henggg's picture
Upload 18 files
86cd44f verified
{"current_steps": 1, "total_steps": 339, "loss": 0.2055, "lr": 9.999785297426788e-05, "epoch": 0.00882515168229454, "percentage": 0.29, "elapsed_time": "0:00:27", "remaining_time": "2:35:54", "throughput": 7338.97, "total_tokens": 203120}
{"current_steps": 2, "total_steps": 339, "loss": 0.1902, "lr": 9.999141208146028e-05, "epoch": 0.01765030336458908, "percentage": 0.59, "elapsed_time": "0:00:54", "remaining_time": "2:32:10", "throughput": 7493.38, "total_tokens": 406048}
{"current_steps": 3, "total_steps": 339, "loss": 0.1421, "lr": 9.998067787472772e-05, "epoch": 0.026475455046883617, "percentage": 0.88, "elapsed_time": "0:01:18", "remaining_time": "2:26:52", "throughput": 7812.96, "total_tokens": 614736}
{"current_steps": 4, "total_steps": 339, "loss": 0.1102, "lr": 9.996565127593488e-05, "epoch": 0.03530060672917816, "percentage": 1.18, "elapsed_time": "0:01:46", "remaining_time": "2:28:36", "throughput": 7668.61, "total_tokens": 816416}
{"current_steps": 5, "total_steps": 339, "loss": 0.0801, "lr": 9.994633357558158e-05, "epoch": 0.0441257584114727, "percentage": 1.47, "elapsed_time": "0:02:12", "remaining_time": "2:27:19", "throughput": 7740.76, "total_tokens": 1024272}
{"current_steps": 6, "total_steps": 339, "loss": 0.0574, "lr": 9.99227264326918e-05, "epoch": 0.052950910093767234, "percentage": 1.77, "elapsed_time": "0:02:38", "remaining_time": "2:26:42", "throughput": 7743.47, "total_tokens": 1228192}
{"current_steps": 7, "total_steps": 339, "loss": 0.0401, "lr": 9.989483187467127e-05, "epoch": 0.06177606177606178, "percentage": 2.06, "elapsed_time": "0:03:03", "remaining_time": "2:24:52", "throughput": 7830.06, "total_tokens": 1434992}
{"current_steps": 8, "total_steps": 339, "loss": 0.0295, "lr": 9.986265229713331e-05, "epoch": 0.07060121345835632, "percentage": 2.36, "elapsed_time": "0:03:31", "remaining_time": "2:25:54", "throughput": 7781.82, "total_tokens": 1646560}
{"current_steps": 9, "total_steps": 339, "loss": 0.0262, "lr": 9.982619046369321e-05, "epoch": 0.07942636514065085, "percentage": 2.65, "elapsed_time": "0:03:55", "remaining_time": "2:23:41", "throughput": 7819.12, "total_tokens": 1838624}
{"current_steps": 10, "total_steps": 339, "loss": 0.0263, "lr": 9.978544950573074e-05, "epoch": 0.0882515168229454, "percentage": 2.95, "elapsed_time": "0:04:23", "remaining_time": "2:24:13", "throughput": 7807.27, "total_tokens": 2053488}
{"current_steps": 11, "total_steps": 339, "loss": 0.022, "lr": 9.974043292212128e-05, "epoch": 0.09707666850523994, "percentage": 3.24, "elapsed_time": "0:04:47", "remaining_time": "2:22:39", "throughput": 7850.91, "total_tokens": 2253680}
{"current_steps": 12, "total_steps": 339, "loss": 0.0202, "lr": 9.96911445789354e-05, "epoch": 0.10590182018753447, "percentage": 3.54, "elapsed_time": "0:05:11", "remaining_time": "2:21:16", "throughput": 7850.63, "total_tokens": 2442000}
{"current_steps": 13, "total_steps": 339, "loss": 0.0202, "lr": 9.963758870910671e-05, "epoch": 0.11472697186982901, "percentage": 3.83, "elapsed_time": "0:05:39", "remaining_time": "2:21:53", "throughput": 7823.47, "total_tokens": 2655920}
{"current_steps": 14, "total_steps": 339, "loss": 0.0178, "lr": 9.957976991206846e-05, "epoch": 0.12355212355212356, "percentage": 4.13, "elapsed_time": "0:06:09", "remaining_time": "2:23:04", "throughput": 7772.01, "total_tokens": 2874064}
{"current_steps": 15, "total_steps": 339, "loss": 0.0158, "lr": 9.951769315335844e-05, "epoch": 0.13237727523441808, "percentage": 4.42, "elapsed_time": "0:06:33", "remaining_time": "2:21:43", "throughput": 7802.71, "total_tokens": 3071744}
{"current_steps": 16, "total_steps": 339, "loss": 0.0159, "lr": 9.945136376419259e-05, "epoch": 0.14120242691671264, "percentage": 4.72, "elapsed_time": "0:07:00", "remaining_time": "2:21:38", "throughput": 7786.47, "total_tokens": 3277904}
{"current_steps": 17, "total_steps": 339, "loss": 0.0147, "lr": 9.938078744100712e-05, "epoch": 0.15002757859900717, "percentage": 5.01, "elapsed_time": "0:07:27", "remaining_time": "2:21:14", "throughput": 7807.8, "total_tokens": 3493136}
{"current_steps": 18, "total_steps": 339, "loss": 0.0138, "lr": 9.930597024496931e-05, "epoch": 0.1588527302813017, "percentage": 5.31, "elapsed_time": "0:07:54", "remaining_time": "2:20:53", "throughput": 7814.87, "total_tokens": 3704288}
{"current_steps": 19, "total_steps": 339, "loss": 0.0128, "lr": 9.922691860145696e-05, "epoch": 0.16767788196359626, "percentage": 5.6, "elapsed_time": "0:08:18", "remaining_time": "2:19:51", "throughput": 7835.96, "total_tokens": 3904352}
{"current_steps": 20, "total_steps": 339, "loss": 0.0124, "lr": 9.914363929950659e-05, "epoch": 0.1765030336458908, "percentage": 5.9, "elapsed_time": "0:08:45", "remaining_time": "2:19:35", "throughput": 7833.94, "total_tokens": 4113888}
{"current_steps": 21, "total_steps": 339, "loss": 0.0116, "lr": 9.905613949123036e-05, "epoch": 0.18532818532818532, "percentage": 6.19, "elapsed_time": "0:09:11", "remaining_time": "2:19:04", "throughput": 7845.67, "total_tokens": 4323504}
{"current_steps": 22, "total_steps": 339, "loss": 0.0109, "lr": 9.896442669120187e-05, "epoch": 0.19415333701047988, "percentage": 6.49, "elapsed_time": "0:09:36", "remaining_time": "2:18:27", "throughput": 7844.79, "total_tokens": 4523008}
{"current_steps": 23, "total_steps": 339, "loss": 0.0106, "lr": 9.886850877581079e-05, "epoch": 0.2029784886927744, "percentage": 6.78, "elapsed_time": "0:10:03", "remaining_time": "2:18:10", "throughput": 7843.06, "total_tokens": 4732864}
{"current_steps": 24, "total_steps": 339, "loss": 0.0099, "lr": 9.876839398258641e-05, "epoch": 0.21180364037506894, "percentage": 7.08, "elapsed_time": "0:10:30", "remaining_time": "2:17:56", "throughput": 7837.07, "total_tokens": 4941936}
{"current_steps": 25, "total_steps": 339, "loss": 0.0109, "lr": 9.866409090949022e-05, "epoch": 0.2206287920573635, "percentage": 7.37, "elapsed_time": "0:10:55", "remaining_time": "2:17:11", "throughput": 7848.7, "total_tokens": 5143584}
{"current_steps": 26, "total_steps": 339, "loss": 0.0084, "lr": 9.855560851417752e-05, "epoch": 0.22945394373965802, "percentage": 7.67, "elapsed_time": "0:11:20", "remaining_time": "2:16:29", "throughput": 7866.16, "total_tokens": 5351024}
{"current_steps": 27, "total_steps": 339, "loss": 0.0081, "lr": 9.844295611322804e-05, "epoch": 0.23827909542195255, "percentage": 7.96, "elapsed_time": "0:11:46", "remaining_time": "2:16:04", "throughput": 7874.35, "total_tokens": 5563760}
{"current_steps": 28, "total_steps": 339, "loss": 0.0078, "lr": 9.832614338134595e-05, "epoch": 0.2471042471042471, "percentage": 8.26, "elapsed_time": "0:12:12", "remaining_time": "2:15:39", "throughput": 7877.49, "total_tokens": 5772416}
{"current_steps": 29, "total_steps": 339, "loss": 0.0081, "lr": 9.820518035052889e-05, "epoch": 0.25592939878654164, "percentage": 8.55, "elapsed_time": "0:12:40", "remaining_time": "2:15:30", "throughput": 7855.15, "total_tokens": 5974464}
{"current_steps": 30, "total_steps": 339, "loss": 0.0087, "lr": 9.808007740920646e-05, "epoch": 0.26475455046883617, "percentage": 8.85, "elapsed_time": "0:13:07", "remaining_time": "2:15:14", "throughput": 7862.08, "total_tokens": 6193520}
{"current_steps": 31, "total_steps": 339, "loss": 0.0079, "lr": 9.795084530134801e-05, "epoch": 0.2735797021511307, "percentage": 9.14, "elapsed_time": "0:13:34", "remaining_time": "2:14:50", "throughput": 7859.19, "total_tokens": 6399792}
{"current_steps": 32, "total_steps": 339, "loss": 0.0086, "lr": 9.781749512553999e-05, "epoch": 0.2824048538334253, "percentage": 9.44, "elapsed_time": "0:14:00", "remaining_time": "2:14:21", "throughput": 7858.66, "total_tokens": 6603584}
{"current_steps": 33, "total_steps": 339, "loss": 0.0079, "lr": 9.768003833403278e-05, "epoch": 0.2912300055157198, "percentage": 9.73, "elapsed_time": "0:14:27", "remaining_time": "2:14:00", "throughput": 7854.06, "total_tokens": 6810656}
{"current_steps": 34, "total_steps": 339, "loss": 0.0069, "lr": 9.753848673175707e-05, "epoch": 0.30005515719801434, "percentage": 10.03, "elapsed_time": "0:14:52", "remaining_time": "2:13:26", "throughput": 7844.67, "total_tokens": 7001792}
{"current_steps": 35, "total_steps": 339, "loss": 0.0064, "lr": 9.739285247531018e-05, "epoch": 0.3088803088803089, "percentage": 10.32, "elapsed_time": "0:15:19", "remaining_time": "2:13:10", "throughput": 7832.92, "total_tokens": 7205952}
{"current_steps": 36, "total_steps": 339, "loss": 0.006, "lr": 9.724314807191195e-05, "epoch": 0.3177054605626034, "percentage": 10.62, "elapsed_time": "0:15:45", "remaining_time": "2:12:36", "throughput": 7834.75, "total_tokens": 7406304}
{"current_steps": 37, "total_steps": 339, "loss": 0.0067, "lr": 9.708938637833065e-05, "epoch": 0.32653061224489793, "percentage": 10.91, "elapsed_time": "0:16:12", "remaining_time": "2:12:17", "throughput": 7845.98, "total_tokens": 7629568}
{"current_steps": 38, "total_steps": 339, "loss": 0.0063, "lr": 9.693158059977878e-05, "epoch": 0.3353557639271925, "percentage": 11.21, "elapsed_time": "0:16:39", "remaining_time": "2:11:53", "throughput": 7852.67, "total_tokens": 7845200}
{"current_steps": 39, "total_steps": 339, "loss": 0.0058, "lr": 9.676974428877901e-05, "epoch": 0.34418091560948705, "percentage": 11.5, "elapsed_time": "0:17:07", "remaining_time": "2:11:43", "throughput": 7846.29, "total_tokens": 8061840}
{"current_steps": 40, "total_steps": 339, "loss": 0.0061, "lr": 9.660389134400033e-05, "epoch": 0.3530060672917816, "percentage": 11.8, "elapsed_time": "0:17:36", "remaining_time": "2:11:38", "throughput": 7836.02, "total_tokens": 8279664}
{"current_steps": 41, "total_steps": 339, "loss": 0.0055, "lr": 9.643403600906433e-05, "epoch": 0.3618312189740761, "percentage": 12.09, "elapsed_time": "0:18:00", "remaining_time": "2:10:56", "throughput": 7840.93, "total_tokens": 8475376}
{"current_steps": 42, "total_steps": 339, "loss": 0.005, "lr": 9.626019287132203e-05, "epoch": 0.37065637065637064, "percentage": 12.39, "elapsed_time": "0:18:28", "remaining_time": "2:10:37", "throughput": 7842.2, "total_tokens": 8691760}
{"current_steps": 43, "total_steps": 339, "loss": 0.006, "lr": 9.608237686060099e-05, "epoch": 0.3794815223386652, "percentage": 12.68, "elapsed_time": "0:18:54", "remaining_time": "2:10:07", "throughput": 7833.15, "total_tokens": 8884736}
