| {"current_steps": 5, "total_steps": 282, "loss": 0.2185, "lr": 4.997518240705502e-05, "epoch": 0.053475935828877004, "percentage": 1.77, "elapsed_time": "0:01:31", "remaining_time": "1:24:21", "throughput": 3058.36, "total_tokens": 279408} | |
| {"current_steps": 10, "total_steps": 282, "loss": 0.1329, "lr": 4.9874445377212606e-05, "epoch": 0.10695187165775401, "percentage": 3.55, "elapsed_time": "0:03:05", "remaining_time": "1:24:06", "throughput": 3055.2, "total_tokens": 566864} | |
| {"current_steps": 15, "total_steps": 282, "loss": 0.1124, "lr": 4.969655004749674e-05, "epoch": 0.16042780748663102, "percentage": 5.32, "elapsed_time": "0:04:43", "remaining_time": "1:23:58", "throughput": 3042.04, "total_tokens": 861088} | |
| {"current_steps": 20, "total_steps": 282, "loss": 0.0841, "lr": 4.944204823327408e-05, "epoch": 0.21390374331550802, "percentage": 7.09, "elapsed_time": "0:06:18", "remaining_time": "1:22:42", "throughput": 3046.79, "total_tokens": 1154080} | |
| {"current_steps": 25, "total_steps": 282, "loss": 0.067, "lr": 4.911172937635942e-05, "epoch": 0.26737967914438504, "percentage": 8.87, "elapsed_time": "0:07:51", "remaining_time": "1:20:46", "throughput": 3053.41, "total_tokens": 1439584} | |
| {"current_steps": 30, "total_steps": 282, "loss": 0.0633, "lr": 4.870661809623788e-05, "epoch": 0.32085561497326204, "percentage": 10.64, "elapsed_time": "0:09:23", "remaining_time": "1:18:51", "throughput": 3059.39, "total_tokens": 1723424} | |
| {"current_steps": 35, "total_steps": 282, "loss": 0.0508, "lr": 4.8227971011787196e-05, "epoch": 0.37433155080213903, "percentage": 12.41, "elapsed_time": "0:10:56", "remaining_time": "1:17:12", "throughput": 3062.17, "total_tokens": 2010112} | |
| {"current_steps": 40, "total_steps": 282, "loss": 0.0452, "lr": 4.767727284335852e-05, "epoch": 0.42780748663101603, "percentage": 14.18, "elapsed_time": "0:12:28", "remaining_time": "1:15:28", "throughput": 3064.58, "total_tokens": 2293712} | |
| {"current_steps": 45, "total_steps": 282, "loss": 0.0401, "lr": 4.705623180730705e-05, "epoch": 0.48128342245989303, "percentage": 15.96, "elapsed_time": "0:14:01", "remaining_time": "1:13:52", "throughput": 3064.56, "total_tokens": 2579088} | |
| {"current_steps": 50, "total_steps": 282, "loss": 0.0418, "lr": 4.6366774317257946e-05, "epoch": 0.5347593582887701, "percentage": 17.73, "elapsed_time": "0:15:33", "remaining_time": "1:12:13", "throughput": 3066.16, "total_tokens": 2863376} | |
| {"current_steps": 55, "total_steps": 282, "loss": 0.0468, "lr": 4.561103900854401e-05, "epoch": 0.5882352941176471, "percentage": 19.5, "elapsed_time": "0:17:10", "remaining_time": "1:10:53", "throughput": 3063.56, "total_tokens": 3157536} | |
| {"current_steps": 60, "total_steps": 282, "loss": 0.0421, "lr": 4.479137010435053e-05, "epoch": 0.6417112299465241, "percentage": 21.28, "elapsed_time": "0:18:41", "remaining_time": "1:09:10", "throughput": 3065.33, "total_tokens": 3438464} | |
| {"current_steps": 65, "total_steps": 282, "loss": 0.04, "lr": 4.391031014414514e-05, "epoch": 0.6951871657754011, "percentage": 23.05, "elapsed_time": "0:20:15", "remaining_time": "1:07:38", "throughput": 3065.66, "total_tokens": 3726720} | |
| {"current_steps": 70, "total_steps": 282, "loss": 0.0279, "lr": 4.2970592096948236e-05, "epoch": 0.7486631016042781, "percentage": 24.82, "elapsed_time": "0:21:48", "remaining_time": "1:06:02", "throughput": 3066.01, "total_tokens": 4011152} | |
