1.5303, "learning_rate": 1.3756618739289278e-06, "epoch": 2.6267281105990783, "percentage": 87.64, "elapsed_time": "9:53:25", "remaining_time": "1:23:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1426, "total_steps": 1626, "loss": 1.532, "learning_rate": 1.36221828548155e-06, "epoch": 2.6285714285714286, "percentage": 87.7, "elapsed_time": "9:53:50", "remaining_time": "1:23:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1427, "total_steps": 1626, "loss": 1.5615, "learning_rate": 1.3488375831340516e-06, "epoch": 2.630414746543779, "percentage": 87.76, "elapsed_time": "9:54:15", "remaining_time": "1:22:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1428, "total_steps": 1626, "loss": 1.5462, "learning_rate": 1.3355198285870935e-06, "epoch": 2.632258064516129, "percentage": 87.82, "elapsed_time": "9:54:40", "remaining_time": "1:22:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1429, "total_steps": 1626, "loss": 1.5803, "learning_rate": 1.322265083251074e-06, "epoch": 2.6341013824884794, "percentage": 87.88, "elapsed_time": "9:55:05", "remaining_time": "1:22:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1430, "total_steps": 1626, "loss": 1.5653, "learning_rate": 1.3090734082458562e-06, "epoch": 2.6359447004608296, "percentage": 87.95, "elapsed_time": "9:55:30", "remaining_time": "1:21:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1431, "total_steps": 1626, "loss": 1.5311, "learning_rate": 1.2959448644004611e-06, "epoch": 2.63778801843318, "percentage": 88.01, "elapsed_time": "9:55:55", "remaining_time": "1:21:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1432, "total_steps": 1626, "loss": 1.5937, "learning_rate": 1.2828795122528076e-06, "epoch": 2.6396313364055297, "percentage": 88.07, "elapsed_time": "9:56:19", "remaining_time": "1:20:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1433, "total_steps": 1626, "loss": 1.5524, "learning_rate": 1.2698774120494294e-06, "epoch": 2.6414746543778804, "percentage": 88.13, "elapsed_time": "9:56:44", "remaining_time": "1:20:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1434, "total_steps": 1626, "loss": 1.5514, "learning_rate": 1.2569386237451912e-06, "epoch": 2.6433179723502302, "percentage": 88.19, "elapsed_time": "9:57:09", "remaining_time": "1:19:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1435, "total_steps": 1626, "loss": 1.5817, "learning_rate": 1.2440632070030145e-06, "epoch": 2.6451612903225805, "percentage": 88.25, "elapsed_time": "9:57:34", "remaining_time": "1:19:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1436, "total_steps": 1626, "loss": 1.5684, "learning_rate": 1.2312512211936105e-06, "epoch": 2.647004608294931, "percentage": 88.31, "elapsed_time": "9:57:59", "remaining_time": "1:19:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1437, "total_steps": 1626, "loss": 1.6047, "learning_rate": 1.2185027253951935e-06, "epoch": 2.648847926267281, "percentage": 88.38, "elapsed_time": "9:58:24", "remaining_time": "1:18:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1438, "total_steps": 1626, "loss": 1.6164, "learning_rate": 1.2058177783932133e-06, "epoch": 2.6506912442396313, "percentage": 88.44, "elapsed_time": "9:58:49", "remaining_time": "1:18:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1439, "total_steps": 1626, "loss": 1.5684, "learning_rate": 1.1931964386800991e-06, "epoch": 2.6525345622119816, "percentage": 88.5, "elapsed_time": "9:59:13", "remaining_time": "1:17:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1440, "total_steps": 1626, "loss": 1.5332, "learning_rate": 1.180638764454955e-06, "epoch": 2.654377880184332, "percentage": 88.56, "elapsed_time": "9:59:38", "remaining_time": "1:17:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1441, "total_steps": 1626, "loss": 1.5561, "learning_rate": 1.1681448136233274e-06, "epoch": 2.656221198156682, "percentage": 88.62, "elapsed_time": "10:00:03", "remaining_time": "1:17:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1442, "total_steps": 1626, "loss": 1.5491, "learning_rate": 1.1557146437969274e-06, "epoch": 2.6580645161290324, "percentage": 88.68, "elapsed_time": "10:00:28", "remaining_time": "1:16:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1443, "total_steps": 1626, "loss": 1.5433, "learning_rate": 1.143348312293342e-06, "epoch": 2.6599078341013827, "percentage": 88.75, "elapsed_time": "10:00:53", "remaining_time": "1:16:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1444, "total_steps": 1626, "loss": 1.5163, "learning_rate": 1.1310458761358057e-06, "epoch": 2.661751152073733, "percentage": 88.81, "elapsed_time": "10:01:18", "remaining_time": "1:15:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1445, "total_steps": 1626, "loss": 1.6365, "learning_rate": 1.1188073920529202e-06, "epoch": 2.6635944700460827, "percentage": 88.87, "elapsed_time": "10:01:43", "remaining_time": "1:15:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1446, "total_steps": 1626, "loss": 1.5565, "learning_rate": 1.106632916478385e-06, "epoch": 2.6654377880184335, "percentage": 88.93, "elapsed_time": "10:02:07", "remaining_time": "1:14:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1447, "total_steps": 1626, "loss": 1.5648, "learning_rate": 1.0945225055507523e-06, "epoch": 2.6672811059907833, "percentage": 88.99, "elapsed_time": "10:02:33", "remaining_time": "1:14:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1448, "total_steps": 1626, "loss": 1.6347, "learning_rate": 1.0824762151131539e-06, "epoch": 2.6691244239631335, "percentage": 89.05, "elapsed_time": "10:02:57", "remaining_time": "1:14:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1449, "total_steps": 1626, "loss": 1.5996, "learning_rate": 1.0704941007130615e-06, "epoch": 2.670967741935484, "percentage": 89.11, "elapsed_time": "10:03:22", "remaining_time": "1:13:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1450, "total_steps": 1626, "loss": 1.5751, "learning_rate": 1.0585762176020148e-06, "epoch": 