{"current_steps": 44, "total_steps": 339, "loss": 0.0048, "lr": 9.590060324792327e-05, "epoch": 0.38830667402095975, "percentage": 12.98, "elapsed_time": "0:19:19", "remaining_time": "2:09:33", "throughput": 7835.19, "total_tokens": 9084064}
{"current_steps": 45, "total_steps": 339, "loss": 0.0047, "lr": 9.571488764419381e-05, "epoch": 0.3971318257032543, "percentage": 13.27, "elapsed_time": "0:19:46", "remaining_time": "2:09:10", "throughput": 7841.66, "total_tokens": 9302144}
{"current_steps": 46, "total_steps": 339, "loss": 0.0053, "lr": 9.552524599885981e-05, "epoch": 0.4059569773855488, "percentage": 13.57, "elapsed_time": "0:20:12", "remaining_time": "2:08:44", "throughput": 7848.48, "total_tokens": 9517456}
{"current_steps": 47, "total_steps": 339, "loss": 0.0044, "lr": 9.533169459854098e-05, "epoch": 0.41478212906784334, "percentage": 13.86, "elapsed_time": "0:20:36", "remaining_time": "2:08:03", "throughput": 7851.65, "total_tokens": 9710768}
{"current_steps": 48, "total_steps": 339, "loss": 0.0043, "lr": 9.513425006563079e-05, "epoch": 0.42360728075013787, "percentage": 14.16, "elapsed_time": "0:21:02", "remaining_time": "2:07:36", "throughput": 7850.33, "total_tokens": 9914064}
{"current_steps": 49, "total_steps": 339, "loss": 0.0041, "lr": 9.493292935686895e-05, "epoch": 0.43243243243243246, "percentage": 14.45, "elapsed_time": "0:21:28", "remaining_time": "2:07:06", "throughput": 7853.4, "total_tokens": 10120208}
{"current_steps": 50, "total_steps": 339, "loss": 0.0044, "lr": 9.472774976188515e-05, "epoch": 0.441257584114727, "percentage": 14.75, "elapsed_time": "0:21:57", "remaining_time": "2:06:57", "throughput": 7850.51, "total_tokens": 10346304}
{"current_steps": 51, "total_steps": 339, "loss": 0.004, "lr": 9.451872890171419e-05, "epoch": 0.4500827357970215, "percentage": 15.04, "elapsed_time": "0:22:24", "remaining_time": "2:06:30", "throughput": 7847.6, "total_tokens": 10547984}
{"current_steps": 52, "total_steps": 339, "loss": 0.0045, "lr": 9.43058847272827e-05, "epoch": 0.45890788747931605, "percentage": 15.34, "elapsed_time": "0:22:49", "remaining_time": "2:05:57", "throughput": 7853.35, "total_tokens": 10754288}
{"current_steps": 53, "total_steps": 339, "loss": 0.0028, "lr": 9.408923551786743e-05, "epoch": 0.4677330391616106, "percentage": 15.63, "elapsed_time": "0:23:14", "remaining_time": "2:05:26", "throughput": 7845.79, "total_tokens": 10942704}
{"current_steps": 54, "total_steps": 339, "loss": 0.0034, "lr": 9.386879987952549e-05, "epoch": 0.4765581908439051, "percentage": 15.93, "elapsed_time": "0:23:39", "remaining_time": "2:04:53", "throughput": 7853.45, "total_tokens": 11150864}
{"current_steps": 55, "total_steps": 339, "loss": 0.0042, "lr": 9.364459674349641e-05, "epoch": 0.4853833425261997, "percentage": 16.22, "elapsed_time": "0:24:07", "remaining_time": "2:04:35", "throughput": 7852.19, "total_tokens": 11367728}
{"current_steps": 56, "total_steps": 339, "loss": 0.0028, "lr": 9.341664536457626e-05, "epoch": 0.4942084942084942, "percentage": 16.52, "elapsed_time": "0:24:31", "remaining_time": "2:03:54", "throughput": 7868.08, "total_tokens": 11575536}
{"current_steps": 57, "total_steps": 339, "loss": 0.0035, "lr": 9.31849653194641e-05, "epoch": 0.5030336458907887, "percentage": 16.81, "elapsed_time": "0:24:55", "remaining_time": "2:03:21", "throughput": 7875.29, "total_tokens": 11781328}
{"current_steps": 58, "total_steps": 339, "loss": 0.0029, "lr": 9.294957650508065e-05, "epoch": 0.5118587975730833, "percentage": 17.11, "elapsed_time": "0:25:19", "remaining_time": "2:02:42", "throughput": 7884.45, "total_tokens": 11981232}
{"current_steps": 59, "total_steps": 339, "loss": 0.0028, "lr": 9.27104991368596e-05, "epoch": 0.5206839492553779, "percentage": 17.4, "elapsed_time": "0:25:44", "remaining_time": "2:02:10", "throughput": 7890.1, "total_tokens": 12187296}
{"current_steps": 60, "total_steps": 339, "loss": 0.0027, "lr": 9.246775374701139e-05, "epoch": 0.5295091009376723, "percentage": 17.7, "elapsed_time": "0:26:08", "remaining_time": "2:01:34", "throughput": 7895.72, "total_tokens": 12385632}
{"current_steps": 61, "total_steps": 339, "loss": 0.0022, "lr": 9.222136118275995e-05, "epoch": 0.5383342526199669, "percentage": 17.99, "elapsed_time": "0:26:34", "remaining_time": "2:01:05", "throughput": 7896.89, "total_tokens": 12588928}
{"current_steps": 62, "total_steps": 339, "loss": 0.0027, "lr": 9.197134260455233e-05, "epoch": 0.5471594043022614, "percentage": 18.29, "elapsed_time": "0:27:05", "remaining_time": "2:01:02", "throughput": 7889.78, "total_tokens": 12825616}
{"current_steps": 63, "total_steps": 339, "loss": 0.0025, "lr": 9.171771948424137e-05, "epoch": 0.555984555984556, "percentage": 18.58, "elapsed_time": "0:27:33", "remaining_time": "2:00:45", "throughput": 7887.26, "total_tokens": 13044976}
{"current_steps": 64, "total_steps": 339, "loss": 0.0025, "lr": 9.146051360324166e-05, "epoch": 0.5648097076668506, "percentage": 18.88, "elapsed_time": "0:27:59", "remaining_time": "2:00:14", "throughput": 7894.29, "total_tokens": 13255280}
{"current_steps": 65, "total_steps": 339, "loss": 0.0022, "lr": 9.119974705065901e-05, "epoch": 0.573634859349145, "percentage": 19.17, "elapsed_time": "0:28:28", "remaining_time": "2:00:03", "throughput": 7878.69, "total_tokens": 13463456}
{"current_steps": 66, "total_steps": 339, "loss": 0.0023, "lr": 9.093544222139337e-05, "epoch": 0.5824600110314396, "percentage": 19.47, "elapsed_time": "0:28:54", "remaining_time": "1:59:35", "throughput": 7879.18, "total_tokens": 13667744}
{"current_steps": 67, "total_steps": 339, "loss": 0.0024, "lr": 9.066762181421552e-05, "epoch": 0.5912851627137341, "percentage": 19.76, "elapsed_time": "0:29:21", "remaining_time": "1:59:10", "throughput": 7877.08, "total_tokens": 13874240}
{"current_steps": 68, "total_steps": 339, "loss": 0.0015, "lr": 9.039630882981768e-05, "epoch": 0.6001103143960287, "percentage": 20.06, "elapsed_time": "0:29:49", "remaining_time": "1:58:53", "throughput": 7867.14, "total_tokens": 14081392}
{"current_steps": 69, "total_steps": 339, "loss": 0.0033, "lr": 9.012152656883823e-05, "epoch": 0.6089354660783233, "percentage": 20.35, "elapsed_time": "0:30:20", "remaining_time": "1:58:42", "throughput": 7856.5, "total_tokens": 14300896}
{"current_steps": 70, "total_steps": 339, "loss": 0.0021, "lr": 8.984329862986056e-05, "epoch": 0.6177606177606177, "percentage": 20.65, "elapsed_time": "0:30:47", "remaining_time": "1:58:20", "throughput": 7860.92, "total_tokens": 14523968}
{"current_steps": 71, "total_steps": 339, "loss": 0.0013, "lr": 8.956164890738643e-05, "epoch": 0.6265857694429123, "percentage": 20.94, "elapsed_time": "0:31:13", "remaining_time": "1:57:50", "throughput": 7863.29, "total_tokens": 14728960}
{"current_steps": 72, "total_steps": 339, "loss": 0.0016, "lr": 8.927660158978392e-05, "epoch": 0.6354109211252068, "percentage": 21.24, "elapsed_time": "0:31:35", "remaining_time": "1:57:09", "throughput": 7866.76, "total_tokens": 14912480}
{"current_steps": 73, "total_steps": 339, "loss": 0.0019, "lr": 8.898818115721008e-05, "epoch": 0.6442360728075014, "percentage": 21.53, "elapsed_time": "0:32:00", "remaining_time": "1:56:38", "throughput": 7870.01, "total_tokens": 15114608}
{"current_steps": 74, "total_steps": 339, "loss": 0.0017, "lr": 8.86964123795085e-05, "epoch": 0.6530612244897959, "percentage": 21.83, "elapsed_time": "0:32:27", "remaining_time": "1:56:13", "throughput": 7870.22, "total_tokens": 15326112}
{"current_steps": 75, "total_steps": 339, "loss": 0.0015, "lr": 8.84013203140821e-05, "epoch": 0.6618863761720905, "percentage": 22.12, "elapsed_time": "0:32:54", "remaining_time": "1:55:50", "throughput": 7872.22, "total_tokens": 15545248}
{"current_steps": 76, "total_steps": 339, "loss": 0.0017, "lr": 8.810293030374126e-05, "epoch": 0.670711527854385, "percentage": 22.42, "elapsed_time": "0:33:22", "remaining_time": "1:55:29", "throughput": 7866.0, "total_tokens": 15751872}
{"current_steps": 77, "total_steps": 339, "loss": 0.001, "lr": 8.780126797452713e-05, "epoch": 0.6795366795366795, "percentage": 22.71, "elapsed_time": "0:33:48", "remaining_time": "1:55:02", "throughput": 7866.6, "total_tokens": 15957872}
{"current_steps": 78, "total_steps": 339, "loss": 0.0018, "lr": 8.749635923351107e-05, "epoch": 0.6883618312189741, "percentage": 23.01, "elapsed_time": "0:34:13", "remaining_time": "1:54:32", "throughput": 7869.35, "total_tokens": 16162640}
{"current_steps": 79, "total_steps": 339, "loss": 0.001, "lr": 8.71882302665696e-05, "epoch": 0.6971869829012686, "percentage": 23.3, "elapsed_time": "0:34:37", "remaining_time": "1:53:56", "throughput": 7871.98, "total_tokens": 16352368}
{"current_steps": 80, "total_steps": 339, "loss": 0.0014, "lr": 8.687690753613554e-05, "epoch": 0.7060121345835632, "percentage": 23.6, "elapsed_time": "0:35:02", "remaining_time": "1:53:27", "throughput": 7877.09, "total_tokens": 16563920}
{"current_steps": 81, "total_steps": 339, "loss": 0.001, "lr": 8.656241777892543e-05, "epoch": 0.7148372862658577, "percentage": 23.89, "elapsed_time": "0:35:28", "remaining_time": "1:52:58", "throughput": 7874.92, "total_tokens": 16759024}
{"current_steps": 82, "total_steps": 339, "loss": 0.0013, "lr": 8.624478800364332e-05, "epoch": 0.7236624379481522, "percentage": 24.19, "elapsed_time": "0:35:58", "remaining_time": "1:52:44", "throughput": 7863.86, "total_tokens": 16973728}
{"current_steps": 83, "total_steps": 339, "loss": 0.0012, "lr": 8.592404548866123e-05, "epoch": 0.7324875896304468, "percentage": 24.48, "elapsed_time": "0:36:22", "remaining_time": "1:52:10", "throughput": 7864.79, "total_tokens": 17162752}
{"current_steps": 84, "total_steps": 339, "loss": 0.0013, "lr": 8.560021777967649e-05, "epoch": 0.7413127413127413, "percentage": 24.78, "elapsed_time": "0:36:46", "remaining_time": "1:51:37", "throughput": 7871.03, "total_tokens": 17364064}
{"current_steps": 85, "total_steps": 339, "loss": 0.0011, "lr": 8.527333268734606e-05, "epoch": 0.7501378929950359, "percentage": 25.07, "elapsed_time": "0:37:11", "remaining_time": "1:51:09", "throughput": 7869.86, "total_tokens": 17564576}