| {"current_steps": 75, "total_steps": 282, "loss": 0.0322, "lr": 4.197513088390813e-05, "epoch": 0.8021390374331551, "percentage": 26.6, "elapsed_time": "0:23:20", "remaining_time": "1:04:24", "throughput": 3067.38, "total_tokens": 4294992} | |
| {"current_steps": 80, "total_steps": 282, "loss": 0.034, "lr": 4.092701433647687e-05, "epoch": 0.8556149732620321, "percentage": 28.37, "elapsed_time": "0:24:52", "remaining_time": "1:02:48", "throughput": 3068.16, "total_tokens": 4579744} | |
| {"current_steps": 85, "total_steps": 282, "loss": 0.0388, "lr": 3.982949361823388e-05, "epoch": 0.9090909090909091, "percentage": 30.14, "elapsed_time": "0:26:21", "remaining_time": "1:01:05", "throughput": 3070.18, "total_tokens": 4856256} | |
| {"current_steps": 90, "total_steps": 282, "loss": 0.0395, "lr": 3.8685973140068e-05, "epoch": 0.9625668449197861, "percentage": 31.91, "elapsed_time": "0:27:49", "remaining_time": "0:59:21", "throughput": 3073.05, "total_tokens": 5130032} | |
| {"current_steps": 95, "total_steps": 282, "loss": 0.03, "lr": 3.7500000000000003e-05, "epoch": 1.0106951871657754, "percentage": 33.69, "elapsed_time": "0:29:16", "remaining_time": "0:57:36", "throughput": 3070.5, "total_tokens": 5392272} | |
| {"current_steps": 100, "total_steps": 282, "loss": 0.0282, "lr": 3.6275252980402544e-05, "epoch": 1.0641711229946524, "percentage": 35.46, "elapsed_time": "0:30:51", "remaining_time": "0:56:09", "throughput": 3070.0, "total_tokens": 5683744} | |
| {"current_steps": 105, "total_steps": 282, "loss": 0.0452, "lr": 3.501553113674699e-05, "epoch": 1.1176470588235294, "percentage": 37.23, "elapsed_time": "0:32:26", "remaining_time": "0:54:41", "throughput": 3067.6, "total_tokens": 5971952} | |
| {"current_steps": 110, "total_steps": 282, "loss": 0.0266, "lr": 3.3724742013273854e-05, "epoch": 1.1711229946524064, "percentage": 39.01, "elapsed_time": "0:34:02", "remaining_time": "0:53:13", "throughput": 3066.95, "total_tokens": 6263424} | |
| {"current_steps": 115, "total_steps": 282, "loss": 0.0329, "lr": 3.2406889522140856e-05, "epoch": 1.2245989304812834, "percentage": 40.78, "elapsed_time": "0:35:35", "remaining_time": "0:51:41", "throughput": 3067.78, "total_tokens": 6551312} | |
| {"current_steps": 120, "total_steps": 282, "loss": 0.0232, "lr": 3.1066061523646295e-05, "epoch": 1.2780748663101604, "percentage": 42.55, "elapsed_time": "0:37:09", "remaining_time": "0:50:10", "throughput": 3067.4, "total_tokens": 6840256} | |
| {"current_steps": 125, "total_steps": 282, "loss": 0.0366, "lr": 2.9706417146052838e-05, "epoch": 1.3315508021390374, "percentage": 44.33, "elapsed_time": "0:38:43", "remaining_time": "0:48:38", "throughput": 3067.8, "total_tokens": 7128624} | |
| {"current_steps": 130, "total_steps": 282, "loss": 0.0301, "lr": 2.8332173884344477e-05, "epoch": 1.3850267379679144, "percentage": 46.1, "elapsed_time": "0:40:18", "remaining_time": "0:47:07", "throughput": 3067.34, "total_tokens": 7418256} | |
| {"current_steps": 135, "total_steps": 282, "loss": 0.0253, "lr": 2.6947594517935083e-05, "epoch": 1.4385026737967914, "percentage": 47.87, "elapsed_time": "0:41:54", "remaining_time": "0:45:37", "throughput": 3066.79, "total_tokens": 7710672} | |
| {"current_steps": 140, "total_steps": 282, "loss": 0.0291, "lr": 2.555697388790885e-05, "epoch": 1.4919786096256684, "percentage": 49.65, "elapsed_time": "0:43:22", "remaining_time": "0:44:00", "throughput": 3067.92, "total_tokens": 7985712} | |