2.672811059907834, "percentage": 89.18, "elapsed_time": "10:03:47", "remaining_time": "1:13:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1451, "total_steps": 1626, "loss": 1.642, "learning_rate": 1.0467226207353675e-06, "epoch": 2.6746543778801843, "percentage": 89.24, "elapsed_time": "10:04:12", "remaining_time": "1:12:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1452, "total_steps": 1626, "loss": 1.5754, "learning_rate": 1.0349333647720506e-06, "epoch": 2.6764976958525346, "percentage": 89.3, "elapsed_time": "10:04:37", "remaining_time": "1:12:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1453, "total_steps": 1626, "loss": 1.5425, "learning_rate": 1.0232085040742983e-06, "epoch": 2.678341013824885, "percentage": 89.36, "elapsed_time": "10:05:02", "remaining_time": "1:12:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1454, "total_steps": 1626, "loss": 1.5795, "learning_rate": 1.0115480927074084e-06, "epoch": 2.680184331797235, "percentage": 89.42, "elapsed_time": "10:05:27", "remaining_time": "1:11:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1455, "total_steps": 1626, "loss": 1.586, "learning_rate": 9.999521844394989e-07, "epoch": 2.6820276497695854, "percentage": 89.48, "elapsed_time": "10:05:51", "remaining_time": "1:11:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1456, "total_steps": 1626, "loss": 1.5383, "learning_rate": 9.884208327412458e-07, "epoch": 2.6838709677419352, "percentage": 89.54, "elapsed_time": "10:06:16", "remaining_time": "1:10:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1457, "total_steps": 1626, "loss": 1.5034, "learning_rate": 9.769540907856472e-07, "epoch": 2.685714285714286, "percentage": 89.61, "elapsed_time": "10:06:42", "remaining_time": "1:10:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1458, "total_steps": 1626, "loss": 1.615, "learning_rate": 9.655520114477772e-07, "epoch": 2.6875576036866358, "percentage": 89.67, "elapsed_time": "10:07:06", "remaining_time": "1:09:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1459, "total_steps": 1626, "loss": 1.5786, "learning_rate": 9.542146473045304e-07, "epoch": 2.689400921658986, "percentage": 89.73, "elapsed_time": "10:07:31", "remaining_time": "1:09:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1460, "total_steps": 1626, "loss": 1.517, "learning_rate": 9.429420506343983e-07, "epoch": 2.6912442396313363, "percentage": 89.79, "elapsed_time": "10:07:56", "remaining_time": "1:09:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1461, "total_steps": 1626, "loss": 1.5848, "learning_rate": 9.317342734172213e-07, "epoch": 2.6930875576036866, "percentage": 89.85, "elapsed_time": "10:08:21", "remaining_time": "1:08:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1462, "total_steps": 1626, "loss": 1.614, "learning_rate": 9.205913673339322e-07, "epoch": 2.694930875576037, "percentage": 89.91, "elapsed_time": "10:08:46", "remaining_time": "1:08:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1463, "total_steps": 1626, "loss": 1.5722, "learning_rate": 9.09513383766345e-07, "epoch": 2.696774193548387, "percentage": 89.98, "elapsed_time": "10:09:11", "remaining_time": "1:07:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1464, "total_steps": 1626, "loss": 1.6079, "learning_rate": 8.985003737969011e-07, "epoch": 2.6986175115207374, "percentage": 90.04, "elapsed_time": "10:09:36", "remaining_time": "1:07:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1465, "total_steps": 1626, "loss": 1.5319, "learning_rate": 8.875523882084352e-07, "epoch": 2.7004608294930876, "percentage": 90.1, "elapsed_time": "10:10:00", "remaining_time": "1:07:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1466, "total_steps": 1626, "loss": 1.5664, "learning_rate": 8.766694774839484e-07, "epoch": 2.702304147465438, "percentage": 90.16, "elapsed_time": "10:10:25", "remaining_time": "1:06:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1467, "total_steps": 1626, "loss": 1.5762, "learning_rate": 8.658516918063652e-07, "epoch": 2.704147465437788, "percentage": 90.22, "elapsed_time": "10:10:50", "remaining_time": "1:06:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1468, "total_steps": 1626, "loss": 1.4808, "learning_rate": 8.550990810583137e-07, "epoch": 2.7059907834101384, "percentage": 90.28, "elapsed_time": "10:11:15", "remaining_time": "1:05:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1469, "total_steps": 1626, "loss": 1.6418, "learning_rate": 8.444116948218855e-07, "epoch": 2.7078341013824883, "percentage": 90.34, "elapsed_time": "10:11:40", "remaining_time": "1:05:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1470, "total_steps": 1626, "loss": 1.5463, "learning_rate": 8.337895823784097e-07, "epoch": 2.709677419354839, "percentage": 90.41, "elapsed_time": "10:12:05", "remaining_time": "1:04:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1471, "total_steps": 1626, "loss": 1.5924, "learning_rate": 8.232327927082328e-07, "epoch": 2.711520737327189, "percentage": 90.47, "elapsed_time": "10:12:30", "remaining_time": "1:04:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1472, "total_steps": 1626, "loss": 1.652, "learning_rate": 8.127413744904805e-07, "epoch": 2.713364055299539, "percentage": 90.53, "elapsed_time": "10:12:55", "remaining_time": "1:04:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1473, "total_steps": 1626, "loss": 1.563, "learning_rate": 8.023153761028412e-07, "epoch": 2.7152073732718893, "percentage": 90.59, "elapsed_time": "10:13:20", "remaining_time": "1:03:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1474, "total_steps": 1626, "loss": 1.5652, "learning_rate": 7.919548456213516e-07, "epoch": 2.7170506912442396, "percentage": 90.65, "elapsed_time": "10:13:44", "remaining_time": "1:03:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1475, "total_steps": 1626, "loss": 1.548, "learning_rate": 7.816598308201428e-07, "epoch": 2.71889400921659, "percentage": 