{"current_steps": 86, "total_steps": 339, "loss": 0.0037, "lr": 8.494341828489812e-05, "epoch": 0.7589630446773304, "percentage": 25.37, "elapsed_time": "0:37:40", "remaining_time": "1:50:49", "throughput": 7865.4, "total_tokens": 17778752}
{"current_steps": 87, "total_steps": 339, "loss": 0.0007, "lr": 8.461050290572114e-05, "epoch": 0.7677881963596249, "percentage": 25.66, "elapsed_time": "0:38:07", "remaining_time": "1:50:26", "throughput": 7860.7, "total_tokens": 17982448}
{"current_steps": 88, "total_steps": 339, "loss": 0.0008, "lr": 8.427461514093056e-05, "epoch": 0.7766133480419195, "percentage": 25.96, "elapsed_time": "0:38:31", "remaining_time": "1:49:52", "throughput": 7865.68, "total_tokens": 18180608}
{"current_steps": 89, "total_steps": 339, "loss": 0.0006, "lr": 8.393578383691329e-05, "epoch": 0.785438499724214, "percentage": 26.25, "elapsed_time": "0:38:59", "remaining_time": "1:49:32", "throughput": 7857.75, "total_tokens": 18384496}
{"current_steps": 90, "total_steps": 339, "loss": 0.001, "lr": 8.359403809285053e-05, "epoch": 0.7942636514065086, "percentage": 26.55, "elapsed_time": "0:39:24", "remaining_time": "1:49:01", "throughput": 7861.64, "total_tokens": 18587744}
{"current_steps": 91, "total_steps": 339, "loss": 0.001, "lr": 8.324940725821852e-05, "epoch": 0.803088803088803, "percentage": 26.84, "elapsed_time": "0:39:49", "remaining_time": "1:48:31", "throughput": 7864.33, "total_tokens": 18791056}
{"current_steps": 92, "total_steps": 339, "loss": 0.0008, "lr": 8.290192093026805e-05, "epoch": 0.8119139547710976, "percentage": 27.14, "elapsed_time": "0:40:14", "remaining_time": "1:48:03", "throughput": 7862.08, "total_tokens": 18985008}
{"current_steps": 93, "total_steps": 339, "loss": 0.0014, "lr": 8.255160895148263e-05, "epoch": 0.8207391064533922, "percentage": 27.43, "elapsed_time": "0:40:39", "remaining_time": "1:47:33", "throughput": 7866.62, "total_tokens": 19193888}
{"current_steps": 94, "total_steps": 339, "loss": 0.001, "lr": 8.219850140701557e-05, "epoch": 0.8295642581356867, "percentage": 27.73, "elapsed_time": "0:41:05", "remaining_time": "1:47:05", "throughput": 7869.38, "total_tokens": 19399552}
{"current_steps": 95, "total_steps": 339, "loss": 0.0007, "lr": 8.184262862210624e-05, "epoch": 0.8383894098179813, "percentage": 28.02, "elapsed_time": "0:41:30", "remaining_time": "1:46:36", "throughput": 7872.25, "total_tokens": 19605120}
{"current_steps": 96, "total_steps": 339, "loss": 0.0008, "lr": 8.148402115947571e-05, "epoch": 0.8472145615002757, "percentage": 28.32, "elapsed_time": "0:41:54", "remaining_time": "1:46:04", "throughput": 7875.39, "total_tokens": 19802480}
{"current_steps": 97, "total_steps": 339, "loss": 0.0011, "lr": 8.112270981670196e-05, "epoch": 0.8560397131825703, "percentage": 28.61, "elapsed_time": "0:42:22", "remaining_time": "1:45:44", "throughput": 7868.64, "total_tokens": 20009520}
{"current_steps": 98, "total_steps": 339, "loss": 0.0009, "lr": 8.075872562357501e-05, "epoch": 0.8648648648648649, "percentage": 28.91, "elapsed_time": "0:42:52", "remaining_time": "1:45:26", "throughput": 7865.85, "total_tokens": 20235888}
{"current_steps": 99, "total_steps": 339, "loss": 0.0006, "lr": 8.039209983943201e-05, "epoch": 0.8736900165471594, "percentage": 29.2, "elapsed_time": "0:43:16", "remaining_time": "1:44:53", "throughput": 7870.61, "total_tokens": 20433600}
{"current_steps": 100, "total_steps": 339, "loss": 0.0009, "lr": 8.002286395047267e-05, "epoch": 0.882515168229454, "percentage": 29.5, "elapsed_time": "0:43:39", "remaining_time": "1:44:20", "throughput": 7876.56, "total_tokens": 20631664}
{"current_steps": 101, "total_steps": 339, "loss": 0.0006, "lr": 7.965104966705518e-05, "epoch": 0.8913403199117484, "percentage": 29.79, "elapsed_time": "0:44:04", "remaining_time": "1:43:52", "throughput": 7876.49, "total_tokens": 20833056}
{"current_steps": 102, "total_steps": 339, "loss": 0.0008, "lr": 7.927668892097289e-05, "epoch": 0.900165471594043, "percentage": 30.09, "elapsed_time": "0:44:33", "remaining_time": "1:43:30", "throughput": 7875.34, "total_tokens": 21051104}
{"current_steps": 103, "total_steps": 339, "loss": 0.0005, "lr": 7.889981386271201e-05, "epoch": 0.9089906232763376, "percentage": 30.38, "elapsed_time": "0:44:56", "remaining_time": "1:42:59", "throughput": 7878.05, "total_tokens": 21246080}
{"current_steps": 104, "total_steps": 339, "loss": 0.0006, "lr": 7.852045685869045e-05, "epoch": 0.9178157749586321, "percentage": 30.68, "elapsed_time": "0:45:20", "remaining_time": "1:42:26", "throughput": 7881.27, "total_tokens": 21439696}
{"current_steps": 105, "total_steps": 339, "loss": 0.0008, "lr": 7.813865048847819e-05, "epoch": 0.9266409266409267, "percentage": 30.97, "elapsed_time": "0:45:48", "remaining_time": "1:42:04", "throughput": 7877.02, "total_tokens": 21648432}
{"current_steps": 106, "total_steps": 339, "loss": 0.0007, "lr": 7.775442754199928e-05, "epoch": 0.9354660783232212, "percentage": 31.27, "elapsed_time": "0:46:15", "remaining_time": "1:41:41", "throughput": 7877.23, "total_tokens": 21864368}
{"current_steps": 107, "total_steps": 339, "loss": 0.0006, "lr": 7.736782101671587e-05, "epoch": 0.9442912300055157, "percentage": 31.56, "elapsed_time": "0:46:40", "remaining_time": "1:41:11", "throughput": 7878.63, "total_tokens": 22061968}
{"current_steps": 108, "total_steps": 339, "loss": 0.0012, "lr": 7.697886411479423e-05, "epoch": 0.9531163816878102, "percentage": 31.86, "elapsed_time": "0:47:06", "remaining_time": "1:40:44", "throughput": 7883.06, "total_tokens": 22278128}
{"current_steps": 109, "total_steps": 339, "loss": 0.0004, "lr": 7.658759024025349e-05, "epoch": 0.9619415333701048, "percentage": 32.15, "elapsed_time": "0:47:30", "remaining_time": "1:40:15", "throughput": 7881.65, "total_tokens": 22469056}
{"current_steps": 110, "total_steps": 339, "loss": 0.0008, "lr": 7.619403299609668e-05, "epoch": 0.9707666850523994, "percentage": 32.45, "elapsed_time": "0:47:54", "remaining_time": "1:39:44", "throughput": 7883.6, "total_tokens": 22662128}
{"current_steps": 111, "total_steps": 339, "loss": 0.0007, "lr": 7.579822618142505e-05, "epoch": 0.9795918367346939, "percentage": 32.74, "elapsed_time": "0:48:22", "remaining_time": "1:39:21", "throughput": 7884.35, "total_tokens": 22883216}
{"current_steps": 112, "total_steps": 339, "loss": 0.0005, "lr": 7.540020378853523e-05, "epoch": 0.9884169884169884, "percentage": 33.04, "elapsed_time": "0:48:46", "remaining_time": "1:38:50", "throughput": 7889.5, "total_tokens": 23085888}
{"current_steps": 113, "total_steps": 339, "loss": 0.0007, "lr": 7.500000000000001e-05, "epoch": 0.9972421400992829, "percentage": 33.33, "elapsed_time": "0:49:14", "remaining_time": "1:38:28", "throughput": 7889.54, "total_tokens": 23307520}
{"current_steps": 114, "total_steps": 339, "loss": 0.0014, "lr": 7.459764918573264e-05, "epoch": 1.0088251516822946, "percentage": 33.63, "elapsed_time": "0:49:46", "remaining_time": "1:38:15", "throughput": 7889.22, "total_tokens": 23564192}
{"current_steps": 115, "total_steps": 339, "loss": 0.0007, "lr": 7.419318590003523e-05, "epoch": 1.0176503033645892, "percentage": 33.92, "elapsed_time": "0:50:13", "remaining_time": "1:37:50", "throughput": 7886.62, "total_tokens": 23768816}
{"current_steps": 116, "total_steps": 339, "loss": 0.0006, "lr": 7.378664487863103e-05, "epoch": 1.0264754550468835, "percentage": 34.22, "elapsed_time": "0:50:40", "remaining_time": "1:37:24", "throughput": 7886.1, "total_tokens": 23974096}
{"current_steps": 117, "total_steps": 339, "loss": 0.0003, "lr": 7.33780610356814e-05, "epoch": 1.0353006067291781, "percentage": 34.51, "elapsed_time": "0:51:05", "remaining_time": "1:36:55", "throughput": 7886.46, "total_tokens": 24172256}
{"current_steps": 118, "total_steps": 339, "loss": 0.0004, "lr": 7.296746946078736e-05, "epoch": 1.0441257584114727, "percentage": 34.81, "elapsed_time": "0:51:27", "remaining_time": "1:36:23", "throughput": 7889.9, "total_tokens": 24362208}
{"current_steps": 119, "total_steps": 339, "loss": 0.0003, "lr": 7.255490541597594e-05, "epoch": 1.0529509100937673, "percentage": 35.1, "elapsed_time": "0:51:53", "remaining_time": "1:35:55", "throughput": 7889.45, "total_tokens": 24562224}
{"current_steps": 120, "total_steps": 339, "loss": 0.0005, "lr": 7.214040433267198e-05, "epoch": 1.0617760617760619, "percentage": 35.4, "elapsed_time": "0:52:21", "remaining_time": "1:35:33", "throughput": 7886.78, "total_tokens": 24776528}
{"current_steps": 121, "total_steps": 339, "loss": 0.0003, "lr": 7.172400180865513e-05, "epoch": 1.0706012134583562, "percentage": 35.69, "elapsed_time": "0:52:45", "remaining_time": "1:35:02", "throughput": 7893.28, "total_tokens": 24985008}
{"current_steps": 122, "total_steps": 339, "loss": 0.0005, "lr": 7.130573360500276e-05, "epoch": 1.0794263651406508, "percentage": 35.99, "elapsed_time": "0:53:11", "remaining_time": "1:34:36", "throughput": 7896.08, "total_tokens": 25200720}
{"current_steps": 123, "total_steps": 339, "loss": 0.0004, "lr": 7.088563564301873e-05, "epoch": 1.0882515168229454, "percentage": 36.28, "elapsed_time": "0:53:36", "remaining_time": "1:34:08", "throughput": 7901.06, "total_tokens": 25413568}
{"current_steps": 124, "total_steps": 339, "loss": 0.0003, "lr": 7.046374400114842e-05, "epoch": 1.09707666850524, "percentage": 36.58, "elapsed_time": "0:53:59", "remaining_time": "1:33:37", "throughput": 7904.61, "total_tokens": 25608576}
{"current_steps": 125, "total_steps": 339, "loss": 0.0003, "lr": 7.004009491188022e-05, "epoch": 1.1059018201875346, "percentage": 36.87, "elapsed_time": "0:54:26", "remaining_time": "1:33:11", "throughput": 7904.82, "total_tokens": 25818400}
{"current_steps": 126, "total_steps": 339, "loss": 0.0005, "lr": 6.961472475863405e-05, "epoch": 1.114726971869829, "percentage": 37.17, "elapsed_time": "0:54:53", "remaining_time": "1:32:47", "throughput": 7905.63, "total_tokens": 26037424}
{"current_steps": 127, "total_steps": 339, "loss": 0.0005, "lr": 6.918767007263646e-05, "epoch": 1.1235521235521235, "percentage": 37.46, "elapsed_time": "0:55:21", "remaining_time": "1:32:23", "throughput": 7904.23, "total_tokens": 26250480}
{"current_steps": 128, "total_steps": 339, "loss": 0.0005, "lr": 6.875896752978344e-05, "epoch": 1.1323772752344181, "percentage": 37.76, "elapsed_time": "0:55:47", "remaining_time": "1:31:58", "throughput": 7903.09, "total_tokens": 26458592}