| {"current_steps": 145, "total_steps": 282, "loss": 0.0236, "lr": 2.4164625574808146e-05, "epoch": 1.5454545454545454, "percentage": 51.42, "elapsed_time": "0:44:57", "remaining_time": "0:42:28", "throughput": 3067.4, "total_tokens": 8274128} | |
| {"current_steps": 150, "total_steps": 282, "loss": 0.0288, "lr": 2.277486851829338e-05, "epoch": 1.5989304812834224, "percentage": 53.19, "elapsed_time": "0:46:31", "remaining_time": "0:40:56", "throughput": 3067.26, "total_tokens": 8561696} | |
| {"current_steps": 155, "total_steps": 282, "loss": 0.0334, "lr": 2.1392013620179337e-05, "epoch": 1.6524064171122994, "percentage": 54.96, "elapsed_time": "0:48:03", "remaining_time": "0:39:22", "throughput": 3067.76, "total_tokens": 8846736} | |
| {"current_steps": 160, "total_steps": 282, "loss": 0.0273, "lr": 2.0020350372404102e-05, "epoch": 1.7058823529411766, "percentage": 56.74, "elapsed_time": "0:49:31", "remaining_time": "0:37:45", "throughput": 3069.37, "total_tokens": 9120352} | |
| {"current_steps": 165, "total_steps": 282, "loss": 0.0219, "lr": 1.8664133551409612e-05, "epoch": 1.7593582887700534, "percentage": 58.51, "elapsed_time": "0:51:01", "remaining_time": "0:36:10", "throughput": 3070.12, "total_tokens": 9398016} | |
| {"current_steps": 170, "total_steps": 282, "loss": 0.0246, "lr": 1.7327570020206504e-05, "epoch": 1.8128342245989306, "percentage": 60.28, "elapsed_time": "0:52:31", "remaining_time": "0:34:36", "throughput": 3070.76, "total_tokens": 9678592} | |
| {"current_steps": 175, "total_steps": 282, "loss": 0.0283, "lr": 1.6014805679062185e-05, "epoch": 1.8663101604278074, "percentage": 62.06, "elapsed_time": "0:54:05", "remaining_time": "0:33:04", "throughput": 3070.8, "total_tokens": 9965712} | |
| {"current_steps": 180, "total_steps": 282, "loss": 0.0196, "lr": 1.4729912605289767e-05, "epoch": 1.9197860962566846, "percentage": 63.83, "elapsed_time": "0:55:35", "remaining_time": "0:31:30", "throughput": 3071.62, "total_tokens": 10244944} | |
| {"current_steps": 185, "total_steps": 282, "loss": 0.0222, "lr": 1.34768764220293e-05, "epoch": 1.9732620320855614, "percentage": 65.6, "elapsed_time": "0:57:07", "remaining_time": "0:29:57", "throughput": 3071.83, "total_tokens": 10529152} | |
| {"current_steps": 190, "total_steps": 282, "loss": 0.0228, "lr": 1.2259583935202062e-05, "epoch": 2.021390374331551, "percentage": 67.38, "elapsed_time": "0:58:31", "remaining_time": "0:28:20", "throughput": 3071.66, "total_tokens": 10786048} | |
| {"current_steps": 195, "total_steps": 282, "loss": 0.0294, "lr": 1.1081811076986965e-05, "epoch": 2.0748663101604277, "percentage": 69.15, "elapsed_time": "1:00:03", "remaining_time": "0:26:47", "throughput": 3071.74, "total_tokens": 11069968} | |
| {"current_steps": 200, "total_steps": 282, "loss": 0.0171, "lr": 9.94721119321739e-06, "epoch": 2.128342245989305, "percentage": 70.92, "elapsed_time": "1:01:37", "remaining_time": "0:25:16", "throughput": 3071.46, "total_tokens": 11358096} | |
| {"current_steps": 205, "total_steps": 282, "loss": 0.0199, "lr": 8.85930371102994e-06, "epoch": 2.1818181818181817, "percentage": 72.7, "elapsed_time": "1:03:09", "remaining_time": "0:23:43", "throughput": 3071.28, "total_tokens": 11639152} | |
| {"current_steps": 210, "total_steps": 282, "loss": 0.025, "lr": 7.8214632219169e-06, "epoch": 2.235294117647059, "percentage": 74.47, "elapsed_time": "1:04:41", "remaining_time": "0:22:10", "throughput": 3071.79, "total_tokens": 11921888} | |
| {"current_steps": 215, "total_steps": 282, "loss": 0.0191, "lr": 6.836909014045925e-06, "epoch": 2.2887700534759357, "percentage": 76.24, "elapsed_time": "1:06:15", "remaining_time": "0:20:38", "throughput": 3071.27, "total_tokens": 12209424} | |