90.71, "elapsed_time": "10:14:09", "remaining_time": "1:02:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1476, "total_steps": 1626, "loss": 1.5781, "learning_rate": 7.714303791712646e-07, "epoch": 2.72073732718894, "percentage": 90.77, "elapsed_time": "10:14:34", "remaining_time": "1:02:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1477, "total_steps": 1626, "loss": 1.5243, "learning_rate": 7.612665378444367e-07, "epoch": 2.7225806451612904, "percentage": 90.84, "elapsed_time": "10:14:59", "remaining_time": "1:02:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1478, "total_steps": 1626, "loss": 1.5718, "learning_rate": 7.511683537068293e-07, "epoch": 2.7244239631336407, "percentage": 90.9, "elapsed_time": "10:15:24", "remaining_time": "1:01:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1479, "total_steps": 1626, "loss": 1.5718, "learning_rate": 7.411358733228679e-07, "epoch": 2.726267281105991, "percentage": 90.96, "elapsed_time": "10:15:49", "remaining_time": "1:01:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1480, "total_steps": 1626, "loss": 1.5086, "learning_rate": 7.311691429540058e-07, "epoch": 2.7281105990783407, "percentage": 91.02, "elapsed_time": "10:16:14", "remaining_time": "1:00:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1481, "total_steps": 1626, "loss": 1.5503, "learning_rate": 7.212682085585032e-07, "epoch": 2.7299539170506915, "percentage": 91.08, "elapsed_time": "10:16:38", "remaining_time": "1:00:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1482, "total_steps": 1626, "loss": 1.5159, "learning_rate": 7.114331157912351e-07, "epoch": 2.7317972350230413, "percentage": 91.14, "elapsed_time": "10:17:03", "remaining_time": "0:59:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1483, "total_steps": 1626, "loss": 1.5547, "learning_rate": 7.016639100034627e-07, "epoch": 2.7336405529953915, "percentage": 91.21, "elapsed_time": "10:17:28", "remaining_time": "0:59:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1484, "total_steps": 1626, "loss": 1.563, "learning_rate": 6.919606362426301e-07, "epoch": 2.735483870967742, "percentage": 91.27, "elapsed_time": "10:17:53", "remaining_time": "0:59:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1485, "total_steps": 1626, "loss": 1.6049, "learning_rate": 6.82323339252166e-07, "epoch": 2.737327188940092, "percentage": 91.33, "elapsed_time": "10:18:18", "remaining_time": "0:58:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1486, "total_steps": 1626, "loss": 1.5664, "learning_rate": 6.727520634712614e-07, "epoch": 2.7391705069124423, "percentage": 91.39, "elapsed_time": "10:18:43", "remaining_time": "0:58:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1487, "total_steps": 1626, "loss": 1.4837, "learning_rate": 6.632468530346736e-07, "epoch": 2.7410138248847926, "percentage": 91.45, "elapsed_time": "10:19:07", "remaining_time": "0:57:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1488, "total_steps": 1626, "loss": 1.5564, "learning_rate": 6.538077517725255e-07, "epoch": 2.742857142857143, "percentage": 91.51, "elapsed_time": "10:19:32", "remaining_time": "0:57:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1489, "total_steps": 1626, "loss": 1.572, "learning_rate": 6.444348032100955e-07, "epoch": 2.744700460829493, "percentage": 91.57, "elapsed_time": "10:19:57", "remaining_time": "0:57:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1490, "total_steps": 1626, "loss": 1.489, "learning_rate": 6.351280505676227e-07, "epoch": 2.7465437788018434, "percentage": 91.64, "elapsed_time": "10:20:22", "remaining_time": "0:56:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1491, "total_steps": 1626, "loss": 1.51, "learning_rate": 6.258875367601052e-07, "epoch": 2.7483870967741937, "percentage": 91.7, "elapsed_time": "10:20:47", "remaining_time": "0:56:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1492, "total_steps": 1626, "loss": 1.5545, "learning_rate": 6.167133043971024e-07, "epoch": 2.750230414746544, "percentage": 91.76, "elapsed_time": "10:21:13", "remaining_time": "0:55:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1493, "total_steps": 1626, "loss": 1.54, "learning_rate": 6.076053957825411e-07, "epoch": 2.7520737327188938, "percentage": 91.82, "elapsed_time": "10:21:37", "remaining_time": "0:55:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1494, "total_steps": 1626, "loss": 1.5578, "learning_rate": 5.985638529145115e-07, "epoch": 2.7539170506912445, "percentage": 91.88, "elapsed_time": "10:22:02", "remaining_time": "0:54:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1495, "total_steps": 1626, "loss": 1.5551, "learning_rate": 5.895887174850866e-07, "epoch": 2.7557603686635943, "percentage": 91.94, "elapsed_time": "10:22:27", "remaining_time": "0:54:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1496, "total_steps": 1626, "loss": 1.5231, "learning_rate": 5.80680030880128e-07, "epoch": 2.7576036866359446, "percentage": 92.0, "elapsed_time": "10:22:52", "remaining_time": "0:54:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1497, "total_steps": 1626, "loss": 1.6274, "learning_rate": 5.718378341790754e-07, "epoch": 2.759447004608295, "percentage": 92.07, "elapsed_time": "10:23:17", "remaining_time": "0:53:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1498, "total_steps": 1626, "loss": 1.5893, "learning_rate": 5.630621681547871e-07, "epoch": 2.761290322580645, "percentage": 92.13, "elapsed_time": "10:23:41", "remaining_time": "0:53:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1499, "total_steps": 1626, "loss": 1.5875, "learning_rate": 5.543530732733304e-07, "epoch": 2.7631336405529954, "percentage": 92.19, "elapsed_time": "10:24:06", "remaining_time": "0:52:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1500, "total_steps": 1626, "loss": 1.5718, "learning_rate": 5.457105896937997e-07, "epoch": 2.7649769585253456, "percentage": 92.25, "elapsed_time": "10:24:31", "remaining_time": "0:52:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1501, "total_steps": 