{"current_steps": 129, "total_steps": 339, "loss": 0.0004, "lr": 6.832865394749065e-05, "epoch": 1.1412024269167127, "percentage": 38.05, "elapsed_time": "0:56:17", "remaining_time": "1:31:38", "throughput": 7898.37, "total_tokens": 26680256}
{"current_steps": 130, "total_steps": 339, "loss": 0.0004, "lr": 6.789676628153143e-05, "epoch": 1.150027578599007, "percentage": 38.35, "elapsed_time": "0:56:44", "remaining_time": "1:31:13", "throughput": 7897.68, "total_tokens": 26887424}
{"current_steps": 131, "total_steps": 339, "loss": 0.0003, "lr": 6.746334162286307e-05, "epoch": 1.1588527302813016, "percentage": 38.64, "elapsed_time": "0:57:13", "remaining_time": "1:30:51", "throughput": 7897.31, "total_tokens": 27112736}
{"current_steps": 132, "total_steps": 339, "loss": 0.0004, "lr": 6.702841719444141e-05, "epoch": 1.1676778819635962, "percentage": 38.94, "elapsed_time": "0:57:40", "remaining_time": "1:30:26", "throughput": 7895.24, "total_tokens": 27320064}
{"current_steps": 133, "total_steps": 339, "loss": 0.0003, "lr": 6.659203034802397e-05, "epoch": 1.1765030336458908, "percentage": 39.23, "elapsed_time": "0:58:05", "remaining_time": "1:29:58", "throughput": 7895.5, "total_tokens": 27520544}
{"current_steps": 134, "total_steps": 339, "loss": 0.0009, "lr": 6.615421856096231e-05, "epoch": 1.1853281853281854, "percentage": 39.53, "elapsed_time": "0:58:32", "remaining_time": "1:29:34", "throughput": 7896.09, "total_tokens": 27737920}
{"current_steps": 135, "total_steps": 339, "loss": 0.0014, "lr": 6.571501943298334e-05, "epoch": 1.19415333701048, "percentage": 39.82, "elapsed_time": "0:59:01", "remaining_time": "1:29:11", "throughput": 7892.01, "total_tokens": 27947552}
{"current_steps": 136, "total_steps": 339, "loss": 0.0003, "lr": 6.527447068296026e-05, "epoch": 1.2029784886927744, "percentage": 40.12, "elapsed_time": "0:59:26", "remaining_time": "1:28:43", "throughput": 7891.89, "total_tokens": 28143808}
{"current_steps": 137, "total_steps": 339, "loss": 0.0002, "lr": 6.483261014567311e-05, "epoch": 1.211803640375069, "percentage": 40.41, "elapsed_time": "0:59:53", "remaining_time": "1:28:18", "throughput": 7888.92, "total_tokens": 28349312}
{"current_steps": 138, "total_steps": 339, "loss": 0.0002, "lr": 6.438947576855968e-05, "epoch": 1.2206287920573635, "percentage": 40.71, "elapsed_time": "1:00:20", "remaining_time": "1:27:53", "throughput": 7888.52, "total_tokens": 28560096}
{"current_steps": 139, "total_steps": 339, "loss": 0.0005, "lr": 6.394510560845637e-05, "epoch": 1.229453943739658, "percentage": 41.0, "elapsed_time": "1:00:45", "remaining_time": "1:27:25", "throughput": 7890.66, "total_tokens": 28764544}
{"current_steps": 140, "total_steps": 339, "loss": 0.0004, "lr": 6.349953782832991e-05, "epoch": 1.2382790954219525, "percentage": 41.3, "elapsed_time": "1:01:07", "remaining_time": "1:26:53", "throughput": 7892.64, "total_tokens": 28949360}
{"current_steps": 141, "total_steps": 339, "loss": 0.0002, "lr": 6.305281069399989e-05, "epoch": 1.247104247104247, "percentage": 41.59, "elapsed_time": "1:01:32", "remaining_time": "1:26:24", "throughput": 7894.92, "total_tokens": 29148112}
{"current_steps": 142, "total_steps": 339, "loss": 0.0004, "lr": 6.26049625708524e-05, "epoch": 1.2559293987865416, "percentage": 41.89, "elapsed_time": "1:02:01", "remaining_time": "1:26:02", "throughput": 7892.49, "total_tokens": 29370624}
{"current_steps": 143, "total_steps": 339, "loss": 0.0003, "lr": 6.215603192054522e-05, "epoch": 1.2647545504688362, "percentage": 42.18, "elapsed_time": "1:02:26", "remaining_time": "1:25:34", "throughput": 7894.05, "total_tokens": 29572464}
{"current_steps": 144, "total_steps": 339, "loss": 0.0006, "lr": 6.17060572977047e-05, "epoch": 1.2735797021511308, "percentage": 42.48, "elapsed_time": "1:02:51", "remaining_time": "1:25:07", "throughput": 7893.7, "total_tokens": 29771152}
{"current_steps": 145, "total_steps": 339, "loss": 0.0003, "lr": 6.125507734661458e-05, "epoch": 1.2824048538334254, "percentage": 42.77, "elapsed_time": "1:03:13", "remaining_time": "1:24:35", "throughput": 7896.62, "total_tokens": 29954960}
{"current_steps": 146, "total_steps": 339, "loss": 0.0004, "lr": 6.080313079789723e-05, "epoch": 1.2912300055157198, "percentage": 43.07, "elapsed_time": "1:03:40", "remaining_time": "1:24:10", "throughput": 7895.09, "total_tokens": 30165568}
{"current_steps": 147, "total_steps": 339, "loss": 0.0005, "lr": 6.035025646518746e-05, "epoch": 1.3000551571980143, "percentage": 43.36, "elapsed_time": "1:04:05", "remaining_time": "1:23:43", "throughput": 7897.58, "total_tokens": 30372160}
{"current_steps": 148, "total_steps": 339, "loss": 0.0003, "lr": 5.989649324179911e-05, "epoch": 1.308880308880309, "percentage": 43.66, "elapsed_time": "1:04:31", "remaining_time": "1:23:16", "throughput": 7896.39, "total_tokens": 30572752}
{"current_steps": 149, "total_steps": 339, "loss": 0.0004, "lr": 5.944188009738483e-05, "epoch": 1.3177054605626033, "percentage": 43.95, "elapsed_time": "1:04:57", "remaining_time": "1:22:49", "throughput": 7897.88, "total_tokens": 30780496}
{"current_steps": 150, "total_steps": 339, "loss": 0.0004, "lr": 5.8986456074589404e-05, "epoch": 1.3265306122448979, "percentage": 44.25, "elapsed_time": "1:05:19", "remaining_time": "1:22:19", "throughput": 7902.0, "total_tokens": 30975120}
{"current_steps": 151, "total_steps": 339, "loss": 0.0002, "lr": 5.853026028569667e-05, "epoch": 1.3353557639271925, "percentage": 44.54, "elapsed_time": "1:05:45", "remaining_time": "1:21:52", "throughput": 7900.57, "total_tokens": 31174000}
{"current_steps": 152, "total_steps": 339, "loss": 0.0003, "lr": 5.807333190927053e-05, "epoch": 1.344180915609487, "percentage": 44.84, "elapsed_time": "1:06:12", "remaining_time": "1:21:27", "throughput": 7901.36, "total_tokens": 31387088}
{"current_steps": 153, "total_steps": 339, "loss": 0.0003, "lr": 5.761571018679025e-05, "epoch": 1.3530060672917816, "percentage": 45.13, "elapsed_time": "1:06:37", "remaining_time": "1:21:00", "throughput": 7898.31, "total_tokens": 31576400}
{"current_steps": 154, "total_steps": 339, "loss": 0.0003, "lr": 5.715743441928041e-05, "epoch": 1.3618312189740762, "percentage": 45.43, "elapsed_time": "1:07:02", "remaining_time": "1:20:32", "throughput": 7901.98, "total_tokens": 31784320}
{"current_steps": 155, "total_steps": 339, "loss": 0.0004, "lr": 5.669854396393559e-05, "epoch": 1.3706563706563706, "percentage": 45.72, "elapsed_time": "1:07:29", "remaining_time": "1:20:07", "throughput": 7898.91, "total_tokens": 31987520}
{"current_steps": 156, "total_steps": 339, "loss": 0.0004, "lr": 5.6239078230740436e-05, "epoch": 1.3794815223386652, "percentage": 46.02, "elapsed_time": "1:07:53", "remaining_time": "1:19:38", "throughput": 7901.45, "total_tokens": 32187456}
{"current_steps": 157, "total_steps": 339, "loss": 0.0002, "lr": 5.5779076679085054e-05, "epoch": 1.3883066740209598, "percentage": 46.31, "elapsed_time": "1:08:18", "remaining_time": "1:19:11", "throughput": 7900.71, "total_tokens": 32384528}
{"current_steps": 158, "total_steps": 339, "loss": 0.0004, "lr": 5.531857881437612e-05, "epoch": 1.3971318257032543, "percentage": 46.61, "elapsed_time": "1:08:46", "remaining_time": "1:18:46", "throughput": 7898.98, "total_tokens": 32593040}
{"current_steps": 159, "total_steps": 339, "loss": 0.0003, "lr": 5.48576241846443e-05, "epoch": 1.4059569773855487, "percentage": 46.9, "elapsed_time": "1:09:12", "remaining_time": "1:18:21", "throughput": 7897.63, "total_tokens": 32797952}
{"current_steps": 160, "total_steps": 339, "loss": 0.0003, "lr": 5.4396252377147615e-05, "epoch": 1.4147821290678433, "percentage": 47.2, "elapsed_time": "1:09:39", "remaining_time": "1:17:55", "throughput": 7897.71, "total_tokens": 33008800}
{"current_steps": 161, "total_steps": 339, "loss": 0.0003, "lr": 5.3934503014971793e-05, "epoch": 1.4236072807501379, "percentage": 47.49, "elapsed_time": "1:10:04", "remaining_time": "1:17:28", "throughput": 7897.58, "total_tokens": 33208352}
{"current_steps": 162, "total_steps": 339, "loss": 0.0002, "lr": 5.347241575362729e-05, "epoch": 1.4324324324324325, "percentage": 47.79, "elapsed_time": "1:10:28", "remaining_time": "1:17:00", "throughput": 7900.98, "total_tokens": 33410208}
{"current_steps": 163, "total_steps": 339, "loss": 0.0003, "lr": 5.30100302776438e-05, "epoch": 1.441257584114727, "percentage": 48.08, "elapsed_time": "1:10:57", "remaining_time": "1:16:37", "throughput": 7899.49, "total_tokens": 33631888}
{"current_steps": 164, "total_steps": 339, "loss": 0.0004, "lr": 5.254738629716186e-05, "epoch": 1.4500827357970216, "percentage": 48.38, "elapsed_time": "1:11:21", "remaining_time": "1:16:09", "throughput": 7899.53, "total_tokens": 33825152}
{"current_steps": 165, "total_steps": 339, "loss": 0.0003, "lr": 5.208452354452274e-05, "epoch": 1.458907887479316, "percentage": 48.67, "elapsed_time": "1:11:45", "remaining_time": "1:15:40", "throughput": 7901.89, "total_tokens": 34020352}
{"current_steps": 166, "total_steps": 339, "loss": 0.0004, "lr": 5.162148177085604e-05, "epoch": 1.4677330391616106, "percentage": 48.97, "elapsed_time": "1:12:11", "remaining_time": "1:15:13", "throughput": 7902.03, "total_tokens": 34226288}
{"current_steps": 167, "total_steps": 339, "loss": 0.0016, "lr": 5.115830074266591e-05, "epoch": 1.4765581908439052, "percentage": 49.26, "elapsed_time": "1:12:37", "remaining_time": "1:14:47", "throughput": 7901.05, "total_tokens": 34426672}
{"current_steps": 168, "total_steps": 339, "loss": 0.0002, "lr": 5.0695020238415756e-05, "epoch": 1.4853833425261997, "percentage": 49.56, "elapsed_time": "1:13:03", "remaining_time": "1:14:21", "throughput": 7901.53, "total_tokens": 34636944}
{"current_steps": 169, "total_steps": 339, "loss": 0.0003, "lr": 5.0231680045112176e-05, "epoch": 1.494208494208494, "percentage": 49.85, "elapsed_time": "1:13:29", "remaining_time": "1:13:55", "throughput": 7901.79, "total_tokens": 34839456}
{"current_steps": 170, "total_steps": 339, "loss": 0.0002, "lr": 4.976831995488784e-05, "epoch": 1.5030336458907887, "percentage": 50.15, "elapsed_time": "1:13:53", "remaining_time": "1:13:27", "throughput": 7901.03, "total_tokens": 35031600}