| {"current_steps": 220, "total_steps": 282, "loss": 0.0276, "lr": 5.908695086316701e-06, "epoch": 2.342245989304813, "percentage": 78.01, "elapsed_time": "1:07:50", "remaining_time": "0:19:07", "throughput": 3070.96, "total_tokens": 12500800} | |
| {"current_steps": 225, "total_steps": 282, "loss": 0.0299, "lr": 5.0397006751301435e-06, "epoch": 2.3957219251336896, "percentage": 79.79, "elapsed_time": "1:09:22", "remaining_time": "0:17:34", "throughput": 3071.27, "total_tokens": 12784480} | |
| {"current_steps": 230, "total_steps": 282, "loss": 0.023, "lr": 4.23262132325514e-06, "epoch": 2.449197860962567, "percentage": 81.56, "elapsed_time": "1:10:56", "remaining_time": "0:16:02", "throughput": 3071.07, "total_tokens": 13070832} | |
| {"current_steps": 235, "total_steps": 282, "loss": 0.0224, "lr": 3.489960518496521e-06, "epoch": 2.502673796791444, "percentage": 83.33, "elapsed_time": "1:12:29", "remaining_time": "0:14:29", "throughput": 3071.01, "total_tokens": 13358112} | |
| {"current_steps": 240, "total_steps": 282, "loss": 0.0246, "lr": 2.8140219281002718e-06, "epoch": 2.556149732620321, "percentage": 85.11, "elapsed_time": "1:14:00", "remaining_time": "0:12:57", "throughput": 3071.67, "total_tokens": 13640608} | |
| {"current_steps": 245, "total_steps": 282, "loss": 0.0249, "lr": 2.2069022529842664e-06, "epoch": 2.6096256684491976, "percentage": 86.88, "elapsed_time": "1:15:30", "remaining_time": "0:11:24", "throughput": 3072.55, "total_tokens": 13919056} | |
| {"current_steps": 250, "total_steps": 282, "loss": 0.0226, "lr": 1.6704847239599364e-06, "epoch": 2.663101604278075, "percentage": 88.65, "elapsed_time": "1:17:02", "remaining_time": "0:09:51", "throughput": 3072.7, "total_tokens": 14203200} | |
| {"current_steps": 255, "total_steps": 282, "loss": 0.0188, "lr": 1.2064332601191163e-06, "epoch": 2.716577540106952, "percentage": 90.43, "elapsed_time": "1:18:35", "remaining_time": "0:08:19", "throughput": 3072.67, "total_tokens": 14488480} | |
| {"current_steps": 260, "total_steps": 282, "loss": 0.0222, "lr": 8.161873075061499e-07, "epoch": 2.770053475935829, "percentage": 92.2, "elapsed_time": "1:20:07", "remaining_time": "0:06:46", "throughput": 3072.99, "total_tokens": 14772448} | |
| {"current_steps": 265, "total_steps": 282, "loss": 0.023, "lr": 5.009573740853313e-07, "epoch": 2.8235294117647056, "percentage": 93.97, "elapsed_time": "1:21:39", "remaining_time": "0:05:14", "throughput": 3073.21, "total_tokens": 15056768} | |
| {"current_steps": 270, "total_steps": 282, "loss": 0.0211, "lr": 2.617212748536491e-07, "epoch": 2.877005347593583, "percentage": 95.74, "elapsed_time": "1:23:16", "remaining_time": "0:03:42", "throughput": 3072.52, "total_tokens": 15352912} | |
| {"current_steps": 275, "total_steps": 282, "loss": 0.0306, "lr": 9.922109874636876e-08, "epoch": 2.93048128342246, "percentage": 97.52, "elapsed_time": "1:24:52", "remaining_time": "0:02:09", "throughput": 3072.24, "total_tokens": 15644144} | |
| {"current_steps": 280, "total_steps": 282, "loss": 0.0195, "lr": 1.3960906743634706e-08, "epoch": 2.983957219251337, "percentage": 99.29, "elapsed_time": "1:26:23", "remaining_time": "0:00:37", "throughput": 3072.67, "total_tokens": 15928032} | |
| {"current_steps": 282, "total_steps": 282, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:26:50", "remaining_time": "0:00:00", "throughput": 3072.25, "total_tokens": 16009072} | |