1626, "loss": 1.5697, "learning_rate": 5.371347572681434e-07, "epoch": 2.766820276497696, "percentage": 92.31, "elapsed_time": "10:24:56", "remaining_time": "0:52:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1502, "total_steps": 1626, "loss": 1.5994, "learning_rate": 5.286256155409607e-07, "epoch": 2.768663594470046, "percentage": 92.37, "elapsed_time": "10:25:21", "remaining_time": "0:51:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1503, "total_steps": 1626, "loss": 1.5469, "learning_rate": 5.201832037493304e-07, "epoch": 2.7705069124423964, "percentage": 92.44, "elapsed_time": "10:25:46", "remaining_time": "0:51:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1504, "total_steps": 1626, "loss": 1.5571, "learning_rate": 5.118075608226335e-07, "epoch": 2.7723502304147467, "percentage": 92.5, "elapsed_time": "10:26:11", "remaining_time": "0:50:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1505, "total_steps": 1626, "loss": 1.6303, "learning_rate": 5.034987253823614e-07, "epoch": 2.774193548387097, "percentage": 92.56, "elapsed_time": "10:26:35", "remaining_time": "0:50:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1506, "total_steps": 1626, "loss": 1.5158, "learning_rate": 4.952567357419496e-07, "epoch": 2.776036866359447, "percentage": 92.62, "elapsed_time": "10:27:00", "remaining_time": "0:49:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1507, "total_steps": 1626, "loss": 1.5806, "learning_rate": 4.870816299065956e-07, "epoch": 2.7778801843317975, "percentage": 92.68, "elapsed_time": "10:27:25", "remaining_time": "0:49:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1508, "total_steps": 1626, "loss": 1.5492, "learning_rate": 4.789734455730848e-07, "epoch": 2.7797235023041473, "percentage": 92.74, "elapsed_time": "10:27:50", "remaining_time": "0:49:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1509, "total_steps": 1626, "loss": 1.5876, "learning_rate": 4.709322201296168e-07, "epoch": 2.7815668202764976, "percentage": 92.8, "elapsed_time": "10:28:15", "remaining_time": "0:48:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1510, "total_steps": 1626, "loss": 1.6046, "learning_rate": 4.629579906556258e-07, "epoch": 2.783410138248848, "percentage": 92.87, "elapsed_time": "10:28:40", "remaining_time": "0:48:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1511, "total_steps": 1626, "loss": 1.5784, "learning_rate": 4.5505079392162696e-07, "epoch": 2.785253456221198, "percentage": 92.93, "elapsed_time": "10:29:05", "remaining_time": "0:47:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1512, "total_steps": 1626, "loss": 1.5573, "learning_rate": 4.4721066638903405e-07, "epoch": 2.7870967741935484, "percentage": 92.99, "elapsed_time": "10:29:30", "remaining_time": "0:47:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1513, "total_steps": 1626, "loss": 1.5233, "learning_rate": 4.3943764420998344e-07, "epoch": 2.7889400921658987, "percentage": 93.05, "elapsed_time": "10:29:54", "remaining_time": "0:47:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1514, "total_steps": 1626, "loss": 1.6014, "learning_rate": 4.317317632271889e-07, "epoch": 2.790783410138249, "percentage": 93.11, "elapsed_time": "10:30:19", "remaining_time": "0:46:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1515, "total_steps": 1626, "loss": 1.6216, "learning_rate": 4.2409305897376015e-07, "epoch": 2.792626728110599, "percentage": 93.17, "elapsed_time": "10:30:44", "remaining_time": "0:46:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1516, "total_steps": 1626, "loss": 1.528, "learning_rate": 4.165215666730415e-07, "epoch": 2.7944700460829495, "percentage": 93.23, "elapsed_time": "10:31:09", "remaining_time": "0:45:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1517, "total_steps": 1626, "loss": 1.5767, "learning_rate": 4.090173212384601e-07, "epoch": 2.7963133640552993, "percentage": 93.3, "elapsed_time": "10:31:34", "remaining_time": "0:45:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1518, "total_steps": 1626, "loss": 1.536, "learning_rate": 4.015803572733462e-07, "epoch": 2.79815668202765, "percentage": 93.36, "elapsed_time": "10:31:59", "remaining_time": "0:44:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1519, "total_steps": 1626, "loss": 1.6378, "learning_rate": 3.9421070907078973e-07, "epoch": 2.8, "percentage": 93.42, "elapsed_time": "10:32:24", "remaining_time": "0:44:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1520, "total_steps": 1626, "loss": 1.5523, "learning_rate": 3.869084106134757e-07, "epoch": 2.80184331797235, "percentage": 93.48, "elapsed_time": "10:32:48", "remaining_time": "0:44:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1521, "total_steps": 1626, "loss": 1.5414, "learning_rate": 3.796734955735276e-07, "epoch": 2.8036866359447004, "percentage": 93.54, "elapsed_time": "10:33:13", "remaining_time": "0:43:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1522, "total_steps": 1626, "loss": 1.5346, "learning_rate": 3.725059973123507e-07, "epoch": 2.8055299539170506, "percentage": 93.6, "elapsed_time": "10:33:38", "remaining_time": "0:43:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1523, "total_steps": 1626, "loss": 1.5582, "learning_rate": 3.654059488804856e-07, "epoch": 2.807373271889401, "percentage": 93.67, "elapsed_time": "10:34:03", "remaining_time": "0:42:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1524, "total_steps": 1626, "loss": 1.5685, "learning_rate": 3.5837338301744516e-07, "epoch": 2.809216589861751, "percentage": 93.73, "elapsed_time": "10:34:28", "remaining_time": "0:42:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1525, "total_steps": 1626, "loss": 1.5728, "learning_rate": 3.5140833215157097e-07, "epoch": 2.8110599078341014, "percentage": 93.79, "elapsed_time": "10:34:53", "remaining_time": "0:42:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1526, "total_steps": 1626, "loss": 1.561, "learning_rate": 3.445108283998805e-07, "epoch": 