{"current_steps": 171, "total_steps": 339, "loss": 0.0004, "lr": 4.9304979761584256e-05, "epoch": 1.5118587975730833, "percentage": 50.44, "elapsed_time": "1:14:16", "remaining_time": "1:12:58", "throughput": 7903.96, "total_tokens": 35227728}
{"current_steps": 172, "total_steps": 339, "loss": 0.0002, "lr": 4.884169925733409e-05, "epoch": 1.5206839492553779, "percentage": 50.74, "elapsed_time": "1:14:42", "remaining_time": "1:12:32", "throughput": 7905.12, "total_tokens": 35436528}
{"current_steps": 173, "total_steps": 339, "loss": 0.0002, "lr": 4.837851822914397e-05, "epoch": 1.5295091009376725, "percentage": 51.03, "elapsed_time": "1:15:04", "remaining_time": "1:12:02", "throughput": 7909.17, "total_tokens": 35628624}
{"current_steps": 174, "total_steps": 339, "loss": 0.0002, "lr": 4.791547645547726e-05, "epoch": 1.538334252619967, "percentage": 51.33, "elapsed_time": "1:15:29", "remaining_time": "1:11:35", "throughput": 7909.02, "total_tokens": 35827376}
{"current_steps": 175, "total_steps": 339, "loss": 0.0003, "lr": 4.745261370283817e-05, "epoch": 1.5471594043022614, "percentage": 51.62, "elapsed_time": "1:16:00", "remaining_time": "1:11:14", "throughput": 7905.59, "total_tokens": 36056560}
{"current_steps": 176, "total_steps": 339, "loss": 0.0002, "lr": 4.698996972235622e-05, "epoch": 1.555984555984556, "percentage": 51.92, "elapsed_time": "1:16:27", "remaining_time": "1:10:48", "throughput": 7905.47, "total_tokens": 36267568}
{"current_steps": 177, "total_steps": 339, "loss": 0.0027, "lr": 4.652758424637271e-05, "epoch": 1.5648097076668506, "percentage": 52.21, "elapsed_time": "1:16:54", "remaining_time": "1:10:23", "throughput": 7904.7, "total_tokens": 36473008}
{"current_steps": 178, "total_steps": 339, "loss": 0.0004, "lr": 4.606549698502823e-05, "epoch": 1.573634859349145, "percentage": 52.51, "elapsed_time": "1:17:18", "remaining_time": "1:09:55", "throughput": 7905.8, "total_tokens": 36670944}
{"current_steps": 179, "total_steps": 339, "loss": 0.0001, "lr": 4.56037476228524e-05, "epoch": 1.5824600110314395, "percentage": 52.8, "elapsed_time": "1:17:44", "remaining_time": "1:09:29", "throughput": 7907.65, "total_tokens": 36882256}
{"current_steps": 180, "total_steps": 339, "loss": 0.0004, "lr": 4.5142375815355706e-05, "epoch": 1.591285162713734, "percentage": 53.1, "elapsed_time": "1:18:10", "remaining_time": "1:09:03", "throughput": 7907.43, "total_tokens": 37091392}
{"current_steps": 181, "total_steps": 339, "loss": 0.0002, "lr": 4.468142118562389e-05, "epoch": 1.6001103143960287, "percentage": 53.39, "elapsed_time": "1:18:41", "remaining_time": "1:08:41", "throughput": 7902.86, "total_tokens": 37309680}
{"current_steps": 182, "total_steps": 339, "loss": 0.0003, "lr": 4.4220923320914964e-05, "epoch": 1.6089354660783233, "percentage": 53.69, "elapsed_time": "1:19:07", "remaining_time": "1:08:15", "throughput": 7903.1, "total_tokens": 37517952}
{"current_steps": 183, "total_steps": 339, "loss": 0.0003, "lr": 4.376092176925958e-05, "epoch": 1.6177606177606179, "percentage": 53.98, "elapsed_time": "1:19:33", "remaining_time": "1:07:49", "throughput": 7904.08, "total_tokens": 37732160}
{"current_steps": 184, "total_steps": 339, "loss": 0.0004, "lr": 4.330145603606441e-05, "epoch": 1.6265857694429124, "percentage": 54.28, "elapsed_time": "1:19:59", "remaining_time": "1:07:22", "throughput": 7905.25, "total_tokens": 37940368}
{"current_steps": 185, "total_steps": 339, "loss": 0.0004, "lr": 4.2842565580719595e-05, "epoch": 1.6354109211252068, "percentage": 54.57, "elapsed_time": "1:20:21", "remaining_time": "1:06:53", "throughput": 7908.78, "total_tokens": 38135024}
{"current_steps": 186, "total_steps": 339, "loss": 0.0002, "lr": 4.238428981320975e-05, "epoch": 1.6442360728075014, "percentage": 54.87, "elapsed_time": "1:20:45", "remaining_time": "1:06:25", "throughput": 7912.45, "total_tokens": 38336176}
{"current_steps": 187, "total_steps": 339, "loss": 0.0003, "lr": 4.192666809072948e-05, "epoch": 1.6530612244897958, "percentage": 55.16, "elapsed_time": "1:21:11", "remaining_time": "1:05:59", "throughput": 7912.95, "total_tokens": 38548880}
{"current_steps": 188, "total_steps": 339, "loss": 0.0003, "lr": 4.146973971430333e-05, "epoch": 1.6618863761720903, "percentage": 55.46, "elapsed_time": "1:21:37", "remaining_time": "1:05:33", "throughput": 7913.14, "total_tokens": 38755920}
{"current_steps": 189, "total_steps": 339, "loss": 0.0002, "lr": 4.101354392541061e-05, "epoch": 1.670711527854385, "percentage": 55.75, "elapsed_time": "1:22:04", "remaining_time": "1:05:08", "throughput": 7914.08, "total_tokens": 38973328}
{"current_steps": 190, "total_steps": 339, "loss": 0.0003, "lr": 4.0558119902615174e-05, "epoch": 1.6795366795366795, "percentage": 56.05, "elapsed_time": "1:22:34", "remaining_time": "1:04:45", "throughput": 7911.16, "total_tokens": 39193232}
{"current_steps": 191, "total_steps": 339, "loss": 0.0003, "lr": 4.010350675820091e-05, "epoch": 1.688361831218974, "percentage": 56.34, "elapsed_time": "1:23:00", "remaining_time": "1:04:19", "throughput": 7911.74, "total_tokens": 39406608}
{"current_steps": 192, "total_steps": 339, "loss": 0.0004, "lr": 3.964974353481254e-05, "epoch": 1.6971869829012687, "percentage": 56.64, "elapsed_time": "1:23:28", "remaining_time": "1:03:54", "throughput": 7911.05, "total_tokens": 39620160}
{"current_steps": 193, "total_steps": 339, "loss": 0.0001, "lr": 3.919686920210277e-05, "epoch": 1.7060121345835633, "percentage": 56.93, "elapsed_time": "1:23:53", "remaining_time": "1:03:27", "throughput": 7910.45, "total_tokens": 39815952}
{"current_steps": 194, "total_steps": 339, "loss": 0.0003, "lr": 3.874492265338544e-05, "epoch": 1.7148372862658579, "percentage": 57.23, "elapsed_time": "1:24:17", "remaining_time": "1:03:00", "throughput": 7911.47, "total_tokens": 40015408}
{"current_steps": 195, "total_steps": 339, "loss": 0.0002, "lr": 3.829394270229531e-05, "epoch": 1.7236624379481522, "percentage": 57.52, "elapsed_time": "1:24:42", "remaining_time": "1:02:32", "throughput": 7913.07, "total_tokens": 40215328}
{"current_steps": 196, "total_steps": 339, "loss": 0.0002, "lr": 3.784396807945477e-05, "epoch": 1.7324875896304468, "percentage": 57.82, "elapsed_time": "1:25:07", "remaining_time": "1:02:06", "throughput": 7912.61, "total_tokens": 40414384}
{"current_steps": 197, "total_steps": 339, "loss": 0.0002, "lr": 3.7395037429147615e-05, "epoch": 1.7413127413127412, "percentage": 58.11, "elapsed_time": "1:25:32", "remaining_time": "1:01:39", "throughput": 7914.15, "total_tokens": 40620656}
{"current_steps": 198, "total_steps": 339, "loss": 0.0003, "lr": 3.694718930600012e-05, "epoch": 1.7501378929950357, "percentage": 58.41, "elapsed_time": "1:26:04", "remaining_time": "1:01:17", "throughput": 7908.9, "total_tokens": 40847008}
{"current_steps": 199, "total_steps": 339, "loss": 0.0001, "lr": 3.65004621716701e-05, "epoch": 1.7589630446773303, "percentage": 58.7, "elapsed_time": "1:26:27", "remaining_time": "1:00:49", "throughput": 7909.88, "total_tokens": 41036368}
{"current_steps": 200, "total_steps": 339, "loss": 0.0003, "lr": 3.6054894391543646e-05, "epoch": 1.767788196359625, "percentage": 59.0, "elapsed_time": "1:26:59", "remaining_time": "1:00:27", "throughput": 7904.23, "total_tokens": 41252976}
{"current_steps": 201, "total_steps": 339, "loss": 0.0002, "lr": 3.561052423144032e-05, "epoch": 1.7766133480419195, "percentage": 59.29, "elapsed_time": "1:27:29", "remaining_time": "1:00:04", "throughput": 7898.91, "total_tokens": 41465104}
{"current_steps": 202, "total_steps": 339, "loss": 0.0002, "lr": 3.5167389854326905e-05, "epoch": 1.785438499724214, "percentage": 59.59, "elapsed_time": "1:27:56", "remaining_time": "0:59:38", "throughput": 7897.44, "total_tokens": 41670800}
{"current_steps": 203, "total_steps": 339, "loss": 0.0013, "lr": 3.4725529317039754e-05, "epoch": 1.7942636514065087, "percentage": 59.88, "elapsed_time": "1:28:25", "remaining_time": "0:59:14", "throughput": 7894.63, "total_tokens": 41883536}
{"current_steps": 204, "total_steps": 339, "loss": 0.0001, "lr": 3.428498056701665e-05, "epoch": 1.803088803088803, "percentage": 60.18, "elapsed_time": "1:28:51", "remaining_time": "0:58:48", "throughput": 7893.32, "total_tokens": 42083360}
{"current_steps": 205, "total_steps": 339, "loss": 0.0002, "lr": 3.38457814390377e-05, "epoch": 1.8119139547710976, "percentage": 60.47, "elapsed_time": "1:29:16", "remaining_time": "0:58:21", "throughput": 7893.48, "total_tokens": 42283120}
{"current_steps": 206, "total_steps": 339, "loss": 0.0003, "lr": 3.340796965197604e-05, "epoch": 1.8207391064533922, "percentage": 60.77, "elapsed_time": "1:29:41", "remaining_time": "0:57:54", "throughput": 7897.32, "total_tokens": 42499088}
{"current_steps": 207, "total_steps": 339, "loss": 0.0001, "lr": 3.297158280555862e-05, "epoch": 1.8295642581356866, "percentage": 61.06, "elapsed_time": "1:30:05", "remaining_time": "0:57:26", "throughput": 7898.07, "total_tokens": 42692976}
{"current_steps": 208, "total_steps": 339, "loss": 0.0003, "lr": 3.2536658377136935e-05, "epoch": 1.8383894098179812, "percentage": 61.36, "elapsed_time": "1:30:32", "remaining_time": "0:57:01", "throughput": 7898.41, "total_tokens": 42907216}
{"current_steps": 209, "total_steps": 339, "loss": 0.0001, "lr": 3.210323371846857e-05, "epoch": 1.8472145615002757, "percentage": 61.65, "elapsed_time": "1:30:58", "remaining_time": "0:56:35", "throughput": 7898.41, "total_tokens": 43112448}
{"current_steps": 210, "total_steps": 339, "loss": 0.0003, "lr": 3.167134605250938e-05, "epoch": 1.8560397131825703, "percentage": 61.95, "elapsed_time": "1:31:27", "remaining_time": "0:56:10", "throughput": 7897.79, "total_tokens": 43340096}
{"current_steps": 211, "total_steps": 339, "loss": 0.0001, "lr": 3.124103247021657e-05, "epoch": 1.864864864864865, "percentage": 62.24, "elapsed_time": "1:31:53", "remaining_time": "0:55:44", "throughput": 7896.37, "total_tokens": 43539664}
{"current_steps": 212, "total_steps": 339, "loss": 0.0003, "lr": 3.081232992736355e-05, "epoch": 1.8736900165471595, "percentage": 62.54, "elapsed_time": "1:32:16", "remaining_time": "0:55:16", "throughput": 7897.48, "total_tokens": 43727664}
{"current_steps": 213, "total_steps": 339, "loss": 0.0002, "lr": 3.0385275241365962e-05, "epoch": 1.882515168229454, "percentage": 62.83, "elapsed_time": "1:32:44", "remaining_time": "0:54:51", "throughput": 7898.39, "total_tokens": 43953584}