2.8129032258064517, "percentage": 93.85, "elapsed_time": "10:35:18", "remaining_time": "0:41:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1527, "total_steps": 1626, "loss": 1.5522, "learning_rate": 3.376809035679218e-07, "epoch": 2.814746543778802, "percentage": 93.91, "elapsed_time": "10:35:43", "remaining_time": "0:41:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1528, "total_steps": 1626, "loss": 1.6082, "learning_rate": 3.3091858914962415e-07, "epoch": 2.8165898617511522, "percentage": 93.97, "elapsed_time": "10:36:08", "remaining_time": "0:40:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1529, "total_steps": 1626, "loss": 1.5906, "learning_rate": 3.2422391632715265e-07, "epoch": 2.8184331797235025, "percentage": 94.03, "elapsed_time": "10:36:32", "remaining_time": "0:40:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1530, "total_steps": 1626, "loss": 1.5849, "learning_rate": 3.1759691597076865e-07, "epoch": 2.8202764976958523, "percentage": 94.1, "elapsed_time": "10:36:57", "remaining_time": "0:39:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1531, "total_steps": 1626, "loss": 1.5678, "learning_rate": 3.1103761863868486e-07, "epoch": 2.822119815668203, "percentage": 94.16, "elapsed_time": "10:37:22", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1532, "total_steps": 1626, "loss": 1.5691, "learning_rate": 3.045460545769152e-07, "epoch": 2.823963133640553, "percentage": 94.22, "elapsed_time": "10:37:47", "remaining_time": "0:39:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1533, "total_steps": 1626, "loss": 1.5847, "learning_rate": 2.981222537191586e-07, "epoch": 2.825806451612903, "percentage": 94.28, "elapsed_time": "10:38:12", "remaining_time": "0:38:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1534, "total_steps": 1626, "loss": 1.5011, "learning_rate": 2.9176624568663377e-07, "epoch": 2.8276497695852534, "percentage": 94.34, "elapsed_time": "10:38:37", "remaining_time": "0:38:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1535, "total_steps": 1626, "loss": 1.5143, "learning_rate": 2.854780597879614e-07, "epoch": 2.8294930875576036, "percentage": 94.4, "elapsed_time": "10:39:02", "remaining_time": "0:37:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1536, "total_steps": 1626, "loss": 1.5417, "learning_rate": 2.792577250190237e-07, "epoch": 2.831336405529954, "percentage": 94.46, "elapsed_time": "10:39:26", "remaining_time": "0:37:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1537, "total_steps": 1626, "loss": 1.5393, "learning_rate": 2.7310527006282505e-07, "epoch": 2.833179723502304, "percentage": 94.53, "elapsed_time": "10:39:51", "remaining_time": "0:37:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1538, "total_steps": 1626, "loss": 1.536, "learning_rate": 2.670207232893684e-07, "epoch": 2.8350230414746544, "percentage": 94.59, "elapsed_time": "10:40:16", "remaining_time": "0:36:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1539, "total_steps": 1626, "loss": 1.5469, "learning_rate": 2.610041127555224e-07, "epoch": 2.8368663594470047, "percentage": 94.65, "elapsed_time": "10:40:41", "remaining_time": "0:36:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1540, "total_steps": 1626, "loss": 1.5668, "learning_rate": 2.5505546620488597e-07, "epoch": 2.838709677419355, "percentage": 94.71, "elapsed_time": "10:41:06", "remaining_time": "0:35:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1541, "total_steps": 1626, "loss": 1.6614, "learning_rate": 2.4917481106766394e-07, "epoch": 2.840552995391705, "percentage": 94.77, "elapsed_time": "10:41:31", "remaining_time": "0:35:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1542, "total_steps": 1626, "loss": 1.5881, "learning_rate": 2.433621744605502e-07, "epoch": 2.8423963133640555, "percentage": 94.83, "elapsed_time": "10:41:56", "remaining_time": "0:34:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1543, "total_steps": 1626, "loss": 1.5014, "learning_rate": 2.3761758318658121e-07, "epoch": 2.8442396313364053, "percentage": 94.9, "elapsed_time": "10:42:21", "remaining_time": "0:34:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1544, "total_steps": 1626, "loss": 1.564, "learning_rate": 2.3194106373503443e-07, "epoch": 2.8460829493087556, "percentage": 94.96, "elapsed_time": "10:42:46", "remaining_time": "0:34:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1545, "total_steps": 1626, "loss": 1.635, "learning_rate": 2.2633264228129336e-07, "epoch": 2.847926267281106, "percentage": 95.02, "elapsed_time": "10:43:11", "remaining_time": "0:33:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1546, "total_steps": 1626, "loss": 1.6251, "learning_rate": 2.2079234468672938e-07, "epoch": 2.849769585253456, "percentage": 95.08, "elapsed_time": "10:43:36", "remaining_time": "0:33:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1547, "total_steps": 1626, "loss": 1.4972, "learning_rate": 2.1532019649858513e-07, "epoch": 2.8516129032258064, "percentage": 95.14, "elapsed_time": "10:44:00", "remaining_time": "0:32:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1548, "total_steps": 1626, "loss": 1.5408, "learning_rate": 2.0991622294985303e-07, "epoch": 2.8534562211981567, "percentage": 95.2, "elapsed_time": "10:44:25", "remaining_time": "0:32:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1549, "total_steps": 1626, "loss": 1.554, "learning_rate": 2.0458044895916516e-07, "epoch": 2.855299539170507, "percentage": 95.26, "elapsed_time": "10:44:50", "remaining_time": "0:32:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1550, "total_steps": 1626, "loss": 1.5957, "learning_rate": 1.9931289913066697e-07, "epoch": 2.857142857142857, "percentage": 95.33, "elapsed_time": "10:45:15", "remaining_time": "0:31:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1551, "total_steps": 1626, "loss": 1.5238, "learning_rate": 1.9411359775391547e-07, "epoch": 2.8589861751152075, "percentage": 95.39, "elapsed_time": "10:45:40", "remaining_time": "0:31:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1552, "total_steps": 1626, "loss": 1.5956, "learning_rate": 1.8898256880376273e-07, "epoch": 2.8608294930875577, "percentage": 95.45, "elapsed_time": "10:46:05", "remaining_time": "0:30:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1553, "total_steps": 1626, "loss": 1.5318, "learning_rate": 1.8391983594024443e-07, "epoch": 2.862672811059908, "percentage": 95.51, "elapsed_time": "10:46:33", "remaining_time": "0:30:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1554, "total_steps": 1626, "loss": 1.636, "learning_rate": 1.7892542250846966e-07, "epoch": 2.864516129032258, "percentage": 95.57, "elapsed_time": "10:46:58", "remaining_time": "0:29:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1555, "total_steps": 1626, "loss": 1.5658, "learning_rate": 1.7399935153851798e-07, "epoch": 2.8663594470046085, "percentage": 95.63, "elapsed_time": "10:47:23", "remaining_time": "0:29:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1556, "total_steps": 1626, "loss": 1.6034, "learning_rate": 1.691416457453293e-07, "epoch": 2.8682027649769584, "percentage": 95.69, "elapsed_time": "10:47:48", "remaining_time": "0:29:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1557, "total_steps": 1626, "loss": 1.5438, "learning_rate": 1.6435232752860074e-07, "epoch": 2.8700460829493086, "percentage": 95.76, "elapsed_time": "10:48:13", "remaining_time": "0:28:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1558, "total_steps": 1626, "loss": 1.5456, "learning_rate": 1.5963141897267998e-07, "epoch": 2.871889400921659, "percentage": 95.82, "elapsed_time": "10:48:38", "remaining_time": "0:28:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1559, "total_steps": 1626, "loss": 1.5934, "learning_rate": 1.5497894184647033e-07, "epoch": 2.873732718894009, "percentage": 95.88, "elapsed_time": "10:49:03", "remaining_time": "0:27:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1560, "total_steps": 1626, "loss": 1.5685, "learning_rate": 1.503949176033259e-07, "epoch": 2.8755760368663594, "percentage": 95.94, "elapsed_time": "10:49:28", "remaining_time": "0:27:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1561, "total_steps": 1626, "loss": 1.5928, "learning_rate": 1.4587936738094665e-07, "epoch": 2.8774193548387097, "percentage": 96.0, "elapsed_time": "10:49:53", "remaining_time": "0:27:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1562, "total_steps": 1626, "loss": 1.5768, "learning_rate": 1.4143231200129835e-07, "epoch": 2.87926267281106, "percentage": 96.06, "elapsed_time": "10:50:18", "remaining_time": "0:26:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1563, "total_steps": 1626, "loss": 1.5445, "learning_rate": 1.3705377197049617e-07, "epoch": 2.8811059907834102, "percentage": 96.13, "elapsed_time": "10:50:42", "remaining_time": "0:26:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1564, "total_steps": 1626, "loss": 1.546, "learning_rate": 1.327437674787213e-07, "epoch": 2.8829493087557605, "percentage": 96.19, "elapsed_time": "10:51:08", "remaining_time": "0:25:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1565, "total_steps": 1626, "loss": 1.5719, "learning_rate": 1.285023184001327e-07, "epoch": 2.8847926267281108, "percentage": 96.25, "elapsed_time": "10:51:33", "remaining_time": "0:25:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1566, "total_steps": 1626, "loss": 1.6046, "learning_rate": 1.2432944429275894e-07, "epoch": 2.886635944700461, "percentage": 96.31, "elapsed_time": "10:51:58", "remaining_time": "0:24:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1567, "total_steps": 1626, "loss": 1.5801, "learning_rate": 1.2022516439842478e-07, "epoch": 2.888479262672811, "percentage": 96.37, "elapsed_time": "10:52:23", "remaining_time": "0:24:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1568, "total_steps": 1626, "loss": 1.5522, "learning_rate": 1.1618949764265474e-07, "epoch": 2.8903225806451616, "percentage": 96.43, "elapsed_time": "10:52:48", "remaining_time": "0:24:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1569, "total_steps": 1626, "loss": 1.5877, "learning_rate": 1.1222246263458469e-07, "epoch": 2.8921658986175114, "percentage": 96.49, "elapsed_time": "10:53:13", "remaining_time": "0:23:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1570, "total_steps": 1626, "loss": 1.6424, "learning_rate": 1.0832407766687535e-07, "epoch": 2.8940092165898617, "percentage": 96.56, "elapsed_time": "10:53:37", "remaining_time": "0:23:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1571, "total_steps": 1626, "loss": 1.6119, "learning_rate": 1.04494360715639e-07, "epoch": 2.895852534562212, "percentage": 96.62, "elapsed_time": "10:54:02", "remaining_time": "0:22:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1572, "total_steps": 1626, "loss": 1.5196, "learning_rate": 1.0073332944034119e-07, "epoch": 2.897695852534562, "percentage": 96.68, "elapsed_time": "10:54:27", "remaining_time": "0:22:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1573, "total_steps": 1626, "loss": 1.5891, "learning_rate": 9.704100118372583e-08, "epoch": 2.8995391705069125, "percentage": 96.74, "elapsed_time": "10:54:52", "remaining_time": "0:22:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1574, "total_steps": 1626, "loss": 1.5766, "learning_rate": 9.34173929717419e-08, "epoch": 2.9013824884792627, "percentage": 96.8, "elapsed_time": "10:55:17", "remaining_time": "0:21:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1575, "total_steps": 1626, "loss": 1.6159, "learning_rate": 8.986252151345353e-08, "epoch": 2.903225806451613, "percentage": 96.86, "elapsed_time": "10:55:42", "remaining_time": "0:21:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1576, "total_steps": 1626, "loss": 1.5603, "learning_rate": 8.63764032009684e-08, "epoch": 2.9050691244239633, "percentage": 96.92, "elapsed_time": "10:56:07", "remaining_time": "0:20:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1577, "total_steps": 