{"current_steps": 214, "total_steps": 339, "loss": 0.0002, "lr": 2.9959905088119776e-05, "epoch": 1.8913403199117484, "percentage": 63.13, "elapsed_time": "1:33:11", "remaining_time": "0:54:25", "throughput": 7897.6, "total_tokens": 44157504}
{"current_steps": 215, "total_steps": 339, "loss": 0.0001, "lr": 2.9536255998851613e-05, "epoch": 1.900165471594043, "percentage": 63.42, "elapsed_time": "1:33:35", "remaining_time": "0:53:58", "throughput": 7898.54, "total_tokens": 44350448}
{"current_steps": 216, "total_steps": 339, "loss": 0.0002, "lr": 2.9114364356981272e-05, "epoch": 1.9089906232763376, "percentage": 63.72, "elapsed_time": "1:33:59", "remaining_time": "0:53:31", "throughput": 7900.99, "total_tokens": 44561472}
{"current_steps": 217, "total_steps": 339, "loss": 0.0002, "lr": 2.8694266394997238e-05, "epoch": 1.917815774958632, "percentage": 64.01, "elapsed_time": "1:34:27", "remaining_time": "0:53:06", "throughput": 7899.67, "total_tokens": 44769936}
{"current_steps": 218, "total_steps": 339, "loss": 0.0002, "lr": 2.8275998191344888e-05, "epoch": 1.9266409266409266, "percentage": 64.31, "elapsed_time": "1:34:54", "remaining_time": "0:52:40", "throughput": 7898.82, "total_tokens": 44979344}
{"current_steps": 219, "total_steps": 339, "loss": 0.0002, "lr": 2.7859595667328026e-05, "epoch": 1.9354660783232212, "percentage": 64.6, "elapsed_time": "1:35:22", "remaining_time": "0:52:15", "throughput": 7898.4, "total_tokens": 45196944}
{"current_steps": 220, "total_steps": 339, "loss": 0.0001, "lr": 2.7445094584024067e-05, "epoch": 1.9442912300055157, "percentage": 64.9, "elapsed_time": "1:35:51", "remaining_time": "0:51:50", "throughput": 7895.44, "total_tokens": 45406832}
{"current_steps": 221, "total_steps": 339, "loss": 0.0003, "lr": 2.7032530539212658e-05, "epoch": 1.9531163816878103, "percentage": 65.19, "elapsed_time": "1:36:18", "remaining_time": "0:51:25", "throughput": 7892.18, "total_tokens": 45603120}
{"current_steps": 222, "total_steps": 339, "loss": 0.0002, "lr": 2.6621938964318595e-05, "epoch": 1.961941533370105, "percentage": 65.49, "elapsed_time": "1:36:44", "remaining_time": "0:50:59", "throughput": 7890.65, "total_tokens": 45805184}
{"current_steps": 223, "total_steps": 339, "loss": 0.0001, "lr": 2.621335512136899e-05, "epoch": 1.9707666850523995, "percentage": 65.78, "elapsed_time": "1:37:08", "remaining_time": "0:50:31", "throughput": 7892.67, "total_tokens": 46001184}
{"current_steps": 224, "total_steps": 339, "loss": 0.0002, "lr": 2.5806814099964772e-05, "epoch": 1.9795918367346939, "percentage": 66.08, "elapsed_time": "1:37:34", "remaining_time": "0:50:05", "throughput": 7892.1, "total_tokens": 46206288}
{"current_steps": 225, "total_steps": 339, "loss": 0.0002, "lr": 2.540235081426736e-05, "epoch": 1.9884169884169884, "percentage": 66.37, "elapsed_time": "1:38:03", "remaining_time": "0:49:40", "throughput": 7891.47, "total_tokens": 46427344}
{"current_steps": 226, "total_steps": 339, "loss": 0.0003, "lr": 2.500000000000001e-05, "epoch": 1.9972421400992828, "percentage": 66.67, "elapsed_time": "1:38:28", "remaining_time": "0:49:14", "throughput": 7891.65, "total_tokens": 46627344}
{"current_steps": 227, "total_steps": 339, "loss": 0.0011, "lr": 2.459979621146477e-05, "epoch": 2.0088251516822946, "percentage": 66.96, "elapsed_time": "1:39:03", "remaining_time": "0:48:52", "throughput": 7890.98, "total_tokens": 46901504}
{"current_steps": 228, "total_steps": 339, "loss": 0.0001, "lr": 2.4201773818574956e-05, "epoch": 2.017650303364589, "percentage": 67.26, "elapsed_time": "1:39:31", "remaining_time": "0:48:27", "throughput": 7888.59, "total_tokens": 47104400}
{"current_steps": 229, "total_steps": 339, "loss": 0.0001, "lr": 2.3805967003903333e-05, "epoch": 2.0264754550468838, "percentage": 67.55, "elapsed_time": "1:39:56", "remaining_time": "0:48:00", "throughput": 7889.79, "total_tokens": 47314176}
{"current_steps": 230, "total_steps": 339, "loss": 0.0003, "lr": 2.3412409759746528e-05, "epoch": 2.0353006067291783, "percentage": 67.85, "elapsed_time": "1:40:25", "remaining_time": "0:47:35", "throughput": 7887.38, "total_tokens": 47525264}
{"current_steps": 231, "total_steps": 339, "loss": 0.0001, "lr": 2.302113588520578e-05, "epoch": 2.0441257584114725, "percentage": 68.14, "elapsed_time": "1:40:49", "remaining_time": "0:47:08", "throughput": 7889.45, "total_tokens": 47724528}
{"current_steps": 232, "total_steps": 339, "loss": 0.0002, "lr": 2.2632178983284153e-05, "epoch": 2.052950910093767, "percentage": 68.44, "elapsed_time": "1:41:17", "remaining_time": "0:46:42", "throughput": 7887.07, "total_tokens": 47932624}
{"current_steps": 233, "total_steps": 339, "loss": 0.0001, "lr": 2.2245572458000712e-05, "epoch": 2.0617760617760617, "percentage": 68.73, "elapsed_time": "1:41:42", "remaining_time": "0:46:16", "throughput": 7889.59, "total_tokens": 48148608}
{"current_steps": 234, "total_steps": 339, "loss": 0.0025, "lr": 2.1861349511521815e-05, "epoch": 2.0706012134583562, "percentage": 69.03, "elapsed_time": "1:42:14", "remaining_time": "0:45:52", "throughput": 7885.55, "total_tokens": 48373632}
{"current_steps": 235, "total_steps": 339, "loss": 0.0013, "lr": 2.147954314130955e-05, "epoch": 2.079426365140651, "percentage": 69.32, "elapsed_time": "1:42:44", "remaining_time": "0:45:28", "throughput": 7881.47, "total_tokens": 48586512}
{"current_steps": 236, "total_steps": 339, "loss": 0.0001, "lr": 2.1100186137288e-05, "epoch": 2.0882515168229454, "percentage": 69.62, "elapsed_time": "1:43:08", "remaining_time": "0:45:01", "throughput": 7884.07, "total_tokens": 48793568}
{"current_steps": 237, "total_steps": 339, "loss": 0.0001, "lr": 2.072331107902713e-05, "epoch": 2.09707666850524, "percentage": 69.91, "elapsed_time": "1:43:35", "remaining_time": "0:44:34", "throughput": 7884.69, "total_tokens": 49006224}
{"current_steps": 238, "total_steps": 339, "loss": 0.0002, "lr": 2.0348950332944834e-05, "epoch": 2.1059018201875346, "percentage": 70.21, "elapsed_time": "1:44:00", "remaining_time": "0:44:08", "throughput": 7886.69, "total_tokens": 49217632}
{"current_steps": 239, "total_steps": 339, "loss": 0.0001, "lr": 1.9977136049527345e-05, "epoch": 2.114726971869829, "percentage": 70.5, "elapsed_time": "1:44:26", "remaining_time": "0:43:42", "throughput": 7886.9, "total_tokens": 49426624}
{"current_steps": 240, "total_steps": 339, "loss": 0.0001, "lr": 1.960790016056801e-05, "epoch": 2.1235521235521237, "percentage": 70.8, "elapsed_time": "1:44:50", "remaining_time": "0:43:14", "throughput": 7888.14, "total_tokens": 49623376}
{"current_steps": 241, "total_steps": 339, "loss": 0.0002, "lr": 1.9241274376425e-05, "epoch": 2.132377275234418, "percentage": 71.09, "elapsed_time": "1:45:16", "remaining_time": "0:42:48", "throughput": 7889.13, "total_tokens": 49828144}
{"current_steps": 242, "total_steps": 339, "loss": 0.0002, "lr": 1.8877290183298057e-05, "epoch": 2.1412024269167125, "percentage": 71.39, "elapsed_time": "1:45:40", "remaining_time": "0:42:21", "throughput": 7888.3, "total_tokens": 50018448}
{"current_steps": 243, "total_steps": 339, "loss": 0.0001, "lr": 1.8515978840524302e-05, "epoch": 2.150027578599007, "percentage": 71.68, "elapsed_time": "1:46:06", "remaining_time": "0:41:55", "throughput": 7887.77, "total_tokens": 50218176}
{"current_steps": 244, "total_steps": 339, "loss": 0.0002, "lr": 1.815737137789377e-05, "epoch": 2.1588527302813016, "percentage": 71.98, "elapsed_time": "1:46:31", "remaining_time": "0:41:28", "throughput": 7889.8, "total_tokens": 50424896}
{"current_steps": 245, "total_steps": 339, "loss": 0.0006, "lr": 1.7801498592984446e-05, "epoch": 2.1676778819635962, "percentage": 72.27, "elapsed_time": "1:46:59", "remaining_time": "0:41:03", "throughput": 7887.66, "total_tokens": 50635088}
{"current_steps": 246, "total_steps": 339, "loss": 0.0001, "lr": 1.7448391048517376e-05, "epoch": 2.176503033645891, "percentage": 72.57, "elapsed_time": "1:47:27", "remaining_time": "0:40:37", "throughput": 7886.91, "total_tokens": 50849552}
{"current_steps": 247, "total_steps": 339, "loss": 0.0002, "lr": 1.7098079069731958e-05, "epoch": 2.1853281853281854, "percentage": 72.86, "elapsed_time": "1:47:49", "remaining_time": "0:40:09", "throughput": 7889.08, "total_tokens": 51037776}
{"current_steps": 248, "total_steps": 339, "loss": 0.0002, "lr": 1.6750592741781497e-05, "epoch": 2.19415333701048, "percentage": 73.16, "elapsed_time": "1:48:14", "remaining_time": "0:39:42", "throughput": 7890.61, "total_tokens": 51242672}
{"current_steps": 249, "total_steps": 339, "loss": 0.0001, "lr": 1.640596190714947e-05, "epoch": 2.2029784886927746, "percentage": 73.45, "elapsed_time": "1:48:39", "remaining_time": "0:39:16", "throughput": 7889.22, "total_tokens": 51437008}
{"current_steps": 250, "total_steps": 339, "loss": 0.0001, "lr": 1.6064216163086716e-05, "epoch": 2.211803640375069, "percentage": 73.75, "elapsed_time": "1:49:04", "remaining_time": "0:38:49", "throughput": 7890.88, "total_tokens": 51641264}
{"current_steps": 251, "total_steps": 339, "loss": 0.0001, "lr": 1.5725384859069455e-05, "epoch": 2.2206287920573633, "percentage": 74.04, "elapsed_time": "1:49:30", "remaining_time": "0:38:23", "throughput": 7890.72, "total_tokens": 51842592}
{"current_steps": 252, "total_steps": 339, "loss": 0.0012, "lr": 1.538949709427886e-05, "epoch": 2.229453943739658, "percentage": 74.34, "elapsed_time": "1:49:55", "remaining_time": "0:37:57", "throughput": 7890.97, "total_tokens": 52047456}
{"current_steps": 253, "total_steps": 339, "loss": 0.0001, "lr": 1.5056581715101886e-05, "epoch": 2.2382790954219525, "percentage": 74.63, "elapsed_time": "1:50:19", "remaining_time": "0:37:30", "throughput": 7892.37, "total_tokens": 52242208}
{"current_steps": 254, "total_steps": 339, "loss": 0.0003, "lr": 1.472666731265394e-05, "epoch": 2.247104247104247, "percentage": 74.93, "elapsed_time": "1:50:42", "remaining_time": "0:37:02", "throughput": 7894.16, "total_tokens": 52436800}
{"current_steps": 255, "total_steps": 339, "loss": 0.0001, "lr": 1.4399782220323515e-05, "epoch": 2.2559293987865416, "percentage": 75.22, "elapsed_time": "1:51:06", "remaining_time": "0:36:35", "throughput": 7894.39, "total_tokens": 52624752}