1626, "loss": 1.5659, "learning_rate": 8.295905410936277e-08, "epoch": 2.9069124423963135, "percentage": 96.99, "elapsed_time": "10:56:32", "remaining_time": "0:20:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1578, "total_steps": 1626, "loss": 1.5797, "learning_rate": 7.961048999660991e-08, "epoch": 2.9087557603686633, "percentage": 97.05, "elapsed_time": "10:56:57", "remaining_time": "0:19:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1579, "total_steps": 1626, "loss": 1.5419, "learning_rate": 7.63307263034968e-08, "epoch": 2.910599078341014, "percentage": 97.11, "elapsed_time": "10:57:22", "remaining_time": "0:19:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1580, "total_steps": 1626, "loss": 1.5759, "learning_rate": 7.311977815356585e-08, "epoch": 2.912442396313364, "percentage": 97.17, "elapsed_time": "10:57:46", "remaining_time": "0:19:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1581, "total_steps": 1626, "loss": 1.5522, "learning_rate": 6.997766035303832e-08, "epoch": 2.914285714285714, "percentage": 97.23, "elapsed_time": "10:58:11", "remaining_time": "0:18:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1582, "total_steps": 1626, "loss": 1.5924, "learning_rate": 6.690438739074767e-08, "epoch": 2.9161290322580644, "percentage": 97.29, "elapsed_time": "10:58:36", "remaining_time": "0:18:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1583, "total_steps": 1626, "loss": 1.5906, "learning_rate": 6.389997343806797e-08, "epoch": 2.9179723502304147, "percentage": 97.36, "elapsed_time": "10:59:01", "remaining_time": "0:17:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1584, "total_steps": 1626, "loss": 1.5351, "learning_rate": 6.096443234885729e-08, "epoch": 2.919815668202765, "percentage": 97.42, "elapsed_time": "10:59:26", "remaining_time": "0:17:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1585, "total_steps": 1626, "loss": 1.5237, "learning_rate": 5.809777765939106e-08, "epoch": 2.921658986175115, "percentage": 97.48, "elapsed_time": "10:59:51", "remaining_time": "0:17:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1586, "total_steps": 1626, "loss": 1.545, "learning_rate": 5.530002258829048e-08, "epoch": 2.9235023041474655, "percentage": 97.54, "elapsed_time": "11:00:17", "remaining_time": "0:16:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1587, "total_steps": 1626, "loss": 1.5029, "learning_rate": 5.257118003647754e-08, "epoch": 2.9253456221198157, "percentage": 97.6, "elapsed_time": "11:00:42", "remaining_time": "0:16:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1588, "total_steps": 1626, "loss": 1.5609, "learning_rate": 4.991126258710177e-08, "epoch": 2.927188940092166, "percentage": 97.66, "elapsed_time": "11:01:07", "remaining_time": "0:15:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1589, "total_steps": 1626, "loss": 1.5528, "learning_rate": 4.732028250548692e-08, "epoch": 2.9290322580645163, "percentage": 97.72, "elapsed_time": "11:01:32", "remaining_time": "0:15:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1590, "total_steps": 1626, "loss": 1.5497, "learning_rate": 4.479825173908103e-08, "epoch": 2.9308755760368665, "percentage": 97.79, "elapsed_time": "11:01:57", "remaining_time": "0:14:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1591, "total_steps": 1626, "loss": 1.5361, "learning_rate": 4.234518191738645e-08, "epoch": 2.9327188940092164, "percentage": 97.85, "elapsed_time": "11:02:22", "remaining_time": "0:14:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1592, "total_steps": 1626, "loss": 1.5902, "learning_rate": 3.996108435192325e-08, "epoch": 2.934562211981567, "percentage": 97.91, "elapsed_time": "11:02:47", "remaining_time": "0:14:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1593, "total_steps": 1626, "loss": 1.5223, "learning_rate": 3.764597003616421e-08, "epoch": 2.936405529953917, "percentage": 97.97, "elapsed_time": "11:03:11", "remaining_time": "0:13:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1594, "total_steps": 1626, "loss": 1.589, "learning_rate": 3.539984964548826e-08, "epoch": 2.938248847926267, "percentage": 98.03, "elapsed_time": "11:03:36", "remaining_time": "0:13:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1595, "total_steps": 1626, "loss": 1.6003, "learning_rate": 3.322273353713712e-08, "epoch": 2.9400921658986174, "percentage": 98.09, "elapsed_time": "11:04:02", "remaining_time": "0:12:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1596, "total_steps": 1626, "loss": 1.6059, "learning_rate": 3.111463175015539e-08, "epoch": 2.9419354838709677, "percentage": 98.15, "elapsed_time": "11:04:27", "remaining_time": "0:12:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1597, "total_steps": 1626, "loss": 1.5694, "learning_rate": 2.907555400535389e-08, "epoch": 2.943778801843318, "percentage": 98.22, "elapsed_time": "11:04:52", "remaining_time": "0:12:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1598, "total_steps": 1626, "loss": 1.5491, "learning_rate": 2.710550970526471e-08, "epoch": 2.9456221198156682, "percentage": 98.28, "elapsed_time": "11:05:16", "remaining_time": "0:11:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1599, "total_steps": 1626, "loss": 1.5421, "learning_rate": 2.5204507934091236e-08, "epoch": 2.9474654377880185, "percentage": 98.34, "elapsed_time": "11:05:41", "remaining_time": "0:11:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1600, "total_steps": 1626, "loss": 1.6343, "learning_rate": 2.3372557457673194e-08, "epoch": 2.9493087557603688, "percentage": 98.4, "elapsed_time": "11:06:06", "remaining_time": "0:10:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1601, "total_steps": 1626, "loss": 1.5433, "learning_rate": 2.1609666723438336e-08, "epoch": 2.951152073732719, "percentage": 98.46, "elapsed_time": "11:06:41", "remaining_time": "0:10:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1602, "total_steps": 1626, "loss": 1.5855, "learning_rate": 1.991584386037415e-08, "epoch": 2.952995391705069, "percentage": 98.52, "elapsed_time": "11:07:06", "remaining_time": "0:09:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1603, "total_steps": 1626, "loss": 1.5476, "learning_rate": 1.8291096678982877e-08, "epoch": 2.9548387096774196, "percentage": 98.59, "elapsed_time": "11:07:31", "remaining_time": "0:09:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1604, "total_steps": 1626, "loss": 1.5871, "learning_rate": 1.6735432671243223e-08, "epoch": 2.9566820276497694, "percentage": 98.65, "elapsed_time": "11:07:56", "remaining_time": "0:09:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1605, "total_steps": 1626, "loss": 1.6034, "learning_rate": 1.524885901058537e-08, "epoch": 2.9585253456221197, "percentage": 98.71, "elapsed_time": "11:08:21", "remaining_time": "0:08:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1606, "total_steps": 1626, "loss": 1.5798, "learning_rate": 1.3831382551849348e-08, "epoch": 2.96036866359447, "percentage": 98.77, "elapsed_time": "11:08:46", "remaining_time": "0:08:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1607, "total_steps": 1626, "loss": 1.5404, "learning_rate": 1.248300983125672e-08, "epoch": 2.96221198156682, "percentage": 98.83, "elapsed_time": "11:09:10", "remaining_time": "0:07:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1608, "total_steps": 1626, "loss": 1.6063, "learning_rate": 1.120374706638061e-08, "epoch": 2.9640552995391705, "percentage": 98.89, "elapsed_time": "11:09:35", "remaining_time": "0:07:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1609, "total_steps": 1626, "loss": 1.5628, "learning_rate": 9.993600156117389e-09, "epoch": 2.9658986175115207, "percentage": 98.95, "elapsed_time": "11:10:01", "remaining_time": "0:07:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1610, "total_steps": 1626, "loss": 1.5652, "learning_rate": 8.852574680655035e-09, "epoch": 2.967741935483871, "percentage": 99.02, "elapsed_time": "11:10:26", "remaining_time": "0:06:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1611, "total_steps": 1626, "loss": 1.5817, "learning_rate": 7.780675901454815e-09, "epoch": 2.9695852534562213, "percentage": 99.08, "elapsed_time": "11:10:51", "remaining_time": "0:06:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1612, "total_steps": 1626, "loss": 1.543, "learning_rate": 6.7779087612229726e-09, "epoch": 2.9714285714285715, "percentage": 99.14, "elapsed_time": "11:11:16", "remaining_time": "0:05:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1613, "total_steps": 1626, "loss": 1.5665, "learning_rate": 5.844277883884086e-09, "epoch": 2.973271889400922, "percentage": 99.2, "elapsed_time": "11:11:41", "remaining_time": "0:05:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1614, "total_steps": 1626, "loss": 1.5279, "learning_rate": 4.979787574569406e-09, "epoch": 2.975115207373272, "percentage": 99.26, "elapsed_time": "11:12:05", "remaining_time": "0:04:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1615, "total_steps": 1626, "loss": 1.5931, "learning_rate": 4.184441819588547e-09, "epoch": 2.976958525345622, "percentage": 99.32, "elapsed_time": "11:12:30", "remaining_time": "0:04:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1616, "total_steps": 1626, "loss": 1.5383, "learning_rate": 3.4582442864145026e-09, "epoch": 2.9788018433179726, "percentage": 99.38, "elapsed_time": "11:12:55", "remaining_time": "0:04:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1617, "total_steps": 1626, "loss": 1.5268, "learning_rate": 2.8011983236636563e-09, "epoch": 2.9806451612903224, "percentage": 99.45, "elapsed_time": "11:13:20", "remaining_time": "0:03:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1618, "total_steps": 1626, "loss": 1.6195, "learning_rate": 2.2133069610874577e-09, "epoch": 2.9824884792626727, "percentage": 99.51, "elapsed_time": "11:13:45", "remaining_time": "0:03:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1619, "total_steps": 1626, "loss": 1.5856, "learning_rate": 1.6945729095507733e-09, "epoch": 2.984331797235023, "percentage": 99.57, "elapsed_time": "11:14:10", "remaining_time": "0:02:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1620, "total_steps": 1626, "loss": 1.5529, "learning_rate": 1.2449985610235582e-09, "epoch": 2.986175115207373, "percentage": 99.63, "elapsed_time": "11:14:35", "remaining_time": "0:02:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1621, "total_steps": 1626, "loss": 1.565, "learning_rate": 8.645859885675345e-10, "epoch": 2.9880184331797235, "percentage": 99.69, "elapsed_time": "11:15:00", "remaining_time": "0:02:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1622, "total_steps": 1626, "loss": 1.5186, "learning_rate": 5.533369463311954e-10, "epoch": 2.9898617511520738, "percentage": 99.75, "elapsed_time": "11:15:25", "remaining_time": "0:01:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1623, "total_steps": 1626, "loss": 1.5845, "learning_rate": 3.1125286953481715e-10, "epoch": 2.991705069124424, "percentage": 99.82, "elapsed_time": "11:15:49", "remaining_time": "0:01:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1624, "total_steps": 1626, "loss": 1.6308, "learning_rate": 1.3833487446712757e-10, "epoch": 2.9935483870967743, "percentage": 99.88, "elapsed_time": "11:16:14", "remaining_time": "0:00:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1625, "total_steps": 1626, "loss": 1.5764, "learning_rate": 3.4583758485307036e-11, "epoch": 2.9953917050691246, "percentage": 99.94, "elapsed_time": "11:16:39", "remaining_time": "0:00:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1626, "total_steps": 1626, "loss": 1.6018, "learning_rate": 0.0, "epoch": 2.9972350230414744, "percentage": 100.0, "elapsed_time": "11:17:04", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1626, "total_steps": 1626, "epoch": 2.9972350230414744, "percentage": 100.0, "elapsed_time": "11:17:04", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}