{"current_steps": 256, "total_steps": 339, "loss": 0.0001, "lr": 1.4075954511338785e-05, "epoch": 2.2647545504688362, "percentage": 75.52, "elapsed_time": "1:51:32", "remaining_time": "0:36:09", "throughput": 7895.04, "total_tokens": 52836384}
{"current_steps": 257, "total_steps": 339, "loss": 0.0001, "lr": 1.3755211996356687e-05, "epoch": 2.273579702151131, "percentage": 75.81, "elapsed_time": "1:52:00", "remaining_time": "0:35:44", "throughput": 7894.62, "total_tokens": 53059296}
{"current_steps": 258, "total_steps": 339, "loss": 0.0001, "lr": 1.3437582221074573e-05, "epoch": 2.2824048538334254, "percentage": 76.11, "elapsed_time": "1:52:28", "remaining_time": "0:35:18", "throughput": 7893.02, "total_tokens": 53267440}
{"current_steps": 259, "total_steps": 339, "loss": 0.0001, "lr": 1.3123092463864456e-05, "epoch": 2.29123000551572, "percentage": 76.4, "elapsed_time": "1:52:59", "remaining_time": "0:34:54", "throughput": 7891.68, "total_tokens": 53501008}
{"current_steps": 260, "total_steps": 339, "loss": 0.0001, "lr": 1.2811769733430406e-05, "epoch": 2.300055157198014, "percentage": 76.7, "elapsed_time": "1:53:24", "remaining_time": "0:34:27", "throughput": 7892.09, "total_tokens": 53700432}
{"current_steps": 261, "total_steps": 339, "loss": 0.0002, "lr": 1.250364076648894e-05, "epoch": 2.3088803088803087, "percentage": 76.99, "elapsed_time": "1:53:50", "remaining_time": "0:34:01", "throughput": 7894.29, "total_tokens": 53919616}
{"current_steps": 262, "total_steps": 339, "loss": 0.0001, "lr": 1.2198732025472876e-05, "epoch": 2.3177054605626033, "percentage": 77.29, "elapsed_time": "1:54:17", "remaining_time": "0:33:35", "throughput": 7893.79, "total_tokens": 54130528}
{"current_steps": 263, "total_steps": 339, "loss": 0.0002, "lr": 1.1897069696258755e-05, "epoch": 2.326530612244898, "percentage": 77.58, "elapsed_time": "1:54:44", "remaining_time": "0:33:09", "throughput": 7894.54, "total_tokens": 54350560}
{"current_steps": 264, "total_steps": 339, "loss": 0.0001, "lr": 1.1598679685917901e-05, "epoch": 2.3353557639271925, "percentage": 77.88, "elapsed_time": "1:55:08", "remaining_time": "0:32:42", "throughput": 7894.72, "total_tokens": 54542224}
{"current_steps": 265, "total_steps": 339, "loss": 0.0002, "lr": 1.1303587620491513e-05, "epoch": 2.344180915609487, "percentage": 78.17, "elapsed_time": "1:55:35", "remaining_time": "0:32:16", "throughput": 7893.77, "total_tokens": 54745136}
{"current_steps": 266, "total_steps": 339, "loss": 0.0001, "lr": 1.1011818842789928e-05, "epoch": 2.3530060672917816, "percentage": 78.47, "elapsed_time": "1:56:01", "remaining_time": "0:31:50", "throughput": 7895.0, "total_tokens": 54957584}
{"current_steps": 267, "total_steps": 339, "loss": 0.0001, "lr": 1.0723398410216084e-05, "epoch": 2.361831218974076, "percentage": 78.76, "elapsed_time": "1:56:26", "remaining_time": "0:31:24", "throughput": 7895.05, "total_tokens": 55162496}
{"current_steps": 268, "total_steps": 339, "loss": 0.0002, "lr": 1.0438351092613569e-05, "epoch": 2.370656370656371, "percentage": 79.06, "elapsed_time": "1:56:53", "remaining_time": "0:30:58", "throughput": 7895.15, "total_tokens": 55376544}
{"current_steps": 269, "total_steps": 339, "loss": 0.0001, "lr": 1.0156701370139454e-05, "epoch": 2.3794815223386654, "percentage": 79.35, "elapsed_time": "1:57:19", "remaining_time": "0:30:31", "throughput": 7895.9, "total_tokens": 55583072}
{"current_steps": 270, "total_steps": 339, "loss": 0.0002, "lr": 9.878473431161767e-06, "epoch": 2.38830667402096, "percentage": 79.65, "elapsed_time": "1:57:46", "remaining_time": "0:30:05", "throughput": 7897.0, "total_tokens": 55801200}
{"current_steps": 271, "total_steps": 339, "loss": 0.0001, "lr": 9.603691170182317e-06, "epoch": 2.397131825703254, "percentage": 79.94, "elapsed_time": "1:58:14", "remaining_time": "0:29:40", "throughput": 7893.16, "total_tokens": 55998080}
{"current_steps": 272, "total_steps": 339, "loss": 0.0002, "lr": 9.33237818578449e-06, "epoch": 2.4059569773855487, "percentage": 80.24, "elapsed_time": "1:58:41", "remaining_time": "0:29:14", "throughput": 7891.24, "total_tokens": 56200448}
{"current_steps": 273, "total_steps": 339, "loss": 0.0001, "lr": 9.064557778606631e-06, "epoch": 2.4147821290678433, "percentage": 80.53, "elapsed_time": "1:59:05", "remaining_time": "0:28:47", "throughput": 7893.3, "total_tokens": 56400416}
{"current_steps": 274, "total_steps": 339, "loss": 0.0002, "lr": 8.800252949340998e-06, "epoch": 2.423607280750138, "percentage": 80.83, "elapsed_time": "1:59:31", "remaining_time": "0:28:21", "throughput": 7893.02, "total_tokens": 56606128}
{"current_steps": 275, "total_steps": 339, "loss": 0.0, "lr": 8.539486396758356e-06, "epoch": 2.4324324324324325, "percentage": 81.12, "elapsed_time": "1:59:56", "remaining_time": "0:27:54", "throughput": 7892.52, "total_tokens": 56797824}
{"current_steps": 276, "total_steps": 339, "loss": 0.0001, "lr": 8.28228051575864e-06, "epoch": 2.441257584114727, "percentage": 81.42, "elapsed_time": "2:00:22", "remaining_time": "0:27:28", "throughput": 7892.63, "total_tokens": 57006384}
{"current_steps": 277, "total_steps": 339, "loss": 0.0001, "lr": 8.02865739544767e-06, "epoch": 2.4500827357970216, "percentage": 81.71, "elapsed_time": "2:00:48", "remaining_time": "0:27:02", "throughput": 7892.41, "total_tokens": 57207824}
{"current_steps": 278, "total_steps": 339, "loss": 0.0001, "lr": 7.778638817240042e-06, "epoch": 2.458907887479316, "percentage": 82.01, "elapsed_time": "2:01:16", "remaining_time": "0:26:36", "throughput": 7889.96, "total_tokens": 57415152}
{"current_steps": 279, "total_steps": 339, "loss": 0.0001, "lr": 7.532246252988617e-06, "epoch": 2.467733039161611, "percentage": 82.3, "elapsed_time": "2:01:41", "remaining_time": "0:26:10", "throughput": 7892.18, "total_tokens": 57628096}
{"current_steps": 280, "total_steps": 339, "loss": 0.0001, "lr": 7.289500863140414e-06, "epoch": 2.476558190843905, "percentage": 82.6, "elapsed_time": "2:02:05", "remaining_time": "0:25:43", "throughput": 7893.12, "total_tokens": 57824064}
{"current_steps": 281, "total_steps": 339, "loss": 0.0002, "lr": 7.05042349491935e-06, "epoch": 2.4853833425261995, "percentage": 82.89, "elapsed_time": "2:02:35", "remaining_time": "0:25:18", "throughput": 7891.37, "total_tokens": 58042720}
{"current_steps": 282, "total_steps": 339, "loss": 0.0001, "lr": 6.815034680535915e-06, "epoch": 2.494208494208494, "percentage": 83.19, "elapsed_time": "2:03:02", "remaining_time": "0:24:52", "throughput": 7891.23, "total_tokens": 58255408}
{"current_steps": 283, "total_steps": 339, "loss": 0.0001, "lr": 6.5833546354237556e-06, "epoch": 2.5030336458907887, "percentage": 83.48, "elapsed_time": "2:03:29", "remaining_time": "0:24:26", "throughput": 7890.21, "total_tokens": 58464800}
{"current_steps": 284, "total_steps": 339, "loss": 0.0001, "lr": 6.355403256503595e-06, "epoch": 2.5118587975730833, "percentage": 83.78, "elapsed_time": "2:03:56", "remaining_time": "0:24:00", "throughput": 7889.96, "total_tokens": 58672496}
{"current_steps": 285, "total_steps": 339, "loss": 0.0002, "lr": 6.1312001204745115e-06, "epoch": 2.520683949255378, "percentage": 84.07, "elapsed_time": "2:04:25", "remaining_time": "0:23:34", "throughput": 7889.86, "total_tokens": 58898256}
{"current_steps": 286, "total_steps": 339, "loss": 0.0001, "lr": 5.910764482132575e-06, "epoch": 2.5295091009376725, "percentage": 84.37, "elapsed_time": "2:04:51", "remaining_time": "0:23:08", "throughput": 7889.91, "total_tokens": 59107152}
{"current_steps": 287, "total_steps": 339, "loss": 0.0002, "lr": 5.6941152727173265e-06, "epoch": 2.538334252619967, "percentage": 84.66, "elapsed_time": "2:05:15", "remaining_time": "0:22:41", "throughput": 7891.05, "total_tokens": 59307664}
{"current_steps": 288, "total_steps": 339, "loss": 0.0003, "lr": 5.481271098285817e-06, "epoch": 2.5471594043022616, "percentage": 84.96, "elapsed_time": "2:05:42", "remaining_time": "0:22:15", "throughput": 7890.97, "total_tokens": 59514736}
{"current_steps": 289, "total_steps": 339, "loss": 0.0001, "lr": 5.272250238114856e-06, "epoch": 2.5559845559845558, "percentage": 85.25, "elapsed_time": "2:06:06", "remaining_time": "0:21:49", "throughput": 7891.95, "total_tokens": 59712512}
{"current_steps": 290, "total_steps": 339, "loss": 0.0001, "lr": 5.067070643131055e-06, "epoch": 2.564809707666851, "percentage": 85.55, "elapsed_time": "2:06:29", "remaining_time": "0:21:22", "throughput": 7893.32, "total_tokens": 59910000}
{"current_steps": 291, "total_steps": 339, "loss": 0.0002, "lr": 4.865749934369223e-06, "epoch": 2.573634859349145, "percentage": 85.84, "elapsed_time": "2:06:55", "remaining_time": "0:20:56", "throughput": 7893.98, "total_tokens": 60116400}
{"current_steps": 292, "total_steps": 339, "loss": 0.0002, "lr": 4.668305401459022e-06, "epoch": 2.5824600110314395, "percentage": 86.14, "elapsed_time": "2:07:22", "remaining_time": "0:20:30", "throughput": 7892.9, "total_tokens": 60320368}
{"current_steps": 293, "total_steps": 339, "loss": 0.0001, "lr": 4.474754001140191e-06, "epoch": 2.591285162713734, "percentage": 86.43, "elapsed_time": "2:07:50", "remaining_time": "0:20:04", "throughput": 7892.36, "total_tokens": 60536528}
{"current_steps": 294, "total_steps": 339, "loss": 0.001, "lr": 4.285112355806192e-06, "epoch": 2.6001103143960287, "percentage": 86.73, "elapsed_time": "2:08:17", "remaining_time": "0:19:38", "throughput": 7891.4, "total_tokens": 60743120}
{"current_steps": 295, "total_steps": 339, "loss": 0.0001, "lr": 4.099396752076745e-06, "epoch": 2.6089354660783233, "percentage": 87.02, "elapsed_time": "2:08:42", "remaining_time": "0:19:11", "throughput": 7891.16, "total_tokens": 60942704}
{"current_steps": 296, "total_steps": 339, "loss": 0.0001, "lr": 3.917623139399018e-06, "epoch": 2.617760617760618, "percentage": 87.32, "elapsed_time": "2:09:07", "remaining_time": "0:18:45", "throughput": 7892.02, "total_tokens": 61140128}
{"current_steps": 297, "total_steps": 339, "loss": 0.0001, "lr": 3.7398071286779857e-06, "epoch": 2.6265857694429124, "percentage": 87.61, "elapsed_time": "2:09:30", "remaining_time": "0:18:18", "throughput": 7892.85, "total_tokens": 61334224}
{"current_steps": 298, "total_steps": 339, "loss": 0.0001, "lr": 3.5659639909356723e-06, "epoch": 2.6354109211252066, "percentage": 87.91, "elapsed_time": "2:09:57", "remaining_time": "0:17:52", "throughput": 7892.72, "total_tokens": 61543280}
{"current_steps": 299, "total_steps": 339, "loss": 0.0002, "lr": 3.3961086559996803e-06, "epoch": 2.6442360728075016, "percentage": 88.2, "elapsed_time": "2:10:23", "remaining_time": "0:17:26", "throughput": 7893.04, "total_tokens": 61750720}
{"current_steps": 300, "total_steps": 339, "loss": 0.0, "lr": 3.230255711220992e-06, "epoch": 2.6530612244897958, "percentage": 88.5, "elapsed_time": "2:10:48", "remaining_time": "0:17:00", "throughput": 7892.55, "total_tokens": 61945952}
{"current_steps": 301, "total_steps": 339, "loss": 0.0001, "lr": 3.0684194002212287e-06, "epoch": 2.6618863761720903, "percentage": 88.79, "elapsed_time": "2:11:14", "remaining_time": "0:16:34", "throughput": 7893.7, "total_tokens": 62155632}
{"current_steps": 302, "total_steps": 339, "loss": 0.0001, "lr": 2.910613621669356e-06, "epoch": 2.670711527854385, "percentage": 89.09, "elapsed_time": "2:11:39", "remaining_time": "0:16:07", "throughput": 7893.69, "total_tokens": 62353216}
{"current_steps": 303, "total_steps": 339, "loss": 0.0001, "lr": 2.7568519280880558e-06, "epoch": 2.6795366795366795, "percentage": 89.38, "elapsed_time": "2:12:03", "remaining_time": "0:15:41", "throughput": 7893.79, "total_tokens": 62544128}
{"current_steps": 304, "total_steps": 339, "loss": 0.0004, "lr": 2.607147524689829e-06, "epoch": 2.688361831218974, "percentage": 89.68, "elapsed_time": "2:12:29", "remaining_time": "0:15:15", "throughput": 7893.85, "total_tokens": 62752688}
{"current_steps": 305, "total_steps": 339, "loss": 0.0001, "lr": 2.4615132682429374e-06, "epoch": 2.6971869829012687, "percentage": 89.97, "elapsed_time": "2:12:58", "remaining_time": "0:14:49", "throughput": 7891.77, "total_tokens": 62963296}
{"current_steps": 306, "total_steps": 339, "loss": 0.0002, "lr": 2.3199616659672354e-06, "epoch": 2.7060121345835633, "percentage": 90.27, "elapsed_time": "2:13:23", "remaining_time": "0:14:23", "throughput": 7892.22, "total_tokens": 63161904}
{"current_steps": 307, "total_steps": 339, "loss": 0.0001, "lr": 2.182504874460006e-06, "epoch": 2.714837286265858, "percentage": 90.56, "elapsed_time": "2:13:49", "remaining_time": "0:13:56", "throughput": 7891.29, "total_tokens": 63365744}
{"current_steps": 308, "total_steps": 339, "loss": 0.0001, "lr": 2.049154698651989e-06, "epoch": 2.7236624379481524, "percentage": 90.86, "elapsed_time": "2:14:14", "remaining_time": "0:13:30", "throughput": 7892.66, "total_tokens": 63571808}
{"current_steps": 309, "total_steps": 339, "loss": 0.0001, "lr": 1.919922590793549e-06, "epoch": 2.7324875896304466, "percentage": 91.15, "elapsed_time": "2:14:39", "remaining_time": "0:13:04", "throughput": 7892.67, "total_tokens": 63768960}
{"current_steps": 310, "total_steps": 339, "loss": 0.0001, "lr": 1.7948196494711188e-06, "epoch": 2.741312741312741, "percentage": 91.45, "elapsed_time": "2:15:05", "remaining_time": "0:12:38", "throughput": 7892.91, "total_tokens": 63979648}
{"current_steps": 311, "total_steps": 339, "loss": 0.0001, "lr": 1.6738566186540627e-06, "epoch": 2.7501378929950357, "percentage": 91.74, "elapsed_time": "2:15:32", "remaining_time": "0:12:12", "throughput": 7892.87, "total_tokens": 64189712}
{"current_steps": 312, "total_steps": 339, "loss": 0.0001, "lr": 1.5570438867719694e-06, "epoch": 2.7589630446773303, "percentage": 92.04, "elapsed_time": "2:15:59", "remaining_time": "0:11:46", "throughput": 7892.66, "total_tokens": 64400624}
{"current_steps": 313, "total_steps": 339, "loss": 0.0001, "lr": 1.4443914858224938e-06, "epoch": 2.767788196359625, "percentage": 92.33, "elapsed_time": "2:16:26", "remaining_time": "0:11:20", "throughput": 7894.09, "total_tokens": 64626320}
{"current_steps": 314, "total_steps": 339, "loss": 0.0001, "lr": 1.3359090905097848e-06, "epoch": 2.7766133480419195, "percentage": 92.63, "elapsed_time": "2:16:51", "remaining_time": "0:10:53", "throughput": 7894.56, "total_tokens": 64826480}
{"current_steps": 315, "total_steps": 339, "loss": 0.0003, "lr": 1.2316060174136002e-06, "epoch": 2.785438499724214, "percentage": 92.92, "elapsed_time": "2:17:18", "remaining_time": "0:10:27", "throughput": 7893.92, "total_tokens": 65031984}
{"current_steps": 316, "total_steps": 339, "loss": 0.0001, "lr": 1.1314912241892183e-06, "epoch": 2.7942636514065087, "percentage": 93.22, "elapsed_time": "2:17:43", "remaining_time": "0:10:01", "throughput": 7894.65, "total_tokens": 65239456}
{"current_steps": 317, "total_steps": 339, "loss": 0.0002, "lr": 1.0355733087981378e-06, "epoch": 2.8030888030888033, "percentage": 93.51, "elapsed_time": "2:18:09", "remaining_time": "0:09:35", "throughput": 7893.46, "total_tokens": 65433888}
{"current_steps": 318, "total_steps": 339, "loss": 0.0001, "lr": 9.43860508769645e-07, "epoch": 2.8119139547710974, "percentage": 93.81, "elapsed_time": "2:18:33", "remaining_time": "0:09:09", "throughput": 7894.99, "total_tokens": 65638288}
{"current_steps": 319, "total_steps": 339, "loss": 0.0002, "lr": 8.563607004934193e-07, "epoch": 2.8207391064533924, "percentage": 94.1, "elapsed_time": "2:19:02", "remaining_time": "0:08:43", "throughput": 7894.0, "total_tokens": 65855952}
{"current_steps": 320, "total_steps": 339, "loss": 0.0002, "lr": 7.730813985430407e-07, "epoch": 2.8295642581356866, "percentage": 94.4, "elapsed_time": "2:19:28", "remaining_time": "0:08:16", "throughput": 7895.06, "total_tokens": 66070192}
{"current_steps": 321, "total_steps": 339, "loss": 0.0001, "lr": 6.940297550306896e-07, "epoch": 2.838389409817981, "percentage": 94.69, "elapsed_time": "2:19:56", "remaining_time": "0:07:50", "throughput": 7894.58, "total_tokens": 66283808}
{"current_steps": 322, "total_steps": 339, "loss": 0.0002, "lr": 6.192125589928821e-07, "epoch": 2.8472145615002757, "percentage": 94.99, "elapsed_time": "2:20:25", "remaining_time": "0:07:24", "throughput": 7893.93, "total_tokens": 66507776}
{"current_steps": 323, "total_steps": 339, "loss": 0.0002, "lr": 5.486362358074094e-07, "epoch": 2.8560397131825703, "percentage": 95.28, "elapsed_time": "2:20:50", "remaining_time": "0:06:58", "throughput": 7893.63, "total_tokens": 66708320}
{"current_steps": 324, "total_steps": 339, "loss": 0.0001, "lr": 4.823068466415615e-07, "epoch": 2.864864864864865, "percentage": 95.58, "elapsed_time": "2:21:16", "remaining_time": "0:06:32", "throughput": 7893.28, "total_tokens": 66910032}
{"current_steps": 325, "total_steps": 339, "loss": 0.0001, "lr": 4.202300879315446e-07, "epoch": 2.8736900165471595, "percentage": 95.87, "elapsed_time": "2:21:41", "remaining_time": "0:06:06", "throughput": 7894.28, "total_tokens": 67112784}
{"current_steps": 326, "total_steps": 339, "loss": 0.0001, "lr": 3.624112908932942e-07, "epoch": 2.882515168229454, "percentage": 96.17, "elapsed_time": "2:22:05", "remaining_time": "0:05:39", "throughput": 7895.04, "total_tokens": 67306464}
{"current_steps": 327, "total_steps": 339, "loss": 0.0001, "lr": 3.088554210646133e-07, "epoch": 2.8913403199117482, "percentage": 96.46, "elapsed_time": "2:22:29", "remaining_time": "0:05:13", "throughput": 7896.03, "total_tokens": 67504720}
{"current_steps": 328, "total_steps": 339, "loss": 0.0001, "lr": 2.595670778787196e-07, "epoch": 2.9001654715940433, "percentage": 96.76, "elapsed_time": "2:22:52", "remaining_time": "0:04:47", "throughput": 7896.57, "total_tokens": 67694048}
{"current_steps": 329, "total_steps": 339, "loss": 0.0002, "lr": 2.1455049426926666e-07, "epoch": 2.9089906232763374, "percentage": 97.05, "elapsed_time": "2:23:16", "remaining_time": "0:04:21", "throughput": 7897.7, "total_tokens": 67895008}
{"current_steps": 330, "total_steps": 339, "loss": 0.0001, "lr": 1.7380953630678488e-07, "epoch": 2.917815774958632, "percentage": 97.35, "elapsed_time": "2:23:41", "remaining_time": "0:03:55", "throughput": 7898.05, "total_tokens": 68093168}
{"current_steps": 331, "total_steps": 339, "loss": 0.0002, "lr": 1.373477028666803e-07, "epoch": 2.9266409266409266, "percentage": 97.64, "elapsed_time": "2:24:08", "remaining_time": "0:03:29", "throughput": 7898.34, "total_tokens": 68305568}
{"current_steps": 332, "total_steps": 339, "loss": 0.0001, "lr": 1.0516812532873621e-07, "epoch": 2.935466078323221, "percentage": 97.94, "elapsed_time": "2:24:32", "remaining_time": "0:03:02", "throughput": 7898.84, "total_tokens": 68506384}
{"current_steps": 333, "total_steps": 339, "loss": 0.0002, "lr": 7.727356730820035e-08, "epoch": 2.9442912300055157, "percentage": 98.23, "elapsed_time": "2:24:57", "remaining_time": "0:02:36", "throughput": 7900.67, "total_tokens": 68716160}
{"current_steps": 334, "total_steps": 339, "loss": 0.0001, "lr": 5.3666424418413744e-08, "epoch": 2.9531163816878103, "percentage": 98.53, "elapsed_time": "2:25:22", "remaining_time": "0:02:10", "throughput": 7901.22, "total_tokens": 68918048}
{"current_steps": 335, "total_steps": 339, "loss": 0.0001, "lr": 3.4348724065119685e-08, "epoch": 2.961941533370105, "percentage": 98.82, "elapsed_time": "2:25:50", "remaining_time": "0:01:44", "throughput": 7899.73, "total_tokens": 69129152}
{"current_steps": 336, "total_steps": 339, "loss": 0.0003, "lr": 1.9322125272297488e-08, "epoch": 2.9707666850523995, "percentage": 99.12, "elapsed_time": "2:26:15", "remaining_time": "0:01:18", "throughput": 7900.03, "total_tokens": 69328576}
{"current_steps": 337, "total_steps": 339, "loss": 0.0001, "lr": 8.587918539726402e-09, "epoch": 2.979591836734694, "percentage": 99.41, "elapsed_time": "2:26:39", "remaining_time": "0:00:52", "throughput": 7902.03, "total_tokens": 69537232}
{"current_steps": 338, "total_steps": 339, "loss": 0.0001, "lr": 2.1470257321298813e-09, "epoch": 2.988416988416988, "percentage": 99.71, "elapsed_time": "2:27:06", "remaining_time": "0:00:26", "throughput": 7903.27, "total_tokens": 69761008}
{"current_steps": 339, "total_steps": 339, "loss": 0.0001, "lr": 0.0, "epoch": 2.997242140099283, "percentage": 100.0, "elapsed_time": "2:27:31", "remaining_time": "0:00:00", "throughput": 7902.86, "total_tokens": 69953200}
{"current_steps": 339, "total_steps": 339, "epoch": 2.997242140099283, "percentage": 100.0, "elapsed_time": "2:27:32", "remaining_time": "0:00:00", "throughput": 7902.18, "total_tokens": 69953200}